4352 files changed, 53515 insertions, 27420 deletions

diff --git a/Documentation/ABI/stable/sysfs-driver-mlxreg-io b/Documentation/ABI/stable/sysfs-driver-mlxreg-io
index 156319fc5b80..cea78cfb79df 100644
--- a/Documentation/ABI/stable/sysfs-driver-mlxreg-io
+++ b/Documentation/ABI/stable/sysfs-driver-mlxreg-io
@@ -32,8 +32,17 @@ Description:	This file shows the system fans direction:
 
 		The files are read only.
 
-What:		/sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/
-							jtag_enable
+What:		/sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/cpld3_version
+
+Date:		November 2018
+KernelVersion:	5.0
+Contact:	Vadim Pasternak <vadimpmellanox.com>
+Description:	These files show with which CPLD versions have been burned
+		on LED or Gearbox board.
+
+		The files are read only.
+
+What:		/sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/cpld4_version
 
 Date:		November 2018
 KernelVersion:	5.0
diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio
index 6aef7dbbde44..b97fde757bfe 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio
+++ b/Documentation/ABI/testing/sysfs-bus-iio
@@ -1563,7 +1563,8 @@ What:		/sys/bus/iio/devices/iio:deviceX/in_concentrationX_voc_raw
 KernelVersion:	4.3
 Contact:	linux-iio@vger.kernel.org
 Description:
-		Raw (unscaled no offset etc.) percentage reading of a substance.
+		Raw (unscaled no offset etc.) reading of a substance. Units
+		after application of scale and offset are percents.
 
 What:		/sys/bus/iio/devices/iio:deviceX/in_resistance_raw
 What:		/sys/bus/iio/devices/iio:deviceX/in_resistanceX_raw
diff --git a/Documentation/ABI/testing/sysfs-bus-mei b/Documentation/ABI/testing/sysfs-bus-mei
index 6bd45346ac7e..3f8701e8fa24 100644
--- a/Documentation/ABI/testing/sysfs-bus-mei
+++ b/Documentation/ABI/testing/sysfs-bus-mei
@@ -4,7 +4,7 @@ KernelVersion:	3.10
 Contact:	Samuel Ortiz <sameo@linux.intel.com>
 		linux-mei@linux.intel.com
 Description:	Stores the same MODALIAS value emitted by uevent
-		Format: mei:<mei device name>:<device uuid>:
+		Format: mei:<mei device name>:<device uuid>:<protocol version>
 
 What:		/sys/bus/mei/devices/.../name
 Date:		May 2015
diff --git a/Documentation/ABI/testing/sysfs-class-devfreq b/Documentation/ABI/testing/sysfs-class-devfreq
index ee39acacf6f8..335595a79866 100644
--- a/Documentation/ABI/testing/sysfs-class-devfreq
+++ b/Documentation/ABI/testing/sysfs-class-devfreq
@@ -7,6 +7,13 @@ Description:
 		The name of devfreq object denoted as ... is same as the
 		name of device using devfreq.
 
+What:		/sys/class/devfreq/.../name
+Date:		November 2019
+Contact:	Chanwoo Choi <cw00.choi@samsung.com>
+Description:
+		The /sys/class/devfreq/.../name shows the name of device
+		of the corresponding devfreq object.
+
 What:		/sys/class/devfreq/.../governor
 Date:		September 2011
 Contact:	MyungJoo Ham <myungjoo.ham@samsung.com>
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 21d30cc37019..214e8d3a60c3 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -485,6 +485,7 @@ What:		/sys/devices/system/cpu/vulnerabilities
 		/sys/devices/system/cpu/vulnerabilities/spec_store_bypass
 		/sys/devices/system/cpu/vulnerabilities/l1tf
 		/sys/devices/system/cpu/vulnerabilities/mds
+		/sys/devices/system/cpu/vulnerabilities/srbds
 		/sys/devices/system/cpu/vulnerabilities/tsx_async_abort
 		/sys/devices/system/cpu/vulnerabilities/itlb_multihit
 Date:		January 2018
diff --git a/Documentation/RCU/Design/Requirements/Requirements.html b/Documentation/RCU/Design/Requirements/Requirements.html
index 5a9238a2883c..bdbc84f1b949 100644
--- a/Documentation/RCU/Design/Requirements/Requirements.html
+++ b/Documentation/RCU/Design/Requirements/Requirements.html
@@ -2512,7 +2512,7 @@ disabled across the entire RCU read-side critical section.
 <p>
 It is possible to use tracing on RCU code, but tracing itself
 uses RCU.
-For this reason, <tt>rcu_dereference_raw_notrace()</tt>
+For this reason, <tt>rcu_dereference_raw_check()</tt>
 is provided for use by tracing, which avoids the destructive
 recursion that could otherwise ensue.
 This API is also used by virtualization in some architectures,
diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst
index 0795e3c2643f..ca4dbdd9016d 100644
--- a/Documentation/admin-guide/hw-vuln/index.rst
+++ b/Documentation/admin-guide/hw-vuln/index.rst
@@ -14,3 +14,4 @@ are configurable at compile, boot or run time.
    mds
    tsx_async_abort
    multihit.rst
+   special-register-buffer-data-sampling.rst
diff --git a/Documentation/admin-guide/hw-vuln/special-register-buffer-data-sampling.rst b/Documentation/admin-guide/hw-vuln/special-register-buffer-data-sampling.rst
new file mode 100644
index 000000000000..47b1b3afac99
--- /dev/null
+++ b/Documentation/admin-guide/hw-vuln/special-register-buffer-data-sampling.rst
@@ -0,0 +1,149 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+SRBDS - Special Register Buffer Data Sampling
+=============================================
+
+SRBDS is a hardware vulnerability that allows MDS :doc:`mds` techniques to
+infer values returned from special register accesses.  Special register
+accesses are accesses to off core registers.  According to Intel's evaluation,
+the special register reads that have a security expectation of privacy are
+RDRAND, RDSEED and SGX EGETKEY.
+
+When RDRAND, RDSEED and EGETKEY instructions are used, the data is moved
+to the core through the special register mechanism that is susceptible
+to MDS attacks.
+
+Affected processors
+--------------------
+Core models (desktop, mobile, Xeon-E3) that implement RDRAND and/or RDSEED may
+be affected.
+
+A processor is affected by SRBDS if its Family_Model and stepping is
+in the following list, with the exception of the listed processors
+exporting MDS_NO while Intel TSX is available yet not enabled. The
+latter class of processors are only affected when Intel TSX is enabled
+by software using TSX_CTRL_MSR otherwise they are not affected.
+
+  =============  ============  ========
+  common name    Family_Model  Stepping
+  =============  ============  ========
+  IvyBridge      06_3AH        All
+
+  Haswell        06_3CH        All
+  Haswell_L      06_45H        All
+  Haswell_G      06_46H        All
+
+  Broadwell_G    06_47H        All
+  Broadwell      06_3DH        All
+
+  Skylake_L      06_4EH        All
+  Skylake        06_5EH        All
+
+  Kabylake_L     06_8EH        <= 0xC
+  Kabylake       06_9EH        <= 0xD
+  =============  ============  ========
+
+Related CVEs
+------------
+
+The following CVE entry is related to this SRBDS issue:
+
+    ==============  =====  =====================================
+    CVE-2020-0543   SRBDS  Special Register Buffer Data Sampling
+    ==============  =====  =====================================
+
+Attack scenarios
+----------------
+An unprivileged user can extract values returned from RDRAND and RDSEED
+executed on another core or sibling thread using MDS techniques.
+
+
+Mitigation mechanism
+-------------------
+Intel will release microcode updates that modify the RDRAND, RDSEED, and
+EGETKEY instructions to overwrite secret special register data in the shared
+staging buffer before the secret data can be accessed by another logical
+processor.
+
+During execution of the RDRAND, RDSEED, or EGETKEY instructions, off-core
+accesses from other logical processors will be delayed until the special
+register read is complete and the secret data in the shared staging buffer is
+overwritten.
+
+This has three effects on performance:
+
+#. RDRAND, RDSEED, or EGETKEY instructions have higher latency.
+
+#. Executing RDRAND at the same time on multiple logical processors will be
+   serialized, resulting in an overall reduction in the maximum RDRAND
+   bandwidth.
+
+#. Executing RDRAND, RDSEED or EGETKEY will delay memory accesses from other
+   logical processors that miss their core caches, with an impact similar to
+   legacy locked cache-line-split accesses.
+
+The microcode updates provide an opt-out mechanism (RNGDS_MITG_DIS) to disable
+the mitigation for RDRAND and RDSEED instructions executed outside of Intel
+Software Guard Extensions (Intel SGX) enclaves. On logical processors that
+disable the mitigation using this opt-out mechanism, RDRAND and RDSEED do not
+take longer to execute and do not impact performance of sibling logical
+processors memory accesses. The opt-out mechanism does not affect Intel SGX
+enclaves (including execution of RDRAND or RDSEED inside an enclave, as well
+as EGETKEY execution).
+
+IA32_MCU_OPT_CTRL MSR Definition
+--------------------------------
+Along with the mitigation for this issue, Intel added a new thread-scope
+IA32_MCU_OPT_CTRL MSR, (address 0x123). The presence of this MSR and
+RNGDS_MITG_DIS (bit 0) is enumerated by CPUID.(EAX=07H,ECX=0).EDX[SRBDS_CTRL =
+9]==1. This MSR is introduced through the microcode update.
+
+Setting IA32_MCU_OPT_CTRL[0] (RNGDS_MITG_DIS) to 1 for a logical processor
+disables the mitigation for RDRAND and RDSEED executed outside of an Intel SGX
+enclave on that logical processor. Opting out of the mitigation for a
+particular logical processor does not affect the RDRAND and RDSEED mitigations
+for other logical processors.
+
+Note that inside of an Intel SGX enclave, the mitigation is applied regardless
+of the value of RNGDS_MITG_DS.
+
+Mitigation control on the kernel command line
+---------------------------------------------
+The kernel command line allows control over the SRBDS mitigation at boot time
+with the option "srbds=".  The option for this is:
+
+  ============= =============================================================
+  off           This option disables SRBDS mitigation for RDRAND and RDSEED on
+                affected platforms.
+  ============= =============================================================
+
+SRBDS System Information
+-----------------------
+The Linux kernel provides vulnerability status information through sysfs.  For
+SRBDS this can be accessed by the following sysfs file:
+/sys/devices/system/cpu/vulnerabilities/srbds
+
+The possible values contained in this file are:
+
+ ============================== =============================================
+ Not affected                   Processor not vulnerable
+ Vulnerable                     Processor vulnerable and mitigation disabled
+ Vulnerable: No microcode       Processor vulnerable and microcode is missing
+                                mitigation
+ Mitigation: Microcode          Processor is vulnerable and mitigation is in
+                                effect.
+ Mitigation: TSX disabled       Processor is only vulnerable when TSX is
+                                enabled while this system was booted with TSX
+                                disabled.
+ Unknown: Dependent on
+ hypervisor status              Running on virtual guest processor that is
+                                affected but with no way to know if host
+                                processor is mitigated or vulnerable.
+ ============================== =============================================
+
+SRBDS Default mitigation
+------------------------
+This new microcode serializes processor access during execution of RDRAND,
+RDSEED ensures that the shared buffer is overwritten before it is released for
+reuse.  Use the "srbds=off" kernel command line to disable the mitigation for
+RDRAND and RDSEED.
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index c10c6a043d4b..6095702c6601 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -113,7 +113,7 @@
 			the GPE dispatcher.
 			This facility can be used to prevent such uncontrolled
 			GPE floodings.
-			Format: <int>
+			Format: <byte>
 
 	acpi_no_auto_serialize	[HW,ACPI]
 			Disable auto-serialization of AML methods
@@ -136,6 +136,10 @@
 			dynamic table installation which will install SSDT
 			tables to /sys/firmware/acpi/tables/dynamic.
 
+	acpi_no_watchdog	[HW,ACPI,WDT]
+			Ignore the ACPI-based watchdog interface (WDAT) and let
+			a native driver control the watchdog device instead.
+
 	acpi_rsdp=	[ACPI,EFI,KEXEC]
 			Pass the RSDP address to the kernel, mostly used
 			on machines running EFI runtime service to boot the
@@ -4510,6 +4514,26 @@
 	spia_pedr=
 	spia_peddr=
 
+	srbds=		[X86,INTEL]
+			Control the Special Register Buffer Data Sampling
+			(SRBDS) mitigation.
+
+			Certain CPUs are vulnerable to an MDS-like
+			exploit which can leak bits from the random
+			number generator.
+
+			By default, this issue is mitigated by
+			microcode.  However, the microcode fix can cause
+			the RDRAND and RDSEED instructions to become
+			much slower.  Among other effects, this will
+			result in reduced throughput from /dev/urandom.
+
+			The microcode mitigation can be disabled with
+			the following option:
+
+			off:    Disable mitigation and remove
+				performance impact to RDRAND and RDSEED
+
 	srcutree.counter_wrap_check [KNL]
 			Specifies how frequently to check for
 			grace-period sequence counter wrap for the
@@ -4952,8 +4976,7 @@
 
 	usbcore.old_scheme_first=
 			[USB] Start with the old device initialization
-			scheme,  applies only to low and full-speed devices
-			 (default 0 = off).
+			scheme (default 0 = off).
 
 	usbcore.usbfs_memory_mb=
 			[USB] Memory limit (in MB) for buffers allocated by
diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt
index 7f0e56e43738..bb2214107a84 100644
--- a/Documentation/arm64/silicon-errata.txt
+++ b/Documentation/arm64/silicon-errata.txt
@@ -63,6 +63,7 @@ stable kernels.
 | ARM            | Cortex-A76      | #1286807        | ARM64_ERRATUM_1286807       |
 | ARM            | Cortex-A76      | #1463225        | ARM64_ERRATUM_1463225       |
 | ARM            | Neoverse-N1     | #1188873,1418040| ARM64_ERRATUM_1418040       |
+| ARM            | Neoverse-N1     | #1542419        | ARM64_ERRATUM_1542419       |
 | ARM            | MMU-500         | #841119,826419  | N/A                         |
 |                |                 |                 |                             |
 | Broadcom       | Brahma-B53      | N/A             | ARM64_ERRATUM_845719        |
diff --git a/Documentation/cgroup-v1/blkio-controller.txt b/Documentation/cgroup-v1/blkio-controller.txt
index d1a1b7bdd03a..7959bee4e013 100644
--- a/Documentation/cgroup-v1/blkio-controller.txt
+++ b/Documentation/cgroup-v1/blkio-controller.txt
@@ -121,12 +121,6 @@ Proportional weight policy files
 	  dev     weight
 	  8:16    300
 
-- blkio.leaf_weight[_device]
-	- Equivalents of blkio.weight[_device] for the purpose of
-          deciding how much weight tasks in the given cgroup has while
-          competing with the cgroup's child cgroups. For details,
-          please refer to Documentation/block/cfq-iosched.txt.
-
 - blkio.time
 	- disk time allocated to cgroup per device in milliseconds. First
 	  two fields specify the major and minor number of the device and
diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst
index ee1bb8983a88..60d2f3522db6 100644
--- a/Documentation/core-api/index.rst
+++ b/Documentation/core-api/index.rst
@@ -25,6 +25,7 @@ Core utilities
    librs
    genalloc
    errseq
+   packing
    printk-formats
    circular-buffers
    generic-radix-tree
diff --git a/Documentation/packing.txt b/Documentation/core-api/packing.rst
index f830c98645f1..d8c341fe383e 100644
--- a/Documentation/packing.txt
+++ b/Documentation/core-api/packing.rst
@@ -30,6 +30,7 @@ The solution
 ------------
 
 This API deals with 2 basic operations:
+
   - Packing a CPU-usable number into a memory buffer (with hardware
     constraints/quirks)
   - Unpacking a memory buffer (which has hardware constraints/quirks)
@@ -49,10 +50,12 @@ What the examples show is where the logical bytes and bits sit.
 
 1. Normally (no quirks), we would do it like this:
 
-63 62 61 60 59 58 57 56 55 54 53 52 51 50 49 48 47 46 45 44 43 42 41 40 39 38 37 36 35 34 33 32
-7                       6                       5                        4
-31 30 29 28 27 26 25 24 23 22 21 20 19 18 17 16 15 14 13 12 11 10  9  8  7  6  5  4  3  2  1  0
-3                       2                       1                        0
+::
+
+  63 62 61 60 59 58 57 56 55 54 53 52 51 50 49 48 47 46 45 44 43 42 41 40 39 38 37 36 35 34 33 32
+  7                       6                       5                        4
+  31 30 29 28 27 26 25 24 23 22 21 20 19 18 17 16 15 14 13 12 11 10  9  8  7  6  5  4  3  2  1  0
+  3                       2                       1                        0
 
 That is, the MSByte (7) of the CPU-usable u64 sits at memory offset 0, and the
 LSByte (0) of the u64 sits at memory offset 7.
@@ -63,10 +66,12 @@ comments as "logical" notation.
 
 2. If QUIRK_MSB_ON_THE_RIGHT is set, we do it like this:
 
-56 57 58 59 60 61 62 63 48 49 50 51 52 53 54 55 40 41 42 43 44 45 46 47 32 33 34 35 36 37 38 39
-7                       6                        5                       4
-24 25 26 27 28 29 30 31 16 17 18 19 20 21 22 23  8  9 10 11 12 13 14 15  0  1  2  3  4  5  6  7
-3                       2                        1                       0
+::
+
+  56 57 58 59 60 61 62 63 48 49 50 51 52 53 54 55 40 41 42 43 44 45 46 47 32 33 34 35 36 37 38 39
+  7                       6                        5                       4
+  24 25 26 27 28 29 30 31 16 17 18 19 20 21 22 23  8  9 10 11 12 13 14 15  0  1  2  3  4  5  6  7
+  3                       2                        1                       0
 
 That is, QUIRK_MSB_ON_THE_RIGHT does not affect byte positioning, but
 inverts bit offsets inside a byte.
@@ -74,10 +79,12 @@ inverts bit offsets inside a byte.
 
 3. If QUIRK_LITTLE_ENDIAN is set, we do it like this:
 
-39 38 37 36 35 34 33 32 47 46 45 44 43 42 41 40 55 54 53 52 51 50 49 48 63 62 61 60 59 58 57 56
-4                       5                       6                       7
-7  6  5  4  3  2  1  0  15 14 13 12 11 10  9  8 23 22 21 20 19 18 17 16 31 30 29 28 27 26 25 24
-0                       1                       2                       3
+::
+
+  39 38 37 36 35 34 33 32 47 46 45 44 43 42 41 40 55 54 53 52 51 50 49 48 63 62 61 60 59 58 57 56
+  4                       5                       6                       7
+  7  6  5  4  3  2  1  0  15 14 13 12 11 10  9  8 23 22 21 20 19 18 17 16 31 30 29 28 27 26 25 24
+  0                       1                       2                       3
 
 Therefore, QUIRK_LITTLE_ENDIAN means that inside the memory region, every
 byte from each 4-byte word is placed at its mirrored position compared to
@@ -86,18 +93,22 @@ the boundary of that word.
 4. If QUIRK_MSB_ON_THE_RIGHT and QUIRK_LITTLE_ENDIAN are both set, we do it
    like this:
 
-32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63
-4                       5                       6                       7
-0  1  2  3  4  5  6  7  8   9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31
-0                       1                       2                       3
+::
+
+  32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63
+  4                       5                       6                       7
+  0  1  2  3  4  5  6  7  8   9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31
+  0                       1                       2                       3
 
 
 5. If just QUIRK_LSW32_IS_FIRST is set, we do it like this:
 
-31 30 29 28 27 26 25 24 23 22 21 20 19 18 17 16 15 14 13 12 11 10  9  8  7  6  5  4  3  2  1  0
-3                       2                       1                        0
-63 62 61 60 59 58 57 56 55 54 53 52 51 50 49 48 47 46 45 44 43 42 41 40 39 38 37 36 35 34 33 32
-7                       6                       5                        4
+::
+
+  31 30 29 28 27 26 25 24 23 22 21 20 19 18 17 16 15 14 13 12 11 10  9  8  7  6  5  4  3  2  1  0
+  3                       2                       1                        0
+  63 62 61 60 59 58 57 56 55 54 53 52 51 50 49 48 47 46 45 44 43 42 41 40 39 38 37 36 35 34 33 32
+  7                       6                       5                        4
 
 In this case the 8 byte memory region is interpreted as follows: first
 4 bytes correspond to the least significant 4-byte word, next 4 bytes to
@@ -107,28 +118,34 @@ the more significant 4-byte word.
 6. If QUIRK_LSW32_IS_FIRST and QUIRK_MSB_ON_THE_RIGHT are set, we do it like
    this:
 
-24 25 26 27 28 29 30 31 16 17 18 19 20 21 22 23  8  9 10 11 12 13 14 15  0  1  2  3  4  5  6  7
-3                       2                        1                       0
-56 57 58 59 60 61 62 63 48 49 50 51 52 53 54 55 40 41 42 43 44 45 46 47 32 33 34 35 36 37 38 39
-7                       6                        5                       4
+::
+
+  24 25 26 27 28 29 30 31 16 17 18 19 20 21 22 23  8  9 10 11 12 13 14 15  0  1  2  3  4  5  6  7
+  3                       2                        1                       0
+  56 57 58 59 60 61 62 63 48 49 50 51 52 53 54 55 40 41 42 43 44 45 46 47 32 33 34 35 36 37 38 39
+  7                       6                        5                       4
 
 
 7. If QUIRK_LSW32_IS_FIRST and QUIRK_LITTLE_ENDIAN are set, it looks like
    this:
 
-7  6  5  4  3  2  1  0  15 14 13 12 11 10  9  8 23 22 21 20 19 18 17 16 31 30 29 28 27 26 25 24
-0                       1                       2                       3
-39 38 37 36 35 34 33 32 47 46 45 44 43 42 41 40 55 54 53 52 51 50 49 48 63 62 61 60 59 58 57 56
-4                       5                       6                       7
+::
+
+  7  6  5  4  3  2  1  0  15 14 13 12 11 10  9  8 23 22 21 20 19 18 17 16 31 30 29 28 27 26 25 24
+  0                       1                       2                       3
+  39 38 37 36 35 34 33 32 47 46 45 44 43 42 41 40 55 54 53 52 51 50 49 48 63 62 61 60 59 58 57 56
+  4                       5                       6                       7
 
 
 8. If QUIRK_LSW32_IS_FIRST, QUIRK_LITTLE_ENDIAN and QUIRK_MSB_ON_THE_RIGHT
    are set, it looks like this:
 
-0  1  2  3  4  5  6  7  8   9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31
-0                       1                       2                       3
-32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63
-4                       5                       6                       7
+::
+
+  0  1  2  3  4  5  6  7  8   9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31
+  0                       1                       2                       3
+  32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63
+  4                       5                       6                       7
 
 
 We always think of our offsets as if there were no quirk, and we translate
diff --git a/Documentation/devicetree/bindings/clock/renesas,rcar-usb2-clock-sel.txt b/Documentation/devicetree/bindings/clock/renesas,rcar-usb2-clock-sel.txt
index e96e085271c1..83f6c6a7c41c 100644
--- a/Documentation/devicetree/bindings/clock/renesas,rcar-usb2-clock-sel.txt
+++ b/Documentation/devicetree/bindings/clock/renesas,rcar-usb2-clock-sel.txt
@@ -46,7 +46,7 @@ Required properties:
 Example (R-Car H3):
 
 	usb2_clksel: clock-controller@e6590630 {
-		compatible = "renesas,r8a77950-rcar-usb2-clock-sel",
+		compatible = "renesas,r8a7795-rcar-usb2-clock-sel",
 			     "renesas,rcar-gen3-usb2-clock-sel";
 		reg = <0 0xe6590630 0 0x02>;
 		clocks = <&cpg CPG_MOD 703>, <&usb_extal>, <&usb_xtal>;
diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,dpi.txt b/Documentation/devicetree/bindings/display/mediatek/mediatek,dpi.txt
index b6a7e7397b8b..b944fe067188 100644
--- a/Documentation/devicetree/bindings/display/mediatek/mediatek,dpi.txt
+++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,dpi.txt
@@ -16,6 +16,9 @@ Required properties:
   Documentation/devicetree/bindings/graph.txt. This port should be connected
   to the input port of an attached HDMI or LVDS encoder chip.
 
+Optional properties:
+- pinctrl-names: Contain "default" and "sleep".
+
 Example:
 
 dpi0: dpi@1401d000 {
@@ -26,6 +29,9 @@ dpi0: dpi@1401d000 {
 		 <&mmsys CLK_MM_DPI_ENGINE>,
 		 <&apmixedsys CLK_APMIXED_TVDPLL>;
 	clock-names = "pixel", "engine", "pll";
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&dpi_pin_func>;
+	pinctrl-1 = <&dpi_pin_idle>;
 
 	port {
 		dpi0_out: endpoint {
diff --git a/Documentation/devicetree/bindings/iio/adc/avia-hx711.yaml b/Documentation/devicetree/bindings/iio/adc/avia-hx711.yaml
index 8a4100ceeaf2..d76ece97c76c 100644
--- a/Documentation/devicetree/bindings/iio/adc/avia-hx711.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/avia-hx711.yaml
@@ -61,6 +61,6 @@ examples:
         compatible = "avia,hx711";
         sck-gpios = <&gpio3 10 GPIO_ACTIVE_HIGH>;
         dout-gpios = <&gpio0 7 GPIO_ACTIVE_HIGH>;
-        avdd-suppy = <&avdd>;
+        avdd-supply = <&avdd>;
         clock-frequency = <100000>;
     };
diff --git a/Documentation/devicetree/bindings/iio/multiplexer/io-channel-mux.txt b/Documentation/devicetree/bindings/iio/multiplexer/io-channel-mux.txt
index c82794002595..89647d714387 100644
--- a/Documentation/devicetree/bindings/iio/multiplexer/io-channel-mux.txt
+++ b/Documentation/devicetree/bindings/iio/multiplexer/io-channel-mux.txt
@@ -21,7 +21,7 @@ controller state. The mux controller state is described in
 
 Example:
 	mux: mux-controller {
-		compatible = "mux-gpio";
+		compatible = "gpio-mux";
 		#mux-control-cells = <0>;
 
 		mux-gpios = <&pioA 0 GPIO_ACTIVE_HIGH>,
diff --git a/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.txt b/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.txt
index 4438432bfe9b..ad76edccf881 100644
--- a/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.txt
+++ b/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.txt
@@ -87,7 +87,7 @@ Example:
 		ranges;
 
 		/* APU<->RPU0 IPI mailbox controller */
-		ipi_mailbox_rpu0: mailbox@ff90400 {
+		ipi_mailbox_rpu0: mailbox@ff990400 {
 			reg = <0xff990400 0x20>,
 			      <0xff990420 0x20>,
 			      <0xff990080 0x20>,
diff --git a/Documentation/devicetree/bindings/net/fsl-fman.txt b/Documentation/devicetree/bindings/net/fsl-fman.txt
index 299c0dcd67db..1316f0aec0cf 100644
--- a/Documentation/devicetree/bindings/net/fsl-fman.txt
+++ b/Documentation/devicetree/bindings/net/fsl-fman.txt
@@ -110,6 +110,13 @@ PROPERTIES
 		Usage: required
 		Definition: See soc/fsl/qman.txt and soc/fsl/bman.txt
 
+- fsl,erratum-a050385
+		Usage: optional
+		Value type: boolean
+		Definition: A boolean property. Indicates the presence of the
+		erratum A050385 which indicates that DMA transactions that are
+		split can result in a FMan lock.
+
 =============================================================================
 FMan MURAM Node
 
diff --git a/Documentation/devicetree/bindings/pinctrl/bitmain,bm1880-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/bitmain,bm1880-pinctrl.txt
index ed34bb1ee81c..cc9a89aa4170 100644
--- a/Documentation/devicetree/bindings/pinctrl/bitmain,bm1880-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/bitmain,bm1880-pinctrl.txt
@@ -85,9 +85,9 @@ Required Properties:
                   spi0
 
 Example:
-        pinctrl: pinctrl@50 {
+        pinctrl: pinctrl@400 {
                 compatible = "bitmain,bm1880-pinctrl";
-                reg = <0x50 0x4B0>;
+                reg = <0x400 0x120>;
 
                 pinctrl_uart0_default: uart0-default {
                         pinmux {
diff --git a/Documentation/devicetree/bindings/reset/brcm,brcmstb-reset.txt b/Documentation/devicetree/bindings/reset/brcm,brcmstb-reset.txt
index 6e5341b4f891..ee59409640f2 100644
--- a/Documentation/devicetree/bindings/reset/brcm,brcmstb-reset.txt
+++ b/Documentation/devicetree/bindings/reset/brcm,brcmstb-reset.txt
@@ -22,6 +22,6 @@ Example:
 	};
 
 	&ethernet_switch {
-		resets = <&reset>;
+		resets = <&reset 26>;
 		reset-names = "switch";
 	};
diff --git a/Documentation/devicetree/bindings/rng/omap3_rom_rng.txt b/Documentation/devicetree/bindings/rng/omap3_rom_rng.txt
new file mode 100644
index 000000000000..f315c9723bd2
--- /dev/null
+++ b/Documentation/devicetree/bindings/rng/omap3_rom_rng.txt
@@ -0,0 +1,27 @@
+OMAP ROM RNG driver binding
+
+Secure SoCs may provide RNG via secure ROM calls like Nokia N900 does. The
+implementation can depend on the SoC secure ROM used.
+
+- compatible:
+	Usage: required
+	Value type: <string>
+	Definition: must be "nokia,n900-rom-rng"
+
+- clocks:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: reference to the the RNG interface clock
+
+- clock-names:
+	Usage: required
+	Value type: <stringlist>
+	Definition: must be "ick"
+
+Example:
+
+	rom_rng: rng {
+		compatible = "nokia,n900-rom-rng";
+		clocks = <&rng_ick>;
+		clock-names = "ick";
+	};
diff --git a/Documentation/devicetree/bindings/usb/dwc3.txt b/Documentation/devicetree/bindings/usb/dwc3.txt
index 8e5265e9f658..14d97c40b75c 100644
--- a/Documentation/devicetree/bindings/usb/dwc3.txt
+++ b/Documentation/devicetree/bindings/usb/dwc3.txt
@@ -73,6 +73,8 @@ Optional properties:
 			from P0 to P1/P2/P3 without delay.
  - snps,dis-tx-ipgap-linecheck-quirk: when set, disable u2mac linestate check
 			during HS transmit.
+ - snps,parkmode-disable-ss-quirk: when set, all SuperSpeed bus instances in
+			park mode are disabled.
  - snps,dis_metastability_quirk: when set, disable metastability workaround.
 			CAUTION: use only if you are absolutely sure of it.
  - snps,is-utmi-l1-suspend: true when DWC3 asserts output signal
diff --git a/Documentation/devicetree/bindings/usb/generic-ehci.yaml b/Documentation/devicetree/bindings/usb/generic-ehci.yaml
index d3b4f6415920..1ca64c85191a 100644
--- a/Documentation/devicetree/bindings/usb/generic-ehci.yaml
+++ b/Documentation/devicetree/bindings/usb/generic-ehci.yaml
@@ -63,7 +63,11 @@ properties:
     description:
       Set this flag to force EHCI reset after resume.
 
-  phys: true
+  phys:
+    description: PHY specifier for the USB PHY
+
+  phy-names:
+    const: usb
 
 required:
   - compatible
@@ -74,7 +78,7 @@ additionalProperties: false
 
 examples:
   - |
-    ehci@e0000300 {
+    usb@e0000300 {
         compatible = "ibm,usb-ehci-440epx", "generic-ehci";
         interrupt-parent = <&UIC0>;
         interrupts = <0x1a 4>;
diff --git a/Documentation/devicetree/bindings/usb/generic-ohci.yaml b/Documentation/devicetree/bindings/usb/generic-ohci.yaml
index da5a14becbe5..bcffec1f1341 100644
--- a/Documentation/devicetree/bindings/usb/generic-ohci.yaml
+++ b/Documentation/devicetree/bindings/usb/generic-ohci.yaml
@@ -67,7 +67,11 @@ properties:
     description:
       Overrides the detected port count
 
-  phys: true
+  phys:
+    description: PHY specifier for the USB PHY
+
+  phy-names:
+    const: usb
 
 required:
   - compatible
@@ -84,6 +88,7 @@ examples:
           interrupts = <64>;
           clocks = <&usb_clk 6>, <&ahb_gates 2>;
           phys = <&usbphy 1>;
+          phy-names = "usb";
       };
 
 ...
diff --git a/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.txt b/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.txt
index 266c2d917a28..bb5f8e80a1f4 100644
--- a/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.txt
+++ b/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.txt
@@ -32,7 +32,7 @@ Required properties:
 	"mcu_ck": mcu_bus clock for register access,
 	"dma_ck": dma_bus clock for data transfer by DMA
 
- - phys : see usb-hcd.txt in the current directory
+ - phys : see usb-hcd.yaml in the current directory
 
 Optional properties:
  - wakeup-source : enable USB remote wakeup;
@@ -52,7 +52,7 @@ Optional properties:
 	See: Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
  - imod-interval-ns: default interrupt moderation interval is 5000ns
 
-additionally the properties from usb-hcd.txt (in the current directory) are
+additionally the properties from usb-hcd.yaml (in the current directory) are
 supported.
 
 Example:
diff --git a/Documentation/devicetree/bindings/usb/mediatek,mtu3.txt b/Documentation/devicetree/bindings/usb/mediatek,mtu3.txt
index 3382b5cb471d..67f8b7fe3a8f 100644
--- a/Documentation/devicetree/bindings/usb/mediatek,mtu3.txt
+++ b/Documentation/devicetree/bindings/usb/mediatek,mtu3.txt
@@ -17,7 +17,7 @@ Required properties:
  - clock-names : must contain "sys_ck" for clock of controller,
 	the following clocks are optional:
 	"ref_ck", "mcu_ck" and "dam_ck";
- - phys : see usb-hcd.txt in the current directory
+ - phys : see usb-hcd.yaml in the current directory
  - dr_mode : should be one of "host", "peripheral" or "otg",
 	refer to usb/generic.txt
 
@@ -53,7 +53,7 @@ Optional properties:
  - mediatek,u3p-dis-msk : mask to disable u3ports, bit0 for u3port0,
 	bit1 for u3port1, ... etc;
 
-additionally the properties from usb-hcd.txt (in the current directory) are
+additionally the properties from usb-hcd.yaml (in the current directory) are
 supported.
 
 Sub-nodes:
diff --git a/Documentation/devicetree/bindings/usb/usb-hcd.yaml b/Documentation/devicetree/bindings/usb/usb-hcd.yaml
index 9c8c56d3a792..7263b7f2b510 100644
--- a/Documentation/devicetree/bindings/usb/usb-hcd.yaml
+++ b/Documentation/devicetree/bindings/usb/usb-hcd.yaml
@@ -18,8 +18,13 @@ properties:
     description:
       List of all the USB PHYs on this HCD
 
+  phy-names:
+    description:
+      Name specifier for the USB PHY
+
 examples:
   - |
     usb {
         phys = <&usb2_phy1>, <&usb3_phy1>;
+        phy-names = "usb";
     };
diff --git a/Documentation/devicetree/bindings/usb/usb-uhci.txt b/Documentation/devicetree/bindings/usb/usb-uhci.txt
index cc2e6f7d602e..d1702eb2c8bd 100644
--- a/Documentation/devicetree/bindings/usb/usb-uhci.txt
+++ b/Documentation/devicetree/bindings/usb/usb-uhci.txt
@@ -6,7 +6,7 @@ Required properties:
 - reg : Should contain 1 register ranges(address and length)
 - interrupts : UHCI controller interrupt
 
-additionally the properties from usb-hcd.txt (in the current directory) are
+additionally the properties from usb-hcd.yaml (in the current directory) are
 supported.
 
 Example:
diff --git a/Documentation/devicetree/bindings/usb/usb-xhci.txt b/Documentation/devicetree/bindings/usb/usb-xhci.txt
index 97400e8f8605..b49b819571f9 100644
--- a/Documentation/devicetree/bindings/usb/usb-xhci.txt
+++ b/Documentation/devicetree/bindings/usb/usb-xhci.txt
@@ -41,9 +41,9 @@ Optional properties:
   - usb3-lpm-capable: determines if platform is USB3 LPM capable
   - quirk-broken-port-ped: set if the controller has broken port disable mechanism
   - imod-interval-ns: default interrupt moderation interval is 5000ns
-  - phys : see usb-hcd.txt in the current directory
+  - phys : see usb-hcd.yaml in the current directory
 
-additionally the properties from usb-hcd.txt (in the current directory) are
+additionally the properties from usb-hcd.yaml (in the current directory) are
 supported.
 
 
diff --git a/Documentation/driver-api/generic-counter.rst b/Documentation/driver-api/generic-counter.rst
index 0c161b1a3be6..8382f01a53e3 100644
--- a/Documentation/driver-api/generic-counter.rst
+++ b/Documentation/driver-api/generic-counter.rst
@@ -233,7 +233,7 @@ Userspace Interface
 Several sysfs attributes are generated by the Generic Counter interface,
 and reside under the /sys/bus/counter/devices/counterX directory, where
 counterX refers to the respective counter device. Please see
-Documentation/ABI/testing/sys-bus-counter-generic-sysfs for detailed
+Documentation/ABI/testing/sysfs-bus-counter for detailed
 information on each Generic Counter interface sysfs attribute.
 
 Through these sysfs attributes, programs and scripts may interact with
@@ -325,7 +325,7 @@ sysfs attributes, where Y is the unique ID of the respective Count:
 
 For a more detailed breakdown of the available Generic Counter interface
 sysfs attributes, please refer to the
-Documentation/ABI/testing/sys-bus-counter file.
+Documentation/ABI/testing/sysfs-bus-counter file.
 
 The Signals and Counts associated with the Counter device are registered
 to the system as well by the counter_register function. The
diff --git a/Documentation/fb/fbcon.txt b/Documentation/fb/fbcon.txt
index 5a865437b33f..1a3b2f256569 100644
--- a/Documentation/fb/fbcon.txt
+++ b/Documentation/fb/fbcon.txt
@@ -124,7 +124,7 @@ C. Boot options
 	is typically located on the same video card.  Thus, the consoles that
 	are controlled by the VGA console will be garbled.
 
-4. fbcon=rotate:<n>
+5. fbcon=rotate:<n>
 
         This option changes the orientation angle of the console display. The
         value 'n' accepts the following:
@@ -149,21 +149,21 @@ C. Boot options
 	Actually, the underlying fb driver is totally ignorant of console
 	rotation.
 
-5. fbcon=margin:<color>
+6. fbcon=margin:<color>
 
 	This option specifies the color of the margins. The margins are the
 	leftover area at the right and the bottom of the screen that are not
 	used by text. By default, this area will be black. The 'color' value
 	is an integer number that depends on the framebuffer driver being used.
 
-6. fbcon=nodefer
+7. fbcon=nodefer
 
 	If the kernel is compiled with deferred fbcon takeover support, normally
 	the framebuffer contents, left in place by the firmware/bootloader, will
 	be preserved until there actually is some text is output to the console.
 	This option causes fbcon to bind immediately to the fbdev device.
 
-7. fbcon=logo-pos:<location>
+8. fbcon=logo-pos:<location>
 
 	The only possible 'location' is 'center' (without quotes), and when
 	given, the bootup logo is moved from the default top-left corner
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index 3bd1148d8bb6..e816d68a7ff3 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -673,3 +673,8 @@ in your dentry operations instead.
 	d_alloc_pseudo() is internal-only; uses outside of alloc_file_pseudo() are
 	very suspect (and won't work in modules).  Such uses are very likely to
 	be misspelled d_alloc_anon().
+--
+[mandatory]
+	[should've been added in 2016] stale comment in finish_open() nonwithstanding,
+	failure exits in ->atomic_open() instances should *NOT* fput() the file,
+	no matter what.  Everything is handled by the caller.
diff --git a/Documentation/lzo.txt b/Documentation/lzo.txt
index ca983328976b..f65b51523014 100644
--- a/Documentation/lzo.txt
+++ b/Documentation/lzo.txt
@@ -159,11 +159,15 @@ Byte sequences
            distance = 16384 + (H << 14) + D
            state = S (copy S literals after this block)
            End of stream is reached if distance == 16384
+           In version 1 only, to prevent ambiguity with the RLE case when
+           ((distance & 0x803f) == 0x803f) && (261 <= length <= 264), the
+           compressor must not emit block copies where distance and length
+           meet these conditions.
 
         In version 1 only, this instruction is also used to encode a run of
-        zeros if distance = 0xbfff, i.e. H = 1 and the D bits are all 1.
+           zeros if distance = 0xbfff, i.e. H = 1 and the D bits are all 1.
            In this case, it is followed by a fourth byte, X.
-           run length = ((X << 3) | (0 0 0 0 0 L L L)) + 4.
+           run length = ((X << 3) | (0 0 0 0 0 L L L)) + 4
 
       0 0 1 L L L L L  (32..63)
            Copy of small block within 16kB distance (preferably less than 34B)
diff --git a/Documentation/networking/nf_flowtable.txt b/Documentation/networking/nf_flowtable.txt
index ca2136c76042..0bf32d1121be 100644
--- a/Documentation/networking/nf_flowtable.txt
+++ b/Documentation/networking/nf_flowtable.txt
@@ -76,7 +76,7 @@ flowtable and add one rule to your forward chain.
 
         table inet x {
 		flowtable f {
-			hook ingress priority 0 devices = { eth0, eth1 };
+			hook ingress priority 0; devices = { eth0, eth1 };
 		}
                 chain y {
                         type filter hook forward priority 0; policy accept;
diff --git a/Documentation/networking/tls-offload.rst b/Documentation/networking/tls-offload.rst
index 178f4104f5cf..d24b46247a4a 100644
--- a/Documentation/networking/tls-offload.rst
+++ b/Documentation/networking/tls-offload.rst
@@ -372,13 +372,24 @@ Statistics
 Following minimum set of TLS-related statistics should be reported
 by the driver:
 
- * ``rx_tls_decrypted`` - number of successfully decrypted TLS segments
- * ``tx_tls_encrypted`` - number of in-order TLS segments passed to device
-   for encryption
+ * ``rx_tls_decrypted_packets`` - number of successfully decrypted RX packets
+   which were part of a TLS stream.
+ * ``rx_tls_decrypted_bytes`` - number of TLS payload bytes in RX packets
+   which were successfully decrypted.
+ * ``tx_tls_encrypted_packets`` - number of TX packets passed to the device
+   for encryption of their TLS payload.
+ * ``tx_tls_encrypted_bytes`` - number of TLS payload bytes in TX packets
+   passed to the device for encryption.
+ * ``tx_tls_ctx`` - number of TLS TX HW offload contexts added to device for
+   encryption.
  * ``tx_tls_ooo`` - number of TX packets which were part of a TLS stream
-   but did not arrive in the expected order
- * ``tx_tls_drop_no_sync_data`` - number of TX packets dropped because
-   they arrived out of order and associated record could not be found
+   but did not arrive in the expected order.
+ * ``tx_tls_drop_no_sync_data`` - number of TX packets which were part of
+   a TLS stream dropped, because they arrived out of order and associated
+   record could not be found.
+ * ``tx_tls_drop_bypass_req`` - number of TX packets which were part of a TLS
+   stream dropped, because they contain both data that has been encrypted by
+   software and data that expects hardware crypto offload.
    (see also :ref:`pre_tls_data`)
 
 Notable corner cases, exceptions and additional requirements
diff --git a/Documentation/s390/vfio-ccw.txt b/Documentation/s390/vfio-ccw.txt
index 2be11ad864ff..827cf74acb8c 100644
--- a/Documentation/s390/vfio-ccw.txt
+++ b/Documentation/s390/vfio-ccw.txt
@@ -173,6 +173,13 @@ The process of how these work together.
    add it to an iommu_group and a vfio_group. Then we could pass through
    the mdev to a guest.
 
+
+VFIO-CCW Regions
+----------------
+
+The vfio-ccw driver exposes MMIO regions to accept requests from and return
+results to userspace.
+
 vfio-ccw I/O region
 -------------------
 
@@ -198,6 +205,25 @@ irb_area stores the I/O result.
 
 ret_code stores a return code for each access of the region.
 
+This region is always available.
+
+vfio-ccw cmd region
+-------------------
+
+The vfio-ccw cmd region is used to accept asynchronous instructions
+from userspace::
+
+  #define VFIO_CCW_ASYNC_CMD_HSCH (1 << 0)
+  #define VFIO_CCW_ASYNC_CMD_CSCH (1 << 1)
+  struct ccw_cmd_region {
+         __u32 command;
+         __u32 ret_code;
+  } __packed;
+
+This region is exposed via region type VFIO_REGION_SUBTYPE_CCW_ASYNC_CMD.
+
+Currently, CLEAR SUBCHANNEL and HALT SUBCHANNEL use this region.
+
 vfio-ccw operation details
 --------------------------
 
@@ -280,9 +306,8 @@ Together with the corresponding work in QEMU, we can bring the passed
 through DASD/ECKD device online in a guest now and use it as a block
 device.
 
-While the current code allows the guest to start channel programs via
-START SUBCHANNEL, support for HALT SUBCHANNEL or CLEAR SUBCHANNEL is
-not yet implemented.
+The current code allows the guest to start channel programs via
+START SUBCHANNEL, and to issue HALT SUBCHANNEL and CLEAR SUBCHANNEL.
 
 vfio-ccw supports classic (command mode) channel I/O only. Transport
 mode (HPF) is not supported.
diff --git a/Documentation/sound/hd-audio/index.rst b/Documentation/sound/hd-audio/index.rst
index f8a72ffffe66..6e12de9fc34e 100644
--- a/Documentation/sound/hd-audio/index.rst
+++ b/Documentation/sound/hd-audio/index.rst
@@ -8,3 +8,4 @@ HD-Audio
    models
    controls
    dp-mst
+   realtek-pc-beep
diff --git a/Documentation/sound/hd-audio/models.rst b/Documentation/sound/hd-audio/models.rst
index 11298f0ce44d..0ea967d34583 100644
--- a/Documentation/sound/hd-audio/models.rst
+++ b/Documentation/sound/hd-audio/models.rst
@@ -216,8 +216,6 @@ alc298-dell-aio
     ALC298 fixups on Dell AIO machines
 alc275-dell-xps
     ALC275 fixups on Dell XPS models
-alc256-dell-xps13
-    ALC256 fixups on Dell XPS13
 lenovo-spk-noise
     Workaround for speaker noise on Lenovo machines
 lenovo-hotkey
diff --git a/Documentation/sound/hd-audio/realtek-pc-beep.rst b/Documentation/sound/hd-audio/realtek-pc-beep.rst
new file mode 100644
index 000000000000..be47c6f76a6e
--- /dev/null
+++ b/Documentation/sound/hd-audio/realtek-pc-beep.rst
@@ -0,0 +1,129 @@
+===============================
+Realtek PC Beep Hidden Register
+===============================
+
+This file documents the "PC Beep Hidden Register", which is present in certain
+Realtek HDA codecs and controls a muxer and pair of passthrough mixers that can
+route audio between pins but aren't themselves exposed as HDA widgets. As far
+as I can tell, these hidden routes are designed to allow flexible PC Beep output
+for codecs that don't have mixer widgets in their output paths. Why it's easier
+to hide a mixer behind an undocumented vendor register than to just expose it
+as a widget, I have no idea.
+
+Register Description
+====================
+
+The register is accessed via processing coefficient 0x36 on NID 20h. Bits not
+identified below have no discernible effect on my machine, a Dell XPS 13 9350::
+
+  MSB                           LSB
+  +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+  | |h|S|L|         | B |R|       | Known bits
+  +=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+
+  |0|0|1|1|  0x7  |0|0x0|1|  0x7  | Reset value
+  +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+
+1Ah input select (B): 2 bits
+  When zero, expose the PC Beep line (from the internal beep generator, when
+  enabled with the Set Beep Generation verb on NID 01h, or else from the
+  external PCBEEP pin) on the 1Ah pin node. When nonzero, expose the headphone
+  jack (or possibly Line In on some machines) input instead. If PC Beep is
+  selected, the 1Ah boost control has no effect.
+
+Amplify 1Ah loopback, left (L): 1 bit
+  Amplify the left channel of 1Ah before mixing it into outputs as specified
+  by h and S bits. Does not affect the level of 1Ah exposed to other widgets.
+
+Amplify 1Ah loopback, right (R): 1 bit
+  Amplify the right channel of 1Ah before mixing it into outputs as specified
+  by h and S bits. Does not affect the level of 1Ah exposed to other widgets.
+
+Loopback 1Ah to 21h [active low] (h): 1 bit
+  When zero, mix 1Ah (possibly with amplification, depending on L and R bits)
+  into 21h (headphone jack on my machine). Mixed signal respects the mute
+  setting on 21h.
+
+Loopback 1Ah to 14h (S): 1 bit
+  When one, mix 1Ah (possibly with amplification, depending on L and R bits)
+  into 14h (internal speaker on my machine). Mixed signal **ignores** the mute
+  setting on 14h and is present whenever 14h is configured as an output.
+
+Path diagrams
+=============
+
+1Ah input selection (DIV is the PC Beep divider set on NID 01h)::
+
+  <Beep generator>   <PCBEEP pin>    <Headphone jack>
+          |                |                |
+          +--DIV--+--!DIV--+       {1Ah boost control}
+                  |                         |
+                  +--(b == 0)--+--(b != 0)--+
+                               |
+               >1Ah (Beep/Headphone Mic/Line In)<
+
+Loopback of 1Ah to 21h/14h::
+
+               <1Ah (Beep/Headphone Mic/Line In)>
+                               |
+                        {amplify if L/R}
+                               |
+                  +-----!h-----+-----S-----+
+                  |                        |
+          {21h mute control}               |
+                  |                        |
+          >21h (Headphone)<     >14h (Internal Speaker)<
+
+Background
+==========
+
+All Realtek HDA codecs have a vendor-defined widget with node ID 20h which
+provides access to a bank of registers that control various codec functions.
+Registers are read and written via the standard HDA processing coefficient
+verbs (Set/Get Coefficient Index, Set/Get Processing Coefficient). The node is
+named "Realtek Vendor Registers" in public datasheets' verb listings and,
+apart from that, is entirely undocumented.
+
+This particular register, exposed at coefficient 0x36 and named in commits from
+Realtek, is of note: unlike most registers, which seem to control detailed
+amplifier parameters not in scope of the HDA specification, it controls audio
+routing which could just as easily have been defined using standard HDA mixer
+and selector widgets.
+
+Specifically, it selects between two sources for the input pin widget with Node
+ID (NID) 1Ah: the widget's signal can come either from an audio jack (on my
+laptop, a Dell XPS 13 9350, it's the headphone jack, but comments in Realtek
+commits indicate that it might be a Line In on some machines) or from the PC
+Beep line (which is itself multiplexed between the codec's internal beep
+generator and external PCBEEP pin, depending on if the beep generator is
+enabled via verbs on NID 01h). Additionally, it can mix (with optional
+amplification) that signal onto the 21h and/or 14h output pins.
+
+The register's reset value is 0x3717, corresponding to PC Beep on 1Ah that is
+then amplified and mixed into both the headphones and the speakers. Not only
+does this violate the HDA specification, which says that "[a vendor defined
+beep input pin] connection may be maintained *only* while the Link reset
+(**RST#**) is asserted", it means that we cannot ignore the register if we care
+about the input that 1Ah would otherwise expose or if the PCBEEP trace is
+poorly shielded and picks up chassis noise (both of which are the case on my
+machine).
+
+Unfortunately, there are lots of ways to get this register configuration wrong.
+Linux, it seems, has gone through most of them. For one, the register resets
+after S3 suspend: judging by existing code, this isn't the case for all vendor
+registers, and it's led to some fixes that improve behavior on cold boot but
+don't last after suspend. Other fixes have successfully switched the 1Ah input
+away from PC Beep but have failed to disable both loopback paths. On my
+machine, this means that the headphone input is amplified and looped back to
+the headphone output, which uses the exact same pins! As you might expect, this
+causes terrible headphone noise, the character of which is controlled by the
+1Ah boost control. (If you've seen instructions online to fix XPS 13 headphone
+noise by changing "Headphone Mic Boost" in ALSA, now you know why.)
+
+The information here has been obtained through black-box reverse engineering of
+the ALC256 codec's behavior and is not guaranteed to be correct. It likely
+also applies for the ALC255, ALC257, ALC235, and ALC236, since those codecs
+seem to be close relatives of the ALC256. (They all share one initialization
+function.) Additionally, other codecs like the ALC225 and ALC285 also have this
+register, judging by existing fixups in ``patch_realtek.c``, but specific
+data (e.g. node IDs, bit positions, pin mappings) for those codecs may differ
+from what I've described here.
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index f0c86fbb3b48..bc8d6d202ffa 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -1070,16 +1070,12 @@ During initialization the kernel sets this value such that even if the
 maximum number of threads is created, the thread structures occupy only
 a part (1/8th) of the available RAM pages.
 
-The minimum value that can be written to threads-max is 20.
+The minimum value that can be written to threads-max is 1.
 The maximum value that can be written to threads-max is given by the
 constant FUTEX_TID_MASK (0x3fffffff).
 If a value outside of this range is written to threads-max an error
 EINVAL occurs.
 
-The value written is checked against the available RAM pages. If the
-thread structures would occupy too much (more than 1/8th) of the
-available RAM pages threads-max is reduced accordingly.
-
 ==============================================================
 
 unknown_nmi_panic:
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 2a4531bb06bd..4ba152d2778c 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -4398,9 +4398,11 @@ EOI was received.
 #define KVM_EXIT_HYPERV_SYNIC          1
 #define KVM_EXIT_HYPERV_HCALL          2
 			__u32 type;
+			__u32 pad1;
 			union {
 				struct {
 					__u32 msr;
+					__u32 pad2;
 					__u64 control;
 					__u64 evt_page;
 					__u64 msg_page;
diff --git a/MAINTAINERS b/MAINTAINERS
index 609ec66e2ce0..c17bdc1f5f14 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -715,7 +715,7 @@ ALTERA SYSTEM MANAGER DRIVER
 M:	Thor Thayer <thor.thayer@linux.intel.com>
 S:	Maintained
 F:	drivers/mfd/altera-sysmgr.c
-F:	include/linux/mfd/altera-sysgmr.h
+F:	include/linux/mfd/altera-sysmgr.h
 
 ALTERA SYSTEM RESOURCE DRIVER FOR ARRIA10 DEVKIT
 M:	Thor Thayer <thor.thayer@linux.intel.com>
@@ -4264,6 +4264,7 @@ F:	crypto/
 F:	drivers/crypto/
 F:	include/crypto/
 F:	include/linux/crypto*
+F:	lib/crypto/
 
 CRYPTOGRAPHIC RANDOM NUMBER GENERATOR
 M:	Neil Horman <nhorman@tuxdriver.com>
@@ -5990,7 +5991,7 @@ M:	Florian Fainelli <f.fainelli@gmail.com>
 M:	Heiner Kallweit <hkallweit1@gmail.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
-F:	Documentation/ABI/testing/sysfs-bus-mdio
+F:	Documentation/ABI/testing/sysfs-class-net-phydev
 F:	Documentation/devicetree/bindings/net/mdio*
 F:	Documentation/networking/phy.rst
 F:	drivers/net/phy/
@@ -7911,7 +7912,7 @@ M:	Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
 M:	Rodrigo Vivi <rodrigo.vivi@intel.com>
 L:	intel-gfx@lists.freedesktop.org
 W:	https://01.org/linuxgraphics/
-B:	https://01.org/linuxgraphics/documentation/how-report-bugs
+B:	https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs
 C:	irc://chat.freenode.net/intel-gfx
 Q:	http://patchwork.freedesktop.org/project/intel-gfx/
 T:	git git://anongit.freedesktop.org/drm-intel
@@ -11888,7 +11889,7 @@ L:	netdev@vger.kernel.org
 S:	Supported
 F:	lib/packing.c
 F:	include/linux/packing.h
-F:	Documentation/packing.txt
+F:	Documentation/core-api/packing.rst
 
 PADATA PARALLEL EXECUTION MECHANISM
 M:	Steffen Klassert <steffen.klassert@secunet.com>
@@ -17521,14 +17522,6 @@ S:	Maintained
 F:	mm/zpool.c
 F:	include/linux/zpool.h
 
-ZR36067 VIDEO FOR LINUX DRIVER
-L:	mjpeg-users@lists.sourceforge.net
-L:	linux-media@vger.kernel.org
-W:	http://mjpeg.sourceforge.net/driver-zoran/
-T:	hg https://linuxtv.org/hg/v4l-dvb
-S:	Odd Fixes
-F:	drivers/staging/media/zoran/
-
 ZRAM COMPRESSED RAM BLOCK DEVICE DRVIER
 M:	Minchan Kim <minchan@kernel.org>
 M:	Nitin Gupta <ngupta@vflare.org>
diff --git a/Makefile b/Makefile
index 15769786db17..bf45ecd4c9ea 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 2
-SUBLEVEL = 34
+SUBLEVEL = 60
 EXTRAVERSION =
 NAME = Bobtail Squid
 
@@ -522,7 +522,7 @@ ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),)
 ifneq ($(CROSS_COMPILE),)
 CLANG_FLAGS	+= --target=$(notdir $(CROSS_COMPILE:%-=%))
 GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)elfedit))
-CLANG_FLAGS	+= --prefix=$(GCC_TOOLCHAIN_DIR)
+CLANG_FLAGS	+= --prefix=$(GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE))
 GCC_TOOLCHAIN	:= $(realpath $(GCC_TOOLCHAIN_DIR)/..)
 endif
 ifneq ($(GCC_TOOLCHAIN),)
@@ -579,12 +579,8 @@ KBUILD_MODULES :=
 KBUILD_BUILTIN := 1
 
 # If we have only "make modules", don't compile built-in objects.
-# When we're building modules with modversions, we need to consider
-# the built-in objects during the descend as well, in order to
-# make sure the checksums are up to date before we record them.
-
 ifeq ($(MAKECMDGOALS),modules)
-  KBUILD_BUILTIN := $(if $(CONFIG_MODVERSIONS),1)
+  KBUILD_BUILTIN :=
 endif
 
 # If we have "make <whatever> modules", compile modules
@@ -702,12 +698,9 @@ else
 KBUILD_CFLAGS   += -O2
 endif
 
-ifdef CONFIG_CC_DISABLE_WARN_MAYBE_UNINITIALIZED
-KBUILD_CFLAGS   += -Wno-maybe-uninitialized
-endif
-
 # Tell gcc to never replace conditional load with a non-conditional one
 KBUILD_CFLAGS	+= $(call cc-option,--param=allow-store-data-races=0)
+KBUILD_CFLAGS	+= $(call cc-option,-fno-allow-store-data-races)
 
 include scripts/Makefile.kcov
 include scripts/Makefile.gcc-plugins
@@ -850,6 +843,17 @@ KBUILD_CFLAGS += -Wno-pointer-sign
 # disable stringop warnings in gcc 8+
 KBUILD_CFLAGS += $(call cc-disable-warning, stringop-truncation)
 
+# We'll want to enable this eventually, but it's not going away for 5.7 at least
+KBUILD_CFLAGS += $(call cc-disable-warning, zero-length-bounds)
+KBUILD_CFLAGS += $(call cc-disable-warning, array-bounds)
+KBUILD_CFLAGS += $(call cc-disable-warning, stringop-overflow)
+
+# Another good warning that we'll want to enable eventually
+KBUILD_CFLAGS += $(call cc-disable-warning, restrict)
+
+# Enabled with W=2, disabled by default as noisy
+KBUILD_CFLAGS += $(call cc-disable-warning, maybe-uninitialized)
+
 # disable invalid "can't wrap" optimizations for signed / pointers
 KBUILD_CFLAGS	+= $(call cc-option,-fno-strict-overflow)
 
@@ -880,6 +884,12 @@ KBUILD_CFLAGS   += $(call cc-option,-Werror=designated-init)
 # change __FILE__ to the relative path from the srctree
 KBUILD_CFLAGS	+= $(call cc-option,-fmacro-prefix-map=$(srctree)/=)
 
+# ensure -fcf-protection is disabled when using retpoline as it is
+# incompatible with -mindirect-branch=thunk-extern
+ifdef CONFIG_RETPOLINE
+KBUILD_CFLAGS += $(call cc-option,-fcf-protection=none)
+endif
+
 # use the deterministic mode of AR if available
 KBUILD_ARFLAGS := $(call ar-option,D)
 
@@ -1103,7 +1113,7 @@ ifneq ($(srctree),.)
 	$(Q)if [ -f $(srctree)/.config -o \
 		 -d $(srctree)/include/config -o \
 		 -d $(srctree)/arch/$(SRCARCH)/include/generated ]; then \
-		echo >&2 "  $(srctree) is not clean, please run 'make mrproper'"; \
+		echo >&2 "  $(srctree) is not clean, please run 'make ARCH=$(ARCH) mrproper'"; \
 		echo >&2 "  in the '$(srctree)' directory.";\
 		/bin/false; \
 	fi;
@@ -1246,12 +1256,16 @@ ifneq ($(dtstree),)
 %.dtb: prepare3 scripts_dtc
 	$(Q)$(MAKE) $(build)=$(dtstree) $(dtstree)/$@
 
-PHONY += dtbs dtbs_install dt_binding_check
-dtbs dtbs_check: prepare3 scripts_dtc
+PHONY += dtbs dtbs_install dtbs_check
+dtbs: prepare3 scripts_dtc
 	$(Q)$(MAKE) $(build)=$(dtstree)
 
+ifneq ($(filter dtbs_check, $(MAKECMDGOALS)),)
+dtbs: dt_binding_check
+endif
+
 dtbs_check: export CHECK_DTBS=1
-dtbs_check: dt_binding_check
+dtbs_check: dtbs
 
 dtbs_install:
 	$(Q)$(MAKE) $(dtbinst)=$(dtstree)
@@ -1266,6 +1280,7 @@ PHONY += scripts_dtc
 scripts_dtc: scripts_basic
 	$(Q)$(MAKE) $(build)=scripts/dtc
 
+PHONY += dt_binding_check
 dt_binding_check: scripts_dtc
 	$(Q)$(MAKE) $(build)=Documentation/devicetree/bindings
 
@@ -1278,6 +1293,13 @@ ifdef CONFIG_MODULES
 
 all: modules
 
+# When we're building modules with modversions, we need to consider
+# the built-in objects during the descend as well, in order to
+# make sure the checksums are up to date before we record them.
+ifdef CONFIG_MODVERSIONS
+  KBUILD_BUILTIN := 1
+endif
+
 # Build modules
 #
 # A module can be listed more than once in obj-m resulting in
diff --git a/arch/Kconfig b/arch/Kconfig
index c47b328eada0..d9c4f1ef885c 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -394,10 +394,10 @@ config HAVE_ARCH_JUMP_LABEL_RELATIVE
 config HAVE_RCU_TABLE_FREE
 	bool
 
-config HAVE_RCU_TABLE_NO_INVALIDATE
+config HAVE_MMU_GATHER_PAGE_SIZE
 	bool
 
-config HAVE_MMU_GATHER_PAGE_SIZE
+config MMU_GATHER_NO_RANGE
 	bool
 
 config HAVE_MMU_GATHER_NO_GATHER
diff --git a/arch/alpha/include/asm/io.h b/arch/alpha/include/asm/io.h
index ccf9d65166bb..ead9c7acb643 100644
--- a/arch/alpha/include/asm/io.h
+++ b/arch/alpha/include/asm/io.h
@@ -327,14 +327,18 @@ static inline int __is_mmio(const volatile void __iomem *addr)
 #if IO_CONCAT(__IO_PREFIX,trivial_io_bw)
 extern inline unsigned int ioread8(void __iomem *addr)
 {
-	unsigned int ret = IO_CONCAT(__IO_PREFIX,ioread8)(addr);
+	unsigned int ret;
+	mb();
+	ret = IO_CONCAT(__IO_PREFIX,ioread8)(addr);
 	mb();
 	return ret;
 }
 
 extern inline unsigned int ioread16(void __iomem *addr)
 {
-	unsigned int ret = IO_CONCAT(__IO_PREFIX,ioread16)(addr);
+	unsigned int ret;
+	mb();
+	ret = IO_CONCAT(__IO_PREFIX,ioread16)(addr);
 	mb();
 	return ret;
 }
@@ -375,7 +379,9 @@ extern inline void outw(u16 b, unsigned long port)
 #if IO_CONCAT(__IO_PREFIX,trivial_io_lq)
 extern inline unsigned int ioread32(void __iomem *addr)
 {
-	unsigned int ret = IO_CONCAT(__IO_PREFIX,ioread32)(addr);
+	unsigned int ret;
+	mb();
+	ret = IO_CONCAT(__IO_PREFIX,ioread32)(addr);
 	mb();
 	return ret;
 }
@@ -420,14 +426,18 @@ extern inline void __raw_writew(u16 b, volatile void __iomem *addr)
 
 extern inline u8 readb(const volatile void __iomem *addr)
 {
-	u8 ret = __raw_readb(addr);
+	u8 ret;
+	mb();
+	ret = __raw_readb(addr);
 	mb();
 	return ret;
 }
 
 extern inline u16 readw(const volatile void __iomem *addr)
 {
-	u16 ret = __raw_readw(addr);
+	u16 ret;
+	mb();
+	ret = __raw_readw(addr);
 	mb();
 	return ret;
 }
@@ -468,14 +478,18 @@ extern inline void __raw_writeq(u64 b, volatile void __iomem *addr)
 
 extern inline u32 readl(const volatile void __iomem *addr)
 {
-	u32 ret = __raw_readl(addr);
+	u32 ret;
+	mb();
+	ret = __raw_readl(addr);
 	mb();
 	return ret;
 }
 
 extern inline u64 readq(const volatile void __iomem *addr)
 {
-	u64 ret = __raw_readq(addr);
+	u64 ret;
+	mb();
+	ret = __raw_readq(addr);
 	mb();
 	return ret;
 }
@@ -504,14 +518,44 @@ extern inline void writeq(u64 b, volatile void __iomem *addr)
 #define outb_p		outb
 #define outw_p		outw
 #define outl_p		outl
-#define readb_relaxed(addr)	__raw_readb(addr)
-#define readw_relaxed(addr)	__raw_readw(addr)
-#define readl_relaxed(addr)	__raw_readl(addr)
-#define readq_relaxed(addr)	__raw_readq(addr)
-#define writeb_relaxed(b, addr)	__raw_writeb(b, addr)
-#define writew_relaxed(b, addr)	__raw_writew(b, addr)
-#define writel_relaxed(b, addr)	__raw_writel(b, addr)
-#define writeq_relaxed(b, addr)	__raw_writeq(b, addr)
+
+extern u8 readb_relaxed(const volatile void __iomem *addr);
+extern u16 readw_relaxed(const volatile void __iomem *addr);
+extern u32 readl_relaxed(const volatile void __iomem *addr);
+extern u64 readq_relaxed(const volatile void __iomem *addr);
+
+#if IO_CONCAT(__IO_PREFIX,trivial_io_bw)
+extern inline u8 readb_relaxed(const volatile void __iomem *addr)
+{
+	mb();
+	return __raw_readb(addr);
+}
+
+extern inline u16 readw_relaxed(const volatile void __iomem *addr)
+{
+	mb();
+	return __raw_readw(addr);
+}
+#endif
+
+#if IO_CONCAT(__IO_PREFIX,trivial_io_lq)
+extern inline u32 readl_relaxed(const volatile void __iomem *addr)
+{
+	mb();
+	return __raw_readl(addr);
+}
+
+extern inline u64 readq_relaxed(const volatile void __iomem *addr)
+{
+	mb();
+	return __raw_readq(addr);
+}
+#endif
+
+#define writeb_relaxed	writeb
+#define writew_relaxed	writew
+#define writel_relaxed	writel
+#define writeq_relaxed	writeq
 
 /*
  * String version of IO memory access ops:
diff --git a/arch/alpha/kernel/io.c b/arch/alpha/kernel/io.c
index c025a3e5e357..938de13adfbf 100644
--- a/arch/alpha/kernel/io.c
+++ b/arch/alpha/kernel/io.c
@@ -16,21 +16,27 @@
 unsigned int
 ioread8(void __iomem *addr)
 {
-	unsigned int ret = IO_CONCAT(__IO_PREFIX,ioread8)(addr);
+	unsigned int ret;
+	mb();
+	ret = IO_CONCAT(__IO_PREFIX,ioread8)(addr);
 	mb();
 	return ret;
 }
 
 unsigned int ioread16(void __iomem *addr)
 {
-	unsigned int ret = IO_CONCAT(__IO_PREFIX,ioread16)(addr);
+	unsigned int ret;
+	mb();
+	ret = IO_CONCAT(__IO_PREFIX,ioread16)(addr);
 	mb();
 	return ret;
 }
 
 unsigned int ioread32(void __iomem *addr)
 {
-	unsigned int ret = IO_CONCAT(__IO_PREFIX,ioread32)(addr);
+	unsigned int ret;
+	mb();
+	ret = IO_CONCAT(__IO_PREFIX,ioread32)(addr);
 	mb();
 	return ret;
 }
@@ -148,28 +154,36 @@ EXPORT_SYMBOL(__raw_writeq);
 
 u8 readb(const volatile void __iomem *addr)
 {
-	u8 ret = __raw_readb(addr);
+	u8 ret;
+	mb();
+	ret = __raw_readb(addr);
 	mb();
 	return ret;
 }
 
 u16 readw(const volatile void __iomem *addr)
 {
-	u16 ret = __raw_readw(addr);
+	u16 ret;
+	mb();
+	ret = __raw_readw(addr);
 	mb();
 	return ret;
 }
 
 u32 readl(const volatile void __iomem *addr)
 {
-	u32 ret = __raw_readl(addr);
+	u32 ret;
+	mb();
+	ret = __raw_readl(addr);
 	mb();
 	return ret;
 }
 
 u64 readq(const volatile void __iomem *addr)
 {
-	u64 ret = __raw_readq(addr);
+	u64 ret;
+	mb();
+	ret = __raw_readq(addr);
 	mb();
 	return ret;
 }
@@ -207,6 +221,38 @@ EXPORT_SYMBOL(writew);
 EXPORT_SYMBOL(writel);
 EXPORT_SYMBOL(writeq);
 
+/*
+ * The _relaxed functions must be ordered w.r.t. each other, but they don't
+ * have to be ordered w.r.t. other memory accesses.
+ */
+u8 readb_relaxed(const volatile void __iomem *addr)
+{
+	mb();
+	return __raw_readb(addr);
+}
+
+u16 readw_relaxed(const volatile void __iomem *addr)
+{
+	mb();
+	return __raw_readw(addr);
+}
+
+u32 readl_relaxed(const volatile void __iomem *addr)
+{
+	mb();
+	return __raw_readl(addr);
+}
+
+u64 readq_relaxed(const volatile void __iomem *addr)
+{
+	mb();
+	return __raw_readq(addr);
+}
+
+EXPORT_SYMBOL(readb_relaxed);
+EXPORT_SYMBOL(readw_relaxed);
+EXPORT_SYMBOL(readl_relaxed);
+EXPORT_SYMBOL(readq_relaxed);
 
 /*
  * Read COUNT 8-bit bytes from port PORT into memory starting at SRC.
diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi
index 08bcfed6b80f..134cc223ea81 100644
--- a/arch/arc/boot/dts/axs10x_mb.dtsi
+++ b/arch/arc/boot/dts/axs10x_mb.dtsi
@@ -77,6 +77,7 @@
 			interrupt-names = "macirq";
 			phy-mode = "rgmii";
 			snps,pbl = < 32 >;
+			snps,multicast-filter-bins = <256>;
 			clocks = <&apbclk>;
 			clock-names = "stmmaceth";
 			max-speed = <100>;
diff --git a/arch/arc/include/asm/elf.h b/arch/arc/include/asm/elf.h
index c77a0e3671ac..0284ace0e1ab 100644
--- a/arch/arc/include/asm/elf.h
+++ b/arch/arc/include/asm/elf.h
@@ -19,7 +19,7 @@
 #define  R_ARC_32_PCREL		0x31
 
 /*to set parameters in the core dumps */
-#define ELF_ARCH		EM_ARCOMPACT
+#define ELF_ARCH		EM_ARC_INUSE
 #define ELF_CLASS		ELFCLASS32
 
 #ifdef CONFIG_CPU_BIG_ENDIAN
diff --git a/arch/arc/include/asm/linkage.h b/arch/arc/include/asm/linkage.h
index 54f5ec5c1759..619866599bff 100644
--- a/arch/arc/include/asm/linkage.h
+++ b/arch/arc/include/asm/linkage.h
@@ -11,6 +11,8 @@
 #ifdef __ASSEMBLY__
 
 #define ASM_NL		 `	/* use '`' to mark new line in macro */
+#define __ALIGN		.align 4
+#define __ALIGN_STR	__stringify(__ALIGN)
 
 /* annotation for data we want in DCCM - if enabled in .config */
 .macro ARCFP_DATA nm
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index a2bfacbcfce1..4bd108d1a14a 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -153,7 +153,6 @@ END(EV_Extension)
 tracesys:
 	; save EFA in case tracer wants the PC of traced task
 	; using ERET won't work since next-PC has already committed
-	lr  r12, [efa]
 	GET_CURR_TASK_FIELD_PTR   TASK_THREAD, r11
 	st  r12, [r11, THREAD_FAULT_ADDR]	; thread.fault_address
 
@@ -196,15 +195,9 @@ tracesys_exit:
 ; Breakpoint TRAP
 ; ---------------------------------------------
 trap_with_param:
-
-	; stop_pc info by gdb needs this info
-	lr  r0, [efa]
+	mov r0, r12	; EFA in case ptracer/gdb wants stop_pc
 	mov r1, sp
 
-	; Now that we have read EFA, it is safe to do "fake" rtie
-	;   and get out of CPU exception mode
-	FAKE_RET_FROM_EXCPN
-
 	; Save callee regs in case gdb wants to have a look
 	; SP will grow up by size of CALLEE Reg-File
 	; NOTE: clobbers r12
@@ -231,6 +224,10 @@ ENTRY(EV_Trap)
 
 	EXCEPTION_PROLOGUE
 
+	lr  r12, [efa]
+
+	FAKE_RET_FROM_EXCPN
+
 	;============ TRAP 1   :breakpoints
 	; Check ECR for trap with arg (PROLOGUE ensures r9 has ECR)
 	bmsk.f 0, r9, 7
@@ -238,9 +235,6 @@ ENTRY(EV_Trap)
 
 	;============ TRAP  (no param): syscall top level
 
-	; First return from Exception to pure K mode (Exception/IRQs renabled)
-	FAKE_RET_FROM_EXCPN
-
 	; If syscall tracing ongoing, invoke pre-post-hooks
 	GET_CURR_THR_INFO_FLAGS   r10
 	btst r10, TIF_SYSCALL_TRACE
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index 7ee89dc61f6e..23dc002aa574 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -12,6 +12,7 @@
 #include <linux/clocksource.h>
 #include <linux/console.h>
 #include <linux/module.h>
+#include <linux/sizes.h>
 #include <linux/cpu.h>
 #include <linux/of_fdt.h>
 #include <linux/of.h>
@@ -409,12 +410,12 @@ static void arc_chk_core_config(void)
 	if ((unsigned int)__arc_dccm_base != cpu->dccm.base_addr)
 		panic("Linux built with incorrect DCCM Base address\n");
 
-	if (CONFIG_ARC_DCCM_SZ != cpu->dccm.sz)
+	if (CONFIG_ARC_DCCM_SZ * SZ_1K != cpu->dccm.sz)
 		panic("Linux built with incorrect DCCM Size\n");
 #endif
 
 #ifdef CONFIG_ARC_HAS_ICCM
-	if (CONFIG_ARC_ICCM_SZ != cpu->iccm.sz)
+	if (CONFIG_ARC_ICCM_SZ * SZ_1K != cpu->iccm.sz)
 		panic("Linux built with incorrect ICCM Size\n");
 #endif
 
diff --git a/arch/arc/plat-eznps/Kconfig b/arch/arc/plat-eznps/Kconfig
index 2eaecfb063a7..ea52d05e1922 100644
--- a/arch/arc/plat-eznps/Kconfig
+++ b/arch/arc/plat-eznps/Kconfig
@@ -6,8 +6,9 @@
 
 menuconfig ARC_PLAT_EZNPS
 	bool "\"EZchip\" ARC dev platform"
+	depends on ISA_ARCOMPACT
 	select CPU_BIG_ENDIAN
-	select CLKSRC_NPS
+	select CLKSRC_NPS if !PHYS_ADDR_T_64BIT
 	select EZNPS_GIC
 	select EZCHIP_NPS_MANAGEMENT_ENET if ETHERNET
 	help
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 6029d324911c..b0eadcba4bd2 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -67,7 +67,7 @@ config ARM
 	select HAVE_EBPF_JIT if !CPU_ENDIAN_BE32
 	select HAVE_CONTEXT_TRACKING
 	select HAVE_C_RECORDMCOUNT
-	select HAVE_DEBUG_KMEMLEAK
+	select HAVE_DEBUG_KMEMLEAK if !XIP_KERNEL
 	select HAVE_DMA_CONTIGUOUS if MMU
 	select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE
@@ -1981,7 +1981,7 @@ config XIP_DEFLATED_DATA
 config KEXEC
 	bool "Kexec system call (EXPERIMENTAL)"
 	depends on (!SMP || PM_SLEEP_SMP)
-	depends on !CPU_V7M
+	depends on MMU
 	select KEXEC_CORE
 	help
 	  kexec is a system call that implements the ability to shutdown your
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 1a63e497493c..d81ebbbbd7ad 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -310,13 +310,15 @@ endif
 ifeq ($(CONFIG_STACKPROTECTOR_PER_TASK),y)
 prepare: stack_protector_prepare
 stack_protector_prepare: prepare0
-	$(eval KBUILD_CFLAGS += \
+	$(eval SSP_PLUGIN_CFLAGS := \
 		-fplugin-arg-arm_ssp_per_task_plugin-tso=$(shell	\
 			awk '{if ($$2 == "THREAD_SZ_ORDER") print $$3;}'\
 				include/generated/asm-offsets.h)	\
 		-fplugin-arg-arm_ssp_per_task_plugin-offset=$(shell	\
 			awk '{if ($$2 == "TI_STACK_CANARY") print $$3;}'\
 				include/generated/asm-offsets.h))
+	$(eval KBUILD_CFLAGS += $(SSP_PLUGIN_CFLAGS))
+	$(eval GCC_PLUGINS_CFLAGS += $(SSP_PLUGIN_CFLAGS))
 endif
 
 all:	$(notdir $(KBUILD_IMAGE))
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 9219389bbe61..1483966dcf23 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -101,7 +101,6 @@ clean-files += piggy_data lib1funcs.S ashldi3.S bswapsdi2.S \
 		$(libfdt) $(libfdt_hdrs) hyp-stub.S
 
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
-KBUILD_CFLAGS += $(DISABLE_ARM_SSP_PER_TASK_PLUGIN)
 
 ifeq ($(CONFIG_FUNCTION_TRACER),y)
 ORIG_CFLAGS := $(KBUILD_CFLAGS)
@@ -117,7 +116,8 @@ CFLAGS_fdt_ro.o := $(nossp_flags)
 CFLAGS_fdt_rw.o := $(nossp_flags)
 CFLAGS_fdt_wip.o := $(nossp_flags)
 
-ccflags-y := -fpic $(call cc-option,-mno-single-pic-base,) -fno-builtin -I$(obj)
+ccflags-y := -fpic $(call cc-option,-mno-single-pic-base,) -fno-builtin \
+	     -I$(obj) $(DISABLE_ARM_SSP_PER_TASK_PLUGIN)
 asflags-y := -DZIMAGE
 
 # Supply kernel BSS size to the decompressor via a linker symbol.
diff --git a/arch/arm/boot/compressed/vmlinux.lds.S b/arch/arm/boot/compressed/vmlinux.lds.S
index fc7ed03d8b93..51b078604978 100644
--- a/arch/arm/boot/compressed/vmlinux.lds.S
+++ b/arch/arm/boot/compressed/vmlinux.lds.S
@@ -43,7 +43,7 @@ SECTIONS
   }
   .table : ALIGN(4) {
     _table_start = .;
-    LONG(ZIMAGE_MAGIC(2))
+    LONG(ZIMAGE_MAGIC(4))
     LONG(ZIMAGE_MAGIC(0x5a534c4b))
     LONG(ZIMAGE_MAGIC(__piggy_size_addr - _start))
     LONG(ZIMAGE_MAGIC(_kernel_bss_size))
diff --git a/arch/arm/boot/dts/am335x-boneblack-common.dtsi b/arch/arm/boot/dts/am335x-boneblack-common.dtsi
index 7ad079861efd..91f93bc89716 100644
--- a/arch/arm/boot/dts/am335x-boneblack-common.dtsi
+++ b/arch/arm/boot/dts/am335x-boneblack-common.dtsi
@@ -131,6 +131,11 @@
 };
 
 / {
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x80000000 0x20000000>; /* 512 MB */
+	};
+
 	clk_mcasp0_fixed: clk_mcasp0_fixed {
 		#clock-cells = <0>;
 		compatible = "fixed-clock";
diff --git a/arch/arm/boot/dts/am335x-pocketbeagle.dts b/arch/arm/boot/dts/am335x-pocketbeagle.dts
index ff4f919d22f6..abf2badce53d 100644
--- a/arch/arm/boot/dts/am335x-pocketbeagle.dts
+++ b/arch/arm/boot/dts/am335x-pocketbeagle.dts
@@ -88,7 +88,6 @@
 			AM33XX_PADCONF(AM335X_PIN_MMC0_DAT3, PIN_INPUT_PULLUP, MUX_MODE0)
 			AM33XX_PADCONF(AM335X_PIN_MMC0_CMD, PIN_INPUT_PULLUP, MUX_MODE0)
 			AM33XX_PADCONF(AM335X_PIN_MMC0_CLK, PIN_INPUT_PULLUP, MUX_MODE0)
-			AM33XX_PADCONF(AM335X_PIN_MCASP0_ACLKR, PIN_INPUT, MUX_MODE4)		/* (B12) mcasp0_aclkr.mmc0_sdwp */
 		>;
 	};
 
diff --git a/arch/arm/boot/dts/am335x-sancloud-bbe.dts b/arch/arm/boot/dts/am335x-sancloud-bbe.dts
index 8678e6e35493..e5fdb7abb0d5 100644
--- a/arch/arm/boot/dts/am335x-sancloud-bbe.dts
+++ b/arch/arm/boot/dts/am335x-sancloud-bbe.dts
@@ -108,7 +108,7 @@
 
 &cpsw_emac0 {
 	phy-handle = <&ethphy0>;
-	phy-mode = "rgmii-txid";
+	phy-mode = "rgmii-id";
 };
 
 &i2c0 {
diff --git a/arch/arm/boot/dts/am437x-gp-evm.dts b/arch/arm/boot/dts/am437x-gp-evm.dts
index cae4500194fe..811c8cae315b 100644
--- a/arch/arm/boot/dts/am437x-gp-evm.dts
+++ b/arch/arm/boot/dts/am437x-gp-evm.dts
@@ -86,7 +86,7 @@
 		};
 
 	lcd0: display {
-		compatible = "osddisplays,osd057T0559-34ts", "panel-dpi";
+		compatible = "osddisplays,osd070t1718-19ts", "panel-dpi";
 		label = "lcd";
 
 		backlight = <&lcd_bl>;
diff --git a/arch/arm/boot/dts/am437x-idk-evm.dts b/arch/arm/boot/dts/am437x-idk-evm.dts
index f3ced6df0c9b..9f66f96d09c9 100644
--- a/arch/arm/boot/dts/am437x-idk-evm.dts
+++ b/arch/arm/boot/dts/am437x-idk-evm.dts
@@ -526,11 +526,11 @@
 	 * Supply voltage supervisor on board will not allow opp50 so
 	 * disable it and set opp100 as suspend OPP.
 	 */
-	opp50@300000000 {
+	opp50-300000000 {
 		status = "disabled";
 	};
 
-	opp100@600000000 {
+	opp100-600000000 {
 		opp-suspend;
 	};
 };
diff --git a/arch/arm/boot/dts/am437x-l4.dtsi b/arch/arm/boot/dts/am437x-l4.dtsi
index 04bee4ff9dcb..53017a1e5ab0 100644
--- a/arch/arm/boot/dts/am437x-l4.dtsi
+++ b/arch/arm/boot/dts/am437x-l4.dtsi
@@ -1578,8 +1578,9 @@
 			reg-names = "rev";
 			ti,hwmods = "d_can0";
 			/* Domains (P, C): per_pwrdm, l4ls_clkdm */
-			clocks = <&l4ls_clkctrl AM4_L4LS_D_CAN0_CLKCTRL 0>;
-			clock-names = "fck";
+			clocks = <&l4ls_clkctrl AM4_L4LS_D_CAN0_CLKCTRL 0>,
+			<&dcan0_fck>;
+			clock-names = "fck", "osc";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x0 0xcc000 0x2000>;
@@ -1587,6 +1588,8 @@
 			dcan0: can@0 {
 				compatible = "ti,am4372-d_can", "ti,am3352-d_can";
 				reg = <0x0 0x2000>;
+				clocks = <&dcan0_fck>;
+				clock-names = "fck";
 				syscon-raminit = <&scm_conf 0x644 0>;
 				interrupts = <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>;
 				status = "disabled";
@@ -1599,8 +1602,9 @@
 			reg-names = "rev";
 			ti,hwmods = "d_can1";
 			/* Domains (P, C): per_pwrdm, l4ls_clkdm */
-			clocks = <&l4ls_clkctrl AM4_L4LS_D_CAN1_CLKCTRL 0>;
-			clock-names = "fck";
+			clocks = <&l4ls_clkctrl AM4_L4LS_D_CAN1_CLKCTRL 0>,
+			<&dcan1_fck>;
+			clock-names = "fck", "osc";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x0 0xd0000 0x2000>;
@@ -1608,6 +1612,8 @@
 			dcan1: can@0 {
 				compatible = "ti,am4372-d_can", "ti,am3352-d_can";
 				reg = <0x0 0x2000>;
+				clocks = <&dcan1_fck>;
+				clock-name = "fck";
 				syscon-raminit = <&scm_conf 0x644 1>;
 				interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>;
 				status = "disabled";
diff --git a/arch/arm/boot/dts/am43x-epos-evm.dts b/arch/arm/boot/dts/am43x-epos-evm.dts
index 95314121d111..a6fbc088daa8 100644
--- a/arch/arm/boot/dts/am43x-epos-evm.dts
+++ b/arch/arm/boot/dts/am43x-epos-evm.dts
@@ -42,7 +42,7 @@
 	};
 
 	lcd0: display {
-		compatible = "osddisplays,osd057T0559-34ts", "panel-dpi";
+		compatible = "osddisplays,osd070t1718-19ts", "panel-dpi";
 		label = "lcd";
 
 		backlight = <&lcd_bl>;
@@ -848,6 +848,7 @@
 	pinctrl-names = "default", "sleep";
 	pinctrl-0 = <&spi0_pins_default>;
 	pinctrl-1 = <&spi0_pins_sleep>;
+	ti,pindir-d0-out-d1-in = <1>;
 };
 
 &spi1 {
@@ -855,6 +856,7 @@
 	pinctrl-names = "default", "sleep";
 	pinctrl-0 = <&spi1_pins_default>;
 	pinctrl-1 = <&spi1_pins_sleep>;
+	ti,pindir-d0-out-d1-in = <1>;
 };
 
 &usb2_phy1 {
diff --git a/arch/arm/boot/dts/am43xx-clocks.dtsi b/arch/arm/boot/dts/am43xx-clocks.dtsi
index 091356f2a8c1..c726cd8dbdf1 100644
--- a/arch/arm/boot/dts/am43xx-clocks.dtsi
+++ b/arch/arm/boot/dts/am43xx-clocks.dtsi
@@ -704,6 +704,60 @@
 		ti,bit-shift = <8>;
 		reg = <0x2a48>;
 	};
+
+	clkout1_osc_div_ck: clkout1-osc-div-ck {
+		#clock-cells = <0>;
+		compatible = "ti,divider-clock";
+		clocks = <&sys_clkin_ck>;
+		ti,bit-shift = <20>;
+		ti,max-div = <4>;
+		reg = <0x4100>;
+	};
+
+	clkout1_src2_mux_ck: clkout1-src2-mux-ck {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&clk_rc32k_ck>, <&sysclk_div>, <&dpll_ddr_m2_ck>,
+			 <&dpll_per_m2_ck>, <&dpll_disp_m2_ck>,
+			 <&dpll_mpu_m2_ck>;
+		reg = <0x4100>;
+	};
+
+	clkout1_src2_pre_div_ck: clkout1-src2-pre-div-ck {
+		#clock-cells = <0>;
+		compatible = "ti,divider-clock";
+		clocks = <&clkout1_src2_mux_ck>;
+		ti,bit-shift = <4>;
+		ti,max-div = <8>;
+		reg = <0x4100>;
+	};
+
+	clkout1_src2_post_div_ck: clkout1-src2-post-div-ck {
+		#clock-cells = <0>;
+		compatible = "ti,divider-clock";
+		clocks = <&clkout1_src2_pre_div_ck>;
+		ti,bit-shift = <8>;
+		ti,max-div = <32>;
+		ti,index-power-of-two;
+		reg = <0x4100>;
+	};
+
+	clkout1_mux_ck: clkout1-mux-ck {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&clkout1_osc_div_ck>, <&clk_rc32k_ck>,
+			 <&clkout1_src2_post_div_ck>, <&dpll_extdev_m2_ck>;
+		ti,bit-shift = <16>;
+		reg = <0x4100>;
+	};
+
+	clkout1_ck: clkout1-ck {
+		#clock-cells = <0>;
+		compatible = "ti,gate-clock";
+		clocks = <&clkout1_mux_ck>;
+		ti,bit-shift = <23>;
+		reg = <0x4100>;
+	};
 };
 
 &prcm {
diff --git a/arch/arm/boot/dts/am571x-idk.dts b/arch/arm/boot/dts/am571x-idk.dts
index 0aaacea1d887..10105a497c1a 100644
--- a/arch/arm/boot/dts/am571x-idk.dts
+++ b/arch/arm/boot/dts/am571x-idk.dts
@@ -167,11 +167,7 @@
 
 &pcie1_rc {
 	status = "okay";
-	gpios = <&gpio3 23 GPIO_ACTIVE_HIGH>;
-};
-
-&pcie1_ep {
-	gpios = <&gpio3 23 GPIO_ACTIVE_HIGH>;
+	gpios = <&gpio5 18 GPIO_ACTIVE_HIGH>;
 };
 
 &mmc1 {
diff --git a/arch/arm/boot/dts/am572x-idk-common.dtsi b/arch/arm/boot/dts/am572x-idk-common.dtsi
index a064f13b3880..ddf123620e96 100644
--- a/arch/arm/boot/dts/am572x-idk-common.dtsi
+++ b/arch/arm/boot/dts/am572x-idk-common.dtsi
@@ -147,10 +147,6 @@
 	gpios = <&gpio3 23 GPIO_ACTIVE_HIGH>;
 };
 
-&pcie1_ep {
-	gpios = <&gpio3 23 GPIO_ACTIVE_HIGH>;
-};
-
 &mailbox5 {
 	status = "okay";
 	mbox_ipu1_ipc3x: mbox_ipu1_ipc3x {
diff --git a/arch/arm/boot/dts/am57xx-beagle-x15-common.dtsi b/arch/arm/boot/dts/am57xx-beagle-x15-common.dtsi
index bc76f1705c0f..a813a0cf3ff3 100644
--- a/arch/arm/boot/dts/am57xx-beagle-x15-common.dtsi
+++ b/arch/arm/boot/dts/am57xx-beagle-x15-common.dtsi
@@ -29,6 +29,27 @@
 		reg = <0x0 0x80000000 0x0 0x80000000>;
 	};
 
+	main_12v0: fixedregulator-main_12v0 {
+		/* main supply */
+		compatible = "regulator-fixed";
+		regulator-name = "main_12v0";
+		regulator-min-microvolt = <12000000>;
+		regulator-max-microvolt = <12000000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	evm_5v0: fixedregulator-evm_5v0 {
+		/* Output of TPS54531D */
+		compatible = "regulator-fixed";
+		regulator-name = "evm_5v0";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&main_12v0>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
 	vdd_3v3: fixedregulator-vdd_3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "vdd_3v3";
@@ -547,10 +568,6 @@
 	gpios = <&gpio2 8 GPIO_ACTIVE_LOW>;
 };
 
-&pcie1_ep {
-	gpios = <&gpio2 8 GPIO_ACTIVE_LOW>;
-};
-
 &mcasp3 {
 	#sound-dai-cells = <0>;
 	assigned-clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP3_CLKCTRL 24>;
diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi
index 3f4bb44d85f0..669da3a33d82 100644
--- a/arch/arm/boot/dts/armada-38x.dtsi
+++ b/arch/arm/boot/dts/armada-38x.dtsi
@@ -339,7 +339,8 @@
 
 			comphy: phy@18300 {
 				compatible = "marvell,armada-380-comphy";
-				reg = <0x18300 0x100>;
+				reg-names = "comphy", "conf";
+				reg = <0x18300 0x100>, <0x18460 4>;
 				#address-cells = <1>;
 				#size-cells = <0>;
 
diff --git a/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts b/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts
index ba7f3e646c26..b8db77b7f5d8 100644
--- a/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts
+++ b/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts
@@ -40,7 +40,7 @@
 
 	ahb {
 		usb0: gadget@300000 {
-			atmel,vbus-gpio = <&pioA PIN_PA27 GPIO_ACTIVE_HIGH>;
+			atmel,vbus-gpio = <&pioA PIN_PB11 GPIO_ACTIVE_HIGH>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinctrl_usba_vbus>;
 			status = "okay";
@@ -125,8 +125,6 @@
 			bus-width = <8>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinctrl_sdmmc0_default>;
-			non-removable;
-			mmc-ddr-1_8v;
 			status = "okay";
 		};
 
diff --git a/arch/arm/boot/dts/at91sam9260.dtsi b/arch/arm/boot/dts/at91sam9260.dtsi
index dee9c0c8a096..16c6fd3c4246 100644
--- a/arch/arm/boot/dts/at91sam9260.dtsi
+++ b/arch/arm/boot/dts/at91sam9260.dtsi
@@ -187,7 +187,7 @@
 				usart0 {
 					pinctrl_usart0: usart0-0 {
 						atmel,pins =
-							<AT91_PIOB 4 AT91_PERIPH_A AT91_PINCTRL_NONE
+							<AT91_PIOB 4 AT91_PERIPH_A AT91_PINCTRL_PULL_UP
 							 AT91_PIOB 5 AT91_PERIPH_A AT91_PINCTRL_PULL_UP>;
 					};
 
@@ -221,7 +221,7 @@
 				usart1 {
 					pinctrl_usart1: usart1-0 {
 						atmel,pins =
-							<AT91_PIOB 6 AT91_PERIPH_A AT91_PINCTRL_NONE
+							<AT91_PIOB 6 AT91_PERIPH_A AT91_PINCTRL_PULL_UP
 							 AT91_PIOB 7 AT91_PERIPH_A AT91_PINCTRL_PULL_UP>;
 					};
 
@@ -239,7 +239,7 @@
 				usart2 {
 					pinctrl_usart2: usart2-0 {
 						atmel,pins =
-							<AT91_PIOB 8 AT91_PERIPH_A AT91_PINCTRL_NONE
+							<AT91_PIOB 8 AT91_PERIPH_A AT91_PINCTRL_PULL_UP
 							 AT91_PIOB 9 AT91_PERIPH_A AT91_PINCTRL_PULL_UP>;
 					};
 
@@ -257,7 +257,7 @@
 				usart3 {
 					pinctrl_usart3: usart3-0 {
 						atmel,pins =
-							<AT91_PIOB 10 AT91_PERIPH_A AT91_PINCTRL_NONE
+							<AT91_PIOB 10 AT91_PERIPH_A AT91_PINCTRL_PULL_UP
 							 AT91_PIOB 11 AT91_PERIPH_A AT91_PINCTRL_PULL_UP>;
 					};
 
@@ -275,7 +275,7 @@
 				uart0 {
 					pinctrl_uart0: uart0-0 {
 						atmel,pins =
-							<AT91_PIOA 31 AT91_PERIPH_B AT91_PINCTRL_NONE
+							<AT91_PIOA 31 AT91_PERIPH_B AT91_PINCTRL_PULL_UP
 							 AT91_PIOA 30 AT91_PERIPH_B AT91_PINCTRL_PULL_UP>;
 					};
 				};
@@ -283,7 +283,7 @@
 				uart1 {
 					pinctrl_uart1: uart1-0 {
 						atmel,pins =
-							<AT91_PIOB 12 AT91_PERIPH_A AT91_PINCTRL_NONE
+							<AT91_PIOB 12 AT91_PERIPH_A AT91_PINCTRL_PULL_UP
 							 AT91_PIOB 13 AT91_PERIPH_A AT91_PINCTRL_PULL_UP>;
 					};
 				};
diff --git a/arch/arm/boot/dts/at91sam9261.dtsi b/arch/arm/boot/dts/at91sam9261.dtsi
index dba025a98527..5ed3d745ac86 100644
--- a/arch/arm/boot/dts/at91sam9261.dtsi
+++ b/arch/arm/boot/dts/at91sam9261.dtsi
@@ -329,7 +329,7 @@
 				usart0 {
 					pinctrl_usart0: usart0-0 {
 						atmel,pins =
-							<AT91_PIOC 8 AT91_PERIPH_A AT91_PINCTRL_NONE>,
+							<AT91_PIOC 8 AT91_PERIPH_A AT91_PINCTRL_PULL_UP>,
 							<AT91_PIOC 9 AT91_PERIPH_A AT91_PINCTRL_PULL_UP>;
 					};
 
@@ -347,7 +347,7 @@
 				usart1 {
 					pinctrl_usart1: usart1-0 {
 						atmel,pins =
-							<AT91_PIOC 12 AT91_PERIPH_A AT91_PINCTRL_NONE>,
+							<AT91_PIOC 12 AT91_PERIPH_A AT91_PINCTRL_PULL_UP>,
 							<AT91_PIOC 13 AT91_PERIPH_A AT91_PINCTRL_PULL_UP>;
 					};
 
@@ -365,7 +365,7 @@
 				usart2 {
 					pinctrl_usart2: usart2-0 {
 						atmel,pins =
-							<AT91_PIOC 14 AT91_PERIPH_A AT91_PINCTRL_NONE>,
+							<AT91_PIOC 14 AT91_PERIPH_A AT91_PINCTRL_PULL_UP>,
 							<AT91_PIOC 15 AT91_PERIPH_A AT91_PINCTRL_PULL_UP>;
 					};
 
diff --git a/arch/arm/boot/dts/at91sam9263.dtsi b/arch/arm/boot/dts/at91sam9263.dtsi
index 99678abdda93..5c990cfae254 100644
--- a/arch/arm/boot/dts/at91sam9263.dtsi
+++ b/arch/arm/boot/dts/at91sam9263.dtsi
@@ -183,7 +183,7 @@
 				usart0 {
 					pinctrl_usart0: usart0-0 {
 						atmel,pins =
-							<AT91_PIOA 26 AT91_PERIPH_A AT91_PINCTRL_NONE
+							<AT91_PIOA 26 AT91_PERIPH_A AT91_PINCTRL_PULL_UP
 							 AT91_PIOA 27 AT91_PERIPH_A AT91_PINCTRL_PULL_UP>;
 					};
 
@@ -201,7 +201,7 @@
 				usart1 {
 					pinctrl_usart1: usart1-0 {
 						atmel,pins =
-							<AT91_PIOD 0 AT91_PERIPH_A AT91_PINCTRL_NONE
+							<AT91_PIOD 0 AT91_PERIPH_A AT91_PINCTRL_PULL_UP
 							 AT91_PIOD 1 AT91_PERIPH_A AT91_PINCTRL_PULL_UP>;
 					};
 
@@ -219,7 +219,7 @@
 				usart2 {
 					pinctrl_usart2: usart2-0 {
 						atmel,pins =
-							<AT91_PIOD 2 AT91_PERIPH_A AT91_PINCTRL_NONE
+							<AT91_PIOD 2 AT91_PERIPH_A AT91_PINCTRL_PULL_UP
 							 AT91_PIOD 3 AT91_PERIPH_A AT91_PINCTRL_PULL_UP>;
 					};
 
diff --git a/arch/arm/boot/dts/at91sam9g45.dtsi b/arch/arm/boot/dts/at91sam9g45.dtsi
index 9483609a2105..53a929b7e4a6 100644
--- a/arch/arm/boot/dts/at91sam9g45.dtsi
+++ b/arch/arm/boot/dts/at91sam9g45.dtsi
@@ -556,7 +556,7 @@
 				usart0 {
 					pinctrl_usart0: usart0-0 {
 						atmel,pins =
-							<AT91_PIOB 19 AT91_PERIPH_A AT91_PINCTRL_NONE
+							<AT91_PIOB 19 AT91_PERIPH_A AT91_PINCTRL_PULL_UP
 							 AT91_PIOB 18 AT91_PERIPH_A AT91_PINCTRL_PULL_UP>;
 					};
 
@@ -574,7 +574,7 @@
 				usart1 {
 					pinctrl_usart1: usart1-0 {
 						atmel,pins =
-							<AT91_PIOB 4 AT91_PERIPH_A AT91_PINCTRL_NONE
+							<AT91_PIOB 4 AT91_PERIPH_A AT91_PINCTRL_PULL_UP
 							 AT91_PIOB 5 AT91_PERIPH_A AT91_PINCTRL_PULL_UP>;
 					};
 
@@ -592,7 +592,7 @@
 				usart2 {
 					pinctrl_usart2: usart2-0 {
 						atmel,pins =
-							<AT91_PIOB 6 AT91_PERIPH_A AT91_PINCTRL_NONE
+							<AT91_PIOB 6 AT91_PERIPH_A AT91_PINCTRL_PULL_UP
 							 AT91_PIOB 7 AT91_PERIPH_A AT91_PINCTRL_PULL_UP>;
 					};
 
@@ -610,7 +610,7 @@
 				usart3 {
 					pinctrl_usart3: usart3-0 {
 						atmel,pins =
-							<AT91_PIOB 8 AT91_PERIPH_A AT91_PINCTRL_NONE
+							<AT91_PIOB 8 AT91_PERIPH_A AT91_PINCTRL_PULL_UP
 							 AT91_PIOB 9 AT91_PERIPH_A AT91_PINCTRL_PULL_UP>;
 					};
 
diff --git a/arch/arm/boot/dts/at91sam9rl.dtsi b/arch/arm/boot/dts/at91sam9rl.dtsi
index e2d38ce43442..f0e1f6ec3600 100644
--- a/arch/arm/boot/dts/at91sam9rl.dtsi
+++ b/arch/arm/boot/dts/at91sam9rl.dtsi
@@ -682,7 +682,7 @@
 				usart0 {
 					pinctrl_usart0: usart0-0 {
 						atmel,pins =
-							<AT91_PIOA 6 AT91_PERIPH_A AT91_PINCTRL_NONE>,
+							<AT91_PIOA 6 AT91_PERIPH_A AT91_PINCTRL_PULL_UP>,
 							<AT91_PIOA 7 AT91_PERIPH_A AT91_PINCTRL_PULL_UP>;
 					};
 
@@ -721,7 +721,7 @@
 				usart1 {
 					pinctrl_usart1: usart1-0 {
 						atmel,pins =
-							<AT91_PIOA 11 AT91_PERIPH_A AT91_PINCTRL_NONE>,
+							<AT91_PIOA 11 AT91_PERIPH_A AT91_PINCTRL_PULL_UP>,
 							<AT91_PIOA 12 AT91_PERIPH_A AT91_PINCTRL_PULL_UP>;
 					};
 
@@ -744,7 +744,7 @@
 				usart2 {
 					pinctrl_usart2: usart2-0 {
 						atmel,pins =
-							<AT91_PIOA 13 AT91_PERIPH_A AT91_PINCTRL_NONE>,
+							<AT91_PIOA 13 AT91_PERIPH_A AT91_PINCTRL_PULL_UP>,
 							<AT91_PIOA 14 AT91_PERIPH_A AT91_PINCTRL_PULL_UP>;
 					};
 
@@ -767,7 +767,7 @@
 				usart3 {
 					pinctrl_usart3: usart3-0 {
 						atmel,pins =
-							<AT91_PIOB 0 AT91_PERIPH_A AT91_PINCTRL_NONE>,
+							<AT91_PIOB 0 AT91_PERIPH_A AT91_PINCTRL_PULL_UP>,
 							<AT91_PIOB 1 AT91_PERIPH_A AT91_PINCTRL_PULL_UP>;
 					};
 
diff --git a/arch/arm/boot/dts/bcm-cygnus.dtsi b/arch/arm/boot/dts/bcm-cygnus.dtsi
index 5f7b46503a51..9cfe5096ebb8 100644
--- a/arch/arm/boot/dts/bcm-cygnus.dtsi
+++ b/arch/arm/boot/dts/bcm-cygnus.dtsi
@@ -174,8 +174,8 @@
 		mdio: mdio@18002000 {
 			compatible = "brcm,iproc-mdio";
 			reg = <0x18002000 0x8>;
-			#size-cells = <1>;
-			#address-cells = <0>;
+			#size-cells = <0>;
+			#address-cells = <1>;
 			status = "disabled";
 
 			gphy0: ethernet-phy@0 {
diff --git a/arch/arm/boot/dts/bcm-hr2.dtsi b/arch/arm/boot/dts/bcm-hr2.dtsi
index e4d49731287f..e35398cc60a0 100644
--- a/arch/arm/boot/dts/bcm-hr2.dtsi
+++ b/arch/arm/boot/dts/bcm-hr2.dtsi
@@ -75,7 +75,7 @@
 		timer@20200 {
 			compatible = "arm,cortex-a9-global-timer";
 			reg = <0x20200 0x100>;
-			interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>;
 			clocks = <&periph_clk>;
 		};
 
@@ -83,7 +83,7 @@
 			compatible = "arm,cortex-a9-twd-timer";
 			reg = <0x20600 0x20>;
 			interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(1) |
-						  IRQ_TYPE_LEVEL_HIGH)>;
+						  IRQ_TYPE_EDGE_RISING)>;
 			clocks = <&periph_clk>;
 		};
 
@@ -91,7 +91,7 @@
 			compatible = "arm,cortex-a9-twd-wdt";
 			reg = <0x20620 0x20>;
 			interrupts = <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(1) |
-						  IRQ_TYPE_LEVEL_HIGH)>;
+						  IRQ_TYPE_EDGE_RISING)>;
 			clocks = <&periph_clk>;
 		};
 
diff --git a/arch/arm/boot/dts/bcm-nsp.dtsi b/arch/arm/boot/dts/bcm-nsp.dtsi
index 6925b30c2253..ff3d4eaf1e7b 100644
--- a/arch/arm/boot/dts/bcm-nsp.dtsi
+++ b/arch/arm/boot/dts/bcm-nsp.dtsi
@@ -257,10 +257,10 @@
 			status = "disabled";
 		};
 
-		mailbox: mailbox@25000 {
+		mailbox: mailbox@25c00 {
 			compatible = "brcm,iproc-fa2-mbox";
-			reg = <0x25000 0x445>;
-			interrupts = <GIC_SPI 150 IRQ_TYPE_LEVEL_HIGH>;
+			reg = <0x25c00 0x400>;
+			interrupts = <GIC_SPI 151 IRQ_TYPE_LEVEL_HIGH>;
 			#mbox-cells = <1>;
 			brcm,rx-status-len = <32>;
 			brcm,use-bcm-hdr;
diff --git a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts
index ba0167df6c5f..f0c504c024d0 100644
--- a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts
+++ b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts
@@ -19,7 +19,7 @@
 
 	leds {
 		act {
-			gpios = <&gpio 47 GPIO_ACTIVE_HIGH>;
+			gpios = <&gpio 47 GPIO_ACTIVE_LOW>;
 		};
 	};
 
@@ -105,6 +105,7 @@
 &sdhci {
 	#address-cells = <1>;
 	#size-cells = <0>;
+	pinctrl-names = "default";
 	pinctrl-0 = <&emmc_gpio34 &gpclk2_gpio43>;
 	mmc-pwrseq = <&wifi_pwrseq>;
 	non-removable;
diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi
index 9777644c6c2b..5e2716678856 100644
--- a/arch/arm/boot/dts/bcm283x.dtsi
+++ b/arch/arm/boot/dts/bcm283x.dtsi
@@ -40,7 +40,7 @@
 
 			trips {
 				cpu-crit {
-					temperature	= <80000>;
+					temperature	= <90000>;
 					hysteresis	= <0>;
 					type		= "critical";
 				};
@@ -486,6 +486,7 @@
 					     "dsi0_ddr2",
 					     "dsi0_ddr";
 
+			status = "disabled";
 		};
 
 		thermal: thermal@7e212000 {
diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi
index ac5266ee8d4c..dc6065de1d69 100644
--- a/arch/arm/boot/dts/bcm5301x.dtsi
+++ b/arch/arm/boot/dts/bcm5301x.dtsi
@@ -353,8 +353,8 @@
 	mdio: mdio@18003000 {
 		compatible = "brcm,iproc-mdio";
 		reg = <0x18003000 0x8>;
-		#size-cells = <1>;
-		#address-cells = <0>;
+		#size-cells = <0>;
+		#address-cells = <1>;
 	};
 
 	mdio-bus-mux {
diff --git a/arch/arm/boot/dts/dm8148-evm.dts b/arch/arm/boot/dts/dm8148-evm.dts
index 3931fb068ff0..91d1018ab75f 100644
--- a/arch/arm/boot/dts/dm8148-evm.dts
+++ b/arch/arm/boot/dts/dm8148-evm.dts
@@ -24,12 +24,12 @@
 
 &cpsw_emac0 {
 	phy-handle = <&ethphy0>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 };
 
 &cpsw_emac1 {
 	phy-handle = <&ethphy1>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 };
 
 &davinci_mdio {
diff --git a/arch/arm/boot/dts/dm8148-t410.dts b/arch/arm/boot/dts/dm8148-t410.dts
index 9e43d5ec0bb2..79ccdd4470f4 100644
--- a/arch/arm/boot/dts/dm8148-t410.dts
+++ b/arch/arm/boot/dts/dm8148-t410.dts
@@ -33,12 +33,12 @@
 
 &cpsw_emac0 {
 	phy-handle = <&ethphy0>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 };
 
 &cpsw_emac1 {
 	phy-handle = <&ethphy1>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 };
 
 &davinci_mdio {
diff --git a/arch/arm/boot/dts/dra62x-j5eco-evm.dts b/arch/arm/boot/dts/dra62x-j5eco-evm.dts
index 861ab90a3f3a..c16e183822be 100644
--- a/arch/arm/boot/dts/dra62x-j5eco-evm.dts
+++ b/arch/arm/boot/dts/dra62x-j5eco-evm.dts
@@ -24,12 +24,12 @@
 
 &cpsw_emac0 {
 	phy-handle = <&ethphy0>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 };
 
 &cpsw_emac1 {
 	phy-handle = <&ethphy1>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 };
 
 &davinci_mdio {
diff --git a/arch/arm/boot/dts/dra7-l4.dtsi b/arch/arm/boot/dts/dra7-l4.dtsi
index 099d6fe2a57a..bb62afecf779 100644
--- a/arch/arm/boot/dts/dra7-l4.dtsi
+++ b/arch/arm/boot/dts/dra7-l4.dtsi
@@ -3450,6 +3450,7 @@
 				clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER13_CLKCTRL 24>;
 				clock-names = "fck";
 				interrupts = <GIC_SPI 339 IRQ_TYPE_LEVEL_HIGH>;
+				ti,timer-pwm;
 			};
 		};
 
@@ -3478,6 +3479,7 @@
 				clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER14_CLKCTRL 24>;
 				clock-names = "fck";
 				interrupts = <GIC_SPI 340 IRQ_TYPE_LEVEL_HIGH>;
+				ti,timer-pwm;
 			};
 		};
 
@@ -3506,6 +3508,7 @@
 				clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER15_CLKCTRL 24>;
 				clock-names = "fck";
 				interrupts = <GIC_SPI 341 IRQ_TYPE_LEVEL_HIGH>;
+				ti,timer-pwm;
 			};
 		};
 
@@ -3534,6 +3537,7 @@
 				clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER16_CLKCTRL 24>;
 				clock-names = "fck";
 				interrupts = <GIC_SPI 342 IRQ_TYPE_LEVEL_HIGH>;
+				ti,timer-pwm;
 			};
 		};
 
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index 953f0ffce2a9..a6ef3d137c7a 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -148,6 +148,7 @@
 		#address-cells = <1>;
 		#size-cells = <1>;
 		ranges = <0x0 0x0 0x0 0xc0000000>;
+		dma-ranges = <0x80000000 0x0 0x80000000 0x80000000>;
 		ti,hwmods = "l3_main_1", "l3_main_2";
 		reg = <0x0 0x44000000 0x0 0x1000000>,
 		      <0x0 0x45000000 0x0 0x1000>;
@@ -171,6 +172,7 @@
 			#address-cells = <1>;
 			ranges = <0x51000000 0x51000000 0x3000
 				  0x0	     0x20000000 0x10000000>;
+			dma-ranges;
 			/**
 			 * To enable PCI endpoint mode, disable the pcie1_rc
 			 * node and enable pcie1_ep mode.
@@ -228,6 +230,7 @@
 			#address-cells = <1>;
 			ranges = <0x51800000 0x51800000 0x3000
 				  0x0	     0x30000000 0x10000000>;
+			dma-ranges;
 			status = "disabled";
 			pcie2_rc: pcie@51800000 {
 				reg = <0x51800000 0x2000>, <0x51802000 0x14c>, <0x1000 0x2000>;
diff --git a/arch/arm/boot/dts/dra76x.dtsi b/arch/arm/boot/dts/dra76x.dtsi
index cdcba3f561c4..9f6fbe4c1fee 100644
--- a/arch/arm/boot/dts/dra76x.dtsi
+++ b/arch/arm/boot/dts/dra76x.dtsi
@@ -86,3 +86,8 @@
 &usb4_tm {
 	status = "disabled";
 };
+
+&mmc3 {
+	/* dra76x is not affected by i887 */
+	max-frequency = <96000000>;
+};
diff --git a/arch/arm/boot/dts/dra7xx-clocks.dtsi b/arch/arm/boot/dts/dra7xx-clocks.dtsi
index 93e1eb83bed9..d7d98d2069df 100644
--- a/arch/arm/boot/dts/dra7xx-clocks.dtsi
+++ b/arch/arm/boot/dts/dra7xx-clocks.dtsi
@@ -796,16 +796,6 @@
 		clock-div = <1>;
 	};
 
-	ipu1_gfclk_mux: ipu1_gfclk_mux@520 {
-		#clock-cells = <0>;
-		compatible = "ti,mux-clock";
-		clocks = <&dpll_abe_m2x2_ck>, <&dpll_core_h22x2_ck>;
-		ti,bit-shift = <24>;
-		reg = <0x0520>;
-		assigned-clocks = <&ipu1_gfclk_mux>;
-		assigned-clock-parents = <&dpll_core_h22x2_ck>;
-	};
-
 	dummy_ck: dummy_ck {
 		#clock-cells = <0>;
 		compatible = "fixed-clock";
@@ -1564,6 +1554,8 @@
 			compatible = "ti,clkctrl";
 			reg = <0x20 0x4>;
 			#clock-cells = <2>;
+			assigned-clocks = <&ipu1_clkctrl DRA7_IPU1_MMU_IPU1_CLKCTRL 24>;
+			assigned-clock-parents = <&dpll_core_h22x2_ck>;
 		};
 
 		ipu_clkctrl: ipu-clkctrl@50 {
diff --git a/arch/arm/boot/dts/exynos4210-universal_c210.dts b/arch/arm/boot/dts/exynos4210-universal_c210.dts
index bf092e97e14f..60f235d7f277 100644
--- a/arch/arm/boot/dts/exynos4210-universal_c210.dts
+++ b/arch/arm/boot/dts/exynos4210-universal_c210.dts
@@ -115,7 +115,7 @@
 		gpio-sck = <&gpy3 1 GPIO_ACTIVE_HIGH>;
 		gpio-mosi = <&gpy3 3 GPIO_ACTIVE_HIGH>;
 		num-chipselects = <1>;
-		cs-gpios = <&gpy4 3 GPIO_ACTIVE_HIGH>;
+		cs-gpios = <&gpy4 3 GPIO_ACTIVE_LOW>;
 
 		lcd@0 {
 			compatible = "samsung,ld9040";
@@ -124,8 +124,6 @@
 			vci-supply = <&ldo17_reg>;
 			reset-gpios = <&gpy4 5 GPIO_ACTIVE_HIGH>;
 			spi-max-frequency = <1200000>;
-			spi-cpol;
-			spi-cpha;
 			power-on-delay = <10>;
 			reset-delay = <10>;
 			panel-width-mm = <90>;
diff --git a/arch/arm/boot/dts/exynos4412-galaxy-s3.dtsi b/arch/arm/boot/dts/exynos4412-galaxy-s3.dtsi
index 30eee5942eff..945ee8f55e65 100644
--- a/arch/arm/boot/dts/exynos4412-galaxy-s3.dtsi
+++ b/arch/arm/boot/dts/exynos4412-galaxy-s3.dtsi
@@ -50,7 +50,7 @@
 
 	i2c_cm36651: i2c-gpio-2 {
 		compatible = "i2c-gpio";
-		gpios = <&gpf0 0 GPIO_ACTIVE_LOW>, <&gpf0 1 GPIO_ACTIVE_LOW>;
+		gpios = <&gpf0 0 GPIO_ACTIVE_HIGH>, <&gpf0 1 GPIO_ACTIVE_HIGH>;
 		i2c-gpio,delay-us = <2>;
 		#address-cells = <1>;
 		#size-cells = <0>;
diff --git a/arch/arm/boot/dts/gemini-dlink-dir-685.dts b/arch/arm/boot/dts/gemini-dlink-dir-685.dts
index bfaa2de63a10..e2030ba16512 100644
--- a/arch/arm/boot/dts/gemini-dlink-dir-685.dts
+++ b/arch/arm/boot/dts/gemini-dlink-dir-685.dts
@@ -72,7 +72,6 @@
 			reg = <0>;
 			/* 50 ns min period = 20 MHz */
 			spi-max-frequency = <20000000>;
-			spi-cpol; /* Clock active low */
 			vcc-supply = <&vdisp>;
 			iovcc-supply = <&vdisp>;
 			vci-supply = <&vdisp>;
diff --git a/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts b/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts
index 5e5e282ed30e..d3681aa2a56a 100644
--- a/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts
+++ b/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts
@@ -75,8 +75,8 @@
 	imx27-phycard-s-rdk {
 		pinctrl_i2c1: i2c1grp {
 			fsl,pins = <
-				MX27_PAD_I2C2_SDA__I2C2_SDA 0x0
-				MX27_PAD_I2C2_SCL__I2C2_SCL 0x0
+				MX27_PAD_I2C_DATA__I2C_DATA 0x0
+				MX27_PAD_I2C_CLK__I2C_CLK 0x0
 			>;
 		};
 
diff --git a/arch/arm/boot/dts/imx6dl-icore-mipi.dts b/arch/arm/boot/dts/imx6dl-icore-mipi.dts
index e43bccb78ab2..d8f3821a0ffd 100644
--- a/arch/arm/boot/dts/imx6dl-icore-mipi.dts
+++ b/arch/arm/boot/dts/imx6dl-icore-mipi.dts
@@ -8,7 +8,7 @@
 /dts-v1/;
 
 #include "imx6dl.dtsi"
-#include "imx6qdl-icore.dtsi"
+#include "imx6qdl-icore-1.5.dtsi"
 
 / {
 	model = "Engicam i.CoreM6 DualLite/Solo MIPI Starter Kit";
diff --git a/arch/arm/boot/dts/imx6dl-yapp4-ursa.dts b/arch/arm/boot/dts/imx6dl-yapp4-ursa.dts
index 0d594e4bd559..a1173bf5bff5 100644
--- a/arch/arm/boot/dts/imx6dl-yapp4-ursa.dts
+++ b/arch/arm/boot/dts/imx6dl-yapp4-ursa.dts
@@ -38,7 +38,7 @@
 };
 
 &switch_ports {
-	/delete-node/ port@2;
+	/delete-node/ port@3;
 };
 
 &touchscreen {
diff --git a/arch/arm/boot/dts/imx6q-b450v3.dts b/arch/arm/boot/dts/imx6q-b450v3.dts
index 95b8f2d71821..fb0980190aa0 100644
--- a/arch/arm/boot/dts/imx6q-b450v3.dts
+++ b/arch/arm/boot/dts/imx6q-b450v3.dts
@@ -65,13 +65,6 @@
 	};
 };
 
-&clks {
-	assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>,
-			  <&clks IMX6QDL_CLK_LDB_DI1_SEL>;
-	assigned-clock-parents = <&clks IMX6QDL_CLK_PLL3_USB_OTG>,
-				 <&clks IMX6QDL_CLK_PLL3_USB_OTG>;
-};
-
 &ldb {
 	status = "okay";
 
diff --git a/arch/arm/boot/dts/imx6q-b650v3.dts b/arch/arm/boot/dts/imx6q-b650v3.dts
index 611cb7ae7e55..8f762d9c5ae9 100644
--- a/arch/arm/boot/dts/imx6q-b650v3.dts
+++ b/arch/arm/boot/dts/imx6q-b650v3.dts
@@ -65,13 +65,6 @@
 	};
 };
 
-&clks {
-	assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>,
-			  <&clks IMX6QDL_CLK_LDB_DI1_SEL>;
-	assigned-clock-parents = <&clks IMX6QDL_CLK_PLL3_USB_OTG>,
-				 <&clks IMX6QDL_CLK_PLL3_USB_OTG>;
-};
-
 &ldb {
 	status = "okay";
 
diff --git a/arch/arm/boot/dts/imx6q-b850v3.dts b/arch/arm/boot/dts/imx6q-b850v3.dts
index e4cb118f88c6..1ea64ecf4291 100644
--- a/arch/arm/boot/dts/imx6q-b850v3.dts
+++ b/arch/arm/boot/dts/imx6q-b850v3.dts
@@ -53,17 +53,6 @@
 	};
 };
 
-&clks {
-	assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>,
-			  <&clks IMX6QDL_CLK_LDB_DI1_SEL>,
-			  <&clks IMX6QDL_CLK_IPU1_DI0_PRE_SEL>,
-			  <&clks IMX6QDL_CLK_IPU2_DI0_PRE_SEL>;
-	assigned-clock-parents = <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>,
-				 <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>,
-				 <&clks IMX6QDL_CLK_PLL2_PFD2_396M>,
-				 <&clks IMX6QDL_CLK_PLL2_PFD2_396M>;
-};
-
 &ldb {
 	fsl,dual-channel;
 	status = "okay";
diff --git a/arch/arm/boot/dts/imx6q-bx50v3.dtsi b/arch/arm/boot/dts/imx6q-bx50v3.dtsi
index fa27dcdf06f1..1938b04199c4 100644
--- a/arch/arm/boot/dts/imx6q-bx50v3.dtsi
+++ b/arch/arm/boot/dts/imx6q-bx50v3.dtsi
@@ -377,3 +377,18 @@
 		#interrupt-cells = <1>;
 	};
 };
+
+&clks {
+	assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>,
+			  <&clks IMX6QDL_CLK_LDB_DI1_SEL>,
+			  <&clks IMX6QDL_CLK_IPU1_DI0_PRE_SEL>,
+			  <&clks IMX6QDL_CLK_IPU1_DI1_PRE_SEL>,
+			  <&clks IMX6QDL_CLK_IPU2_DI0_PRE_SEL>,
+			  <&clks IMX6QDL_CLK_IPU2_DI1_PRE_SEL>;
+	assigned-clock-parents = <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>,
+				 <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>,
+				 <&clks IMX6QDL_CLK_PLL2_PFD0_352M>,
+				 <&clks IMX6QDL_CLK_PLL2_PFD0_352M>,
+				 <&clks IMX6QDL_CLK_PLL2_PFD0_352M>,
+				 <&clks IMX6QDL_CLK_PLL2_PFD0_352M>;
+};
diff --git a/arch/arm/boot/dts/imx6q-dhcom-pdk2.dts b/arch/arm/boot/dts/imx6q-dhcom-pdk2.dts
index 9c61e3be2d9a..1c46df6827f5 100644
--- a/arch/arm/boot/dts/imx6q-dhcom-pdk2.dts
+++ b/arch/arm/boot/dts/imx6q-dhcom-pdk2.dts
@@ -55,7 +55,7 @@
 		#sound-dai-cells = <0>;
 		clocks = <&clk_ext_audio_codec>;
 		VDDA-supply = <&reg_3p3v>;
-		VDDIO-supply = <&reg_3p3v>;
+		VDDIO-supply = <&sw2_reg>;
 	};
 };
 
diff --git a/arch/arm/boot/dts/imx6q-dhcom-som.dtsi b/arch/arm/boot/dts/imx6q-dhcom-som.dtsi
index 387801dde02e..08a2e17e0539 100644
--- a/arch/arm/boot/dts/imx6q-dhcom-som.dtsi
+++ b/arch/arm/boot/dts/imx6q-dhcom-som.dtsi
@@ -206,7 +206,7 @@
 	};
 
 	rtc@56 {
-		compatible = "rv3029c2";
+		compatible = "microcrystal,rv3029";
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_rtc_hw300>;
 		reg = <0x56>;
diff --git a/arch/arm/boot/dts/imx6qdl-gw551x.dtsi b/arch/arm/boot/dts/imx6qdl-gw551x.dtsi
index c23ba229fd05..8c33510c9519 100644
--- a/arch/arm/boot/dts/imx6qdl-gw551x.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-gw551x.dtsi
@@ -105,19 +105,16 @@
 	sound-digital {
 		compatible = "simple-audio-card";
 		simple-audio-card,name = "tda1997x-audio";
+		simple-audio-card,format = "i2s";
+		simple-audio-card,bitclock-master = <&sound_codec>;
+		simple-audio-card,frame-master = <&sound_codec>;
 
-		simple-audio-card,dai-link@0 {
-			format = "i2s";
-
-			cpu {
-				sound-dai = <&ssi2>;
-			};
+		sound_cpu: simple-audio-card,cpu {
+			sound-dai = <&ssi1>;
+		};
 
-			codec {
-				bitclock-master;
-				frame-master;
-				sound-dai = <&hdmi_receiver>;
-			};
+		sound_codec: simple-audio-card,codec {
+			sound-dai = <&hdmi_receiver>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/imx6qdl-icore.dtsi b/arch/arm/boot/dts/imx6qdl-icore.dtsi
index 7814f1ef0804..fde56f98398d 100644
--- a/arch/arm/boot/dts/imx6qdl-icore.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-icore.dtsi
@@ -384,7 +384,7 @@
 
 	pinctrl_usbotg: usbotggrp {
 		fsl,pins = <
-			MX6QDL_PAD_GPIO_1__USB_OTG_ID 0x17059
+			MX6QDL_PAD_ENET_RX_ER__USB_OTG_ID 0x17059
 		>;
 	};
 
@@ -396,6 +396,7 @@
 			MX6QDL_PAD_SD1_DAT1__SD1_DATA1 0x17070
 			MX6QDL_PAD_SD1_DAT2__SD1_DATA2 0x17070
 			MX6QDL_PAD_SD1_DAT3__SD1_DATA3 0x17070
+			MX6QDL_PAD_GPIO_1__GPIO1_IO01  0x1b0b0
 		>;
 	};
 
diff --git a/arch/arm/boot/dts/imx6qdl-phytec-phycore-som.dtsi b/arch/arm/boot/dts/imx6qdl-phytec-phycore-som.dtsi
index 6486df3e2942..31fa37d2fe47 100644
--- a/arch/arm/boot/dts/imx6qdl-phytec-phycore-som.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-phytec-phycore-som.dtsi
@@ -107,14 +107,14 @@
 		regulators {
 			vdd_arm: buck1 {
 				regulator-name = "vdd_arm";
-				regulator-min-microvolt = <730000>;
+				regulator-min-microvolt = <925000>;
 				regulator-max-microvolt = <1380000>;
 				regulator-always-on;
 			};
 
 			vdd_soc: buck2 {
 				regulator-name = "vdd_soc";
-				regulator-min-microvolt = <730000>;
+				regulator-min-microvolt = <1150000>;
 				regulator-max-microvolt = <1380000>;
 				regulator-always-on;
 			};
@@ -183,7 +183,6 @@
 	pinctrl-0 = <&pinctrl_usdhc4>;
 	bus-width = <8>;
 	non-removable;
-	vmmc-supply = <&vdd_emmc_1p8>;
 	status = "disabled";
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl-sr-som-ti.dtsi b/arch/arm/boot/dts/imx6qdl-sr-som-ti.dtsi
index 44a97ba93a95..352ac585ca6b 100644
--- a/arch/arm/boot/dts/imx6qdl-sr-som-ti.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-sr-som-ti.dtsi
@@ -153,6 +153,7 @@
 	bus-width = <4>;
 	keep-power-in-suspend;
 	mmc-pwrseq = <&pwrseq_ti_wifi>;
+	cap-power-off-card;
 	non-removable;
 	vmmc-supply = <&vcc_3v3>;
 	/* vqmmc-supply = <&nvcc_sd1>; - MMC layer doesn't like it! */
diff --git a/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi b/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi
index 93be00a60c88..a66c4fac6baf 100644
--- a/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi
@@ -627,7 +627,7 @@
 	pinctrl-0 = <&pinctrl_usdhc2>;
 	bus-width = <4>;
 	cd-gpios = <&gpio2 2 GPIO_ACTIVE_LOW>;
-	wp-gpios = <&gpio2 3 GPIO_ACTIVE_HIGH>;
+	disable-wp;
 	vmmc-supply = <&reg_3p3v_sd>;
 	vqmmc-supply = <&reg_3p3v>;
 	no-1-8-v;
@@ -640,7 +640,7 @@
 	pinctrl-0 = <&pinctrl_usdhc3>;
 	bus-width = <4>;
 	cd-gpios = <&gpio2 0 GPIO_ACTIVE_LOW>;
-	wp-gpios = <&gpio2 1 GPIO_ACTIVE_HIGH>;
+	disable-wp;
 	vmmc-supply = <&reg_3p3v_sd>;
 	vqmmc-supply = <&reg_3p3v>;
 	no-1-8-v;
@@ -774,6 +774,7 @@
 &usbh1 {
 	vbus-supply = <&reg_5p0v_main>;
 	disable-over-current;
+	maximum-speed = "full-speed";
 	status = "okay";
 };
 
@@ -1055,7 +1056,6 @@
 			MX6QDL_PAD_SD2_DAT1__SD2_DATA1		0x17059
 			MX6QDL_PAD_SD2_DAT2__SD2_DATA2		0x17059
 			MX6QDL_PAD_SD2_DAT3__SD2_DATA3		0x17059
-			MX6QDL_PAD_NANDF_D3__GPIO2_IO03		0x40010040
 			MX6QDL_PAD_NANDF_D2__GPIO2_IO02		0x40010040
 		>;
 	};
@@ -1068,7 +1068,6 @@
 			MX6QDL_PAD_SD3_DAT1__SD3_DATA1		0x17059
 			MX6QDL_PAD_SD3_DAT2__SD3_DATA2		0x17059
 			MX6QDL_PAD_SD3_DAT3__SD3_DATA3		0x17059
-			MX6QDL_PAD_NANDF_D1__GPIO2_IO01		0x40010040
 			MX6QDL_PAD_NANDF_D0__GPIO2_IO00		0x40010040
 
 		>;
diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi
index b3a77bcf00d5..b6bf9ff93105 100644
--- a/arch/arm/boot/dts/imx6qdl.dtsi
+++ b/arch/arm/boot/dts/imx6qdl.dtsi
@@ -1040,9 +1040,8 @@
 				compatible = "fsl,imx6q-fec";
 				reg = <0x02188000 0x4000>;
 				interrupt-names = "int0", "pps";
-				interrupts-extended =
-					<&intc 0 118 IRQ_TYPE_LEVEL_HIGH>,
-					<&intc 0 119 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <0 118 IRQ_TYPE_LEVEL_HIGH>,
+					     <0 119 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX6QDL_CLK_ENET>,
 					 <&clks IMX6QDL_CLK_ENET>,
 					 <&clks IMX6QDL_CLK_ENET_REF>;
diff --git a/arch/arm/boot/dts/imx6qp.dtsi b/arch/arm/boot/dts/imx6qp.dtsi
index 5f51f8e5c1fa..d91f92f944c5 100644
--- a/arch/arm/boot/dts/imx6qp.dtsi
+++ b/arch/arm/boot/dts/imx6qp.dtsi
@@ -77,7 +77,6 @@
 };
 
 &fec {
-	/delete-property/interrupts-extended;
 	interrupts = <0 118 IRQ_TYPE_LEVEL_HIGH>,
 		     <0 119 IRQ_TYPE_LEVEL_HIGH>;
 };
diff --git a/arch/arm/boot/dts/imx6sx-sabreauto.dts b/arch/arm/boot/dts/imx6sx-sabreauto.dts
index 315044ccd65f..e4719566133c 100644
--- a/arch/arm/boot/dts/imx6sx-sabreauto.dts
+++ b/arch/arm/boot/dts/imx6sx-sabreauto.dts
@@ -99,7 +99,7 @@
 &fec2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_enet2>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-handle = <&ethphy0>;
 	fsl,magic-packet;
 	status = "okay";
diff --git a/arch/arm/boot/dts/imx6sx-sdb.dtsi b/arch/arm/boot/dts/imx6sx-sdb.dtsi
index f6972deb5e39..865528b134d8 100644
--- a/arch/arm/boot/dts/imx6sx-sdb.dtsi
+++ b/arch/arm/boot/dts/imx6sx-sdb.dtsi
@@ -213,7 +213,7 @@
 &fec2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_enet2>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-handle = <&ethphy2>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi b/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi
index d556f7c541ce..49554af90a4e 100644
--- a/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi
+++ b/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi
@@ -215,7 +215,7 @@
 	flash0: n25q256a@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
-		compatible = "micron,n25q256a";
+		compatible = "micron,n25q256a", "jedec,spi-nor";
 		spi-max-frequency = <29000000>;
 		spi-rx-bus-width = <4>;
 		spi-tx-bus-width = <4>;
diff --git a/arch/arm/boot/dts/imx7-colibri.dtsi b/arch/arm/boot/dts/imx7-colibri.dtsi
index c1ed83131b49..1dcec20328df 100644
--- a/arch/arm/boot/dts/imx7-colibri.dtsi
+++ b/arch/arm/boot/dts/imx7-colibri.dtsi
@@ -115,6 +115,18 @@
 	fsl,magic-packet;
 };
 
+&flexcan1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_flexcan1>;
+	status = "disabled";
+};
+
+&flexcan2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_flexcan2>;
+	status = "disabled";
+};
+
 &gpmi {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_gpmi_nand>;
@@ -319,7 +331,6 @@
 	assigned-clock-rates = <400000000>;
 	bus-width = <8>;
 	fsl,tuning-step = <2>;
-	max-frequency = <100000000>;
 	vmmc-supply = <&reg_module_3v3>;
 	vqmmc-supply = <&reg_DCDC3>;
 	non-removable;
@@ -328,12 +339,11 @@
 
 &iomuxc {
 	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_gpio1 &pinctrl_gpio2 &pinctrl_gpio3 &pinctrl_gpio4>;
+	pinctrl-0 = <&pinctrl_gpio1 &pinctrl_gpio2 &pinctrl_gpio3 &pinctrl_gpio4
+		     &pinctrl_gpio7 &pinctrl_usbc_det>;
 
 	pinctrl_gpio1: gpio1-grp {
 		fsl,pins = <
-			MX7D_PAD_ENET1_RGMII_RD3__GPIO7_IO3	0x74 /* SODIMM 55 */
-			MX7D_PAD_ENET1_RGMII_RD2__GPIO7_IO2	0x74 /* SODIMM 63 */
 			MX7D_PAD_SAI1_RX_SYNC__GPIO6_IO16	0x14 /* SODIMM 77 */
 			MX7D_PAD_EPDC_DATA09__GPIO2_IO9		0x14 /* SODIMM 89 */
 			MX7D_PAD_EPDC_DATA08__GPIO2_IO8		0x74 /* SODIMM 91 */
@@ -414,6 +424,13 @@
 		>;
 	};
 
+	pinctrl_gpio7: gpio7-grp { /* Alternatively CAN1 */
+		fsl,pins = <
+			MX7D_PAD_ENET1_RGMII_RD3__GPIO7_IO3	0x14 /* SODIMM 55 */
+			MX7D_PAD_ENET1_RGMII_RD2__GPIO7_IO2	0x14 /* SODIMM 63 */
+		>;
+	};
+
 	pinctrl_i2c1_int: i2c1-int-grp { /* PMIC / TOUCH */
 		fsl,pins = <
 			MX7D_PAD_GPIO1_IO13__GPIO1_IO13	0x79
@@ -428,7 +445,6 @@
 
 	pinctrl_enet1: enet1grp {
 		fsl,pins = <
-			MX7D_PAD_ENET1_CRS__GPIO7_IO14			0x14
 			MX7D_PAD_ENET1_RGMII_RX_CTL__ENET1_RGMII_RX_CTL	0x73
 			MX7D_PAD_ENET1_RGMII_RD0__ENET1_RGMII_RD0	0x73
 			MX7D_PAD_ENET1_RGMII_RD1__ENET1_RGMII_RD1	0x73
@@ -457,10 +473,17 @@
 		>;
 	};
 
+	pinctrl_flexcan1: flexcan1-grp {
+		fsl,pins = <
+			MX7D_PAD_ENET1_RGMII_RD3__FLEXCAN1_TX	0x79 /* SODIMM 55 */
+			MX7D_PAD_ENET1_RGMII_RD2__FLEXCAN1_RX	0x79 /* SODIMM 63 */
+		>;
+	};
+
 	pinctrl_flexcan2: flexcan2-grp {
 		fsl,pins = <
-			MX7D_PAD_GPIO1_IO14__FLEXCAN2_RX	0x59
-			MX7D_PAD_GPIO1_IO15__FLEXCAN2_TX	0x59
+			MX7D_PAD_GPIO1_IO14__FLEXCAN2_RX	0x79 /* SODIMM 188 */
+			MX7D_PAD_GPIO1_IO15__FLEXCAN2_TX	0x79 /* SODIMM 178 */
 		>;
 	};
 
@@ -596,6 +619,12 @@
 		>;
 	};
 
+	pinctrl_usbc_det: gpio-usbc-det {
+		fsl,pins = <
+			MX7D_PAD_ENET1_CRS__GPIO7_IO14	0x14
+		>;
+	};
+
 	pinctrl_usbh_reg: gpio-usbh-vbus {
 		fsl,pins = <
 			MX7D_PAD_UART3_CTS_B__GPIO4_IO7	0x14 /* SODIMM 129 USBH PEN */
diff --git a/arch/arm/boot/dts/imx7s-colibri.dtsi b/arch/arm/boot/dts/imx7s-colibri.dtsi
index 1fb1ec5d3d70..6d16e32aed89 100644
--- a/arch/arm/boot/dts/imx7s-colibri.dtsi
+++ b/arch/arm/boot/dts/imx7s-colibri.dtsi
@@ -49,3 +49,7 @@
 		reg = <0x80000000 0x10000000>;
 	};
 };
+
+&gpmi {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/imx7ulp.dtsi b/arch/arm/boot/dts/imx7ulp.dtsi
index d6b711011cba..efb05cc48521 100644
--- a/arch/arm/boot/dts/imx7ulp.dtsi
+++ b/arch/arm/boot/dts/imx7ulp.dtsi
@@ -36,10 +36,10 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		cpu0: cpu@0 {
+		cpu0: cpu@f00 {
 			compatible = "arm,cortex-a7";
 			device_type = "cpu";
-			reg = <0>;
+			reg = <0xf00>;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/ls1021a.dtsi b/arch/arm/boot/dts/ls1021a.dtsi
index 464df4290ffc..cf0c991bb15b 100644
--- a/arch/arm/boot/dts/ls1021a.dtsi
+++ b/arch/arm/boot/dts/ls1021a.dtsi
@@ -728,7 +728,7 @@
 		};
 
 		mdio0: mdio@2d24000 {
-			compatible = "fsl,etsec2-mdio";
+			compatible = "gianfar";
 			device_type = "mdio";
 			#address-cells = <1>;
 			#size-cells = <0>;
@@ -737,7 +737,7 @@
 		};
 
 		mdio1: mdio@2d64000 {
-			compatible = "fsl,etsec2-mdio";
+			compatible = "gianfar";
 			device_type = "mdio";
 			#address-cells = <1>;
 			#size-cells = <0>;
diff --git a/arch/arm/boot/dts/meson8.dtsi b/arch/arm/boot/dts/meson8.dtsi
index 40c11b6b217a..4dd8a4f6b393 100644
--- a/arch/arm/boot/dts/meson8.dtsi
+++ b/arch/arm/boot/dts/meson8.dtsi
@@ -169,8 +169,8 @@
 	gpu_opp_table: gpu-opp-table {
 		compatible = "operating-points-v2";
 
-		opp-182150000 {
-			opp-hz = /bits/ 64 <182150000>;
+		opp-182142857 {
+			opp-hz = /bits/ 64 <182142857>;
 			opp-microvolt = <1150000>;
 		};
 		opp-318750000 {
@@ -271,7 +271,7 @@
 &aobus {
 	pmu: pmu@e0 {
 		compatible = "amlogic,meson8-pmu", "syscon";
-		reg = <0xe0 0x8>;
+		reg = <0xe0 0x18>;
 	};
 
 	pinctrl_aobus: pinctrl@84 {
diff --git a/arch/arm/boot/dts/meson8b.dtsi b/arch/arm/boot/dts/meson8b.dtsi
index ec67f49116d9..c95510001dc1 100644
--- a/arch/arm/boot/dts/meson8b.dtsi
+++ b/arch/arm/boot/dts/meson8b.dtsi
@@ -165,8 +165,8 @@
 			opp-hz = /bits/ 64 <255000000>;
 			opp-microvolt = <1100000>;
 		};
-		opp-364300000 {
-			opp-hz = /bits/ 64 <364300000>;
+		opp-364285714 {
+			opp-hz = /bits/ 64 <364285714>;
 			opp-microvolt = <1100000>;
 		};
 		opp-425000000 {
diff --git a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi
index 82f7ae030600..ab91c4ebb146 100644
--- a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi
+++ b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi
@@ -13,8 +13,10 @@
 		#interrupt-cells = <2>;
 		#address-cells = <1>;
 		#size-cells = <0>;
-		spi-max-frequency = <3000000>;
+		spi-max-frequency = <9600000>;
 		spi-cs-high;
+		spi-cpol;
+		spi-cpha;
 
 		cpcap_adc: adc {
 			compatible = "motorola,mapphone-cpcap-adc";
diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts
index 84a5ade1e865..4227da71cc62 100644
--- a/arch/arm/boot/dts/omap3-n900.dts
+++ b/arch/arm/boot/dts/omap3-n900.dts
@@ -105,6 +105,14 @@
 			linux,code = <SW_FRONT_PROXIMITY>;
 			linux,can-disable;
 		};
+
+		machine_cover {
+			label = "Machine Cover";
+			gpios = <&gpio6 0 GPIO_ACTIVE_LOW>; /* 160 */
+			linux,input-type = <EV_SW>;
+			linux,code = <SW_MACHINE_COVER>;
+			linux,can-disable;
+		};
 	};
 
 	isp1707: isp1707 {
@@ -155,6 +163,12 @@
 		pwms = <&pwm9 0 26316 0>; /* 38000 Hz */
 	};
 
+	rom_rng: rng {
+		compatible = "nokia,n900-rom-rng";
+		clocks = <&rng_ick>;
+		clock-names = "ick";
+	};
+
 	/* controlled (enabled/disabled) directly by bcm2048 and wl1251 */
 	vctcxo: vctcxo {
 		compatible = "fixed-clock";
@@ -808,10 +822,6 @@
 	pinctrl-0 = <&mmc1_pins>;
 	vmmc-supply = <&vmmc1>;
 	bus-width = <4>;
-	/* For debugging, it is often good idea to remove this GPIO.
-	   It means you can remove back cover (to reboot by removing
-	   battery) and still use the MMC card. */
-	cd-gpios = <&gpio6 0 GPIO_ACTIVE_LOW>; /* 160 */
 };
 
 /* most boards use vaux3, only some old versions use vmmc2 instead */
@@ -843,34 +853,46 @@
 		compatible = "ti,omap2-onenand";
 		reg = <0 0 0x20000>;	/* CS0, offset 0, IO size 128K */
 
+		/*
+		 * These timings are based on CONFIG_OMAP_GPMC_DEBUG=y reported
+		 * bootloader set values when booted with v5.1
+		 * (OneNAND Manufacturer: Samsung):
+		 *
+		 *   cs0 GPMC_CS_CONFIG1: 0xfb001202
+		 *   cs0 GPMC_CS_CONFIG2: 0x00111100
+		 *   cs0 GPMC_CS_CONFIG3: 0x00020200
+		 *   cs0 GPMC_CS_CONFIG4: 0x11001102
+		 *   cs0 GPMC_CS_CONFIG5: 0x03101616
+		 *   cs0 GPMC_CS_CONFIG6: 0x90060000
+		 */
 		gpmc,sync-read;
 		gpmc,sync-write;
 		gpmc,burst-length = <16>;
 		gpmc,burst-read;
 		gpmc,burst-wrap;
 		gpmc,burst-write;
-		gpmc,device-width = <2>; /* GPMC_DEVWIDTH_16BIT */
-		gpmc,mux-add-data = <2>; /* GPMC_MUX_AD */
+		gpmc,device-width = <2>;
+		gpmc,mux-add-data = <2>;
 		gpmc,cs-on-ns = <0>;
-		gpmc,cs-rd-off-ns = <87>;
-		gpmc,cs-wr-off-ns = <87>;
+		gpmc,cs-rd-off-ns = <102>;
+		gpmc,cs-wr-off-ns = <102>;
 		gpmc,adv-on-ns = <0>;
-		gpmc,adv-rd-off-ns = <10>;
-		gpmc,adv-wr-off-ns = <10>;
-		gpmc,oe-on-ns = <15>;
-		gpmc,oe-off-ns = <87>;
+		gpmc,adv-rd-off-ns = <12>;
+		gpmc,adv-wr-off-ns = <12>;
+		gpmc,oe-on-ns = <12>;
+		gpmc,oe-off-ns = <102>;
 		gpmc,we-on-ns = <0>;
-		gpmc,we-off-ns = <87>;
-		gpmc,rd-cycle-ns = <112>;
-		gpmc,wr-cycle-ns = <112>;
-		gpmc,access-ns = <81>;
-		gpmc,page-burst-access-ns = <15>;
+		gpmc,we-off-ns = <102>;
+		gpmc,rd-cycle-ns = <132>;
+		gpmc,wr-cycle-ns = <132>;
+		gpmc,access-ns = <96>;
+		gpmc,page-burst-access-ns = <18>;
 		gpmc,bus-turnaround-ns = <0>;
 		gpmc,cycle2cycle-delay-ns = <0>;
 		gpmc,wait-monitoring-ns = <0>;
-		gpmc,clk-activation-ns = <5>;
-		gpmc,wr-data-mux-bus-ns = <30>;
-		gpmc,wr-access-ns = <81>;
+		gpmc,clk-activation-ns = <6>;
+		gpmc,wr-data-mux-bus-ns = <36>;
+		gpmc,wr-access-ns = <96>;
 		gpmc,sync-clk-ps = <15000>;
 
 		/*
diff --git a/arch/arm/boot/dts/omap4-duovero-parlor.dts b/arch/arm/boot/dts/omap4-duovero-parlor.dts
index 8047e8cdb3af..4548d87534e3 100644
--- a/arch/arm/boot/dts/omap4-duovero-parlor.dts
+++ b/arch/arm/boot/dts/omap4-duovero-parlor.dts
@@ -139,7 +139,7 @@
 	ethernet@gpmc {
 		reg = <5 0 0xff>;
 		interrupt-parent = <&gpio2>;
-		interrupts = <12 IRQ_TYPE_EDGE_FALLING>;	/* gpio_44 */
+		interrupts = <12 IRQ_TYPE_LEVEL_LOW>;		/* gpio_44 */
 
 		phy-mode = "mii";
 
diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi
index c43e52fd5f65..e9c5ee154786 100644
--- a/arch/arm/boot/dts/omap4.dtsi
+++ b/arch/arm/boot/dts/omap4.dtsi
@@ -331,8 +331,8 @@
 		target-module@56000000 {
 			compatible = "ti,sysc-omap4", "ti,sysc";
 			ti,hwmods = "gpu";
-			reg = <0x5601fc00 0x4>,
-			      <0x5601fc10 0x4>;
+			reg = <0x5600fe00 0x4>,
+			      <0x5600fe10 0x4>;
 			reg-names = "rev", "sysc";
 			ti,sysc-midle = <SYSC_IDLE_FORCE>,
 					<SYSC_IDLE_NO>,
diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi
index edfd26c03462..d6cb07a822f5 100644
--- a/arch/arm/boot/dts/omap5.dtsi
+++ b/arch/arm/boot/dts/omap5.dtsi
@@ -143,6 +143,7 @@
 		#address-cells = <1>;
 		#size-cells = <1>;
 		ranges = <0 0 0 0xc0000000>;
+		dma-ranges = <0x80000000 0x0 0x80000000 0x80000000>;
 		ti,hwmods = "l3_main_1", "l3_main_2", "l3_main_3";
 		reg = <0 0x44000000 0 0x2000>,
 		      <0 0x44800000 0 0x3000>,
diff --git a/arch/arm/boot/dts/ox810se.dtsi b/arch/arm/boot/dts/ox810se.dtsi
index 9f6c2b660ed3..0755e5864c4a 100644
--- a/arch/arm/boot/dts/ox810se.dtsi
+++ b/arch/arm/boot/dts/ox810se.dtsi
@@ -323,8 +323,8 @@
 					interrupt-controller;
 					reg = <0 0x200>;
 					#interrupt-cells = <1>;
-					valid-mask = <0xFFFFFFFF>;
-					clear-mask = <0>;
+					valid-mask = <0xffffffff>;
+					clear-mask = <0xffffffff>;
 				};
 
 				timer0: timer@200 {
diff --git a/arch/arm/boot/dts/ox820.dtsi b/arch/arm/boot/dts/ox820.dtsi
index c9b327732063..90846a7655b4 100644
--- a/arch/arm/boot/dts/ox820.dtsi
+++ b/arch/arm/boot/dts/ox820.dtsi
@@ -240,8 +240,8 @@
 					reg = <0 0x200>;
 					interrupts = <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>;
 					#interrupt-cells = <1>;
-					valid-mask = <0xFFFFFFFF>;
-					clear-mask = <0>;
+					valid-mask = <0xffffffff>;
+					clear-mask = <0xffffffff>;
 				};
 
 				timer0: timer@200 {
diff --git a/arch/arm/boot/dts/r8a73a4.dtsi b/arch/arm/boot/dts/r8a73a4.dtsi
index dd865f3c2eda..4447f45f0cba 100644
--- a/arch/arm/boot/dts/r8a73a4.dtsi
+++ b/arch/arm/boot/dts/r8a73a4.dtsi
@@ -131,7 +131,14 @@
 	cmt1: timer@e6130000 {
 		compatible = "renesas,r8a73a4-cmt1", "renesas,rcar-gen2-cmt1";
 		reg = <0 0xe6130000 0 0x1004>;
-		interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 124 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 126 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A73A4_CLK_CMT1>;
 		clock-names = "fck";
 		power-domains = <&pd_c5>;
diff --git a/arch/arm/boot/dts/r8a7740.dtsi b/arch/arm/boot/dts/r8a7740.dtsi
index 12ffe73bf2bc..155f58e6d4e8 100644
--- a/arch/arm/boot/dts/r8a7740.dtsi
+++ b/arch/arm/boot/dts/r8a7740.dtsi
@@ -479,7 +479,7 @@
 		cpg_clocks: cpg_clocks@e6150000 {
 			compatible = "renesas,r8a7740-cpg-clocks";
 			reg = <0xe6150000 0x10000>;
-			clocks = <&extal1_clk>, <&extalr_clk>;
+			clocks = <&extal1_clk>, <&extal2_clk>, <&extalr_clk>;
 			#clock-cells = <1>;
 			clock-output-names = "system", "pllc0", "pllc1",
 					     "pllc2", "r",
diff --git a/arch/arm/boot/dts/r8a7743.dtsi b/arch/arm/boot/dts/r8a7743.dtsi
index de981d629bdd..fdd267819319 100644
--- a/arch/arm/boot/dts/r8a7743.dtsi
+++ b/arch/arm/boot/dts/r8a7743.dtsi
@@ -338,7 +338,7 @@
 			#thermal-sensor-cells = <0>;
 		};
 
-		ipmmu_sy0: mmu@e6280000 {
+		ipmmu_sy0: iommu@e6280000 {
 			compatible = "renesas,ipmmu-r8a7743",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe6280000 0 0x1000>;
@@ -348,7 +348,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_sy1: mmu@e6290000 {
+		ipmmu_sy1: iommu@e6290000 {
 			compatible = "renesas,ipmmu-r8a7743",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe6290000 0 0x1000>;
@@ -357,7 +357,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_ds: mmu@e6740000 {
+		ipmmu_ds: iommu@e6740000 {
 			compatible = "renesas,ipmmu-r8a7743",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe6740000 0 0x1000>;
@@ -367,7 +367,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_mp: mmu@ec680000 {
+		ipmmu_mp: iommu@ec680000 {
 			compatible = "renesas,ipmmu-r8a7743",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xec680000 0 0x1000>;
@@ -376,7 +376,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_mx: mmu@fe951000 {
+		ipmmu_mx: iommu@fe951000 {
 			compatible = "renesas,ipmmu-r8a7743",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xfe951000 0 0x1000>;
@@ -386,7 +386,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_gp: mmu@e62a0000 {
+		ipmmu_gp: iommu@e62a0000 {
 			compatible = "renesas,ipmmu-r8a7743",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe62a0000 0 0x1000>;
diff --git a/arch/arm/boot/dts/r8a7744.dtsi b/arch/arm/boot/dts/r8a7744.dtsi
index fa74a262107b..8264481bf876 100644
--- a/arch/arm/boot/dts/r8a7744.dtsi
+++ b/arch/arm/boot/dts/r8a7744.dtsi
@@ -338,7 +338,7 @@
 			#thermal-sensor-cells = <0>;
 		};
 
-		ipmmu_sy0: mmu@e6280000 {
+		ipmmu_sy0: iommu@e6280000 {
 			compatible = "renesas,ipmmu-r8a7744",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe6280000 0 0x1000>;
@@ -348,7 +348,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_sy1: mmu@e6290000 {
+		ipmmu_sy1: iommu@e6290000 {
 			compatible = "renesas,ipmmu-r8a7744",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe6290000 0 0x1000>;
@@ -357,7 +357,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_ds: mmu@e6740000 {
+		ipmmu_ds: iommu@e6740000 {
 			compatible = "renesas,ipmmu-r8a7744",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe6740000 0 0x1000>;
@@ -367,7 +367,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_mp: mmu@ec680000 {
+		ipmmu_mp: iommu@ec680000 {
 			compatible = "renesas,ipmmu-r8a7744",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xec680000 0 0x1000>;
@@ -376,7 +376,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_mx: mmu@fe951000 {
+		ipmmu_mx: iommu@fe951000 {
 			compatible = "renesas,ipmmu-r8a7744",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xfe951000 0 0x1000>;
@@ -386,7 +386,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_gp: mmu@e62a0000 {
+		ipmmu_gp: iommu@e62a0000 {
 			compatible = "renesas,ipmmu-r8a7744",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe62a0000 0 0x1000>;
diff --git a/arch/arm/boot/dts/r8a7745.dtsi b/arch/arm/boot/dts/r8a7745.dtsi
index c53f7ff20695..c306713f2ab7 100644
--- a/arch/arm/boot/dts/r8a7745.dtsi
+++ b/arch/arm/boot/dts/r8a7745.dtsi
@@ -302,7 +302,7 @@
 			resets = <&cpg 407>;
 		};
 
-		ipmmu_sy0: mmu@e6280000 {
+		ipmmu_sy0: iommu@e6280000 {
 			compatible = "renesas,ipmmu-r8a7745",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe6280000 0 0x1000>;
@@ -312,7 +312,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_sy1: mmu@e6290000 {
+		ipmmu_sy1: iommu@e6290000 {
 			compatible = "renesas,ipmmu-r8a7745",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe6290000 0 0x1000>;
@@ -321,7 +321,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_ds: mmu@e6740000 {
+		ipmmu_ds: iommu@e6740000 {
 			compatible = "renesas,ipmmu-r8a7745",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe6740000 0 0x1000>;
@@ -331,7 +331,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_mp: mmu@ec680000 {
+		ipmmu_mp: iommu@ec680000 {
 			compatible = "renesas,ipmmu-r8a7745",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xec680000 0 0x1000>;
@@ -340,7 +340,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_mx: mmu@fe951000 {
+		ipmmu_mx: iommu@fe951000 {
 			compatible = "renesas,ipmmu-r8a7745",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xfe951000 0 0x1000>;
@@ -350,7 +350,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_gp: mmu@e62a0000 {
+		ipmmu_gp: iommu@e62a0000 {
 			compatible = "renesas,ipmmu-r8a7745",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe62a0000 0 0x1000>;
diff --git a/arch/arm/boot/dts/r8a7779.dtsi b/arch/arm/boot/dts/r8a7779.dtsi
index 3ff259207527..c2400e440b93 100644
--- a/arch/arm/boot/dts/r8a7779.dtsi
+++ b/arch/arm/boot/dts/r8a7779.dtsi
@@ -68,6 +68,14 @@
 		      <0xf0000100 0x100>;
 	};
 
+	timer@f0000200 {
+		compatible = "arm,cortex-a9-global-timer";
+		reg = <0xf0000200 0x100>;
+		interrupts = <GIC_PPI 11
+			(GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>;
+		clocks = <&cpg_clocks R8A7779_CLK_ZS>;
+	};
+
 	timer@f0000600 {
 		compatible = "arm,cortex-a9-twd-timer";
 		reg = <0xf0000600 0x20>;
diff --git a/arch/arm/boot/dts/r8a7790.dtsi b/arch/arm/boot/dts/r8a7790.dtsi
index 5a2747758f67..e3ba00a22eeb 100644
--- a/arch/arm/boot/dts/r8a7790.dtsi
+++ b/arch/arm/boot/dts/r8a7790.dtsi
@@ -427,7 +427,7 @@
 			#thermal-sensor-cells = <0>;
 		};
 
-		ipmmu_sy0: mmu@e6280000 {
+		ipmmu_sy0: iommu@e6280000 {
 			compatible = "renesas,ipmmu-r8a7790",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe6280000 0 0x1000>;
@@ -437,7 +437,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_sy1: mmu@e6290000 {
+		ipmmu_sy1: iommu@e6290000 {
 			compatible = "renesas,ipmmu-r8a7790",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe6290000 0 0x1000>;
@@ -446,7 +446,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_ds: mmu@e6740000 {
+		ipmmu_ds: iommu@e6740000 {
 			compatible = "renesas,ipmmu-r8a7790",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe6740000 0 0x1000>;
@@ -456,7 +456,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_mp: mmu@ec680000 {
+		ipmmu_mp: iommu@ec680000 {
 			compatible = "renesas,ipmmu-r8a7790",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xec680000 0 0x1000>;
@@ -465,7 +465,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_mx: mmu@fe951000 {
+		ipmmu_mx: iommu@fe951000 {
 			compatible = "renesas,ipmmu-r8a7790",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xfe951000 0 0x1000>;
@@ -475,7 +475,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_rt: mmu@ffc80000 {
+		ipmmu_rt: iommu@ffc80000 {
 			compatible = "renesas,ipmmu-r8a7790",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xffc80000 0 0x1000>;
diff --git a/arch/arm/boot/dts/r8a7791.dtsi b/arch/arm/boot/dts/r8a7791.dtsi
index 6f875502453c..a26f86ccc579 100644
--- a/arch/arm/boot/dts/r8a7791.dtsi
+++ b/arch/arm/boot/dts/r8a7791.dtsi
@@ -350,7 +350,7 @@
 			#thermal-sensor-cells = <0>;
 		};
 
-		ipmmu_sy0: mmu@e6280000 {
+		ipmmu_sy0: iommu@e6280000 {
 			compatible = "renesas,ipmmu-r8a7791",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe6280000 0 0x1000>;
@@ -360,7 +360,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_sy1: mmu@e6290000 {
+		ipmmu_sy1: iommu@e6290000 {
 			compatible = "renesas,ipmmu-r8a7791",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe6290000 0 0x1000>;
@@ -369,7 +369,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_ds: mmu@e6740000 {
+		ipmmu_ds: iommu@e6740000 {
 			compatible = "renesas,ipmmu-r8a7791",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe6740000 0 0x1000>;
@@ -379,7 +379,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_mp: mmu@ec680000 {
+		ipmmu_mp: iommu@ec680000 {
 			compatible = "renesas,ipmmu-r8a7791",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xec680000 0 0x1000>;
@@ -388,7 +388,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_mx: mmu@fe951000 {
+		ipmmu_mx: iommu@fe951000 {
 			compatible = "renesas,ipmmu-r8a7791",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xfe951000 0 0x1000>;
@@ -398,7 +398,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_rt: mmu@ffc80000 {
+		ipmmu_rt: iommu@ffc80000 {
 			compatible = "renesas,ipmmu-r8a7791",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xffc80000 0 0x1000>;
@@ -407,7 +407,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_gp: mmu@e62a0000 {
+		ipmmu_gp: iommu@e62a0000 {
 			compatible = "renesas,ipmmu-r8a7791",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe62a0000 0 0x1000>;
diff --git a/arch/arm/boot/dts/r8a7793-gose.dts b/arch/arm/boot/dts/r8a7793-gose.dts
index f51601af89a2..68da21cbdd8f 100644
--- a/arch/arm/boot/dts/r8a7793-gose.dts
+++ b/arch/arm/boot/dts/r8a7793-gose.dts
@@ -339,7 +339,7 @@
 			reg = <0x20>;
 			remote = <&vin1>;
 
-			port {
+			ports {
 				#address-cells = <1>;
 				#size-cells = <0>;
 
@@ -399,7 +399,7 @@
 			interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
 			default-input = <0>;
 
-			port {
+			ports {
 				#address-cells = <1>;
 				#size-cells = <0>;
 
diff --git a/arch/arm/boot/dts/r8a7793.dtsi b/arch/arm/boot/dts/r8a7793.dtsi
index bf05110fac4e..fa3839795018 100644
--- a/arch/arm/boot/dts/r8a7793.dtsi
+++ b/arch/arm/boot/dts/r8a7793.dtsi
@@ -336,7 +336,7 @@
 			#thermal-sensor-cells = <0>;
 		};
 
-		ipmmu_sy0: mmu@e6280000 {
+		ipmmu_sy0: iommu@e6280000 {
 			compatible = "renesas,ipmmu-r8a7793",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe6280000 0 0x1000>;
@@ -346,7 +346,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_sy1: mmu@e6290000 {
+		ipmmu_sy1: iommu@e6290000 {
 			compatible = "renesas,ipmmu-r8a7793",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe6290000 0 0x1000>;
@@ -355,7 +355,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_ds: mmu@e6740000 {
+		ipmmu_ds: iommu@e6740000 {
 			compatible = "renesas,ipmmu-r8a7793",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe6740000 0 0x1000>;
@@ -365,7 +365,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_mp: mmu@ec680000 {
+		ipmmu_mp: iommu@ec680000 {
 			compatible = "renesas,ipmmu-r8a7793",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xec680000 0 0x1000>;
@@ -374,7 +374,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_mx: mmu@fe951000 {
+		ipmmu_mx: iommu@fe951000 {
 			compatible = "renesas,ipmmu-r8a7793",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xfe951000 0 0x1000>;
@@ -384,7 +384,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_rt: mmu@ffc80000 {
+		ipmmu_rt: iommu@ffc80000 {
 			compatible = "renesas,ipmmu-r8a7793",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xffc80000 0 0x1000>;
@@ -393,7 +393,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_gp: mmu@e62a0000 {
+		ipmmu_gp: iommu@e62a0000 {
 			compatible = "renesas,ipmmu-r8a7793",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe62a0000 0 0x1000>;
diff --git a/arch/arm/boot/dts/r8a7794.dtsi b/arch/arm/boot/dts/r8a7794.dtsi
index 8d797d34816e..9dd952479e68 100644
--- a/arch/arm/boot/dts/r8a7794.dtsi
+++ b/arch/arm/boot/dts/r8a7794.dtsi
@@ -290,7 +290,7 @@
 			resets = <&cpg 407>;
 		};
 
-		ipmmu_sy0: mmu@e6280000 {
+		ipmmu_sy0: iommu@e6280000 {
 			compatible = "renesas,ipmmu-r8a7794",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe6280000 0 0x1000>;
@@ -300,7 +300,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_sy1: mmu@e6290000 {
+		ipmmu_sy1: iommu@e6290000 {
 			compatible = "renesas,ipmmu-r8a7794",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe6290000 0 0x1000>;
@@ -309,7 +309,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_ds: mmu@e6740000 {
+		ipmmu_ds: iommu@e6740000 {
 			compatible = "renesas,ipmmu-r8a7794",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe6740000 0 0x1000>;
@@ -319,7 +319,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_mp: mmu@ec680000 {
+		ipmmu_mp: iommu@ec680000 {
 			compatible = "renesas,ipmmu-r8a7794",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xec680000 0 0x1000>;
@@ -328,7 +328,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_mx: mmu@fe951000 {
+		ipmmu_mx: iommu@fe951000 {
 			compatible = "renesas,ipmmu-r8a7794",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xfe951000 0 0x1000>;
@@ -338,7 +338,7 @@
 			status = "disabled";
 		};
 
-		ipmmu_gp: mmu@e62a0000 {
+		ipmmu_gp: iommu@e62a0000 {
 			compatible = "renesas,ipmmu-r8a7794",
 				     "renesas,ipmmu-vmsa";
 			reg = <0 0xe62a0000 0 0x1000>;
diff --git a/arch/arm/boot/dts/rk3036.dtsi b/arch/arm/boot/dts/rk3036.dtsi
index 0290ea4edd32..d03c95abc873 100644
--- a/arch/arm/boot/dts/rk3036.dtsi
+++ b/arch/arm/boot/dts/rk3036.dtsi
@@ -128,7 +128,7 @@
 		assigned-clocks = <&cru SCLK_GPU>;
 		assigned-clock-rates = <100000000>;
 		clocks = <&cru SCLK_GPU>, <&cru SCLK_GPU>;
-		clock-names = "core", "bus";
+		clock-names = "bus", "core";
 		resets = <&cru SRST_GPU>;
 		status = "disabled";
 	};
diff --git a/arch/arm/boot/dts/rk3188-bqedison2qc.dts b/arch/arm/boot/dts/rk3188-bqedison2qc.dts
index c8b62bbd6a4a..66a0ff196eb1 100644
--- a/arch/arm/boot/dts/rk3188-bqedison2qc.dts
+++ b/arch/arm/boot/dts/rk3188-bqedison2qc.dts
@@ -58,20 +58,25 @@
 
 	lvds-encoder {
 		compatible = "ti,sn75lvds83", "lvds-encoder";
-		#address-cells = <1>;
-		#size-cells = <0>;
 
-		port@0 {
-			reg = <0>;
-			lvds_in_vop0: endpoint {
-				remote-endpoint = <&vop0_out_lvds>;
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				lvds_in_vop0: endpoint {
+					remote-endpoint = <&vop0_out_lvds>;
+				};
 			};
-		};
 
-		port@1 {
-			reg = <1>;
-			lvds_out_panel: endpoint {
-				remote-endpoint = <&panel_in_lvds>;
+			port@1 {
+				reg = <1>;
+
+				lvds_out_panel: endpoint {
+					remote-endpoint = <&panel_in_lvds>;
+				};
 			};
 		};
 	};
@@ -465,10 +470,13 @@
 	non-removable;
 	pinctrl-names = "default";
 	pinctrl-0 = <&sd1_clk>, <&sd1_cmd>, <&sd1_bus4>;
-	vmmcq-supply = <&vccio_wl>;
+	vqmmc-supply = <&vccio_wl>;
+	#address-cells = <1>;
+	#size-cells = <0>;
 	status = "okay";
 
 	brcmf: wifi@1 {
+		reg = <1>;
 		compatible = "brcm,bcm4329-fmac";
 		interrupt-parent = <&gpio3>;
 		interrupts = <RK_PD2 GPIO_ACTIVE_HIGH>;
diff --git a/arch/arm/boot/dts/rk3228-evb.dts b/arch/arm/boot/dts/rk3228-evb.dts
index 5670b33fd1bd..aed879db6c15 100644
--- a/arch/arm/boot/dts/rk3228-evb.dts
+++ b/arch/arm/boot/dts/rk3228-evb.dts
@@ -46,7 +46,7 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		phy: phy@0 {
+		phy: ethernet-phy@0 {
 			compatible = "ethernet-phy-id1234.d400", "ethernet-phy-ieee802.3-c22";
 			reg = <0>;
 			clocks = <&cru SCLK_MAC_PHY>;
diff --git a/arch/arm/boot/dts/rk322x.dtsi b/arch/arm/boot/dts/rk322x.dtsi
index da102fff96a2..46ab3740d902 100644
--- a/arch/arm/boot/dts/rk322x.dtsi
+++ b/arch/arm/boot/dts/rk322x.dtsi
@@ -545,7 +545,7 @@
 				  "pp1",
 				  "ppmmu1";
 		clocks = <&cru ACLK_GPU>, <&cru ACLK_GPU>;
-		clock-names = "core", "bus";
+		clock-names = "bus", "core";
 		resets = <&cru SRST_GPU_A>;
 		status = "disabled";
 	};
@@ -950,7 +950,7 @@
 			};
 		};
 
-		spi-0 {
+		spi0 {
 			spi0_clk: spi0-clk {
 				rockchip,pins = <0 RK_PB1 2 &pcfg_pull_up>;
 			};
@@ -968,7 +968,7 @@
 			};
 		};
 
-		spi-1 {
+		spi1 {
 			spi1_clk: spi1-clk {
 				rockchip,pins = <0 RK_PC7 2 &pcfg_pull_up>;
 			};
diff --git a/arch/arm/boot/dts/rk3xxx.dtsi b/arch/arm/boot/dts/rk3xxx.dtsi
index 97307a405e60..bce0b05ef7bf 100644
--- a/arch/arm/boot/dts/rk3xxx.dtsi
+++ b/arch/arm/boot/dts/rk3xxx.dtsi
@@ -84,7 +84,7 @@
 		compatible = "arm,mali-400";
 		reg = <0x10090000 0x10000>;
 		clocks = <&cru ACLK_GPU>, <&cru ACLK_GPU>;
-		clock-names = "core", "bus";
+		clock-names = "bus", "core";
 		assigned-clocks = <&cru ACLK_GPU>;
 		assigned-clock-rates = <100000000>;
 		resets = <&cru SRST_GPU>;
diff --git a/arch/arm/boot/dts/s5pv210-aries.dtsi b/arch/arm/boot/dts/s5pv210-aries.dtsi
index 8ff70b856334..d419b77201f7 100644
--- a/arch/arm/boot/dts/s5pv210-aries.dtsi
+++ b/arch/arm/boot/dts/s5pv210-aries.dtsi
@@ -454,6 +454,7 @@
 	pinctrl-names = "default";
 	cap-sd-highspeed;
 	cap-mmc-highspeed;
+	keep-power-in-suspend;
 
 	mmc-pwrseq = <&wifi_pwrseq>;
 	non-removable;
diff --git a/arch/arm/boot/dts/sama5d3.dtsi b/arch/arm/boot/dts/sama5d3.dtsi
index 3bbc84bf8dbf..7a7c229a4ed6 100644
--- a/arch/arm/boot/dts/sama5d3.dtsi
+++ b/arch/arm/boot/dts/sama5d3.dtsi
@@ -1188,49 +1188,49 @@
 					usart0_clk: usart0_clk {
 						#clock-cells = <0>;
 						reg = <12>;
-						atmel,clk-output-range = <0 66000000>;
+						atmel,clk-output-range = <0 83000000>;
 					};
 
 					usart1_clk: usart1_clk {
 						#clock-cells = <0>;
 						reg = <13>;
-						atmel,clk-output-range = <0 66000000>;
+						atmel,clk-output-range = <0 83000000>;
 					};
 
 					usart2_clk: usart2_clk {
 						#clock-cells = <0>;
 						reg = <14>;
-						atmel,clk-output-range = <0 66000000>;
+						atmel,clk-output-range = <0 83000000>;
 					};
 
 					usart3_clk: usart3_clk {
 						#clock-cells = <0>;
 						reg = <15>;
-						atmel,clk-output-range = <0 66000000>;
+						atmel,clk-output-range = <0 83000000>;
 					};
 
 					uart0_clk: uart0_clk {
 						#clock-cells = <0>;
 						reg = <16>;
-						atmel,clk-output-range = <0 66000000>;
+						atmel,clk-output-range = <0 83000000>;
 					};
 
 					twi0_clk: twi0_clk {
 						reg = <18>;
 						#clock-cells = <0>;
-						atmel,clk-output-range = <0 16625000>;
+						atmel,clk-output-range = <0 41500000>;
 					};
 
 					twi1_clk: twi1_clk {
 						#clock-cells = <0>;
 						reg = <19>;
-						atmel,clk-output-range = <0 16625000>;
+						atmel,clk-output-range = <0 41500000>;
 					};
 
 					twi2_clk: twi2_clk {
 						#clock-cells = <0>;
 						reg = <20>;
-						atmel,clk-output-range = <0 16625000>;
+						atmel,clk-output-range = <0 41500000>;
 					};
 
 					mci0_clk: mci0_clk {
@@ -1246,19 +1246,19 @@
 					spi0_clk: spi0_clk {
 						#clock-cells = <0>;
 						reg = <24>;
-						atmel,clk-output-range = <0 133000000>;
+						atmel,clk-output-range = <0 166000000>;
 					};
 
 					spi1_clk: spi1_clk {
 						#clock-cells = <0>;
 						reg = <25>;
-						atmel,clk-output-range = <0 133000000>;
+						atmel,clk-output-range = <0 166000000>;
 					};
 
 					tcb0_clk: tcb0_clk {
 						#clock-cells = <0>;
 						reg = <26>;
-						atmel,clk-output-range = <0 133000000>;
+						atmel,clk-output-range = <0 166000000>;
 					};
 
 					pwm_clk: pwm_clk {
@@ -1269,7 +1269,7 @@
 					adc_clk: adc_clk {
 						#clock-cells = <0>;
 						reg = <29>;
-						atmel,clk-output-range = <0 66000000>;
+						atmel,clk-output-range = <0 83000000>;
 					};
 
 					dma0_clk: dma0_clk {
@@ -1300,13 +1300,13 @@
 					ssc0_clk: ssc0_clk {
 						#clock-cells = <0>;
 						reg = <38>;
-						atmel,clk-output-range = <0 66000000>;
+						atmel,clk-output-range = <0 83000000>;
 					};
 
 					ssc1_clk: ssc1_clk {
 						#clock-cells = <0>;
 						reg = <39>;
-						atmel,clk-output-range = <0 66000000>;
+						atmel,clk-output-range = <0 83000000>;
 					};
 
 					sha_clk: sha_clk {
diff --git a/arch/arm/boot/dts/sama5d3_can.dtsi b/arch/arm/boot/dts/sama5d3_can.dtsi
index cf06a018ed0f..2470dd3fff25 100644
--- a/arch/arm/boot/dts/sama5d3_can.dtsi
+++ b/arch/arm/boot/dts/sama5d3_can.dtsi
@@ -36,13 +36,13 @@
 					can0_clk: can0_clk {
 						#clock-cells = <0>;
 						reg = <40>;
-						atmel,clk-output-range = <0 66000000>;
+						atmel,clk-output-range = <0 83000000>;
 					};
 
 					can1_clk: can1_clk {
 						#clock-cells = <0>;
 						reg = <41>;
-						atmel,clk-output-range = <0 66000000>;
+						atmel,clk-output-range = <0 83000000>;
 					};
 				};
 			};
diff --git a/arch/arm/boot/dts/sama5d3_tcb1.dtsi b/arch/arm/boot/dts/sama5d3_tcb1.dtsi
index 1584035daf51..215802b8db30 100644
--- a/arch/arm/boot/dts/sama5d3_tcb1.dtsi
+++ b/arch/arm/boot/dts/sama5d3_tcb1.dtsi
@@ -22,6 +22,7 @@
 					tcb1_clk: tcb1_clk {
 						#clock-cells = <0>;
 						reg = <27>;
+						atmel,clk-output-range = <0 166000000>;
 					};
 				};
 			};
diff --git a/arch/arm/boot/dts/sama5d3_uart.dtsi b/arch/arm/boot/dts/sama5d3_uart.dtsi
index 4316bdbdc25d..cb62adbd28ed 100644
--- a/arch/arm/boot/dts/sama5d3_uart.dtsi
+++ b/arch/arm/boot/dts/sama5d3_uart.dtsi
@@ -41,13 +41,13 @@
 					uart0_clk: uart0_clk {
 						#clock-cells = <0>;
 						reg = <16>;
-						atmel,clk-output-range = <0 66000000>;
+						atmel,clk-output-range = <0 83000000>;
 					};
 
 					uart1_clk: uart1_clk {
 						#clock-cells = <0>;
 						reg = <17>;
-						atmel,clk-output-range = <0 66000000>;
+						atmel,clk-output-range = <0 83000000>;
 					};
 				};
 			};
diff --git a/arch/arm/boot/dts/socfpga.dtsi b/arch/arm/boot/dts/socfpga.dtsi
index ec1966480f2f..9a14b5fe3b57 100644
--- a/arch/arm/boot/dts/socfpga.dtsi
+++ b/arch/arm/boot/dts/socfpga.dtsi
@@ -709,7 +709,7 @@
 			};
 		};
 
-		L2: l2-cache@fffef000 {
+		L2: cache-controller@fffef000 {
 			compatible = "arm,pl310-cache";
 			reg = <0xfffef000 0x1000>;
 			interrupts = <0 38 0x04>;
diff --git a/arch/arm/boot/dts/socfpga_arria10.dtsi b/arch/arm/boot/dts/socfpga_arria10.dtsi
index ae24599d5829..6378e6461bf7 100644
--- a/arch/arm/boot/dts/socfpga_arria10.dtsi
+++ b/arch/arm/boot/dts/socfpga_arria10.dtsi
@@ -633,7 +633,7 @@
 			reg = <0xffcfb100 0x80>;
 		};
 
-		L2: l2-cache@fffff000 {
+		L2: cache-controller@fffff000 {
 			compatible = "arm,pl310-cache";
 			reg = <0xfffff000 0x1000>;
 			interrupts = <0 18 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm/boot/dts/stihxxx-b2120.dtsi b/arch/arm/boot/dts/stihxxx-b2120.dtsi
index 60e11045ad76..d051f080e52e 100644
--- a/arch/arm/boot/dts/stihxxx-b2120.dtsi
+++ b/arch/arm/boot/dts/stihxxx-b2120.dtsi
@@ -46,7 +46,7 @@
 			/* DAC */
 			format = "i2s";
 			mclk-fs = <256>;
-			frame-inversion = <1>;
+			frame-inversion;
 			cpu {
 				sound-dai = <&sti_uni_player2>;
 			};
diff --git a/arch/arm/boot/dts/stm32f469-disco.dts b/arch/arm/boot/dts/stm32f469-disco.dts
index a3ff04940aec..c6dc6d1a051b 100644
--- a/arch/arm/boot/dts/stm32f469-disco.dts
+++ b/arch/arm/boot/dts/stm32f469-disco.dts
@@ -76,6 +76,13 @@
 		regulator-max-microvolt = <3300000>;
 	};
 
+	vdd_dsi: vdd-dsi {
+		compatible = "regulator-fixed";
+		regulator-name = "vdd_dsi";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
+
 	soc {
 		dma-ranges = <0xc0000000 0x0 0x10000000>;
 	};
@@ -155,6 +162,7 @@
 		compatible = "orisetech,otm8009a";
 		reg = <0>; /* dsi virtual channel (0..3) */
 		reset-gpios = <&gpioh 7 GPIO_ACTIVE_LOW>;
+		power-supply = <&vdd_dsi>;
 		status = "okay";
 
 		port {
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index e88daa4ef1af..d777ec70a6f0 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -198,7 +198,7 @@
 		default-pool {
 			compatible = "shared-dma-pool";
 			size = <0x6000000>;
-			alloc-ranges = <0x4a000000 0x6000000>;
+			alloc-ranges = <0x40000000 0x10000000>;
 			reusable;
 			linux,cma-default;
 		};
@@ -520,6 +520,7 @@
 			interrupts = <39>;
 			clocks = <&ccu CLK_AHB_EHCI0>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -529,6 +530,7 @@
 			interrupts = <64>;
 			clocks = <&ccu CLK_USB_OHCI0>, <&ccu CLK_AHB_OHCI0>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -608,6 +610,7 @@
 			interrupts = <40>;
 			clocks = <&ccu CLK_AHB_EHCI1>;
 			phys = <&usbphy 2>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -617,6 +620,7 @@
 			interrupts = <65>;
 			clocks = <&ccu CLK_USB_OHCI1>, <&ccu CLK_AHB_OHCI1>;
 			phys = <&usbphy 2>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/sun5i.dtsi b/arch/arm/boot/dts/sun5i.dtsi
index 2fb438c4fe9d..c0775e391df8 100644
--- a/arch/arm/boot/dts/sun5i.dtsi
+++ b/arch/arm/boot/dts/sun5i.dtsi
@@ -117,7 +117,7 @@
 		default-pool {
 			compatible = "shared-dma-pool";
 			size = <0x6000000>;
-			alloc-ranges = <0x4a000000 0x6000000>;
+			alloc-ranges = <0x40000000 0x10000000>;
 			reusable;
 			linux,cma-default;
 		};
@@ -391,6 +391,7 @@
 			interrupts = <39>;
 			clocks = <&ccu CLK_AHB_EHCI>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -400,6 +401,7 @@
 			interrupts = <40>;
 			clocks = <&ccu CLK_USB_OHCI>, <&ccu CLK_AHB_OHCI>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/sun6i-a31.dtsi b/arch/arm/boot/dts/sun6i-a31.dtsi
index c04efad81bbc..fa983f9ff5f5 100644
--- a/arch/arm/boot/dts/sun6i-a31.dtsi
+++ b/arch/arm/boot/dts/sun6i-a31.dtsi
@@ -543,6 +543,7 @@
 			clocks = <&ccu CLK_AHB1_EHCI0>;
 			resets = <&ccu RST_AHB1_EHCI0>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -553,6 +554,7 @@
 			clocks = <&ccu CLK_AHB1_OHCI0>, <&ccu CLK_USB_OHCI0>;
 			resets = <&ccu RST_AHB1_OHCI0>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -563,6 +565,7 @@
 			clocks = <&ccu CLK_AHB1_EHCI1>;
 			resets = <&ccu RST_AHB1_EHCI1>;
 			phys = <&usbphy 2>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -573,6 +576,7 @@
 			clocks = <&ccu CLK_AHB1_OHCI1>, <&ccu CLK_USB_OHCI1>;
 			resets = <&ccu RST_AHB1_OHCI1>;
 			phys = <&usbphy 2>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index 9ad8e445b240..259b9e1555b6 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -180,7 +180,7 @@
 		default-pool {
 			compatible = "shared-dma-pool";
 			size = <0x6000000>;
-			alloc-ranges = <0x4a000000 0x6000000>;
+			alloc-ranges = <0x40000000 0x10000000>;
 			reusable;
 			linux,cma-default;
 		};
@@ -612,6 +612,7 @@
 			interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&ccu CLK_AHB_EHCI0>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -621,6 +622,7 @@
 			interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&ccu CLK_USB_OHCI0>, <&ccu CLK_AHB_OHCI0>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -703,6 +705,7 @@
 			interrupts = <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&ccu CLK_AHB_EHCI1>;
 			phys = <&usbphy 2>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -712,6 +715,7 @@
 			interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&ccu CLK_USB_OHCI1>, <&ccu CLK_AHB_OHCI1>;
 			phys = <&usbphy 2>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/sun8i-a23-a33.dtsi b/arch/arm/boot/dts/sun8i-a23-a33.dtsi
index af2fa694a467..f76aad0c5d4d 100644
--- a/arch/arm/boot/dts/sun8i-a23-a33.dtsi
+++ b/arch/arm/boot/dts/sun8i-a23-a33.dtsi
@@ -307,6 +307,7 @@
 			clocks = <&ccu CLK_BUS_EHCI>;
 			resets = <&ccu RST_BUS_EHCI>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -317,6 +318,7 @@
 			clocks = <&ccu CLK_BUS_OHCI>, <&ccu CLK_USB_OHCI>;
 			resets = <&ccu RST_BUS_OHCI>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts b/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts
index ea299d3d84d0..bb4667643df7 100644
--- a/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts
+++ b/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts
@@ -90,7 +90,7 @@
 		initial-mode = <1>; /* initialize in HUB mode */
 		disabled-ports = <1>;
 		intn-gpios = <&pio 7 5 GPIO_ACTIVE_HIGH>; /* PH5 */
-		reset-gpios = <&pio 4 16 GPIO_ACTIVE_HIGH>; /* PE16 */
+		reset-gpios = <&pio 4 16 GPIO_ACTIVE_LOW>; /* PE16 */
 		connect-gpios = <&pio 4 17 GPIO_ACTIVE_HIGH>; /* PE17 */
 		refclk-frequency = <19200000>;
 	};
diff --git a/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts b/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts
index 1f55811baee8..7ed0fcec004d 100644
--- a/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts
+++ b/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts
@@ -358,8 +358,8 @@
 };
 
 &reg_dldo3 {
-	regulator-min-microvolt = <2800000>;
-	regulator-max-microvolt = <2800000>;
+	regulator-min-microvolt = <1800000>;
+	regulator-max-microvolt = <1800000>;
 	regulator-name = "vdd-csi";
 };
 
@@ -482,7 +482,8 @@
 };
 
 &usbphy {
-	usb0_id_det-gpios = <&pio 7 11 GPIO_ACTIVE_HIGH>; /* PH11 */
+	usb0_id_det-gpios = <&pio 7 11 (GPIO_ACTIVE_HIGH | GPIO_PULL_UP)>; /* PH11 */
+	usb0_vbus_power-supply = <&usb_power_supply>;
 	usb0_vbus-supply = <&reg_drivevbus>;
 	usb1_vbus-supply = <&reg_vmain>;
 	usb2_vbus-supply = <&reg_vmain>;
diff --git a/arch/arm/boot/dts/sun8i-a83t.dtsi b/arch/arm/boot/dts/sun8i-a83t.dtsi
index 392b0cabbf0d..10cc220c7034 100644
--- a/arch/arm/boot/dts/sun8i-a83t.dtsi
+++ b/arch/arm/boot/dts/sun8i-a83t.dtsi
@@ -313,11 +313,11 @@
 
 		display_clocks: clock@1000000 {
 			compatible = "allwinner,sun8i-a83t-de2-clk";
-			reg = <0x01000000 0x100000>;
-			clocks = <&ccu CLK_PLL_DE>,
-				 <&ccu CLK_BUS_DE>;
-			clock-names = "mod",
-				      "bus";
+			reg = <0x01000000 0x10000>;
+			clocks = <&ccu CLK_BUS_DE>,
+				 <&ccu CLK_PLL_DE>;
+			clock-names = "bus",
+				      "mod";
 			resets = <&ccu RST_BUS_DE>;
 			#clock-cells = <1>;
 			#reset-cells = <1>;
@@ -632,6 +632,7 @@
 			clocks = <&ccu CLK_BUS_EHCI0>;
 			resets = <&ccu RST_BUS_EHCI0>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -643,6 +644,7 @@
 			clocks = <&ccu CLK_BUS_OHCI0>, <&ccu CLK_USB_OHCI0>;
 			resets = <&ccu RST_BUS_OHCI0>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -654,6 +656,7 @@
 			clocks = <&ccu CLK_BUS_EHCI1>;
 			resets = <&ccu RST_BUS_EHCI1>;
 			phys = <&usbphy 2>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/sun8i-h2-plus-bananapi-m2-zero.dts b/arch/arm/boot/dts/sun8i-h2-plus-bananapi-m2-zero.dts
index 78a37a47185a..07784d76dd53 100644
--- a/arch/arm/boot/dts/sun8i-h2-plus-bananapi-m2-zero.dts
+++ b/arch/arm/boot/dts/sun8i-h2-plus-bananapi-m2-zero.dts
@@ -31,7 +31,7 @@
 
 		pwr_led {
 			label = "bananapi-m2-zero:red:pwr";
-			gpios = <&r_pio 0 10 GPIO_ACTIVE_HIGH>; /* PL10 */
+			gpios = <&r_pio 0 10 GPIO_ACTIVE_LOW>; /* PL10 */
 			default-state = "on";
 		};
 	};
diff --git a/arch/arm/boot/dts/sun8i-h3.dtsi b/arch/arm/boot/dts/sun8i-h3.dtsi
index e37c30e811d3..6056f206c9e3 100644
--- a/arch/arm/boot/dts/sun8i-h3.dtsi
+++ b/arch/arm/boot/dts/sun8i-h3.dtsi
@@ -80,7 +80,7 @@
 			#cooling-cells = <2>;
 		};
 
-		cpu@1 {
+		cpu1: cpu@1 {
 			compatible = "arm,cortex-a7";
 			device_type = "cpu";
 			reg = <1>;
@@ -90,7 +90,7 @@
 			#cooling-cells = <2>;
 		};
 
-		cpu@2 {
+		cpu2: cpu@2 {
 			compatible = "arm,cortex-a7";
 			device_type = "cpu";
 			reg = <2>;
@@ -100,7 +100,7 @@
 			#cooling-cells = <2>;
 		};
 
-		cpu@3 {
+		cpu3: cpu@3 {
 			compatible = "arm,cortex-a7";
 			device_type = "cpu";
 			reg = <3>;
@@ -111,6 +111,15 @@
 		};
 	};
 
+	pmu {
+		compatible = "arm,cortex-a7-pmu";
+		interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-affinity = <&cpu0>, <&cpu1>, <&cpu2>, <&cpu3>;
+	};
+
 	timer {
 		compatible = "arm,armv7-timer";
 		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
diff --git a/arch/arm/boot/dts/sun8i-r40.dtsi b/arch/arm/boot/dts/sun8i-r40.dtsi
index bb856e53b806..cf771e99cb89 100644
--- a/arch/arm/boot/dts/sun8i-r40.dtsi
+++ b/arch/arm/boot/dts/sun8i-r40.dtsi
@@ -118,11 +118,11 @@
 		display_clocks: clock@1000000 {
 			compatible = "allwinner,sun8i-r40-de2-clk",
 				     "allwinner,sun8i-h3-de2-clk";
-			reg = <0x01000000 0x100000>;
-			clocks = <&ccu CLK_DE>,
-				 <&ccu CLK_BUS_DE>;
-			clock-names = "mod",
-				      "bus";
+			reg = <0x01000000 0x10000>;
+			clocks = <&ccu CLK_BUS_DE>,
+				 <&ccu CLK_DE>;
+			clock-names = "bus",
+				      "mod";
 			resets = <&ccu RST_BUS_DE>;
 			#clock-cells = <1>;
 			#reset-cells = <1>;
@@ -266,6 +266,16 @@
 			#phy-cells = <1>;
 		};
 
+		ahci: sata@1c18000 {
+			compatible = "allwinner,sun8i-r40-ahci";
+			reg = <0x01c18000 0x1000>;
+			interrupts = <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&ccu CLK_BUS_SATA>, <&ccu CLK_SATA>;
+			resets = <&ccu RST_BUS_SATA>;
+			reset-names = "ahci";
+			status = "disabled";
+		};
+
 		ehci1: usb@1c19000 {
 			compatible = "allwinner,sun8i-r40-ehci", "generic-ehci";
 			reg = <0x01c19000 0x100>;
@@ -273,6 +283,7 @@
 			clocks = <&ccu CLK_BUS_EHCI1>;
 			resets = <&ccu RST_BUS_EHCI1>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -284,6 +295,7 @@
 				 <&ccu CLK_USB_OHCI1>;
 			resets = <&ccu RST_BUS_OHCI1>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -294,6 +306,7 @@
 			clocks = <&ccu CLK_BUS_EHCI2>;
 			resets = <&ccu RST_BUS_EHCI2>;
 			phys = <&usbphy 2>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -305,6 +318,7 @@
 				 <&ccu CLK_USB_OHCI2>;
 			resets = <&ccu RST_BUS_OHCI2>;
 			phys = <&usbphy 2>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -552,17 +566,6 @@
 			#size-cells = <0>;
 		};
 
-		ahci: sata@1c18000 {
-			compatible = "allwinner,sun8i-r40-ahci";
-			reg = <0x01c18000 0x1000>;
-			interrupts = <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&ccu CLK_BUS_SATA>, <&ccu CLK_SATA>;
-			resets = <&ccu RST_BUS_SATA>;
-			reset-names = "ahci";
-			status = "disabled";
-
-		};
-
 		gmac: ethernet@1c50000 {
 			compatible = "allwinner,sun8i-r40-gmac";
 			syscon = <&ccu>;
diff --git a/arch/arm/boot/dts/sun8i-v3s.dtsi b/arch/arm/boot/dts/sun8i-v3s.dtsi
index df72b1719c34..98d1920a7620 100644
--- a/arch/arm/boot/dts/sun8i-v3s.dtsi
+++ b/arch/arm/boot/dts/sun8i-v3s.dtsi
@@ -103,11 +103,11 @@
 
 		display_clocks: clock@1000000 {
 			compatible = "allwinner,sun8i-v3s-de2-clk";
-			reg = <0x01000000 0x100000>;
-			clocks = <&ccu CLK_DE>,
-				 <&ccu CLK_BUS_DE>;
-			clock-names = "mod",
-				      "bus";
+			reg = <0x01000000 0x10000>;
+			clocks = <&ccu CLK_BUS_DE>,
+				 <&ccu CLK_DE>;
+			clock-names = "bus",
+				      "mod";
 			resets = <&ccu RST_BUS_DE>;
 			#clock-cells = <1>;
 			#reset-cells = <1>;
diff --git a/arch/arm/boot/dts/sun9i-a80.dtsi b/arch/arm/boot/dts/sun9i-a80.dtsi
index 0c1eec9000e3..c1aa26db44ae 100644
--- a/arch/arm/boot/dts/sun9i-a80.dtsi
+++ b/arch/arm/boot/dts/sun9i-a80.dtsi
@@ -342,6 +342,7 @@
 			clocks = <&usb_clocks CLK_BUS_HCI0>;
 			resets = <&usb_clocks RST_USB0_HCI>;
 			phys = <&usbphy1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -353,6 +354,7 @@
 				 <&usb_clocks CLK_USB_OHCI0>;
 			resets = <&usb_clocks RST_USB0_HCI>;
 			phys = <&usbphy1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -374,6 +376,7 @@
 			clocks = <&usb_clocks CLK_BUS_HCI1>;
 			resets = <&usb_clocks RST_USB1_HCI>;
 			phys = <&usbphy2>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -403,6 +406,7 @@
 			clocks = <&usb_clocks CLK_BUS_HCI2>;
 			resets = <&usb_clocks RST_USB2_HCI>;
 			phys = <&usbphy3>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -414,6 +418,7 @@
 				 <&usb_clocks CLK_USB_OHCI2>;
 			resets = <&usb_clocks RST_USB2_HCI>;
 			phys = <&usbphy3>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/sunxi-bananapi-m2-plus-v1.2.dtsi b/arch/arm/boot/dts/sunxi-bananapi-m2-plus-v1.2.dtsi
index 53edd1faee99..3635b251e250 100644
--- a/arch/arm/boot/dts/sunxi-bananapi-m2-plus-v1.2.dtsi
+++ b/arch/arm/boot/dts/sunxi-bananapi-m2-plus-v1.2.dtsi
@@ -16,16 +16,28 @@
 		regulator-type = "voltage";
 		regulator-boot-on;
 		regulator-always-on;
-		regulator-min-microvolt = <1100000>;
-		regulator-max-microvolt = <1300000>;
+		regulator-min-microvolt = <1108475>;
+		regulator-max-microvolt = <1308475>;
 		regulator-ramp-delay = <50>; /* 4ms */
 		gpios = <&r_pio 0 1 GPIO_ACTIVE_HIGH>; /* PL1 */
 		gpios-states = <0x1>;
-		states = <1100000 0x0
-			  1300000 0x1>;
+		states = <1108475 0x0
+			  1308475 0x1>;
 	};
 };
 
 &cpu0 {
 	cpu-supply = <&reg_vdd_cpux>;
 };
+
+&cpu1 {
+	cpu-supply = <&reg_vdd_cpux>;
+};
+
+&cpu2 {
+	cpu-supply = <&reg_vdd_cpux>;
+};
+
+&cpu3 {
+	cpu-supply = <&reg_vdd_cpux>;
+};
diff --git a/arch/arm/boot/dts/sunxi-h3-h5.dtsi b/arch/arm/boot/dts/sunxi-h3-h5.dtsi
index 84977d4eb97a..23bebc80164a 100644
--- a/arch/arm/boot/dts/sunxi-h3-h5.dtsi
+++ b/arch/arm/boot/dts/sunxi-h3-h5.dtsi
@@ -113,11 +113,11 @@
 
 		display_clocks: clock@1000000 {
 			/* compatible is in per SoC .dtsi file */
-			reg = <0x01000000 0x100000>;
-			clocks = <&ccu CLK_DE>,
-				 <&ccu CLK_BUS_DE>;
-			clock-names = "mod",
-				      "bus";
+			reg = <0x01000000 0x10000>;
+			clocks = <&ccu CLK_BUS_DE>,
+				 <&ccu CLK_DE>;
+			clock-names = "bus",
+				      "mod";
 			resets = <&ccu RST_BUS_DE>;
 			#clock-cells = <1>;
 			#reset-cells = <1>;
@@ -304,6 +304,7 @@
 			clocks = <&ccu CLK_BUS_EHCI1>, <&ccu CLK_BUS_OHCI1>;
 			resets = <&ccu RST_BUS_EHCI1>, <&ccu RST_BUS_OHCI1>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -315,6 +316,7 @@
 				 <&ccu CLK_USB_OHCI1>;
 			resets = <&ccu RST_BUS_EHCI1>, <&ccu RST_BUS_OHCI1>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -325,6 +327,7 @@
 			clocks = <&ccu CLK_BUS_EHCI2>, <&ccu CLK_BUS_OHCI2>;
 			resets = <&ccu RST_BUS_EHCI2>, <&ccu RST_BUS_OHCI2>;
 			phys = <&usbphy 2>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -336,6 +339,7 @@
 				 <&ccu CLK_USB_OHCI2>;
 			resets = <&ccu RST_BUS_EHCI2>, <&ccu RST_BUS_OHCI2>;
 			phys = <&usbphy 2>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -346,6 +350,7 @@
 			clocks = <&ccu CLK_BUS_EHCI3>, <&ccu CLK_BUS_OHCI3>;
 			resets = <&ccu RST_BUS_EHCI3>, <&ccu RST_BUS_OHCI3>;
 			phys = <&usbphy 3>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -357,6 +362,7 @@
 				 <&ccu CLK_USB_OHCI3>;
 			resets = <&ccu RST_BUS_EHCI3>, <&ccu RST_BUS_OHCI3>;
 			phys = <&usbphy 3>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
index d3963e9eaf48..1aa543eeb96f 100644
--- a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
+++ b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
@@ -30,20 +30,20 @@
 			#interrupt-cells = <1>;
 			ranges;
 
-			flash@0,00000000 {
+			flash@0 {
 				compatible = "arm,vexpress-flash", "cfi-flash";
 				reg = <0 0x00000000 0x04000000>,
 				      <4 0x00000000 0x04000000>;
 				bank-width = <4>;
 			};
 
-			psram@1,00000000 {
+			psram@100000000 {
 				compatible = "arm,vexpress-psram", "mtd-ram";
 				reg = <1 0x00000000 0x02000000>;
 				bank-width = <4>;
 			};
 
-			ethernet@2,02000000 {
+			ethernet@202000000 {
 				compatible = "smsc,lan9118", "smsc,lan9115";
 				reg = <2 0x02000000 0x10000>;
 				interrupts = <15>;
@@ -55,14 +55,14 @@
 				vddvario-supply = <&v2m_fixed_3v3>;
 			};
 
-			usb@2,03000000 {
+			usb@203000000 {
 				compatible = "nxp,usb-isp1761";
 				reg = <2 0x03000000 0x20000>;
 				interrupts = <16>;
 				port1-otg;
 			};
 
-			iofpga@3,00000000 {
+			iofpga@300000000 {
 				compatible = "simple-bus";
 				#address-cells = <1>;
 				#size-cells = <1>;
diff --git a/arch/arm/configs/aspeed_g5_defconfig b/arch/arm/configs/aspeed_g5_defconfig
index 407ffb7655a8..229561ecee06 100644
--- a/arch/arm/configs/aspeed_g5_defconfig
+++ b/arch/arm/configs/aspeed_g5_defconfig
@@ -137,6 +137,7 @@ CONFIG_SERIAL_8250_RUNTIME_UARTS=6
 CONFIG_SERIAL_8250_EXTENDED=y
 CONFIG_SERIAL_8250_ASPEED_VUART=y
 CONFIG_SERIAL_8250_SHARE_IRQ=y
+CONFIG_SERIAL_8250_DW=y
 CONFIG_SERIAL_OF_PLATFORM=y
 CONFIG_ASPEED_KCS_IPMI_BMC=y
 CONFIG_ASPEED_BT_IPMI_BMC=y
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 64eb896907bf..ab046eb41c7a 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -364,6 +364,7 @@ CONFIG_DRM_OMAP_PANEL_TPO_TD043MTEA1=m
 CONFIG_DRM_OMAP_PANEL_NEC_NL8048HL11=m
 CONFIG_DRM_TILCDC=m
 CONFIG_DRM_PANEL_SIMPLE=m
+CONFIG_DRM_TI_TFP410=m
 CONFIG_FB=y
 CONFIG_FIRMWARE_EDID=y
 CONFIG_FB_MODE_HELPERS=y
diff --git a/arch/arm/crypto/nhpoly1305-neon-glue.c b/arch/arm/crypto/nhpoly1305-neon-glue.c
index ae5aefc44a4d..ffa8d73fe722 100644
--- a/arch/arm/crypto/nhpoly1305-neon-glue.c
+++ b/arch/arm/crypto/nhpoly1305-neon-glue.c
@@ -30,7 +30,7 @@ static int nhpoly1305_neon_update(struct shash_desc *desc,
 		return crypto_nhpoly1305_update(desc, src, srclen);
 
 	do {
-		unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE);
+		unsigned int n = min_t(unsigned int, srclen, SZ_4K);
 
 		kernel_neon_begin();
 		crypto_nhpoly1305_update_helper(desc, src, n, _nh_neon);
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 99929122dad7..3546d294d55f 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -18,11 +18,11 @@
 #endif
 
 #include <asm/ptrace.h>
-#include <asm/domain.h>
 #include <asm/opcodes-virt.h>
 #include <asm/asm-offsets.h>
 #include <asm/page.h>
 #include <asm/thread_info.h>
+#include <asm/uaccess-asm.h>
 
 #define IOMEM(x)	(x)
 
@@ -446,79 +446,6 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	.size \name , . - \name
 	.endm
 
-	.macro	csdb
-#ifdef CONFIG_THUMB2_KERNEL
-	.inst.w	0xf3af8014
-#else
-	.inst	0xe320f014
-#endif
-	.endm
-
-	.macro check_uaccess, addr:req, size:req, limit:req, tmp:req, bad:req
-#ifndef CONFIG_CPU_USE_DOMAINS
-	adds	\tmp, \addr, #\size - 1
-	sbcscc	\tmp, \tmp, \limit
-	bcs	\bad
-#ifdef CONFIG_CPU_SPECTRE
-	movcs	\addr, #0
-	csdb
-#endif
-#endif
-	.endm
-
-	.macro uaccess_mask_range_ptr, addr:req, size:req, limit:req, tmp:req
-#ifdef CONFIG_CPU_SPECTRE
-	sub	\tmp, \limit, #1
-	subs	\tmp, \tmp, \addr	@ tmp = limit - 1 - addr
-	addhs	\tmp, \tmp, #1		@ if (tmp >= 0) {
-	subshs	\tmp, \tmp, \size	@ tmp = limit - (addr + size) }
-	movlo	\addr, #0		@ if (tmp < 0) addr = NULL
-	csdb
-#endif
-	.endm
-
-	.macro	uaccess_disable, tmp, isb=1
-#ifdef CONFIG_CPU_SW_DOMAIN_PAN
-	/*
-	 * Whenever we re-enter userspace, the domains should always be
-	 * set appropriately.
-	 */
-	mov	\tmp, #DACR_UACCESS_DISABLE
-	mcr	p15, 0, \tmp, c3, c0, 0		@ Set domain register
-	.if	\isb
-	instr_sync
-	.endif
-#endif
-	.endm
-
-	.macro	uaccess_enable, tmp, isb=1
-#ifdef CONFIG_CPU_SW_DOMAIN_PAN
-	/*
-	 * Whenever we re-enter userspace, the domains should always be
-	 * set appropriately.
-	 */
-	mov	\tmp, #DACR_UACCESS_ENABLE
-	mcr	p15, 0, \tmp, c3, c0, 0
-	.if	\isb
-	instr_sync
-	.endif
-#endif
-	.endm
-
-	.macro	uaccess_save, tmp
-#ifdef CONFIG_CPU_SW_DOMAIN_PAN
-	mrc	p15, 0, \tmp, c3, c0, 0
-	str	\tmp, [sp, #SVC_DACR]
-#endif
-	.endm
-
-	.macro	uaccess_restore
-#ifdef CONFIG_CPU_SW_DOMAIN_PAN
-	ldr	r0, [sp, #SVC_DACR]
-	mcr	p15, 0, r0, c3, c0, 0
-#endif
-	.endm
-
 	.irp	c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo
 	.macro	ret\c, reg
 #if __LINUX_ARM_ARCH__ < 6
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 83c391b597d4..fdc4ae3e7378 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -164,8 +164,13 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
 	preempt_enable();
 #endif
 
-	if (!ret)
-		*oval = oldval;
+	/*
+	 * Store unconditionally. If ret != 0 the extra store is the least
+	 * of the worries but GCC cannot figure out that __futex_atomic_op()
+	 * is either setting ret to -EFAULT or storing the old value in
+	 * oldval which results in a uninitialized warning at the call site.
+	 */
+	*oval = oldval;
 
 	return ret;
 }
diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index 6b7644a383f6..468e5b5e8be6 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -14,13 +14,25 @@
 #include <asm/cputype.h>
 
 /* arm64 compatibility macros */
+#define PSR_AA32_MODE_FIQ	FIQ_MODE
+#define PSR_AA32_MODE_SVC	SVC_MODE
 #define PSR_AA32_MODE_ABT	ABT_MODE
 #define PSR_AA32_MODE_UND	UND_MODE
 #define PSR_AA32_T_BIT		PSR_T_BIT
+#define PSR_AA32_F_BIT		PSR_F_BIT
 #define PSR_AA32_I_BIT		PSR_I_BIT
 #define PSR_AA32_A_BIT		PSR_A_BIT
 #define PSR_AA32_E_BIT		PSR_E_BIT
 #define PSR_AA32_IT_MASK	PSR_IT_MASK
+#define PSR_AA32_GE_MASK	0x000f0000
+#define PSR_AA32_DIT_BIT	0x00200000
+#define PSR_AA32_PAN_BIT	0x00400000
+#define PSR_AA32_SSBS_BIT	0x00800000
+#define PSR_AA32_Q_BIT		PSR_Q_BIT
+#define PSR_AA32_V_BIT		PSR_V_BIT
+#define PSR_AA32_C_BIT		PSR_C_BIT
+#define PSR_AA32_Z_BIT		PSR_Z_BIT
+#define PSR_AA32_N_BIT		PSR_N_BIT
 
 unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num);
 
@@ -41,6 +53,11 @@ static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v)
 	*__vcpu_spsr(vcpu) = v;
 }
 
+static inline unsigned long host_spsr_to_spsr32(unsigned long spsr)
+{
+	return spsr;
+}
+
 static inline unsigned long vcpu_get_reg(struct kvm_vcpu *vcpu,
 					 u8 reg_num)
 {
@@ -177,6 +194,11 @@ static inline bool kvm_vcpu_dabt_issext(struct kvm_vcpu *vcpu)
 	return kvm_vcpu_get_hsr(vcpu) & HSR_SSE;
 }
 
+static inline bool kvm_vcpu_dabt_issf(const struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+
 static inline int kvm_vcpu_dabt_get_rd(struct kvm_vcpu *vcpu)
 {
 	return (kvm_vcpu_get_hsr(vcpu) & HSR_SRT_MASK) >> HSR_SRT_SHIFT;
diff --git a/arch/arm/include/asm/kvm_mmio.h b/arch/arm/include/asm/kvm_mmio.h
index 7c0eddb0adb2..32fbf82e3ebc 100644
--- a/arch/arm/include/asm/kvm_mmio.h
+++ b/arch/arm/include/asm/kvm_mmio.h
@@ -14,6 +14,8 @@
 struct kvm_decode {
 	unsigned long rt;
 	bool sign_extend;
+	/* Not used on 32-bit arm */
+	bool sixty_four;
 };
 
 void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data);
diff --git a/arch/arm/include/asm/percpu.h b/arch/arm/include/asm/percpu.h
index f44f448537f2..1a3eedbac4a2 100644
--- a/arch/arm/include/asm/percpu.h
+++ b/arch/arm/include/asm/percpu.h
@@ -5,6 +5,8 @@
 #ifndef _ASM_ARM_PERCPU_H_
 #define _ASM_ARM_PERCPU_H_
 
+#include <asm/thread_info.h>
+
 /*
  * Same as asm-generic/percpu.h, except that we store the per cpu offset
  * in the TPIDRPRW. TPIDRPRW only exists on V6K and V7
diff --git a/arch/arm/include/asm/uaccess-asm.h b/arch/arm/include/asm/uaccess-asm.h
new file mode 100644
index 000000000000..907571fd05c6
--- /dev/null
+++ b/arch/arm/include/asm/uaccess-asm.h
@@ -0,0 +1,117 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_UACCESS_ASM_H__
+#define __ASM_UACCESS_ASM_H__
+
+#include <asm/asm-offsets.h>
+#include <asm/domain.h>
+#include <asm/memory.h>
+#include <asm/thread_info.h>
+
+	.macro	csdb
+#ifdef CONFIG_THUMB2_KERNEL
+	.inst.w	0xf3af8014
+#else
+	.inst	0xe320f014
+#endif
+	.endm
+
+	.macro check_uaccess, addr:req, size:req, limit:req, tmp:req, bad:req
+#ifndef CONFIG_CPU_USE_DOMAINS
+	adds	\tmp, \addr, #\size - 1
+	sbcscc	\tmp, \tmp, \limit
+	bcs	\bad
+#ifdef CONFIG_CPU_SPECTRE
+	movcs	\addr, #0
+	csdb
+#endif
+#endif
+	.endm
+
+	.macro uaccess_mask_range_ptr, addr:req, size:req, limit:req, tmp:req
+#ifdef CONFIG_CPU_SPECTRE
+	sub	\tmp, \limit, #1
+	subs	\tmp, \tmp, \addr	@ tmp = limit - 1 - addr
+	addhs	\tmp, \tmp, #1		@ if (tmp >= 0) {
+	subshs	\tmp, \tmp, \size	@ tmp = limit - (addr + size) }
+	movlo	\addr, #0		@ if (tmp < 0) addr = NULL
+	csdb
+#endif
+	.endm
+
+	.macro	uaccess_disable, tmp, isb=1
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	/*
+	 * Whenever we re-enter userspace, the domains should always be
+	 * set appropriately.
+	 */
+	mov	\tmp, #DACR_UACCESS_DISABLE
+	mcr	p15, 0, \tmp, c3, c0, 0		@ Set domain register
+	.if	\isb
+	instr_sync
+	.endif
+#endif
+	.endm
+
+	.macro	uaccess_enable, tmp, isb=1
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	/*
+	 * Whenever we re-enter userspace, the domains should always be
+	 * set appropriately.
+	 */
+	mov	\tmp, #DACR_UACCESS_ENABLE
+	mcr	p15, 0, \tmp, c3, c0, 0
+	.if	\isb
+	instr_sync
+	.endif
+#endif
+	.endm
+
+#if defined(CONFIG_CPU_SW_DOMAIN_PAN) || defined(CONFIG_CPU_USE_DOMAINS)
+#define DACR(x...)	x
+#else
+#define DACR(x...)
+#endif
+
+	/*
+	 * Save the address limit on entry to a privileged exception.
+	 *
+	 * If we are using the DACR for kernel access by the user accessors
+	 * (CONFIG_CPU_USE_DOMAINS=y), always reset the DACR kernel domain
+	 * back to client mode, whether or not \disable is set.
+	 *
+	 * If we are using SW PAN, set the DACR user domain to no access
+	 * if \disable is set.
+	 */
+	.macro	uaccess_entry, tsk, tmp0, tmp1, tmp2, disable
+	ldr	\tmp1, [\tsk, #TI_ADDR_LIMIT]
+	mov	\tmp2, #TASK_SIZE
+	str	\tmp2, [\tsk, #TI_ADDR_LIMIT]
+ DACR(	mrc	p15, 0, \tmp0, c3, c0, 0)
+ DACR(	str	\tmp0, [sp, #SVC_DACR])
+	str	\tmp1, [sp, #SVC_ADDR_LIMIT]
+	.if \disable && IS_ENABLED(CONFIG_CPU_SW_DOMAIN_PAN)
+	/* kernel=client, user=no access */
+	mov	\tmp2, #DACR_UACCESS_DISABLE
+	mcr	p15, 0, \tmp2, c3, c0, 0
+	instr_sync
+	.elseif IS_ENABLED(CONFIG_CPU_USE_DOMAINS)
+	/* kernel=client */
+	bic	\tmp2, \tmp0, #domain_mask(DOMAIN_KERNEL)
+	orr	\tmp2, \tmp2, #domain_val(DOMAIN_KERNEL, DOMAIN_CLIENT)
+	mcr	p15, 0, \tmp2, c3, c0, 0
+	instr_sync
+	.endif
+	.endm
+
+	/* Restore the user access state previously saved by uaccess_entry */
+	.macro	uaccess_exit, tsk, tmp0, tmp1
+	ldr	\tmp1, [sp, #SVC_ADDR_LIMIT]
+ DACR(	ldr	\tmp0, [sp, #SVC_DACR])
+	str	\tmp1, [\tsk, #TI_ADDR_LIMIT]
+ DACR(	mcr	p15, 0, \tmp0, c3, c0, 0)
+	.endm
+
+#undef DACR
+
+#endif /* __ASM_UACCESS_ASM_H__ */
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 8cad59465af3..8b679e2ca3c3 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -17,10 +17,14 @@ CFLAGS_REMOVE_return_address.o = -pg
 # Object file lists.
 
 obj-y		:= elf.o entry-common.o irq.o opcodes.o \
-		   process.o ptrace.o reboot.o return_address.o \
+		   process.o ptrace.o reboot.o \
 		   setup.o signal.o sigreturn_codes.o \
 		   stacktrace.o sys_arm.o time.o traps.o
 
+ifneq ($(CONFIG_ARM_UNWIND),y)
+obj-$(CONFIG_FRAME_POINTER)	+= return_address.o
+endif
+
 obj-$(CONFIG_ATAGS)		+= atags_parse.o
 obj-$(CONFIG_ATAGS_PROC)	+= atags_proc.o
 obj-$(CONFIG_DEPRECATED_PARAM_STRUCT) += atags_compat.o
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 0b8cfdd60b90..9780b690c3ed 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -27,6 +27,7 @@
 #include <asm/unistd.h>
 #include <asm/tls.h>
 #include <asm/system_info.h>
+#include <asm/uaccess-asm.h>
 
 #include "entry-header.S"
 #include <asm/entry-macro-multi.S>
@@ -179,15 +180,7 @@ ENDPROC(__und_invalid)
 	stmia	r7, {r2 - r6}
 
 	get_thread_info tsk
-	ldr	r0, [tsk, #TI_ADDR_LIMIT]
-	mov	r1, #TASK_SIZE
-	str	r1, [tsk, #TI_ADDR_LIMIT]
-	str	r0, [sp, #SVC_ADDR_LIMIT]
-
-	uaccess_save r0
-	.if \uaccess
-	uaccess_disable r0
-	.endif
+	uaccess_entry tsk, r0, r1, r2, \uaccess
 
 	.if \trace
 #ifdef CONFIG_TRACE_IRQFLAGS
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 32051ec5b33f..40db0f9188b6 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -6,6 +6,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/errno.h>
 #include <asm/thread_info.h>
+#include <asm/uaccess-asm.h>
 #include <asm/v7m.h>
 
 @ Bad Abort numbers
@@ -217,9 +218,7 @@
 	blne	trace_hardirqs_off
 #endif
 	.endif
-	ldr	r1, [sp, #SVC_ADDR_LIMIT]
-	uaccess_restore
-	str	r1, [tsk, #TI_ADDR_LIMIT]
+	uaccess_exit tsk, r0, r1
 
 #ifndef CONFIG_THUMB2_KERNEL
 	@ ARM mode SVC restore
@@ -263,9 +262,7 @@
 	@ on the stack remains correct).
 	@
 	.macro  svc_exit_via_fiq
-	ldr	r1, [sp, #SVC_ADDR_LIMIT]
-	uaccess_restore
-	str	r1, [tsk, #TI_ADDR_LIMIT]
+	uaccess_exit tsk, r0, r1
 #ifndef CONFIG_THUMB2_KERNEL
 	@ ARM mode restore
 	mov	r0, sp
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index af8b8e15f589..35cec1c78485 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -677,6 +677,12 @@ static void disable_single_step(struct perf_event *bp)
 	arch_install_hw_breakpoint(bp);
 }
 
+static int watchpoint_fault_on_uaccess(struct pt_regs *regs,
+				       struct arch_hw_breakpoint *info)
+{
+	return !user_mode(regs) && info->ctrl.privilege == ARM_BREAKPOINT_USER;
+}
+
 static void watchpoint_handler(unsigned long addr, unsigned int fsr,
 			       struct pt_regs *regs)
 {
@@ -736,16 +742,27 @@ static void watchpoint_handler(unsigned long addr, unsigned int fsr,
 		}
 
 		pr_debug("watchpoint fired: address = 0x%x\n", info->trigger);
+
+		/*
+		 * If we triggered a user watchpoint from a uaccess routine,
+		 * then handle the stepping ourselves since userspace really
+		 * can't help us with this.
+		 */
+		if (watchpoint_fault_on_uaccess(regs, info))
+			goto step;
+
 		perf_bp_event(wp, regs);
 
 		/*
-		 * If no overflow handler is present, insert a temporary
-		 * mismatch breakpoint so we can single-step over the
-		 * watchpoint trigger.
+		 * Defer stepping to the overflow handler if one is installed.
+		 * Otherwise, insert a temporary mismatch breakpoint so that
+		 * we can single-step over the watchpoint trigger.
 		 */
-		if (is_default_overflow_handler(wp))
-			enable_single_step(wp, instruction_pointer(regs));
+		if (!is_default_overflow_handler(wp))
+			goto unlock;
 
+step:
+		enable_single_step(wp, instruction_pointer(regs));
 unlock:
 		rcu_read_unlock();
 	}
diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S
index ae5020302de4..6607fa817bba 100644
--- a/arch/arm/kernel/hyp-stub.S
+++ b/arch/arm/kernel/hyp-stub.S
@@ -146,10 +146,9 @@ ARM_BE8(orr	r7, r7, #(1 << 25))     @ HSCTLR.EE
 #if !defined(ZIMAGE) && defined(CONFIG_ARM_ARCH_TIMER)
 	@ make CNTP_* and CNTPCT accessible from PL1
 	mrc	p15, 0, r7, c0, c1, 1	@ ID_PFR1
-	lsr	r7, #16
-	and	r7, #0xf
-	cmp	r7, #1
-	bne	1f
+	ubfx	r7, r7, #16, #4
+	teq	r7, #0
+	beq	1f
 	mrc	p15, 4, r7, c14, c1, 0	@ CNTHCTL
 	orr	r7, r7, #3		@ PL1PCEN | PL1PCTEN
 	mcr	p15, 4, r7, c14, c1, 0	@ CNTHCTL
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index afcb4d3b14dc..d8ccdd5d09a3 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -219,8 +219,8 @@ static struct undef_hook arm_break_hook = {
 };
 
 static struct undef_hook thumb_break_hook = {
-	.instr_mask	= 0xffff,
-	.instr_val	= 0xde01,
+	.instr_mask	= 0xffffffff,
+	.instr_val	= 0x0000de01,
 	.cpsr_mask	= PSR_T_BIT,
 	.cpsr_val	= PSR_T_BIT,
 	.fn		= break_trap,
diff --git a/arch/arm/kernel/return_address.c b/arch/arm/kernel/return_address.c
index b0d2f1fe891d..7b42ac010fdf 100644
--- a/arch/arm/kernel/return_address.c
+++ b/arch/arm/kernel/return_address.c
@@ -7,8 +7,6 @@
  */
 #include <linux/export.h>
 #include <linux/ftrace.h>
-
-#if defined(CONFIG_FRAME_POINTER) && !defined(CONFIG_ARM_UNWIND)
 #include <linux/sched.h>
 
 #include <asm/stacktrace.h>
@@ -53,6 +51,4 @@ void *return_address(unsigned int level)
 		return NULL;
 }
 
-#endif /* if defined(CONFIG_FRAME_POINTER) && !defined(CONFIG_ARM_UNWIND) */
-
 EXPORT_SYMBOL_GPL(return_address);
diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index 71778bb0475b..a082f6e4f0f4 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -22,6 +22,19 @@
  * A simple function epilogue looks like this:
  *	ldm	sp, {fp, sp, pc}
  *
+ * When compiled with clang, pc and sp are not pushed. A simple function
+ * prologue looks like this when built with clang:
+ *
+ *	stmdb	{..., fp, lr}
+ *	add	fp, sp, #x
+ *	sub	sp, sp, #y
+ *
+ * A simple function epilogue looks like this when built with clang:
+ *
+ *	sub	sp, fp, #x
+ *	ldm	{..., fp, pc}
+ *
+ *
  * Note that with framepointer enabled, even the leaf functions have the same
  * prologue and epilogue, therefore we can ignore the LR value in this case.
  */
@@ -34,6 +47,16 @@ int notrace unwind_frame(struct stackframe *frame)
 	low = frame->sp;
 	high = ALIGN(low, THREAD_SIZE);
 
+#ifdef CONFIG_CC_IS_CLANG
+	/* check current frame pointer is within bounds */
+	if (fp < low + 4 || fp > high - 4)
+		return -EINVAL;
+
+	frame->sp = frame->fp;
+	frame->fp = *(unsigned long *)(fp);
+	frame->pc = frame->lr;
+	frame->lr = *(unsigned long *)(fp + 4);
+#else
 	/* check current frame pointer is within bounds */
 	if (fp < low + 12 || fp > high - 4)
 		return -EINVAL;
@@ -42,6 +65,7 @@ int notrace unwind_frame(struct stackframe *frame)
 	frame->fp = *(unsigned long *)(fp - 12);
 	frame->sp = *(unsigned long *)(fp - 8);
 	frame->pc = *(unsigned long *)(fp - 4);
+#endif
 
 	return 0;
 }
diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c
index 8872acf9ff99..15f21694b532 100644
--- a/arch/arm/kernel/vdso.c
+++ b/arch/arm/kernel/vdso.c
@@ -93,6 +93,8 @@ static bool __init cntvct_functional(void)
 	 */
 	np = of_find_compatible_node(NULL, NULL, "arm,armv7-timer");
 	if (!np)
+		np = of_find_compatible_node(NULL, NULL, "arm,armv8-timer");
+	if (!np)
 		goto out_put;
 
 	if (of_property_read_bool(np, "arm,cpu-registers-not-fw-configured"))
diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S
index 95b2e1ce559c..f8016e3db65d 100644
--- a/arch/arm/lib/copy_from_user.S
+++ b/arch/arm/lib/copy_from_user.S
@@ -118,7 +118,7 @@ ENTRY(arm_copy_from_user)
 
 ENDPROC(arm_copy_from_user)
 
-	.pushsection .fixup,"ax"
+	.pushsection .text.fixup,"ax"
 	.align 0
 	copy_abort_preamble
 	ldmfd	sp!, {r1, r2, r3}
diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c
index da85e64143e9..21591fff6b0e 100644
--- a/arch/arm/mach-at91/pm.c
+++ b/arch/arm/mach-at91/pm.c
@@ -591,13 +591,13 @@ static void __init at91_pm_sram_init(void)
 	sram_pool = gen_pool_get(&pdev->dev, NULL);
 	if (!sram_pool) {
 		pr_warn("%s: sram pool unavailable!\n", __func__);
-		return;
+		goto out_put_device;
 	}
 
 	sram_base = gen_pool_alloc(sram_pool, at91_pm_suspend_in_sram_sz);
 	if (!sram_base) {
 		pr_warn("%s: unable to alloc sram!\n", __func__);
-		return;
+		goto out_put_device;
 	}
 
 	sram_pbase = gen_pool_virt_to_phys(sram_pool, sram_base);
@@ -605,12 +605,17 @@ static void __init at91_pm_sram_init(void)
 					at91_pm_suspend_in_sram_sz, false);
 	if (!at91_suspend_sram_fn) {
 		pr_warn("SRAM: Could not map\n");
-		return;
+		goto out_put_device;
 	}
 
 	/* Copy the pm suspend handler to SRAM */
 	at91_suspend_sram_fn = fncpy(at91_suspend_sram_fn,
 			&at91_pm_suspend_in_sram, at91_pm_suspend_in_sram_sz);
+	return;
+
+out_put_device:
+	put_device(&pdev->dev);
+	return;
 }
 
 static bool __init at91_is_pm_mode_active(int pm_mode)
@@ -690,6 +695,12 @@ static void __init at91_pm_use_default_mode(int pm_mode)
 		soc_pm.data.suspend_mode = AT91_PM_ULP0;
 }
 
+static const struct of_device_id atmel_shdwc_ids[] = {
+	{ .compatible = "atmel,sama5d2-shdwc" },
+	{ .compatible = "microchip,sam9x60-shdwc" },
+	{ /* sentinel. */ }
+};
+
 static void __init at91_pm_modes_init(void)
 {
 	struct device_node *np;
@@ -699,7 +710,7 @@ static void __init at91_pm_modes_init(void)
 	    !at91_is_pm_mode_active(AT91_PM_ULP1))
 		return;
 
-	np = of_find_compatible_node(NULL, NULL, "atmel,sama5d2-shdwc");
+	np = of_find_matching_node(NULL, atmel_shdwc_ids);
 	if (!np) {
 		pr_warn("%s: failed to find shdwc!\n", __func__);
 		goto ulp1_default;
@@ -750,6 +761,7 @@ static const struct of_device_id atmel_pmc_ids[] __initconst = {
 	{ .compatible = "atmel,sama5d3-pmc", .data = &pmc_infos[1] },
 	{ .compatible = "atmel,sama5d4-pmc", .data = &pmc_infos[1] },
 	{ .compatible = "atmel,sama5d2-pmc", .data = &pmc_infos[1] },
+	{ .compatible = "microchip,sam9x60-pmc", .data = &pmc_infos[1] },
 	{ /* sentinel */ },
 };
 
diff --git a/arch/arm/mach-at91/pm_suspend.S b/arch/arm/mach-at91/pm_suspend.S
index ed57c879d4e1..2591cba61937 100644
--- a/arch/arm/mach-at91/pm_suspend.S
+++ b/arch/arm/mach-at91/pm_suspend.S
@@ -268,6 +268,10 @@ ENDPROC(at91_backup_mode)
 	orr	tmp1, tmp1, #AT91_PMC_KEY
 	str	tmp1, [pmc, #AT91_CKGR_MOR]
 
+	/* Quirk for SAM9X60's PMC */
+	nop
+	nop
+
 	wait_mckrdy
 
 	/* Enable the crystal oscillator */
diff --git a/arch/arm/mach-exynos/mcpm-exynos.c b/arch/arm/mach-exynos/mcpm-exynos.c
index 9a681b421ae1..cd861c57d5ad 100644
--- a/arch/arm/mach-exynos/mcpm-exynos.c
+++ b/arch/arm/mach-exynos/mcpm-exynos.c
@@ -26,6 +26,7 @@
 #define EXYNOS5420_USE_L2_COMMON_UP_STATE	BIT(30)
 
 static void __iomem *ns_sram_base_addr __ro_after_init;
+static bool secure_firmware __ro_after_init;
 
 /*
  * The common v7_exit_coherency_flush API could not be used because of the
@@ -58,15 +59,16 @@ static void __iomem *ns_sram_base_addr __ro_after_init;
 static int exynos_cpu_powerup(unsigned int cpu, unsigned int cluster)
 {
 	unsigned int cpunr = cpu + (cluster * EXYNOS5420_CPUS_PER_CLUSTER);
+	bool state;
 
 	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
 	if (cpu >= EXYNOS5420_CPUS_PER_CLUSTER ||
 		cluster >= EXYNOS5420_NR_CLUSTERS)
 		return -EINVAL;
 
-	if (!exynos_cpu_power_state(cpunr)) {
-		exynos_cpu_power_up(cpunr);
-
+	state = exynos_cpu_power_state(cpunr);
+	exynos_cpu_power_up(cpunr);
+	if (!state && secure_firmware) {
 		/*
 		 * This assumes the cluster number of the big cores(Cortex A15)
 		 * is 0 and the Little cores(Cortex A7) is 1.
@@ -258,6 +260,8 @@ static int __init exynos_mcpm_init(void)
 		return -ENOMEM;
 	}
 
+	secure_firmware = exynos_secure_firmware_available();
+
 	/*
 	 * To increase the stability of KFC reset we need to program
 	 * the PMU SPARE3 register
diff --git a/arch/arm/mach-imx/Kconfig b/arch/arm/mach-imx/Kconfig
index 593bf1519608..95584ee02b55 100644
--- a/arch/arm/mach-imx/Kconfig
+++ b/arch/arm/mach-imx/Kconfig
@@ -520,6 +520,7 @@ config SOC_IMX6UL
 	bool "i.MX6 UltraLite support"
 	select PINCTRL_IMX6UL
 	select SOC_IMX6
+	select ARM_ERRATA_814220
 
 	help
 	  This enables support for Freescale i.MX6 UltraLite processor.
@@ -556,6 +557,7 @@ config SOC_IMX7D
 	select PINCTRL_IMX7D
 	select SOC_IMX7D_CA7 if ARCH_MULTI_V7
 	select SOC_IMX7D_CM4 if ARM_SINGLE_ARMV7M
+	select ARM_ERRATA_814220 if ARCH_MULTI_V7
 	help
 		This enables support for Freescale i.MX7 Dual processor.
 
diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile
index 35ff620537e6..e7364e6c8c6b 100644
--- a/arch/arm/mach-imx/Makefile
+++ b/arch/arm/mach-imx/Makefile
@@ -91,6 +91,10 @@ AFLAGS_suspend-imx6.o :=-Wa,-march=armv7-a
 obj-$(CONFIG_SOC_IMX6) += suspend-imx6.o
 obj-$(CONFIG_SOC_IMX53) += suspend-imx53.o
 endif
+ifeq ($(CONFIG_ARM_CPU_SUSPEND),y)
+AFLAGS_resume-imx6.o :=-Wa,-march=armv7-a
+obj-$(CONFIG_SOC_IMX6) += resume-imx6.o
+endif
 obj-$(CONFIG_SOC_IMX6) += pm-imx6.o
 
 obj-$(CONFIG_SOC_IMX1) += mach-imx1.o
diff --git a/arch/arm/mach-imx/common.h b/arch/arm/mach-imx/common.h
index 912aeceb4ff8..5aa5796cff0e 100644
--- a/arch/arm/mach-imx/common.h
+++ b/arch/arm/mach-imx/common.h
@@ -109,17 +109,17 @@ void imx_cpu_die(unsigned int cpu);
 int imx_cpu_kill(unsigned int cpu);
 
 #ifdef CONFIG_SUSPEND
-void v7_cpu_resume(void);
 void imx53_suspend(void __iomem *ocram_vbase);
 extern const u32 imx53_suspend_sz;
 void imx6_suspend(void __iomem *ocram_vbase);
 #else
-static inline void v7_cpu_resume(void) {}
 static inline void imx53_suspend(void __iomem *ocram_vbase) {}
 static const u32 imx53_suspend_sz;
 static inline void imx6_suspend(void __iomem *ocram_vbase) {}
 #endif
 
+void v7_cpu_resume(void);
+
 void imx6_pm_ccm_init(const char *ccm_compat);
 void imx6q_pm_init(void);
 void imx6dl_pm_init(void);
diff --git a/arch/arm/mach-imx/devices/devices-common.h b/arch/arm/mach-imx/devices/devices-common.h
index 2a685adec1df..ae84c08e11fa 100644
--- a/arch/arm/mach-imx/devices/devices-common.h
+++ b/arch/arm/mach-imx/devices/devices-common.h
@@ -289,6 +289,6 @@ struct platform_device *__init imx_add_spi_imx(
 		const struct spi_imx_master *pdata);
 
 struct platform_device *imx_add_imx_dma(char *name, resource_size_t iobase,
-					int irq, int irq_err);
+					int irq);
 struct platform_device *imx_add_imx_sdma(char *name,
 	resource_size_t iobase, int irq, struct sdma_platform_data *pdata);
diff --git a/arch/arm/mach-imx/devices/platform-gpio-mxc.c b/arch/arm/mach-imx/devices/platform-gpio-mxc.c
index 78628ef12672..355de845224c 100644
--- a/arch/arm/mach-imx/devices/platform-gpio-mxc.c
+++ b/arch/arm/mach-imx/devices/platform-gpio-mxc.c
@@ -24,7 +24,8 @@ struct platform_device *__init mxc_register_gpio(char *name, int id,
 			.flags = IORESOURCE_IRQ,
 		},
 	};
+	unsigned int nres;
 
-	return platform_device_register_resndata(&mxc_aips_bus,
-			name, id, res, ARRAY_SIZE(res), NULL, 0);
+	nres = irq_high ? ARRAY_SIZE(res) : ARRAY_SIZE(res) - 1;
+	return platform_device_register_resndata(&mxc_aips_bus, name, id, res, nres, NULL, 0);
 }
diff --git a/arch/arm/mach-imx/devices/platform-imx-dma.c b/arch/arm/mach-imx/devices/platform-imx-dma.c
index 26b47b36257b..12656f24ad0d 100644
--- a/arch/arm/mach-imx/devices/platform-imx-dma.c
+++ b/arch/arm/mach-imx/devices/platform-imx-dma.c
@@ -6,7 +6,7 @@
 #include "devices-common.h"
 
 struct platform_device __init __maybe_unused *imx_add_imx_dma(char *name,
-	resource_size_t iobase, int irq, int irq_err)
+	resource_size_t iobase, int irq)
 {
 	struct resource res[] = {
 		{
@@ -17,10 +17,6 @@ struct platform_device __init __maybe_unused *imx_add_imx_dma(char *name,
 			.start = irq,
 			.end = irq,
 			.flags = IORESOURCE_IRQ,
-		}, {
-			.start = irq_err,
-			.end = irq_err,
-			.flags = IORESOURCE_IRQ,
 		},
 	};
 
diff --git a/arch/arm/mach-imx/mm-imx21.c b/arch/arm/mach-imx/mm-imx21.c
index e117d2883df9..0b4db806d905 100644
--- a/arch/arm/mach-imx/mm-imx21.c
+++ b/arch/arm/mach-imx/mm-imx21.c
@@ -79,8 +79,7 @@ void __init imx21_soc_init(void)
 	mxc_register_gpio("imx21-gpio", 5, MX21_GPIO6_BASE_ADDR, SZ_256, MX21_INT_GPIO, 0);
 
 	pinctrl_provide_dummies();
-	imx_add_imx_dma("imx21-dma", MX21_DMA_BASE_ADDR,
-			MX21_INT_DMACH0, 0); /* No ERR irq */
+	imx_add_imx_dma("imx21-dma", MX21_DMA_BASE_ADDR, MX21_INT_DMACH0);
 	platform_device_register_simple("imx21-audmux", 0, imx21_audmux_res,
 					ARRAY_SIZE(imx21_audmux_res));
 }
diff --git a/arch/arm/mach-imx/mm-imx27.c b/arch/arm/mach-imx/mm-imx27.c
index dcbe7ec6d543..9da34d50023f 100644
--- a/arch/arm/mach-imx/mm-imx27.c
+++ b/arch/arm/mach-imx/mm-imx27.c
@@ -80,8 +80,7 @@ void __init imx27_soc_init(void)
 	mxc_register_gpio("imx21-gpio", 5, MX27_GPIO6_BASE_ADDR, SZ_256, MX27_INT_GPIO, 0);
 
 	pinctrl_provide_dummies();
-	imx_add_imx_dma("imx27-dma", MX27_DMA_BASE_ADDR,
-			MX27_INT_DMACH0, 0); /* No ERR irq */
+	imx_add_imx_dma("imx27-dma", MX27_DMA_BASE_ADDR, MX27_INT_DMACH0);
 	/* imx27 has the imx21 type audmux */
 	platform_device_register_simple("imx21-audmux", 0, imx27_audmux_res,
 					ARRAY_SIZE(imx27_audmux_res));
diff --git a/arch/arm/mach-imx/pm-imx5.c b/arch/arm/mach-imx/pm-imx5.c
index f057df813f83..e9962b48e30c 100644
--- a/arch/arm/mach-imx/pm-imx5.c
+++ b/arch/arm/mach-imx/pm-imx5.c
@@ -295,14 +295,14 @@ static int __init imx_suspend_alloc_ocram(
 	if (!ocram_pool) {
 		pr_warn("%s: ocram pool unavailable!\n", __func__);
 		ret = -ENODEV;
-		goto put_node;
+		goto put_device;
 	}
 
 	ocram_base = gen_pool_alloc(ocram_pool, size);
 	if (!ocram_base) {
 		pr_warn("%s: unable to alloc ocram!\n", __func__);
 		ret = -ENOMEM;
-		goto put_node;
+		goto put_device;
 	}
 
 	phys = gen_pool_virt_to_phys(ocram_pool, ocram_base);
@@ -312,6 +312,8 @@ static int __init imx_suspend_alloc_ocram(
 	if (virt_out)
 		*virt_out = virt;
 
+put_device:
+	put_device(&pdev->dev);
 put_node:
 	of_node_put(node);
 
diff --git a/arch/arm/mach-imx/pm-imx6.c b/arch/arm/mach-imx/pm-imx6.c
index 1c0ecad3620e..baf3b47601af 100644
--- a/arch/arm/mach-imx/pm-imx6.c
+++ b/arch/arm/mach-imx/pm-imx6.c
@@ -493,14 +493,14 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata)
 	if (!ocram_pool) {
 		pr_warn("%s: ocram pool unavailable!\n", __func__);
 		ret = -ENODEV;
-		goto put_node;
+		goto put_device;
 	}
 
 	ocram_base = gen_pool_alloc(ocram_pool, MX6Q_SUSPEND_OCRAM_SIZE);
 	if (!ocram_base) {
 		pr_warn("%s: unable to alloc ocram!\n", __func__);
 		ret = -ENOMEM;
-		goto put_node;
+		goto put_device;
 	}
 
 	ocram_pbase = gen_pool_virt_to_phys(ocram_pool, ocram_base);
@@ -523,7 +523,7 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata)
 	ret = imx6_pm_get_base(&pm_info->mmdc_base, socdata->mmdc_compat);
 	if (ret) {
 		pr_warn("%s: failed to get mmdc base %d!\n", __func__, ret);
-		goto put_node;
+		goto put_device;
 	}
 
 	ret = imx6_pm_get_base(&pm_info->src_base, socdata->src_compat);
@@ -570,7 +570,7 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata)
 		&imx6_suspend,
 		MX6Q_SUSPEND_OCRAM_SIZE - sizeof(*pm_info));
 
-	goto put_node;
+	goto put_device;
 
 pl310_cache_map_failed:
 	iounmap(pm_info->gpc_base.vbase);
@@ -580,6 +580,8 @@ iomuxc_map_failed:
 	iounmap(pm_info->src_base.vbase);
 src_map_failed:
 	iounmap(pm_info->mmdc_base.vbase);
+put_device:
+	put_device(&pdev->dev);
 put_node:
 	of_node_put(node);
 
diff --git a/arch/arm/mach-imx/resume-imx6.S b/arch/arm/mach-imx/resume-imx6.S
new file mode 100644
index 000000000000..5bd1ba7ef15b
--- /dev/null
+++ b/arch/arm/mach-imx/resume-imx6.S
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright 2014 Freescale Semiconductor, Inc.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/asm-offsets.h>
+#include <asm/hardware/cache-l2x0.h>
+#include "hardware.h"
+
+/*
+ * The following code must assume it is running from physical address
+ * where absolute virtual addresses to the data section have to be
+ * turned into relative ones.
+ */
+
+ENTRY(v7_cpu_resume)
+	bl	v7_invalidate_l1
+#ifdef CONFIG_CACHE_L2X0
+	bl	l2c310_early_resume
+#endif
+	b	cpu_resume
+ENDPROC(v7_cpu_resume)
diff --git a/arch/arm/mach-imx/suspend-imx6.S b/arch/arm/mach-imx/suspend-imx6.S
index 062391ff13da..1eabf2d2834b 100644
--- a/arch/arm/mach-imx/suspend-imx6.S
+++ b/arch/arm/mach-imx/suspend-imx6.S
@@ -327,17 +327,3 @@ resume:
 
 	ret	lr
 ENDPROC(imx6_suspend)
-
-/*
- * The following code must assume it is running from physical address
- * where absolute virtual addresses to the data section have to be
- * turned into relative ones.
- */
-
-ENTRY(v7_cpu_resume)
-	bl	v7_invalidate_l1
-#ifdef CONFIG_CACHE_L2X0
-	bl	l2c310_early_resume
-#endif
-	b	cpu_resume
-ENDPROC(v7_cpu_resume)
diff --git a/arch/arm/mach-integrator/Kconfig b/arch/arm/mach-integrator/Kconfig
index 982eabc36163..2406cab73835 100644
--- a/arch/arm/mach-integrator/Kconfig
+++ b/arch/arm/mach-integrator/Kconfig
@@ -4,6 +4,8 @@ menuconfig ARCH_INTEGRATOR
 	depends on ARCH_MULTI_V4T || ARCH_MULTI_V5 || ARCH_MULTI_V6
 	select ARM_AMBA
 	select COMMON_CLK_VERSATILE
+	select CMA
+	select DMA_CMA
 	select HAVE_TCM
 	select ICST
 	select MFD_SYSCON
@@ -35,14 +37,13 @@ config INTEGRATOR_IMPD1
 	select ARM_VIC
 	select GPIO_PL061
 	select GPIOLIB
+	select REGULATOR
+	select REGULATOR_FIXED_VOLTAGE
 	help
 	  The IM-PD1 is an add-on logic module for the Integrator which
 	  allows ARM(R) Ltd PrimeCells to be developed and evaluated.
 	  The IM-PD1 can be found on the Integrator/PP2 platform.
 
-	  To compile this driver as a module, choose M here: the
-	  module will be called impd1.
-
 config INTEGRATOR_CM7TDMI
 	bool "Integrator/CM7TDMI core module"
 	depends on ARCH_INTEGRATOR_AP
diff --git a/arch/arm/mach-npcm/Kconfig b/arch/arm/mach-npcm/Kconfig
index 880bc2a5cada..7f7002dc2b21 100644
--- a/arch/arm/mach-npcm/Kconfig
+++ b/arch/arm/mach-npcm/Kconfig
@@ -11,7 +11,7 @@ config ARCH_NPCM7XX
 	depends on ARCH_MULTI_V7
 	select PINCTRL_NPCM7XX
 	select NPCM7XX_TIMER
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select CACHE_L2X0
 	select ARM_GIC
 	select HAVE_ARM_TWD if SMP
diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c
index 439e143cad7b..46012ca812f4 100644
--- a/arch/arm/mach-omap2/display.c
+++ b/arch/arm/mach-omap2/display.c
@@ -265,6 +265,7 @@ static int __init omapdss_init_of(void)
 	r = of_platform_populate(node, NULL, NULL, &pdev->dev);
 	if (r) {
 		pr_err("Unable to populate DSS submodule devices\n");
+		put_device(&pdev->dev);
 		return r;
 	}
 
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index e0350476feaa..500e694669e7 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -3565,7 +3565,7 @@ static const struct omap_hwmod_reset dra7_reset_quirks[] = {
 };
 
 static const struct omap_hwmod_reset omap_reset_quirks[] = {
-	{ .match = "dss", .len = 3, .reset = omap_dss_reset, },
+	{ .match = "dss_core", .len = 8, .reset = omap_dss_reset, },
 	{ .match = "hdq1w", .len = 5, .reset = omap_hdq1w_reset, },
 	{ .match = "i2c", .len = 3, .reset = omap_i2c_reset, },
 	{ .match = "wd_timer", .len = 8, .reset = omap2_wd_timer_reset, },
diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c
index 7e018f674fb0..f53c4a331856 100644
--- a/arch/arm/mach-omap2/pdata-quirks.c
+++ b/arch/arm/mach-omap2/pdata-quirks.c
@@ -260,14 +260,6 @@ static void __init am3517_evm_legacy_init(void)
 	am35xx_emac_reset();
 }
 
-static struct platform_device omap3_rom_rng_device = {
-	.name		= "omap3-rom-rng",
-	.id		= -1,
-	.dev	= {
-		.platform_data	= rx51_secure_rng_call,
-	},
-};
-
 static void __init nokia_n900_legacy_init(void)
 {
 	hsmmc2_internal_input_clk();
@@ -283,9 +275,6 @@ static void __init nokia_n900_legacy_init(void)
 			pr_warn("RX-51: Not enabling ARM errata 430973 workaround\n");
 			pr_warn("Thumb binaries may crash randomly without this workaround\n");
 		}
-
-		pr_info("RX-51: Registering OMAP3 HWRNG device\n");
-		platform_device_register(&omap3_rom_rng_device);
 	}
 }
 
@@ -463,6 +452,7 @@ static struct of_dev_auxdata omap_auxdata_lookup[] = {
 	OF_DEV_AUXDATA("ti,davinci_mdio", 0x5c030000, "davinci_mdio.0", NULL),
 	OF_DEV_AUXDATA("ti,am3517-emac", 0x5c000000, "davinci_emac.0",
 		       &am35xx_emac_pdata),
+	OF_DEV_AUXDATA("nokia,n900-rom-rng", 0, NULL, rx51_secure_rng_call),
 	/* McBSP modules with sidetone core */
 #if IS_ENABLED(CONFIG_SND_SOC_OMAP_MCBSP)
 	OF_DEV_AUXDATA("ti,omap3-mcbsp", 0x49022000, "49022000.mcbsp", &mcbsp_pdata),
diff --git a/arch/arm/mach-socfpga/pm.c b/arch/arm/mach-socfpga/pm.c
index 6ed887cf8dc9..365c0428b21b 100644
--- a/arch/arm/mach-socfpga/pm.c
+++ b/arch/arm/mach-socfpga/pm.c
@@ -49,14 +49,14 @@ static int socfpga_setup_ocram_self_refresh(void)
 	if (!ocram_pool) {
 		pr_warn("%s: ocram pool unavailable!\n", __func__);
 		ret = -ENODEV;
-		goto put_node;
+		goto put_device;
 	}
 
 	ocram_base = gen_pool_alloc(ocram_pool, socfpga_sdram_self_refresh_sz);
 	if (!ocram_base) {
 		pr_warn("%s: unable to alloc ocram!\n", __func__);
 		ret = -ENOMEM;
-		goto put_node;
+		goto put_device;
 	}
 
 	ocram_pbase = gen_pool_virt_to_phys(ocram_pool, ocram_base);
@@ -67,7 +67,7 @@ static int socfpga_setup_ocram_self_refresh(void)
 	if (!suspend_ocram_base) {
 		pr_warn("%s: __arm_ioremap_exec failed!\n", __func__);
 		ret = -ENOMEM;
-		goto put_node;
+		goto put_device;
 	}
 
 	/* Copy the code that puts DDR in self refresh to ocram */
@@ -81,6 +81,8 @@ static int socfpga_setup_ocram_self_refresh(void)
 	if (!socfpga_sdram_self_refresh_in_ocram)
 		ret = -EFAULT;
 
+put_device:
+	put_device(&pdev->dev);
 put_node:
 	of_node_put(np);
 
diff --git a/arch/arm/mach-tegra/sleep-tegra30.S b/arch/arm/mach-tegra/sleep-tegra30.S
index b408fa56eb89..6922dd8d3e2d 100644
--- a/arch/arm/mach-tegra/sleep-tegra30.S
+++ b/arch/arm/mach-tegra/sleep-tegra30.S
@@ -370,6 +370,14 @@ _pll_m_c_x_done:
 	pll_locked r1, r0, CLK_RESET_PLLC_BASE
 	pll_locked r1, r0, CLK_RESET_PLLX_BASE
 
+	tegra_get_soc_id TEGRA_APB_MISC_BASE, r1
+	cmp	r1, #TEGRA30
+	beq	1f
+	ldr	r1, [r0, #CLK_RESET_PLLP_BASE]
+	bic	r1, r1, #(1<<31)	@ disable PllP bypass
+	str	r1, [r0, #CLK_RESET_PLLP_BASE]
+1:
+
 	mov32	r7, TEGRA_TMRUS_BASE
 	ldr	r1, [r7]
 	add	r1, r1, #LOCK_DELAY
@@ -630,7 +638,10 @@ tegra30_switch_cpu_to_clk32k:
 	str	r0, [r4, #PMC_PLLP_WB0_OVERRIDE]
 
 	/* disable PLLP, PLLA, PLLC and PLLX */
+	tegra_get_soc_id TEGRA_APB_MISC_BASE, r1
+	cmp	r1, #TEGRA30
 	ldr	r0, [r5, #CLK_RESET_PLLP_BASE]
+	orrne	r0, r0, #(1 << 31)	@ enable PllP bypass on fast cluster
 	bic	r0, r0, #(1 << 30)
 	str	r0, [r5, #CLK_RESET_PLLP_BASE]
 	ldr	r0, [r5, #CLK_RESET_PLLA_BASE]
diff --git a/arch/arm/mach-tegra/tegra.c b/arch/arm/mach-tegra/tegra.c
index e512e606eabd..5ea3421fa1e8 100644
--- a/arch/arm/mach-tegra/tegra.c
+++ b/arch/arm/mach-tegra/tegra.c
@@ -106,8 +106,8 @@ static const char * const tegra_dt_board_compat[] = {
 };
 
 DT_MACHINE_START(TEGRA_DT, "NVIDIA Tegra SoC (Flattened Device Tree)")
-	.l2c_aux_val	= 0x3c400001,
-	.l2c_aux_mask	= 0xc20fc3fe,
+	.l2c_aux_val	= 0x3c400000,
+	.l2c_aux_mask	= 0xc20fc3ff,
 	.smp		= smp_ops(tegra_smp_ops),
 	.map_io		= tegra_map_common_io,
 	.init_early	= tegra_init_early,
diff --git a/arch/arm/mach-vexpress/spc.c b/arch/arm/mach-vexpress/spc.c
index 0f5381d13494..55bbbc3b328f 100644
--- a/arch/arm/mach-vexpress/spc.c
+++ b/arch/arm/mach-vexpress/spc.c
@@ -551,8 +551,9 @@ static struct clk *ve_spc_clk_register(struct device *cpu_dev)
 
 static int __init ve_spc_clk_init(void)
 {
-	int cpu;
+	int cpu, cluster;
 	struct clk *clk;
+	bool init_opp_table[MAX_CLUSTERS] = { false };
 
 	if (!info)
 		return 0; /* Continue only if SPC is initialised */
@@ -578,8 +579,17 @@ static int __init ve_spc_clk_init(void)
 			continue;
 		}
 
+		cluster = topology_physical_package_id(cpu_dev->id);
+		if (init_opp_table[cluster])
+			continue;
+
 		if (ve_init_opp_table(cpu_dev))
 			pr_warn("failed to initialise cpu%d opp table\n", cpu);
+		else if (dev_pm_opp_set_sharing_cpus(cpu_dev,
+			 topology_core_cpumask(cpu_dev->id)))
+			pr_warn("failed to mark OPPs shared for cpu%d\n", cpu);
+		else
+			init_opp_table[cluster] = true;
 	}
 
 	platform_device_register_simple("vexpress-spc-cpufreq", -1, NULL, 0);
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index 5461d589a1e2..60ac7c5999a9 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -5,6 +5,7 @@
  *  VMA_VM_FLAGS
  *  VM_EXEC
  */
+#include <linux/const.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 
@@ -30,7 +31,7 @@
  * act_mm - get current->active_mm
  */
 	.macro	act_mm, rd
-	bic	\rd, sp, #8128
+	bic	\rd, sp, #(THREAD_SIZE - 1) & ~63
 	bic	\rd, \rd, #63
 	ldr	\rd, [\rd, #TI_TASK]
 	.if (TSK_ACTIVE_MM > IMM12_MASK)
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index adff54c312bf..6484d0fc4c93 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -927,7 +927,11 @@ static inline void emit_a32_rsh_i64(const s8 dst[],
 	rd = arm_bpf_get_reg64(dst, tmp, ctx);
 
 	/* Do LSR operation */
-	if (val < 32) {
+	if (val == 0) {
+		/* An immediate value of 0 encodes a shift amount of 32
+		 * for LSR. To shift by 0, don't do anything.
+		 */
+	} else if (val < 32) {
 		emit(ARM_MOV_SI(tmp2[1], rd[1], SRTYPE_LSR, val), ctx);
 		emit(ARM_ORR_SI(rd[1], tmp2[1], rd[0], SRTYPE_ASL, 32 - val), ctx);
 		emit(ARM_MOV_SI(rd[0], rd[0], SRTYPE_LSR, val), ctx);
@@ -953,7 +957,11 @@ static inline void emit_a32_arsh_i64(const s8 dst[],
 	rd = arm_bpf_get_reg64(dst, tmp, ctx);
 
 	/* Do ARSH operation */
-	if (val < 32) {
+	if (val == 0) {
+		/* An immediate value of 0 encodes a shift amount of 32
+		 * for ASR. To shift by 0, don't do anything.
+		 */
+	} else if (val < 32) {
 		emit(ARM_MOV_SI(tmp2[1], rd[1], SRTYPE_LSR, val), ctx);
 		emit(ARM_ORR_SI(rd[1], tmp2[1], rd[0], SRTYPE_ASL, 32 - val), ctx);
 		emit(ARM_MOV_SI(rd[0], rd[0], SRTYPE_ASR, val), ctx);
@@ -990,21 +998,35 @@ static inline void emit_a32_mul_r64(const s8 dst[], const s8 src[],
 	arm_bpf_put_reg32(dst_hi, rd[0], ctx);
 }
 
+static bool is_ldst_imm(s16 off, const u8 size)
+{
+	s16 off_max = 0;
+
+	switch (size) {
+	case BPF_B:
+	case BPF_W:
+		off_max = 0xfff;
+		break;
+	case BPF_H:
+		off_max = 0xff;
+		break;
+	case BPF_DW:
+		/* Need to make sure off+4 does not overflow. */
+		off_max = 0xfff - 4;
+		break;
+	}
+	return -off_max <= off && off <= off_max;
+}
+
 /* *(size *)(dst + off) = src */
 static inline void emit_str_r(const s8 dst, const s8 src[],
-			      s32 off, struct jit_ctx *ctx, const u8 sz){
+			      s16 off, struct jit_ctx *ctx, const u8 sz){
 	const s8 *tmp = bpf2a32[TMP_REG_1];
-	s32 off_max;
 	s8 rd;
 
 	rd = arm_bpf_get_reg32(dst, tmp[1], ctx);
 
-	if (sz == BPF_H)
-		off_max = 0xff;
-	else
-		off_max = 0xfff;
-
-	if (off < 0 || off > off_max) {
+	if (!is_ldst_imm(off, sz)) {
 		emit_a32_mov_i(tmp[0], off, ctx);
 		emit(ARM_ADD_R(tmp[0], tmp[0], rd), ctx);
 		rd = tmp[0];
@@ -1033,18 +1055,12 @@ static inline void emit_str_r(const s8 dst, const s8 src[],
 
 /* dst = *(size*)(src + off) */
 static inline void emit_ldx_r(const s8 dst[], const s8 src,
-			      s32 off, struct jit_ctx *ctx, const u8 sz){
+			      s16 off, struct jit_ctx *ctx, const u8 sz){
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	const s8 *rd = is_stacked(dst_lo) ? tmp : dst;
 	s8 rm = src;
-	s32 off_max;
-
-	if (sz == BPF_H)
-		off_max = 0xff;
-	else
-		off_max = 0xfff;
 
-	if (off < 0 || off > off_max) {
+	if (!is_ldst_imm(off, sz)) {
 		emit_a32_mov_i(tmp[0], off, ctx);
 		emit(ARM_ADD_R(tmp[0], tmp[0], src), ctx);
 		rm = tmp[0];
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 0c2270ebcf30..5a785e62d882 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -539,6 +539,22 @@ config ARM64_ERRATUM_1463225
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_1542419
+	bool "Neoverse-N1: workaround mis-ordering of instruction fetches"
+	default y
+	help
+	  This option adds a workaround for ARM Neoverse-N1 erratum
+	  1542419.
+
+	  Affected Neoverse-N1 cores could execute a stale instruction when
+	  modified by another CPU. The workaround depends on a firmware
+	  counterpart.
+
+	  Workaround the issue by hiding the DIC feature from EL0. This
+	  forces user-space to perform cache maintenance.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_22375
 	bool "Cavium erratum 22375, 24313"
 	default y
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index e9d2e578cbe6..20bd72e1b8fe 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -67,6 +67,10 @@ stack_protector_prepare: prepare0
 					include/generated/asm-offsets.h))
 endif
 
+# Ensure that if the compiler supports branch protection we default it
+# off.
+KBUILD_CFLAGS += $(call cc-option,-mbranch-protection=none)
+
 ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
 KBUILD_CPPFLAGS	+= -mbig-endian
 CHECKFLAGS	+= -D__AARCH64EB__
diff --git a/arch/arm64/boot/Makefile b/arch/arm64/boot/Makefile
index 1f012c506434..cd3414898d10 100644
--- a/arch/arm64/boot/Makefile
+++ b/arch/arm64/boot/Makefile
@@ -16,7 +16,7 @@
 
 OBJCOPYFLAGS_Image :=-O binary -R .note -R .note.gnu.build-id -R .comment -S
 
-targets := Image Image.gz
+targets := Image Image.bz2 Image.gz Image.lz4 Image.lzma Image.lzo
 
 $(obj)/Image: vmlinux FORCE
 	$(call if_changed,objcopy)
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-olinuxino.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-olinuxino.dts
index 01a9a52edae4..393c1948a495 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-olinuxino.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-olinuxino.dts
@@ -140,7 +140,7 @@
 &mmc1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc1_pins>;
-	vmmc-supply = <&reg_aldo2>;
+	vmmc-supply = <&reg_dcdc1>;
 	vqmmc-supply = <&reg_dldo4>;
 	mmc-pwrseq = <&wifi_pwrseq>;
 	bus-width = <4>;
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pinebook.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pinebook.dts
index 2b6345db7dc0..78c82a665c84 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pinebook.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pinebook.dts
@@ -104,6 +104,7 @@
 
 &ehci0 {
 	phys = <&usbphy 0>;
+	phy-names = "usb";
 	status = "okay";
 };
 
@@ -150,6 +151,7 @@
 
 &ohci0 {
 	phys = <&usbphy 0>;
+	phy-names = "usb";
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
index 6eb66f7b8a90..822f821e9d65 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
@@ -227,11 +227,11 @@
 
 			display_clocks: clock@0 {
 				compatible = "allwinner,sun50i-a64-de2-clk";
-				reg = <0x0 0x100000>;
-				clocks = <&ccu CLK_DE>,
-					 <&ccu CLK_BUS_DE>;
-				clock-names = "mod",
-					      "bus";
+				reg = <0x0 0x10000>;
+				clocks = <&ccu CLK_BUS_DE>,
+					 <&ccu CLK_DE>;
+				clock-names = "bus",
+					      "mod";
 				resets = <&ccu RST_BUS_DE>;
 				#clock-cells = <1>;
 				#reset-cells = <1>;
@@ -553,6 +553,7 @@
 			resets = <&ccu RST_BUS_OHCI1>,
 				 <&ccu RST_BUS_EHCI1>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -564,6 +565,7 @@
 				 <&ccu CLK_USB_OHCI1>;
 			resets = <&ccu RST_BUS_OHCI1>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi
index f002a496d7cb..eaf8f83794fd 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi
@@ -54,21 +54,21 @@
 			enable-method = "psci";
 		};
 
-		cpu@1 {
+		cpu1: cpu@1 {
 			compatible = "arm,cortex-a53";
 			device_type = "cpu";
 			reg = <1>;
 			enable-method = "psci";
 		};
 
-		cpu@2 {
+		cpu2: cpu@2 {
 			compatible = "arm,cortex-a53";
 			device_type = "cpu";
 			reg = <2>;
 			enable-method = "psci";
 		};
 
-		cpu@3 {
+		cpu3: cpu@3 {
 			compatible = "arm,cortex-a53";
 			device_type = "cpu";
 			reg = <3>;
@@ -76,6 +76,15 @@
 		};
 	};
 
+	pmu {
+		compatible = "arm,cortex-a53-pmu";
+		interrupts = <GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 117 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 118 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 119 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-affinity = <&cpu0>, <&cpu1>, <&cpu2>, <&cpu3>;
+	};
+
 	psci {
 		compatible = "arm,psci-0.2";
 		method = "smc";
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi
index 16c5c3d0fd81..1d6c8566fd5e 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi
@@ -78,6 +78,15 @@
 		clock-output-names = "osc32k";
 	};
 
+	pmu {
+		compatible = "arm,cortex-a53-pmu";
+		interrupts = <GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-affinity = <&cpu0>, <&cpu1>, <&cpu2>, <&cpu3>;
+	};
+
 	psci {
 		compatible = "arm,psci-0.2";
 		method = "smc";
@@ -456,6 +465,7 @@
 			resets = <&ccu RST_BUS_OHCI3>,
 				 <&ccu RST_BUS_EHCI3>;
 			phys = <&usb2phy 3>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -467,6 +477,7 @@
 				 <&ccu CLK_USB_OHCI3>;
 			resets = <&ccu RST_BUS_OHCI3>;
 			phys = <&usb2phy 3>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
index 470dcfd9de91..3df00f987e25 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
@@ -61,10 +61,10 @@
 
 	pmu {
 		compatible = "arm,armv8-pmuv3";
-		interrupts = <0 120 8>,
-			     <0 121 8>,
-			     <0 122 8>,
-			     <0 123 8>;
+		interrupts = <0 170 4>,
+			     <0 171 4>,
+			     <0 172 4>,
+			     <0 173 4>;
 		interrupt-affinity = <&cpu0>,
 				     <&cpu1>,
 				     <&cpu2>,
diff --git a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
index 34704fecf756..0b31c6b940a1 100644
--- a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
@@ -1141,7 +1141,7 @@
 
 			toddr_a: audio-controller@100 {
 				compatible = "amlogic,axg-toddr";
-				reg = <0x0 0x100 0x0 0x1c>;
+				reg = <0x0 0x100 0x0 0x2c>;
 				#sound-dai-cells = <0>;
 				sound-name-prefix = "TODDR_A";
 				interrupts = <GIC_SPI 84 IRQ_TYPE_EDGE_RISING>;
@@ -1152,7 +1152,7 @@
 
 			toddr_b: audio-controller@140 {
 				compatible = "amlogic,axg-toddr";
-				reg = <0x0 0x140 0x0 0x1c>;
+				reg = <0x0 0x140 0x0 0x2c>;
 				#sound-dai-cells = <0>;
 				sound-name-prefix = "TODDR_B";
 				interrupts = <GIC_SPI 85 IRQ_TYPE_EDGE_RISING>;
@@ -1163,7 +1163,7 @@
 
 			toddr_c: audio-controller@180 {
 				compatible = "amlogic,axg-toddr";
-				reg = <0x0 0x180 0x0 0x1c>;
+				reg = <0x0 0x180 0x0 0x2c>;
 				#sound-dai-cells = <0>;
 				sound-name-prefix = "TODDR_C";
 				interrupts = <GIC_SPI 86 IRQ_TYPE_EDGE_RISING>;
@@ -1174,7 +1174,7 @@
 
 			frddr_a: audio-controller@1c0 {
 				compatible = "amlogic,axg-frddr";
-				reg = <0x0 0x1c0 0x0 0x1c>;
+				reg = <0x0 0x1c0 0x0 0x2c>;
 				#sound-dai-cells = <0>;
 				sound-name-prefix = "FRDDR_A";
 				interrupts = <GIC_SPI 88 IRQ_TYPE_EDGE_RISING>;
@@ -1185,7 +1185,7 @@
 
 			frddr_b: audio-controller@200 {
 				compatible = "amlogic,axg-frddr";
-				reg = <0x0 0x200 0x0 0x1c>;
+				reg = <0x0 0x200 0x0 0x2c>;
 				#sound-dai-cells = <0>;
 				sound-name-prefix = "FRDDR_B";
 				interrupts = <GIC_SPI 89 IRQ_TYPE_EDGE_RISING>;
@@ -1196,7 +1196,7 @@
 
 			frddr_c: audio-controller@240 {
 				compatible = "amlogic,axg-frddr";
-				reg = <0x0 0x240 0x0 0x1c>;
+				reg = <0x0 0x240 0x0 0x2c>;
 				#sound-dai-cells = <0>;
 				sound-name-prefix = "FRDDR_C";
 				interrupts = <GIC_SPI 90 IRQ_TYPE_EDGE_RISING>;
@@ -1707,18 +1707,18 @@
 		};
 
 		sram: sram@fffc0000 {
-			compatible = "amlogic,meson-axg-sram", "mmio-sram";
+			compatible = "mmio-sram";
 			reg = <0x0 0xfffc0000 0x0 0x20000>;
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0 0x0 0xfffc0000 0x20000>;
 
-			cpu_scp_lpri: scp-shmem@13000 {
+			cpu_scp_lpri: scp-sram@13000 {
 				compatible = "amlogic,meson-axg-scp-shmem";
 				reg = <0x13000 0x400>;
 			};
 
-			cpu_scp_hpri: scp-shmem@13400 {
+			cpu_scp_hpri: scp-sram@13400 {
 				compatible = "amlogic,meson-axg-scp-shmem";
 				reg = <0x13400 0x400>;
 			};
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12a.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12a.dtsi
index 4c92c197aeb8..85b3ba605a23 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12a.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-g12a.dtsi
@@ -589,7 +589,7 @@
 				reg = <0x0 0xff400000 0x0 0x40000>;
 				interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clkc CLKID_USB1_DDR_BRIDGE>;
-				clock-names = "ddr";
+				clock-names = "otg";
 				phys = <&usb2_phy1>;
 				phy-names = "usb2-phy";
 				dr_mode = "peripheral";
@@ -605,6 +605,7 @@
 				dr_mode = "host";
 				snps,dis_u2_susphy_quirk;
 				snps,quirk-frame-length-adjustment;
+				snps,parkmode-disable-ss-quirk;
 			};
 		};
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
index 6772709b9e19..0e7e844d0508 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
@@ -345,20 +345,20 @@
 		};
 
 		sram: sram@c8000000 {
-			compatible = "amlogic,meson-gx-sram", "amlogic,meson-gxbb-sram", "mmio-sram";
+			compatible = "mmio-sram";
 			reg = <0x0 0xc8000000 0x0 0x14000>;
 
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0 0x0 0xc8000000 0x14000>;
 
-			cpu_scp_lpri: scp-shmem@0 {
-				compatible = "amlogic,meson-gx-scp-shmem", "amlogic,meson-gxbb-scp-shmem";
+			cpu_scp_lpri: scp-sram@0 {
+				compatible = "amlogic,meson-gxbb-scp-shmem";
 				reg = <0x13000 0x400>;
 			};
 
-			cpu_scp_hpri: scp-shmem@200 {
-				compatible = "amlogic,meson-gx-scp-shmem", "amlogic,meson-gxbb-scp-shmem";
+			cpu_scp_hpri: scp-sram@200 {
+				compatible = "amlogic,meson-gxbb-scp-shmem";
 				reg = <0x13400 0x400>;
 			};
 		};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
index 1cc9dc68ef00..52517f9520b5 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
@@ -291,7 +291,7 @@
 };
 
 &usb0_phy {
-	status = "okay";
+	status = "disabled";
 	phy-supply = <&usb_otg_pwr>;
 };
 
@@ -301,7 +301,7 @@
 };
 
 &usb0 {
-	status = "okay";
+	status = "disabled";
 };
 
 &usb1 {
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-libretech-ac.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-libretech-ac.dts
index 82b1c4851147..e034bbff8e66 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-libretech-ac.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-libretech-ac.dts
@@ -9,7 +9,7 @@
 
 #include <dt-bindings/input/input.h>
 
-#include "meson-gxl-s905x.dtsi"
+#include "meson-gxl-s805x.dtsi"
 
 / {
 	compatible = "libretech,aml-s805x-ac", "amlogic,s805x",
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts
index 70433e023fda..9abfc2512b69 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts
@@ -9,7 +9,7 @@
 
 #include <dt-bindings/input/input.h>
 
-#include "meson-gxl-s905x.dtsi"
+#include "meson-gxl-s805x.dtsi"
 
 / {
 	compatible = "amlogic,p241", "amlogic,s805x", "amlogic,meson-gxl";
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x.dtsi
new file mode 100644
index 000000000000..f9d705648426
--- /dev/null
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x.dtsi
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2020 BayLibre SAS
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ */
+
+#include "meson-gxl-s905x.dtsi"
+
+/ {
+	compatible = "amlogic,s805x", "amlogic,meson-gxl";
+};
+
+/* The S805X Package doesn't seem to handle the 744MHz OPP correctly */
+&mali {
+	assigned-clocks = <&clkc CLKID_MALI_0_SEL>,
+			  <&clkc CLKID_MALI_0>,
+			  <&clkc CLKID_MALI>; /* Glitch free mux */
+	assigned-clock-parents = <&clkc CLKID_FCLK_DIV3>,
+				 <0>, /* Do Nothing */
+				 <&clkc CLKID_MALI_0>;
+	assigned-clock-rates = <0>, /* Do Nothing */
+			       <666666666>,
+			       <0>; /* Do Nothing */
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts
index 5499e8de5c74..2ab7d8437462 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts
@@ -33,11 +33,9 @@
 
 	gpio-keys-polled {
 		compatible = "gpio-keys-polled";
-		#address-cells = <1>;
-		#size-cells = <0>;
 		poll-interval = <100>;
 
-		button@0 {
+		power-button {
 			label = "power";
 			linux,code = <KEY_POWER>;
 			gpios = <&gpio_ao GPIOAO_2 GPIO_ACTIVE_LOW>;
@@ -192,6 +190,9 @@
 	bluetooth {
 		compatible = "brcm,bcm43438-bt";
 		shutdown-gpios = <&gpio GPIOX_17 GPIO_ACTIVE_HIGH>;
+		max-speed = <2000000>;
+		clocks = <&wifi32k>;
+		clock-names = "lpo";
 	};
 };
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
index 3093ae421b17..f66a545aab51 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
@@ -291,6 +291,11 @@
 	};
 };
 
+&hwrng {
+	clocks = <&clkc CLKID_RNG0>;
+	clock-names = "core";
+};
+
 &i2c_A {
 	clocks = <&clkc CLKID_I2C>;
 };
diff --git a/arch/arm64/boot/dts/arm/foundation-v8-gicv2.dtsi b/arch/arm64/boot/dts/arm/foundation-v8-gicv2.dtsi
index 15fe81738e94..dfb23dfc0b0f 100644
--- a/arch/arm64/boot/dts/arm/foundation-v8-gicv2.dtsi
+++ b/arch/arm64/boot/dts/arm/foundation-v8-gicv2.dtsi
@@ -8,7 +8,7 @@
 	gic: interrupt-controller@2c001000 {
 		compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
 		#interrupt-cells = <3>;
-		#address-cells = <2>;
+		#address-cells = <1>;
 		interrupt-controller;
 		reg = <0x0 0x2c001000 0 0x1000>,
 		      <0x0 0x2c002000 0 0x2000>,
diff --git a/arch/arm64/boot/dts/arm/foundation-v8-gicv3.dtsi b/arch/arm64/boot/dts/arm/foundation-v8-gicv3.dtsi
index f2c75c756039..906f51935b36 100644
--- a/arch/arm64/boot/dts/arm/foundation-v8-gicv3.dtsi
+++ b/arch/arm64/boot/dts/arm/foundation-v8-gicv3.dtsi
@@ -8,9 +8,9 @@
 	gic: interrupt-controller@2f000000 {
 		compatible = "arm,gic-v3";
 		#interrupt-cells = <3>;
-		#address-cells = <2>;
-		#size-cells = <2>;
-		ranges;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x0 0x0 0x2f000000 0x100000>;
 		interrupt-controller;
 		reg =	<0x0 0x2f000000 0x0 0x10000>,
 			<0x0 0x2f100000 0x0 0x200000>,
@@ -22,7 +22,7 @@
 		its: its@2f020000 {
 			compatible = "arm,gic-v3-its";
 			msi-controller;
-			reg = <0x0 0x2f020000 0x0 0x20000>;
+			reg = <0x20000 0x20000>;
 		};
 	};
 };
diff --git a/arch/arm64/boot/dts/arm/foundation-v8.dtsi b/arch/arm64/boot/dts/arm/foundation-v8.dtsi
index 3f78373f708a..05d1657170b4 100644
--- a/arch/arm64/boot/dts/arm/foundation-v8.dtsi
+++ b/arch/arm64/boot/dts/arm/foundation-v8.dtsi
@@ -107,51 +107,51 @@
 
 		#interrupt-cells = <1>;
 		interrupt-map-mask = <0 0 63>;
-		interrupt-map = <0 0  0 &gic 0 0 GIC_SPI  0 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0  1 &gic 0 0 GIC_SPI  1 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0  2 &gic 0 0 GIC_SPI  2 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0  3 &gic 0 0 GIC_SPI  3 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0  4 &gic 0 0 GIC_SPI  4 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0  5 &gic 0 0 GIC_SPI  5 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0  6 &gic 0 0 GIC_SPI  6 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0  7 &gic 0 0 GIC_SPI  7 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0  8 &gic 0 0 GIC_SPI  8 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0  9 &gic 0 0 GIC_SPI  9 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 10 &gic 0 0 GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 11 &gic 0 0 GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 12 &gic 0 0 GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 13 &gic 0 0 GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 14 &gic 0 0 GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 15 &gic 0 0 GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 16 &gic 0 0 GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 17 &gic 0 0 GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 18 &gic 0 0 GIC_SPI 18 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 19 &gic 0 0 GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 20 &gic 0 0 GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 21 &gic 0 0 GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 22 &gic 0 0 GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 23 &gic 0 0 GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 24 &gic 0 0 GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 25 &gic 0 0 GIC_SPI 25 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 26 &gic 0 0 GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 27 &gic 0 0 GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 28 &gic 0 0 GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 29 &gic 0 0 GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 30 &gic 0 0 GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 31 &gic 0 0 GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 32 &gic 0 0 GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 33 &gic 0 0 GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 34 &gic 0 0 GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 35 &gic 0 0 GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 36 &gic 0 0 GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 37 &gic 0 0 GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 38 &gic 0 0 GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 39 &gic 0 0 GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 40 &gic 0 0 GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 41 &gic 0 0 GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 42 &gic 0 0 GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>;
-
-		ethernet@2,02000000 {
+		interrupt-map = <0 0  0 &gic 0 GIC_SPI  0 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  1 &gic 0 GIC_SPI  1 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  2 &gic 0 GIC_SPI  2 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  3 &gic 0 GIC_SPI  3 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  4 &gic 0 GIC_SPI  4 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  5 &gic 0 GIC_SPI  5 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  6 &gic 0 GIC_SPI  6 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  7 &gic 0 GIC_SPI  7 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  8 &gic 0 GIC_SPI  8 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  9 &gic 0 GIC_SPI  9 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 10 &gic 0 GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 11 &gic 0 GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 12 &gic 0 GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 13 &gic 0 GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 14 &gic 0 GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 15 &gic 0 GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 16 &gic 0 GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 17 &gic 0 GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 18 &gic 0 GIC_SPI 18 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 19 &gic 0 GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 20 &gic 0 GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 21 &gic 0 GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 22 &gic 0 GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 23 &gic 0 GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 24 &gic 0 GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 25 &gic 0 GIC_SPI 25 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 26 &gic 0 GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 27 &gic 0 GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 28 &gic 0 GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 29 &gic 0 GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 30 &gic 0 GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 31 &gic 0 GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 32 &gic 0 GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 33 &gic 0 GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 34 &gic 0 GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 35 &gic 0 GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 36 &gic 0 GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 37 &gic 0 GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 38 &gic 0 GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 39 &gic 0 GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 40 &gic 0 GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 41 &gic 0 GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 42 &gic 0 GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>;
+
+		ethernet@202000000 {
 			compatible = "smsc,lan91c111";
 			reg = <2 0x02000000 0x10000>;
 			interrupts = <15>;
@@ -178,7 +178,7 @@
 			clock-output-names = "v2m:refclk32khz";
 		};
 
-		iofpga@3,00000000 {
+		iofpga@300000000 {
 			compatible = "simple-bus";
 			#address-cells = <1>;
 			#size-cells = <1>;
diff --git a/arch/arm64/boot/dts/arm/fvp-base-revc.dts b/arch/arm64/boot/dts/arm/fvp-base-revc.dts
index 687707020ec1..10a7b5550681 100644
--- a/arch/arm64/boot/dts/arm/fvp-base-revc.dts
+++ b/arch/arm64/boot/dts/arm/fvp-base-revc.dts
@@ -161,10 +161,10 @@
 		bus-range = <0x0 0x1>;
 		reg = <0x0 0x40000000 0x0 0x10000000>;
 		ranges = <0x2000000 0x0 0x50000000 0x0 0x50000000 0x0 0x10000000>;
-		interrupt-map = <0 0 0 1 &gic GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 0 2 &gic GIC_SPI 169 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 0 3 &gic GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 0 4 &gic GIC_SPI 171 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-map = <0 0 0 1 &gic 0 0 GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 0 2 &gic 0 0 GIC_SPI 169 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 0 3 &gic 0 0 GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 0 4 &gic 0 0 GIC_SPI 171 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-map-mask = <0x0 0x0 0x0 0x7>;
 		msi-map = <0x0 &its 0x0 0x10000>;
 		iommu-map = <0x0 &smmu 0x0 0x10000>;
diff --git a/arch/arm64/boot/dts/arm/juno-base.dtsi b/arch/arm64/boot/dts/arm/juno-base.dtsi
index 7446e0dc154d..24e040970190 100644
--- a/arch/arm64/boot/dts/arm/juno-base.dtsi
+++ b/arch/arm64/boot/dts/arm/juno-base.dtsi
@@ -6,7 +6,6 @@
 	/*
 	 *  Devices shared by all Juno boards
 	 */
-	dma-ranges = <0 0 0 0 0x100 0>;
 
 	memtimer: timer@2a810000 {
 		compatible = "arm,armv7-timer-mem";
@@ -63,35 +62,35 @@
 		      <0x0 0x2c02f000 0 0x2000>,
 		      <0x0 0x2c04f000 0 0x2000>,
 		      <0x0 0x2c06f000 0 0x2000>;
-		#address-cells = <2>;
+		#address-cells = <1>;
 		#interrupt-cells = <3>;
-		#size-cells = <2>;
+		#size-cells = <1>;
 		interrupt-controller;
 		interrupts = <GIC_PPI 9 (GIC_CPU_MASK_SIMPLE(6) | IRQ_TYPE_LEVEL_HIGH)>;
-		ranges = <0 0 0 0x2c1c0000 0 0x40000>;
+		ranges = <0 0 0x2c1c0000 0x40000>;
 
 		v2m_0: v2m@0 {
 			compatible = "arm,gic-v2m-frame";
 			msi-controller;
-			reg = <0 0 0 0x10000>;
+			reg = <0 0x10000>;
 		};
 
 		v2m@10000 {
 			compatible = "arm,gic-v2m-frame";
 			msi-controller;
-			reg = <0 0x10000 0 0x10000>;
+			reg = <0x10000 0x10000>;
 		};
 
 		v2m@20000 {
 			compatible = "arm,gic-v2m-frame";
 			msi-controller;
-			reg = <0 0x20000 0 0x10000>;
+			reg = <0x20000 0x10000>;
 		};
 
 		v2m@30000 {
 			compatible = "arm,gic-v2m-frame";
 			msi-controller;
-			reg = <0 0x30000 0 0x10000>;
+			reg = <0x30000 0x10000>;
 		};
 	};
 
@@ -520,10 +519,10 @@
 			 <0x42000000 0x40 0x00000000 0x40 0x00000000 0x1 0x00000000>;
 		#interrupt-cells = <1>;
 		interrupt-map-mask = <0 0 0 7>;
-		interrupt-map = <0 0 0 1 &gic 0 0 GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 0 2 &gic 0 0 GIC_SPI 137 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 0 3 &gic 0 0 GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 0 4 &gic 0 0 GIC_SPI 139 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-map = <0 0 0 1 &gic 0 GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 0 2 &gic 0 GIC_SPI 137 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 0 3 &gic 0 GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 0 4 &gic 0 GIC_SPI 139 IRQ_TYPE_LEVEL_HIGH>;
 		msi-parent = <&v2m_0>;
 		status = "disabled";
 		iommu-map-mask = <0x0>;	/* RC has no means to output PCI RID */
@@ -787,19 +786,19 @@
 
 		#interrupt-cells = <1>;
 		interrupt-map-mask = <0 0 15>;
-		interrupt-map = <0 0  0 &gic 0 0 GIC_SPI  68 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0  1 &gic 0 0 GIC_SPI  69 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0  2 &gic 0 0 GIC_SPI  70 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0  3 &gic 0 0 GIC_SPI 160 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0  4 &gic 0 0 GIC_SPI 161 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0  5 &gic 0 0 GIC_SPI 162 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0  6 &gic 0 0 GIC_SPI 163 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0  7 &gic 0 0 GIC_SPI 164 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0  8 &gic 0 0 GIC_SPI 165 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0  9 &gic 0 0 GIC_SPI 166 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 10 &gic 0 0 GIC_SPI 167 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 11 &gic 0 0 GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>,
-				<0 0 12 &gic 0 0 GIC_SPI 169 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-map = <0 0  0 &gic 0 GIC_SPI  68 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  1 &gic 0 GIC_SPI  69 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  2 &gic 0 GIC_SPI  70 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  3 &gic 0 GIC_SPI 160 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  4 &gic 0 GIC_SPI 161 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  5 &gic 0 GIC_SPI 162 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  6 &gic 0 GIC_SPI 163 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  7 &gic 0 GIC_SPI 164 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  8 &gic 0 GIC_SPI 165 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  9 &gic 0 GIC_SPI 166 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 10 &gic 0 GIC_SPI 167 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 11 &gic 0 GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 12 &gic 0 GIC_SPI 169 IRQ_TYPE_LEVEL_HIGH>;
 	};
 
 	site2: tlx@60000000 {
@@ -809,6 +808,6 @@
 		ranges = <0 0 0x60000000 0x10000000>;
 		#interrupt-cells = <1>;
 		interrupt-map-mask = <0 0>;
-		interrupt-map = <0 0 &gic 0 0 GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-map = <0 0 &gic 0 GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>;
 	};
 };
diff --git a/arch/arm64/boot/dts/arm/juno-clocks.dtsi b/arch/arm64/boot/dts/arm/juno-clocks.dtsi
index e5e265dfa902..2870b5eeb198 100644
--- a/arch/arm64/boot/dts/arm/juno-clocks.dtsi
+++ b/arch/arm64/boot/dts/arm/juno-clocks.dtsi
@@ -8,10 +8,10 @@
  */
 / {
 	/* SoC fixed clocks */
-	soc_uartclk: refclk7273800hz {
+	soc_uartclk: refclk7372800hz {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
-		clock-frequency = <7273800>;
+		clock-frequency = <7372800>;
 		clock-output-names = "juno:uartclk";
 	};
 
diff --git a/arch/arm64/boot/dts/arm/juno-motherboard.dtsi b/arch/arm64/boot/dts/arm/juno-motherboard.dtsi
index 1792b074e9a3..cad3b16dba24 100644
--- a/arch/arm64/boot/dts/arm/juno-motherboard.dtsi
+++ b/arch/arm64/boot/dts/arm/juno-motherboard.dtsi
@@ -103,7 +103,7 @@
 				};
 			};
 
-			flash@0,00000000 {
+			flash@0 {
 				/* 2 * 32MiB NOR Flash memory mounted on CS0 */
 				compatible = "arm,vexpress-flash", "cfi-flash";
 				linux,part-probe = "afs";
@@ -118,7 +118,7 @@
 				status = "disabled";
 			};
 
-			ethernet@2,00000000 {
+			ethernet@200000000 {
 				compatible = "smsc,lan9118", "smsc,lan9115";
 				reg = <2 0x00000000 0x10000>;
 				interrupts = <3>;
@@ -131,7 +131,7 @@
 				vddvario-supply = <&mb_fixed_3v3>;
 			};
 
-			iofpga@3,00000000 {
+			iofpga@300000000 {
 				compatible = "simple-bus";
 				#address-cells = <1>;
 				#size-cells = <1>;
diff --git a/arch/arm64/boot/dts/arm/rtsm_ve-motherboard-rs2.dtsi b/arch/arm64/boot/dts/arm/rtsm_ve-motherboard-rs2.dtsi
index 57b0b9d7f3fa..29e6962c70bd 100644
--- a/arch/arm64/boot/dts/arm/rtsm_ve-motherboard-rs2.dtsi
+++ b/arch/arm64/boot/dts/arm/rtsm_ve-motherboard-rs2.dtsi
@@ -9,7 +9,7 @@
 		motherboard {
 			arm,v2m-memory-map = "rs2";
 
-			iofpga@3,00000000 {
+			iofpga@300000000 {
 				virtio-p9@140000 {
 					compatible = "virtio,mmio";
 					reg = <0x140000 0x200>;
diff --git a/arch/arm64/boot/dts/arm/rtsm_ve-motherboard.dtsi b/arch/arm64/boot/dts/arm/rtsm_ve-motherboard.dtsi
index 454cf6c44c49..768e34fc3485 100644
--- a/arch/arm64/boot/dts/arm/rtsm_ve-motherboard.dtsi
+++ b/arch/arm64/boot/dts/arm/rtsm_ve-motherboard.dtsi
@@ -17,14 +17,14 @@
 			#interrupt-cells = <1>;
 			ranges;
 
-			flash@0,00000000 {
+			flash@0 {
 				compatible = "arm,vexpress-flash", "cfi-flash";
 				reg = <0 0x00000000 0x04000000>,
 				      <4 0x00000000 0x04000000>;
 				bank-width = <4>;
 			};
 
-			ethernet@2,02000000 {
+			ethernet@202000000 {
 				compatible = "smsc,lan91c111";
 				reg = <2 0x02000000 0x10000>;
 				interrupts = <15>;
@@ -51,7 +51,7 @@
 				clock-output-names = "v2m:refclk32khz";
 			};
 
-			iofpga@3,00000000 {
+			iofpga@300000000 {
 				compatible = "simple-bus";
 				#address-cells = <1>;
 				#size-cells = <1>;
diff --git a/arch/arm64/boot/dts/exynos/exynos7-espresso.dts b/arch/arm64/boot/dts/exynos/exynos7-espresso.dts
index 00dd89b92b42..d991eae5202f 100644
--- a/arch/arm64/boot/dts/exynos/exynos7-espresso.dts
+++ b/arch/arm64/boot/dts/exynos/exynos7-espresso.dts
@@ -152,6 +152,7 @@
 				regulator-min-microvolt = <700000>;
 				regulator-max-microvolt = <1150000>;
 				regulator-enable-ramp-delay = <125>;
+				regulator-always-on;
 			};
 
 			ldo8_reg: LDO8 {
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
index bf7f845447ed..72946d42257d 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
@@ -72,7 +72,7 @@
 
 	reboot {
 		compatible ="syscon-reboot";
-		regmap = <&dcfg>;
+		regmap = <&rst>;
 		offset = <0xb0>;
 		mask = <0x02>;
 	};
@@ -128,7 +128,13 @@
 		dcfg: syscon@1e00000 {
 			compatible = "fsl,ls1028a-dcfg", "syscon";
 			reg = <0x0 0x1e00000 0x0 0x10000>;
-			big-endian;
+			little-endian;
+		};
+
+		rst: syscon@1e60000 {
+			compatible = "syscon";
+			reg = <0x0 0x1e60000 0x0 0x10000>;
+			little-endian;
 		};
 
 		scfg: syscon@1fc0000 {
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi
index 6082ae022136..d237162a8744 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi
@@ -20,6 +20,8 @@
 };
 
 &fman0 {
+	fsl,erratum-a050385;
+
 	/* these aliases provide the FMan ports mapping */
 	enet0: ethernet@e0000 {
 	};
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts b/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts
index 4223a2352d45..dde50c88f5e3 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts
@@ -119,12 +119,12 @@
 
 	ethernet@e4000 {
 		phy-handle = <&rgmii_phy1>;
-		phy-connection-type = "rgmii-txid";
+		phy-connection-type = "rgmii-id";
 	};
 
 	ethernet@e6000 {
 		phy-handle = <&rgmii_phy2>;
-		phy-connection-type = "rgmii-txid";
+		phy-connection-type = "rgmii-id";
 	};
 
 	ethernet@e8000 {
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a-rdb.dts b/arch/arm64/boot/dts/freescale/fsl-ls1046a-rdb.dts
index 6a6514d0e5a9..274339759114 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1046a-rdb.dts
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a-rdb.dts
@@ -127,12 +127,12 @@
 &fman0 {
 	ethernet@e4000 {
 		phy-handle = <&rgmii_phy1>;
-		phy-connection-type = "rgmii";
+		phy-connection-type = "rgmii-id";
 	};
 
 	ethernet@e6000 {
 		phy-handle = <&rgmii_phy2>;
-		phy-connection-type = "rgmii";
+		phy-connection-type = "rgmii-id";
 	};
 
 	ethernet@e8000 {
diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi
index 85b11d7b9e49..5a2811707d0e 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi
@@ -601,7 +601,7 @@
 				reg = <0x30bd0000 0x10000>;
 				interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MM_CLK_SDMA1_ROOT>,
-					 <&clk IMX8MM_CLK_SDMA1_ROOT>;
+					 <&clk IMX8MM_CLK_AHB>;
 				clock-names = "ipg", "ahb";
 				#dma-cells = <3>;
 				fsl,sdma-ram-script-name = "imx/sdma/sdma-imx7d.bin";
diff --git a/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts b/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts
index bfdada2db176..399767d25725 100644
--- a/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts
+++ b/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts
@@ -52,11 +52,6 @@
 			compatible = "ethernet-phy-ieee802.3-c22";
 			reg = <0>;
 		};
-
-		ethphy1: ethernet-phy@1 {
-			compatible = "ethernet-phy-ieee802.3-c22";
-			reg = <1>;
-		};
 	};
 };
 
diff --git a/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts b/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts
index e035cf195b19..8c4bfbaf3a80 100644
--- a/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts
+++ b/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts
@@ -530,6 +530,17 @@
 		status = "ok";
 		compatible = "adi,adv7533";
 		reg = <0x39>;
+		adi,dsi-lanes = <4>;
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			port@0 {
+				reg = <0>;
+			};
+			port@1 {
+				reg = <1>;
+			};
+		};
 	};
 };
 
diff --git a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
index c14205cd6bf5..3e47150c05ec 100644
--- a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
+++ b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
@@ -516,7 +516,7 @@
 		reg = <0x39>;
 		interrupt-parent = <&gpio1>;
 		interrupts = <1 2>;
-		pd-gpio = <&gpio0 4 0>;
+		pd-gpios = <&gpio0 4 0>;
 		adi,dsi-lanes = <4>;
 		#sound-dai-cells = <0>;
 
diff --git a/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi b/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi
index e4ceb3a73c81..bf2d744185df 100644
--- a/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi
+++ b/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi
@@ -47,10 +47,10 @@
 
 	pmu {
 		compatible = "arm,armv8-pmuv3";
-		interrupts = <0 120 8>,
-			     <0 121 8>,
-			     <0 122 8>,
-			     <0 123 8>;
+		interrupts = <0 170 4>,
+			     <0 171 4>,
+			     <0 172 4>,
+			     <0 173 4>;
 		interrupt-affinity = <&cpu0>,
 				     <&cpu1>,
 				     <&cpu2>,
@@ -82,7 +82,7 @@
 		ranges = <0 0 0 0xffffffff>;
 
 		gmac0: ethernet@ff800000 {
-			compatible = "altr,socfpga-stmmac", "snps,dwmac-3.74a", "snps,dwmac";
+			compatible = "altr,socfpga-stmmac-a10-s10", "snps,dwmac-3.74a", "snps,dwmac";
 			reg = <0xff800000 0x2000>;
 			interrupts = <0 90 4>;
 			interrupt-names = "macirq";
@@ -97,7 +97,7 @@
 		};
 
 		gmac1: ethernet@ff802000 {
-			compatible = "altr,socfpga-stmmac", "snps,dwmac-3.74a", "snps,dwmac";
+			compatible = "altr,socfpga-stmmac-a10-s10", "snps,dwmac-3.74a", "snps,dwmac";
 			reg = <0xff802000 0x2000>;
 			interrupts = <0 91 4>;
 			interrupt-names = "macirq";
@@ -112,7 +112,7 @@
 		};
 
 		gmac2: ethernet@ff804000 {
-			compatible = "altr,socfpga-stmmac", "snps,dwmac-3.74a", "snps,dwmac";
+			compatible = "altr,socfpga-stmmac-a10-s10", "snps,dwmac-3.74a", "snps,dwmac";
 			reg = <0xff804000 0x2000>;
 			interrupts = <0 92 4>;
 			interrupt-names = "macirq";
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-uDPU.dts b/arch/arm64/boot/dts/marvell/armada-3720-uDPU.dts
index bd4aab6092e0..e31813a4f972 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-uDPU.dts
+++ b/arch/arm64/boot/dts/marvell/armada-3720-uDPU.dts
@@ -143,6 +143,7 @@
 	phy-mode = "sgmii";
 	status = "okay";
 	managed = "in-band-status";
+	phys = <&comphy1 0>;
 	sfp = <&sfp_eth0>;
 };
 
@@ -150,11 +151,14 @@
 	phy-mode = "sgmii";
 	status = "okay";
 	managed = "in-band-status";
+	phys = <&comphy0 1>;
 	sfp = <&sfp_eth1>;
 };
 
 &usb3 {
 	status = "okay";
+	phys = <&usb2_utmi_otg_phy>;
+	phy-names = "usb2-utmi-otg-phy";
 };
 
 &uart0 {
diff --git a/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts b/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts
index 9143aa13ceb1..e88efafbda39 100644
--- a/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts
+++ b/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts
@@ -364,6 +364,7 @@
 		pinctrl-0 = <&cp0_copper_eth_phy_reset>;
 		reset-gpios = <&cp0_gpio2 11 GPIO_ACTIVE_LOW>;
 		reset-assert-us = <10000>;
+		reset-deassert-us = <10000>;
 	};
 
 	switch0: switch0@4 {
@@ -405,6 +406,8 @@
 				reg = <5>;
 				label = "cpu";
 				ethernet = <&cp1_eth2>;
+				phy-mode = "2500base-x";
+				managed = "in-band-status";
 			};
 		};
 
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
index 4d6e4a097f72..eeaaaf188bd4 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
@@ -423,10 +423,10 @@
 
 		CP110_LABEL(nand_controller): nand@720000 {
 			/*
-			* Due to the limitation of the pins available
-			* this controller is only usable on the CPM
-			* for A7K and on the CPS for A8K.
-			*/
+			 * Due to the limitation of the pins available
+			 * this controller is only usable on the CPM
+			 * for A7K and on the CPS for A8K.
+			 */
 			compatible = "marvell,armada-8k-nand-controller",
 				"marvell,armada370-nand-controller";
 			reg = <0x720000 0x54>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
index 15f1842f6df3..dec5e4113ce4 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
@@ -238,21 +238,21 @@
 		cpu_on	      = <0x84000003>;
 	};
 
-	clk26m: oscillator@0 {
+	clk26m: oscillator0 {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <26000000>;
 		clock-output-names = "clk26m";
 	};
 
-	clk32k: oscillator@1 {
+	clk32k: oscillator1 {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <32000>;
 		clock-output-names = "clk32k";
 	};
 
-	cpum_ck: oscillator@2 {
+	cpum_ck: oscillator2 {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <0>;
@@ -268,19 +268,19 @@
 			sustainable-power = <1500>; /* milliwatts */
 
 			trips {
-				threshold: trip-point@0 {
+				threshold: trip-point0 {
 					temperature = <68000>;
 					hysteresis = <2000>;
 					type = "passive";
 				};
 
-				target: trip-point@1 {
+				target: trip-point1 {
 					temperature = <85000>;
 					hysteresis = <2000>;
 					type = "passive";
 				};
 
-				cpu_crit: cpu_crit@0 {
+				cpu_crit: cpu_crit0 {
 					temperature = <115000>;
 					hysteresis = <2000>;
 					type = "critical";
@@ -288,13 +288,13 @@
 			};
 
 			cooling-maps {
-				map@0 {
+				map0 {
 					trip = <&target>;
 					cooling-device = <&cpu0 0 0>,
 							 <&cpu1 0 0>;
 					contribution = <3072>;
 				};
-				map@1 {
+				map1 {
 					trip = <&target>;
 					cooling-device = <&cpu2 0 0>,
 							 <&cpu3 0 0>;
@@ -308,7 +308,7 @@
 		#address-cells = <2>;
 		#size-cells = <2>;
 		ranges;
-		vpu_dma_reserved: vpu_dma_mem_region {
+		vpu_dma_reserved: vpu_dma_mem_region@b7000000 {
 			compatible = "shared-dma-pool";
 			reg = <0 0xb7000000 0 0x500000>;
 			alignment = <0x1000>;
@@ -360,7 +360,7 @@
 			reg = <0 0x10005000 0 0x1000>;
 		};
 
-		pio: pinctrl@10005000 {
+		pio: pinctrl@1000b000 {
 			compatible = "mediatek,mt8173-pinctrl";
 			reg = <0 0x1000b000 0 0x1000>;
 			mediatek,pctl-regmap = <&syscfg_pctl_a>;
@@ -567,7 +567,7 @@
 			status = "disabled";
 		};
 
-		gic: interrupt-controller@10220000 {
+		gic: interrupt-controller@10221000 {
 			compatible = "arm,gic-400";
 			#interrupt-cells = <3>;
 			interrupt-parent = <&gic>;
@@ -1397,8 +1397,8 @@
 				      "venc_lt_sel";
 			assigned-clocks = <&topckgen CLK_TOP_VENC_SEL>,
 					  <&topckgen CLK_TOP_VENC_LT_SEL>;
-			assigned-clock-parents = <&topckgen CLK_TOP_VENCPLL_D2>,
-						 <&topckgen CLK_TOP_UNIVPLL1_D2>;
+			assigned-clock-parents = <&topckgen CLK_TOP_VCODECPLL>,
+						 <&topckgen CLK_TOP_VCODECPLL_370P5>;
 		};
 
 		vencltsys: clock-controller@19000000 {
diff --git a/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi b/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi
index 0fd5bd29fbf9..e56fb39e9eb2 100644
--- a/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi
@@ -32,7 +32,7 @@
 
 			phy-reset-gpios = <&gpio TEGRA194_MAIN_GPIO(G, 5) GPIO_ACTIVE_LOW>;
 			phy-handle = <&phy>;
-			phy-mode = "rgmii";
+			phy-mode = "rgmii-id";
 
 			mdio {
 				#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi b/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi
index 04ad2fb22b9a..dba3488492f1 100644
--- a/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi
+++ b/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi
@@ -623,6 +623,8 @@
 				l21 {
 					regulator-min-microvolt = <2950000>;
 					regulator-max-microvolt = <2950000>;
+					regulator-allow-set-load;
+					regulator-system-load = <200000>;
 				};
 				l22 {
 					regulator-min-microvolt = <3300000>;
diff --git a/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi b/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi
index 242aaea68804..1235830ffd0b 100644
--- a/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi
@@ -508,7 +508,7 @@
 				pins = "gpio63", "gpio64", "gpio65", "gpio66",
 				       "gpio67", "gpio68";
 				drive-strength = <8>;
-				bias-pull-none;
+				bias-disable;
 			};
 		};
 		cdc_pdm_lines_sus: pdm_lines_off {
@@ -537,7 +537,7 @@
 				pins = "gpio113", "gpio114", "gpio115",
 				       "gpio116";
 				drive-strength = <8>;
-				bias-pull-none;
+				bias-disable;
 			};
 		};
 
@@ -565,7 +565,7 @@
 			pinconf {
 				pins = "gpio110";
 				drive-strength = <8>;
-				bias-pull-none;
+				bias-disable;
 			};
 		};
 
@@ -591,7 +591,7 @@
 			pinconf {
 				pins = "gpio116";
 				drive-strength = <8>;
-				bias-pull-none;
+				bias-disable;
 			};
 		};
 		ext_mclk_tlmm_lines_sus: mclk_lines_off {
@@ -619,7 +619,7 @@
 				pins = "gpio112", "gpio117", "gpio118",
 					"gpio119";
 				drive-strength = <8>;
-				bias-pull-none;
+				bias-disable;
 			};
 		};
 		ext_sec_tlmm_lines_sus: tlmm_lines_off {
diff --git a/arch/arm64/boot/dts/qcom/msm8916.dtsi b/arch/arm64/boot/dts/qcom/msm8916.dtsi
index dacd465fc62e..35a6609f5228 100644
--- a/arch/arm64/boot/dts/qcom/msm8916.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8916.dtsi
@@ -209,7 +209,7 @@
 			thermal-sensors = <&tsens 3>;
 
 			trips {
-				cpu2_3_alert0: trip-point@0 {
+				cpu2_3_alert0: trip-point0 {
 					temperature = <75000>;
 					hysteresis = <2000>;
 					type = "passive";
@@ -239,7 +239,7 @@
 			thermal-sensors = <&tsens 2>;
 
 			trips {
-				gpu_alert0: trip-point@0 {
+				gpu_alert0: trip-point0 {
 					temperature = <75000>;
 					hysteresis = <2000>;
 					type = "passive";
@@ -259,7 +259,7 @@
 			thermal-sensors = <&tsens 1>;
 
 			trips {
-				cam_alert0: trip-point@0 {
+				cam_alert0: trip-point0 {
 					temperature = <75000>;
 					hysteresis = <2000>;
 					type = "hot";
@@ -274,7 +274,7 @@
 			thermal-sensors = <&tsens 0>;
 
 			trips {
-				modem_alert0: trip-point@0 {
+				modem_alert0: trip-point0 {
 					temperature = <85000>;
 					hysteresis = <2000>;
 					type = "hot";
diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi
index 942465d8aeb7..f976221ff144 100644
--- a/arch/arm64/boot/dts/qcom/msm8996.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi
@@ -1107,6 +1107,8 @@
 				interrupts = <0 138 IRQ_TYPE_LEVEL_HIGH>;
 				phys = <&hsusb_phy2>;
 				phy-names = "usb2-phy";
+				snps,dis_u2_susphy_quirk;
+				snps,dis_enblslpm_quirk;
 			};
 		};
 
@@ -1137,6 +1139,8 @@
 				interrupts = <0 131 IRQ_TYPE_LEVEL_HIGH>;
 				phys = <&hsusb_phy1>, <&ssusb_phy_0>;
 				phy-names = "usb2-phy", "usb3-phy";
+				snps,dis_u2_susphy_quirk;
+				snps,dis_enblslpm_quirk;
 			};
 		};
 
@@ -1187,16 +1191,16 @@
 				"csi_clk_mux",
 				"vfe0",
 				"vfe1";
-			interrupts = <GIC_SPI 78 0>,
-				<GIC_SPI 79 0>,
-				<GIC_SPI 80 0>,
-				<GIC_SPI 296 0>,
-				<GIC_SPI 297 0>,
-				<GIC_SPI 298 0>,
-				<GIC_SPI 299 0>,
-				<GIC_SPI 309 0>,
-				<GIC_SPI 314 0>,
-				<GIC_SPI 315 0>;
+			interrupts = <GIC_SPI 78 IRQ_TYPE_EDGE_RISING>,
+				<GIC_SPI 79 IRQ_TYPE_EDGE_RISING>,
+				<GIC_SPI 80 IRQ_TYPE_EDGE_RISING>,
+				<GIC_SPI 296 IRQ_TYPE_EDGE_RISING>,
+				<GIC_SPI 297 IRQ_TYPE_EDGE_RISING>,
+				<GIC_SPI 298 IRQ_TYPE_EDGE_RISING>,
+				<GIC_SPI 299 IRQ_TYPE_EDGE_RISING>,
+				<GIC_SPI 309 IRQ_TYPE_EDGE_RISING>,
+				<GIC_SPI 314 IRQ_TYPE_EDGE_RISING>,
+				<GIC_SPI 315 IRQ_TYPE_EDGE_RISING>;
 			interrupt-names = "csiphy0",
 				"csiphy1",
 				"csiphy2",
diff --git a/arch/arm64/boot/dts/qcom/msm8998.dtsi b/arch/arm64/boot/dts/qcom/msm8998.dtsi
index 574be78a936e..c57f4fe0ea9f 100644
--- a/arch/arm64/boot/dts/qcom/msm8998.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8998.dtsi
@@ -760,7 +760,7 @@
 
 		tcsr_mutex_regs: syscon@1f40000 {
 			compatible = "syscon";
-			reg = <0x1f40000 0x20000>;
+			reg = <0x1f40000 0x40000>;
 		};
 
 		apcs_glb: mailbox@9820000 {
diff --git a/arch/arm64/boot/dts/qcom/qcs404-evb.dtsi b/arch/arm64/boot/dts/qcom/qcs404-evb.dtsi
index d987d6741e40..9c1803f7e493 100644
--- a/arch/arm64/boot/dts/qcom/qcs404-evb.dtsi
+++ b/arch/arm64/boot/dts/qcom/qcs404-evb.dtsi
@@ -63,6 +63,7 @@
 		regulator-always-on;
 		regulator-boot-on;
 		regulator-name = "vdd_apc";
+		regulator-initial-mode = <1>;
 		regulator-min-microvolt = <1048000>;
 		regulator-max-microvolt = <1352000>;
 	};
diff --git a/arch/arm64/boot/dts/renesas/r8a774a1.dtsi b/arch/arm64/boot/dts/renesas/r8a774a1.dtsi
index de282c4794ed..7180e51d389f 100644
--- a/arch/arm64/boot/dts/renesas/r8a774a1.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a774a1.dtsi
@@ -883,6 +883,8 @@
 				 <&cpg CPG_CORE R8A774A1_CLK_CANFD>,
 				 <&can_clk>;
 			clock-names = "clkp1", "clkp2", "can_clk";
+			assigned-clocks = <&cpg CPG_CORE R8A774A1_CLK_CANFD>;
+			assigned-clock-rates = <40000000>;
 			power-domains = <&sysc R8A774A1_PD_ALWAYS_ON>;
 			resets = <&cpg 916>;
 			status = "disabled";
@@ -897,6 +899,8 @@
 				 <&cpg CPG_CORE R8A774A1_CLK_CANFD>,
 				 <&can_clk>;
 			clock-names = "clkp1", "clkp2", "can_clk";
+			assigned-clocks = <&cpg CPG_CORE R8A774A1_CLK_CANFD>;
+			assigned-clock-rates = <40000000>;
 			power-domains = <&sysc R8A774A1_PD_ALWAYS_ON>;
 			resets = <&cpg 915>;
 			status = "disabled";
diff --git a/arch/arm64/boot/dts/renesas/r8a774c0.dtsi b/arch/arm64/boot/dts/renesas/r8a774c0.dtsi
index 3f86db199dbf..1e070139be2f 100644
--- a/arch/arm64/boot/dts/renesas/r8a774c0.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a774c0.dtsi
@@ -973,6 +973,8 @@
 				 <&cpg CPG_CORE R8A774C0_CLK_CANFD>,
 				 <&can_clk>;
 			clock-names = "clkp1", "clkp2", "can_clk";
+			assigned-clocks = <&cpg CPG_CORE R8A774C0_CLK_CANFD>;
+			assigned-clock-rates = <40000000>;
 			power-domains = <&sysc R8A774C0_PD_ALWAYS_ON>;
 			resets = <&cpg 916>;
 			status = "disabled";
@@ -987,6 +989,8 @@
 				 <&cpg CPG_CORE R8A774C0_CLK_CANFD>,
 				 <&can_clk>;
 			clock-names = "clkp1", "clkp2", "can_clk";
+			assigned-clocks = <&cpg CPG_CORE R8A774C0_CLK_CANFD>;
+			assigned-clock-rates = <40000000>;
 			power-domains = <&sysc R8A774C0_PD_ALWAYS_ON>;
 			resets = <&cpg 915>;
 			status = "disabled";
diff --git a/arch/arm64/boot/dts/renesas/r8a77970.dtsi b/arch/arm64/boot/dts/renesas/r8a77970.dtsi
index 5b6164d4b8e3..d8b29753c450 100644
--- a/arch/arm64/boot/dts/renesas/r8a77970.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a77970.dtsi
@@ -652,7 +652,7 @@
 		};
 
 		pwm3: pwm@e6e33000 {
-			compatible = "renesas,pwm-r8a7790", "renesas,pwm-rcar";
+			compatible = "renesas,pwm-r8a77970", "renesas,pwm-rcar";
 			reg = <0 0xe6e33000 0 8>;
 			#pwm-cells = <2>;
 			clocks = <&cpg CPG_MOD 523>;
diff --git a/arch/arm64/boot/dts/renesas/r8a77980.dtsi b/arch/arm64/boot/dts/renesas/r8a77980.dtsi
index a901a341dcf7..8a0bb4b6ceff 100644
--- a/arch/arm64/boot/dts/renesas/r8a77980.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a77980.dtsi
@@ -1318,6 +1318,7 @@
 		ipmmu_vip0: mmu@e7b00000 {
 			compatible = "renesas,ipmmu-r8a77980";
 			reg = <0 0xe7b00000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 4>;
 			power-domains = <&sysc R8A77980_PD_ALWAYS_ON>;
 			#iommu-cells = <1>;
 		};
@@ -1325,6 +1326,7 @@
 		ipmmu_vip1: mmu@e7960000 {
 			compatible = "renesas,ipmmu-r8a77980";
 			reg = <0 0xe7960000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 11>;
 			power-domains = <&sysc R8A77980_PD_ALWAYS_ON>;
 			#iommu-cells = <1>;
 		};
diff --git a/arch/arm64/boot/dts/renesas/r8a77990-ebisu.dts b/arch/arm64/boot/dts/renesas/r8a77990-ebisu.dts
index c72772589953..6e048f45cb40 100644
--- a/arch/arm64/boot/dts/renesas/r8a77990-ebisu.dts
+++ b/arch/arm64/boot/dts/renesas/r8a77990-ebisu.dts
@@ -629,7 +629,6 @@
 	/* audio_clkout0/1/2/3 */
 	#clock-cells = <1>;
 	clock-frequency = <12288000 11289600>;
-	clkout-lr-synchronous;
 
 	status = "okay";
 
diff --git a/arch/arm64/boot/dts/rockchip/px30.dtsi b/arch/arm64/boot/dts/rockchip/px30.dtsi
index eb992d60e6ba..9e09909a510a 100644
--- a/arch/arm64/boot/dts/rockchip/px30.dtsi
+++ b/arch/arm64/boot/dts/rockchip/px30.dtsi
@@ -768,7 +768,7 @@
 		interrupts = <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru HCLK_SDMMC>, <&cru SCLK_SDMMC>,
 			 <&cru SCLK_SDMMC_DRV>, <&cru SCLK_SDMMC_SAMPLE>;
-		clock-names = "biu", "ciu", "ciu-drv", "ciu-sample";
+		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		fifo-depth = <0x100>;
 		max-frequency = <150000000>;
 		pinctrl-names = "default";
@@ -783,7 +783,7 @@
 		interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru HCLK_SDIO>, <&cru SCLK_SDIO>,
 			 <&cru SCLK_SDIO_DRV>, <&cru SCLK_SDIO_SAMPLE>;
-		clock-names = "biu", "ciu", "ciu-drv", "ciu-sample";
+		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		fifo-depth = <0x100>;
 		max-frequency = <150000000>;
 		pinctrl-names = "default";
@@ -798,7 +798,7 @@
 		interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru HCLK_EMMC>, <&cru SCLK_EMMC>,
 			 <&cru SCLK_EMMC_DRV>, <&cru SCLK_EMMC_SAMPLE>;
-		clock-names = "biu", "ciu", "ciu-drv", "ciu-sample";
+		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		fifo-depth = <0x100>;
 		max-frequency = <150000000>;
 		power-domains = <&power PX30_PD_MMC_NAND>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-evb.dts b/arch/arm64/boot/dts/rockchip/rk3328-evb.dts
index 49c4b96da3d4..05265b38cc02 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-evb.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-evb.dts
@@ -86,13 +86,13 @@
 	assigned-clock-rate = <50000000>;
 	assigned-clocks = <&cru SCLK_MAC2PHY>;
 	assigned-clock-parents = <&cru SCLK_MAC2PHY_SRC>;
-
+	status = "okay";
 };
 
 &i2c1 {
 	status = "okay";
 
-	rk805: rk805@18 {
+	rk805: pmic@18 {
 		compatible = "rockchip,rk805";
 		reg = <0x18>;
 		interrupt-parent = <&gpio2>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
index 7cfd5ca6cc85..fdee0115c19e 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
@@ -170,7 +170,7 @@
 &i2c1 {
 	status = "okay";
 
-	rk805: rk805@18 {
+	rk805: pmic@18 {
 		compatible = "rockchip,rk805";
 		reg = <0x18>;
 		interrupt-parent = <&gpio2>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3368-lion.dtsi b/arch/arm64/boot/dts/rockchip/rk3368-lion.dtsi
index e17311e09082..216aafd90e7f 100644
--- a/arch/arm64/boot/dts/rockchip/rk3368-lion.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3368-lion.dtsi
@@ -156,7 +156,7 @@
 	pinctrl-0 = <&rgmii_pins>;
 	snps,reset-active-low;
 	snps,reset-delays-us = <0 10000 50000>;
-	snps,reset-gpio = <&gpio3 RK_PB3 GPIO_ACTIVE_HIGH>;
+	snps,reset-gpio = <&gpio3 RK_PB3 GPIO_ACTIVE_LOW>;
 	tx_delay = <0x10>;
 	rx_delay = <0x10>;
 	status = "okay";
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-nanopc-t4.dts b/arch/arm64/boot/dts/rockchip/rk3399-nanopc-t4.dts
index 2a127985ab17..d3ed8e5e770f 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-nanopc-t4.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-nanopc-t4.dts
@@ -94,33 +94,6 @@
 	};
 };
 
-&gpu_thermal {
-	trips {
-		gpu_warm: gpu_warm {
-			temperature = <55000>;
-			hysteresis = <2000>;
-			type = "active";
-		};
-
-		gpu_hot: gpu_hot {
-			temperature = <65000>;
-			hysteresis = <2000>;
-			type = "active";
-		};
-	};
-	cooling-maps {
-		map1 {
-			trip = <&gpu_warm>;
-			cooling-device = <&fan THERMAL_NO_LIMIT 1>;
-		};
-
-		map2 {
-			trip = <&gpu_hot>;
-			cooling-device = <&fan 2 THERMAL_NO_LIMIT>;
-		};
-	};
-};
-
 &pinctrl {
 	ir {
 		ir_rx: ir-rx {
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
index 62ea288a1a70..45b86933c6ea 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
@@ -101,7 +101,7 @@
 
 	vcc5v0_host: vcc5v0-host-regulator {
 		compatible = "regulator-fixed";
-		gpio = <&gpio4 RK_PA3 GPIO_ACTIVE_HIGH>;
+		gpio = <&gpio4 RK_PA3 GPIO_ACTIVE_LOW>;
 		enable-active-low;
 		pinctrl-names = "default";
 		pinctrl-0 = <&vcc5v0_host_en>;
@@ -157,7 +157,7 @@
 	phy-mode = "rgmii";
 	pinctrl-names = "default";
 	pinctrl-0 = <&rgmii_pins>;
-	snps,reset-gpio = <&gpio3 RK_PC0 GPIO_ACTIVE_HIGH>;
+	snps,reset-gpio = <&gpio3 RK_PC0 GPIO_ACTIVE_LOW>;
 	snps,reset-active-low;
 	snps,reset-delays-us = <0 10000 50000>;
 	tx_delay = <0x10>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
index 89594a7276f4..a7e245d1bf8d 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
@@ -410,7 +410,7 @@
 		reset-names = "usb3-otg";
 		status = "disabled";
 
-		usbdrd_dwc3_0: dwc3 {
+		usbdrd_dwc3_0: usb@fe800000 {
 			compatible = "snps,dwc3";
 			reg = <0x0 0xfe800000 0x0 0x100000>;
 			interrupts = <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH 0>;
@@ -443,7 +443,7 @@
 		reset-names = "usb3-otg";
 		status = "disabled";
 
-		usbdrd_dwc3_1: dwc3 {
+		usbdrd_dwc3_1: usb@fe900000 {
 			compatible = "snps,dwc3";
 			reg = <0x0 0xfe900000 0x0 0x100000>;
 			interrupts = <GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH 0>;
@@ -1884,10 +1884,10 @@
 	gpu: gpu@ff9a0000 {
 		compatible = "rockchip,rk3399-mali", "arm,mali-t860";
 		reg = <0x0 0xff9a0000 0x0 0x10000>;
-		interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH 0>;
-		interrupt-names = "gpu", "job", "mmu";
+		interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH 0>;
+		interrupt-names = "job", "mmu", "gpu";
 		clocks = <&cru ACLK_GPU>;
 		power-domains = <&power RK3399_PD_GPU>;
 		status = "disabled";
diff --git a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi
index 6297ec7f4e58..334cbf04e6bc 100644
--- a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi
@@ -256,6 +256,7 @@
 		interrupts = <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>;
 		dma-coherent;
 		power-domains = <&k3_pds 151>;
+		clocks = <&k3_clks 151 2>, <&k3_clks 151 7>;
 		assigned-clocks = <&k3_clks 151 2>, <&k3_clks 151 7>;
 		assigned-clock-parents = <&k3_clks 151 4>,	/* set REF_CLK to 20MHz i.e. PER0_PLL/48 */
 					 <&k3_clks 151 9>;	/* set PIPE3_TXB_CLK to CLK_12M_RC/256 (for HS only) */
@@ -295,6 +296,7 @@
 		interrupts = <GIC_SPI 117 IRQ_TYPE_LEVEL_HIGH>;
 		dma-coherent;
 		power-domains = <&k3_pds 152>;
+		clocks = <&k3_clks 152 2>;
 		assigned-clocks = <&k3_clks 152 2>;
 		assigned-clock-parents = <&k3_clks 152 4>;	/* set REF_CLK to 20MHz i.e. PER0_PLL/48 */
 
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index 16c5da9be9fb..7ef982a84331 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -263,7 +263,7 @@ static int ghash_setkey(struct crypto_shash *tfm,
 static struct shash_alg ghash_alg[] = {{
 	.base.cra_name		= "ghash",
 	.base.cra_driver_name	= "ghash-neon",
-	.base.cra_priority	= 100,
+	.base.cra_priority	= 150,
 	.base.cra_blocksize	= GHASH_BLOCK_SIZE,
 	.base.cra_ctxsize	= sizeof(struct ghash_key),
 	.base.cra_module	= THIS_MODULE,
diff --git a/arch/arm64/crypto/nhpoly1305-neon-glue.c b/arch/arm64/crypto/nhpoly1305-neon-glue.c
index 895d3727c1fb..c5405e6a6db7 100644
--- a/arch/arm64/crypto/nhpoly1305-neon-glue.c
+++ b/arch/arm64/crypto/nhpoly1305-neon-glue.c
@@ -30,7 +30,7 @@ static int nhpoly1305_neon_update(struct shash_desc *desc,
 		return crypto_nhpoly1305_update(desc, src, srclen);
 
 	do {
-		unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE);
+		unsigned int n = min_t(unsigned int, srclen, SZ_4K);
 
 		kernel_neon_begin();
 		crypto_nhpoly1305_update_helper(desc, src, n, _nh_neon);
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h
index b9f8d787eea9..aa9ad4097361 100644
--- a/arch/arm64/include/asm/alternative.h
+++ b/arch/arm64/include/asm/alternative.h
@@ -71,13 +71,13 @@ static inline void apply_alternatives_module(void *start, size_t length) { }
 	ALTINSTR_ENTRY(feature,cb)					\
 	".popsection\n"							\
 	" .if " __stringify(cb) " == 0\n"				\
-	".pushsection .altinstr_replacement, \"a\"\n"			\
+	".subsection 1\n"						\
 	"663:\n\t"							\
 	newinstr "\n"							\
 	"664:\n\t"							\
-	".popsection\n\t"						\
 	".org	. - (664b-663b) + (662b-661b)\n\t"			\
-	".org	. - (662b-661b) + (664b-663b)\n"			\
+	".org	. - (662b-661b) + (664b-663b)\n\t"			\
+	".previous\n"							\
 	".else\n\t"							\
 	"663:\n\t"							\
 	"664:\n\t"							\
@@ -107,9 +107,9 @@ static inline void apply_alternatives_module(void *start, size_t length) { }
 662:	.pushsection .altinstructions, "a"
 	altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f
 	.popsection
-	.pushsection .altinstr_replacement, "ax"
+	.subsection 1
 663:	\insn2
-664:	.popsection
+664:	.previous
 	.org	. - (664b-663b) + (662b-661b)
 	.org	. - (662b-661b) + (664b-663b)
 	.endif
@@ -150,7 +150,7 @@ static inline void apply_alternatives_module(void *start, size_t length) { }
 	.pushsection .altinstructions, "a"
 	altinstruction_entry 663f, 661f, \cap, 664f-663f, 662f-661f
 	.popsection
-	.pushsection .altinstr_replacement, "ax"
+	.subsection 1
 	.align 2	/* So GAS knows label 661 is suitably aligned */
 661:
 .endm
@@ -169,9 +169,9 @@ static inline void apply_alternatives_module(void *start, size_t length) { }
 .macro alternative_else
 662:
 	.if .Lasm_alt_mode==0
-	.pushsection .altinstr_replacement, "ax"
+	.subsection 1
 	.else
-	.popsection
+	.previous
 	.endif
 663:
 .endm
@@ -182,7 +182,7 @@ static inline void apply_alternatives_module(void *start, size_t length) { }
 .macro alternative_endif
 664:
 	.if .Lasm_alt_mode==0
-	.popsection
+	.previous
 	.endif
 	.org	. - (664b-663b) + (662b-661b)
 	.org	. - (662b-661b) + (664b-663b)
@@ -211,7 +211,7 @@ alternative_endif
 
 .macro user_alt, label, oldinstr, newinstr, cond
 9999:	alternative_insn "\oldinstr", "\newinstr", \cond
-	_ASM_EXTABLE 9999b, \label
+	_asm_extable 9999b, \label
 .endm
 
 /*
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index 89e4c8b79349..ee9bdaa40532 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -109,7 +109,7 @@ static inline u32 gic_read_pmr(void)
 	return read_sysreg_s(SYS_ICC_PMR_EL1);
 }
 
-static inline void gic_write_pmr(u32 val)
+static __always_inline void gic_write_pmr(u32 val)
 {
 	write_sysreg_s(val, SYS_ICC_PMR_EL1);
 }
diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index a05db636981a..842bad6cba3f 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -11,6 +11,7 @@
 #define CTR_L1IP_MASK		3
 #define CTR_DMINLINE_SHIFT	16
 #define CTR_IMINLINE_SHIFT	0
+#define CTR_IMINLINE_MASK	0xf
 #define CTR_ERG_SHIFT		20
 #define CTR_CWG_SHIFT		24
 #define CTR_CWG_MASK		15
@@ -18,7 +19,7 @@
 #define CTR_DIC_SHIFT		29
 
 #define CTR_CACHE_MINLINE_MASK	\
-	(0xf << CTR_DMINLINE_SHIFT | 0xf << CTR_IMINLINE_SHIFT)
+	(0xf << CTR_DMINLINE_SHIFT | CTR_IMINLINE_MASK << CTR_IMINLINE_SHIFT)
 
 #define CTR_L1IP(ctr)		(((ctr) >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK)
 
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index 1fe4467442aa..c0d07ca5a1a7 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -79,7 +79,7 @@ static inline void flush_icache_range(unsigned long start, unsigned long end)
 	 * IPI all online CPUs so that they undergo a context synchronization
 	 * event and are forced to refetch the new instructions.
 	 */
-#ifdef CONFIG_KGDB
+
 	/*
 	 * KGDB performs cache maintenance with interrupts disabled, so we
 	 * will deadlock trying to IPI the secondary CPUs. In theory, we can
@@ -89,9 +89,9 @@ static inline void flush_icache_range(unsigned long start, unsigned long end)
 	 * the patching operation, so we don't need extra IPIs here anyway.
 	 * In which case, add a KGDB-specific bodge and return early.
 	 */
-	if (kgdb_connected && irqs_disabled())
+	if (in_dbg_master())
 		return;
-#endif
+
 	kick_all_cpus_sync();
 }
 
diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h
index d064a50deb5f..5665a3fc14be 100644
--- a/arch/arm64/include/asm/checksum.h
+++ b/arch/arm64/include/asm/checksum.h
@@ -19,16 +19,17 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 {
 	__uint128_t tmp;
 	u64 sum;
+	int n = ihl; /* we want it signed */
 
 	tmp = *(const __uint128_t *)iph;
 	iph += 16;
-	ihl -= 4;
+	n -= 4;
 	tmp += ((tmp >> 64) | (tmp << 64));
 	sum = tmp >> 64;
 	do {
 		sum += *(const u32 *)iph;
 		iph += 4;
-	} while (--ihl);
+	} while (--n > 0);
 
 	sum += ((sum >> 32) | (sum << 32));
 	return csum_fold((__force u32)(sum >> 32));
diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index fb8ad4616b3b..eab4f4946d6c 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -5,6 +5,9 @@
 #ifndef __ASM_COMPAT_H
 #define __ASM_COMPAT_H
 #ifdef __KERNEL__
+
+#include <asm-generic/compat.h>
+
 #ifdef CONFIG_COMPAT
 
 /*
@@ -14,8 +17,6 @@
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
 
-#include <asm-generic/compat.h>
-
 #define COMPAT_USER_HZ		100
 #ifdef __AARCH64EB__
 #define COMPAT_UTS_MACHINE	"armv8b\0\0"
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 782e5403027c..3886b8f1f9dc 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -54,7 +54,8 @@
 #define ARM64_WORKAROUND_1463225		44
 #define ARM64_WORKAROUND_CAVIUM_36890		45
 #define ARM64_WORKAROUND_MRVL_37119		46
+#define ARM64_WORKAROUND_1542419		47
 
-#define ARM64_NCAPS				47
+#define ARM64_NCAPS				48
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 0a61344ab243..731f2c4161b9 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -609,7 +609,7 @@ static inline bool system_supports_generic_auth(void)
 		 cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH_IMP_DEF));
 }
 
-static inline bool system_uses_irq_prio_masking(void)
+static __always_inline bool system_uses_irq_prio_masking(void)
 {
 	return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) &&
 	       cpus_have_const_cap(ARM64_HAS_IRQ_PRIO_MASKING);
diff --git a/arch/arm64/include/asm/daifflags.h b/arch/arm64/include/asm/daifflags.h
index 9c0e0178ea29..c9db3a5704a9 100644
--- a/arch/arm64/include/asm/daifflags.h
+++ b/arch/arm64/include/asm/daifflags.h
@@ -32,7 +32,7 @@ static inline void local_daif_mask(void)
 	trace_hardirqs_off();
 }
 
-static inline unsigned long local_daif_save(void)
+static inline unsigned long local_daif_save_flags(void)
 {
 	unsigned long flags;
 
@@ -44,6 +44,15 @@ static inline unsigned long local_daif_save(void)
 			flags |= PSR_I_BIT;
 	}
 
+	return flags;
+}
+
+static inline unsigned long local_daif_save(void)
+{
+	unsigned long flags;
+
+	flags = local_daif_save_flags();
+
 	local_daif_mask();
 
 	return flags;
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index d8ec5bb881c2..6c289542cee5 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -111,6 +111,8 @@ void disable_debug_monitors(enum dbg_active_el el);
 
 void user_rewind_single_step(struct task_struct *task);
 void user_fastforward_single_step(struct task_struct *task);
+void user_regs_reset_single_step(struct user_pt_regs *regs,
+				 struct task_struct *task);
 
 void kernel_enable_single_step(struct pt_regs *regs);
 void kernel_disable_single_step(void);
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 897029c8e9b5..b6a2c352f4c3 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -37,8 +37,6 @@ struct task_struct;
 extern void fpsimd_save_state(struct user_fpsimd_state *state);
 extern void fpsimd_load_state(struct user_fpsimd_state *state);
 
-extern void fpsimd_save(void);
-
 extern void fpsimd_thread_switch(struct task_struct *next);
 extern void fpsimd_flush_thread(void);
 
@@ -52,8 +50,7 @@ extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state,
 				     void *sve_state, unsigned int sve_vl);
 
 extern void fpsimd_flush_task_state(struct task_struct *target);
-extern void fpsimd_flush_cpu_state(void);
-extern void sve_flush_cpu_state(void);
+extern void fpsimd_save_and_flush_cpu_state(void);
 
 /* Maximum VL that SVE VL-agnostic software can transparently support */
 #define SVE_VL_ARCH_MAX 0x100
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 034dadec7168..53bc52270236 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -97,12 +97,6 @@ static inline void vcpu_ptrauth_disable(struct kvm_vcpu *vcpu)
 	vcpu->arch.hcr_el2 &= ~(HCR_API | HCR_APK);
 }
 
-static inline void vcpu_ptrauth_setup_lazy(struct kvm_vcpu *vcpu)
-{
-	if (vcpu_has_ptrauth(vcpu))
-		vcpu_ptrauth_disable(vcpu);
-}
-
 static inline unsigned long vcpu_get_vsesr(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.vsesr_el2;
@@ -204,6 +198,38 @@ static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v)
 		vcpu_gp_regs(vcpu)->spsr[KVM_SPSR_EL1] = v;
 }
 
+/*
+ * The layout of SPSR for an AArch32 state is different when observed from an
+ * AArch64 SPSR_ELx or an AArch32 SPSR_*. This function generates the AArch32
+ * view given an AArch64 view.
+ *
+ * In ARM DDI 0487E.a see:
+ *
+ * - The AArch64 view (SPSR_EL2) in section C5.2.18, page C5-426
+ * - The AArch32 view (SPSR_abt) in section G8.2.126, page G8-6256
+ * - The AArch32 view (SPSR_und) in section G8.2.132, page G8-6280
+ *
+ * Which show the following differences:
+ *
+ * | Bit | AA64 | AA32 | Notes                       |
+ * +-----+------+------+-----------------------------|
+ * | 24  | DIT  | J    | J is RES0 in ARMv8          |
+ * | 21  | SS   | DIT  | SS doesn't exist in AArch32 |
+ *
+ * ... and all other bits are (currently) common.
+ */
+static inline unsigned long host_spsr_to_spsr32(unsigned long spsr)
+{
+	const unsigned long overlap = BIT(24) | BIT(21);
+	unsigned long dit = !!(spsr & PSR_AA32_DIT_BIT);
+
+	spsr &= ~overlap;
+
+	spsr |= dit << 21;
+
+	return spsr;
+}
+
 static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu)
 {
 	u32 mode;
@@ -263,6 +289,11 @@ static inline bool kvm_vcpu_dabt_issext(const struct kvm_vcpu *vcpu)
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SSE);
 }
 
+static inline bool kvm_vcpu_dabt_issf(const struct kvm_vcpu *vcpu)
+{
+	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SF);
+}
+
 static inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu)
 {
 	return (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT;
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 9f19c354b165..5ecf3ea2ede4 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -392,8 +392,10 @@ void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg);
  * CP14 and CP15 live in the same array, as they are backed by the
  * same system registers.
  */
-#define vcpu_cp14(v,r)		((v)->arch.ctxt.copro[(r)])
-#define vcpu_cp15(v,r)		((v)->arch.ctxt.copro[(r)])
+#define CPx_BIAS		IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)
+
+#define vcpu_cp14(v,r)		((v)->arch.ctxt.copro[(r) ^ CPx_BIAS])
+#define vcpu_cp15(v,r)		((v)->arch.ctxt.copro[(r) ^ CPx_BIAS])
 
 struct kvm_vm_stat {
 	ulong remote_tlb_flush;
diff --git a/arch/arm64/include/asm/kvm_mmio.h b/arch/arm64/include/asm/kvm_mmio.h
index 02b5c48fd467..b204501a0c39 100644
--- a/arch/arm64/include/asm/kvm_mmio.h
+++ b/arch/arm64/include/asm/kvm_mmio.h
@@ -10,13 +10,11 @@
 #include <linux/kvm_host.h>
 #include <asm/kvm_arm.h>
 
-/*
- * This is annoying. The mmio code requires this, even if we don't
- * need any decoding. To be fixed.
- */
 struct kvm_decode {
 	unsigned long rt;
 	bool sign_extend;
+	/* Witdth of the register accessed by the faulting instruction is 64-bits */
+	bool sixty_four;
 };
 
 void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data);
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 87808be11ffa..3b3c5e4f8e61 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -54,7 +54,7 @@
 #define PAGE_HYP		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN)
 #define PAGE_HYP_EXEC		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY)
 #define PAGE_HYP_RO		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN)
-#define PAGE_HYP_DEVICE		__pgprot(PROT_DEVICE_nGnRE | PTE_HYP)
+#define PAGE_HYP_DEVICE		__pgprot(_PROT_DEFAULT | PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_HYP | PTE_HYP_XN)
 
 #define PAGE_S2_MEMATTR(attr)						\
 	({								\
@@ -85,13 +85,12 @@
 #define PAGE_SHARED_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_WRITE)
 #define PAGE_READONLY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
 #define PAGE_READONLY_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN)
-#define PAGE_EXECONLY		__pgprot(_PAGE_DEFAULT | PTE_RDONLY | PTE_NG | PTE_PXN)
 
 #define __P000  PAGE_NONE
 #define __P001  PAGE_READONLY
 #define __P010  PAGE_READONLY
 #define __P011  PAGE_READONLY
-#define __P100  PAGE_EXECONLY
+#define __P100  PAGE_READONLY_EXEC
 #define __P101  PAGE_READONLY_EXEC
 #define __P110  PAGE_READONLY_EXEC
 #define __P111  PAGE_READONLY_EXEC
@@ -100,7 +99,7 @@
 #define __S001  PAGE_READONLY
 #define __S010  PAGE_SHARED
 #define __S011  PAGE_SHARED
-#define __S100  PAGE_EXECONLY
+#define __S100  PAGE_READONLY_EXEC
 #define __S101  PAGE_READONLY_EXEC
 #define __S110  PAGE_SHARED_EXEC
 #define __S111  PAGE_SHARED_EXEC
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 7b55a2c604bd..0edd9a0e945f 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -95,12 +95,8 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 #define pte_dirty(pte)		(pte_sw_dirty(pte) || pte_hw_dirty(pte))
 
 #define pte_valid(pte)		(!!(pte_val(pte) & PTE_VALID))
-/*
- * Execute-only user mappings do not have the PTE_USER bit set. All valid
- * kernel mappings have the PTE_UXN bit set.
- */
 #define pte_valid_not_user(pte) \
-	((pte_val(pte) & (PTE_VALID | PTE_USER | PTE_UXN)) == (PTE_VALID | PTE_UXN))
+	((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
 #define pte_valid_young(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF))
 #define pte_valid_user(pte) \
@@ -116,8 +112,8 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 
 /*
  * p??_access_permitted() is true for valid user mappings (subject to the
- * write permission check) other than user execute-only which do not have the
- * PTE_USER bit set. PROT_NONE mappings do not have the PTE_VALID bit set.
+ * write permission check). PROT_NONE mappings do not have the PTE_VALID bit
+ * set.
  */
 #define pte_access_permitted(pte, write) \
 	(pte_valid_user(pte) && (!(write) || pte_write(pte)))
@@ -417,6 +413,7 @@ extern pgd_t init_pg_dir[PTRS_PER_PGD];
 extern pgd_t init_pg_end[];
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
+extern pgd_t idmap_pg_end[];
 extern pgd_t tramp_pg_dir[PTRS_PER_PGD];
 
 extern void set_swapper_pgd(pgd_t *pgdp, pgd_t pgd);
diff --git a/arch/arm64/include/asm/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h
index d328540cb85e..a7ac50fb5abc 100644
--- a/arch/arm64/include/asm/pointer_auth.h
+++ b/arch/arm64/include/asm/pointer_auth.h
@@ -3,7 +3,6 @@
 #define __ASM_POINTER_AUTH_H
 
 #include <linux/bitops.h>
-#include <linux/random.h>
 
 #include <asm/cpufeature.h>
 #include <asm/memory.h>
@@ -30,6 +29,13 @@ struct ptrauth_keys {
 	struct ptrauth_key apga;
 };
 
+/*
+ * Only include random.h once ptrauth_keys_* structures are defined
+ * to avoid yet another circular include hell (random.h * ends up
+ * including asm/smp.h, which requires ptrauth_keys_kernel).
+ */
+#include <linux/random.h>
+
 static inline void ptrauth_keys_init(struct ptrauth_keys *keys)
 {
 	if (system_supports_address_auth()) {
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 701eaa738187..1dc2f99e6508 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -62,6 +62,7 @@
 #define PSR_AA32_I_BIT		0x00000080
 #define PSR_AA32_A_BIT		0x00000100
 #define PSR_AA32_E_BIT		0x00000200
+#define PSR_AA32_PAN_BIT	0x00400000
 #define PSR_AA32_SSBS_BIT	0x00800000
 #define PSR_AA32_DIT_BIT	0x01000000
 #define PSR_AA32_Q_BIT		0x08000000
diff --git a/arch/arm64/include/asm/simd.h b/arch/arm64/include/asm/simd.h
index 7e245b9e03a5..7434844036d3 100644
--- a/arch/arm64/include/asm/simd.h
+++ b/arch/arm64/include/asm/simd.h
@@ -12,9 +12,9 @@
 #include <linux/preempt.h>
 #include <linux/types.h>
 
-#ifdef CONFIG_KERNEL_MODE_NEON
+DECLARE_PER_CPU(bool, fpsimd_context_busy);
 
-DECLARE_PER_CPU(bool, kernel_neon_busy);
+#ifdef CONFIG_KERNEL_MODE_NEON
 
 /*
  * may_use_simd - whether it is allowable at this time to issue SIMD
@@ -26,15 +26,15 @@ DECLARE_PER_CPU(bool, kernel_neon_busy);
 static __must_check inline bool may_use_simd(void)
 {
 	/*
-	 * kernel_neon_busy is only set while preemption is disabled,
+	 * fpsimd_context_busy is only set while preemption is disabled,
 	 * and is clear whenever preemption is enabled. Since
-	 * this_cpu_read() is atomic w.r.t. preemption, kernel_neon_busy
+	 * this_cpu_read() is atomic w.r.t. preemption, fpsimd_context_busy
 	 * cannot change under our feet -- if it's set we cannot be
 	 * migrated, and if it's clear we cannot be migrated to a CPU
 	 * where it is set.
 	 */
 	return !in_irq() && !irqs_disabled() && !in_nmi() &&
-		!this_cpu_read(kernel_neon_busy);
+		!this_cpu_read(fpsimd_context_busy);
 }
 
 #else /* ! CONFIG_KERNEL_MODE_NEON */
diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h
index 65299a2dcf9c..cfc0672013f6 100644
--- a/arch/arm64/include/asm/syscall.h
+++ b/arch/arm64/include/asm/syscall.h
@@ -34,6 +34,10 @@ static inline long syscall_get_error(struct task_struct *task,
 				     struct pt_regs *regs)
 {
 	unsigned long error = regs->regs[0];
+
+	if (is_compat_thread(task_thread_info(task)))
+		error = sign_extend64(error, 31);
+
 	return IS_ERR_VALUE(error) ? error : 0;
 }
 
@@ -47,7 +51,13 @@ static inline void syscall_set_return_value(struct task_struct *task,
 					    struct pt_regs *regs,
 					    int error, long val)
 {
-	regs->regs[0] = (long) error ? error : val;
+	if (error)
+		val = error;
+
+	if (is_compat_thread(task_thread_info(task)))
+		val = lower_32_bits(val);
+
+	regs->regs[0] = val;
 }
 
 #define SYSCALL_MAX_ARGS 6
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index cd7f7ce1a56a..8692ee6b56f3 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -49,7 +49,9 @@
 #ifndef CONFIG_BROKEN_GAS_INST
 
 #ifdef __ASSEMBLY__
-#define __emit_inst(x)			.inst (x)
+// The space separator is omitted so that __emit_inst(x) can be parsed as
+// either an assembler directive or an assembler macro argument.
+#define __emit_inst(x)			.inst(x)
 #else
 #define __emit_inst(x)			".inst " __stringify((x)) "\n\t"
 #endif
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 2372e97db29c..90441da764ab 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -100,6 +100,7 @@ void arch_release_task_struct(struct task_struct *tsk);
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
 #define _TIF_FSCHECK		(1 << TIF_FSCHECK)
+#define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
 #define _TIF_32BIT		(1 << TIF_32BIT)
 #define _TIF_SVE		(1 << TIF_SVE)
 
diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h
index e932284993d4..b1296c839a3e 100644
--- a/arch/arm64/include/uapi/asm/ptrace.h
+++ b/arch/arm64/include/uapi/asm/ptrace.h
@@ -49,6 +49,7 @@
 #define PSR_SSBS_BIT	0x00001000
 #define PSR_PAN_BIT	0x00400000
 #define PSR_UAO_BIT	0x00800000
+#define PSR_DIT_BIT	0x01000000
 #define PSR_V_BIT	0x10000000
 #define PSR_C_BIT	0x20000000
 #define PSR_Z_BIT	0x40000000
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index 3a58e9db5cfe..a100483b47c4 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -274,7 +274,7 @@ int apei_claim_sea(struct pt_regs *regs)
 	if (!IS_ENABLED(CONFIG_ACPI_APEI_GHES))
 		return err;
 
-	current_flags = arch_local_save_flags();
+	current_flags = local_daif_save_flags();
 
 	/*
 	 * SEA can interrupt SError, mask it and describe this as an NMI so
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index d1757ef1b1e7..73039949b5ce 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -43,20 +43,8 @@ bool alternative_is_applied(u16 cpufeature)
  */
 static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc)
 {
-	unsigned long replptr;
-
-	if (kernel_text_address(pc))
-		return true;
-
-	replptr = (unsigned long)ALT_REPL_PTR(alt);
-	if (pc >= replptr && pc <= (replptr + alt->alt_len))
-		return false;
-
-	/*
-	 * Branching into *another* alternate sequence is doomed, and
-	 * we're not even trying to fix it up.
-	 */
-	BUG();
+	unsigned long replptr = (unsigned long)ALT_REPL_PTR(alt);
+	return !(pc >= replptr && pc <= (replptr + alt->alt_len));
 }
 
 #define align_down(x, a)	((unsigned long)(x) & ~(((unsigned long)(a)) - 1))
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index ca158be21f83..bcb14d11232f 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -601,7 +601,7 @@ static struct undef_hook setend_hooks[] = {
 	},
 	{
 		/* Thumb mode */
-		.instr_mask	= 0x0000fff7,
+		.instr_mask	= 0xfffffff7,
 		.instr_val	= 0x0000b650,
 		.pstate_mask	= (PSR_AA32_T_BIT | PSR_AA32_MODE_MASK),
 		.pstate_val	= (PSR_AA32_T_BIT | PSR_AA32_MODE_USR),
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index c87593ea489b..2ce5da59778d 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -87,13 +87,21 @@ has_mismatched_cache_type(const struct arm64_cpu_capabilities *entry,
 }
 
 static void
-cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *__unused)
+cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *cap)
 {
 	u64 mask = arm64_ftr_reg_ctrel0.strict_mask;
+	bool enable_uct_trap = false;
 
 	/* Trap CTR_EL0 access on this CPU, only if it has a mismatch */
 	if ((read_cpuid_cachetype() & mask) !=
 	    (arm64_ftr_reg_ctrel0.sys_val & mask))
+		enable_uct_trap = true;
+
+	/* ... or if the system is affected by an erratum */
+	if (cap->capability == ARM64_WORKAROUND_1542419)
+		enable_uct_trap = true;
+
+	if (enable_uct_trap)
 		sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0);
 }
 
@@ -580,6 +588,7 @@ static const struct midr_range spectre_v2_safe_list[] = {
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
 	MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53),
+	MIDR_ALL_VERSIONS(MIDR_HISI_TSV110),
 	{ /* sentinel */ }
 };
 
@@ -631,6 +640,18 @@ check_branch_predictor(const struct arm64_cpu_capabilities *entry, int scope)
 	return (need_wa > 0);
 }
 
+static bool __maybe_unused
+has_neoverse_n1_erratum_1542419(const struct arm64_cpu_capabilities *entry,
+				int scope)
+{
+	u32 midr = read_cpuid_id();
+	bool has_dic = read_cpuid_cachetype() & BIT(CTR_DIC_SHIFT);
+	const struct midr_range range = MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1);
+
+	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+	return is_midr_in_range(midr, &range) && has_dic;
+}
+
 #ifdef CONFIG_HARDEN_EL2_VECTORS
 
 static const struct midr_range arm64_harden_el2_vectors[] = {
@@ -936,6 +957,16 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.matches = has_cortex_a76_erratum_1463225,
 	},
 #endif
+#ifdef CONFIG_ARM64_ERRATUM_1542419
+	{
+		/* we depend on the firmware portion for correctness */
+		.desc = "ARM erratum 1542419 (kernel portion)",
+		.capability = ARM64_WORKAROUND_1542419,
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.matches = has_neoverse_n1_erratum_1542419,
+		.cpu_enable = cpu_enable_trap_ctr_access,
+	},
+#endif
 	{
 	}
 };
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index d3fbb89a31e5..7bbea1b179f8 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -32,9 +32,7 @@ static unsigned long elf_hwcap __read_mostly;
 #define COMPAT_ELF_HWCAP_DEFAULT	\
 				(COMPAT_HWCAP_HALF|COMPAT_HWCAP_THUMB|\
 				 COMPAT_HWCAP_FAST_MULT|COMPAT_HWCAP_EDSP|\
-				 COMPAT_HWCAP_TLS|COMPAT_HWCAP_VFP|\
-				 COMPAT_HWCAP_VFPv3|COMPAT_HWCAP_VFPv4|\
-				 COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV|\
+				 COMPAT_HWCAP_TLS|COMPAT_HWCAP_IDIV|\
 				 COMPAT_HWCAP_LPAE)
 unsigned int compat_elf_hwcap __read_mostly = COMPAT_ELF_HWCAP_DEFAULT;
 unsigned int compat_elf_hwcap2 __read_mostly;
@@ -175,11 +173,16 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = {
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SM4_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SHA3_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BITPERM_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_AES_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SVEVER_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SM4_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SHA3_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BITPERM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_AES_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SVEVER_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
@@ -1361,7 +1364,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 	{
 		/* FP/SIMD is not implemented */
 		.capability = ARM64_HAS_NO_FPSIMD,
-		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.type = ARM64_CPUCAP_BOOT_RESTRICTED_CPU_LOCAL_FEATURE,
 		.min_field_value = 0,
 		.matches = has_no_fpsimd,
 	},
@@ -1589,6 +1592,12 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.match_list = list,						\
 	}
 
+#define HWCAP_CAP_MATCH(match, cap_type, cap)					\
+	{									\
+		__HWCAP_CAP(#cap, cap_type, cap)				\
+		.matches = match,						\
+	}
+
 #ifdef CONFIG_ARM64_PTR_AUTH
 static const struct arm64_cpu_capabilities ptr_auth_hwcap_addr_matches[] = {
 	{
@@ -1660,8 +1669,35 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	{},
 };
 
+#ifdef CONFIG_COMPAT
+static bool compat_has_neon(const struct arm64_cpu_capabilities *cap, int scope)
+{
+	/*
+	 * Check that all of MVFR1_EL1.{SIMDSP, SIMDInt, SIMDLS} are available,
+	 * in line with that of arm32 as in vfp_init(). We make sure that the
+	 * check is future proof, by making sure value is non-zero.
+	 */
+	u32 mvfr1;
+
+	WARN_ON(scope == SCOPE_LOCAL_CPU && preemptible());
+	if (scope == SCOPE_SYSTEM)
+		mvfr1 = read_sanitised_ftr_reg(SYS_MVFR1_EL1);
+	else
+		mvfr1 = read_sysreg_s(SYS_MVFR1_EL1);
+
+	return cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_SIMDSP_SHIFT) &&
+		cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_SIMDINT_SHIFT) &&
+		cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_SIMDLS_SHIFT);
+}
+#endif
+
 static const struct arm64_cpu_capabilities compat_elf_hwcaps[] = {
 #ifdef CONFIG_COMPAT
+	HWCAP_CAP_MATCH(compat_has_neon, CAP_COMPAT_HWCAP, COMPAT_HWCAP_NEON),
+	HWCAP_CAP(SYS_MVFR1_EL1, MVFR1_SIMDFMAC_SHIFT, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv4),
+	/* Arm v8 mandates MVFR0.FPDP == {0, 2}. So, piggy back on this for the presence of VFP support */
+	HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_FPDP_SHIFT, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFP),
+	HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_FPDP_SHIFT, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv3),
 	HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_AES_SHIFT, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_PMULL),
 	HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_AES_SHIFT, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_AES),
 	HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_SHA1_SHIFT, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA1),
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 48222a4760c2..d64a3c1e1b6b 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -141,17 +141,20 @@ postcore_initcall(debug_monitors_init);
 /*
  * Single step API and exception handling.
  */
-static void set_regs_spsr_ss(struct pt_regs *regs)
+static void set_user_regs_spsr_ss(struct user_pt_regs *regs)
 {
 	regs->pstate |= DBG_SPSR_SS;
 }
-NOKPROBE_SYMBOL(set_regs_spsr_ss);
+NOKPROBE_SYMBOL(set_user_regs_spsr_ss);
 
-static void clear_regs_spsr_ss(struct pt_regs *regs)
+static void clear_user_regs_spsr_ss(struct user_pt_regs *regs)
 {
 	regs->pstate &= ~DBG_SPSR_SS;
 }
-NOKPROBE_SYMBOL(clear_regs_spsr_ss);
+NOKPROBE_SYMBOL(clear_user_regs_spsr_ss);
+
+#define set_regs_spsr_ss(r)	set_user_regs_spsr_ss(&(r)->user_regs)
+#define clear_regs_spsr_ss(r)	clear_user_regs_spsr_ss(&(r)->user_regs)
 
 static DEFINE_SPINLOCK(debug_hook_lock);
 static LIST_HEAD(user_step_hook);
@@ -393,17 +396,26 @@ void user_rewind_single_step(struct task_struct *task)
 	 * If single step is active for this thread, then set SPSR.SS
 	 * to 1 to avoid returning to the active-pending state.
 	 */
-	if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP))
+	if (test_tsk_thread_flag(task, TIF_SINGLESTEP))
 		set_regs_spsr_ss(task_pt_regs(task));
 }
 NOKPROBE_SYMBOL(user_rewind_single_step);
 
 void user_fastforward_single_step(struct task_struct *task)
 {
-	if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP))
+	if (test_tsk_thread_flag(task, TIF_SINGLESTEP))
 		clear_regs_spsr_ss(task_pt_regs(task));
 }
 
+void user_regs_reset_single_step(struct user_pt_regs *regs,
+				 struct task_struct *task)
+{
+	if (test_tsk_thread_flag(task, TIF_SINGLESTEP))
+		set_user_regs_spsr_ss(regs);
+	else
+		clear_user_regs_spsr_ss(regs);
+}
+
 /* Kernel API */
 void kernel_enable_single_step(struct pt_regs *regs)
 {
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 0cfcf5c237c5..eef3dc2488e2 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -82,7 +82,8 @@
  * To prevent this from racing with the manipulation of the task's FPSIMD state
  * from task context and thereby corrupting the state, it is necessary to
  * protect any manipulation of a task's fpsimd_state or TIF_FOREIGN_FPSTATE
- * flag with local_bh_disable() unless softirqs are already masked.
+ * flag with {, __}get_cpu_fpsimd_context(). This will still allow softirqs to
+ * run but prevent them to use FPSIMD.
  *
  * For a certain task, the sequence may look something like this:
  * - the task gets scheduled in; if both the task's fpsimd_cpu field
@@ -145,6 +146,56 @@ extern void __percpu *efi_sve_state;
 
 #endif /* ! CONFIG_ARM64_SVE */
 
+DEFINE_PER_CPU(bool, fpsimd_context_busy);
+EXPORT_PER_CPU_SYMBOL(fpsimd_context_busy);
+
+static void __get_cpu_fpsimd_context(void)
+{
+	bool busy = __this_cpu_xchg(fpsimd_context_busy, true);
+
+	WARN_ON(busy);
+}
+
+/*
+ * Claim ownership of the CPU FPSIMD context for use by the calling context.
+ *
+ * The caller may freely manipulate the FPSIMD context metadata until
+ * put_cpu_fpsimd_context() is called.
+ *
+ * The double-underscore version must only be called if you know the task
+ * can't be preempted.
+ */
+static void get_cpu_fpsimd_context(void)
+{
+	preempt_disable();
+	__get_cpu_fpsimd_context();
+}
+
+static void __put_cpu_fpsimd_context(void)
+{
+	bool busy = __this_cpu_xchg(fpsimd_context_busy, false);
+
+	WARN_ON(!busy); /* No matching get_cpu_fpsimd_context()? */
+}
+
+/*
+ * Release the CPU FPSIMD context.
+ *
+ * Must be called from a context in which get_cpu_fpsimd_context() was
+ * previously called, with no call to put_cpu_fpsimd_context() in the
+ * meantime.
+ */
+static void put_cpu_fpsimd_context(void)
+{
+	__put_cpu_fpsimd_context();
+	preempt_enable();
+}
+
+static bool have_cpu_fpsimd_context(void)
+{
+	return !preemptible() && __this_cpu_read(fpsimd_context_busy);
+}
+
 /*
  * Call __sve_free() directly only if you know task can't be scheduled
  * or preempted.
@@ -215,12 +266,11 @@ static void sve_free(struct task_struct *task)
  * This function should be called only when the FPSIMD/SVE state in
  * thread_struct is known to be up to date, when preparing to enter
  * userspace.
- *
- * Softirqs (and preemption) must be disabled.
  */
 static void task_fpsimd_load(void)
 {
-	WARN_ON(!in_softirq() && !irqs_disabled());
+	WARN_ON(!system_supports_fpsimd());
+	WARN_ON(!have_cpu_fpsimd_context());
 
 	if (system_supports_sve() && test_thread_flag(TIF_SVE))
 		sve_load_state(sve_pffr(&current->thread),
@@ -233,16 +283,15 @@ static void task_fpsimd_load(void)
 /*
  * Ensure FPSIMD/SVE storage in memory for the loaded context is up to
  * date with respect to the CPU registers.
- *
- * Softirqs (and preemption) must be disabled.
  */
-void fpsimd_save(void)
+static void fpsimd_save(void)
 {
 	struct fpsimd_last_state_struct const *last =
 		this_cpu_ptr(&fpsimd_last_state);
 	/* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */
 
-	WARN_ON(!in_softirq() && !irqs_disabled());
+	WARN_ON(!system_supports_fpsimd());
+	WARN_ON(!have_cpu_fpsimd_context());
 
 	if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) {
 		if (system_supports_sve() && test_thread_flag(TIF_SVE)) {
@@ -289,7 +338,7 @@ static unsigned int find_supported_vector_length(unsigned int vl)
 	return sve_vl_from_vq(__bit_to_vq(bit));
 }
 
-#ifdef CONFIG_SYSCTL
+#if defined(CONFIG_ARM64_SVE) && defined(CONFIG_SYSCTL)
 
 static int sve_proc_do_default_vl(struct ctl_table *table, int write,
 				  void __user *buffer, size_t *lenp,
@@ -335,9 +384,9 @@ static int __init sve_sysctl_init(void)
 	return 0;
 }
 
-#else /* ! CONFIG_SYSCTL */
+#else /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */
 static int __init sve_sysctl_init(void) { return 0; }
-#endif /* ! CONFIG_SYSCTL */
+#endif /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */
 
 #define ZREG(sve_state, vq, n) ((char *)(sve_state) +		\
 	(SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET))
@@ -364,7 +413,8 @@ static __uint128_t arm64_cpu_to_le128(__uint128_t x)
  * task->thread.sve_state.
  *
  * Task can be a non-runnable task, or current.  In the latter case,
- * softirqs (and preemption) must be disabled.
+ * the caller must have ownership of the cpu FPSIMD context before calling
+ * this function.
  * task->thread.sve_state must point to at least sve_state_size(task)
  * bytes of allocated kernel memory.
  * task->thread.uw.fpsimd_state must be up to date before calling this
@@ -393,7 +443,8 @@ static void fpsimd_to_sve(struct task_struct *task)
  * task->thread.uw.fpsimd_state.
  *
  * Task can be a non-runnable task, or current.  In the latter case,
- * softirqs (and preemption) must be disabled.
+ * the caller must have ownership of the cpu FPSIMD context before calling
+ * this function.
  * task->thread.sve_state must point to at least sve_state_size(task)
  * bytes of allocated kernel memory.
  * task->thread.sve_state must be up to date before calling this function.
@@ -557,7 +608,7 @@ int sve_set_vector_length(struct task_struct *task,
 	 * non-SVE thread.
 	 */
 	if (task == current) {
-		local_bh_disable();
+		get_cpu_fpsimd_context();
 
 		fpsimd_save();
 	}
@@ -567,7 +618,7 @@ int sve_set_vector_length(struct task_struct *task,
 		sve_to_fpsimd(task);
 
 	if (task == current)
-		local_bh_enable();
+		put_cpu_fpsimd_context();
 
 	/*
 	 * Force reallocation of task SVE state to the correct size
@@ -880,7 +931,7 @@ asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs)
 
 	sve_alloc(current);
 
-	local_bh_disable();
+	get_cpu_fpsimd_context();
 
 	fpsimd_save();
 
@@ -891,7 +942,7 @@ asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs)
 	if (test_and_set_thread_flag(TIF_SVE))
 		WARN_ON(1); /* SVE access shouldn't have trapped */
 
-	local_bh_enable();
+	put_cpu_fpsimd_context();
 }
 
 /*
@@ -935,6 +986,8 @@ void fpsimd_thread_switch(struct task_struct *next)
 	if (!system_supports_fpsimd())
 		return;
 
+	__get_cpu_fpsimd_context();
+
 	/* Save unsaved fpsimd state, if any: */
 	fpsimd_save();
 
@@ -949,6 +1002,8 @@ void fpsimd_thread_switch(struct task_struct *next)
 
 	update_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE,
 			       wrong_task || wrong_cpu);
+
+	__put_cpu_fpsimd_context();
 }
 
 void fpsimd_flush_thread(void)
@@ -958,7 +1013,7 @@ void fpsimd_flush_thread(void)
 	if (!system_supports_fpsimd())
 		return;
 
-	local_bh_disable();
+	get_cpu_fpsimd_context();
 
 	fpsimd_flush_task_state(current);
 	memset(&current->thread.uw.fpsimd_state, 0,
@@ -999,7 +1054,7 @@ void fpsimd_flush_thread(void)
 			current->thread.sve_vl_onexec = 0;
 	}
 
-	local_bh_enable();
+	put_cpu_fpsimd_context();
 }
 
 /*
@@ -1011,9 +1066,9 @@ void fpsimd_preserve_current_state(void)
 	if (!system_supports_fpsimd())
 		return;
 
-	local_bh_disable();
+	get_cpu_fpsimd_context();
 	fpsimd_save();
-	local_bh_enable();
+	put_cpu_fpsimd_context();
 }
 
 /*
@@ -1030,13 +1085,15 @@ void fpsimd_signal_preserve_current_state(void)
 
 /*
  * Associate current's FPSIMD context with this cpu
- * Preemption must be disabled when calling this function.
+ * The caller must have ownership of the cpu FPSIMD context before calling
+ * this function.
  */
 void fpsimd_bind_task_to_cpu(void)
 {
 	struct fpsimd_last_state_struct *last =
 		this_cpu_ptr(&fpsimd_last_state);
 
+	WARN_ON(!system_supports_fpsimd());
 	last->st = &current->thread.uw.fpsimd_state;
 	last->sve_state = current->thread.sve_state;
 	last->sve_vl = current->thread.sve_vl;
@@ -1059,6 +1116,7 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
 	struct fpsimd_last_state_struct *last =
 		this_cpu_ptr(&fpsimd_last_state);
 
+	WARN_ON(!system_supports_fpsimd());
 	WARN_ON(!in_softirq() && !irqs_disabled());
 
 	last->st = st;
@@ -1073,17 +1131,28 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
  */
 void fpsimd_restore_current_state(void)
 {
-	if (!system_supports_fpsimd())
+	/*
+	 * For the tasks that were created before we detected the absence of
+	 * FP/SIMD, the TIF_FOREIGN_FPSTATE could be set via fpsimd_thread_switch(),
+	 * e.g, init. This could be then inherited by the children processes.
+	 * If we later detect that the system doesn't support FP/SIMD,
+	 * we must clear the flag for  all the tasks to indicate that the
+	 * FPSTATE is clean (as we can't have one) to avoid looping for ever in
+	 * do_notify_resume().
+	 */
+	if (!system_supports_fpsimd()) {
+		clear_thread_flag(TIF_FOREIGN_FPSTATE);
 		return;
+	}
 
-	local_bh_disable();
+	get_cpu_fpsimd_context();
 
 	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
 		task_fpsimd_load();
 		fpsimd_bind_task_to_cpu();
 	}
 
-	local_bh_enable();
+	put_cpu_fpsimd_context();
 }
 
 /*
@@ -1093,10 +1162,10 @@ void fpsimd_restore_current_state(void)
  */
 void fpsimd_update_current_state(struct user_fpsimd_state const *state)
 {
-	if (!system_supports_fpsimd())
+	if (WARN_ON(!system_supports_fpsimd()))
 		return;
 
-	local_bh_disable();
+	get_cpu_fpsimd_context();
 
 	current->thread.uw.fpsimd_state = *state;
 	if (system_supports_sve() && test_thread_flag(TIF_SVE))
@@ -1107,7 +1176,7 @@ void fpsimd_update_current_state(struct user_fpsimd_state const *state)
 
 	clear_thread_flag(TIF_FOREIGN_FPSTATE);
 
-	local_bh_enable();
+	put_cpu_fpsimd_context();
 }
 
 /*
@@ -1124,7 +1193,13 @@ void fpsimd_update_current_state(struct user_fpsimd_state const *state)
 void fpsimd_flush_task_state(struct task_struct *t)
 {
 	t->thread.fpsimd_cpu = NR_CPUS;
-
+	/*
+	 * If we don't support fpsimd, bail out after we have
+	 * reset the fpsimd_cpu for this task and clear the
+	 * FPSTATE.
+	 */
+	if (!system_supports_fpsimd())
+		return;
 	barrier();
 	set_tsk_thread_flag(t, TIF_FOREIGN_FPSTATE);
 
@@ -1133,18 +1208,32 @@ void fpsimd_flush_task_state(struct task_struct *t)
 
 /*
  * Invalidate any task's FPSIMD state that is present on this cpu.
- * This function must be called with softirqs disabled.
+ * The FPSIMD context should be acquired with get_cpu_fpsimd_context()
+ * before calling this function.
  */
-void fpsimd_flush_cpu_state(void)
+static void fpsimd_flush_cpu_state(void)
 {
+	WARN_ON(!system_supports_fpsimd());
 	__this_cpu_write(fpsimd_last_state.st, NULL);
 	set_thread_flag(TIF_FOREIGN_FPSTATE);
 }
 
-#ifdef CONFIG_KERNEL_MODE_NEON
+/*
+ * Save the FPSIMD state to memory and invalidate cpu view.
+ * This function must be called with preemption disabled.
+ */
+void fpsimd_save_and_flush_cpu_state(void)
+{
+	if (!system_supports_fpsimd())
+		return;
+	WARN_ON(preemptible());
+	__get_cpu_fpsimd_context();
+	fpsimd_save();
+	fpsimd_flush_cpu_state();
+	__put_cpu_fpsimd_context();
+}
 
-DEFINE_PER_CPU(bool, kernel_neon_busy);
-EXPORT_PER_CPU_SYMBOL(kernel_neon_busy);
+#ifdef CONFIG_KERNEL_MODE_NEON
 
 /*
  * Kernel-side NEON support functions
@@ -1170,19 +1259,13 @@ void kernel_neon_begin(void)
 
 	BUG_ON(!may_use_simd());
 
-	local_bh_disable();
-
-	__this_cpu_write(kernel_neon_busy, true);
+	get_cpu_fpsimd_context();
 
 	/* Save unsaved fpsimd state, if any: */
 	fpsimd_save();
 
 	/* Invalidate any task state remaining in the fpsimd regs: */
 	fpsimd_flush_cpu_state();
-
-	preempt_disable();
-
-	local_bh_enable();
 }
 EXPORT_SYMBOL(kernel_neon_begin);
 
@@ -1197,15 +1280,10 @@ EXPORT_SYMBOL(kernel_neon_begin);
  */
 void kernel_neon_end(void)
 {
-	bool busy;
-
 	if (!system_supports_fpsimd())
 		return;
 
-	busy = __this_cpu_xchg(kernel_neon_busy, false);
-	WARN_ON(!busy);	/* No matching kernel_neon_begin()? */
-
-	preempt_enable();
+	put_cpu_fpsimd_context();
 }
 EXPORT_SYMBOL(kernel_neon_end);
 
@@ -1297,8 +1375,7 @@ static int fpsimd_cpu_pm_notifier(struct notifier_block *self,
 {
 	switch (cmd) {
 	case CPU_PM_ENTER:
-		fpsimd_save();
-		fpsimd_flush_cpu_state();
+		fpsimd_save_and_flush_cpu_state();
 		break;
 	case CPU_PM_EXIT:
 		break;
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 2cdacd1c141b..191ad192a741 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -391,13 +391,19 @@ __create_page_tables:
 
 	/*
 	 * Since the page tables have been populated with non-cacheable
-	 * accesses (MMU disabled), invalidate the idmap and swapper page
-	 * tables again to remove any speculatively loaded cache lines.
+	 * accesses (MMU disabled), invalidate those tables again to
+	 * remove any speculatively loaded cache lines.
 	 */
+	dmb	sy
+
 	adrp	x0, idmap_pg_dir
+	adrp	x1, idmap_pg_end
+	sub	x1, x1, x0
+	bl	__inval_dcache_area
+
+	adrp	x0, init_pg_dir
 	adrp	x1, init_pg_end
 	sub	x1, x1, x0
-	dmb	sy
 	bl	__inval_dcache_area
 
 	ret	x28
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 67b3bae50b92..29eb4636d095 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -726,6 +726,27 @@ static u64 get_distance_from_watchpoint(unsigned long addr, u64 val,
 		return 0;
 }
 
+static int watchpoint_report(struct perf_event *wp, unsigned long addr,
+			     struct pt_regs *regs)
+{
+	int step = is_default_overflow_handler(wp);
+	struct arch_hw_breakpoint *info = counter_arch_bp(wp);
+
+	info->trigger = addr;
+
+	/*
+	 * If we triggered a user watchpoint from a uaccess routine, then
+	 * handle the stepping ourselves since userspace really can't help
+	 * us with this.
+	 */
+	if (!user_mode(regs) && info->ctrl.privilege == AARCH64_BREAKPOINT_EL0)
+		step = 1;
+	else
+		perf_bp_event(wp, regs);
+
+	return step;
+}
+
 static int watchpoint_handler(unsigned long addr, unsigned int esr,
 			      struct pt_regs *regs)
 {
@@ -735,7 +756,6 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr,
 	u64 val;
 	struct perf_event *wp, **slots;
 	struct debug_info *debug_info;
-	struct arch_hw_breakpoint *info;
 	struct arch_hw_breakpoint_ctrl ctrl;
 
 	slots = this_cpu_ptr(wp_on_reg);
@@ -773,25 +793,13 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr,
 		if (dist != 0)
 			continue;
 
-		info = counter_arch_bp(wp);
-		info->trigger = addr;
-		perf_bp_event(wp, regs);
-
-		/* Do we need to handle the stepping? */
-		if (is_default_overflow_handler(wp))
-			step = 1;
+		step = watchpoint_report(wp, addr, regs);
 	}
-	if (min_dist > 0 && min_dist != -1) {
-		/* No exact match found. */
-		wp = slots[closest_match];
-		info = counter_arch_bp(wp);
-		info->trigger = addr;
-		perf_bp_event(wp, regs);
 
-		/* Do we need to handle the stepping? */
-		if (is_default_overflow_handler(wp))
-			step = 1;
-	}
+	/* No exact match found? */
+	if (min_dist > 0 && min_dist != -1)
+		step = watchpoint_report(slots[closest_match], addr, regs);
+
 	rcu_read_unlock();
 
 	if (!step)
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index 84b059ed04fc..63b511735e5c 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -1508,16 +1508,10 @@ static u32 aarch64_encode_immediate(u64 imm,
 				    u32 insn)
 {
 	unsigned int immr, imms, n, ones, ror, esz, tmp;
-	u64 mask = ~0UL;
-
-	/* Can't encode full zeroes or full ones */
-	if (!imm || !~imm)
-		return AARCH64_BREAK_FAULT;
+	u64 mask;
 
 	switch (variant) {
 	case AARCH64_INSN_VARIANT_32BIT:
-		if (upper_32_bits(imm))
-			return AARCH64_BREAK_FAULT;
 		esz = 32;
 		break;
 	case AARCH64_INSN_VARIANT_64BIT:
@@ -1529,6 +1523,12 @@ static u32 aarch64_encode_immediate(u64 imm,
 		return AARCH64_BREAK_FAULT;
 	}
 
+	mask = GENMASK(esz - 1, 0);
+
+	/* Can't encode full zeroes, full ones, or value wider than the mask */
+	if (!imm || imm == mask || imm & ~mask)
+		return AARCH64_BREAK_FAULT;
+
 	/*
 	 * Inverse of Replicate(). Try to spot a repeating pattern
 	 * with a pow2 stride.
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index 43119922341f..1a157ca33262 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -252,7 +252,7 @@ static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
 	if (!kgdb_single_step)
 		return DBG_HOOK_ERROR;
 
-	kgdb_handle_exception(1, SIGTRAP, 0, regs);
+	kgdb_handle_exception(0, SIGTRAP, 0, regs);
 	return DBG_HOOK_HANDLED;
 }
 NOKPROBE_SYMBOL(kgdb_step_brk_fn);
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index 0df8493624e0..cc049ff5c6a5 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -189,6 +189,7 @@ void machine_kexec(struct kimage *kimage)
 	 * the offline CPUs. Therefore, we must use the __* variant here.
 	 */
 	__flush_icache_range((uintptr_t)reboot_code_buffer,
+			     (uintptr_t)reboot_code_buffer +
 			     arm64_relocate_new_kernel_size);
 
 	/* Flush the kimage list and its buffers. */
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 96e90e270042..1439cff99a28 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -154,7 +154,7 @@ armv8pmu_events_sysfs_show(struct device *dev,
 
 	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
 
-	return sprintf(page, "event=0x%03llx\n", pmu_attr->id);
+	return sprintf(page, "event=0x%04llx\n", pmu_attr->id);
 }
 
 #define ARMV8_EVENT_ATTR_RESOLVE(m) #m
@@ -303,10 +303,13 @@ armv8pmu_event_attr_is_visible(struct kobject *kobj,
 	    test_bit(pmu_attr->id, cpu_pmu->pmceid_bitmap))
 		return attr->mode;
 
-	pmu_attr->id -= ARMV8_PMUV3_EXT_COMMON_EVENT_BASE;
-	if (pmu_attr->id < ARMV8_PMUV3_MAX_COMMON_EVENTS &&
-	    test_bit(pmu_attr->id, cpu_pmu->pmceid_ext_bitmap))
-		return attr->mode;
+	if (pmu_attr->id >= ARMV8_PMUV3_EXT_COMMON_EVENT_BASE) {
+		u64 id = pmu_attr->id - ARMV8_PMUV3_EXT_COMMON_EVENT_BASE;
+
+		if (id < ARMV8_PMUV3_MAX_COMMON_EVENTS &&
+		    test_bit(id, cpu_pmu->pmceid_ext_bitmap))
+			return attr->mode;
+	}
 
 	return 0;
 }
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
index 0bbac612146e..7c6ae5cf0365 100644
--- a/arch/arm64/kernel/perf_regs.c
+++ b/arch/arm64/kernel/perf_regs.c
@@ -15,15 +15,34 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 		return 0;
 
 	/*
-	 * Compat (i.e. 32 bit) mode:
-	 * - PC has been set in the pt_regs struct in kernel_entry,
-	 * - Handle SP and LR here.
+	 * Our handling of compat tasks (PERF_SAMPLE_REGS_ABI_32) is weird, but
+	 * we're stuck with it for ABI compatability reasons.
+	 *
+	 * For a 32-bit consumer inspecting a 32-bit task, then it will look at
+	 * the first 16 registers (see arch/arm/include/uapi/asm/perf_regs.h).
+	 * These correspond directly to a prefix of the registers saved in our
+	 * 'struct pt_regs', with the exception of the PC, so we copy that down
+	 * (x15 corresponds to SP_hyp in the architecture).
+	 *
+	 * So far, so good.
+	 *
+	 * The oddity arises when a 64-bit consumer looks at a 32-bit task and
+	 * asks for registers beyond PERF_REG_ARM_MAX. In this case, we return
+	 * SP_usr, LR_usr and PC in the positions where the AArch64 SP, LR and
+	 * PC registers would normally live. The initial idea was to allow a
+	 * 64-bit unwinder to unwind a 32-bit task and, although it's not clear
+	 * how well that works in practice, somebody might be relying on it.
+	 *
+	 * At the time we make a sample, we don't know whether the consumer is
+	 * 32-bit or 64-bit, so we have to cater for both possibilities.
 	 */
 	if (compat_user_mode(regs)) {
 		if ((u32)idx == PERF_REG_ARM64_SP)
 			return regs->compat_sp;
 		if ((u32)idx == PERF_REG_ARM64_LR)
 			return regs->compat_lr;
+		if (idx == 15)
+			return regs->pc;
 	}
 
 	if ((u32)idx == PERF_REG_ARM64_SP)
@@ -32,6 +51,10 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 	if ((u32)idx == PERF_REG_ARM64_PC)
 		return regs->pc;
 
+	if (perf_reg_abi(current) == PERF_SAMPLE_REGS_ABI_32
+		&& idx == 15)
+		return regs->pc;
+
 	return regs->regs[idx];
 }
 
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 398601b29627..c6d7a2912e30 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -455,6 +455,13 @@ static void ssbs_thread_switch(struct task_struct *next)
 	if (unlikely(next->flags & PF_KTHREAD))
 		return;
 
+	/*
+	 * If all CPUs implement the SSBS extension, then we just need to
+	 * context-switch the PSTATE field.
+	 */
+	if (cpu_have_feature(cpu_feature(SSBS)))
+		return;
+
 	/* If the mitigation is enabled, then we leave SSBS clear. */
 	if ((arm64_get_ssbd_state() == ARM64_SSBD_FORCE_ENABLE) ||
 	    test_tsk_thread_flag(next, TIF_SSBD))
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index da2441d7b066..49bc065cf3f0 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -615,6 +615,13 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset,
 	return 0;
 }
 
+static int fpr_active(struct task_struct *target, const struct user_regset *regset)
+{
+	if (!system_supports_fpsimd())
+		return -ENODEV;
+	return regset->n;
+}
+
 /*
  * TODO: update fp accessors for lazy context switching (sync/flush hwstate)
  */
@@ -637,6 +644,9 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset,
 		   unsigned int pos, unsigned int count,
 		   void *kbuf, void __user *ubuf)
 {
+	if (!system_supports_fpsimd())
+		return -EINVAL;
+
 	if (target == current)
 		fpsimd_preserve_current_state();
 
@@ -676,6 +686,9 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset,
 {
 	int ret;
 
+	if (!system_supports_fpsimd())
+		return -EINVAL;
+
 	ret = __fpr_set(target, regset, pos, count, kbuf, ubuf, 0);
 	if (ret)
 		return ret;
@@ -1134,6 +1147,7 @@ static const struct user_regset aarch64_regsets[] = {
 		 */
 		.size = sizeof(u32),
 		.align = sizeof(u32),
+		.active = fpr_active,
 		.get = fpr_get,
 		.set = fpr_set
 	},
@@ -1348,6 +1362,9 @@ static int compat_vfp_get(struct task_struct *target,
 	compat_ulong_t fpscr;
 	int ret, vregs_end_pos;
 
+	if (!system_supports_fpsimd())
+		return -EINVAL;
+
 	uregs = &target->thread.uw.fpsimd_state;
 
 	if (target == current)
@@ -1381,6 +1398,9 @@ static int compat_vfp_set(struct task_struct *target,
 	compat_ulong_t fpscr;
 	int ret, vregs_end_pos;
 
+	if (!system_supports_fpsimd())
+		return -EINVAL;
+
 	uregs = &target->thread.uw.fpsimd_state;
 
 	vregs_end_pos = VFP_STATE_SIZE - sizeof(compat_ulong_t);
@@ -1438,6 +1458,7 @@ static const struct user_regset aarch32_regsets[] = {
 		.n = VFP_STATE_SIZE / sizeof(compat_ulong_t),
 		.size = sizeof(compat_ulong_t),
 		.align = sizeof(compat_ulong_t),
+		.active = fpr_active,
 		.get = compat_vfp_get,
 		.set = compat_vfp_set
 	},
@@ -1798,12 +1819,23 @@ static void tracehook_report_syscall(struct pt_regs *regs,
 	saved_reg = regs->regs[regno];
 	regs->regs[regno] = dir;
 
-	if (dir == PTRACE_SYSCALL_EXIT)
+	if (dir == PTRACE_SYSCALL_ENTER) {
+		if (tracehook_report_syscall_entry(regs))
+			forget_syscall(regs);
+		regs->regs[regno] = saved_reg;
+	} else if (!test_thread_flag(TIF_SINGLESTEP)) {
 		tracehook_report_syscall_exit(regs, 0);
-	else if (tracehook_report_syscall_entry(regs))
-		forget_syscall(regs);
+		regs->regs[regno] = saved_reg;
+	} else {
+		regs->regs[regno] = saved_reg;
 
-	regs->regs[regno] = saved_reg;
+		/*
+		 * Signal a pseudo-step exception since we are stepping but
+		 * tracer modifications to the registers may have rewound the
+		 * state machine.
+		 */
+		tracehook_report_syscall_exit(regs, 1);
+	}
 }
 
 int syscall_trace_enter(struct pt_regs *regs)
@@ -1826,12 +1858,14 @@ int syscall_trace_enter(struct pt_regs *regs)
 
 void syscall_trace_exit(struct pt_regs *regs)
 {
+	unsigned long flags = READ_ONCE(current_thread_info()->flags);
+
 	audit_syscall_exit(regs);
 
-	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+	if (flags & _TIF_SYSCALL_TRACEPOINT)
 		trace_sys_exit(regs, regs_return_value(regs));
 
-	if (test_thread_flag(TIF_SYSCALL_TRACE))
+	if (flags & (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP))
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT);
 
 	rseq_syscall(regs);
@@ -1909,8 +1943,8 @@ static int valid_native_regs(struct user_pt_regs *regs)
  */
 int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task)
 {
-	if (!test_tsk_thread_flag(task, TIF_SINGLESTEP))
-		regs->pstate &= ~DBG_SPSR_SS;
+	/* https://lore.kernel.org/lkml/20191118131525.GA4180@willie-the-truck */
+	user_regs_reset_single_step(regs, task);
 
 	if (is_compat_thread(task_thread_info(task)))
 		return valid_compat_regs(regs);
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index dd2cdc0d5be2..ddb757b2c3e5 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -782,7 +782,6 @@ static void setup_restart_syscall(struct pt_regs *regs)
  */
 static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 {
-	struct task_struct *tsk = current;
 	sigset_t *oldset = sigmask_to_save();
 	int usig = ksig->sig;
 	int ret;
@@ -806,14 +805,8 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	 */
 	ret |= !valid_user_regs(&regs->user_regs, current);
 
-	/*
-	 * Fast forward the stepping logic so we step into the signal
-	 * handler.
-	 */
-	if (!ret)
-		user_fastforward_single_step(tsk);
-
-	signal_setup_done(ret, ksig, 0);
+	/* Step into the signal handler if we are stepping */
+	signal_setup_done(ret, ksig, test_thread_flag(TIF_SINGLESTEP));
 }
 
 /*
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index a1aed6a1b8da..538b4ba66f5f 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -959,11 +959,22 @@ void tick_broadcast(const struct cpumask *mask)
 }
 #endif
 
+/*
+ * The number of CPUs online, not counting this CPU (which may not be
+ * fully online and so not counted in num_online_cpus()).
+ */
+static inline unsigned int num_other_online_cpus(void)
+{
+	unsigned int this_cpu_online = cpu_online(smp_processor_id());
+
+	return num_online_cpus() - this_cpu_online;
+}
+
 void smp_send_stop(void)
 {
 	unsigned long timeout;
 
-	if (num_online_cpus() > 1) {
+	if (num_other_online_cpus()) {
 		cpumask_t mask;
 
 		cpumask_copy(&mask, cpu_online_mask);
@@ -976,10 +987,10 @@ void smp_send_stop(void)
 
 	/* Wait up to one second for other CPUs to stop */
 	timeout = USEC_PER_SEC;
-	while (num_online_cpus() > 1 && timeout--)
+	while (num_other_online_cpus() && timeout--)
 		udelay(1);
 
-	if (num_online_cpus() > 1)
+	if (num_other_online_cpus())
 		pr_warning("SMP: failed to stop secondary CPUs %*pbl\n",
 			   cpumask_pr_args(cpu_online_mask));
 
@@ -1002,7 +1013,11 @@ void crash_smp_send_stop(void)
 
 	cpus_stopped = 1;
 
-	if (num_online_cpus() == 1) {
+	/*
+	 * If this cpu is the only one alive at this point in time, online or
+	 * not, there are no stop messages to be sent around, so just back out.
+	 */
+	if (num_other_online_cpus() == 0) {
 		sdei_mask_local_cpu();
 		return;
 	}
@@ -1010,7 +1025,7 @@ void crash_smp_send_stop(void)
 	cpumask_copy(&mask, cpu_online_mask);
 	cpumask_clear_cpu(smp_processor_id(), &mask);
 
-	atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
+	atomic_set(&waiting_for_crash_ipi, num_other_online_cpus());
 
 	pr_crit("SMP: stopping secondary CPUs\n");
 	smp_cross_call(&mask, IPI_CPU_CRASH_STOP);
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index f1cb64959427..3c18c2454089 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/compat.h>
+#include <linux/cpufeature.h>
 #include <linux/personality.h>
 #include <linux/sched.h>
 #include <linux/sched/signal.h>
@@ -17,6 +18,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/system_misc.h>
+#include <asm/tlbflush.h>
 #include <asm/unistd.h>
 
 static long
@@ -30,6 +32,15 @@ __do_compat_cache_op(unsigned long start, unsigned long end)
 		if (fatal_signal_pending(current))
 			return 0;
 
+		if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) {
+			/*
+			 * The workaround requires an inner-shareable tlbi.
+			 * We pick the reserved-ASID to minimise the impact.
+			 */
+			__tlbi(aside1is, __TLBI_VADDR(0, 0));
+			dsb(ish);
+		}
+
 		ret = __flush_cache_user_range(start, start + chunk);
 		if (ret)
 			return ret;
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index 871c739f060a..1457a0ba83db 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -50,6 +50,9 @@ static void invoke_syscall(struct pt_regs *regs, unsigned int scno,
 		ret = do_ni_syscall(regs, scno);
 	}
 
+	if (is_compat_task())
+		ret = lower_32_bits(ret);
+
 	regs->regs[0] = ret;
 }
 
@@ -121,7 +124,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 	if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) {
 		local_daif_mask();
 		flags = current_thread_info()->flags;
-		if (!has_syscall_work(flags)) {
+		if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) {
 			/*
 			 * We're off to userspace, where interrupts are
 			 * always enabled after we restore the flags from
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index b6706a886037..7788e4ea131b 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -480,6 +480,15 @@ static void ctr_read_handler(unsigned int esr, struct pt_regs *regs)
 	int rt = ESR_ELx_SYS64_ISS_RT(esr);
 	unsigned long val = arm64_ftr_reg_user_value(&arm64_ftr_reg_ctrel0);
 
+	if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) {
+		/* Hide DIC so that we can trap the unnecessary maintenance...*/
+		val &= ~BIT(CTR_DIC_SHIFT);
+
+		/* ... and fake IminLine to reduce the number of traps. */
+		val &= ~CTR_IMINLINE_MASK;
+		val |= (PAGE_SHIFT - 2) & CTR_IMINLINE_MASK;
+	}
+
 	pt_regs_write_reg(regs, rt, val);
 
 	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 803b24d2464a..61d63657ab59 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -142,6 +142,7 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);
 	idmap_pg_dir = .;
 	. += IDMAP_DIR_SIZE;
+	idmap_pg_end = .;
 
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 	tramp_pg_dir = .;
@@ -171,9 +172,6 @@ SECTIONS
 		*(.altinstructions)
 		__alt_instructions_end = .;
 	}
-	.altinstr_replacement : {
-		*(.altinstr_replacement)
-	}
 
 	. = ALIGN(PAGE_SIZE);
 	__inittext_end = .;
diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c
index 43487f035385..7a7e425616b5 100644
--- a/arch/arm64/kvm/debug.c
+++ b/arch/arm64/kvm/debug.c
@@ -101,7 +101,7 @@ void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu)
 void kvm_arm_setup_debug(struct kvm_vcpu *vcpu)
 {
 	bool trap_debug = !(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY);
-	unsigned long mdscr;
+	unsigned long mdscr, orig_mdcr_el2 = vcpu->arch.mdcr_el2;
 
 	trace_kvm_arm_setup_debug(vcpu, vcpu->guest_debug);
 
@@ -197,6 +197,10 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu)
 	if (vcpu_read_sys_reg(vcpu, MDSCR_EL1) & (DBG_MDSCR_KDE | DBG_MDSCR_MDE))
 		vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY;
 
+	/* Write mdcr_el2 changes since vcpu_load on VHE systems */
+	if (has_vhe() && orig_mdcr_el2 != vcpu->arch.mdcr_el2)
+		write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
+
 	trace_kvm_arm_set_dreg32("MDCR_EL2", vcpu->arch.mdcr_el2);
 	trace_kvm_arm_set_dreg32("MDSCR_EL1", vcpu_read_sys_reg(vcpu, MDSCR_EL1));
 }
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index 6e3c9c8b2df9..525010504f9d 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -112,9 +112,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) {
 		u64 *guest_zcr = &vcpu->arch.ctxt.sys_regs[ZCR_EL1];
 
-		/* Clean guest FP state to memory and invalidate cpu view */
-		fpsimd_save();
-		fpsimd_flush_cpu_state();
+		fpsimd_save_and_flush_cpu_state();
 
 		if (guest_has_sve)
 			*guest_zcr = read_sysreg_s(SYS_ZCR_EL12);
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index dfd626447482..5271ab366bee 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -202,6 +202,13 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	}
 
 	memcpy((u32 *)regs + off, valp, KVM_REG_SIZE(reg->id));
+
+	if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) {
+		int i;
+
+		for (i = 0; i < 16; i++)
+			*vcpu_reg32(vcpu, i) = (u32)*vcpu_reg32(vcpu, i);
+	}
 out:
 	return err;
 }
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 706cca23f0d2..1249f68a9418 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -162,31 +162,16 @@ static int handle_sve(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return 1;
 }
 
-#define __ptrauth_save_key(regs, key)						\
-({										\
-	regs[key ## KEYLO_EL1] = read_sysreg_s(SYS_ ## key ## KEYLO_EL1);	\
-	regs[key ## KEYHI_EL1] = read_sysreg_s(SYS_ ## key ## KEYHI_EL1);	\
-})
-
 /*
  * Handle the guest trying to use a ptrauth instruction, or trying to access a
  * ptrauth register.
  */
 void kvm_arm_vcpu_ptrauth_trap(struct kvm_vcpu *vcpu)
 {
-	struct kvm_cpu_context *ctxt;
-
-	if (vcpu_has_ptrauth(vcpu)) {
+	if (vcpu_has_ptrauth(vcpu))
 		vcpu_ptrauth_enable(vcpu);
-		ctxt = vcpu->arch.host_cpu_context;
-		__ptrauth_save_key(ctxt->sys_regs, APIA);
-		__ptrauth_save_key(ctxt->sys_regs, APIB);
-		__ptrauth_save_key(ctxt->sys_regs, APDA);
-		__ptrauth_save_key(ctxt->sys_regs, APDB);
-		__ptrauth_save_key(ctxt->sys_regs, APGA);
-	} else {
+	else
 		kvm_inject_undefined(vcpu);
-	}
 }
 
 /*
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 160be2b4696d..dc41b505507d 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -136,11 +136,15 @@ ENTRY(__kvm_handle_stub_hvc)
 
 1:	cmp	x0, #HVC_RESET_VECTORS
 	b.ne	1f
-reset:
+
 	/*
-	 * Reset kvm back to the hyp stub. Do not clobber x0-x4 in
-	 * case we coming via HVC_SOFT_RESTART.
+	 * Set the HVC_RESET_VECTORS return code before entering the common
+	 * path so that we do not clobber x0-x2 in case we are coming via
+	 * HVC_SOFT_RESTART.
 	 */
+	mov	x0, xzr
+reset:
+	/* Reset kvm back to the hyp stub. */
 	mrs	x5, sctlr_el2
 	ldr	x6, =SCTLR_ELx_FLAGS
 	bic	x5, x5, x6		// Clear SCTL_M and etc
@@ -151,7 +155,6 @@ reset:
 	/* Install stub vectors */
 	adr_l	x5, __hyp_stub_vectors
 	msr	vbar_el2, x5
-	mov	x0, xzr
 	eret
 
 1:	/* Bad stub call */
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 58f281b6ca4a..9c7912923b74 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -28,7 +28,15 @@
 /* Check whether the FP regs were dirtied while in the host-side run loop: */
 static bool __hyp_text update_fp_enabled(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->arch.host_thread_info->flags & _TIF_FOREIGN_FPSTATE)
+	/*
+	 * When the system doesn't support FP/SIMD, we cannot rely on
+	 * the _TIF_FOREIGN_FPSTATE flag. However, we always inject an
+	 * abort on the very first access to FP and thus we should never
+	 * see KVM_ARM64_FP_ENABLED. For added safety, make sure we always
+	 * trap the accesses.
+	 */
+	if (!system_supports_fpsimd() ||
+	    vcpu->arch.host_thread_info->flags & _TIF_FOREIGN_FPSTATE)
 		vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED |
 				      KVM_ARM64_FP_HOST);
 
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index a9d25a305af5..a364a4ad5479 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -14,9 +14,6 @@
 #include <asm/kvm_emulate.h>
 #include <asm/esr.h>
 
-#define PSTATE_FAULT_BITS_64 	(PSR_MODE_EL1h | PSR_A_BIT | PSR_F_BIT | \
-				 PSR_I_BIT | PSR_D_BIT)
-
 #define CURRENT_EL_SP_EL0_VECTOR	0x0
 #define CURRENT_EL_SP_ELx_VECTOR	0x200
 #define LOWER_EL_AArch64_VECTOR		0x400
@@ -50,6 +47,69 @@ static u64 get_except_vector(struct kvm_vcpu *vcpu, enum exception_type type)
 	return vcpu_read_sys_reg(vcpu, VBAR_EL1) + exc_offset + type;
 }
 
+/*
+ * When an exception is taken, most PSTATE fields are left unchanged in the
+ * handler. However, some are explicitly overridden (e.g. M[4:0]). Luckily all
+ * of the inherited bits have the same position in the AArch64/AArch32 SPSR_ELx
+ * layouts, so we don't need to shuffle these for exceptions from AArch32 EL0.
+ *
+ * For the SPSR_ELx layout for AArch64, see ARM DDI 0487E.a page C5-429.
+ * For the SPSR_ELx layout for AArch32, see ARM DDI 0487E.a page C5-426.
+ *
+ * Here we manipulate the fields in order of the AArch64 SPSR_ELx layout, from
+ * MSB to LSB.
+ */
+static unsigned long get_except64_pstate(struct kvm_vcpu *vcpu)
+{
+	unsigned long sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1);
+	unsigned long old, new;
+
+	old = *vcpu_cpsr(vcpu);
+	new = 0;
+
+	new |= (old & PSR_N_BIT);
+	new |= (old & PSR_Z_BIT);
+	new |= (old & PSR_C_BIT);
+	new |= (old & PSR_V_BIT);
+
+	// TODO: TCO (if/when ARMv8.5-MemTag is exposed to guests)
+
+	new |= (old & PSR_DIT_BIT);
+
+	// PSTATE.UAO is set to zero upon any exception to AArch64
+	// See ARM DDI 0487E.a, page D5-2579.
+
+	// PSTATE.PAN is unchanged unless SCTLR_ELx.SPAN == 0b0
+	// SCTLR_ELx.SPAN is RES1 when ARMv8.1-PAN is not implemented
+	// See ARM DDI 0487E.a, page D5-2578.
+	new |= (old & PSR_PAN_BIT);
+	if (!(sctlr & SCTLR_EL1_SPAN))
+		new |= PSR_PAN_BIT;
+
+	// PSTATE.SS is set to zero upon any exception to AArch64
+	// See ARM DDI 0487E.a, page D2-2452.
+
+	// PSTATE.IL is set to zero upon any exception to AArch64
+	// See ARM DDI 0487E.a, page D1-2306.
+
+	// PSTATE.SSBS is set to SCTLR_ELx.DSSBS upon any exception to AArch64
+	// See ARM DDI 0487E.a, page D13-3258
+	if (sctlr & SCTLR_ELx_DSSBS)
+		new |= PSR_SSBS_BIT;
+
+	// PSTATE.BTYPE is set to zero upon any exception to AArch64
+	// See ARM DDI 0487E.a, pages D1-2293 to D1-2294.
+
+	new |= PSR_D_BIT;
+	new |= PSR_A_BIT;
+	new |= PSR_I_BIT;
+	new |= PSR_F_BIT;
+
+	new |= PSR_MODE_EL1h;
+
+	return new;
+}
+
 static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr)
 {
 	unsigned long cpsr = *vcpu_cpsr(vcpu);
@@ -59,7 +119,7 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr
 	vcpu_write_elr_el1(vcpu, *vcpu_pc(vcpu));
 	*vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync);
 
-	*vcpu_cpsr(vcpu) = PSTATE_FAULT_BITS_64;
+	*vcpu_cpsr(vcpu) = get_except64_pstate(vcpu);
 	vcpu_write_spsr(vcpu, cpsr);
 
 	vcpu_write_sys_reg(vcpu, addr, FAR_EL1);
@@ -94,7 +154,7 @@ static void inject_undef64(struct kvm_vcpu *vcpu)
 	vcpu_write_elr_el1(vcpu, *vcpu_pc(vcpu));
 	*vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync);
 
-	*vcpu_cpsr(vcpu) = PSTATE_FAULT_BITS_64;
+	*vcpu_cpsr(vcpu) = get_except64_pstate(vcpu);
 	vcpu_write_spsr(vcpu, cpsr);
 
 	/*
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index f4a8ae918827..784d485218ca 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -258,7 +258,7 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 {
 	const struct kvm_regs *cpu_reset;
-	int ret = -EINVAL;
+	int ret;
 	bool loaded;
 
 	/* Reset PMU outside of the non-preemptible section */
@@ -281,15 +281,19 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 
 	if (test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) ||
 	    test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features)) {
-		if (kvm_vcpu_enable_ptrauth(vcpu))
+		if (kvm_vcpu_enable_ptrauth(vcpu)) {
+			ret = -EINVAL;
 			goto out;
+		}
 	}
 
 	switch (vcpu->arch.target) {
 	default:
 		if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) {
-			if (!cpu_has_32bit_el1())
+			if (!cpu_has_32bit_el1()) {
+				ret = -EINVAL;
 				goto out;
+			}
 			cpu_reset = &default_regs_reset32;
 		} else {
 			cpu_reset = &default_regs_reset;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 9a7de66f4476..6c888d5431b5 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1276,10 +1276,16 @@ static bool access_clidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 static bool access_csselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 			  const struct sys_reg_desc *r)
 {
+	int reg = r->reg;
+
+	/* See the 32bit mapping in kvm_host.h */
+	if (p->is_aarch32)
+		reg = r->reg / 2;
+
 	if (p->is_write)
-		vcpu_write_sys_reg(vcpu, p->regval, r->reg);
+		vcpu_write_sys_reg(vcpu, p->regval, reg);
 	else
-		p->regval = vcpu_read_sys_reg(vcpu, r->reg);
+		p->regval = vcpu_read_sys_reg(vcpu, reg);
 	return true;
 }
 
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 414b8e0f19e0..b071c6cdf999 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -432,7 +432,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	struct task_struct *tsk;
 	struct mm_struct *mm;
 	vm_fault_t fault, major = 0;
-	unsigned long vm_flags = VM_READ | VM_WRITE;
+	unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC;
 	unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	if (notify_page_fault(regs, esr))
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index f475e54fbc43..946414cd9ca9 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -230,6 +230,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 		ptep = (pte_t *)pudp;
 	} else if (sz == (PAGE_SIZE * CONT_PTES)) {
 		pmdp = pmd_alloc(mm, pudp, addr);
+		if (!pmdp)
+			return NULL;
 
 		WARN_ON(addr & (sz - 1));
 		/*
diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig
index cf798a1628cf..820438c14f34 100644
--- a/arch/csky/Kconfig
+++ b/arch/csky/Kconfig
@@ -32,6 +32,7 @@ config CSKY
 	select GENERIC_SMP_IDLE_THREAD
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_AUDITSYSCALL
+	select HAVE_COPY_THREAD_TLS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
@@ -70,7 +71,7 @@ config CPU_HAS_TLBI
 config CPU_HAS_LDSTEX
 	bool
 	help
-	  For SMP, CPU needs "ldex&stex" instrcutions to atomic operations.
+	  For SMP, CPU needs "ldex&stex" instructions for atomic operations.
 
 config CPU_NEED_TLBSYNC
 	bool
diff --git a/arch/csky/abiv1/inc/abi/entry.h b/arch/csky/abiv1/inc/abi/entry.h
index 7ab78bd0f3b1..61d94ec7dd16 100644
--- a/arch/csky/abiv1/inc/abi/entry.h
+++ b/arch/csky/abiv1/inc/abi/entry.h
@@ -16,14 +16,16 @@
 #define LSAVE_A4	40
 #define LSAVE_A5	44
 
+#define usp ss1
+
 .macro USPTOKSP
-	mtcr	sp, ss1
+	mtcr	sp, usp
 	mfcr	sp, ss0
 .endm
 
 .macro KSPTOUSP
 	mtcr	sp, ss0
-	mfcr	sp, ss1
+	mfcr	sp, usp
 .endm
 
 .macro	SAVE_ALL epc_inc
@@ -45,7 +47,13 @@
 	add	lr, r13
 	stw     lr, (sp, 8)
 
+	mov	lr, sp
+	addi	lr, 32
+	addi	lr, 32
+	addi	lr, 16
+	bt	2f
 	mfcr	lr, ss1
+2:
 	stw     lr, (sp, 16)
 
 	stw     a0, (sp, 20)
@@ -79,9 +87,10 @@
 	ldw     a0, (sp, 12)
 	mtcr    a0, epsr
 	btsti   a0, 31
+	bt      1f
 	ldw     a0, (sp, 16)
 	mtcr	a0, ss1
-
+1:
 	ldw     a0, (sp, 24)
 	ldw     a1, (sp, 28)
 	ldw     a2, (sp, 32)
@@ -102,9 +111,9 @@
 	addi	sp, 32
 	addi	sp, 8
 
-	bt      1f
+	bt      2f
 	KSPTOUSP
-1:
+2:
 	rte
 .endm
 
@@ -158,15 +167,12 @@
 	 *   BA     Reserved  C   D   V
 	 */
 	cprcr	r6, cpcr30
-	lsri	r6, 28
-	lsli	r6, 28
+	lsri	r6, 29
+	lsli	r6, 29
 	addi	r6, 0xe
 	cpwcr	r6, cpcr30
 
-	lsri	r6, 28
-	addi	r6, 2
-	lsli	r6, 28
-	addi	r6, 0xe
+	movi	r6, 0
 	cpwcr	r6, cpcr31
 .endm
 
diff --git a/arch/csky/abiv2/fpu.c b/arch/csky/abiv2/fpu.c
index e7e11344005a..ff92bf4af7df 100644
--- a/arch/csky/abiv2/fpu.c
+++ b/arch/csky/abiv2/fpu.c
@@ -10,11 +10,6 @@
 #define MTCR_DIST	0xC0006420
 #define MFCR_DIST	0xC0006020
 
-void __init init_fpu(void)
-{
-	mtcr("cr<1, 2>", 0);
-}
-
 /*
  * fpu_libc_helper() is to help libc to excute:
  *  - mfcr %a, cr<1, 2>
diff --git a/arch/csky/abiv2/inc/abi/entry.h b/arch/csky/abiv2/inc/abi/entry.h
index 9897a16b45e5..ac8f65a3e75a 100644
--- a/arch/csky/abiv2/inc/abi/entry.h
+++ b/arch/csky/abiv2/inc/abi/entry.h
@@ -13,6 +13,8 @@
 #define LSAVE_A1	28
 #define LSAVE_A2	32
 #define LSAVE_A3	36
+#define LSAVE_A4	40
+#define LSAVE_A5	44
 
 #define KSPTOUSP
 #define USPTOKSP
@@ -31,7 +33,13 @@
 
 	mfcr	lr, epsr
 	stw	lr, (sp, 12)
+	btsti   lr, 31
+	bf      1f
+	addi    lr, sp, 152
+	br	2f
+1:
 	mfcr	lr, usp
+2:
 	stw	lr, (sp, 16)
 
 	stw     a0, (sp, 20)
@@ -64,8 +72,10 @@
 	mtcr	a0, epc
 	ldw	a0, (sp, 12)
 	mtcr	a0, epsr
+	btsti   a0, 31
 	ldw	a0, (sp, 16)
 	mtcr	a0, usp
+	mtcr	a0, ss0
 
 #ifdef CONFIG_CPU_HAS_HILO
 	ldw	a0, (sp, 140)
@@ -86,6 +96,9 @@
 	addi    sp, 40
 	ldm     r16-r30, (sp)
 	addi    sp, 72
+	bf	1f
+	mfcr	sp, ss0
+1:
 	rte
 .endm
 
@@ -214,16 +227,13 @@
 	 */
 	mfcr	r6, cr<30, 15> /* Get MSA0 */
 2:
-	lsri	r6, 28
-	lsli	r6, 28
+	lsri	r6, 29
+	lsli	r6, 29
 	addi	r6, 0x1ce
 	mtcr	r6, cr<30, 15> /* Set MSA0 */
 
-	lsri	r6, 28
-	addi	r6, 2
-	lsli	r6, 28
-	addi	r6, 0x1ce
-	mtcr	r6, cr<31, 15> /* Set MSA1 */
+	movi    r6, 0
+	mtcr	r6, cr<31, 15> /* Clr MSA1 */
 
 	/* enable MMU */
 	mfcr    r6, cr18
diff --git a/arch/csky/abiv2/inc/abi/fpu.h b/arch/csky/abiv2/inc/abi/fpu.h
index 22ca3cf2794a..09e2700a3693 100644
--- a/arch/csky/abiv2/inc/abi/fpu.h
+++ b/arch/csky/abiv2/inc/abi/fpu.h
@@ -9,7 +9,8 @@
 
 int fpu_libc_helper(struct pt_regs *regs);
 void fpu_fpe(struct pt_regs *regs);
-void __init init_fpu(void);
+
+static inline void init_fpu(void) { mtcr("cr<1, 2>", 0); }
 
 void save_to_user_fp(struct user_fp *user_fp);
 void restore_from_user_fp(struct user_fp *user_fp);
diff --git a/arch/csky/include/asm/processor.h b/arch/csky/include/asm/processor.h
index 21e0bd5293dd..c6bcd7f7c720 100644
--- a/arch/csky/include/asm/processor.h
+++ b/arch/csky/include/asm/processor.h
@@ -43,6 +43,7 @@ extern struct cpuinfo_csky cpu_data[];
 struct thread_struct {
 	unsigned long  ksp;       /* kernel stack pointer */
 	unsigned long  sr;        /* saved status register */
+	unsigned long  trap_no;   /* saved status register */
 
 	/* FPU regs */
 	struct user_fp __aligned(16) user_fp;
diff --git a/arch/csky/include/asm/uaccess.h b/arch/csky/include/asm/uaccess.h
index eaa1c3403a42..60f8a4112588 100644
--- a/arch/csky/include/asm/uaccess.h
+++ b/arch/csky/include/asm/uaccess.h
@@ -254,7 +254,7 @@ do {								\
 
 extern int __get_user_bad(void);
 
-#define __copy_user(to, from, n)			\
+#define ___copy_to_user(to, from, n)			\
 do {							\
 	int w0, w1, w2, w3;				\
 	asm volatile(					\
@@ -289,31 +289,34 @@ do {							\
 	"       subi    %0, 4           \n"		\
 	"       br      3b              \n"		\
 	"5:     cmpnei  %0, 0           \n"  /* 1B */   \
-	"       bf      8f              \n"		\
+	"       bf      13f             \n"		\
 	"       ldb     %3, (%2, 0)     \n"		\
 	"6:     stb     %3, (%1, 0)     \n"		\
 	"       addi    %2,  1          \n"		\
 	"       addi    %1,  1          \n"		\
 	"       subi    %0,  1          \n"		\
 	"       br      5b              \n"		\
-	"7:     br      8f              \n"		\
+	"7:     subi	%0,  4          \n"		\
+	"8:     subi	%0,  4          \n"		\
+	"12:    subi	%0,  4          \n"		\
+	"       br      13f             \n"		\
 	".section __ex_table, \"a\"     \n"		\
 	".align   2                     \n"		\
-	".long    2b, 7b                \n"		\
-	".long    9b, 7b                \n"		\
-	".long   10b, 7b                \n"		\
+	".long    2b, 13f               \n"		\
+	".long    4b, 13f               \n"		\
+	".long    6b, 13f               \n"		\
+	".long    9b, 12b               \n"		\
+	".long   10b, 8b                \n"		\
 	".long   11b, 7b                \n"		\
-	".long    4b, 7b                \n"		\
-	".long    6b, 7b                \n"		\
 	".previous                      \n"		\
-	"8:                             \n"		\
+	"13:                            \n"		\
 	: "=r"(n), "=r"(to), "=r"(from), "=r"(w0),	\
 	  "=r"(w1), "=r"(w2), "=r"(w3)			\
 	: "0"(n), "1"(to), "2"(from)			\
 	: "memory");					\
 } while (0)
 
-#define __copy_user_zeroing(to, from, n)		\
+#define ___copy_from_user(to, from, n)			\
 do {							\
 	int tmp;					\
 	int nsave;					\
@@ -356,22 +359,22 @@ do {							\
 	"       addi    %1,  1          \n"		\
 	"       subi    %0,  1          \n"		\
 	"       br      5b              \n"		\
-	"8:     mov     %3, %0          \n"		\
-	"       movi    %4, 0           \n"		\
-	"9:     stb     %4, (%1, 0)     \n"		\
-	"       addi    %1, 1           \n"		\
-	"       subi    %3, 1           \n"		\
-	"       cmpnei  %3, 0           \n"		\
-	"       bt      9b              \n"		\
-	"       br      7f              \n"		\
+	"8:     stw     %3, (%1, 0)     \n"		\
+	"       subi    %0, 4           \n"		\
+	"       bf      7f              \n"		\
+	"9:     subi    %0, 8           \n"		\
+	"       bf      7f              \n"		\
+	"13:    stw     %3, (%1, 8)     \n"		\
+	"       subi    %0, 12          \n"		\
+	"       bf      7f              \n"		\
 	".section __ex_table, \"a\"     \n"		\
 	".align   2                     \n"		\
-	".long    2b, 8b                \n"		\
+	".long    2b, 7f                \n"		\
+	".long    4b, 7f                \n"		\
+	".long    6b, 7f                \n"		\
 	".long   10b, 8b                \n"		\
-	".long   11b, 8b                \n"		\
-	".long   12b, 8b                \n"		\
-	".long    4b, 8b                \n"		\
-	".long    6b, 8b                \n"		\
+	".long   11b, 9b                \n"		\
+	".long   12b,13b                \n"		\
 	".previous                      \n"		\
 	"7:                             \n"		\
 	: "=r"(n), "=r"(to), "=r"(from), "=r"(nsave),	\
diff --git a/arch/csky/include/uapi/asm/unistd.h b/arch/csky/include/uapi/asm/unistd.h
index ec60e49cea66..78c2a35e4c8a 100644
--- a/arch/csky/include/uapi/asm/unistd.h
+++ b/arch/csky/include/uapi/asm/unistd.h
@@ -1,7 +1,10 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
 
+#define __ARCH_WANT_STAT64
+#define __ARCH_WANT_NEW_STAT
 #define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_CLONE3
 #define __ARCH_WANT_SET_GET_RLIMIT
 #define __ARCH_WANT_TIME32_SYSCALLS
 #include <asm-generic/unistd.h>
diff --git a/arch/csky/kernel/atomic.S b/arch/csky/kernel/atomic.S
index 5b84f11485ae..3821ef9b7567 100644
--- a/arch/csky/kernel/atomic.S
+++ b/arch/csky/kernel/atomic.S
@@ -17,10 +17,12 @@ ENTRY(csky_cmpxchg)
 	mfcr	a3, epc
 	addi	a3, TRAP0_SIZE
 
-	subi    sp, 8
+	subi    sp, 16
 	stw     a3, (sp, 0)
 	mfcr    a3, epsr
 	stw     a3, (sp, 4)
+	mfcr	a3, usp
+	stw     a3, (sp, 8)
 
 	psrset	ee
 #ifdef CONFIG_CPU_HAS_LDSTEX
@@ -47,7 +49,9 @@ ENTRY(csky_cmpxchg)
 	mtcr	a3, epc
 	ldw     a3, (sp, 4)
 	mtcr	a3, epsr
-	addi	sp, 8
+	ldw     a3, (sp, 8)
+	mtcr	a3, usp
+	addi	sp, 16
 	KSPTOUSP
 	rte
 END(csky_cmpxchg)
diff --git a/arch/csky/kernel/entry.S b/arch/csky/kernel/entry.S
index a7e84ccccbd8..e18c2f02b6f3 100644
--- a/arch/csky/kernel/entry.S
+++ b/arch/csky/kernel/entry.S
@@ -162,8 +162,10 @@ csky_syscall_trace:
 	ldw	a3, (sp, LSAVE_A3)
 #if defined(__CSKYABIV2__)
 	subi	sp, 8
-	stw	r5, (sp, 0x4)
-	stw	r4, (sp, 0x0)
+	ldw	r9, (sp, LSAVE_A4)
+	stw	r9, (sp, 0x0)
+	ldw	r9, (sp, LSAVE_A5)
+	stw	r9, (sp, 0x4)
 #else
 	ldw	r6, (sp, LSAVE_A4)
 	ldw	r7, (sp, LSAVE_A5)
@@ -312,8 +314,6 @@ ENTRY(__switch_to)
 
 	mfcr	a2, psr			/* Save PSR value */
 	stw	a2, (a3, THREAD_SR)	/* Save PSR in task struct */
-	bclri	a2, 6			/* Disable interrupts */
-	mtcr	a2, psr
 
 	SAVE_SWITCH_STACK
 
diff --git a/arch/csky/kernel/head.S b/arch/csky/kernel/head.S
index 61989f9241c0..17ed9d250480 100644
--- a/arch/csky/kernel/head.S
+++ b/arch/csky/kernel/head.S
@@ -21,6 +21,11 @@ END(_start)
 ENTRY(_start_smp_secondary)
 	SETUP_MMU
 
+	/* copy msa1 from CPU0 */
+	lrw     r6, secondary_msa1
+	ld.w	r6, (r6, 0)
+	mtcr	r6, cr<31, 15>
+
 	/* set stack point */
 	lrw     r6, secondary_stack
 	ld.w	r6, (r6, 0)
diff --git a/arch/csky/kernel/perf_callchain.c b/arch/csky/kernel/perf_callchain.c
index e68ff375c8f8..ab55e98ee8f6 100644
--- a/arch/csky/kernel/perf_callchain.c
+++ b/arch/csky/kernel/perf_callchain.c
@@ -12,12 +12,17 @@ struct stackframe {
 
 static int unwind_frame_kernel(struct stackframe *frame)
 {
-	if (kstack_end((void *)frame->fp))
+	unsigned long low = (unsigned long)task_stack_page(current);
+	unsigned long high = low + THREAD_SIZE;
+
+	if (unlikely(frame->fp < low || frame->fp > high))
 		return -EPERM;
-	if (frame->fp & 0x3 || frame->fp < TASK_SIZE)
+
+	if (kstack_end((void *)frame->fp) || frame->fp & 0x3)
 		return -EPERM;
 
 	*frame = *(struct stackframe *)frame->fp;
+
 	if (__kernel_text_address(frame->lr)) {
 		int graph = 0;
 
diff --git a/arch/csky/kernel/process.c b/arch/csky/kernel/process.c
index e555740c0be5..1bde082990ef 100644
--- a/arch/csky/kernel/process.c
+++ b/arch/csky/kernel/process.c
@@ -34,10 +34,11 @@ unsigned long thread_saved_pc(struct task_struct *tsk)
 	return sw->r15;
 }
 
-int copy_thread(unsigned long clone_flags,
+int copy_thread_tls(unsigned long clone_flags,
 		unsigned long usp,
 		unsigned long kthread_arg,
-		struct task_struct *p)
+		struct task_struct *p,
+		unsigned long tls)
 {
 	struct switch_stack *childstack;
 	struct pt_regs *childregs = task_pt_regs(p);
@@ -64,7 +65,7 @@ int copy_thread(unsigned long clone_flags,
 			childregs->usp = usp;
 		if (clone_flags & CLONE_SETTLS)
 			task_thread_info(p)->tp_value = childregs->tls
-						      = childregs->regs[0];
+						      = tls;
 
 		childregs->a0 = 0;
 		childstack->r15 = (unsigned long) ret_from_fork;
diff --git a/arch/csky/kernel/setup.c b/arch/csky/kernel/setup.c
index 23ee604aafdb..2c1e253abb74 100644
--- a/arch/csky/kernel/setup.c
+++ b/arch/csky/kernel/setup.c
@@ -24,26 +24,9 @@ struct screen_info screen_info = {
 };
 #endif
 
-phys_addr_t __init_memblock memblock_end_of_REG0(void)
-{
-	return (memblock.memory.regions[0].base +
-		memblock.memory.regions[0].size);
-}
-
-phys_addr_t __init_memblock memblock_start_of_REG1(void)
-{
-	return memblock.memory.regions[1].base;
-}
-
-size_t __init_memblock memblock_size_of_REG1(void)
-{
-	return memblock.memory.regions[1].size;
-}
-
 static void __init csky_memblock_init(void)
 {
 	unsigned long zone_size[MAX_NR_ZONES];
-	unsigned long zhole_size[MAX_NR_ZONES];
 	signed long size;
 
 	memblock_reserve(__pa(_stext), _end - _stext);
@@ -57,54 +40,36 @@ static void __init csky_memblock_init(void)
 	memblock_dump_all();
 
 	memset(zone_size, 0, sizeof(zone_size));
-	memset(zhole_size, 0, sizeof(zhole_size));
 
 	min_low_pfn = PFN_UP(memblock_start_of_DRAM());
-	max_pfn	    = PFN_DOWN(memblock_end_of_DRAM());
-
-	max_low_pfn = PFN_UP(memblock_end_of_REG0());
-	if (max_low_pfn == 0)
-		max_low_pfn = max_pfn;
+	max_low_pfn = max_pfn = PFN_DOWN(memblock_end_of_DRAM());
 
 	size = max_pfn - min_low_pfn;
 
-	if (memblock.memory.cnt > 1) {
-		zone_size[ZONE_NORMAL]  =
-			PFN_DOWN(memblock_start_of_REG1()) - min_low_pfn;
-		zhole_size[ZONE_NORMAL] =
-			PFN_DOWN(memblock_start_of_REG1()) - max_low_pfn;
+	if (size <= PFN_DOWN(SSEG_SIZE - PHYS_OFFSET_OFFSET))
+		zone_size[ZONE_NORMAL] = size;
+	else if (size < PFN_DOWN(LOWMEM_LIMIT - PHYS_OFFSET_OFFSET)) {
+		zone_size[ZONE_NORMAL] =
+				PFN_DOWN(SSEG_SIZE - PHYS_OFFSET_OFFSET);
+		max_low_pfn = min_low_pfn + zone_size[ZONE_NORMAL];
 	} else {
-		if (size <= PFN_DOWN(LOWMEM_LIMIT - PHYS_OFFSET_OFFSET))
-			zone_size[ZONE_NORMAL] = max_pfn - min_low_pfn;
-		else {
-			zone_size[ZONE_NORMAL] =
+		zone_size[ZONE_NORMAL] =
 				PFN_DOWN(LOWMEM_LIMIT - PHYS_OFFSET_OFFSET);
-			max_low_pfn = min_low_pfn + zone_size[ZONE_NORMAL];
-		}
+		max_low_pfn = min_low_pfn + zone_size[ZONE_NORMAL];
+		write_mmu_msa1(read_mmu_msa0() + SSEG_SIZE);
 	}
 
 #ifdef CONFIG_HIGHMEM
-	size = 0;
-	if (memblock.memory.cnt > 1) {
-		size = PFN_DOWN(memblock_size_of_REG1());
-		highstart_pfn = PFN_DOWN(memblock_start_of_REG1());
-	} else {
-		size = max_pfn - min_low_pfn -
-			PFN_DOWN(LOWMEM_LIMIT - PHYS_OFFSET_OFFSET);
-		highstart_pfn =  min_low_pfn +
-			PFN_DOWN(LOWMEM_LIMIT - PHYS_OFFSET_OFFSET);
-	}
-
-	if (size > 0)
-		zone_size[ZONE_HIGHMEM] = size;
+	zone_size[ZONE_HIGHMEM] = max_pfn - max_low_pfn;
 
-	highend_pfn = max_pfn;
+	highstart_pfn = max_low_pfn;
+	highend_pfn   = max_pfn;
 #endif
 	memblock_set_current_limit(PFN_PHYS(max_low_pfn));
 
 	dma_contiguous_reserve(0);
 
-	free_area_init_node(0, zone_size, min_low_pfn, zhole_size);
+	free_area_init_node(0, zone_size, min_low_pfn, NULL);
 }
 
 void __init setup_arch(char **cmdline_p)
diff --git a/arch/csky/kernel/smp.c b/arch/csky/kernel/smp.c
index b07a534b3062..609123c975c1 100644
--- a/arch/csky/kernel/smp.c
+++ b/arch/csky/kernel/smp.c
@@ -22,6 +22,9 @@
 #include <asm/sections.h>
 #include <asm/mmu_context.h>
 #include <asm/pgalloc.h>
+#ifdef CONFIG_CPU_HAS_FPU
+#include <abi/fpu.h>
+#endif
 
 struct ipi_data_struct {
 	unsigned long bits ____cacheline_aligned;
@@ -120,7 +123,7 @@ void __init setup_smp_ipi(void)
 	int rc;
 
 	if (ipi_irq == 0)
-		panic("%s IRQ mapping failed\n", __func__);
+		return;
 
 	rc = request_percpu_irq(ipi_irq, handle_ipi, "IPI Interrupt",
 				&ipi_dummy_dev);
@@ -156,6 +159,8 @@ volatile unsigned int secondary_hint;
 volatile unsigned int secondary_ccr;
 volatile unsigned int secondary_stack;
 
+unsigned long secondary_msa1;
+
 int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
 	unsigned long mask = 1 << cpu;
@@ -164,6 +169,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 		(unsigned int) task_stack_page(tidle) + THREAD_SIZE - 8;
 	secondary_hint = mfcr("cr31");
 	secondary_ccr  = mfcr("cr18");
+	secondary_msa1 = read_mmu_msa1();
 
 	/*
 	 * Because other CPUs are in reset status, we must flush data
diff --git a/arch/csky/kernel/traps.c b/arch/csky/kernel/traps.c
index f487a9b996ae..de903b18cd2a 100644
--- a/arch/csky/kernel/traps.c
+++ b/arch/csky/kernel/traps.c
@@ -115,8 +115,9 @@ asmlinkage void trap_c(struct pt_regs *regs)
 	int sig;
 	unsigned long vector;
 	siginfo_t info;
+	struct task_struct *tsk = current;
 
-	vector = (mfcr("psr") >> 16) & 0xff;
+	vector = (regs->sr >> 16) & 0xff;
 
 	switch (vector) {
 	case VEC_ZERODIV:
@@ -128,6 +129,7 @@ asmlinkage void trap_c(struct pt_regs *regs)
 		sig = SIGTRAP;
 		break;
 	case VEC_ILLEGAL:
+		tsk->thread.trap_no = vector;
 #ifndef CONFIG_CPU_NO_USER_BKPT
 		if (*(uint16_t *)instruction_pointer(regs) != USR_BKPT)
 #endif
@@ -143,15 +145,19 @@ asmlinkage void trap_c(struct pt_regs *regs)
 		sig = SIGTRAP;
 		break;
 	case VEC_ACCESS:
+		tsk->thread.trap_no = vector;
 		return buserr(regs);
 #ifdef CONFIG_CPU_NEED_SOFTALIGN
 	case VEC_ALIGN:
+		tsk->thread.trap_no = vector;
 		return csky_alignment(regs);
 #endif
 #ifdef CONFIG_CPU_HAS_FPU
 	case VEC_FPE:
+		tsk->thread.trap_no = vector;
 		return fpu_fpe(regs);
 	case VEC_PRIV:
+		tsk->thread.trap_no = vector;
 		if (fpu_libc_helper(regs))
 			return;
 #endif
@@ -159,5 +165,8 @@ asmlinkage void trap_c(struct pt_regs *regs)
 		sig = SIGSEGV;
 		break;
 	}
+
+	tsk->thread.trap_no = vector;
+
 	send_sig(sig, current, 0);
 }
diff --git a/arch/csky/lib/usercopy.c b/arch/csky/lib/usercopy.c
index 647a23986fb5..3c9bd645e643 100644
--- a/arch/csky/lib/usercopy.c
+++ b/arch/csky/lib/usercopy.c
@@ -7,10 +7,7 @@
 unsigned long raw_copy_from_user(void *to, const void *from,
 			unsigned long n)
 {
-	if (access_ok(from, n))
-		__copy_user_zeroing(to, from, n);
-	else
-		memset(to, 0, n);
+	___copy_from_user(to, from, n);
 	return n;
 }
 EXPORT_SYMBOL(raw_copy_from_user);
@@ -18,8 +15,7 @@ EXPORT_SYMBOL(raw_copy_from_user);
 unsigned long raw_copy_to_user(void *to, const void *from,
 			unsigned long n)
 {
-	if (access_ok(to, n))
-		__copy_user(to, from, n);
+	___copy_to_user(to, from, n);
 	return n;
 }
 EXPORT_SYMBOL(raw_copy_to_user);
diff --git a/arch/csky/mm/Makefile b/arch/csky/mm/Makefile
index 4eebebdcd1bf..1e5fb600216a 100644
--- a/arch/csky/mm/Makefile
+++ b/arch/csky/mm/Makefile
@@ -1,8 +1,10 @@
 # SPDX-License-Identifier: GPL-2.0-only
 ifeq ($(CONFIG_CPU_HAS_CACHEV2),y)
 obj-y +=			cachev2.o
+CFLAGS_REMOVE_cachev2.o = $(CC_FLAGS_FTRACE)
 else
 obj-y +=			cachev1.o
+CFLAGS_REMOVE_cachev1.o = $(CC_FLAGS_FTRACE)
 endif
 
 obj-y +=			dma-mapping.o
diff --git a/arch/csky/mm/fault.c b/arch/csky/mm/fault.c
index 18041f46ded1..01290c551071 100644
--- a/arch/csky/mm/fault.c
+++ b/arch/csky/mm/fault.c
@@ -179,11 +179,14 @@ bad_area:
 bad_area_nosemaphore:
 	/* User mode accesses just cause a SIGSEGV */
 	if (user_mode(regs)) {
+		tsk->thread.trap_no = (regs->sr >> 16) & 0xff;
 		force_sig_fault(SIGSEGV, si_code, (void __user *)address, current);
 		return;
 	}
 
 no_context:
+	tsk->thread.trap_no = (regs->sr >> 16) & 0xff;
+
 	/* Are we prepared to handle this kernel fault? */
 	if (fixup_exception(regs))
 		return;
@@ -198,6 +201,8 @@ no_context:
 	die_if_kernel("Oops", regs, write);
 
 out_of_memory:
+	tsk->thread.trap_no = (regs->sr >> 16) & 0xff;
+
 	/*
 	 * We ran out of memory, call the OOM killer, and return the userspace
 	 * (which will retry the fault, or kill us if we got oom-killed).
@@ -206,6 +211,8 @@ out_of_memory:
 	return;
 
 do_sigbus:
+	tsk->thread.trap_no = (regs->sr >> 16) & 0xff;
+
 	up_read(&mm->mmap_sem);
 
 	/* Kernel mode? Handle exceptions or die */
diff --git a/arch/csky/mm/init.c b/arch/csky/mm/init.c
index 66e597053488..a0b9b8210af1 100644
--- a/arch/csky/mm/init.c
+++ b/arch/csky/mm/init.c
@@ -31,6 +31,7 @@
 
 pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
 pte_t invalid_pte_table[PTRS_PER_PTE] __page_aligned_bss;
+EXPORT_SYMBOL(invalid_pte_table);
 unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
 						__page_aligned_bss;
 EXPORT_SYMBOL(empty_zero_page);
diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h
index 12cd9231c4b8..0231d69c8bf2 100644
--- a/arch/hexagon/include/asm/atomic.h
+++ b/arch/hexagon/include/asm/atomic.h
@@ -91,7 +91,7 @@ static inline void atomic_##op(int i, atomic_t *v)			\
 		"1:	%0 = memw_locked(%1);\n"			\
 		"	%0 = "#op "(%0,%2);\n"				\
 		"	memw_locked(%1,P3)=%0;\n"			\
-		"	if !P3 jump 1b;\n"				\
+		"	if (!P3) jump 1b;\n"				\
 		: "=&r" (output)					\
 		: "r" (&v->counter), "r" (i)				\
 		: "memory", "p3"					\
@@ -107,7 +107,7 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 		"1:	%0 = memw_locked(%1);\n"			\
 		"	%0 = "#op "(%0,%2);\n"				\
 		"	memw_locked(%1,P3)=%0;\n"			\
-		"	if !P3 jump 1b;\n"				\
+		"	if (!P3) jump 1b;\n"				\
 		: "=&r" (output)					\
 		: "r" (&v->counter), "r" (i)				\
 		: "memory", "p3"					\
@@ -124,7 +124,7 @@ static inline int atomic_fetch_##op(int i, atomic_t *v)			\
 		"1:	%0 = memw_locked(%2);\n"			\
 		"	%1 = "#op "(%0,%3);\n"				\
 		"	memw_locked(%2,P3)=%1;\n"			\
-		"	if !P3 jump 1b;\n"				\
+		"	if (!P3) jump 1b;\n"				\
 		: "=&r" (output), "=&r" (val)				\
 		: "r" (&v->counter), "r" (i)				\
 		: "memory", "p3"					\
@@ -173,7 +173,7 @@ static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 		"	}"
 		"	memw_locked(%2, p3) = %1;"
 		"	{"
-		"		if !p3 jump 1b;"
+		"		if (!p3) jump 1b;"
 		"	}"
 		"2:"
 		: "=&r" (__oldval), "=&r" (tmp)
diff --git a/arch/hexagon/include/asm/bitops.h b/arch/hexagon/include/asm/bitops.h
index 47384b094b94..71429f756af0 100644
--- a/arch/hexagon/include/asm/bitops.h
+++ b/arch/hexagon/include/asm/bitops.h
@@ -38,7 +38,7 @@ static inline int test_and_clear_bit(int nr, volatile void *addr)
 	"1:	R12 = memw_locked(R10);\n"
 	"	{ P0 = tstbit(R12,R11); R12 = clrbit(R12,R11); }\n"
 	"	memw_locked(R10,P1) = R12;\n"
-	"	{if !P1 jump 1b; %0 = mux(P0,#1,#0);}\n"
+	"	{if (!P1) jump 1b; %0 = mux(P0,#1,#0);}\n"
 	: "=&r" (oldval)
 	: "r" (addr), "r" (nr)
 	: "r10", "r11", "r12", "p0", "p1", "memory"
@@ -62,7 +62,7 @@ static inline int test_and_set_bit(int nr, volatile void *addr)
 	"1:	R12 = memw_locked(R10);\n"
 	"	{ P0 = tstbit(R12,R11); R12 = setbit(R12,R11); }\n"
 	"	memw_locked(R10,P1) = R12;\n"
-	"	{if !P1 jump 1b; %0 = mux(P0,#1,#0);}\n"
+	"	{if (!P1) jump 1b; %0 = mux(P0,#1,#0);}\n"
 	: "=&r" (oldval)
 	: "r" (addr), "r" (nr)
 	: "r10", "r11", "r12", "p0", "p1", "memory"
@@ -88,7 +88,7 @@ static inline int test_and_change_bit(int nr, volatile void *addr)
 	"1:	R12 = memw_locked(R10);\n"
 	"	{ P0 = tstbit(R12,R11); R12 = togglebit(R12,R11); }\n"
 	"	memw_locked(R10,P1) = R12;\n"
-	"	{if !P1 jump 1b; %0 = mux(P0,#1,#0);}\n"
+	"	{if (!P1) jump 1b; %0 = mux(P0,#1,#0);}\n"
 	: "=&r" (oldval)
 	: "r" (addr), "r" (nr)
 	: "r10", "r11", "r12", "p0", "p1", "memory"
@@ -223,7 +223,7 @@ static inline int ffs(int x)
 	int r;
 
 	asm("{ P0 = cmp.eq(%1,#0); %0 = ct0(%1);}\n"
-		"{ if P0 %0 = #0; if !P0 %0 = add(%0,#1);}\n"
+		"{ if (P0) %0 = #0; if (!P0) %0 = add(%0,#1);}\n"
 		: "=&r" (r)
 		: "r" (x)
 		: "p0");
diff --git a/arch/hexagon/include/asm/cmpxchg.h b/arch/hexagon/include/asm/cmpxchg.h
index 6091322c3af9..92b8a02e588a 100644
--- a/arch/hexagon/include/asm/cmpxchg.h
+++ b/arch/hexagon/include/asm/cmpxchg.h
@@ -30,7 +30,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
 	__asm__ __volatile__ (
 	"1:	%0 = memw_locked(%1);\n"    /*  load into retval */
 	"	memw_locked(%1,P0) = %2;\n" /*  store into memory */
-	"	if !P0 jump 1b;\n"
+	"	if (!P0) jump 1b;\n"
 	: "=&r" (retval)
 	: "r" (ptr), "r" (x)
 	: "memory", "p0"
diff --git a/arch/hexagon/include/asm/futex.h b/arch/hexagon/include/asm/futex.h
index cb635216a732..0191f7c7193e 100644
--- a/arch/hexagon/include/asm/futex.h
+++ b/arch/hexagon/include/asm/futex.h
@@ -16,7 +16,7 @@
 	    /* For example: %1 = %4 */ \
 	    insn \
 	"2: memw_locked(%3,p2) = %1;\n" \
-	"   if !p2 jump 1b;\n" \
+	"   if (!p2) jump 1b;\n" \
 	"   %1 = #0;\n" \
 	"3:\n" \
 	".section .fixup,\"ax\"\n" \
@@ -84,10 +84,10 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval,
 	"1: %1 = memw_locked(%3)\n"
 	"   {\n"
 	"      p2 = cmp.eq(%1,%4)\n"
-	"      if !p2.new jump:NT 3f\n"
+	"      if (!p2.new) jump:NT 3f\n"
 	"   }\n"
 	"2: memw_locked(%3,p2) = %5\n"
-	"   if !p2 jump 1b\n"
+	"   if (!p2) jump 1b\n"
 	"3:\n"
 	".section .fixup,\"ax\"\n"
 	"4: %0 = #%6\n"
diff --git a/arch/hexagon/include/asm/io.h b/arch/hexagon/include/asm/io.h
index ba1a444d55b3..68a68147504d 100644
--- a/arch/hexagon/include/asm/io.h
+++ b/arch/hexagon/include/asm/io.h
@@ -171,16 +171,10 @@ static inline void writel(u32 data, volatile void __iomem *addr)
 #define writew_relaxed __raw_writew
 #define writel_relaxed __raw_writel
 
-/*
- * Need an mtype somewhere in here, for cache type deals?
- * This is probably too long for an inline.
- */
-void __iomem *ioremap_nocache(unsigned long phys_addr, unsigned long size);
+void __iomem *ioremap(unsigned long phys_addr, unsigned long size);
+#define ioremap_nocache ioremap
+#define ioremap_uc(X, Y) ioremap((X), (Y))
 
-static inline void __iomem *ioremap(unsigned long phys_addr, unsigned long size)
-{
-	return ioremap_nocache(phys_addr, size);
-}
 
 static inline void iounmap(volatile void __iomem *addr)
 {
diff --git a/arch/hexagon/include/asm/spinlock.h b/arch/hexagon/include/asm/spinlock.h
index bfe07d842ff3..ef103b73bec8 100644
--- a/arch/hexagon/include/asm/spinlock.h
+++ b/arch/hexagon/include/asm/spinlock.h
@@ -30,9 +30,9 @@ static inline void arch_read_lock(arch_rwlock_t *lock)
 	__asm__ __volatile__(
 		"1:	R6 = memw_locked(%0);\n"
 		"	{ P3 = cmp.ge(R6,#0); R6 = add(R6,#1);}\n"
-		"	{ if !P3 jump 1b; }\n"
+		"	{ if (!P3) jump 1b; }\n"
 		"	memw_locked(%0,P3) = R6;\n"
-		"	{ if !P3 jump 1b; }\n"
+		"	{ if (!P3) jump 1b; }\n"
 		:
 		: "r" (&lock->lock)
 		: "memory", "r6", "p3"
@@ -46,7 +46,7 @@ static inline void arch_read_unlock(arch_rwlock_t *lock)
 		"1:	R6 = memw_locked(%0);\n"
 		"	R6 = add(R6,#-1);\n"
 		"	memw_locked(%0,P3) = R6\n"
-		"	if !P3 jump 1b;\n"
+		"	if (!P3) jump 1b;\n"
 		:
 		: "r" (&lock->lock)
 		: "memory", "r6", "p3"
@@ -61,7 +61,7 @@ static inline int arch_read_trylock(arch_rwlock_t *lock)
 	__asm__ __volatile__(
 		"	R6 = memw_locked(%1);\n"
 		"	{ %0 = #0; P3 = cmp.ge(R6,#0); R6 = add(R6,#1);}\n"
-		"	{ if !P3 jump 1f; }\n"
+		"	{ if (!P3) jump 1f; }\n"
 		"	memw_locked(%1,P3) = R6;\n"
 		"	{ %0 = P3 }\n"
 		"1:\n"
@@ -78,9 +78,9 @@ static inline void arch_write_lock(arch_rwlock_t *lock)
 	__asm__ __volatile__(
 		"1:	R6 = memw_locked(%0)\n"
 		"	{ P3 = cmp.eq(R6,#0);  R6 = #-1;}\n"
-		"	{ if !P3 jump 1b; }\n"
+		"	{ if (!P3) jump 1b; }\n"
 		"	memw_locked(%0,P3) = R6;\n"
-		"	{ if !P3 jump 1b; }\n"
+		"	{ if (!P3) jump 1b; }\n"
 		:
 		: "r" (&lock->lock)
 		: "memory", "r6", "p3"
@@ -94,7 +94,7 @@ static inline int arch_write_trylock(arch_rwlock_t *lock)
 	__asm__ __volatile__(
 		"	R6 = memw_locked(%1)\n"
 		"	{ %0 = #0; P3 = cmp.eq(R6,#0);  R6 = #-1;}\n"
-		"	{ if !P3 jump 1f; }\n"
+		"	{ if (!P3) jump 1f; }\n"
 		"	memw_locked(%1,P3) = R6;\n"
 		"	%0 = P3;\n"
 		"1:\n"
@@ -117,9 +117,9 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 	__asm__ __volatile__(
 		"1:	R6 = memw_locked(%0);\n"
 		"	P3 = cmp.eq(R6,#0);\n"
-		"	{ if !P3 jump 1b; R6 = #1; }\n"
+		"	{ if (!P3) jump 1b; R6 = #1; }\n"
 		"	memw_locked(%0,P3) = R6;\n"
-		"	{ if !P3 jump 1b; }\n"
+		"	{ if (!P3) jump 1b; }\n"
 		:
 		: "r" (&lock->lock)
 		: "memory", "r6", "p3"
@@ -139,7 +139,7 @@ static inline unsigned int arch_spin_trylock(arch_spinlock_t *lock)
 	__asm__ __volatile__(
 		"	R6 = memw_locked(%1);\n"
 		"	P3 = cmp.eq(R6,#0);\n"
-		"	{ if !P3 jump 1f; R6 = #1; %0 = #0; }\n"
+		"	{ if (!P3) jump 1f; R6 = #1; %0 = #0; }\n"
 		"	memw_locked(%1,P3) = R6;\n"
 		"	%0 = P3;\n"
 		"1:\n"
diff --git a/arch/hexagon/kernel/hexagon_ksyms.c b/arch/hexagon/kernel/hexagon_ksyms.c
index cf8974beb500..b3dbb472572e 100644
--- a/arch/hexagon/kernel/hexagon_ksyms.c
+++ b/arch/hexagon/kernel/hexagon_ksyms.c
@@ -20,7 +20,7 @@ EXPORT_SYMBOL(__vmgetie);
 EXPORT_SYMBOL(__vmsetie);
 EXPORT_SYMBOL(__vmyield);
 EXPORT_SYMBOL(empty_zero_page);
-EXPORT_SYMBOL(ioremap_nocache);
+EXPORT_SYMBOL(ioremap);
 EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(memset);
 
diff --git a/arch/hexagon/kernel/stacktrace.c b/arch/hexagon/kernel/stacktrace.c
index 35f29423fda8..5ed02f699479 100644
--- a/arch/hexagon/kernel/stacktrace.c
+++ b/arch/hexagon/kernel/stacktrace.c
@@ -11,8 +11,6 @@
 #include <linux/thread_info.h>
 #include <linux/module.h>
 
-register unsigned long current_frame_pointer asm("r30");
-
 struct stackframe {
 	unsigned long fp;
 	unsigned long rets;
@@ -30,7 +28,7 @@ void save_stack_trace(struct stack_trace *trace)
 
 	low = (unsigned long)task_stack_page(current);
 	high = low + THREAD_SIZE;
-	fp = current_frame_pointer;
+	fp = (unsigned long)__builtin_frame_address(0);
 
 	while (fp >= low && fp <= (high - sizeof(*frame))) {
 		frame = (struct stackframe *)fp;
diff --git a/arch/hexagon/kernel/vm_entry.S b/arch/hexagon/kernel/vm_entry.S
index 12242c27e2df..4023fdbea490 100644
--- a/arch/hexagon/kernel/vm_entry.S
+++ b/arch/hexagon/kernel/vm_entry.S
@@ -369,7 +369,7 @@ ret_from_fork:
 		R26.L = #LO(do_work_pending);
 		R0 = #VM_INT_DISABLE;
 	}
-	if P0 jump check_work_pending
+	if (P0) jump check_work_pending
 	{
 		R0 = R25;
 		callr R24
diff --git a/arch/hexagon/mm/ioremap.c b/arch/hexagon/mm/ioremap.c
index 77d8e1e69e9b..b103d83b5fbb 100644
--- a/arch/hexagon/mm/ioremap.c
+++ b/arch/hexagon/mm/ioremap.c
@@ -9,7 +9,7 @@
 #include <linux/vmalloc.h>
 #include <linux/mm.h>
 
-void __iomem *ioremap_nocache(unsigned long phys_addr, unsigned long size)
+void __iomem *ioremap(unsigned long phys_addr, unsigned long size)
 {
 	unsigned long last_addr, addr;
 	unsigned long offset = phys_addr & ~PAGE_MASK;
diff --git a/arch/m68k/coldfire/pci.c b/arch/m68k/coldfire/pci.c
index 62b0eb6cf69a..84eab0f5e00a 100644
--- a/arch/m68k/coldfire/pci.c
+++ b/arch/m68k/coldfire/pci.c
@@ -216,8 +216,10 @@ static int __init mcf_pci_init(void)
 
 	/* Keep a virtual mapping to IO/config space active */
 	iospace = (unsigned long) ioremap(PCI_IO_PA, PCI_IO_SIZE);
-	if (iospace == 0)
+	if (iospace == 0) {
+		pci_free_host_bridge(bridge);
 		return -ENODEV;
+	}
 	pr_info("Coldfire: PCI IO/config window mapped to 0x%x\n",
 		(u32) iospace);
 
diff --git a/arch/m68k/include/asm/mac_via.h b/arch/m68k/include/asm/mac_via.h
index de1470c4d829..1149251ea58d 100644
--- a/arch/m68k/include/asm/mac_via.h
+++ b/arch/m68k/include/asm/mac_via.h
@@ -257,6 +257,7 @@ extern int rbv_present,via_alt_mapping;
 
 struct irq_desc;
 
+extern void via_l2_flush(int writeback);
 extern void via_register_interrupts(void);
 extern void via_irq_enable(int);
 extern void via_irq_disable(int);
diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c
index 3c5def10d486..caa260f877f2 100644
--- a/arch/m68k/kernel/setup_no.c
+++ b/arch/m68k/kernel/setup_no.c
@@ -139,7 +139,8 @@ void __init setup_arch(char **cmdline_p)
 	pr_debug("MEMORY -> ROMFS=0x%p-0x%06lx MEM=0x%06lx-0x%06lx\n ",
 		 __bss_stop, memory_start, memory_start, memory_end);
 
-	memblock_add(memory_start, memory_end - memory_start);
+	memblock_add(_rambase, memory_end - _rambase);
+	memblock_reserve(_rambase, memory_start - _rambase);
 
 	/* Keep a copy of command line */
 	*cmdline_p = &command_line[0];
diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c
index 11be08f4f750..b3d2dbb27231 100644
--- a/arch/m68k/mac/config.c
+++ b/arch/m68k/mac/config.c
@@ -59,7 +59,6 @@ extern void iop_preinit(void);
 extern void iop_init(void);
 extern void via_init(void);
 extern void via_init_clock(irq_handler_t func);
-extern void via_flush_cache(void);
 extern void oss_init(void);
 extern void psc_init(void);
 extern void baboon_init(void);
@@ -130,21 +129,6 @@ int __init mac_parse_bootinfo(const struct bi_record *record)
 	return unknown;
 }
 
-/*
- * Flip into 24bit mode for an instant - flushes the L2 cache card. We
- * have to disable interrupts for this. Our IRQ handlers will crap
- * themselves if they take an IRQ in 24bit mode!
- */
-
-static void mac_cache_card_flush(int writeback)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	via_flush_cache();
-	local_irq_restore(flags);
-}
-
 void __init config_mac(void)
 {
 	if (!MACH_IS_MAC)
@@ -175,9 +159,8 @@ void __init config_mac(void)
 	 * not.
 	 */
 
-	if (macintosh_config->ident == MAC_MODEL_IICI
-	    || macintosh_config->ident == MAC_MODEL_IIFX)
-		mach_l2_flush = mac_cache_card_flush;
+	if (macintosh_config->ident == MAC_MODEL_IICI)
+		mach_l2_flush = via_l2_flush;
 }
 
 
diff --git a/arch/m68k/mac/iop.c b/arch/m68k/mac/iop.c
index 9bfa17015768..c432bfafe63e 100644
--- a/arch/m68k/mac/iop.c
+++ b/arch/m68k/mac/iop.c
@@ -183,7 +183,7 @@ static __inline__ void iop_writeb(volatile struct mac_iop *iop, __u16 addr, __u8
 
 static __inline__ void iop_stop(volatile struct mac_iop *iop)
 {
-	iop->status_ctrl &= ~IOP_RUN;
+	iop->status_ctrl = IOP_AUTOINC;
 }
 
 static __inline__ void iop_start(volatile struct mac_iop *iop)
@@ -191,14 +191,9 @@ static __inline__ void iop_start(volatile struct mac_iop *iop)
 	iop->status_ctrl = IOP_RUN | IOP_AUTOINC;
 }
 
-static __inline__ void iop_bypass(volatile struct mac_iop *iop)
-{
-	iop->status_ctrl |= IOP_BYPASS;
-}
-
 static __inline__ void iop_interrupt(volatile struct mac_iop *iop)
 {
-	iop->status_ctrl |= IOP_IRQ;
+	iop->status_ctrl = IOP_IRQ | IOP_RUN | IOP_AUTOINC;
 }
 
 static int iop_alive(volatile struct mac_iop *iop)
@@ -244,7 +239,6 @@ void __init iop_preinit(void)
 		} else {
 			iop_base[IOP_NUM_SCC] = (struct mac_iop *) SCC_IOP_BASE_QUADRA;
 		}
-		iop_base[IOP_NUM_SCC]->status_ctrl = 0x87;
 		iop_scc_present = 1;
 	} else {
 		iop_base[IOP_NUM_SCC] = NULL;
@@ -256,7 +250,7 @@ void __init iop_preinit(void)
 		} else {
 			iop_base[IOP_NUM_ISM] = (struct mac_iop *) ISM_IOP_BASE_QUADRA;
 		}
-		iop_base[IOP_NUM_ISM]->status_ctrl = 0;
+		iop_stop(iop_base[IOP_NUM_ISM]);
 		iop_ism_present = 1;
 	} else {
 		iop_base[IOP_NUM_ISM] = NULL;
@@ -416,7 +410,8 @@ static void iop_handle_send(uint iop_num, uint chan)
 	msg->status = IOP_MSGSTATUS_UNUSED;
 	msg = msg->next;
 	iop_send_queue[iop_num][chan] = msg;
-	if (msg) iop_do_send(msg);
+	if (msg && iop_readb(iop, IOP_ADDR_SEND_STATE + chan) == IOP_MSG_IDLE)
+		iop_do_send(msg);
 }
 
 /*
@@ -490,16 +485,12 @@ int iop_send_message(uint iop_num, uint chan, void *privdata,
 
 	if (!(q = iop_send_queue[iop_num][chan])) {
 		iop_send_queue[iop_num][chan] = msg;
+		iop_do_send(msg);
 	} else {
 		while (q->next) q = q->next;
 		q->next = msg;
 	}
 
-	if (iop_readb(iop_base[iop_num],
-	    IOP_ADDR_SEND_STATE + chan) == IOP_MSG_IDLE) {
-		iop_do_send(msg);
-	}
-
 	return 0;
 }
 
diff --git a/arch/m68k/mac/via.c b/arch/m68k/mac/via.c
index 3c2cfcb74982..1f0fad2a98a0 100644
--- a/arch/m68k/mac/via.c
+++ b/arch/m68k/mac/via.c
@@ -294,10 +294,14 @@ void via_debug_dump(void)
  * the system into 24-bit mode for an instant.
  */
 
-void via_flush_cache(void)
+void via_l2_flush(int writeback)
 {
+	unsigned long flags;
+
+	local_irq_save(flags);
 	via2[gBufB] &= ~VIA2B_vMode32;
 	via2[gBufB] |= VIA2B_vMode32;
+	local_irq_restore(flags);
 }
 
 /*
diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c
index 6cb1e41d58d0..70a5f55ea664 100644
--- a/arch/m68k/mm/mcfmmu.c
+++ b/arch/m68k/mm/mcfmmu.c
@@ -164,7 +164,7 @@ void __init cf_bootmem_alloc(void)
 	m68k_memory[0].addr = _rambase;
 	m68k_memory[0].size = _ramend - _rambase;
 
-	memblock_add(m68k_memory[0].addr, m68k_memory[0].size);
+	memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0);
 
 	/* compute total pages in system */
 	num_pages = PFN_DOWN(_ramend - _rambase);
diff --git a/arch/microblaze/kernel/cpu/cache.c b/arch/microblaze/kernel/cpu/cache.c
index 0bde47e4fa69..dcba53803fa5 100644
--- a/arch/microblaze/kernel/cpu/cache.c
+++ b/arch/microblaze/kernel/cpu/cache.c
@@ -92,7 +92,8 @@ static inline void __disable_dcache_nomsr(void)
 #define CACHE_LOOP_LIMITS(start, end, cache_line_length, cache_size)	\
 do {									\
 	int align = ~(cache_line_length - 1);				\
-	end = min(start + cache_size, end);				\
+	if (start <  UINT_MAX - cache_size)				\
+		end = min(start + cache_size, end);			\
 	start &= align;							\
 } while (0)
 
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 70d3200476bf..53025ec6795f 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -43,7 +43,7 @@ config MIPS
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE if CPU_SUPPORTS_HUGEPAGES && 64BIT
-	select HAVE_EBPF_JIT if (!CPU_MICROMIPS)
+	select HAVE_EBPF_JIT if 64BIT && !CPU_MICROMIPS && TARGET_ISA_REV >= 2
 	select HAVE_CONTEXT_TRACKING
 	select HAVE_COPY_THREAD_TLS
 	select HAVE_C_RECORDMCOUNT
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index eceff9b75b22..cc7e25d0df57 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -289,12 +289,23 @@ ifdef CONFIG_64BIT
   endif
 endif
 
+# When linking a 32-bit executable the LLVM linker cannot cope with a
+# 32-bit load address that has been sign-extended to 64 bits.  Simply
+# remove the upper 32 bits then, as it is safe to do so with other
+# linkers.
+ifdef CONFIG_64BIT
+	load-ld			= $(load-y)
+else
+	load-ld			= $(subst 0xffffffff,0x,$(load-y))
+endif
+
 KBUILD_AFLAGS	+= $(cflags-y)
 KBUILD_CFLAGS	+= $(cflags-y)
-KBUILD_CPPFLAGS += -DVMLINUX_LOAD_ADDRESS=$(load-y)
+KBUILD_CPPFLAGS += -DVMLINUX_LOAD_ADDRESS=$(load-y) -DLINKER_LOAD_ADDRESS=$(load-ld)
 KBUILD_CPPFLAGS += -DDATAOFFSET=$(if $(dataoffset-y),$(dataoffset-y),0)
 
 bootvars-y	= VMLINUX_LOAD_ADDRESS=$(load-y) \
+		  LINKER_LOAD_ADDRESS=$(load-ld) \
 		  VMLINUX_ENTRY_ADDRESS=$(entry-y) \
 		  PLATFORM="$(platform-y)" \
 		  ITS_INPUTS="$(its-y)"
diff --git a/arch/mips/Makefile.postlink b/arch/mips/Makefile.postlink
index 4eea4188cb20..13e0beb9eee3 100644
--- a/arch/mips/Makefile.postlink
+++ b/arch/mips/Makefile.postlink
@@ -12,7 +12,7 @@ __archpost:
 include scripts/Kbuild.include
 
 CMD_RELOCS = arch/mips/boot/tools/relocs
-quiet_cmd_relocs = RELOCS $@
+quiet_cmd_relocs = RELOCS  $@
       cmd_relocs = $(CMD_RELOCS) $@
 
 # `@true` prevents complaint when there is nothing to be done
diff --git a/arch/mips/boot/Makefile b/arch/mips/boot/Makefile
index 3ce4dd578370..c66199e38694 100644
--- a/arch/mips/boot/Makefile
+++ b/arch/mips/boot/Makefile
@@ -123,7 +123,7 @@ $(obj)/vmlinux.its.S: $(addprefix $(srctree)/arch/mips/$(PLATFORM)/,$(ITS_INPUTS
 targets += vmlinux.its
 targets += vmlinux.gz.its
 targets += vmlinux.bz2.its
-targets += vmlinux.lzmo.its
+targets += vmlinux.lzma.its
 targets += vmlinux.lzo.its
 
 quiet_cmd_cpp_its_S = ITS     $@
diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile
index 172801ed35b8..378cbfb31ee7 100644
--- a/arch/mips/boot/compressed/Makefile
+++ b/arch/mips/boot/compressed/Makefile
@@ -29,6 +29,9 @@ KBUILD_AFLAGS := $(KBUILD_AFLAGS) -D__ASSEMBLY__ \
 	-DBOOT_HEAP_SIZE=$(BOOT_HEAP_SIZE) \
 	-DKERNEL_ENTRY=$(VMLINUX_ENTRY_ADDRESS)
 
+# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
+KCOV_INSTRUMENT		:= n
+
 # decompressor objects (linked with vmlinuz)
 vmlinuzobjs-y := $(obj)/head.o $(obj)/decompress.o $(obj)/string.o
 
@@ -87,7 +90,7 @@ ifneq ($(zload-y),)
 VMLINUZ_LOAD_ADDRESS := $(zload-y)
 else
 VMLINUZ_LOAD_ADDRESS = $(shell $(obj)/calc_vmlinuz_load_addr \
-		$(obj)/vmlinux.bin $(VMLINUX_LOAD_ADDRESS))
+		$(obj)/vmlinux.bin $(LINKER_LOAD_ADDRESS))
 endif
 UIMAGE_LOADADDR = $(VMLINUZ_LOAD_ADDRESS)
 
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index f97be32bf699..3ad1f76c063a 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -2199,6 +2199,9 @@ static int octeon_irq_cib_map(struct irq_domain *d,
 	}
 
 	cd = kzalloc(sizeof(*cd), GFP_KERNEL);
+	if (!cd)
+		return -ENOMEM;
+
 	cd->host_data = host_data;
 	cd->bit = hw;
 
diff --git a/arch/mips/cavium-octeon/octeon-usb.c b/arch/mips/cavium-octeon/octeon-usb.c
index 1f730ded5224..5ab29c18aacd 100644
--- a/arch/mips/cavium-octeon/octeon-usb.c
+++ b/arch/mips/cavium-octeon/octeon-usb.c
@@ -517,6 +517,7 @@ static int __init dwc3_octeon_device_init(void)
 
 			res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 			if (res == NULL) {
+				put_device(&pdev->dev);
 				dev_err(&pdev->dev, "No memory resources\n");
 				return -ENXIO;
 			}
@@ -528,8 +529,10 @@ static int __init dwc3_octeon_device_init(void)
 			 * know the difference.
 			 */
 			base = devm_ioremap_resource(&pdev->dev, res);
-			if (IS_ERR(base))
+			if (IS_ERR(base)) {
+				put_device(&pdev->dev);
 				return PTR_ERR(base);
+			}
 
 			mutex_lock(&dwc3_octeon_clocks_mutex);
 			dwc3_octeon_clocks_start(&pdev->dev, (u64)base);
diff --git a/arch/mips/configs/loongson3_defconfig b/arch/mips/configs/loongson3_defconfig
index 1322adb705c8..1ef17ca93ac1 100644
--- a/arch/mips/configs/loongson3_defconfig
+++ b/arch/mips/configs/loongson3_defconfig
@@ -232,7 +232,7 @@ CONFIG_MEDIA_CAMERA_SUPPORT=y
 CONFIG_MEDIA_USB_SUPPORT=y
 CONFIG_USB_VIDEO_CLASS=m
 CONFIG_DRM=y
-CONFIG_DRM_RADEON=y
+CONFIG_DRM_RADEON=m
 CONFIG_FB_RADEON=y
 CONFIG_LCD_CLASS_DEVICE=y
 CONFIG_LCD_PLATFORM=m
diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h
index 4e2bea8875f5..92ec31166edd 100644
--- a/arch/mips/include/asm/cpu-features.h
+++ b/arch/mips/include/asm/cpu-features.h
@@ -291,10 +291,12 @@
 # define cpu_has_mips32r6	__isa_ge_or_flag(6, MIPS_CPU_ISA_M32R6)
 #endif
 #ifndef cpu_has_mips64r1
-# define cpu_has_mips64r1	__isa_range_or_flag(1, 6, MIPS_CPU_ISA_M64R1)
+# define cpu_has_mips64r1	(cpu_has_64bits && \
+				 __isa_range_or_flag(1, 6, MIPS_CPU_ISA_M64R1))
 #endif
 #ifndef cpu_has_mips64r2
-# define cpu_has_mips64r2	__isa_range_or_flag(2, 6, MIPS_CPU_ISA_M64R2)
+# define cpu_has_mips64r2	(cpu_has_64bits && \
+				 __isa_range_or_flag(2, 6, MIPS_CPU_ISA_M64R2))
 #endif
 #ifndef cpu_has_mips64r6
 # define cpu_has_mips64r6	__isa_ge_and_flag(6, MIPS_CPU_ISA_M64R6)
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 41204a49cf95..7b47a323dc23 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -274,8 +274,12 @@ enum emulation_result {
 #define MIPS3_PG_SHIFT		6
 #define MIPS3_PG_FRAME		0x3fffffc0
 
+#if defined(CONFIG_64BIT)
+#define VPN2_MASK		GENMASK(cpu_vmbits - 1, 13)
+#else
 #define VPN2_MASK		0xffffe000
-#define KVM_ENTRYHI_ASID	MIPS_ENTRYHI_ASID
+#endif
+#define KVM_ENTRYHI_ASID	cpu_asid_mask(&boot_cpu_data)
 #define TLB_IS_GLOBAL(x)	((x).tlb_lo[0] & (x).tlb_lo[1] & ENTRYLO_G)
 #define TLB_VPN2(x)		((x).tlb_hi & VPN2_MASK)
 #define TLB_ASID(x)		((x).tlb_hi & KVM_ENTRYHI_ASID)
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index bdbdc19a2b8f..3afdb39d092a 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -750,7 +750,7 @@
 
 /* MAAR bit definitions */
 #define MIPS_MAAR_VH		(_U64CAST_(1) << 63)
-#define MIPS_MAAR_ADDR		((BIT_ULL(BITS_PER_LONG - 12) - 1) << 12)
+#define MIPS_MAAR_ADDR		GENMASK_ULL(55, 12)
 #define MIPS_MAAR_ADDR_SHIFT	12
 #define MIPS_MAAR_S		(_ULCAST_(1) << 1)
 #define MIPS_MAAR_VL		(_ULCAST_(1) << 0)
diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h
index 4993db40482c..ee26f9a4575d 100644
--- a/arch/mips/include/asm/thread_info.h
+++ b/arch/mips/include/asm/thread_info.h
@@ -49,8 +49,26 @@ struct thread_info {
 	.addr_limit	= KERNEL_DS,		\
 }
 
-/* How to get the thread information struct from C.  */
+/*
+ * A pointer to the struct thread_info for the currently executing thread is
+ * held in register $28/$gp.
+ *
+ * We declare __current_thread_info as a global register variable rather than a
+ * local register variable within current_thread_info() because clang doesn't
+ * support explicit local register variables.
+ *
+ * When building the VDSO we take care not to declare the global register
+ * variable because this causes GCC to not preserve the value of $28/$gp in
+ * functions that change its value (which is common in the PIC VDSO when
+ * accessing the GOT). Since the VDSO shouldn't be accessing
+ * __current_thread_info anyway we declare it extern in order to cause a link
+ * failure if it's referenced.
+ */
+#ifdef __VDSO__
+extern struct thread_info *__current_thread_info;
+#else
 register struct thread_info *__current_thread_info __asm__("$28");
+#endif
 
 static inline struct thread_info *current_thread_info(void)
 {
diff --git a/arch/mips/kernel/cacheinfo.c b/arch/mips/kernel/cacheinfo.c
index f777e44653d5..47312c529410 100644
--- a/arch/mips/kernel/cacheinfo.c
+++ b/arch/mips/kernel/cacheinfo.c
@@ -50,6 +50,25 @@ static int __init_cache_level(unsigned int cpu)
 	return 0;
 }
 
+static void fill_cpumask_siblings(int cpu, cpumask_t *cpu_map)
+{
+	int cpu1;
+
+	for_each_possible_cpu(cpu1)
+		if (cpus_are_siblings(cpu, cpu1))
+			cpumask_set_cpu(cpu1, cpu_map);
+}
+
+static void fill_cpumask_cluster(int cpu, cpumask_t *cpu_map)
+{
+	int cpu1;
+	int cluster = cpu_cluster(&cpu_data[cpu]);
+
+	for_each_possible_cpu(cpu1)
+		if (cpu_cluster(&cpu_data[cpu1]) == cluster)
+			cpumask_set_cpu(cpu1, cpu_map);
+}
+
 static int __populate_cache_leaves(unsigned int cpu)
 {
 	struct cpuinfo_mips *c = &current_cpu_data;
@@ -57,14 +76,20 @@ static int __populate_cache_leaves(unsigned int cpu)
 	struct cacheinfo *this_leaf = this_cpu_ci->info_list;
 
 	if (c->icache.waysize) {
+		/* L1 caches are per core */
+		fill_cpumask_siblings(cpu, &this_leaf->shared_cpu_map);
 		populate_cache(dcache, this_leaf, 1, CACHE_TYPE_DATA);
+		fill_cpumask_siblings(cpu, &this_leaf->shared_cpu_map);
 		populate_cache(icache, this_leaf, 1, CACHE_TYPE_INST);
 	} else {
 		populate_cache(dcache, this_leaf, 1, CACHE_TYPE_UNIFIED);
 	}
 
-	if (c->scache.waysize)
+	if (c->scache.waysize) {
+		/* L2 cache is per cluster */
+		fill_cpumask_cluster(cpu, &this_leaf->shared_cpu_map);
 		populate_cache(scache, this_leaf, 2, CACHE_TYPE_UNIFIED);
+	}
 
 	if (c->tcache.waysize)
 		populate_cache(tcache, this_leaf, 3, CACHE_TYPE_UNIFIED);
diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index 398b905b027d..370ffc7dc6e3 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -477,20 +477,20 @@ NESTED(nmi_handler, PT_SIZE, sp)
 	.endm
 
 	.macro	__build_clear_fpe
+	CLI
+	TRACE_IRQS_OFF
 	.set	push
 	/* gas fails to assemble cfc1 for some archs (octeon).*/ \
 	.set	mips1
 	SET_HARDFLOAT
 	cfc1	a1, fcr31
 	.set	pop
-	CLI
-	TRACE_IRQS_OFF
 	.endm
 
 	.macro	__build_clear_msa_fpe
-	_cfcmsa	a1, MSA_CSR
 	CLI
 	TRACE_IRQS_OFF
+	_cfcmsa	a1, MSA_CSR
 	.endm
 
 	.macro	__build_clear_ade
diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c
index e5ea3db23d6b..a9eab83d9148 100644
--- a/arch/mips/kernel/mips-cm.c
+++ b/arch/mips/kernel/mips-cm.c
@@ -119,9 +119,9 @@ static char *cm2_causes[32] = {
 	"COH_RD_ERR", "MMIO_WR_ERR", "MMIO_RD_ERR", "0x07",
 	"0x08", "0x09", "0x0a", "0x0b",
 	"0x0c", "0x0d", "0x0e", "0x0f",
-	"0x10", "0x11", "0x12", "0x13",
-	"0x14", "0x15", "0x16", "INTVN_WR_ERR",
-	"INTVN_RD_ERR", "0x19", "0x1a", "0x1b",
+	"0x10", "INTVN_WR_ERR", "INTVN_RD_ERR", "0x13",
+	"0x14", "0x15", "0x16", "0x17",
+	"0x18", "0x19", "0x1a", "0x1b",
 	"0x1c", "0x1d", "0x1e", "0x1f"
 };
 
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index ab349d2381c3..569f46e95c5a 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -817,7 +817,17 @@ static void __init arch_mem_init(char **cmdline_p)
 				 crashk_res.end - crashk_res.start + 1);
 #endif
 	device_tree_init();
+
+	/*
+	 * In order to reduce the possibility of kernel panic when failed to
+	 * get IO TLB memory under CONFIG_SWIOTLB, it is better to allocate
+	 * low memory as small as possible before plat_swiotlb_setup(), so
+	 * make sparse_init() using top-down allocation.
+	 */
+	memblock_set_bottom_up(false);
 	sparse_init();
+	memblock_set_bottom_up(true);
+
 	plat_swiotlb_setup();
 
 	dma_contiguous_reserve(PFN_PHYS(max_low_pfn));
diff --git a/arch/mips/kernel/syscalls/Makefile b/arch/mips/kernel/syscalls/Makefile
index a3d4bec695c6..6efb2f6889a7 100644
--- a/arch/mips/kernel/syscalls/Makefile
+++ b/arch/mips/kernel/syscalls/Makefile
@@ -18,7 +18,7 @@ quiet_cmd_syshdr = SYSHDR  $@
 		   '$(syshdr_pfx_$(basetarget))'		\
 		   '$(syshdr_offset_$(basetarget))'
 
-quiet_cmd_sysnr = SYSNR  $@
+quiet_cmd_sysnr = SYSNR   $@
       cmd_sysnr = $(CONFIG_SHELL) '$(sysnr)' '$<' '$@'		\
 		  '$(sysnr_abis_$(basetarget))'			\
 		  '$(sysnr_pfx_$(basetarget))'			\
diff --git a/arch/mips/kernel/time.c b/arch/mips/kernel/time.c
index 37e9413a393d..caa01457dce6 100644
--- a/arch/mips/kernel/time.c
+++ b/arch/mips/kernel/time.c
@@ -18,12 +18,82 @@
 #include <linux/smp.h>
 #include <linux/spinlock.h>
 #include <linux/export.h>
+#include <linux/cpufreq.h>
+#include <linux/delay.h>
 
 #include <asm/cpu-features.h>
 #include <asm/cpu-type.h>
 #include <asm/div64.h>
 #include <asm/time.h>
 
+#ifdef CONFIG_CPU_FREQ
+
+static DEFINE_PER_CPU(unsigned long, pcp_lpj_ref);
+static DEFINE_PER_CPU(unsigned long, pcp_lpj_ref_freq);
+static unsigned long glb_lpj_ref;
+static unsigned long glb_lpj_ref_freq;
+
+static int cpufreq_callback(struct notifier_block *nb,
+			    unsigned long val, void *data)
+{
+	struct cpufreq_freqs *freq = data;
+	struct cpumask *cpus = freq->policy->cpus;
+	unsigned long lpj;
+	int cpu;
+
+	/*
+	 * Skip lpj numbers adjustment if the CPU-freq transition is safe for
+	 * the loops delay. (Is this possible?)
+	 */
+	if (freq->flags & CPUFREQ_CONST_LOOPS)
+		return NOTIFY_OK;
+
+	/* Save the initial values of the lpjes for future scaling. */
+	if (!glb_lpj_ref) {
+		glb_lpj_ref = boot_cpu_data.udelay_val;
+		glb_lpj_ref_freq = freq->old;
+
+		for_each_online_cpu(cpu) {
+			per_cpu(pcp_lpj_ref, cpu) =
+				cpu_data[cpu].udelay_val;
+			per_cpu(pcp_lpj_ref_freq, cpu) = freq->old;
+		}
+	}
+
+	/*
+	 * Adjust global lpj variable and per-CPU udelay_val number in
+	 * accordance with the new CPU frequency.
+	 */
+	if ((val == CPUFREQ_PRECHANGE  && freq->old < freq->new) ||
+	    (val == CPUFREQ_POSTCHANGE && freq->old > freq->new)) {
+		loops_per_jiffy = cpufreq_scale(glb_lpj_ref,
+						glb_lpj_ref_freq,
+						freq->new);
+
+		for_each_cpu(cpu, cpus) {
+			lpj = cpufreq_scale(per_cpu(pcp_lpj_ref, cpu),
+					    per_cpu(pcp_lpj_ref_freq, cpu),
+					    freq->new);
+			cpu_data[cpu].udelay_val = (unsigned int)lpj;
+		}
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block cpufreq_notifier = {
+	.notifier_call  = cpufreq_callback,
+};
+
+static int __init register_cpufreq_notifier(void)
+{
+	return cpufreq_register_notifier(&cpufreq_notifier,
+					 CPUFREQ_TRANSITION_NOTIFIER);
+}
+core_initcall(register_cpufreq_notifier);
+
+#endif /* CONFIG_CPU_FREQ */
+
 /*
  * forward reference
  */
diff --git a/arch/mips/kernel/topology.c b/arch/mips/kernel/topology.c
index cd3e1f82e1a5..08ad6371fbe0 100644
--- a/arch/mips/kernel/topology.c
+++ b/arch/mips/kernel/topology.c
@@ -20,7 +20,7 @@ static int __init topology_init(void)
 	for_each_present_cpu(i) {
 		struct cpu *c = &per_cpu(cpu_devices, i);
 
-		c->hotpluggable = 1;
+		c->hotpluggable = !!i;
 		ret = register_cpu(c, i);
 		if (ret)
 			printk(KERN_WARNING "topology_init: register_cpu %d "
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index c52766a5b85f..ec09e594ac8a 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -2126,6 +2126,7 @@ static void configure_status(void)
 
 	change_c0_status(ST0_CU|ST0_MX|ST0_RE|ST0_FR|ST0_BEV|ST0_TS|ST0_KX|ST0_SX|ST0_UX,
 			 status_set);
+	back_to_back_c0_hazard();
 }
 
 unsigned int hwrena;
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index 33ee0d18fb0a..eb9d7af93836 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -50,7 +50,7 @@ SECTIONS
 	/* . = 0xa800000000300000; */
 	. = 0xffffffff80300000;
 #endif
-	. = VMLINUX_LOAD_ADDRESS;
+	. = LINKER_LOAD_ADDRESS;
 	/* read-only */
 	_text = .;	/* Text and read-only data */
 	.text : {
diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c
index 6176b9acba95..d0d832ab3d3b 100644
--- a/arch/mips/kernel/vpe.c
+++ b/arch/mips/kernel/vpe.c
@@ -134,7 +134,7 @@ void release_vpe(struct vpe *v)
 {
 	list_del(&v->list);
 	if (v->load_addr)
-		release_progmem(v);
+		release_progmem(v->load_addr);
 	kfree(v);
 }
 
diff --git a/arch/mips/lantiq/xway/sysctrl.c b/arch/mips/lantiq/xway/sysctrl.c
index b4323b2214e2..49a79cd67c0f 100644
--- a/arch/mips/lantiq/xway/sysctrl.c
+++ b/arch/mips/lantiq/xway/sysctrl.c
@@ -514,8 +514,8 @@ void __init ltq_soc_init(void)
 		clkdev_add_pmu("1e10b308.eth", NULL, 0, 0, PMU_SWITCH |
 			       PMU_PPE_DP | PMU_PPE_TC);
 		clkdev_add_pmu("1da00000.usif", "NULL", 1, 0, PMU_USIF);
-		clkdev_add_pmu("1e108000.gswip", "gphy0", 0, 0, PMU_GPHY);
-		clkdev_add_pmu("1e108000.gswip", "gphy1", 0, 0, PMU_GPHY);
+		clkdev_add_pmu("1e108000.switch", "gphy0", 0, 0, PMU_GPHY);
+		clkdev_add_pmu("1e108000.switch", "gphy1", 0, 0, PMU_GPHY);
 		clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU);
 		clkdev_add_pmu("1e116000.mei", "afe", 1, 2, PMU_ANALOG_DSL_AFE);
 		clkdev_add_pmu("1e116000.mei", "dfe", 1, 0, PMU_DFE);
@@ -538,8 +538,8 @@ void __init ltq_soc_init(void)
 				PMU_SWITCH | PMU_PPE_DPLUS | PMU_PPE_DPLUM |
 				PMU_PPE_EMA | PMU_PPE_TC | PMU_PPE_SLL01 |
 				PMU_PPE_QSB | PMU_PPE_TOP);
-		clkdev_add_pmu("1e108000.gswip", "gphy0", 0, 0, PMU_GPHY);
-		clkdev_add_pmu("1e108000.gswip", "gphy1", 0, 0, PMU_GPHY);
+		clkdev_add_pmu("1e108000.switch", "gphy0", 0, 0, PMU_GPHY);
+		clkdev_add_pmu("1e108000.switch", "gphy1", 0, 0, PMU_GPHY);
 		clkdev_add_pmu("1e103000.sdio", NULL, 1, 0, PMU_SDIO);
 		clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU);
 		clkdev_add_pmu("1e116000.mei", "dfe", 1, 0, PMU_DFE);
diff --git a/arch/mips/loongson64/loongson-3/platform.c b/arch/mips/loongson64/loongson-3/platform.c
index 13f3404f0030..9674ae1361a8 100644
--- a/arch/mips/loongson64/loongson-3/platform.c
+++ b/arch/mips/loongson64/loongson-3/platform.c
@@ -27,6 +27,9 @@ static int __init loongson3_platform_init(void)
 			continue;
 
 		pdev = kzalloc(sizeof(struct platform_device), GFP_KERNEL);
+		if (!pdev)
+			return -ENOMEM;
+
 		pdev->name = loongson_sysconf.sensors[i].name;
 		pdev->id = loongson_sysconf.sensors[i].id;
 		pdev->dev.platform_data = &loongson_sysconf.sensors[i];
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 3faf80c894ec..f6ab5825c03c 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -1483,6 +1483,7 @@ static void build_r4000_tlb_refill_handler(void)
 
 static void setup_pw(void)
 {
+	unsigned int pwctl;
 	unsigned long pgd_i, pgd_w;
 #ifndef __PAGETABLE_PMD_FOLDED
 	unsigned long pmd_i, pmd_w;
@@ -1509,6 +1510,7 @@ static void setup_pw(void)
 
 	pte_i = ilog2(_PAGE_GLOBAL);
 	pte_w = 0;
+	pwctl = 1 << 30; /* Set PWDirExt */
 
 #ifndef __PAGETABLE_PMD_FOLDED
 	write_c0_pwfield(pgd_i << 24 | pmd_i << 12 | pt_i << 6 | pte_i);
@@ -1519,8 +1521,9 @@ static void setup_pw(void)
 #endif
 
 #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
-	write_c0_pwctl(1 << 6 | psn);
+	pwctl |= (1 << 6 | psn);
 #endif
+	write_c0_pwctl(pwctl);
 	write_c0_kpgd((long)swapper_pg_dir);
 	kscratch_used_mask |= (1 << 7); /* KScratch6 is used for KPGD */
 }
diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c
index 46b76751f3a5..561154cbcc40 100644
--- a/arch/mips/net/ebpf_jit.c
+++ b/arch/mips/net/ebpf_jit.c
@@ -604,6 +604,7 @@ static void emit_const_to_reg(struct jit_ctx *ctx, int dst, u64 value)
 static int emit_bpf_tail_call(struct jit_ctx *ctx, int this_idx)
 {
 	int off, b_off;
+	int tcc_reg;
 
 	ctx->flags |= EBPF_SEEN_TC;
 	/*
@@ -616,14 +617,14 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx, int this_idx)
 	b_off = b_imm(this_idx + 1, ctx);
 	emit_instr(ctx, bne, MIPS_R_AT, MIPS_R_ZERO, b_off);
 	/*
-	 * if (--TCC < 0)
+	 * if (TCC-- < 0)
 	 *     goto out;
 	 */
 	/* Delay slot */
-	emit_instr(ctx, daddiu, MIPS_R_T5,
-		   (ctx->flags & EBPF_TCC_IN_V1) ? MIPS_R_V1 : MIPS_R_S4, -1);
+	tcc_reg = (ctx->flags & EBPF_TCC_IN_V1) ? MIPS_R_V1 : MIPS_R_S4;
+	emit_instr(ctx, daddiu, MIPS_R_T5, tcc_reg, -1);
 	b_off = b_imm(this_idx + 1, ctx);
-	emit_instr(ctx, bltz, MIPS_R_T5, b_off);
+	emit_instr(ctx, bltz, tcc_reg, b_off);
 	/*
 	 * prog = array->ptrs[index];
 	 * if (prog == NULL)
@@ -1803,7 +1804,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	unsigned int image_size;
 	u8 *image_ptr;
 
-	if (!prog->jit_requested || MIPS_ISA_REV < 2)
+	if (!prog->jit_requested)
 		return prog;
 
 	tmp = bpf_jit_blind_constants(prog);
diff --git a/arch/mips/pci/pci-xtalk-bridge.c b/arch/mips/pci/pci-xtalk-bridge.c
index bcf7f559789a..c1b8c545ef92 100644
--- a/arch/mips/pci/pci-xtalk-bridge.c
+++ b/arch/mips/pci/pci-xtalk-bridge.c
@@ -322,16 +322,15 @@ static int bridge_set_affinity(struct irq_data *d, const struct cpumask *mask,
 	struct bridge_irq_chip_data *data = d->chip_data;
 	int bit = d->parent_data->hwirq;
 	int pin = d->hwirq;
-	nasid_t nasid;
 	int ret, cpu;
 
 	ret = irq_chip_set_affinity_parent(d, mask, force);
 	if (ret >= 0) {
 		cpu = cpumask_first_and(mask, cpu_online_mask);
-		nasid = COMPACT_TO_NASID_NODEID(cpu_to_node(cpu));
+		data->nasid = COMPACT_TO_NASID_NODEID(cpu_to_node(cpu));
 		bridge_write(data->bc, b_int_addr[pin].addr,
 			     (((data->bc->intr_addr >> 30) & 0x30000) |
-			      bit | (nasid << 8)));
+			      bit | (data->nasid << 8)));
 		bridge_read(data->bc, b_wid_tflush);
 	}
 	return ret;
diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c
index 37be04975831..79a2f6bd2b5a 100644
--- a/arch/mips/sgi-ip27/ip27-irq.c
+++ b/arch/mips/sgi-ip27/ip27-irq.c
@@ -73,6 +73,9 @@ static void setup_hub_mask(struct hub_irq_data *hd, const struct cpumask *mask)
 	int cpu;
 
 	cpu = cpumask_first_and(mask, cpu_online_mask);
+	if (cpu >= nr_cpu_ids)
+		cpu = cpumask_any(cpu_online_mask);
+
 	nasid = COMPACT_TO_NASID_NODEID(cpu_to_node(cpu));
 	hd->cpu = cpu;
 	if (!cputoslice(cpu)) {
@@ -139,6 +142,7 @@ static int hub_domain_alloc(struct irq_domain *domain, unsigned int virq,
 	/* use CPU connected to nearest hub */
 	hub = hub_data(NASID_TO_COMPACT_NODEID(info->nasid));
 	setup_hub_mask(hd, &hub->h_cpus);
+	info->nasid = cpu_to_node(hd->cpu);
 
 	/* Make sure it's not already pending when we connect it. */
 	REMOTE_HUB_CLR_INTR(info->nasid, swlevel);
diff --git a/arch/mips/tools/elf-entry.c b/arch/mips/tools/elf-entry.c
index adde79ce7fc0..dbd14ff05b4c 100644
--- a/arch/mips/tools/elf-entry.c
+++ b/arch/mips/tools/elf-entry.c
@@ -51,11 +51,14 @@ int main(int argc, const char *argv[])
 	nread = fread(&hdr, 1, sizeof(hdr), file);
 	if (nread != sizeof(hdr)) {
 		perror("Unable to read input file");
+		fclose(file);
 		return EXIT_FAILURE;
 	}
 
-	if (memcmp(hdr.ehdr32.e_ident, ELFMAG, SELFMAG))
+	if (memcmp(hdr.ehdr32.e_ident, ELFMAG, SELFMAG)) {
+		fclose(file);
 		die("Input is not an ELF\n");
+	}
 
 	switch (hdr.ehdr32.e_ident[EI_CLASS]) {
 	case ELFCLASS32:
@@ -67,6 +70,7 @@ int main(int argc, const char *argv[])
 			entry = be32toh(hdr.ehdr32.e_entry);
 			break;
 		default:
+			fclose(file);
 			die("Invalid ELF encoding\n");
 		}
 
@@ -83,14 +87,17 @@ int main(int argc, const char *argv[])
 			entry = be64toh(hdr.ehdr64.e_entry);
 			break;
 		default:
+			fclose(file);
 			die("Invalid ELF encoding\n");
 		}
 		break;
 
 	default:
+		fclose(file);
 		die("Invalid ELF class\n");
 	}
 
 	printf("0x%016" PRIx64 "\n", entry);
+	fclose(file);
 	return EXIT_SUCCESS;
 }
diff --git a/arch/openrisc/kernel/entry.S b/arch/openrisc/kernel/entry.S
index e4a78571f883..c6481cfc5220 100644
--- a/arch/openrisc/kernel/entry.S
+++ b/arch/openrisc/kernel/entry.S
@@ -1166,13 +1166,13 @@ ENTRY(__sys_clone)
 	l.movhi	r29,hi(sys_clone)
 	l.ori	r29,r29,lo(sys_clone)
 	l.j	_fork_save_extra_regs_and_call
-	 l.addi	r7,r1,0
+	 l.nop
 
 ENTRY(__sys_fork)
 	l.movhi	r29,hi(sys_fork)
 	l.ori	r29,r29,lo(sys_fork)
 	l.j	_fork_save_extra_regs_and_call
-	 l.addi	r3,r1,0
+	 l.nop
 
 ENTRY(sys_rt_sigreturn)
 	l.jal	_sys_rt_sigreturn
diff --git a/arch/openrisc/kernel/stacktrace.c b/arch/openrisc/kernel/stacktrace.c
index 43f140a28bc7..54d38809e22c 100644
--- a/arch/openrisc/kernel/stacktrace.c
+++ b/arch/openrisc/kernel/stacktrace.c
@@ -13,6 +13,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/stacktrace.h>
 
 #include <asm/processor.h>
@@ -68,12 +69,25 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 {
 	unsigned long *sp = NULL;
 
+	if (!try_get_task_stack(tsk))
+		return;
+
 	if (tsk == current)
 		sp = (unsigned long *) &sp;
-	else
-		sp = (unsigned long *) KSTK_ESP(tsk);
+	else {
+		unsigned long ksp;
+
+		/* Locate stack from kernel context */
+		ksp = task_thread_info(tsk)->ksp;
+		ksp += STACK_FRAME_OVERHEAD;	/* redzone */
+		ksp += sizeof(struct pt_regs);
+
+		sp = (unsigned long *) ksp;
+	}
 
 	unwind_stack(trace, sp, save_stack_address_nosched);
+
+	put_task_stack(tsk);
 }
 EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
 
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 118953d41763..6dd4171c9530 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -212,6 +212,8 @@ atomic64_set(atomic64_t *v, s64 i)
 	_atomic_spin_unlock_irqrestore(v, flags);
 }
 
+#define atomic64_set_release(v, i)	atomic64_set((v), (i))
+
 static __inline__ s64
 atomic64_read(const atomic64_t *v)
 {
diff --git a/arch/parisc/include/asm/barrier.h b/arch/parisc/include/asm/barrier.h
index dbaaca84f27f..640d46edf32e 100644
--- a/arch/parisc/include/asm/barrier.h
+++ b/arch/parisc/include/asm/barrier.h
@@ -26,6 +26,67 @@
 #define __smp_rmb()	mb()
 #define __smp_wmb()	mb()
 
+#define __smp_store_release(p, v)					\
+do {									\
+	typeof(p) __p = (p);						\
+        union { typeof(*p) __val; char __c[1]; } __u =			\
+                { .__val = (__force typeof(*p)) (v) };			\
+	compiletime_assert_atomic_type(*p);				\
+	switch (sizeof(*p)) {						\
+	case 1:								\
+		asm volatile("stb,ma %0,0(%1)"				\
+				: : "r"(*(__u8 *)__u.__c), "r"(__p)	\
+				: "memory");				\
+		break;							\
+	case 2:								\
+		asm volatile("sth,ma %0,0(%1)"				\
+				: : "r"(*(__u16 *)__u.__c), "r"(__p)	\
+				: "memory");				\
+		break;							\
+	case 4:								\
+		asm volatile("stw,ma %0,0(%1)"				\
+				: : "r"(*(__u32 *)__u.__c), "r"(__p)	\
+				: "memory");				\
+		break;							\
+	case 8:								\
+		if (IS_ENABLED(CONFIG_64BIT))				\
+			asm volatile("std,ma %0,0(%1)"			\
+				: : "r"(*(__u64 *)__u.__c), "r"(__p)	\
+				: "memory");				\
+		break;							\
+	}								\
+} while (0)
+
+#define __smp_load_acquire(p)						\
+({									\
+	union { typeof(*p) __val; char __c[1]; } __u;			\
+	typeof(p) __p = (p);						\
+	compiletime_assert_atomic_type(*p);				\
+	switch (sizeof(*p)) {						\
+	case 1:								\
+		asm volatile("ldb,ma 0(%1),%0"				\
+				: "=r"(*(__u8 *)__u.__c) : "r"(__p)	\
+				: "memory");				\
+		break;							\
+	case 2:								\
+		asm volatile("ldh,ma 0(%1),%0"				\
+				: "=r"(*(__u16 *)__u.__c) : "r"(__p)	\
+				: "memory");				\
+		break;							\
+	case 4:								\
+		asm volatile("ldw,ma 0(%1),%0"				\
+				: "=r"(*(__u32 *)__u.__c) : "r"(__p)	\
+				: "memory");				\
+		break;							\
+	case 8:								\
+		if (IS_ENABLED(CONFIG_64BIT))				\
+			asm volatile("ldd,ma 0(%1),%0"			\
+				: "=r"(*(__u64 *)__u.__c) : "r"(__p)	\
+				: "memory");				\
+		break;							\
+	}								\
+	__u.__val;							\
+})
 #include <asm-generic/barrier.h>
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/parisc/include/asm/cmpxchg.h b/arch/parisc/include/asm/cmpxchg.h
index f627c37dad9c..068958575871 100644
--- a/arch/parisc/include/asm/cmpxchg.h
+++ b/arch/parisc/include/asm/cmpxchg.h
@@ -44,8 +44,14 @@ __xchg(unsigned long x, __volatile__ void *ptr, int size)
 **		if (((unsigned long)p & 0xf) == 0)
 **			return __ldcw(p);
 */
-#define xchg(ptr, x) \
-	((__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
+#define xchg(ptr, x)							\
+({									\
+	__typeof__(*(ptr)) __ret;					\
+	__typeof__(*(ptr)) _x_ = (x);					\
+	__ret = (__typeof__(*(ptr)))					\
+		__xchg((unsigned long)_x_, (ptr), sizeof(*(ptr)));	\
+	__ret;								\
+})
 
 /* bug catcher for when unsupported size is used - won't link */
 extern void __cmpxchg_called_with_bad_pointer(void);
@@ -54,6 +60,7 @@ extern void __cmpxchg_called_with_bad_pointer(void);
 extern unsigned long __cmpxchg_u32(volatile unsigned int *m, unsigned int old,
 				   unsigned int new_);
 extern u64 __cmpxchg_u64(volatile u64 *ptr, u64 old, u64 new_);
+extern u8 __cmpxchg_u8(volatile u8 *ptr, u8 old, u8 new_);
 
 /* don't worry...optimizer will get rid of most of this */
 static inline unsigned long
@@ -65,6 +72,7 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new_, int size)
 #endif
 	case 4: return __cmpxchg_u32((unsigned int *)ptr,
 				     (unsigned int)old, (unsigned int)new_);
+	case 1: return __cmpxchg_u8((u8 *)ptr, (u8)old, (u8)new_);
 	}
 	__cmpxchg_called_with_bad_pointer();
 	return old;
diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h
index 197d2247e4db..16aec9ba2580 100644
--- a/arch/parisc/include/asm/spinlock.h
+++ b/arch/parisc/include/asm/spinlock.h
@@ -37,12 +37,8 @@ static inline void arch_spin_unlock(arch_spinlock_t *x)
 	volatile unsigned int *a;
 
 	a = __ldcw_align(x);
-#ifdef CONFIG_SMP
-	(void) __ldcw(a);
-#else
-	mb();
-#endif
-	*a = 1;
+	/* Release with ordered store. */
+	__asm__ __volatile__("stw,ma %0,0(%1)" : : "r"(1), "r"(a) : "memory");
 }
 
 static inline int arch_spin_trylock(arch_spinlock_t *x)
diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c
index 3b330e58a4f0..a5f3e50fe976 100644
--- a/arch/parisc/kernel/drivers.c
+++ b/arch/parisc/kernel/drivers.c
@@ -810,7 +810,7 @@ EXPORT_SYMBOL(device_to_hwpath);
 static void walk_native_bus(unsigned long io_io_low, unsigned long io_io_high,
                             struct device *parent);
 
-static void walk_lower_bus(struct parisc_device *dev)
+static void __init walk_lower_bus(struct parisc_device *dev)
 {
 	unsigned long io_io_low, io_io_high;
 
@@ -889,8 +889,8 @@ static void print_parisc_device(struct parisc_device *dev)
 	static int count;
 
 	print_pa_hwpath(dev, hw_path);
-	pr_info("%d. %s at 0x%px [%s] { %d, 0x%x, 0x%.3x, 0x%.5x }",
-		++count, dev->name, (void*) dev->hpa.start, hw_path, dev->id.hw_type,
+	pr_info("%d. %s at %pap [%s] { %d, 0x%x, 0x%.3x, 0x%.5x }",
+		++count, dev->name, &(dev->hpa.start), hw_path, dev->id.hw_type,
 		dev->id.hversion_rev, dev->id.hversion, dev->id.sversion);
 
 	if (dev->num_addrs) {
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index 89c801c2b5d1..d4acd0fce6f9 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -454,7 +454,6 @@
 	nop
 	LDREG		0(\ptp),\pte
 	bb,<,n		\pte,_PAGE_PRESENT_BIT,3f
-	LDCW		0(\tmp),\tmp1
 	b		\fault
 	stw		\spc,0(\tmp)
 99:	ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP)
@@ -464,23 +463,26 @@
 3:
 	.endm
 
-	/* Release pa_tlb_lock lock without reloading lock address. */
-	.macro		tlb_unlock0	spc,tmp,tmp1
+	/* Release pa_tlb_lock lock without reloading lock address.
+	   Note that the values in the register spc are limited to
+	   NR_SPACE_IDS (262144). Thus, the stw instruction always
+	   stores a nonzero value even when register spc is 64 bits.
+	   We use an ordered store to ensure all prior accesses are
+	   performed prior to releasing the lock. */
+	.macro		tlb_unlock0	spc,tmp
 #ifdef CONFIG_SMP
 98:	or,COND(=)	%r0,\spc,%r0
-	LDCW		0(\tmp),\tmp1
-	or,COND(=)	%r0,\spc,%r0
-	stw		\spc,0(\tmp)
+	stw,ma		\spc,0(\tmp)
 99:	ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP)
 #endif
 	.endm
 
 	/* Release pa_tlb_lock lock. */
-	.macro		tlb_unlock1	spc,tmp,tmp1
+	.macro		tlb_unlock1	spc,tmp
 #ifdef CONFIG_SMP
 98:	load_pa_tlb_lock \tmp
 99:	ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP)
-	tlb_unlock0	\spc,\tmp,\tmp1
+	tlb_unlock0	\spc,\tmp
 #endif
 	.endm
 
@@ -1163,7 +1165,7 @@ dtlb_miss_20w:
 	
 	idtlbt          pte,prot
 
-	tlb_unlock1	spc,t0,t1
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1189,7 +1191,7 @@ nadtlb_miss_20w:
 
 	idtlbt          pte,prot
 
-	tlb_unlock1	spc,t0,t1
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1223,7 +1225,7 @@ dtlb_miss_11:
 
 	mtsp		t1, %sr1	/* Restore sr1 */
 
-	tlb_unlock1	spc,t0,t1
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1256,7 +1258,7 @@ nadtlb_miss_11:
 
 	mtsp		t1, %sr1	/* Restore sr1 */
 
-	tlb_unlock1	spc,t0,t1
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1285,7 +1287,7 @@ dtlb_miss_20:
 
 	idtlbt          pte,prot
 
-	tlb_unlock1	spc,t0,t1
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1313,7 +1315,7 @@ nadtlb_miss_20:
 	
 	idtlbt		pte,prot
 
-	tlb_unlock1	spc,t0,t1
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1420,7 +1422,7 @@ itlb_miss_20w:
 	
 	iitlbt          pte,prot
 
-	tlb_unlock1	spc,t0,t1
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1444,7 +1446,7 @@ naitlb_miss_20w:
 
 	iitlbt          pte,prot
 
-	tlb_unlock1	spc,t0,t1
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1478,7 +1480,7 @@ itlb_miss_11:
 
 	mtsp		t1, %sr1	/* Restore sr1 */
 
-	tlb_unlock1	spc,t0,t1
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1502,7 +1504,7 @@ naitlb_miss_11:
 
 	mtsp		t1, %sr1	/* Restore sr1 */
 
-	tlb_unlock1	spc,t0,t1
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1532,7 +1534,7 @@ itlb_miss_20:
 
 	iitlbt          pte,prot
 
-	tlb_unlock1	spc,t0,t1
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1552,7 +1554,7 @@ naitlb_miss_20:
 
 	iitlbt          pte,prot
 
-	tlb_unlock1	spc,t0,t1
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1582,7 +1584,7 @@ dbit_trap_20w:
 		
 	idtlbt          pte,prot
 
-	tlb_unlock0	spc,t0,t1
+	tlb_unlock0	spc,t0
 	rfir
 	nop
 #else
@@ -1608,7 +1610,7 @@ dbit_trap_11:
 
 	mtsp            t1, %sr1     /* Restore sr1 */
 
-	tlb_unlock0	spc,t0,t1
+	tlb_unlock0	spc,t0
 	rfir
 	nop
 
@@ -1628,7 +1630,7 @@ dbit_trap_20:
 	
 	idtlbt		pte,prot
 
-	tlb_unlock0	spc,t0,t1
+	tlb_unlock0	spc,t0
 	rfir
 	nop
 #endif
diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S
index 97ac707c6bff..a37814cb66c7 100644
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -640,11 +640,7 @@ cas_action:
 	sub,<>	%r28, %r25, %r0
 2:	stw	%r24, 0(%r26)
 	/* Free lock */
-#ifdef CONFIG_SMP
-98:	LDCW	0(%sr2,%r20), %r1			/* Barrier */
-99:	ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP)
-#endif
-	stw	%r20, 0(%sr2,%r20)
+	stw,ma	%r20, 0(%sr2,%r20)
 #if ENABLE_LWS_DEBUG
 	/* Clear thread register indicator */
 	stw	%r0, 4(%sr2,%r20)
@@ -658,11 +654,7 @@ cas_action:
 3:		
 	/* Error occurred on load or store */
 	/* Free lock */
-#ifdef CONFIG_SMP
-98:	LDCW	0(%sr2,%r20), %r1			/* Barrier */
-99:	ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP)
-#endif
-	stw	%r20, 0(%sr2,%r20)
+	stw,ma	%r20, 0(%sr2,%r20)
 #if ENABLE_LWS_DEBUG
 	stw	%r0, 4(%sr2,%r20)
 #endif
@@ -863,11 +855,7 @@ cas2_action:
 
 cas2_end:
 	/* Free lock */
-#ifdef CONFIG_SMP
-98:	LDCW	0(%sr2,%r20), %r1			/* Barrier */
-99:	ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP)
-#endif
-	stw	%r20, 0(%sr2,%r20)
+	stw,ma	%r20, 0(%sr2,%r20)
 	/* Enable interrupts */
 	ssm	PSW_SM_I, %r0
 	/* Return to userspace, set no error */
@@ -877,11 +865,7 @@ cas2_end:
 22:
 	/* Error occurred on load or store */
 	/* Free lock */
-#ifdef CONFIG_SMP
-98:	LDCW	0(%sr2,%r20), %r1			/* Barrier */
-99:	ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP)
-#endif
-	stw	%r20, 0(%sr2,%r20)
+	stw,ma	%r20, 0(%sr2,%r20)
 	ssm	PSW_SM_I, %r0
 	ldo	1(%r0),%r28
 	b	lws_exit
diff --git a/arch/parisc/lib/bitops.c b/arch/parisc/lib/bitops.c
index 70ffbcf889b8..2e4d1f05a926 100644
--- a/arch/parisc/lib/bitops.c
+++ b/arch/parisc/lib/bitops.c
@@ -79,3 +79,15 @@ unsigned long __cmpxchg_u32(volatile unsigned int *ptr, unsigned int old, unsign
 	_atomic_spin_unlock_irqrestore(ptr, flags);
 	return (unsigned long)prev;
 }
+
+u8 __cmpxchg_u8(volatile u8 *ptr, u8 old, u8 new)
+{
+	unsigned long flags;
+	u8 prev;
+
+	_atomic_spin_lock_irqsave(ptr, flags);
+	if ((prev = *ptr) == old)
+		*ptr = new;
+	_atomic_spin_unlock_irqrestore(ptr, flags);
+	return prev;
+}
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index ddca8287d43b..3e54484797f6 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -588,7 +588,7 @@ void __init mem_init(void)
 			> BITS_PER_LONG);
 
 	high_memory = __va((max_pfn << PAGE_SHIFT));
-	set_max_mapnr(page_to_pfn(virt_to_page(high_memory - 1)) + 1);
+	set_max_mapnr(max_low_pfn);
 	memblock_free_all();
 
 #ifdef CONFIG_PA11
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index f7a363cbc1bb..1cbadb60612d 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -126,13 +126,14 @@ config PPC
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_KCOV
+	select ARCH_HAS_HUGEPD			if HUGETLB_PAGE
 	select ARCH_HAS_MMIOWB			if PPC64
 	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_HAS_PMEM_API                if PPC64
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_MEMBARRIER_CALLBACKS
 	select ARCH_HAS_SCALED_CPUTIME		if VIRT_CPU_ACCOUNTING_NATIVE && PPC64
-	select ARCH_HAS_STRICT_KERNEL_RWX	if ((PPC_BOOK3S_64 || PPC32) && !RELOCATABLE && !HIBERNATION)
+	select ARCH_HAS_STRICT_KERNEL_RWX	if (PPC32 && !HIBERNATION)
 	select ARCH_HAS_TICK_BROADCAST		if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if PPC64
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
@@ -214,8 +215,7 @@ config PPC
 	select HAVE_HARDLOCKUP_DETECTOR_PERF	if PERF_EVENTS && HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
-	select HAVE_RCU_TABLE_FREE		if SMP
-	select HAVE_RCU_TABLE_NO_INVALIDATE	if HAVE_RCU_TABLE_FREE
+	select HAVE_RCU_TABLE_FREE
 	select HAVE_MMU_GATHER_PAGE_SIZE
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE		if PPC_BOOK3S_64 && CPU_LITTLE_ENDIAN
@@ -230,11 +230,13 @@ config PPC
 	select NEED_DMA_MAP_STATE		if PPC64 || NOT_COHERENT_CACHE
 	select NEED_SG_DMA_LENGTH
 	select OF
+	select OF_DMA_DEFAULT_COHERENT		if !NOT_COHERENT_CACHE
 	select OF_EARLY_FLATTREE
 	select OLD_SIGACTION			if PPC32
 	select OLD_SIGSUSPEND
 	select PCI_DOMAINS			if PCI
 	select PCI_SYSCALL			if PCI
+	select PPC_DAWR				if PPC64
 	select RTC_LIB
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
@@ -371,6 +373,9 @@ config PPC_ADV_DEBUG_DAC_RANGE
 	depends on PPC_ADV_DEBUG_REGS && 44x
 	default y
 
+config PPC_DAWR
+	bool
+
 config ZONE_DMA
 	bool
 	default y if PPC_BOOK3E_64
@@ -716,6 +721,7 @@ config THREAD_SHIFT
 	range 13 15
 	default "15" if PPC_256K_PAGES
 	default "14" if PPC64
+	default "14" if KASAN
 	default "13"
 	help
 	  Used to define the stack size. The default is almost always what you
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index c59920920ddc..b915fe658979 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -371,7 +371,7 @@ config PPC_PTDUMP
 
 config PPC_DEBUG_WX
 	bool "Warn on W+X mappings at boot"
-	depends on PPC_PTDUMP
+	depends on PPC_PTDUMP && STRICT_KERNEL_RWX
 	help
 	  Generate a warning if any W+X mappings are found at boot.
 
diff --git a/arch/powerpc/Makefile.postlink b/arch/powerpc/Makefile.postlink
index 83f8e5ba2722..1dc88ad66867 100644
--- a/arch/powerpc/Makefile.postlink
+++ b/arch/powerpc/Makefile.postlink
@@ -17,11 +17,11 @@ quiet_cmd_head_check = CHKHEAD $@
 quiet_cmd_relocs_check = CHKREL  $@
 ifdef CONFIG_PPC_BOOK3S_64
       cmd_relocs_check =						\
-	$(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$@" ; \
+	$(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$(NM)" "$@" ; \
 	$(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/unrel_branch_check.sh "$(OBJDUMP)" "$@"
 else
       cmd_relocs_check =						\
-	$(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$@"
+	$(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$(NM)" "$@"
 endif
 
 # `@true` prevents complaint when there is nothing to be done
diff --git a/arch/powerpc/boot/4xx.c b/arch/powerpc/boot/4xx.c
index 1699e9531552..00c4d843a023 100644
--- a/arch/powerpc/boot/4xx.c
+++ b/arch/powerpc/boot/4xx.c
@@ -228,7 +228,7 @@ void ibm4xx_denali_fixup_memsize(void)
 		dpath = 8; /* 64 bits */
 
 	/* get address pins (rows) */
- 	val = SDRAM0_READ(DDR0_42);
+	val = SDRAM0_READ(DDR0_42);
 
 	row = DDR_GET_VAL(val, DDR_APIN, DDR_APIN_SHIFT);
 	if (row > max_row)
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 73d1f3562978..a6fd5d43a9ba 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -122,7 +122,7 @@ src-wlib-y := string.S crt0.S stdio.c decompress.c main.c \
 		elf_util.c $(zlib-y) devtree.c stdlib.c \
 		oflib.c ofconsole.c cuboot.c
 
-src-wlib-$(CONFIG_PPC_MPC52XX) += mpc52xx-psc.c
+src-wlib-$(CONFIG_PPC_MPC52xx) += mpc52xx-psc.c
 src-wlib-$(CONFIG_PPC64_BOOT_WRAPPER) += opal-calls.S opal.c
 ifndef CONFIG_PPC64_BOOT_WRAPPER
 src-wlib-y += crtsavres.S
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0-best-effort.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0-best-effort.dtsi
index e1a961f05dcd..baa0c503e741 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0-best-effort.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0-best-effort.dtsi
@@ -63,6 +63,7 @@ fman@400000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xe1000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy0: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0.dtsi
index c288f3c6c637..93095600e808 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0.dtsi
@@ -60,6 +60,7 @@ fman@400000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xf1000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy6: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi
index 94f3e7175012..ff4bd38f0645 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi
@@ -63,6 +63,7 @@ fman@400000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xe3000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy1: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1.dtsi
index 94a76982d214..1fa38ed6f59e 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1.dtsi
@@ -60,6 +60,7 @@ fman@400000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xf3000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy7: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-0.dtsi
index b5ff5f71c6b8..a8cc9780c0c4 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-0.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-0.dtsi
@@ -59,6 +59,7 @@ fman@400000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xe1000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy0: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-1.dtsi
index ee44182c6348..8b8bd70c9382 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-1.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-1.dtsi
@@ -59,6 +59,7 @@ fman@400000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xe3000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy1: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-2.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-2.dtsi
index f05f0d775039..619c880b54d8 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-2.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-2.dtsi
@@ -59,6 +59,7 @@ fman@400000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xe5000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy2: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-3.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-3.dtsi
index a9114ec51075..d7ebb73a400d 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-3.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-3.dtsi
@@ -59,6 +59,7 @@ fman@400000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xe7000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy3: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-4.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-4.dtsi
index 44dd00ac7367..b151d696a069 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-4.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-4.dtsi
@@ -59,6 +59,7 @@ fman@400000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xe9000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy4: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-5.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-5.dtsi
index 5b1b84b58602..adc0ae0013a3 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-5.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-5.dtsi
@@ -59,6 +59,7 @@ fman@400000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xeb000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy5: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-0.dtsi
index 0e1daaef9e74..435047e0e250 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-0.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-0.dtsi
@@ -60,6 +60,7 @@ fman@500000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xf1000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy14: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-1.dtsi
index 68c5ef779266..c098657cca0a 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-1.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-1.dtsi
@@ -60,6 +60,7 @@ fman@500000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xf3000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy15: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-0.dtsi
index 605363cc1117..9d06824815f3 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-0.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-0.dtsi
@@ -59,6 +59,7 @@ fman@500000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xe1000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy8: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-1.dtsi
index 1955dfa13634..70e947730c4b 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-1.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-1.dtsi
@@ -59,6 +59,7 @@ fman@500000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xe3000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy9: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-2.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-2.dtsi
index 2c1476454ee0..ad96e6529595 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-2.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-2.dtsi
@@ -59,6 +59,7 @@ fman@500000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xe5000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy10: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-3.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-3.dtsi
index b8b541ff5fb0..034bc4b71f7a 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-3.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-3.dtsi
@@ -59,6 +59,7 @@ fman@500000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xe7000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy11: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-4.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-4.dtsi
index 4b2cfddd1b15..93ca23d82b39 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-4.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-4.dtsi
@@ -59,6 +59,7 @@ fman@500000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xe9000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy12: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-5.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-5.dtsi
index 0a52ddf7cc17..23b3117a2fd2 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-5.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-5.dtsi
@@ -59,6 +59,7 @@ fman@500000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xeb000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy13: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/serial.c b/arch/powerpc/boot/serial.c
index b0491b8c0199..afef4fcdea98 100644
--- a/arch/powerpc/boot/serial.c
+++ b/arch/powerpc/boot/serial.c
@@ -129,7 +129,7 @@ int serial_console_init(void)
 	         dt_is_compatible(devp, "fsl,cpm2-smc-uart"))
 		rc = cpm_console_init(devp, &serial_cd);
 #endif
-#ifdef CONFIG_PPC_MPC52XX
+#ifdef CONFIG_PPC_MPC52xx
 	else if (dt_is_compatible(devp, "fsl,mpc5200-psc-uart"))
 		rc = mpc5200_psc_console_init(devp, &serial_cd);
 #endif
diff --git a/arch/powerpc/include/asm/archrandom.h b/arch/powerpc/include/asm/archrandom.h
index 9c63b596e6ce..a09595f00cab 100644
--- a/arch/powerpc/include/asm/archrandom.h
+++ b/arch/powerpc/include/asm/archrandom.h
@@ -28,7 +28,7 @@ static inline int arch_get_random_seed_int(unsigned int *v)
 	unsigned long val;
 	int rc;
 
-	rc = arch_get_random_long(&val);
+	rc = arch_get_random_seed_long(&val);
 	if (rc)
 		*v = val;
 
diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h
index f9dc597b0b86..6eb311eb818b 100644
--- a/arch/powerpc/include/asm/book3s/32/kup.h
+++ b/arch/powerpc/include/asm/book3s/32/kup.h
@@ -2,6 +2,7 @@
 #ifndef _ASM_POWERPC_BOOK3S_32_KUP_H
 #define _ASM_POWERPC_BOOK3S_32_KUP_H
 
+#include <asm/bug.h>
 #include <asm/book3s/32/mmu-hash.h>
 
 #ifdef __ASSEMBLY__
@@ -75,7 +76,7 @@
 
 .macro kuap_check	current, gpr
 #ifdef CONFIG_PPC_KUAP_DEBUG
-	lwz	\gpr2, KUAP(thread)
+	lwz	\gpr, THREAD + KUAP(\current)
 999:	twnei	\gpr, 0
 	EMIT_BUG_ENTRY 999b, __FILE__, __LINE__, (BUGFLAG_WARNING | BUGFLAG_ONCE)
 #endif
@@ -102,11 +103,13 @@ static inline void kuap_update_sr(u32 sr, u32 addr, u32 end)
 	isync();	/* Context sync required after mtsrin() */
 }
 
-static inline void allow_user_access(void __user *to, const void __user *from, u32 size)
+static __always_inline void allow_user_access(void __user *to, const void __user *from,
+					      u32 size, unsigned long dir)
 {
 	u32 addr, end;
 
-	if (__builtin_constant_p(to) && to == NULL)
+	BUILD_BUG_ON(!__builtin_constant_p(dir));
+	if (!(dir & KUAP_WRITE))
 		return;
 
 	addr = (__force u32)to;
@@ -119,11 +122,16 @@ static inline void allow_user_access(void __user *to, const void __user *from, u
 	kuap_update_sr(mfsrin(addr) & ~SR_KS, addr, end);	/* Clear Ks */
 }
 
-static inline void prevent_user_access(void __user *to, const void __user *from, u32 size)
+static __always_inline void prevent_user_access(void __user *to, const void __user *from,
+						u32 size, unsigned long dir)
 {
 	u32 addr = (__force u32)to;
 	u32 end = min(addr + size, TASK_SIZE);
 
+	BUILD_BUG_ON(!__builtin_constant_p(dir));
+	if (!(dir & KUAP_WRITE))
+		return;
+
 	if (!addr || addr >= TASK_SIZE || !size)
 		return;
 
@@ -131,12 +139,17 @@ static inline void prevent_user_access(void __user *to, const void __user *from,
 	kuap_update_sr(mfsrin(addr) | SR_KS, addr, end);	/* set Ks */
 }
 
-static inline bool bad_kuap_fault(struct pt_regs *regs, bool is_write)
+static inline bool
+bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
 {
+	unsigned long begin = regs->kuap & 0xf0000000;
+	unsigned long end = regs->kuap << 28;
+
 	if (!is_write)
 		return false;
 
-	return WARN(!regs->kuap, "Bug: write fault blocked by segment registers !");
+	return WARN(address < begin || address >= end,
+		    "Bug: write fault blocked by segment registers !");
 }
 
 #endif /* CONFIG_PPC_KUAP */
diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h
index 998317702630..dc5c039eb28e 100644
--- a/arch/powerpc/include/asm/book3s/32/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h
@@ -49,7 +49,6 @@ static inline void pgtable_free(void *table, unsigned index_size)
 
 #define get_hugepd_cache_index(x)  (x)
 
-#ifdef CONFIG_SMP
 static inline void pgtable_free_tlb(struct mmu_gather *tlb,
 				    void *table, int shift)
 {
@@ -66,13 +65,6 @@ static inline void __tlb_remove_table(void *_table)
 
 	pgtable_free(table, shift);
 }
-#else
-static inline void pgtable_free_tlb(struct mmu_gather *tlb,
-				    void *table, int shift)
-{
-	pgtable_free(table, shift);
-}
-#endif
 
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
 				  unsigned long address)
diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index 8fd8599c9395..3f9ae3585ab9 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -156,6 +156,12 @@ extern pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm,
 extern int hash__has_transparent_hugepage(void);
 #endif
 
+static inline pmd_t hash__pmd_mkdevmap(pmd_t pmd)
+{
+	BUG();
+	return pmd;
+}
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_BOOK3S_64_HASH_4K_H */
diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
index d1d9177d9ebd..0729c034e56f 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -246,7 +246,7 @@ static inline void mark_hpte_slot_valid(unsigned char *hpte_slot_array,
  */
 static inline int hash__pmd_trans_huge(pmd_t pmd)
 {
-	return !!((pmd_val(pmd) & (_PAGE_PTE | H_PAGE_THP_HUGE)) ==
+	return !!((pmd_val(pmd) & (_PAGE_PTE | H_PAGE_THP_HUGE | _PAGE_DEVMAP)) ==
 		  (_PAGE_PTE | H_PAGE_THP_HUGE));
 }
 
@@ -272,6 +272,12 @@ extern pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm,
 				       unsigned long addr, pmd_t *pmdp);
 extern int hash__has_transparent_hugepage(void);
 #endif /*  CONFIG_TRANSPARENT_HUGEPAGE */
+
+static inline pmd_t hash__pmd_mkdevmap(pmd_t pmd)
+{
+	return __pmd(pmd_val(pmd) | (_PAGE_PTE | H_PAGE_THP_HUGE | _PAGE_DEVMAP));
+}
+
 #endif	/* __ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_BOOK3S_64_HASH_64K_H */
diff --git a/arch/powerpc/include/asm/book3s/64/kup-radix.h b/arch/powerpc/include/asm/book3s/64/kup-radix.h
index f254de956d6a..c8d1076e0ebb 100644
--- a/arch/powerpc/include/asm/book3s/64/kup-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/kup-radix.h
@@ -77,25 +77,27 @@ static inline void set_kuap(unsigned long value)
 	isync();
 }
 
-static inline void allow_user_access(void __user *to, const void __user *from,
-				     unsigned long size)
+static __always_inline void allow_user_access(void __user *to, const void __user *from,
+					      unsigned long size, unsigned long dir)
 {
 	// This is written so we can resolve to a single case at build time
-	if (__builtin_constant_p(to) && to == NULL)
+	BUILD_BUG_ON(!__builtin_constant_p(dir));
+	if (dir == KUAP_READ)
 		set_kuap(AMR_KUAP_BLOCK_WRITE);
-	else if (__builtin_constant_p(from) && from == NULL)
+	else if (dir == KUAP_WRITE)
 		set_kuap(AMR_KUAP_BLOCK_READ);
 	else
 		set_kuap(0);
 }
 
 static inline void prevent_user_access(void __user *to, const void __user *from,
-				       unsigned long size)
+				       unsigned long size, unsigned long dir)
 {
 	set_kuap(AMR_KUAP_BLOCKED);
 }
 
-static inline bool bad_kuap_fault(struct pt_regs *regs, bool is_write)
+static inline bool
+bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
 {
 	return WARN(mmu_has_feature(MMU_FTR_RADIX_KUAP) &&
 		    (regs->kuap & (is_write ? AMR_KUAP_BLOCK_WRITE : AMR_KUAP_BLOCK_READ)),
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index 15b75005bc34..3fa1b962dc27 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -600,8 +600,11 @@ extern void slb_set_size(u16 size);
  *
  */
 #define MAX_USER_CONTEXT	((ASM_CONST(1) << CONTEXT_BITS) - 2)
+
+// The + 2 accounts for INVALID_REGION and 1 more to avoid overlap with kernel
 #define MIN_USER_CONTEXT	(MAX_KERNEL_CTX_CNT + MAX_VMALLOC_CTX_CNT + \
-				 MAX_IO_CTX_CNT + MAX_VMEMMAP_CTX_CNT)
+				 MAX_IO_CTX_CNT + MAX_VMEMMAP_CTX_CNT + 2)
+
 /*
  * For platforms that support on 65bit VA we limit the context bits
  */
diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h
index d5a44912902f..cae9e814593a 100644
--- a/arch/powerpc/include/asm/book3s/64/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h
@@ -19,9 +19,7 @@ extern struct vmemmap_backing *vmemmap_list;
 extern pmd_t *pmd_fragment_alloc(struct mm_struct *, unsigned long);
 extern void pmd_fragment_free(unsigned long *);
 extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift);
-#ifdef CONFIG_SMP
 extern void __tlb_remove_table(void *_table);
-#endif
 void pte_frag_destroy(void *pte_frag);
 
 static inline pgd_t *radix__pgd_alloc(struct mm_struct *mm)
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index ccf00a8b98c6..e8b60bc8e7b9 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -990,10 +990,25 @@ extern struct page *pgd_page(pgd_t pgd);
 #define pud_page_vaddr(pud)	__va(pud_val(pud) & ~PUD_MASKED_BITS)
 #define pgd_page_vaddr(pgd)	__va(pgd_val(pgd) & ~PGD_MASKED_BITS)
 
-#define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & (PTRS_PER_PGD - 1))
-#define pud_index(address) (((address) >> (PUD_SHIFT)) & (PTRS_PER_PUD - 1))
-#define pmd_index(address) (((address) >> (PMD_SHIFT)) & (PTRS_PER_PMD - 1))
-#define pte_index(address) (((address) >> (PAGE_SHIFT)) & (PTRS_PER_PTE - 1))
+static inline unsigned long pgd_index(unsigned long address)
+{
+	return (address >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1);
+}
+
+static inline unsigned long pud_index(unsigned long address)
+{
+	return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1);
+}
+
+static inline unsigned long pmd_index(unsigned long address)
+{
+	return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1);
+}
+
+static inline unsigned long pte_index(unsigned long address)
+{
+	return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
+}
 
 /*
  * Find an entry in a page-table-directory.  We combine the address region
@@ -1295,7 +1310,9 @@ extern void serialize_against_pte_lookup(struct mm_struct *mm);
 
 static inline pmd_t pmd_mkdevmap(pmd_t pmd)
 {
-	return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_DEVMAP));
+	if (radix_enabled())
+		return radix__pmd_mkdevmap(pmd);
+	return hash__pmd_mkdevmap(pmd);
 }
 
 static inline int pmd_devmap(pmd_t pmd)
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index 574eca33f893..0efada5b4600 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -257,6 +257,11 @@ extern pmd_t radix__pmdp_huge_get_and_clear(struct mm_struct *mm,
 extern int radix__has_transparent_hugepage(void);
 #endif
 
+static inline pmd_t radix__pmd_mkdevmap(pmd_t pmd)
+{
+	return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_DEVMAP));
+}
+
 extern int __meminit radix__vmemmap_create_mapping(unsigned long start,
 					     unsigned long page_size,
 					     unsigned long phys);
diff --git a/arch/powerpc/include/asm/drmem.h b/arch/powerpc/include/asm/drmem.h
index 3d76e1c388c2..28c3d936fdf3 100644
--- a/arch/powerpc/include/asm/drmem.h
+++ b/arch/powerpc/include/asm/drmem.h
@@ -27,12 +27,12 @@ struct drmem_lmb_info {
 extern struct drmem_lmb_info *drmem_info;
 
 #define for_each_drmem_lmb_in_range(lmb, start, end)		\
-	for ((lmb) = (start); (lmb) <= (end); (lmb)++)
+	for ((lmb) = (start); (lmb) < (end); (lmb)++)
 
 #define for_each_drmem_lmb(lmb)					\
 	for_each_drmem_lmb_in_range((lmb),			\
 		&drmem_info->lmbs[0],				\
-		&drmem_info->lmbs[drmem_info->n_lmbs - 1])
+		&drmem_info->lmbs[drmem_info->n_lmbs])
 
 /*
  * The of_drconf_cell_v1 struct defines the layout of the LMB data
diff --git a/arch/powerpc/include/asm/futex.h b/arch/powerpc/include/asm/futex.h
index eea28ca679db..bc7d9d06a6d9 100644
--- a/arch/powerpc/include/asm/futex.h
+++ b/arch/powerpc/include/asm/futex.h
@@ -35,7 +35,7 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
 {
 	int oldval = 0, ret;
 
-	allow_write_to_user(uaddr, sizeof(*uaddr));
+	allow_read_write_user(uaddr, uaddr, sizeof(*uaddr));
 	pagefault_disable();
 
 	switch (op) {
@@ -62,7 +62,7 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
 
 	*oval = oldval;
 
-	prevent_write_to_user(uaddr, sizeof(*uaddr));
+	prevent_read_write_user(uaddr, uaddr, sizeof(*uaddr));
 	return ret;
 }
 
@@ -76,7 +76,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	if (!access_ok(uaddr, sizeof(u32)))
 		return -EFAULT;
 
-	allow_write_to_user(uaddr, sizeof(*uaddr));
+	allow_read_write_user(uaddr, uaddr, sizeof(*uaddr));
+
         __asm__ __volatile__ (
         PPC_ATOMIC_ENTRY_BARRIER
 "1:     lwarx   %1,0,%3         # futex_atomic_cmpxchg_inatomic\n\
@@ -97,7 +98,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
         : "cc", "memory");
 
 	*uval = prev;
-	prevent_write_to_user(uaddr, sizeof(*uaddr));
+	prevent_read_write_user(uaddr, uaddr, sizeof(*uaddr));
+
         return ret;
 }
 
diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h
index 78202d5fb13a..67e2da195eae 100644
--- a/arch/powerpc/include/asm/hw_breakpoint.h
+++ b/arch/powerpc/include/asm/hw_breakpoint.h
@@ -76,18 +76,25 @@ static inline void hw_breakpoint_disable(void)
 extern void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs);
 int hw_breakpoint_handler(struct die_args *args);
 
-extern int set_dawr(struct arch_hw_breakpoint *brk);
+#else	/* CONFIG_HAVE_HW_BREAKPOINT */
+static inline void hw_breakpoint_disable(void) { }
+static inline void thread_change_pc(struct task_struct *tsk,
+					struct pt_regs *regs) { }
+
+#endif	/* CONFIG_HAVE_HW_BREAKPOINT */
+
+
+#ifdef CONFIG_PPC_DAWR
 extern bool dawr_force_enable;
 static inline bool dawr_enabled(void)
 {
 	return dawr_force_enable;
 }
-
-#else	/* CONFIG_HAVE_HW_BREAKPOINT */
-static inline void hw_breakpoint_disable(void) { }
-static inline void thread_change_pc(struct task_struct *tsk,
-					struct pt_regs *regs) { }
+int set_dawr(struct arch_hw_breakpoint *brk);
+#else
 static inline bool dawr_enabled(void) { return false; }
-#endif	/* CONFIG_HAVE_HW_BREAKPOINT */
+static inline int set_dawr(struct arch_hw_breakpoint *brk) { return -1; }
+#endif
+
 #endif	/* __KERNEL__ */
 #endif	/* _PPC_BOOK3S_64_HW_BREAKPOINT_H */
diff --git a/arch/powerpc/include/asm/kasan.h b/arch/powerpc/include/asm/kasan.h
index 296e51c2f066..6db06f58deed 100644
--- a/arch/powerpc/include/asm/kasan.h
+++ b/arch/powerpc/include/asm/kasan.h
@@ -23,9 +23,7 @@
 
 #define KASAN_SHADOW_OFFSET	ASM_CONST(CONFIG_KASAN_SHADOW_OFFSET)
 
-#define KASAN_SHADOW_END	0UL
-
-#define KASAN_SHADOW_SIZE	(KASAN_SHADOW_END - KASAN_SHADOW_START)
+#define KASAN_SHADOW_END	(-(-KASAN_SHADOW_START >> KASAN_SHADOW_SCALE_SHIFT))
 
 #ifdef CONFIG_KASAN
 void kasan_early_init(void);
diff --git a/arch/powerpc/include/asm/kup.h b/arch/powerpc/include/asm/kup.h
index 5b5e39643a27..94f24928916a 100644
--- a/arch/powerpc/include/asm/kup.h
+++ b/arch/powerpc/include/asm/kup.h
@@ -2,6 +2,10 @@
 #ifndef _ASM_POWERPC_KUP_H_
 #define _ASM_POWERPC_KUP_H_
 
+#define KUAP_READ	1
+#define KUAP_WRITE	2
+#define KUAP_READ_WRITE	(KUAP_READ | KUAP_WRITE)
+
 #ifdef CONFIG_PPC64
 #include <asm/book3s/64/kup-radix.h>
 #endif
@@ -42,32 +46,48 @@ void setup_kuap(bool disabled);
 #else
 static inline void setup_kuap(bool disabled) { }
 static inline void allow_user_access(void __user *to, const void __user *from,
-				     unsigned long size) { }
+				     unsigned long size, unsigned long dir) { }
 static inline void prevent_user_access(void __user *to, const void __user *from,
-				       unsigned long size) { }
-static inline bool bad_kuap_fault(struct pt_regs *regs, bool is_write) { return false; }
+				       unsigned long size, unsigned long dir) { }
+static inline bool
+bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
+{
+	return false;
+}
 #endif /* CONFIG_PPC_KUAP */
 
 static inline void allow_read_from_user(const void __user *from, unsigned long size)
 {
-	allow_user_access(NULL, from, size);
+	allow_user_access(NULL, from, size, KUAP_READ);
 }
 
 static inline void allow_write_to_user(void __user *to, unsigned long size)
 {
-	allow_user_access(to, NULL, size);
+	allow_user_access(to, NULL, size, KUAP_WRITE);
+}
+
+static inline void allow_read_write_user(void __user *to, const void __user *from,
+					 unsigned long size)
+{
+	allow_user_access(to, from, size, KUAP_READ_WRITE);
 }
 
 static inline void prevent_read_from_user(const void __user *from, unsigned long size)
 {
-	prevent_user_access(NULL, from, size);
+	prevent_user_access(NULL, from, size, KUAP_READ);
 }
 
 static inline void prevent_write_to_user(void __user *to, unsigned long size)
 {
-	prevent_user_access(to, NULL, size);
+	prevent_user_access(to, NULL, size, KUAP_WRITE);
+}
+
+static inline void prevent_read_write_user(void __user *to, const void __user *from,
+					   unsigned long size)
+{
+	prevent_user_access(to, from, size, KUAP_READ_WRITE);
 }
 
 #endif /* !__ASSEMBLY__ */
 
-#endif /* _ASM_POWERPC_KUP_H_ */
+#endif /* _ASM_POWERPC_KUAP_H_ */
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index bb7c8cc77f1a..04b2b927bb5a 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -535,7 +535,7 @@ static inline void note_hpte_modification(struct kvm *kvm,
  */
 static inline struct kvm_memslots *kvm_memslots_raw(struct kvm *kvm)
 {
-	return rcu_dereference_raw_notrace(kvm->memslots[0]);
+	return rcu_dereference_raw_check(kvm->memslots[0]);
 }
 
 extern void kvmppc_mmu_debugfs_init(struct kvm *kvm);
diff --git a/arch/powerpc/include/asm/nohash/32/kup-8xx.h b/arch/powerpc/include/asm/nohash/32/kup-8xx.h
index 1c3133b5f86a..6fe97465e350 100644
--- a/arch/powerpc/include/asm/nohash/32/kup-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/kup-8xx.h
@@ -34,18 +34,19 @@
 #include <asm/reg.h>
 
 static inline void allow_user_access(void __user *to, const void __user *from,
-				     unsigned long size)
+				     unsigned long size, unsigned long dir)
 {
 	mtspr(SPRN_MD_AP, MD_APG_INIT);
 }
 
 static inline void prevent_user_access(void __user *to, const void __user *from,
-				       unsigned long size)
+				       unsigned long size, unsigned long dir)
 {
 	mtspr(SPRN_MD_AP, MD_APG_KUAP);
 }
 
-static inline bool bad_kuap_fault(struct pt_regs *regs, bool is_write)
+static inline bool
+bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
 {
 	return WARN(!((regs->kuap ^ MD_APG_KUAP) & 0xf0000000),
 		    "Bug: fault blocked by AP register !");
diff --git a/arch/powerpc/include/asm/nohash/pgalloc.h b/arch/powerpc/include/asm/nohash/pgalloc.h
index 332b13b4ecdb..29c43665a753 100644
--- a/arch/powerpc/include/asm/nohash/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/pgalloc.h
@@ -46,7 +46,6 @@ static inline void pgtable_free(void *table, int shift)
 
 #define get_hugepd_cache_index(x)	(x)
 
-#ifdef CONFIG_SMP
 static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
 {
 	unsigned long pgf = (unsigned long)table;
@@ -64,13 +63,6 @@ static inline void __tlb_remove_table(void *_table)
 	pgtable_free(table, shift);
 }
 
-#else
-static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
-{
-	pgtable_free(table, shift);
-}
-#endif
-
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
 				  unsigned long address)
 {
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 0d52f57fca04..f3e5b3c73432 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -285,8 +285,13 @@ static inline bool pfn_valid(unsigned long pfn)
 /*
  * Some number of bits at the level of the page table that points to
  * a hugepte are used to encode the size.  This masks those bits.
+ * On 8xx, HW assistance requires 4k alignment for the hugepte.
  */
+#ifdef CONFIG_PPC_8xx
+#define HUGEPD_SHIFT_MASK     0xfff
+#else
 #define HUGEPD_SHIFT_MASK     0x3f
+#endif
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/powerpc/include/asm/percpu.h b/arch/powerpc/include/asm/percpu.h
index dce863a7635c..8e5b7d0b851c 100644
--- a/arch/powerpc/include/asm/percpu.h
+++ b/arch/powerpc/include/asm/percpu.h
@@ -10,8 +10,6 @@
 
 #ifdef CONFIG_SMP
 
-#include <asm/paca.h>
-
 #define __my_cpu_offset local_paca->data_offset
 
 #endif /* CONFIG_SMP */
@@ -19,4 +17,6 @@
 
 #include <asm-generic/percpu.h>
 
+#include <asm/paca.h>
+
 #endif /* _ASM_POWERPC_PERCPU_H_ */
diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h
index 7426d7a90e1e..7aba3c7ea25c 100644
--- a/arch/powerpc/include/asm/perf_event.h
+++ b/arch/powerpc/include/asm/perf_event.h
@@ -12,6 +12,8 @@
 
 #ifdef CONFIG_PPC_PERF_CTRS
 #include <asm/perf_event_server.h>
+#else
+static inline bool is_sier_available(void) { return false; }
 #endif
 
 #ifdef CONFIG_FSL_EMB_PERF_EVENT
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 64145751b2fd..f7ee707734bc 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -144,13 +144,9 @@ static inline void pte_frag_set(mm_context_t *ctx, void *p)
 #define is_ioremap_addr is_ioremap_addr
 static inline bool is_ioremap_addr(const void *x)
 {
-#ifdef CONFIG_MMU
 	unsigned long addr = (unsigned long)x;
 
 	return addr >= IOREMAP_BASE && addr < IOREMAP_END;
-#else
-	return false;
-#endif
 }
 #endif /* CONFIG_PPC64 */
 
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index ef573fe9873e..c92795f55ffb 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -291,7 +291,6 @@ struct thread_struct {
 #else
 #define INIT_THREAD  { \
 	.ksp = INIT_SP, \
-	.regs = (struct pt_regs *)INIT_SP - 1, /* XXX bogus, I think */ \
 	.addr_limit = KERNEL_DS, \
 	.fpexc_mode = 0, \
 	.fscr = FSCR_TAR | FSCR_EBB \
diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index 3c1887351c71..bd227e0eab07 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -368,8 +368,6 @@ extern int rtas_set_indicator_fast(int indicator, int index, int new_value);
 extern void rtas_progress(char *s, unsigned short hex);
 extern int rtas_suspend_cpu(struct rtas_suspend_me_data *data);
 extern int rtas_suspend_last_cpu(struct rtas_suspend_me_data *data);
-extern int rtas_online_cpus_mask(cpumask_var_t cpus);
-extern int rtas_offline_cpus_mask(cpumask_var_t cpus);
 extern int rtas_ibm_suspend_me(u64 handle);
 
 struct rtc_time;
diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h
index ccf44c135389..7c05e95a5c44 100644
--- a/arch/powerpc/include/asm/security_features.h
+++ b/arch/powerpc/include/asm/security_features.h
@@ -9,7 +9,7 @@
 #define _ASM_POWERPC_SECURITY_FEATURES_H
 
 
-extern unsigned long powerpc_security_features;
+extern u64 powerpc_security_features;
 extern bool rfi_flush;
 
 /* These are bit flags */
@@ -24,17 +24,17 @@ void setup_stf_barrier(void);
 void do_stf_barrier_fixups(enum stf_barrier_type types);
 void setup_count_cache_flush(void);
 
-static inline void security_ftr_set(unsigned long feature)
+static inline void security_ftr_set(u64 feature)
 {
 	powerpc_security_features |= feature;
 }
 
-static inline void security_ftr_clear(unsigned long feature)
+static inline void security_ftr_clear(u64 feature)
 {
 	powerpc_security_features &= ~feature;
 }
 
-static inline bool security_ftr_enabled(unsigned long feature)
+static inline bool security_ftr_enabled(u64 feature)
 {
 	return !!(powerpc_security_features & feature);
 }
diff --git a/arch/powerpc/include/asm/setjmp.h b/arch/powerpc/include/asm/setjmp.h
index d995061f5f86..f7d9b9f5c7ff 100644
--- a/arch/powerpc/include/asm/setjmp.h
+++ b/arch/powerpc/include/asm/setjmp.h
@@ -7,7 +7,9 @@
 
 #define JMP_BUF_LEN    23
 
-extern long setjmp(long *);
-extern void longjmp(long *, long);
+typedef long jmp_buf[JMP_BUF_LEN];
+
+extern int setjmp(jmp_buf env);
+extern void longjmp(jmp_buf env, int val);
 
 #endif /* _ASM_POWERPC_SETJMP_H */
diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
index a47f827bc5f1..ff0dffb19aea 100644
--- a/arch/powerpc/include/asm/spinlock.h
+++ b/arch/powerpc/include/asm/spinlock.h
@@ -15,6 +15,7 @@
  *
  * (the type definitions are in asm/spinlock_types.h)
  */
+#include <linux/jump_label.h>
 #include <linux/irqflags.h>
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
@@ -36,10 +37,12 @@
 #endif
 
 #ifdef CONFIG_PPC_PSERIES
+DECLARE_STATIC_KEY_FALSE(shared_processor);
+
 #define vcpu_is_preempted vcpu_is_preempted
 static inline bool vcpu_is_preempted(int cpu)
 {
-	if (!firmware_has_feature(FW_FEATURE_SPLPAR))
+	if (!static_branch_unlikely(&shared_processor))
 		return false;
 	return !!(be32_to_cpu(lppaca_of(cpu).yield_count) & 1);
 }
diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index b2c0be93929d..7f3a8b902325 100644
--- a/arch/powerpc/include/asm/tlb.h
+++ b/arch/powerpc/include/asm/tlb.h
@@ -26,6 +26,17 @@
 
 #define tlb_flush tlb_flush
 extern void tlb_flush(struct mmu_gather *tlb);
+/*
+ * book3s:
+ * Hash does not use the linux page-tables, so we can avoid
+ * the TLB invalidate for page-table freeing, Radix otoh does use the
+ * page-tables and needs the TLBI.
+ *
+ * nohash:
+ * We still do TLB invalidate in the __pte_free_tlb routine before we
+ * add the page table pages to mmu gather table batch.
+ */
+#define tlb_needs_table_invalidate()	radix_enabled()
 
 /* Get the generic bits... */
 #include <asm-generic/tlb.h>
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index f2d3c29185fd..d02ac21558b4 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -313,9 +313,9 @@ raw_copy_in_user(void __user *to, const void __user *from, unsigned long n)
 	unsigned long ret;
 
 	barrier_nospec();
-	allow_user_access(to, from, n);
+	allow_read_write_user(to, from, n);
 	ret = __copy_tofrom_user(to, from, n);
-	prevent_user_access(to, from, n);
+	prevent_read_write_user(to, from, n);
 	return ret;
 }
 #endif /* __powerpc64__ */
diff --git a/arch/powerpc/include/asm/xive-regs.h b/arch/powerpc/include/asm/xive-regs.h
index f2dfcd50a2d3..33aee7490cbb 100644
--- a/arch/powerpc/include/asm/xive-regs.h
+++ b/arch/powerpc/include/asm/xive-regs.h
@@ -39,6 +39,7 @@
 
 #define XIVE_ESB_VAL_P		0x2
 #define XIVE_ESB_VAL_Q		0x1
+#define XIVE_ESB_INVALID	0xFF
 
 /*
  * Thread Management (aka "TM") registers
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 0df7b6691e3e..447b7d935f4c 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -7,9 +7,6 @@ CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"' $(call cc-disable-warning,
 CFLAGS_ptrace.o		+= $(call cc-disable-warning, array-bounds)
 CFLAGS_syscalls.o	+= $(call cc-disable-warning, attribute-alias)
 
-# Avoid clang warnings around longjmp/setjmp declarations
-CFLAGS_crash.o += -ffreestanding
-
 ifdef CONFIG_PPC64
 CFLAGS_prom_init.o	+= $(NO_MINIMAL_TOC)
 endif
@@ -59,6 +56,7 @@ obj-$(CONFIG_PPC64)		+= setup_64.o sys_ppc32.o \
 obj-$(CONFIG_VDSO32)		+= vdso32/
 obj-$(CONFIG_PPC_WATCHDOG)	+= watchdog.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
+obj-$(CONFIG_PPC_DAWR)		+= dawr.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_ppc970.o cpu_setup_pa6t.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_power.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= mce.o mce_power.o
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index bfe5f4a2886b..3b7cb01a4139 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -2191,11 +2191,13 @@ static struct cpu_spec * __init setup_cpu_spec(unsigned long offset,
 		 * oprofile_cpu_type already has a value, then we are
 		 * possibly overriding a real PVR with a logical one,
 		 * and, in that case, keep the current value for
-		 * oprofile_cpu_type.
+		 * oprofile_cpu_type. Futhermore, let's ensure that the
+		 * fix for the PMAO bug is enabled on compatibility mode.
 		 */
 		if (old.oprofile_cpu_type != NULL) {
 			t->oprofile_cpu_type = old.oprofile_cpu_type;
 			t->oprofile_type = old.oprofile_type;
+			t->cpu_features |= old.cpu_features & CPU_FTR_PMAO_BUG;
 		}
 	}
 
diff --git a/arch/powerpc/kernel/dawr.c b/arch/powerpc/kernel/dawr.c
new file mode 100644
index 000000000000..5f66b95b6858
--- /dev/null
+++ b/arch/powerpc/kernel/dawr.c
@@ -0,0 +1,101 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * DAWR infrastructure
+ *
+ * Copyright 2019, Michael Neuling, IBM Corporation.
+ */
+
+#include <linux/types.h>
+#include <linux/export.h>
+#include <linux/fs.h>
+#include <linux/debugfs.h>
+#include <asm/debugfs.h>
+#include <asm/machdep.h>
+#include <asm/hvcall.h>
+
+bool dawr_force_enable;
+EXPORT_SYMBOL_GPL(dawr_force_enable);
+
+int set_dawr(struct arch_hw_breakpoint *brk)
+{
+	unsigned long dawr, dawrx, mrd;
+
+	dawr = brk->address;
+
+	dawrx  = (brk->type & (HW_BRK_TYPE_READ | HW_BRK_TYPE_WRITE))
+		<< (63 - 58);
+	dawrx |= ((brk->type & (HW_BRK_TYPE_TRANSLATE)) >> 2) << (63 - 59);
+	dawrx |= (brk->type & (HW_BRK_TYPE_PRIV_ALL)) >> 3;
+	/*
+	 * DAWR length is stored in field MDR bits 48:53.  Matches range in
+	 * doublewords (64 bits) baised by -1 eg. 0b000000=1DW and
+	 * 0b111111=64DW.
+	 * brk->len is in bytes.
+	 * This aligns up to double word size, shifts and does the bias.
+	 */
+	mrd = ((brk->len + 7) >> 3) - 1;
+	dawrx |= (mrd & 0x3f) << (63 - 53);
+
+	if (ppc_md.set_dawr)
+		return ppc_md.set_dawr(dawr, dawrx);
+
+	mtspr(SPRN_DAWR, dawr);
+	mtspr(SPRN_DAWRX, dawrx);
+
+	return 0;
+}
+
+static void set_dawr_cb(void *info)
+{
+	set_dawr(info);
+}
+
+static ssize_t dawr_write_file_bool(struct file *file,
+				    const char __user *user_buf,
+				    size_t count, loff_t *ppos)
+{
+	struct arch_hw_breakpoint null_brk = {0, 0, 0};
+	size_t rc;
+
+	/* Send error to user if they hypervisor won't allow us to write DAWR */
+	if (!dawr_force_enable &&
+	    firmware_has_feature(FW_FEATURE_LPAR) &&
+	    set_dawr(&null_brk) != H_SUCCESS)
+		return -ENODEV;
+
+	rc = debugfs_write_file_bool(file, user_buf, count, ppos);
+	if (rc)
+		return rc;
+
+	/* If we are clearing, make sure all CPUs have the DAWR cleared */
+	if (!dawr_force_enable)
+		smp_call_function(set_dawr_cb, &null_brk, 0);
+
+	return rc;
+}
+
+static const struct file_operations dawr_enable_fops = {
+	.read =		debugfs_read_file_bool,
+	.write =	dawr_write_file_bool,
+	.open =		simple_open,
+	.llseek =	default_llseek,
+};
+
+static int __init dawr_force_setup(void)
+{
+	if (cpu_has_feature(CPU_FTR_DAWR)) {
+		/* Don't setup sysfs file for user control on P8 */
+		dawr_force_enable = true;
+		return 0;
+	}
+
+	if (PVR_VER(mfspr(SPRN_PVR)) == PVR_POWER9) {
+		/* Turn DAWR off by default, but allow admin to turn it on */
+		debugfs_create_file_unsafe("dawr_enable_dangerous", 0600,
+					   powerpc_debugfs_root,
+					   &dawr_force_enable,
+					   &dawr_enable_fops);
+	}
+	return 0;
+}
+arch_initcall(dawr_force_setup);
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 864cc55fa03c..cf55c756f829 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -139,7 +139,6 @@ static void __init cpufeatures_setup_cpu(void)
 	/* Initialize the base environment -- clear FSCR/HFSCR.  */
 	hv_mode = !!(mfmsr() & MSR_HV);
 	if (hv_mode) {
-		/* CPU_FTR_HVMODE is used early in PACA setup */
 		cur_cpu_spec->cpu_features |= CPU_FTR_HVMODE;
 		mtspr(SPRN_HFSCR, 0);
 	}
@@ -346,6 +345,14 @@ static int __init feat_enable_dscr(struct dt_cpu_feature *f)
 {
 	u64 lpcr;
 
+	/*
+	 * Linux relies on FSCR[DSCR] being clear, so that we can take the
+	 * facility unavailable interrupt and track the task's usage of DSCR.
+	 * See facility_unavailable_exception().
+	 * Clear the bit here so that feat_enable() doesn't set it.
+	 */
+	f->fscr_bit_nr = -1;
+
 	feat_enable(f);
 
 	lpcr = mfspr(SPRN_LPCR);
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index fe0c32fb9f96..d147bc212405 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -540,12 +540,6 @@ static void *eeh_rmv_device(struct eeh_dev *edev, void *userdata)
 
 		pci_iov_remove_virtfn(edev->physfn, pdn->vf_index);
 		edev->pdev = NULL;
-
-		/*
-		 * We have to set the VF PE number to invalid one, which is
-		 * required to plug the VF successfully.
-		 */
-		pdn->pe_number = IODA_INVALID_PE;
 #endif
 		if (rmv_data)
 			list_add(&edev->rmv_entry, &rmv_data->removed_vf_list);
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 85fdb6d879f1..2c46a45f53e6 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -179,7 +179,7 @@ transfer_to_handler:
 2:	/* if from kernel, check interrupted DOZE/NAP mode and
          * check for stack overflow
          */
-	kuap_save_and_lock r11, r12, r9, r2, r0
+	kuap_save_and_lock r11, r12, r9, r2, r6
 	addi	r2, r12, -THREAD
 	lwz	r9,KSP_LIMIT(r12)
 	cmplw	r1,r9			/* if r1 <= ksp_limit */
@@ -284,6 +284,7 @@ reenable_mmu:
 	rlwinm	r9,r9,0,~MSR_EE
 	lwz	r12,_LINK(r11)		/* and return to address in LR */
 	kuap_restore r11, r2, r3, r4, r5
+	lwz	r2, GPR2(r11)
 	b	fast_exception_return
 #endif
 
@@ -696,7 +697,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_SPE)
 	stw	r10,_CCR(r1)
 	stw	r1,KSP(r3)	/* Set old stack pointer */
 
-	kuap_check r2, r4
+	kuap_check r2, r0
 #ifdef CONFIG_SMP
 	/* We need a sync somewhere here to make sure that if the
 	 * previous task gets rescheduled on another CPU, it sees all
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 3e564536a237..7c07c66cd80b 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -424,17 +424,19 @@ EXC_COMMON_BEGIN(machine_check_idle_common)
 	bl	machine_check_queue_event
 
 	/*
-	 * We have not used any non-volatile GPRs here, and as a rule
-	 * most exception code including machine check does not.
-	 * Therefore PACA_NAPSTATELOST does not need to be set. Idle
-	 * wakeup will restore volatile registers.
+	 * GPR-loss wakeups are relatively straightforward, because the
+	 * idle sleep code has saved all non-volatile registers on its
+	 * own stack, and r1 in PACAR1.
 	 *
-	 * Load the original SRR1 into r3 for pnv_powersave_wakeup_mce.
+	 * For no-loss wakeups the r1 and lr registers used by the
+	 * early machine check handler have to be restored first. r2 is
+	 * the kernel TOC, so no need to restore it.
 	 *
 	 * Then decrement MCE nesting after finishing with the stack.
 	 */
 	ld	r3,_MSR(r1)
 	ld	r4,_LINK(r1)
+	ld	r1,GPR1(r1)
 
 	lhz	r11,PACA_IN_MCE(r13)
 	subi	r11,r11,1
@@ -443,7 +445,7 @@ EXC_COMMON_BEGIN(machine_check_idle_common)
 	mtlr	r4
 	rlwinm	r10,r3,47-31,30,31
 	cmpwi	cr1,r10,2
-	bltlr	cr1	/* no state loss, return to idle caller */
+	bltlr	cr1	/* no state loss, return to idle caller with r3=SRR1 */
 	b	idle_return_gpr_loss
 #endif
 	/*
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index b5a5c6896019..b838f08929cb 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -900,6 +900,7 @@ p_toc:	.8byte	__toc_start + 0x8000 - 0b
 /*
  * This is where the main kernel code starts.
  */
+__REF
 start_here_multiplatform:
 	/* set up the TOC */
 	bl      relative_toc
@@ -943,15 +944,8 @@ start_here_multiplatform:
 	std	r0,0(r4)
 #endif
 
-	/* The following gets the stack set up with the regs */
-	/* pointing to the real addr of the kernel stack.  This is   */
-	/* all done to support the C function call below which sets  */
-	/* up the htab.  This is done because we have relocated the  */
-	/* kernel but are still running in real mode. */
-
-	LOAD_REG_ADDR(r3,init_thread_union)
-
 	/* set up a stack pointer */
+	LOAD_REG_ADDR(r3,init_thread_union)
 	LOAD_REG_IMMEDIATE(r1,THREAD_SIZE)
 	add	r1,r3,r1
 	li	r0,0
@@ -975,6 +969,7 @@ start_here_multiplatform:
 	RFI
 	b	.	/* prevent speculative execution */
 
+	.previous
 	/* This is where all platforms converge execution */
 
 start_here_common:
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 5ab9178c2347..acd038b59dd3 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -288,7 +288,7 @@ InstructionTLBMiss:
 	 * set.  All other Linux PTE bits control the behavior
 	 * of the MMU.
 	 */
-	rlwimi	r10, r10, 0, 0x0f00	/* Clear bits 20-23 */
+	rlwinm	r10, r10, 0, ~0x0f00	/* Clear bits 20-23 */
 	rlwimi	r10, r10, 4, 0x0400	/* Copy _PAGE_EXEC into bit 21 */
 	ori	r10, r10, RPN_PATTERN | 0x200 /* Set 22 and 24-27 */
 	mtspr	SPRN_MI_RPN, r10	/* Update TLB entry */
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index adf0505dbe02..519d49547e2f 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -238,6 +238,9 @@ set_ivor:
 
 	bl	early_init
 
+#ifdef CONFIG_KASAN
+	bl	kasan_early_init
+#endif
 #ifdef CONFIG_RELOCATABLE
 	mr	r3,r30
 	mr	r4,r31
@@ -264,9 +267,6 @@ set_ivor:
 /*
  * Decide what sort of machine this is and initialize the MMU.
  */
-#ifdef CONFIG_KASAN
-	bl	kasan_early_init
-#endif
 	mr	r3,r30
 	mr	r4,r31
 	bl	machine_init
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 50262597c222..c8d1fa2e9d53 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -366,64 +366,3 @@ void hw_breakpoint_pmu_read(struct perf_event *bp)
 {
 	/* TODO */
 }
-
-bool dawr_force_enable;
-EXPORT_SYMBOL_GPL(dawr_force_enable);
-
-static void set_dawr_cb(void *info)
-{
-	set_dawr(info);
-}
-
-static ssize_t dawr_write_file_bool(struct file *file,
-				    const char __user *user_buf,
-				    size_t count, loff_t *ppos)
-{
-	struct arch_hw_breakpoint null_brk = {0, 0, 0};
-	size_t rc;
-
-	/* Send error to user if they hypervisor won't allow us to write DAWR */
-	if ((!dawr_force_enable) &&
-	    (firmware_has_feature(FW_FEATURE_LPAR)) &&
-	    (set_dawr(&null_brk) != H_SUCCESS))
-		return -1;
-
-	rc = debugfs_write_file_bool(file, user_buf, count, ppos);
-	if (rc)
-		return rc;
-
-	/* If we are clearing, make sure all CPUs have the DAWR cleared */
-	if (!dawr_force_enable)
-		smp_call_function(set_dawr_cb, &null_brk, 0);
-
-	return rc;
-}
-
-static const struct file_operations dawr_enable_fops = {
-	.read =		debugfs_read_file_bool,
-	.write =	dawr_write_file_bool,
-	.open =		simple_open,
-	.llseek =	default_llseek,
-};
-
-static int __init dawr_force_setup(void)
-{
-	dawr_force_enable = false;
-
-	if (cpu_has_feature(CPU_FTR_DAWR)) {
-		/* Don't setup sysfs file for user control on P8 */
-		dawr_force_enable = true;
-		return 0;
-	}
-
-	if (PVR_VER(mfspr(SPRN_PVR)) == PVR_POWER9) {
-		/* Turn DAWR off by default, but allow admin to turn it on */
-		dawr_force_enable = false;
-		debugfs_create_file_unsafe("dawr_enable_dangerous", 0600,
-					   powerpc_debugfs_root,
-					   &dawr_force_enable,
-					   &dawr_enable_fops);
-	}
-	return 0;
-}
-arch_initcall(dawr_force_setup);
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 2d27ec4feee4..9b340af02c38 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -264,6 +264,9 @@ int kprobe_handler(struct pt_regs *regs)
 	if (user_mode(regs))
 		return 0;
 
+	if (!(regs->msr & MSR_IR) || !(regs->msr & MSR_DR))
+		return 0;
+
 	/*
 	 * We don't want to be preempted for the entire
 	 * duration of kprobe processing
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
index c4ed328a7b96..7a1c11a7cba5 100644
--- a/arch/powerpc/kernel/machine_kexec.c
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -114,11 +114,12 @@ void machine_kexec(struct kimage *image)
 
 void __init reserve_crashkernel(void)
 {
-	unsigned long long crash_size, crash_base;
+	unsigned long long crash_size, crash_base, total_mem_sz;
 	int ret;
 
+	total_mem_sz = memory_limit ? memory_limit : memblock_phys_mem_size();
 	/* use common parsing */
-	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
+	ret = parse_crashkernel(boot_command_line, total_mem_sz,
 			&crash_size, &crash_base);
 	if (ret == 0 && crash_size > 0) {
 		crashk_res.start = crash_base;
@@ -177,6 +178,7 @@ void __init reserve_crashkernel(void)
 	/* Crash kernel trumps memory limit */
 	if (memory_limit && memory_limit <= crashk_res.end) {
 		memory_limit = crashk_res.end + 1;
+		total_mem_sz = memory_limit;
 		printk("Adjusted memory limit for crashkernel, now 0x%llx\n",
 		       memory_limit);
 	}
@@ -185,7 +187,7 @@ void __init reserve_crashkernel(void)
 			"for crashkernel (System RAM: %ldMB)\n",
 			(unsigned long)(crash_size >> 20),
 			(unsigned long)(crashk_res.start >> 20),
-			(unsigned long)(memblock_phys_mem_size() >> 20));
+			(unsigned long)(total_mem_sz >> 20));
 
 	if (!memblock_is_region_memory(crashk_res.start, crash_size) ||
 	    memblock_reserve(crashk_res.start, crash_size)) {
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index e3ad8aa4730d..01800e5c4118 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -134,7 +134,7 @@ static struct slb_shadow * __init new_slb_shadow(int cpu, unsigned long limit)
 struct paca_struct **paca_ptrs __read_mostly;
 EXPORT_SYMBOL(paca_ptrs);
 
-void __init initialise_paca(struct paca_struct *new_paca, int cpu)
+void __init __nostackprotector initialise_paca(struct paca_struct *new_paca, int cpu)
 {
 #ifdef CONFIG_PPC_PSERIES
 	new_paca->lppaca_ptr = NULL;
@@ -163,7 +163,7 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu)
 }
 
 /* Put the paca pointer into r13 and SPRG_PACA */
-void setup_paca(struct paca_struct *new_paca)
+void __nostackprotector setup_paca(struct paca_struct *new_paca)
 {
 	/* Setup r13 */
 	local_paca = new_paca;
@@ -172,11 +172,15 @@ void setup_paca(struct paca_struct *new_paca)
 	/* On Book3E, initialize the TLB miss exception frames */
 	mtspr(SPRN_SPRG_TLB_EXFRAME, local_paca->extlb);
 #else
-	/* In HV mode, we setup both HPACA and PACA to avoid problems
+	/*
+	 * In HV mode, we setup both HPACA and PACA to avoid problems
 	 * if we do a GET_PACA() before the feature fixups have been
-	 * applied
+	 * applied.
+	 *
+	 * Normally you should test against CPU_FTR_HVMODE, but CPU features
+	 * are not yet set up when we first reach here.
 	 */
-	if (early_cpu_has_feature(CPU_FTR_HVMODE))
+	if (mfmsr() & MSR_HV)
 		mtspr(SPRN_SPRG_HPACA, local_paca);
 #endif
 	mtspr(SPRN_SPRG_PACA, local_paca);
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index c4c8c237a106..eca72c460151 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -244,9 +244,22 @@ void remove_dev_pci_data(struct pci_dev *pdev)
 				continue;
 
 #ifdef CONFIG_EEH
-			/* Release EEH device for the VF */
+			/*
+			 * Release EEH state for this VF. The PCI core
+			 * has already torn down the pci_dev for this VF, but
+			 * we're responsible to removing the eeh_dev since it
+			 * has the same lifetime as the pci_dn that spawned it.
+			 */
 			edev = pdn_to_eeh_dev(pdn);
 			if (edev) {
+				/*
+				 * We allocate pci_dn's for the totalvfs count,
+				 * but only only the vfs that were activated
+				 * have a configured PE.
+				 */
+				if (edev->pe)
+					eeh_rmv_from_parent_pe(edev);
+
 				pdn->edev = NULL;
 				kfree(edev);
 			}
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 4f9bfe9fd960..642b248ff41f 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -780,34 +780,6 @@ static inline int set_dabr(struct arch_hw_breakpoint *brk)
 	return __set_dabr(dabr, dabrx);
 }
 
-int set_dawr(struct arch_hw_breakpoint *brk)
-{
-	unsigned long dawr, dawrx, mrd;
-
-	dawr = brk->address;
-
-	dawrx  = (brk->type & (HW_BRK_TYPE_READ | HW_BRK_TYPE_WRITE)) \
-		                   << (63 - 58); //* read/write bits */
-	dawrx |= ((brk->type & (HW_BRK_TYPE_TRANSLATE)) >> 2) \
-		                   << (63 - 59); //* translate */
-	dawrx |= (brk->type & (HW_BRK_TYPE_PRIV_ALL)) \
-		                   >> 3; //* PRIM bits */
-	/* dawr length is stored in field MDR bits 48:53.  Matches range in
-	   doublewords (64 bits) baised by -1 eg. 0b000000=1DW and
-	   0b111111=64DW.
-	   brk->len is in bytes.
-	   This aligns up to double word size, shifts and does the bias.
-	*/
-	mrd = ((brk->len + 7) >> 3) - 1;
-	dawrx |= (mrd & 0x3f) << (63 - 53);
-
-	if (ppc_md.set_dawr)
-		return ppc_md.set_dawr(dawr, dawrx);
-	mtspr(SPRN_DAWR, dawr);
-	mtspr(SPRN_DAWRX, dawrx);
-	return 0;
-}
-
 void __set_breakpoint(struct arch_hw_breakpoint *brk)
 {
 	memcpy(this_cpu_ptr(&current_brk), brk, sizeof(*brk));
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 7159e791a70d..0d1a67b3e8da 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -684,6 +684,23 @@ static void __init tm_init(void)
 static void tm_init(void) { }
 #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
 
+#ifdef CONFIG_PPC64
+static void __init save_fscr_to_task(void)
+{
+	/*
+	 * Ensure the init_task (pid 0, aka swapper) uses the value of FSCR we
+	 * have configured via the device tree features or via __init_FSCR().
+	 * That value will then be propagated to pid 1 (init) and all future
+	 * processes.
+	 */
+	if (early_cpu_has_feature(CPU_FTR_ARCH_207S))
+		init_task.thread.fscr = mfspr(SPRN_FSCR);
+}
+#else
+static inline void save_fscr_to_task(void) {};
+#endif
+
+
 void __init early_init_devtree(void *params)
 {
 	phys_addr_t limit;
@@ -769,6 +786,8 @@ void __init early_init_devtree(void *params)
 		BUG();
 	}
 
+	save_fscr_to_task();
+
 #if defined(CONFIG_SMP) && defined(CONFIG_PPC64)
 	/* We'll later wait for secondaries to check in; there are
 	 * NCPUS-1 non-boot CPUs  :-)
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 6d600c977c09..e1186a0deb23 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -1037,7 +1037,7 @@ static const struct ibm_arch_vec ibm_architecture_vec_template __initconst = {
 		.reserved2 = 0,
 		.reserved3 = 0,
 		.subprocessors = 1,
-		.byte22 = OV5_FEAT(OV5_DRMEM_V2),
+		.byte22 = OV5_FEAT(OV5_DRMEM_V2) | OV5_FEAT(OV5_DRC_INFO),
 		.intarch = 0,
 		.mmu = 0,
 		.hash_ext = 0,
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 65cd96c3b1d6..5e468938a661 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -841,97 +841,6 @@ static void rtas_percpu_suspend_me(void *info)
 	__rtas_suspend_cpu((struct rtas_suspend_me_data *)info, 1);
 }
 
-enum rtas_cpu_state {
-	DOWN,
-	UP,
-};
-
-#ifndef CONFIG_SMP
-static int rtas_cpu_state_change_mask(enum rtas_cpu_state state,
-				cpumask_var_t cpus)
-{
-	if (!cpumask_empty(cpus)) {
-		cpumask_clear(cpus);
-		return -EINVAL;
-	} else
-		return 0;
-}
-#else
-/* On return cpumask will be altered to indicate CPUs changed.
- * CPUs with states changed will be set in the mask,
- * CPUs with status unchanged will be unset in the mask. */
-static int rtas_cpu_state_change_mask(enum rtas_cpu_state state,
-				cpumask_var_t cpus)
-{
-	int cpu;
-	int cpuret = 0;
-	int ret = 0;
-
-	if (cpumask_empty(cpus))
-		return 0;
-
-	for_each_cpu(cpu, cpus) {
-		struct device *dev = get_cpu_device(cpu);
-
-		switch (state) {
-		case DOWN:
-			cpuret = device_offline(dev);
-			break;
-		case UP:
-			cpuret = device_online(dev);
-			break;
-		}
-		if (cpuret < 0) {
-			pr_debug("%s: cpu_%s for cpu#%d returned %d.\n",
-					__func__,
-					((state == UP) ? "up" : "down"),
-					cpu, cpuret);
-			if (!ret)
-				ret = cpuret;
-			if (state == UP) {
-				/* clear bits for unchanged cpus, return */
-				cpumask_shift_right(cpus, cpus, cpu);
-				cpumask_shift_left(cpus, cpus, cpu);
-				break;
-			} else {
-				/* clear bit for unchanged cpu, continue */
-				cpumask_clear_cpu(cpu, cpus);
-			}
-		}
-	}
-
-	return ret;
-}
-#endif
-
-int rtas_online_cpus_mask(cpumask_var_t cpus)
-{
-	int ret;
-
-	ret = rtas_cpu_state_change_mask(UP, cpus);
-
-	if (ret) {
-		cpumask_var_t tmp_mask;
-
-		if (!alloc_cpumask_var(&tmp_mask, GFP_KERNEL))
-			return ret;
-
-		/* Use tmp_mask to preserve cpus mask from first failure */
-		cpumask_copy(tmp_mask, cpus);
-		rtas_offline_cpus_mask(tmp_mask);
-		free_cpumask_var(tmp_mask);
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL(rtas_online_cpus_mask);
-
-int rtas_offline_cpus_mask(cpumask_var_t cpus)
-{
-	return rtas_cpu_state_change_mask(DOWN, cpus);
-}
-EXPORT_SYMBOL(rtas_offline_cpus_mask);
-
 int rtas_ibm_suspend_me(u64 handle)
 {
 	long state;
@@ -939,8 +848,6 @@ int rtas_ibm_suspend_me(u64 handle)
 	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
 	struct rtas_suspend_me_data data;
 	DECLARE_COMPLETION_ONSTACK(done);
-	cpumask_var_t offline_mask;
-	int cpuret;
 
 	if (!rtas_service_present("ibm,suspend-me"))
 		return -ENOSYS;
@@ -961,9 +868,6 @@ int rtas_ibm_suspend_me(u64 handle)
 		return -EIO;
 	}
 
-	if (!alloc_cpumask_var(&offline_mask, GFP_KERNEL))
-		return -ENOMEM;
-
 	atomic_set(&data.working, 0);
 	atomic_set(&data.done, 0);
 	atomic_set(&data.error, 0);
@@ -972,24 +876,8 @@ int rtas_ibm_suspend_me(u64 handle)
 
 	lock_device_hotplug();
 
-	/* All present CPUs must be online */
-	cpumask_andnot(offline_mask, cpu_present_mask, cpu_online_mask);
-	cpuret = rtas_online_cpus_mask(offline_mask);
-	if (cpuret) {
-		pr_err("%s: Could not bring present CPUs online.\n", __func__);
-		atomic_set(&data.error, cpuret);
-		goto out;
-	}
-
 	cpu_hotplug_disable();
 
-	/* Check if we raced with a CPU-Offline Operation */
-	if (!cpumask_equal(cpu_present_mask, cpu_online_mask)) {
-		pr_info("%s: Raced against a concurrent CPU-Offline\n", __func__);
-		atomic_set(&data.error, -EAGAIN);
-		goto out_hotplug_enable;
-	}
-
 	/* Call function on all CPUs.  One of us will make the
 	 * rtas call
 	 */
@@ -1001,18 +889,11 @@ int rtas_ibm_suspend_me(u64 handle)
 	if (atomic_read(&data.error) != 0)
 		printk(KERN_ERR "Error doing global join\n");
 
-out_hotplug_enable:
-	cpu_hotplug_enable();
 
-	/* Take down CPUs not online prior to suspend */
-	cpuret = rtas_offline_cpus_mask(offline_mask);
-	if (cpuret)
-		pr_warn("%s: Could not restore CPUs to offline state.\n",
-				__func__);
+	cpu_hotplug_enable();
 
-out:
 	unlock_device_hotplug();
-	free_cpumask_var(offline_mask);
+
 	return atomic_read(&data.error);
 }
 #else /* CONFIG_PPC_PSERIES */
diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c
index d341b464f23c..1740a66cea84 100644
--- a/arch/powerpc/kernel/security.c
+++ b/arch/powerpc/kernel/security.c
@@ -16,7 +16,7 @@
 #include <asm/setup.h>
 
 
-unsigned long powerpc_security_features __read_mostly = SEC_FTR_DEFAULT;
+u64 powerpc_security_features __read_mostly = SEC_FTR_DEFAULT;
 
 enum count_cache_flush_type {
 	COUNT_CACHE_FLUSH_NONE	= 0x1,
@@ -109,7 +109,7 @@ device_initcall(barrier_nospec_debugfs_init);
 static __init int security_feature_debugfs_init(void)
 {
 	debugfs_create_x64("security_features", 0400, powerpc_debugfs_root,
-			   (u64 *)&powerpc_security_features);
+			   &powerpc_security_features);
 	return 0;
 }
 device_initcall(security_feature_debugfs_init);
diff --git a/arch/powerpc/kernel/setup.h b/arch/powerpc/kernel/setup.h
index c82577c4b15d..1b02d338a5f5 100644
--- a/arch/powerpc/kernel/setup.h
+++ b/arch/powerpc/kernel/setup.h
@@ -8,6 +8,12 @@
 #ifndef __ARCH_POWERPC_KERNEL_SETUP_H
 #define __ARCH_POWERPC_KERNEL_SETUP_H
 
+#ifdef CONFIG_CC_IS_CLANG
+#define __nostackprotector
+#else
+#define __nostackprotector __attribute__((__optimize__("no-stack-protector")))
+#endif
+
 void initialize_cache_info(void);
 void irqstack_early_init(void);
 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 44b4c432a273..e50fbed36651 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -284,24 +284,42 @@ void __init record_spr_defaults(void)
  * device-tree is not accessible via normal means at this point.
  */
 
-void __init early_setup(unsigned long dt_ptr)
+void __init __nostackprotector early_setup(unsigned long dt_ptr)
 {
 	static __initdata struct paca_struct boot_paca;
 
 	/* -------- printk is _NOT_ safe to use here ! ------- */
 
-	/* Try new device tree based feature discovery ... */
-	if (!dt_cpu_ftrs_init(__va(dt_ptr)))
-		/* Otherwise use the old style CPU table */
-		identify_cpu(0, mfspr(SPRN_PVR));
-
-	/* Assume we're on cpu 0 for now. Don't write to the paca yet! */
+	/*
+	 * Assume we're on cpu 0 for now.
+	 *
+	 * We need to load a PACA very early for a few reasons.
+	 *
+	 * The stack protector canary is stored in the paca, so as soon as we
+	 * call any stack protected code we need r13 pointing somewhere valid.
+	 *
+	 * If we are using kcov it will call in_task() in its instrumentation,
+	 * which relies on the current task from the PACA.
+	 *
+	 * dt_cpu_ftrs_init() calls into generic OF/fdt code, as well as
+	 * printk(), which can trigger both stack protector and kcov.
+	 *
+	 * percpu variables and spin locks also use the paca.
+	 *
+	 * So set up a temporary paca. It will be replaced below once we know
+	 * what CPU we are on.
+	 */
 	initialise_paca(&boot_paca, 0);
 	setup_paca(&boot_paca);
 	fixup_boot_paca();
 
 	/* -------- printk is now safe to use ------- */
 
+	/* Try new device tree based feature discovery ... */
+	if (!dt_cpu_ftrs_init(__va(dt_ptr)))
+		/* Otherwise use the old style CPU table */
+		identify_cpu(0, mfspr(SPRN_PVR));
+
 	/* Enable early debugging if any specified (see udbg.h) */
 	udbg_early_init();
 
@@ -523,6 +541,8 @@ static bool __init parse_cache_info(struct device_node *np,
 	lsizep = of_get_property(np, propnames[3], NULL);
 	if (bsizep == NULL)
 		bsizep = lsizep;
+	if (lsizep == NULL)
+		lsizep = bsizep;
 	if (lsizep != NULL)
 		lsize = be32_to_cpu(*lsizep);
 	if (bsizep != NULL)
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index e6c30cee6abf..d215f9554553 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -200,14 +200,27 @@ unsigned long get_tm_stackpointer(struct task_struct *tsk)
 	 * normal/non-checkpointed stack pointer.
 	 */
 
+	unsigned long ret = tsk->thread.regs->gpr[1];
+
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	BUG_ON(tsk != current);
 
 	if (MSR_TM_ACTIVE(tsk->thread.regs->msr)) {
+		preempt_disable();
 		tm_reclaim_current(TM_CAUSE_SIGNAL);
 		if (MSR_TM_TRANSACTIONAL(tsk->thread.regs->msr))
-			return tsk->thread.ckpt_regs.gpr[1];
+			ret = tsk->thread.ckpt_regs.gpr[1];
+
+		/*
+		 * If we treclaim, we must clear the current thread's TM bits
+		 * before re-enabling preemption. Otherwise we might be
+		 * preempted and have the live MSR[TS] changed behind our back
+		 * (tm_recheckpoint_new_task() would recheckpoint). Besides, we
+		 * enter the signal handler in non-transactional state.
+		 */
+		tsk->thread.regs->msr &= ~MSR_TS_MASK;
+		preempt_enable();
 	}
 #endif
-	return tsk->thread.regs->gpr[1];
+	return ret;
 }
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index ebb78effd280..6c18d58eca11 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -489,19 +489,11 @@ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame,
  */
 static int save_tm_user_regs(struct pt_regs *regs,
 			     struct mcontext __user *frame,
-			     struct mcontext __user *tm_frame, int sigret)
+			     struct mcontext __user *tm_frame, int sigret,
+			     unsigned long msr)
 {
-	unsigned long msr = regs->msr;
-
 	WARN_ON(tm_suspend_disabled);
 
-	/* Remove TM bits from thread's MSR.  The MSR in the sigcontext
-	 * just indicates to userland that we were doing a transaction, but we
-	 * don't want to return in transactional state.  This also ensures
-	 * that flush_fp_to_thread won't set TIF_RESTORE_TM again.
-	 */
-	regs->msr &= ~MSR_TS_MASK;
-
 	/* Save both sets of general registers */
 	if (save_general_regs(&current->thread.ckpt_regs, frame)
 	    || save_general_regs(regs, tm_frame))
@@ -912,6 +904,10 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset,
 	int sigret;
 	unsigned long tramp;
 	struct pt_regs *regs = tsk->thread.regs;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	/* Save the thread's msr before get_tm_stackpointer() changes it */
+	unsigned long msr = regs->msr;
+#endif
 
 	BUG_ON(tsk != current);
 
@@ -944,13 +940,13 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset,
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	tm_frame = &rt_sf->uc_transact.uc_mcontext;
-	if (MSR_TM_ACTIVE(regs->msr)) {
+	if (MSR_TM_ACTIVE(msr)) {
 		if (__put_user((unsigned long)&rt_sf->uc_transact,
 			       &rt_sf->uc.uc_link) ||
 		    __put_user((unsigned long)tm_frame,
 			       &rt_sf->uc_transact.uc_regs))
 			goto badframe;
-		if (save_tm_user_regs(regs, frame, tm_frame, sigret))
+		if (save_tm_user_regs(regs, frame, tm_frame, sigret, msr))
 			goto badframe;
 	}
 	else
@@ -1369,6 +1365,10 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset,
 	int sigret;
 	unsigned long tramp;
 	struct pt_regs *regs = tsk->thread.regs;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	/* Save the thread's msr before get_tm_stackpointer() changes it */
+	unsigned long msr = regs->msr;
+#endif
 
 	BUG_ON(tsk != current);
 
@@ -1402,9 +1402,9 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset,
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	tm_mctx = &frame->mctx_transact;
-	if (MSR_TM_ACTIVE(regs->msr)) {
+	if (MSR_TM_ACTIVE(msr)) {
 		if (save_tm_user_regs(regs, &frame->mctx, &frame->mctx_transact,
-				      sigret))
+				      sigret, msr))
 			goto badframe;
 	}
 	else
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index bee704f32f96..a521f82a789a 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -192,7 +192,8 @@ static long setup_sigcontext(struct sigcontext __user *sc,
 static long setup_tm_sigcontexts(struct sigcontext __user *sc,
 				 struct sigcontext __user *tm_sc,
 				 struct task_struct *tsk,
-				 int signr, sigset_t *set, unsigned long handler)
+				 int signr, sigset_t *set, unsigned long handler,
+				 unsigned long msr)
 {
 	/* When CONFIG_ALTIVEC is set, we _always_ setup v_regs even if the
 	 * process never used altivec yet (MSR_VEC is zero in pt_regs of
@@ -207,12 +208,11 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc,
 	elf_vrreg_t __user *tm_v_regs = sigcontext_vmx_regs(tm_sc);
 #endif
 	struct pt_regs *regs = tsk->thread.regs;
-	unsigned long msr = tsk->thread.regs->msr;
 	long err = 0;
 
 	BUG_ON(tsk != current);
 
-	BUG_ON(!MSR_TM_ACTIVE(regs->msr));
+	BUG_ON(!MSR_TM_ACTIVE(msr));
 
 	WARN_ON(tm_suspend_disabled);
 
@@ -222,13 +222,6 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc,
 	 */
 	msr |= tsk->thread.ckpt_regs.msr & (MSR_FP | MSR_VEC | MSR_VSX);
 
-	/* Remove TM bits from thread's MSR.  The MSR in the sigcontext
-	 * just indicates to userland that we were doing a transaction, but we
-	 * don't want to return in transactional state.  This also ensures
-	 * that flush_fp_to_thread won't set TIF_RESTORE_TM again.
-	 */
-	regs->msr &= ~MSR_TS_MASK;
-
 #ifdef CONFIG_ALTIVEC
 	err |= __put_user(v_regs, &sc->v_regs);
 	err |= __put_user(tm_v_regs, &tm_sc->v_regs);
@@ -480,8 +473,10 @@ static long restore_tm_sigcontexts(struct task_struct *tsk,
 	err |= __get_user(tsk->thread.ckpt_regs.ccr,
 			  &sc->gp_regs[PT_CCR]);
 
+	/* Don't allow userspace to set the trap value */
+	regs->trap = 0;
+
 	/* These regs are not checkpointed; they can go in 'regs'. */
-	err |= __get_user(regs->trap, &sc->gp_regs[PT_TRAP]);
 	err |= __get_user(regs->dar, &sc->gp_regs[PT_DAR]);
 	err |= __get_user(regs->dsisr, &sc->gp_regs[PT_DSISR]);
 	err |= __get_user(regs->result, &sc->gp_regs[PT_RESULT]);
@@ -824,6 +819,10 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set,
 	unsigned long newsp = 0;
 	long err = 0;
 	struct pt_regs *regs = tsk->thread.regs;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	/* Save the thread's msr before get_tm_stackpointer() changes it */
+	unsigned long msr = regs->msr;
+#endif
 
 	BUG_ON(tsk != current);
 
@@ -841,7 +840,7 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set,
 	err |= __put_user(0, &frame->uc.uc_flags);
 	err |= __save_altstack(&frame->uc.uc_stack, regs->gpr[1]);
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	if (MSR_TM_ACTIVE(regs->msr)) {
+	if (MSR_TM_ACTIVE(msr)) {
 		/* The ucontext_t passed to userland points to the second
 		 * ucontext_t (for transactional state) with its uc_link ptr.
 		 */
@@ -849,7 +848,8 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set,
 		err |= setup_tm_sigcontexts(&frame->uc.uc_mcontext,
 					    &frame->uc_transact.uc_mcontext,
 					    tsk, ksig->sig, NULL,
-					    (unsigned long)ksig->ka.sa.sa_handler);
+					    (unsigned long)ksig->ka.sa.sa_handler,
+					    msr);
 	} else
 #endif
 	{
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 11301a1187f3..0e0a2227af7d 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -522,35 +522,6 @@ static inline void clear_irq_work_pending(void)
 		"i" (offsetof(struct paca_struct, irq_work_pending)));
 }
 
-void arch_irq_work_raise(void)
-{
-	preempt_disable();
-	set_irq_work_pending_flag();
-	/*
-	 * Non-nmi code running with interrupts disabled will replay
-	 * irq_happened before it re-enables interrupts, so setthe
-	 * decrementer there instead of causing a hardware exception
-	 * which would immediately hit the masked interrupt handler
-	 * and have the net effect of setting the decrementer in
-	 * irq_happened.
-	 *
-	 * NMI interrupts can not check this when they return, so the
-	 * decrementer hardware exception is raised, which will fire
-	 * when interrupts are next enabled.
-	 *
-	 * BookE does not support this yet, it must audit all NMI
-	 * interrupt handlers to ensure they call nmi_enter() so this
-	 * check would be correct.
-	 */
-	if (IS_ENABLED(CONFIG_BOOKE) || !irqs_disabled() || in_nmi()) {
-		set_dec(1);
-	} else {
-		hard_irq_disable();
-		local_paca->irq_happened |= PACA_IRQ_DEC;
-	}
-	preempt_enable();
-}
-
 #else /* 32-bit */
 
 DEFINE_PER_CPU(u8, irq_work_pending);
@@ -559,16 +530,27 @@ DEFINE_PER_CPU(u8, irq_work_pending);
 #define test_irq_work_pending()		__this_cpu_read(irq_work_pending)
 #define clear_irq_work_pending()	__this_cpu_write(irq_work_pending, 0)
 
+#endif /* 32 vs 64 bit */
+
 void arch_irq_work_raise(void)
 {
+	/*
+	 * 64-bit code that uses irq soft-mask can just cause an immediate
+	 * interrupt here that gets soft masked, if this is called under
+	 * local_irq_disable(). It might be possible to prevent that happening
+	 * by noticing interrupts are disabled and setting decrementer pending
+	 * to be replayed when irqs are enabled. The problem there is that
+	 * tracing can call irq_work_raise, including in code that does low
+	 * level manipulations of irq soft-mask state (e.g., trace_hardirqs_on)
+	 * which could get tangled up if we're messing with the same state
+	 * here.
+	 */
 	preempt_disable();
 	set_irq_work_pending_flag();
 	set_dec(1);
 	preempt_enable();
 }
 
-#endif /* 32 vs 64 bit */
-
 #else  /* CONFIG_IRQ_WORK */
 
 #define test_irq_work_pending()	0
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index d60598113a9f..36849b693d86 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -704,7 +704,7 @@ int vdso_getcpu_init(void)
 	node = cpu_to_node(cpu);
 	WARN_ON_ONCE(node > 0xffff);
 
-	val = (cpu & 0xfff) | ((node & 0xffff) << 16);
+	val = (cpu & 0xffff) | ((node & 0xffff) << 16);
 	mtspr(SPRN_SPRG_VDSO_WRITE, val);
 	get_paca()->sprg_vdso = val;
 
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 060a1acd7c6d..4638d2863388 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -326,6 +326,12 @@ SECTIONS
 		*(.branch_lt)
 	}
 
+#ifdef CONFIG_DEBUG_INFO_BTF
+	.BTF : AT(ADDR(.BTF) - LOAD_OFFSET) {
+		*(.BTF)
+	}
+#endif
+
 	.opd : AT(ADDR(.opd) - LOAD_OFFSET) {
 		__start_opd = .;
 		KEEP(*(.opd))
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index f53997a8ca62..b8e13d5a4a31 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -38,6 +38,7 @@ config KVM_BOOK3S_32_HANDLER
 config KVM_BOOK3S_64_HANDLER
 	bool
 	select KVM_BOOK3S_HANDLER
+	select PPC_DAWR_FORCE_ENABLE
 
 config KVM_BOOK3S_PR_POSSIBLE
 	bool
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 08b2dfbc5305..56dbc2f6e3d2 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -38,7 +38,8 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
 	/* Can't access quadrants 1 or 2 in non-HV mode, call the HV to do it */
 	if (kvmhv_on_pseries())
 		return plpar_hcall_norets(H_COPY_TOFROM_GUEST, lpid, pid, eaddr,
-					  __pa(to), __pa(from), n);
+					  (to != NULL) ? __pa(to): 0,
+					  (from != NULL) ? __pa(from): 0, n);
 
 	quadrant = 1;
 	if (!pid)
@@ -353,7 +354,13 @@ static struct kmem_cache *kvm_pmd_cache;
 
 static pte_t *kvmppc_pte_alloc(void)
 {
-	return kmem_cache_alloc(kvm_pte_cache, GFP_KERNEL);
+	pte_t *pte;
+
+	pte = kmem_cache_alloc(kvm_pte_cache, GFP_KERNEL);
+	/* pmd_populate() will only reference _pa(pte). */
+	kmemleak_ignore(pte);
+
+	return pte;
 }
 
 static void kvmppc_pte_free(pte_t *ptep)
@@ -369,7 +376,13 @@ static inline int pmd_is_leaf(pmd_t pmd)
 
 static pmd_t *kvmppc_pmd_alloc(void)
 {
-	return kmem_cache_alloc(kvm_pmd_cache, GFP_KERNEL);
+	pmd_t *pmd;
+
+	pmd = kmem_cache_alloc(kvm_pmd_cache, GFP_KERNEL);
+	/* pud_populate() will only reference _pa(pmd). */
+	kmemleak_ignore(pmd);
+
+	return pmd;
 }
 
 static void kvmppc_pmd_free(pmd_t *pmdp)
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index 446d91d6cf70..2ae6ee1d5755 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -110,6 +110,7 @@ extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm,
 	struct kvmppc_spapr_tce_iommu_table *stit, *tmp;
 	struct iommu_table_group *table_group = NULL;
 
+	rcu_read_lock();
 	list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) {
 
 		table_group = iommu_group_get_iommudata(grp);
@@ -124,7 +125,9 @@ extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm,
 				kref_put(&stit->kref, kvm_spapr_tce_liobn_put);
 			}
 		}
+		cond_resched_rcu();
 	}
+	rcu_read_unlock();
 }
 
 extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
@@ -142,12 +145,14 @@ extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
 	if (!f.file)
 		return -EBADF;
 
+	rcu_read_lock();
 	list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) {
 		if (stt == f.file->private_data) {
 			found = true;
 			break;
 		}
 	}
+	rcu_read_unlock();
 
 	fdput(f);
 
@@ -180,6 +185,7 @@ extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
 	if (!tbl)
 		return -EINVAL;
 
+	rcu_read_lock();
 	list_for_each_entry_rcu(stit, &stt->iommu_tables, next) {
 		if (tbl != stit->tbl)
 			continue;
@@ -187,14 +193,17 @@ extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
 		if (!kref_get_unless_zero(&stit->kref)) {
 			/* stit is being destroyed */
 			iommu_tce_table_put(tbl);
+			rcu_read_unlock();
 			return -ENOTTY;
 		}
 		/*
 		 * The table is already known to this KVM, we just increased
 		 * its KVM reference counter and can return.
 		 */
+		rcu_read_unlock();
 		return 0;
 	}
+	rcu_read_unlock();
 
 	stit = kzalloc(sizeof(*stit), GFP_KERNEL);
 	if (!stit) {
@@ -400,18 +409,19 @@ static long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *stt,
 	if (kvmppc_tce_to_ua(stt->kvm, tce, &ua))
 		return H_TOO_HARD;
 
+	rcu_read_lock();
 	list_for_each_entry_rcu(stit, &stt->iommu_tables, next) {
 		unsigned long hpa = 0;
 		struct mm_iommu_table_group_mem_t *mem;
 		long shift = stit->tbl->it_page_shift;
 
 		mem = mm_iommu_lookup(stt->kvm->mm, ua, 1ULL << shift);
-		if (!mem)
-			return H_TOO_HARD;
-
-		if (mm_iommu_ua_to_hpa(mem, ua, shift, &hpa))
+		if (!mem || mm_iommu_ua_to_hpa(mem, ua, shift, &hpa)) {
+			rcu_read_unlock();
 			return H_TOO_HARD;
+		}
 	}
+	rcu_read_unlock();
 
 	return H_SUCCESS;
 }
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index f8975c620f41..cc4279bc6da6 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2351,7 +2351,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
 	mutex_unlock(&kvm->lock);
 
 	if (!vcore)
-		goto free_vcpu;
+		goto uninit_vcpu;
 
 	spin_lock(&vcore->lock);
 	++vcore->num_threads;
@@ -2368,6 +2368,8 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
 
 	return vcpu;
 
+uninit_vcpu:
+	kvm_vcpu_uninit(vcpu);
 free_vcpu:
 	kmem_cache_free(kvm_vcpu_cache, vcpu);
 out:
@@ -3618,6 +3620,7 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 		if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested &&
 		    kvmppc_get_gpr(vcpu, 3) == H_CEDE) {
 			kvmppc_nested_cede(vcpu);
+			kvmppc_set_gpr(vcpu, 3, 0);
 			trap = 0;
 		}
 	} else {
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index cc65af8fe6f7..3f6ad3f58628 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1769,10 +1769,12 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_pr(struct kvm *kvm,
 
 	err = kvmppc_mmu_init(vcpu);
 	if (err < 0)
-		goto uninit_vcpu;
+		goto free_shared_page;
 
 	return vcpu;
 
+free_shared_page:
+	free_page((unsigned long)vcpu->arch.shared);
 uninit_vcpu:
 	kvm_vcpu_uninit(vcpu);
 free_shadow_vcpu:
diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c
index 5a3373e06e60..235d57d6c205 100644
--- a/arch/powerpc/kvm/book3s_xive_native.c
+++ b/arch/powerpc/kvm/book3s_xive_native.c
@@ -638,7 +638,7 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive,
 	srcu_idx = srcu_read_lock(&kvm->srcu);
 	gfn = gpa_to_gfn(kvm_eq.qaddr);
 
-	page_size = kvm_host_page_size(kvm, gfn);
+	page_size = kvm_host_page_size(vcpu, gfn);
 	if (1ull << kvm_eq.qshift > page_size) {
 		srcu_read_unlock(&kvm->srcu, srcu_idx);
 		pr_warn("Incompatible host page size %lx!\n", page_size);
diff --git a/arch/powerpc/kvm/emulate_loadstore.c b/arch/powerpc/kvm/emulate_loadstore.c
index 9208c82ed08d..88f62cf2dbb9 100644
--- a/arch/powerpc/kvm/emulate_loadstore.c
+++ b/arch/powerpc/kvm/emulate_loadstore.c
@@ -73,7 +73,6 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
 	u32 inst;
-	int ra, rs, rt;
 	enum emulation_result emulated = EMULATE_FAIL;
 	int advance = 1;
 	struct instruction_op op;
@@ -85,10 +84,6 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 	if (emulated != EMULATE_DONE)
 		return emulated;
 
-	ra = get_ra(inst);
-	rs = get_rs(inst);
-	rt = get_rt(inst);
-
 	/*
 	 * if mmio_vsx_tx_sx_enabled == 0, copy data between
 	 * VSR[0..31] and memory
diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c
index 8d68f03bf5a4..55c0208e7bfd 100644
--- a/arch/powerpc/mm/book3s32/mmu.c
+++ b/arch/powerpc/mm/book3s32/mmu.c
@@ -187,6 +187,7 @@ void mmu_mark_initmem_nx(void)
 	int i;
 	unsigned long base = (unsigned long)_stext - PAGE_OFFSET;
 	unsigned long top = (unsigned long)_etext - PAGE_OFFSET;
+	unsigned long border = (unsigned long)__init_begin - PAGE_OFFSET;
 	unsigned long size;
 
 	if (cpu_has_feature(CPU_FTR_601))
@@ -201,9 +202,10 @@ void mmu_mark_initmem_nx(void)
 		size = block_size(base, top);
 		size = max(size, 128UL << 10);
 		if ((top - base) > size) {
-			if (strict_kernel_rwx_enabled())
-				pr_warn("Kernel _etext not properly aligned\n");
 			size <<= 1;
+			if (strict_kernel_rwx_enabled() && base + size > border)
+				pr_warn("Some RW data is getting mapped X. "
+					"Adjust CONFIG_DATA_SHIFT to avoid that.\n");
 		}
 		setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_TEXT);
 		base += size;
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index 01bc9663360d..c7e3cc805cef 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -354,7 +354,6 @@ static inline void pgtable_free(void *table, int index)
 	}
 }
 
-#ifdef CONFIG_SMP
 void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int index)
 {
 	unsigned long pgf = (unsigned long)table;
@@ -371,12 +370,6 @@ void __tlb_remove_table(void *_table)
 
 	return pgtable_free(table, index);
 }
-#else
-void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int index)
-{
-	return pgtable_free(table, index);
-}
-#endif
 
 #ifdef CONFIG_PROC_FS
 atomic_long_t direct_pages_count[MMU_PAGE_COUNT];
diff --git a/arch/powerpc/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c
index ae7fca40e5b3..432fd9fa8c3f 100644
--- a/arch/powerpc/mm/book3s64/pkeys.c
+++ b/arch/powerpc/mm/book3s64/pkeys.c
@@ -83,13 +83,17 @@ static int pkey_initialize(void)
 	scan_pkey_feature();
 
 	/*
-	 * Let's assume 32 pkeys on P8 bare metal, if its not defined by device
-	 * tree. We make this exception since skiboot forgot to expose this
-	 * property on power8.
+	 * Let's assume 32 pkeys on P8/P9 bare metal, if its not defined by device
+	 * tree. We make this exception since some version of skiboot forgot to
+	 * expose this property on power8/9.
 	 */
-	if (!pkeys_devtree_defined && !firmware_has_feature(FW_FEATURE_LPAR) &&
-			cpu_has_feature(CPU_FTRS_POWER8))
-		pkeys_total = 32;
+	if (!pkeys_devtree_defined && !firmware_has_feature(FW_FEATURE_LPAR)) {
+		unsigned long pvr = mfspr(SPRN_PVR);
+
+		if (PVR_VER(pvr) == PVR_POWER8 || PVR_VER(pvr) == PVR_POWER8E ||
+		    PVR_VER(pvr) == PVR_POWER8NVL || PVR_VER(pvr) == PVR_POWER9)
+			pkeys_total = 32;
+	}
 
 	/*
 	 * Adjust the upper limit, based on the number of bits supported by
@@ -367,12 +371,14 @@ static bool pkey_access_permitted(int pkey, bool write, bool execute)
 		return true;
 
 	pkey_shift = pkeyshift(pkey);
-	if (execute && !(read_iamr() & (IAMR_EX_BIT << pkey_shift)))
-		return true;
+	if (execute)
+		return !(read_iamr() & (IAMR_EX_BIT << pkey_shift));
+
+	amr = read_amr();
+	if (write)
+		return !(amr & (AMR_WR_BIT << pkey_shift));
 
-	amr = read_amr(); /* Delay reading amr until absolutely needed */
-	return ((!write && !(amr & (AMR_RD_BIT << pkey_shift))) ||
-		(write &&  !(amr & (AMR_WR_BIT << pkey_shift))));
+	return !(amr & (AMR_RD_BIT << pkey_shift));
 }
 
 bool arch_pte_access_permitted(u64 pte, bool write, bool execute)
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index ec6b7ad70659..74b3a03a578e 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -254,7 +254,7 @@ static bool bad_kernel_fault(struct pt_regs *regs, unsigned long error_code,
 
 	// Read/write fault in a valid region (the exception table search passed
 	// above), but blocked by KUAP is bad, it can never succeed.
-	if (bad_kuap_fault(regs, is_write))
+	if (bad_kuap_fault(regs, address, is_write))
 		return true;
 
 	// What's left? Kernel fault on user in well defined regions (extable
@@ -262,6 +262,9 @@ static bool bad_kernel_fault(struct pt_regs *regs, unsigned long error_code,
 	return false;
 }
 
+// This comes from 64-bit struct rt_sigframe + __SIGNAL_FRAMESIZE
+#define SIGFRAME_MAX_SIZE	(4096 + 128)
+
 static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address,
 				struct vm_area_struct *vma, unsigned int flags,
 				bool *must_retry)
@@ -269,7 +272,7 @@ static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address,
 	/*
 	 * N.B. The POWER/Open ABI allows programs to access up to
 	 * 288 bytes below the stack pointer.
-	 * The kernel signal delivery code writes up to about 1.5kB
+	 * The kernel signal delivery code writes a bit over 4KB
 	 * below the stack pointer (r1) before decrementing it.
 	 * The exec code can write slightly over 640kB to the stack
 	 * before setting the user r1.  Thus we allow the stack to
@@ -294,7 +297,7 @@ static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address,
 		 * between the last mapped region and the stack will
 		 * expand the stack rather than segfaulting.
 		 */
-		if (address + 2048 >= uregs->gpr[1])
+		if (address + SIGFRAME_MAX_SIZE >= uregs->gpr[1])
 			return false;
 
 		if ((flags & FAULT_FLAG_WRITE) && (flags & FAULT_FLAG_USER) &&
@@ -375,6 +378,9 @@ static void sanity_check_fault(bool is_write, bool is_user,
 	 * Userspace trying to access kernel address, we get PROTFAULT for that.
 	 */
 	if (is_user && address >= TASK_SIZE) {
+		if ((long)address == -1)
+			return;
+
 		pr_crit_ratelimited("%s[%d]: User access of kernel address (%lx) - exploit attempt? (uid: %d)\n",
 				   current->comm, current->pid, address,
 				   from_kuid(&init_user_ns, current_uid()));
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 1de0f43a68e5..e8157325e089 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -53,20 +53,29 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 	if (pshift >= pdshift) {
 		cachep = PGT_CACHE(PTE_T_ORDER);
 		num_hugepd = 1 << (pshift - pdshift);
+		new = NULL;
 	} else if (IS_ENABLED(CONFIG_PPC_8xx)) {
-		cachep = PGT_CACHE(PTE_INDEX_SIZE);
+		cachep = NULL;
 		num_hugepd = 1;
+		new = pte_alloc_one(mm);
 	} else {
 		cachep = PGT_CACHE(pdshift - pshift);
 		num_hugepd = 1;
+		new = NULL;
 	}
 
-	new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL));
+	if (!cachep && !new) {
+		WARN_ONCE(1, "No page table cache created for hugetlb tables");
+		return -ENOMEM;
+	}
+
+	if (cachep)
+		new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL));
 
 	BUG_ON(pshift > HUGEPD_SHIFT_MASK);
 	BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK);
 
-	if (! new)
+	if (!new)
 		return -ENOMEM;
 
 	/*
@@ -92,7 +101,10 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 	if (i < num_hugepd) {
 		for (i = i - 1 ; i >= 0; i--, hpdp--)
 			*hpdp = __hugepd(0);
-		kmem_cache_free(cachep, new);
+		if (cachep)
+			kmem_cache_free(cachep, new);
+		else
+			pte_free(mm, new);
 	} else {
 		kmemleak_ignore(new);
 	}
@@ -319,8 +331,7 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif
 	if (shift >= pdshift)
 		hugepd_free(tlb, hugepte);
 	else if (IS_ENABLED(CONFIG_PPC_8xx))
-		pgtable_free_tlb(tlb, hugepte,
-				 get_hugepd_cache_index(PTE_INDEX_SIZE));
+		pgtable_free_tlb(tlb, hugepte, 0);
 	else
 		pgtable_free_tlb(tlb, hugepte,
 				 get_hugepd_cache_index(pdshift - shift));
@@ -519,13 +530,6 @@ retry:
 	return page;
 }
 
-static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
-				      unsigned long sz)
-{
-	unsigned long __boundary = (addr + sz) & ~(sz-1);
-	return (__boundary - 1 < end - 1) ? __boundary : end;
-}
-
 #ifdef CONFIG_PPC_MM_SLICES
 unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 					unsigned long len, unsigned long pgoff,
@@ -596,6 +600,7 @@ __setup("hugepagesz=", hugepage_setup_sz);
 
 static int __init hugetlbpage_init(void)
 {
+	bool configured = false;
 	int psize;
 
 	if (hugetlb_disabled) {
@@ -640,16 +645,22 @@ static int __init hugetlbpage_init(void)
 		 * if we have pdshift and shift value same, we don't
 		 * use pgt cache for hugepd.
 		 */
-		if (pdshift > shift && IS_ENABLED(CONFIG_PPC_8xx))
-			pgtable_cache_add(PTE_INDEX_SIZE);
-		else if (pdshift > shift)
-			pgtable_cache_add(pdshift - shift);
-		else if (IS_ENABLED(CONFIG_PPC_FSL_BOOK3E) || IS_ENABLED(CONFIG_PPC_8xx))
+		if (pdshift > shift) {
+			if (!IS_ENABLED(CONFIG_PPC_8xx))
+				pgtable_cache_add(pdshift - shift);
+		} else if (IS_ENABLED(CONFIG_PPC_FSL_BOOK3E) ||
+			   IS_ENABLED(CONFIG_PPC_8xx)) {
 			pgtable_cache_add(PTE_T_ORDER);
+		}
+
+		configured = true;
 	}
 
-	if (IS_ENABLED(CONFIG_HUGETLB_PAGE_SIZE_VARIABLE))
-		hugetlbpage_init_default();
+	if (configured) {
+		if (IS_ENABLED(CONFIG_HUGETLB_PAGE_SIZE_VARIABLE))
+			hugetlbpage_init_default();
+	} else
+		pr_info("Failed to initialize. Disabling HugeTLB");
 
 	return 0;
 }
@@ -673,68 +684,3 @@ void flush_dcache_icache_hugepage(struct page *page)
 		}
 	}
 }
-
-static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
-		       unsigned long end, int write, struct page **pages, int *nr)
-{
-	unsigned long pte_end;
-	struct page *head, *page;
-	pte_t pte;
-	int refs;
-
-	pte_end = (addr + sz) & ~(sz-1);
-	if (pte_end < end)
-		end = pte_end;
-
-	pte = READ_ONCE(*ptep);
-
-	if (!pte_access_permitted(pte, write))
-		return 0;
-
-	/* hugepages are never "special" */
-	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
-
-	refs = 0;
-	head = pte_page(pte);
-
-	page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
-	do {
-		VM_BUG_ON(compound_head(page) != head);
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
-
-	if (!page_cache_add_speculative(head, refs)) {
-		*nr -= refs;
-		return 0;
-	}
-
-	if (unlikely(pte_val(pte) != pte_val(*ptep))) {
-		/* Could be optimized better */
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
-		return 0;
-	}
-
-	return 1;
-}
-
-int gup_huge_pd(hugepd_t hugepd, unsigned long addr, unsigned int pdshift,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	pte_t *ptep;
-	unsigned long sz = 1UL << hugepd_shift(hugepd);
-	unsigned long next;
-
-	ptep = hugepte_offset(hugepd, addr, pdshift);
-	do {
-		next = hugepte_addr_end(addr, end, sz);
-		if (!gup_hugepte(ptep, sz, addr, end, write, pages, nr))
-			return 0;
-	} while (ptep++, addr = next, addr != end);
-
-	return 1;
-}
diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c
index 0e6ed4413eea..1cfe57b51d7e 100644
--- a/arch/powerpc/mm/kasan/kasan_init_32.c
+++ b/arch/powerpc/mm/kasan/kasan_init_32.c
@@ -117,7 +117,7 @@ static void __init kasan_remap_early_shadow_ro(void)
 
 	kasan_populate_pte(kasan_early_shadow_pte, prot);
 
-	for (k_cur = k_start & PAGE_MASK; k_cur < k_end; k_cur += PAGE_SIZE) {
+	for (k_cur = k_start & PAGE_MASK; k_cur != k_end; k_cur += PAGE_SIZE) {
 		pmd_t *pmd = pmd_offset(pud_offset(pgd_offset_k(k_cur), k_cur), k_cur);
 		pte_t *ptep = pte_offset_kernel(pmd, k_cur);
 
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 2eda1ec36f55..99fcdf73f207 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -270,6 +270,14 @@ void __init mem_init(void)
 	BUILD_BUG_ON(MMU_PAGE_COUNT > 16);
 
 #ifdef CONFIG_SWIOTLB
+	/*
+	 * Some platforms (e.g. 85xx) limit DMA-able memory way below
+	 * 4G. We force memblock to bottom-up mode to ensure that the
+	 * memory allocated in swiotlb_init() is DMA-able.
+	 * As it's the last memblock allocation, no need to reset it
+	 * back to to-down.
+	 */
+	memblock_set_bottom_up(true);
 	swiotlb_init(0);
 #endif
 
diff --git a/arch/powerpc/mm/nohash/tlb_low.S b/arch/powerpc/mm/nohash/tlb_low.S
index 2ca407cedbe7..eaeee402f96e 100644
--- a/arch/powerpc/mm/nohash/tlb_low.S
+++ b/arch/powerpc/mm/nohash/tlb_low.S
@@ -397,7 +397,7 @@ _GLOBAL(set_context)
  * extern void loadcam_entry(unsigned int index)
  *
  * Load TLBCAM[index] entry in to the L2 CAM MMU
- * Must preserve r7, r8, r9, and r10
+ * Must preserve r7, r8, r9, r10 and r11
  */
 _GLOBAL(loadcam_entry)
 	mflr	r5
@@ -433,6 +433,10 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS)
  */
 _GLOBAL(loadcam_multi)
 	mflr	r8
+	/* Don't switch to AS=1 if already there */
+	mfmsr	r11
+	andi.	r11,r11,MSR_IS
+	bne	10f
 
 	/*
 	 * Set up temporary TLB entry that is the same as what we're
@@ -458,6 +462,7 @@ _GLOBAL(loadcam_multi)
 	mtmsr	r6
 	isync
 
+10:
 	mr	r9,r3
 	add	r10,r3,r4
 2:	bl	loadcam_entry
@@ -466,6 +471,10 @@ _GLOBAL(loadcam_multi)
 	mr	r3,r9
 	blt	2b
 
+	/* Don't return to AS=0 if we were in AS=1 at function start */
+	andi.	r11,r11,MSR_IS
+	bne	3f
+
 	/* Return to AS=0 and clear the temporary entry */
 	mfmsr	r6
 	rlwinm.	r6,r6,0,~(MSR_IS|MSR_DS)
@@ -481,6 +490,7 @@ _GLOBAL(loadcam_multi)
 	tlbwe
 	isync
 
+3:
 	mtlr	r8
 	blr
 #endif
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 35cb96cfc258..5159445a21dd 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -360,7 +360,7 @@ void mark_initmem_nx(void)
 	unsigned long numpages = PFN_UP((unsigned long)_einittext) -
 				 PFN_DOWN((unsigned long)_sinittext);
 
-	if (v_block_mapped((unsigned long)_stext + 1))
+	if (v_block_mapped((unsigned long)_sinittext))
 		mmu_mark_initmem_nx();
 	else
 		change_page_attr(page, numpages, PAGE_KERNEL);
@@ -372,8 +372,9 @@ void mark_rodata_ro(void)
 	struct page *page;
 	unsigned long numpages;
 
-	if (v_block_mapped((unsigned long)_sinittext)) {
+	if (v_block_mapped((unsigned long)_stext + 1)) {
 		mmu_mark_rodata_ro();
+		ptdump_check_wx();
 		return;
 	}
 
diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c
index b69912854dc3..485363358395 100644
--- a/arch/powerpc/mm/ptdump/ptdump.c
+++ b/arch/powerpc/mm/ptdump/ptdump.c
@@ -62,6 +62,7 @@ struct pg_state {
 	unsigned long start_address;
 	unsigned long start_pa;
 	unsigned long last_pa;
+	unsigned long page_size;
 	unsigned int level;
 	u64 current_flags;
 	bool check_wx;
@@ -163,9 +164,9 @@ static void dump_addr(struct pg_state *st, unsigned long addr)
 #endif
 
 	pt_dump_seq_printf(st->seq, REG "-" REG " ", st->start_address, addr - 1);
-	if (st->start_pa == st->last_pa && st->start_address + PAGE_SIZE != addr) {
+	if (st->start_pa == st->last_pa && st->start_address + st->page_size != addr) {
 		pt_dump_seq_printf(st->seq, "[" REG "]", st->start_pa);
-		delta = PAGE_SIZE >> 10;
+		delta = st->page_size >> 10;
 	} else {
 		pt_dump_seq_printf(st->seq, " " REG " ", st->start_pa);
 		delta = (addr - st->start_address) >> 10;
@@ -181,10 +182,12 @@ static void dump_addr(struct pg_state *st, unsigned long addr)
 
 static void note_prot_wx(struct pg_state *st, unsigned long addr)
 {
+	pte_t pte = __pte(st->current_flags);
+
 	if (!st->check_wx)
 		return;
 
-	if (!((st->current_flags & pgprot_val(PAGE_KERNEL_X)) == pgprot_val(PAGE_KERNEL_X)))
+	if (!pte_write(pte) || !pte_exec(pte))
 		return;
 
 	WARN_ONCE(1, "powerpc/mm: Found insecure W+X mapping at address %p/%pS\n",
@@ -194,7 +197,7 @@ static void note_prot_wx(struct pg_state *st, unsigned long addr)
 }
 
 static void note_page(struct pg_state *st, unsigned long addr,
-	       unsigned int level, u64 val)
+	       unsigned int level, u64 val, unsigned long page_size)
 {
 	u64 flag = val & pg_level[level].mask;
 	u64 pa = val & PTE_RPN_MASK;
@@ -206,6 +209,7 @@ static void note_page(struct pg_state *st, unsigned long addr,
 		st->start_address = addr;
 		st->start_pa = pa;
 		st->last_pa = pa;
+		st->page_size = page_size;
 		pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
 	/*
 	 * Dump the section of virtual memory when:
@@ -217,7 +221,7 @@ static void note_page(struct pg_state *st, unsigned long addr,
 	 */
 	} else if (flag != st->current_flags || level != st->level ||
 		   addr >= st->marker[1].start_address ||
-		   (pa != st->last_pa + PAGE_SIZE &&
+		   (pa != st->last_pa + st->page_size &&
 		    (pa != st->start_pa || st->start_pa != st->last_pa))) {
 
 		/* Check the PTE flags */
@@ -245,6 +249,7 @@ static void note_page(struct pg_state *st, unsigned long addr,
 		st->start_address = addr;
 		st->start_pa = pa;
 		st->last_pa = pa;
+		st->page_size = page_size;
 		st->current_flags = flag;
 		st->level = level;
 	} else {
@@ -260,7 +265,7 @@ static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start)
 
 	for (i = 0; i < PTRS_PER_PTE; i++, pte++) {
 		addr = start + i * PAGE_SIZE;
-		note_page(st, addr, 4, pte_val(*pte));
+		note_page(st, addr, 4, pte_val(*pte), PAGE_SIZE);
 
 	}
 }
@@ -277,7 +282,7 @@ static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start)
 			/* pmd exists */
 			walk_pte(st, pmd, addr);
 		else
-			note_page(st, addr, 3, pmd_val(*pmd));
+			note_page(st, addr, 3, pmd_val(*pmd), PMD_SIZE);
 	}
 }
 
@@ -293,7 +298,7 @@ static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start)
 			/* pud exists */
 			walk_pmd(st, pud, addr);
 		else
-			note_page(st, addr, 2, pud_val(*pud));
+			note_page(st, addr, 2, pud_val(*pud), PUD_SIZE);
 	}
 }
 
@@ -314,7 +319,7 @@ static void walk_pagetables(struct pg_state *st)
 			/* pgd exists */
 			walk_pud(st, pgd, addr);
 		else
-			note_page(st, addr, 1, pgd_val(*pgd));
+			note_page(st, addr, 1, pgd_val(*pgd), PGDIR_SIZE);
 	}
 }
 
@@ -373,7 +378,7 @@ static int ptdump_show(struct seq_file *m, void *v)
 
 	/* Traverse kernel page tables */
 	walk_pagetables(&st);
-	note_page(&st, 0, 0, 0);
+	note_page(&st, 0, 0, 0, 0);
 	return 0;
 }
 
diff --git a/arch/powerpc/mm/ptdump/shared.c b/arch/powerpc/mm/ptdump/shared.c
index f7ed2f187cb0..784f8df17f73 100644
--- a/arch/powerpc/mm/ptdump/shared.c
+++ b/arch/powerpc/mm/ptdump/shared.c
@@ -31,6 +31,11 @@ static const struct flag_info flag_array[] = {
 		.set	= "present",
 		.clear	= "       ",
 	}, {
+		.mask	= _PAGE_COHERENT,
+		.val	= _PAGE_COHERENT,
+		.set	= "coherent",
+		.clear	= "        ",
+	}, {
 		.mask	= _PAGE_GUARDED,
 		.val	= _PAGE_GUARDED,
 		.set	= "guarded",
diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index 42bbcd47cc85..dffe1a45b6ed 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -50,7 +50,7 @@ static void slice_print_mask(const char *label, const struct slice_mask *mask) {
 
 #endif
 
-static inline bool slice_addr_is_low(unsigned long addr)
+static inline notrace bool slice_addr_is_low(unsigned long addr)
 {
 	u64 tmp = (u64)addr;
 
@@ -659,7 +659,7 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp,
 				       mm_ctx_user_psize(&current->mm->context), 1);
 }
 
-unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr)
+unsigned int notrace get_slice_psize(struct mm_struct *mm, unsigned long addr)
 {
 	unsigned char *psizes;
 	int index, mask_index;
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index faad5b315f49..5834ac3dd474 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -1400,16 +1400,6 @@ static void h_24x7_event_read(struct perf_event *event)
 			h24x7hw = &get_cpu_var(hv_24x7_hw);
 			h24x7hw->events[i] = event;
 			put_cpu_var(h24x7hw);
-			/*
-			 * Clear the event count so we can compute the _change_
-			 * in the 24x7 raw counter value at the end of the txn.
-			 *
-			 * Note that we could alternatively read the 24x7 value
-			 * now and save its value in event->hw.prev_count. But
-			 * that would require issuing a hcall, which would then
-			 * defeat the purpose of using the txn interface.
-			 */
-			local64_set(&event->count, 0);
 		}
 
 		put_cpu_var(hv_24x7_reqb);
diff --git a/arch/powerpc/platforms/4xx/pci.c b/arch/powerpc/platforms/4xx/pci.c
index e6e2adcc7b64..c13d64c3b019 100644
--- a/arch/powerpc/platforms/4xx/pci.c
+++ b/arch/powerpc/platforms/4xx/pci.c
@@ -1242,7 +1242,7 @@ static void __init ppc460sx_pciex_check_link(struct ppc4xx_pciex_port *port)
 	if (mbase == NULL) {
 		printk(KERN_ERR "%pOF: Can't map internal config space !",
 			port->node);
-		goto done;
+		return;
 	}
 
 	while (attempt && (0 == (in_le32(mbase + PECFG_460SX_DLLSTA)
@@ -1252,9 +1252,7 @@ static void __init ppc460sx_pciex_check_link(struct ppc4xx_pciex_port *port)
 	}
 	if (attempt)
 		port->link = 1;
-done:
 	iounmap(mbase);
-
 }
 
 static struct ppc4xx_pciex_hwops ppc460sx_pcie_hwops __initdata = {
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 2794235e9d3e..98d824563b35 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -379,7 +379,7 @@ config PPC_KUAP
 
 config PPC_KUAP_DEBUG
 	bool "Extra debugging for Kernel Userspace Access Protection"
-	depends on PPC_HAVE_KUAP && (PPC_RADIX_MMU || PPC_32)
+	depends on PPC_KUAP && (PPC_RADIX_MMU || PPC32)
 	help
 	  Add extra debugging for Kernel Userspace Access Protection (KUAP)
 	  If you're unsure, say N.
diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index d40253a18b1c..512c87bc20a3 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -1978,8 +1978,9 @@ static ssize_t __spufs_mbox_info_read(struct spu_context *ctx,
 static ssize_t spufs_mbox_info_read(struct file *file, char __user *buf,
 				   size_t len, loff_t *pos)
 {
-	int ret;
 	struct spu_context *ctx = file->private_data;
+	u32 stat, data;
+	int ret;
 
 	if (!access_ok(buf, len))
 		return -EFAULT;
@@ -1988,11 +1989,16 @@ static ssize_t spufs_mbox_info_read(struct file *file, char __user *buf,
 	if (ret)
 		return ret;
 	spin_lock(&ctx->csa.register_lock);
-	ret = __spufs_mbox_info_read(ctx, buf, len, pos);
+	stat = ctx->csa.prob.mb_stat_R;
+	data = ctx->csa.prob.pu_mb_R;
 	spin_unlock(&ctx->csa.register_lock);
 	spu_release_saved(ctx);
 
-	return ret;
+	/* EOF if there's no entry in the mbox */
+	if (!(stat & 0x0000ff))
+		return 0;
+
+	return simple_read_from_buffer(buf, len, pos, &data, sizeof(data));
 }
 
 static const struct file_operations spufs_mbox_info_fops = {
@@ -2019,6 +2025,7 @@ static ssize_t spufs_ibox_info_read(struct file *file, char __user *buf,
 				   size_t len, loff_t *pos)
 {
 	struct spu_context *ctx = file->private_data;
+	u32 stat, data;
 	int ret;
 
 	if (!access_ok(buf, len))
@@ -2028,11 +2035,16 @@ static ssize_t spufs_ibox_info_read(struct file *file, char __user *buf,
 	if (ret)
 		return ret;
 	spin_lock(&ctx->csa.register_lock);
-	ret = __spufs_ibox_info_read(ctx, buf, len, pos);
+	stat = ctx->csa.prob.mb_stat_R;
+	data = ctx->csa.priv2.puint_mb_R;
 	spin_unlock(&ctx->csa.register_lock);
 	spu_release_saved(ctx);
 
-	return ret;
+	/* EOF if there's no entry in the ibox */
+	if (!(stat & 0xff0000))
+		return 0;
+
+	return simple_read_from_buffer(buf, len, pos, &data, sizeof(data));
 }
 
 static const struct file_operations spufs_ibox_info_fops = {
@@ -2041,6 +2053,11 @@ static const struct file_operations spufs_ibox_info_fops = {
 	.llseek  = generic_file_llseek,
 };
 
+static size_t spufs_wbox_info_cnt(struct spu_context *ctx)
+{
+	return (4 - ((ctx->csa.prob.mb_stat_R & 0x00ff00) >> 8)) * sizeof(u32);
+}
+
 static ssize_t __spufs_wbox_info_read(struct spu_context *ctx,
 			char __user *buf, size_t len, loff_t *pos)
 {
@@ -2049,7 +2066,7 @@ static ssize_t __spufs_wbox_info_read(struct spu_context *ctx,
 	u32 wbox_stat;
 
 	wbox_stat = ctx->csa.prob.mb_stat_R;
-	cnt = 4 - ((wbox_stat & 0x00ff00) >> 8);
+	cnt = spufs_wbox_info_cnt(ctx);
 	for (i = 0; i < cnt; i++) {
 		data[i] = ctx->csa.spu_mailbox_data[i];
 	}
@@ -2062,7 +2079,8 @@ static ssize_t spufs_wbox_info_read(struct file *file, char __user *buf,
 				   size_t len, loff_t *pos)
 {
 	struct spu_context *ctx = file->private_data;
-	int ret;
+	u32 data[ARRAY_SIZE(ctx->csa.spu_mailbox_data)];
+	int ret, count;
 
 	if (!access_ok(buf, len))
 		return -EFAULT;
@@ -2071,11 +2089,13 @@ static ssize_t spufs_wbox_info_read(struct file *file, char __user *buf,
 	if (ret)
 		return ret;
 	spin_lock(&ctx->csa.register_lock);
-	ret = __spufs_wbox_info_read(ctx, buf, len, pos);
+	count = spufs_wbox_info_cnt(ctx);
+	memcpy(&data, &ctx->csa.spu_mailbox_data, sizeof(data));
 	spin_unlock(&ctx->csa.register_lock);
 	spu_release_saved(ctx);
 
-	return ret;
+	return simple_read_from_buffer(buf, len, pos, &data,
+				count * sizeof(u32));
 }
 
 static const struct file_operations spufs_wbox_info_fops = {
@@ -2084,27 +2104,33 @@ static const struct file_operations spufs_wbox_info_fops = {
 	.llseek  = generic_file_llseek,
 };
 
-static ssize_t __spufs_dma_info_read(struct spu_context *ctx,
-			char __user *buf, size_t len, loff_t *pos)
+static void spufs_get_dma_info(struct spu_context *ctx,
+		struct spu_dma_info *info)
 {
-	struct spu_dma_info info;
-	struct mfc_cq_sr *qp, *spuqp;
 	int i;
 
-	info.dma_info_type = ctx->csa.priv2.spu_tag_status_query_RW;
-	info.dma_info_mask = ctx->csa.lscsa->tag_mask.slot[0];
-	info.dma_info_status = ctx->csa.spu_chnldata_RW[24];
-	info.dma_info_stall_and_notify = ctx->csa.spu_chnldata_RW[25];
-	info.dma_info_atomic_command_status = ctx->csa.spu_chnldata_RW[27];
+	info->dma_info_type = ctx->csa.priv2.spu_tag_status_query_RW;
+	info->dma_info_mask = ctx->csa.lscsa->tag_mask.slot[0];
+	info->dma_info_status = ctx->csa.spu_chnldata_RW[24];
+	info->dma_info_stall_and_notify = ctx->csa.spu_chnldata_RW[25];
+	info->dma_info_atomic_command_status = ctx->csa.spu_chnldata_RW[27];
 	for (i = 0; i < 16; i++) {
-		qp = &info.dma_info_command_data[i];
-		spuqp = &ctx->csa.priv2.spuq[i];
+		struct mfc_cq_sr *qp = &info->dma_info_command_data[i];
+		struct mfc_cq_sr *spuqp = &ctx->csa.priv2.spuq[i];
 
 		qp->mfc_cq_data0_RW = spuqp->mfc_cq_data0_RW;
 		qp->mfc_cq_data1_RW = spuqp->mfc_cq_data1_RW;
 		qp->mfc_cq_data2_RW = spuqp->mfc_cq_data2_RW;
 		qp->mfc_cq_data3_RW = spuqp->mfc_cq_data3_RW;
 	}
+}
+
+static ssize_t __spufs_dma_info_read(struct spu_context *ctx,
+			char __user *buf, size_t len, loff_t *pos)
+{
+	struct spu_dma_info info;
+
+	spufs_get_dma_info(ctx, &info);
 
 	return simple_read_from_buffer(buf, len, pos, &info,
 				sizeof info);
@@ -2114,6 +2140,7 @@ static ssize_t spufs_dma_info_read(struct file *file, char __user *buf,
 			      size_t len, loff_t *pos)
 {
 	struct spu_context *ctx = file->private_data;
+	struct spu_dma_info info;
 	int ret;
 
 	if (!access_ok(buf, len))
@@ -2123,11 +2150,12 @@ static ssize_t spufs_dma_info_read(struct file *file, char __user *buf,
 	if (ret)
 		return ret;
 	spin_lock(&ctx->csa.register_lock);
-	ret = __spufs_dma_info_read(ctx, buf, len, pos);
+	spufs_get_dma_info(ctx, &info);
 	spin_unlock(&ctx->csa.register_lock);
 	spu_release_saved(ctx);
 
-	return ret;
+	return simple_read_from_buffer(buf, len, pos, &info,
+				sizeof(info));
 }
 
 static const struct file_operations spufs_dma_info_fops = {
@@ -2136,13 +2164,31 @@ static const struct file_operations spufs_dma_info_fops = {
 	.llseek = no_llseek,
 };
 
+static void spufs_get_proxydma_info(struct spu_context *ctx,
+		struct spu_proxydma_info *info)
+{
+	int i;
+
+	info->proxydma_info_type = ctx->csa.prob.dma_querytype_RW;
+	info->proxydma_info_mask = ctx->csa.prob.dma_querymask_RW;
+	info->proxydma_info_status = ctx->csa.prob.dma_tagstatus_R;
+
+	for (i = 0; i < 8; i++) {
+		struct mfc_cq_sr *qp = &info->proxydma_info_command_data[i];
+		struct mfc_cq_sr *puqp = &ctx->csa.priv2.puq[i];
+
+		qp->mfc_cq_data0_RW = puqp->mfc_cq_data0_RW;
+		qp->mfc_cq_data1_RW = puqp->mfc_cq_data1_RW;
+		qp->mfc_cq_data2_RW = puqp->mfc_cq_data2_RW;
+		qp->mfc_cq_data3_RW = puqp->mfc_cq_data3_RW;
+	}
+}
+
 static ssize_t __spufs_proxydma_info_read(struct spu_context *ctx,
 			char __user *buf, size_t len, loff_t *pos)
 {
 	struct spu_proxydma_info info;
-	struct mfc_cq_sr *qp, *puqp;
 	int ret = sizeof info;
-	int i;
 
 	if (len < ret)
 		return -EINVAL;
@@ -2150,18 +2196,7 @@ static ssize_t __spufs_proxydma_info_read(struct spu_context *ctx,
 	if (!access_ok(buf, len))
 		return -EFAULT;
 
-	info.proxydma_info_type = ctx->csa.prob.dma_querytype_RW;
-	info.proxydma_info_mask = ctx->csa.prob.dma_querymask_RW;
-	info.proxydma_info_status = ctx->csa.prob.dma_tagstatus_R;
-	for (i = 0; i < 8; i++) {
-		qp = &info.proxydma_info_command_data[i];
-		puqp = &ctx->csa.priv2.puq[i];
-
-		qp->mfc_cq_data0_RW = puqp->mfc_cq_data0_RW;
-		qp->mfc_cq_data1_RW = puqp->mfc_cq_data1_RW;
-		qp->mfc_cq_data2_RW = puqp->mfc_cq_data2_RW;
-		qp->mfc_cq_data3_RW = puqp->mfc_cq_data3_RW;
-	}
+	spufs_get_proxydma_info(ctx, &info);
 
 	return simple_read_from_buffer(buf, len, pos, &info,
 				sizeof info);
@@ -2171,17 +2206,19 @@ static ssize_t spufs_proxydma_info_read(struct file *file, char __user *buf,
 				   size_t len, loff_t *pos)
 {
 	struct spu_context *ctx = file->private_data;
+	struct spu_proxydma_info info;
 	int ret;
 
 	ret = spu_acquire_saved(ctx);
 	if (ret)
 		return ret;
 	spin_lock(&ctx->csa.register_lock);
-	ret = __spufs_proxydma_info_read(ctx, buf, len, pos);
+	spufs_get_proxydma_info(ctx, &info);
 	spin_unlock(&ctx->csa.register_lock);
 	spu_release_saved(ctx);
 
-	return ret;
+	return simple_read_from_buffer(buf, len, pos, &info,
+				sizeof(info));
 }
 
 static const struct file_operations spufs_proxydma_info_fops = {
diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c
index 9cd6f3e1000b..09a0594350b6 100644
--- a/arch/powerpc/platforms/maple/setup.c
+++ b/arch/powerpc/platforms/maple/setup.c
@@ -294,23 +294,6 @@ static int __init maple_probe(void)
 	return 1;
 }
 
-define_machine(maple) {
-	.name			= "Maple",
-	.probe			= maple_probe,
-	.setup_arch		= maple_setup_arch,
-	.init_IRQ		= maple_init_IRQ,
-	.pci_irq_fixup		= maple_pci_irq_fixup,
-	.pci_get_legacy_ide_irq	= maple_pci_get_legacy_ide_irq,
-	.restart		= maple_restart,
-	.halt			= maple_halt,
-       	.get_boot_time		= maple_get_boot_time,
-       	.set_rtc_time		= maple_set_rtc_time,
-       	.get_rtc_time		= maple_get_rtc_time,
-      	.calibrate_decr		= generic_calibrate_decr,
-	.progress		= maple_progress,
-	.power_save		= power4_idle,
-};
-
 #ifdef CONFIG_EDAC
 /*
  * Register a platform device for CPC925 memory controller on
@@ -367,3 +350,20 @@ static int __init maple_cpc925_edac_setup(void)
 }
 machine_device_initcall(maple, maple_cpc925_edac_setup);
 #endif
+
+define_machine(maple) {
+	.name			= "Maple",
+	.probe			= maple_probe,
+	.setup_arch		= maple_setup_arch,
+	.init_IRQ		= maple_init_IRQ,
+	.pci_irq_fixup		= maple_pci_irq_fixup,
+	.pci_get_legacy_ide_irq	= maple_pci_get_legacy_ide_irq,
+	.restart		= maple_restart,
+	.halt			= maple_halt,
+	.get_boot_time		= maple_get_boot_time,
+	.set_rtc_time		= maple_set_rtc_time,
+	.get_rtc_time		= maple_get_rtc_time,
+	.calibrate_decr		= generic_calibrate_decr,
+	.progress		= maple_progress,
+	.power_save		= power4_idle,
+};
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index fd14a6237954..28330c150d4f 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -1155,10 +1155,10 @@ static void __init pnv_power9_idle_init(void)
 			pnv_deepest_stop_psscr_mask);
 	}
 
-	pr_info("cpuidle-powernv: First stop level that may lose SPRs = 0x%lld\n",
+	pr_info("cpuidle-powernv: First stop level that may lose SPRs = 0x%llx\n",
 		pnv_first_spr_loss_level);
 
-	pr_info("cpuidle-powernv: First stop level that may lose timebase = 0x%lld\n",
+	pr_info("cpuidle-powernv: First stop level that may lose timebase = 0x%llx\n",
 		pnv_first_tb_loss_level);
 }
 
diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c
index 7ccc5c85c74e..000b350d4060 100644
--- a/arch/powerpc/platforms/powernv/opal-imc.c
+++ b/arch/powerpc/platforms/powernv/opal-imc.c
@@ -59,10 +59,6 @@ static void export_imc_mode_and_cmd(struct device_node *node,
 
 	imc_debugfs_parent = debugfs_create_dir("imc", powerpc_debugfs_root);
 
-	/*
-	 * Return here, either because 'imc' directory already exists,
-	 * Or failed to create a new one.
-	 */
 	if (!imc_debugfs_parent)
 		return;
 
@@ -135,7 +131,6 @@ static int imc_get_mem_addr_nest(struct device_node *node,
 	}
 
 	pmu_ptr->imc_counter_mmaped = true;
-	export_imc_mode_and_cmd(node, pmu_ptr);
 	kfree(base_addr_arr);
 	kfree(chipid_arr);
 	return 0;
@@ -151,7 +146,7 @@ error:
  *		    and domain as the inputs.
  * Allocates memory for the struct imc_pmu, sets up its domain, size and offsets
  */
-static int imc_pmu_create(struct device_node *parent, int pmu_index, int domain)
+static struct imc_pmu *imc_pmu_create(struct device_node *parent, int pmu_index, int domain)
 {
 	int ret = 0;
 	struct imc_pmu *pmu_ptr;
@@ -159,27 +154,23 @@ static int imc_pmu_create(struct device_node *parent, int pmu_index, int domain)
 
 	/* Return for unknown domain */
 	if (domain < 0)
-		return -EINVAL;
+		return NULL;
 
 	/* memory for pmu */
 	pmu_ptr = kzalloc(sizeof(*pmu_ptr), GFP_KERNEL);
 	if (!pmu_ptr)
-		return -ENOMEM;
+		return NULL;
 
 	/* Set the domain */
 	pmu_ptr->domain = domain;
 
 	ret = of_property_read_u32(parent, "size", &pmu_ptr->counter_mem_size);
-	if (ret) {
-		ret = -EINVAL;
+	if (ret)
 		goto free_pmu;
-	}
 
 	if (!of_property_read_u32(parent, "offset", &offset)) {
-		if (imc_get_mem_addr_nest(parent, pmu_ptr, offset)) {
-			ret = -EINVAL;
+		if (imc_get_mem_addr_nest(parent, pmu_ptr, offset))
 			goto free_pmu;
-		}
 	}
 
 	/* Function to register IMC pmu */
@@ -190,14 +181,14 @@ static int imc_pmu_create(struct device_node *parent, int pmu_index, int domain)
 		if (pmu_ptr->domain == IMC_DOMAIN_NEST)
 			kfree(pmu_ptr->mem_info);
 		kfree(pmu_ptr);
-		return ret;
+		return NULL;
 	}
 
-	return 0;
+	return pmu_ptr;
 
 free_pmu:
 	kfree(pmu_ptr);
-	return ret;
+	return NULL;
 }
 
 static void disable_nest_pmu_counters(void)
@@ -254,6 +245,7 @@ int get_max_nest_dev(void)
 static int opal_imc_counters_probe(struct platform_device *pdev)
 {
 	struct device_node *imc_dev = pdev->dev.of_node;
+	struct imc_pmu *pmu;
 	int pmu_count = 0, domain;
 	bool core_imc_reg = false, thread_imc_reg = false;
 	u32 type;
@@ -269,6 +261,7 @@ static int opal_imc_counters_probe(struct platform_device *pdev)
 	}
 
 	for_each_compatible_node(imc_dev, NULL, IMC_DTB_UNIT_COMPAT) {
+		pmu = NULL;
 		if (of_property_read_u32(imc_dev, "type", &type)) {
 			pr_warn("IMC Device without type property\n");
 			continue;
@@ -300,9 +293,13 @@ static int opal_imc_counters_probe(struct platform_device *pdev)
 			break;
 		}
 
-		if (!imc_pmu_create(imc_dev, pmu_count, domain)) {
-			if (domain == IMC_DOMAIN_NEST)
+		pmu = imc_pmu_create(imc_dev, pmu_count, domain);
+		if (pmu != NULL) {
+			if (domain == IMC_DOMAIN_NEST) {
+				if (!imc_debugfs_parent)
+					export_imc_mode_and_cmd(imc_dev, pmu);
 				pmu_count++;
+			}
 			if (domain == IMC_DOMAIN_CORE)
 				core_imc_reg = true;
 			if (domain == IMC_DOMAIN_THREAD)
@@ -310,10 +307,6 @@ static int opal_imc_counters_probe(struct platform_device *pdev)
 		}
 	}
 
-	/* If none of the nest units are registered, remove debugfs interface */
-	if (pmu_count == 0)
-		debugfs_remove_recursive(imc_debugfs_parent);
-
 	/* If core imc is not registered, unregister thread-imc */
 	if (!core_imc_reg && thread_imc_reg)
 		unregister_thread_imc();
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 0f72c7484824..050131e886f1 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1556,6 +1556,10 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
 
 	/* Reserve PE for each VF */
 	for (vf_index = 0; vf_index < num_vfs; vf_index++) {
+		int vf_devfn = pci_iov_virtfn_devfn(pdev, vf_index);
+		int vf_bus = pci_iov_virtfn_bus(pdev, vf_index);
+		struct pci_dn *vf_pdn;
+
 		if (pdn->m64_single_mode)
 			pe_num = pdn->pe_num_map[vf_index];
 		else
@@ -1568,13 +1572,11 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
 		pe->pbus = NULL;
 		pe->parent_dev = pdev;
 		pe->mve_number = -1;
-		pe->rid = (pci_iov_virtfn_bus(pdev, vf_index) << 8) |
-			   pci_iov_virtfn_devfn(pdev, vf_index);
+		pe->rid = (vf_bus << 8) | vf_devfn;
 
 		pe_info(pe, "VF %04d:%02d:%02d.%d associated with PE#%x\n",
 			hose->global_number, pdev->bus->number,
-			PCI_SLOT(pci_iov_virtfn_devfn(pdev, vf_index)),
-			PCI_FUNC(pci_iov_virtfn_devfn(pdev, vf_index)), pe_num);
+			PCI_SLOT(vf_devfn), PCI_FUNC(vf_devfn), pe_num);
 
 		if (pnv_ioda_configure_pe(phb, pe)) {
 			/* XXX What do we do here ? */
@@ -1588,6 +1590,15 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
 		list_add_tail(&pe->list, &phb->ioda.pe_list);
 		mutex_unlock(&phb->ioda.pe_list_mutex);
 
+		/* associate this pe to it's pdn */
+		list_for_each_entry(vf_pdn, &pdn->parent->child_list, list) {
+			if (vf_pdn->busno == vf_bus &&
+			    vf_pdn->devfn == vf_devfn) {
+				vf_pdn->pe_number = pe_num;
+				break;
+			}
+		}
+
 		pnv_pci_ioda2_setup_dma_pe(phb, pe);
 #ifdef CONFIG_IOMMU_API
 		iommu_register_group(&pe->table_group,
@@ -2897,9 +2908,6 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev)
 	struct pci_dn *pdn;
 	int mul, total_vfs;
 
-	if (!pdev->is_physfn || pci_dev_is_added(pdev))
-		return;
-
 	pdn = pci_get_pdn(pdev);
 	pdn->vfs_expanded = 0;
 	pdn->m64_single_mode = false;
@@ -2974,6 +2982,30 @@ truncate_iov:
 		res->end = res->start - 1;
 	}
 }
+
+static void pnv_pci_ioda_fixup_iov(struct pci_dev *pdev)
+{
+	if (WARN_ON(pci_dev_is_added(pdev)))
+		return;
+
+	if (pdev->is_virtfn) {
+		struct pnv_ioda_pe *pe = pnv_ioda_get_pe(pdev);
+
+		/*
+		 * VF PEs are single-device PEs so their pdev pointer needs to
+		 * be set. The pdev doesn't exist when the PE is allocated (in
+		 * (pcibios_sriov_enable()) so we fix it up here.
+		 */
+		pe->pdev = pdev;
+		WARN_ON(!(pe->flags & PNV_IODA_PE_VF));
+	} else if (pdev->is_physfn) {
+		/*
+		 * For PFs adjust their allocated IOV resources to match what
+		 * the PHB can support using it's M64 BAR table.
+		 */
+		pnv_pci_ioda_fixup_iov_resources(pdev);
+	}
+}
 #endif /* CONFIG_PCI_IOV */
 
 static void pnv_ioda_setup_pe_res(struct pnv_ioda_pe *pe,
@@ -3870,7 +3902,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	ppc_md.pcibios_default_alignment = pnv_pci_default_alignment;
 
 #ifdef CONFIG_PCI_IOV
-	ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov_resources;
+	ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov;
 	ppc_md.pcibios_iov_resource_alignment = pnv_pci_iov_resource_alignment;
 	ppc_md.pcibios_sriov_enable = pnv_pcibios_sriov_enable;
 	ppc_md.pcibios_sriov_disable = pnv_pcibios_sriov_disable;
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index ff1a33fee8e6..2bfb72d057a7 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -814,24 +814,6 @@ void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
 {
 	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
 	struct pnv_phb *phb = hose->private_data;
-#ifdef CONFIG_PCI_IOV
-	struct pnv_ioda_pe *pe;
-	struct pci_dn *pdn;
-
-	/* Fix the VF pdn PE number */
-	if (pdev->is_virtfn) {
-		pdn = pci_get_pdn(pdev);
-		WARN_ON(pdn->pe_number != IODA_INVALID_PE);
-		list_for_each_entry(pe, &phb->ioda.pe_list, list) {
-			if (pe->rid == ((pdev->bus->number << 8) |
-			    (pdev->devfn & 0xff))) {
-				pdn->pe_number = pe->pe_number;
-				pe->pdev = pdev;
-				break;
-			}
-		}
-	}
-#endif /* CONFIG_PCI_IOV */
 
 	if (phb && phb->dma_dev_setup)
 		phb->dma_dev_setup(phb, pdev);
@@ -1089,6 +1071,23 @@ void __init pnv_pci_init(void)
 	if (!firmware_has_feature(FW_FEATURE_OPAL))
 		return;
 
+#ifdef CONFIG_PCIEPORTBUS
+	/*
+	 * On PowerNV PCIe devices are (currently) managed in cooperation
+	 * with firmware. This isn't *strictly* required, but there's enough
+	 * assumptions baked into both firmware and the platform code that
+	 * it's unwise to allow the portbus services to be used.
+	 *
+	 * We need to fix this eventually, but for now set this flag to disable
+	 * the portbus driver. The AER service isn't required since that AER
+	 * events are handled via EEH. The pciehp hotplug driver can't work
+	 * without kernel changes (and portbus binding breaks pnv_php). The
+	 * other services also require some thinking about how we're going
+	 * to integrate them.
+	 */
+	pcie_ports_disabled = true;
+#endif
+
 	/* Look for IODA IO-Hubs. */
 	for_each_compatible_node(np, NULL, "ibm,ioda-hub") {
 		pnv_pci_init_ioda_hub(np);
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 001dfac8354a..d87981f90fdc 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -167,7 +167,6 @@ static void pnv_smp_cpu_kill_self(void)
 	/* Standard hot unplug procedure */
 
 	idle_task_exit();
-	current->active_mm = NULL; /* for sanity */
 	cpu = smp_processor_id();
 	DBG("CPU%d offline\n", cpu);
 	generic_set_cpu_dead(cpu);
diff --git a/arch/powerpc/platforms/ps3/mm.c b/arch/powerpc/platforms/ps3/mm.c
index 423be34f0f5f..f42fe4e86ce5 100644
--- a/arch/powerpc/platforms/ps3/mm.c
+++ b/arch/powerpc/platforms/ps3/mm.c
@@ -200,13 +200,14 @@ void ps3_mm_vas_destroy(void)
 {
 	int result;
 
-	DBG("%s:%d: map.vas_id    = %llu\n", __func__, __LINE__, map.vas_id);
-
 	if (map.vas_id) {
 		result = lv1_select_virtual_address_space(0);
-		BUG_ON(result);
-		result = lv1_destruct_virtual_address_space(map.vas_id);
-		BUG_ON(result);
+		result += lv1_destruct_virtual_address_space(map.vas_id);
+
+		if (result) {
+			lv1_panic(0);
+		}
+
 		map.vas_id = 0;
 	}
 }
@@ -304,19 +305,20 @@ static void ps3_mm_region_destroy(struct mem_region *r)
 	int result;
 
 	if (!r->destroy) {
-		pr_info("%s:%d: Not destroying high region: %llxh %llxh\n",
-			__func__, __LINE__, r->base, r->size);
 		return;
 	}
 
-	DBG("%s:%d: r->base = %llxh\n", __func__, __LINE__, r->base);
-
 	if (r->base) {
 		result = lv1_release_memory(r->base);
-		BUG_ON(result);
+
+		if (result) {
+			lv1_panic(0);
+		}
+
 		r->size = r->base = r->offset = 0;
 		map.total = map.rm.size;
 	}
+
 	ps3_mm_set_repository_highmem(NULL);
 }
 
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 46d0d35b9ca4..c5de633e8436 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -27,7 +27,7 @@ static bool rtas_hp_event;
 unsigned long pseries_memory_block_size(void)
 {
 	struct device_node *np;
-	unsigned int memblock_size = MIN_MEMORY_BLOCK_SIZE;
+	u64 memblock_size = MIN_MEMORY_BLOCK_SIZE;
 	struct resource r;
 
 	np = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
@@ -223,7 +223,7 @@ static int get_lmb_range(u32 drc_index, int n_lmbs,
 			 struct drmem_lmb **end_lmb)
 {
 	struct drmem_lmb *lmb, *start, *end;
-	struct drmem_lmb *last_lmb;
+	struct drmem_lmb *limit;
 
 	start = NULL;
 	for_each_drmem_lmb(lmb) {
@@ -236,10 +236,10 @@ static int get_lmb_range(u32 drc_index, int n_lmbs,
 	if (!start)
 		return -EINVAL;
 
-	end = &start[n_lmbs - 1];
+	end = &start[n_lmbs];
 
-	last_lmb = &drmem_info->lmbs[drmem_info->n_lmbs - 1];
-	if (end > last_lmb)
+	limit = &drmem_info->lmbs[drmem_info->n_lmbs];
+	if (end > limit)
 		return -EINVAL;
 
 	*start_lmb = start;
@@ -360,8 +360,10 @@ static bool lmb_is_removable(struct drmem_lmb *lmb)
 
 	for (i = 0; i < scns_per_block; i++) {
 		pfn = PFN_DOWN(phys_addr);
-		if (!pfn_present(pfn))
+		if (!pfn_present(pfn)) {
+			phys_addr += MIN_MEMORY_BLOCK_SIZE;
 			continue;
+		}
 
 		rc &= is_mem_section_removable(pfn, PAGES_PER_SECTION);
 		phys_addr += MIN_MEMORY_BLOCK_SIZE;
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 889dc2e44b89..3eddad5f9be0 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -132,10 +132,10 @@ static unsigned long tce_get_pseries(struct iommu_table *tbl, long index)
 	return be64_to_cpu(*tcep);
 }
 
-static void tce_free_pSeriesLP(struct iommu_table*, long, long);
+static void tce_free_pSeriesLP(unsigned long liobn, long, long);
 static void tce_freemulti_pSeriesLP(struct iommu_table*, long, long);
 
-static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum,
+static int tce_build_pSeriesLP(unsigned long liobn, long tcenum, long tceshift,
 				long npages, unsigned long uaddr,
 				enum dma_data_direction direction,
 				unsigned long attrs)
@@ -146,25 +146,25 @@ static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum,
 	int ret = 0;
 	long tcenum_start = tcenum, npages_start = npages;
 
-	rpn = __pa(uaddr) >> TCE_SHIFT;
+	rpn = __pa(uaddr) >> tceshift;
 	proto_tce = TCE_PCI_READ;
 	if (direction != DMA_TO_DEVICE)
 		proto_tce |= TCE_PCI_WRITE;
 
 	while (npages--) {
-		tce = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT;
-		rc = plpar_tce_put((u64)tbl->it_index, (u64)tcenum << 12, tce);
+		tce = proto_tce | (rpn & TCE_RPN_MASK) << tceshift;
+		rc = plpar_tce_put((u64)liobn, (u64)tcenum << tceshift, tce);
 
 		if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) {
 			ret = (int)rc;
-			tce_free_pSeriesLP(tbl, tcenum_start,
+			tce_free_pSeriesLP(liobn, tcenum_start,
 			                   (npages_start - (npages + 1)));
 			break;
 		}
 
 		if (rc && printk_ratelimit()) {
 			printk("tce_build_pSeriesLP: plpar_tce_put failed. rc=%lld\n", rc);
-			printk("\tindex   = 0x%llx\n", (u64)tbl->it_index);
+			printk("\tindex   = 0x%llx\n", (u64)liobn);
 			printk("\ttcenum  = 0x%llx\n", (u64)tcenum);
 			printk("\ttce val = 0x%llx\n", tce );
 			dump_stack();
@@ -193,7 +193,8 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 	unsigned long flags;
 
 	if ((npages == 1) || !firmware_has_feature(FW_FEATURE_MULTITCE)) {
-		return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr,
+		return tce_build_pSeriesLP(tbl->it_index, tcenum,
+					   tbl->it_page_shift, npages, uaddr,
 		                           direction, attrs);
 	}
 
@@ -209,8 +210,9 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		/* If allocation fails, fall back to the loop implementation */
 		if (!tcep) {
 			local_irq_restore(flags);
-			return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr,
-					    direction, attrs);
+			return tce_build_pSeriesLP(tbl->it_index, tcenum,
+					tbl->it_page_shift,
+					npages, uaddr, direction, attrs);
 		}
 		__this_cpu_write(tce_page, tcep);
 	}
@@ -261,16 +263,16 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 	return ret;
 }
 
-static void tce_free_pSeriesLP(struct iommu_table *tbl, long tcenum, long npages)
+static void tce_free_pSeriesLP(unsigned long liobn, long tcenum, long npages)
 {
 	u64 rc;
 
 	while (npages--) {
-		rc = plpar_tce_put((u64)tbl->it_index, (u64)tcenum << 12, 0);
+		rc = plpar_tce_put((u64)liobn, (u64)tcenum << 12, 0);
 
 		if (rc && printk_ratelimit()) {
 			printk("tce_free_pSeriesLP: plpar_tce_put failed. rc=%lld\n", rc);
-			printk("\tindex   = 0x%llx\n", (u64)tbl->it_index);
+			printk("\tindex   = 0x%llx\n", (u64)liobn);
 			printk("\ttcenum  = 0x%llx\n", (u64)tcenum);
 			dump_stack();
 		}
@@ -285,7 +287,7 @@ static void tce_freemulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long n
 	u64 rc;
 
 	if (!firmware_has_feature(FW_FEATURE_MULTITCE))
-		return tce_free_pSeriesLP(tbl, tcenum, npages);
+		return tce_free_pSeriesLP(tbl->it_index, tcenum, npages);
 
 	rc = plpar_tce_stuff((u64)tbl->it_index, (u64)tcenum << 12, 0, npages);
 
@@ -400,6 +402,19 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn,
 	u64 rc = 0;
 	long l, limit;
 
+	if (!firmware_has_feature(FW_FEATURE_MULTITCE)) {
+		unsigned long tceshift = be32_to_cpu(maprange->tce_shift);
+		unsigned long dmastart = (start_pfn << PAGE_SHIFT) +
+				be64_to_cpu(maprange->dma_base);
+		unsigned long tcenum = dmastart >> tceshift;
+		unsigned long npages = num_pfn << PAGE_SHIFT >> tceshift;
+		void *uaddr = __va(start_pfn << PAGE_SHIFT);
+
+		return tce_build_pSeriesLP(be32_to_cpu(maprange->liobn),
+				tcenum, tceshift, npages, (unsigned long) uaddr,
+				DMA_BIDIRECTIONAL, 0);
+	}
+
 	local_irq_disable();	/* to protect tcep and the page behind it */
 	tcep = __this_cpu_read(tce_page);
 
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 15fe7213aa6b..aa7cc6f2a125 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -1255,7 +1255,7 @@ static int __init vpa_debugfs_init(void)
 {
 	char name[16];
 	long i;
-	static struct dentry *vpa_dir;
+	struct dentry *vpa_dir;
 
 	if (!firmware_has_feature(FW_FEATURE_SPLPAR))
 		return 0;
diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
index e33e8bc4b69b..38c306551f76 100644
--- a/arch/powerpc/platforms/pseries/lparcfg.c
+++ b/arch/powerpc/platforms/pseries/lparcfg.c
@@ -435,10 +435,10 @@ static void maxmem_data(struct seq_file *m)
 {
 	unsigned long maxmem = 0;
 
-	maxmem += drmem_info->n_lmbs * drmem_info->lmb_size;
+	maxmem += (unsigned long)drmem_info->n_lmbs * drmem_info->lmb_size;
 	maxmem += hugetlb_total_pages() * PAGE_SIZE;
 
-	seq_printf(m, "MaxMem=%ld\n", maxmem);
+	seq_printf(m, "MaxMem=%lu\n", maxmem);
 }
 
 static int pseries_lparcfg_data(struct seq_file *m, void *v)
diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c
index 3c17fc7c2b93..8debe017c0d6 100644
--- a/arch/powerpc/platforms/pseries/papr_scm.c
+++ b/arch/powerpc/platforms/pseries/papr_scm.c
@@ -238,6 +238,7 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
 	p->bus = nvdimm_bus_register(NULL, &p->bus_desc);
 	if (!p->bus) {
 		dev_err(dev, "Error creating nvdimm bus %pOF\n", p->dn);
+		kfree(p->bus_desc.provider_name);
 		return -ENXIO;
 	}
 
@@ -382,6 +383,7 @@ static int papr_scm_remove(struct platform_device *pdev)
 
 	nvdimm_bus_unregister(p->bus);
 	drc_pmem_unbind(p);
+	kfree(p->bus_desc.provider_name);
 	kfree(p);
 
 	return 0;
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index f16fdd0f71f7..68eec766a5d8 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -412,10 +412,11 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id)
 /*
  * Some versions of FWNMI place the buffer inside the 4kB page starting at
  * 0x7000. Other versions place it inside the rtas buffer. We check both.
+ * Minimum size of the buffer is 16 bytes.
  */
 #define VALID_FWNMI_BUFFER(A) \
-	((((A) >= 0x7000) && ((A) < 0x7ff0)) || \
-	(((A) >= rtas.base) && ((A) < (rtas.base + rtas.size - 16))))
+	((((A) >= 0x7000) && ((A) <= 0x8000 - 16)) || \
+	(((A) >= rtas.base) && ((A) <= (rtas.base + rtas.size - 16))))
 
 static inline struct rtas_error_log *fwnmi_get_errlog(void)
 {
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index cc682759feae..c0a87b1cee24 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -71,6 +71,9 @@
 #include "pseries.h"
 #include "../../../../drivers/pci/pci.h"
 
+DEFINE_STATIC_KEY_FALSE(shared_processor);
+EXPORT_SYMBOL_GPL(shared_processor);
+
 int CMO_PrPSP = -1;
 int CMO_SecPSP = -1;
 unsigned long CMO_PageSize = (ASM_CONST(1) << IOMMU_PAGE_SHIFT_4K);
@@ -780,6 +783,10 @@ static void __init pSeries_setup_arch(void)
 
 	if (firmware_has_feature(FW_FEATURE_LPAR)) {
 		vpa_init(boot_cpuid);
+
+		if (lppaca_shared_proc(get_lppaca()))
+			static_branch_enable(&shared_processor);
+
 		ppc_md.power_save = pseries_lpar_idle;
 		ppc_md.enable_pmcs = pseries_lpar_enable_pmcs;
 #ifdef CONFIG_PCI_IOV
diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c
index 0a24a5a185f0..f789693f61f4 100644
--- a/arch/powerpc/platforms/pseries/suspend.c
+++ b/arch/powerpc/platforms/pseries/suspend.c
@@ -132,15 +132,11 @@ static ssize_t store_hibernate(struct device *dev,
 			       struct device_attribute *attr,
 			       const char *buf, size_t count)
 {
-	cpumask_var_t offline_mask;
 	int rc;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	if (!alloc_cpumask_var(&offline_mask, GFP_KERNEL))
-		return -ENOMEM;
-
 	stream_id = simple_strtoul(buf, NULL, 16);
 
 	do {
@@ -150,32 +146,16 @@ static ssize_t store_hibernate(struct device *dev,
 	} while (rc == -EAGAIN);
 
 	if (!rc) {
-		/* All present CPUs must be online */
-		cpumask_andnot(offline_mask, cpu_present_mask,
-				cpu_online_mask);
-		rc = rtas_online_cpus_mask(offline_mask);
-		if (rc) {
-			pr_err("%s: Could not bring present CPUs online.\n",
-					__func__);
-			goto out;
-		}
-
 		stop_topology_update();
 		rc = pm_suspend(PM_SUSPEND_MEM);
 		start_topology_update();
-
-		/* Take down CPUs not online prior to suspend */
-		if (!rtas_offline_cpus_mask(offline_mask))
-			pr_warn("%s: Could not restore CPUs to offline "
-					"state.\n", __func__);
 	}
 
 	stream_id = 0;
 
 	if (!rc)
 		rc = count;
-out:
-	free_cpumask_var(offline_mask);
+
 	return rc;
 }
 
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index ba758f4be328..63c8dc080770 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -1174,6 +1174,8 @@ static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev)
 	if (tbl == NULL)
 		return NULL;
 
+	kref_init(&tbl->it_kref);
+
 	of_parse_dma_window(dev->dev.of_node, dma_window,
 			    &tbl->it_index, &offset, &size);
 
diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c
index 723db3ceeaa8..9542394300ec 100644
--- a/arch/powerpc/sysdev/xive/common.c
+++ b/arch/powerpc/sysdev/xive/common.c
@@ -19,6 +19,7 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/msi.h>
+#include <linux/vmalloc.h>
 
 #include <asm/prom.h>
 #include <asm/io.h>
@@ -68,13 +69,6 @@ static u32 xive_ipi_irq;
 /* Xive state for each CPU */
 static DEFINE_PER_CPU(struct xive_cpu *, xive_cpu);
 
-/*
- * A "disabled" interrupt should never fire, to catch problems
- * we set its logical number to this
- */
-#define XIVE_BAD_IRQ		0x7fffffff
-#define XIVE_MAX_IRQ		(XIVE_BAD_IRQ - 1)
-
 /* An invalid CPU target */
 #define XIVE_INVALID_TARGET	(-1)
 
@@ -937,12 +931,21 @@ static int xive_get_irqchip_state(struct irq_data *data,
 				  enum irqchip_irq_state which, bool *state)
 {
 	struct xive_irq_data *xd = irq_data_get_irq_handler_data(data);
+	u8 pq;
 
 	switch (which) {
 	case IRQCHIP_STATE_ACTIVE:
-		*state = !xd->stale_p &&
-			 (xd->saved_p ||
-			  !!(xive_esb_read(xd, XIVE_ESB_GET) & XIVE_ESB_VAL_P));
+		pq = xive_esb_read(xd, XIVE_ESB_GET);
+
+		/*
+		 * The esb value being all 1's means we couldn't get
+		 * the PQ state of the interrupt through mmio. It may
+		 * happen, for example when querying a PHB interrupt
+		 * while the PHB is in an error state. We consider the
+		 * interrupt to be inactive in that case.
+		 */
+		*state = (pq != XIVE_ESB_INVALID) && !xd->stale_p &&
+			(xd->saved_p || !!(pq & XIVE_ESB_VAL_P));
 		return 0;
 	default:
 		return -EINVAL;
@@ -972,12 +975,16 @@ EXPORT_SYMBOL_GPL(is_xive_irq);
 void xive_cleanup_irq_data(struct xive_irq_data *xd)
 {
 	if (xd->eoi_mmio) {
+		unmap_kernel_range((unsigned long)xd->eoi_mmio,
+				   1u << xd->esb_shift);
 		iounmap(xd->eoi_mmio);
 		if (xd->eoi_mmio == xd->trig_mmio)
 			xd->trig_mmio = NULL;
 		xd->eoi_mmio = NULL;
 	}
 	if (xd->trig_mmio) {
+		unmap_kernel_range((unsigned long)xd->trig_mmio,
+				   1u << xd->esb_shift);
 		iounmap(xd->trig_mmio);
 		xd->trig_mmio = NULL;
 	}
@@ -1106,7 +1113,7 @@ static int xive_setup_cpu_ipi(unsigned int cpu)
 	xc = per_cpu(xive_cpu, cpu);
 
 	/* Check if we are already setup */
-	if (xc->hw_ipi != 0)
+	if (xc->hw_ipi != XIVE_BAD_IRQ)
 		return 0;
 
 	/* Grab an IPI from the backend, this will populate xc->hw_ipi */
@@ -1143,7 +1150,7 @@ static void xive_cleanup_cpu_ipi(unsigned int cpu, struct xive_cpu *xc)
 	/* Disable the IPI and free the IRQ data */
 
 	/* Already cleaned up ? */
-	if (xc->hw_ipi == 0)
+	if (xc->hw_ipi == XIVE_BAD_IRQ)
 		return;
 
 	/* Mask the IPI */
@@ -1299,6 +1306,7 @@ static int xive_prepare_cpu(unsigned int cpu)
 		if (np)
 			xc->chip_id = of_get_ibm_chip_id(np);
 		of_node_put(np);
+		xc->hw_ipi = XIVE_BAD_IRQ;
 
 		per_cpu(xive_cpu, cpu) = xc;
 	}
diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c
index ad8ee7dd7f57..43f1f587a956 100644
--- a/arch/powerpc/sysdev/xive/native.c
+++ b/arch/powerpc/sysdev/xive/native.c
@@ -298,7 +298,7 @@ static void xive_native_put_ipi(unsigned int cpu, struct xive_cpu *xc)
 	s64 rc;
 
 	/* Free the IPI */
-	if (!xc->hw_ipi)
+	if (xc->hw_ipi == XIVE_BAD_IRQ)
 		return;
 	for (;;) {
 		rc = opal_xive_free_irq(xc->hw_ipi);
@@ -306,7 +306,7 @@ static void xive_native_put_ipi(unsigned int cpu, struct xive_cpu *xc)
 			msleep(OPAL_BUSY_DELAY_MS);
 			continue;
 		}
-		xc->hw_ipi = 0;
+		xc->hw_ipi = XIVE_BAD_IRQ;
 		break;
 	}
 }
diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c
index 238207cd6bc3..ce756997054f 100644
--- a/arch/powerpc/sysdev/xive/spapr.c
+++ b/arch/powerpc/sysdev/xive/spapr.c
@@ -506,11 +506,11 @@ static int xive_spapr_get_ipi(unsigned int cpu, struct xive_cpu *xc)
 
 static void xive_spapr_put_ipi(unsigned int cpu, struct xive_cpu *xc)
 {
-	if (!xc->hw_ipi)
+	if (xc->hw_ipi == XIVE_BAD_IRQ)
 		return;
 
 	xive_irq_bitmap_free(xc->hw_ipi);
-	xc->hw_ipi = 0;
+	xc->hw_ipi = XIVE_BAD_IRQ;
 }
 #endif /* CONFIG_SMP */
 
diff --git a/arch/powerpc/sysdev/xive/xive-internal.h b/arch/powerpc/sysdev/xive/xive-internal.h
index 211725dbf364..a2f8d9361e6e 100644
--- a/arch/powerpc/sysdev/xive/xive-internal.h
+++ b/arch/powerpc/sysdev/xive/xive-internal.h
@@ -5,6 +5,13 @@
 #ifndef __XIVE_INTERNAL_H
 #define __XIVE_INTERNAL_H
 
+/*
+ * A "disabled" interrupt should never fire, to catch problems
+ * we set its logical number to this
+ */
+#define XIVE_BAD_IRQ		0x7fffffff
+#define XIVE_MAX_IRQ		(XIVE_BAD_IRQ - 1)
+
 /* Each CPU carry one of these with various per-CPU state */
 struct xive_cpu {
 #ifdef CONFIG_SMP
diff --git a/arch/powerpc/tools/relocs_check.sh b/arch/powerpc/tools/relocs_check.sh
index 7b9fe0a567cf..014e00e74d2b 100755
--- a/arch/powerpc/tools/relocs_check.sh
+++ b/arch/powerpc/tools/relocs_check.sh
@@ -10,14 +10,21 @@
 # based on relocs_check.pl
 # Copyright © 2009 IBM Corporation
 
-if [ $# -lt 2 ]; then
-	echo "$0 [path to objdump] [path to vmlinux]" 1>&2
+if [ $# -lt 3 ]; then
+	echo "$0 [path to objdump] [path to nm] [path to vmlinux]" 1>&2
 	exit 1
 fi
 
-# Have Kbuild supply the path to objdump so we handle cross compilation.
+# Have Kbuild supply the path to objdump and nm so we handle cross compilation.
 objdump="$1"
-vmlinux="$2"
+nm="$2"
+vmlinux="$3"
+
+# Remove from the bad relocations those that match an undefined weak symbol
+# which will result in an absolute relocation to 0.
+# Weak unresolved symbols are of that form in nm output:
+# "                  w _binary__btf_vmlinux_bin_end"
+undef_weak_symbols=$($nm "$vmlinux" | awk '$1 ~ /w/ { print $2 }')
 
 bad_relocs=$(
 $objdump -R "$vmlinux" |
@@ -26,8 +33,6 @@ $objdump -R "$vmlinux" |
 	# These relocations are okay
 	# On PPC64:
 	#	R_PPC64_RELATIVE, R_PPC64_NONE
-	#	R_PPC64_ADDR64 mach_<name>
-	#	R_PPC64_ADDR64 __crc_<name>
 	# On PPC:
 	#	R_PPC_RELATIVE, R_PPC_ADDR16_HI,
 	#	R_PPC_ADDR16_HA,R_PPC_ADDR16_LO,
@@ -39,8 +44,7 @@ R_PPC_ADDR16_HI
 R_PPC_ADDR16_HA
 R_PPC_RELATIVE
 R_PPC_NONE' |
-	grep -E -v '\<R_PPC64_ADDR64[[:space:]]+mach_' |
-	grep -E -v '\<R_PPC64_ADDR64[[:space:]]+__crc_'
+	([ "$undef_weak_symbols" ] && grep -F -w -v "$undef_weak_symbols" || cat)
 )
 
 if [ -z "$bad_relocs" ]; then
diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile
index c3842dbeb1b7..6f9cccea54f3 100644
--- a/arch/powerpc/xmon/Makefile
+++ b/arch/powerpc/xmon/Makefile
@@ -1,9 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for xmon
 
-# Avoid clang warnings around longjmp/setjmp declarations
-subdir-ccflags-y := -ffreestanding
-
 GCOV_PROFILE := n
 KCOV_INSTRUMENT := n
 UBSAN_SANITIZE := n
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index e15ccf19c153..79ac87f4d87b 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -1894,15 +1894,14 @@ static void dump_300_sprs(void)
 
 	printf("pidr   = %.16lx  tidr  = %.16lx\n",
 		mfspr(SPRN_PID), mfspr(SPRN_TIDR));
-	printf("asdr   = %.16lx  psscr = %.16lx\n",
-		mfspr(SPRN_ASDR), hv ? mfspr(SPRN_PSSCR)
-					: mfspr(SPRN_PSSCR_PR));
+	printf("psscr  = %.16lx\n",
+		hv ? mfspr(SPRN_PSSCR) : mfspr(SPRN_PSSCR_PR));
 
 	if (!hv)
 		return;
 
-	printf("ptcr   = %.16lx\n",
-		mfspr(SPRN_PTCR));
+	printf("ptcr   = %.16lx  asdr  = %.16lx\n",
+		mfspr(SPRN_PTCR), mfspr(SPRN_ASDR));
 #endif
 }
 
diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h
index 3f1737f301cc..d0e24aaa2aa0 100644
--- a/arch/riscv/include/asm/barrier.h
+++ b/arch/riscv/include/asm/barrier.h
@@ -58,8 +58,16 @@ do {									\
  * The AQ/RL pair provides a RCpc critical section, but there's not really any
  * way we can take advantage of that here because the ordering is only enforced
  * on that one lock.  Thus, we're just doing a full fence.
+ *
+ * Since we allow writeX to be called from preemptive regions we need at least
+ * an "o" in the predecessor set to ensure device writes are visible before the
+ * task is marked as available for scheduling on a new hart.  While I don't see
+ * any concrete reason we need a full IO fence, it seems safer to just upgrade
+ * this in order to avoid any IO crossing a scheduling boundary.  In both
+ * instances the scheduler pairs this with an mb(), so nothing is necessary on
+ * the new hart.
  */
-#define smp_mb__after_spinlock()	RISCV_FENCE(rw,rw)
+#define smp_mb__after_spinlock()	RISCV_FENCE(iorw,iorw)
 
 #include <asm-generic/barrier.h>
 
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index d969bab4a26b..262e5bbb2776 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -179,7 +179,7 @@
 			"	bnez %1, 0b\n"				\
 			"1:\n"						\
 			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
-			: "rJ" (__old), "rJ" (__new)			\
+			: "rJ" ((long)__old), "rJ" (__new)		\
 			: "memory");					\
 		break;							\
 	case 8:								\
@@ -224,7 +224,7 @@
 			RISCV_ACQUIRE_BARRIER				\
 			"1:\n"						\
 			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
-			: "rJ" (__old), "rJ" (__new)			\
+			: "rJ" ((long)__old), "rJ" (__new)		\
 			: "memory");					\
 		break;							\
 	case 8:								\
@@ -270,7 +270,7 @@
 			"	bnez %1, 0b\n"				\
 			"1:\n"						\
 			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
-			: "rJ" (__old), "rJ" (__new)			\
+			: "rJ" ((long)__old), "rJ" (__new)		\
 			: "memory");					\
 		break;							\
 	case 8:								\
@@ -316,7 +316,7 @@
 			"	fence rw, rw\n"				\
 			"1:\n"						\
 			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
-			: "rJ" (__old), "rJ" (__new)			\
+			: "rJ" ((long)__old), "rJ" (__new)		\
 			: "memory");					\
 		break;							\
 	case 8:								\
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
index 905372d7eeb8..3df9a82bdbfd 100644
--- a/arch/riscv/include/asm/thread_info.h
+++ b/arch/riscv/include/asm/thread_info.h
@@ -12,7 +12,11 @@
 #include <linux/const.h>
 
 /* thread information allocation */
+#ifdef CONFIG_64BIT
+#define THREAD_SIZE_ORDER	(2)
+#else
 #define THREAD_SIZE_ORDER	(1)
+#endif
 #define THREAD_SIZE		(PAGE_SIZE << THREAD_SIZE_ORDER)
 
 #ifndef __ASSEMBLY__
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index b94d8db5ddcc..c40fdcdeb950 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -142,7 +142,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 	 */
 	old = *parent;
 
-	if (function_graph_enter(old, self_addr, frame_pointer, parent))
+	if (!function_graph_enter(old, self_addr, frame_pointer, parent))
 		*parent = return_hooker;
 }
 
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index 70bb94ae61c5..6bf5b1674384 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -8,6 +8,10 @@
 #include <linux/err.h>
 #include <linux/errno.h>
 #include <linux/moduleloader.h>
+#include <linux/vmalloc.h>
+#include <linux/sizes.h>
+#include <asm/pgtable.h>
+#include <asm/sections.h>
 
 static int apply_r_riscv_32_rela(struct module *me, u32 *location, Elf_Addr v)
 {
@@ -386,3 +390,15 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 
 	return 0;
 }
+
+#if defined(CONFIG_MMU) && defined(CONFIG_64BIT)
+#define VMALLOC_MODULE_START \
+	 max(PFN_ALIGN((unsigned long)&_end - SZ_2G), VMALLOC_START)
+void *module_alloc(unsigned long size)
+{
+	return __vmalloc_node_range(size, 1, VMALLOC_MODULE_START,
+				    VMALLOC_END, GFP_KERNEL,
+				    PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
+				    __builtin_return_address(0));
+}
+#endif
diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
index f15642715d1a..0a6659865b21 100644
--- a/arch/riscv/kernel/stacktrace.c
+++ b/arch/riscv/kernel/stacktrace.c
@@ -63,7 +63,7 @@ static void notrace walk_stackframe(struct task_struct *task,
 
 #else /* !CONFIG_FRAME_POINTER */
 
-static void notrace walk_stackframe(struct task_struct *task,
+void notrace walk_stackframe(struct task_struct *task,
 	struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg)
 {
 	unsigned long sp, pc;
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index f3619f59d85c..12f8a7fce78b 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -8,6 +8,7 @@
 #include <linux/syscalls.h>
 #include <asm/unistd.h>
 #include <asm/cacheflush.h>
+#include <asm-generic/mman-common.h>
 
 static long riscv_sys_mmap(unsigned long addr, unsigned long len,
 			   unsigned long prot, unsigned long flags,
@@ -16,6 +17,11 @@ static long riscv_sys_mmap(unsigned long addr, unsigned long len,
 {
 	if (unlikely(offset & (~PAGE_MASK >> page_shift_offset)))
 		return -EINVAL;
+
+	if ((prot & PROT_WRITE) && (prot & PROT_EXEC))
+		if (unlikely(!(prot & PROT_READ)))
+			return -EINVAL;
+
 	return ksys_mmap_pgoff(addr, len, prot, flags, fd,
 			       offset >> (PAGE_SHIFT - page_shift_offset));
 }
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 49a5852fd07d..a4ee3a0e7d20 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -33,15 +33,15 @@ $(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso) FORCE
 	$(call if_changed,vdsold)
 
 # We also create a special relocatable object that should mirror the symbol
-# table and layout of the linked DSO.  With ld -R we can then refer to
-# these symbols in the kernel code rather than hand-coded addresses.
+# table and layout of the linked DSO. With ld --just-symbols we can then
+# refer to these symbols in the kernel code rather than hand-coded addresses.
 
 SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \
 	-Wl,--build-id -Wl,--hash-style=both
 $(obj)/vdso-dummy.o: $(src)/vdso.lds $(obj)/rt_sigreturn.o FORCE
 	$(call if_changed,vdsold)
 
-LDFLAGS_vdso-syms.o := -r -R
+LDFLAGS_vdso-syms.o := -r --just-symbols
 $(obj)/vdso-syms.o: $(obj)/vdso-dummy.o FORCE
 	$(call if_changed,ld)
 
@@ -58,7 +58,8 @@ quiet_cmd_vdsold = VDSOLD  $@
       cmd_vdsold = $(CC) $(KBUILD_CFLAGS) $(call cc-option, -no-pie) -nostdlib -nostartfiles $(SYSCFLAGS_$(@F)) \
                            -Wl,-T,$(filter-out FORCE,$^) -o $@.tmp && \
                    $(CROSS_COMPILE)objcopy \
-                           $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@
+                           $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@ && \
+                   rm $@.tmp
 
 # install commands for the unstripped file
 quiet_cmd_vdso_install = INSTALL $@
diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c
index 9ebcff8ba263..4a2e5bf8b21a 100644
--- a/arch/riscv/mm/cacheflush.c
+++ b/arch/riscv/mm/cacheflush.c
@@ -14,6 +14,7 @@ void flush_icache_all(void)
 {
 	sbi_remote_fence_i(NULL);
 }
+EXPORT_SYMBOL(flush_icache_all);
 
 /*
  * Performs an icache flush for the given MM context.  RISC-V has no direct
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 84747d7a1e85..67d7fb8924ff 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -120,8 +120,9 @@ void __init setup_bootmem(void)
 	}
 	BUG_ON(mem_size == 0);
 
-	set_max_mapnr(PFN_DOWN(mem_size));
-	max_low_pfn = PFN_DOWN(memblock_end_of_DRAM());
+	max_pfn = PFN_DOWN(memblock_end_of_DRAM());
+	max_low_pfn = max_pfn;
+	set_max_mapnr(max_low_pfn);
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	setup_initrd();
diff --git a/arch/riscv/net/bpf_jit_comp.c b/arch/riscv/net/bpf_jit_comp.c
index 426d5c33ea90..18d5ca64d2d3 100644
--- a/arch/riscv/net/bpf_jit_comp.c
+++ b/arch/riscv/net/bpf_jit_comp.c
@@ -120,6 +120,11 @@ static bool seen_reg(int reg, struct rv_jit_context *ctx)
 	return false;
 }
 
+static void mark_fp(struct rv_jit_context *ctx)
+{
+	__set_bit(RV_CTX_F_SEEN_S5, &ctx->flags);
+}
+
 static void mark_call(struct rv_jit_context *ctx)
 {
 	__set_bit(RV_CTX_F_SEEN_CALL, &ctx->flags);
@@ -596,7 +601,8 @@ static void __build_epilogue(u8 reg, struct rv_jit_context *ctx)
 
 	emit(rv_addi(RV_REG_SP, RV_REG_SP, stack_adjust), ctx);
 	/* Set return value. */
-	emit(rv_addi(RV_REG_A0, RV_REG_A5, 0), ctx);
+	if (reg == RV_REG_RA)
+		emit(rv_addi(RV_REG_A0, RV_REG_A5, 0), ctx);
 	emit(rv_jalr(RV_REG_ZERO, reg, 0), ctx);
 }
 
@@ -631,14 +637,14 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx)
 		return -1;
 	emit(rv_bgeu(RV_REG_A2, RV_REG_T1, off >> 1), ctx);
 
-	/* if (--TCC < 0)
+	/* if (TCC-- < 0)
 	 *     goto out;
 	 */
 	emit(rv_addi(RV_REG_T1, tcc, -1), ctx);
 	off = (tc_ninsn - (ctx->ninsns - start_insn)) << 2;
 	if (is_13b_check(off, insn))
 		return -1;
-	emit(rv_blt(RV_REG_T1, RV_REG_ZERO, off >> 1), ctx);
+	emit(rv_blt(tcc, RV_REG_ZERO, off >> 1), ctx);
 
 	/* prog = array->ptrs[index];
 	 * if (!prog)
@@ -1414,6 +1420,10 @@ static void build_prologue(struct rv_jit_context *ctx)
 {
 	int stack_adjust = 0, store_offset, bpf_stack_adjust;
 
+	bpf_stack_adjust = round_up(ctx->prog->aux->stack_depth, 16);
+	if (bpf_stack_adjust)
+		mark_fp(ctx);
+
 	if (seen_reg(RV_REG_RA, ctx))
 		stack_adjust += 8;
 	stack_adjust += 8; /* RV_REG_FP */
@@ -1431,7 +1441,6 @@ static void build_prologue(struct rv_jit_context *ctx)
 		stack_adjust += 8;
 
 	stack_adjust = round_up(stack_adjust, 16);
-	bpf_stack_adjust = round_up(ctx->prog->aux->stack_depth, 16);
 	stack_adjust += bpf_stack_adjust;
 
 	store_offset = stack_adjust - 8;
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index e48013cf50a2..1d53ea0a4e14 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -69,7 +69,7 @@ cflags-y += -Wa,-I$(srctree)/arch/$(ARCH)/include
 #
 cflags-$(CONFIG_FRAME_POINTER) += -fno-optimize-sibling-calls
 
-ifeq ($(call cc-option-yn,-mpacked-stack),y)
+ifeq ($(call cc-option-yn,-mpacked-stack -mbackchain -msoft-float),y)
 cflags-$(CONFIG_PACK_STACK)  += -mpacked-stack -D__PACK_STACK
 aflags-$(CONFIG_PACK_STACK)  += -D__PACK_STACK
 endif
@@ -146,7 +146,7 @@ all: bzImage
 #KBUILD_IMAGE is necessary for packaging targets like rpm-pkg, deb-pkg...
 KBUILD_IMAGE	:= $(boot)/bzImage
 
-install: vmlinux
+install:
 	$(Q)$(MAKE) $(build)=$(boot) $@
 
 bzImage: vmlinux
diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index 7cba96e7587b..98e808b4e6ec 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -70,7 +70,7 @@ $(obj)/compressed/vmlinux: $(obj)/startup.a FORCE
 $(obj)/startup.a: $(OBJECTS) FORCE
 	$(call if_changed,ar)
 
-install: $(CONFIGURE) $(obj)/bzImage
+install:
 	sh -x  $(srctree)/$(obj)/install.sh $(KERNELRELEASE) $(obj)/bzImage \
 	      System.map "$(INSTALL_PATH)"
 
diff --git a/arch/s390/boot/kaslr.c b/arch/s390/boot/kaslr.c
index 3bdd8132e56b..ae3e22355b9f 100644
--- a/arch/s390/boot/kaslr.c
+++ b/arch/s390/boot/kaslr.c
@@ -73,7 +73,7 @@ static unsigned long get_random(unsigned long limit)
 		*(unsigned long *) prng.parm_block ^= seed;
 		for (i = 0; i < 16; i++) {
 			cpacf_kmc(CPACF_KMC_PRNG, prng.parm_block,
-				  (char *) entropy, (char *) entropy,
+				  (u8 *) entropy, (u8 *) entropy,
 				  sizeof(entropy));
 			memcpy(prng.parm_block, entropy, sizeof(entropy));
 		}
diff --git a/arch/s390/boot/uv.c b/arch/s390/boot/uv.c
index ed007f4a6444..3f501159ee9f 100644
--- a/arch/s390/boot/uv.c
+++ b/arch/s390/boot/uv.c
@@ -15,7 +15,8 @@ void uv_query_info(void)
 	if (!test_facility(158))
 		return;
 
-	if (uv_call(0, (uint64_t)&uvcb))
+	/* rc==0x100 means that there is additional data we do not process */
+	if (uv_call(0, (uint64_t)&uvcb) && uvcb.header.rc != 0x100)
 		return;
 
 	if (test_bit_inv(BIT_UVC_CMD_SET_SHARED_ACCESS, (unsigned long *)uvcb.inst_calls_list) &&
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 2b00a3ebee08..8b5a39e4739a 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -30,12 +30,12 @@
 #define KVM_USER_MEM_SLOTS 32
 
 /*
- * These seem to be used for allocating ->chip in the routing table,
- * which we don't use. 4096 is an out-of-thin-air value. If we need
- * to look at ->chip later on, we'll need to revisit this.
+ * These seem to be used for allocating ->chip in the routing table, which we
+ * don't use. 1 is as small as we can get to reduce the needed memory. If we
+ * need to look at ->chip later on, we'll need to revisit this.
  */
 #define KVM_NR_IRQCHIPS 1
-#define KVM_IRQCHIP_NUM_PINS 4096
+#define KVM_IRQCHIP_NUM_PINS 1
 #define KVM_HALT_POLL_NS_DEFAULT 50000
 
 /* s390-specific vcpu->requests bit members */
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 237ee0c4169f..612ed3c6d581 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -141,7 +141,9 @@ struct lowcore {
 
 	/* br %r1 trampoline */
 	__u16	br_r1_trampoline;		/* 0x0400 */
-	__u8	pad_0x0402[0x0e00-0x0402];	/* 0x0402 */
+	__u32	return_lpswe;			/* 0x0402 */
+	__u32	return_mcck_lpswe;		/* 0x0406 */
+	__u8	pad_0x040a[0x0e00-0x040a];	/* 0x040a */
 
 	/*
 	 * 0xe00 contains the address of the IPL Parameter Information
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index 823578c6b9e2..e399102367af 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -33,6 +33,8 @@
 #define ARCH_HAS_PREPARE_HUGEPAGE
 #define ARCH_HAS_HUGEPAGE_CLEAR_FLUSH
 
+#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
+
 #include <asm/setup.h>
 #ifndef __ASSEMBLY__
 
@@ -40,7 +42,7 @@ void __storage_key_init_range(unsigned long start, unsigned long end);
 
 static inline void storage_key_init_range(unsigned long start, unsigned long end)
 {
-	if (PAGE_DEFAULT_KEY)
+	if (PAGE_DEFAULT_KEY != 0)
 		__storage_key_init_range(start, end);
 }
 
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 305befd55326..0cca0e2d2a35 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -183,7 +183,7 @@ void zpci_remove_reserved_devices(void);
 /* CLP */
 int clp_scan_pci_devices(void);
 int clp_rescan_pci_devices(void);
-int clp_rescan_pci_devices_simple(void);
+int clp_rescan_pci_devices_simple(u32 *fid);
 int clp_add_pci_device(u32, u32, int);
 int clp_enable_fh(struct zpci_dev *, u8);
 int clp_disable_fh(struct zpci_dev *);
diff --git a/arch/s390/include/asm/pci_insn.h b/arch/s390/include/asm/pci_insn.h
index ff81ed19c506..61cf9531f68f 100644
--- a/arch/s390/include/asm/pci_insn.h
+++ b/arch/s390/include/asm/pci_insn.h
@@ -143,14 +143,4 @@ static inline int zpci_set_irq_ctrl(u16 ctl, u8 isc)
 	return __zpci_set_irq_ctrl(ctl, isc, &iib);
 }
 
-#ifdef CONFIG_PCI
-static inline void enable_mio_ctl(void)
-{
-	if (static_branch_likely(&have_mio))
-		__ctl_set_bit(2, 5);
-}
-#else /* CONFIG_PCI */
-static inline void enable_mio_ctl(void) {}
-#endif /* CONFIG_PCI */
-
 #endif
diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h
index cd060b5dd8fd..e4dc64cc9c55 100644
--- a/arch/s390/include/asm/pci_io.h
+++ b/arch/s390/include/asm/pci_io.h
@@ -8,6 +8,10 @@
 #include <linux/slab.h>
 #include <asm/pci_insn.h>
 
+/* I/O size constraints */
+#define ZPCI_MAX_READ_SIZE	8
+#define ZPCI_MAX_WRITE_SIZE	128
+
 /* I/O Map */
 #define ZPCI_IOMAP_SHIFT		48
 #define ZPCI_IOMAP_ADDR_BASE		0x8000000000000000UL
@@ -140,7 +144,8 @@ static inline int zpci_memcpy_fromio(void *dst,
 
 	while (n > 0) {
 		size = zpci_get_max_write_size((u64 __force) src,
-					       (u64) dst, n, 8);
+					       (u64) dst, n,
+					       ZPCI_MAX_READ_SIZE);
 		rc = zpci_read_single(dst, src, size);
 		if (rc)
 			break;
@@ -161,7 +166,8 @@ static inline int zpci_memcpy_toio(volatile void __iomem *dst,
 
 	while (n > 0) {
 		size = zpci_get_max_write_size((u64 __force) dst,
-					       (u64) src, n, 128);
+					       (u64) src, n,
+					       ZPCI_MAX_WRITE_SIZE);
 		if (size > 8) /* main path */
 			rc = zpci_write_block(dst, src, size);
 		else
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 6251bfa11d5c..cb9ded67c77c 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -755,6 +755,12 @@ static inline int pmd_write(pmd_t pmd)
 	return (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE) != 0;
 }
 
+#define pud_write pud_write
+static inline int pud_write(pud_t pud)
+{
+	return (pud_val(pud) & _REGION3_ENTRY_WRITE) != 0;
+}
+
 static inline int pmd_dirty(pmd_t pmd)
 {
 	int dirty = 1;
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index b0fcbc37b637..2c0b8b5fe19a 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -161,6 +161,7 @@ typedef struct thread_struct thread_struct;
 #define INIT_THREAD {							\
 	.ksp = sizeof(init_stack) + (unsigned long) &init_stack,	\
 	.fpu.regs = (void *) init_task.thread.fpu.fprs,			\
+	.last_break = 1,						\
 }
 
 /*
diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h
index db5ef22c46e4..b265106ca331 100644
--- a/arch/s390/include/asm/qdio.h
+++ b/arch/s390/include/asm/qdio.h
@@ -228,7 +228,7 @@ struct qdio_buffer {
  * @sbal: absolute SBAL address
  */
 struct sl_element {
-	unsigned long sbal;
+	u64 sbal;
 } __attribute__ ((packed));
 
 /**
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 925889d360c1..eb83a57cb503 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -8,6 +8,7 @@
 
 #include <linux/const.h>
 #include <uapi/asm/setup.h>
+#include <linux/build_bug.h>
 
 #define EP_OFFSET		0x10008
 #define EP_STRING		"S390EP"
@@ -153,6 +154,12 @@ static inline unsigned long kaslr_offset(void)
 	return __kaslr_offset;
 }
 
+static inline u32 gen_lpswe(unsigned long addr)
+{
+	BUILD_BUG_ON(addr > 0xfff);
+	return 0xb2b20000 | addr;
+}
+
 #else /* __ASSEMBLY__ */
 
 #define IPL_DEVICE	(IPL_DEVICE_OFFSET)
diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h
index f073292e9fdb..d9d5de0f67ff 100644
--- a/arch/s390/include/asm/syscall.h
+++ b/arch/s390/include/asm/syscall.h
@@ -33,7 +33,17 @@ static inline void syscall_rollback(struct task_struct *task,
 static inline long syscall_get_error(struct task_struct *task,
 				     struct pt_regs *regs)
 {
-	return IS_ERR_VALUE(regs->gprs[2]) ? regs->gprs[2] : 0;
+	unsigned long error = regs->gprs[2];
+#ifdef CONFIG_COMPAT
+	if (test_tsk_thread_flag(task, TIF_31BIT)) {
+		/*
+		 * Sign-extend the value so (int)-EFOO becomes (long)-EFOO
+		 * and will match correctly in comparisons.
+		 */
+		error = (long)(int)error;
+	}
+#endif
+	return IS_ERR_VALUE(error) ? error : 0;
 }
 
 static inline long syscall_get_return_value(struct task_struct *task,
diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index 2dc9eb4e1acc..b6a4ce9dafaf 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -155,7 +155,7 @@ static inline void get_tod_clock_ext(char *clk)
 
 static inline unsigned long long get_tod_clock(void)
 {
-	unsigned char clk[STORE_CLOCK_EXT_SIZE];
+	char clk[STORE_CLOCK_EXT_SIZE];
 
 	get_tod_clock_ext(clk);
 	return *((unsigned long long *)&clk[1]);
diff --git a/arch/s390/include/asm/vdso.h b/arch/s390/include/asm/vdso.h
index 169d7604eb80..f3ba84fa9bd1 100644
--- a/arch/s390/include/asm/vdso.h
+++ b/arch/s390/include/asm/vdso.h
@@ -36,6 +36,7 @@ struct vdso_data {
 	__u32 tk_shift;			/* Shift used for xtime_nsec	0x60 */
 	__u32 ts_dir;			/* TOD steering direction	0x64 */
 	__u64 ts_end;			/* TOD steering end		0x68 */
+	__u32 hrtimer_res;		/* hrtimer resolution		0x70 */
 };
 
 struct vdso_per_cpu_data {
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 41ac4ad21311..a65cb4924bdb 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -76,6 +76,7 @@ int main(void)
 	OFFSET(__VDSO_TK_SHIFT, vdso_data, tk_shift);
 	OFFSET(__VDSO_TS_DIR, vdso_data, ts_dir);
 	OFFSET(__VDSO_TS_END, vdso_data, ts_end);
+	OFFSET(__VDSO_CLOCK_REALTIME_RES, vdso_data, hrtimer_res);
 	OFFSET(__VDSO_ECTG_BASE, vdso_per_cpu_data, ectg_timer_base);
 	OFFSET(__VDSO_ECTG_USER, vdso_per_cpu_data, ectg_user_time);
 	OFFSET(__VDSO_CPU_NR, vdso_per_cpu_data, cpu_nr);
@@ -87,7 +88,6 @@ int main(void)
 	DEFINE(__CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
 	DEFINE(__CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE);
 	DEFINE(__CLOCK_THREAD_CPUTIME_ID, CLOCK_THREAD_CPUTIME_ID);
-	DEFINE(__CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC);
 	DEFINE(__CLOCK_COARSE_RES, LOW_RES_NSEC);
 	BLANK();
 	/* idle data offsets */
@@ -125,6 +125,8 @@ int main(void)
 	OFFSET(__LC_EXT_DAMAGE_CODE, lowcore, external_damage_code);
 	OFFSET(__LC_MCCK_FAIL_STOR_ADDR, lowcore, failing_storage_address);
 	OFFSET(__LC_LAST_BREAK, lowcore, breaking_event_addr);
+	OFFSET(__LC_RETURN_LPSWE, lowcore, return_lpswe);
+	OFFSET(__LC_RETURN_MCCK_LPSWE, lowcore, return_mcck_lpswe);
 	OFFSET(__LC_RST_OLD_PSW, lowcore, restart_old_psw);
 	OFFSET(__LC_EXT_OLD_PSW, lowcore, external_old_psw);
 	OFFSET(__LC_SVC_OLD_PSW, lowcore, svc_old_psw);
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index 0ebf08c3b35e..b46a3c27eb08 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -198,9 +198,10 @@ static debug_entry_t ***debug_areas_alloc(int pages_per_area, int nr_areas)
 	if (!areas)
 		goto fail_malloc_areas;
 	for (i = 0; i < nr_areas; i++) {
+		/* GFP_NOWARN to avoid user triggerable WARN, we handle fails */
 		areas[i] = kmalloc_array(pages_per_area,
 					 sizeof(debug_entry_t *),
-					 GFP_KERNEL);
+					 GFP_KERNEL | __GFP_NOWARN);
 		if (!areas[i])
 			goto fail_malloc_areas2;
 		for (j = 0; j < pages_per_area; j++) {
diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag.c
index e9dac9a24d3f..61f2b0412345 100644
--- a/arch/s390/kernel/diag.c
+++ b/arch/s390/kernel/diag.c
@@ -84,7 +84,7 @@ static int show_diag_stat(struct seq_file *m, void *v)
 
 static void *show_diag_stat_start(struct seq_file *m, loff_t *pos)
 {
-	return *pos <= nr_cpu_ids ? (void *)((unsigned long) *pos + 1) : NULL;
+	return *pos <= NR_DIAG_STAT ? (void *)((unsigned long) *pos + 1) : NULL;
 }
 
 static void *show_diag_stat_next(struct seq_file *m, void *v, loff_t *pos)
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 629f173f60cd..9cebf0487ebd 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -30,7 +30,6 @@
 #include <asm/sclp.h>
 #include <asm/facility.h>
 #include <asm/boot_data.h>
-#include <asm/pci_insn.h>
 #include "entry.h"
 
 /*
@@ -155,6 +154,8 @@ static noinline __init void setup_lowcore_early(void)
 	psw_t psw;
 
 	psw.mask = PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA;
+	if (IS_ENABLED(CONFIG_KASAN))
+		psw.mask |= PSW_MASK_DAT;
 	psw.addr = (unsigned long) s390_base_ext_handler;
 	S390_lowcore.external_new_psw = psw;
 	psw.addr = (unsigned long) s390_base_pgm_handler;
@@ -236,7 +237,6 @@ static __init void detect_machine_facilities(void)
 		clock_comparator_max = -1ULL >> 1;
 		__ctl_set_bit(0, 53);
 	}
-	enable_mio_ctl();
 }
 
 static inline void save_vector_registers(void)
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 3f4d272577d3..de7918a6830c 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -115,26 +115,29 @@ _LPP_OFFSET	= __LC_LPP
 
 	.macro	SWITCH_ASYNC savearea,timer
 	tmhh	%r8,0x0001		# interrupting from user ?
-	jnz	1f
+	jnz	2f
 	lgr	%r14,%r9
+	cghi	%r14,__LC_RETURN_LPSWE
+	je	0f
 	slg	%r14,BASED(.Lcritical_start)
 	clg	%r14,BASED(.Lcritical_length)
-	jhe	0f
+	jhe	1f
+0:
 	lghi	%r11,\savearea		# inside critical section, do cleanup
 	brasl	%r14,cleanup_critical
 	tmhh	%r8,0x0001		# retest problem state after cleanup
-	jnz	1f
-0:	lg	%r14,__LC_ASYNC_STACK	# are we already on the target stack?
+	jnz	2f
+1:	lg	%r14,__LC_ASYNC_STACK	# are we already on the target stack?
 	slgr	%r14,%r15
 	srag	%r14,%r14,STACK_SHIFT
-	jnz	2f
+	jnz	3f
 	CHECK_STACK \savearea
 	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
-	j	3f
-1:	UPDATE_VTIME %r14,%r15,\timer
+	j	4f
+2:	UPDATE_VTIME %r14,%r15,\timer
 	BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP
-2:	lg	%r15,__LC_ASYNC_STACK	# load async stack
-3:	la	%r11,STACK_FRAME_OVERHEAD(%r15)
+3:	lg	%r15,__LC_ASYNC_STACK	# load async stack
+4:	la	%r11,STACK_FRAME_OVERHEAD(%r15)
 	.endm
 
 	.macro UPDATE_VTIME w1,w2,enter_timer
@@ -365,9 +368,9 @@ ENTRY(system_call)
 	jnz	.Lsysc_nr_ok
 	# svc 0: system call number in %r1
 	llgfr	%r1,%r1				# clear high word in r1
+	sth	%r1,__PT_INT_CODE+2(%r11)
 	cghi	%r1,NR_syscalls
 	jnl	.Lsysc_nr_ok
-	sth	%r1,__PT_INT_CODE+2(%r11)
 	slag	%r8,%r1,3
 .Lsysc_nr_ok:
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
@@ -401,7 +404,7 @@ ENTRY(system_call)
 	stpt	__LC_EXIT_TIMER
 	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
 	lmg	%r11,%r15,__PT_R11(%r11)
-	lpswe	__LC_RETURN_PSW
+	b	__LC_RETURN_LPSWE(%r0)
 .Lsysc_done:
 
 #
@@ -608,43 +611,50 @@ ENTRY(pgm_check_handler)
 	BPOFF
 	stmg	%r8,%r15,__LC_SAVE_AREA_SYNC
 	lg	%r10,__LC_LAST_BREAK
-	lg	%r12,__LC_CURRENT
+	srag	%r11,%r10,12
+	jnz	0f
+	/* if __LC_LAST_BREAK is < 4096, it contains one of
+	 * the lpswe addresses in lowcore. Set it to 1 (initial state)
+	 * to prevent leaking that address to userspace.
+	 */
+	lghi	%r10,1
+0:	lg	%r12,__LC_CURRENT
 	lghi	%r11,0
 	larl	%r13,cleanup_critical
 	lmg	%r8,%r9,__LC_PGM_OLD_PSW
 	tmhh	%r8,0x0001		# test problem state bit
-	jnz	2f			# -> fault in user space
+	jnz	3f			# -> fault in user space
 #if IS_ENABLED(CONFIG_KVM)
 	# cleanup critical section for program checks in sie64a
 	lgr	%r14,%r9
 	slg	%r14,BASED(.Lsie_critical_start)
 	clg	%r14,BASED(.Lsie_critical_length)
-	jhe	0f
+	jhe	1f
 	lg	%r14,__SF_SIE_CONTROL(%r15)	# get control block pointer
 	ni	__SIE_PROG0C+3(%r14),0xfe	# no longer in SIE
 	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
 	larl	%r9,sie_exit			# skip forward to sie_exit
 	lghi	%r11,_PIF_GUEST_FAULT
 #endif
-0:	tmhh	%r8,0x4000		# PER bit set in old PSW ?
-	jnz	1f			# -> enabled, can't be a double fault
+1:	tmhh	%r8,0x4000		# PER bit set in old PSW ?
+	jnz	2f			# -> enabled, can't be a double fault
 	tm	__LC_PGM_ILC+3,0x80	# check for per exception
 	jnz	.Lpgm_svcper		# -> single stepped svc
-1:	CHECK_STACK __LC_SAVE_AREA_SYNC
+2:	CHECK_STACK __LC_SAVE_AREA_SYNC
 	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
-	# CHECK_VMAP_STACK branches to stack_overflow or 4f
-	CHECK_VMAP_STACK __LC_SAVE_AREA_SYNC,4f
-2:	UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER
+	# CHECK_VMAP_STACK branches to stack_overflow or 5f
+	CHECK_VMAP_STACK __LC_SAVE_AREA_SYNC,5f
+3:	UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER
 	BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP
 	lg	%r15,__LC_KERNEL_STACK
 	lgr	%r14,%r12
 	aghi	%r14,__TASK_thread	# pointer to thread_struct
 	lghi	%r13,__LC_PGM_TDB
 	tm	__LC_PGM_ILC+2,0x02	# check for transaction abort
-	jz	3f
+	jz	4f
 	mvc	__THREAD_trap_tdb(256,%r14),0(%r13)
-3:	stg	%r10,__THREAD_last_break(%r14)
-4:	lgr	%r13,%r11
+4:	stg	%r10,__THREAD_last_break(%r14)
+5:	lgr	%r13,%r11
 	la	%r11,STACK_FRAME_OVERHEAD(%r15)
 	stmg	%r0,%r7,__PT_R0(%r11)
 	# clear user controlled registers to prevent speculative use
@@ -663,14 +673,14 @@ ENTRY(pgm_check_handler)
 	stg	%r13,__PT_FLAGS(%r11)
 	stg	%r10,__PT_ARGS(%r11)
 	tm	__LC_PGM_ILC+3,0x80	# check for per exception
-	jz	5f
+	jz	6f
 	tmhh	%r8,0x0001		# kernel per event ?
 	jz	.Lpgm_kprobe
 	oi	__PT_FLAGS+7(%r11),_PIF_PER_TRAP
 	mvc	__THREAD_per_address(8,%r14),__LC_PER_ADDRESS
 	mvc	__THREAD_per_cause(2,%r14),__LC_PER_CODE
 	mvc	__THREAD_per_paid(1,%r14),__LC_PER_ACCESS_ID
-5:	REENABLE_IRQS
+6:	REENABLE_IRQS
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 	larl	%r1,pgm_check_table
 	llgh	%r10,__PT_INT_CODE+2(%r11)
@@ -775,7 +785,7 @@ ENTRY(io_int_handler)
 	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
 .Lio_exit_kernel:
 	lmg	%r11,%r15,__PT_R11(%r11)
-	lpswe	__LC_RETURN_PSW
+	b	__LC_RETURN_LPSWE(%r0)
 .Lio_done:
 
 #
@@ -1216,7 +1226,7 @@ ENTRY(mcck_int_handler)
 	stpt	__LC_EXIT_TIMER
 	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
 0:	lmg	%r11,%r15,__PT_R11(%r11)
-	lpswe	__LC_RETURN_MCCK_PSW
+	b	__LC_RETURN_MCCK_LPSWE
 
 .Lmcck_panic:
 	lg	%r15,__LC_NODAT_STACK
@@ -1273,6 +1283,8 @@ ENDPROC(stack_overflow)
 #endif
 
 ENTRY(cleanup_critical)
+	cghi	%r9,__LC_RETURN_LPSWE
+	je	.Lcleanup_lpswe
 #if IS_ENABLED(CONFIG_KVM)
 	clg	%r9,BASED(.Lcleanup_table_sie)	# .Lsie_gmap
 	jl	0f
@@ -1426,6 +1438,7 @@ ENDPROC(cleanup_critical)
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r9)
 	mvc	0(64,%r11),__PT_R8(%r9)
 	lmg	%r0,%r7,__PT_R0(%r9)
+.Lcleanup_lpswe:
 1:	lmg	%r8,%r9,__LC_RETURN_PSW
 	BR_EX	%r14,%r11
 .Lcleanup_sysc_restore_insn:
diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c
index fbdd3ea73667..bb7ed0d1a351 100644
--- a/arch/s390/kernel/machine_kexec_file.c
+++ b/arch/s390/kernel/machine_kexec_file.c
@@ -173,7 +173,7 @@ static int kexec_file_add_initrd(struct kimage *image,
 		buf.mem += crashk_res.start;
 	buf.memsz = buf.bufsz;
 
-	data->parm->initrd_start = buf.mem;
+	data->parm->initrd_start = data->memsz;
 	data->parm->initrd_size = buf.memsz;
 	data->memsz += buf.memsz;
 
diff --git a/arch/s390/kernel/machine_kexec_reloc.c b/arch/s390/kernel/machine_kexec_reloc.c
index 99e7951c199c..a77d7f72dd4a 100644
--- a/arch/s390/kernel/machine_kexec_reloc.c
+++ b/arch/s390/kernel/machine_kexec_reloc.c
@@ -27,6 +27,7 @@ int arch_kexec_do_relocs(int r_type, void *loc, unsigned long val,
 		break;
 	case R_390_64:		/* Direct 64 bit.  */
 	case R_390_GLOB_DAT:
+	case R_390_JMP_SLOT:
 		*(u64 *)loc = val;
 		break;
 	case R_390_PC16:	/* PC relative 16 bit.	*/
diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S
index 9e1660a6b9db..f942341429b1 100644
--- a/arch/s390/kernel/mcount.S
+++ b/arch/s390/kernel/mcount.S
@@ -26,6 +26,12 @@ ENDPROC(ftrace_stub)
 #define STACK_PTREGS	  (STACK_FRAME_OVERHEAD)
 #define STACK_PTREGS_GPRS (STACK_PTREGS + __PT_GPRS)
 #define STACK_PTREGS_PSW  (STACK_PTREGS + __PT_PSW)
+#ifdef __PACK_STACK
+/* allocate just enough for r14, r15 and backchain */
+#define TRACED_FUNC_FRAME_SIZE	24
+#else
+#define TRACED_FUNC_FRAME_SIZE	STACK_FRAME_OVERHEAD
+#endif
 
 ENTRY(_mcount)
 	BR_EX	%r14
@@ -35,13 +41,21 @@ EXPORT_SYMBOL(_mcount)
 ENTRY(ftrace_caller)
 	.globl	ftrace_regs_caller
 	.set	ftrace_regs_caller,ftrace_caller
+	stg	%r14,(__SF_GPRS+8*8)(%r15)	# save traced function caller
 	lgr	%r1,%r15
 #if !(defined(CC_USING_HOTPATCH) || defined(CC_USING_NOP_MCOUNT))
 	aghi	%r0,MCOUNT_RETURN_FIXUP
 #endif
-	aghi	%r15,-STACK_FRAME_SIZE
+	# allocate stack frame for ftrace_caller to contain traced function
+	aghi	%r15,-TRACED_FUNC_FRAME_SIZE
 	stg	%r1,__SF_BACKCHAIN(%r15)
+	stg	%r0,(__SF_GPRS+8*8)(%r15)
+	stg	%r15,(__SF_GPRS+9*8)(%r15)
+	# allocate pt_regs and stack frame for ftrace_trace_function
+	aghi	%r15,-STACK_FRAME_SIZE
 	stg	%r1,(STACK_PTREGS_GPRS+15*8)(%r15)
+	aghi	%r1,-TRACED_FUNC_FRAME_SIZE
+	stg	%r1,__SF_BACKCHAIN(%r15)
 	stg	%r0,(STACK_PTREGS_PSW+8)(%r15)
 	stmg	%r2,%r14,(STACK_PTREGS_GPRS+2*8)(%r15)
 #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index de38fa5bbedf..20e07fdb3710 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -1261,18 +1261,28 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all)
 		 */
 		if (flush_all && done)
 			break;
-
-		/* If an event overflow happened, discard samples by
-		 * processing any remaining sample-data-blocks.
-		 */
-		if (event_overflow)
-			flush_all = 1;
 	}
 
 	/* Account sample overflows in the event hardware structure */
 	if (sampl_overflow)
 		OVERFLOW_REG(hwc) = DIV_ROUND_UP(OVERFLOW_REG(hwc) +
 						 sampl_overflow, 1 + num_sdb);
+
+	/* Perf_event_overflow() and perf_event_account_interrupt() limit
+	 * the interrupt rate to an upper limit. Roughly 1000 samples per
+	 * task tick.
+	 * Hitting this limit results in a large number
+	 * of throttled REF_REPORT_THROTTLE entries and the samples
+	 * are dropped.
+	 * Slightly increase the interval to avoid hitting this limit.
+	 */
+	if (event_overflow) {
+		SAMPL_RATE(hwc) += DIV_ROUND_UP(SAMPL_RATE(hwc), 10);
+		debug_sprintf_event(sfdbg, 1, "%s: rate adjustment %ld\n",
+				    __func__,
+				    DIV_ROUND_UP(SAMPL_RATE(hwc), 10));
+	}
+
 	if (sampl_overflow || event_overflow)
 		debug_sprintf_event(sfdbg, 4, "hw_perf_event_update: "
 				    "overflow stats: sample=%llu event=%llu\n",
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 9f2727bf3cbe..e72b1cde227d 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -105,6 +105,7 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long new_stackp,
 	p->thread.system_timer = 0;
 	p->thread.hardirq_timer = 0;
 	p->thread.softirq_timer = 0;
+	p->thread.last_break = 1;
 
 	frame->sf.back_chain = 0;
 	/* new return point is ret_from_fork */
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 5de13307b703..28b6cddc7d07 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -158,8 +158,9 @@ static void show_cpu_mhz(struct seq_file *m, unsigned long n)
 static int show_cpuinfo(struct seq_file *m, void *v)
 {
 	unsigned long n = (unsigned long) v - 1;
+	unsigned long first = cpumask_first(cpu_online_mask);
 
-	if (!n)
+	if (n == first)
 		show_cpu_summary(m, v);
 	if (!machine_has_cpu_mhz)
 		return 0;
@@ -172,6 +173,8 @@ static inline void *c_update(loff_t *pos)
 {
 	if (*pos)
 		*pos = cpumask_next(*pos - 1, cpu_online_mask);
+	else
+		*pos = cpumask_first(cpu_online_mask);
 	return *pos < nr_cpu_ids ? (void *)*pos + 1 : NULL;
 }
 
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index ad71132374f0..5aa786063eb3 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -324,6 +324,25 @@ static inline void __poke_user_per(struct task_struct *child,
 		child->thread.per_user.end = data;
 }
 
+static void fixup_int_code(struct task_struct *child, addr_t data)
+{
+	struct pt_regs *regs = task_pt_regs(child);
+	int ilc = regs->int_code >> 16;
+	u16 insn;
+
+	if (ilc > 6)
+		return;
+
+	if (ptrace_access_vm(child, regs->psw.addr - (regs->int_code >> 16),
+			&insn, sizeof(insn), FOLL_FORCE) != sizeof(insn))
+		return;
+
+	/* double check that tracee stopped on svc instruction */
+	if ((insn >> 8) != 0xa)
+		return;
+
+	regs->int_code = 0x20000 | (data & 0xffff);
+}
 /*
  * Write a word to the user area of a process at location addr. This
  * operation does have an additional problem compared to peek_user.
@@ -335,7 +354,9 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data)
 	struct user *dummy = NULL;
 	addr_t offset;
 
+
 	if (addr < (addr_t) &dummy->regs.acrs) {
+		struct pt_regs *regs = task_pt_regs(child);
 		/*
 		 * psw and gprs are stored on the stack
 		 */
@@ -353,7 +374,11 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data)
 				/* Invalid addressing mode bits */
 				return -EINVAL;
 		}
-		*(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data;
+
+		if (test_pt_regs_flag(regs, PIF_SYSCALL) &&
+			addr == offsetof(struct user, regs.gprs[2]))
+			fixup_int_code(child, data);
+		*(addr_t *)((addr_t) &regs->psw + addr) = data;
 
 	} else if (addr < (addr_t) (&dummy->regs.orig_gpr2)) {
 		/*
@@ -719,6 +744,10 @@ static int __poke_user_compat(struct task_struct *child,
 			regs->psw.mask = (regs->psw.mask & ~PSW_MASK_BA) |
 				(__u64)(tmp & PSW32_ADDR_AMODE);
 		} else {
+
+			if (test_pt_regs_flag(regs, PIF_SYSCALL) &&
+				addr == offsetof(struct compat_user, regs.gprs[2]))
+				fixup_int_code(child, data);
 			/* gpr 0-15 */
 			*(__u32*)((addr_t) &regs->psw + addr*2 + 4) = tmp;
 		}
@@ -844,11 +873,9 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 	 * call number to gprs[2].
 	 */
 	if (test_thread_flag(TIF_SYSCALL_TRACE) &&
-	    (tracehook_report_syscall_entry(regs) ||
-	     regs->gprs[2] >= NR_syscalls)) {
+	    tracehook_report_syscall_entry(regs)) {
 		/*
-		 * Tracing decided this syscall should not happen or the
-		 * debugger stored an invalid system call number. Skip
+		 * Tracing decided this syscall should not happen. Skip
 		 * the system call and the system call restart handling.
 		 */
 		clear_pt_regs_flag(regs, PIF_SYSCALL);
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index f8544d517430..8fe09a672396 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -73,6 +73,7 @@
 #include <asm/nospec-branch.h>
 #include <asm/mem_detect.h>
 #include <asm/uv.h>
+#include <asm/asm-offsets.h>
 #include "entry.h"
 
 /*
@@ -467,6 +468,8 @@ static void __init setup_lowcore_dat_off(void)
 	arch_spin_lock_setup(0);
 #endif
 	lc->br_r1_trampoline = 0x07f1;	/* br %r1 */
+	lc->return_lpswe = gen_lpswe(__LC_RETURN_PSW);
+	lc->return_mcck_lpswe = gen_lpswe(__LC_RETURN_MCCK_PSW);
 
 	set_prefix((u32)(unsigned long) lc);
 	lowcore_ptr[0] = lc;
@@ -1066,7 +1069,7 @@ static void __init log_component_list(void)
 
 	if (!early_ipl_comp_list_addr)
 		return;
-	if (ipl_block.hdr.flags & IPL_PL_FLAG_IPLSR)
+	if (ipl_block.hdr.flags & IPL_PL_FLAG_SIPL)
 		pr_info("Linux is running with Secure-IPL enabled\n");
 	else
 		pr_info("Linux is running with Secure-IPL disabled\n");
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index fd742511985a..9760101e9d47 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -212,6 +212,8 @@ static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu)
 	lc->spinlock_lockval = arch_spin_lockval(cpu);
 	lc->spinlock_index = 0;
 	lc->br_r1_trampoline = 0x07f1;	/* br %r1 */
+	lc->return_lpswe = gen_lpswe(__LC_RETURN_PSW);
+	lc->return_mcck_lpswe = gen_lpswe(__LC_RETURN_MCCK_PSW);
 	if (nmi_alloc_per_cpu(lc))
 		goto out_async;
 	if (vdso_alloc_per_cpu(lc))
@@ -731,39 +733,67 @@ static void __ref smp_get_core_info(struct sclp_core_info *info, int early)
 
 static int smp_add_present_cpu(int cpu);
 
-static int __smp_rescan_cpus(struct sclp_core_info *info, int sysfs_add)
+static int smp_add_core(struct sclp_core_entry *core, cpumask_t *avail,
+			bool configured, bool early)
 {
 	struct pcpu *pcpu;
-	cpumask_t avail;
-	int cpu, nr, i, j;
+	int cpu, nr, i;
 	u16 address;
 
 	nr = 0;
-	cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask);
-	cpu = cpumask_first(&avail);
-	for (i = 0; (i < info->combined) && (cpu < nr_cpu_ids); i++) {
-		if (sclp.has_core_type && info->core[i].type != boot_core_type)
+	if (sclp.has_core_type && core->type != boot_core_type)
+		return nr;
+	cpu = cpumask_first(avail);
+	address = core->core_id << smp_cpu_mt_shift;
+	for (i = 0; (i <= smp_cpu_mtid) && (cpu < nr_cpu_ids); i++) {
+		if (pcpu_find_address(cpu_present_mask, address + i))
 			continue;
-		address = info->core[i].core_id << smp_cpu_mt_shift;
-		for (j = 0; j <= smp_cpu_mtid; j++) {
-			if (pcpu_find_address(cpu_present_mask, address + j))
-				continue;
-			pcpu = pcpu_devices + cpu;
-			pcpu->address = address + j;
-			pcpu->state =
-				(cpu >= info->configured*(smp_cpu_mtid + 1)) ?
-				CPU_STATE_STANDBY : CPU_STATE_CONFIGURED;
-			smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
-			set_cpu_present(cpu, true);
-			if (sysfs_add && smp_add_present_cpu(cpu) != 0)
-				set_cpu_present(cpu, false);
-			else
-				nr++;
-			cpu = cpumask_next(cpu, &avail);
-			if (cpu >= nr_cpu_ids)
+		pcpu = pcpu_devices + cpu;
+		pcpu->address = address + i;
+		if (configured)
+			pcpu->state = CPU_STATE_CONFIGURED;
+		else
+			pcpu->state = CPU_STATE_STANDBY;
+		smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
+		set_cpu_present(cpu, true);
+		if (!early && smp_add_present_cpu(cpu) != 0)
+			set_cpu_present(cpu, false);
+		else
+			nr++;
+		cpumask_clear_cpu(cpu, avail);
+		cpu = cpumask_next(cpu, avail);
+	}
+	return nr;
+}
+
+static int __smp_rescan_cpus(struct sclp_core_info *info, bool early)
+{
+	struct sclp_core_entry *core;
+	cpumask_t avail;
+	bool configured;
+	u16 core_id;
+	int nr, i;
+
+	nr = 0;
+	cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask);
+	/*
+	 * Add IPL core first (which got logical CPU number 0) to make sure
+	 * that all SMT threads get subsequent logical CPU numbers.
+	 */
+	if (early) {
+		core_id = pcpu_devices[0].address >> smp_cpu_mt_shift;
+		for (i = 0; i < info->configured; i++) {
+			core = &info->core[i];
+			if (core->core_id == core_id) {
+				nr += smp_add_core(core, &avail, true, early);
 				break;
+			}
 		}
 	}
+	for (i = 0; i < info->combined; i++) {
+		configured = i < info->configured;
+		nr += smp_add_core(&info->core[i], &avail, configured, early);
+	}
 	return nr;
 }
 
@@ -812,7 +842,7 @@ void __init smp_detect_cpus(void)
 
 	/* Add CPUs present at boot */
 	get_online_cpus();
-	__smp_rescan_cpus(info, 0);
+	__smp_rescan_cpus(info, true);
 	put_online_cpus();
 	memblock_free_early((unsigned long)info, sizeof(*info));
 }
@@ -1169,7 +1199,7 @@ int __ref smp_rescan_cpus(void)
 	smp_get_core_info(info, 0);
 	get_online_cpus();
 	mutex_lock(&smp_cpu_state_mutex);
-	nr = __smp_rescan_cpus(info, 1);
+	nr = __smp_rescan_cpus(info, false);
 	mutex_unlock(&smp_cpu_state_mutex);
 	put_online_cpus();
 	kfree(info);
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index e8766beee5ad..8ea9db599d38 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -310,6 +310,7 @@ void update_vsyscall(struct timekeeper *tk)
 
 	vdso_data->tk_mult = tk->tkr_mono.mult;
 	vdso_data->tk_shift = tk->tkr_mono.shift;
+	vdso_data->hrtimer_res = hrtimer_resolution;
 	smp_wmb();
 	++vdso_data->tb_update_count;
 }
diff --git a/arch/s390/kernel/unwind_bc.c b/arch/s390/kernel/unwind_bc.c
index 5cee3b8fe8e6..f515aa7cc9e5 100644
--- a/arch/s390/kernel/unwind_bc.c
+++ b/arch/s390/kernel/unwind_bc.c
@@ -50,14 +50,14 @@ bool unwind_next_frame(struct unwind_state *state)
 			sp = state->sp;
 			state->reuse_sp = false;
 		} else {
-			sp = READ_ONCE_TASK_STACK(state->task, regs->gprs[15]);
+			sp = READ_ONCE_NOCHECK(regs->gprs[15]);
 			if (unlikely(outside_of_stack(state, sp))) {
 				if (!update_stack_info(state, sp))
 					goto out_err;
 			}
 		}
 		sf = (struct stack_frame *) sp;
-		ip = READ_ONCE_TASK_STACK(state->task, sf->gprs[8]);
+		ip = READ_ONCE_NOCHECK(sf->gprs[8]);
 		reliable = false;
 		regs = NULL;
 		if (!__kernel_text_address(ip)) {
@@ -67,7 +67,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		}
 	} else {
 		sf = (struct stack_frame *) state->sp;
-		sp = READ_ONCE_TASK_STACK(state->task, sf->back_chain);
+		sp = READ_ONCE_NOCHECK(sf->back_chain);
 		if (likely(sp)) {
 			/* Non-zero back-chain points to the previous frame */
 			if (unlikely(outside_of_stack(state, sp))) {
@@ -75,7 +75,7 @@ bool unwind_next_frame(struct unwind_state *state)
 					goto out_err;
 			}
 			sf = (struct stack_frame *) sp;
-			ip = READ_ONCE_TASK_STACK(state->task, sf->gprs[8]);
+			ip = READ_ONCE_NOCHECK(sf->gprs[8]);
 			reliable = true;
 		} else {
 			/* No back-chain, look for a pt_regs structure */
@@ -83,9 +83,9 @@ bool unwind_next_frame(struct unwind_state *state)
 			if (!on_stack(info, sp, sizeof(struct pt_regs)))
 				goto out_stop;
 			regs = (struct pt_regs *) sp;
-			if (user_mode(regs))
+			if (READ_ONCE_NOCHECK(regs->psw.mask) & PSW_MASK_PSTATE)
 				goto out_stop;
-			ip = READ_ONCE_TASK_STACK(state->task, regs->psw.addr);
+			ip = READ_ONCE_NOCHECK(regs->psw.addr);
 			reliable = true;
 		}
 	}
@@ -142,12 +142,12 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 
 	/* Get the instruction pointer from pt_regs or the stack frame */
 	if (regs) {
-		ip = READ_ONCE_TASK_STACK(state->task, regs->psw.addr);
+		ip = READ_ONCE_NOCHECK(regs->psw.addr);
 		reliable = true;
 		reuse_sp = true;
 	} else {
 		sf = (struct stack_frame *) sp;
-		ip = READ_ONCE_TASK_STACK(state->task, sf->gprs[8]);
+		ip = READ_ONCE_NOCHECK(sf->gprs[8]);
 		reliable = false;
 		reuse_sp = false;
 	}
diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile
index bec19e7e6e1c..4a66a1cb919b 100644
--- a/arch/s390/kernel/vdso64/Makefile
+++ b/arch/s390/kernel/vdso64/Makefile
@@ -18,8 +18,8 @@ KBUILD_AFLAGS_64 += -m64 -s
 
 KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS))
 KBUILD_CFLAGS_64 += -m64 -fPIC -shared -fno-common -fno-builtin
-KBUILD_CFLAGS_64 += -nostdlib -Wl,-soname=linux-vdso64.so.1 \
-		    -Wl,--hash-style=both
+ldflags-y := -fPIC -shared -nostdlib -soname=linux-vdso64.so.1 \
+	     --hash-style=both --build-id -T
 
 $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64)
 $(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_64)
@@ -37,8 +37,8 @@ KASAN_SANITIZE := n
 $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so
 
 # link rule for the .so file, .lds has to be first
-$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) FORCE
-	$(call if_changed,vdso64ld)
+$(obj)/vdso64.so.dbg: $(obj)/vdso64.lds $(obj-vdso64) FORCE
+	$(call if_changed,ld)
 
 # strip rule for the .so file
 $(obj)/%.so: OBJCOPYFLAGS := -S
@@ -50,8 +50,6 @@ $(obj-vdso64): %.o: %.S FORCE
 	$(call if_changed_dep,vdso64as)
 
 # actual build commands
-quiet_cmd_vdso64ld = VDSO64L $@
-      cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $(filter %.lds %.o,$^) -o $@
 quiet_cmd_vdso64as = VDSO64A $@
       cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $<
 
diff --git a/arch/s390/kernel/vdso64/clock_getres.S b/arch/s390/kernel/vdso64/clock_getres.S
index 081435398e0a..0c79caa32b59 100644
--- a/arch/s390/kernel/vdso64/clock_getres.S
+++ b/arch/s390/kernel/vdso64/clock_getres.S
@@ -17,12 +17,14 @@
 	.type  __kernel_clock_getres,@function
 __kernel_clock_getres:
 	CFI_STARTPROC
-	larl	%r1,4f
+	larl	%r1,3f
+	lg	%r0,0(%r1)
 	cghi	%r2,__CLOCK_REALTIME_COARSE
 	je	0f
 	cghi	%r2,__CLOCK_MONOTONIC_COARSE
 	je	0f
-	larl	%r1,3f
+	larl	%r1,_vdso_data
+	llgf	%r0,__VDSO_CLOCK_REALTIME_RES(%r1)
 	cghi	%r2,__CLOCK_REALTIME
 	je	0f
 	cghi	%r2,__CLOCK_MONOTONIC
@@ -36,7 +38,6 @@ __kernel_clock_getres:
 	jz	2f
 0:	ltgr	%r3,%r3
 	jz	1f				/* res == NULL */
-	lg	%r0,0(%r1)
 	xc	0(8,%r3),0(%r3)			/* set tp->tv_sec to zero */
 	stg	%r0,8(%r3)			/* store tp->tv_usec */
 1:	lghi	%r2,0
@@ -45,6 +46,5 @@ __kernel_clock_getres:
 	svc	0
 	br	%r14
 	CFI_ENDPROC
-3:	.quad	__CLOCK_REALTIME_RES
-4:	.quad	__CLOCK_COARSE_RES
+3:	.quad	__CLOCK_COARSE_RES
 	.size	__kernel_clock_getres,.-__kernel_clock_getres
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 149525b5df1b..f5d3b8711e20 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -2208,7 +2208,7 @@ static int flic_ais_mode_get_all(struct kvm *kvm, struct kvm_device_attr *attr)
 		return -EINVAL;
 
 	if (!test_kvm_facility(kvm, 72))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	mutex_lock(&fi->ais_lock);
 	ais.simm = fi->simm;
@@ -2517,7 +2517,7 @@ static int modify_ais_mode(struct kvm *kvm, struct kvm_device_attr *attr)
 	int ret = 0;
 
 	if (!test_kvm_facility(kvm, 72))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	if (copy_from_user(&req, (void __user *)attr->addr, sizeof(req)))
 		return -EFAULT;
@@ -2597,7 +2597,7 @@ static int flic_ais_mode_set_all(struct kvm *kvm, struct kvm_device_attr *attr)
 	struct kvm_s390_ais_all ais;
 
 	if (!test_kvm_facility(kvm, 72))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	if (copy_from_user(&ais, (void __user *)attr->addr, sizeof(ais)))
 		return -EFAULT;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 681deaf9f20a..41455c6caae8 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1927,6 +1927,9 @@ static int gfn_to_memslot_approx(struct kvm_memslots *slots, gfn_t gfn)
 			start = slot + 1;
 	}
 
+	if (start >= slots->used_slots)
+		return slots->used_slots - 1;
+
 	if (gfn >= memslots[start].base_gfn &&
 	    gfn < memslots[start].base_gfn + memslots[start].npages) {
 		atomic_set(&slots->lru_slot, start);
@@ -2865,9 +2868,7 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 	vcpu->arch.sie_block->gcr[14] = CR14_UNUSED_32 |
 					CR14_UNUSED_33 |
 					CR14_EXTERNAL_DAMAGE_SUBMASK;
-	/* make sure the new fpc will be lazily loaded */
-	save_fpu_regs();
-	current->thread.fpu.fpc = 0;
+	vcpu->run->s.regs.fpc = 0;
 	vcpu->arch.sie_block->gbea = 1;
 	vcpu->arch.sie_block->pp = 0;
 	vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
@@ -4352,7 +4353,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	switch (ioctl) {
 	case KVM_S390_STORE_STATUS:
 		idx = srcu_read_lock(&vcpu->kvm->srcu);
-		r = kvm_s390_vcpu_store_status(vcpu, arg);
+		r = kvm_s390_store_status_unloaded(vcpu, arg);
 		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	case KVM_S390_SET_INITIAL_PSW: {
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index 076090f9e666..4f6c22d72072 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -1202,6 +1202,7 @@ static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 		scb_s->iprcc = PGM_ADDRESSING;
 		scb_s->pgmilc = 4;
 		scb_s->gpsw.addr = __rewind_psw(scb_s->gpsw, 4);
+		rc = 1;
 	}
 	return rc;
 }
diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c
index c4f8039a35e8..0267405ab7c6 100644
--- a/arch/s390/lib/uaccess.c
+++ b/arch/s390/lib/uaccess.c
@@ -64,10 +64,13 @@ mm_segment_t enable_sacf_uaccess(void)
 {
 	mm_segment_t old_fs;
 	unsigned long asce, cr;
+	unsigned long flags;
 
 	old_fs = current->thread.mm_segment;
 	if (old_fs & 1)
 		return old_fs;
+	/* protect against a concurrent page table upgrade */
+	local_irq_save(flags);
 	current->thread.mm_segment |= 1;
 	asce = S390_lowcore.kernel_asce;
 	if (likely(old_fs == USER_DS)) {
@@ -83,6 +86,7 @@ mm_segment_t enable_sacf_uaccess(void)
 		__ctl_load(asce, 7, 7);
 		set_cpu_flag(CIF_ASCE_SECONDARY);
 	}
+	local_irq_restore(flags);
 	return old_fs;
 }
 EXPORT_SYMBOL(enable_sacf_uaccess);
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 1e668b95e0c6..f41053055c6f 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -787,14 +787,18 @@ static void gmap_call_notifier(struct gmap *gmap, unsigned long start,
 static inline unsigned long *gmap_table_walk(struct gmap *gmap,
 					     unsigned long gaddr, int level)
 {
+	const int asce_type = gmap->asce & _ASCE_TYPE_MASK;
 	unsigned long *table;
 
 	if ((gmap->asce & _ASCE_TYPE_MASK) + 4 < (level * 4))
 		return NULL;
 	if (gmap_is_shadow(gmap) && gmap->removed)
 		return NULL;
-	if (gaddr & (-1UL << (31 + ((gmap->asce & _ASCE_TYPE_MASK) >> 2)*11)))
+
+	if (asce_type != _ASCE_TYPE_REGION1 &&
+	    gaddr & (-1UL << (31 + (asce_type >> 2) * 11)))
 		return NULL;
+
 	table = gmap->table;
 	switch (gmap->asce & _ASCE_TYPE_MASK) {
 	case _ASCE_TYPE_REGION1:
@@ -1840,6 +1844,7 @@ int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t,
 		goto out_free;
 	} else if (*table & _REGION_ENTRY_ORIGIN) {
 		rc = -EAGAIN;		/* Race with shadow */
+		goto out_free;
 	}
 	crst_table_init(s_r3t, _REGION3_ENTRY_EMPTY);
 	/* mark as invalid as long as the parent table is not protected */
@@ -2480,23 +2485,36 @@ void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long bitmap[4],
 }
 EXPORT_SYMBOL_GPL(gmap_sync_dirty_log_pmd);
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static int thp_split_walk_pmd_entry(pmd_t *pmd, unsigned long addr,
+				    unsigned long end, struct mm_walk *walk)
+{
+	struct vm_area_struct *vma = walk->vma;
+
+	split_huge_pmd(vma, pmd, addr);
+	return 0;
+}
+
+static const struct mm_walk_ops thp_split_walk_ops = {
+	.pmd_entry	= thp_split_walk_pmd_entry,
+};
+
 static inline void thp_split_mm(struct mm_struct *mm)
 {
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	struct vm_area_struct *vma;
-	unsigned long addr;
 
 	for (vma = mm->mmap; vma != NULL; vma = vma->vm_next) {
-		for (addr = vma->vm_start;
-		     addr < vma->vm_end;
-		     addr += PAGE_SIZE)
-			follow_page(vma, addr, FOLL_SPLIT);
 		vma->vm_flags &= ~VM_HUGEPAGE;
 		vma->vm_flags |= VM_NOHUGEPAGE;
+		walk_page_vma(vma, &thp_split_walk_ops, NULL);
 	}
 	mm->def_flags |= VM_NOHUGEPAGE;
-#endif
 }
+#else
+static inline void thp_split_mm(struct mm_struct *mm)
+{
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 /*
  * Remove all empty zero pages from the mapping for lazy refaulting
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index b0246c705a19..ff8234bca56c 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -2,7 +2,7 @@
 /*
  *  IBM System z Huge TLB Page Support for Kernel.
  *
- *    Copyright IBM Corp. 2007,2016
+ *    Copyright IBM Corp. 2007,2020
  *    Author(s): Gerald Schaefer <gerald.schaefer@de.ibm.com>
  */
 
@@ -11,6 +11,9 @@
 
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
+#include <linux/mman.h>
+#include <linux/sched/mm.h>
+#include <linux/security.h>
 
 /*
  * If the bit selected by single-bit bitmask "a" is set within "x", move
@@ -114,7 +117,7 @@ static inline pte_t __rste_to_pte(unsigned long rste)
 					     _PAGE_YOUNG);
 #ifdef CONFIG_MEM_SOFT_DIRTY
 		pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_SOFT_DIRTY,
-					     _PAGE_DIRTY);
+					     _PAGE_SOFT_DIRTY);
 #endif
 		pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_NOEXEC,
 					     _PAGE_NOEXEC);
@@ -156,10 +159,13 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		rste &= ~_SEGMENT_ENTRY_NOEXEC;
 
 	/* Set correct table type for 2G hugepages */
-	if ((pte_val(*ptep) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3)
-		rste |= _REGION_ENTRY_TYPE_R3 | _REGION3_ENTRY_LARGE;
-	else
+	if ((pte_val(*ptep) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3) {
+		if (likely(pte_present(pte)))
+			rste |= _REGION3_ENTRY_LARGE;
+		rste |= _REGION_ENTRY_TYPE_R3;
+	} else if (likely(pte_present(pte)))
 		rste |= _SEGMENT_ENTRY_LARGE;
+
 	clear_huge_pte_skeys(mm, rste);
 	pte_val(*ptep) = rste;
 }
@@ -267,3 +273,98 @@ static __init int setup_hugepagesz(char *opt)
 	return 1;
 }
 __setup("hugepagesz=", setup_hugepagesz);
+
+static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
+		unsigned long addr, unsigned long len,
+		unsigned long pgoff, unsigned long flags)
+{
+	struct hstate *h = hstate_file(file);
+	struct vm_unmapped_area_info info;
+
+	info.flags = 0;
+	info.length = len;
+	info.low_limit = current->mm->mmap_base;
+	info.high_limit = TASK_SIZE;
+	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
+	info.align_offset = 0;
+	return vm_unmapped_area(&info);
+}
+
+static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
+		unsigned long addr0, unsigned long len,
+		unsigned long pgoff, unsigned long flags)
+{
+	struct hstate *h = hstate_file(file);
+	struct vm_unmapped_area_info info;
+	unsigned long addr;
+
+	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
+	info.length = len;
+	info.low_limit = max(PAGE_SIZE, mmap_min_addr);
+	info.high_limit = current->mm->mmap_base;
+	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
+	info.align_offset = 0;
+	addr = vm_unmapped_area(&info);
+
+	/*
+	 * A failed mmap() very likely causes application failure,
+	 * so fall back to the bottom-up function here. This scenario
+	 * can happen with large stack limits and large mmap()
+	 * allocations.
+	 */
+	if (addr & ~PAGE_MASK) {
+		VM_BUG_ON(addr != -ENOMEM);
+		info.flags = 0;
+		info.low_limit = TASK_UNMAPPED_BASE;
+		info.high_limit = TASK_SIZE;
+		addr = vm_unmapped_area(&info);
+	}
+
+	return addr;
+}
+
+unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
+		unsigned long len, unsigned long pgoff, unsigned long flags)
+{
+	struct hstate *h = hstate_file(file);
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	int rc;
+
+	if (len & ~huge_page_mask(h))
+		return -EINVAL;
+	if (len > TASK_SIZE - mmap_min_addr)
+		return -ENOMEM;
+
+	if (flags & MAP_FIXED) {
+		if (prepare_hugepage_range(file, addr, len))
+			return -EINVAL;
+		goto check_asce_limit;
+	}
+
+	if (addr) {
+		addr = ALIGN(addr, huge_page_size(h));
+		vma = find_vma(mm, addr);
+		if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
+		    (!vma || addr + len <= vm_start_gap(vma)))
+			goto check_asce_limit;
+	}
+
+	if (mm->get_unmapped_area == arch_get_unmapped_area)
+		addr = hugetlb_get_unmapped_area_bottomup(file, addr, len,
+				pgoff, flags);
+	else
+		addr = hugetlb_get_unmapped_area_topdown(file, addr, len,
+				pgoff, flags);
+	if (addr & ~PAGE_MASK)
+		return addr;
+
+check_asce_limit:
+	if (addr + len > current->mm->context.asce_limit &&
+	    addr + len <= TASK_SIZE) {
+		rc = crst_table_upgrade(mm, addr + len);
+		if (rc)
+			return (unsigned long) rc;
+	}
+	return addr;
+}
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index 99e06213a22b..2b366abca8c1 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -72,8 +72,20 @@ static void __crst_table_upgrade(void *arg)
 {
 	struct mm_struct *mm = arg;
 
-	if (current->active_mm == mm)
-		set_user_asce(mm);
+	/* we must change all active ASCEs to avoid the creation of new TLBs */
+	if (current->active_mm == mm) {
+		S390_lowcore.user_asce = mm->context.asce;
+		if (current->thread.mm_segment == USER_DS) {
+			__ctl_load(S390_lowcore.user_asce, 1, 1);
+			/* Mark user-ASCE present in CR1 */
+			clear_cpu_flag(CIF_ASCE_PRIMARY);
+		}
+		if (current->thread.mm_segment == USER_DS_SACF) {
+			__ctl_load(S390_lowcore.user_asce, 7, 7);
+			/* enable_sacf_uaccess does all or nothing */
+			WARN_ON(!test_cpu_flag(CIF_ASCE_SECONDARY));
+		}
+	}
 	__tlb_flush_local();
 }
 
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index b403fa14847d..f810930aff42 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -415,6 +415,10 @@ void __init vmem_map_init(void)
 		     SET_MEMORY_RO | SET_MEMORY_X);
 	__set_memory(__stext_dma, (__etext_dma - __stext_dma) >> PAGE_SHIFT,
 		     SET_MEMORY_RO | SET_MEMORY_X);
+
+	/* we need lowcore executable for our LPSWE instructions */
+	set_memory_x(0, 1);
+
 	pr_info("Write protected kernel read-only data: %luk\n",
 		(unsigned long)(__end_rodata - _stext) >> 10);
 }
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 86ca7f88fb22..42f360fa8833 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -423,7 +423,7 @@ static void zpci_map_resources(struct pci_dev *pdev)
 
 		if (static_branch_likely(&have_mio))
 			pdev->resource[i].start =
-				(resource_size_t __force) zdev->bars[i].mio_wb;
+				(resource_size_t __force) zdev->bars[i].mio_wt;
 		else
 			pdev->resource[i].start =
 				(resource_size_t __force) pci_iomap(pdev, i, 0);
@@ -529,7 +529,7 @@ static int zpci_setup_bus_resources(struct zpci_dev *zdev,
 			flags |= IORESOURCE_MEM_64;
 
 		if (static_branch_likely(&have_mio))
-			addr = (unsigned long) zdev->bars[i].mio_wb;
+			addr = (unsigned long) zdev->bars[i].mio_wt;
 		else
 			addr = ZPCI_ADDR(entry);
 		size = 1UL << zdev->bars[i].size;
@@ -889,8 +889,10 @@ static int __init pci_base_init(void)
 	if (!test_facility(69) || !test_facility(71))
 		return 0;
 
-	if (test_facility(153) && !s390_pci_no_mio)
+	if (test_facility(153) && !s390_pci_no_mio) {
 		static_branch_enable(&have_mio);
+		ctl_set_bit(2, 5);
+	}
 
 	rc = zpci_debug_init();
 	if (rc)
@@ -931,5 +933,5 @@ subsys_initcall_sync(pci_base_init);
 void zpci_rescan(void)
 {
 	if (zpci_is_enabled())
-		clp_rescan_pci_devices_simple();
+		clp_rescan_pci_devices_simple(NULL);
 }
diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
index d03631dba7c2..64674b49d951 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -240,12 +240,14 @@ error:
 }
 
 /*
- * Enable/Disable a given PCI function defined by its function handle.
+ * Enable/Disable a given PCI function and update its function handle if
+ * necessary
  */
-static int clp_set_pci_fn(u32 *fh, u8 nr_dma_as, u8 command)
+static int clp_set_pci_fn(struct zpci_dev *zdev, u8 nr_dma_as, u8 command)
 {
 	struct clp_req_rsp_set_pci *rrb;
 	int rc, retries = 100;
+	u32 fid = zdev->fid;
 
 	rrb = clp_alloc_block(GFP_KERNEL);
 	if (!rrb)
@@ -256,7 +258,7 @@ static int clp_set_pci_fn(u32 *fh, u8 nr_dma_as, u8 command)
 		rrb->request.hdr.len = sizeof(rrb->request);
 		rrb->request.hdr.cmd = CLP_SET_PCI_FN;
 		rrb->response.hdr.len = sizeof(rrb->response);
-		rrb->request.fh = *fh;
+		rrb->request.fh = zdev->fh;
 		rrb->request.oc = command;
 		rrb->request.ndas = nr_dma_as;
 
@@ -269,12 +271,17 @@ static int clp_set_pci_fn(u32 *fh, u8 nr_dma_as, u8 command)
 		}
 	} while (rrb->response.hdr.rsp == CLP_RC_SETPCIFN_BUSY);
 
-	if (!rc && rrb->response.hdr.rsp == CLP_RC_OK)
-		*fh = rrb->response.fh;
-	else {
+	if (rc || rrb->response.hdr.rsp != CLP_RC_OK) {
 		zpci_err("Set PCI FN:\n");
 		zpci_err_clp(rrb->response.hdr.rsp, rc);
-		rc = -EIO;
+	}
+
+	if (!rc && rrb->response.hdr.rsp == CLP_RC_OK) {
+		zdev->fh = rrb->response.fh;
+	} else if (!rc && rrb->response.hdr.rsp == CLP_RC_SETPCIFN_ALRDY &&
+			rrb->response.fh == 0) {
+		/* Function is already in desired state - update handle */
+		rc = clp_rescan_pci_devices_simple(&fid);
 	}
 	clp_free_block(rrb);
 	return rc;
@@ -282,18 +289,17 @@ static int clp_set_pci_fn(u32 *fh, u8 nr_dma_as, u8 command)
 
 int clp_enable_fh(struct zpci_dev *zdev, u8 nr_dma_as)
 {
-	u32 fh = zdev->fh;
 	int rc;
 
-	rc = clp_set_pci_fn(&fh, nr_dma_as, CLP_SET_ENABLE_PCI_FN);
-	zpci_dbg(3, "ena fid:%x, fh:%x, rc:%d\n", zdev->fid, fh, rc);
+	rc = clp_set_pci_fn(zdev, nr_dma_as, CLP_SET_ENABLE_PCI_FN);
+	zpci_dbg(3, "ena fid:%x, fh:%x, rc:%d\n", zdev->fid, zdev->fh, rc);
 	if (rc)
 		goto out;
 
-	zdev->fh = fh;
 	if (zdev->mio_capable) {
-		rc = clp_set_pci_fn(&fh, nr_dma_as, CLP_SET_ENABLE_MIO);
-		zpci_dbg(3, "ena mio fid:%x, fh:%x, rc:%d\n", zdev->fid, fh, rc);
+		rc = clp_set_pci_fn(zdev, nr_dma_as, CLP_SET_ENABLE_MIO);
+		zpci_dbg(3, "ena mio fid:%x, fh:%x, rc:%d\n",
+				zdev->fid, zdev->fh, rc);
 		if (rc)
 			clp_disable_fh(zdev);
 	}
@@ -303,17 +309,13 @@ out:
 
 int clp_disable_fh(struct zpci_dev *zdev)
 {
-	u32 fh = zdev->fh;
 	int rc;
 
 	if (!zdev_enabled(zdev))
 		return 0;
 
-	rc = clp_set_pci_fn(&fh, 0, CLP_SET_DISABLE_PCI_FN);
-	zpci_dbg(3, "dis fid:%x, fh:%x, rc:%d\n", zdev->fid, fh, rc);
-	if (!rc)
-		zdev->fh = fh;
-
+	rc = clp_set_pci_fn(zdev, 0, CLP_SET_DISABLE_PCI_FN);
+	zpci_dbg(3, "dis fid:%x, fh:%x, rc:%d\n", zdev->fid, zdev->fh, rc);
 	return rc;
 }
 
@@ -370,10 +372,14 @@ static void __clp_add(struct clp_fh_list_entry *entry, void *data)
 static void __clp_update(struct clp_fh_list_entry *entry, void *data)
 {
 	struct zpci_dev *zdev;
+	u32 *fid = data;
 
 	if (!entry->vendor_id)
 		return;
 
+	if (fid && *fid != entry->fid)
+		return;
+
 	zdev = get_zdev_by_fid(entry->fid);
 	if (!zdev)
 		return;
@@ -413,7 +419,10 @@ int clp_rescan_pci_devices(void)
 	return rc;
 }
 
-int clp_rescan_pci_devices_simple(void)
+/* Rescan PCI functions and refresh function handles. If fid is non-NULL only
+ * refresh the handle of the function matching @fid
+ */
+int clp_rescan_pci_devices_simple(u32 *fid)
 {
 	struct clp_req_rsp_list_pci *rrb;
 	int rc;
@@ -422,7 +431,7 @@ int clp_rescan_pci_devices_simple(void)
 	if (!rrb)
 		return -ENOMEM;
 
-	rc = clp_list_pci(rrb, NULL, __clp_update);
+	rc = clp_list_pci(rrb, fid, __clp_update);
 
 	clp_free_block(rrb);
 	return rc;
diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c
index fbe97ab2e228..743f257cf2cb 100644
--- a/arch/s390/pci/pci_irq.c
+++ b/arch/s390/pci/pci_irq.c
@@ -115,7 +115,6 @@ static struct irq_chip zpci_irq_chip = {
 	.name = "PCI-MSI",
 	.irq_unmask = pci_msi_unmask_irq,
 	.irq_mask = pci_msi_mask_irq,
-	.irq_set_affinity = zpci_set_irq_affinity,
 };
 
 static void zpci_handle_cpu_local_irq(bool rescan)
@@ -276,7 +275,9 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 		rc = -EIO;
 		if (hwirq - bit >= msi_vecs)
 			break;
-		irq = __irq_alloc_descs(-1, 0, 1, 0, THIS_MODULE, msi->affinity);
+		irq = __irq_alloc_descs(-1, 0, 1, 0, THIS_MODULE,
+				(irq_delivery == DIRECTED) ?
+				msi->affinity : NULL);
 		if (irq < 0)
 			return -ENOMEM;
 		rc = irq_set_msi_desc(irq, msi);
diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c
index 7d42a8794f10..020a2c514d96 100644
--- a/arch/s390/pci/pci_mmio.c
+++ b/arch/s390/pci/pci_mmio.c
@@ -11,6 +11,113 @@
 #include <linux/mm.h>
 #include <linux/errno.h>
 #include <linux/pci.h>
+#include <asm/pci_io.h>
+#include <asm/pci_debug.h>
+
+static inline void zpci_err_mmio(u8 cc, u8 status, u64 offset)
+{
+	struct {
+		u64 offset;
+		u8 cc;
+		u8 status;
+	} data = {offset, cc, status};
+
+	zpci_err_hex(&data, sizeof(data));
+}
+
+static inline int __pcistb_mio_inuser(
+		void __iomem *ioaddr, const void __user *src,
+		u64 len, u8 *status)
+{
+	int cc = -ENXIO;
+
+	asm volatile (
+		"       sacf 256\n"
+		"0:     .insn   rsy,0xeb00000000d4,%[len],%[ioaddr],%[src]\n"
+		"1:     ipm     %[cc]\n"
+		"       srl     %[cc],28\n"
+		"2:     sacf 768\n"
+		EX_TABLE(0b, 2b) EX_TABLE(1b, 2b)
+		: [cc] "+d" (cc), [len] "+d" (len)
+		: [ioaddr] "a" (ioaddr), [src] "Q" (*((u8 __force *)src))
+		: "cc", "memory");
+	*status = len >> 24 & 0xff;
+	return cc;
+}
+
+static inline int __pcistg_mio_inuser(
+		void __iomem *ioaddr, const void __user *src,
+		u64 ulen, u8 *status)
+{
+	register u64 addr asm("2") = (u64 __force) ioaddr;
+	register u64 len asm("3") = ulen;
+	int cc = -ENXIO;
+	u64 val = 0;
+	u64 cnt = ulen;
+	u8 tmp;
+
+	/*
+	 * copy 0 < @len <= 8 bytes from @src into the right most bytes of
+	 * a register, then store it to PCI at @ioaddr while in secondary
+	 * address space. pcistg then uses the user mappings.
+	 */
+	asm volatile (
+		"       sacf    256\n"
+		"0:     llgc    %[tmp],0(%[src])\n"
+		"       sllg    %[val],%[val],8\n"
+		"       aghi    %[src],1\n"
+		"       ogr     %[val],%[tmp]\n"
+		"       brctg   %[cnt],0b\n"
+		"1:     .insn   rre,0xb9d40000,%[val],%[ioaddr]\n"
+		"2:     ipm     %[cc]\n"
+		"       srl     %[cc],28\n"
+		"3:     sacf    768\n"
+		EX_TABLE(0b, 3b) EX_TABLE(1b, 3b) EX_TABLE(2b, 3b)
+		:
+		[src] "+a" (src), [cnt] "+d" (cnt),
+		[val] "+d" (val), [tmp] "=d" (tmp),
+		[len] "+d" (len), [cc] "+d" (cc),
+		[ioaddr] "+a" (addr)
+		:: "cc", "memory");
+	*status = len >> 24 & 0xff;
+
+	/* did we read everything from user memory? */
+	if (!cc && cnt != 0)
+		cc = -EFAULT;
+
+	return cc;
+}
+
+static inline int __memcpy_toio_inuser(void __iomem *dst,
+				   const void __user *src, size_t n)
+{
+	int size, rc = 0;
+	u8 status = 0;
+	mm_segment_t old_fs;
+
+	if (!src)
+		return -EINVAL;
+
+	old_fs = enable_sacf_uaccess();
+	while (n > 0) {
+		size = zpci_get_max_write_size((u64 __force) dst,
+					       (u64 __force) src, n,
+					       ZPCI_MAX_WRITE_SIZE);
+		if (size > 8) /* main path */
+			rc = __pcistb_mio_inuser(dst, src, size, &status);
+		else
+			rc = __pcistg_mio_inuser(dst, src, size, &status);
+		if (rc)
+			break;
+		src += size;
+		dst += size;
+		n -= size;
+	}
+	disable_sacf_uaccess(old_fs);
+	if (rc)
+		zpci_err_mmio(rc, status, (__force u64) dst);
+	return rc;
+}
 
 static long get_pfn(unsigned long user_addr, unsigned long access,
 		    unsigned long *pfn)
@@ -46,6 +153,20 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr,
 
 	if (length <= 0 || PAGE_SIZE - (mmio_addr & ~PAGE_MASK) < length)
 		return -EINVAL;
+
+	/*
+	 * Only support read access to MIO capable devices on a MIO enabled
+	 * system. Otherwise we would have to check for every address if it is
+	 * a special ZPCI_ADDR and we would have to do a get_pfn() which we
+	 * don't need for MIO capable devices.
+	 */
+	if (static_branch_likely(&have_mio)) {
+		ret = __memcpy_toio_inuser((void  __iomem *) mmio_addr,
+					user_buffer,
+					length);
+		return ret;
+	}
+
 	if (length > 64) {
 		buf = kmalloc(length, GFP_KERNEL);
 		if (!buf)
@@ -56,7 +177,8 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr,
 	ret = get_pfn(mmio_addr, VM_WRITE, &pfn);
 	if (ret)
 		goto out;
-	io_addr = (void __iomem *)((pfn << PAGE_SHIFT) | (mmio_addr & ~PAGE_MASK));
+	io_addr = (void __iomem *)((pfn << PAGE_SHIFT) |
+			(mmio_addr & ~PAGE_MASK));
 
 	ret = -EFAULT;
 	if ((unsigned long) io_addr < ZPCI_IOMAP_ADDR_BASE)
@@ -72,6 +194,78 @@ out:
 	return ret;
 }
 
+static inline int __pcilg_mio_inuser(
+		void __user *dst, const void __iomem *ioaddr,
+		u64 ulen, u8 *status)
+{
+	register u64 addr asm("2") = (u64 __force) ioaddr;
+	register u64 len asm("3") = ulen;
+	u64 cnt = ulen;
+	int shift = ulen * 8;
+	int cc = -ENXIO;
+	u64 val, tmp;
+
+	/*
+	 * read 0 < @len <= 8 bytes from the PCI memory mapped at @ioaddr (in
+	 * user space) into a register using pcilg then store these bytes at
+	 * user address @dst
+	 */
+	asm volatile (
+		"       sacf    256\n"
+		"0:     .insn   rre,0xb9d60000,%[val],%[ioaddr]\n"
+		"1:     ipm     %[cc]\n"
+		"       srl     %[cc],28\n"
+		"       ltr     %[cc],%[cc]\n"
+		"       jne     4f\n"
+		"2:     ahi     %[shift],-8\n"
+		"       srlg    %[tmp],%[val],0(%[shift])\n"
+		"3:     stc     %[tmp],0(%[dst])\n"
+		"       aghi    %[dst],1\n"
+		"       brctg   %[cnt],2b\n"
+		"4:     sacf    768\n"
+		EX_TABLE(0b, 4b) EX_TABLE(1b, 4b) EX_TABLE(3b, 4b)
+		:
+		[cc] "+d" (cc), [val] "=d" (val), [len] "+d" (len),
+		[dst] "+a" (dst), [cnt] "+d" (cnt), [tmp] "=d" (tmp),
+		[shift] "+d" (shift)
+		:
+		[ioaddr] "a" (addr)
+		: "cc", "memory");
+
+	/* did we write everything to the user space buffer? */
+	if (!cc && cnt != 0)
+		cc = -EFAULT;
+
+	*status = len >> 24 & 0xff;
+	return cc;
+}
+
+static inline int __memcpy_fromio_inuser(void __user *dst,
+				     const void __iomem *src,
+				     unsigned long n)
+{
+	int size, rc = 0;
+	u8 status;
+	mm_segment_t old_fs;
+
+	old_fs = enable_sacf_uaccess();
+	while (n > 0) {
+		size = zpci_get_max_write_size((u64 __force) src,
+					       (u64 __force) dst, n,
+					       ZPCI_MAX_READ_SIZE);
+		rc = __pcilg_mio_inuser(dst, src, size, &status);
+		if (rc)
+			break;
+		src += size;
+		dst += size;
+		n -= size;
+	}
+	disable_sacf_uaccess(old_fs);
+	if (rc)
+		zpci_err_mmio(rc, status, (__force u64) dst);
+	return rc;
+}
+
 SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr,
 		void __user *, user_buffer, size_t, length)
 {
@@ -86,12 +280,27 @@ SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr,
 
 	if (length <= 0 || PAGE_SIZE - (mmio_addr & ~PAGE_MASK) < length)
 		return -EINVAL;
+
+	/*
+	 * Only support write access to MIO capable devices on a MIO enabled
+	 * system. Otherwise we would have to check for every address if it is
+	 * a special ZPCI_ADDR and we would have to do a get_pfn() which we
+	 * don't need for MIO capable devices.
+	 */
+	if (static_branch_likely(&have_mio)) {
+		ret = __memcpy_fromio_inuser(
+				user_buffer, (const void __iomem *)mmio_addr,
+				length);
+		return ret;
+	}
+
 	if (length > 64) {
 		buf = kmalloc(length, GFP_KERNEL);
 		if (!buf)
 			return -ENOMEM;
-	} else
+	} else {
 		buf = local_buf;
+	}
 
 	ret = get_pfn(mmio_addr, VM_READ, &pfn);
 	if (ret)
diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c
index 430c14b006d1..0e11fc023fe7 100644
--- a/arch/s390/pci/pci_sysfs.c
+++ b/arch/s390/pci/pci_sysfs.c
@@ -13,6 +13,8 @@
 #include <linux/stat.h>
 #include <linux/pci.h>
 
+#include "../../../drivers/pci/pci.h"
+
 #include <asm/sclp.h>
 
 #define zpci_attr(name, fmt, member)					\
@@ -40,31 +42,50 @@ zpci_attr(segment3, "0x%02x\n", pfip[3]);
 static ssize_t recover_store(struct device *dev, struct device_attribute *attr,
 			     const char *buf, size_t count)
 {
+	struct kernfs_node *kn;
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct zpci_dev *zdev = to_zpci(pdev);
-	int ret;
-
-	if (!device_remove_file_self(dev, attr))
-		return count;
-
+	int ret = 0;
+
+	/* Can't use device_remove_self() here as that would lead us to lock
+	 * the pci_rescan_remove_lock while holding the device' kernfs lock.
+	 * This would create a possible deadlock with disable_slot() which is
+	 * not directly protected by the device' kernfs lock but takes it
+	 * during the device removal which happens under
+	 * pci_rescan_remove_lock.
+	 *
+	 * This is analogous to sdev_store_delete() in
+	 * drivers/scsi/scsi_sysfs.c
+	 */
+	kn = sysfs_break_active_protection(&dev->kobj, &attr->attr);
+	WARN_ON_ONCE(!kn);
+	/* device_remove_file() serializes concurrent calls ignoring all but
+	 * the first
+	 */
+	device_remove_file(dev, attr);
+
+	/* A concurrent call to recover_store() may slip between
+	 * sysfs_break_active_protection() and the sysfs file removal.
+	 * Once it unblocks from pci_lock_rescan_remove() the original pdev
+	 * will already be removed.
+	 */
 	pci_lock_rescan_remove();
-	pci_stop_and_remove_bus_device(pdev);
-	ret = zpci_disable_device(zdev);
-	if (ret)
-		goto error;
-
-	ret = zpci_enable_device(zdev);
-	if (ret)
-		goto error;
-
-	pci_rescan_bus(zdev->bus);
+	if (pci_dev_is_added(pdev)) {
+		pci_stop_and_remove_bus_device(pdev);
+		ret = zpci_disable_device(zdev);
+		if (ret)
+			goto out;
+
+		ret = zpci_enable_device(zdev);
+		if (ret)
+			goto out;
+		pci_rescan_bus(zdev->bus);
+	}
+out:
 	pci_unlock_rescan_remove();
-
-	return count;
-
-error:
-	pci_unlock_rescan_remove();
-	return ret;
+	if (kn)
+		sysfs_unbreak_active_protection(kn);
+	return ret ? ret : count;
 }
 static DEVICE_ATTR_WO(recover);
 
diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile
index dc1ae4ff79d7..ff318acb3d77 100644
--- a/arch/s390/purgatory/Makefile
+++ b/arch/s390/purgatory/Makefile
@@ -13,8 +13,10 @@ $(obj)/sha256.o: $(srctree)/lib/sha256.c FORCE
 $(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S FORCE
 	$(call if_changed_rule,as_o_S)
 
-$(obj)/string.o: $(srctree)/arch/s390/lib/string.c FORCE
-	$(call if_changed_rule,cc_o_c)
+KCOV_INSTRUMENT := n
+GCOV_PROFILE := n
+UBSAN_SANITIZE := n
+KASAN_SANITIZE := n
 
 KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes
 KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare
diff --git a/arch/s390/purgatory/string.c b/arch/s390/purgatory/string.c
new file mode 100644
index 000000000000..c98c22a72db7
--- /dev/null
+++ b/arch/s390/purgatory/string.c
@@ -0,0 +1,3 @@
+// SPDX-License-Identifier: GPL-2.0
+#define __HAVE_ARCH_MEMCMP	/* arch function */
+#include "../lib/string.c"
diff --git a/arch/sh/boards/mach-landisk/setup.c b/arch/sh/boards/mach-landisk/setup.c
index 16b4d8b0bb85..2c44b94f82fb 100644
--- a/arch/sh/boards/mach-landisk/setup.c
+++ b/arch/sh/boards/mach-landisk/setup.c
@@ -82,6 +82,9 @@ device_initcall(landisk_devices_setup);
 
 static void __init landisk_setup(char **cmdline_p)
 {
+	/* I/O port identity mapping */
+	__set_io_port_base(0);
+
 	/* LED ON */
 	__raw_writeb(__raw_readb(PA_LED) | 0x03, PA_LED);
 
diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h
index b56f908b1395..c267035421f1 100644
--- a/arch/sh/include/asm/pgalloc.h
+++ b/arch/sh/include/asm/pgalloc.h
@@ -14,6 +14,7 @@ extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
 extern void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd);
 extern pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address);
 extern void pmd_free(struct mm_struct *mm, pmd_t *pmd);
+#define __pmd_free_tlb(tlb, pmdp, addr)		pmd_free((tlb)->mm, (pmdp))
 #endif
 
 static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
@@ -70,15 +71,6 @@ do {							\
 	tlb_remove_page((tlb), (pte));			\
 } while (0)
 
-#if CONFIG_PGTABLE_LEVELS > 2
-#define __pmd_free_tlb(tlb, pmdp, addr)			\
-do {							\
-	struct page *page = virt_to_page(pmdp);		\
-	pgtable_pmd_page_dtor(page);			\
-	tlb_remove_page((tlb), page);			\
-} while (0);
-#endif
-
 static inline void check_pgt_cache(void)
 {
 	quicklist_trim(QUICK_PT, NULL, 25, 16);
diff --git a/arch/sh/include/cpu-sh2a/cpu/sh7269.h b/arch/sh/include/cpu-sh2a/cpu/sh7269.h
index d516e5d48818..b887cc402b71 100644
--- a/arch/sh/include/cpu-sh2a/cpu/sh7269.h
+++ b/arch/sh/include/cpu-sh2a/cpu/sh7269.h
@@ -78,8 +78,15 @@ enum {
 	GPIO_FN_WDTOVF,
 
 	/* CAN */
-	GPIO_FN_CTX1, GPIO_FN_CRX1, GPIO_FN_CTX0, GPIO_FN_CTX0_CTX1,
-	GPIO_FN_CRX0, GPIO_FN_CRX0_CRX1, GPIO_FN_CRX0_CRX1_CRX2,
+	GPIO_FN_CTX2, GPIO_FN_CRX2,
+	GPIO_FN_CTX1, GPIO_FN_CRX1,
+	GPIO_FN_CTX0, GPIO_FN_CRX0,
+	GPIO_FN_CTX0_CTX1, GPIO_FN_CRX0_CRX1,
+	GPIO_FN_CTX0_CTX1_CTX2, GPIO_FN_CRX0_CRX1_CRX2,
+	GPIO_FN_CTX2_PJ21, GPIO_FN_CRX2_PJ20,
+	GPIO_FN_CTX1_PJ23, GPIO_FN_CRX1_PJ22,
+	GPIO_FN_CTX0_CTX1_PJ23, GPIO_FN_CRX0_CRX1_PJ22,
+	GPIO_FN_CTX0_CTX1_CTX2_PJ21, GPIO_FN_CRX0_CRX1_CRX2_PJ20,
 
 	/* DMAC */
 	GPIO_FN_TEND0, GPIO_FN_DACK0, GPIO_FN_DREQ0,
diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S
index d31f66e82ce5..4a8ec9e40cc2 100644
--- a/arch/sh/kernel/entry-common.S
+++ b/arch/sh/kernel/entry-common.S
@@ -199,7 +199,7 @@ syscall_trace_entry:
 	mov.l	@(OFF_R7,r15), r7   ! arg3
 	mov.l	@(OFF_R3,r15), r3   ! syscall_nr
 	!
-	mov.l	2f, r10			! Number of syscalls
+	mov.l	6f, r10			! Number of syscalls
 	cmp/hs	r10, r3
 	bf	syscall_call
 	mov	#-ENOSYS, r0
@@ -353,7 +353,7 @@ ENTRY(system_call)
 	tst	r9, r8
 	bf	syscall_trace_entry
 	!
-	mov.l	2f, r8			! Number of syscalls
+	mov.l	6f, r8			! Number of syscalls
 	cmp/hs	r8, r3
 	bt	syscall_badsys
 	!
@@ -392,7 +392,7 @@ syscall_exit:
 #if !defined(CONFIG_CPU_SH2)
 1:	.long	TRA
 #endif
-2:	.long	NR_syscalls
+6:	.long	NR_syscalls
 3:	.long	sys_call_table
 7:	.long	do_syscall_trace_enter
 8:	.long	do_syscall_trace_leave
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 26ab6f5bbaaf..4dcb8cd8f612 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -64,7 +64,6 @@ config SPARC64
 	select HAVE_KRETPROBES
 	select HAVE_KPROBES
 	select HAVE_RCU_TABLE_FREE if SMP
-	select HAVE_RCU_TABLE_NO_INVALIDATE if HAVE_RCU_TABLE_FREE
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select HAVE_DYNAMIC_FTRACE
diff --git a/arch/sparc/include/asm/tlb_64.h b/arch/sparc/include/asm/tlb_64.h
index a2f3fa61ee36..8cb8f3833239 100644
--- a/arch/sparc/include/asm/tlb_64.h
+++ b/arch/sparc/include/asm/tlb_64.h
@@ -28,6 +28,15 @@ void flush_tlb_pending(void);
 #define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
 #define tlb_flush(tlb)	flush_tlb_pending()
 
+/*
+ * SPARC64's hardware TLB fill does not use the Linux page-tables
+ * and therefore we don't need a TLBI when freeing page-table pages.
+ */
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+#define tlb_needs_table_invalidate()	(false)
+#endif
+
 #include <asm-generic/tlb.h>
 
 #endif /* _SPARC64_TLB_H */
diff --git a/arch/sparc/include/uapi/asm/ipcbuf.h b/arch/sparc/include/uapi/asm/ipcbuf.h
index 9d0d125500e2..084b8949ddff 100644
--- a/arch/sparc/include/uapi/asm/ipcbuf.h
+++ b/arch/sparc/include/uapi/asm/ipcbuf.h
@@ -15,19 +15,19 @@
 
 struct ipc64_perm
 {
-	__kernel_key_t	key;
-	__kernel_uid_t	uid;
-	__kernel_gid_t	gid;
-	__kernel_uid_t	cuid;
-	__kernel_gid_t	cgid;
+	__kernel_key_t		key;
+	__kernel_uid32_t	uid;
+	__kernel_gid32_t	gid;
+	__kernel_uid32_t	cuid;
+	__kernel_gid32_t	cgid;
 #ifndef __arch64__
-	unsigned short	__pad0;
+	unsigned short		__pad0;
 #endif
-	__kernel_mode_t	mode;
-	unsigned short	__pad1;
-	unsigned short	seq;
-	unsigned long long __unused1;
-	unsigned long long __unused2;
+	__kernel_mode_t		mode;
+	unsigned short		__pad1;
+	unsigned short		seq;
+	unsigned long long	__unused1;
+	unsigned long long	__unused2;
 };
 
 #endif /* __SPARC_IPCBUF_H */
diff --git a/arch/sparc/kernel/ptrace_32.c b/arch/sparc/kernel/ptrace_32.c
index 16b50afe7b52..646dd58169ec 100644
--- a/arch/sparc/kernel/ptrace_32.c
+++ b/arch/sparc/kernel/ptrace_32.c
@@ -46,82 +46,79 @@ enum sparc_regset {
 	REGSET_FP,
 };
 
+static int regwindow32_get(struct task_struct *target,
+			   const struct pt_regs *regs,
+			   u32 *uregs)
+{
+	unsigned long reg_window = regs->u_regs[UREG_I6];
+	int size = 16 * sizeof(u32);
+
+	if (target == current) {
+		if (copy_from_user(uregs, (void __user *)reg_window, size))
+			return -EFAULT;
+	} else {
+		if (access_process_vm(target, reg_window, uregs, size,
+				      FOLL_FORCE) != size)
+			return -EFAULT;
+	}
+	return 0;
+}
+
+static int regwindow32_set(struct task_struct *target,
+			   const struct pt_regs *regs,
+			   u32 *uregs)
+{
+	unsigned long reg_window = regs->u_regs[UREG_I6];
+	int size = 16 * sizeof(u32);
+
+	if (target == current) {
+		if (copy_to_user((void __user *)reg_window, uregs, size))
+			return -EFAULT;
+	} else {
+		if (access_process_vm(target, reg_window, uregs, size,
+				      FOLL_FORCE | FOLL_WRITE) != size)
+			return -EFAULT;
+	}
+	return 0;
+}
+
 static int genregs32_get(struct task_struct *target,
 			 const struct user_regset *regset,
 			 unsigned int pos, unsigned int count,
 			 void *kbuf, void __user *ubuf)
 {
 	const struct pt_regs *regs = target->thread.kregs;
-	unsigned long __user *reg_window;
-	unsigned long *k = kbuf;
-	unsigned long __user *u = ubuf;
-	unsigned long reg;
+	u32 uregs[16];
+	int ret;
 
 	if (target == current)
 		flush_user_windows();
 
-	pos /= sizeof(reg);
-	count /= sizeof(reg);
-
-	if (kbuf) {
-		for (; count > 0 && pos < 16; count--)
-			*k++ = regs->u_regs[pos++];
-
-		reg_window = (unsigned long __user *) regs->u_regs[UREG_I6];
-		reg_window -= 16;
-		for (; count > 0 && pos < 32; count--) {
-			if (get_user(*k++, &reg_window[pos++]))
-				return -EFAULT;
-		}
-	} else {
-		for (; count > 0 && pos < 16; count--) {
-			if (put_user(regs->u_regs[pos++], u++))
-				return -EFAULT;
-		}
-
-		reg_window = (unsigned long __user *) regs->u_regs[UREG_I6];
-		reg_window -= 16;
-		for (; count > 0 && pos < 32; count--) {
-			if (get_user(reg, &reg_window[pos++]) ||
-			    put_user(reg, u++))
-				return -EFAULT;
-		}
-	}
-	while (count > 0) {
-		switch (pos) {
-		case 32: /* PSR */
-			reg = regs->psr;
-			break;
-		case 33: /* PC */
-			reg = regs->pc;
-			break;
-		case 34: /* NPC */
-			reg = regs->npc;
-			break;
-		case 35: /* Y */
-			reg = regs->y;
-			break;
-		case 36: /* WIM */
-		case 37: /* TBR */
-			reg = 0;
-			break;
-		default:
-			goto finish;
-		}
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  regs->u_regs,
+				  0, 16 * sizeof(u32));
+	if (ret || !count)
+		return ret;
 
-		if (kbuf)
-			*k++ = reg;
-		else if (put_user(reg, u++))
+	if (pos < 32 * sizeof(u32)) {
+		if (regwindow32_get(target, regs, uregs))
 			return -EFAULT;
-		pos++;
-		count--;
+		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+					  uregs,
+					  16 * sizeof(u32), 32 * sizeof(u32));
+		if (ret || !count)
+			return ret;
 	}
-finish:
-	pos *= sizeof(reg);
-	count *= sizeof(reg);
 
-	return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
-					38 * sizeof(reg), -1);
+	uregs[0] = regs->psr;
+	uregs[1] = regs->pc;
+	uregs[2] = regs->npc;
+	uregs[3] = regs->y;
+	uregs[4] = 0;	/* WIM */
+	uregs[5] = 0;	/* TBR */
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  uregs,
+				  32 * sizeof(u32), 38 * sizeof(u32));
 }
 
 static int genregs32_set(struct task_struct *target,
@@ -130,82 +127,58 @@ static int genregs32_set(struct task_struct *target,
 			 const void *kbuf, const void __user *ubuf)
 {
 	struct pt_regs *regs = target->thread.kregs;
-	unsigned long __user *reg_window;
-	const unsigned long *k = kbuf;
-	const unsigned long __user *u = ubuf;
-	unsigned long reg;
+	u32 uregs[16];
+	u32 psr;
+	int ret;
 
 	if (target == current)
 		flush_user_windows();
 
-	pos /= sizeof(reg);
-	count /= sizeof(reg);
-
-	if (kbuf) {
-		for (; count > 0 && pos < 16; count--)
-			regs->u_regs[pos++] = *k++;
-
-		reg_window = (unsigned long __user *) regs->u_regs[UREG_I6];
-		reg_window -= 16;
-		for (; count > 0 && pos < 32; count--) {
-			if (put_user(*k++, &reg_window[pos++]))
-				return -EFAULT;
-		}
-	} else {
-		for (; count > 0 && pos < 16; count--) {
-			if (get_user(reg, u++))
-				return -EFAULT;
-			regs->u_regs[pos++] = reg;
-		}
-
-		reg_window = (unsigned long __user *) regs->u_regs[UREG_I6];
-		reg_window -= 16;
-		for (; count > 0 && pos < 32; count--) {
-			if (get_user(reg, u++) ||
-			    put_user(reg, &reg_window[pos++]))
-				return -EFAULT;
-		}
-	}
-	while (count > 0) {
-		unsigned long psr;
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 regs->u_regs,
+				 0, 16 * sizeof(u32));
+	if (ret || !count)
+		return ret;
 
-		if (kbuf)
-			reg = *k++;
-		else if (get_user(reg, u++))
+	if (pos < 32 * sizeof(u32)) {
+		if (regwindow32_get(target, regs, uregs))
 			return -EFAULT;
-
-		switch (pos) {
-		case 32: /* PSR */
-			psr = regs->psr;
-			psr &= ~(PSR_ICC | PSR_SYSCALL);
-			psr |= (reg & (PSR_ICC | PSR_SYSCALL));
-			regs->psr = psr;
-			break;
-		case 33: /* PC */
-			regs->pc = reg;
-			break;
-		case 34: /* NPC */
-			regs->npc = reg;
-			break;
-		case 35: /* Y */
-			regs->y = reg;
-			break;
-		case 36: /* WIM */
-		case 37: /* TBR */
-			break;
-		default:
-			goto finish;
-		}
-
-		pos++;
-		count--;
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+					 uregs,
+					 16 * sizeof(u32), 32 * sizeof(u32));
+		if (ret)
+			return ret;
+		if (regwindow32_set(target, regs, uregs))
+			return -EFAULT;
+		if (!count)
+			return 0;
 	}
-finish:
-	pos *= sizeof(reg);
-	count *= sizeof(reg);
-
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &psr,
+				 32 * sizeof(u32), 33 * sizeof(u32));
+	if (ret)
+		return ret;
+	regs->psr = (regs->psr & ~(PSR_ICC | PSR_SYSCALL)) |
+		    (psr & (PSR_ICC | PSR_SYSCALL));
+	if (!count)
+		return 0;
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &regs->pc,
+				 33 * sizeof(u32), 34 * sizeof(u32));
+	if (ret || !count)
+		return ret;
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &regs->npc,
+				 34 * sizeof(u32), 35 * sizeof(u32));
+	if (ret || !count)
+		return ret;
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &regs->y,
+				 35 * sizeof(u32), 36 * sizeof(u32));
+	if (ret || !count)
+		return ret;
 	return user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
-					 38 * sizeof(reg), -1);
+					 36 * sizeof(u32), 38 * sizeof(u32));
 }
 
 static int fpregs32_get(struct task_struct *target,
diff --git a/arch/sparc/kernel/ptrace_64.c b/arch/sparc/kernel/ptrace_64.c
index c9d41a96468f..3f5930bfab06 100644
--- a/arch/sparc/kernel/ptrace_64.c
+++ b/arch/sparc/kernel/ptrace_64.c
@@ -572,19 +572,13 @@ static int genregs32_get(struct task_struct *target,
 			for (; count > 0 && pos < 32; count--) {
 				if (access_process_vm(target,
 						      (unsigned long)
-						      &reg_window[pos],
+						      &reg_window[pos++],
 						      &reg, sizeof(reg),
 						      FOLL_FORCE)
 				    != sizeof(reg))
 					return -EFAULT;
-				if (access_process_vm(target,
-						      (unsigned long) u,
-						      &reg, sizeof(reg),
-						      FOLL_FORCE | FOLL_WRITE)
-				    != sizeof(reg))
+				if (put_user(reg, u++))
 					return -EFAULT;
-				pos++;
-				u++;
 			}
 		}
 	}
@@ -684,12 +678,7 @@ static int genregs32_set(struct task_struct *target,
 			}
 		} else {
 			for (; count > 0 && pos < 32; count--) {
-				if (access_process_vm(target,
-						      (unsigned long)
-						      u,
-						      &reg, sizeof(reg),
-						      FOLL_FORCE)
-				    != sizeof(reg))
+				if (get_user(reg, u++))
 					return -EFAULT;
 				if (access_process_vm(target,
 						      (unsigned long)
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index 61afd787bd0c..59b6df13ddea 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -172,12 +172,14 @@ SECTIONS
 	}
 	PERCPU_SECTION(SMP_CACHE_BYTES)
 
-#ifdef CONFIG_JUMP_LABEL
 	. = ALIGN(PAGE_SIZE);
 	.exit.text : {
 		EXIT_TEXT
 	}
-#endif
+
+	.exit.data : {
+		EXIT_DATA
+	}
 
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index aaebbc00d262..ae22398c3157 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -379,7 +379,6 @@ pgtable_t pte_alloc_one(struct mm_struct *mm)
 		return NULL;
 	page = pfn_to_page(__nocache_pa(pte) >> PAGE_SHIFT);
 	if (!pgtable_page_ctor(page)) {
-		__free_page(page);
 		return NULL;
 	}
 	return page;
diff --git a/arch/um/Makefile b/arch/um/Makefile
index 273130cf91d1..fcf9bf31c176 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -140,6 +140,7 @@ export CFLAGS_vmlinux := $(LINK-y) $(LINK_WRAPS) $(LD_FLAGS_CMDLINE)
 # When cleaning we don't include .config, so we don't include
 # TT or skas makefiles and don't clean skas_ptregs.h.
 CLEAN_FILES += linux x.i gmon.out
+MRPROPER_DIRS += arch/$(SUBARCH)/include/generated
 
 archclean:
 	@find . \( -name '*.bb' -o -name '*.bbg' -o -name '*.da' \
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 40ab9ad7aa96..d75ed5e1e5eb 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -1606,7 +1606,9 @@ int io_thread(void *arg)
 		written = 0;
 
 		do {
-			res = os_write_file(kernel_fd, ((char *) io_req_buffer) + written, n);
+			res = os_write_file(kernel_fd,
+					    ((char *) io_req_buffer) + written,
+					    n - written);
 			if (res >= 0) {
 				written += res;
 			}
diff --git a/arch/um/os-Linux/file.c b/arch/um/os-Linux/file.c
index f25b110d4e70..60bc6a1c7ae6 100644
--- a/arch/um/os-Linux/file.c
+++ b/arch/um/os-Linux/file.c
@@ -8,6 +8,7 @@
 #include <errno.h>
 #include <fcntl.h>
 #include <signal.h>
+#include <linux/falloc.h>
 #include <sys/ioctl.h>
 #include <sys/mount.h>
 #include <sys/socket.h>
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index e2839b5c246c..6539c50fb9aa 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -87,7 +87,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE
 
 SETUP_OBJS = $(addprefix $(obj)/,$(setup-y))
 
-sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p'
+sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p'
 
 quiet_cmd_zoffset = ZOFFSET $@
       cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@
diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c
index 15255f388a85..c4ff6580cfeb 100644
--- a/arch/x86/boot/compressed/acpi.c
+++ b/arch/x86/boot/compressed/acpi.c
@@ -386,7 +386,13 @@ int count_immovable_mem_regions(void)
 	table = table_addr + sizeof(struct acpi_table_srat);
 
 	while (table + sizeof(struct acpi_subtable_header) < table_end) {
+
 		sub_table = (struct acpi_subtable_header *)table;
+		if (!sub_table->length) {
+			debug_putstr("Invalid zero length SRAT subtable.\n");
+			return 0;
+		}
+
 		if (sub_table->type == ACPI_SRAT_TYPE_MEMORY_AFFINITY) {
 			struct acpi_srat_mem_affinity *ma;
 
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 37380c0d5999..c6c4b877f3d2 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -49,16 +49,17 @@
  * Position Independent Executable (PIE) so that linker won't optimize
  * R_386_GOT32X relocation to its fixed symbol address.  Older
  * linkers generate R_386_32 relocations against locally defined symbols,
- * _bss, _ebss, _got and _egot, in PIE.  It isn't wrong, just less
+ * _bss, _ebss, _got, _egot and _end, in PIE.  It isn't wrong, just less
  * optimal than R_386_RELATIVE.  But the x86 kernel fails to properly handle
  * R_386_32 relocations when relocating the kernel.  To generate
- * R_386_RELATIVE relocations, we mark _bss, _ebss, _got and _egot as
+ * R_386_RELATIVE relocations, we mark _bss, _ebss, _got, _egot and _end as
  * hidden:
  */
 	.hidden _bss
 	.hidden _ebss
 	.hidden _got
 	.hidden _egot
+	.hidden _end
 
 	__HEAD
 ENTRY(startup_32)
@@ -106,7 +107,7 @@ ENTRY(startup_32)
 	notl	%eax
 	andl    %eax, %ebx
 	cmpl	$LOAD_PHYSICAL_ADDR, %ebx
-	jge	1f
+	jae	1f
 #endif
 	movl	$LOAD_PHYSICAL_ADDR, %ebx
 1:
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index fafb75c6c592..0ad88e343ec5 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -42,6 +42,7 @@
 	.hidden _ebss
 	.hidden _got
 	.hidden _egot
+	.hidden _end
 
 	__HEAD
 	.code32
@@ -106,7 +107,7 @@ ENTRY(startup_32)
 	notl	%eax
 	andl	%eax, %ebx
 	cmpl	$LOAD_PHYSICAL_ADDR, %ebx
-	jge	1f
+	jae	1f
 #endif
 	movl	$LOAD_PHYSICAL_ADDR, %ebx
 1:
@@ -244,6 +245,11 @@ ENTRY(efi32_stub_entry)
 	leal	efi32_config(%ebp), %eax
 	movl	%eax, efi_config(%ebp)
 
+	/* Disable paging */
+	movl	%cr0, %eax
+	btrl	$X86_CR0_PG_BIT, %eax
+	movl	%eax, %cr0
+
 	jmp	startup_32
 ENDPROC(efi32_stub_entry)
 #endif
@@ -292,7 +298,7 @@ ENTRY(startup_64)
 	notq	%rax
 	andq	%rax, %rbp
 	cmpq	$LOAD_PHYSICAL_ADDR, %rbp
-	jge	1f
+	jae	1f
 #endif
 	movq	$LOAD_PHYSICAL_ADDR, %rbp
 1:
diff --git a/arch/x86/boot/compressed/kaslr_64.c b/arch/x86/boot/compressed/kaslr_64.c
index 748456c365f4..9557c5a15b91 100644
--- a/arch/x86/boot/compressed/kaslr_64.c
+++ b/arch/x86/boot/compressed/kaslr_64.c
@@ -29,9 +29,6 @@
 #define __PAGE_OFFSET __PAGE_OFFSET_BASE
 #include "../../mm/ident_map.c"
 
-/* Used by pgtable.h asm code to force instruction serialization. */
-unsigned long __force_order;
-
 /* Used to track our page table allocation area. */
 struct alloc_pgt_data {
 	unsigned char *pgt_buf;
diff --git a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
index 5f6a5af9c489..77043a82da51 100644
--- a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
+++ b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
@@ -127,10 +127,6 @@ ddq_add_8:
 
 /* generate a unique variable for ddq_add_x */
 
-.macro setddq n
-	var_ddq_add = ddq_add_\n
-.endm
-
 /* generate a unique variable for xmm register */
 .macro setxdata n
 	var_xdata = %xmm\n
@@ -140,9 +136,7 @@ ddq_add_8:
 
 .macro club name, id
 .altmacro
-	.if \name == DDQ_DATA
-		setddq %\id
-	.elseif \name == XDATA
+	.if \name == XDATA
 		setxdata %\id
 	.endif
 .noaltmacro
@@ -165,9 +159,8 @@ ddq_add_8:
 
 	.set i, 1
 	.rept (by - 1)
-		club DDQ_DATA, i
 		club XDATA, i
-		vpaddq	var_ddq_add(%rip), xcounter, var_xdata
+		vpaddq	(ddq_add_1 + 16 * (i - 1))(%rip), xcounter, var_xdata
 		vptest	ddq_low_msk(%rip), var_xdata
 		jnz 1f
 		vpaddq	ddq_high_add_1(%rip), var_xdata, var_xdata
@@ -180,8 +173,7 @@ ddq_add_8:
 	vmovdqa	1*16(p_keys), xkeyA
 
 	vpxor	xkey0, xdata0, xdata0
-	club DDQ_DATA, by
-	vpaddq	var_ddq_add(%rip), xcounter, xcounter
+	vpaddq	(ddq_add_1 + 16 * (by - 1))(%rip), xcounter, xcounter
 	vptest	ddq_low_msk(%rip), xcounter
 	jnz	1f
 	vpaddq	ddq_high_add_1(%rip), xcounter, xcounter
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index e40bdf024ba7..9afeb58c910e 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -266,7 +266,7 @@ ALL_F:      .octa 0xffffffffffffffffffffffffffffffff
 	PSHUFB_XMM %xmm2, %xmm0
 	movdqu %xmm0, CurCount(%arg2) # ctx_data.current_counter = iv
 
-	PRECOMPUTE \SUBKEY, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7,
+	PRECOMPUTE \SUBKEY, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7
 	movdqu HashKey(%arg2), %xmm13
 
 	CALC_AAD_HASH %xmm13, \AAD, \AADLEN, %xmm0, %xmm1, %xmm2, %xmm3, \
@@ -978,7 +978,7 @@ _initial_blocks_done\@:
 * arg1, %arg3, %arg4 are used as pointers only, not modified
 * %r11 is the data offset value
 */
-.macro GHASH_4_ENCRYPT_4_PARALLEL_ENC TMP1 TMP2 TMP3 TMP4 TMP5 \
+.macro GHASH_4_ENCRYPT_4_PARALLEL_enc TMP1 TMP2 TMP3 TMP4 TMP5 \
 TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 
 	movdqa	  \XMM1, \XMM5
@@ -1186,7 +1186,7 @@ aes_loop_par_enc_done\@:
 * arg1, %arg3, %arg4 are used as pointers only, not modified
 * %r11 is the data offset value
 */
-.macro GHASH_4_ENCRYPT_4_PARALLEL_DEC TMP1 TMP2 TMP3 TMP4 TMP5 \
+.macro GHASH_4_ENCRYPT_4_PARALLEL_dec TMP1 TMP2 TMP3 TMP4 TMP5 \
 TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
 
 	movdqa	  \XMM1, \XMM5
diff --git a/arch/x86/crypto/nhpoly1305-avx2-glue.c b/arch/x86/crypto/nhpoly1305-avx2-glue.c
index f7567cbd35b6..80fcb85736e1 100644
--- a/arch/x86/crypto/nhpoly1305-avx2-glue.c
+++ b/arch/x86/crypto/nhpoly1305-avx2-glue.c
@@ -29,7 +29,7 @@ static int nhpoly1305_avx2_update(struct shash_desc *desc,
 		return crypto_nhpoly1305_update(desc, src, srclen);
 
 	do {
-		unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE);
+		unsigned int n = min_t(unsigned int, srclen, SZ_4K);
 
 		kernel_fpu_begin();
 		crypto_nhpoly1305_update_helper(desc, src, n, _nh_avx2);
diff --git a/arch/x86/crypto/nhpoly1305-sse2-glue.c b/arch/x86/crypto/nhpoly1305-sse2-glue.c
index a661ede3b5cf..cc6b7c1a2705 100644
--- a/arch/x86/crypto/nhpoly1305-sse2-glue.c
+++ b/arch/x86/crypto/nhpoly1305-sse2-glue.c
@@ -29,7 +29,7 @@ static int nhpoly1305_sse2_update(struct shash_desc *desc,
 		return crypto_nhpoly1305_update(desc, src, srclen);
 
 	do {
-		unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE);
+		unsigned int n = min_t(unsigned int, srclen, SZ_4K);
 
 		kernel_fpu_begin();
 		crypto_nhpoly1305_update_helper(desc, src, n, _nh_sse2);
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 515c0ceeb4a3..b3f121478738 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -98,13 +98,6 @@ For 32-bit we have the following conventions - kernel is built with
 #define SIZEOF_PTREGS	21*8
 
 .macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0
-	/*
-	 * Push registers and sanitize registers of values that a
-	 * speculation attack might otherwise want to exploit. The
-	 * lower registers are likely clobbered well before they
-	 * could be put to use in a speculative execution gadget.
-	 * Interleave XOR with PUSH for better uop scheduling:
-	 */
 	.if \save_ret
 	pushq	%rsi		/* pt_regs->si */
 	movq	8(%rsp), %rsi	/* temporarily store the return address in %rsi */
@@ -114,34 +107,43 @@ For 32-bit we have the following conventions - kernel is built with
 	pushq   %rsi		/* pt_regs->si */
 	.endif
 	pushq	\rdx		/* pt_regs->dx */
-	xorl	%edx, %edx	/* nospec   dx */
 	pushq   %rcx		/* pt_regs->cx */
-	xorl	%ecx, %ecx	/* nospec   cx */
 	pushq   \rax		/* pt_regs->ax */
 	pushq   %r8		/* pt_regs->r8 */
-	xorl	%r8d, %r8d	/* nospec   r8 */
 	pushq   %r9		/* pt_regs->r9 */
-	xorl	%r9d, %r9d	/* nospec   r9 */
 	pushq   %r10		/* pt_regs->r10 */
-	xorl	%r10d, %r10d	/* nospec   r10 */
 	pushq   %r11		/* pt_regs->r11 */
-	xorl	%r11d, %r11d	/* nospec   r11*/
 	pushq	%rbx		/* pt_regs->rbx */
-	xorl    %ebx, %ebx	/* nospec   rbx*/
 	pushq	%rbp		/* pt_regs->rbp */
-	xorl    %ebp, %ebp	/* nospec   rbp*/
 	pushq	%r12		/* pt_regs->r12 */
-	xorl	%r12d, %r12d	/* nospec   r12*/
 	pushq	%r13		/* pt_regs->r13 */
-	xorl	%r13d, %r13d	/* nospec   r13*/
 	pushq	%r14		/* pt_regs->r14 */
-	xorl	%r14d, %r14d	/* nospec   r14*/
 	pushq	%r15		/* pt_regs->r15 */
-	xorl	%r15d, %r15d	/* nospec   r15*/
 	UNWIND_HINT_REGS
+
 	.if \save_ret
 	pushq	%rsi		/* return address on top of stack */
 	.endif
+
+	/*
+	 * Sanitize registers of values that a speculation attack might
+	 * otherwise want to exploit. The lower registers are likely clobbered
+	 * well before they could be put to use in a speculative execution
+	 * gadget.
+	 */
+	xorl	%edx,  %edx	/* nospec dx  */
+	xorl	%ecx,  %ecx	/* nospec cx  */
+	xorl	%r8d,  %r8d	/* nospec r8  */
+	xorl	%r9d,  %r9d	/* nospec r9  */
+	xorl	%r10d, %r10d	/* nospec r10 */
+	xorl	%r11d, %r11d	/* nospec r11 */
+	xorl	%ebx,  %ebx	/* nospec rbx */
+	xorl	%ebp,  %ebp	/* nospec rbp */
+	xorl	%r12d, %r12d	/* nospec r12 */
+	xorl	%r13d, %r13d	/* nospec r13 */
+	xorl	%r14d, %r14d	/* nospec r14 */
+	xorl	%r15d, %r15d	/* nospec r15 */
+
 .endm
 
 .macro POP_REGS pop_rdi=1 skip_r11rcx=0
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 2418804e66b4..73c216d73417 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -290,15 +290,16 @@ __visible void do_syscall_64(unsigned long nr, struct pt_regs *regs)
 	if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY)
 		nr = syscall_trace_enter(regs);
 
-	/*
-	 * NB: Native and x32 syscalls are dispatched from the same
-	 * table.  The only functional difference is the x32 bit in
-	 * regs->orig_ax, which changes the behavior of some syscalls.
-	 */
-	nr &= __SYSCALL_MASK;
 	if (likely(nr < NR_syscalls)) {
 		nr = array_index_nospec(nr, NR_syscalls);
 		regs->ax = sys_call_table[nr](regs);
+#ifdef CONFIG_X86_X32_ABI
+	} else if (likely((nr & __X32_SYSCALL_BIT) &&
+			  (nr & ~__X32_SYSCALL_BIT) < X32_NR_syscalls)) {
+		nr = array_index_nospec(nr & ~__X32_SYSCALL_BIT,
+					X32_NR_syscalls);
+		regs->ax = x32_sys_call_table[nr](regs);
+#endif
 	}
 
 	syscall_return_slowpath(regs);
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 1153e510cedd..e5530e74b738 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -1647,6 +1647,7 @@ ENTRY(int3)
 END(int3)
 
 ENTRY(general_protection)
+	ASM_CLAC
 	pushl	$do_general_protection
 	jmp	common_exception
 END(general_protection)
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 7d81e14b6226..b83feb7d9464 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -249,7 +249,6 @@ GLOBAL(entry_SYSCALL_64_after_hwframe)
 	 */
 syscall_return_via_sysret:
 	/* rcx and r11 are already restored (see code above) */
-	UNWIND_HINT_EMPTY
 	POP_REGS pop_rdi=0 skip_r11rcx=1
 
 	/*
@@ -258,6 +257,7 @@ syscall_return_via_sysret:
 	 */
 	movq	%rsp, %rdi
 	movq	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp
+	UNWIND_HINT_EMPTY
 
 	pushq	RSP-RDI(%rdi)	/* RSP */
 	pushq	(%rdi)		/* RDI */
@@ -512,7 +512,7 @@ END(spurious_entries_start)
  * +----------------------------------------------------+
  */
 ENTRY(interrupt_entry)
-	UNWIND_HINT_FUNC
+	UNWIND_HINT_IRET_REGS offset=16
 	ASM_CLAC
 	cld
 
@@ -544,9 +544,9 @@ ENTRY(interrupt_entry)
 	pushq	5*8(%rdi)		/* regs->eflags */
 	pushq	4*8(%rdi)		/* regs->cs */
 	pushq	3*8(%rdi)		/* regs->ip */
+	UNWIND_HINT_IRET_REGS
 	pushq	2*8(%rdi)		/* regs->orig_ax */
 	pushq	8(%rdi)			/* return address */
-	UNWIND_HINT_FUNC
 
 	movq	(%rdi), %rdi
 	jmp	2f
@@ -637,6 +637,7 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode)
 	 */
 	movq	%rsp, %rdi
 	movq	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp
+	UNWIND_HINT_EMPTY
 
 	/* Copy the IRET frame to the trampoline stack. */
 	pushq	6*8(%rdi)	/* SS */
@@ -1734,7 +1735,7 @@ ENTRY(rewind_stack_do_exit)
 
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rax
 	leaq	-PTREGS_SIZE(%rax), %rsp
-	UNWIND_HINT_FUNC sp_offset=PTREGS_SIZE
+	UNWIND_HINT_REGS
 
 	call	do_exit
 END(rewind_stack_do_exit)
diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c
index aa3336a7cb15..7d17b3addbbb 100644
--- a/arch/x86/entry/syscall_32.c
+++ b/arch/x86/entry/syscall_32.c
@@ -10,13 +10,11 @@
 #ifdef CONFIG_IA32_EMULATION
 /* On X86_64, we use struct pt_regs * to pass parameters to syscalls */
 #define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(const struct pt_regs *);
-
-/* this is a lie, but it does not hurt as sys_ni_syscall just returns -EINVAL */
-extern asmlinkage long sys_ni_syscall(const struct pt_regs *);
-
+#define __sys_ni_syscall __ia32_sys_ni_syscall
 #else /* CONFIG_IA32_EMULATION */
 #define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
 extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
+#define __sys_ni_syscall sys_ni_syscall
 #endif /* CONFIG_IA32_EMULATION */
 
 #include <asm/syscalls_32.h>
@@ -29,6 +27,6 @@ __visible const sys_call_ptr_t ia32_sys_call_table[__NR_syscall_compat_max+1] =
 	 * Smells like a compiler bug -- it doesn't work
 	 * when the & below is removed.
 	 */
-	[0 ... __NR_syscall_compat_max] = &sys_ni_syscall,
+	[0 ... __NR_syscall_compat_max] = &__sys_ni_syscall,
 #include <asm/syscalls_32.h>
 };
diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c
index d5252bc1e380..adf619a856e8 100644
--- a/arch/x86/entry/syscall_64.c
+++ b/arch/x86/entry/syscall_64.c
@@ -4,22 +4,53 @@
 #include <linux/linkage.h>
 #include <linux/sys.h>
 #include <linux/cache.h>
+#include <linux/syscalls.h>
 #include <asm/asm-offsets.h>
 #include <asm/syscall.h>
 
-/* this is a lie, but it does not hurt as sys_ni_syscall just returns -EINVAL */
-extern asmlinkage long sys_ni_syscall(const struct pt_regs *);
+extern asmlinkage long sys_ni_syscall(void);
+
+SYSCALL_DEFINE0(ni_syscall)
+{
+	return sys_ni_syscall();
+}
+
 #define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(const struct pt_regs *);
+#define __SYSCALL_X32(nr, sym, qual) __SYSCALL_64(nr, sym, qual)
 #include <asm/syscalls_64.h>
 #undef __SYSCALL_64
+#undef __SYSCALL_X32
 
 #define __SYSCALL_64(nr, sym, qual) [nr] = sym,
+#define __SYSCALL_X32(nr, sym, qual)
 
 asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = {
 	/*
 	 * Smells like a compiler bug -- it doesn't work
 	 * when the & below is removed.
 	 */
-	[0 ... __NR_syscall_max] = &sys_ni_syscall,
+	[0 ... __NR_syscall_max] = &__x64_sys_ni_syscall,
+#include <asm/syscalls_64.h>
+};
+
+#undef __SYSCALL_64
+#undef __SYSCALL_X32
+
+#ifdef CONFIG_X86_X32_ABI
+
+#define __SYSCALL_64(nr, sym, qual)
+#define __SYSCALL_X32(nr, sym, qual) [nr] = sym,
+
+asmlinkage const sys_call_ptr_t x32_sys_call_table[__NR_syscall_x32_max+1] = {
+	/*
+	 * Smells like a compiler bug -- it doesn't work
+	 * when the & below is removed.
+	 */
+	[0 ... __NR_syscall_x32_max] = &__x64_sys_ni_syscall,
 #include <asm/syscalls_64.h>
 };
+
+#undef __SYSCALL_64
+#undef __SYSCALL_X32
+
+#endif
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index ad968b7bac72..8e5a3cc5eba2 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -124,13 +124,13 @@
 110	i386	iopl			sys_iopl			__ia32_sys_iopl
 111	i386	vhangup			sys_vhangup			__ia32_sys_vhangup
 112	i386	idle
-113	i386	vm86old			sys_vm86old			sys_ni_syscall
+113	i386	vm86old			sys_vm86old			__ia32_sys_ni_syscall
 114	i386	wait4			sys_wait4			__ia32_compat_sys_wait4
 115	i386	swapoff			sys_swapoff			__ia32_sys_swapoff
 116	i386	sysinfo			sys_sysinfo			__ia32_compat_sys_sysinfo
 117	i386	ipc			sys_ipc				__ia32_compat_sys_ipc
 118	i386	fsync			sys_fsync			__ia32_sys_fsync
-119	i386	sigreturn		sys_sigreturn			sys32_sigreturn
+119	i386	sigreturn		sys_sigreturn			__ia32_compat_sys_sigreturn
 120	i386	clone			sys_clone			__ia32_compat_sys_x86_clone
 121	i386	setdomainname		sys_setdomainname		__ia32_sys_setdomainname
 122	i386	uname			sys_newuname			__ia32_sys_newuname
@@ -177,20 +177,20 @@
 163	i386	mremap			sys_mremap			__ia32_sys_mremap
 164	i386	setresuid		sys_setresuid16			__ia32_sys_setresuid16
 165	i386	getresuid		sys_getresuid16			__ia32_sys_getresuid16
-166	i386	vm86			sys_vm86			sys_ni_syscall
+166	i386	vm86			sys_vm86			__ia32_sys_ni_syscall
 167	i386	query_module
 168	i386	poll			sys_poll			__ia32_sys_poll
 169	i386	nfsservctl
 170	i386	setresgid		sys_setresgid16			__ia32_sys_setresgid16
 171	i386	getresgid		sys_getresgid16			__ia32_sys_getresgid16
 172	i386	prctl			sys_prctl			__ia32_sys_prctl
-173	i386	rt_sigreturn		sys_rt_sigreturn		sys32_rt_sigreturn
+173	i386	rt_sigreturn		sys_rt_sigreturn		__ia32_compat_sys_rt_sigreturn
 174	i386	rt_sigaction		sys_rt_sigaction		__ia32_compat_sys_rt_sigaction
-175	i386	rt_sigprocmask		sys_rt_sigprocmask		__ia32_sys_rt_sigprocmask
+175	i386	rt_sigprocmask		sys_rt_sigprocmask		__ia32_compat_sys_rt_sigprocmask
 176	i386	rt_sigpending		sys_rt_sigpending		__ia32_compat_sys_rt_sigpending
 177	i386	rt_sigtimedwait		sys_rt_sigtimedwait_time32	__ia32_compat_sys_rt_sigtimedwait_time32
 178	i386	rt_sigqueueinfo		sys_rt_sigqueueinfo		__ia32_compat_sys_rt_sigqueueinfo
-179	i386	rt_sigsuspend		sys_rt_sigsuspend		__ia32_sys_rt_sigsuspend
+179	i386	rt_sigsuspend		sys_rt_sigsuspend		__ia32_compat_sys_rt_sigsuspend
 180	i386	pread64			sys_pread64			__ia32_compat_sys_x86_pread
 181	i386	pwrite64		sys_pwrite64			__ia32_compat_sys_x86_pwrite
 182	i386	chown			sys_chown16			__ia32_sys_chown16
diff --git a/arch/x86/entry/syscalls/syscalltbl.sh b/arch/x86/entry/syscalls/syscalltbl.sh
index 94fcd1951aca..1af2be39e7d9 100644
--- a/arch/x86/entry/syscalls/syscalltbl.sh
+++ b/arch/x86/entry/syscalls/syscalltbl.sh
@@ -1,13 +1,13 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
 in="$1"
 out="$2"
 
 syscall_macro() {
-    abi="$1"
-    nr="$2"
-    entry="$3"
+    local abi="$1"
+    local nr="$2"
+    local entry="$3"
 
     # Entry can be either just a function name or "function/qualifier"
     real_entry="${entry%%/*}"
@@ -21,14 +21,14 @@ syscall_macro() {
 }
 
 emit() {
-    abi="$1"
-    nr="$2"
-    entry="$3"
-    compat="$4"
-    umlentry=""
+    local abi="$1"
+    local nr="$2"
+    local entry="$3"
+    local compat="$4"
+    local umlentry=""
 
-    if [ "$abi" = "64" -a -n "$compat" ]; then
-	echo "a compat entry for a 64-bit syscall makes no sense" >&2
+    if [ "$abi" != "I386" -a -n "$compat" ]; then
+	echo "a compat entry ($abi: $compat) for a 64-bit syscall makes no sense" >&2
 	exit 1
     fi
 
@@ -62,14 +62,17 @@ grep '^[0-9]' "$in" | sort -n | (
     while read nr abi name entry compat; do
 	abi=`echo "$abi" | tr '[a-z]' '[A-Z]'`
 	if [ "$abi" = "COMMON" -o "$abi" = "64" ]; then
-	    # COMMON is the same as 64, except that we don't expect X32
-	    # programs to use it.  Our expectation has nothing to do with
-	    # any generated code, so treat them the same.
 	    emit 64 "$nr" "$entry" "$compat"
+	    if [ "$abi" = "COMMON" ]; then
+		# COMMON means that this syscall exists in the same form for
+		# 64-bit and X32.
+		echo "#ifdef CONFIG_X86_X32_ABI"
+		emit X32 "$nr" "$entry" "$compat"
+		echo "#endif"
+	    fi
 	elif [ "$abi" = "X32" ]; then
-	    # X32 is equivalent to 64 on an X32-compatible kernel.
 	    echo "#ifdef CONFIG_X86_X32_ABI"
-	    emit 64 "$nr" "$entry" "$compat"
+	    emit X32 "$nr" "$entry" "$compat"
 	    echo "#endif"
 	elif [ "$abi" = "I386" ]; then
 	    emit "$abi" "$nr" "$entry" "$compat"
diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c
index 42d4c89f990e..ddff0ca6f509 100644
--- a/arch/x86/entry/vdso/vdso32-setup.c
+++ b/arch/x86/entry/vdso/vdso32-setup.c
@@ -11,6 +11,7 @@
 #include <linux/smp.h>
 #include <linux/kernel.h>
 #include <linux/mm_types.h>
+#include <linux/elf.h>
 
 #include <asm/processor.h>
 #include <asm/vdso.h>
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 64c3e70b0556..3ea8056148d8 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -246,6 +246,7 @@ static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] =
 	[PERF_COUNT_HW_CPU_CYCLES]		= 0x0076,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
 	[PERF_COUNT_HW_CACHE_REFERENCES]	= 0xff60,
+	[PERF_COUNT_HW_CACHE_MISSES]		= 0x0964,
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c2,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c3,
 	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= 0x0287,
@@ -301,6 +302,25 @@ static inline int amd_pmu_addr_offset(int index, bool eventsel)
 	return offset;
 }
 
+/*
+ * AMD64 events are detected based on their event codes.
+ */
+static inline unsigned int amd_get_event_code(struct hw_perf_event *hwc)
+{
+	return ((hwc->config >> 24) & 0x0f00) | (hwc->config & 0x00ff);
+}
+
+static inline bool amd_is_pair_event_code(struct hw_perf_event *hwc)
+{
+	if (!(x86_pmu.flags & PMU_FL_PAIR))
+		return false;
+
+	switch (amd_get_event_code(hwc)) {
+	case 0x003:	return true;	/* Retired SSE/AVX FLOPs */
+	default:	return false;
+	}
+}
+
 static int amd_core_hw_config(struct perf_event *event)
 {
 	if (event->attr.exclude_host && event->attr.exclude_guest)
@@ -319,14 +339,6 @@ static int amd_core_hw_config(struct perf_event *event)
 	return 0;
 }
 
-/*
- * AMD64 events are detected based on their event codes.
- */
-static inline unsigned int amd_get_event_code(struct hw_perf_event *hwc)
-{
-	return ((hwc->config >> 24) & 0x0f00) | (hwc->config & 0x00ff);
-}
-
 static inline int amd_is_nb_event(struct hw_perf_event *hwc)
 {
 	return (hwc->config & 0xe0) == 0xe0;
@@ -864,6 +876,20 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, int idx,
 	}
 }
 
+static struct event_constraint pair_constraint;
+
+static struct event_constraint *
+amd_get_event_constraints_f17h(struct cpu_hw_events *cpuc, int idx,
+			       struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (amd_is_pair_event_code(hwc))
+		return &pair_constraint;
+
+	return &unconstrained;
+}
+
 static ssize_t amd_event_sysfs_show(char *page, u64 config)
 {
 	u64 event = (config & ARCH_PERFMON_EVENTSEL_EVENT) |
@@ -907,33 +933,15 @@ static __initconst const struct x86_pmu amd_pmu = {
 
 static int __init amd_core_pmu_init(void)
 {
+	u64 even_ctr_mask = 0ULL;
+	int i;
+
 	if (!boot_cpu_has(X86_FEATURE_PERFCTR_CORE))
 		return 0;
 
-	/* Avoid calulating the value each time in the NMI handler */
+	/* Avoid calculating the value each time in the NMI handler */
 	perf_nmi_window = msecs_to_jiffies(100);
 
-	switch (boot_cpu_data.x86) {
-	case 0x15:
-		pr_cont("Fam15h ");
-		x86_pmu.get_event_constraints = amd_get_event_constraints_f15h;
-		break;
-	case 0x17:
-		pr_cont("Fam17h ");
-		/*
-		 * In family 17h, there are no event constraints in the PMC hardware.
-		 * We fallback to using default amd_get_event_constraints.
-		 */
-		break;
-	case 0x18:
-		pr_cont("Fam18h ");
-		/* Using default amd_get_event_constraints. */
-		break;
-	default:
-		pr_err("core perfctr but no constraints; unknown hardware!\n");
-		return -ENODEV;
-	}
-
 	/*
 	 * If core performance counter extensions exists, we must use
 	 * MSR_F15H_PERF_CTL/MSR_F15H_PERF_CTR msrs. See also
@@ -948,6 +956,30 @@ static int __init amd_core_pmu_init(void)
 	 */
 	x86_pmu.amd_nb_constraints = 0;
 
+	if (boot_cpu_data.x86 == 0x15) {
+		pr_cont("Fam15h ");
+		x86_pmu.get_event_constraints = amd_get_event_constraints_f15h;
+	}
+	if (boot_cpu_data.x86 >= 0x17) {
+		pr_cont("Fam17h+ ");
+		/*
+		 * Family 17h and compatibles have constraints for Large
+		 * Increment per Cycle events: they may only be assigned an
+		 * even numbered counter that has a consecutive adjacent odd
+		 * numbered counter following it.
+		 */
+		for (i = 0; i < x86_pmu.num_counters - 1; i += 2)
+			even_ctr_mask |= 1 << i;
+
+		pair_constraint = (struct event_constraint)
+				    __EVENT_CONSTRAINT(0, even_ctr_mask, 0,
+				    x86_pmu.num_counters / 2, 0,
+				    PERF_X86_EVENT_PAIR);
+
+		x86_pmu.get_event_constraints = amd_get_event_constraints_f17h;
+		x86_pmu.flags |= PMU_FL_PAIR;
+	}
+
 	pr_cont("core perfctr, ");
 	return 0;
 }
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index a6ea07f2aa84..4d867a752f0e 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -190,15 +190,12 @@ static int amd_uncore_event_init(struct perf_event *event)
 
 	/*
 	 * NB and Last level cache counters (MSRs) are shared across all cores
-	 * that share the same NB / Last level cache. Interrupts can be directed
-	 * to a single target core, however, event counts generated by processes
-	 * running on other cores cannot be masked out. So we do not support
-	 * sampling and per-thread events.
+	 * that share the same NB / Last level cache.  On family 16h and below,
+	 * Interrupts can be directed to a single target core, however, event
+	 * counts generated by processes running on other cores cannot be masked
+	 * out. So we do not support sampling and per-thread events via
+	 * CAP_NO_INTERRUPT, and we do not enable counter overflow interrupts:
 	 */
-	if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
-		return -EINVAL;
-
-	/* and we do not enable counter overflow interrupts */
 	hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB;
 	hwc->idx = -1;
 
@@ -306,7 +303,7 @@ static struct pmu amd_nb_pmu = {
 	.start		= amd_uncore_start,
 	.stop		= amd_uncore_stop,
 	.read		= amd_uncore_read,
-	.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
+	.capabilities	= PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
 };
 
 static struct pmu amd_llc_pmu = {
@@ -317,7 +314,7 @@ static struct pmu amd_llc_pmu = {
 	.start		= amd_uncore_start,
 	.stop		= amd_uncore_stop,
 	.read		= amd_uncore_read,
-	.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
+	.capabilities	= PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
 };
 
 static struct amd_uncore *amd_uncore_alloc(unsigned int cpu)
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 3cd94a21bd53..bfcb077503e6 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -375,7 +375,7 @@ int x86_add_exclusive(unsigned int what)
 	 * LBR and BTS are still mutually exclusive.
 	 */
 	if (x86_pmu.lbr_pt_coexist && what == x86_lbr_exclusive_pt)
-		return 0;
+		goto out;
 
 	if (!atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) {
 		mutex_lock(&pmc_reserve_mutex);
@@ -387,6 +387,7 @@ int x86_add_exclusive(unsigned int what)
 		mutex_unlock(&pmc_reserve_mutex);
 	}
 
+out:
 	atomic_inc(&active_events);
 	return 0;
 
@@ -397,11 +398,15 @@ fail_unlock:
 
 void x86_del_exclusive(unsigned int what)
 {
+	atomic_dec(&active_events);
+
+	/*
+	 * See the comment in x86_add_exclusive().
+	 */
 	if (x86_pmu.lbr_pt_coexist && what == x86_lbr_exclusive_pt)
 		return;
 
 	atomic_dec(&x86_pmu.lbr_exclusive[what]);
-	atomic_dec(&active_events);
 }
 
 int x86_setup_perfctr(struct perf_event *event)
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 5ee3fed881d3..741540d849f3 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -63,9 +63,17 @@ struct bts_buffer {
 
 static struct pmu bts_pmu;
 
+static int buf_nr_pages(struct page *page)
+{
+	if (!PagePrivate(page))
+		return 1;
+
+	return 1 << page_private(page);
+}
+
 static size_t buf_size(struct page *page)
 {
-	return 1 << (PAGE_SHIFT + page_private(page));
+	return buf_nr_pages(page) * PAGE_SIZE;
 }
 
 static void *
@@ -83,9 +91,7 @@ bts_buffer_setup_aux(struct perf_event *event, void **pages,
 	/* count all the high order buffers */
 	for (pg = 0, nbuf = 0; pg < nr_pages;) {
 		page = virt_to_page(pages[pg]);
-		if (WARN_ON_ONCE(!PagePrivate(page) && nr_pages > 1))
-			return NULL;
-		pg += 1 << page_private(page);
+		pg += buf_nr_pages(page);
 		nbuf++;
 	}
 
@@ -109,7 +115,7 @@ bts_buffer_setup_aux(struct perf_event *event, void **pages,
 		unsigned int __nr_pages;
 
 		page = virt_to_page(pages[pg]);
-		__nr_pages = PagePrivate(page) ? 1 << page_private(page) : 1;
+		__nr_pages = buf_nr_pages(page);
 		buf->buf[nbuf].page = page;
 		buf->buf[nbuf].offset = offset;
 		buf->buf[nbuf].displacement = (pad ? BTS_RECORD_SIZE - pad : 0);
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 2369ea1a1db7..512bf05751c6 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -1891,8 +1891,8 @@ static __initconst const u64 tnt_hw_cache_extra_regs
 
 static struct extra_reg intel_tnt_extra_regs[] __read_mostly = {
 	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
-	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0xffffff9fffull, RSP_0),
-	INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0xffffff9fffull, RSP_1),
+	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x800ff0ffffff9fffull, RSP_0),
+	INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0xff0ffffff9fffull, RSP_1),
 	EVENT_EXTRA_END
 };
 
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 6601b8759c92..4e52c51c402e 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1670,6 +1670,8 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count)
 	old = ((s64)(prev_raw_count << shift) >> shift);
 	local64_add(new - old + count * period, &event->count);
 
+	local64_set(&hwc->period_left, -new);
+
 	perf_event_update_userpage(event);
 
 	return 0;
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index f8431819b3e1..5c1da571a5aa 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -15,6 +15,7 @@
 #define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC	0x1910
 #define PCI_DEVICE_ID_INTEL_SKL_SD_IMC	0x190f
 #define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC	0x191f
+#define PCI_DEVICE_ID_INTEL_SKL_E3_IMC	0x1918
 #define PCI_DEVICE_ID_INTEL_KBL_Y_IMC	0x590c
 #define PCI_DEVICE_ID_INTEL_KBL_U_IMC	0x5904
 #define PCI_DEVICE_ID_INTEL_KBL_UQ_IMC	0x5914
@@ -662,6 +663,10 @@ static const struct pci_device_id skl_uncore_pci_ids[] = {
 		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
 	},
 	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_E3_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_Y_IMC),
 		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
 	},
@@ -802,6 +807,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
 	IMC_DEV(SKL_HQ_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core H Quad Core */
 	IMC_DEV(SKL_SD_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core S Dual Core */
 	IMC_DEV(SKL_SQ_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core S Quad Core */
+	IMC_DEV(SKL_E3_IMC, &skl_uncore_pci_driver),  /* Xeon E3 V5 Gen Core processor */
 	IMC_DEV(KBL_Y_IMC, &skl_uncore_pci_driver),  /* 7th Gen Core Y */
 	IMC_DEV(KBL_U_IMC, &skl_uncore_pci_driver),  /* 7th Gen Core U */
 	IMC_DEV(KBL_UQ_IMC, &skl_uncore_pci_driver),  /* 7th Gen Core U Quad Core */
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 4e346856ee19..134c89d815d7 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -76,6 +76,7 @@ static inline bool constraint_match(struct event_constraint *c, u64 ecode)
 #define PERF_X86_EVENT_EXCL_ACCT	0x0100 /* accounted EXCL event */
 #define PERF_X86_EVENT_AUTO_RELOAD	0x0200 /* use PEBS auto-reload */
 #define PERF_X86_EVENT_LARGE_PEBS	0x0400 /* use large PEBS */
+#define PERF_X86_EVENT_PAIR		0x1000 /* Large Increment per Cycle */
 
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
@@ -726,6 +727,7 @@ do {									\
 #define PMU_FL_EXCL_ENABLED	0x8 /* exclusive counter active */
 #define PMU_FL_PEBS_ALL		0x10 /* all events are valid PEBS events */
 #define PMU_FL_TFA		0x20 /* deal with TSX force abort */
+#define PMU_FL_PAIR		0x40 /* merge counters for large incr. events */
 
 #define EVENT_VAR(_id)  event_attr_##_id
 #define EVENT_PTR(_id) &event_attr_##_id.attr.attr
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index dd92d8b438d4..18c3c2bb17b0 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -20,6 +20,7 @@
 #include <linux/clockchips.h>
 #include <linux/hyperv.h>
 #include <linux/slab.h>
+#include <linux/kernel.h>
 #include <linux/cpuhotplug.h>
 
 #ifdef CONFIG_HYPERV_TSCPAGE
@@ -427,11 +428,14 @@ void hyperv_cleanup(void)
 }
 EXPORT_SYMBOL_GPL(hyperv_cleanup);
 
-void hyperv_report_panic(struct pt_regs *regs, long err)
+void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die)
 {
 	static bool panic_reported;
 	u64 guest_id;
 
+	if (in_die && !panic_on_oops)
+		return;
+
 	/*
 	 * We prefer to report panic on 'die' chain as we have proper
 	 * registers to report, but if we miss it (e.g. on BUG()) we need
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 629d1ee05599..08ee9e6da915 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -21,6 +21,7 @@
 #include <linux/personality.h>
 #include <linux/compat.h>
 #include <linux/binfmts.h>
+#include <linux/syscalls.h>
 #include <asm/ucontext.h>
 #include <linux/uaccess.h>
 #include <asm/fpu/internal.h>
@@ -118,7 +119,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
 	return err;
 }
 
-asmlinkage long sys32_sigreturn(void)
+COMPAT_SYSCALL_DEFINE0(sigreturn)
 {
 	struct pt_regs *regs = current_pt_regs();
 	struct sigframe_ia32 __user *frame = (struct sigframe_ia32 __user *)(regs->sp-8);
@@ -144,7 +145,7 @@ badframe:
 	return 0;
 }
 
-asmlinkage long sys32_rt_sigreturn(void)
+COMPAT_SYSCALL_DEFINE0(rt_sigreturn)
 {
 	struct pt_regs *regs = current_pt_regs();
 	struct rt_sigframe_ia32 __user *frame;
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 2e599384abd8..84402de885b9 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -53,7 +53,7 @@ extern int apic_verbosity;
 extern int local_apic_timer_c2_ok;
 
 extern int disable_apic;
-extern unsigned int lapic_timer_frequency;
+extern unsigned int lapic_timer_period;
 
 extern enum apic_intr_mode_id apic_intr_mode;
 enum apic_intr_mode_id {
@@ -448,6 +448,14 @@ static inline void ack_APIC_irq(void)
 	apic_eoi();
 }
 
+
+static inline bool lapic_vector_set_in_irr(unsigned int vector)
+{
+	u32 irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
+
+	return !!(irr & (1U << (vector % 32)));
+}
+
 static inline unsigned default_get_apic_id(unsigned long x)
 {
 	unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR));
diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h
index 31c379c1da41..0c814cd9ea42 100644
--- a/arch/x86/include/asm/cpu_device_id.h
+++ b/arch/x86/include/asm/cpu_device_id.h
@@ -9,6 +9,36 @@
 
 #include <linux/mod_devicetable.h>
 
+#define X86_CENTAUR_FAM6_C7_D		0xd
+#define X86_CENTAUR_FAM6_NANO		0xf
+
+#define X86_STEPPINGS(mins, maxs)    GENMASK(maxs, mins)
+
+/**
+ * X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE - Base macro for CPU matching
+ * @_vendor:	The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY
+ *		The name is expanded to X86_VENDOR_@_vendor
+ * @_family:	The family number or X86_FAMILY_ANY
+ * @_model:	The model number, model constant or X86_MODEL_ANY
+ * @_steppings:	Bitmask for steppings, stepping constant or X86_STEPPING_ANY
+ * @_feature:	A X86_FEATURE bit or X86_FEATURE_ANY
+ * @_data:	Driver specific data or NULL. The internal storage
+ *		format is unsigned long. The supplied value, pointer
+ *		etc. is casted to unsigned long internally.
+ *
+ * Backport version to keep the SRBDS pile consistant. No shorter variants
+ * required for this.
+ */
+#define X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(_vendor, _family, _model, \
+						    _steppings, _feature, _data) { \
+	.vendor		= X86_VENDOR_##_vendor,				\
+	.family		= _family,					\
+	.model		= _model,					\
+	.steppings	= _steppings,					\
+	.feature	= _feature,					\
+	.driver_data	= (unsigned long) _data				\
+}
+
 /*
  * Match specific microcode revisions.
  *
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 6086e00f4b97..463395d7a306 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -351,6 +351,7 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
 #define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_SRBDS_CTRL		(18*32+ 9) /* "" SRBDS mitigation MSR available */
 #define X86_FEATURE_MD_CLEAR		(18*32+10) /* VERW clears CPU buffers */
 #define X86_FEATURE_TSX_FORCE_ABORT	(18*32+13) /* "" TSX_FORCE_ABORT */
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
@@ -395,5 +396,6 @@
 #define X86_BUG_SWAPGS			X86_BUG(21) /* CPU is affected by speculation through SWAPGS */
 #define X86_BUG_TAA			X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */
 #define X86_BUG_ITLB_MULTIHIT		X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */
+#define X86_BUG_SRBDS			X86_BUG(24) /* CPU may leak RNG bits if not mitigated */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/dma.h b/arch/x86/include/asm/dma.h
index 00f7cf45e699..8e95aa4b0d17 100644
--- a/arch/x86/include/asm/dma.h
+++ b/arch/x86/include/asm/dma.h
@@ -74,7 +74,7 @@
 #define MAX_DMA_PFN   ((16UL * 1024 * 1024) >> PAGE_SHIFT)
 
 /* 4GB broken PCI/AGP hardware bus master zone */
-#define MAX_DMA32_PFN ((4UL * 1024 * 1024 * 1024) >> PAGE_SHIFT)
+#define MAX_DMA32_PFN (1UL << (32 - PAGE_SHIFT))
 
 #ifdef CONFIG_X86_32
 /* The maximum address that we can perform a DMA transfer to on this platform */
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 44c48e34d799..00eac7f1529b 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -619,6 +619,11 @@ static inline void switch_fpu_finish(struct fpu *new_fpu)
  * MXCSR and XCR definitions:
  */
 
+static inline void ldmxcsr(u32 mxcsr)
+{
+	asm volatile("ldmxcsr %0" :: "m" (mxcsr));
+}
+
 extern unsigned int mxcsr_feature_mask;
 
 #define XCR_XFEATURE_ENABLED_MASK	0x00000000
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 83350f210be9..c58b42c1011c 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -385,12 +385,12 @@ struct kvm_mmu {
 	void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root);
 	unsigned long (*get_cr3)(struct kvm_vcpu *vcpu);
 	u64 (*get_pdptr)(struct kvm_vcpu *vcpu, int index);
-	int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err,
+	int (*page_fault)(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 err,
 			  bool prefault);
 	void (*inject_page_fault)(struct kvm_vcpu *vcpu,
 				  struct x86_exception *fault);
-	gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva, u32 access,
-			    struct x86_exception *exception);
+	gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t gva_or_gpa,
+			    u32 access, struct x86_exception *exception);
 	gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
 			       struct x86_exception *exception);
 	int (*sync_page)(struct kvm_vcpu *vcpu,
@@ -555,6 +555,7 @@ struct kvm_vcpu_arch {
 	unsigned long cr4;
 	unsigned long cr4_guest_owned_bits;
 	unsigned long cr8;
+	u32 host_pkru;
 	u32 pkru;
 	u32 hflags;
 	u64 efer;
@@ -570,6 +571,7 @@ struct kvm_vcpu_arch {
 	u64 smbase;
 	u64 smi_count;
 	bool tpr_access_reporting;
+	bool xsaves_enabled;
 	u64 ia32_xss;
 	u64 microcode_version;
 	u64 arch_capabilities;
@@ -620,7 +622,7 @@ struct kvm_vcpu_arch {
 	 * "guest_fpu" state here contains the guest FPU context, with the
 	 * host PRKU bits.
 	 */
-	struct fpu user_fpu;
+	struct fpu *user_fpu;
 	struct fpu *guest_fpu;
 
 	u64 xcr0;
@@ -1094,7 +1096,7 @@ struct kvm_x86_ops {
 	void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
 	void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu);
 	void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa);
-	void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
+	int (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
 	int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu);
 	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
 	int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr);
@@ -1124,8 +1126,9 @@ struct kvm_x86_ops {
 	bool (*xsaves_supported)(void);
 	bool (*umip_emulated)(void);
 	bool (*pt_supported)(void);
+	bool (*pku_supported)(void);
 
-	int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr);
+	int (*check_nested_events)(struct kvm_vcpu *vcpu);
 	void (*request_immediate_exit)(struct kvm_vcpu *vcpu);
 
 	void (*sched_in)(struct kvm_vcpu *kvm, int cpu);
@@ -1154,7 +1157,7 @@ struct kvm_x86_ops {
 	void (*enable_log_dirty_pt_masked)(struct kvm *kvm,
 					   struct kvm_memory_slot *slot,
 					   gfn_t offset, unsigned long mask);
-	int (*write_log_dirty)(struct kvm_vcpu *vcpu);
+	int (*write_log_dirty)(struct kvm_vcpu *vcpu, gpa_t l2_gpa);
 
 	/* pmu operations of sub-arch */
 	const struct kvm_pmu_ops *pmu_ops;
@@ -1417,7 +1420,7 @@ void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu);
 
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
 
-int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u64 error_code,
+int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
 		       void *insn, int insn_len);
 void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
 void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid);
@@ -1585,8 +1588,8 @@ void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
 static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq)
 {
 	/* We can only post Fixed and LowPrio IRQs */
-	return (irq->delivery_mode == dest_Fixed ||
-		irq->delivery_mode == dest_LowestPrio);
+	return (irq->delivery_mode == APIC_DM_FIXED ||
+		irq->delivery_mode == APIC_DM_LOWEST);
 }
 
 static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h
index 209492849566..5c524d4f71cd 100644
--- a/arch/x86/include/asm/microcode_amd.h
+++ b/arch/x86/include/asm/microcode_amd.h
@@ -41,7 +41,7 @@ struct microcode_amd {
 	unsigned int			mpb[0];
 };
 
-#define PATCH_MAX_SIZE PAGE_SIZE
+#define PATCH_MAX_SIZE (3 * PAGE_SIZE)
 
 #ifdef CONFIG_MICROCODE_AMD
 extern void __init load_ucode_amd_bsp(unsigned int family);
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index cc60e617931c..ae44aa1f8a80 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -343,7 +343,7 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset,
 
 void __init hyperv_init(void);
 void hyperv_setup_mmu_ops(void);
-void hyperv_report_panic(struct pt_regs *regs, long err);
+void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die);
 void hyperv_report_panic_msg(phys_addr_t pa, size_t size);
 bool hv_is_hyperv_initialized(void);
 void hyperv_cleanup(void);
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index bae74871c017..e1c4bf0fa66c 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -110,6 +110,10 @@
 #define TSX_CTRL_RTM_DISABLE		BIT(0)	/* Disable RTM feature */
 #define TSX_CTRL_CPUID_CLEAR		BIT(1)	/* Disable TSX enumeration */
 
+/* SRBDS support */
+#define MSR_IA32_MCU_OPT_CTRL		0x00000123
+#define RNGDS_MITG_DIS			BIT(0)
+
 #define MSR_IA32_SYSENTER_CS		0x00000174
 #define MSR_IA32_SYSENTER_ESP		0x00000175
 #define MSR_IA32_SYSENTER_EIP		0x00000176
@@ -493,6 +497,8 @@
 #define MSR_K7_HWCR			0xc0010015
 #define MSR_K7_HWCR_SMMLOCK_BIT		0
 #define MSR_K7_HWCR_SMMLOCK		BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT)
+#define MSR_K7_HWCR_IRPERF_EN_BIT	30
+#define MSR_K7_HWCR_IRPERF_EN		BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT)
 #define MSR_K7_FID_VID_CTL		0xc0010041
 #define MSR_K7_FID_VID_STATUS		0xc0010042
 
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 75ded1d13d98..9d5d949e662e 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -41,7 +41,6 @@ struct nmiaction {
 	struct list_head	list;
 	nmi_handler_t		handler;
 	u64			max_duration;
-	struct irq_work		irq_work;
 	unsigned long		flags;
 	const char		*name;
 };
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 5e0509b41986..c8e859cdead7 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -253,6 +253,7 @@ static inline int pmd_large(pmd_t pte)
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+/* NOTE: when predicate huge page, consider also pmd_devmap, or use pmd_large */
 static inline int pmd_trans_huge(pmd_t pmd)
 {
 	return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE;
@@ -624,12 +625,15 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 	return __pmd(val);
 }
 
-/* mprotect needs to preserve PAT bits when updating vm_page_prot */
+/*
+ * mprotect needs to preserve PAT and encryption bits when updating
+ * vm_page_prot
+ */
 #define pgprot_modify pgprot_modify
 static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 {
 	pgprotval_t preservebits = pgprot_val(oldprot) & _PAGE_CHG_MASK;
-	pgprotval_t addbits = pgprot_val(newprot);
+	pgprotval_t addbits = pgprot_val(newprot) & ~_PAGE_CHG_MASK;
 	return __pgprot(preservebits | addbits);
 }
 
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index d6ff0bbdb394..9484b06291ec 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -124,7 +124,7 @@
  */
 #define _PAGE_CHG_MASK	(PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT |		\
 			 _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY |	\
-			 _PAGE_SOFT_DIRTY | _PAGE_DEVMAP)
+			 _PAGE_SOFT_DIRTY | _PAGE_DEVMAP | _PAGE_ENC)
 #define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE)
 
 /*
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 5024aa0f82a7..f9300c86d95d 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -331,7 +331,7 @@ struct x86_hw_tss {
 #define INVALID_IO_BITMAP_OFFSET	0x8000
 
 struct entry_stack {
-	unsigned long		words[64];
+	char	stack[PAGE_SIZE];
 };
 
 struct entry_stack_page {
diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index ae7b909dc242..75d298cbc780 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -93,28 +93,35 @@ void set_kernel_text_rw(void);
 void set_kernel_text_ro(void);
 
 #ifdef CONFIG_X86_64
-static inline int set_mce_nospec(unsigned long pfn)
+/*
+ * Prevent speculative access to the page by either unmapping
+ * it (if we do not require access to any part of the page) or
+ * marking it uncacheable (if we want to try to retrieve data
+ * from non-poisoned lines in the page).
+ */
+static inline int set_mce_nospec(unsigned long pfn, bool unmap)
 {
 	unsigned long decoy_addr;
 	int rc;
 
 	/*
-	 * Mark the linear address as UC to make sure we don't log more
-	 * errors because of speculative access to the page.
 	 * We would like to just call:
-	 *      set_memory_uc((unsigned long)pfn_to_kaddr(pfn), 1);
+	 *      set_memory_XX((unsigned long)pfn_to_kaddr(pfn), 1);
 	 * but doing that would radically increase the odds of a
 	 * speculative access to the poison page because we'd have
 	 * the virtual address of the kernel 1:1 mapping sitting
 	 * around in registers.
 	 * Instead we get tricky.  We create a non-canonical address
 	 * that looks just like the one we want, but has bit 63 flipped.
-	 * This relies on set_memory_uc() properly sanitizing any __pa()
+	 * This relies on set_memory_XX() properly sanitizing any __pa()
 	 * results with __PHYSICAL_MASK or PTE_PFN_MASK.
 	 */
 	decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63));
 
-	rc = set_memory_uc(decoy_addr, 1);
+	if (unmap)
+		rc = set_memory_np(decoy_addr, 1);
+	else
+		rc = set_memory_uc(decoy_addr, 1);
 	if (rc)
 		pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn);
 	return rc;
diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h
index 27c47d183f4b..8b58d6975d5d 100644
--- a/arch/x86/include/asm/smap.h
+++ b/arch/x86/include/asm/smap.h
@@ -57,8 +57,10 @@ static __always_inline unsigned long smap_save(void)
 {
 	unsigned long flags;
 
-	asm volatile (ALTERNATIVE("", "pushf; pop %0; " __ASM_CLAC,
-				  X86_FEATURE_SMAP)
+	asm volatile ("# smap_save\n\t"
+		      ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP)
+		      "pushf; pop %0; " __ASM_CLAC "\n\t"
+		      "1:"
 		      : "=rm" (flags) : : "memory", "cc");
 
 	return flags;
@@ -66,7 +68,10 @@ static __always_inline unsigned long smap_save(void)
 
 static __always_inline void smap_restore(unsigned long flags)
 {
-	asm volatile (ALTERNATIVE("", "push %0; popf", X86_FEATURE_SMAP)
+	asm volatile ("# smap_restore\n\t"
+		      ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP)
+		      "push %0; popf\n\t"
+		      "1:"
 		      : : "g" (flags) : "memory", "cc");
 }
 
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 91e29b6a86a5..9804a7957f4e 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -55,8 +55,13 @@
 /*
  * Initialize the stackprotector canary value.
  *
- * NOTE: this must only be called from functions that never return,
+ * NOTE: this must only be called from functions that never return
  * and it must always be inlined.
+ *
+ * In addition, it should be called from a compilation unit for which
+ * stack protector is disabled. Alternatively, the caller should not end
+ * with a function call which gets tail-call optimized as that would
+ * lead to checking a modified canary value.
  */
 static __always_inline void boot_init_stack_canary(void)
 {
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index 2dc4a021beea..8db3fdb6102e 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -36,6 +36,10 @@ extern const sys_call_ptr_t sys_call_table[];
 extern const sys_call_ptr_t ia32_sys_call_table[];
 #endif
 
+#ifdef CONFIG_X86_X32_ABI
+extern const sys_call_ptr_t x32_sys_call_table[];
+#endif
+
 /*
  * Only the low 32 bits of orig_ax are meaningful, so we return int.
  * This importantly ignores the high bits on 64-bit, so comparisons
diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h
index 90eb70df0b18..e2389ce9bf58 100644
--- a/arch/x86/include/asm/syscall_wrapper.h
+++ b/arch/x86/include/asm/syscall_wrapper.h
@@ -6,6 +6,8 @@
 #ifndef _ASM_X86_SYSCALL_WRAPPER_H
 #define _ASM_X86_SYSCALL_WRAPPER_H
 
+struct pt_regs;
+
 /* Mapping of registers to parameters for syscalls on x86-64 and x32 */
 #define SC_X86_64_REGS_TO_ARGS(x, ...)					\
 	__MAP(x,__SC_ARGS						\
@@ -28,13 +30,21 @@
  * kernel/sys_ni.c and SYS_NI in kernel/time/posix-stubs.c to cover this
  * case as well.
  */
+#define __IA32_COMPAT_SYS_STUB0(x, name)				\
+	asmlinkage long __ia32_compat_sys_##name(const struct pt_regs *regs);\
+	ALLOW_ERROR_INJECTION(__ia32_compat_sys_##name, ERRNO);		\
+	asmlinkage long __ia32_compat_sys_##name(const struct pt_regs *regs)\
+	{								\
+		return __se_compat_sys_##name();			\
+	}
+
 #define __IA32_COMPAT_SYS_STUBx(x, name, ...)				\
 	asmlinkage long __ia32_compat_sys##name(const struct pt_regs *regs);\
 	ALLOW_ERROR_INJECTION(__ia32_compat_sys##name, ERRNO);		\
 	asmlinkage long __ia32_compat_sys##name(const struct pt_regs *regs)\
 	{								\
 		return __se_compat_sys##name(SC_IA32_REGS_TO_ARGS(x,__VA_ARGS__));\
-	}								\
+	}
 
 #define __IA32_SYS_STUBx(x, name, ...)					\
 	asmlinkage long __ia32_sys##name(const struct pt_regs *regs);	\
@@ -56,9 +66,15 @@
 	SYSCALL_ALIAS(__ia32_sys_##sname, __x64_sys_##sname);		\
 	asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused)
 
-#define COND_SYSCALL(name)						\
-	cond_syscall(__x64_sys_##name);					\
-	cond_syscall(__ia32_sys_##name)
+#define COND_SYSCALL(name)							\
+	asmlinkage __weak long __x64_sys_##name(const struct pt_regs *__unused)	\
+	{									\
+		return sys_ni_syscall();					\
+	}									\
+	asmlinkage __weak long __ia32_sys_##name(const struct pt_regs *__unused)\
+	{									\
+		return sys_ni_syscall();					\
+	}
 
 #define SYS_NI(name)							\
 	SYSCALL_ALIAS(__x64_sys_##name, sys_ni_posix_timers);		\
@@ -76,15 +92,24 @@
  * of the x86-64-style parameter ordering of x32 syscalls. The syscalls common
  * with x86_64 obviously do not need such care.
  */
+#define __X32_COMPAT_SYS_STUB0(x, name, ...)				\
+	asmlinkage long __x32_compat_sys_##name(const struct pt_regs *regs);\
+	ALLOW_ERROR_INJECTION(__x32_compat_sys_##name, ERRNO);		\
+	asmlinkage long __x32_compat_sys_##name(const struct pt_regs *regs)\
+	{								\
+		return __se_compat_sys_##name();\
+	}
+
 #define __X32_COMPAT_SYS_STUBx(x, name, ...)				\
 	asmlinkage long __x32_compat_sys##name(const struct pt_regs *regs);\
 	ALLOW_ERROR_INJECTION(__x32_compat_sys##name, ERRNO);		\
 	asmlinkage long __x32_compat_sys##name(const struct pt_regs *regs)\
 	{								\
 		return __se_compat_sys##name(SC_X86_64_REGS_TO_ARGS(x,__VA_ARGS__));\
-	}								\
+	}
 
 #else /* CONFIG_X86_X32 */
+#define __X32_COMPAT_SYS_STUB0(x, name)
 #define __X32_COMPAT_SYS_STUBx(x, name, ...)
 #endif /* CONFIG_X86_X32 */
 
@@ -95,6 +120,17 @@
  * mapping of registers to parameters, we need to generate stubs for each
  * of them.
  */
+#define COMPAT_SYSCALL_DEFINE0(name)					\
+	static long __se_compat_sys_##name(void);			\
+	static inline long __do_compat_sys_##name(void);		\
+	__IA32_COMPAT_SYS_STUB0(x, name)				\
+	__X32_COMPAT_SYS_STUB0(x, name)					\
+	static long __se_compat_sys_##name(void)			\
+	{								\
+		return __do_compat_sys_##name();			\
+	}								\
+	static inline long __do_compat_sys_##name(void)
+
 #define COMPAT_SYSCALL_DEFINEx(x, name, ...)					\
 	static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__));	\
 	static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\
@@ -190,7 +226,11 @@
 #endif
 
 #ifndef COND_SYSCALL
-#define COND_SYSCALL(name) cond_syscall(__x64_sys_##name)
+#define COND_SYSCALL(name) 							\
+	asmlinkage __weak long __x64_sys_##name(const struct pt_regs *__unused)	\
+	{									\
+		return sys_ni_syscall();					\
+	}
 #endif
 
 #ifndef SYS_NI
@@ -202,7 +242,6 @@
  * For VSYSCALLS, we need to declare these three syscalls with the new
  * pt_regs-based calling convention for in-kernel use.
  */
-struct pt_regs;
 asmlinkage long __x64_sys_getcpu(const struct pt_regs *regs);
 asmlinkage long __x64_sys_gettimeofday(const struct pt_regs *regs);
 asmlinkage long __x64_sys_time(const struct pt_regs *regs);
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
index 146859efd83c..b923b8d333d4 100644
--- a/arch/x86/include/asm/unistd.h
+++ b/arch/x86/include/asm/unistd.h
@@ -5,12 +5,6 @@
 #include <uapi/asm/unistd.h>
 
 
-# ifdef CONFIG_X86_X32_ABI
-#  define __SYSCALL_MASK (~(__X32_SYSCALL_BIT))
-# else
-#  define __SYSCALL_MASK (~0)
-# endif
-
 # ifdef CONFIG_X86_32
 
 #  include <asm/unistd_32.h>
diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h
index 499578f7e6d7..70fc159ebe69 100644
--- a/arch/x86/include/asm/unwind.h
+++ b/arch/x86/include/asm/unwind.h
@@ -19,7 +19,7 @@ struct unwind_state {
 #if defined(CONFIG_UNWINDER_ORC)
 	bool signal, full_regs;
 	unsigned long sp, bp, ip;
-	struct pt_regs *regs;
+	struct pt_regs *regs, *prev_regs;
 #elif defined(CONFIG_UNWINDER_FRAME_POINTER)
 	bool got_irq;
 	unsigned long *bp, *orig_sp, ip;
diff --git a/arch/x86/include/uapi/asm/unistd.h b/arch/x86/include/uapi/asm/unistd.h
index 30d7d04d72d6..be5e2e747f50 100644
--- a/arch/x86/include/uapi/asm/unistd.h
+++ b/arch/x86/include/uapi/asm/unistd.h
@@ -2,7 +2,14 @@
 #ifndef _UAPI_ASM_X86_UNISTD_H
 #define _UAPI_ASM_X86_UNISTD_H
 
-/* x32 syscall flag bit */
+/*
+ * x32 syscall flag bit.  Some user programs expect syscall NR macros
+ * and __X32_SYSCALL_BIT to have type int, even though syscall numbers
+ * are, for practical purposes, unsigned long.
+ *
+ * Fortunately, expressions like (nr & ~__X32_SYSCALL_BIT) do the right
+ * thing regardless.
+ */
 #define __X32_SYSCALL_BIT	0x40000000
 
 #ifndef __KERNEL__
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 17b33ef604f3..ea019ba02942 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -1740,7 +1740,7 @@ int __acpi_acquire_global_lock(unsigned int *lock)
 		new = (((old & ~0x3) + 2) + ((old >> 1) & 0x1));
 		val = cmpxchg(lock, old, new);
 	} while (unlikely (val != old));
-	return (new < 3) ? -1 : 0;
+	return ((new & 0x3) < 3) ? -1 : 0;
 }
 
 int __acpi_release_global_lock(unsigned int *lock)
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index a5e5484988fd..a5d650a15d55 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -146,7 +146,8 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu,
 
 	/* Make sure we are running on right CPU */
 
-	retval = work_on_cpu(cpu, acpi_processor_ffh_cstate_probe_cpu, cx);
+	retval = call_on_cpu(cpu, acpi_processor_ffh_cstate_probe_cpu, cx,
+			     false);
 	if (retval == 0) {
 		/* Use the hint in CST */
 		percpu_entry->states[cx->index].eax = cx->address;
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 8c26b696d893..8e283685f471 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -18,10 +18,13 @@
 #define PCI_DEVICE_ID_AMD_17H_ROOT	0x1450
 #define PCI_DEVICE_ID_AMD_17H_M10H_ROOT	0x15d0
 #define PCI_DEVICE_ID_AMD_17H_M30H_ROOT	0x1480
+#define PCI_DEVICE_ID_AMD_17H_M60H_ROOT	0x1630
 #define PCI_DEVICE_ID_AMD_17H_DF_F4	0x1464
 #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec
 #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F4 0x1494
+#define PCI_DEVICE_ID_AMD_17H_M60H_DF_F4 0x144c
 #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F4 0x1444
+#define PCI_DEVICE_ID_AMD_19H_DF_F4	0x1654
 
 /* Protect the PCI config register pairs used for SMN and DF indirect access. */
 static DEFINE_MUTEX(smn_mutex);
@@ -32,6 +35,7 @@ static const struct pci_device_id amd_root_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_ROOT) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_ROOT) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_ROOT) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_ROOT) },
 	{}
 };
 
@@ -50,8 +54,10 @@ const struct pci_device_id amd_nb_misc_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F3) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_DF_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F3) },
 	{}
 };
 EXPORT_SYMBOL_GPL(amd_nb_misc_ids);
@@ -65,7 +71,9 @@ static const struct pci_device_id amd_nb_link_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F4) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_DF_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F4) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) },
 	{}
 };
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 142e7cfa8a3c..8dadfd73c5ad 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -195,7 +195,7 @@ static struct resource lapic_resource = {
 	.flags = IORESOURCE_MEM | IORESOURCE_BUSY,
 };
 
-unsigned int lapic_timer_frequency = 0;
+unsigned int lapic_timer_period = 0;
 
 static void apic_pm_activate(void);
 
@@ -352,8 +352,6 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
 		 * According to Intel, MFENCE can do the serialization here.
 		 */
 		asm volatile("mfence" : : : "memory");
-
-		printk_once(KERN_DEBUG "TSC deadline timer enabled\n");
 		return;
 	}
 
@@ -501,7 +499,7 @@ lapic_timer_set_periodic_oneshot(struct clock_event_device *evt, bool oneshot)
 	if (evt->features & CLOCK_EVT_FEAT_DUMMY)
 		return 0;
 
-	__setup_APIC_LVTT(lapic_timer_frequency, oneshot, 1);
+	__setup_APIC_LVTT(lapic_timer_period, oneshot, 1);
 	return 0;
 }
 
@@ -552,7 +550,7 @@ static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
 #define DEADLINE_MODEL_MATCH_REV(model, rev)	\
 	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)rev }
 
-static u32 hsx_deadline_rev(void)
+static __init u32 hsx_deadline_rev(void)
 {
 	switch (boot_cpu_data.x86_stepping) {
 	case 0x02: return 0x3a; /* EP */
@@ -562,7 +560,7 @@ static u32 hsx_deadline_rev(void)
 	return ~0U;
 }
 
-static u32 bdx_deadline_rev(void)
+static __init u32 bdx_deadline_rev(void)
 {
 	switch (boot_cpu_data.x86_stepping) {
 	case 0x02: return 0x00000011;
@@ -574,7 +572,7 @@ static u32 bdx_deadline_rev(void)
 	return ~0U;
 }
 
-static u32 skx_deadline_rev(void)
+static __init u32 skx_deadline_rev(void)
 {
 	switch (boot_cpu_data.x86_stepping) {
 	case 0x03: return 0x01000136;
@@ -587,7 +585,7 @@ static u32 skx_deadline_rev(void)
 	return ~0U;
 }
 
-static const struct x86_cpu_id deadline_match[] = {
+static const struct x86_cpu_id deadline_match[] __initconst = {
 	DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_HASWELL_X,	hsx_deadline_rev),
 	DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_X,	0x0b000020),
 	DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_BROADWELL_XEON_D,	bdx_deadline_rev),
@@ -609,18 +607,19 @@ static const struct x86_cpu_id deadline_match[] = {
 	{},
 };
 
-static void apic_check_deadline_errata(void)
+static __init bool apic_validate_deadline_timer(void)
 {
 	const struct x86_cpu_id *m;
 	u32 rev;
 
-	if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER) ||
-	    boot_cpu_has(X86_FEATURE_HYPERVISOR))
-		return;
+	if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER))
+		return false;
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+		return true;
 
 	m = x86_match_cpu(deadline_match);
 	if (!m)
-		return;
+		return true;
 
 	/*
 	 * Function pointers will have the MSB set due to address layout,
@@ -632,11 +631,12 @@ static void apic_check_deadline_errata(void)
 		rev = (u32)m->driver_data;
 
 	if (boot_cpu_data.microcode >= rev)
-		return;
+		return true;
 
 	setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
 	pr_err(FW_BUG "TSC_DEADLINE disabled due to Errata; "
 	       "please update microcode to version: 0x%x (or later)\n", rev);
+	return false;
 }
 
 /*
@@ -805,11 +805,11 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc)
 
 static int __init lapic_init_clockevent(void)
 {
-	if (!lapic_timer_frequency)
+	if (!lapic_timer_period)
 		return -1;
 
 	/* Calculate the scaled math multiplication factor */
-	lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR,
+	lapic_clockevent.mult = div_sc(lapic_timer_period/APIC_DIVISOR,
 					TICK_NSEC, lapic_clockevent.shift);
 	lapic_clockevent.max_delta_ns =
 		clockevent_delta2ns(0x7FFFFFFF, &lapic_clockevent);
@@ -840,7 +840,7 @@ static int __init calibrate_APIC_clock(void)
 	 */
 	if (!lapic_init_clockevent()) {
 		apic_printk(APIC_VERBOSE, "lapic timer already calibrated %d\n",
-			    lapic_timer_frequency);
+			    lapic_timer_period);
 		/*
 		 * Direct calibration methods must have an always running
 		 * local APIC timer, no need for broadcast timer.
@@ -921,13 +921,13 @@ static int __init calibrate_APIC_clock(void)
 	pm_referenced = !calibrate_by_pmtimer(lapic_cal_pm2 - lapic_cal_pm1,
 					&delta, &deltatsc);
 
-	lapic_timer_frequency = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS;
+	lapic_timer_period = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS;
 	lapic_init_clockevent();
 
 	apic_printk(APIC_VERBOSE, "..... delta %ld\n", delta);
 	apic_printk(APIC_VERBOSE, "..... mult: %u\n", lapic_clockevent.mult);
 	apic_printk(APIC_VERBOSE, "..... calibration result: %u\n",
-		    lapic_timer_frequency);
+		    lapic_timer_period);
 
 	if (boot_cpu_has(X86_FEATURE_TSC)) {
 		apic_printk(APIC_VERBOSE, "..... CPU clock speed is "
@@ -938,13 +938,13 @@ static int __init calibrate_APIC_clock(void)
 
 	apic_printk(APIC_VERBOSE, "..... host bus clock speed is "
 		    "%u.%04u MHz.\n",
-		    lapic_timer_frequency / (1000000 / HZ),
-		    lapic_timer_frequency % (1000000 / HZ));
+		    lapic_timer_period / (1000000 / HZ),
+		    lapic_timer_period % (1000000 / HZ));
 
 	/*
 	 * Do a sanity check on the APIC calibration result
 	 */
-	if (lapic_timer_frequency < (1000000 / HZ)) {
+	if (lapic_timer_period < (1000000 / HZ)) {
 		local_irq_enable();
 		pr_warning("APIC frequency too slow, disabling apic timer\n");
 		return -1;
@@ -2037,7 +2037,8 @@ void __init init_apic_mappings(void)
 {
 	unsigned int new_apicid;
 
-	apic_check_deadline_errata();
+	if (apic_validate_deadline_timer())
+		pr_info("TSC deadline timer available\n");
 
 	if (x2apic_mode) {
 		boot_cpu_physical_apicid = read_apic_id();
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index dad0dd759de2..e0c3c57ed7c0 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -23,10 +23,8 @@
 
 static struct irq_domain *msi_default_domain;
 
-static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg)
+static void __irq_msi_compose_msg(struct irq_cfg *cfg, struct msi_msg *msg)
 {
-	struct irq_cfg *cfg = irqd_cfg(data);
-
 	msg->address_hi = MSI_ADDR_BASE_HI;
 
 	if (x2apic_enabled())
@@ -47,6 +45,127 @@ static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg)
 		MSI_DATA_VECTOR(cfg->vector);
 }
 
+static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg)
+{
+	__irq_msi_compose_msg(irqd_cfg(data), msg);
+}
+
+static void irq_msi_update_msg(struct irq_data *irqd, struct irq_cfg *cfg)
+{
+	struct msi_msg msg[2] = { [1] = { }, };
+
+	__irq_msi_compose_msg(cfg, msg);
+	irq_data_get_irq_chip(irqd)->irq_write_msi_msg(irqd, msg);
+}
+
+static int
+msi_set_affinity(struct irq_data *irqd, const struct cpumask *mask, bool force)
+{
+	struct irq_cfg old_cfg, *cfg = irqd_cfg(irqd);
+	struct irq_data *parent = irqd->parent_data;
+	unsigned int cpu;
+	int ret;
+
+	/* Save the current configuration */
+	cpu = cpumask_first(irq_data_get_effective_affinity_mask(irqd));
+	old_cfg = *cfg;
+
+	/* Allocate a new target vector */
+	ret = parent->chip->irq_set_affinity(parent, mask, force);
+	if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
+		return ret;
+
+	/*
+	 * For non-maskable and non-remapped MSI interrupts the migration
+	 * to a different destination CPU and a different vector has to be
+	 * done careful to handle the possible stray interrupt which can be
+	 * caused by the non-atomic update of the address/data pair.
+	 *
+	 * Direct update is possible when:
+	 * - The MSI is maskable (remapped MSI does not use this code path)).
+	 *   The quirk bit is not set in this case.
+	 * - The new vector is the same as the old vector
+	 * - The old vector is MANAGED_IRQ_SHUTDOWN_VECTOR (interrupt starts up)
+	 * - The new destination CPU is the same as the old destination CPU
+	 */
+	if (!irqd_msi_nomask_quirk(irqd) ||
+	    cfg->vector == old_cfg.vector ||
+	    old_cfg.vector == MANAGED_IRQ_SHUTDOWN_VECTOR ||
+	    cfg->dest_apicid == old_cfg.dest_apicid) {
+		irq_msi_update_msg(irqd, cfg);
+		return ret;
+	}
+
+	/*
+	 * Paranoia: Validate that the interrupt target is the local
+	 * CPU.
+	 */
+	if (WARN_ON_ONCE(cpu != smp_processor_id())) {
+		irq_msi_update_msg(irqd, cfg);
+		return ret;
+	}
+
+	/*
+	 * Redirect the interrupt to the new vector on the current CPU
+	 * first. This might cause a spurious interrupt on this vector if
+	 * the device raises an interrupt right between this update and the
+	 * update to the final destination CPU.
+	 *
+	 * If the vector is in use then the installed device handler will
+	 * denote it as spurious which is no harm as this is a rare event
+	 * and interrupt handlers have to cope with spurious interrupts
+	 * anyway. If the vector is unused, then it is marked so it won't
+	 * trigger the 'No irq handler for vector' warning in do_IRQ().
+	 *
+	 * This requires to hold vector lock to prevent concurrent updates to
+	 * the affected vector.
+	 */
+	lock_vector_lock();
+
+	/*
+	 * Mark the new target vector on the local CPU if it is currently
+	 * unused. Reuse the VECTOR_RETRIGGERED state which is also used in
+	 * the CPU hotplug path for a similar purpose. This cannot be
+	 * undone here as the current CPU has interrupts disabled and
+	 * cannot handle the interrupt before the whole set_affinity()
+	 * section is done. In the CPU unplug case, the current CPU is
+	 * about to vanish and will not handle any interrupts anymore. The
+	 * vector is cleaned up when the CPU comes online again.
+	 */
+	if (IS_ERR_OR_NULL(this_cpu_read(vector_irq[cfg->vector])))
+		this_cpu_write(vector_irq[cfg->vector], VECTOR_RETRIGGERED);
+
+	/* Redirect it to the new vector on the local CPU temporarily */
+	old_cfg.vector = cfg->vector;
+	irq_msi_update_msg(irqd, &old_cfg);
+
+	/* Now transition it to the target CPU */
+	irq_msi_update_msg(irqd, cfg);
+
+	/*
+	 * All interrupts after this point are now targeted at the new
+	 * vector/CPU.
+	 *
+	 * Drop vector lock before testing whether the temporary assignment
+	 * to the local CPU was hit by an interrupt raised in the device,
+	 * because the retrigger function acquires vector lock again.
+	 */
+	unlock_vector_lock();
+
+	/*
+	 * Check whether the transition raced with a device interrupt and
+	 * is pending in the local APICs IRR. It is safe to do this outside
+	 * of vector lock as the irq_desc::lock of this interrupt is still
+	 * held and interrupts are disabled: The check is not accessing the
+	 * underlying vector store. It's just checking the local APIC's
+	 * IRR.
+	 */
+	if (lapic_vector_set_in_irr(cfg->vector))
+		irq_data_get_irq_chip(irqd)->irq_retrigger(irqd);
+
+	return ret;
+}
+
 /*
  * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices,
  * which implement the MSI or MSI-X Capability Structure.
@@ -58,6 +177,7 @@ static struct irq_chip pci_msi_controller = {
 	.irq_ack		= irq_chip_ack_parent,
 	.irq_retrigger		= irq_chip_retrigger_hierarchy,
 	.irq_compose_msi_msg	= irq_msi_compose_msg,
+	.irq_set_affinity	= msi_set_affinity,
 	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
@@ -146,6 +266,8 @@ void __init arch_init_msi_domain(struct irq_domain *parent)
 	}
 	if (!msi_default_domain)
 		pr_warn("failed to initialize irqdomain for MSI/MSI-x.\n");
+	else
+		msi_default_domain->flags |= IRQ_DOMAIN_MSI_NOMASK_QUIRK;
 }
 
 #ifdef CONFIG_IRQ_REMAP
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 2c5676b0a6e7..259d17d08983 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -446,12 +446,10 @@ static int x86_vector_activate(struct irq_domain *dom, struct irq_data *irqd,
 	trace_vector_activate(irqd->irq, apicd->is_managed,
 			      apicd->can_reserve, reserve);
 
-	/* Nothing to do for fixed assigned vectors */
-	if (!apicd->can_reserve && !apicd->is_managed)
-		return 0;
-
 	raw_spin_lock_irqsave(&vector_lock, flags);
-	if (reserve || irqd_is_managed_and_shutdown(irqd))
+	if (!apicd->can_reserve && !apicd->is_managed)
+		assign_irq_vector_any_locked(irqd);
+	else if (reserve || irqd_is_managed_and_shutdown(irqd))
 		vector_assign_managed_shutdown(irqd);
 	else if (apicd->is_managed)
 		ret = activate_managed(irqd);
@@ -557,6 +555,16 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
 		irqd->hwirq = virq + i;
 		irqd_set_single_target(irqd);
 		/*
+		 * Prevent that any of these interrupts is invoked in
+		 * non interrupt context via e.g. generic_handle_irq()
+		 * as that can corrupt the affinity move state.
+		 */
+		irqd_set_handle_enforce_irqctx(irqd);
+
+		/* Don't invoke affinity setter on deactivated interrupts */
+		irqd_set_affinity_on_activate(irqd);
+
+		/*
 		 * Legacy vectors are already assigned when the IOAPIC
 		 * takes them over. They stay on the same vector. This is
 		 * required for check_timer() to work correctly as it might
@@ -769,20 +777,10 @@ void lapic_offline(void)
 static int apic_set_affinity(struct irq_data *irqd,
 			     const struct cpumask *dest, bool force)
 {
-	struct apic_chip_data *apicd = apic_chip_data(irqd);
 	int err;
 
-	/*
-	 * Core code can call here for inactive interrupts. For inactive
-	 * interrupts which use managed or reservation mode there is no
-	 * point in going through the vector assignment right now as the
-	 * activation will assign a vector which fits the destination
-	 * cpumask. Let the core code store the destination mask and be
-	 * done with it.
-	 */
-	if (!irqd_is_activated(irqd) &&
-	    (apicd->is_managed || apicd->can_reserve))
-		return IRQ_SET_MASK_OK;
+	if (WARN_ON_ONCE(!irqd_is_activated(irqd)))
+		return -EIO;
 
 	raw_spin_lock(&vector_lock);
 	cpumask_and(vector_searchmask, dest, cpu_online_mask);
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index d3d075226c0a..70e97727a26a 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -6,13 +6,28 @@
 #include <asm/ia32.h>
 
 #define __SYSCALL_64(nr, sym, qual) [nr] = 1,
+#define __SYSCALL_X32(nr, sym, qual)
 static char syscalls_64[] = {
 #include <asm/syscalls_64.h>
 };
+#undef __SYSCALL_64
+#undef __SYSCALL_X32
+
+#ifdef CONFIG_X86_X32_ABI
+#define __SYSCALL_64(nr, sym, qual)
+#define __SYSCALL_X32(nr, sym, qual) [nr] = 1,
+static char syscalls_x32[] = {
+#include <asm/syscalls_64.h>
+};
+#undef __SYSCALL_64
+#undef __SYSCALL_X32
+#endif
+
 #define __SYSCALL_I386(nr, sym, qual) [nr] = 1,
 static char syscalls_ia32[] = {
 #include <asm/syscalls_32.h>
 };
+#undef __SYSCALL_I386
 
 #if defined(CONFIG_KVM_GUEST) && defined(CONFIG_PARAVIRT_SPINLOCKS)
 #include <asm/kvm_para.h>
@@ -80,6 +95,11 @@ int main(void)
 	DEFINE(__NR_syscall_max, sizeof(syscalls_64) - 1);
 	DEFINE(NR_syscalls, sizeof(syscalls_64));
 
+#ifdef CONFIG_X86_X32_ABI
+	DEFINE(__NR_syscall_x32_max, sizeof(syscalls_x32) - 1);
+	DEFINE(X32_NR_syscalls, sizeof(syscalls_x32));
+#endif
+
 	DEFINE(__NR_syscall_compat_max, sizeof(syscalls_ia32) - 1);
 	DEFINE(IA32_NR_syscalls, sizeof(syscalls_ia32));
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 68c363c341bf..fe3649f725dc 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -27,6 +27,7 @@
 
 static const int amd_erratum_383[];
 static const int amd_erratum_400[];
+static const int amd_erratum_1054[];
 static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum);
 
 /*
@@ -614,9 +615,9 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
 		return;
 
 clear_all:
-		clear_cpu_cap(c, X86_FEATURE_SME);
+		setup_clear_cpu_cap(X86_FEATURE_SME);
 clear_sev:
-		clear_cpu_cap(c, X86_FEATURE_SEV);
+		setup_clear_cpu_cap(X86_FEATURE_SEV);
 	}
 }
 
@@ -988,6 +989,15 @@ static void init_amd(struct cpuinfo_x86 *c)
 	/* AMD CPUs don't reset SS attributes on SYSRET, Xen does. */
 	if (!cpu_has(c, X86_FEATURE_XENPV))
 		set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
+
+	/*
+	 * Turn on the Instructions Retired free counter on machines not
+	 * susceptible to erratum #1054 "Instructions Retired Performance
+	 * Counter May Be Inaccurate".
+	 */
+	if (cpu_has(c, X86_FEATURE_IRPERF) &&
+	    !cpu_has_amd_erratum(c, amd_erratum_1054))
+		msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT);
 }
 
 #ifdef CONFIG_X86_32
@@ -1115,6 +1125,9 @@ static const int amd_erratum_400[] =
 static const int amd_erratum_383[] =
 	AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf));
 
+/* #1054: Instructions Retired Performance Counter May Be Inaccurate */
+static const int amd_erratum_1054[] =
+	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf));
 
 static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
 {
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 08bbc67adf13..a277fa17c4ee 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -41,6 +41,7 @@ static void __init l1tf_select_mitigation(void);
 static void __init mds_select_mitigation(void);
 static void __init mds_print_mitigation(void);
 static void __init taa_select_mitigation(void);
+static void __init srbds_select_mitigation(void);
 
 /* The base value of the SPEC_CTRL MSR that always has to be preserved. */
 u64 x86_spec_ctrl_base;
@@ -108,6 +109,7 @@ void __init check_bugs(void)
 	l1tf_select_mitigation();
 	mds_select_mitigation();
 	taa_select_mitigation();
+	srbds_select_mitigation();
 
 	/*
 	 * As MDS and TAA mitigations are inter-related, print MDS
@@ -391,6 +393,97 @@ static int __init tsx_async_abort_parse_cmdline(char *str)
 early_param("tsx_async_abort", tsx_async_abort_parse_cmdline);
 
 #undef pr_fmt
+#define pr_fmt(fmt)	"SRBDS: " fmt
+
+enum srbds_mitigations {
+	SRBDS_MITIGATION_OFF,
+	SRBDS_MITIGATION_UCODE_NEEDED,
+	SRBDS_MITIGATION_FULL,
+	SRBDS_MITIGATION_TSX_OFF,
+	SRBDS_MITIGATION_HYPERVISOR,
+};
+
+static enum srbds_mitigations srbds_mitigation __ro_after_init = SRBDS_MITIGATION_FULL;
+
+static const char * const srbds_strings[] = {
+	[SRBDS_MITIGATION_OFF]		= "Vulnerable",
+	[SRBDS_MITIGATION_UCODE_NEEDED]	= "Vulnerable: No microcode",
+	[SRBDS_MITIGATION_FULL]		= "Mitigation: Microcode",
+	[SRBDS_MITIGATION_TSX_OFF]	= "Mitigation: TSX disabled",
+	[SRBDS_MITIGATION_HYPERVISOR]	= "Unknown: Dependent on hypervisor status",
+};
+
+static bool srbds_off;
+
+void update_srbds_msr(void)
+{
+	u64 mcu_ctrl;
+
+	if (!boot_cpu_has_bug(X86_BUG_SRBDS))
+		return;
+
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+		return;
+
+	if (srbds_mitigation == SRBDS_MITIGATION_UCODE_NEEDED)
+		return;
+
+	rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+
+	switch (srbds_mitigation) {
+	case SRBDS_MITIGATION_OFF:
+	case SRBDS_MITIGATION_TSX_OFF:
+		mcu_ctrl |= RNGDS_MITG_DIS;
+		break;
+	case SRBDS_MITIGATION_FULL:
+		mcu_ctrl &= ~RNGDS_MITG_DIS;
+		break;
+	default:
+		break;
+	}
+
+	wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+}
+
+static void __init srbds_select_mitigation(void)
+{
+	u64 ia32_cap;
+
+	if (!boot_cpu_has_bug(X86_BUG_SRBDS))
+		return;
+
+	/*
+	 * Check to see if this is one of the MDS_NO systems supporting
+	 * TSX that are only exposed to SRBDS when TSX is enabled.
+	 */
+	ia32_cap = x86_read_arch_cap_msr();
+	if ((ia32_cap & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM))
+		srbds_mitigation = SRBDS_MITIGATION_TSX_OFF;
+	else if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+		srbds_mitigation = SRBDS_MITIGATION_HYPERVISOR;
+	else if (!boot_cpu_has(X86_FEATURE_SRBDS_CTRL))
+		srbds_mitigation = SRBDS_MITIGATION_UCODE_NEEDED;
+	else if (cpu_mitigations_off() || srbds_off)
+		srbds_mitigation = SRBDS_MITIGATION_OFF;
+
+	update_srbds_msr();
+	pr_info("%s\n", srbds_strings[srbds_mitigation]);
+}
+
+static int __init srbds_parse_cmdline(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (!boot_cpu_has_bug(X86_BUG_SRBDS))
+		return 0;
+
+	srbds_off = !strcmp(str, "off");
+	return 0;
+}
+early_param("srbds", srbds_parse_cmdline);
+
+#undef pr_fmt
 #define pr_fmt(fmt)     "Spectre V1 : " fmt
 
 enum spectre_v1_mitigation {
@@ -488,7 +581,9 @@ early_param("nospectre_v1", nospectre_v1_cmdline);
 static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init =
 	SPECTRE_V2_NONE;
 
-static enum spectre_v2_user_mitigation spectre_v2_user __ro_after_init =
+static enum spectre_v2_user_mitigation spectre_v2_user_stibp __ro_after_init =
+	SPECTRE_V2_USER_NONE;
+static enum spectre_v2_user_mitigation spectre_v2_user_ibpb __ro_after_init =
 	SPECTRE_V2_USER_NONE;
 
 #ifdef CONFIG_RETPOLINE
@@ -634,15 +729,6 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd)
 		break;
 	}
 
-	/*
-	 * At this point, an STIBP mode other than "off" has been set.
-	 * If STIBP support is not being forced, check if STIBP always-on
-	 * is preferred.
-	 */
-	if (mode != SPECTRE_V2_USER_STRICT &&
-	    boot_cpu_has(X86_FEATURE_AMD_STIBP_ALWAYS_ON))
-		mode = SPECTRE_V2_USER_STRICT_PREFERRED;
-
 	/* Initialize Indirect Branch Prediction Barrier */
 	if (boot_cpu_has(X86_FEATURE_IBPB)) {
 		setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
@@ -665,23 +751,36 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd)
 		pr_info("mitigation: Enabling %s Indirect Branch Prediction Barrier\n",
 			static_key_enabled(&switch_mm_always_ibpb) ?
 			"always-on" : "conditional");
+
+		spectre_v2_user_ibpb = mode;
 	}
 
-	/* If enhanced IBRS is enabled no STIBP required */
-	if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
+	/*
+	 * If enhanced IBRS is enabled or SMT impossible, STIBP is not
+	 * required.
+	 */
+	if (!smt_possible || spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
 		return;
 
 	/*
-	 * If SMT is not possible or STIBP is not available clear the STIBP
-	 * mode.
+	 * At this point, an STIBP mode other than "off" has been set.
+	 * If STIBP support is not being forced, check if STIBP always-on
+	 * is preferred.
+	 */
+	if (mode != SPECTRE_V2_USER_STRICT &&
+	    boot_cpu_has(X86_FEATURE_AMD_STIBP_ALWAYS_ON))
+		mode = SPECTRE_V2_USER_STRICT_PREFERRED;
+
+	/*
+	 * If STIBP is not available, clear the STIBP mode.
 	 */
-	if (!smt_possible || !boot_cpu_has(X86_FEATURE_STIBP))
+	if (!boot_cpu_has(X86_FEATURE_STIBP))
 		mode = SPECTRE_V2_USER_NONE;
+
+	spectre_v2_user_stibp = mode;
+
 set_mode:
-	spectre_v2_user = mode;
-	/* Only print the STIBP mode when SMT possible */
-	if (smt_possible)
-		pr_info("%s\n", spectre_v2_user_strings[mode]);
+	pr_info("%s\n", spectre_v2_user_strings[mode]);
 }
 
 static const char * const spectre_v2_strings[] = {
@@ -914,7 +1013,7 @@ void cpu_bugs_smt_update(void)
 {
 	mutex_lock(&spec_ctrl_mutex);
 
-	switch (spectre_v2_user) {
+	switch (spectre_v2_user_stibp) {
 	case SPECTRE_V2_USER_NONE:
 		break;
 	case SPECTRE_V2_USER_STRICT:
@@ -1157,14 +1256,19 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl)
 {
 	switch (ctrl) {
 	case PR_SPEC_ENABLE:
-		if (spectre_v2_user == SPECTRE_V2_USER_NONE)
+		if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE &&
+		    spectre_v2_user_stibp == SPECTRE_V2_USER_NONE)
 			return 0;
 		/*
 		 * Indirect branch speculation is always disabled in strict
-		 * mode.
+		 * mode. It can neither be enabled if it was force-disabled
+		 * by a  previous prctl call.
+
 		 */
-		if (spectre_v2_user == SPECTRE_V2_USER_STRICT ||
-		    spectre_v2_user == SPECTRE_V2_USER_STRICT_PREFERRED)
+		if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
+		    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
+		    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED ||
+		    task_spec_ib_force_disable(task))
 			return -EPERM;
 		task_clear_spec_ib_disable(task);
 		task_update_spec_tif(task);
@@ -1175,10 +1279,12 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl)
 		 * Indirect branch speculation is always allowed when
 		 * mitigation is force disabled.
 		 */
-		if (spectre_v2_user == SPECTRE_V2_USER_NONE)
+		if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE &&
+		    spectre_v2_user_stibp == SPECTRE_V2_USER_NONE)
 			return -EPERM;
-		if (spectre_v2_user == SPECTRE_V2_USER_STRICT ||
-		    spectre_v2_user == SPECTRE_V2_USER_STRICT_PREFERRED)
+		if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
+		    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
+		    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED)
 			return 0;
 		task_set_spec_ib_disable(task);
 		if (ctrl == PR_SPEC_FORCE_DISABLE)
@@ -1209,7 +1315,8 @@ void arch_seccomp_spec_mitigate(struct task_struct *task)
 {
 	if (ssb_mode == SPEC_STORE_BYPASS_SECCOMP)
 		ssb_prctl_set(task, PR_SPEC_FORCE_DISABLE);
-	if (spectre_v2_user == SPECTRE_V2_USER_SECCOMP)
+	if (spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP ||
+	    spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP)
 		ib_prctl_set(task, PR_SPEC_FORCE_DISABLE);
 }
 #endif
@@ -1240,22 +1347,24 @@ static int ib_prctl_get(struct task_struct *task)
 	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
 		return PR_SPEC_NOT_AFFECTED;
 
-	switch (spectre_v2_user) {
-	case SPECTRE_V2_USER_NONE:
+	if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE &&
+	    spectre_v2_user_stibp == SPECTRE_V2_USER_NONE)
 		return PR_SPEC_ENABLE;
-	case SPECTRE_V2_USER_PRCTL:
-	case SPECTRE_V2_USER_SECCOMP:
+	else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
+	    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
+	    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED)
+		return PR_SPEC_DISABLE;
+	else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_PRCTL ||
+	    spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP ||
+	    spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL ||
+	    spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP) {
 		if (task_spec_ib_force_disable(task))
 			return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE;
 		if (task_spec_ib_disable(task))
 			return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
 		return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
-	case SPECTRE_V2_USER_STRICT:
-	case SPECTRE_V2_USER_STRICT_PREFERRED:
-		return PR_SPEC_DISABLE;
-	default:
+	} else
 		return PR_SPEC_NOT_AFFECTED;
-	}
 }
 
 int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
@@ -1494,7 +1603,7 @@ static char *stibp_state(void)
 	if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
 		return "";
 
-	switch (spectre_v2_user) {
+	switch (spectre_v2_user_stibp) {
 	case SPECTRE_V2_USER_NONE:
 		return ", STIBP: disabled";
 	case SPECTRE_V2_USER_STRICT:
@@ -1521,6 +1630,11 @@ static char *ibpb_state(void)
 	return "";
 }
 
+static ssize_t srbds_show_state(char *buf)
+{
+	return sprintf(buf, "%s\n", srbds_strings[srbds_mitigation]);
+}
+
 static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
 			       char *buf, unsigned int bug)
 {
@@ -1565,6 +1679,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 	case X86_BUG_ITLB_MULTIHIT:
 		return itlb_multihit_show_state(buf);
 
+	case X86_BUG_SRBDS:
+		return srbds_show_state(buf);
+
 	default:
 		break;
 	}
@@ -1611,4 +1728,9 @@ ssize_t cpu_show_itlb_multihit(struct device *dev, struct device_attribute *attr
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_ITLB_MULTIHIT);
 }
+
+ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_SRBDS);
+}
 #endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index f6bc5b879e51..1c44715818e6 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -366,6 +366,9 @@ out:
 	cr4_clear_bits(X86_CR4_UMIP);
 }
 
+/* These bits should not change their value after CPU init is finished. */
+static const unsigned long cr4_pinned_mask =
+	X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP | X86_CR4_FSGSBASE;
 static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning);
 static unsigned long cr4_pinned_bits __ro_after_init;
 
@@ -390,20 +393,20 @@ EXPORT_SYMBOL(native_write_cr0);
 
 void native_write_cr4(unsigned long val)
 {
-	unsigned long bits_missing = 0;
+	unsigned long bits_changed = 0;
 
 set_register:
 	asm volatile("mov %0,%%cr4": "+r" (val), "+m" (cr4_pinned_bits));
 
 	if (static_branch_likely(&cr_pinning)) {
-		if (unlikely((val & cr4_pinned_bits) != cr4_pinned_bits)) {
-			bits_missing = ~val & cr4_pinned_bits;
-			val |= bits_missing;
+		if (unlikely((val & cr4_pinned_mask) != cr4_pinned_bits)) {
+			bits_changed = (val & cr4_pinned_mask) ^ cr4_pinned_bits;
+			val = (val & ~cr4_pinned_mask) | cr4_pinned_bits;
 			goto set_register;
 		}
-		/* Warn after we've set the missing bits. */
-		WARN_ONCE(bits_missing, "CR4 bits went missing: %lx!?\n",
-			  bits_missing);
+		/* Warn after we've corrected the changed bits. */
+		WARN_ONCE(bits_changed, "pinned CR4 bits changed: 0x%lx!?\n",
+			  bits_changed);
 	}
 }
 EXPORT_SYMBOL(native_write_cr4);
@@ -415,7 +418,7 @@ void cr4_init(void)
 	if (boot_cpu_has(X86_FEATURE_PCID))
 		cr4 |= X86_CR4_PCIDE;
 	if (static_branch_likely(&cr_pinning))
-		cr4 |= cr4_pinned_bits;
+		cr4 = (cr4 & ~cr4_pinned_mask) | cr4_pinned_bits;
 
 	__write_cr4(cr4);
 
@@ -430,10 +433,7 @@ void cr4_init(void)
  */
 static void __init setup_cr_pinning(void)
 {
-	unsigned long mask;
-
-	mask = (X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP);
-	cr4_pinned_bits = this_cpu_read(cpu_tlbstate.cr4) & mask;
+	cr4_pinned_bits = this_cpu_read(cpu_tlbstate.cr4) & cr4_pinned_mask;
 	static_key_enable(&cr_pinning.key);
 }
 
@@ -464,7 +464,7 @@ static __always_inline void setup_pku(struct cpuinfo_x86 *c)
 	 * cpuid bit to be set.  We need to ensure that we
 	 * update that bit in this CPU's "cpu_info".
 	 */
-	get_cpu_cap(c);
+	set_cpu_cap(c, X86_FEATURE_OSPKE);
 }
 
 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
@@ -1081,9 +1081,30 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 	{}
 };
 
-static bool __init cpu_matches(unsigned long which)
+#define VULNBL_INTEL_STEPPINGS(model, steppings, issues)		   \
+	X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(INTEL, 6,		   \
+					    INTEL_FAM6_##model, steppings, \
+					    X86_FEATURE_ANY, issues)
+
+#define SRBDS		BIT(0)
+
+static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
+	VULNBL_INTEL_STEPPINGS(IVYBRIDGE,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(HASWELL_CORE,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(HASWELL_ULT,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(HASWELL_GT3E,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(BROADWELL_GT3E,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(BROADWELL_CORE,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(SKYLAKE_MOBILE,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(SKYLAKE_DESKTOP,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(KABYLAKE_MOBILE,	X86_STEPPINGS(0x0, 0xC),	SRBDS),
+	VULNBL_INTEL_STEPPINGS(KABYLAKE_DESKTOP,X86_STEPPINGS(0x0, 0xD),	SRBDS),
+	{}
+};
+
+static bool __init cpu_matches(const struct x86_cpu_id *table, unsigned long which)
 {
-	const struct x86_cpu_id *m = x86_match_cpu(cpu_vuln_whitelist);
+	const struct x86_cpu_id *m = x86_match_cpu(table);
 
 	return m && !!(m->driver_data & which);
 }
@@ -1103,29 +1124,32 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	u64 ia32_cap = x86_read_arch_cap_msr();
 
 	/* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */
-	if (!cpu_matches(NO_ITLB_MULTIHIT) && !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO))
+	if (!cpu_matches(cpu_vuln_whitelist, NO_ITLB_MULTIHIT) &&
+	    !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO))
 		setup_force_cpu_bug(X86_BUG_ITLB_MULTIHIT);
 
-	if (cpu_matches(NO_SPECULATION))
+	if (cpu_matches(cpu_vuln_whitelist, NO_SPECULATION))
 		return;
 
 	setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
 	setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
 
-	if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) &&
+	if (!cpu_matches(cpu_vuln_whitelist, NO_SSB) &&
+	    !(ia32_cap & ARCH_CAP_SSB_NO) &&
 	   !cpu_has(c, X86_FEATURE_AMD_SSB_NO))
 		setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
 
 	if (ia32_cap & ARCH_CAP_IBRS_ALL)
 		setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED);
 
-	if (!cpu_matches(NO_MDS) && !(ia32_cap & ARCH_CAP_MDS_NO)) {
+	if (!cpu_matches(cpu_vuln_whitelist, NO_MDS) &&
+	    !(ia32_cap & ARCH_CAP_MDS_NO)) {
 		setup_force_cpu_bug(X86_BUG_MDS);
-		if (cpu_matches(MSBDS_ONLY))
+		if (cpu_matches(cpu_vuln_whitelist, MSBDS_ONLY))
 			setup_force_cpu_bug(X86_BUG_MSBDS_ONLY);
 	}
 
-	if (!cpu_matches(NO_SWAPGS))
+	if (!cpu_matches(cpu_vuln_whitelist, NO_SWAPGS))
 		setup_force_cpu_bug(X86_BUG_SWAPGS);
 
 	/*
@@ -1143,7 +1167,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	     (ia32_cap & ARCH_CAP_TSX_CTRL_MSR)))
 		setup_force_cpu_bug(X86_BUG_TAA);
 
-	if (cpu_matches(NO_MELTDOWN))
+	/*
+	 * SRBDS affects CPUs which support RDRAND or RDSEED and are listed
+	 * in the vulnerability blacklist.
+	 */
+	if ((cpu_has(c, X86_FEATURE_RDRAND) ||
+	     cpu_has(c, X86_FEATURE_RDSEED)) &&
+	    cpu_matches(cpu_vuln_blacklist, SRBDS))
+		    setup_force_cpu_bug(X86_BUG_SRBDS);
+
+	if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
 		return;
 
 	/* Rogue Data Cache Load? No! */
@@ -1152,7 +1185,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 
 	setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
 
-	if (cpu_matches(NO_L1TF))
+	if (cpu_matches(cpu_vuln_whitelist, NO_L1TF))
 		return;
 
 	setup_force_cpu_bug(X86_BUG_L1TF);
@@ -1589,6 +1622,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c)
 	mtrr_ap_init();
 	validate_apic_and_package_id(c);
 	x86_spec_ctrl_setup_ap();
+	update_srbds_msr();
 }
 
 static __init int setup_noclflush(char *arg)
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 38ab6e115eac..9d033693519a 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -77,6 +77,7 @@ extern void detect_ht(struct cpuinfo_x86 *c);
 unsigned int aperfmperf_get_khz(int cpu);
 
 extern void x86_spec_ctrl_setup_ap(void);
+extern void update_srbds_msr(void);
 
 extern u64 x86_read_arch_cap_msr(void);
 
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 92b107ab283f..c979a056a46f 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -66,6 +66,32 @@ void check_mpx_erratum(struct cpuinfo_x86 *c)
 	}
 }
 
+/*
+ * Processors which have self-snooping capability can handle conflicting
+ * memory type across CPUs by snooping its own cache. However, there exists
+ * CPU models in which having conflicting memory types still leads to
+ * unpredictable behavior, machine check errors, or hangs. Clear this
+ * feature to prevent its use on machines with known erratas.
+ */
+static void check_memory_type_self_snoop_errata(struct cpuinfo_x86 *c)
+{
+	switch (c->x86_model) {
+	case INTEL_FAM6_CORE_YONAH:
+	case INTEL_FAM6_CORE2_MEROM:
+	case INTEL_FAM6_CORE2_MEROM_L:
+	case INTEL_FAM6_CORE2_PENRYN:
+	case INTEL_FAM6_CORE2_DUNNINGTON:
+	case INTEL_FAM6_NEHALEM:
+	case INTEL_FAM6_NEHALEM_G:
+	case INTEL_FAM6_NEHALEM_EP:
+	case INTEL_FAM6_NEHALEM_EX:
+	case INTEL_FAM6_WESTMERE:
+	case INTEL_FAM6_WESTMERE_EP:
+	case INTEL_FAM6_SANDYBRIDGE:
+		setup_clear_cpu_cap(X86_FEATURE_SELFSNOOP);
+	}
+}
+
 static bool ring3mwait_disabled __read_mostly;
 
 static int __init ring3mwait_disable(char *__unused)
@@ -239,9 +265,9 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	/* Penwell and Cloverview have the TSC which doesn't sleep on S3 */
 	if (c->x86 == 6) {
 		switch (c->x86_model) {
-		case 0x27:	/* Penwell */
-		case 0x35:	/* Cloverview */
-		case 0x4a:	/* Merrifield */
+		case INTEL_FAM6_ATOM_SALTWELL_MID:
+		case INTEL_FAM6_ATOM_SALTWELL_TABLET:
+		case INTEL_FAM6_ATOM_SILVERMONT_MID:
 			set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC_S3);
 			break;
 		default:
@@ -304,6 +330,7 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	}
 
 	check_mpx_erratum(c);
+	check_memory_type_self_snoop_errata(c);
 
 	/*
 	 * Get the number of SMT siblings early from the extended topology
diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c
index 6dd78d8235e4..2f163e6646b6 100644
--- a/arch/x86/kernel/cpu/match.c
+++ b/arch/x86/kernel/cpu/match.c
@@ -34,13 +34,18 @@ const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match)
 	const struct x86_cpu_id *m;
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 
-	for (m = match; m->vendor | m->family | m->model | m->feature; m++) {
+	for (m = match;
+	     m->vendor | m->family | m->model | m->steppings | m->feature;
+	     m++) {
 		if (m->vendor != X86_VENDOR_ANY && c->x86_vendor != m->vendor)
 			continue;
 		if (m->family != X86_FAMILY_ANY && c->x86 != m->family)
 			continue;
 		if (m->model != X86_MODEL_ANY && c->x86_model != m->model)
 			continue;
+		if (m->steppings != X86_STEPPING_ANY &&
+		    !(BIT(c->x86_stepping) & m->steppings))
+			continue;
 		if (m->feature != X86_FEATURE_ANY && !cpu_has(c, m->feature))
 			continue;
 		return m;
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 303b8c58845e..f1c845416790 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -1159,9 +1159,12 @@ static const struct sysfs_ops threshold_ops = {
 	.store			= store,
 };
 
+static void threshold_block_release(struct kobject *kobj);
+
 static struct kobj_type threshold_ktype = {
 	.sysfs_ops		= &threshold_ops,
 	.default_attrs		= default_attrs,
+	.release		= threshold_block_release,
 };
 
 static const char *get_name(unsigned int bank, struct threshold_block *b)
@@ -1194,8 +1197,9 @@ static const char *get_name(unsigned int bank, struct threshold_block *b)
 	return buf_mcatype;
 }
 
-static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank,
-				     unsigned int block, u32 address)
+static int allocate_threshold_blocks(unsigned int cpu, struct threshold_bank *tb,
+				     unsigned int bank, unsigned int block,
+				     u32 address)
 {
 	struct threshold_block *b = NULL;
 	u32 low, high;
@@ -1239,16 +1243,12 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank,
 
 	INIT_LIST_HEAD(&b->miscj);
 
-	if (per_cpu(threshold_banks, cpu)[bank]->blocks) {
-		list_add(&b->miscj,
-			 &per_cpu(threshold_banks, cpu)[bank]->blocks->miscj);
-	} else {
-		per_cpu(threshold_banks, cpu)[bank]->blocks = b;
-	}
+	if (tb->blocks)
+		list_add(&b->miscj, &tb->blocks->miscj);
+	else
+		tb->blocks = b;
 
-	err = kobject_init_and_add(&b->kobj, &threshold_ktype,
-				   per_cpu(threshold_banks, cpu)[bank]->kobj,
-				   get_name(bank, b));
+	err = kobject_init_and_add(&b->kobj, &threshold_ktype, tb->kobj, get_name(bank, b));
 	if (err)
 		goto out_free;
 recurse:
@@ -1256,7 +1256,7 @@ recurse:
 	if (!address)
 		return 0;
 
-	err = allocate_threshold_blocks(cpu, bank, block, address);
+	err = allocate_threshold_blocks(cpu, tb, bank, block, address);
 	if (err)
 		goto out_free;
 
@@ -1341,8 +1341,6 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank)
 		goto out_free;
 	}
 
-	per_cpu(threshold_banks, cpu)[bank] = b;
-
 	if (is_shared_bank(bank)) {
 		refcount_set(&b->cpus, 1);
 
@@ -1353,9 +1351,13 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank)
 		}
 	}
 
-	err = allocate_threshold_blocks(cpu, bank, 0, msr_ops.misc(bank));
-	if (!err)
-		goto out;
+	err = allocate_threshold_blocks(cpu, b, bank, 0, msr_ops.misc(bank));
+	if (err)
+		goto out_free;
+
+	per_cpu(threshold_banks, cpu)[bank] = b;
+
+	return 0;
 
  out_free:
 	kfree(b);
@@ -1364,8 +1366,12 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank)
 	return err;
 }
 
-static void deallocate_threshold_block(unsigned int cpu,
-						 unsigned int bank)
+static void threshold_block_release(struct kobject *kobj)
+{
+	kfree(to_block(kobj));
+}
+
+static void deallocate_threshold_block(unsigned int cpu, unsigned int bank)
 {
 	struct threshold_block *pos = NULL;
 	struct threshold_block *tmp = NULL;
@@ -1375,13 +1381,11 @@ static void deallocate_threshold_block(unsigned int cpu,
 		return;
 
 	list_for_each_entry_safe(pos, tmp, &head->blocks->miscj, miscj) {
-		kobject_put(&pos->kobj);
 		list_del(&pos->miscj);
-		kfree(pos);
+		kobject_put(&pos->kobj);
 	}
 
-	kfree(per_cpu(threshold_banks, cpu)[bank]->blocks);
-	per_cpu(threshold_banks, cpu)[bank]->blocks = NULL;
+	kobject_put(&head->blocks->kobj);
 }
 
 static void __threshold_remove_blocks(struct threshold_bank *b)
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index b259ba60ec36..db1a8a1612f9 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -517,6 +517,13 @@ bool mce_is_memory_error(struct mce *m)
 }
 EXPORT_SYMBOL_GPL(mce_is_memory_error);
 
+static bool whole_page(struct mce *m)
+{
+	if (!mca_cfg.ser || !(m->status & MCI_STATUS_MISCV))
+		return true;
+	return MCI_MISC_ADDR_LSB(m->misc) >= PAGE_SHIFT;
+}
+
 bool mce_is_correctable(struct mce *m)
 {
 	if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED)
@@ -585,7 +592,7 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val,
 	if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) {
 		pfn = mce->addr >> PAGE_SHIFT;
 		if (!memory_failure(pfn, 0))
-			set_mce_nospec(pfn);
+			set_mce_nospec(pfn, whole_page(mce));
 	}
 
 	return NOTIFY_OK;
@@ -1086,7 +1093,7 @@ static int do_memory_failure(struct mce *m)
 	if (ret)
 		pr_err("Memory error not recovered");
 	else
-		set_mce_nospec(m->addr >> PAGE_SHIFT);
+		set_mce_nospec(m->addr >> PAGE_SHIFT, whole_page(m));
 	return ret;
 }
 
diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c
index 5d108f70f315..799b74b1582c 100644
--- a/arch/x86/kernel/cpu/mce/inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@@ -511,7 +511,7 @@ static void do_inject(void)
 	 */
 	if (inj_type == DFR_INT_INJ) {
 		i_mce.status |= MCI_STATUS_DEFERRED;
-		i_mce.status |= (i_mce.status & ~MCI_STATUS_UC);
+		i_mce.status &= ~MCI_STATUS_UC;
 	}
 
 	/*
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index e43eb6732630..693c8cfac75d 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -489,17 +489,18 @@ static void intel_ppin_init(struct cpuinfo_x86 *c)
 			return;
 
 		if ((val & 3UL) == 1UL) {
-			/* PPIN available but disabled: */
+			/* PPIN locked in disabled mode */
 			return;
 		}
 
-		/* If PPIN is disabled, but not locked, try to enable: */
-		if (!(val & 3UL)) {
+		/* If PPIN is disabled, try to enable */
+		if (!(val & 2UL)) {
 			wrmsrl_safe(MSR_PPIN_CTL,  val | 2UL);
 			rdmsrl_safe(MSR_PPIN_CTL, &val);
 		}
 
-		if ((val & 3UL) == 2UL)
+		/* Is the enable bit set? */
+		if (val & 2UL)
 			set_cpu_cap(c, X86_FEATURE_INTEL_PPIN);
 	}
 }
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 7df29f08871b..920aa2f0b52b 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -220,8 +220,8 @@ static void __init ms_hyperv_init_platform(void)
 	ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES);
 	ms_hyperv.hints    = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO);
 
-	pr_info("Hyper-V: features 0x%x, hints 0x%x\n",
-		ms_hyperv.features, ms_hyperv.hints);
+	pr_info("Hyper-V: features 0x%x, hints 0x%x, misc 0x%x\n",
+		ms_hyperv.features, ms_hyperv.hints, ms_hyperv.misc_features);
 
 	ms_hyperv.max_vp_index = cpuid_eax(HYPERV_CPUID_IMPLEMENT_LIMITS);
 	ms_hyperv.max_lp_index = cpuid_ebx(HYPERV_CPUID_IMPLEMENT_LIMITS);
@@ -256,6 +256,16 @@ static void __init ms_hyperv_init_platform(void)
 			cpuid_eax(HYPERV_CPUID_NESTED_FEATURES);
 	}
 
+	/*
+	 * Hyper-V expects to get crash register data or kmsg when
+	 * crash enlightment is available and system crashes. Set
+	 * crash_kexec_post_notifiers to be true to make sure that
+	 * calling crash enlightment interface before running kdump
+	 * kernel.
+	 */
+	if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE)
+		crash_kexec_post_notifiers = true;
+
 #ifdef CONFIG_X86_LOCAL_APIC
 	if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS &&
 	    ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) {
@@ -266,9 +276,9 @@ static void __init ms_hyperv_init_platform(void)
 
 		rdmsrl(HV_X64_MSR_APIC_FREQUENCY, hv_lapic_frequency);
 		hv_lapic_frequency = div_u64(hv_lapic_frequency, HZ);
-		lapic_timer_frequency = hv_lapic_frequency;
+		lapic_timer_period = hv_lapic_frequency;
 		pr_info("Hyper-V: LAPIC Timer Frequency: %#x\n",
-			lapic_timer_frequency);
+			lapic_timer_period);
 	}
 
 	register_nmi_handler(NMI_UNKNOWN, hv_nmi_unknown, NMI_FLAG_FIRST,
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 03eb90d00af0..d8cc5223b7ce 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -578,6 +578,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 	d->id = id;
 	cpumask_set_cpu(cpu, &d->cpu_mask);
 
+	rdt_domain_reconfigure_cdp(r);
+
 	if (r->alloc_capable && domain_setup_ctrlval(r, d)) {
 		kfree(d);
 		return;
@@ -618,7 +620,7 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 		if (static_branch_unlikely(&rdt_mon_enable_key))
 			rmdir_mondata_subdir_allrdtgrp(r, d->id);
 		list_del(&d->list);
-		if (is_mbm_enabled())
+		if (r->mon_capable && is_mbm_enabled())
 			cancel_delayed_work(&d->mbm_over);
 		if (is_llc_occupancy_enabled() &&  has_busy_rmid(r, d)) {
 			/*
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index e49b77283924..3dd13f3a8b23 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -57,6 +57,7 @@ static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc)
 }
 
 DECLARE_STATIC_KEY_FALSE(rdt_enable_key);
+DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key);
 
 /**
  * struct mon_evt - Entry in the event list of a resource
@@ -600,5 +601,6 @@ bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d);
 void __check_limbo(struct rdt_domain *d, bool force_free);
 bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r);
 bool cbm_validate_amd(char *buf, u32 *data, struct rdt_resource *r);
+void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
 
 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 397206f23d14..773124b0e18a 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -514,7 +514,7 @@ void mbm_handle_overflow(struct work_struct *work)
 
 	mutex_lock(&rdtgroup_mutex);
 
-	if (!static_branch_likely(&rdt_enable_key))
+	if (!static_branch_likely(&rdt_mon_enable_key))
 		goto out_unlock;
 
 	d = get_domain_from_cpu(cpu, &rdt_resources_all[RDT_RESOURCE_L3]);
@@ -543,7 +543,7 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
 	unsigned long delay = msecs_to_jiffies(delay_ms);
 	int cpu;
 
-	if (!static_branch_likely(&rdt_enable_key))
+	if (!static_branch_likely(&rdt_mon_enable_key))
 		return;
 	cpu = cpumask_any(&dom->cpu_mask);
 	dom->mbm_work_cpu = cpu;
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 74f51676ca4e..81200c253002 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -1027,6 +1027,7 @@ static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d,
 	_d_cdp = rdt_find_domain(_r_cdp, d->id, NULL);
 	if (WARN_ON(IS_ERR_OR_NULL(_d_cdp))) {
 		_r_cdp = NULL;
+		_d_cdp = NULL;
 		ret = -EINVAL;
 	}
 
@@ -1741,9 +1742,6 @@ static int set_cache_qos_cfg(int level, bool enable)
 	struct rdt_domain *d;
 	int cpu;
 
-	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
-		return -ENOMEM;
-
 	if (level == RDT_RESOURCE_L3)
 		update = l3_qos_cfg_update;
 	else if (level == RDT_RESOURCE_L2)
@@ -1751,6 +1749,9 @@ static int set_cache_qos_cfg(int level, bool enable)
 	else
 		return -EINVAL;
 
+	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
+		return -ENOMEM;
+
 	r_l = &rdt_resources_all[level];
 	list_for_each_entry(d, &r_l->domains, list) {
 		/* Pick one CPU from each domain instance to update MSR */
@@ -1769,6 +1770,19 @@ static int set_cache_qos_cfg(int level, bool enable)
 	return 0;
 }
 
+/* Restore the qos cfg state when a domain comes online */
+void rdt_domain_reconfigure_cdp(struct rdt_resource *r)
+{
+	if (!r->alloc_capable)
+		return;
+
+	if (r == &rdt_resources_all[RDT_RESOURCE_L2DATA])
+		l2_qos_cfg_update(&r->alloc_enabled);
+
+	if (r == &rdt_resources_all[RDT_RESOURCE_L3DATA])
+		l3_qos_cfg_update(&r->alloc_enabled);
+}
+
 /*
  * Enable or disable the MBA software controller
  * which helps user specify bandwidth in MBps.
@@ -1970,7 +1984,7 @@ static int rdt_get_tree(struct fs_context *fc)
 
 	if (rdt_mon_capable) {
 		ret = mongroup_create_dir(rdtgroup_default.kn,
-					  NULL, "mon_groups",
+					  &rdtgroup_default, "mon_groups",
 					  &kn_mongrp);
 		if (ret < 0)
 			goto out_info;
@@ -2206,7 +2220,11 @@ static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp)
 	list_for_each_entry_safe(sentry, stmp, head, mon.crdtgrp_list) {
 		free_rmid(sentry->mon.rmid);
 		list_del(&sentry->mon.crdtgrp_list);
-		kfree(sentry);
+
+		if (atomic_read(&sentry->waitcount) != 0)
+			sentry->flags = RDT_DELETED;
+		else
+			kfree(sentry);
 	}
 }
 
@@ -2244,7 +2262,11 @@ static void rmdir_all_sub(void)
 
 		kernfs_remove(rdtgrp->kn);
 		list_del(&rdtgrp->rdtgroup_list);
-		kfree(rdtgrp);
+
+		if (atomic_read(&rdtgrp->waitcount) != 0)
+			rdtgrp->flags = RDT_DELETED;
+		else
+			kfree(rdtgrp);
 	}
 	/* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */
 	update_closid_rmid(cpu_online_mask, &rdtgroup_default);
@@ -2447,7 +2469,7 @@ static int mkdir_mondata_all(struct kernfs_node *parent_kn,
 	/*
 	 * Create the mon_data directory first.
 	 */
-	ret = mongroup_create_dir(parent_kn, NULL, "mon_data", &kn);
+	ret = mongroup_create_dir(parent_kn, prgrp, "mon_data", &kn);
 	if (ret)
 		return ret;
 
@@ -2646,7 +2668,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 	uint files = 0;
 	int ret;
 
-	prdtgrp = rdtgroup_kn_lock_live(prgrp_kn);
+	prdtgrp = rdtgroup_kn_lock_live(parent_kn);
 	if (!prdtgrp) {
 		ret = -ENODEV;
 		goto out_unlock;
@@ -2719,7 +2741,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 	kernfs_activate(kn);
 
 	/*
-	 * The caller unlocks the prgrp_kn upon success.
+	 * The caller unlocks the parent_kn upon success.
 	 */
 	return 0;
 
@@ -2730,7 +2752,7 @@ out_destroy:
 out_free_rgrp:
 	kfree(rdtgrp);
 out_unlock:
-	rdtgroup_kn_unlock(prgrp_kn);
+	rdtgroup_kn_unlock(parent_kn);
 	return ret;
 }
 
@@ -2768,7 +2790,7 @@ static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn,
 	 */
 	list_add_tail(&rdtgrp->mon.crdtgrp_list, &prgrp->mon.crdtgrp_list);
 
-	rdtgroup_kn_unlock(prgrp_kn);
+	rdtgroup_kn_unlock(parent_kn);
 	return ret;
 }
 
@@ -2811,7 +2833,7 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
 		 * Create an empty mon_groups directory to hold the subset
 		 * of tasks and cpus to monitor.
 		 */
-		ret = mongroup_create_dir(kn, NULL, "mon_groups", NULL);
+		ret = mongroup_create_dir(kn, rdtgrp, "mon_groups", NULL);
 		if (ret) {
 			rdt_last_cmd_puts("kernfs subdir error\n");
 			goto out_del_list;
@@ -2827,7 +2849,7 @@ out_id_free:
 out_common_fail:
 	mkdir_rdt_prepare_clean(rdtgrp);
 out_unlock:
-	rdtgroup_kn_unlock(prgrp_kn);
+	rdtgroup_kn_unlock(parent_kn);
 	return ret;
 }
 
@@ -2953,13 +2975,13 @@ static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp,
 	closid_free(rdtgrp->closid);
 	free_rmid(rdtgrp->mon.rmid);
 
+	rdtgroup_ctrl_remove(kn, rdtgrp);
+
 	/*
 	 * Free all the child monitor group rmids.
 	 */
 	free_all_child_rdtgrp(rdtgrp);
 
-	rdtgroup_ctrl_remove(kn, rdtgrp);
-
 	return 0;
 }
 
@@ -2986,7 +3008,8 @@ static int rdtgroup_rmdir(struct kernfs_node *kn)
 	 * If the rdtgroup is a mon group and parent directory
 	 * is a valid "mon_groups" directory, remove the mon group.
 	 */
-	if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn) {
+	if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn &&
+	    rdtgrp != &rdtgroup_default) {
 		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
 		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
 			ret = rdtgroup_ctrl_remove(kn, rdtgrp);
diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c
index 3e20d322bc98..032509adf9de 100644
--- a/arch/x86/kernel/cpu/tsx.c
+++ b/arch/x86/kernel/cpu/tsx.c
@@ -115,11 +115,12 @@ void __init tsx_init(void)
 		tsx_disable();
 
 		/*
-		 * tsx_disable() will change the state of the
-		 * RTM CPUID bit.  Clear it here since it is now
-		 * expected to be not set.
+		 * tsx_disable() will change the state of the RTM and HLE CPUID
+		 * bits. Clear them here since they are now expected to be not
+		 * set.
 		 */
 		setup_clear_cpu_cap(X86_FEATURE_RTM);
+		setup_clear_cpu_cap(X86_FEATURE_HLE);
 	} else if (tsx_ctrl_state == TSX_CTRL_ENABLE) {
 
 		/*
@@ -131,10 +132,10 @@ void __init tsx_init(void)
 		tsx_enable();
 
 		/*
-		 * tsx_enable() will change the state of the
-		 * RTM CPUID bit.  Force it here since it is now
-		 * expected to be set.
+		 * tsx_enable() will change the state of the RTM and HLE CPUID
+		 * bits. Force them here since they are now expected to be set.
 		 */
 		setup_force_cpu_cap(X86_FEATURE_RTM);
+		setup_force_cpu_cap(X86_FEATURE_HLE);
 	}
 }
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 34ab4161fc39..88569536d529 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -158,7 +158,7 @@ static void __init vmware_platform_setup(void)
 
 #ifdef CONFIG_X86_LOCAL_APIC
 		/* Skip lapic calibration since we know the bus frequency. */
-		lapic_timer_frequency = ecx / HZ;
+		lapic_timer_period = ecx / HZ;
 		pr_info("Host bus clock speed read from hypervisor : %u Hz\n",
 			ecx);
 #endif
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 21f4b9d352fb..7c9259306d74 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -713,6 +713,8 @@ static struct chipset early_qrk[] __initdata = {
 		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
 	{ PCI_VENDOR_ID_INTEL, 0x3ec4,
 		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
+	{ PCI_VENDOR_ID_INTEL, 0x8a12,
+		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
 	{ PCI_VENDOR_ID_BROADCOM, 0x4331,
 	  PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset},
 	{}
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 649fbc3fcf9f..8ba0e53dec75 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -113,6 +113,12 @@ static void __kernel_fpu_begin(void)
 		}
 	}
 	__cpu_invalidate_fpregs_state();
+
+	if (boot_cpu_has(X86_FEATURE_XMM))
+		ldmxcsr(MXCSR_DEFAULT);
+
+	if (boot_cpu_has(X86_FEATURE_FPU))
+		asm volatile ("fninit");
 }
 
 static void __kernel_fpu_end(void)
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 0071b794ed19..400a05e1c1c5 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -352,6 +352,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 			fpregs_unlock();
 			return 0;
 		}
+		fpregs_deactivate(fpu);
 		fpregs_unlock();
 	}
 
@@ -403,6 +404,8 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 	}
 	if (!ret)
 		fpregs_mark_activate();
+	else
+		fpregs_deactivate(fpu);
 	fpregs_unlock();
 
 err_out:
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 3c36dd1784db..085afecd878c 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -959,18 +959,31 @@ static inline bool xfeatures_mxcsr_quirk(u64 xfeatures)
 	return true;
 }
 
-/*
- * This is similar to user_regset_copyout(), but will not add offset to
- * the source data pointer or increment pos, count, kbuf, and ubuf.
- */
-static inline void
-__copy_xstate_to_kernel(void *kbuf, const void *data,
-			unsigned int offset, unsigned int size, unsigned int size_total)
+static void fill_gap(unsigned to, void **kbuf, unsigned *pos, unsigned *count)
 {
-	if (offset < size_total) {
-		unsigned int copy = min(size, size_total - offset);
+	if (*pos < to) {
+		unsigned size = to - *pos;
+
+		if (size > *count)
+			size = *count;
+		memcpy(*kbuf, (void *)&init_fpstate.xsave + *pos, size);
+		*kbuf += size;
+		*pos += size;
+		*count -= size;
+	}
+}
 
-		memcpy(kbuf + offset, data, copy);
+static void copy_part(unsigned offset, unsigned size, void *from,
+			void **kbuf, unsigned *pos, unsigned *count)
+{
+	fill_gap(offset, kbuf, pos, count);
+	if (size > *count)
+		size = *count;
+	if (size) {
+		memcpy(*kbuf, from, size);
+		*kbuf += size;
+		*pos += size;
+		*count -= size;
 	}
 }
 
@@ -983,8 +996,9 @@ __copy_xstate_to_kernel(void *kbuf, const void *data,
  */
 int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total)
 {
-	unsigned int offset, size;
 	struct xstate_header header;
+	const unsigned off_mxcsr = offsetof(struct fxregs_state, mxcsr);
+	unsigned count = size_total;
 	int i;
 
 	/*
@@ -1000,46 +1014,42 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of
 	header.xfeatures = xsave->header.xfeatures;
 	header.xfeatures &= ~XFEATURE_MASK_SUPERVISOR;
 
+	if (header.xfeatures & XFEATURE_MASK_FP)
+		copy_part(0, off_mxcsr,
+			  &xsave->i387, &kbuf, &offset_start, &count);
+	if (header.xfeatures & (XFEATURE_MASK_SSE | XFEATURE_MASK_YMM))
+		copy_part(off_mxcsr, MXCSR_AND_FLAGS_SIZE,
+			  &xsave->i387.mxcsr, &kbuf, &offset_start, &count);
+	if (header.xfeatures & XFEATURE_MASK_FP)
+		copy_part(offsetof(struct fxregs_state, st_space), 128,
+			  &xsave->i387.st_space, &kbuf, &offset_start, &count);
+	if (header.xfeatures & XFEATURE_MASK_SSE)
+		copy_part(xstate_offsets[XFEATURE_SSE], 256,
+			  &xsave->i387.xmm_space, &kbuf, &offset_start, &count);
+	/*
+	 * Fill xsave->i387.sw_reserved value for ptrace frame:
+	 */
+	copy_part(offsetof(struct fxregs_state, sw_reserved), 48,
+		  xstate_fx_sw_bytes, &kbuf, &offset_start, &count);
 	/*
 	 * Copy xregs_state->header:
 	 */
-	offset = offsetof(struct xregs_state, header);
-	size = sizeof(header);
-
-	__copy_xstate_to_kernel(kbuf, &header, offset, size, size_total);
+	copy_part(offsetof(struct xregs_state, header), sizeof(header),
+		  &header, &kbuf, &offset_start, &count);
 
-	for (i = 0; i < XFEATURE_MAX; i++) {
+	for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
 		/*
 		 * Copy only in-use xstates:
 		 */
 		if ((header.xfeatures >> i) & 1) {
 			void *src = __raw_xsave_addr(xsave, i);
 
-			offset = xstate_offsets[i];
-			size = xstate_sizes[i];
-
-			/* The next component has to fit fully into the output buffer: */
-			if (offset + size > size_total)
-				break;
-
-			__copy_xstate_to_kernel(kbuf, src, offset, size, size_total);
+			copy_part(xstate_offsets[i], xstate_sizes[i],
+				  src, &kbuf, &offset_start, &count);
 		}
 
 	}
-
-	if (xfeatures_mxcsr_quirk(header.xfeatures)) {
-		offset = offsetof(struct fxregs_state, mxcsr);
-		size = MXCSR_AND_FLAGS_SIZE;
-		__copy_xstate_to_kernel(kbuf, &xsave->i387.mxcsr, offset, size, size_total);
-	}
-
-	/*
-	 * Fill xsave->i387.sw_reserved value for ptrace frame:
-	 */
-	offset = offsetof(struct fxregs_state, sw_reserved);
-	size = sizeof(xstate_fx_sw_bytes);
-
-	__copy_xstate_to_kernel(kbuf, xstate_fx_sw_bytes, offset, size, size_total);
+	fill_gap(size_total, &kbuf, &offset_start, &count);
 
 	return 0;
 }
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 519649ddf100..fe522691ac71 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -207,7 +207,7 @@ spurious_8259A_irq:
 		 * lets ACK and report it. [once per IRQ]
 		 */
 		if (!(spurious_irq_mask & irqmask)) {
-			printk(KERN_DEBUG
+			printk_deferred(KERN_DEBUG
 			       "spurious 8259A interrupt: IRQ%d.\n", irq);
 			spurious_irq_mask |= irqmask;
 		}
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index 87ef69a72c52..7bb4c3cbf4dc 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -318,7 +318,11 @@ void __init idt_setup_apic_and_irq_gates(void)
 
 #ifdef CONFIG_X86_LOCAL_APIC
 	for_each_clear_bit_from(i, system_vectors, NR_VECTORS) {
-		set_bit(i, system_vectors);
+		/*
+		 * Don't set the non assigned system vectors in the
+		 * system_vectors bitmap. Otherwise they show up in
+		 * /proc/interrupts.
+		 */
 		entry = spurious_entries_start + 8 * (i - FIRST_SYSTEM_VECTOR);
 		set_intr_gate(i, entry);
 	}
diff --git a/arch/x86/kernel/ima_arch.c b/arch/x86/kernel/ima_arch.c
index 4c407833faca..fa188de3f424 100644
--- a/arch/x86/kernel/ima_arch.c
+++ b/arch/x86/kernel/ima_arch.c
@@ -10,8 +10,6 @@ extern struct boot_params boot_params;
 
 static enum efi_secureboot_mode get_sb_mode(void)
 {
-	efi_char16_t efi_SecureBoot_name[] = L"SecureBoot";
-	efi_char16_t efi_SetupMode_name[] = L"SecureBoot";
 	efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID;
 	efi_status_t status;
 	unsigned long size;
@@ -25,7 +23,7 @@ static enum efi_secureboot_mode get_sb_mode(void)
 	}
 
 	/* Get variable contents into buffer */
-	status = efi.get_variable(efi_SecureBoot_name, &efi_variable_guid,
+	status = efi.get_variable(L"SecureBoot", &efi_variable_guid,
 				  NULL, &size, &secboot);
 	if (status == EFI_NOT_FOUND) {
 		pr_info("ima: secureboot mode disabled\n");
@@ -38,7 +36,7 @@ static enum efi_secureboot_mode get_sb_mode(void)
 	}
 
 	size = sizeof(setupmode);
-	status = efi.get_variable(efi_SetupMode_name, &efi_variable_guid,
+	status = efi.get_variable(L"SetupMode", &efi_variable_guid,
 				  NULL, &size, &setupmode);
 
 	if (status != EFI_SUCCESS)	/* ignore unknown SetupMode */
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 6bf6517a05bb..5bfa35f3dbac 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -52,7 +52,7 @@ static int map_irq_stack(unsigned int cpu)
 		pages[i] = pfn_to_page(pa >> PAGE_SHIFT);
 	}
 
-	va = vmap(pages, IRQ_STACK_SIZE / PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL);
+	va = vmap(pages, IRQ_STACK_SIZE / PAGE_SIZE, VM_MAP, PAGE_KERNEL);
 	if (!va)
 		return -ENOMEM;
 
diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c
index 1b2ee55a2dfb..ba95bc70460d 100644
--- a/arch/x86/kernel/jailhouse.c
+++ b/arch/x86/kernel/jailhouse.c
@@ -45,7 +45,7 @@ static void jailhouse_get_wallclock(struct timespec64 *now)
 
 static void __init jailhouse_timer_init(void)
 {
-	lapic_timer_frequency = setup_data.apic_khz * (1000 / HZ);
+	lapic_timer_period = setup_data.apic_khz * (1000 / HZ);
 }
 
 static unsigned long jailhouse_get_tsc(void)
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index bd17dbb15d6a..27159a40dc93 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -746,16 +746,11 @@ asm(
 NOKPROBE_SYMBOL(kretprobe_trampoline);
 STACK_FRAME_NON_STANDARD(kretprobe_trampoline);
 
-static struct kprobe kretprobe_kprobe = {
-	.addr = (void *)kretprobe_trampoline,
-};
-
 /*
  * Called from kretprobe_trampoline
  */
 __used __visible void *trampoline_handler(struct pt_regs *regs)
 {
-	struct kprobe_ctlblk *kcb;
 	struct kretprobe_instance *ri = NULL;
 	struct hlist_head *head, empty_rp;
 	struct hlist_node *tmp;
@@ -765,16 +760,12 @@ __used __visible void *trampoline_handler(struct pt_regs *regs)
 	void *frame_pointer;
 	bool skipped = false;
 
-	preempt_disable();
-
 	/*
 	 * Set a dummy kprobe for avoiding kretprobe recursion.
 	 * Since kretprobe never run in kprobe handler, kprobe must not
 	 * be running at this point.
 	 */
-	kcb = get_kprobe_ctlblk();
-	__this_cpu_write(current_kprobe, &kretprobe_kprobe);
-	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+	kprobe_busy_begin();
 
 	INIT_HLIST_HEAD(&empty_rp);
 	kretprobe_hash_lock(current, &head, &flags);
@@ -850,7 +841,7 @@ __used __visible void *trampoline_handler(struct pt_regs *regs)
 			__this_cpu_write(current_kprobe, &ri->rp->kp);
 			ri->ret_addr = correct_ret_addr;
 			ri->rp->handler(ri, regs);
-			__this_cpu_write(current_kprobe, &kretprobe_kprobe);
+			__this_cpu_write(current_kprobe, &kprobe_busy);
 		}
 
 		recycle_rp_inst(ri, &empty_rp);
@@ -866,8 +857,7 @@ __used __visible void *trampoline_handler(struct pt_regs *regs)
 
 	kretprobe_hash_unlock(current, &flags);
 
-	__this_cpu_write(current_kprobe, NULL);
-	preempt_enable();
+	kprobe_busy_end();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 4df7705022b9..d7f40ad34432 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -104,18 +104,22 @@ static int __init nmi_warning_debugfs(void)
 }
 fs_initcall(nmi_warning_debugfs);
 
-static void nmi_max_handler(struct irq_work *w)
+static void nmi_check_duration(struct nmiaction *action, u64 duration)
 {
-	struct nmiaction *a = container_of(w, struct nmiaction, irq_work);
+	u64 whole_msecs = READ_ONCE(action->max_duration);
 	int remainder_ns, decimal_msecs;
-	u64 whole_msecs = READ_ONCE(a->max_duration);
+
+	if (duration < nmi_longest_ns || duration < action->max_duration)
+		return;
+
+	action->max_duration = duration;
 
 	remainder_ns = do_div(whole_msecs, (1000 * 1000));
 	decimal_msecs = remainder_ns / 1000;
 
 	printk_ratelimited(KERN_INFO
 		"INFO: NMI handler (%ps) took too long to run: %lld.%03d msecs\n",
-		a->handler, whole_msecs, decimal_msecs);
+		action->handler, whole_msecs, decimal_msecs);
 }
 
 static int nmi_handle(unsigned int type, struct pt_regs *regs)
@@ -142,11 +146,7 @@ static int nmi_handle(unsigned int type, struct pt_regs *regs)
 		delta = sched_clock() - delta;
 		trace_nmi_handler(a->handler, (int)delta, thishandled);
 
-		if (delta < nmi_longest_ns || delta < a->max_duration)
-			continue;
-
-		a->max_duration = delta;
-		irq_work_queue(&a->irq_work);
+		nmi_check_duration(a, delta);
 	}
 
 	rcu_read_unlock();
@@ -164,8 +164,6 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action)
 	if (!action->handler)
 		return -EINVAL;
 
-	init_irq_work(&action->irq_work, nmi_max_handler);
-
 	raw_spin_lock_irqsave(&desc->lock, flags);
 
 	/*
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 75fea0d48c0e..a04e43ff4b5e 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -428,28 +428,20 @@ static __always_inline void __speculation_ctrl_update(unsigned long tifp,
 
 	lockdep_assert_irqs_disabled();
 
-	/*
-	 * If TIF_SSBD is different, select the proper mitigation
-	 * method. Note that if SSBD mitigation is disabled or permanentely
-	 * enabled this branch can't be taken because nothing can set
-	 * TIF_SSBD.
-	 */
-	if (tif_diff & _TIF_SSBD) {
-		if (static_cpu_has(X86_FEATURE_VIRT_SSBD)) {
+	/* Handle change of TIF_SSBD depending on the mitigation method. */
+	if (static_cpu_has(X86_FEATURE_VIRT_SSBD)) {
+		if (tif_diff & _TIF_SSBD)
 			amd_set_ssb_virt_state(tifn);
-		} else if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD)) {
+	} else if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD)) {
+		if (tif_diff & _TIF_SSBD)
 			amd_set_core_ssb_state(tifn);
-		} else if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) ||
-			   static_cpu_has(X86_FEATURE_AMD_SSBD)) {
-			msr |= ssbd_tif_to_spec_ctrl(tifn);
-			updmsr  = true;
-		}
+	} else if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) ||
+		   static_cpu_has(X86_FEATURE_AMD_SSBD)) {
+		updmsr |= !!(tif_diff & _TIF_SSBD);
+		msr |= ssbd_tif_to_spec_ctrl(tifn);
 	}
 
-	/*
-	 * Only evaluate TIF_SPEC_IB if conditional STIBP is enabled,
-	 * otherwise avoid the MSR write.
-	 */
+	/* Only evaluate TIF_SPEC_IB if conditional STIBP is enabled. */
 	if (IS_ENABLED(CONFIG_SMP) &&
 	    static_branch_unlikely(&switch_to_cond_stibp)) {
 		updmsr |= !!(tif_diff & _TIF_SPEC_IB);
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 250e4c4ac6d9..d02874cddda3 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -326,7 +326,7 @@ static unsigned long x86_fsgsbase_read_task(struct task_struct *task,
 		 */
 		mutex_lock(&task->mm->context.lock);
 		ldt = task->mm->context.ldt;
-		if (unlikely(idx >= ldt->nr_entries))
+		if (unlikely(!ldt || idx >= ldt->nr_entries))
 			base = 0;
 		else
 			base = get_desc_base(ldt->entries + idx);
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 09d6bded3c1e..3f677832fc12 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -197,6 +197,14 @@ static const struct dmi_system_id reboot_dmi_table[] __initconst = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "MacBook5"),
 		},
 	},
+	{	/* Handle problems with rebooting on Apple MacBook6,1 */
+		.callback = set_pci_reboot,
+		.ident = "Apple MacBook6,1",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "MacBook6,1"),
+		},
+	},
 	{	/* Handle problems with rebooting on Apple MacBookPro5 */
 		.callback = set_pci_reboot,
 		.ident = "Apple MacBookPro5",
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 0bacaeaeeac4..5fe11d5d29c1 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -257,6 +257,14 @@ static void notrace start_secondary(void *unused)
 
 	wmb();
 	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
+
+	/*
+	 * Prevent tail call to cpu_startup_entry() because the stack protector
+	 * guard has been changed a couple of function calls up, in
+	 * boot_init_stack_canary() and must not be checked before tail calling
+	 * another function.
+	 */
+	prevent_tail_call_optimization();
 }
 
 /**
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 2d6898c2cb64..6d83b4b857e6 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -58,7 +58,6 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry,
 			 * or a page fault), which can make frame pointers
 			 * unreliable.
 			 */
-
 			if (IS_ENABLED(CONFIG_FRAME_POINTER))
 				return -EINVAL;
 		}
@@ -81,10 +80,6 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry,
 	if (unwind_error(&state))
 		return -EINVAL;
 
-	/* Success path for non-user tasks, i.e. kthreads and idle tasks */
-	if (!(task->flags & (PF_KTHREAD | PF_IDLE)))
-		return -EINVAL;
-
 	return 0;
 }
 
diff --git a/arch/x86/kernel/sysfb_simplefb.c b/arch/x86/kernel/sysfb_simplefb.c
index 01f0e2263b86..298fc1edd9c9 100644
--- a/arch/x86/kernel/sysfb_simplefb.c
+++ b/arch/x86/kernel/sysfb_simplefb.c
@@ -90,11 +90,11 @@ __init int create_simplefb(const struct screen_info *si,
 	if (si->orig_video_isVGA == VIDEO_TYPE_VLFB)
 		size <<= 16;
 	length = mode->height * mode->stride;
-	length = PAGE_ALIGN(length);
 	if (length > size) {
 		printk(KERN_WARNING "sysfb: VRAM smaller than advertised\n");
 		return -EINVAL;
 	}
+	length = PAGE_ALIGN(length);
 
 	/* setup IORESOURCE_MEM as framebuffer memory */
 	memset(&res, 0, sizeof(res));
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index 2acbab329754..befb70359551 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -25,10 +25,6 @@
 #include <asm/hpet.h>
 #include <asm/time.h>
 
-#ifdef CONFIG_X86_64
-__visible volatile unsigned long jiffies __cacheline_aligned_in_smp = INITIAL_JIFFIES;
-#endif
-
 unsigned long profile_pc(struct pt_regs *regs)
 {
 	unsigned long pc = instruction_pointer(regs);
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index c42baeaf8100..f30730621c8a 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -665,6 +665,16 @@ unsigned long native_calibrate_tsc(void)
 	if (boot_cpu_data.x86_model == INTEL_FAM6_ATOM_GOLDMONT)
 		setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
 
+#ifdef CONFIG_X86_LOCAL_APIC
+	/*
+	 * The local APIC appears to be fed by the core crystal clock
+	 * (which sounds entirely sensible). We can set the global
+	 * lapic_timer_period here to avoid having to calibrate the APIC
+	 * timer later.
+	 */
+	lapic_timer_period = crystal_khz * 1000 / HZ;
+#endif
+
 	return crystal_khz * ebx_numerator / eax_denominator;
 }
 
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index 3d0e9aeea7c8..6f56071aa909 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -15,18 +15,46 @@
 #include <asm/param.h>
 #include <asm/tsc.h>
 
-#define MAX_NUM_FREQS	9
+#define MAX_NUM_FREQS	16 /* 4 bits to select the frequency */
+
+/*
+ * The frequency numbers in the SDM are e.g. 83.3 MHz, which does not contain a
+ * lot of accuracy which leads to clock drift. As far as we know Bay Trail SoCs
+ * use a 25 MHz crystal and Cherry Trail uses a 19.2 MHz crystal, the crystal
+ * is the source clk for a root PLL which outputs 1600 and 100 MHz. It is
+ * unclear if the root PLL outputs are used directly by the CPU clock PLL or
+ * if there is another PLL in between.
+ * This does not matter though, we can model the chain of PLLs as a single PLL
+ * with a quotient equal to the quotients of all PLLs in the chain multiplied.
+ * So we can create a simplified model of the CPU clock setup using a reference
+ * clock of 100 MHz plus a quotient which gets us as close to the frequency
+ * from the SDM as possible.
+ * For the 83.3 MHz example from above this would give us 100 MHz * 5 / 6 =
+ * 83 and 1/3 MHz, which matches exactly what has been measured on actual hw.
+ */
+#define TSC_REFERENCE_KHZ 100000
+
+struct muldiv {
+	u32 multiplier;
+	u32 divider;
+};
 
 /*
  * If MSR_PERF_STAT[31] is set, the maximum resolved bus ratio can be
  * read in MSR_PLATFORM_ID[12:8], otherwise in MSR_PERF_STAT[44:40].
  * Unfortunately some Intel Atom SoCs aren't quite compliant to this,
  * so we need manually differentiate SoC families. This is what the
- * field msr_plat does.
+ * field use_msr_plat does.
  */
 struct freq_desc {
-	u8 msr_plat;	/* 1: use MSR_PLATFORM_INFO, 0: MSR_IA32_PERF_STATUS */
+	bool use_msr_plat;
+	struct muldiv muldiv[MAX_NUM_FREQS];
+	/*
+	 * Some CPU frequencies in the SDM do not map to known PLL freqs, in
+	 * that case the muldiv array is empty and the freqs array is used.
+	 */
 	u32 freqs[MAX_NUM_FREQS];
+	u32 mask;
 };
 
 /*
@@ -35,27 +63,74 @@ struct freq_desc {
  * by MSR based on SDM.
  */
 static const struct freq_desc freq_desc_pnw = {
-	0, { 0, 0, 0, 0, 0, 99840, 0, 83200 }
+	.use_msr_plat = false,
+	.freqs = { 0, 0, 0, 0, 0, 99840, 0, 83200 },
+	.mask = 0x07,
 };
 
 static const struct freq_desc freq_desc_clv = {
-	0, { 0, 133200, 0, 0, 0, 99840, 0, 83200 }
+	.use_msr_plat = false,
+	.freqs = { 0, 133200, 0, 0, 0, 99840, 0, 83200 },
+	.mask = 0x07,
 };
 
+/*
+ * Bay Trail SDM MSR_FSB_FREQ frequencies simplified PLL model:
+ *  000:   100 *  5 /  6  =  83.3333 MHz
+ *  001:   100 *  1 /  1  = 100.0000 MHz
+ *  010:   100 *  4 /  3  = 133.3333 MHz
+ *  011:   100 *  7 /  6  = 116.6667 MHz
+ *  100:   100 *  4 /  5  =  80.0000 MHz
+ */
 static const struct freq_desc freq_desc_byt = {
-	1, { 83300, 100000, 133300, 116700, 80000, 0, 0, 0 }
+	.use_msr_plat = true,
+	.muldiv = { { 5, 6 }, { 1, 1 }, { 4, 3 }, { 7, 6 },
+		    { 4, 5 } },
+	.mask = 0x07,
 };
 
+/*
+ * Cherry Trail SDM MSR_FSB_FREQ frequencies simplified PLL model:
+ * 0000:   100 *  5 /  6  =  83.3333 MHz
+ * 0001:   100 *  1 /  1  = 100.0000 MHz
+ * 0010:   100 *  4 /  3  = 133.3333 MHz
+ * 0011:   100 *  7 /  6  = 116.6667 MHz
+ * 0100:   100 *  4 /  5  =  80.0000 MHz
+ * 0101:   100 * 14 / 15  =  93.3333 MHz
+ * 0110:   100 *  9 / 10  =  90.0000 MHz
+ * 0111:   100 *  8 /  9  =  88.8889 MHz
+ * 1000:   100 *  7 /  8  =  87.5000 MHz
+ */
 static const struct freq_desc freq_desc_cht = {
-	1, { 83300, 100000, 133300, 116700, 80000, 93300, 90000, 88900, 87500 }
+	.use_msr_plat = true,
+	.muldiv = { { 5, 6 }, {  1,  1 }, { 4,  3 }, { 7, 6 },
+		    { 4, 5 }, { 14, 15 }, { 9, 10 }, { 8, 9 },
+		    { 7, 8 } },
+	.mask = 0x0f,
 };
 
+/*
+ * Merriefield SDM MSR_FSB_FREQ frequencies simplified PLL model:
+ * 0001:   100 *  1 /  1  = 100.0000 MHz
+ * 0010:   100 *  4 /  3  = 133.3333 MHz
+ */
 static const struct freq_desc freq_desc_tng = {
-	1, { 0, 100000, 133300, 0, 0, 0, 0, 0 }
+	.use_msr_plat = true,
+	.muldiv = { { 0, 0 }, { 1, 1 }, { 4, 3 } },
+	.mask = 0x07,
 };
 
+/*
+ * Moorefield SDM MSR_FSB_FREQ frequencies simplified PLL model:
+ * 0000:   100 *  5 /  6  =  83.3333 MHz
+ * 0001:   100 *  1 /  1  = 100.0000 MHz
+ * 0010:   100 *  4 /  3  = 133.3333 MHz
+ * 0011:   100 *  1 /  1  = 100.0000 MHz
+ */
 static const struct freq_desc freq_desc_ann = {
-	1, { 83300, 100000, 133300, 100000, 0, 0, 0, 0 }
+	.use_msr_plat = true,
+	.muldiv = { { 5, 6 }, { 1, 1 }, { 4, 3 }, { 1, 1 } },
+	.mask = 0x0f,
 };
 
 static const struct x86_cpu_id tsc_msr_cpu_ids[] = {
@@ -71,22 +146,24 @@ static const struct x86_cpu_id tsc_msr_cpu_ids[] = {
 /*
  * MSR-based CPU/TSC frequency discovery for certain CPUs.
  *
- * Set global "lapic_timer_frequency" to bus_clock_cycles/jiffy
+ * Set global "lapic_timer_period" to bus_clock_cycles/jiffy
  * Return processor base frequency in KHz, or 0 on failure.
  */
 unsigned long cpu_khz_from_msr(void)
 {
-	u32 lo, hi, ratio, freq;
+	u32 lo, hi, ratio, freq, tscref;
 	const struct freq_desc *freq_desc;
 	const struct x86_cpu_id *id;
+	const struct muldiv *md;
 	unsigned long res;
+	int index;
 
 	id = x86_match_cpu(tsc_msr_cpu_ids);
 	if (!id)
 		return 0;
 
 	freq_desc = (struct freq_desc *)id->driver_data;
-	if (freq_desc->msr_plat) {
+	if (freq_desc->use_msr_plat) {
 		rdmsr(MSR_PLATFORM_INFO, lo, hi);
 		ratio = (lo >> 8) & 0xff;
 	} else {
@@ -96,15 +173,31 @@ unsigned long cpu_khz_from_msr(void)
 
 	/* Get FSB FREQ ID */
 	rdmsr(MSR_FSB_FREQ, lo, hi);
+	index = lo & freq_desc->mask;
+	md = &freq_desc->muldiv[index];
 
-	/* Map CPU reference clock freq ID(0-7) to CPU reference clock freq(KHz) */
-	freq = freq_desc->freqs[lo & 0x7];
+	/*
+	 * Note this also catches cases where the index points to an unpopulated
+	 * part of muldiv, in that case the else will set freq and res to 0.
+	 */
+	if (md->divider) {
+		tscref = TSC_REFERENCE_KHZ * md->multiplier;
+		freq = DIV_ROUND_CLOSEST(tscref, md->divider);
+		/*
+		 * Multiplying by ratio before the division has better
+		 * accuracy than just calculating freq * ratio.
+		 */
+		res = DIV_ROUND_CLOSEST(tscref * ratio, md->divider);
+	} else {
+		freq = freq_desc->freqs[index];
+		res = freq * ratio;
+	}
 
-	/* TSC frequency = maximum resolved freq * maximum resolved bus ratio */
-	res = freq * ratio;
+	if (freq == 0)
+		pr_err("Error MSR_FSB_FREQ index %d is unknown\n", index);
 
 #ifdef CONFIG_X86_LOCAL_APIC
-	lapic_timer_frequency = (freq * 1000) / HZ;
+	lapic_timer_period = (freq * 1000) / HZ;
 #endif
 
 	/*
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 332ae6530fa8..187a86e0e753 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -142,9 +142,6 @@ static struct orc_entry *orc_find(unsigned long ip)
 {
 	static struct orc_entry *orc;
 
-	if (!orc_init)
-		return NULL;
-
 	if (ip == 0)
 		return &null_orc_entry;
 
@@ -314,12 +311,19 @@ EXPORT_SYMBOL_GPL(unwind_get_return_address);
 
 unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
 {
+	struct task_struct *task = state->task;
+
 	if (unwind_done(state))
 		return NULL;
 
 	if (state->regs)
 		return &state->regs->ip;
 
+	if (task != current && state->sp == task->thread.sp) {
+		struct inactive_task_frame *frame = (void *)task->thread.sp;
+		return &frame->ret_addr;
+	}
+
 	if (state->sp)
 		return (unsigned long *)state->sp - 1;
 
@@ -378,9 +382,38 @@ static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr
 	return true;
 }
 
+/*
+ * If state->regs is non-NULL, and points to a full pt_regs, just get the reg
+ * value from state->regs.
+ *
+ * Otherwise, if state->regs just points to IRET regs, and the previous frame
+ * had full regs, it's safe to get the value from the previous regs.  This can
+ * happen when early/late IRQ entry code gets interrupted by an NMI.
+ */
+static bool get_reg(struct unwind_state *state, unsigned int reg_off,
+		    unsigned long *val)
+{
+	unsigned int reg = reg_off/8;
+
+	if (!state->regs)
+		return false;
+
+	if (state->full_regs) {
+		*val = ((unsigned long *)state->regs)[reg];
+		return true;
+	}
+
+	if (state->prev_regs) {
+		*val = ((unsigned long *)state->prev_regs)[reg];
+		return true;
+	}
+
+	return false;
+}
+
 bool unwind_next_frame(struct unwind_state *state)
 {
-	unsigned long ip_p, sp, orig_ip = state->ip, prev_sp = state->sp;
+	unsigned long ip_p, sp, tmp, orig_ip = state->ip, prev_sp = state->sp;
 	enum stack_type prev_type = state->stack_info.type;
 	struct orc_entry *orc;
 	bool indirect = false;
@@ -398,8 +431,11 @@ bool unwind_next_frame(struct unwind_state *state)
 	/*
 	 * Find the orc_entry associated with the text address.
 	 *
-	 * Decrement call return addresses by one so they work for sibling
-	 * calls and calls to noreturn functions.
+	 * For a call frame (as opposed to a signal frame), state->ip points to
+	 * the instruction after the call.  That instruction's stack layout
+	 * could be different from the call instruction's layout, for example
+	 * if the call was to a noreturn function.  So get the ORC data for the
+	 * call instruction itself.
 	 */
 	orc = orc_find(state->signal ? state->ip : state->ip - 1);
 	if (!orc) {
@@ -442,39 +478,35 @@ bool unwind_next_frame(struct unwind_state *state)
 		break;
 
 	case ORC_REG_R10:
-		if (!state->regs || !state->full_regs) {
+		if (!get_reg(state, offsetof(struct pt_regs, r10), &sp)) {
 			orc_warn("missing regs for base reg R10 at ip %pB\n",
 				 (void *)state->ip);
 			goto err;
 		}
-		sp = state->regs->r10;
 		break;
 
 	case ORC_REG_R13:
-		if (!state->regs || !state->full_regs) {
+		if (!get_reg(state, offsetof(struct pt_regs, r13), &sp)) {
 			orc_warn("missing regs for base reg R13 at ip %pB\n",
 				 (void *)state->ip);
 			goto err;
 		}
-		sp = state->regs->r13;
 		break;
 
 	case ORC_REG_DI:
-		if (!state->regs || !state->full_regs) {
+		if (!get_reg(state, offsetof(struct pt_regs, di), &sp)) {
 			orc_warn("missing regs for base reg DI at ip %pB\n",
 				 (void *)state->ip);
 			goto err;
 		}
-		sp = state->regs->di;
 		break;
 
 	case ORC_REG_DX:
-		if (!state->regs || !state->full_regs) {
+		if (!get_reg(state, offsetof(struct pt_regs, dx), &sp)) {
 			orc_warn("missing regs for base reg DX at ip %pB\n",
 				 (void *)state->ip);
 			goto err;
 		}
-		sp = state->regs->dx;
 		break;
 
 	default:
@@ -501,6 +533,7 @@ bool unwind_next_frame(struct unwind_state *state)
 
 		state->sp = sp;
 		state->regs = NULL;
+		state->prev_regs = NULL;
 		state->signal = false;
 		break;
 
@@ -512,6 +545,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		}
 
 		state->regs = (struct pt_regs *)sp;
+		state->prev_regs = NULL;
 		state->full_regs = true;
 		state->signal = true;
 		break;
@@ -523,6 +557,8 @@ bool unwind_next_frame(struct unwind_state *state)
 			goto err;
 		}
 
+		if (state->full_regs)
+			state->prev_regs = state->regs;
 		state->regs = (void *)sp - IRET_FRAME_OFFSET;
 		state->full_regs = false;
 		state->signal = true;
@@ -531,14 +567,14 @@ bool unwind_next_frame(struct unwind_state *state)
 	default:
 		orc_warn("unknown .orc_unwind entry type %d for ip %pB\n",
 			 orc->type, (void *)orig_ip);
-		break;
+		goto err;
 	}
 
 	/* Find BP: */
 	switch (orc->bp_reg) {
 	case ORC_REG_UNDEFINED:
-		if (state->regs && state->full_regs)
-			state->bp = state->regs->bp;
+		if (get_reg(state, offsetof(struct pt_regs, bp), &tmp))
+			state->bp = tmp;
 		break;
 
 	case ORC_REG_PREV_SP:
@@ -585,17 +621,20 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 	memset(state, 0, sizeof(*state));
 	state->task = task;
 
+	if (!orc_init)
+		goto err;
+
 	/*
 	 * Refuse to unwind the stack of a task while it's executing on another
 	 * CPU.  This check is racy, but that's ok: the unwinder has other
 	 * checks to prevent it from going off the rails.
 	 */
 	if (task_on_another_cpu(task))
-		goto done;
+		goto err;
 
 	if (regs) {
 		if (user_mode(regs))
-			goto done;
+			goto the_end;
 
 		state->ip = regs->ip;
 		state->sp = regs->sp;
@@ -617,6 +656,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 		state->sp = task->thread.sp;
 		state->bp = READ_ONCE_NOCHECK(frame->bp);
 		state->ip = READ_ONCE_NOCHECK(frame->ret_addr);
+		state->signal = (void *)state->ip == ret_from_fork;
 	}
 
 	if (get_stack_info((unsigned long *)state->sp, state->task,
@@ -628,6 +668,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 		 * generate some kind of backtrace if this happens.
 		 */
 		void *next_page = (void *)PAGE_ALIGN((unsigned long)state->sp);
+		state->error = true;
 		if (get_stack_info(next_page, state->task, &state->stack_info,
 				   &state->stack_mask))
 			return;
@@ -648,13 +689,14 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 	/* Otherwise, skip ahead to the user-specified starting frame: */
 	while (!unwind_done(state) &&
 	       (!on_stack(&state->stack_info, first_frame, sizeof(long)) ||
-			state->sp <= (unsigned long)first_frame))
+			state->sp < (unsigned long)first_frame))
 		unwind_next_frame(state);
 
 	return;
 
-done:
+err:
+	state->error = true;
+the_end:
 	state->stack_info.type = STACK_TYPE_UNKNOWN;
-	return;
 }
 EXPORT_SYMBOL_GPL(__unwind_start);
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 4d1517022a14..96d8025ea1b0 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -36,13 +36,13 @@ OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT)
 #ifdef CONFIG_X86_32
 OUTPUT_ARCH(i386)
 ENTRY(phys_startup_32)
-jiffies = jiffies_64;
 #else
 OUTPUT_ARCH(i386:x86-64)
 ENTRY(phys_startup_64)
-jiffies_64 = jiffies;
 #endif
 
+jiffies = jiffies_64;
+
 #if defined(CONFIG_X86_64)
 /*
  * On 64-bit, align RODATA to 2MB so we retain large page mappings for
@@ -362,6 +362,7 @@ SECTIONS
 	.bss : AT(ADDR(.bss) - LOAD_OFFSET) {
 		__bss_start = .;
 		*(.bss..page_aligned)
+		. = ALIGN(PAGE_SIZE);
 		*(BSS_MAIN)
 		BSS_DECRYPTED
 		. = ALIGN(PAGE_SIZE);
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 4d2c84520bd2..e8e7d053c7b4 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -333,6 +333,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	unsigned f_umip = kvm_x86_ops->umip_emulated() ? F(UMIP) : 0;
 	unsigned f_intel_pt = kvm_x86_ops->pt_supported() ? F(INTEL_PT) : 0;
 	unsigned f_la57 = 0;
+	unsigned f_pku = kvm_x86_ops->pku_supported() ? F(PKU) : 0;
 
 	/* cpuid 1.edx */
 	const u32 kvm_cpuid_1_edx_x86_features =
@@ -399,7 +400,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 
 	/* cpuid 7.0.ecx*/
 	const u32 kvm_cpuid_7_0_ecx_x86_features =
-		F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ |
+		F(AVX512VBMI) | F(LA57) | 0 /*PKU*/ | 0 /*OSPKE*/ |
 		F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) |
 		F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) |
 		F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B);
@@ -494,6 +495,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			/* Set LA57 based on hardware capability. */
 			entry->ecx |= f_la57;
 			entry->ecx |= f_umip;
+			entry->ecx |= f_pku;
 			/* PKU is not yet implemented for shadow paging. */
 			if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE))
 				entry->ecx &= ~F(PKU);
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 2fe9912aeed7..5560ac478135 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -22,6 +22,7 @@
 #include "kvm_cache_regs.h"
 #include <asm/kvm_emulate.h>
 #include <linux/stringify.h>
+#include <asm/fpu/api.h>
 #include <asm/debugreg.h>
 #include <asm/nospec-branch.h>
 
@@ -1057,8 +1058,23 @@ static void fetch_register_operand(struct operand *op)
 	}
 }
 
+static void emulator_get_fpu(void)
+{
+	fpregs_lock();
+
+	fpregs_assert_state_consistent();
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		switch_fpu_return();
+}
+
+static void emulator_put_fpu(void)
+{
+	fpregs_unlock();
+}
+
 static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg)
 {
+	emulator_get_fpu();
 	switch (reg) {
 	case 0: asm("movdqa %%xmm0, %0" : "=m"(*data)); break;
 	case 1: asm("movdqa %%xmm1, %0" : "=m"(*data)); break;
@@ -1080,11 +1096,13 @@ static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg)
 #endif
 	default: BUG();
 	}
+	emulator_put_fpu();
 }
 
 static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data,
 			  int reg)
 {
+	emulator_get_fpu();
 	switch (reg) {
 	case 0: asm("movdqa %0, %%xmm0" : : "m"(*data)); break;
 	case 1: asm("movdqa %0, %%xmm1" : : "m"(*data)); break;
@@ -1106,10 +1124,12 @@ static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data,
 #endif
 	default: BUG();
 	}
+	emulator_put_fpu();
 }
 
 static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
 {
+	emulator_get_fpu();
 	switch (reg) {
 	case 0: asm("movq %%mm0, %0" : "=m"(*data)); break;
 	case 1: asm("movq %%mm1, %0" : "=m"(*data)); break;
@@ -1121,10 +1141,12 @@ static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
 	case 7: asm("movq %%mm7, %0" : "=m"(*data)); break;
 	default: BUG();
 	}
+	emulator_put_fpu();
 }
 
 static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
 {
+	emulator_get_fpu();
 	switch (reg) {
 	case 0: asm("movq %0, %%mm0" : : "m"(*data)); break;
 	case 1: asm("movq %0, %%mm1" : : "m"(*data)); break;
@@ -1136,6 +1158,7 @@ static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
 	case 7: asm("movq %0, %%mm7" : : "m"(*data)); break;
 	default: BUG();
 	}
+	emulator_put_fpu();
 }
 
 static int em_fninit(struct x86_emulate_ctxt *ctxt)
@@ -1143,7 +1166,9 @@ static int em_fninit(struct x86_emulate_ctxt *ctxt)
 	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
 		return emulate_nm(ctxt);
 
+	emulator_get_fpu();
 	asm volatile("fninit");
+	emulator_put_fpu();
 	return X86EMUL_CONTINUE;
 }
 
@@ -1154,7 +1179,9 @@ static int em_fnstcw(struct x86_emulate_ctxt *ctxt)
 	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
 		return emulate_nm(ctxt);
 
+	emulator_get_fpu();
 	asm volatile("fnstcw %0": "+m"(fcw));
+	emulator_put_fpu();
 
 	ctxt->dst.val = fcw;
 
@@ -1168,7 +1195,9 @@ static int em_fnstsw(struct x86_emulate_ctxt *ctxt)
 	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
 		return emulate_nm(ctxt);
 
+	emulator_get_fpu();
 	asm volatile("fnstsw %0": "+m"(fsw));
+	emulator_put_fpu();
 
 	ctxt->dst.val = fsw;
 
@@ -4076,8 +4105,12 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt)
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
+	emulator_get_fpu();
+
 	rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state));
 
+	emulator_put_fpu();
+
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
@@ -4120,6 +4153,8 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
+	emulator_get_fpu();
+
 	if (size < __fxstate_size(16)) {
 		rc = fxregs_fixup(&fx_state, size);
 		if (rc != X86EMUL_CONTINUE)
@@ -4135,6 +4170,8 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
 		rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state));
 
 out:
+	emulator_put_fpu();
+
 	return rc;
 }
 
@@ -5121,6 +5158,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
 	ctxt->fetch.ptr = ctxt->fetch.data;
 	ctxt->fetch.end = ctxt->fetch.data + insn_len;
 	ctxt->opcode_len = 1;
+	ctxt->intercept = x86_intercept_none;
 	if (insn_len > 0)
 		memcpy(ctxt->fetch.data, insn, insn_len);
 	else {
@@ -5173,16 +5211,28 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
 				ctxt->ad_bytes = def_ad_bytes ^ 6;
 			break;
 		case 0x26:	/* ES override */
+			has_seg_override = true;
+			ctxt->seg_override = VCPU_SREG_ES;
+			break;
 		case 0x2e:	/* CS override */
+			has_seg_override = true;
+			ctxt->seg_override = VCPU_SREG_CS;
+			break;
 		case 0x36:	/* SS override */
+			has_seg_override = true;
+			ctxt->seg_override = VCPU_SREG_SS;
+			break;
 		case 0x3e:	/* DS override */
 			has_seg_override = true;
-			ctxt->seg_override = (ctxt->b >> 3) & 3;
+			ctxt->seg_override = VCPU_SREG_DS;
 			break;
 		case 0x64:	/* FS override */
+			has_seg_override = true;
+			ctxt->seg_override = VCPU_SREG_FS;
+			break;
 		case 0x65:	/* GS override */
 			has_seg_override = true;
-			ctxt->seg_override = ctxt->b & 7;
+			ctxt->seg_override = VCPU_SREG_GS;
 			break;
 		case 0x40 ... 0x4f: /* REX */
 			if (mode != X86EMUL_MODE_PROT64)
@@ -5266,10 +5316,15 @@ done_prefixes:
 			}
 			break;
 		case Escape:
-			if (ctxt->modrm > 0xbf)
-				opcode = opcode.u.esc->high[ctxt->modrm - 0xc0];
-			else
+			if (ctxt->modrm > 0xbf) {
+				size_t size = ARRAY_SIZE(opcode.u.esc->high);
+				u32 index = array_index_nospec(
+					ctxt->modrm - 0xc0, size);
+
+				opcode = opcode.u.esc->high[index];
+			} else {
 				opcode = opcode.u.esc->op[(ctxt->modrm >> 3) & 7];
+			}
 			break;
 		case InstrDual:
 			if ((ctxt->modrm >> 6) == 3)
@@ -5411,7 +5466,9 @@ static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt)
 {
 	int rc;
 
+	emulator_get_fpu();
 	rc = asm_safe("fwait");
+	emulator_put_fpu();
 
 	if (unlikely(rc != X86EMUL_CONTINUE))
 		return emulate_exception(ctxt, MF_VECTOR, 0, false);
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 72200998687c..2d4c1fe5f380 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -808,11 +808,12 @@ static int kvm_hv_msr_get_crash_data(struct kvm_vcpu *vcpu,
 				     u32 index, u64 *pdata)
 {
 	struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+	size_t size = ARRAY_SIZE(hv->hv_crash_param);
 
-	if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param)))
+	if (WARN_ON_ONCE(index >= size))
 		return -EINVAL;
 
-	*pdata = hv->hv_crash_param[index];
+	*pdata = hv->hv_crash_param[array_index_nospec(index, size)];
 	return 0;
 }
 
@@ -851,11 +852,12 @@ static int kvm_hv_msr_set_crash_data(struct kvm_vcpu *vcpu,
 				     u32 index, u64 data)
 {
 	struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+	size_t size = ARRAY_SIZE(hv->hv_crash_param);
 
-	if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param)))
+	if (WARN_ON_ONCE(index >= size))
 		return -EINVAL;
 
-	hv->hv_crash_param[index] = data;
+	hv->hv_crash_param[array_index_nospec(index, size)] = data;
 	return 0;
 }
 
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index 8b38bb4868a6..629a09ca9860 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -460,10 +460,14 @@ static int picdev_write(struct kvm_pic *s,
 	switch (addr) {
 	case 0x20:
 	case 0x21:
+		pic_lock(s);
+		pic_ioport_write(&s->pics[0], addr, data);
+		pic_unlock(s);
+		break;
 	case 0xa0:
 	case 0xa1:
 		pic_lock(s);
-		pic_ioport_write(&s->pics[addr >> 7], addr, data);
+		pic_ioport_write(&s->pics[1], addr, data);
 		pic_unlock(s);
 		break;
 	case 0x4d0:
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 1add1bc881e2..9446613625e1 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -36,6 +36,7 @@
 #include <linux/io.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/nospec.h>
 #include <asm/processor.h>
 #include <asm/page.h>
 #include <asm/current.h>
@@ -73,13 +74,14 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic,
 	default:
 		{
 			u32 redir_index = (ioapic->ioregsel - 0x10) >> 1;
-			u64 redir_content;
+			u64 redir_content = ~0ULL;
 
-			if (redir_index < IOAPIC_NUM_PINS)
-				redir_content =
-					ioapic->redirtbl[redir_index].bits;
-			else
-				redir_content = ~0ULL;
+			if (redir_index < IOAPIC_NUM_PINS) {
+				u32 index = array_index_nospec(
+					redir_index, IOAPIC_NUM_PINS);
+
+				redir_content = ioapic->redirtbl[index].bits;
+			}
 
 			result = (ioapic->ioregsel & 0x1) ?
 			    (redir_content >> 32) & 0xffffffff :
@@ -297,6 +299,7 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 		ioapic_debug("change redir index %x val %x\n", index, val);
 		if (index >= IOAPIC_NUM_PINS)
 			return;
+		index = array_index_nospec(index, IOAPIC_NUM_PINS);
 		e = &ioapic->redirtbl[index];
 		mask_before = e->fields.mask;
 		/* Preserve read-only fields */
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 924b3bd5a7b7..e3ab10d6b12e 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -416,7 +416,7 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
 
 			kvm_set_msi_irq(vcpu->kvm, entry, &irq);
 
-			if (irq.level && kvm_apic_match_dest(vcpu, NULL, 0,
+			if (irq.trig_mode && kvm_apic_match_dest(vcpu, NULL, 0,
 						irq.dest_id, irq.dest_mode))
 				__set_bit(irq.vector, ioapic_handled_vectors);
 		}
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index 1cc6c47dc77e..341f58a01de0 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -7,7 +7,7 @@
 #define KVM_POSSIBLE_CR0_GUEST_BITS X86_CR0_TS
 #define KVM_POSSIBLE_CR4_GUEST_BITS				  \
 	(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR  \
-	 | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE)
+	 | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE | X86_CR4_TSD)
 
 #define BUILD_KVM_GPR_ACCESSORS(lname, uname)				      \
 static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 8d22c79f5333..9483b9da8864 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -59,9 +59,6 @@
 #define APIC_VERSION			(0x14UL | ((KVM_APIC_LVT_NUM - 1) << 16))
 #define LAPIC_MMIO_LENGTH		(1 << 12)
 /* followed define is not in apicdef.h */
-#define APIC_SHORT_MASK			0xc0000
-#define APIC_DEST_NOSHORT		0x0
-#define APIC_DEST_MASK			0x800
 #define MAX_APIC_VECTOR			256
 #define APIC_VECTORS_PER_REG		32
 
@@ -635,9 +632,11 @@ static inline bool pv_eoi_enabled(struct kvm_vcpu *vcpu)
 static bool pv_eoi_get_pending(struct kvm_vcpu *vcpu)
 {
 	u8 val;
-	if (pv_eoi_get_user(vcpu, &val) < 0)
+	if (pv_eoi_get_user(vcpu, &val) < 0) {
 		apic_debug("Can't read EOI MSR value: 0x%llx\n",
 			   (unsigned long long)vcpu->arch.pv_eoi.msr_val);
+		return false;
+	}
 	return val & 0x1;
 }
 
@@ -1063,11 +1062,8 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 				apic_clear_vector(vector, apic->regs + APIC_TMR);
 		}
 
-		if (vcpu->arch.apicv_active)
-			kvm_x86_ops->deliver_posted_interrupt(vcpu, vector);
-		else {
+		if (kvm_x86_ops->deliver_posted_interrupt(vcpu, vector)) {
 			kvm_lapic_set_irr(vector, apic);
-
 			kvm_make_request(KVM_REQ_EVENT, vcpu);
 			kvm_vcpu_kick(vcpu);
 		}
@@ -1918,15 +1914,20 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 	case APIC_LVTTHMR:
 	case APIC_LVTPC:
 	case APIC_LVT1:
-	case APIC_LVTERR:
+	case APIC_LVTERR: {
 		/* TODO: Check vector */
+		size_t size;
+		u32 index;
+
 		if (!kvm_apic_sw_enabled(apic))
 			val |= APIC_LVT_MASKED;
-
-		val &= apic_lvt_mask[(reg - APIC_LVTT) >> 4];
+		size = ARRAY_SIZE(apic_lvt_mask);
+		index = array_index_nospec(
+				(reg - APIC_LVTT) >> 4, size);
+		val &= apic_lvt_mask[index];
 		kvm_lapic_set_reg(apic, reg, val);
-
 		break;
+	}
 
 	case APIC_LVTT:
 		if (!kvm_apic_sw_enabled(apic))
@@ -2086,7 +2087,7 @@ void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (!lapic_in_kernel(vcpu) || apic_lvtt_oneshot(apic) ||
+	if (!kvm_apic_present(vcpu) || apic_lvtt_oneshot(apic) ||
 			apic_lvtt_period(apic))
 		return;
 
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index d6d049ba3045..29980b4cc57b 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -10,8 +10,9 @@
 #define KVM_APIC_SIPI		1
 #define KVM_APIC_LVT_NUM	6
 
-#define KVM_APIC_SHORT_MASK	0xc0000
-#define KVM_APIC_DEST_MASK	0x800
+#define APIC_SHORT_MASK			0xc0000
+#define APIC_DEST_NOSHORT		0x0
+#define APIC_DEST_MASK			0x800
 
 #define APIC_BUS_CYCLE_NS       1
 #define APIC_BUS_FREQUENCY      (1000000000ULL / APIC_BUS_CYCLE_NS)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 35348302a6e0..bc5154c57b4e 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -154,11 +154,6 @@ module_param(dbg, bool, 0644);
 #define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | shadow_user_mask \
 			| shadow_x_mask | shadow_nx_mask | shadow_me_mask)
 
-#define ACC_EXEC_MASK    1
-#define ACC_WRITE_MASK   PT_WRITABLE_MASK
-#define ACC_USER_MASK    PT_USER_MASK
-#define ACC_ALL          (ACC_EXEC_MASK | ACC_WRITE_MASK | ACC_USER_MASK)
-
 /* The mask for the R/X bits in EPT PTEs */
 #define PT64_EPT_READABLE_MASK			0x1ull
 #define PT64_EPT_EXECUTABLE_MASK		0x4ull
@@ -242,6 +237,7 @@ static u64 __read_mostly shadow_accessed_mask;
 static u64 __read_mostly shadow_dirty_mask;
 static u64 __read_mostly shadow_mmio_mask;
 static u64 __read_mostly shadow_mmio_value;
+static u64 __read_mostly shadow_mmio_access_mask;
 static u64 __read_mostly shadow_present_mask;
 static u64 __read_mostly shadow_me_mask;
 
@@ -284,6 +280,11 @@ static const u64 shadow_nonpresent_or_rsvd_mask_len = 5;
  */
 static u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask;
 
+/*
+ * The number of non-reserved physical address bits irrespective of features
+ * that repurpose legal bits, e.g. MKTME.
+ */
+u8 __read_mostly shadow_phys_bits;
 
 static void mmu_spte_set(u64 *sptep, u64 spte);
 static union kvm_mmu_page_role
@@ -318,11 +319,15 @@ static void kvm_flush_remote_tlbs_with_address(struct kvm *kvm,
 	kvm_flush_remote_tlbs_with_range(kvm, &range);
 }
 
-void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value)
+void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value, u64 access_mask)
 {
+	BUG_ON((u64)(unsigned)access_mask != access_mask);
 	BUG_ON((mmio_mask & mmio_value) != mmio_value);
+	WARN_ON(mmio_value & (shadow_nonpresent_or_rsvd_mask << shadow_nonpresent_or_rsvd_mask_len));
+	WARN_ON(mmio_value & shadow_nonpresent_or_rsvd_lower_gfn_mask);
 	shadow_mmio_value = mmio_value | SPTE_SPECIAL_MASK;
 	shadow_mmio_mask = mmio_mask | SPTE_SPECIAL_MASK;
+	shadow_mmio_access_mask = access_mask;
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask);
 
@@ -413,7 +418,7 @@ static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn,
 	u64 mask = generation_mmio_spte_mask(gen);
 	u64 gpa = gfn << PAGE_SHIFT;
 
-	access &= ACC_WRITE_MASK | ACC_USER_MASK;
+	access &= shadow_mmio_access_mask;
 	mask |= shadow_mmio_value | access;
 	mask |= gpa | shadow_nonpresent_or_rsvd_mask;
 	mask |= (gpa & shadow_nonpresent_or_rsvd_mask)
@@ -440,8 +445,7 @@ static gfn_t get_mmio_spte_gfn(u64 spte)
 
 static unsigned get_mmio_spte_access(u64 spte)
 {
-	u64 mask = generation_mmio_spte_mask(MMIO_SPTE_GEN_MASK) | shadow_mmio_mask;
-	return (spte & ~mask) & ~PAGE_MASK;
+	return spte & shadow_mmio_access_mask;
 }
 
 static bool set_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn,
@@ -496,6 +500,25 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
 
+static u8 kvm_get_shadow_phys_bits(void)
+{
+	/*
+	 * boot_cpu_data.x86_phys_bits is reduced when MKTME or SME are detected
+	 * in CPU detection code, but the processor treats those reduced bits as
+	 * 'keyID' thus they are not reserved bits. Therefore KVM needs to look at
+	 * the physical address bits reported by CPUID.
+	 */
+	if (likely(boot_cpu_data.extended_cpuid_level >= 0x80000008))
+		return cpuid_eax(0x80000008) & 0xff;
+
+	/*
+	 * Quite weird to have VMX or SVM but not MAXPHYADDR; probably a VM with
+	 * custom CPUID.  Proceed with whatever the kernel found since these features
+	 * aren't virtualizable (SME/SEV also require CPUIDs higher than 0x80000008).
+	 */
+	return boot_cpu_data.x86_phys_bits;
+}
+
 static void kvm_mmu_reset_all_pte_masks(void)
 {
 	u8 low_phys_bits;
@@ -509,6 +532,8 @@ static void kvm_mmu_reset_all_pte_masks(void)
 	shadow_present_mask = 0;
 	shadow_acc_track_mask = 0;
 
+	shadow_phys_bits = kvm_get_shadow_phys_bits();
+
 	/*
 	 * If the CPU has 46 or less physical address bits, then set an
 	 * appropriate mask to guard against L1TF attacks. Otherwise, it is
@@ -520,16 +545,15 @@ static void kvm_mmu_reset_all_pte_masks(void)
 	 * the most significant bits of legal physical address space.
 	 */
 	shadow_nonpresent_or_rsvd_mask = 0;
-	low_phys_bits = boot_cpu_data.x86_cache_bits;
-	if (boot_cpu_data.x86_cache_bits <
-	    52 - shadow_nonpresent_or_rsvd_mask_len) {
+	low_phys_bits = boot_cpu_data.x86_phys_bits;
+	if (boot_cpu_has_bug(X86_BUG_L1TF) &&
+	    !WARN_ON_ONCE(boot_cpu_data.x86_cache_bits >=
+			  52 - shadow_nonpresent_or_rsvd_mask_len)) {
+		low_phys_bits = boot_cpu_data.x86_cache_bits
+			- shadow_nonpresent_or_rsvd_mask_len;
 		shadow_nonpresent_or_rsvd_mask =
-			rsvd_bits(boot_cpu_data.x86_cache_bits -
-				  shadow_nonpresent_or_rsvd_mask_len,
-				  boot_cpu_data.x86_cache_bits - 1);
-		low_phys_bits -= shadow_nonpresent_or_rsvd_mask_len;
-	} else
-		WARN_ON_ONCE(boot_cpu_has_bug(X86_BUG_L1TF));
+			rsvd_bits(low_phys_bits, boot_cpu_data.x86_cache_bits - 1);
+	}
 
 	shadow_nonpresent_or_rsvd_lower_gfn_mask =
 		GENMASK_ULL(low_phys_bits - 1, PAGE_SHIFT);
@@ -1220,12 +1244,12 @@ static bool mmu_gfn_lpage_is_disallowed(struct kvm_vcpu *vcpu, gfn_t gfn,
 	return __mmu_gfn_lpage_is_disallowed(gfn, level, slot);
 }
 
-static int host_mapping_level(struct kvm *kvm, gfn_t gfn)
+static int host_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn)
 {
 	unsigned long page_size;
 	int i, ret = 0;
 
-	page_size = kvm_host_page_size(kvm, gfn);
+	page_size = kvm_host_page_size(vcpu, gfn);
 
 	for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
 		if (page_size >= KVM_HPAGE_SIZE(i))
@@ -1275,7 +1299,7 @@ static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn,
 	if (unlikely(*force_pt_level))
 		return PT_PAGE_TABLE_LEVEL;
 
-	host_level = host_mapping_level(vcpu->kvm, large_gfn);
+	host_level = host_mapping_level(vcpu, large_gfn);
 
 	if (host_level == PT_PAGE_TABLE_LEVEL)
 		return host_level;
@@ -1747,10 +1771,10 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
  * Emulate arch specific page modification logging for the
  * nested hypervisor
  */
-int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu)
+int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa)
 {
 	if (kvm_x86_ops->write_log_dirty)
-		return kvm_x86_ops->write_log_dirty(vcpu);
+		return kvm_x86_ops->write_log_dirty(vcpu, l2_gpa);
 
 	return 0;
 }
@@ -3363,7 +3387,8 @@ static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
 	}
 
 	if (unlikely(is_noslot_pfn(pfn)))
-		vcpu_cache_mmio_info(vcpu, gva, gfn, access);
+		vcpu_cache_mmio_info(vcpu, gva, gfn,
+				     access & shadow_mmio_access_mask);
 
 	return false;
 }
@@ -3457,7 +3482,7 @@ static bool is_access_allowed(u32 fault_err_code, u64 spte)
  * - true: let the vcpu to access on the same address again.
  * - false: let the real page fault path to fix it.
  */
-static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
+static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int level,
 			    u32 error_code)
 {
 	struct kvm_shadow_walk_iterator iterator;
@@ -3477,7 +3502,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
 	do {
 		u64 new_spte;
 
-		for_each_shadow_entry_lockless(vcpu, gva, iterator, spte)
+		for_each_shadow_entry_lockless(vcpu, cr2_or_gpa, iterator, spte)
 			if (!is_shadow_present_pte(spte) ||
 			    iterator.level < level)
 				break;
@@ -3555,7 +3580,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
 
 	} while (true);
 
-	trace_fast_page_fault(vcpu, gva, error_code, iterator.sptep,
+	trace_fast_page_fault(vcpu, cr2_or_gpa, error_code, iterator.sptep,
 			      spte, fault_handled);
 	walk_shadow_page_lockless_end(vcpu);
 
@@ -3563,10 +3588,11 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
 }
 
 static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
-			 gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable);
+			 gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write,
+			 bool *writable);
 static int make_mmu_pages_available(struct kvm_vcpu *vcpu);
 
-static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
+static int nonpaging_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 			 gfn_t gfn, bool prefault)
 {
 	int r;
@@ -3592,16 +3618,16 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
 		gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1);
 	}
 
-	if (fast_page_fault(vcpu, v, level, error_code))
+	if (fast_page_fault(vcpu, gpa, level, error_code))
 		return RET_PF_RETRY;
 
 	mmu_seq = vcpu->kvm->mmu_notifier_seq;
 	smp_rmb();
 
-	if (try_async_pf(vcpu, prefault, gfn, v, &pfn, write, &map_writable))
+	if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable))
 		return RET_PF_RETRY;
 
-	if (handle_abnormal_pfn(vcpu, v, gfn, pfn, ACC_ALL, &r))
+	if (handle_abnormal_pfn(vcpu, gpa, gfn, pfn, ACC_ALL, &r))
 		return r;
 
 	spin_lock(&vcpu->kvm->mmu_lock);
@@ -3611,7 +3637,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
 		goto out_unlock;
 	if (likely(!force_pt_level))
 		transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level);
-	r = __direct_map(vcpu, v, write, map_writable, level, pfn,
+	r = __direct_map(vcpu, gpa, write, map_writable, level, pfn,
 			 prefault, false);
 	spin_unlock(&vcpu->kvm->mmu_lock);
 
@@ -3912,7 +3938,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_sync_roots);
 
-static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr,
+static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gpa_t vaddr,
 				  u32 access, struct x86_exception *exception)
 {
 	if (exception)
@@ -3920,7 +3946,7 @@ static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr,
 	return vaddr;
 }
 
-static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr,
+static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gpa_t vaddr,
 					 u32 access,
 					 struct x86_exception *exception)
 {
@@ -4080,13 +4106,14 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr)
 	walk_shadow_page_lockless_end(vcpu);
 }
 
-static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
+static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa,
 				u32 error_code, bool prefault)
 {
-	gfn_t gfn = gva >> PAGE_SHIFT;
+	gfn_t gfn = gpa >> PAGE_SHIFT;
 	int r;
 
-	pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code);
+	/* Note, paging is disabled, ergo gva == gpa. */
+	pgprintk("%s: gva %lx error %x\n", __func__, gpa, error_code);
 
 	if (page_fault_handle_page_track(vcpu, error_code, gfn))
 		return RET_PF_EMULATE;
@@ -4098,11 +4125,12 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
 	MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa));
 
 
-	return nonpaging_map(vcpu, gva & PAGE_MASK,
+	return nonpaging_map(vcpu, gpa & PAGE_MASK,
 			     error_code, gfn, prefault);
 }
 
-static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
+static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+				   gfn_t gfn)
 {
 	struct kvm_arch_async_pf arch;
 
@@ -4111,7 +4139,8 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
 	arch.direct_map = vcpu->arch.mmu->direct_map;
 	arch.cr3 = vcpu->arch.mmu->get_cr3(vcpu);
 
-	return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
+	return kvm_setup_async_pf(vcpu, cr2_or_gpa,
+				  kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
 }
 
 bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
@@ -4128,7 +4157,8 @@ bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
 }
 
 static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
-			 gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable)
+			 gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write,
+			 bool *writable)
 {
 	struct kvm_memory_slot *slot;
 	bool async;
@@ -4148,12 +4178,12 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
 		return false; /* *pfn has correct page already */
 
 	if (!prefault && kvm_can_do_async_pf(vcpu)) {
-		trace_kvm_try_async_get_page(gva, gfn);
+		trace_kvm_try_async_get_page(cr2_or_gpa, gfn);
 		if (kvm_find_async_pf_gfn(vcpu, gfn)) {
-			trace_kvm_async_pf_doublefault(gva, gfn);
+			trace_kvm_async_pf_doublefault(cr2_or_gpa, gfn);
 			kvm_make_request(KVM_REQ_APF_HALT, vcpu);
 			return true;
-		} else if (kvm_arch_setup_async_pf(vcpu, gva, gfn))
+		} else if (kvm_arch_setup_async_pf(vcpu, cr2_or_gpa, gfn))
 			return true;
 	}
 
@@ -4166,6 +4196,12 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
 {
 	int r = 1;
 
+#ifndef CONFIG_X86_64
+	/* A 64-bit CR2 should be impossible on 32-bit KVM. */
+	if (WARN_ON_ONCE(fault_address >> 32))
+		return -EFAULT;
+#endif
+
 	vcpu->arch.l1tf_flush_l1d = true;
 	switch (vcpu->arch.apf.host_apf_reason) {
 	default:
@@ -4203,7 +4239,7 @@ check_hugepage_cache_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int level)
 	return kvm_mtrr_check_gfn_range_consistency(vcpu, gfn, page_num);
 }
 
-static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
+static int tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 			  bool prefault)
 {
 	kvm_pfn_t pfn;
@@ -4510,7 +4546,7 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 			nonleaf_bit8_rsvd | rsvd_bits(7, 7) |
 			rsvd_bits(maxphyaddr, 51);
 		rsvd_check->rsvd_bits_mask[0][2] = exb_bit_rsvd |
-			nonleaf_bit8_rsvd | gbpages_bit_rsvd |
+			gbpages_bit_rsvd |
 			rsvd_bits(maxphyaddr, 51);
 		rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 51);
@@ -4603,7 +4639,7 @@ reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
 	 */
 	shadow_zero_check = &context->shadow_zero_check;
 	__reset_rsvds_bits_mask(vcpu, shadow_zero_check,
-				boot_cpu_data.x86_phys_bits,
+				shadow_phys_bits,
 				context->shadow_root_level, uses_nx,
 				guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES),
 				is_pse(vcpu), true);
@@ -4640,13 +4676,13 @@ reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
 
 	if (boot_cpu_is_amd())
 		__reset_rsvds_bits_mask(vcpu, shadow_zero_check,
-					boot_cpu_data.x86_phys_bits,
+					shadow_phys_bits,
 					context->shadow_root_level, false,
 					boot_cpu_has(X86_FEATURE_GBPAGES),
 					true, true);
 	else
 		__reset_rsvds_bits_mask_ept(shadow_zero_check,
-					    boot_cpu_data.x86_phys_bits,
+					    shadow_phys_bits,
 					    false);
 
 	if (!shadow_me_mask)
@@ -4667,7 +4703,7 @@ reset_ept_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
 				struct kvm_mmu *context, bool execonly)
 {
 	__reset_rsvds_bits_mask_ept(&context->shadow_zero_check,
-				    boot_cpu_data.x86_phys_bits, execonly);
+				    shadow_phys_bits, execonly);
 }
 
 #define BYTE_MASK(access) \
@@ -5462,7 +5498,7 @@ static int make_mmu_pages_available(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
+int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
 		       void *insn, int insn_len)
 {
 	int r, emulation_type = 0;
@@ -5472,18 +5508,18 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
 	/* With shadow page tables, fault_address contains a GVA or nGPA.  */
 	if (vcpu->arch.mmu->direct_map) {
 		vcpu->arch.gpa_available = true;
-		vcpu->arch.gpa_val = cr2;
+		vcpu->arch.gpa_val = cr2_or_gpa;
 	}
 
 	r = RET_PF_INVALID;
 	if (unlikely(error_code & PFERR_RSVD_MASK)) {
-		r = handle_mmio_page_fault(vcpu, cr2, direct);
+		r = handle_mmio_page_fault(vcpu, cr2_or_gpa, direct);
 		if (r == RET_PF_EMULATE)
 			goto emulate;
 	}
 
 	if (r == RET_PF_INVALID) {
-		r = vcpu->arch.mmu->page_fault(vcpu, cr2,
+		r = vcpu->arch.mmu->page_fault(vcpu, cr2_or_gpa,
 					       lower_32_bits(error_code),
 					       false);
 		WARN_ON(r == RET_PF_INVALID);
@@ -5503,7 +5539,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
 	 */
 	if (vcpu->arch.mmu->direct_map &&
 	    (error_code & PFERR_NESTED_GUEST_PAGE) == PFERR_NESTED_GUEST_PAGE) {
-		kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2));
+		kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2_or_gpa));
 		return 1;
 	}
 
@@ -5518,7 +5554,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
 	 * explicitly shadowing L1's page tables, i.e. unprotecting something
 	 * for L1 isn't going to magically fix whatever issue cause L2 to fail.
 	 */
-	if (!mmio_info_in_cache(vcpu, cr2, direct) && !is_guest_mode(vcpu))
+	if (!mmio_info_in_cache(vcpu, cr2_or_gpa, direct) && !is_guest_mode(vcpu))
 		emulation_type = EMULTYPE_ALLOW_RETRY;
 emulate:
 	/*
@@ -5533,7 +5569,7 @@ emulate:
 			return 1;
 	}
 
-	er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len);
+	er = x86_emulate_instruction(vcpu, cr2_or_gpa, emulation_type, insn, insn_len);
 
 	switch (er) {
 	case EMULATE_DONE:
@@ -6189,14 +6225,13 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp)
 
 	if (new_val != old_val) {
 		struct kvm *kvm;
-		int idx;
 
 		spin_lock(&kvm_lock);
 
 		list_for_each_entry(kvm, &vm_list, vm_list) {
-			idx = srcu_read_lock(&kvm->srcu);
+			mutex_lock(&kvm->slots_lock);
 			kvm_mmu_zap_all_fast(kvm);
-			srcu_read_unlock(&kvm->srcu, idx);
+			mutex_unlock(&kvm->slots_lock);
 
 			wake_up_process(kvm->arch.nx_lpage_recovery_thread);
 		}
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 4610230ddaea..b0fefb3ccc87 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -43,6 +43,11 @@
 #define PT32_ROOT_LEVEL 2
 #define PT32E_ROOT_LEVEL 3
 
+#define ACC_EXEC_MASK	1
+#define ACC_WRITE_MASK	PT_WRITABLE_MASK
+#define ACC_USER_MASK	PT_USER_MASK
+#define ACC_ALL		(ACC_EXEC_MASK | ACC_WRITE_MASK | ACC_USER_MASK)
+
 static inline u64 rsvd_bits(int s, int e)
 {
 	if (e < s)
@@ -51,7 +56,7 @@ static inline u64 rsvd_bits(int s, int e)
 	return ((1ULL << (e - s + 1)) - 1) << s;
 }
 
-void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value);
+void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value, u64 access_mask);
 
 void
 reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context);
@@ -209,7 +214,7 @@ void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
 void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
 bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
 				    struct kvm_memory_slot *slot, u64 gfn);
-int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu);
+int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa);
 
 int kvm_mmu_post_init_vm(struct kvm *kvm);
 void kvm_mmu_pre_destroy_vm(struct kvm *kvm);
diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h
index dd30dccd2ad5..c2cabd4c6678 100644
--- a/arch/x86/kvm/mmutrace.h
+++ b/arch/x86/kvm/mmutrace.h
@@ -246,13 +246,13 @@ TRACE_EVENT(
 
 TRACE_EVENT(
 	fast_page_fault,
-	TP_PROTO(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code,
+	TP_PROTO(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 error_code,
 		 u64 *sptep, u64 old_spte, bool retry),
-	TP_ARGS(vcpu, gva, error_code, sptep, old_spte, retry),
+	TP_ARGS(vcpu, cr2_or_gpa, error_code, sptep, old_spte, retry),
 
 	TP_STRUCT__entry(
 		__field(int, vcpu_id)
-		__field(gva_t, gva)
+		__field(gpa_t, cr2_or_gpa)
 		__field(u32, error_code)
 		__field(u64 *, sptep)
 		__field(u64, old_spte)
@@ -262,7 +262,7 @@ TRACE_EVENT(
 
 	TP_fast_assign(
 		__entry->vcpu_id = vcpu->vcpu_id;
-		__entry->gva = gva;
+		__entry->cr2_or_gpa = cr2_or_gpa;
 		__entry->error_code = error_code;
 		__entry->sptep = sptep;
 		__entry->old_spte = old_spte;
@@ -270,9 +270,9 @@ TRACE_EVENT(
 		__entry->retry = retry;
 	),
 
-	TP_printk("vcpu %d gva %lx error_code %s sptep %p old %#llx"
+	TP_printk("vcpu %d gva %llx error_code %s sptep %p old %#llx"
 		  " new %llx spurious %d fixed %d", __entry->vcpu_id,
-		  __entry->gva, __print_flags(__entry->error_code, "|",
+		  __entry->cr2_or_gpa, __print_flags(__entry->error_code, "|",
 		  kvm_mmu_trace_pferr_flags), __entry->sptep,
 		  __entry->old_spte, __entry->new_spte,
 		  __spte_satisfied(old_spte), __spte_satisfied(new_spte)
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index 25ce3edd1872..7f0059aa30e1 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -192,11 +192,15 @@ static bool fixed_msr_to_seg_unit(u32 msr, int *seg, int *unit)
 		break;
 	case MSR_MTRRfix16K_80000 ... MSR_MTRRfix16K_A0000:
 		*seg = 1;
-		*unit = msr - MSR_MTRRfix16K_80000;
+		*unit = array_index_nospec(
+			msr - MSR_MTRRfix16K_80000,
+			MSR_MTRRfix16K_A0000 - MSR_MTRRfix16K_80000 + 1);
 		break;
 	case MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000:
 		*seg = 2;
-		*unit = msr - MSR_MTRRfix4K_C0000;
+		*unit = array_index_nospec(
+			msr - MSR_MTRRfix4K_C0000,
+			MSR_MTRRfix4K_F8000 - MSR_MTRRfix4K_C0000 + 1);
 		break;
 	default:
 		return false;
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 4a906f7111ce..7f64d44735f9 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -33,7 +33,7 @@
 	#define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT
 	#define PT_HAVE_ACCESSED_DIRTY(mmu) true
 	#ifdef CONFIG_X86_64
-	#define PT_MAX_FULL_LEVELS 4
+	#define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL
 	#define CMPXCHG cmpxchg
 	#else
 	#define CMPXCHG cmpxchg64
@@ -220,7 +220,7 @@ static inline unsigned FNAME(gpte_access)(u64 gpte)
 static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
 					     struct kvm_mmu *mmu,
 					     struct guest_walker *walker,
-					     int write_fault)
+					     gpa_t addr, int write_fault)
 {
 	unsigned level, index;
 	pt_element_t pte, orig_pte;
@@ -245,7 +245,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
 				!(pte & PT_GUEST_DIRTY_MASK)) {
 			trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
 #if PTTYPE == PTTYPE_EPT
-			if (kvm_arch_write_log_dirty(vcpu))
+			if (kvm_arch_write_log_dirty(vcpu, addr))
 				return -EINVAL;
 #endif
 			pte |= PT_GUEST_DIRTY_MASK;
@@ -291,11 +291,11 @@ static inline unsigned FNAME(gpte_pkeys)(struct kvm_vcpu *vcpu, u64 gpte)
 }
 
 /*
- * Fetch a guest pte for a guest virtual address
+ * Fetch a guest pte for a guest virtual address, or for an L2's GPA.
  */
 static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 				    struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
-				    gva_t addr, u32 access)
+				    gpa_t addr, u32 access)
 {
 	int ret;
 	pt_element_t pte;
@@ -442,7 +442,8 @@ retry_walk:
 			(PT_GUEST_DIRTY_SHIFT - PT_GUEST_ACCESSED_SHIFT);
 
 	if (unlikely(!accessed_dirty)) {
-		ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, write_fault);
+		ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker,
+							addr, write_fault);
 		if (unlikely(ret < 0))
 			goto error;
 		else if (ret)
@@ -496,7 +497,7 @@ error:
 }
 
 static int FNAME(walk_addr)(struct guest_walker *walker,
-			    struct kvm_vcpu *vcpu, gva_t addr, u32 access)
+			    struct kvm_vcpu *vcpu, gpa_t addr, u32 access)
 {
 	return FNAME(walk_addr_generic)(walker, vcpu, vcpu->arch.mmu, addr,
 					access);
@@ -610,7 +611,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
  * If the guest tries to write a write-protected page, we need to
  * emulate this operation, return 1 to indicate this case.
  */
-static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
+static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr,
 			 struct guest_walker *gw,
 			 int write_fault, int hlevel,
 			 kvm_pfn_t pfn, bool map_writable, bool prefault,
@@ -763,7 +764,7 @@ FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu,
  *  Returns: 1 if we need to emulate the instruction, 0 otherwise, or
  *           a negative value on error.
  */
-static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
+static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
 			     bool prefault)
 {
 	int write_fault = error_code & PFERR_WRITE_MASK;
@@ -945,18 +946,19 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa)
 	spin_unlock(&vcpu->kvm->mmu_lock);
 }
 
-static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access,
+/* Note, @addr is a GPA when gva_to_gpa() translates an L2 GPA to an L1 GPA. */
+static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t addr, u32 access,
 			       struct x86_exception *exception)
 {
 	struct guest_walker walker;
 	gpa_t gpa = UNMAPPED_GVA;
 	int r;
 
-	r = FNAME(walk_addr)(&walker, vcpu, vaddr, access);
+	r = FNAME(walk_addr)(&walker, vcpu, addr, access);
 
 	if (r) {
 		gpa = gfn_to_gpa(walker.gfn);
-		gpa |= vaddr & ~PAGE_MASK;
+		gpa |= addr & ~PAGE_MASK;
 	} else if (exception)
 		*exception = walker.fault;
 
@@ -964,7 +966,8 @@ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access,
 }
 
 #if PTTYPE != PTTYPE_EPT
-static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr,
+/* Note, gva_to_gpa_nested() is only used to translate L2 GVAs. */
+static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gpa_t vaddr,
 				      u32 access,
 				      struct x86_exception *exception)
 {
@@ -972,6 +975,11 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr,
 	gpa_t gpa = UNMAPPED_GVA;
 	int r;
 
+#ifndef CONFIG_X86_64
+	/* A 64-bit GVA should be impossible on 32-bit KVM. */
+	WARN_ON_ONCE(vaddr >> 32);
+#endif
+
 	r = FNAME(walk_addr_nested)(&walker, vcpu, vaddr, access);
 
 	if (r) {
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 22dff661145a..7b4828e50ab3 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -2,6 +2,8 @@
 #ifndef __KVM_X86_PMU_H
 #define __KVM_X86_PMU_H
 
+#include <linux/nospec.h>
+
 #define vcpu_to_pmu(vcpu) (&(vcpu)->arch.pmu)
 #define pmu_to_vcpu(pmu)  (container_of((pmu), struct kvm_vcpu, arch.pmu))
 #define pmc_to_pmu(pmc)   (&(pmc)->vcpu->arch.pmu)
@@ -86,8 +88,12 @@ static inline bool pmc_is_enabled(struct kvm_pmc *pmc)
 static inline struct kvm_pmc *get_gp_pmc(struct kvm_pmu *pmu, u32 msr,
 					 u32 base)
 {
-	if (msr >= base && msr < base + pmu->nr_arch_gp_counters)
-		return &pmu->gp_counters[msr - base];
+	if (msr >= base && msr < base + pmu->nr_arch_gp_counters) {
+		u32 index = array_index_nospec(msr - base,
+					       pmu->nr_arch_gp_counters);
+
+		return &pmu->gp_counters[index];
+	}
 
 	return NULL;
 }
@@ -97,8 +103,12 @@ static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr)
 {
 	int base = MSR_CORE_PERF_FIXED_CTR0;
 
-	if (msr >= base && msr < base + pmu->nr_arch_fixed_counters)
-		return &pmu->fixed_counters[msr - base];
+	if (msr >= base && msr < base + pmu->nr_arch_fixed_counters) {
+		u32 index = array_index_nospec(msr - base,
+					       pmu->nr_arch_fixed_counters);
+
+		return &pmu->fixed_counters[index];
+	}
 
 	return NULL;
 }
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 68f63d9684a6..bf0d805e75c9 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -996,33 +996,32 @@ static void svm_cpu_uninit(int cpu)
 static int svm_cpu_init(int cpu)
 {
 	struct svm_cpu_data *sd;
-	int r;
 
 	sd = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL);
 	if (!sd)
 		return -ENOMEM;
 	sd->cpu = cpu;
-	r = -ENOMEM;
 	sd->save_area = alloc_page(GFP_KERNEL);
 	if (!sd->save_area)
-		goto err_1;
+		goto free_cpu_data;
 
 	if (svm_sev_enabled()) {
-		r = -ENOMEM;
 		sd->sev_vmcbs = kmalloc_array(max_sev_asid + 1,
 					      sizeof(void *),
 					      GFP_KERNEL);
 		if (!sd->sev_vmcbs)
-			goto err_1;
+			goto free_save_area;
 	}
 
 	per_cpu(svm_data, cpu) = sd;
 
 	return 0;
 
-err_1:
+free_save_area:
+	__free_page(sd->save_area);
+free_cpu_data:
 	kfree(sd);
-	return r;
+	return -ENOMEM;
 
 }
 
@@ -1296,6 +1295,47 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu)
 				    control->pause_filter_count, old);
 }
 
+/*
+ * The default MMIO mask is a single bit (excluding the present bit),
+ * which could conflict with the memory encryption bit. Check for
+ * memory encryption support and override the default MMIO mask if
+ * memory encryption is enabled.
+ */
+static __init void svm_adjust_mmio_mask(void)
+{
+	unsigned int enc_bit, mask_bit;
+	u64 msr, mask;
+
+	/* If there is no memory encryption support, use existing mask */
+	if (cpuid_eax(0x80000000) < 0x8000001f)
+		return;
+
+	/* If memory encryption is not enabled, use existing mask */
+	rdmsrl(MSR_K8_SYSCFG, msr);
+	if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT))
+		return;
+
+	enc_bit = cpuid_ebx(0x8000001f) & 0x3f;
+	mask_bit = boot_cpu_data.x86_phys_bits;
+
+	/* Increment the mask bit if it is the same as the encryption bit */
+	if (enc_bit == mask_bit)
+		mask_bit++;
+
+	/*
+	 * If the mask bit location is below 52, then some bits above the
+	 * physical addressing limit will always be reserved, so use the
+	 * rsvd_bits() function to generate the mask. This mask, along with
+	 * the present bit, will be used to generate a page fault with
+	 * PFER.RSV = 1.
+	 *
+	 * If the mask bit location is 52 (or above), then clear the mask.
+	 */
+	mask = (mask_bit < 52) ? rsvd_bits(mask_bit, 51) | PT_PRESENT_MASK : 0;
+
+	kvm_mmu_set_mmio_spte_mask(mask, mask, PT_WRITABLE_MASK | PT_USER_MASK);
+}
+
 static __init int svm_hardware_setup(void)
 {
 	int cpu;
@@ -1350,6 +1390,8 @@ static __init int svm_hardware_setup(void)
 		}
 	}
 
+	svm_adjust_mmio_mask();
+
 	for_each_possible_cpu(cpu) {
 		r = svm_cpu_init(cpu);
 		if (r)
@@ -1811,7 +1853,7 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr,
 		return NULL;
 
 	/* Pin the user virtual address. */
-	npinned = get_user_pages_fast(uaddr, npages, FOLL_WRITE, pages);
+	npinned = get_user_pages_fast(uaddr, npages, write ? FOLL_WRITE : 0, pages);
 	if (npinned != npages) {
 		pr_err("SEV: Failure locking %lu pages.\n", npages);
 		goto err;
@@ -1876,6 +1918,10 @@ static struct kvm *svm_vm_alloc(void)
 	struct kvm_svm *kvm_svm = __vmalloc(sizeof(struct kvm_svm),
 					    GFP_KERNEL_ACCOUNT | __GFP_ZERO,
 					    PAGE_KERNEL);
+
+	if (!kvm_svm)
+		return NULL;
+
 	return &kvm_svm->kvm;
 }
 
@@ -2140,12 +2186,20 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 		goto out;
 	}
 
+	svm->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache,
+						     GFP_KERNEL_ACCOUNT);
+	if (!svm->vcpu.arch.user_fpu) {
+		printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n");
+		err = -ENOMEM;
+		goto free_partial_svm;
+	}
+
 	svm->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache,
 						     GFP_KERNEL_ACCOUNT);
 	if (!svm->vcpu.arch.guest_fpu) {
 		printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n");
 		err = -ENOMEM;
-		goto free_partial_svm;
+		goto free_user_fpu;
 	}
 
 	err = kvm_vcpu_init(&svm->vcpu, kvm, id);
@@ -2208,6 +2262,8 @@ uninit:
 	kvm_vcpu_uninit(&svm->vcpu);
 free_svm:
 	kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu);
+free_user_fpu:
+	kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu);
 free_partial_svm:
 	kmem_cache_free(kvm_vcpu_cache, svm);
 out:
@@ -2238,6 +2294,7 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu)
 	__free_page(virt_to_page(svm->nested.hsave));
 	__free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER);
 	kvm_vcpu_uninit(vcpu);
+	kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu);
 	kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu);
 	kmem_cache_free(kvm_vcpu_cache, svm);
 }
@@ -3171,8 +3228,8 @@ static int nested_svm_exit_special(struct vcpu_svm *svm)
 			return NESTED_EXIT_HOST;
 		break;
 	case SVM_EXIT_EXCP_BASE + PF_VECTOR:
-		/* When we're shadowing, trap PFs, but not async PF */
-		if (!npt_enabled && svm->vcpu.arch.apf.host_apf_reason == 0)
+		/* Trap async PF even if not shadowing */
+		if (!npt_enabled || svm->vcpu.arch.apf.host_apf_reason)
 			return NESTED_EXIT_HOST;
 		break;
 	default:
@@ -3261,7 +3318,7 @@ static inline void copy_vmcb_control_area(struct vmcb *dst_vmcb, struct vmcb *fr
 	dst->iopm_base_pa         = from->iopm_base_pa;
 	dst->msrpm_base_pa        = from->msrpm_base_pa;
 	dst->tsc_offset           = from->tsc_offset;
-	dst->asid                 = from->asid;
+	/* asid not copied, it is handled manually for svm->vmcb.  */
 	dst->tlb_ctl              = from->tlb_ctl;
 	dst->int_ctl              = from->int_ctl;
 	dst->int_vector           = from->int_vector;
@@ -4537,9 +4594,9 @@ static int avic_incomplete_ipi_interception(struct vcpu_svm *svm)
 		 */
 		kvm_for_each_vcpu(i, vcpu, kvm) {
 			bool m = kvm_apic_match_dest(vcpu, apic,
-						     icrl & KVM_APIC_SHORT_MASK,
+						     icrl & APIC_SHORT_MASK,
 						     GET_APIC_DEST_FIELD(icrh),
-						     icrl & KVM_APIC_DEST_MASK);
+						     icrl & APIC_DEST_MASK);
 
 			if (m && !avic_vcpu_is_running(vcpu))
 				kvm_vcpu_wake_up(vcpu);
@@ -5161,8 +5218,11 @@ static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
 	return;
 }
 
-static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
+static int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
 {
+	if (!vcpu->arch.apicv_active)
+		return -1;
+
 	kvm_lapic_set_irr(vec, vcpu->arch.apic);
 	smp_mb__after_atomic();
 
@@ -5171,6 +5231,8 @@ static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
 		       kvm_cpu_get_apicid(vcpu->cpu));
 	else
 		kvm_vcpu_wake_up(vcpu);
+
+	return 0;
 }
 
 static bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu)
@@ -5905,6 +5967,9 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
+				    boot_cpu_has(X86_FEATURE_XSAVES);
+
 	/* Update nrips enabled cache */
 	svm->nrips_enabled = !!guest_cpuid_has(&svm->vcpu, X86_FEATURE_NRIPS);
 
@@ -5991,6 +6056,11 @@ static bool svm_has_wbinvd_exit(void)
 	return true;
 }
 
+static bool svm_pku_supported(void)
+{
+	return false;
+}
+
 #define PRE_EX(exit)  { .exit_code = (exit), \
 			.stage = X86_ICPT_PRE_EXCEPT, }
 #define POST_EX(exit) { .exit_code = (exit), \
@@ -7280,6 +7350,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.xsaves_supported = svm_xsaves_supported,
 	.umip_emulated = svm_umip_emulated,
 	.pt_supported = svm_pt_supported,
+	.pku_supported = svm_pku_supported,
 
 	.set_supported_cpuid = svm_set_supported_cpuid,
 
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index d6664ee3d127..7cd3f8683b8c 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -12,6 +12,7 @@ extern bool __read_mostly enable_ept;
 extern bool __read_mostly enable_unrestricted_guest;
 extern bool __read_mostly enable_ept_ad_bits;
 extern bool __read_mostly enable_pml;
+extern bool __read_mostly enable_apicv;
 extern int __read_mostly pt_mode;
 
 #define PT_MODE_SYSTEM		0
@@ -145,6 +146,11 @@ static inline bool vmx_umip_emulated(void)
 		SECONDARY_EXEC_DESC;
 }
 
+static inline bool vmx_pku_supported(void)
+{
+	return boot_cpu_has(X86_FEATURE_PKU);
+}
+
 static inline bool cpu_has_vmx_rdtscp(void)
 {
 	return vmcs_config.cpu_based_2nd_exec_ctrl &
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 5e5104697fa3..c6deeed854f1 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -3367,7 +3367,7 @@ static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu,
 	nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, intr_info, exit_qual);
 }
 
-static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
+static int vmx_check_nested_events(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	unsigned long exit_qual;
@@ -3405,8 +3405,7 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 		return 0;
 	}
 
-	if ((kvm_cpu_has_interrupt(vcpu) || external_intr) &&
-	    nested_exit_on_intr(vcpu)) {
+	if (kvm_cpu_has_interrupt(vcpu) && nested_exit_on_intr(vcpu)) {
 		if (block_nested_events)
 			return -EBUSY;
 		nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0);
@@ -3980,17 +3979,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 
 	if (likely(!vmx->fail)) {
-		/*
-		 * TODO: SDM says that with acknowledge interrupt on
-		 * exit, bit 31 of the VM-exit interrupt information
-		 * (valid interrupt) is always set to 1 on
-		 * EXIT_REASON_EXTERNAL_INTERRUPT, so we shouldn't
-		 * need kvm_cpu_has_interrupt().  See the commit
-		 * message for details.
-		 */
-		if (nested_exit_intr_ack_set(vcpu) &&
-		    exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT &&
-		    kvm_cpu_has_interrupt(vcpu)) {
+		if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT &&
+		    nested_exit_intr_ack_set(vcpu)) {
 			int irq = kvm_cpu_get_interrupt(vcpu);
 			WARN_ON(irq < 0);
 			vmcs12->vm_exit_intr_info = irq |
@@ -4462,8 +4452,10 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
 				vmx_instruction_info, true, len, &gva))
 			return 1;
 		/* _system ok, nested_vmx_check_permission has verified cpl=0 */
-		if (kvm_write_guest_virt_system(vcpu, gva, &field_value, len, &e))
+		if (kvm_write_guest_virt_system(vcpu, gva, &field_value, len, &e)) {
 			kvm_inject_page_fault(vcpu, &e);
+			return 1;
+		}
 	}
 
 	return nested_vmx_succeed(vcpu);
@@ -4892,24 +4884,17 @@ fail:
 	return 1;
 }
 
-
-static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu,
-				       struct vmcs12 *vmcs12)
+/*
+ * Return true if an IO instruction with the specified port and size should cause
+ * a VM-exit into L1.
+ */
+bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port,
+				 int size)
 {
-	unsigned long exit_qualification;
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	gpa_t bitmap, last_bitmap;
-	unsigned int port;
-	int size;
 	u8 b;
 
-	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
-		return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING);
-
-	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-
-	port = exit_qualification >> 16;
-	size = (exit_qualification & 7) + 1;
-
 	last_bitmap = (gpa_t)-1;
 	b = -1;
 
@@ -4936,6 +4921,24 @@ static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu,
 	return false;
 }
 
+static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu,
+				       struct vmcs12 *vmcs12)
+{
+	unsigned long exit_qualification;
+	unsigned short port;
+	int size;
+
+	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
+		return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING);
+
+	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+
+	port = exit_qualification >> 16;
+	size = (exit_qualification & 7) + 1;
+
+	return nested_vmx_check_io_bitmaps(vcpu, port, size);
+}
+
 /*
  * Return 1 if we should exit from L2 to L1 to handle an MSR access access,
  * rather than handle it ourselves in L0. I.e., check whether L1 expressed
@@ -5122,7 +5125,7 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason)
 				vmcs_read32(VM_EXIT_INTR_ERROR_CODE),
 				KVM_ISA_VMX);
 
-	switch (exit_reason) {
+	switch ((u16)exit_reason) {
 	case EXIT_REASON_EXCEPTION_NMI:
 		if (is_nmi(intr_info))
 			return false;
@@ -5556,8 +5559,7 @@ void nested_vmx_vcpu_setup(void)
  * bit in the high half is on if the corresponding bit in the control field
  * may be on. See also vmx_control_verify().
  */
-void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps,
-				bool apicv)
+void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
 {
 	/*
 	 * Note that as a general rule, the high half of the MSRs (bits in
@@ -5584,7 +5586,7 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps,
 		PIN_BASED_EXT_INTR_MASK |
 		PIN_BASED_NMI_EXITING |
 		PIN_BASED_VIRTUAL_NMIS |
-		(apicv ? PIN_BASED_POSTED_INTR : 0);
+		(enable_apicv ? PIN_BASED_POSTED_INTR : 0);
 	msrs->pinbased_ctls_high |=
 		PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR |
 		PIN_BASED_VMX_PREEMPTION_TIMER;
diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h
index 29d205bb4e4f..161c305de3f3 100644
--- a/arch/x86/kvm/vmx/nested.h
+++ b/arch/x86/kvm/vmx/nested.h
@@ -7,8 +7,7 @@
 #include "vmx.h"
 
 void vmx_leave_nested(struct kvm_vcpu *vcpu);
-void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps,
-				bool apicv);
+void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps);
 void nested_vmx_hardware_unsetup(void);
 __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *));
 void nested_vmx_vcpu_setup(void);
@@ -22,6 +21,8 @@ int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
 int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata);
 int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification,
 			u32 vmx_instruction_info, bool wr, int len, gva_t *ret);
+bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port,
+				 int size);
 
 static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu)
 {
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 68d231d49c7a..cb3d9872a88d 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -84,10 +84,14 @@ static unsigned intel_find_arch_event(struct kvm_pmu *pmu,
 
 static unsigned intel_find_fixed_event(int idx)
 {
-	if (idx >= ARRAY_SIZE(fixed_pmc_events))
+	u32 event;
+	size_t size = ARRAY_SIZE(fixed_pmc_events);
+
+	if (idx >= size)
 		return PERF_COUNT_HW_MAX;
 
-	return intel_arch_events[fixed_pmc_events[idx]].event_type;
+	event = fixed_pmc_events[array_index_nospec(idx, size)];
+	return intel_arch_events[event].event_type;
 }
 
 /* check if a PMC is enabled by comparing it with globl_ctrl bits. */
@@ -128,16 +132,20 @@ static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu,
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	bool fixed = idx & (1u << 30);
 	struct kvm_pmc *counters;
+	unsigned int num_counters;
 
 	idx &= ~(3u << 30);
-	if (!fixed && idx >= pmu->nr_arch_gp_counters)
-		return NULL;
-	if (fixed && idx >= pmu->nr_arch_fixed_counters)
+	if (fixed) {
+		counters = pmu->fixed_counters;
+		num_counters = pmu->nr_arch_fixed_counters;
+	} else {
+		counters = pmu->gp_counters;
+		num_counters = pmu->nr_arch_gp_counters;
+	}
+	if (idx >= num_counters)
 		return NULL;
-	counters = fixed ? pmu->fixed_counters : pmu->gp_counters;
 	*mask &= pmu->counter_bitmask[fixed ? KVM_PMC_FIXED : KVM_PMC_GP];
-
-	return &counters[idx];
+	return &counters[array_index_nospec(idx, num_counters)];
 }
 
 static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index d4cb1945b2e3..f83368b5af87 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -86,6 +86,9 @@ ENTRY(vmx_vmexit)
 	/* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
 	FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
 
+	/* Clear RFLAGS.CF and RFLAGS.ZF to preserve VM-Exit, i.e. !VM-Fail. */
+	or $1, %_ASM_AX
+
 	pop %_ASM_AX
 .Lvmexit_skip_rsb:
 #endif
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index e56451e20768..b177e25e3786 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -95,7 +95,7 @@ module_param(emulate_invalid_guest_state, bool, S_IRUGO);
 static bool __read_mostly fasteoi = 1;
 module_param(fasteoi, bool, S_IRUGO);
 
-static bool __read_mostly enable_apicv = 1;
+bool __read_mostly enable_apicv = 1;
 module_param(enable_apicv, bool, S_IRUGO);
 
 /*
@@ -402,6 +402,7 @@ const u32 vmx_msr_index[] = {
 	MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR,
 #endif
 	MSR_EFER, MSR_TSC_AUX, MSR_STAR,
+	MSR_IA32_TSX_CTRL,
 };
 
 #if IS_ENABLED(CONFIG_HYPERV)
@@ -565,6 +566,23 @@ struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr)
 	return NULL;
 }
 
+static int vmx_set_guest_msr(struct vcpu_vmx *vmx, struct shared_msr_entry *msr, u64 data)
+{
+	int ret = 0;
+
+	u64 old_msr_data = msr->data;
+	msr->data = data;
+	if (msr - vmx->guest_msrs < vmx->save_nmsrs) {
+		preempt_disable();
+		ret = kvm_set_shared_msr(msr->index, msr->data,
+					 msr->mask);
+		preempt_enable();
+		if (ret)
+			msr->data = old_msr_data;
+	}
+	return ret;
+}
+
 void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs)
 {
 	vmcs_clear(loaded_vmcs->vmcs);
@@ -575,43 +593,15 @@ void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs)
 }
 
 #ifdef CONFIG_KEXEC_CORE
-/*
- * This bitmap is used to indicate whether the vmclear
- * operation is enabled on all cpus. All disabled by
- * default.
- */
-static cpumask_t crash_vmclear_enabled_bitmap = CPU_MASK_NONE;
-
-static inline void crash_enable_local_vmclear(int cpu)
-{
-	cpumask_set_cpu(cpu, &crash_vmclear_enabled_bitmap);
-}
-
-static inline void crash_disable_local_vmclear(int cpu)
-{
-	cpumask_clear_cpu(cpu, &crash_vmclear_enabled_bitmap);
-}
-
-static inline int crash_local_vmclear_enabled(int cpu)
-{
-	return cpumask_test_cpu(cpu, &crash_vmclear_enabled_bitmap);
-}
-
 static void crash_vmclear_local_loaded_vmcss(void)
 {
 	int cpu = raw_smp_processor_id();
 	struct loaded_vmcs *v;
 
-	if (!crash_local_vmclear_enabled(cpu))
-		return;
-
 	list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu),
 			    loaded_vmcss_on_cpu_link)
 		vmcs_clear(v->vmcs);
 }
-#else
-static inline void crash_enable_local_vmclear(int cpu) { }
-static inline void crash_disable_local_vmclear(int cpu) { }
 #endif /* CONFIG_KEXEC_CORE */
 
 static void __loaded_vmcs_clear(void *arg)
@@ -623,19 +613,24 @@ static void __loaded_vmcs_clear(void *arg)
 		return; /* vcpu migration can race with cpu offline */
 	if (per_cpu(current_vmcs, cpu) == loaded_vmcs->vmcs)
 		per_cpu(current_vmcs, cpu) = NULL;
-	crash_disable_local_vmclear(cpu);
+
+	vmcs_clear(loaded_vmcs->vmcs);
+	if (loaded_vmcs->shadow_vmcs && loaded_vmcs->launched)
+		vmcs_clear(loaded_vmcs->shadow_vmcs);
+
 	list_del(&loaded_vmcs->loaded_vmcss_on_cpu_link);
 
 	/*
-	 * we should ensure updating loaded_vmcs->loaded_vmcss_on_cpu_link
-	 * is before setting loaded_vmcs->vcpu to -1 which is done in
-	 * loaded_vmcs_init. Otherwise, other cpu can see vcpu = -1 fist
-	 * then adds the vmcs into percpu list before it is deleted.
+	 * Ensure all writes to loaded_vmcs, including deleting it from its
+	 * current percpu list, complete before setting loaded_vmcs->vcpu to
+	 * -1, otherwise a different cpu can see vcpu == -1 first and add
+	 * loaded_vmcs to its percpu list before it's deleted from this cpu's
+	 * list. Pairs with the smp_rmb() in vmx_vcpu_load_vmcs().
 	 */
 	smp_wmb();
 
-	loaded_vmcs_init(loaded_vmcs);
-	crash_enable_local_vmclear(cpu);
+	loaded_vmcs->cpu = -1;
+	loaded_vmcs->launched = 0;
 }
 
 void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs)
@@ -1229,18 +1224,17 @@ void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	if (!already_loaded) {
 		loaded_vmcs_clear(vmx->loaded_vmcs);
 		local_irq_disable();
-		crash_disable_local_vmclear(cpu);
 
 		/*
-		 * Read loaded_vmcs->cpu should be before fetching
-		 * loaded_vmcs->loaded_vmcss_on_cpu_link.
-		 * See the comments in __loaded_vmcs_clear().
+		 * Ensure loaded_vmcs->cpu is read before adding loaded_vmcs to
+		 * this cpu's percpu list, otherwise it may not yet be deleted
+		 * from its previous cpu's percpu list.  Pairs with the
+		 * smb_wmb() in __loaded_vmcs_clear().
 		 */
 		smp_rmb();
 
 		list_add(&vmx->loaded_vmcs->loaded_vmcss_on_cpu_link,
 			 &per_cpu(loaded_vmcss_on_cpu, cpu));
-		crash_enable_local_vmclear(cpu);
 		local_irq_enable();
 	}
 
@@ -1284,7 +1278,6 @@ void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		decache_tsc_multiplier(vmx);
 
 	vmx_vcpu_pi_load(vcpu, cpu);
-	vmx->host_pkru = read_pkru();
 	vmx->host_debugctlmsr = get_debugctlmsr();
 }
 
@@ -1569,6 +1562,9 @@ static void setup_msrs(struct vcpu_vmx *vmx)
 	index = __find_msr_index(vmx, MSR_TSC_AUX);
 	if (index >= 0 && guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP))
 		move_msr_up(vmx, index, save_nmsrs++);
+	index = __find_msr_index(vmx, MSR_IA32_TSX_CTRL);
+	if (index >= 0)
+		move_msr_up(vmx, index, save_nmsrs++);
 
 	vmx->save_nmsrs = save_nmsrs;
 	vmx->guest_msrs_dirty = true;
@@ -1668,6 +1664,11 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 #endif
 	case MSR_EFER:
 		return kvm_get_msr_common(vcpu, msr_info);
+	case MSR_IA32_TSX_CTRL:
+		if (!msr_info->host_initiated &&
+		    !(vcpu->arch.arch_capabilities & ARCH_CAP_TSX_CTRL_MSR))
+			return 1;
+		goto find_shared_msr;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr_info->host_initiated &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
@@ -1710,10 +1711,8 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		return vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index,
 				       &msr_info->data);
 	case MSR_IA32_XSS:
-		if (!vmx_xsaves_supported() ||
-		    (!msr_info->host_initiated &&
-		     !(guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
-		       guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))))
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))
 			return 1;
 		msr_info->data = vcpu->arch.ia32_xss;
 		break;
@@ -1767,8 +1766,9 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!msr_info->host_initiated &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP))
 			return 1;
-		/* Else, falls through */
+		goto find_shared_msr;
 	default:
+	find_shared_msr:
 		msr = find_msr_entry(vmx, msr_info->index);
 		if (msr) {
 			msr_info->data = msr->data;
@@ -1863,6 +1863,13 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 					      MSR_IA32_SPEC_CTRL,
 					      MSR_TYPE_RW);
 		break;
+	case MSR_IA32_TSX_CTRL:
+		if (!msr_info->host_initiated &&
+		    !(vcpu->arch.arch_capabilities & ARCH_CAP_TSX_CTRL_MSR))
+			return 1;
+		if (data & ~(TSX_CTRL_RTM_DISABLE | TSX_CTRL_CPUID_CLEAR))
+			return 1;
+		goto find_shared_msr;
 	case MSR_IA32_PRED_CMD:
 		if (!msr_info->host_initiated &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
@@ -1928,10 +1935,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		return vmx_set_vmx_msr(vcpu, msr_index, data);
 	case MSR_IA32_XSS:
-		if (!vmx_xsaves_supported() ||
-		    (!msr_info->host_initiated &&
-		     !(guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
-		       guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))))
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))
 			return 1;
 		/*
 		 * The only supported bit as of Skylake is bit 8, but
@@ -1940,11 +1945,13 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (data != 0)
 			return 1;
 		vcpu->arch.ia32_xss = data;
-		if (vcpu->arch.ia32_xss != host_xss)
-			add_atomic_switch_msr(vmx, MSR_IA32_XSS,
-				vcpu->arch.ia32_xss, host_xss, false);
-		else
-			clear_atomic_switch_msr(vmx, MSR_IA32_XSS);
+		if (vcpu->arch.xsaves_enabled) {
+			if (vcpu->arch.ia32_xss != host_xss)
+				add_atomic_switch_msr(vmx, MSR_IA32_XSS,
+					vcpu->arch.ia32_xss, host_xss, false);
+			else
+				clear_atomic_switch_msr(vmx, MSR_IA32_XSS);
+		}
 		break;
 	case MSR_IA32_RTIT_CTL:
 		if ((pt_mode != PT_MODE_HOST_GUEST) ||
@@ -1998,6 +2005,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			(index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps,
 					PT_CAP_num_address_ranges)))
 			return 1;
+		if (is_noncanonical_address(data, vcpu))
+			return 1;
 		if (index % 2)
 			vmx->pt_desc.guest.addr_b[index / 2] = data;
 		else
@@ -2010,23 +2019,15 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		/* Check reserved bit, higher 32 bits should be zero */
 		if ((data >> 32) != 0)
 			return 1;
-		/* Else, falls through */
+		goto find_shared_msr;
+
 	default:
+	find_shared_msr:
 		msr = find_msr_entry(vmx, msr_index);
-		if (msr) {
-			u64 old_msr_data = msr->data;
-			msr->data = data;
-			if (msr - vmx->guest_msrs < vmx->save_nmsrs) {
-				preempt_disable();
-				ret = kvm_set_shared_msr(msr->index, msr->data,
-							 msr->mask);
-				preempt_enable();
-				if (ret)
-					msr->data = old_msr_data;
-			}
-			break;
-		}
-		ret = kvm_set_msr_common(vcpu, msr_info);
+		if (msr)
+			ret = vmx_set_guest_msr(vmx, msr, data);
+		else
+			ret = kvm_set_msr_common(vcpu, msr_info);
 	}
 
 	return ret;
@@ -2108,21 +2109,6 @@ static int hardware_enable(void)
 	    !hv_get_vp_assist_page(cpu))
 		return -EFAULT;
 
-	INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));
-	INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu));
-	spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
-
-	/*
-	 * Now we can enable the vmclear operation in kdump
-	 * since the loaded_vmcss_on_cpu list on this cpu
-	 * has been initialized.
-	 *
-	 * Though the cpu is not in VMX operation now, there
-	 * is no problem to enable the vmclear operation
-	 * for the loaded_vmcss_on_cpu list is empty!
-	 */
-	crash_enable_local_vmclear(cpu);
-
 	rdmsrl(MSR_IA32_FEATURE_CONTROL, old);
 
 	test_bits = FEATURE_CONTROL_LOCKED;
@@ -2829,6 +2815,9 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 
 static int get_ept_level(struct kvm_vcpu *vcpu)
 {
+	/* Nested EPT currently only supports 4-level walks. */
+	if (is_guest_mode(vcpu) && nested_cpu_has_ept(get_vmcs12(vcpu)))
+		return 4;
 	if (cpu_has_vmx_ept_5levels() && (cpuid_maxphyaddr(vcpu) > 48))
 		return 5;
 	return 4;
@@ -2868,13 +2857,12 @@ void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 			spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock);
 		}
 
-		/* Loading vmcs02.GUEST_CR3 is handled by nested VM-Enter. */
-		if (is_guest_mode(vcpu))
-			update_guest_cr3 = false;
-		else if (enable_unrestricted_guest || is_paging(vcpu))
-			guest_cr3 = kvm_read_cr3(vcpu);
-		else
+		if (!enable_unrestricted_guest && !is_paging(vcpu))
 			guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr;
+		else if (test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail))
+			guest_cr3 = vcpu->arch.cr3;
+		else /* vmcs01.GUEST_CR3 is already up-to-date. */
+			update_guest_cr3 = false;
 		ept_load_pdptrs(vcpu);
 	}
 
@@ -3704,24 +3692,29 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
  * 2. If target vcpu isn't running(root mode), kick it to pick up the
  * interrupt from PIR in next vmentry.
  */
-static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
+static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	int r;
 
 	r = vmx_deliver_nested_posted_interrupt(vcpu, vector);
 	if (!r)
-		return;
+		return 0;
+
+	if (!vcpu->arch.apicv_active)
+		return -1;
 
 	if (pi_test_and_set_pir(vector, &vmx->pi_desc))
-		return;
+		return 0;
 
 	/* If a previous notification has sent the IPI, nothing to do.  */
 	if (pi_test_and_set_on(&vmx->pi_desc))
-		return;
+		return 0;
 
 	if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false))
 		kvm_vcpu_kick(vcpu);
+
+	return 0;
 }
 
 /*
@@ -3792,6 +3785,8 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
 
 void set_cr4_guest_host_mask(struct vcpu_vmx *vmx)
 {
+	BUILD_BUG_ON(KVM_CR4_GUEST_OWNED_BITS & ~KVM_POSSIBLE_CR4_GUEST_BITS);
+
 	vmx->vcpu.arch.cr4_guest_owned_bits = KVM_CR4_GUEST_OWNED_BITS;
 	if (enable_ept)
 		vmx->vcpu.arch.cr4_guest_owned_bits |= X86_CR4_PGE;
@@ -3908,6 +3903,8 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx)
 			guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
 			guest_cpuid_has(vcpu, X86_FEATURE_XSAVES);
 
+		vcpu->arch.xsaves_enabled = xsaves_enabled;
+
 		if (!xsaves_enabled)
 			exec_control &= ~SECONDARY_EXEC_XSAVES;
 
@@ -3997,7 +3994,7 @@ static void ept_set_mmio_spte_mask(void)
 	 * of an EPT paging-structure entry is 110b (write/execute).
 	 */
 	kvm_mmu_set_mmio_spte_mask(VMX_EPT_RWX_MASK,
-				   VMX_EPT_MISCONFIG_WX_VALUE);
+				   VMX_EPT_MISCONFIG_WX_VALUE, 0);
 }
 
 #define VMX_XSS_EXIT_BITMAP 0
@@ -4080,7 +4077,20 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
 			continue;
 		vmx->guest_msrs[j].index = i;
 		vmx->guest_msrs[j].data = 0;
-		vmx->guest_msrs[j].mask = -1ull;
+
+		switch (index) {
+		case MSR_IA32_TSX_CTRL:
+			/*
+			 * No need to pass TSX_CTRL_CPUID_CLEAR through, so
+			 * let's avoid changing CPUID bits under the host
+			 * kernel's feet.
+			 */
+			vmx->guest_msrs[j].mask = ~(u64)TSX_CTRL_CPUID_CLEAR;
+			break;
+		default:
+			vmx->guest_msrs[j].mask = -1ull;
+			break;
+		}
 		++vmx->nmsrs;
 	}
 
@@ -4338,8 +4348,13 @@ static int vmx_nmi_allowed(struct kvm_vcpu *vcpu)
 
 static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu)
 {
-	return (!to_vmx(vcpu)->nested.nested_run_pending &&
-		vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
+	if (to_vmx(vcpu)->nested.nested_run_pending)
+		return false;
+
+	if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu))
+		return true;
+
+	return (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
 		!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
 			(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS));
 }
@@ -4433,7 +4448,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu,
  */
 static void kvm_machine_check(void)
 {
-#if defined(CONFIG_X86_MCE) && defined(CONFIG_X86_64)
+#if defined(CONFIG_X86_MCE)
 	struct pt_regs regs = {
 		.cs = 3, /* Fake ring 3 no matter what the guest ran on */
 		.flags = X86_EFLAGS_IF,
@@ -6094,7 +6109,11 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 
 static bool vmx_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu)
 {
-	return pi_test_on(vcpu_to_pi_desc(vcpu));
+	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+
+	return pi_test_on(pi_desc) ||
+		(pi_test_sn(pi_desc) &&
+		!bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS));
 }
 
 static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
@@ -6433,11 +6452,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 
 	kvm_load_guest_xcr0(vcpu);
 
-	if (static_cpu_has(X86_FEATURE_PKU) &&
-	    kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
-	    vcpu->arch.pkru != vmx->host_pkru)
-		__write_pkru(vcpu->arch.pkru);
-
 	pt_guest_enter(vmx);
 
 	atomic_switch_perf_msrs(vmx);
@@ -6517,18 +6531,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 
 	pt_guest_exit(vmx);
 
-	/*
-	 * eager fpu is enabled if PKEY is supported and CR4 is switched
-	 * back on host, so it is safe to read guest PKRU from current
-	 * XSAVE.
-	 */
-	if (static_cpu_has(X86_FEATURE_PKU) &&
-	    kvm_read_cr4_bits(vcpu, X86_CR4_PKE)) {
-		vcpu->arch.pkru = rdpkru();
-		if (vcpu->arch.pkru != vmx->host_pkru)
-			__write_pkru(vmx->host_pkru);
-	}
-
 	kvm_put_guest_xcr0(vcpu);
 
 	vmx->nested.nested_run_pending = 0;
@@ -6554,6 +6556,10 @@ static struct kvm *vmx_vm_alloc(void)
 	struct kvm_vmx *kvm_vmx = __vmalloc(sizeof(struct kvm_vmx),
 					    GFP_KERNEL_ACCOUNT | __GFP_ZERO,
 					    PAGE_KERNEL);
+
+	if (!kvm_vmx)
+		return NULL;
+
 	return &kvm_vmx->kvm;
 }
 
@@ -6573,6 +6579,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 	free_loaded_vmcs(vmx->loaded_vmcs);
 	kfree(vmx->guest_msrs);
 	kvm_vcpu_uninit(vcpu);
+	kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu);
 	kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu);
 	kmem_cache_free(kvm_vcpu_cache, vmx);
 }
@@ -6588,12 +6595,20 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	if (!vmx)
 		return ERR_PTR(-ENOMEM);
 
+	vmx->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache,
+			GFP_KERNEL_ACCOUNT);
+	if (!vmx->vcpu.arch.user_fpu) {
+		printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n");
+		err = -ENOMEM;
+		goto free_partial_vcpu;
+	}
+
 	vmx->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache,
 			GFP_KERNEL_ACCOUNT);
 	if (!vmx->vcpu.arch.guest_fpu) {
 		printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n");
 		err = -ENOMEM;
-		goto free_partial_vcpu;
+		goto free_user_fpu;
 	}
 
 	vmx->vpid = allocate_vpid();
@@ -6658,8 +6673,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 
 	if (nested)
 		nested_vmx_setup_ctls_msrs(&vmx->nested.msrs,
-					   vmx_capability.ept,
-					   kvm_vcpu_apicv_active(&vmx->vcpu));
+					   vmx_capability.ept);
 	else
 		memset(&vmx->nested.msrs, 0, sizeof(vmx->nested.msrs));
 
@@ -6690,6 +6704,8 @@ uninit_vcpu:
 free_vcpu:
 	free_vpid(vmx->vpid);
 	kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu);
+free_user_fpu:
+	kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu);
 free_partial_vcpu:
 	kmem_cache_free(kvm_vcpu_cache, vmx);
 	return ERR_PTR(err);
@@ -6740,8 +6756,7 @@ static void __init vmx_check_processor_compat(void *rtn)
 	if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0)
 		*(int *)rtn = -EIO;
 	if (nested)
-		nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept,
-					   enable_apicv);
+		nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept);
 	if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) {
 		printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n",
 				smp_processor_id());
@@ -6953,6 +6968,9 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
+	/* xsaves_enabled is recomputed in vmx_compute_secondary_exec_control(). */
+	vcpu->arch.xsaves_enabled = false;
+
 	if (cpu_has_secondary_exec_ctrls()) {
 		vmx_compute_secondary_exec_control(vmx);
 		vmcs_set_secondary_exec_control(vmx->secondary_exec_control);
@@ -6973,6 +6991,15 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 	if (boot_cpu_has(X86_FEATURE_INTEL_PT) &&
 			guest_cpuid_has(vcpu, X86_FEATURE_INTEL_PT))
 		update_intel_pt_cfg(vcpu);
+
+	if (boot_cpu_has(X86_FEATURE_RTM)) {
+		struct shared_msr_entry *msr;
+		msr = find_msr_entry(vmx, MSR_IA32_TSX_CTRL);
+		if (msr) {
+			bool enabled = guest_cpuid_has(vcpu, X86_FEATURE_RTM);
+			vmx_set_guest_msr(vmx, msr, enabled ? 0 : TSX_CTRL_RTM_DISABLE);
+		}
+	}
 }
 
 static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
@@ -6986,6 +7013,40 @@ static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu)
 	to_vmx(vcpu)->req_immediate_exit = true;
 }
 
+static int vmx_check_intercept_io(struct kvm_vcpu *vcpu,
+				  struct x86_instruction_info *info)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	unsigned short port;
+	bool intercept;
+	int size;
+
+	if (info->intercept == x86_intercept_in ||
+	    info->intercept == x86_intercept_ins) {
+		port = info->src_val;
+		size = info->dst_bytes;
+	} else {
+		port = info->dst_val;
+		size = info->src_bytes;
+	}
+
+	/*
+	 * If the 'use IO bitmaps' VM-execution control is 0, IO instruction
+	 * VM-exits depend on the 'unconditional IO exiting' VM-execution
+	 * control.
+	 *
+	 * Otherwise, IO instruction VM-exits are controlled by the IO bitmaps.
+	 */
+	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
+		intercept = nested_cpu_has(vmcs12,
+					   CPU_BASED_UNCOND_IO_EXITING);
+	else
+		intercept = nested_vmx_check_io_bitmaps(vcpu, port, size);
+
+	/* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED.  */
+	return intercept ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE;
+}
+
 static int vmx_check_intercept(struct kvm_vcpu *vcpu,
 			       struct x86_instruction_info *info,
 			       enum x86_intercept_stage stage)
@@ -6993,19 +7054,45 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu,
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
 
+	switch (info->intercept) {
 	/*
 	 * RDPID causes #UD if disabled through secondary execution controls.
 	 * Because it is marked as EmulateOnUD, we need to intercept it here.
 	 */
-	if (info->intercept == x86_intercept_rdtscp &&
-	    !nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) {
-		ctxt->exception.vector = UD_VECTOR;
-		ctxt->exception.error_code_valid = false;
-		return X86EMUL_PROPAGATE_FAULT;
-	}
+	case x86_intercept_rdtscp:
+		if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) {
+			ctxt->exception.vector = UD_VECTOR;
+			ctxt->exception.error_code_valid = false;
+			return X86EMUL_PROPAGATE_FAULT;
+		}
+		break;
+
+	case x86_intercept_in:
+	case x86_intercept_ins:
+	case x86_intercept_out:
+	case x86_intercept_outs:
+		return vmx_check_intercept_io(vcpu, info);
+
+	case x86_intercept_lgdt:
+	case x86_intercept_lidt:
+	case x86_intercept_lldt:
+	case x86_intercept_ltr:
+	case x86_intercept_sgdt:
+	case x86_intercept_sidt:
+	case x86_intercept_sldt:
+	case x86_intercept_str:
+		if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_DESC))
+			return X86EMUL_CONTINUE;
+
+		/* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED.  */
+		break;
 
 	/* TODO: check more intercepts... */
-	return X86EMUL_CONTINUE;
+	default:
+		break;
+	}
+
+	return X86EMUL_UNHANDLEABLE;
 }
 
 #ifdef CONFIG_X86_64
@@ -7100,11 +7187,11 @@ static void vmx_flush_log_dirty(struct kvm *kvm)
 	kvm_flush_pml_buffers(kvm);
 }
 
-static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu)
+static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu, gpa_t gpa)
 {
 	struct vmcs12 *vmcs12;
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	gpa_t gpa, dst;
+	gpa_t dst;
 
 	if (is_guest_mode(vcpu)) {
 		WARN_ON_ONCE(vmx->nested.pml_full);
@@ -7123,7 +7210,7 @@ static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu)
 			return 1;
 		}
 
-		gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS) & ~0xFFFull;
+		gpa &= ~0xFFFull;
 		dst = vmcs12->pml_address + sizeof(u64) * vmcs12->guest_pml_index;
 
 		if (kvm_write_guest_page(vcpu->kvm, gpa_to_gfn(dst), &gpa,
@@ -7564,7 +7651,7 @@ static __init int hardware_setup(void)
 
 	if (nested) {
 		nested_vmx_setup_ctls_msrs(&vmcs_config.nested,
-					   vmx_capability.ept, enable_apicv);
+					   vmx_capability.ept);
 
 		r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers);
 		if (r)
@@ -7698,6 +7785,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.xsaves_supported = vmx_xsaves_supported,
 	.umip_emulated = vmx_umip_emulated,
 	.pt_supported = vmx_pt_supported,
+	.pku_supported = vmx_pku_supported,
 
 	.request_immediate_exit = vmx_request_immediate_exit,
 
@@ -7784,7 +7872,7 @@ module_exit(vmx_exit);
 
 static int __init vmx_init(void)
 {
-	int r;
+	int r, cpu;
 
 #if IS_ENABLED(CONFIG_HYPERV)
 	/*
@@ -7835,6 +7923,12 @@ static int __init vmx_init(void)
 		}
 	}
 
+	for_each_possible_cpu(cpu) {
+		INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));
+		INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu));
+		spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+	}
+
 #ifdef CONFIG_KEXEC_CORE
 	rcu_assign_pointer(crash_vmclear_loaded_vmcss,
 			   crash_vmclear_local_loaded_vmcss);
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 61128b48c503..6935eff28122 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -256,8 +256,6 @@ struct vcpu_vmx {
 
 	u64 current_tsc_ratio;
 
-	u32 host_pkru;
-
 	unsigned long host_debugctlmsr;
 
 	u64 msr_ia32_power_ctl;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0e2fd2941068..df6f6df902c6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -90,6 +90,8 @@ u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA));
 static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE);
 #endif
 
+static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS;
+
 #define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__
 #define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__
 
@@ -438,6 +440,14 @@ void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu)
 		 * for #DB exceptions under VMX.
 		 */
 		vcpu->arch.dr6 ^= payload & DR6_RTM;
+
+		/*
+		 * The #DB payload is defined as compatible with the 'pending
+		 * debug exceptions' field under VMX, not DR6. While bit 12 is
+		 * defined in the 'pending debug exceptions' field (enabled
+		 * breakpoint), it is reserved and must be zero in DR6.
+		 */
+		vcpu->arch.dr6 &= ~BIT(12);
 		break;
 	case PF_VECTOR:
 		vcpu->arch.cr2 = payload;
@@ -817,11 +827,25 @@ void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
 			xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0);
 		vcpu->guest_xcr0_loaded = 1;
 	}
+
+	if (static_cpu_has(X86_FEATURE_PKU) &&
+	    (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) ||
+	     (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU)) &&
+	    vcpu->arch.pkru != vcpu->arch.host_pkru)
+		__write_pkru(vcpu->arch.pkru);
 }
 EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0);
 
 void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
 {
+	if (static_cpu_has(X86_FEATURE_PKU) &&
+	    (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) ||
+	     (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU))) {
+		vcpu->arch.pkru = rdpkru();
+		if (vcpu->arch.pkru != vcpu->arch.host_pkru)
+			__write_pkru(vcpu->arch.host_pkru);
+	}
+
 	if (vcpu->guest_xcr0_loaded) {
 		if (vcpu->arch.xcr0 != host_xcr0)
 			xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0);
@@ -881,9 +905,38 @@ int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 }
 EXPORT_SYMBOL_GPL(kvm_set_xcr);
 
+static u64 kvm_host_cr4_reserved_bits(struct cpuinfo_x86 *c)
+{
+	u64 reserved_bits = CR4_RESERVED_BITS;
+
+	if (!cpu_has(c, X86_FEATURE_XSAVE))
+		reserved_bits |= X86_CR4_OSXSAVE;
+
+	if (!cpu_has(c, X86_FEATURE_SMEP))
+		reserved_bits |= X86_CR4_SMEP;
+
+	if (!cpu_has(c, X86_FEATURE_SMAP))
+		reserved_bits |= X86_CR4_SMAP;
+
+	if (!cpu_has(c, X86_FEATURE_FSGSBASE))
+		reserved_bits |= X86_CR4_FSGSBASE;
+
+	if (!cpu_has(c, X86_FEATURE_PKU))
+		reserved_bits |= X86_CR4_PKE;
+
+	if (!cpu_has(c, X86_FEATURE_LA57) &&
+	    !(cpuid_ecx(0x7) & bit(X86_FEATURE_LA57)))
+		reserved_bits |= X86_CR4_LA57;
+
+	if (!cpu_has(c, X86_FEATURE_UMIP) && !kvm_x86_ops->umip_emulated())
+		reserved_bits |= X86_CR4_UMIP;
+
+	return reserved_bits;
+}
+
 static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
-	if (cr4 & CR4_RESERVED_BITS)
+	if (cr4 & cr4_reserved_bits)
 		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && (cr4 & X86_CR4_OSXSAVE))
@@ -922,6 +975,8 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	if (is_long_mode(vcpu)) {
 		if (!(cr4 & X86_CR4_PAE))
 			return 1;
+		if ((cr4 ^ old_cr4) & X86_CR4_LA57)
+			return 1;
 	} else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE)
 		   && ((cr4 ^ old_cr4) & pdptr_bits)
 		   && !load_pdptrs(vcpu, vcpu->arch.walk_mmu,
@@ -1049,9 +1104,11 @@ static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu)
 
 static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
 {
+	size_t size = ARRAY_SIZE(vcpu->arch.db);
+
 	switch (dr) {
 	case 0 ... 3:
-		vcpu->arch.db[dr] = val;
+		vcpu->arch.db[array_index_nospec(dr, size)] = val;
 		if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
 			vcpu->arch.eff_db[dr] = val;
 		break;
@@ -1088,9 +1145,11 @@ EXPORT_SYMBOL_GPL(kvm_set_dr);
 
 int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val)
 {
+	size_t size = ARRAY_SIZE(vcpu->arch.db);
+
 	switch (dr) {
 	case 0 ... 3:
-		*val = vcpu->arch.db[dr];
+		*val = vcpu->arch.db[array_index_nospec(dr, size)];
 		break;
 	case 4:
 		/* fall through */
@@ -1251,29 +1310,16 @@ u64 kvm_get_arch_capabilities(void)
 		data |= ARCH_CAP_SKIP_VMENTRY_L1DFLUSH;
 
 	/*
-	 * On TAA affected systems, export MDS_NO=0 when:
-	 *	- TSX is enabled on the host, i.e. X86_FEATURE_RTM=1.
-	 *	- Updated microcode is present. This is detected by
-	 *	  the presence of ARCH_CAP_TSX_CTRL_MSR and ensures
-	 *	  that VERW clears CPU buffers.
-	 *
-	 * When MDS_NO=0 is exported, guests deploy clear CPU buffer
-	 * mitigation and don't complain:
-	 *
-	 *	"Vulnerable: Clear CPU buffers attempted, no microcode"
-	 *
-	 * If TSX is disabled on the system, guests are also mitigated against
-	 * TAA and clear CPU buffer mitigation is not required for guests.
+	 * On TAA affected systems:
+	 *      - nothing to do if TSX is disabled on the host.
+	 *      - we emulate TSX_CTRL if present on the host.
+	 *	  This lets the guest use VERW to clear CPU buffers.
 	 */
 	if (!boot_cpu_has(X86_FEATURE_RTM))
-		data &= ~ARCH_CAP_TAA_NO;
+		data &= ~(ARCH_CAP_TAA_NO | ARCH_CAP_TSX_CTRL_MSR);
 	else if (!boot_cpu_has_bug(X86_BUG_TAA))
 		data |= ARCH_CAP_TAA_NO;
-	else if (data & ARCH_CAP_TSX_CTRL_MSR)
-		data &= ~ARCH_CAP_MDS_NO;
 
-	/* KVM does not emulate MSR_IA32_TSX_CTRL.  */
-	data &= ~ARCH_CAP_TSX_CTRL_MSR;
 	return data;
 }
 
@@ -2377,7 +2423,10 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	default:
 		if (msr >= MSR_IA32_MC0_CTL &&
 		    msr < MSR_IA32_MCx_CTL(bank_num)) {
-			u32 offset = msr - MSR_IA32_MC0_CTL;
+			u32 offset = array_index_nospec(
+				msr - MSR_IA32_MC0_CTL,
+				MSR_IA32_MCx_CTL(bank_num) - MSR_IA32_MC0_CTL);
+
 			/* only 0 or all 1s can be written to IA32_MCi_CTL
 			 * some Linux kernels though clear bit 10 in bank 4 to
 			 * workaround a BIOS/GART TBL issue on AMD K8s, ignore
@@ -2579,7 +2628,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		return kvm_mtrr_set_msr(vcpu, msr, data);
 	case MSR_IA32_APICBASE:
 		return kvm_set_apic_base(vcpu, msr_info);
-	case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
+	case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:
 		return kvm_x2apic_msr_write(vcpu, msr, data);
 	case MSR_IA32_TSCDEADLINE:
 		kvm_set_lapic_tscdeadline_msr(vcpu, data);
@@ -2796,7 +2845,10 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host)
 	default:
 		if (msr >= MSR_IA32_MC0_CTL &&
 		    msr < MSR_IA32_MCx_CTL(bank_num)) {
-			u32 offset = msr - MSR_IA32_MC0_CTL;
+			u32 offset = array_index_nospec(
+				msr - MSR_IA32_MC0_CTL,
+				MSR_IA32_MCx_CTL(bank_num) - MSR_IA32_MC0_CTL);
+
 			data = vcpu->arch.mce_banks[offset];
 			break;
 		}
@@ -2873,7 +2925,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_APICBASE:
 		msr_info->data = kvm_get_apic_base(vcpu);
 		break;
-	case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
+	case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:
 		return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data);
 		break;
 	case MSR_IA32_TSCDEADLINE:
@@ -3309,9 +3361,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	kvm_x86_ops->vcpu_load(vcpu, cpu);
 
-	fpregs_assert_state_consistent();
-	if (test_thread_flag(TIF_NEED_FPU_LOAD))
-		switch_fpu_return();
+	/* Save host pkru register if supported */
+	vcpu->arch.host_pkru = read_pkru();
 
 	/* Apply any externally detected TSC adjustments (due to suspend) */
 	if (unlikely(vcpu->arch.tsc_offset_adjustment)) {
@@ -3506,7 +3557,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu,
 	unsigned bank_num = mcg_cap & 0xff, bank;
 
 	r = -EINVAL;
-	if (!bank_num || bank_num >= KVM_MAX_MCE_BANKS)
+	if (!bank_num || bank_num > KVM_MAX_MCE_BANKS)
 		goto out;
 	if (mcg_cap & ~(kvm_mce_cap_supported | 0xff | 0xff0000))
 		goto out;
@@ -6231,11 +6282,11 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type)
 	return r;
 }
 
-static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
+static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 				  bool write_fault_to_shadow_pgtable,
 				  int emulation_type)
 {
-	gpa_t gpa = cr2;
+	gpa_t gpa = cr2_or_gpa;
 	kvm_pfn_t pfn;
 
 	if (!(emulation_type & EMULTYPE_ALLOW_RETRY))
@@ -6249,7 +6300,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
 		 * Write permission should be allowed since only
 		 * write access need to be emulated.
 		 */
-		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL);
+		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL);
 
 		/*
 		 * If the mapping is invalid in guest, let cpu retry
@@ -6306,10 +6357,10 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
 }
 
 static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
-			      unsigned long cr2,  int emulation_type)
+			      gpa_t cr2_or_gpa,  int emulation_type)
 {
 	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
-	unsigned long last_retry_eip, last_retry_addr, gpa = cr2;
+	unsigned long last_retry_eip, last_retry_addr, gpa = cr2_or_gpa;
 
 	last_retry_eip = vcpu->arch.last_retry_eip;
 	last_retry_addr = vcpu->arch.last_retry_addr;
@@ -6338,14 +6389,14 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
 	if (x86_page_table_writing_insn(ctxt))
 		return false;
 
-	if (ctxt->eip == last_retry_eip && last_retry_addr == cr2)
+	if (ctxt->eip == last_retry_eip && last_retry_addr == cr2_or_gpa)
 		return false;
 
 	vcpu->arch.last_retry_eip = ctxt->eip;
-	vcpu->arch.last_retry_addr = cr2;
+	vcpu->arch.last_retry_addr = cr2_or_gpa;
 
 	if (!vcpu->arch.mmu->direct_map)
-		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL);
+		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL);
 
 	kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa));
 
@@ -6489,11 +6540,8 @@ static bool is_vmware_backdoor_opcode(struct x86_emulate_ctxt *ctxt)
 	return false;
 }
 
-int x86_emulate_instruction(struct kvm_vcpu *vcpu,
-			    unsigned long cr2,
-			    int emulation_type,
-			    void *insn,
-			    int insn_len)
+int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+			    int emulation_type, void *insn, int insn_len)
 {
 	int r;
 	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
@@ -6536,8 +6584,9 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 		if (r != EMULATION_OK)  {
 			if (emulation_type & EMULTYPE_TRAP_UD)
 				return EMULATE_FAIL;
-			if (reexecute_instruction(vcpu, cr2, write_fault_to_spt,
-						emulation_type))
+			if (reexecute_instruction(vcpu, cr2_or_gpa,
+						  write_fault_to_spt,
+						  emulation_type))
 				return EMULATE_DONE;
 			if (ctxt->have_exception) {
 				/*
@@ -6566,7 +6615,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 		return EMULATE_DONE;
 	}
 
-	if (retry_instruction(ctxt, cr2, emulation_type))
+	if (retry_instruction(ctxt, cr2_or_gpa, emulation_type))
 		return EMULATE_DONE;
 
 	/* this is needed for vmware backdoor interface to work since it
@@ -6578,7 +6627,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 
 restart:
 	/* Save the faulting GPA (cr2) in the address field */
-	ctxt->exception.address = cr2;
+	ctxt->exception.address = cr2_or_gpa;
 
 	r = x86_emulate_insn(ctxt);
 
@@ -6586,7 +6635,7 @@ restart:
 		return EMULATE_DONE;
 
 	if (r == EMULATION_FAILED) {
-		if (reexecute_instruction(vcpu, cr2, write_fault_to_spt,
+		if (reexecute_instruction(vcpu, cr2_or_gpa, write_fault_to_spt,
 					emulation_type))
 			return EMULATE_DONE;
 
@@ -6623,7 +6672,7 @@ restart:
 		if (!ctxt->have_exception ||
 		    exception_type(ctxt->exception.vector) == EXCPT_TRAP) {
 			kvm_rip_write(vcpu, ctxt->eip);
-			if (r == EMULATE_DONE && ctxt->tf)
+			if (r == EMULATE_DONE && (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)))
 				kvm_vcpu_do_singlestep(vcpu, &r);
 			__kvm_set_rflags(vcpu, ctxt->eflags);
 		}
@@ -6985,33 +7034,25 @@ static struct perf_guest_info_callbacks kvm_guest_cbs = {
 	.handle_intel_pt_intr	= kvm_handle_intel_pt_intr,
 };
 
+extern u8 __read_mostly shadow_phys_bits;
+
 static void kvm_set_mmio_spte_mask(void)
 {
 	u64 mask;
-	int maxphyaddr = boot_cpu_data.x86_phys_bits;
-
-	/*
-	 * Set the reserved bits and the present bit of an paging-structure
-	 * entry to generate page fault with PFER.RSV = 1.
-	 */
 
 	/*
-	 * Mask the uppermost physical address bit, which would be reserved as
-	 * long as the supported physical address width is less than 52.
+	 * Set a reserved PA bit in MMIO SPTEs to generate page faults with
+	 * PFEC.RSVD=1 on MMIO accesses.  64-bit PTEs (PAE, x86-64, and EPT
+	 * paging) support a maximum of 52 bits of PA, i.e. if the CPU supports
+	 * 52-bit physical addresses then there are no reserved PA bits in the
+	 * PTEs and so the reserved PA approach must be disabled.
 	 */
-	mask = 1ull << 51;
-
-	/* Set the present bit. */
-	mask |= 1ull;
-
-	/*
-	 * If reserved bit is not supported, clear the present bit to disable
-	 * mmio page fault.
-	 */
-	if (IS_ENABLED(CONFIG_X86_64) && maxphyaddr == 52)
-		mask &= ~1ull;
+	if (shadow_phys_bits < 52)
+		mask = BIT_ULL(51) | PT_PRESENT_MASK;
+	else
+		mask = 0;
 
-	kvm_mmu_set_mmio_spte_mask(mask, mask);
+	kvm_mmu_set_mmio_spte_mask(mask, mask, ACC_WRITE_MASK | ACC_USER_MASK);
 }
 
 #ifdef CONFIG_X86_64
@@ -7367,7 +7408,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu)
 	kvm_x86_ops->update_cr8_intercept(vcpu, tpr, max_irr);
 }
 
-static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
+static int inject_pending_event(struct kvm_vcpu *vcpu)
 {
 	int r;
 
@@ -7403,7 +7444,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
 	 * from L2 to L1.
 	 */
 	if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) {
-		r = kvm_x86_ops->check_nested_events(vcpu, req_int_win);
+		r = kvm_x86_ops->check_nested_events(vcpu);
 		if (r != 0)
 			return r;
 	}
@@ -7465,7 +7506,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
 		 * KVM_REQ_EVENT only on certain events and not unconditionally?
 		 */
 		if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) {
-			r = kvm_x86_ops->check_nested_events(vcpu, req_int_win);
+			r = kvm_x86_ops->check_nested_events(vcpu);
 			if (r != 0)
 				return r;
 		}
@@ -7776,9 +7817,8 @@ static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu)
 	kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap);
 }
 
-int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
-		unsigned long start, unsigned long end,
-		bool blockable)
+void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
+					    unsigned long start, unsigned long end)
 {
 	unsigned long apic_address;
 
@@ -7789,8 +7829,6 @@ int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
 	apic_address = gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
 	if (start <= apic_address && apic_address < end)
 		kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD);
-
-	return 0;
 }
 
 void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
@@ -7938,7 +7976,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			goto out;
 		}
 
-		if (inject_pending_event(vcpu, req_int_win) != 0)
+		if (inject_pending_event(vcpu) != 0)
 			req_immediate_exit = true;
 		else {
 			/* Enable SMI/NMI/IRQ window open exits if needed.
@@ -8033,8 +8071,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		wait_lapic_expire(vcpu);
 	guest_enter_irqoff();
 
-	/* The preempt notifier should have taken care of the FPU already.  */
-	WARN_ON_ONCE(test_thread_flag(TIF_NEED_FPU_LOAD));
+	fpregs_assert_state_consistent();
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		switch_fpu_return();
 
 	if (unlikely(vcpu->arch.switch_db_regs)) {
 		set_debugreg(0, 7);
@@ -8154,7 +8193,7 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu)
 static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu)
 {
 	if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events)
-		kvm_x86_ops->check_nested_events(vcpu, false);
+		kvm_x86_ops->check_nested_events(vcpu);
 
 	return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE &&
 		!vcpu->arch.apf.halted);
@@ -8291,12 +8330,26 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static void kvm_save_current_fpu(struct fpu *fpu)
+{
+	/*
+	 * If the target FPU state is not resident in the CPU registers, just
+	 * memcpy() from current, else save CPU state directly to the target.
+	 */
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		memcpy(&fpu->state, &current->thread.fpu.state,
+		       fpu_kernel_xstate_size);
+	else
+		copy_fpregs_to_fpstate(fpu);
+}
+
 /* Swap (qemu) user FPU context for the guest FPU context. */
 static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 {
 	fpregs_lock();
 
-	copy_fpregs_to_fpstate(&vcpu->arch.user_fpu);
+	kvm_save_current_fpu(vcpu->arch.user_fpu);
+
 	/* PKRU is separately restored in kvm_x86_ops->run.  */
 	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state,
 				~XFEATURE_MASK_PKRU);
@@ -8312,8 +8365,9 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
 	fpregs_lock();
 
-	copy_fpregs_to_fpstate(vcpu->arch.guest_fpu);
-	copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state);
+	kvm_save_current_fpu(vcpu->arch.guest_fpu);
+
+	copy_kernel_to_fpregs(&vcpu->arch.user_fpu->state);
 
 	fpregs_mark_activate();
 	fpregs_unlock();
@@ -8534,6 +8588,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
 	vcpu_load(vcpu);
+	if (kvm_mpx_supported())
+		kvm_load_guest_fpu(vcpu);
 
 	kvm_apic_accept_events(vcpu);
 	if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED &&
@@ -8542,6 +8598,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 	else
 		mp_state->mp_state = vcpu->arch.mp_state;
 
+	if (kvm_mpx_supported())
+		kvm_put_guest_fpu(vcpu);
 	vcpu_put(vcpu);
 	return 0;
 }
@@ -8961,13 +9019,7 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.apf.msr_val = 0;
-
-	vcpu_load(vcpu);
-	kvm_mmu_unload(vcpu);
-	vcpu_put(vcpu);
-
-	kvm_x86_ops->vcpu_free(vcpu);
+	kvm_arch_vcpu_free(vcpu);
 }
 
 void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
@@ -9159,6 +9211,8 @@ int kvm_arch_hardware_setup(void)
 	if (r != 0)
 		return r;
 
+	cr4_reserved_bits = kvm_host_cr4_reserved_bits(&boot_cpu_data);
+
 	if (kvm_has_tsc_control) {
 		/*
 		 * Make sure the user can only configure tsc_khz values that
@@ -9500,6 +9554,13 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 {
 	int i;
 
+	/*
+	 * Clear out the previous array pointers for the KVM_MR_MOVE case.  The
+	 * old arrays will be freed by __kvm_set_memory_region() if installing
+	 * the new memslot is successful.
+	 */
+	memset(&slot->arch, 0, sizeof(slot->arch));
+
 	for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) {
 		struct kvm_lpage_info *linfo;
 		unsigned long ugfn;
@@ -9581,6 +9642,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				const struct kvm_userspace_memory_region *mem,
 				enum kvm_mr_change change)
 {
+	if (change == KVM_MR_MOVE)
+		return kvm_arch_create_memslot(kvm, memslot,
+					       mem->memory_size >> PAGE_SHIFT);
+
 	return 0;
 }
 
@@ -9820,7 +9885,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
 	      work->arch.cr3 != vcpu->arch.mmu->get_cr3(vcpu))
 		return;
 
-	vcpu->arch.mmu->page_fault(vcpu, work->gva, 0, true);
+	vcpu->arch.mmu->page_fault(vcpu, work->cr2_or_gpa, 0, true);
 }
 
 static inline u32 kvm_async_pf_hash_fn(gfn_t gfn)
@@ -9903,7 +9968,7 @@ void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
 {
 	struct x86_exception fault;
 
-	trace_kvm_async_pf_not_present(work->arch.token, work->gva);
+	trace_kvm_async_pf_not_present(work->arch.token, work->cr2_or_gpa);
 	kvm_add_async_pf_gfn(vcpu, work->arch.gfn);
 
 	if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) ||
@@ -9931,7 +9996,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 		work->arch.token = ~0; /* broadcast wakeup */
 	else
 		kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
-	trace_kvm_async_pf_ready(work->arch.token, work->gva);
+	trace_kvm_async_pf_ready(work->arch.token, work->cr2_or_gpa);
 
 	if (vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED &&
 	    !apf_get_user(vcpu, &val)) {
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index a470ff0868c5..8c0b13cc3c6a 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -281,7 +281,7 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
 bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn,
 					  int page_num);
 bool kvm_vector_hashing_enabled(void);
-int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2,
+int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 			    int emulation_type, void *insn, int insn_len);
 
 #define KVM_SUPPORTED_XCR0     (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index e0e006f1624e..67a91fd38eef 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -24,6 +24,7 @@ unsigned long __clear_user(void __user *addr, unsigned long size)
 	asm volatile(
 		"	testq  %[size8],%[size8]\n"
 		"	jz     4f\n"
+		"	.align 16\n"
 		"0:	movq $0,(%[dst])\n"
 		"	addq   $8,%[dst]\n"
 		"	decl %%ecx ; jnz   0b\n"
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index 0a0e9112f284..5cb9f009f2be 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -909,7 +909,7 @@ EndTable
 
 GrpTable: Grp3_2
 0: TEST Ev,Iz
-1:
+1: TEST Ev,Iz
 2: NOT Ev
 3: NEG Ev
 4: MUL rAX,Ev
diff --git a/arch/x86/math-emu/wm_sqrt.S b/arch/x86/math-emu/wm_sqrt.S
index f031c0e19356..515cdee90df7 100644
--- a/arch/x86/math-emu/wm_sqrt.S
+++ b/arch/x86/math-emu/wm_sqrt.S
@@ -209,7 +209,7 @@ sqrt_stage_2_finish:
 
 #ifdef PARANOID
 /* It should be possible to get here only if the arg is ffff....ffff */
-	cmp	$0xffffffff,FPU_fsqrt_arg_1
+	cmpl	$0xffffffff,FPU_fsqrt_arg_1
 	jnz	sqrt_stage_2_error
 #endif /* PARANOID */
 
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 3589db475280..7aa188950d42 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -206,7 +206,7 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
 	return pmd_k;
 }
 
-void vmalloc_sync_all(void)
+static void vmalloc_sync(void)
 {
 	unsigned long address;
 
@@ -233,6 +233,16 @@ void vmalloc_sync_all(void)
 	}
 }
 
+void vmalloc_sync_mappings(void)
+{
+	vmalloc_sync();
+}
+
+void vmalloc_sync_unmappings(void)
+{
+	vmalloc_sync();
+}
+
 /*
  * 32-bit:
  *
@@ -335,11 +345,23 @@ out:
 
 #else /* CONFIG_X86_64: */
 
-void vmalloc_sync_all(void)
+void vmalloc_sync_mappings(void)
 {
+	/*
+	 * 64-bit mappings might allocate new p4d/pud pages
+	 * that need to be propagated to all tasks' PGDs.
+	 */
 	sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END);
 }
 
+void vmalloc_sync_unmappings(void)
+{
+	/*
+	 * Unmappings never allocate or free p4d/pud pages.
+	 * No work is required here.
+	 */
+}
+
 /*
  * 64-bit:
  *
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index fd10d91a6115..af352e228fa2 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -121,8 +121,6 @@ __ref void *alloc_low_pages(unsigned int num)
 	} else {
 		pfn = pgt_buf_end;
 		pgt_buf_end += num;
-		printk(KERN_DEBUG "BRK [%#010lx, %#010lx] PGTABLE\n",
-			pfn << PAGE_SHIFT, (pgt_buf_end << PAGE_SHIFT) - 1);
 	}
 
 	for (i = 0; i < num; i++) {
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index b8ef8557d4b3..2a36902d418c 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -372,7 +372,7 @@ static void enter_uniprocessor(void)
 	int cpu;
 	int err;
 
-	if (downed_cpus == NULL &&
+	if (!cpumask_available(downed_cpus) &&
 	    !alloc_cpumask_var(&downed_cpus, GFP_KERNEL)) {
 		pr_notice("Failed to allocate mask\n");
 		goto out;
@@ -402,7 +402,7 @@ static void leave_uniprocessor(void)
 	int cpu;
 	int err;
 
-	if (downed_cpus == NULL || cpumask_weight(downed_cpus) == 0)
+	if (!cpumask_available(downed_cpus) || cpumask_weight(downed_cpus) == 0)
 		return;
 	pr_notice("Re-enabling CPUs...\n");
 	for_each_cpu(cpu, downed_cpus) {
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index e14e95ea7338..7155b7e0899e 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -42,7 +42,8 @@ struct cpa_data {
 	unsigned long	pfn;
 	unsigned int	flags;
 	unsigned int	force_split		: 1,
-			force_static_prot	: 1;
+			force_static_prot	: 1,
+			force_flush_all		: 1;
 	struct page	**pages;
 };
 
@@ -352,10 +353,10 @@ static void cpa_flush(struct cpa_data *data, int cache)
 		return;
 	}
 
-	if (cpa->numpages <= tlb_single_page_flush_ceiling)
-		on_each_cpu(__cpa_flush_tlb, cpa, 1);
-	else
+	if (cpa->force_flush_all || cpa->numpages > tlb_single_page_flush_ceiling)
 		flush_tlb_all();
+	else
+		on_each_cpu(__cpa_flush_tlb, cpa, 1);
 
 	if (!cache)
 		return;
@@ -1584,6 +1585,8 @@ static int cpa_process_alias(struct cpa_data *cpa)
 		alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
 		alias_cpa.curpage = 0;
 
+		cpa->force_flush_all = 1;
+
 		ret = __change_page_attr_set_clr(&alias_cpa, 0);
 		if (ret)
 			return ret;
@@ -1604,6 +1607,7 @@ static int cpa_process_alias(struct cpa_data *cpa)
 		alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
 		alias_cpa.curpage = 0;
 
+		cpa->force_flush_all = 1;
 		/*
 		 * The high mapping range is imprecise, so ignore the
 		 * return value.
@@ -2325,7 +2329,7 @@ int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
 		.pgd = pgd,
 		.numpages = numpages,
 		.mask_set = __pgprot(0),
-		.mask_clr = __pgprot(0),
+		.mask_clr = __pgprot(~page_flags & (_PAGE_NX|_PAGE_RW)),
 		.flags = 0,
 	};
 
@@ -2334,12 +2338,6 @@ int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
 	if (!(__supported_pte_mask & _PAGE_NX))
 		goto out;
 
-	if (!(page_flags & _PAGE_NX))
-		cpa.mask_clr = __pgprot(_PAGE_NX);
-
-	if (!(page_flags & _PAGE_RW))
-		cpa.mask_clr = __pgprot(_PAGE_RW);
-
 	if (!(page_flags & _PAGE_ENC))
 		cpa.mask_clr = pgprot_encrypted(cpa.mask_clr);
 
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index eaaed5bfc4a4..bd318043b259 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -138,6 +138,19 @@ static bool is_ereg(u32 reg)
 			     BIT(BPF_REG_AX));
 }
 
+/*
+ * is_ereg_8l() == true if BPF register 'reg' is mapped to access x86-64
+ * lower 8-bit registers dil,sil,bpl,spl,r8b..r15b, which need extra byte
+ * of encoding. al,cl,dl,bl have simpler encoding.
+ */
+static bool is_ereg_8l(u32 reg)
+{
+	return is_ereg(reg) ||
+	    (1 << reg) & (BIT(BPF_REG_1) |
+			  BIT(BPF_REG_2) |
+			  BIT(BPF_REG_FP));
+}
+
 static bool is_axreg(u32 reg)
 {
 	return reg == BPF_REG_0;
@@ -747,9 +760,8 @@ st:			if (is_imm8(insn->off))
 			/* STX: *(u8*)(dst_reg + off) = src_reg */
 		case BPF_STX | BPF_MEM | BPF_B:
 			/* Emit 'mov byte ptr [rax + off], al' */
-			if (is_ereg(dst_reg) || is_ereg(src_reg) ||
-			    /* We have to add extra byte for x86 SIL, DIL regs */
-			    src_reg == BPF_REG_1 || src_reg == BPF_REG_2)
+			if (is_ereg(dst_reg) || is_ereg_8l(src_reg))
+				/* Add extra byte for eregs or SIL,DIL,BPL in src_reg */
 				EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88);
 			else
 				EMIT1(0x88);
diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c
index b29e82f190c7..4c9f10b73eb6 100644
--- a/arch/x86/net/bpf_jit_comp32.c
+++ b/arch/x86/net/bpf_jit_comp32.c
@@ -2056,7 +2056,9 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 					      STACK_VAR(dst_hi));
 					EMIT(0x0, 4);
 				} else {
-					EMIT3(0xC7, add_1reg(0xC0, dst_hi), 0);
+					/* xor dst_hi,dst_hi */
+					EMIT2(0x33,
+					      add_2reg(0xC0, dst_hi, dst_hi));
 				}
 				break;
 			case BPF_DW:
@@ -2157,6 +2159,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 					      add_2reg(0x40, IA32_EBP,
 						       IA32_EDX),
 					      STACK_VAR(dst_hi));
+			} else {
+				/* mov dreg_lo,dst_lo */
+				EMIT2(0x89, add_2reg(0xC0, dreg_lo, dst_lo));
+				if (is_jmp64)
+					/* mov dreg_hi,dst_hi */
+					EMIT2(0x89,
+					      add_2reg(0xC0, dreg_hi, dst_hi));
 			}
 
 			if (sstk) {
@@ -2215,8 +2224,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		case BPF_JMP | BPF_JSET | BPF_X:
 		case BPF_JMP32 | BPF_JSET | BPF_X: {
 			bool is_jmp64 = BPF_CLASS(insn->code) == BPF_JMP;
-			u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
-			u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+			u8 dreg_lo = IA32_EAX;
+			u8 dreg_hi = IA32_EDX;
 			u8 sreg_lo = sstk ? IA32_ECX : src_lo;
 			u8 sreg_hi = sstk ? IA32_EBX : src_hi;
 
@@ -2241,17 +2250,19 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			}
 			/* and dreg_lo,sreg_lo */
 			EMIT2(0x23, add_2reg(0xC0, sreg_lo, dreg_lo));
-			/* and dreg_hi,sreg_hi */
-			EMIT2(0x23, add_2reg(0xC0, sreg_hi, dreg_hi));
-			/* or dreg_lo,dreg_hi */
-			EMIT2(0x09, add_2reg(0xC0, dreg_lo, dreg_hi));
+			if (is_jmp64) {
+				/* and dreg_hi,sreg_hi */
+				EMIT2(0x23, add_2reg(0xC0, sreg_hi, dreg_hi));
+				/* or dreg_lo,dreg_hi */
+				EMIT2(0x09, add_2reg(0xC0, dreg_lo, dreg_hi));
+			}
 			goto emit_cond_jmp;
 		}
 		case BPF_JMP | BPF_JSET | BPF_K:
 		case BPF_JMP32 | BPF_JSET | BPF_K: {
 			bool is_jmp64 = BPF_CLASS(insn->code) == BPF_JMP;
-			u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
-			u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+			u8 dreg_lo = IA32_EAX;
+			u8 dreg_hi = IA32_EDX;
 			u8 sreg_lo = IA32_ECX;
 			u8 sreg_hi = IA32_EBX;
 			u32 hi;
@@ -2264,6 +2275,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 					      add_2reg(0x40, IA32_EBP,
 						       IA32_EDX),
 					      STACK_VAR(dst_hi));
+			} else {
+				/* mov dreg_lo,dst_lo */
+				EMIT2(0x89, add_2reg(0xC0, dreg_lo, dst_lo));
+				if (is_jmp64)
+					/* mov dreg_hi,dst_hi */
+					EMIT2(0x89,
+					      add_2reg(0xC0, dreg_hi, dst_hi));
 			}
 
 			/* mov ecx,imm32 */
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index e723559c386a..0c67a5a94de3 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -572,6 +572,10 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, pci_invalid_bar);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6f60, pci_invalid_bar);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_invalid_bar);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0xa1ec, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0xa1ed, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0xa26c, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0xa26d, pci_invalid_bar);
 
 /*
  * Device [1022:7808]
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 3304f61538a2..9b1b133c860a 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -481,7 +481,6 @@ void __init efi_init(void)
 	efi_char16_t *c16;
 	char vendor[100] = "unknown";
 	int i = 0;
-	void *tmp;
 
 #ifdef CONFIG_X86_32
 	if (boot_params.efi_info.efi_systab_hi ||
@@ -506,14 +505,16 @@ void __init efi_init(void)
 	/*
 	 * Show what we know for posterity
 	 */
-	c16 = tmp = early_memremap(efi.systab->fw_vendor, 2);
+	c16 = early_memremap_ro(efi.systab->fw_vendor,
+				sizeof(vendor) * sizeof(efi_char16_t));
 	if (c16) {
-		for (i = 0; i < sizeof(vendor) - 1 && *c16; ++i)
-			vendor[i] = *c16++;
+		for (i = 0; i < sizeof(vendor) - 1 && c16[i]; ++i)
+			vendor[i] = c16[i];
 		vendor[i] = '\0';
-	} else
+		early_memunmap(c16, sizeof(vendor) * sizeof(efi_char16_t));
+	} else {
 		pr_err("Could not map the firmware vendor!\n");
-	early_memunmap(tmp, 2);
+	}
 
 	pr_info("EFI v%u.%.02u by %s\n",
 		efi.systab->hdr.revision >> 16,
@@ -930,16 +931,14 @@ static void __init __efi_enter_virtual_mode(void)
 
 	if (efi_alloc_page_tables()) {
 		pr_err("Failed to allocate EFI page tables\n");
-		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
-		return;
+		goto err;
 	}
 
 	efi_merge_regions();
 	new_memmap = efi_map_regions(&count, &pg_shift);
 	if (!new_memmap) {
 		pr_err("Error reallocating memory, EFI runtime non-functional!\n");
-		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
-		return;
+		goto err;
 	}
 
 	pa = __pa(new_memmap);
@@ -953,8 +952,7 @@ static void __init __efi_enter_virtual_mode(void)
 
 	if (efi_memmap_init_late(pa, efi.memmap.desc_size * count)) {
 		pr_err("Failed to remap late EFI memory map\n");
-		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
-		return;
+		goto err;
 	}
 
 	if (efi_enabled(EFI_DBG)) {
@@ -962,12 +960,11 @@ static void __init __efi_enter_virtual_mode(void)
 		efi_print_memmap();
 	}
 
-	BUG_ON(!efi.systab);
+	if (WARN_ON(!efi.systab))
+		goto err;
 
-	if (efi_setup_page_tables(pa, 1 << pg_shift)) {
-		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
-		return;
-	}
+	if (efi_setup_page_tables(pa, 1 << pg_shift))
+		goto err;
 
 	efi_sync_low_kernel_mappings();
 
@@ -987,9 +984,9 @@ static void __init __efi_enter_virtual_mode(void)
 	}
 
 	if (status != EFI_SUCCESS) {
-		pr_alert("Unable to switch EFI into virtual mode (status=%lx)!\n",
-			 status);
-		panic("EFI call to SetVirtualAddressMap() failed!");
+		pr_err("Unable to switch EFI into virtual mode (status=%lx)!\n",
+		       status);
+		goto err;
 	}
 
 	efi_free_boot_services();
@@ -1018,6 +1015,10 @@ static void __init __efi_enter_virtual_mode(void)
 
 	/* clean DUMMY object */
 	efi_delete_dummy_variable();
+	return;
+
+err:
+	clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
 }
 
 void __init efi_enter_virtual_mode(void)
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 08ce8177c3af..e39c930cfbd1 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -316,7 +316,7 @@ void efi_sync_low_kernel_mappings(void)
 static inline phys_addr_t
 virt_to_phys_or_null_size(void *va, unsigned long size)
 {
-	bool bad_size;
+	phys_addr_t pa;
 
 	if (!va)
 		return 0;
@@ -324,16 +324,13 @@ virt_to_phys_or_null_size(void *va, unsigned long size)
 	if (virt_addr_valid(va))
 		return virt_to_phys(va);
 
-	/*
-	 * A fully aligned variable on the stack is guaranteed not to
-	 * cross a page bounary. Try to catch strings on the stack by
-	 * checking that 'size' is a power of two.
-	 */
-	bad_size = size > PAGE_SIZE || !is_power_of_2(size);
+	pa = slow_virt_to_phys(va);
 
-	WARN_ON(!IS_ALIGNED((unsigned long)va, size) || bad_size);
+	/* check if the object crosses a page boundary */
+	if (WARN_ON((pa ^ (pa + size - 1)) & PAGE_MASK))
+		return 0;
 
-	return slow_virt_to_phys(va);
+	return pa;
 }
 
 #define virt_to_phys_or_null(addr)				\
@@ -392,11 +389,12 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 		return 0;
 
 	page = alloc_page(GFP_KERNEL|__GFP_DMA32);
-	if (!page)
-		panic("Unable to allocate EFI runtime stack < 4GB\n");
+	if (!page) {
+		pr_err("Unable to allocate EFI runtime stack < 4GB\n");
+		return 1;
+	}
 
-	efi_scratch.phys_stack = virt_to_phys(page_address(page));
-	efi_scratch.phys_stack += PAGE_SIZE; /* stack grows down */
+	efi_scratch.phys_stack = page_to_phys(page + 1); /* stack grows down */
 
 	npages = (_etext - _text) >> PAGE_SHIFT;
 	text = __pa(_text);
@@ -790,6 +788,8 @@ static efi_status_t
 efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor,
 		       u32 *attr, unsigned long *data_size, void *data)
 {
+	u8 buf[24] __aligned(8);
+	efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd));
 	efi_status_t status;
 	u32 phys_name, phys_vendor, phys_attr;
 	u32 phys_data_size, phys_data;
@@ -797,14 +797,19 @@ efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor,
 
 	spin_lock_irqsave(&efi_runtime_lock, flags);
 
+	*vnd = *vendor;
+
 	phys_data_size = virt_to_phys_or_null(data_size);
-	phys_vendor = virt_to_phys_or_null(vendor);
+	phys_vendor = virt_to_phys_or_null(vnd);
 	phys_name = virt_to_phys_or_null_size(name, efi_name_size(name));
 	phys_attr = virt_to_phys_or_null(attr);
 	phys_data = virt_to_phys_or_null_size(data, *data_size);
 
-	status = efi_thunk(get_variable, phys_name, phys_vendor,
-			   phys_attr, phys_data_size, phys_data);
+	if (!phys_name || (data && !phys_data))
+		status = EFI_INVALID_PARAMETER;
+	else
+		status = efi_thunk(get_variable, phys_name, phys_vendor,
+				   phys_attr, phys_data_size, phys_data);
 
 	spin_unlock_irqrestore(&efi_runtime_lock, flags);
 
@@ -815,19 +820,25 @@ static efi_status_t
 efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor,
 		       u32 attr, unsigned long data_size, void *data)
 {
+	u8 buf[24] __aligned(8);
+	efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd));
 	u32 phys_name, phys_vendor, phys_data;
 	efi_status_t status;
 	unsigned long flags;
 
 	spin_lock_irqsave(&efi_runtime_lock, flags);
 
+	*vnd = *vendor;
+
 	phys_name = virt_to_phys_or_null_size(name, efi_name_size(name));
-	phys_vendor = virt_to_phys_or_null(vendor);
+	phys_vendor = virt_to_phys_or_null(vnd);
 	phys_data = virt_to_phys_or_null_size(data, data_size);
 
-	/* If data_size is > sizeof(u32) we've got problems */
-	status = efi_thunk(set_variable, phys_name, phys_vendor,
-			   attr, data_size, phys_data);
+	if (!phys_name || (data && !phys_data))
+		status = EFI_INVALID_PARAMETER;
+	else
+		status = efi_thunk(set_variable, phys_name, phys_vendor,
+				   attr, data_size, phys_data);
 
 	spin_unlock_irqrestore(&efi_runtime_lock, flags);
 
@@ -839,6 +850,8 @@ efi_thunk_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor,
 				   u32 attr, unsigned long data_size,
 				   void *data)
 {
+	u8 buf[24] __aligned(8);
+	efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd));
 	u32 phys_name, phys_vendor, phys_data;
 	efi_status_t status;
 	unsigned long flags;
@@ -846,13 +859,17 @@ efi_thunk_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor,
 	if (!spin_trylock_irqsave(&efi_runtime_lock, flags))
 		return EFI_NOT_READY;
 
+	*vnd = *vendor;
+
 	phys_name = virt_to_phys_or_null_size(name, efi_name_size(name));
-	phys_vendor = virt_to_phys_or_null(vendor);
+	phys_vendor = virt_to_phys_or_null(vnd);
 	phys_data = virt_to_phys_or_null_size(data, data_size);
 
-	/* If data_size is > sizeof(u32) we've got problems */
-	status = efi_thunk(set_variable, phys_name, phys_vendor,
-			   attr, data_size, phys_data);
+	if (!phys_name || (data && !phys_data))
+		status = EFI_INVALID_PARAMETER;
+	else
+		status = efi_thunk(set_variable, phys_name, phys_vendor,
+				   attr, data_size, phys_data);
 
 	spin_unlock_irqrestore(&efi_runtime_lock, flags);
 
@@ -864,21 +881,29 @@ efi_thunk_get_next_variable(unsigned long *name_size,
 			    efi_char16_t *name,
 			    efi_guid_t *vendor)
 {
+	u8 buf[24] __aligned(8);
+	efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd));
 	efi_status_t status;
 	u32 phys_name_size, phys_name, phys_vendor;
 	unsigned long flags;
 
 	spin_lock_irqsave(&efi_runtime_lock, flags);
 
+	*vnd = *vendor;
+
 	phys_name_size = virt_to_phys_or_null(name_size);
-	phys_vendor = virt_to_phys_or_null(vendor);
+	phys_vendor = virt_to_phys_or_null(vnd);
 	phys_name = virt_to_phys_or_null_size(name, *name_size);
 
-	status = efi_thunk(get_next_variable, phys_name_size,
-			   phys_name, phys_vendor);
+	if (!phys_name)
+		status = EFI_INVALID_PARAMETER;
+	else
+		status = efi_thunk(get_next_variable, phys_name_size,
+				   phys_name, phys_vendor);
 
 	spin_unlock_irqrestore(&efi_runtime_lock, flags);
 
+	*vendor = *vnd;
 	return status;
 }
 
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 3b9fd679cea9..aefe845dff59 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -260,10 +260,6 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size)
 		return;
 	}
 
-	/* No need to reserve regions that will never be freed. */
-	if (md.attribute & EFI_MEMORY_RUNTIME)
-		return;
-
 	size += addr % EFI_PAGE_SIZE;
 	size = round_up(size, EFI_PAGE_SIZE);
 	addr = round_down(addr, EFI_PAGE_SIZE);
@@ -293,6 +289,8 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size)
 	early_memunmap(new, new_size);
 
 	efi_memmap_install(new_phys, num_entries);
+	e820__range_update(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED);
+	e820__update_table(e820_table);
 }
 
 /*
diff --git a/arch/x86/platform/olpc/olpc_dt.c b/arch/x86/platform/olpc/olpc_dt.c
index c78bfc16a3ca..26d1f6693789 100644
--- a/arch/x86/platform/olpc/olpc_dt.c
+++ b/arch/x86/platform/olpc/olpc_dt.c
@@ -216,7 +216,7 @@ static u32 __init olpc_dt_get_board_revision(void)
 	return be32_to_cpu(rev);
 }
 
-int olpc_dt_compatible_match(phandle node, const char *compat)
+static int __init olpc_dt_compatible_match(phandle node, const char *compat)
 {
 	char buf[64], *p;
 	int plen, len;
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index b81b5172cf99..2cfa0caef133 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -15,7 +15,10 @@ $(obj)/sha256.o: $(srctree)/lib/sha256.c FORCE
 LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib -z nodefaultlib
 targets += purgatory.ro
 
+# Sanitizer, etc. runtimes are unavailable and cannot be linked here.
+GCOV_PROFILE	:= n
 KASAN_SANITIZE	:= n
+UBSAN_SANITIZE	:= n
 KCOV_INSTRUMENT := n
 
 # These are adjustments to the compiler flags used for objects that
@@ -23,7 +26,7 @@ KCOV_INSTRUMENT := n
 
 PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel
 PURGATORY_CFLAGS := -mcmodel=large -ffreestanding -fno-zero-initialized-in-bss
-PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN)
+PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN) -DDISABLE_BRANCH_PROFILING
 
 # Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That
 # in turn leaves some undefined symbols like __fentry__ in purgatory and not
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 896cfd22cfda..c9b51e1a0c53 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -907,14 +907,15 @@ static u64 xen_read_msr_safe(unsigned int msr, int *err)
 static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
 {
 	int ret;
+#ifdef CONFIG_X86_64
+	unsigned int which;
+	u64 base;
+#endif
 
 	ret = 0;
 
 	switch (msr) {
 #ifdef CONFIG_X86_64
-		unsigned which;
-		u64 base;
-
 	case MSR_FS_BASE:		which = SEGBASE_FS; goto set;
 	case MSR_KERNEL_GS_BASE:	which = SEGBASE_GS_USER; goto set;
 	case MSR_GS_BASE:		which = SEGBASE_GS_KERNEL; goto set;
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 72e658c0c7c6..0d2f07d23f72 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -92,6 +92,7 @@ asmlinkage __visible void cpu_bringup_and_idle(void)
 	cpu_bringup();
 	boot_init_stack_canary();
 	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
+	prevent_tail_call_optimization();
 }
 
 void xen_smp_intr_free_pv(unsigned int cpu)
diff --git a/arch/xtensa/include/asm/thread_info.h b/arch/xtensa/include/asm/thread_info.h
index f092cc3f4e66..956d4d47c6cd 100644
--- a/arch/xtensa/include/asm/thread_info.h
+++ b/arch/xtensa/include/asm/thread_info.h
@@ -55,6 +55,10 @@ struct thread_info {
 	mm_segment_t		addr_limit;	/* thread address space */
 
 	unsigned long		cpenable;
+#if XCHAL_HAVE_EXCLUSIVE
+	/* result of the most recent exclusive store */
+	unsigned long		atomctl8;
+#endif
 
 	/* Allocate storage for extra user states and coprocessor states. */
 #if XTENSA_HAVE_COPROCESSORS
diff --git a/arch/xtensa/kernel/asm-offsets.c b/arch/xtensa/kernel/asm-offsets.c
index 33a257b33723..dc5c83cad9be 100644
--- a/arch/xtensa/kernel/asm-offsets.c
+++ b/arch/xtensa/kernel/asm-offsets.c
@@ -93,6 +93,9 @@ int main(void)
 	DEFINE(THREAD_RA, offsetof (struct task_struct, thread.ra));
 	DEFINE(THREAD_SP, offsetof (struct task_struct, thread.sp));
 	DEFINE(THREAD_CPENABLE, offsetof (struct thread_info, cpenable));
+#if XCHAL_HAVE_EXCLUSIVE
+	DEFINE(THREAD_ATOMCTL8, offsetof (struct thread_info, atomctl8));
+#endif
 #if XTENSA_HAVE_COPROCESSORS
 	DEFINE(THREAD_XTREGS_CP0, offsetof(struct thread_info, xtregs_cp.cp0));
 	DEFINE(THREAD_XTREGS_CP1, offsetof(struct thread_info, xtregs_cp.cp1));
diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S
index e54af8b7e0f8..f9c7a02acc29 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -374,6 +374,11 @@ common_exception:
 	s32i	a2, a1, PT_LCOUNT
 #endif
 
+#if XCHAL_HAVE_EXCLUSIVE
+	/* Clear exclusive access monitor set by interrupted code */
+	clrex
+#endif
+
 	/* It is now save to restore the EXC_TABLE_FIXUP variable. */
 
 	rsr	a2, exccause
@@ -1989,6 +1994,12 @@ ENTRY(_switch_to)
 	s32i	a3, a4, THREAD_CPENABLE
 #endif
 
+#if XCHAL_HAVE_EXCLUSIVE
+	l32i	a3, a5, THREAD_ATOMCTL8
+	getex	a3
+	s32i	a3, a4, THREAD_ATOMCTL8
+#endif
+
 	/* Flush register file. */
 
 	spill_registers_kernel
diff --git a/arch/xtensa/kernel/perf_event.c b/arch/xtensa/kernel/perf_event.c
index 9bae79f70301..86c9ba963155 100644
--- a/arch/xtensa/kernel/perf_event.c
+++ b/arch/xtensa/kernel/perf_event.c
@@ -401,7 +401,7 @@ static struct pmu xtensa_pmu = {
 	.read = xtensa_pmu_read,
 };
 
-static int xtensa_pmu_setup(int cpu)
+static int xtensa_pmu_setup(unsigned int cpu)
 {
 	unsigned i;
 
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 0634bfb82a0b..5ea7f39e5d62 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -723,7 +723,8 @@ c_start(struct seq_file *f, loff_t *pos)
 static void *
 c_next(struct seq_file *f, void *v, loff_t *pos)
 {
-	return NULL;
+	++*pos;
+	return c_start(f, pos);
 }
 
 static void
diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c
index 4092555828b1..24cf6972eace 100644
--- a/arch/xtensa/kernel/xtensa_ksyms.c
+++ b/arch/xtensa/kernel/xtensa_ksyms.c
@@ -87,13 +87,13 @@ void __xtensa_libgcc_window_spill(void)
 }
 EXPORT_SYMBOL(__xtensa_libgcc_window_spill);
 
-unsigned long __sync_fetch_and_and_4(unsigned long *p, unsigned long v)
+unsigned int __sync_fetch_and_and_4(volatile void *p, unsigned int v)
 {
 	BUG();
 }
 EXPORT_SYMBOL(__sync_fetch_and_and_4);
 
-unsigned long __sync_fetch_and_or_4(unsigned long *p, unsigned long v)
+unsigned int __sync_fetch_and_or_4(volatile void *p, unsigned int v)
 {
 	BUG();
 }
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index b3796a40a61a..a1b4821bc103 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -516,12 +516,13 @@ struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
 	 */
 	entity = &bfqg->entity;
 	for_each_entity(entity) {
-		bfqg = container_of(entity, struct bfq_group, entity);
-		if (bfqg != bfqd->root_group) {
-			parent = bfqg_parent(bfqg);
+		struct bfq_group *curr_bfqg = container_of(entity,
+						struct bfq_group, entity);
+		if (curr_bfqg != bfqd->root_group) {
+			parent = bfqg_parent(curr_bfqg);
 			if (!parent)
 				parent = bfqd->root_group;
-			bfq_group_set_parent(bfqg, parent);
+			bfq_group_set_parent(curr_bfqg, parent);
 		}
 	}
 
@@ -547,6 +548,12 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 {
 	struct bfq_entity *entity = &bfqq->entity;
 
+	/*
+	 * Get extra reference to prevent bfqq from being freed in
+	 * next possible expire or deactivate.
+	 */
+	bfqq->ref++;
+
 	/* If bfqq is empty, then bfq_bfqq_expire also invokes
 	 * bfq_del_bfqq_busy, thereby removing bfqq and its entity
 	 * from data structures related to current group. Otherwise we
@@ -576,6 +583,8 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 
 	if (!bfqd->in_service_queue && !bfqd->rq_in_driver)
 		bfq_schedule_dispatch(bfqd);
+	/* release extra ref taken above, bfqq may happen to be freed now */
+	bfq_put_queue(bfqq);
 }
 
 /**
@@ -611,10 +620,7 @@ static struct bfq_group *__bfq_bic_change_cgroup(struct bfq_data *bfqd,
 
 		if (entity->sched_data != &bfqg->sched_data) {
 			bic_set_bfqq(bic, NULL, 0);
-			bfq_log_bfqq(bfqd, async_bfqq,
-				     "bic_change_group: %p %d",
-				     async_bfqq, async_bfqq->ref);
-			bfq_put_queue(async_bfqq);
+			bfq_release_process_ref(bfqd, async_bfqq);
 		}
 	}
 
@@ -715,39 +721,53 @@ static void bfq_flush_idle_tree(struct bfq_service_tree *st)
 /**
  * bfq_reparent_leaf_entity - move leaf entity to the root_group.
  * @bfqd: the device data structure with the root group.
- * @entity: the entity to move.
+ * @entity: the entity to move, if entity is a leaf; or the parent entity
+ *	    of an active leaf entity to move, if entity is not a leaf.
  */
 static void bfq_reparent_leaf_entity(struct bfq_data *bfqd,
-				     struct bfq_entity *entity)
+				     struct bfq_entity *entity,
+				     int ioprio_class)
 {
-	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+	struct bfq_queue *bfqq;
+	struct bfq_entity *child_entity = entity;
+
+	while (child_entity->my_sched_data) { /* leaf not reached yet */
+		struct bfq_sched_data *child_sd = child_entity->my_sched_data;
+		struct bfq_service_tree *child_st = child_sd->service_tree +
+			ioprio_class;
+		struct rb_root *child_active = &child_st->active;
 
+		child_entity = bfq_entity_of(rb_first(child_active));
+
+		if (!child_entity)
+			child_entity = child_sd->in_service_entity;
+	}
+
+	bfqq = bfq_entity_to_bfqq(child_entity);
 	bfq_bfqq_move(bfqd, bfqq, bfqd->root_group);
 }
 
 /**
- * bfq_reparent_active_entities - move to the root group all active
- *                                entities.
+ * bfq_reparent_active_queues - move to the root group all active queues.
  * @bfqd: the device data structure with the root group.
  * @bfqg: the group to move from.
- * @st: the service tree with the entities.
+ * @st: the service tree to start the search from.
  */
-static void bfq_reparent_active_entities(struct bfq_data *bfqd,
-					 struct bfq_group *bfqg,
-					 struct bfq_service_tree *st)
+static void bfq_reparent_active_queues(struct bfq_data *bfqd,
+				       struct bfq_group *bfqg,
+				       struct bfq_service_tree *st,
+				       int ioprio_class)
 {
 	struct rb_root *active = &st->active;
-	struct bfq_entity *entity = NULL;
-
-	if (!RB_EMPTY_ROOT(&st->active))
-		entity = bfq_entity_of(rb_first(active));
+	struct bfq_entity *entity;
 
-	for (; entity ; entity = bfq_entity_of(rb_first(active)))
-		bfq_reparent_leaf_entity(bfqd, entity);
+	while ((entity = bfq_entity_of(rb_first(active))))
+		bfq_reparent_leaf_entity(bfqd, entity, ioprio_class);
 
 	if (bfqg->sched_data.in_service_entity)
 		bfq_reparent_leaf_entity(bfqd,
-			bfqg->sched_data.in_service_entity);
+					 bfqg->sched_data.in_service_entity,
+					 ioprio_class);
 }
 
 /**
@@ -780,13 +800,6 @@ static void bfq_pd_offline(struct blkg_policy_data *pd)
 		st = bfqg->sched_data.service_tree + i;
 
 		/*
-		 * The idle tree may still contain bfq_queues belonging
-		 * to exited task because they never migrated to a different
-		 * cgroup from the one being destroyed now.
-		 */
-		bfq_flush_idle_tree(st);
-
-		/*
 		 * It may happen that some queues are still active
 		 * (busy) upon group destruction (if the corresponding
 		 * processes have been forced to terminate). We move
@@ -798,7 +811,20 @@ static void bfq_pd_offline(struct blkg_policy_data *pd)
 		 * There is no need to put the sync queues, as the
 		 * scheduler has taken no reference.
 		 */
-		bfq_reparent_active_entities(bfqd, bfqg, st);
+		bfq_reparent_active_queues(bfqd, bfqg, st, i);
+
+		/*
+		 * The idle tree may still contain bfq_queues
+		 * belonging to exited task because they never
+		 * migrated to a different cgroup from the one being
+		 * destroyed now. In addition, even
+		 * bfq_reparent_active_queues() may happen to add some
+		 * entities to the idle tree. It happens if, in some
+		 * of the calls to bfq_bfqq_move() performed by
+		 * bfq_reparent_active_queues(), the queue to move is
+		 * empty and gets expired.
+		 */
+		bfq_flush_idle_tree(st);
 	}
 
 	__bfq_deactivate_entity(entity, false);
@@ -1208,6 +1234,10 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq)
 	return bfqq->bfqd->root_group;
 }
 
+void bfqg_and_blkg_get(struct bfq_group *bfqg) {}
+
+void bfqg_and_blkg_put(struct bfq_group *bfqg) {}
+
 struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node)
 {
 	struct bfq_group *bfqg;
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index ed3b97dbcf63..a4d558acc48b 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -613,6 +613,10 @@ bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 		bfqq->pos_root = NULL;
 	}
 
+	/* oom_bfqq does not participate in queue merging */
+	if (bfqq == &bfqd->oom_bfqq)
+		return;
+
 	/*
 	 * bfqq cannot be merged any longer (see comments in
 	 * bfq_setup_cooperator): no point in adding bfqq into the
@@ -2532,8 +2536,6 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
 	}
 }
 
-
-static
 void bfq_release_process_ref(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 {
 	/*
@@ -4518,9 +4520,7 @@ static struct request *bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
  */
 void bfq_put_queue(struct bfq_queue *bfqq)
 {
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
 	struct bfq_group *bfqg = bfqq_group(bfqq);
-#endif
 
 	if (bfqq->bfqd)
 		bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p %d",
@@ -4563,9 +4563,7 @@ void bfq_put_queue(struct bfq_queue *bfqq)
 	}
 
 	kmem_cache_free(bfq_pool, bfqq);
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
 	bfqg_and_blkg_put(bfqg);
-#endif
 }
 
 static void bfq_put_cooperator(struct bfq_queue *bfqq)
@@ -5776,20 +5774,28 @@ static struct bfq_queue *bfq_init_rq(struct request *rq)
 	return bfqq;
 }
 
-static void bfq_idle_slice_timer_body(struct bfq_queue *bfqq)
+static void
+bfq_idle_slice_timer_body(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 {
-	struct bfq_data *bfqd = bfqq->bfqd;
 	enum bfqq_expiration reason;
 	unsigned long flags;
 
 	spin_lock_irqsave(&bfqd->lock, flags);
-	bfq_clear_bfqq_wait_request(bfqq);
 
+	/*
+	 * Considering that bfqq may be in race, we should firstly check
+	 * whether bfqq is in service before doing something on it. If
+	 * the bfqq in race is not in service, it has already been expired
+	 * through __bfq_bfqq_expire func and its wait_request flags has
+	 * been cleared in __bfq_bfqd_reset_in_service func.
+	 */
 	if (bfqq != bfqd->in_service_queue) {
 		spin_unlock_irqrestore(&bfqd->lock, flags);
 		return;
 	}
 
+	bfq_clear_bfqq_wait_request(bfqq);
+
 	if (bfq_bfqq_budget_timeout(bfqq))
 		/*
 		 * Also here the queue can be safely expired
@@ -5834,7 +5840,7 @@ static enum hrtimer_restart bfq_idle_slice_timer(struct hrtimer *timer)
 	 * early.
 	 */
 	if (bfqq)
-		bfq_idle_slice_timer_body(bfqq);
+		bfq_idle_slice_timer_body(bfqd, bfqq);
 
 	return HRTIMER_NORESTART;
 }
@@ -5949,10 +5955,10 @@ static void bfq_exit_queue(struct elevator_queue *e)
 
 	hrtimer_cancel(&bfqd->idle_slice_timer);
 
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
 	/* release oom-queue reference to root group */
 	bfqg_and_blkg_put(bfqd->root_group);
 
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
 	blkcg_deactivate_policy(bfqd->queue, &blkcg_policy_bfq);
 #else
 	spin_lock_irq(&bfqd->lock);
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index c2faa77824f8..54d2e5cc9b52 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -885,6 +885,7 @@ struct bfq_group {
 
 #else
 struct bfq_group {
+	struct bfq_entity entity;
 	struct bfq_sched_data sched_data;
 
 	struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR];
@@ -918,6 +919,7 @@ void bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		     bool compensate, enum bfqq_expiration reason);
 void bfq_put_queue(struct bfq_queue *bfqq);
 void bfq_end_wr_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
+void bfq_release_process_ref(struct bfq_data *bfqd, struct bfq_queue *bfqq);
 void bfq_schedule_dispatch(struct bfq_data *bfqd);
 void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
 
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index fb95dbb21dd8..c9dc2b17ce25 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -24,6 +24,18 @@ void blk_flush_integrity(void)
 	flush_workqueue(kintegrityd_wq);
 }
 
+void __bio_integrity_free(struct bio_set *bs, struct bio_integrity_payload *bip)
+{
+	if (bs && mempool_initialized(&bs->bio_integrity_pool)) {
+		if (bip->bip_vec)
+			bvec_free(&bs->bvec_integrity_pool, bip->bip_vec,
+				  bip->bip_slab);
+		mempool_free(bip, &bs->bio_integrity_pool);
+	} else {
+		kfree(bip);
+	}
+}
+
 /**
  * bio_integrity_alloc - Allocate integrity payload and attach it to bio
  * @bio:	bio to attach integrity metadata to
@@ -75,7 +87,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 
 	return bip;
 err:
-	mempool_free(bip, &bs->bio_integrity_pool);
+	__bio_integrity_free(bs, bip);
 	return ERR_PTR(-ENOMEM);
 }
 EXPORT_SYMBOL(bio_integrity_alloc);
@@ -87,7 +99,7 @@ EXPORT_SYMBOL(bio_integrity_alloc);
  * Description: Used to free the integrity portion of a bio. Usually
  * called from bio_free().
  */
-static void bio_integrity_free(struct bio *bio)
+void bio_integrity_free(struct bio *bio)
 {
 	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct bio_set *bs = bio->bi_pool;
@@ -96,14 +108,7 @@ static void bio_integrity_free(struct bio *bio)
 		kfree(page_address(bip->bip_vec->bv_page) +
 		      bip->bip_vec->bv_offset);
 
-	if (bs && mempool_initialized(&bs->bio_integrity_pool)) {
-		bvec_free(&bs->bvec_integrity_pool, bip->bip_vec, bip->bip_slab);
-
-		mempool_free(bip, &bs->bio_integrity_pool);
-	} else {
-		kfree(bip);
-	}
-
+	__bio_integrity_free(bs, bip);
 	bio->bi_integrity = NULL;
 	bio->bi_opf &= ~REQ_INTEGRITY;
 }
@@ -278,7 +283,6 @@ bool bio_integrity_prep(struct bio *bio)
 
 		if (ret == 0) {
 			printk(KERN_ERR "could not attach integrity payload\n");
-			kfree(buf);
 			status = BLK_STS_RESOURCE;
 			goto err_end_io;
 		}
diff --git a/block/bio.c b/block/bio.c
index 8ef5fcaba6ad..22280cfba22f 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -233,6 +233,9 @@ fallback:
 void bio_uninit(struct bio *bio)
 {
 	bio_disassociate_blkg(bio);
+
+	if (bio_integrity(bio))
+		bio_integrity_free(bio);
 }
 EXPORT_SYMBOL(bio_uninit);
 
@@ -536,6 +539,55 @@ void zero_fill_bio_iter(struct bio *bio, struct bvec_iter start)
 EXPORT_SYMBOL(zero_fill_bio_iter);
 
 /**
+ * bio_truncate - truncate the bio to small size of @new_size
+ * @bio:	the bio to be truncated
+ * @new_size:	new size for truncating the bio
+ *
+ * Description:
+ *   Truncate the bio to new size of @new_size. If bio_op(bio) is
+ *   REQ_OP_READ, zero the truncated part. This function should only
+ *   be used for handling corner cases, such as bio eod.
+ */
+void bio_truncate(struct bio *bio, unsigned new_size)
+{
+	struct bio_vec bv;
+	struct bvec_iter iter;
+	unsigned int done = 0;
+	bool truncated = false;
+
+	if (new_size >= bio->bi_iter.bi_size)
+		return;
+
+	if (bio_op(bio) != REQ_OP_READ)
+		goto exit;
+
+	bio_for_each_segment(bv, bio, iter) {
+		if (done + bv.bv_len > new_size) {
+			unsigned offset;
+
+			if (!truncated)
+				offset = new_size - done;
+			else
+				offset = 0;
+			zero_user(bv.bv_page, offset, bv.bv_len - offset);
+			truncated = true;
+		}
+		done += bv.bv_len;
+	}
+
+ exit:
+	/*
+	 * Don't touch bvec table here and make it really immutable, since
+	 * fs bio user has to retrieve all pages via bio_for_each_segment_all
+	 * in its .end_bio() callback.
+	 *
+	 * It is enough to truncate bio by updating .bi_size since we can make
+	 * correct bvec with the updated .bi_size for drivers.
+	 */
+	bio->bi_iter.bi_size = new_size;
+}
+
+/**
  * bio_put - release a reference to a bio
  * @bio:   bio to release reference to
  *
@@ -783,8 +835,10 @@ bool __bio_try_merge_page(struct bio *bio, struct page *page,
 		struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
 
 		if (page_is_mergeable(bv, page, len, off, same_page)) {
-			if (bio->bi_iter.bi_size > UINT_MAX - len)
+			if (bio->bi_iter.bi_size > UINT_MAX - len) {
+				*same_page = false;
 				return false;
+			}
 			bv->bv_len += len;
 			bio->bi_iter.bi_size += len;
 			return true;
diff --git a/block/blk-core.c b/block/blk-core.c
index 5183fca0818a..48f417d0806d 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -848,11 +848,14 @@ generic_make_request_checks(struct bio *bio)
 	}
 
 	/*
-	 * For a REQ_NOWAIT based request, return -EOPNOTSUPP
-	 * if queue is not a request based queue.
+	 * Non-mq queues do not honor REQ_NOWAIT, so complete a bio
+	 * with BLK_STS_AGAIN status in order to catch -EAGAIN and
+	 * to give a chance to the caller to repeat request gracefully.
 	 */
-	if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_mq(q))
-		goto not_supported;
+	if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_mq(q)) {
+		status = BLK_STS_AGAIN;
+		goto end_io;
+	}
 
 	if (should_fail_bio(bio))
 		goto end_io;
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 1eec9cbe5a0a..5aa6fada2259 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -69,6 +69,7 @@
 #include <linux/blkdev.h>
 #include <linux/gfp.h>
 #include <linux/blk-mq.h>
+#include <linux/lockdep.h>
 
 #include "blk.h"
 #include "blk-mq.h"
@@ -398,7 +399,7 @@ void blk_insert_flush(struct request *rq)
 	 */
 	if ((policy & REQ_FSEQ_DATA) &&
 	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
-		blk_mq_request_bypass_insert(rq, false);
+		blk_mq_request_bypass_insert(rq, false, false);
 		return;
 	}
 
@@ -492,6 +493,9 @@ struct blk_flush_queue *blk_alloc_flush_queue(struct request_queue *q,
 	INIT_LIST_HEAD(&fq->flush_queue[1]);
 	INIT_LIST_HEAD(&fq->flush_data_in_flight);
 
+	lockdep_register_key(&fq->key);
+	lockdep_set_class(&fq->mq_flush_lock, &fq->key);
+
 	return fq;
 
  fail_rq:
@@ -506,6 +510,7 @@ void blk_free_flush_queue(struct blk_flush_queue *fq)
 	if (!fq)
 		return;
 
+	lockdep_unregister_key(&fq->key);
 	kfree(fq->flush_rq);
 	kfree(fq);
 }
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 5ed59ac6ae58..9df50fb507ca 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -84,6 +84,7 @@ static void ioc_destroy_icq(struct io_cq *icq)
 	 * making it impossible to determine icq_cache.  Record it in @icq.
 	 */
 	icq->__rcu_icq_cache = et->icq_cache;
+	icq->flags |= ICQ_DESTROYED;
 	call_rcu(&icq->__rcu_head, icq_free_icq_rcu);
 }
 
@@ -212,15 +213,21 @@ static void __ioc_clear_queue(struct list_head *icq_list)
 {
 	unsigned long flags;
 
+	rcu_read_lock();
 	while (!list_empty(icq_list)) {
 		struct io_cq *icq = list_entry(icq_list->next,
 						struct io_cq, q_node);
 		struct io_context *ioc = icq->ioc;
 
 		spin_lock_irqsave(&ioc->lock, flags);
+		if (icq->flags & ICQ_DESTROYED) {
+			spin_unlock_irqrestore(&ioc->lock, flags);
+			continue;
+		}
 		ioc_destroy_icq(icq);
 		spin_unlock_irqrestore(&ioc->lock, flags);
 	}
+	rcu_read_unlock();
 }
 
 /**
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 5f2c429d4378..bdcfe4fbeac7 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -47,6 +47,15 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		op = REQ_OP_DISCARD;
 	}
 
+	/* In case the discard granularity isn't set by buggy device driver */
+	if (WARN_ON_ONCE(!q->limits.discard_granularity)) {
+		char dev_name[BDEVNAME_SIZE];
+
+		bdevname(bdev, dev_name);
+		pr_err_ratelimited("%s: Error: discard_granularity is 0.\n", dev_name);
+		return -EOPNOTSUPP;
+	}
+
 	bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
 	if ((sector | nr_sects) & bs_mask)
 		return -EINVAL;
diff --git a/block/blk-map.c b/block/blk-map.c
index db9373bd31ac..9d8627acc2f5 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -145,7 +145,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 	return 0;
 
 unmap_rq:
-	__blk_rq_unmap_user(bio);
+	blk_rq_unmap_user(bio);
 fail:
 	rq->bio = NULL;
 	return ret;
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 17713d7d98d5..4140c9594b92 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -144,17 +144,20 @@ static inline unsigned get_max_io_size(struct request_queue *q,
 	return sectors;
 }
 
-static unsigned get_max_segment_size(struct request_queue *q,
-				     unsigned offset)
+static inline unsigned get_max_segment_size(struct request_queue *q,
+					    struct page *start_page,
+					    unsigned long offset)
 {
 	unsigned long mask = queue_segment_boundary(q);
 
-	/* default segment boundary mask means no boundary limit */
-	if (mask == BLK_SEG_BOUNDARY_MASK)
-		return queue_max_segment_size(q);
+	offset = mask & (page_to_phys(start_page) + offset);
 
-	return min_t(unsigned long, mask - (mask & offset) + 1,
-		     queue_max_segment_size(q));
+	/*
+	 * overflow may be triggered in case of zero page physical address
+	 * on 32bit arch, use queue's max segment size when that happens.
+	 */
+	return min_not_zero(mask - offset + 1,
+			(unsigned long)queue_max_segment_size(q));
 }
 
 /*
@@ -173,7 +176,8 @@ static bool bvec_split_segs(struct request_queue *q, struct bio_vec *bv,
 	 * current bvec has to be splitted as multiple segments.
 	 */
 	while (len && new_nsegs + *nsegs < max_segs) {
-		seg_size = get_max_segment_size(q, bv->bv_offset + total_len);
+		seg_size = get_max_segment_size(q, bv->bv_page,
+						bv->bv_offset + total_len);
 		seg_size = min(seg_size, len);
 
 		new_nsegs++;
@@ -375,7 +379,8 @@ static unsigned blk_bvec_map_sg(struct request_queue *q,
 
 	while (nbytes > 0) {
 		unsigned offset = bvec->bv_offset + total;
-		unsigned len = min(get_max_segment_size(q, offset), nbytes);
+		unsigned len = min(get_max_segment_size(q, bvec->bv_page,
+					offset), nbytes);
 		struct page *page = bvec->bv_page;
 
 		/*
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 3afe327f816f..082faacb9993 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -125,6 +125,7 @@ static const char *const blk_queue_flag_name[] = {
 	QUEUE_FLAG_NAME(REGISTERED),
 	QUEUE_FLAG_NAME(SCSI_PASSTHROUGH),
 	QUEUE_FLAG_NAME(QUIESCED),
+	QUEUE_FLAG_NAME(PCI_P2PDMA),
 };
 #undef QUEUE_FLAG_NAME
 
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 3cf555f12700..553a317a0e6e 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -360,13 +360,19 @@ static bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx,
 				       bool has_sched,
 				       struct request *rq)
 {
-	/* dispatch flush rq directly */
-	if (rq->rq_flags & RQF_FLUSH_SEQ) {
-		spin_lock(&hctx->lock);
-		list_add(&rq->queuelist, &hctx->dispatch);
-		spin_unlock(&hctx->lock);
+	/*
+	 * dispatch flush and passthrough rq directly
+	 *
+	 * passthrough request has to be added to hctx->dispatch directly.
+	 * For some reason, device may be in one situation which can't
+	 * handle FS request, so STS_RESOURCE is always returned and the
+	 * FS request will be added to hctx->dispatch. However passthrough
+	 * request may be required at that time for fixing the problem. If
+	 * passthrough request is added to scheduler queue, there isn't any
+	 * chance to dispatch it given we prioritize requests in hctx->dispatch.
+	 */
+	if ((rq->rq_flags & RQF_FLUSH_SEQ) || blk_rq_is_passthrough(rq))
 		return true;
-	}
 
 	if (has_sched)
 		rq->rq_flags |= RQF_SORTED;
@@ -390,8 +396,32 @@ void blk_mq_sched_insert_request(struct request *rq, bool at_head,
 
 	WARN_ON(e && (rq->tag != -1));
 
-	if (blk_mq_sched_bypass_insert(hctx, !!e, rq))
+	if (blk_mq_sched_bypass_insert(hctx, !!e, rq)) {
+		/*
+		 * Firstly normal IO request is inserted to scheduler queue or
+		 * sw queue, meantime we add flush request to dispatch queue(
+		 * hctx->dispatch) directly and there is at most one in-flight
+		 * flush request for each hw queue, so it doesn't matter to add
+		 * flush request to tail or front of the dispatch queue.
+		 *
+		 * Secondly in case of NCQ, flush request belongs to non-NCQ
+		 * command, and queueing it will fail when there is any
+		 * in-flight normal IO request(NCQ command). When adding flush
+		 * rq to the front of hctx->dispatch, it is easier to introduce
+		 * extra time to flush rq's latency because of S_SCHED_RESTART
+		 * compared with adding to the tail of dispatch queue, then
+		 * chance of flush merge is increased, and less flush requests
+		 * will be issued to controller. It is observed that ~10% time
+		 * is saved in blktests block/004 on disk attached to AHCI/NCQ
+		 * drive when adding flush rq to the front of hctx->dispatch.
+		 *
+		 * Simply queue flush rq to the front of hctx->dispatch so that
+		 * intensive flush workloads can benefit in case of NCQ HW.
+		 */
+		at_head = (rq->rq_flags & RQF_FLUSH_SEQ) ? true : at_head;
+		blk_mq_request_bypass_insert(rq, at_head, false);
 		goto run;
+	}
 
 	if (e && e->type->ops.insert_requests) {
 		LIST_HEAD(list);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4af0941fbb67..fc9829a5e4a4 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -753,7 +753,7 @@ static void blk_mq_requeue_work(struct work_struct *work)
 		 * merge.
 		 */
 		if (rq->rq_flags & RQF_DONTPREP)
-			blk_mq_request_bypass_insert(rq, false);
+			blk_mq_request_bypass_insert(rq, false, false);
 		else
 			blk_mq_sched_insert_request(rq, true, false, false);
 	}
@@ -821,10 +821,10 @@ static bool blk_mq_rq_inflight(struct blk_mq_hw_ctx *hctx, struct request *rq,
 			       void *priv, bool reserved)
 {
 	/*
-	 * If we find a request that is inflight and the queue matches,
+	 * If we find a request that isn't idle and the queue matches,
 	 * we know the queue is busy. Return false to stop the iteration.
 	 */
-	if (rq->state == MQ_RQ_IN_FLIGHT && rq->q == hctx->queue) {
+	if (blk_mq_request_started(rq) && rq->q == hctx->queue) {
 		bool *busy = priv;
 
 		*busy = true;
@@ -1224,8 +1224,10 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 		rq = list_first_entry(list, struct request, queuelist);
 
 		hctx = rq->mq_hctx;
-		if (!got_budget && !blk_mq_get_dispatch_budget(hctx))
+		if (!got_budget && !blk_mq_get_dispatch_budget(hctx)) {
+			blk_mq_put_driver_tag(rq);
 			break;
+		}
 
 		if (!blk_mq_get_driver_tag(rq)) {
 			/*
@@ -1305,7 +1307,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 			q->mq_ops->commit_rqs(hctx);
 
 		spin_lock(&hctx->lock);
-		list_splice_init(list, &hctx->dispatch);
+		list_splice_tail_init(list, &hctx->dispatch);
 		spin_unlock(&hctx->lock);
 
 		/*
@@ -1660,12 +1662,16 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
  * Should only be used carefully, when the caller knows we want to
  * bypass a potential IO scheduler on the target device.
  */
-void blk_mq_request_bypass_insert(struct request *rq, bool run_queue)
+void blk_mq_request_bypass_insert(struct request *rq, bool at_head,
+				  bool run_queue)
 {
 	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
 
 	spin_lock(&hctx->lock);
-	list_add_tail(&rq->queuelist, &hctx->dispatch);
+	if (at_head)
+		list_add(&rq->queuelist, &hctx->dispatch);
+	else
+		list_add_tail(&rq->queuelist, &hctx->dispatch);
 	spin_unlock(&hctx->lock);
 
 	if (run_queue)
@@ -1849,7 +1855,7 @@ insert:
 	if (bypass_insert)
 		return BLK_STS_RESOURCE;
 
-	blk_mq_request_bypass_insert(rq, run_queue);
+	blk_mq_request_bypass_insert(rq, false, run_queue);
 	return BLK_STS_OK;
 }
 
@@ -1865,7 +1871,7 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 
 	ret = __blk_mq_try_issue_directly(hctx, rq, cookie, false, true);
 	if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE)
-		blk_mq_request_bypass_insert(rq, true);
+		blk_mq_request_bypass_insert(rq, false, true);
 	else if (ret != BLK_STS_OK)
 		blk_mq_end_request(rq, ret);
 
@@ -1899,7 +1905,7 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 		if (ret != BLK_STS_OK) {
 			if (ret == BLK_STS_RESOURCE ||
 					ret == BLK_STS_DEV_RESOURCE) {
-				blk_mq_request_bypass_insert(rq,
+				blk_mq_request_bypass_insert(rq, false,
 							list_empty(list));
 				break;
 			}
@@ -2484,18 +2490,6 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 	 * If the cpu isn't present, the cpu is mapped to first hctx.
 	 */
 	for_each_possible_cpu(i) {
-		hctx_idx = set->map[HCTX_TYPE_DEFAULT].mq_map[i];
-		/* unmapped hw queue can be remapped after CPU topo changed */
-		if (!set->tags[hctx_idx] &&
-		    !__blk_mq_alloc_rq_map(set, hctx_idx)) {
-			/*
-			 * If tags initialization fail for some hctx,
-			 * that hctx won't be brought online.  In this
-			 * case, remap the current ctx to hctx[0] which
-			 * is guaranteed to always have tags allocated
-			 */
-			set->map[HCTX_TYPE_DEFAULT].mq_map[i] = 0;
-		}
 
 		ctx = per_cpu_ptr(q->queue_ctx, i);
 		for (j = 0; j < set->nr_maps; j++) {
@@ -2504,6 +2498,18 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 						HCTX_TYPE_DEFAULT, i);
 				continue;
 			}
+			hctx_idx = set->map[j].mq_map[i];
+			/* unmapped hw queue can be remapped after CPU topo changed */
+			if (!set->tags[hctx_idx] &&
+			    !__blk_mq_alloc_rq_map(set, hctx_idx)) {
+				/*
+				 * If tags initialization fail for some hctx,
+				 * that hctx won't be brought online.  In this
+				 * case, remap the current ctx to hctx[0] which
+				 * is guaranteed to always have tags allocated
+				 */
+				set->map[j].mq_map[i] = 0;
+			}
 
 			hctx = blk_mq_map_queue_type(q, j, i);
 			ctx->hctxs[j] = hctx;
@@ -3004,6 +3010,14 @@ static int blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
 
 static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
 {
+	/*
+	 * blk_mq_map_queues() and multiple .map_queues() implementations
+	 * expect that set->map[HCTX_TYPE_DEFAULT].nr_queues is set to the
+	 * number of hardware queues.
+	 */
+	if (set->nr_maps == 1)
+		set->map[HCTX_TYPE_DEFAULT].nr_queues = set->nr_hw_queues;
+
 	if (set->ops->map_queues && !is_kdump_kernel()) {
 		int i;
 
@@ -3266,7 +3280,9 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 
 	if (set->nr_maps == 1 && nr_hw_queues > nr_cpu_ids)
 		nr_hw_queues = nr_cpu_ids;
-	if (nr_hw_queues < 1 || nr_hw_queues == set->nr_hw_queues)
+	if (nr_hw_queues < 1)
+		return;
+	if (set->nr_maps == 1 && nr_hw_queues == set->nr_hw_queues)
 		return;
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
@@ -3291,8 +3307,8 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 
 	prev_nr_hw_queues = set->nr_hw_queues;
 	set->nr_hw_queues = nr_hw_queues;
-	blk_mq_update_queue_map(set);
 fallback:
+	blk_mq_update_queue_map(set);
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_realloc_hw_ctxs(set, q);
 		if (q->nr_hw_queues != set->nr_hw_queues) {
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 633a5a77ee8b..165efcaedf0d 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -66,7 +66,8 @@ int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
  */
 void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 				bool at_head);
-void blk_mq_request_bypass_insert(struct request *rq, bool run_queue);
+void blk_mq_request_bypass_insert(struct request *rq, bool at_head,
+				  bool run_queue);
 void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 				struct list_head *list);
 
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 2ae348c101a0..2790f5365523 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -327,7 +327,7 @@ EXPORT_SYMBOL(blk_queue_max_segment_size);
  *   storage device can address.  The default of 512 covers most
  *   hardware.
  **/
-void blk_queue_logical_block_size(struct request_queue *q, unsigned short size)
+void blk_queue_logical_block_size(struct request_queue *q, unsigned int size)
 {
 	q->limits.logical_block_size = size;
 
@@ -663,6 +663,9 @@ void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
 		printk(KERN_NOTICE "%s: Warning: Device %s is misaligned\n",
 		       top, bottom);
 	}
+
+	t->backing_dev_info->io_pages =
+		t->limits.max_sectors >> (PAGE_SHIFT - 9);
 }
 EXPORT_SYMBOL(disk_stack_limits);
 
diff --git a/block/blk.h b/block/blk.h
index 5a470b97204f..363ec641354c 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -30,6 +30,7 @@ struct blk_flush_queue {
 	 * at the same time
 	 */
 	struct request		*orig_rq;
+	struct lock_class_key	key;
 	spinlock_t		mq_flush_lock;
 };
 
@@ -111,6 +112,7 @@ static inline bool bvec_gap_to_prev(struct request_queue *q,
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 void blk_flush_integrity(void);
 bool __bio_integrity_endio(struct bio *);
+void bio_integrity_free(struct bio *bio);
 static inline bool bio_integrity_endio(struct bio *bio)
 {
 	if (bio_integrity(bio))
@@ -156,6 +158,9 @@ static inline bool bio_integrity_endio(struct bio *bio)
 {
 	return true;
 }
+static inline void bio_integrity_free(struct bio *bio)
+{
+}
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
 unsigned long blk_rq_timeout(unsigned long timeout);
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index 6ca015f92766..7f053468b50d 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -6,6 +6,7 @@
 #include <linux/compat.h>
 #include <linux/elevator.h>
 #include <linux/hdreg.h>
+#include <linux/pr.h>
 #include <linux/slab.h>
 #include <linux/syscalls.h>
 #include <linux/types.h>
@@ -354,6 +355,10 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	 * but we call blkdev_ioctl, which gets the lock for us
 	 */
 	case BLKRRPART:
+	case BLKREPORTZONE:
+	case BLKRESETZONE:
+	case BLKGETZONESZ:
+	case BLKGETNRZONES:
 		return blkdev_ioctl(bdev, mode, cmd,
 				(unsigned long)compat_ptr(arg));
 	case BLKBSZSET_32:
@@ -401,6 +406,14 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	case BLKTRACETEARDOWN: /* compatible */
 		ret = blk_trace_ioctl(bdev, cmd, compat_ptr(arg));
 		return ret;
+	case IOC_PR_REGISTER:
+	case IOC_PR_RESERVE:
+	case IOC_PR_RELEASE:
+	case IOC_PR_PREEMPT:
+	case IOC_PR_PREEMPT_ABORT:
+	case IOC_PR_CLEAR:
+		return blkdev_ioctl(bdev, mode, cmd,
+				(unsigned long)compat_ptr(arg));
 	default:
 		if (disk->fops->compat_ioctl)
 			ret = disk->fops->compat_ioctl(bdev, mode, cmd, arg);
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 3d056e7da65f..5114b35ef3b4 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -1230,9 +1230,13 @@ config CRYPTO_ANUBIS
 	  <https://www.cosic.esat.kuleuven.be/nessie/reports/>
 	  <http://www.larc.usp.br/~pbarreto/AnubisPage.html>
 
+config CRYPTO_LIB_ARC4
+	tristate
+
 config CRYPTO_ARC4
 	tristate "ARC4 cipher algorithm"
 	select CRYPTO_BLKCIPHER
+	select CRYPTO_LIB_ARC4
 	help
 	  ARC4 cipher algorithm.
 
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 0dceaabc6321..1d4b0157ee5d 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -16,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/net.h>
 #include <linux/rwsem.h>
+#include <linux/sched.h>
 #include <linux/sched/signal.h>
 #include <linux/security.h>
 
@@ -128,19 +129,15 @@ EXPORT_SYMBOL_GPL(af_alg_release);
 void af_alg_release_parent(struct sock *sk)
 {
 	struct alg_sock *ask = alg_sk(sk);
-	unsigned int nokey = ask->nokey_refcnt;
-	bool last = nokey && !ask->refcnt;
+	unsigned int nokey = atomic_read(&ask->nokey_refcnt);
 
 	sk = ask->parent;
 	ask = alg_sk(sk);
 
-	lock_sock(sk);
-	ask->nokey_refcnt -= nokey;
-	if (!last)
-		last = !--ask->refcnt;
-	release_sock(sk);
+	if (nokey)
+		atomic_dec(&ask->nokey_refcnt);
 
-	if (last)
+	if (atomic_dec_and_test(&ask->refcnt))
 		sock_put(sk);
 }
 EXPORT_SYMBOL_GPL(af_alg_release_parent);
@@ -185,7 +182,7 @@ static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 
 	err = -EBUSY;
 	lock_sock(sk);
-	if (ask->refcnt | ask->nokey_refcnt)
+	if (atomic_read(&ask->refcnt))
 		goto unlock;
 
 	swap(ask->type, type);
@@ -234,7 +231,7 @@ static int alg_setsockopt(struct socket *sock, int level, int optname,
 	int err = -EBUSY;
 
 	lock_sock(sk);
-	if (ask->refcnt)
+	if (atomic_read(&ask->refcnt) != atomic_read(&ask->nokey_refcnt))
 		goto unlock;
 
 	type = ask->type;
@@ -299,12 +296,14 @@ int af_alg_accept(struct sock *sk, struct socket *newsock, bool kern)
 	if (err)
 		goto unlock;
 
-	if (nokey || !ask->refcnt++)
+	if (atomic_inc_return_relaxed(&ask->refcnt) == 1)
 		sock_hold(sk);
-	ask->nokey_refcnt += nokey;
+	if (nokey) {
+		atomic_inc(&ask->nokey_refcnt);
+		atomic_set(&alg_sk(sk2)->nokey_refcnt, 1);
+	}
 	alg_sk(sk2)->parent = sk;
 	alg_sk(sk2)->type = type;
-	alg_sk(sk2)->nokey_refcnt = nokey;
 
 	newsock->ops = type->ops;
 	newsock->state = SS_CONNECTED;
@@ -637,6 +636,7 @@ void af_alg_pull_tsgl(struct sock *sk, size_t used, struct scatterlist *dst,
 
 	if (!ctx->used)
 		ctx->merge = 0;
+	ctx->init = ctx->more;
 }
 EXPORT_SYMBOL_GPL(af_alg_pull_tsgl);
 
@@ -736,9 +736,10 @@ EXPORT_SYMBOL_GPL(af_alg_wmem_wakeup);
  *
  * @sk socket of connection to user space
  * @flags If MSG_DONTWAIT is set, then only report if function would sleep
+ * @min Set to minimum request size if partial requests are allowed.
  * @return 0 when writable memory is available, < 0 upon error
  */
-int af_alg_wait_for_data(struct sock *sk, unsigned flags)
+int af_alg_wait_for_data(struct sock *sk, unsigned flags, unsigned min)
 {
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	struct alg_sock *ask = alg_sk(sk);
@@ -756,7 +757,9 @@ int af_alg_wait_for_data(struct sock *sk, unsigned flags)
 		if (signal_pending(current))
 			break;
 		timeout = MAX_SCHEDULE_TIMEOUT;
-		if (sk_wait_event(sk, &timeout, (ctx->used || !ctx->more),
+		if (sk_wait_event(sk, &timeout,
+				  ctx->init && (!ctx->more ||
+						(min && ctx->used >= min)),
 				  &wait)) {
 			err = 0;
 			break;
@@ -845,10 +848,17 @@ int af_alg_sendmsg(struct socket *sock, struct msghdr *msg, size_t size,
 	}
 
 	lock_sock(sk);
-	if (!ctx->more && ctx->used) {
-		err = -EINVAL;
-		goto unlock;
+	if (ctx->init && !ctx->more) {
+		if (ctx->used) {
+			err = -EINVAL;
+			goto unlock;
+		}
+
+		pr_info_once(
+			"%s sent an empty control message without MSG_MORE.\n",
+			current->comm);
 	}
+	ctx->init = true;
 
 	if (init) {
 		ctx->enc = enc;
diff --git a/crypto/algapi.c b/crypto/algapi.c
index 313a7682cef1..9baf5791af8d 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -107,15 +107,17 @@ static struct list_head *crypto_more_spawns(struct crypto_alg *alg,
 	if (!spawn)
 		return NULL;
 
-	n = list_next_entry(spawn, list);
+	n = list_prev_entry(spawn, list);
+	list_move(&spawn->list, secondary_spawns);
 
-	if (spawn->alg && &n->list != stack && !n->alg)
-		n->alg = (n->list.next == stack) ? alg :
-			 &list_next_entry(n, list)->inst->alg;
+	if (list_is_last(&n->list, stack))
+		return top;
 
-	list_move(&spawn->list, secondary_spawns);
+	n = list_next_entry(n, list);
+	if (!spawn->dead)
+		n->dead = false;
 
-	return &n->list == stack ? top : &n->inst->alg.cra_users;
+	return &n->inst->alg.cra_users;
 }
 
 static void crypto_remove_instance(struct crypto_instance *inst,
@@ -174,7 +176,7 @@ void crypto_remove_spawns(struct crypto_alg *alg, struct list_head *list,
 			if (&inst->alg == nalg)
 				break;
 
-			spawn->alg = NULL;
+			spawn->dead = true;
 			spawns = &inst->alg.cra_users;
 
 			/*
@@ -193,7 +195,7 @@ void crypto_remove_spawns(struct crypto_alg *alg, struct list_head *list,
 					      &secondary_spawns)));
 
 	list_for_each_entry_safe(spawn, n, &secondary_spawns, list) {
-		if (spawn->alg)
+		if (!spawn->dead)
 			list_move(&spawn->list, &spawn->alg->cra_users);
 		else
 			crypto_remove_instance(spawn->inst, list);
@@ -271,6 +273,7 @@ void crypto_alg_tested(const char *name, int err)
 	struct crypto_alg *alg;
 	struct crypto_alg *q;
 	LIST_HEAD(list);
+	bool best;
 
 	down_write(&crypto_alg_sem);
 	list_for_each_entry(q, &crypto_alg_list, cra_list) {
@@ -294,6 +297,21 @@ found:
 
 	alg->cra_flags |= CRYPTO_ALG_TESTED;
 
+	/* Only satisfy larval waiters if we are the best. */
+	best = true;
+	list_for_each_entry(q, &crypto_alg_list, cra_list) {
+		if (crypto_is_moribund(q) || !crypto_is_larval(q))
+			continue;
+
+		if (strcmp(alg->cra_name, q->cra_name))
+			continue;
+
+		if (q->cra_priority > alg->cra_priority) {
+			best = false;
+			break;
+		}
+	}
+
 	list_for_each_entry(q, &crypto_alg_list, cra_list) {
 		if (q == alg)
 			continue;
@@ -317,10 +335,12 @@ found:
 				continue;
 			if ((q->cra_flags ^ alg->cra_flags) & larval->mask)
 				continue;
-			if (!crypto_mod_get(alg))
-				continue;
 
-			larval->adult = alg;
+			if (best && crypto_mod_get(alg))
+				larval->adult = alg;
+			else
+				larval->adult = ERR_PTR(-EAGAIN);
+
 			continue;
 		}
 
@@ -370,7 +390,7 @@ static void crypto_wait_for_test(struct crypto_larval *larval)
 	err = wait_for_completion_killable(&larval->completion);
 	WARN_ON(err);
 	if (!err)
-		crypto_probing_notify(CRYPTO_MSG_ALG_LOADED, larval);
+		crypto_notify(CRYPTO_MSG_ALG_LOADED, larval);
 
 out:
 	crypto_larval_kill(&larval->alg);
@@ -683,31 +703,33 @@ EXPORT_SYMBOL_GPL(crypto_grab_spawn);
 
 void crypto_drop_spawn(struct crypto_spawn *spawn)
 {
-	if (!spawn->alg)
-		return;
-
 	down_write(&crypto_alg_sem);
-	list_del(&spawn->list);
+	if (!spawn->dead)
+		list_del(&spawn->list);
 	up_write(&crypto_alg_sem);
 }
 EXPORT_SYMBOL_GPL(crypto_drop_spawn);
 
 static struct crypto_alg *crypto_spawn_alg(struct crypto_spawn *spawn)
 {
-	struct crypto_alg *alg;
-	struct crypto_alg *alg2;
+	struct crypto_alg *alg = ERR_PTR(-EAGAIN);
+	struct crypto_alg *target;
+	bool shoot = false;
 
 	down_read(&crypto_alg_sem);
-	alg = spawn->alg;
-	alg2 = alg;
-	if (alg2)
-		alg2 = crypto_mod_get(alg2);
+	if (!spawn->dead) {
+		alg = spawn->alg;
+		if (!crypto_mod_get(alg)) {
+			target = crypto_alg_get(alg);
+			shoot = true;
+			alg = ERR_PTR(-EAGAIN);
+		}
+	}
 	up_read(&crypto_alg_sem);
 
-	if (!alg2) {
-		if (alg)
-			crypto_shoot_alg(alg);
-		return ERR_PTR(-EAGAIN);
+	if (shoot) {
+		crypto_shoot_alg(target);
+		crypto_alg_put(target);
 	}
 
 	return alg;
diff --git a/crypto/algboss.c b/crypto/algboss.c
index a62149d6c839..2d41e67532c0 100644
--- a/crypto/algboss.c
+++ b/crypto/algboss.c
@@ -188,8 +188,6 @@ static int cryptomgr_schedule_probe(struct crypto_larval *larval)
 	if (IS_ERR(thread))
 		goto err_put_larval;
 
-	wait_for_completion_interruptible(&larval->completion);
-
 	return NOTIFY_STOP;
 
 err_put_larval:
diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index eb1910b6d434..43c6aa784858 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -106,8 +106,8 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg,
 	size_t usedpages = 0;		/* [in]  RX bufs to be used from user */
 	size_t processed = 0;		/* [in]  TX bufs to be consumed */
 
-	if (!ctx->used) {
-		err = af_alg_wait_for_data(sk, flags);
+	if (!ctx->init || ctx->more) {
+		err = af_alg_wait_for_data(sk, flags, 0);
 		if (err)
 			return err;
 	}
@@ -384,7 +384,7 @@ static int aead_check_key(struct socket *sock)
 	struct alg_sock *ask = alg_sk(sk);
 
 	lock_sock(sk);
-	if (ask->refcnt)
+	if (!atomic_read(&ask->nokey_refcnt))
 		goto unlock_child;
 
 	psk = ask->parent;
@@ -396,11 +396,8 @@ static int aead_check_key(struct socket *sock)
 	if (crypto_aead_get_flags(tfm->aead) & CRYPTO_TFM_NEED_KEY)
 		goto unlock;
 
-	if (!pask->refcnt++)
-		sock_hold(psk);
-
-	ask->refcnt = 1;
-	sock_put(psk);
+	atomic_dec(&pask->nokey_refcnt);
+	atomic_set(&ask->nokey_refcnt, 0);
 
 	err = 0;
 
@@ -561,12 +558,6 @@ static int aead_accept_parent_nokey(void *private, struct sock *sk)
 
 	INIT_LIST_HEAD(&ctx->tsgl_list);
 	ctx->len = len;
-	ctx->used = 0;
-	atomic_set(&ctx->rcvused, 0);
-	ctx->more = 0;
-	ctx->merge = 0;
-	ctx->enc = 0;
-	ctx->aead_assoclen = 0;
 	crypto_init_wait(&ctx->wait);
 
 	ask->private = ctx;
diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 178f4cd75ef1..8673ac8828e9 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -301,7 +301,7 @@ static int hash_check_key(struct socket *sock)
 	struct alg_sock *ask = alg_sk(sk);
 
 	lock_sock(sk);
-	if (ask->refcnt)
+	if (!atomic_read(&ask->nokey_refcnt))
 		goto unlock_child;
 
 	psk = ask->parent;
@@ -313,11 +313,8 @@ static int hash_check_key(struct socket *sock)
 	if (crypto_ahash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY)
 		goto unlock;
 
-	if (!pask->refcnt++)
-		sock_hold(psk);
-
-	ask->refcnt = 1;
-	sock_put(psk);
+	atomic_dec(&pask->nokey_refcnt);
+	atomic_set(&ask->nokey_refcnt, 0);
 
 	err = 0;
 
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index c1601edd70e3..81c4022285a7 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -56,13 +56,13 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 	struct alg_sock *pask = alg_sk(psk);
 	struct af_alg_ctx *ctx = ask->private;
 	struct crypto_skcipher *tfm = pask->private;
-	unsigned int bs = crypto_skcipher_blocksize(tfm);
+	unsigned int bs = crypto_skcipher_chunksize(tfm);
 	struct af_alg_async_req *areq;
 	int err = 0;
 	size_t len = 0;
 
-	if (!ctx->used) {
-		err = af_alg_wait_for_data(sk, flags);
+	if (!ctx->init || (ctx->more && ctx->used < bs)) {
+		err = af_alg_wait_for_data(sk, flags, bs);
 		if (err)
 			return err;
 	}
@@ -74,14 +74,10 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 		return PTR_ERR(areq);
 
 	/* convert iovecs of output buffers into RX SGL */
-	err = af_alg_get_rsgl(sk, msg, flags, areq, -1, &len);
+	err = af_alg_get_rsgl(sk, msg, flags, areq, ctx->used, &len);
 	if (err)
 		goto free;
 
-	/* Process only as much RX buffers for which we have TX data */
-	if (len > ctx->used)
-		len = ctx->used;
-
 	/*
 	 * If more buffers are to be expected to be processed, process only
 	 * full block size buffers.
@@ -215,7 +211,7 @@ static int skcipher_check_key(struct socket *sock)
 	struct alg_sock *ask = alg_sk(sk);
 
 	lock_sock(sk);
-	if (ask->refcnt)
+	if (!atomic_read(&ask->nokey_refcnt))
 		goto unlock_child;
 
 	psk = ask->parent;
@@ -227,11 +223,8 @@ static int skcipher_check_key(struct socket *sock)
 	if (crypto_skcipher_get_flags(tfm) & CRYPTO_TFM_NEED_KEY)
 		goto unlock;
 
-	if (!pask->refcnt++)
-		sock_hold(psk);
-
-	ask->refcnt = 1;
-	sock_put(psk);
+	atomic_dec(&pask->nokey_refcnt);
+	atomic_set(&ask->nokey_refcnt, 0);
 
 	err = 0;
 
@@ -340,6 +333,7 @@ static int skcipher_accept_parent_nokey(void *private, struct sock *sk)
 	ctx = sock_kmalloc(sk, len, GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
+	memset(ctx, 0, len);
 
 	ctx->iv = sock_kmalloc(sk, crypto_skcipher_ivsize(tfm),
 			       GFP_KERNEL);
@@ -347,16 +341,10 @@ static int skcipher_accept_parent_nokey(void *private, struct sock *sk)
 		sock_kfree_s(sk, ctx, len);
 		return -ENOMEM;
 	}
-
 	memset(ctx->iv, 0, crypto_skcipher_ivsize(tfm));
 
 	INIT_LIST_HEAD(&ctx->tsgl_list);
 	ctx->len = len;
-	ctx->used = 0;
-	atomic_set(&ctx->rcvused, 0);
-	ctx->more = 0;
-	ctx->merge = 0;
-	ctx->enc = 0;
 	crypto_init_wait(&ctx->wait);
 
 	ask->private = ctx;
diff --git a/crypto/api.c b/crypto/api.c
index d8ba54142620..9f99d0e70384 100644
--- a/crypto/api.c
+++ b/crypto/api.c
@@ -97,7 +97,7 @@ static void crypto_larval_destroy(struct crypto_alg *alg)
 	struct crypto_larval *larval = (void *)alg;
 
 	BUG_ON(!crypto_is_larval(alg));
-	if (larval->adult)
+	if (!IS_ERR_OR_NULL(larval->adult))
 		crypto_mod_put(larval->adult);
 	kfree(larval);
 }
@@ -178,6 +178,8 @@ static struct crypto_alg *crypto_larval_wait(struct crypto_alg *alg)
 		alg = ERR_PTR(-ETIMEDOUT);
 	else if (!alg)
 		alg = ERR_PTR(-ENOENT);
+	else if (IS_ERR(alg))
+		;
 	else if (crypto_is_test_larval(larval) &&
 		 !(alg->cra_flags & CRYPTO_ALG_TESTED))
 		alg = ERR_PTR(-EAGAIN);
diff --git a/crypto/arc4.c b/crypto/arc4.c
index a2120e06bf84..6974dba1b7b9 100644
--- a/crypto/arc4.c
+++ b/crypto/arc4.c
@@ -13,33 +13,12 @@
 #include <linux/init.h>
 #include <linux/module.h>
 
-struct arc4_ctx {
-	u32 S[256];
-	u32 x, y;
-};
-
 static int arc4_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 			unsigned int key_len)
 {
 	struct arc4_ctx *ctx = crypto_tfm_ctx(tfm);
-	int i, j = 0, k = 0;
-
-	ctx->x = 1;
-	ctx->y = 0;
 
-	for (i = 0; i < 256; i++)
-		ctx->S[i] = i;
-
-	for (i = 0; i < 256; i++) {
-		u32 a = ctx->S[i];
-		j = (j + in_key[k] + a) & 0xff;
-		ctx->S[i] = ctx->S[j];
-		ctx->S[j] = a;
-		if (++k >= key_len)
-			k = 0;
-	}
-
-	return 0;
+	return arc4_setkey(ctx, in_key, key_len);
 }
 
 static int arc4_set_key_skcipher(struct crypto_skcipher *tfm, const u8 *in_key,
@@ -48,43 +27,6 @@ static int arc4_set_key_skcipher(struct crypto_skcipher *tfm, const u8 *in_key,
 	return arc4_set_key(&tfm->base, in_key, key_len);
 }
 
-static void arc4_crypt(struct arc4_ctx *ctx, u8 *out, const u8 *in,
-		       unsigned int len)
-{
-	u32 *const S = ctx->S;
-	u32 x, y, a, b;
-	u32 ty, ta, tb;
-
-	if (len == 0)
-		return;
-
-	x = ctx->x;
-	y = ctx->y;
-
-	a = S[x];
-	y = (y + a) & 0xff;
-	b = S[y];
-
-	do {
-		S[y] = a;
-		a = (a + b) & 0xff;
-		S[x] = b;
-		x = (x + 1) & 0xff;
-		ta = S[x];
-		ty = (y + ta) & 0xff;
-		tb = S[ty];
-		*out++ = *in++ ^ S[a];
-		if (--len == 0)
-			break;
-		y = ty;
-		a = ta;
-		b = tb;
-	} while (true);
-
-	ctx->x = x;
-	ctx->y = y;
-}
-
 static void arc4_crypt_one(struct crypto_tfm *tfm, u8 *out, const u8 *in)
 {
 	arc4_crypt(crypto_tfm_ctx(tfm), out, in, 1);
diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c
index d7f43d4ea925..e5fae4e838c0 100644
--- a/crypto/asymmetric_keys/public_key.c
+++ b/crypto/asymmetric_keys/public_key.c
@@ -119,6 +119,7 @@ static int software_key_query(const struct kernel_pkey_params *params,
 	if (IS_ERR(tfm))
 		return PTR_ERR(tfm);
 
+	ret = -ENOMEM;
 	key = kmalloc(pkey->keylen + sizeof(u32) * 2 + pkey->paramlen,
 		      GFP_KERNEL);
 	if (!key)
diff --git a/crypto/hash_info.c b/crypto/hash_info.c
index c754cb75dd1a..a49ff96bde77 100644
--- a/crypto/hash_info.c
+++ b/crypto/hash_info.c
@@ -26,7 +26,7 @@ const char *const hash_algo_name[HASH_ALGO__LAST] = {
 	[HASH_ALGO_TGR_128]	= "tgr128",
 	[HASH_ALGO_TGR_160]	= "tgr160",
 	[HASH_ALGO_TGR_192]	= "tgr192",
-	[HASH_ALGO_SM3_256]	= "sm3-256",
+	[HASH_ALGO_SM3_256]	= "sm3",
 	[HASH_ALGO_STREEBOG_256] = "streebog256",
 	[HASH_ALGO_STREEBOG_512] = "streebog512",
 };
diff --git a/crypto/lrw.c b/crypto/lrw.c
index be829f6afc8e..3d40e1f32bea 100644
--- a/crypto/lrw.c
+++ b/crypto/lrw.c
@@ -289,7 +289,7 @@ static void exit_tfm(struct crypto_skcipher *tfm)
 	crypto_free_skcipher(ctx->child);
 }
 
-static void free(struct skcipher_instance *inst)
+static void free_inst(struct skcipher_instance *inst)
 {
 	crypto_drop_skcipher(skcipher_instance_ctx(inst));
 	kfree(inst);
@@ -401,7 +401,7 @@ static int create(struct crypto_template *tmpl, struct rtattr **tb)
 	inst->alg.encrypt = encrypt;
 	inst->alg.decrypt = decrypt;
 
-	inst->free = free;
+	inst->free = free_inst;
 
 	err = skcipher_register_instance(tmpl, inst);
 	if (err)
diff --git a/crypto/pcrypt.c b/crypto/pcrypt.c
index 0edf5b54fc77..ac2789c306e9 100644
--- a/crypto/pcrypt.c
+++ b/crypto/pcrypt.c
@@ -118,7 +118,6 @@ static void pcrypt_aead_done(struct crypto_async_request *areq, int err)
 	struct padata_priv *padata = pcrypt_request_padata(preq);
 
 	padata->info = err;
-	req->base.flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	padata_do_serial(padata);
 }
@@ -493,11 +492,12 @@ err:
 
 static void __exit pcrypt_exit(void)
 {
+	crypto_unregister_template(&pcrypt_tmpl);
+
 	pcrypt_fini_padata(&pencrypt);
 	pcrypt_fini_padata(&pdecrypt);
 
 	kset_unregister(pcrypt_kset);
-	crypto_unregister_template(&pcrypt_tmpl);
 }
 
 subsys_initcall(pcrypt_init);
diff --git a/crypto/rng.c b/crypto/rng.c
index 1e21231f71c9..1490d210f1a1 100644
--- a/crypto/rng.c
+++ b/crypto/rng.c
@@ -37,12 +37,16 @@ int crypto_rng_reset(struct crypto_rng *tfm, const u8 *seed, unsigned int slen)
 	crypto_stats_get(alg);
 	if (!seed && slen) {
 		buf = kmalloc(slen, GFP_KERNEL);
-		if (!buf)
+		if (!buf) {
+			crypto_alg_put(alg);
 			return -ENOMEM;
+		}
 
 		err = get_random_bytes_wait(buf, slen);
-		if (err)
+		if (err) {
+			crypto_alg_put(alg);
 			goto out;
+		}
 		seed = buf;
 	}
 
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index 292d28caf00f..5721bf4a1c89 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -1291,14 +1291,12 @@ static int test_hash_vec(const char *driver, const struct hash_testvec *vec,
  * Generate a hash test vector from the given implementation.
  * Assumes the buffers in 'vec' were already allocated.
  */
-static void generate_random_hash_testvec(struct crypto_shash *tfm,
+static void generate_random_hash_testvec(struct shash_desc *desc,
 					 struct hash_testvec *vec,
 					 unsigned int maxkeysize,
 					 unsigned int maxdatasize,
 					 char *name, size_t max_namelen)
 {
-	SHASH_DESC_ON_STACK(desc, tfm);
-
 	/* Data */
 	vec->psize = generate_random_length(maxdatasize);
 	generate_random_bytes((u8 *)vec->plaintext, vec->psize);
@@ -1315,7 +1313,7 @@ static void generate_random_hash_testvec(struct crypto_shash *tfm,
 			vec->ksize = 1 + (prandom_u32() % maxkeysize);
 		generate_random_bytes((u8 *)vec->key, vec->ksize);
 
-		vec->setkey_error = crypto_shash_setkey(tfm, vec->key,
+		vec->setkey_error = crypto_shash_setkey(desc->tfm, vec->key,
 							vec->ksize);
 		/* If the key couldn't be set, no need to continue to digest. */
 		if (vec->setkey_error)
@@ -1323,7 +1321,6 @@ static void generate_random_hash_testvec(struct crypto_shash *tfm,
 	}
 
 	/* Digest */
-	desc->tfm = tfm;
 	vec->digest_error = crypto_shash_digest(desc, vec->plaintext,
 						vec->psize, (u8 *)vec->digest);
 done:
@@ -1349,10 +1346,11 @@ static int test_hash_vs_generic_impl(const char *driver,
 	const char *algname = crypto_hash_alg_common(tfm)->base.cra_name;
 	char _generic_driver[CRYPTO_MAX_ALG_NAME];
 	struct crypto_shash *generic_tfm = NULL;
+	struct shash_desc *generic_desc = NULL;
 	unsigned int i;
 	struct hash_testvec vec = { 0 };
 	char vec_name[64];
-	struct testvec_config cfg;
+	struct testvec_config *cfg;
 	char cfgname[TESTVEC_CONFIG_NAMELEN];
 	int err;
 
@@ -1382,6 +1380,20 @@ static int test_hash_vs_generic_impl(const char *driver,
 		return err;
 	}
 
+	cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
+	if (!cfg) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	generic_desc = kzalloc(sizeof(*desc) +
+			       crypto_shash_descsize(generic_tfm), GFP_KERNEL);
+	if (!generic_desc) {
+		err = -ENOMEM;
+		goto out;
+	}
+	generic_desc->tfm = generic_tfm;
+
 	/* Check the algorithm properties for consistency. */
 
 	if (digestsize != crypto_shash_digestsize(generic_tfm)) {
@@ -1413,12 +1425,12 @@ static int test_hash_vs_generic_impl(const char *driver,
 	}
 
 	for (i = 0; i < fuzz_iterations * 8; i++) {
-		generate_random_hash_testvec(generic_tfm, &vec,
+		generate_random_hash_testvec(generic_desc, &vec,
 					     maxkeysize, maxdatasize,
 					     vec_name, sizeof(vec_name));
-		generate_random_testvec_config(&cfg, cfgname, sizeof(cfgname));
+		generate_random_testvec_config(cfg, cfgname, sizeof(cfgname));
 
-		err = test_hash_vec_cfg(driver, &vec, vec_name, &cfg,
+		err = test_hash_vec_cfg(driver, &vec, vec_name, cfg,
 					req, tsgl, hashstate);
 		if (err)
 			goto out;
@@ -1426,10 +1438,12 @@ static int test_hash_vs_generic_impl(const char *driver,
 	}
 	err = 0;
 out:
+	kfree(cfg);
 	kfree(vec.key);
 	kfree(vec.plaintext);
 	kfree(vec.digest);
 	crypto_free_shash(generic_tfm);
+	kzfree(generic_desc);
 	return err;
 }
 #else /* !CONFIG_CRYPTO_MANAGER_EXTRA_TESTS */
@@ -1820,6 +1834,7 @@ static void generate_random_aead_testvec(struct aead_request *req,
 	 * If the key or authentication tag size couldn't be set, no need to
 	 * continue to encrypt.
 	 */
+	vec->crypt_error = 0;
 	if (vec->setkey_error || vec->setauthsize_error)
 		goto done;
 
@@ -1867,7 +1882,7 @@ static int test_aead_vs_generic_impl(const char *driver,
 	unsigned int i;
 	struct aead_testvec vec = { 0 };
 	char vec_name[64];
-	struct testvec_config cfg;
+	struct testvec_config *cfg;
 	char cfgname[TESTVEC_CONFIG_NAMELEN];
 	int err;
 
@@ -1897,6 +1912,12 @@ static int test_aead_vs_generic_impl(const char *driver,
 		return err;
 	}
 
+	cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
+	if (!cfg) {
+		err = -ENOMEM;
+		goto out;
+	}
+
 	generic_req = aead_request_alloc(generic_tfm, GFP_KERNEL);
 	if (!generic_req) {
 		err = -ENOMEM;
@@ -1951,20 +1972,23 @@ static int test_aead_vs_generic_impl(const char *driver,
 		generate_random_aead_testvec(generic_req, &vec,
 					     maxkeysize, maxdatasize,
 					     vec_name, sizeof(vec_name));
-		generate_random_testvec_config(&cfg, cfgname, sizeof(cfgname));
+		generate_random_testvec_config(cfg, cfgname, sizeof(cfgname));
 
-		err = test_aead_vec_cfg(driver, ENCRYPT, &vec, vec_name, &cfg,
-					req, tsgls);
-		if (err)
-			goto out;
-		err = test_aead_vec_cfg(driver, DECRYPT, &vec, vec_name, &cfg,
+		err = test_aead_vec_cfg(driver, ENCRYPT, &vec, vec_name, cfg,
 					req, tsgls);
 		if (err)
 			goto out;
+		if (vec.crypt_error == 0) {
+			err = test_aead_vec_cfg(driver, DECRYPT, &vec, vec_name,
+						cfg, req, tsgls);
+			if (err)
+				goto out;
+		}
 		cond_resched();
 	}
 	err = 0;
 out:
+	kfree(cfg);
 	kfree(vec.key);
 	kfree(vec.iv);
 	kfree(vec.assoc);
@@ -2389,6 +2413,15 @@ static void generate_random_cipher_testvec(struct skcipher_request *req,
 	skcipher_request_set_callback(req, 0, crypto_req_done, &wait);
 	skcipher_request_set_crypt(req, &src, &dst, vec->len, iv);
 	vec->crypt_error = crypto_wait_req(crypto_skcipher_encrypt(req), &wait);
+	if (vec->crypt_error != 0) {
+		/*
+		 * The only acceptable error here is for an invalid length, so
+		 * skcipher decryption should fail with the same error too.
+		 * We'll test for this.  But to keep the API usage well-defined,
+		 * explicitly initialize the ciphertext buffer too.
+		 */
+		memset((u8 *)vec->ctext, 0, vec->len);
+	}
 done:
 	snprintf(name, max_namelen, "\"random: len=%u klen=%u\"",
 		 vec->len, vec->klen);
@@ -2414,7 +2447,7 @@ static int test_skcipher_vs_generic_impl(const char *driver,
 	unsigned int i;
 	struct cipher_testvec vec = { 0 };
 	char vec_name[64];
-	struct testvec_config cfg;
+	struct testvec_config *cfg;
 	char cfgname[TESTVEC_CONFIG_NAMELEN];
 	int err;
 
@@ -2448,6 +2481,12 @@ static int test_skcipher_vs_generic_impl(const char *driver,
 		return err;
 	}
 
+	cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
+	if (!cfg) {
+		err = -ENOMEM;
+		goto out;
+	}
+
 	generic_req = skcipher_request_alloc(generic_tfm, GFP_KERNEL);
 	if (!generic_req) {
 		err = -ENOMEM;
@@ -2495,20 +2534,21 @@ static int test_skcipher_vs_generic_impl(const char *driver,
 	for (i = 0; i < fuzz_iterations * 8; i++) {
 		generate_random_cipher_testvec(generic_req, &vec, maxdatasize,
 					       vec_name, sizeof(vec_name));
-		generate_random_testvec_config(&cfg, cfgname, sizeof(cfgname));
+		generate_random_testvec_config(cfg, cfgname, sizeof(cfgname));
 
 		err = test_skcipher_vec_cfg(driver, ENCRYPT, &vec, vec_name,
-					    &cfg, req, tsgls);
+					    cfg, req, tsgls);
 		if (err)
 			goto out;
 		err = test_skcipher_vec_cfg(driver, DECRYPT, &vec, vec_name,
-					    &cfg, req, tsgls);
+					    cfg, req, tsgls);
 		if (err)
 			goto out;
 		cond_resched();
 	}
 	err = 0;
 out:
+	kfree(cfg);
 	kfree(vec.key);
 	kfree(vec.iv);
 	kfree(vec.ptext);
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index 1fdae5993bc3..b4d1b32885b6 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -38,7 +38,7 @@ struct hash_testvec {
 	const char *key;
 	const char *plaintext;
 	const char *digest;
-	unsigned short psize;
+	unsigned int psize;
 	unsigned short ksize;
 	int setkey_error;
 	int digest_error;
@@ -69,7 +69,7 @@ struct cipher_testvec {
 	const char *ctext;
 	unsigned char wk; /* weak key flag */
 	unsigned short klen;
-	unsigned short len;
+	unsigned int len;
 	bool fips_skip;
 	bool generates_iv;
 	int setkey_error;
@@ -105,9 +105,9 @@ struct aead_testvec {
 	unsigned char novrfy;
 	unsigned char wk;
 	unsigned char klen;
-	unsigned short plen;
-	unsigned short clen;
-	unsigned short alen;
+	unsigned int plen;
+	unsigned int clen;
+	unsigned int alen;
 	int setkey_error;
 	int setauthsize_error;
 	int crypt_error;
diff --git a/crypto/xts.c b/crypto/xts.c
index 11211003db7e..6aaed7e50366 100644
--- a/crypto/xts.c
+++ b/crypto/xts.c
@@ -216,7 +216,7 @@ static void exit_tfm(struct crypto_skcipher *tfm)
 	crypto_free_cipher(ctx->tweak);
 }
 
-static void free(struct skcipher_instance *inst)
+static void free_inst(struct skcipher_instance *inst)
 {
 	crypto_drop_skcipher(skcipher_instance_ctx(inst));
 	kfree(inst);
@@ -327,7 +327,7 @@ static int create(struct crypto_template *tmpl, struct rtattr **tb)
 	inst->alg.encrypt = encrypt;
 	inst->alg.decrypt = decrypt;
 
-	inst->free = free;
+	inst->free = free_inst;
 
 	err = skcipher_register_instance(tmpl, inst);
 	if (err)
diff --git a/drivers/acpi/acpi_watchdog.c b/drivers/acpi/acpi_watchdog.c
index b5516b04ffc0..6e9ec6e3fe47 100644
--- a/drivers/acpi/acpi_watchdog.c
+++ b/drivers/acpi/acpi_watchdog.c
@@ -55,12 +55,14 @@ static bool acpi_watchdog_uses_rtc(const struct acpi_table_wdat *wdat)
 }
 #endif
 
+static bool acpi_no_watchdog;
+
 static const struct acpi_table_wdat *acpi_watchdog_get_wdat(void)
 {
 	const struct acpi_table_wdat *wdat = NULL;
 	acpi_status status;
 
-	if (acpi_disabled)
+	if (acpi_disabled || acpi_no_watchdog)
 		return NULL;
 
 	status = acpi_get_table(ACPI_SIG_WDAT, 0,
@@ -88,6 +90,14 @@ bool acpi_has_watchdog(void)
 }
 EXPORT_SYMBOL_GPL(acpi_has_watchdog);
 
+/* ACPI watchdog can be disabled on boot command line */
+static int __init disable_acpi_watchdog(char *str)
+{
+	acpi_no_watchdog = true;
+	return 1;
+}
+__setup("acpi_no_watchdog", disable_acpi_watchdog);
+
 void __init acpi_watchdog_init(void)
 {
 	const struct acpi_wdat_entry *entries;
@@ -126,12 +136,11 @@ void __init acpi_watchdog_init(void)
 		gas = &entries[i].register_region;
 
 		res.start = gas->address;
+		res.end = res.start + ACPI_ACCESS_BYTE_WIDTH(gas->access_width) - 1;
 		if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) {
 			res.flags = IORESOURCE_MEM;
-			res.end = res.start + ALIGN(gas->access_width, 4) - 1;
 		} else if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_IO) {
 			res.flags = IORESOURCE_IO;
-			res.end = res.start + gas->access_width - 1;
 		} else {
 			pr_warn("Unsupported address space: %u\n",
 				gas->space_id);
diff --git a/drivers/acpi/acpica/acnamesp.h b/drivers/acpi/acpica/acnamesp.h
index 39812fc4386a..28fe8767ccda 100644
--- a/drivers/acpi/acpica/acnamesp.h
+++ b/drivers/acpi/acpica/acnamesp.h
@@ -258,6 +258,8 @@ u32
 acpi_ns_build_normalized_path(struct acpi_namespace_node *node,
 			      char *full_path, u32 path_size, u8 no_trailing);
 
+void acpi_ns_normalize_pathname(char *original_path);
+
 char *acpi_ns_get_normalized_pathname(struct acpi_namespace_node *node,
 				      u8 no_trailing);
 
diff --git a/drivers/acpi/acpica/dbinput.c b/drivers/acpi/acpica/dbinput.c
index 3e5f95390f0d..8b9a0f09d0bc 100644
--- a/drivers/acpi/acpica/dbinput.c
+++ b/drivers/acpi/acpica/dbinput.c
@@ -464,16 +464,14 @@ char *acpi_db_get_next_token(char *string,
 		return (NULL);
 	}
 
-	/* Remove any spaces at the beginning */
+	/* Remove any spaces at the beginning, ignore blank lines */
 
-	if (*string == ' ') {
-		while (*string && (*string == ' ')) {
-			string++;
-		}
+	while (*string && isspace(*string)) {
+		string++;
+	}
 
-		if (!(*string)) {
-			return (NULL);
-		}
+	if (!(*string)) {
+		return (NULL);
 	}
 
 	switch (*string) {
@@ -551,7 +549,7 @@ char *acpi_db_get_next_token(char *string,
 
 		/* Find end of token */
 
-		while (*string && (*string != ' ')) {
+		while (*string && !isspace(*string)) {
 			string++;
 		}
 		break;
diff --git a/drivers/acpi/acpica/dsfield.c b/drivers/acpi/acpica/dsfield.c
index cf4e061bb0f0..fd9028a6bc20 100644
--- a/drivers/acpi/acpica/dsfield.c
+++ b/drivers/acpi/acpica/dsfield.c
@@ -244,7 +244,7 @@ cleanup:
  * FUNCTION:    acpi_ds_get_field_names
  *
  * PARAMETERS:  info            - create_field info structure
- *  `           walk_state      - Current method state
+ *              walk_state      - Current method state
  *              arg             - First parser arg for the field name list
  *
  * RETURN:      Status
@@ -518,13 +518,20 @@ acpi_ds_create_field(union acpi_parse_object *op,
 	info.region_node = region_node;
 
 	status = acpi_ds_get_field_names(&info, walk_state, arg->common.next);
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
+
 	if (info.region_node->object->region.space_id ==
-	    ACPI_ADR_SPACE_PLATFORM_COMM
-	    && !(region_node->object->field.internal_pcc_buffer =
-		 ACPI_ALLOCATE_ZEROED(info.region_node->object->region.
-				      length))) {
-		return_ACPI_STATUS(AE_NO_MEMORY);
+	    ACPI_ADR_SPACE_PLATFORM_COMM) {
+		region_node->object->field.internal_pcc_buffer =
+		    ACPI_ALLOCATE_ZEROED(info.region_node->object->region.
+					 length);
+		if (!region_node->object->field.internal_pcc_buffer) {
+			return_ACPI_STATUS(AE_NO_MEMORY);
+		}
 	}
+
 	return_ACPI_STATUS(status);
 }
 
diff --git a/drivers/acpi/acpica/dswexec.c b/drivers/acpi/acpica/dswexec.c
index d75aae304595..a68237b97c4c 100644
--- a/drivers/acpi/acpica/dswexec.c
+++ b/drivers/acpi/acpica/dswexec.c
@@ -16,6 +16,9 @@
 #include "acinterp.h"
 #include "acnamesp.h"
 #include "acdebug.h"
+#ifdef ACPI_EXEC_APP
+#include "aecommon.h"
+#endif
 
 #define _COMPONENT          ACPI_DISPATCHER
 ACPI_MODULE_NAME("dswexec")
@@ -329,6 +332,10 @@ acpi_status acpi_ds_exec_end_op(struct acpi_walk_state *walk_state)
 	u32 op_class;
 	union acpi_parse_object *next_op;
 	union acpi_parse_object *first_arg;
+#ifdef ACPI_EXEC_APP
+	char *namepath;
+	union acpi_operand_object *obj_desc;
+#endif
 
 	ACPI_FUNCTION_TRACE_PTR(ds_exec_end_op, walk_state);
 
@@ -537,6 +544,32 @@ acpi_status acpi_ds_exec_end_op(struct acpi_walk_state *walk_state)
 
 			status =
 			    acpi_ds_eval_buffer_field_operands(walk_state, op);
+			if (ACPI_FAILURE(status)) {
+				break;
+			}
+#ifdef ACPI_EXEC_APP
+			/*
+			 * acpi_exec support for namespace initialization file (initialize
+			 * buffer_fields in this code.)
+			 */
+			namepath =
+			    acpi_ns_get_external_pathname(op->common.node);
+			status = ae_lookup_init_file_entry(namepath, &obj_desc);
+			if (ACPI_SUCCESS(status)) {
+				status =
+				    acpi_ex_write_data_to_field(obj_desc,
+								op->common.
+								node->object,
+								NULL);
+				if ACPI_FAILURE
+					(status) {
+					ACPI_EXCEPTION((AE_INFO, status,
+							"While writing to buffer field"));
+					}
+			}
+			ACPI_FREE(namepath);
+			status = AE_OK;
+#endif
 			break;
 
 		case AML_TYPE_CREATE_OBJECT:
diff --git a/drivers/acpi/acpica/dswload.c b/drivers/acpi/acpica/dswload.c
index c88fd31208a5..6cf93fae4d07 100644
--- a/drivers/acpi/acpica/dswload.c
+++ b/drivers/acpi/acpica/dswload.c
@@ -14,7 +14,6 @@
 #include "acdispat.h"
 #include "acinterp.h"
 #include "acnamesp.h"
-
 #ifdef ACPI_ASL_COMPILER
 #include "acdisasm.h"
 #endif
@@ -399,7 +398,6 @@ acpi_status acpi_ds_load1_end_op(struct acpi_walk_state *walk_state)
 	union acpi_parse_object *op;
 	acpi_object_type object_type;
 	acpi_status status = AE_OK;
-
 #ifdef ACPI_ASL_COMPILER
 	u8 param_count;
 #endif
@@ -410,6 +408,27 @@ acpi_status acpi_ds_load1_end_op(struct acpi_walk_state *walk_state)
 	ACPI_DEBUG_PRINT((ACPI_DB_DISPATCH, "Op=%p State=%p\n", op,
 			  walk_state));
 
+	/*
+	 * Disassembler: handle create field operators here.
+	 *
+	 * create_buffer_field is a deferred op that is typically processed in load
+	 * pass 2. However, disassembly of control method contents walk the parse
+	 * tree with ACPI_PARSE_LOAD_PASS1 and AML_CREATE operators are processed
+	 * in a later walk. This is a problem when there is a control method that
+	 * has the same name as the AML_CREATE object. In this case, any use of the
+	 * name segment will be detected as a method call rather than a reference
+	 * to a buffer field.
+	 *
+	 * This earlier creation during disassembly solves this issue by inserting
+	 * the named object in the ACPI namespace so that references to this name
+	 * would be a name string rather than a method call.
+	 */
+	if ((walk_state->parse_flags & ACPI_PARSE_DISASSEMBLE) &&
+	    (walk_state->op_info->flags & AML_CREATE)) {
+		status = acpi_ds_create_buffer_field(op, walk_state);
+		return_ACPI_STATUS(status);
+	}
+
 	/* We are only interested in opcodes that have an associated name */
 
 	if (!(walk_state->op_info->flags & (AML_NAMED | AML_FIELD))) {
diff --git a/drivers/acpi/acpica/dswload2.c b/drivers/acpi/acpica/dswload2.c
index 935a8e2623e4..15d92bf15f0b 100644
--- a/drivers/acpi/acpica/dswload2.c
+++ b/drivers/acpi/acpica/dswload2.c
@@ -15,6 +15,9 @@
 #include "acinterp.h"
 #include "acnamesp.h"
 #include "acevents.h"
+#ifdef ACPI_EXEC_APP
+#include "aecommon.h"
+#endif
 
 #define _COMPONENT          ACPI_DISPATCHER
 ACPI_MODULE_NAME("dswload2")
@@ -373,6 +376,10 @@ acpi_status acpi_ds_load2_end_op(struct acpi_walk_state *walk_state)
 	struct acpi_namespace_node *new_node;
 	u32 i;
 	u8 region_space;
+#ifdef ACPI_EXEC_APP
+	union acpi_operand_object *obj_desc;
+	char *namepath;
+#endif
 
 	ACPI_FUNCTION_TRACE(ds_load2_end_op);
 
@@ -466,6 +473,11 @@ acpi_status acpi_ds_load2_end_op(struct acpi_walk_state *walk_state)
 		 * be evaluated later during the execution phase
 		 */
 		status = acpi_ds_create_buffer_field(op, walk_state);
+		if (ACPI_FAILURE(status)) {
+			ACPI_EXCEPTION((AE_INFO, status,
+					"CreateBufferField failure"));
+			goto cleanup;
+			}
 		break;
 
 	case AML_TYPE_NAMED_FIELD:
@@ -604,6 +616,29 @@ acpi_status acpi_ds_load2_end_op(struct acpi_walk_state *walk_state)
 		case AML_NAME_OP:
 
 			status = acpi_ds_create_node(walk_state, node, op);
+			if (ACPI_FAILURE(status)) {
+				goto cleanup;
+			}
+#ifdef ACPI_EXEC_APP
+			/*
+			 * acpi_exec support for namespace initialization file (initialize
+			 * Name opcodes in this code.)
+			 */
+			namepath = acpi_ns_get_external_pathname(node);
+			status = ae_lookup_init_file_entry(namepath, &obj_desc);
+			if (ACPI_SUCCESS(status)) {
+
+				/* Detach any existing object, attach new object */
+
+				if (node->object) {
+					acpi_ns_detach_object(node);
+				}
+				acpi_ns_attach_object(node, obj_desc,
+						      obj_desc->common.type);
+			}
+			ACPI_FREE(namepath);
+			status = AE_OK;
+#endif
 			break;
 
 		case AML_METHOD_OP:
diff --git a/drivers/acpi/acpica/exprep.c b/drivers/acpi/acpica/exprep.c
index 728d752f7adc..85f799c9c25c 100644
--- a/drivers/acpi/acpica/exprep.c
+++ b/drivers/acpi/acpica/exprep.c
@@ -473,10 +473,6 @@ acpi_status acpi_ex_prep_field_value(struct acpi_create_field_info *info)
 				    (u8)access_byte_width;
 			}
 		}
-		/* An additional reference for the container */
-
-		acpi_ut_add_reference(obj_desc->field.region_obj);
-
 		ACPI_DEBUG_PRINT((ACPI_DB_BFIELD,
 				  "RegionField: BitOff %X, Off %X, Gran %X, Region %p\n",
 				  obj_desc->field.start_field_bit_offset,
diff --git a/drivers/acpi/acpica/nsnames.c b/drivers/acpi/acpica/nsnames.c
index 370bbc867745..c717fff7d9b5 100644
--- a/drivers/acpi/acpica/nsnames.c
+++ b/drivers/acpi/acpica/nsnames.c
@@ -13,9 +13,6 @@
 #define _COMPONENT          ACPI_NAMESPACE
 ACPI_MODULE_NAME("nsnames")
 
-/* Local Prototypes */
-static void acpi_ns_normalize_pathname(char *original_path);
-
 /*******************************************************************************
  *
  * FUNCTION:    acpi_ns_get_external_pathname
@@ -30,7 +27,6 @@ static void acpi_ns_normalize_pathname(char *original_path);
  *              for error and debug statements.
  *
  ******************************************************************************/
-
 char *acpi_ns_get_external_pathname(struct acpi_namespace_node *node)
 {
 	char *name_buffer;
@@ -411,7 +407,7 @@ cleanup:
  *
  ******************************************************************************/
 
-static void acpi_ns_normalize_pathname(char *original_path)
+void acpi_ns_normalize_pathname(char *original_path)
 {
 	char *input_path = original_path;
 	char *new_path_buffer;
diff --git a/drivers/acpi/acpica/utdelete.c b/drivers/acpi/acpica/utdelete.c
index eee263cb7beb..4c0d4e434196 100644
--- a/drivers/acpi/acpica/utdelete.c
+++ b/drivers/acpi/acpica/utdelete.c
@@ -452,13 +452,13 @@ acpi_ut_update_ref_count(union acpi_operand_object *object, u32 action)
  *
  * FUNCTION:    acpi_ut_update_object_reference
  *
- * PARAMETERS:  object              - Increment ref count for this object
- *                                    and all sub-objects
+ * PARAMETERS:  object              - Increment or decrement the ref count for
+ *                                    this object and all sub-objects
  *              action              - Either REF_INCREMENT or REF_DECREMENT
  *
  * RETURN:      Status
  *
- * DESCRIPTION: Increment the object reference count
+ * DESCRIPTION: Increment or decrement the object reference count
  *
  * Object references are incremented when:
  * 1) An object is attached to a Node (namespace object)
@@ -492,7 +492,7 @@ acpi_ut_update_object_reference(union acpi_operand_object *object, u16 action)
 		}
 
 		/*
-		 * All sub-objects must have their reference count incremented
+		 * All sub-objects must have their reference count updated
 		 * also. Different object types have different subobjects.
 		 */
 		switch (object->common.type) {
@@ -559,6 +559,7 @@ acpi_ut_update_object_reference(union acpi_operand_object *object, u16 action)
 					break;
 				}
 			}
+
 			next_object = NULL;
 			break;
 
@@ -567,11 +568,6 @@ acpi_ut_update_object_reference(union acpi_operand_object *object, u16 action)
 			next_object = object->buffer_field.buffer_obj;
 			break;
 
-		case ACPI_TYPE_LOCAL_REGION_FIELD:
-
-			next_object = object->field.region_obj;
-			break;
-
 		case ACPI_TYPE_LOCAL_BANK_FIELD:
 
 			next_object = object->bank_field.bank_obj;
@@ -612,6 +608,7 @@ acpi_ut_update_object_reference(union acpi_operand_object *object, u16 action)
 			}
 			break;
 
+		case ACPI_TYPE_LOCAL_REGION_FIELD:
 		case ACPI_TYPE_REGION:
 		default:
 
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 6875bf629f16..3760b5ebf1a6 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -171,7 +171,7 @@ int ghes_estatus_pool_init(int num_ghes)
 	 * New allocation must be visible in all pgd before it can be found by
 	 * an NMI allocating from the pool.
 	 */
-	vmalloc_sync_all();
+	vmalloc_sync_mappings();
 
 	rc = gen_pool_add(ghes_estatus_pool, addr, PAGE_ALIGN(len), -1);
 	if (rc)
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 8569b79e8b58..2124c3a2b24b 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -361,6 +361,7 @@ static struct acpi_iort_node *iort_node_get_id(struct acpi_iort_node *node,
 static int iort_get_id_mapping_index(struct acpi_iort_node *node)
 {
 	struct acpi_iort_smmu_v3 *smmu;
+	struct acpi_iort_pmcg *pmcg;
 
 	switch (node->type) {
 	case ACPI_IORT_NODE_SMMU_V3:
@@ -388,6 +389,10 @@ static int iort_get_id_mapping_index(struct acpi_iort_node *node)
 
 		return smmu->id_mapping_index;
 	case ACPI_IORT_NODE_PMCG:
+		pmcg = (struct acpi_iort_pmcg *)node->node_data;
+		if (pmcg->overflow_gsiv || node->mapping_count == 0)
+			return -EINVAL;
+
 		return 0;
 	default:
 		return -EINVAL;
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index 558fedf8a7a1..254a7d98b9d4 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -38,6 +38,8 @@
 #define PREFIX "ACPI: "
 
 #define ACPI_BATTERY_VALUE_UNKNOWN 0xFFFFFFFF
+#define ACPI_BATTERY_CAPACITY_VALID(capacity) \
+	((capacity) != 0 && (capacity) != ACPI_BATTERY_VALUE_UNKNOWN)
 
 #define ACPI_BATTERY_DEVICE_NAME	"Battery"
 
@@ -192,7 +194,8 @@ static int acpi_battery_is_charged(struct acpi_battery *battery)
 
 static bool acpi_battery_is_degraded(struct acpi_battery *battery)
 {
-	return battery->full_charge_capacity && battery->design_capacity &&
+	return ACPI_BATTERY_CAPACITY_VALID(battery->full_charge_capacity) &&
+		ACPI_BATTERY_CAPACITY_VALID(battery->design_capacity) &&
 		battery->full_charge_capacity < battery->design_capacity;
 }
 
@@ -214,7 +217,7 @@ static int acpi_battery_get_property(struct power_supply *psy,
 				     enum power_supply_property psp,
 				     union power_supply_propval *val)
 {
-	int ret = 0;
+	int full_capacity = ACPI_BATTERY_VALUE_UNKNOWN, ret = 0;
 	struct acpi_battery *battery = to_acpi_battery(psy);
 
 	if (acpi_battery_present(battery)) {
@@ -263,14 +266,14 @@ static int acpi_battery_get_property(struct power_supply *psy,
 		break;
 	case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN:
 	case POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN:
-		if (battery->design_capacity == ACPI_BATTERY_VALUE_UNKNOWN)
+		if (!ACPI_BATTERY_CAPACITY_VALID(battery->design_capacity))
 			ret = -ENODEV;
 		else
 			val->intval = battery->design_capacity * 1000;
 		break;
 	case POWER_SUPPLY_PROP_CHARGE_FULL:
 	case POWER_SUPPLY_PROP_ENERGY_FULL:
-		if (battery->full_charge_capacity == ACPI_BATTERY_VALUE_UNKNOWN)
+		if (!ACPI_BATTERY_CAPACITY_VALID(battery->full_charge_capacity))
 			ret = -ENODEV;
 		else
 			val->intval = battery->full_charge_capacity * 1000;
@@ -283,11 +286,17 @@ static int acpi_battery_get_property(struct power_supply *psy,
 			val->intval = battery->capacity_now * 1000;
 		break;
 	case POWER_SUPPLY_PROP_CAPACITY:
-		if (battery->capacity_now && battery->full_charge_capacity)
-			val->intval = battery->capacity_now * 100/
-					battery->full_charge_capacity;
+		if (ACPI_BATTERY_CAPACITY_VALID(battery->full_charge_capacity))
+			full_capacity = battery->full_charge_capacity;
+		else if (ACPI_BATTERY_CAPACITY_VALID(battery->design_capacity))
+			full_capacity = battery->design_capacity;
+
+		if (battery->capacity_now == ACPI_BATTERY_VALUE_UNKNOWN ||
+		    full_capacity == ACPI_BATTERY_VALUE_UNKNOWN)
+			ret = -ENODEV;
 		else
-			val->intval = 0;
+			val->intval = battery->capacity_now * 100/
+					full_capacity;
 		break;
 	case POWER_SUPPLY_PROP_CAPACITY_LEVEL:
 		if (battery->state & ACPI_BATTERY_STATE_CRITICAL)
@@ -333,6 +342,20 @@ static enum power_supply_property charge_battery_props[] = {
 	POWER_SUPPLY_PROP_SERIAL_NUMBER,
 };
 
+static enum power_supply_property charge_battery_full_cap_broken_props[] = {
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_PRESENT,
+	POWER_SUPPLY_PROP_TECHNOLOGY,
+	POWER_SUPPLY_PROP_CYCLE_COUNT,
+	POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_CURRENT_NOW,
+	POWER_SUPPLY_PROP_CHARGE_NOW,
+	POWER_SUPPLY_PROP_MODEL_NAME,
+	POWER_SUPPLY_PROP_MANUFACTURER,
+	POWER_SUPPLY_PROP_SERIAL_NUMBER,
+};
+
 static enum power_supply_property energy_battery_props[] = {
 	POWER_SUPPLY_PROP_STATUS,
 	POWER_SUPPLY_PROP_PRESENT,
@@ -794,20 +817,34 @@ static void __exit battery_hook_exit(void)
 static int sysfs_add_battery(struct acpi_battery *battery)
 {
 	struct power_supply_config psy_cfg = { .drv_data = battery, };
+	bool full_cap_broken = false;
+
+	if (!ACPI_BATTERY_CAPACITY_VALID(battery->full_charge_capacity) &&
+	    !ACPI_BATTERY_CAPACITY_VALID(battery->design_capacity))
+		full_cap_broken = true;
 
 	if (battery->power_unit == ACPI_BATTERY_POWER_UNIT_MA) {
-		battery->bat_desc.properties = charge_battery_props;
-		battery->bat_desc.num_properties =
-			ARRAY_SIZE(charge_battery_props);
-	} else if (battery->full_charge_capacity == 0) {
-		battery->bat_desc.properties =
-			energy_battery_full_cap_broken_props;
-		battery->bat_desc.num_properties =
-			ARRAY_SIZE(energy_battery_full_cap_broken_props);
+		if (full_cap_broken) {
+			battery->bat_desc.properties =
+			    charge_battery_full_cap_broken_props;
+			battery->bat_desc.num_properties =
+			    ARRAY_SIZE(charge_battery_full_cap_broken_props);
+		} else {
+			battery->bat_desc.properties = charge_battery_props;
+			battery->bat_desc.num_properties =
+			    ARRAY_SIZE(charge_battery_props);
+		}
 	} else {
-		battery->bat_desc.properties = energy_battery_props;
-		battery->bat_desc.num_properties =
-			ARRAY_SIZE(energy_battery_props);
+		if (full_cap_broken) {
+			battery->bat_desc.properties =
+			    energy_battery_full_cap_broken_props;
+			battery->bat_desc.num_properties =
+			    ARRAY_SIZE(energy_battery_full_cap_broken_props);
+		} else {
+			battery->bat_desc.properties = energy_battery_props;
+			battery->bat_desc.num_properties =
+			    ARRAY_SIZE(energy_battery_props);
+		}
 	}
 
 	battery->bat_desc.name = acpi_device_bid(battery->device);
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index 4a2cde2c536a..7f1eb7e65f6a 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -78,6 +78,17 @@ static const struct dmi_system_id lid_blacklst[] = {
 			DMI_MATCH(DMI_BIOS_VERSION, "BYT70A.YNCHENG.WIN.007"),
 		},
 	},
+	{
+		/*
+		 * Razer Blade Stealth 13 late 2019, notification of the LID device
+		 * only happens on close, not on open and _LID always returns closed.
+		 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Razer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Razer Blade Stealth 13 Late 2019"),
+		},
+		.driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN,
+	},
 	{}
 };
 
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index a1a858ad4d18..f9b1a2abdbe2 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -865,6 +865,7 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
 			"acpi_cppc");
 	if (ret) {
 		per_cpu(cpc_desc_ptr, pr->id) = NULL;
+		kobject_put(&cpc_ptr->kobj);
 		goto out_free;
 	}
 
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 018e6baf758f..8663d8c25867 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -165,7 +165,7 @@ int acpi_device_set_power(struct acpi_device *device, int state)
 		 * possibly drop references to the power resources in use.
 		 */
 		state = ACPI_STATE_D3_HOT;
-		/* If _PR3 is not available, use D3hot as the target state. */
+		/* If D3cold is not supported, use D3hot as the target state. */
 		if (!device->power.states[ACPI_STATE_D3_COLD].flags.valid)
 			target_state = state;
 	} else if (!device->power.states[state].flags.valid) {
@@ -220,13 +220,13 @@ int acpi_device_set_power(struct acpi_device *device, int state)
  end:
 	if (result) {
 		dev_warn(&device->dev, "Failed to change power state to %s\n",
-			 acpi_power_state_string(state));
+			 acpi_power_state_string(target_state));
 	} else {
 		device->power.state = target_state;
 		ACPI_DEBUG_PRINT((ACPI_DB_INFO,
 				  "Device [%s] transitioned to %s\n",
 				  device->pnp.bus_id,
-				  acpi_power_state_string(state)));
+				  acpi_power_state_string(target_state)));
 	}
 
 	return result;
diff --git a/drivers/acpi/evged.c b/drivers/acpi/evged.c
index aba0d0027586..ccd900690b6f 100644
--- a/drivers/acpi/evged.c
+++ b/drivers/acpi/evged.c
@@ -79,6 +79,8 @@ static acpi_status acpi_ged_request_interrupt(struct acpi_resource *ares,
 	struct resource r;
 	struct acpi_resource_irq *p = &ares->data.irq;
 	struct acpi_resource_extended_irq *pext = &ares->data.extended_irq;
+	char ev_name[5];
+	u8 trigger;
 
 	if (ares->type == ACPI_RESOURCE_TYPE_END_TAG)
 		return AE_OK;
@@ -87,14 +89,28 @@ static acpi_status acpi_ged_request_interrupt(struct acpi_resource *ares,
 		dev_err(dev, "unable to parse IRQ resource\n");
 		return AE_ERROR;
 	}
-	if (ares->type == ACPI_RESOURCE_TYPE_IRQ)
+	if (ares->type == ACPI_RESOURCE_TYPE_IRQ) {
 		gsi = p->interrupts[0];
-	else
+		trigger = p->triggering;
+	} else {
 		gsi = pext->interrupts[0];
+		trigger = pext->triggering;
+	}
 
 	irq = r.start;
 
-	if (ACPI_FAILURE(acpi_get_handle(handle, "_EVT", &evt_handle))) {
+	switch (gsi) {
+	case 0 ... 255:
+		sprintf(ev_name, "_%c%02hhX",
+			trigger == ACPI_EDGE_SENSITIVE ? 'E' : 'L', gsi);
+
+		if (ACPI_SUCCESS(acpi_get_handle(handle, ev_name, &evt_handle)))
+			break;
+		/* fall through */
+	default:
+		if (ACPI_SUCCESS(acpi_get_handle(handle, "_EVT", &evt_handle)))
+			break;
+
 		dev_err(dev, "cannot locate _EVT method\n");
 		return AE_ERROR;
 	}
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 23022cf20d26..4c342736d5a8 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -360,7 +360,7 @@ static union acpi_object *acpi_label_info(acpi_handle handle)
 
 static u8 nfit_dsm_revid(unsigned family, unsigned func)
 {
-	static const u8 revid_table[NVDIMM_FAMILY_MAX+1][32] = {
+	static const u8 revid_table[NVDIMM_FAMILY_MAX+1][NVDIMM_CMD_MAX+1] = {
 		[NVDIMM_FAMILY_INTEL] = {
 			[NVDIMM_INTEL_GET_MODES] = 2,
 			[NVDIMM_INTEL_GET_FWINFO] = 2,
@@ -386,7 +386,7 @@ static u8 nfit_dsm_revid(unsigned family, unsigned func)
 
 	if (family > NVDIMM_FAMILY_MAX)
 		return 0;
-	if (func > 31)
+	if (func > NVDIMM_CMD_MAX)
 		return 0;
 	id = revid_table[family][func];
 	if (id == 0)
@@ -492,7 +492,8 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 	 * Check for a valid command.  For ND_CMD_CALL, we also have to
 	 * make sure that the DSM function is supported.
 	 */
-	if (cmd == ND_CMD_CALL && !test_bit(func, &dsm_mask))
+	if (cmd == ND_CMD_CALL &&
+	    (func > NVDIMM_CMD_MAX || !test_bit(func, &dsm_mask)))
 		return -ENOTTY;
 	else if (!test_bit(cmd, &cmd_mask))
 		return -ENOTTY;
@@ -3499,7 +3500,8 @@ static int acpi_nfit_clear_to_send(struct nvdimm_bus_descriptor *nd_desc,
 	if (nvdimm && cmd == ND_CMD_CALL &&
 			call_pkg->nd_family == NVDIMM_FAMILY_INTEL) {
 		func = call_pkg->nd_command;
-		if ((1 << func) & NVDIMM_INTEL_SECURITY_CMDMASK)
+		if (func > NVDIMM_CMD_MAX ||
+		    (1 << func) & NVDIMM_INTEL_SECURITY_CMDMASK)
 			return -EOPNOTSUPP;
 	}
 
diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h
index 6ee2b02af73e..d99eab327df2 100644
--- a/drivers/acpi/nfit/nfit.h
+++ b/drivers/acpi/nfit/nfit.h
@@ -34,6 +34,7 @@
 		| ACPI_NFIT_MEM_NOT_ARMED | ACPI_NFIT_MEM_MAP_FAILED)
 
 #define NVDIMM_FAMILY_MAX NVDIMM_FAMILY_HYPERV
+#define NVDIMM_CMD_MAX 31
 
 #define NVDIMM_STANDARD_CMDMASK \
 (1 << ND_CMD_SMART | 1 << ND_CMD_SMART_THRESHOLD | 1 << ND_CMD_DIMM_FLAGS \
diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c
index 532a1ae3595a..a0bd56ece3ff 100644
--- a/drivers/acpi/processor_throttling.c
+++ b/drivers/acpi/processor_throttling.c
@@ -897,13 +897,6 @@ static long __acpi_processor_get_throttling(void *data)
 	return pr->throttling.acpi_processor_get_throttling(pr);
 }
 
-static int call_on_cpu(int cpu, long (*fn)(void *), void *arg, bool direct)
-{
-	if (direct || (is_percpu_thread() && cpu == smp_processor_id()))
-		return fn(arg);
-	return work_on_cpu(cpu, fn, arg);
-}
-
 static int acpi_processor_get_throttling(struct acpi_processor *pr)
 {
 	if (!pr)
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 0e28270b0fd8..d8c0193744cd 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -919,12 +919,9 @@ static void acpi_bus_init_power_state(struct acpi_device *device, int state)
 
 		if (buffer.length && package
 		    && package->type == ACPI_TYPE_PACKAGE
-		    && package->package.count) {
-			int err = acpi_extract_power_resources(package, 0,
-							       &ps->resources);
-			if (!err)
-				device->power.flags.power_resources = 1;
-		}
+		    && package->package.count)
+			acpi_extract_power_resources(package, 0, &ps->resources);
+
 		ACPI_FREE(buffer.pointer);
 	}
 
@@ -971,14 +968,27 @@ static void acpi_bus_get_power_flags(struct acpi_device *device)
 		acpi_bus_init_power_state(device, i);
 
 	INIT_LIST_HEAD(&device->power.states[ACPI_STATE_D3_COLD].resources);
-	if (!list_empty(&device->power.states[ACPI_STATE_D3_HOT].resources))
-		device->power.states[ACPI_STATE_D3_COLD].flags.valid = 1;
 
-	/* Set defaults for D0 and D3hot states (always valid) */
+	/* Set the defaults for D0 and D3hot (always supported). */
 	device->power.states[ACPI_STATE_D0].flags.valid = 1;
 	device->power.states[ACPI_STATE_D0].power = 100;
 	device->power.states[ACPI_STATE_D3_HOT].flags.valid = 1;
 
+	/*
+	 * Use power resources only if the D0 list of them is populated, because
+	 * some platforms may provide _PR3 only to indicate D3cold support and
+	 * in those cases the power resources list returned by it may be bogus.
+	 */
+	if (!list_empty(&device->power.states[ACPI_STATE_D0].resources)) {
+		device->power.flags.power_resources = 1;
+		/*
+		 * D3cold is supported if the D3hot list of power resources is
+		 * not empty.
+		 */
+		if (!list_empty(&device->power.states[ACPI_STATE_D3_HOT].resources))
+			device->power.states[ACPI_STATE_D3_COLD].flags.valid = 1;
+	}
+
 	if (acpi_bus_init_power(device))
 		device->flags.power_manageable = 0;
 }
diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c
index 75948a3f1a20..76c668c05fa0 100644
--- a/drivers/acpi/sysfs.c
+++ b/drivers/acpi/sysfs.c
@@ -819,14 +819,14 @@ end:
  * interface:
  *   echo unmask > /sys/firmware/acpi/interrupts/gpe00
  */
-#define ACPI_MASKABLE_GPE_MAX	0xFF
+#define ACPI_MASKABLE_GPE_MAX	0x100
 static DECLARE_BITMAP(acpi_masked_gpes_map, ACPI_MASKABLE_GPE_MAX) __initdata;
 
 static int __init acpi_gpe_set_masked_gpes(char *val)
 {
 	u8 gpe;
 
-	if (kstrtou8(val, 0, &gpe) || gpe > ACPI_MASKABLE_GPE_MAX)
+	if (kstrtou8(val, 0, &gpe))
 		return -EINVAL;
 	set_bit(gpe, acpi_masked_gpes_map);
 
@@ -838,7 +838,7 @@ void __init acpi_gpe_apply_masked_gpes(void)
 {
 	acpi_handle handle;
 	acpi_status status;
-	u8 gpe;
+	u16 gpe;
 
 	for_each_set_bit(gpe, acpi_masked_gpes_map, ACPI_MASKABLE_GPE_MAX) {
 		status = acpi_get_gpe_device(gpe, &handle);
@@ -938,13 +938,13 @@ static void __exit interrupt_stats_exit(void)
 }
 
 static ssize_t
-acpi_show_profile(struct device *dev, struct device_attribute *attr,
+acpi_show_profile(struct kobject *kobj, struct kobj_attribute *attr,
 		  char *buf)
 {
 	return sprintf(buf, "%d\n", acpi_gbl_FADT.preferred_profile);
 }
 
-static const struct device_attribute pm_profile_attr =
+static const struct kobj_attribute pm_profile_attr =
 	__ATTR(pm_profile, S_IRUGO, acpi_show_profile, NULL);
 
 static ssize_t hotplug_enabled_show(struct kobject *kobj,
@@ -993,8 +993,10 @@ void acpi_sysfs_add_hotplug_profile(struct acpi_hotplug_profile *hotplug,
 
 	error = kobject_init_and_add(&hotplug->kobj,
 		&acpi_hotplug_profile_ktype, hotplug_kobj, "%s", name);
-	if (error)
+	if (error) {
+		kobject_put(&hotplug->kobj);
 		goto err_out;
+	}
 
 	kobject_uevent(&hotplug->kobj, KOBJ_ADD);
 	return;
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index 31014c7d3793..5bcb4c01ec5f 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -337,6 +337,30 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
 		},
 	},
 	{
+	 .callback = video_detect_force_native,
+	 .ident = "Acer Aspire 5738z",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5738"),
+		DMI_MATCH(DMI_BOARD_NAME, "JV50"),
+		},
+	},
+	{
+	 /* https://bugzilla.kernel.org/show_bug.cgi?id=207835 */
+	 .callback = video_detect_force_native,
+	 .ident = "Acer TravelMate 5735Z",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 5735Z"),
+		DMI_MATCH(DMI_BOARD_NAME, "BA51_MV"),
+		},
+	},
+
+	/*
+	 * Desktops which falsely report a backlight and which our heuristics
+	 * for this do not catch.
+	 */
+	{
 	 .callback = video_detect_force_none,
 	 .ident = "Dell OptiPlex 9020M",
 	 .matches = {
@@ -344,6 +368,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 9020M"),
 		},
 	},
+	{
+	 .callback = video_detect_force_none,
+	 .ident = "MSI MS-7721",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "MSI"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "MS-7721"),
+		},
+	},
 	{ },
 };
 
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index dbc6aacd07a3..4fe23f28514e 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -3002,6 +3002,12 @@ static void binder_transaction(struct binder_proc *proc,
 			goto err_dead_binder;
 		}
 		e->to_node = target_node->debug_id;
+		if (WARN_ON(proc == target_proc)) {
+			return_error = BR_FAILED_REPLY;
+			return_error_param = -EINVAL;
+			return_error_line = __LINE__;
+			goto err_invalid_target_handle;
+		}
 		if (security_binder_transaction(proc->tsk,
 						target_proc->tsk) < 0) {
 			return_error = BR_FAILED_REPLY;
@@ -3655,10 +3661,17 @@ static int binder_thread_write(struct binder_proc *proc,
 				struct binder_node *ctx_mgr_node;
 				mutex_lock(&context->context_mgr_node_lock);
 				ctx_mgr_node = context->binder_context_mgr_node;
-				if (ctx_mgr_node)
+				if (ctx_mgr_node) {
+					if (ctx_mgr_node->proc == proc) {
+						binder_user_error("%d:%d context manager tried to acquire desc 0\n",
+								  proc->pid, thread->pid);
+						mutex_unlock(&context->context_mgr_node_lock);
+						return -EINVAL;
+					}
 					ret = binder_inc_ref_for_node(
 							proc, ctx_mgr_node,
 							strong, NULL, &rdata);
+				}
 				mutex_unlock(&context->context_mgr_node_lock);
 			}
 			if (ret)
@@ -4706,8 +4719,15 @@ static struct binder_thread *binder_get_thread(struct binder_proc *proc)
 
 static void binder_free_proc(struct binder_proc *proc)
 {
+	struct binder_device *device;
+
 	BUG_ON(!list_empty(&proc->todo));
 	BUG_ON(!list_empty(&proc->delivered_death));
+	device = container_of(proc->context, struct binder_device, context);
+	if (refcount_dec_and_test(&device->ref)) {
+		kfree(proc->context->name);
+		kfree(device);
+	}
 	binder_alloc_deferred_release(&proc->alloc);
 	put_task_struct(proc->tsk);
 	binder_stats_deleted(BINDER_STAT_PROC);
@@ -5242,6 +5262,7 @@ static int binder_open(struct inode *nodp, struct file *filp)
 	else
 		binder_dev = container_of(filp->private_data,
 					  struct binder_device, miscdev);
+	refcount_inc(&binder_dev->ref);
 	proc->context = &binder_dev->context;
 	binder_alloc_init(&proc->alloc);
 
@@ -6061,6 +6082,7 @@ static int __init init_binder_device(const char *name)
 	binder_device->miscdev.minor = MISC_DYNAMIC_MINOR;
 	binder_device->miscdev.name = name;
 
+	refcount_set(&binder_device->ref, 1);
 	binder_device->context.binder_context_mgr_uid = INVALID_UID;
 	binder_device->context.name = name;
 	mutex_init(&binder_device->context.context_mgr_node_lock);
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index bb0a732cd98a..f8953fcbcc0e 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -948,7 +948,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
 		trace_binder_unmap_user_end(alloc, index);
 	}
 	up_read(&mm->mmap_sem);
-	mmput(mm);
+	mmput_async(mm);
 
 	trace_binder_unmap_kernel_start(alloc, index);
 
diff --git a/drivers/android/binder_internal.h b/drivers/android/binder_internal.h
index 045b3e42d98b..31da3d935039 100644
--- a/drivers/android/binder_internal.h
+++ b/drivers/android/binder_internal.h
@@ -8,6 +8,7 @@
 #include <linux/list.h>
 #include <linux/miscdevice.h>
 #include <linux/mutex.h>
+#include <linux/refcount.h>
 #include <linux/stddef.h>
 #include <linux/types.h>
 #include <linux/uidgid.h>
@@ -33,6 +34,7 @@ struct binder_device {
 	struct miscdevice miscdev;
 	struct binder_context context;
 	struct inode *binderfs_inode;
+	refcount_t ref;
 };
 
 extern const struct file_operations binder_fops;
diff --git a/drivers/android/binderfs.c b/drivers/android/binderfs.c
index e773f45d19d9..67982cabe068 100644
--- a/drivers/android/binderfs.c
+++ b/drivers/android/binderfs.c
@@ -176,6 +176,7 @@ static int binderfs_binder_device_create(struct inode *ref_inode,
 	if (!name)
 		goto err;
 
+	refcount_set(&device->ref, 1);
 	device->binderfs_inode = inode;
 	device->context.binder_context_mgr_uid = INVALID_UID;
 	device->context.name = name;
@@ -280,8 +281,10 @@ static void binderfs_evict_inode(struct inode *inode)
 	ida_free(&binderfs_minors, device->miscdev.minor);
 	mutex_unlock(&binderfs_minors_mutex);
 
-	kfree(device->context.name);
-	kfree(device);
+	if (refcount_dec_and_test(&device->ref)) {
+		kfree(device->context.name);
+		kfree(device);
+	}
 }
 
 /**
@@ -436,6 +439,7 @@ static int binderfs_binder_ctl_create(struct super_block *sb)
 	inode->i_uid = info->root_uid;
 	inode->i_gid = info->root_gid;
 
+	refcount_set(&device->ref, 1);
 	device->binderfs_inode = inode;
 	device->miscdev.minor = minor;
 
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 691852b8bb41..c6cf0ba16c82 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -80,6 +80,7 @@ enum board_ids {
 
 static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
 static void ahci_remove_one(struct pci_dev *dev);
+static void ahci_shutdown_one(struct pci_dev *dev);
 static int ahci_vt8251_hardreset(struct ata_link *link, unsigned int *class,
 				 unsigned long deadline);
 static int ahci_avn_hardreset(struct ata_link *link, unsigned int *class,
@@ -392,6 +393,7 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, 0xa252), board_ahci }, /* Lewisburg RAID*/
 	{ PCI_VDEVICE(INTEL, 0xa256), board_ahci }, /* Lewisburg RAID*/
 	{ PCI_VDEVICE(INTEL, 0xa356), board_ahci }, /* Cannon Lake PCH-H RAID */
+	{ PCI_VDEVICE(INTEL, 0x06d7), board_ahci }, /* Comet Lake-H RAID */
 	{ PCI_VDEVICE(INTEL, 0x0f22), board_ahci_mobile }, /* Bay Trail AHCI */
 	{ PCI_VDEVICE(INTEL, 0x0f23), board_ahci_mobile }, /* Bay Trail AHCI */
 	{ PCI_VDEVICE(INTEL, 0x22a3), board_ahci_mobile }, /* Cherry Tr. AHCI */
@@ -593,6 +595,7 @@ static struct pci_driver ahci_pci_driver = {
 	.id_table		= ahci_pci_tbl,
 	.probe			= ahci_init_one,
 	.remove			= ahci_remove_one,
+	.shutdown		= ahci_shutdown_one,
 	.driver = {
 		.pm		= &ahci_pci_pm_ops,
 	},
@@ -1881,6 +1884,11 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	return 0;
 }
 
+static void ahci_shutdown_one(struct pci_dev *pdev)
+{
+	ata_pci_shutdown_one(pdev);
+}
+
 static void ahci_remove_one(struct pci_dev *pdev)
 {
 	pm_runtime_get_noresume(&pdev->dev);
diff --git a/drivers/ata/ahci_brcm.c b/drivers/ata/ahci_brcm.c
index f41744b9b38a..66a570d0da83 100644
--- a/drivers/ata/ahci_brcm.c
+++ b/drivers/ata/ahci_brcm.c
@@ -76,8 +76,7 @@ enum brcm_ahci_version {
 };
 
 enum brcm_ahci_quirks {
-	BRCM_AHCI_QUIRK_NO_NCQ		= BIT(0),
-	BRCM_AHCI_QUIRK_SKIP_PHY_ENABLE	= BIT(1),
+	BRCM_AHCI_QUIRK_SKIP_PHY_ENABLE	= BIT(0),
 };
 
 struct brcm_ahci_priv {
@@ -213,19 +212,12 @@ static void brcm_sata_phys_disable(struct brcm_ahci_priv *priv)
 			brcm_sata_phy_disable(priv, i);
 }
 
-static u32 brcm_ahci_get_portmask(struct platform_device *pdev,
+static u32 brcm_ahci_get_portmask(struct ahci_host_priv *hpriv,
 				  struct brcm_ahci_priv *priv)
 {
-	void __iomem *ahci;
-	struct resource *res;
 	u32 impl;
 
-	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "ahci");
-	ahci = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(ahci))
-		return 0;
-
-	impl = readl(ahci + HOST_PORTS_IMPL);
+	impl = readl(hpriv->mmio + HOST_PORTS_IMPL);
 
 	if (fls(impl) > SATA_TOP_MAX_PHYS)
 		dev_warn(priv->dev, "warning: more ports than PHYs (%#x)\n",
@@ -233,9 +225,6 @@ static u32 brcm_ahci_get_portmask(struct platform_device *pdev,
 	else if (!impl)
 		dev_info(priv->dev, "no ports found\n");
 
-	devm_iounmap(&pdev->dev, ahci);
-	devm_release_mem_region(&pdev->dev, res->start, resource_size(res));
-
 	return impl;
 }
 
@@ -285,6 +274,13 @@ static unsigned int brcm_ahci_read_id(struct ata_device *dev,
 	/* Perform the SATA PHY reset sequence */
 	brcm_sata_phy_disable(priv, ap->port_no);
 
+	/* Reset the SATA clock */
+	ahci_platform_disable_clks(hpriv);
+	msleep(10);
+
+	ahci_platform_enable_clks(hpriv);
+	msleep(10);
+
 	/* Bring the PHY back on */
 	brcm_sata_phy_enable(priv, ap->port_no);
 
@@ -347,11 +343,10 @@ static int brcm_ahci_suspend(struct device *dev)
 	struct ata_host *host = dev_get_drvdata(dev);
 	struct ahci_host_priv *hpriv = host->private_data;
 	struct brcm_ahci_priv *priv = hpriv->plat_data;
-	int ret;
 
-	ret = ahci_platform_suspend(dev);
 	brcm_sata_phys_disable(priv);
-	return ret;
+
+	return ahci_platform_suspend(dev);
 }
 
 static int brcm_ahci_resume(struct device *dev)
@@ -359,11 +354,44 @@ static int brcm_ahci_resume(struct device *dev)
 	struct ata_host *host = dev_get_drvdata(dev);
 	struct ahci_host_priv *hpriv = host->private_data;
 	struct brcm_ahci_priv *priv = hpriv->plat_data;
+	int ret;
+
+	/* Make sure clocks are turned on before re-configuration */
+	ret = ahci_platform_enable_clks(hpriv);
+	if (ret)
+		return ret;
 
 	brcm_sata_init(priv);
 	brcm_sata_phys_enable(priv);
 	brcm_sata_alpm_init(hpriv);
-	return ahci_platform_resume(dev);
+
+	/* Since we had to enable clocks earlier on, we cannot use
+	 * ahci_platform_resume() as-is since a second call to
+	 * ahci_platform_enable_resources() would bump up the resources
+	 * (regulators, clocks, PHYs) count artificially so we copy the part
+	 * after ahci_platform_enable_resources().
+	 */
+	ret = ahci_platform_enable_phys(hpriv);
+	if (ret)
+		goto out_disable_phys;
+
+	ret = ahci_platform_resume_host(dev);
+	if (ret)
+		goto out_disable_platform_phys;
+
+	/* We resumed so update PM runtime state */
+	pm_runtime_disable(dev);
+	pm_runtime_set_active(dev);
+	pm_runtime_enable(dev);
+
+	return 0;
+
+out_disable_platform_phys:
+	ahci_platform_disable_phys(hpriv);
+out_disable_phys:
+	brcm_sata_phys_disable(priv);
+	ahci_platform_disable_clks(hpriv);
+	return ret;
 }
 #endif
 
@@ -410,44 +438,71 @@ static int brcm_ahci_probe(struct platform_device *pdev)
 	if (!IS_ERR_OR_NULL(priv->rcdev))
 		reset_control_deassert(priv->rcdev);
 
-	if ((priv->version == BRCM_SATA_BCM7425) ||
-		(priv->version == BRCM_SATA_NSP)) {
-		priv->quirks |= BRCM_AHCI_QUIRK_NO_NCQ;
+	hpriv = ahci_platform_get_resources(pdev, 0);
+	if (IS_ERR(hpriv)) {
+		ret = PTR_ERR(hpriv);
+		goto out_reset;
+	}
+
+	hpriv->plat_data = priv;
+	hpriv->flags = AHCI_HFLAG_WAKE_BEFORE_STOP | AHCI_HFLAG_NO_WRITE_TO_RO;
+
+	switch (priv->version) {
+	case BRCM_SATA_BCM7425:
+		hpriv->flags |= AHCI_HFLAG_DELAY_ENGINE;
+		/* fall through */
+	case BRCM_SATA_NSP:
+		hpriv->flags |= AHCI_HFLAG_NO_NCQ;
 		priv->quirks |= BRCM_AHCI_QUIRK_SKIP_PHY_ENABLE;
+		break;
+	default:
+		break;
 	}
 
+	ret = ahci_platform_enable_clks(hpriv);
+	if (ret)
+		goto out_reset;
+
+	/* Must be first so as to configure endianness including that
+	 * of the standard AHCI register space.
+	 */
 	brcm_sata_init(priv);
 
-	priv->port_mask = brcm_ahci_get_portmask(pdev, priv);
-	if (!priv->port_mask)
-		return -ENODEV;
+	/* Initializes priv->port_mask which is used below */
+	priv->port_mask = brcm_ahci_get_portmask(hpriv, priv);
+	if (!priv->port_mask) {
+		ret = -ENODEV;
+		goto out_disable_clks;
+	}
 
+	/* Must be done before ahci_platform_enable_phys() */
 	brcm_sata_phys_enable(priv);
 
-	hpriv = ahci_platform_get_resources(pdev, 0);
-	if (IS_ERR(hpriv))
-		return PTR_ERR(hpriv);
-	hpriv->plat_data = priv;
-	hpriv->flags = AHCI_HFLAG_WAKE_BEFORE_STOP;
-
 	brcm_sata_alpm_init(hpriv);
 
-	ret = ahci_platform_enable_resources(hpriv);
+	ret = ahci_platform_enable_phys(hpriv);
 	if (ret)
-		return ret;
-
-	if (priv->quirks & BRCM_AHCI_QUIRK_NO_NCQ)
-		hpriv->flags |= AHCI_HFLAG_NO_NCQ;
-	hpriv->flags |= AHCI_HFLAG_NO_WRITE_TO_RO;
+		goto out_disable_phys;
 
 	ret = ahci_platform_init_host(pdev, hpriv, &ahci_brcm_port_info,
 				      &ahci_platform_sht);
 	if (ret)
-		return ret;
+		goto out_disable_platform_phys;
 
 	dev_info(dev, "Broadcom AHCI SATA3 registered\n");
 
 	return 0;
+
+out_disable_platform_phys:
+	ahci_platform_disable_phys(hpriv);
+out_disable_phys:
+	brcm_sata_phys_disable(priv);
+out_disable_clks:
+	ahci_platform_disable_clks(hpriv);
+out_reset:
+	if (!IS_ERR_OR_NULL(priv->rcdev))
+		reset_control_assert(priv->rcdev);
+	return ret;
 }
 
 static int brcm_ahci_remove(struct platform_device *pdev)
@@ -457,12 +512,12 @@ static int brcm_ahci_remove(struct platform_device *pdev)
 	struct brcm_ahci_priv *priv = hpriv->plat_data;
 	int ret;
 
+	brcm_sata_phys_disable(priv);
+
 	ret = ata_platform_remove_one(pdev);
 	if (ret)
 		return ret;
 
-	brcm_sata_phys_disable(priv);
-
 	return 0;
 }
 
diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c
index c25cdbf817f1..2cb16817e540 100644
--- a/drivers/ata/libahci_platform.c
+++ b/drivers/ata/libahci_platform.c
@@ -43,7 +43,7 @@ EXPORT_SYMBOL_GPL(ahci_platform_ops);
  * RETURNS:
  * 0 on success otherwise a negative error code
  */
-static int ahci_platform_enable_phys(struct ahci_host_priv *hpriv)
+int ahci_platform_enable_phys(struct ahci_host_priv *hpriv)
 {
 	int rc, i;
 
@@ -74,6 +74,7 @@ disable_phys:
 	}
 	return rc;
 }
+EXPORT_SYMBOL_GPL(ahci_platform_enable_phys);
 
 /**
  * ahci_platform_disable_phys - Disable PHYs
@@ -81,7 +82,7 @@ disable_phys:
  *
  * This function disables all PHYs found in hpriv->phys.
  */
-static void ahci_platform_disable_phys(struct ahci_host_priv *hpriv)
+void ahci_platform_disable_phys(struct ahci_host_priv *hpriv)
 {
 	int i;
 
@@ -90,6 +91,7 @@ static void ahci_platform_disable_phys(struct ahci_host_priv *hpriv)
 		phy_exit(hpriv->phys[i]);
 	}
 }
+EXPORT_SYMBOL_GPL(ahci_platform_disable_phys);
 
 /**
  * ahci_platform_enable_clks - Enable platform clocks
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 119ab0fd3f82..8a7d117a03b9 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -41,7 +41,6 @@
 #include <linux/workqueue.h>
 #include <linux/scatterlist.h>
 #include <linux/io.h>
-#include <linux/async.h>
 #include <linux/log2.h>
 #include <linux/slab.h>
 #include <linux/glob.h>
@@ -5328,6 +5327,30 @@ void ata_qc_complete(struct ata_queued_cmd *qc)
 }
 
 /**
+ *	ata_qc_get_active - get bitmask of active qcs
+ *	@ap: port in question
+ *
+ *	LOCKING:
+ *	spin_lock_irqsave(host lock)
+ *
+ *	RETURNS:
+ *	Bitmask of active qcs
+ */
+u64 ata_qc_get_active(struct ata_port *ap)
+{
+	u64 qc_active = ap->qc_active;
+
+	/* ATA_TAG_INTERNAL is sent to hw as tag 0 */
+	if (qc_active & (1ULL << ATA_TAG_INTERNAL)) {
+		qc_active |= (1 << 0);
+		qc_active &= ~(1ULL << ATA_TAG_INTERNAL);
+	}
+
+	return qc_active;
+}
+EXPORT_SYMBOL_GPL(ata_qc_get_active);
+
+/**
  *	ata_qc_complete_multiple - Complete multiple qcs successfully
  *	@ap: port in question
  *	@qc_active: new qc_active mask
@@ -6570,7 +6593,7 @@ int ata_host_register(struct ata_host *host, struct scsi_host_template *sht)
 	/* perform each probe asynchronously */
 	for (i = 0; i < host->n_ports; i++) {
 		struct ata_port *ap = host->ports[i];
-		async_schedule(async_port_probe, ap);
+		ap->cookie = async_schedule(async_port_probe, ap);
 	}
 
 	return 0;
@@ -6710,11 +6733,11 @@ void ata_host_detach(struct ata_host *host)
 {
 	int i;
 
-	/* Ensure ata_port probe has completed */
-	async_synchronize_full();
-
-	for (i = 0; i < host->n_ports; i++)
+	for (i = 0; i < host->n_ports; i++) {
+		/* Ensure ata_port probe has completed */
+		async_synchronize_cookie(host->ports[i]->cookie + 1);
 		ata_port_detach(host->ports[i]);
+	}
 
 	/* the host is dead now, dissociate ACPI */
 	ata_acpi_dissociate(host);
@@ -6740,6 +6763,26 @@ void ata_pci_remove_one(struct pci_dev *pdev)
 	ata_host_detach(host);
 }
 
+void ata_pci_shutdown_one(struct pci_dev *pdev)
+{
+	struct ata_host *host = pci_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < host->n_ports; i++) {
+		struct ata_port *ap = host->ports[i];
+
+		ap->pflags |= ATA_PFLAG_FROZEN;
+
+		/* Disable port interrupts */
+		if (ap->ops->freeze)
+			ap->ops->freeze(ap);
+
+		/* Stop the port DMA engines */
+		if (ap->ops->port_stop)
+			ap->ops->port_stop(ap);
+	}
+}
+
 /* move to PCI subsystem */
 int pci_test_config_bits(struct pci_dev *pdev, const struct pci_bits *bits)
 {
@@ -7360,6 +7403,7 @@ EXPORT_SYMBOL_GPL(ata_timing_cycle2mode);
 
 #ifdef CONFIG_PCI
 EXPORT_SYMBOL_GPL(pci_test_config_bits);
+EXPORT_SYMBOL_GPL(ata_pci_shutdown_one);
 EXPORT_SYMBOL_GPL(ata_pci_remove_one);
 #ifdef CONFIG_PM
 EXPORT_SYMBOL_GPL(ata_pci_device_do_suspend);
diff --git a/drivers/ata/libata-pmp.c b/drivers/ata/libata-pmp.c
index 3ff14071617c..79f2aeeb482a 100644
--- a/drivers/ata/libata-pmp.c
+++ b/drivers/ata/libata-pmp.c
@@ -763,6 +763,7 @@ static int sata_pmp_eh_recover_pmp(struct ata_port *ap,
 
 	if (dev->flags & ATA_DFLAG_DETACH) {
 		detach = 1;
+		rc = -ENODEV;
 		goto fail;
 	}
 
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 76d0f9de767b..d3ba0fb0b5b7 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -3978,12 +3978,13 @@ static unsigned int ata_scsi_mode_select_xlat(struct ata_queued_cmd *qc)
 {
 	struct scsi_cmnd *scmd = qc->scsicmd;
 	const u8 *cdb = scmd->cmnd;
-	const u8 *p;
 	u8 pg, spg;
 	unsigned six_byte, pg_len, hdr_len, bd_len;
 	int len;
 	u16 fp = (u16)-1;
 	u8 bp = 0xff;
+	u8 buffer[64];
+	const u8 *p = buffer;
 
 	VPRINTK("ENTER\n");
 
@@ -4017,12 +4018,14 @@ static unsigned int ata_scsi_mode_select_xlat(struct ata_queued_cmd *qc)
 	if (!scsi_sg_count(scmd) || scsi_sglist(scmd)->length < len)
 		goto invalid_param_len;
 
-	p = page_address(sg_page(scsi_sglist(scmd)));
-
 	/* Move past header and block descriptors.  */
 	if (len < hdr_len)
 		goto invalid_param_len;
 
+	if (!sg_copy_to_buffer(scsi_sglist(scmd), scsi_sg_count(scmd),
+			       buffer, sizeof(buffer)))
+		goto invalid_param_len;
+
 	if (six_byte)
 		bd_len = p[3];
 	else
@@ -4553,22 +4556,19 @@ int ata_scsi_add_hosts(struct ata_host *host, struct scsi_host_template *sht)
 		 */
 		shost->max_host_blocked = 1;
 
-		rc = scsi_add_host_with_dma(ap->scsi_host,
-						&ap->tdev, ap->host->dev);
+		rc = scsi_add_host_with_dma(shost, &ap->tdev, ap->host->dev);
 		if (rc)
-			goto err_add;
+			goto err_alloc;
 	}
 
 	return 0;
 
- err_add:
-	scsi_host_put(host->ports[i]->scsi_host);
  err_alloc:
 	while (--i >= 0) {
 		struct Scsi_Host *shost = host->ports[i]->scsi_host;
 
+		/* scsi_host_put() is in ata_devres_release() */
 		scsi_remove_host(shost);
-		scsi_host_put(shost);
 	}
 	return rc;
 }
diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c
index 8e9cb198fcd1..ca6c706e9c25 100644
--- a/drivers/ata/sata_fsl.c
+++ b/drivers/ata/sata_fsl.c
@@ -1278,7 +1278,7 @@ static void sata_fsl_host_intr(struct ata_port *ap)
 				     i, ioread32(hcr_base + CC),
 				     ioread32(hcr_base + CA));
 		}
-		ata_qc_complete_multiple(ap, ap->qc_active ^ done_mask);
+		ata_qc_complete_multiple(ap, ata_qc_get_active(ap) ^ done_mask);
 		return;
 
 	} else if ((ap->qc_active & (1ULL << ATA_TAG_INTERNAL))) {
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index da585d2bded6..ca5634cb9c78 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -2827,7 +2827,7 @@ static void mv_process_crpb_entries(struct ata_port *ap, struct mv_port_priv *pp
 	}
 
 	if (work_done) {
-		ata_qc_complete_multiple(ap, ap->qc_active ^ done_mask);
+		ata_qc_complete_multiple(ap, ata_qc_get_active(ap) ^ done_mask);
 
 		/* Update the software queue position index in hardware */
 		writelfl((pp->crpb_dma & EDMA_RSP_Q_BASE_LO_MASK) |
diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c
index 54bfab15c74a..fbd78cb57351 100644
--- a/drivers/ata/sata_nv.c
+++ b/drivers/ata/sata_nv.c
@@ -984,7 +984,7 @@ static irqreturn_t nv_adma_interrupt(int irq, void *dev_instance)
 					check_commands = 0;
 				check_commands &= ~(1 << pos);
 			}
-			ata_qc_complete_multiple(ap, ap->qc_active ^ done_mask);
+			ata_qc_complete_multiple(ap, ata_qc_get_active(ap) ^ done_mask);
 		}
 	}
 
diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c
index 3495e1733a8e..c35b7b993133 100644
--- a/drivers/ata/sata_rcar.c
+++ b/drivers/ata/sata_rcar.c
@@ -905,7 +905,7 @@ static int sata_rcar_probe(struct platform_device *pdev)
 	pm_runtime_enable(dev);
 	ret = pm_runtime_get_sync(dev);
 	if (ret < 0)
-		goto err_pm_disable;
+		goto err_pm_put;
 
 	host = ata_host_alloc(dev, 1);
 	if (!host) {
@@ -935,7 +935,6 @@ static int sata_rcar_probe(struct platform_device *pdev)
 
 err_pm_put:
 	pm_runtime_put(dev);
-err_pm_disable:
 	pm_runtime_disable(dev);
 	return ret;
 }
@@ -989,8 +988,10 @@ static int sata_rcar_resume(struct device *dev)
 	int ret;
 
 	ret = pm_runtime_get_sync(dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put(dev);
 		return ret;
+	}
 
 	if (priv->type == RCAR_GEN3_SATA) {
 		sata_rcar_init_module(priv);
@@ -1015,8 +1016,10 @@ static int sata_rcar_restore(struct device *dev)
 	int ret;
 
 	ret = pm_runtime_get_sync(dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put(dev);
 		return ret;
+	}
 
 	sata_rcar_setup_port(host);
 
diff --git a/drivers/atm/atmtcp.c b/drivers/atm/atmtcp.c
index d9fd70280482..7f814da3c2d0 100644
--- a/drivers/atm/atmtcp.c
+++ b/drivers/atm/atmtcp.c
@@ -433,9 +433,15 @@ static int atmtcp_remove_persistent(int itf)
 		return -EMEDIUMTYPE;
 	}
 	dev_data = PRIV(dev);
-	if (!dev_data->persist) return 0;
+	if (!dev_data->persist) {
+		atm_dev_put(dev);
+		return 0;
+	}
 	dev_data->persist = 0;
-	if (PRIV(dev)->vcc) return 0;
+	if (PRIV(dev)->vcc) {
+		atm_dev_put(dev);
+		return 0;
+	}
 	kfree(dev_data);
 	atm_dev_put(dev);
 	atm_dev_deregister(dev);
diff --git a/drivers/atm/eni.c b/drivers/atm/eni.c
index 79b718430cd1..d3067d8ea91b 100644
--- a/drivers/atm/eni.c
+++ b/drivers/atm/eni.c
@@ -374,7 +374,7 @@ static int do_rx_dma(struct atm_vcc *vcc,struct sk_buff *skb,
 		here = (eni_vcc->descr+skip) & (eni_vcc->words-1);
 		dma[j++] = (here << MID_DMA_COUNT_SHIFT) | (vcc->vci
 		    << MID_DMA_VCI_SHIFT) | MID_DT_JK;
-		j++;
+		dma[j++] = 0;
 	}
 	here = (eni_vcc->descr+size+skip) & (eni_vcc->words-1);
 	if (!eff) size += skip;
@@ -447,7 +447,7 @@ static int do_rx_dma(struct atm_vcc *vcc,struct sk_buff *skb,
 	if (size != eff) {
 		dma[j++] = (here << MID_DMA_COUNT_SHIFT) |
 		    (vcc->vci << MID_DMA_VCI_SHIFT) | MID_DT_JK;
-		j++;
+		dma[j++] = 0;
 	}
 	if (!j || j > 2*RX_DMA_BUF) {
 		printk(KERN_CRIT DEV_LABEL "!j or j too big!!!\n");
diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c
index 2bbab0230aeb..d287837ed755 100644
--- a/drivers/atm/firestream.c
+++ b/drivers/atm/firestream.c
@@ -912,6 +912,7 @@ static int fs_open(struct atm_vcc *atm_vcc)
 			}
 			if (!to) {
 				printk ("No more free channels for FS50..\n");
+				kfree(vcc);
 				return -EBUSY;
 			}
 			vcc->channo = dev->channo;
@@ -922,6 +923,7 @@ static int fs_open(struct atm_vcc *atm_vcc)
 			if (((DO_DIRECTION(rxtp) && dev->atm_vccs[vcc->channo])) ||
 			    ( DO_DIRECTION(txtp) && test_bit (vcc->channo, dev->tx_inuse))) {
 				printk ("Channel is in use for FS155.\n");
+				kfree(vcc);
 				return -EBUSY;
 			}
 		}
@@ -935,6 +937,7 @@ static int fs_open(struct atm_vcc *atm_vcc)
 			    tc, sizeof (struct fs_transmit_config));
 		if (!tc) {
 			fs_dprintk (FS_DEBUG_OPEN, "fs: can't alloc transmit_config.\n");
+			kfree(vcc);
 			return -ENOMEM;
 		}
 
diff --git a/drivers/atm/fore200e.c b/drivers/atm/fore200e.c
index f1a500205313..8fbd36eb8941 100644
--- a/drivers/atm/fore200e.c
+++ b/drivers/atm/fore200e.c
@@ -1414,12 +1414,14 @@ fore200e_open(struct atm_vcc *vcc)
 static void
 fore200e_close(struct atm_vcc* vcc)
 {
-    struct fore200e*        fore200e = FORE200E_DEV(vcc->dev);
     struct fore200e_vcc*    fore200e_vcc;
+    struct fore200e*        fore200e;
     struct fore200e_vc_map* vc_map;
     unsigned long           flags;
 
     ASSERT(vcc);
+    fore200e = FORE200E_DEV(vcc->dev);
+
     ASSERT((vcc->vpi >= 0) && (vcc->vpi < 1<<FORE200E_VPI_BITS));
     ASSERT((vcc->vci >= 0) && (vcc->vci < 1<<FORE200E_VCI_BITS));
 
@@ -1464,10 +1466,10 @@ fore200e_close(struct atm_vcc* vcc)
 static int
 fore200e_send(struct atm_vcc *vcc, struct sk_buff *skb)
 {
-    struct fore200e*        fore200e     = FORE200E_DEV(vcc->dev);
-    struct fore200e_vcc*    fore200e_vcc = FORE200E_VCC(vcc);
+    struct fore200e*        fore200e;
+    struct fore200e_vcc*    fore200e_vcc;
     struct fore200e_vc_map* vc_map;
-    struct host_txq*        txq          = &fore200e->host_txq;
+    struct host_txq*        txq;
     struct host_txq_entry*  entry;
     struct tpd*             tpd;
     struct tpd_haddr        tpd_haddr;
@@ -1480,9 +1482,18 @@ fore200e_send(struct atm_vcc *vcc, struct sk_buff *skb)
     unsigned char*          data;
     unsigned long           flags;
 
-    ASSERT(vcc);
-    ASSERT(fore200e);
-    ASSERT(fore200e_vcc);
+    if (!vcc)
+        return -EINVAL;
+
+    fore200e = FORE200E_DEV(vcc->dev);
+    fore200e_vcc = FORE200E_VCC(vcc);
+
+    if (!fore200e)
+        return -EINVAL;
+
+    txq = &fore200e->host_txq;
+    if (!fore200e_vcc)
+        return -EINVAL;
 
     if (!test_bit(ATM_VF_READY, &vcc->flags)) {
 	DPRINTK(1, "VC %d.%d.%d not ready for tx\n", vcc->itf, vcc->vpi, vcc->vpi);
diff --git a/drivers/base/component.c b/drivers/base/component.c
index 532a3a5d8f63..b9f20ada68b0 100644
--- a/drivers/base/component.c
+++ b/drivers/base/component.c
@@ -102,11 +102,11 @@ static int component_devices_show(struct seq_file *s, void *data)
 	seq_printf(s, "%-40s %20s\n", "device name", "status");
 	seq_puts(s, "-------------------------------------------------------------\n");
 	for (i = 0; i < match->num; i++) {
-		struct device *d = (struct device *)match->compare[i].data;
+		struct component *component = match->compare[i].component;
 
-		seq_printf(s, "%-40s %20s\n", dev_name(d),
-			   match->compare[i].component ?
-			   "registered" : "not registered");
+		seq_printf(s, "%-40s %20s\n",
+			   component ? dev_name(component->dev) : "(unknown)",
+			   component ? (component->bound ? "bound" : "not bound") : "not registered");
 	}
 	mutex_unlock(&component_mutex);
 
@@ -257,7 +257,8 @@ static int try_to_bring_up_master(struct master *master,
 	ret = master->ops->bind(master->dev);
 	if (ret < 0) {
 		devres_release_group(master->dev, NULL);
-		dev_info(master->dev, "master bind failed: %d\n", ret);
+		if (ret != -EPROBE_DEFER)
+			dev_info(master->dev, "master bind failed: %d\n", ret);
 		return ret;
 	}
 
@@ -611,8 +612,9 @@ static int component_bind(struct component *component, struct master *master,
 		devres_release_group(component->dev, NULL);
 		devres_release_group(master->dev, NULL);
 
-		dev_err(master->dev, "failed to bind %s (ops %ps): %d\n",
-			dev_name(component->dev), component->ops, ret);
+		if (ret != -EPROBE_DEFER)
+			dev_err(master->dev, "failed to bind %s (ops %ps): %d\n",
+				dev_name(component->dev), component->ops, ret);
 	}
 
 	return ret;
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 6265871a4af2..f00da44ae6fe 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -567,6 +567,12 @@ ssize_t __weak cpu_show_itlb_multihit(struct device *dev,
 	return sprintf(buf, "Not affected\n");
 }
 
+ssize_t __weak cpu_show_srbds(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "Not affected\n");
+}
+
 static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
 static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
 static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL);
@@ -575,6 +581,7 @@ static DEVICE_ATTR(l1tf, 0444, cpu_show_l1tf, NULL);
 static DEVICE_ATTR(mds, 0444, cpu_show_mds, NULL);
 static DEVICE_ATTR(tsx_async_abort, 0444, cpu_show_tsx_async_abort, NULL);
 static DEVICE_ATTR(itlb_multihit, 0444, cpu_show_itlb_multihit, NULL);
+static DEVICE_ATTR(srbds, 0444, cpu_show_srbds, NULL);
 
 static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_meltdown.attr,
@@ -585,6 +592,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_mds.attr,
 	&dev_attr_tsx_async_abort.attr,
 	&dev_attr_itlb_multihit.attr,
+	&dev_attr_srbds.attr,
 	NULL
 };
 
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index 0df9b4461766..432a6f52cadb 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -250,10 +250,10 @@ int driver_deferred_probe_check_state(struct device *dev)
 {
 	if (initcalls_done) {
 		if (!deferred_probe_timeout) {
-			dev_WARN(dev, "deferred probe timeout, ignoring dependency");
+			dev_WARN(dev, "deferred probe timeout, ignoring dependency\n");
 			return -ETIMEDOUT;
 		}
-		dev_warn(dev, "ignoring dependency for device, assuming no driver");
+		dev_warn(dev, "ignoring dependency for device, assuming no driver\n");
 		return -ENODEV;
 	}
 	return -EPROBE_DEFER;
@@ -268,7 +268,7 @@ static void deferred_probe_timeout_work_func(struct work_struct *work)
 	flush_work(&deferred_probe_work);
 
 	list_for_each_entry_safe(private, p, &deferred_probe_pending_list, deferred_probe)
-		dev_info(private->device, "deferred probe pending");
+		dev_info(private->device, "deferred probe pending\n");
 }
 static DECLARE_DELAYED_WORK(deferred_probe_timeout_work, deferred_probe_timeout_work_func);
 
@@ -328,7 +328,7 @@ bool device_is_bound(struct device *dev)
 static void driver_bound(struct device *dev)
 {
 	if (device_is_bound(dev)) {
-		printk(KERN_WARNING "%s: device %s already bound\n",
+		pr_warn("%s: device %s already bound\n",
 			__func__, kobject_name(&dev->kobj));
 		return;
 	}
@@ -477,7 +477,10 @@ static int really_probe(struct device *dev, struct device_driver *drv)
 	atomic_inc(&probe_count);
 	pr_debug("bus: '%s': %s: probing driver %s with device %s\n",
 		 drv->bus->name, __func__, drv->name, dev_name(dev));
-	WARN_ON(!list_empty(&dev->devres_head));
+	if (!list_empty(&dev->devres_head)) {
+		dev_crit(dev, "Resources present before probing\n");
+		return -EBUSY;
+	}
 
 re_probe:
 	dev->driver = drv;
@@ -494,8 +497,8 @@ re_probe:
 	}
 
 	if (driver_sysfs_add(dev)) {
-		printk(KERN_ERR "%s: driver_sysfs_add(%s) failed\n",
-			__func__, dev_name(dev));
+		pr_err("%s: driver_sysfs_add(%s) failed\n",
+		       __func__, dev_name(dev));
 		goto probe_failed;
 	}
 
@@ -574,9 +577,8 @@ pinctrl_bind_failed:
 		break;
 	default:
 		/* driver matched but the probe failed */
-		printk(KERN_WARNING
-		       "%s: probe of %s failed with error %d\n",
-		       drv->name, dev_name(dev), ret);
+		pr_warn("%s: probe of %s failed with error %d\n",
+			drv->name, dev_name(dev), ret);
 	}
 	/*
 	 * Ignore errors returned by ->probe so that the next driver can try
@@ -601,8 +603,8 @@ static int really_probe_debug(struct device *dev, struct device_driver *drv)
 	ret = really_probe(dev, drv);
 	rettime = ktime_get();
 	delta = ktime_sub(rettime, calltime);
-	printk(KERN_DEBUG "probe of %s returned %d after %lld usecs\n",
-	       dev_name(dev), ret, (s64) ktime_to_us(delta));
+	pr_debug("probe of %s returned %d after %lld usecs\n",
+		 dev_name(dev), ret, (s64) ktime_to_us(delta));
 	return ret;
 }
 
@@ -686,8 +688,7 @@ static inline bool cmdline_requested_async_probing(const char *drv_name)
 static int __init save_async_options(char *buf)
 {
 	if (strlen(buf) >= ASYNC_DRV_NAMES_MAX_LEN)
-		printk(KERN_WARNING
-			"Too long list of driver names for 'driver_async_probe'!\n");
+		pr_warn("Too long list of driver names for 'driver_async_probe'!\n");
 
 	strlcpy(async_probe_drv_names, buf, ASYNC_DRV_NAMES_MAX_LEN);
 	return 0;
@@ -762,7 +763,7 @@ static int __device_attach_driver(struct device_driver *drv, void *_data)
 		dev_dbg(dev, "Device match requests probe deferral\n");
 		driver_deferred_probe_add(dev);
 	} else if (ret < 0) {
-		dev_dbg(dev, "Bus failed to match device: %d", ret);
+		dev_dbg(dev, "Bus failed to match device: %d\n", ret);
 		return ret;
 	} /* ret > 0 means positive match */
 
@@ -818,7 +819,9 @@ static int __device_attach(struct device *dev, bool allow_async)
 	int ret = 0;
 
 	device_lock(dev);
-	if (dev->driver) {
+	if (dev->p->dead) {
+		goto out_unlock;
+	} else if (dev->driver) {
 		if (device_is_bound(dev)) {
 			ret = 1;
 			goto out_unlock;
@@ -995,7 +998,7 @@ static int __driver_attach(struct device *dev, void *data)
 		dev_dbg(dev, "Device match requests probe deferral\n");
 		driver_deferred_probe_add(dev);
 	} else if (ret < 0) {
-		dev_dbg(dev, "Bus failed to match device: %d", ret);
+		dev_dbg(dev, "Bus failed to match device: %d\n", ret);
 		return ret;
 	} /* ret > 0 means positive match */
 
diff --git a/drivers/base/firmware_loader/builtin/Makefile b/drivers/base/firmware_loader/builtin/Makefile
index 4a66888e7253..5fa7ce3745a0 100644
--- a/drivers/base/firmware_loader/builtin/Makefile
+++ b/drivers/base/firmware_loader/builtin/Makefile
@@ -17,7 +17,7 @@ PROGBITS  = $(if $(CONFIG_ARM),%,@)progbits
 filechk_fwbin = \
 	echo "/* Generated by $(src)/Makefile */"		;\
 	echo "    .section .rodata"				;\
-	echo "    .p2align $(ASM_ALIGN)"			;\
+	echo "    .p2align 4"					;\
 	echo "_fw_$(FWSTR)_bin:"				;\
 	echo "    .incbin \"$(fwdir)/$(FWNAME)\""		;\
 	echo "_fw_end:"						;\
diff --git a/drivers/base/firmware_loader/fallback.c b/drivers/base/firmware_loader/fallback.c
index 103b5d37fa86..91c5091f9c60 100644
--- a/drivers/base/firmware_loader/fallback.c
+++ b/drivers/base/firmware_loader/fallback.c
@@ -572,7 +572,7 @@ static int fw_load_sysfs_fallback(struct fw_sysfs *fw_sysfs,
 	}
 
 	retval = fw_sysfs_wait_timeout(fw_priv, timeout);
-	if (retval < 0) {
+	if (retval < 0 && retval != -ENOENT) {
 		mutex_lock(&fw_lock);
 		fw_load_abort(fw_sysfs);
 		mutex_unlock(&fw_lock);
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index acd5814ed20e..94e37a56df6f 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -121,27 +121,13 @@ static ssize_t phys_index_show(struct device *dev,
 }
 
 /*
- * Show whether the section of memory is likely to be hot-removable
+ * Legacy interface that we cannot remove. Always indicate "removable"
+ * with CONFIG_MEMORY_HOTREMOVE - bad heuristic.
  */
 static ssize_t removable_show(struct device *dev, struct device_attribute *attr,
 			      char *buf)
 {
-	unsigned long i, pfn;
-	int ret = 1;
-	struct memory_block *mem = to_memory_block(dev);
-
-	if (mem->state != MEM_ONLINE)
-		goto out;
-
-	for (i = 0; i < sections_per_block; i++) {
-		if (!present_section_nr(mem->start_section_nr + i))
-			continue;
-		pfn = section_nr_to_pfn(mem->start_section_nr + i);
-		ret &= is_mem_section_removable(pfn, PAGES_PER_SECTION);
-	}
-
-out:
-	return sprintf(buf, "%d\n", ret);
+	return sprintf(buf, "%d\n", (int)IS_ENABLED(CONFIG_MEMORY_HOTREMOVE));
 }
 
 /*
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 8b25c7b12179..639c427258a5 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -27,6 +27,7 @@
 #include <linux/limits.h>
 #include <linux/property.h>
 #include <linux/kmemleak.h>
+#include <linux/types.h>
 
 #include "base.h"
 #include "power/power.h"
@@ -67,7 +68,7 @@ void __weak arch_setup_pdev_archdata(struct platform_device *pdev)
 struct resource *platform_get_resource(struct platform_device *dev,
 				       unsigned int type, unsigned int num)
 {
-	int i;
+	u32 i;
 
 	for (i = 0; i < dev->num_resources; i++) {
 		struct resource *r = &dev->resource[i];
@@ -100,35 +101,46 @@ EXPORT_SYMBOL_GPL(devm_platform_ioremap_resource);
 #endif /* CONFIG_HAS_IOMEM */
 
 /**
- * platform_get_irq - get an IRQ for a device
+ * platform_get_irq_optional - get an optional IRQ for a device
  * @dev: platform device
  * @num: IRQ number index
+ *
+ * Gets an IRQ for a platform device. Device drivers should check the return
+ * value for errors so as to not pass a negative integer value to the
+ * request_irq() APIs. This is the same as platform_get_irq(), except that it
+ * does not print an error message if an IRQ can not be obtained.
+ *
+ * Example:
+ *		int irq = platform_get_irq_optional(pdev, 0);
+ *		if (irq < 0)
+ *			return irq;
+ *
+ * Return: non-zero IRQ number on success, negative error number on failure.
  */
-int platform_get_irq(struct platform_device *dev, unsigned int num)
+int platform_get_irq_optional(struct platform_device *dev, unsigned int num)
 {
+	int ret;
 #ifdef CONFIG_SPARC
 	/* sparc does not have irqs represented as IORESOURCE_IRQ resources */
 	if (!dev || num >= dev->archdata.num_irqs)
 		return -ENXIO;
-	return dev->archdata.irqs[num];
+	ret = dev->archdata.irqs[num];
+	goto out;
 #else
 	struct resource *r;
-	if (IS_ENABLED(CONFIG_OF_IRQ) && dev->dev.of_node) {
-		int ret;
 
+	if (IS_ENABLED(CONFIG_OF_IRQ) && dev->dev.of_node) {
 		ret = of_irq_get(dev->dev.of_node, num);
 		if (ret > 0 || ret == -EPROBE_DEFER)
-			return ret;
+			goto out;
 	}
 
 	r = platform_get_resource(dev, IORESOURCE_IRQ, num);
 	if (has_acpi_companion(&dev->dev)) {
 		if (r && r->flags & IORESOURCE_DISABLED) {
-			int ret;
-
 			ret = acpi_irq_get(ACPI_HANDLE(&dev->dev), num, r);
 			if (ret)
-				return ret;
+				goto out;
 		}
 	}
 
@@ -142,13 +154,17 @@ int platform_get_irq(struct platform_device *dev, unsigned int num)
 		struct irq_data *irqd;
 
 		irqd = irq_get_irq_data(r->start);
-		if (!irqd)
-			return -ENXIO;
+		if (!irqd) {
+			ret = -ENXIO;
+			goto out;
+		}
 		irqd_set_trigger_type(irqd, r->flags & IORESOURCE_BITS);
 	}
 
-	if (r)
-		return r->start;
+	if (r) {
+		ret = r->start;
+		goto out;
+	}
 
 	/*
 	 * For the index 0 interrupt, allow falling back to GpioInt
@@ -158,15 +174,45 @@ int platform_get_irq(struct platform_device *dev, unsigned int num)
 	 * allows a common code path across either kind of resource.
 	 */
 	if (num == 0 && has_acpi_companion(&dev->dev)) {
-		int ret = acpi_dev_gpio_irq_get(ACPI_COMPANION(&dev->dev), num);
-
+		ret = acpi_dev_gpio_irq_get(ACPI_COMPANION(&dev->dev), num);
 		/* Our callers expect -ENXIO for missing IRQs. */
 		if (ret >= 0 || ret == -EPROBE_DEFER)
-			return ret;
+			goto out;
 	}
 
-	return -ENXIO;
+	ret = -ENXIO;
 #endif
+out:
+	WARN(ret == 0, "0 is an invalid IRQ number\n");
+	return ret;
+}
+EXPORT_SYMBOL_GPL(platform_get_irq_optional);
+
+/**
+ * platform_get_irq - get an IRQ for a device
+ * @dev: platform device
+ * @num: IRQ number index
+ *
+ * Gets an IRQ for a platform device and prints an error message if finding the
+ * IRQ fails. Device drivers should check the return value for errors so as to
+ * not pass a negative integer value to the request_irq() APIs.
+ *
+ * Example:
+ *		int irq = platform_get_irq(pdev, 0);
+ *		if (irq < 0)
+ *			return irq;
+ *
+ * Return: non-zero IRQ number on success, negative error number on failure.
+ */
+int platform_get_irq(struct platform_device *dev, unsigned int num)
+{
+	int ret;
+
+	ret = platform_get_irq_optional(dev, num);
+	if (ret < 0 && ret != -EPROBE_DEFER)
+		dev_err(&dev->dev, "IRQ index %u not found\n", num);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(platform_get_irq);
 
@@ -180,7 +226,7 @@ int platform_irq_count(struct platform_device *dev)
 {
 	int ret, nr = 0;
 
-	while ((ret = platform_get_irq(dev, nr)) >= 0)
+	while ((ret = platform_get_irq_optional(dev, nr)) >= 0)
 		nr++;
 
 	if (ret == -EPROBE_DEFER)
@@ -200,7 +246,7 @@ struct resource *platform_get_resource_byname(struct platform_device *dev,
 					      unsigned int type,
 					      const char *name)
 {
-	int i;
+	u32 i;
 
 	for (i = 0; i < dev->num_resources; i++) {
 		struct resource *r = &dev->resource[i];
@@ -215,29 +261,66 @@ struct resource *platform_get_resource_byname(struct platform_device *dev,
 }
 EXPORT_SYMBOL_GPL(platform_get_resource_byname);
 
-/**
- * platform_get_irq_byname - get an IRQ for a device by name
- * @dev: platform device
- * @name: IRQ name
- */
-int platform_get_irq_byname(struct platform_device *dev, const char *name)
+static int __platform_get_irq_byname(struct platform_device *dev,
+				     const char *name)
 {
 	struct resource *r;
+	int ret;
 
 	if (IS_ENABLED(CONFIG_OF_IRQ) && dev->dev.of_node) {
-		int ret;
-
 		ret = of_irq_get_byname(dev->dev.of_node, name);
 		if (ret > 0 || ret == -EPROBE_DEFER)
 			return ret;
 	}
 
 	r = platform_get_resource_byname(dev, IORESOURCE_IRQ, name);
-	return r ? r->start : -ENXIO;
+	if (r) {
+		WARN(r->start == 0, "0 is an invalid IRQ number\n");
+		return r->start;
+	}
+
+	return -ENXIO;
+}
+
+/**
+ * platform_get_irq_byname - get an IRQ for a device by name
+ * @dev: platform device
+ * @name: IRQ name
+ *
+ * Get an IRQ like platform_get_irq(), but then by name rather then by index.
+ *
+ * Return: non-zero IRQ number on success, negative error number on failure.
+ */
+int platform_get_irq_byname(struct platform_device *dev, const char *name)
+{
+	int ret;
+
+	ret = __platform_get_irq_byname(dev, name);
+	if (ret < 0 && ret != -EPROBE_DEFER)
+		dev_err(&dev->dev, "IRQ %s not found\n", name);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(platform_get_irq_byname);
 
 /**
+ * platform_get_irq_byname_optional - get an optional IRQ for a device by name
+ * @dev: platform device
+ * @name: IRQ name
+ *
+ * Get an optional IRQ by name like platform_get_irq_byname(). Except that it
+ * does not print an error message if an IRQ can not be obtained.
+ *
+ * Return: non-zero IRQ number on success, negative error number on failure.
+ */
+int platform_get_irq_byname_optional(struct platform_device *dev,
+				     const char *name)
+{
+	return __platform_get_irq_byname(dev, name);
+}
+EXPORT_SYMBOL_GPL(platform_get_irq_byname_optional);
+
+/**
  * platform_add_devices - add a numbers of platform devices
  * @devs: array of platform devices to add
  * @num: number of platform devices in array
@@ -397,7 +480,8 @@ EXPORT_SYMBOL_GPL(platform_device_add_properties);
  */
 int platform_device_add(struct platform_device *pdev)
 {
-	int i, ret;
+	u32 i;
+	int ret;
 
 	if (!pdev)
 		return -EINVAL;
@@ -465,7 +549,7 @@ int platform_device_add(struct platform_device *pdev)
 		pdev->id = PLATFORM_DEVID_AUTO;
 	}
 
-	while (--i >= 0) {
+	while (i--) {
 		struct resource *r = &pdev->resource[i];
 		if (r->parent)
 			release_resource(r);
@@ -486,7 +570,7 @@ EXPORT_SYMBOL_GPL(platform_device_add);
  */
 void platform_device_del(struct platform_device *pdev)
 {
-	int i;
+	u32 i;
 
 	if (!IS_ERR_OR_NULL(pdev)) {
 		device_del(&pdev->dev);
@@ -737,6 +821,8 @@ int __init_or_module __platform_driver_probe(struct platform_driver *drv,
 	/* temporary section violation during probe() */
 	drv->probe = probe;
 	retval = code = __platform_driver_register(drv, module);
+	if (retval)
+		return retval;
 
 	/*
 	 * Fixup that section violation, being paranoid about code scanning
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 33c30c1e6a30..dc135a7dfbe9 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -2618,7 +2618,7 @@ static int genpd_iterate_idle_states(struct device_node *dn,
 
 	ret = of_count_phandle_with_args(dn, "domain-idle-states", NULL);
 	if (ret <= 0)
-		return ret;
+		return ret == -ENOENT ? 0 : ret;
 
 	/* Loop over the phandles until all the requested entry is found */
 	of_for_each_phandle(&it, ret, dn, "domain-idle-states", NULL, 0) {
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index dcfc0a36c8f7..2445c2522218 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -273,10 +273,38 @@ static void dpm_wait_for_suppliers(struct device *dev, bool async)
 	device_links_read_unlock(idx);
 }
 
-static void dpm_wait_for_superior(struct device *dev, bool async)
+static bool dpm_wait_for_superior(struct device *dev, bool async)
 {
-	dpm_wait(dev->parent, async);
+	struct device *parent;
+
+	/*
+	 * If the device is resumed asynchronously and the parent's callback
+	 * deletes both the device and the parent itself, the parent object may
+	 * be freed while this function is running, so avoid that by reference
+	 * counting the parent once more unless the device has been deleted
+	 * already (in which case return right away).
+	 */
+	mutex_lock(&dpm_list_mtx);
+
+	if (!device_pm_initialized(dev)) {
+		mutex_unlock(&dpm_list_mtx);
+		return false;
+	}
+
+	parent = get_device(dev->parent);
+
+	mutex_unlock(&dpm_list_mtx);
+
+	dpm_wait(parent, async);
+	put_device(parent);
+
 	dpm_wait_for_suppliers(dev, async);
+
+	/*
+	 * If the parent's callback has deleted the device, attempting to resume
+	 * it would be invalid, so avoid doing that then.
+	 */
+	return device_pm_initialized(dev);
 }
 
 static void dpm_wait_for_consumers(struct device *dev, bool async)
@@ -636,7 +664,8 @@ static int device_resume_noirq(struct device *dev, pm_message_t state, bool asyn
 	if (!dev->power.is_noirq_suspended)
 		goto Out;
 
-	dpm_wait_for_superior(dev, async);
+	if (!dpm_wait_for_superior(dev, async))
+		goto Out;
 
 	skip_resume = dev_pm_may_skip_resume(dev);
 
@@ -710,7 +739,7 @@ static bool dpm_async_fn(struct device *dev, async_func_t func)
 
 	if (is_async(dev)) {
 		get_device(dev);
-		async_schedule(func, dev);
+		async_schedule_dev(func, dev);
 		return true;
 	}
 
@@ -845,7 +874,8 @@ static int device_resume_early(struct device *dev, pm_message_t state, bool asyn
 	if (!dev->power.is_late_suspended)
 		goto Out;
 
-	dpm_wait_for_superior(dev, async);
+	if (!dpm_wait_for_superior(dev, async))
+		goto Out;
 
 	callback = dpm_subsys_resume_early_cb(dev, state, &info);
 
@@ -960,7 +990,9 @@ static int device_resume(struct device *dev, pm_message_t state, bool async)
 		goto Complete;
 	}
 
-	dpm_wait_for_superior(dev, async);
+	if (!dpm_wait_for_superior(dev, async))
+		goto Complete;
+
 	dpm_watchdog_set(&wd, dev);
 	device_lock(dev);
 
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index 5b2b6a05a4f3..50f9e89c3f4e 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -1053,6 +1053,9 @@ static void *wakeup_sources_stats_seq_next(struct seq_file *m,
 		break;
 	}
 
+	if (!next_ws)
+		print_wakeup_source_stats(m, &deleted_ws);
+
 	return next_ws;
 }
 
diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c
index e5e1b3a01b1a..bfb357e273fb 100644
--- a/drivers/base/regmap/regmap-debugfs.c
+++ b/drivers/base/regmap/regmap-debugfs.c
@@ -227,6 +227,9 @@ static ssize_t regmap_read_debugfs(struct regmap *map, unsigned int from,
 	if (*ppos < 0 || !count)
 		return -EINVAL;
 
+	if (count > (PAGE_SIZE << (MAX_ORDER - 1)))
+		count = PAGE_SIZE << (MAX_ORDER - 1);
+
 	buf = kmalloc(count, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
@@ -371,6 +374,9 @@ static ssize_t regmap_reg_ranges_read_file(struct file *file,
 	if (*ppos < 0 || !count)
 		return -EINVAL;
 
+	if (count > (PAGE_SIZE << (MAX_ORDER - 1)))
+		count = PAGE_SIZE << (MAX_ORDER - 1);
+
 	buf = kmalloc(count, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
@@ -457,29 +463,31 @@ static ssize_t regmap_cache_only_write_file(struct file *file,
 {
 	struct regmap *map = container_of(file->private_data,
 					  struct regmap, cache_only);
-	ssize_t result;
-	bool was_enabled, require_sync = false;
+	bool new_val, require_sync = false;
 	int err;
 
-	map->lock(map->lock_arg);
+	err = kstrtobool_from_user(user_buf, count, &new_val);
+	/* Ignore malforned data like debugfs_write_file_bool() */
+	if (err)
+		return count;
 
-	was_enabled = map->cache_only;
+	err = debugfs_file_get(file->f_path.dentry);
+	if (err)
+		return err;
 
-	result = debugfs_write_file_bool(file, user_buf, count, ppos);
-	if (result < 0) {
-		map->unlock(map->lock_arg);
-		return result;
-	}
+	map->lock(map->lock_arg);
 
-	if (map->cache_only && !was_enabled) {
+	if (new_val && !map->cache_only) {
 		dev_warn(map->dev, "debugfs cache_only=Y forced\n");
 		add_taint(TAINT_USER, LOCKDEP_STILL_OK);
-	} else if (!map->cache_only && was_enabled) {
+	} else if (!new_val && map->cache_only) {
 		dev_warn(map->dev, "debugfs cache_only=N forced: syncing cache\n");
 		require_sync = true;
 	}
+	map->cache_only = new_val;
 
 	map->unlock(map->lock_arg);
+	debugfs_file_put(file->f_path.dentry);
 
 	if (require_sync) {
 		err = regcache_sync(map);
@@ -487,7 +495,7 @@ static ssize_t regmap_cache_only_write_file(struct file *file,
 			dev_err(map->dev, "Failed to sync cache %d\n", err);
 	}
 
-	return result;
+	return count;
 }
 
 static const struct file_operations regmap_cache_only_fops = {
@@ -502,28 +510,32 @@ static ssize_t regmap_cache_bypass_write_file(struct file *file,
 {
 	struct regmap *map = container_of(file->private_data,
 					  struct regmap, cache_bypass);
-	ssize_t result;
-	bool was_enabled;
+	bool new_val;
+	int err;
 
-	map->lock(map->lock_arg);
+	err = kstrtobool_from_user(user_buf, count, &new_val);
+	/* Ignore malforned data like debugfs_write_file_bool() */
+	if (err)
+		return count;
 
-	was_enabled = map->cache_bypass;
+	err = debugfs_file_get(file->f_path.dentry);
+	if (err)
+		return err;
 
-	result = debugfs_write_file_bool(file, user_buf, count, ppos);
-	if (result < 0)
-		goto out;
+	map->lock(map->lock_arg);
 
-	if (map->cache_bypass && !was_enabled) {
+	if (new_val && !map->cache_bypass) {
 		dev_warn(map->dev, "debugfs cache_bypass=Y forced\n");
 		add_taint(TAINT_USER, LOCKDEP_STILL_OK);
-	} else if (!map->cache_bypass && was_enabled) {
+	} else if (!new_val && map->cache_bypass) {
 		dev_warn(map->dev, "debugfs cache_bypass=N forced\n");
 	}
+	map->cache_bypass = new_val;
 
-out:
 	map->unlock(map->lock_arg);
+	debugfs_file_put(file->f_path.dentry);
 
-	return result;
+	return count;
 }
 
 static const struct file_operations regmap_cache_bypass_fops = {
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 19f57ccfbe1d..927ebde1607b 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -17,6 +17,7 @@
 #include <linux/delay.h>
 #include <linux/log2.h>
 #include <linux/hwspinlock.h>
+#include <asm/unaligned.h>
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
@@ -249,22 +250,20 @@ static void regmap_format_8(void *buf, unsigned int val, unsigned int shift)
 
 static void regmap_format_16_be(void *buf, unsigned int val, unsigned int shift)
 {
-	__be16 *b = buf;
-
-	b[0] = cpu_to_be16(val << shift);
+	put_unaligned_be16(val << shift, buf);
 }
 
 static void regmap_format_16_le(void *buf, unsigned int val, unsigned int shift)
 {
-	__le16 *b = buf;
-
-	b[0] = cpu_to_le16(val << shift);
+	put_unaligned_le16(val << shift, buf);
 }
 
 static void regmap_format_16_native(void *buf, unsigned int val,
 				    unsigned int shift)
 {
-	*(u16 *)buf = val << shift;
+	u16 v = val << shift;
+
+	memcpy(buf, &v, sizeof(v));
 }
 
 static void regmap_format_24(void *buf, unsigned int val, unsigned int shift)
@@ -280,43 +279,39 @@ static void regmap_format_24(void *buf, unsigned int val, unsigned int shift)
 
 static void regmap_format_32_be(void *buf, unsigned int val, unsigned int shift)
 {
-	__be32 *b = buf;
-
-	b[0] = cpu_to_be32(val << shift);
+	put_unaligned_be32(val << shift, buf);
 }
 
 static void regmap_format_32_le(void *buf, unsigned int val, unsigned int shift)
 {
-	__le32 *b = buf;
-
-	b[0] = cpu_to_le32(val << shift);
+	put_unaligned_le32(val << shift, buf);
 }
 
 static void regmap_format_32_native(void *buf, unsigned int val,
 				    unsigned int shift)
 {
-	*(u32 *)buf = val << shift;
+	u32 v = val << shift;
+
+	memcpy(buf, &v, sizeof(v));
 }
 
 #ifdef CONFIG_64BIT
 static void regmap_format_64_be(void *buf, unsigned int val, unsigned int shift)
 {
-	__be64 *b = buf;
-
-	b[0] = cpu_to_be64((u64)val << shift);
+	put_unaligned_be64((u64) val << shift, buf);
 }
 
 static void regmap_format_64_le(void *buf, unsigned int val, unsigned int shift)
 {
-	__le64 *b = buf;
-
-	b[0] = cpu_to_le64((u64)val << shift);
+	put_unaligned_le64((u64) val << shift, buf);
 }
 
 static void regmap_format_64_native(void *buf, unsigned int val,
 				    unsigned int shift)
 {
-	*(u64 *)buf = (u64)val << shift;
+	u64 v = (u64) val << shift;
+
+	memcpy(buf, &v, sizeof(v));
 }
 #endif
 
@@ -333,35 +328,34 @@ static unsigned int regmap_parse_8(const void *buf)
 
 static unsigned int regmap_parse_16_be(const void *buf)
 {
-	const __be16 *b = buf;
-
-	return be16_to_cpu(b[0]);
+	return get_unaligned_be16(buf);
 }
 
 static unsigned int regmap_parse_16_le(const void *buf)
 {
-	const __le16 *b = buf;
-
-	return le16_to_cpu(b[0]);
+	return get_unaligned_le16(buf);
 }
 
 static void regmap_parse_16_be_inplace(void *buf)
 {
-	__be16 *b = buf;
+	u16 v = get_unaligned_be16(buf);
 
-	b[0] = be16_to_cpu(b[0]);
+	memcpy(buf, &v, sizeof(v));
 }
 
 static void regmap_parse_16_le_inplace(void *buf)
 {
-	__le16 *b = buf;
+	u16 v = get_unaligned_le16(buf);
 
-	b[0] = le16_to_cpu(b[0]);
+	memcpy(buf, &v, sizeof(v));
 }
 
 static unsigned int regmap_parse_16_native(const void *buf)
 {
-	return *(u16 *)buf;
+	u16 v;
+
+	memcpy(&v, buf, sizeof(v));
+	return v;
 }
 
 static unsigned int regmap_parse_24(const void *buf)
@@ -376,69 +370,67 @@ static unsigned int regmap_parse_24(const void *buf)
 
 static unsigned int regmap_parse_32_be(const void *buf)
 {
-	const __be32 *b = buf;
-
-	return be32_to_cpu(b[0]);
+	return get_unaligned_be32(buf);
 }
 
 static unsigned int regmap_parse_32_le(const void *buf)
 {
-	const __le32 *b = buf;
-
-	return le32_to_cpu(b[0]);
+	return get_unaligned_le32(buf);
 }
 
 static void regmap_parse_32_be_inplace(void *buf)
 {
-	__be32 *b = buf;
+	u32 v = get_unaligned_be32(buf);
 
-	b[0] = be32_to_cpu(b[0]);
+	memcpy(buf, &v, sizeof(v));
 }
 
 static void regmap_parse_32_le_inplace(void *buf)
 {
-	__le32 *b = buf;
+	u32 v = get_unaligned_le32(buf);
 
-	b[0] = le32_to_cpu(b[0]);
+	memcpy(buf, &v, sizeof(v));
 }
 
 static unsigned int regmap_parse_32_native(const void *buf)
 {
-	return *(u32 *)buf;
+	u32 v;
+
+	memcpy(&v, buf, sizeof(v));
+	return v;
 }
 
 #ifdef CONFIG_64BIT
 static unsigned int regmap_parse_64_be(const void *buf)
 {
-	const __be64 *b = buf;
-
-	return be64_to_cpu(b[0]);
+	return get_unaligned_be64(buf);
 }
 
 static unsigned int regmap_parse_64_le(const void *buf)
 {
-	const __le64 *b = buf;
-
-	return le64_to_cpu(b[0]);
+	return get_unaligned_le64(buf);
 }
 
 static void regmap_parse_64_be_inplace(void *buf)
 {
-	__be64 *b = buf;
+	u64 v =  get_unaligned_be64(buf);
 
-	b[0] = be64_to_cpu(b[0]);
+	memcpy(buf, &v, sizeof(v));
 }
 
 static void regmap_parse_64_le_inplace(void *buf)
 {
-	__le64 *b = buf;
+	u64 v = get_unaligned_le64(buf);
 
-	b[0] = le64_to_cpu(b[0]);
+	memcpy(buf, &v, sizeof(v));
 }
 
 static unsigned int regmap_parse_64_native(const void *buf)
 {
-	return *(u64 *)buf;
+	u64 v;
+
+	memcpy(&v, buf, sizeof(v));
+	return v;
 }
 #endif
 
@@ -1356,6 +1348,7 @@ void regmap_exit(struct regmap *map)
 	if (map->hwlock)
 		hwspin_lock_free(map->hwlock);
 	kfree_const(map->name);
+	kfree(map->patch);
 	kfree(map);
 }
 EXPORT_SYMBOL_GPL(regmap_exit);
@@ -1370,7 +1363,7 @@ static int dev_get_regmap_match(struct device *dev, void *res, void *data)
 
 	/* If the user didn't specify a name match any */
 	if (data)
-		return (*r)->name == data;
+		return !strcmp((*r)->name, data);
 	else
 		return 1;
 }
@@ -1488,11 +1481,18 @@ static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg,
 
 	WARN_ON(!map->bus);
 
-	/* Check for unwritable registers before we start */
-	for (i = 0; i < val_len / map->format.val_bytes; i++)
-		if (!regmap_writeable(map,
-				     reg + regmap_get_offset(map, i)))
-			return -EINVAL;
+	/* Check for unwritable or noinc registers in range
+	 * before we start
+	 */
+	if (!regmap_writeable_noinc(map, reg)) {
+		for (i = 0; i < val_len / map->format.val_bytes; i++) {
+			unsigned int element =
+				reg + regmap_get_offset(map, i);
+			if (!regmap_writeable(map, element) ||
+				regmap_writeable_noinc(map, element))
+				return -EINVAL;
+		}
+	}
 
 	if (!map->cache_bypass && map->format.parse_val) {
 		unsigned int ival;
diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c
index 7fc5a18e02ad..891a8a301f78 100644
--- a/drivers/base/swnode.c
+++ b/drivers/base/swnode.c
@@ -477,8 +477,10 @@ software_node_get_parent(const struct fwnode_handle *fwnode)
 {
 	struct software_node *swnode = to_software_node(fwnode);
 
-	return swnode ? (swnode->parent ? &swnode->parent->fwnode : NULL) :
-			NULL;
+	if (!swnode || !swnode->parent)
+		return NULL;
+
+	return fwnode_handle_get(&swnode->parent->fwnode);
 }
 
 static struct fwnode_handle *
diff --git a/drivers/base/test/test_async_driver_probe.c b/drivers/base/test/test_async_driver_probe.c
index f4b1d8e54daf..3bb7beb127a9 100644
--- a/drivers/base/test/test_async_driver_probe.c
+++ b/drivers/base/test/test_async_driver_probe.c
@@ -44,7 +44,8 @@ static int test_probe(struct platform_device *pdev)
 	 * performing an async init on that node.
 	 */
 	if (dev->driver->probe_type == PROBE_PREFER_ASYNCHRONOUS) {
-		if (dev_to_node(dev) != numa_node_id()) {
+		if (IS_ENABLED(CONFIG_NUMA) &&
+		    dev_to_node(dev) != numa_node_id()) {
 			dev_warn(dev, "NUMA node mismatch %d != %d\n",
 				 dev_to_node(dev), numa_node_id());
 			atomic_inc(&warnings);
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index c548a5a6c1a0..79f18cfa7049 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -470,6 +470,25 @@ static struct kobject *brd_probe(dev_t dev, int *part, void *data)
 	return kobj;
 }
 
+static inline void brd_check_and_reset_par(void)
+{
+	if (unlikely(!max_part))
+		max_part = 1;
+
+	/*
+	 * make sure 'max_part' can be divided exactly by (1U << MINORBITS),
+	 * otherwise, it is possiable to get same dev_t when adding partitions.
+	 */
+	if ((1U << MINORBITS) % max_part != 0)
+		max_part = 1UL << fls(max_part);
+
+	if (max_part > DISK_MAX_PARTS) {
+		pr_info("brd: max_part can't be larger than %d, reset max_part = %d.\n",
+			DISK_MAX_PARTS, DISK_MAX_PARTS);
+		max_part = DISK_MAX_PARTS;
+	}
+}
+
 static int __init brd_init(void)
 {
 	struct brd_device *brd, *next;
@@ -493,8 +512,7 @@ static int __init brd_init(void)
 	if (register_blkdev(RAMDISK_MAJOR, "ramdisk"))
 		return -EIO;
 
-	if (unlikely(!max_part))
-		max_part = 1;
+	brd_check_and_reset_par();
 
 	for (i = 0; i < rd_nr; i++) {
 		brd = brd_alloc(i);
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 3cd4af25f5b3..580b5391705c 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -2902,17 +2902,17 @@ static blk_status_t floppy_queue_rq(struct blk_mq_hw_ctx *hctx,
 		 (unsigned long long) current_req->cmd_flags))
 		return BLK_STS_IOERR;
 
-	spin_lock_irq(&floppy_lock);
-	list_add_tail(&bd->rq->queuelist, &floppy_reqs);
-	spin_unlock_irq(&floppy_lock);
-
 	if (test_and_set_bit(0, &fdc_busy)) {
 		/* fdc busy, this new request will be treated when the
 		   current one is done */
 		is_alive(__func__, "old request running");
-		return BLK_STS_OK;
+		return BLK_STS_RESOURCE;
 	}
 
+	spin_lock_irq(&floppy_lock);
+	list_add_tail(&bd->rq->queuelist, &floppy_reqs);
+	spin_unlock_irq(&floppy_lock);
+
 	command_status = FD_COMMAND_NONE;
 	__reschedule_timeout(MAXTIMEOUT, "fd_request");
 	set_fdc(0);
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 984d12a8030b..a1522cd580de 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -435,11 +435,12 @@ static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos,
 	 * information.
 	 */
 	struct file *file = lo->lo_backing_file;
+	struct request_queue *q = lo->lo_queue;
 	int ret;
 
 	mode |= FALLOC_FL_KEEP_SIZE;
 
-	if ((!file->f_op->fallocate) || lo->lo_encrypt_key_size) {
+	if (!blk_queue_discard(q)) {
 		ret = -EOPNOTSUPP;
 		goto out;
 	}
@@ -888,6 +889,23 @@ static void loop_config_discard(struct loop_device *lo)
 	struct file *file = lo->lo_backing_file;
 	struct inode *inode = file->f_mapping->host;
 	struct request_queue *q = lo->lo_queue;
+	u32 granularity, max_discard_sectors;
+
+	/*
+	 * If the backing device is a block device, mirror its zeroing
+	 * capability. Set the discard sectors to the block device's zeroing
+	 * capabilities because loop discards result in blkdev_issue_zeroout(),
+	 * not blkdev_issue_discard(). This maintains consistent behavior with
+	 * file-backed loop devices: discarded regions read back as zero.
+	 */
+	if (S_ISBLK(inode->i_mode) && !lo->lo_encrypt_key_size) {
+		struct request_queue *backingq;
+
+		backingq = bdev_get_queue(inode->i_bdev);
+
+		max_discard_sectors = backingq->limits.max_write_zeroes_sectors;
+		granularity = backingq->limits.discard_granularity ?:
+			queue_physical_block_size(backingq);
 
 	/*
 	 * We use punch hole to reclaim the free space used by the
@@ -895,22 +913,27 @@ static void loop_config_discard(struct loop_device *lo)
 	 * encryption is enabled, because it may give an attacker
 	 * useful information.
 	 */
-	if ((!file->f_op->fallocate) ||
-	    lo->lo_encrypt_key_size) {
+	} else if (!file->f_op->fallocate || lo->lo_encrypt_key_size) {
+		max_discard_sectors = 0;
+		granularity = 0;
+
+	} else {
+		max_discard_sectors = UINT_MAX >> 9;
+		granularity = inode->i_sb->s_blocksize;
+	}
+
+	if (max_discard_sectors) {
+		q->limits.discard_granularity = granularity;
+		blk_queue_max_discard_sectors(q, max_discard_sectors);
+		blk_queue_max_write_zeroes_sectors(q, max_discard_sectors);
+		blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
+	} else {
 		q->limits.discard_granularity = 0;
-		q->limits.discard_alignment = 0;
 		blk_queue_max_discard_sectors(q, 0);
 		blk_queue_max_write_zeroes_sectors(q, 0);
 		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q);
-		return;
 	}
-
-	q->limits.discard_granularity = inode->i_sb->s_blocksize;
 	q->limits.discard_alignment = 0;
-
-	blk_queue_max_discard_sectors(q, UINT_MAX >> 9);
-	blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9);
-	blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
 }
 
 static void loop_unprepare_queue(struct loop_device *lo)
@@ -1290,7 +1313,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	if (lo->lo_offset != info->lo_offset ||
 	    lo->lo_sizelimit != info->lo_sizelimit) {
 		sync_blockdev(lo->lo_device);
-		kill_bdev(lo->lo_device);
+		invalidate_bdev(lo->lo_device);
 	}
 
 	/* I/O need to be drained during transfer transition */
@@ -1564,12 +1587,12 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg)
 
 	if (lo->lo_queue->limits.logical_block_size != arg) {
 		sync_blockdev(lo->lo_device);
-		kill_bdev(lo->lo_device);
+		invalidate_bdev(lo->lo_device);
 	}
 
 	blk_mq_freeze_queue(lo->lo_queue);
 
-	/* kill_bdev should have truncated all the pages */
+	/* invalidate_bdev should have truncated all the pages */
 	if (lo->lo_queue->limits.logical_block_size != arg &&
 			lo->lo_device->bd_inode->i_mapping->nrpages) {
 		err = -EAGAIN;
@@ -2331,6 +2354,8 @@ static void __exit loop_exit(void)
 
 	range = max_loop ? max_loop << part_shift : 1UL << MINORBITS;
 
+	mutex_lock(&loop_ctl_mutex);
+
 	idr_for_each(&loop_index_idr, &loop_exit_cb, NULL);
 	idr_destroy(&loop_index_idr);
 
@@ -2338,6 +2363,8 @@ static void __exit loop_exit(void)
 	unregister_blkdev(LOOP_MAJOR, "loop");
 
 	misc_deregister(&loop_misc);
+
+	mutex_unlock(&loop_ctl_mutex);
 }
 
 module_init(loop_init);
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 72f4df37f625..b74293762be7 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -135,6 +135,8 @@ static struct dentry *nbd_dbg_dir;
 
 #define NBD_MAGIC 0x68797548
 
+#define NBD_DEF_BLKSIZE 1024
+
 static unsigned int nbds_max = 16;
 static int max_part = 16;
 static int part_shift;
@@ -983,25 +985,26 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
 	     test_bit(NBD_BOUND, &config->runtime_flags))) {
 		dev_err(disk_to_dev(nbd->disk),
 			"Device being setup by another task");
-		sockfd_put(sock);
-		return -EBUSY;
+		err = -EBUSY;
+		goto put_socket;
+	}
+
+	nsock = kzalloc(sizeof(*nsock), GFP_KERNEL);
+	if (!nsock) {
+		err = -ENOMEM;
+		goto put_socket;
 	}
 
 	socks = krealloc(config->socks, (config->num_connections + 1) *
 			 sizeof(struct nbd_sock *), GFP_KERNEL);
 	if (!socks) {
-		sockfd_put(sock);
-		return -ENOMEM;
+		kfree(nsock);
+		err = -ENOMEM;
+		goto put_socket;
 	}
 
 	config->socks = socks;
 
-	nsock = kzalloc(sizeof(struct nbd_sock), GFP_KERNEL);
-	if (!nsock) {
-		sockfd_put(sock);
-		return -ENOMEM;
-	}
-
 	nsock->fallback_index = -1;
 	nsock->dead = false;
 	mutex_init(&nsock->tx_lock);
@@ -1013,6 +1016,10 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
 	atomic_inc(&config->live_connections);
 
 	return 0;
+
+put_socket:
+	sockfd_put(sock);
+	return err;
 }
 
 static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg)
@@ -1225,6 +1232,16 @@ static int nbd_start_device(struct nbd_device *nbd)
 		args = kzalloc(sizeof(*args), GFP_KERNEL);
 		if (!args) {
 			sock_shutdown(nbd);
+			/*
+			 * If num_connections is m (2 < m),
+			 * and NO.1 ~ NO.n(1 < n < m) kzallocs are successful.
+			 * But NO.(n + 1) failed. We still have n recv threads.
+			 * So, add flush_workqueue here to prevent recv threads
+			 * dropping the last config_refs and trying to destroy
+			 * the workqueue from inside the workqueue.
+			 */
+			if (i)
+				flush_workqueue(nbd->recv_workq);
 			return -ENOMEM;
 		}
 		sk_set_memalloc(config->socks[i]->sock->sk);
@@ -1281,6 +1298,14 @@ static void nbd_clear_sock_ioctl(struct nbd_device *nbd,
 		nbd_config_put(nbd);
 }
 
+static bool nbd_is_valid_blksize(unsigned long blksize)
+{
+	if (!blksize || !is_power_of_2(blksize) || blksize < 512 ||
+	    blksize > PAGE_SIZE)
+		return false;
+	return true;
+}
+
 /* Must be called with config_lock held */
 static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 		       unsigned int cmd, unsigned long arg)
@@ -1296,8 +1321,9 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 	case NBD_SET_SOCK:
 		return nbd_add_socket(nbd, arg, false);
 	case NBD_SET_BLKSIZE:
-		if (!arg || !is_power_of_2(arg) || arg < 512 ||
-		    arg > PAGE_SIZE)
+		if (!arg)
+			arg = NBD_DEF_BLKSIZE;
+		if (!nbd_is_valid_blksize(arg))
 			return -EINVAL;
 		nbd_size_set(nbd, arg,
 			     div_s64(config->bytesize, arg));
@@ -1377,7 +1403,7 @@ static struct nbd_config *nbd_alloc_config(void)
 	atomic_set(&config->recv_threads, 0);
 	init_waitqueue_head(&config->recv_wq);
 	init_waitqueue_head(&config->conn_wait);
-	config->blksize = 1024;
+	config->blksize = NBD_DEF_BLKSIZE;
 	atomic_set(&config->live_connections, 0);
 	try_module_get(THIS_MODULE);
 	return config;
@@ -1813,6 +1839,12 @@ again:
 	if (info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]) {
 		u64 bsize =
 			nla_get_u64(info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]);
+		if (!bsize)
+			bsize = NBD_DEF_BLKSIZE;
+		if (!nbd_is_valid_blksize(bsize)) {
+			ret = -EINVAL;
+			goto out;
+		}
 		nbd_size_set(nbd, bsize, div64_u64(config->bytesize, bsize));
 	}
 	if (info->attrs[NBD_ATTR_TIMEOUT]) {
diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c
index 2a4f8bc4f930..fef05888032a 100644
--- a/drivers/block/null_blk_main.c
+++ b/drivers/block/null_blk_main.c
@@ -579,6 +579,7 @@ static struct nullb_cmd *__alloc_cmd(struct nullb_queue *nq)
 	if (tag != -1U) {
 		cmd = &nq->cmds[tag];
 		cmd->tag = tag;
+		cmd->error = BLK_STS_OK;
 		cmd->nq = nq;
 		if (nq->dev->irqmode == NULL_IRQ_TIMER) {
 			hrtimer_init(&cmd->timer, CLOCK_MONOTONIC,
@@ -1329,6 +1330,7 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
 		cmd->timer.function = null_cmd_timer_expired;
 	}
 	cmd->rq = bd->rq;
+	cmd->error = BLK_STS_OK;
 	cmd->nq = nq;
 
 	blk_mq_start_request(bd->rq);
@@ -1376,7 +1378,12 @@ static void cleanup_queues(struct nullb *nullb)
 
 static void null_del_dev(struct nullb *nullb)
 {
-	struct nullb_device *dev = nullb->dev;
+	struct nullb_device *dev;
+
+	if (!nullb)
+		return;
+
+	dev = nullb->dev;
 
 	ida_simple_remove(&nullb_indexes, nullb->index);
 
@@ -1728,6 +1735,7 @@ out_cleanup_queues:
 	cleanup_queues(nullb);
 out_free_nullb:
 	kfree(nullb);
+	dev->nullb = NULL;
 out:
 	return rv;
 }
diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c
index fca0c97ff1aa..4eaee2c9a4d8 100644
--- a/drivers/block/null_blk_zoned.c
+++ b/drivers/block/null_blk_zoned.c
@@ -20,6 +20,10 @@ int null_zone_init(struct nullb_device *dev)
 		pr_err("null_blk: zone_size must be power-of-two\n");
 		return -EINVAL;
 	}
+	if (dev->zone_size > dev->size) {
+		pr_err("Zone size larger than device capacity\n");
+		return -EINVAL;
+	}
 
 	dev->zone_size_sects = dev->zone_size << ZONE_SIZE_SHIFT;
 	dev->nr_zones = dev_size >>
diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c
index c5c6487a19d5..7b55811c2a81 100644
--- a/drivers/block/ps3disk.c
+++ b/drivers/block/ps3disk.c
@@ -454,7 +454,6 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev)
 	queue->queuedata = dev;
 
 	blk_queue_max_hw_sectors(queue, dev->bounce_size >> 9);
-	blk_queue_segment_boundary(queue, -1UL);
 	blk_queue_dma_alignment(queue, dev->blk_size-1);
 	blk_queue_logical_block_size(queue, dev->blk_size);
 
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index e5009a34f9c2..fa49b2a0dba2 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -2202,7 +2202,7 @@ static int rbd_img_fill_nodata(struct rbd_img_request *img_req,
 			       u64 off, u64 len)
 {
 	struct ceph_file_extent ex = { off, len };
-	union rbd_img_fill_iter dummy;
+	union rbd_img_fill_iter dummy = {};
 	struct rbd_img_fill_ctx fctx = {
 		.pos_type = OBJ_REQUEST_NODATA,
 		.pos = &dummy,
@@ -4305,6 +4305,9 @@ static ssize_t rbd_config_info_show(struct device *dev,
 {
 	struct rbd_device *rbd_dev = dev_to_rbd_dev(dev);
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	return sprintf(buf, "%s\n", rbd_dev->config_info);
 }
 
@@ -4416,6 +4419,9 @@ static ssize_t rbd_image_refresh(struct device *dev,
 	struct rbd_device *rbd_dev = dev_to_rbd_dev(dev);
 	int ret;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	ret = rbd_dev_refresh(rbd_dev);
 	if (ret)
 		return ret;
@@ -6012,6 +6018,9 @@ static ssize_t do_rbd_add(struct bus_type *bus,
 	struct rbd_client *rbdc;
 	int rc;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	if (!try_module_get(THIS_MODULE))
 		return -ENODEV;
 
@@ -6167,6 +6176,9 @@ static ssize_t do_rbd_remove(struct bus_type *bus,
 	bool force = false;
 	int ret;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	dev_id = -1;
 	opt_buf[0] = '\0';
 	sscanf(buf, "%d %5s", &dev_id, opt_buf);
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 7ffd719d89de..c1de270046bf 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -33,6 +33,15 @@ struct virtio_blk_vq {
 } ____cacheline_aligned_in_smp;
 
 struct virtio_blk {
+	/*
+	 * This mutex must be held by anything that may run after
+	 * virtblk_remove() sets vblk->vdev to NULL.
+	 *
+	 * blk-mq, virtqueue processing, and sysfs attribute code paths are
+	 * shut down before vblk->vdev is set to NULL and therefore do not need
+	 * to hold this mutex.
+	 */
+	struct mutex vdev_mutex;
 	struct virtio_device *vdev;
 
 	/* The disk structure for the kernel. */
@@ -44,6 +53,13 @@ struct virtio_blk {
 	/* Process context for config space updates */
 	struct work_struct config_work;
 
+	/*
+	 * Tracks references from block_device_operations open/release and
+	 * virtio_driver probe/remove so this object can be freed once no
+	 * longer in use.
+	 */
+	refcount_t refs;
+
 	/* What host tells us, plus 2 for header & tailer. */
 	unsigned int sg_elems;
 
@@ -339,13 +355,20 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 		err = virtblk_add_req(vblk->vqs[qid].vq, vbr, vbr->sg, num);
 	if (err) {
 		virtqueue_kick(vblk->vqs[qid].vq);
-		blk_mq_stop_hw_queue(hctx);
+		/* Don't stop the queue if -ENOMEM: we may have failed to
+		 * bounce the buffer due to global resource outage.
+		 */
+		if (err == -ENOSPC)
+			blk_mq_stop_hw_queue(hctx);
 		spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
-		/* Out of mem doesn't actually happen, since we fall back
-		 * to direct descriptors */
-		if (err == -ENOMEM || err == -ENOSPC)
+		switch (err) {
+		case -ENOSPC:
 			return BLK_STS_DEV_RESOURCE;
-		return BLK_STS_IOERR;
+		case -ENOMEM:
+			return BLK_STS_RESOURCE;
+		default:
+			return BLK_STS_IOERR;
+		}
 	}
 
 	if (bd->last && virtqueue_kick_prepare(vblk->vqs[qid].vq))
@@ -381,10 +404,55 @@ out:
 	return err;
 }
 
+static void virtblk_get(struct virtio_blk *vblk)
+{
+	refcount_inc(&vblk->refs);
+}
+
+static void virtblk_put(struct virtio_blk *vblk)
+{
+	if (refcount_dec_and_test(&vblk->refs)) {
+		ida_simple_remove(&vd_index_ida, vblk->index);
+		mutex_destroy(&vblk->vdev_mutex);
+		kfree(vblk);
+	}
+}
+
+static int virtblk_open(struct block_device *bd, fmode_t mode)
+{
+	struct virtio_blk *vblk = bd->bd_disk->private_data;
+	int ret = 0;
+
+	mutex_lock(&vblk->vdev_mutex);
+
+	if (vblk->vdev)
+		virtblk_get(vblk);
+	else
+		ret = -ENXIO;
+
+	mutex_unlock(&vblk->vdev_mutex);
+	return ret;
+}
+
+static void virtblk_release(struct gendisk *disk, fmode_t mode)
+{
+	struct virtio_blk *vblk = disk->private_data;
+
+	virtblk_put(vblk);
+}
+
 /* We provide getgeo only to please some old bootloader/partitioning tools */
 static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo)
 {
 	struct virtio_blk *vblk = bd->bd_disk->private_data;
+	int ret = 0;
+
+	mutex_lock(&vblk->vdev_mutex);
+
+	if (!vblk->vdev) {
+		ret = -ENXIO;
+		goto out;
+	}
 
 	/* see if the host passed in geometry config */
 	if (virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_GEOMETRY)) {
@@ -400,12 +468,16 @@ static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo)
 		geo->sectors = 1 << 5;
 		geo->cylinders = get_capacity(bd->bd_disk) >> 11;
 	}
-	return 0;
+out:
+	mutex_unlock(&vblk->vdev_mutex);
+	return ret;
 }
 
 static const struct block_device_operations virtblk_fops = {
 	.ioctl  = virtblk_ioctl,
 	.owner  = THIS_MODULE,
+	.open = virtblk_open,
+	.release = virtblk_release,
 	.getgeo = virtblk_getgeo,
 };
 
@@ -760,6 +832,10 @@ static int virtblk_probe(struct virtio_device *vdev)
 		goto out_free_index;
 	}
 
+	/* This reference is dropped in virtblk_remove(). */
+	refcount_set(&vblk->refs, 1);
+	mutex_init(&vblk->vdev_mutex);
+
 	vblk->vdev = vdev;
 	vblk->sg_elems = sg_elems;
 
@@ -914,6 +990,7 @@ out_put_disk:
 	put_disk(vblk->disk);
 out_free_vq:
 	vdev->config->del_vqs(vdev);
+	kfree(vblk->vqs);
 out_free_vblk:
 	kfree(vblk);
 out_free_index:
@@ -925,8 +1002,6 @@ out:
 static void virtblk_remove(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk = vdev->priv;
-	int index = vblk->index;
-	int refc;
 
 	/* Make sure no work handler is accessing the device. */
 	flush_work(&vblk->config_work);
@@ -936,18 +1011,21 @@ static void virtblk_remove(struct virtio_device *vdev)
 
 	blk_mq_free_tag_set(&vblk->tag_set);
 
+	mutex_lock(&vblk->vdev_mutex);
+
 	/* Stop all the virtqueues. */
 	vdev->config->reset(vdev);
 
-	refc = kref_read(&disk_to_dev(vblk->disk)->kobj.kref);
+	/* Virtqueues are stopped, nothing can use vblk->vdev anymore. */
+	vblk->vdev = NULL;
+
 	put_disk(vblk->disk);
 	vdev->config->del_vqs(vdev);
 	kfree(vblk->vqs);
-	kfree(vblk);
 
-	/* Only free device id if we don't have any users */
-	if (refc == 1)
-		ida_simple_remove(&vd_index_ida, index);
+	mutex_unlock(&vblk->vdev_mutex);
+
+	virtblk_put(vblk);
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index fd1e19f1a49f..3666afa639d1 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -936,6 +936,8 @@ next:
 out_of_memory:
 	pr_alert("%s: out of memory\n", __func__);
 	put_free_pages(ring, pages_to_gnt, segs_to_map);
+	for (i = last_map; i < num; i++)
+		pages[i]->handle = BLKBACK_INVALID_HANDLE;
 	return -ENOMEM;
 }
 
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index b90dbcd99c03..c4cd68116e7f 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -171,6 +171,15 @@ static struct xen_blkif *xen_blkif_alloc(domid_t domid)
 	blkif->domid = domid;
 	atomic_set(&blkif->refcnt, 1);
 	init_completion(&blkif->drain_complete);
+
+	/*
+	 * Because freeing back to the cache may be deferred, it is not
+	 * safe to unload the module (and hence destroy the cache) until
+	 * this has completed. To prevent premature unloading, take an
+	 * extra module reference here and release only when the object
+	 * has been freed back to the cache.
+	 */
+	__module_get(THIS_MODULE);
 	INIT_WORK(&blkif->free_work, xen_blkif_deferred_free);
 
 	return blkif;
@@ -320,6 +329,7 @@ static void xen_blkif_free(struct xen_blkif *blkif)
 
 	/* Make sure everything is drained before shutting down */
 	kmem_cache_free(xen_blkif_cachep, blkif);
+	module_put(THIS_MODULE);
 }
 
 int __init xen_blkif_interface_init(void)
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index a74d03913822..ab5482202cfb 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -47,6 +47,7 @@
 #include <linux/bitmap.h>
 #include <linux/list.h>
 #include <linux/workqueue.h>
+#include <linux/sched/mm.h>
 
 #include <xen/xen.h>
 #include <xen/xenbus.h>
@@ -1113,8 +1114,8 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 	if (!VDEV_IS_EXTENDED(info->vdevice)) {
 		err = xen_translate_vdev(info->vdevice, &minor, &offset);
 		if (err)
-			return err;		
- 		nr_parts = PARTS_PER_DISK;
+			return err;
+		nr_parts = PARTS_PER_DISK;
 	} else {
 		minor = BLKIF_MINOR_EXT(info->vdevice);
 		nr_parts = PARTS_PER_EXT_DISK;
@@ -2188,10 +2189,12 @@ static void blkfront_setup_discard(struct blkfront_info *info)
 
 static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo)
 {
-	unsigned int psegs, grants;
+	unsigned int psegs, grants, memflags;
 	int err, i;
 	struct blkfront_info *info = rinfo->dev_info;
 
+	memflags = memalloc_noio_save();
+
 	if (info->max_indirect_segments == 0) {
 		if (!HAS_EXTRA_REQ)
 			grants = BLKIF_MAX_SEGMENTS_PER_REQUEST;
@@ -2223,7 +2226,7 @@ static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo)
 
 		BUG_ON(!list_empty(&rinfo->indirect_pages));
 		for (i = 0; i < num; i++) {
-			struct page *indirect_page = alloc_page(GFP_NOIO);
+			struct page *indirect_page = alloc_page(GFP_KERNEL);
 			if (!indirect_page)
 				goto out_of_memory;
 			list_add(&indirect_page->lru, &rinfo->indirect_pages);
@@ -2234,15 +2237,15 @@ static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo)
 		rinfo->shadow[i].grants_used =
 			kvcalloc(grants,
 				 sizeof(rinfo->shadow[i].grants_used[0]),
-				 GFP_NOIO);
+				 GFP_KERNEL);
 		rinfo->shadow[i].sg = kvcalloc(psegs,
 					       sizeof(rinfo->shadow[i].sg[0]),
-					       GFP_NOIO);
+					       GFP_KERNEL);
 		if (info->max_indirect_segments)
 			rinfo->shadow[i].indirect_grants =
 				kvcalloc(INDIRECT_GREFS(grants),
 					 sizeof(rinfo->shadow[i].indirect_grants[0]),
-					 GFP_NOIO);
+					 GFP_KERNEL);
 		if ((rinfo->shadow[i].grants_used == NULL) ||
 			(rinfo->shadow[i].sg == NULL) ||
 		     (info->max_indirect_segments &&
@@ -2251,6 +2254,7 @@ static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo)
 		sg_init_table(rinfo->shadow[i].sg, psegs);
 	}
 
+	memalloc_noio_restore(memflags);
 
 	return 0;
 
@@ -2270,6 +2274,9 @@ out_of_memory:
 			__free_page(indirect_page);
 		}
 	}
+
+	memalloc_noio_restore(memflags);
+
 	return -ENOMEM;
 }
 
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 4285e75e52c3..36d49159140f 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -626,7 +626,7 @@ static ssize_t writeback_store(struct device *dev,
 	struct bio bio;
 	struct bio_vec bio_vec;
 	struct page *page;
-	ssize_t ret;
+	ssize_t ret = len;
 	int mode;
 	unsigned long blk_idx = 0;
 
@@ -762,7 +762,6 @@ next:
 
 	if (blk_idx)
 		free_block_bdev(zram, blk_idx);
-	ret = len;
 	__free_page(page);
 release_init_lock:
 	up_read(&zram->init_lock);
@@ -2024,7 +2023,8 @@ static ssize_t hot_add_show(struct class *class,
 		return ret;
 	return scnprintf(buf, PAGE_SIZE, "%d\n", ret);
 }
-static CLASS_ATTR_RO(hot_add);
+static struct class_attribute class_attr_hot_add =
+	__ATTR(hot_add, 0400, hot_add_show, NULL);
 
 static ssize_t hot_remove_store(struct class *class,
 			struct class_attribute *attr,
diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c
index 3fe941539a1f..27790f332241 100644
--- a/drivers/bluetooth/btbcm.c
+++ b/drivers/bluetooth/btbcm.c
@@ -327,6 +327,7 @@ static const struct bcm_subver_table bcm_uart_subver_table[] = {
 	{ 0x410e, "BCM43341B0"	},	/* 002.001.014 */
 	{ 0x4204, "BCM2076B1"	},	/* 002.002.004 */
 	{ 0x4406, "BCM4324B3"	},	/* 002.004.006 */
+	{ 0x4606, "BCM4324B5"	},	/* 002.006.006 */
 	{ 0x6109, "BCM4335C0"	},	/* 003.001.009 */
 	{ 0x610c, "BCM4354"	},	/* 003.001.012 */
 	{ 0x2122, "BCM4343A0"	},	/* 001.001.034 */
@@ -339,6 +340,7 @@ static const struct bcm_subver_table bcm_uart_subver_table[] = {
 };
 
 static const struct bcm_subver_table bcm_usb_subver_table[] = {
+	{ 0x2105, "BCM20703A1"	},	/* 001.001.005 */
 	{ 0x210b, "BCM43142A0"	},	/* 001.001.011 */
 	{ 0x2112, "BCM4314A0"	},	/* 001.001.018 */
 	{ 0x2118, "BCM20702A0"	},	/* 001.001.024 */
@@ -436,6 +438,12 @@ int btbcm_finalize(struct hci_dev *hdev)
 
 	set_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks);
 
+	/* Some devices ship with the controller default address.
+	 * Allow the bootloader to set a valid address through the
+	 * device tree.
+	 */
+	set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(btbcm_finalize);
diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c
index 0f3a020703ab..4c7978cb1786 100644
--- a/drivers/bluetooth/btmrvl_sdio.c
+++ b/drivers/bluetooth/btmrvl_sdio.c
@@ -328,7 +328,7 @@ static const struct btmrvl_sdio_device btmrvl_sdio_sd8897 = {
 
 static const struct btmrvl_sdio_device btmrvl_sdio_sd8977 = {
 	.helper         = NULL,
-	.firmware       = "mrvl/sd8977_uapsta.bin",
+	.firmware       = "mrvl/sdsd8977_combo_v2.bin",
 	.reg            = &btmrvl_reg_8977,
 	.support_pscan_win_report = true,
 	.sd_blksz_fw_dl = 256,
@@ -346,7 +346,7 @@ static const struct btmrvl_sdio_device btmrvl_sdio_sd8987 = {
 
 static const struct btmrvl_sdio_device btmrvl_sdio_sd8997 = {
 	.helper         = NULL,
-	.firmware       = "mrvl/sd8997_uapsta.bin",
+	.firmware       = "mrvl/sdsd8997_combo_v4.bin",
 	.reg            = &btmrvl_reg_8997,
 	.support_pscan_win_report = true,
 	.sd_blksz_fw_dl = 256,
@@ -1831,6 +1831,6 @@ MODULE_FIRMWARE("mrvl/sd8787_uapsta.bin");
 MODULE_FIRMWARE("mrvl/sd8797_uapsta.bin");
 MODULE_FIRMWARE("mrvl/sd8887_uapsta.bin");
 MODULE_FIRMWARE("mrvl/sd8897_uapsta.bin");
-MODULE_FIRMWARE("mrvl/sd8977_uapsta.bin");
+MODULE_FIRMWARE("mrvl/sdsd8977_combo_v2.bin");
 MODULE_FIRMWARE("mrvl/sd8987_uapsta.bin");
-MODULE_FIRMWARE("mrvl/sd8997_uapsta.bin");
+MODULE_FIRMWARE("mrvl/sdsd8997_combo_v4.bin");
diff --git a/drivers/bluetooth/btmtksdio.c b/drivers/bluetooth/btmtksdio.c
index 813338288453..b7de7cb8cca9 100644
--- a/drivers/bluetooth/btmtksdio.c
+++ b/drivers/bluetooth/btmtksdio.c
@@ -684,7 +684,7 @@ static int mtk_setup_firmware(struct hci_dev *hdev, const char *fwname)
 	const u8 *fw_ptr;
 	size_t fw_size;
 	int err, dlen;
-	u8 flag;
+	u8 flag, param;
 
 	err = request_firmware(&fw, fwname, &hdev->dev);
 	if (err < 0) {
@@ -692,6 +692,20 @@ static int mtk_setup_firmware(struct hci_dev *hdev, const char *fwname)
 		return err;
 	}
 
+	/* Power on data RAM the firmware relies on. */
+	param = 1;
+	wmt_params.op = MTK_WMT_FUNC_CTRL;
+	wmt_params.flag = 3;
+	wmt_params.dlen = sizeof(param);
+	wmt_params.data = &param;
+	wmt_params.status = NULL;
+
+	err = mtk_hci_wmt_sync(hdev, &wmt_params);
+	if (err < 0) {
+		bt_dev_err(hdev, "Failed to power on data RAM (%d)", err);
+		return err;
+	}
+
 	fw_ptr = fw->data;
 	fw_size = fw->size;
 
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index aa6e2f9d4861..d392524dac14 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -1161,7 +1161,7 @@ static int btusb_open(struct hci_dev *hdev)
 	if (data->setup_on_usb) {
 		err = data->setup_on_usb(hdev);
 		if (err < 0)
-			return err;
+			goto setup_fail;
 	}
 
 	data->intf->needs_remote_wakeup = 1;
@@ -1193,6 +1193,7 @@ done:
 
 failed:
 	clear_bit(BTUSB_INTR_RUNNING, &data->flags);
+setup_fail:
 	usb_autopm_put_interface(data->intf);
 	return err;
 }
diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c
index ae2624fce913..02b742270047 100644
--- a/drivers/bluetooth/hci_bcm.c
+++ b/drivers/bluetooth/hci_bcm.c
@@ -107,6 +107,7 @@ struct bcm_device {
 	u32			oper_speed;
 	int			irq;
 	bool			irq_active_low;
+	bool			irq_acquired;
 
 #ifdef CONFIG_PM
 	struct hci_uart		*hu;
@@ -319,6 +320,8 @@ static int bcm_request_irq(struct bcm_data *bcm)
 		goto unlock;
 	}
 
+	bdev->irq_acquired = true;
+
 	device_init_wakeup(bdev->dev, true);
 
 	pm_runtime_set_autosuspend_delay(bdev->dev,
@@ -487,7 +490,7 @@ static int bcm_close(struct hci_uart *hu)
 	}
 
 	if (bdev) {
-		if (IS_ENABLED(CONFIG_PM) && bdev->irq > 0) {
+		if (IS_ENABLED(CONFIG_PM) && bdev->irq_acquired) {
 			devm_free_irq(bdev->dev, bdev->irq, bdev);
 			device_init_wakeup(bdev->dev, false);
 			pm_runtime_disable(bdev->dev);
diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c
index dacf297baf59..5df0651b6cd5 100644
--- a/drivers/bluetooth/hci_h5.c
+++ b/drivers/bluetooth/hci_h5.c
@@ -790,7 +790,7 @@ static int h5_serdev_probe(struct serdev_device *serdev)
 	if (!h5)
 		return -ENOMEM;
 
-	set_bit(HCI_UART_RESET_ON_INIT, &h5->serdev_hu.flags);
+	set_bit(HCI_UART_RESET_ON_INIT, &h5->serdev_hu.hdev_flags);
 
 	h5->hu = &h5->serdev_hu;
 	h5->serdev_hu.serdev = serdev;
diff --git a/drivers/bluetooth/hci_serdev.c b/drivers/bluetooth/hci_serdev.c
index 4652896d4990..ad2f26cb2622 100644
--- a/drivers/bluetooth/hci_serdev.c
+++ b/drivers/bluetooth/hci_serdev.c
@@ -357,7 +357,8 @@ void hci_uart_unregister_device(struct hci_uart *hu)
 	struct hci_dev *hdev = hu->hdev;
 
 	clear_bit(HCI_UART_PROTO_READY, &hu->flags);
-	hci_unregister_dev(hdev);
+	if (test_bit(HCI_UART_REGISTERED, &hu->flags))
+		hci_unregister_dev(hdev);
 	hci_free_dev(hdev);
 
 	cancel_work_sync(&hu->write_work);
diff --git a/drivers/bus/Kconfig b/drivers/bus/Kconfig
index 1851112ccc29..4587ef22ee0b 100644
--- a/drivers/bus/Kconfig
+++ b/drivers/bus/Kconfig
@@ -128,7 +128,6 @@ config TEGRA_ACONNECT
 	tristate "Tegra ACONNECT Bus Driver"
 	depends on ARCH_TEGRA_210_SOC
 	depends on OF && PM
-	select PM_CLK
 	help
 	  Driver for the Tegra ACONNECT bus which is used to interface with
 	  the devices inside the Audio Processing Engine (APE) for Tegra210.
diff --git a/drivers/bus/sunxi-rsb.c b/drivers/bus/sunxi-rsb.c
index 1b76d9585902..2ca2cc56bcef 100644
--- a/drivers/bus/sunxi-rsb.c
+++ b/drivers/bus/sunxi-rsb.c
@@ -345,7 +345,7 @@ static int sunxi_rsb_read(struct sunxi_rsb *rsb, u8 rtaddr, u8 addr,
 	if (ret)
 		goto unlock;
 
-	*buf = readl(rsb->regs + RSB_DATA);
+	*buf = readl(rsb->regs + RSB_DATA) & GENMASK(len * 8 - 1, 0);
 
 unlock:
 	mutex_unlock(&rsb->lock);
diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c
index 0d122440d111..801c39ca46a5 100644
--- a/drivers/bus/ti-sysc.c
+++ b/drivers/bus/ti-sysc.c
@@ -296,6 +296,12 @@ static int sysc_get_clocks(struct sysc *ddata)
 		return -EINVAL;
 	}
 
+	/* Always add a slot for main clocks fck and ick even if unused */
+	if (!nr_fck)
+		ddata->nr_clocks++;
+	if (!nr_ick)
+		ddata->nr_clocks++;
+
 	ddata->clocks = devm_kcalloc(ddata->dev,
 				     ddata->nr_clocks, sizeof(*ddata->clocks),
 				     GFP_KERNEL);
@@ -374,7 +380,7 @@ static int sysc_enable_opt_clocks(struct sysc *ddata)
 	struct clk *clock;
 	int i, error;
 
-	if (!ddata->clocks)
+	if (!ddata->clocks || ddata->nr_clocks < SYSC_OPTFCK0 + 1)
 		return 0;
 
 	for (i = SYSC_OPTFCK0; i < SYSC_MAX_CLOCKS; i++) {
@@ -408,7 +414,7 @@ static void sysc_disable_opt_clocks(struct sysc *ddata)
 	struct clk *clock;
 	int i;
 
-	if (!ddata->clocks)
+	if (!ddata->clocks || ddata->nr_clocks < SYSC_OPTFCK0 + 1)
 		return;
 
 	for (i = SYSC_OPTFCK0; i < SYSC_MAX_CLOCKS; i++) {
@@ -844,6 +850,9 @@ set_midle:
 	reg |= best_mode << regbits->midle_shift;
 	sysc_write(ddata, ddata->offsets[SYSC_SYSCONFIG], reg);
 
+	/* Flush posted write */
+	sysc_read(ddata, ddata->offsets[SYSC_SYSCONFIG]);
+
 	return 0;
 }
 
@@ -911,6 +920,9 @@ set_sidle:
 	reg |= best_mode << regbits->sidle_shift;
 	sysc_write(ddata, ddata->offsets[SYSC_SYSCONFIG], reg);
 
+	/* Flush posted write */
+	sysc_read(ddata, ddata->offsets[SYSC_SYSCONFIG]);
+
 	return 0;
 }
 
@@ -1097,6 +1109,10 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = {
 		   SYSC_QUIRK_LEGACY_IDLE),
 	SYSC_QUIRK("smartreflex", 0, -1, 0x24, -1, 0x00000000, 0xffffffff,
 		   SYSC_QUIRK_LEGACY_IDLE),
+	SYSC_QUIRK("usb_host_hs", 0, 0, 0x10, 0x14, 0x50700100, 0xffffffff,
+		   SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_SWSUP_MSTANDBY),
+	SYSC_QUIRK("usb_host_hs", 0, 0, 0x10, -1, 0x50700101, 0xffffffff,
+		   SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_SWSUP_MSTANDBY),
 	SYSC_QUIRK("smartreflex", 0, -1, 0x38, -1, 0x00000000, 0xffffffff,
 		   SYSC_QUIRK_LEGACY_IDLE),
 	SYSC_QUIRK("timer", 0, 0, 0x10, 0x14, 0x00000015, 0xffffffff,
@@ -1169,8 +1185,6 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = {
 	SYSC_QUIRK("timer32k", 0, 0, 0x4, -1, 0x00000060, 0xffffffff, 0),
 	SYSC_QUIRK("usbhstll", 0, 0, 0x10, 0x14, 0x00000004, 0xffffffff, 0),
 	SYSC_QUIRK("usbhstll", 0, 0, 0x10, 0x14, 0x00000008, 0xffffffff, 0),
-	SYSC_QUIRK("usb_host_hs", 0, 0, 0x10, 0x14, 0x50700100, 0xffffffff, 0),
-	SYSC_QUIRK("usb_host_hs", 0, 0, 0x10, -1, 0x50700101, 0xffffffff, 0),
 	SYSC_QUIRK("usb_otg_hs", 0, 0x400, 0x404, 0x408, 0x00000050,
 		   0xffffffff, 0),
 	SYSC_QUIRK("wdt", 0, 0, 0x10, 0x14, 0x502a0500, 0xfffff0f0, 0),
diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c
index c6271ce250b3..0941d38b2d32 100644
--- a/drivers/char/agp/intel-gtt.c
+++ b/drivers/char/agp/intel-gtt.c
@@ -304,8 +304,10 @@ static int intel_gtt_setup_scratch_page(void)
 	if (intel_private.needs_dmar) {
 		dma_addr = pci_map_page(intel_private.pcidev, page, 0,
 				    PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
-		if (pci_dma_mapping_error(intel_private.pcidev, dma_addr))
+		if (pci_dma_mapping_error(intel_private.pcidev, dma_addr)) {
+			__free_page(page);
 			return -EINVAL;
+		}
 
 		intel_private.scratch_page_dma = dma_addr;
 	} else
@@ -846,6 +848,7 @@ void intel_gtt_insert_page(dma_addr_t addr,
 			   unsigned int flags)
 {
 	intel_private.driver->write_entry(addr, pg, flags);
+	readl(intel_private.gtt + pg);
 	if (intel_private.driver->chipset_flush)
 		intel_private.driver->chipset_flush();
 }
@@ -871,7 +874,7 @@ void intel_gtt_insert_sg_entries(struct sg_table *st,
 			j++;
 		}
 	}
-	wmb();
+	readl(intel_private.gtt + j - 1);
 	if (intel_private.driver->chipset_flush)
 		intel_private.driver->chipset_flush();
 }
@@ -1105,6 +1108,7 @@ static void i9xx_cleanup(void)
 
 static void i9xx_chipset_flush(void)
 {
+	wmb();
 	if (intel_private.i9xx_flush_page)
 		writel(1, intel_private.i9xx_flush_page);
 }
diff --git a/drivers/char/hw_random/imx-rngc.c b/drivers/char/hw_random/imx-rngc.c
index 69f537980004..76ac1365646e 100644
--- a/drivers/char/hw_random/imx-rngc.c
+++ b/drivers/char/hw_random/imx-rngc.c
@@ -105,8 +105,10 @@ static int imx_rngc_self_test(struct imx_rngc *rngc)
 		return -ETIMEDOUT;
 	}
 
-	if (rngc->err_reg != 0)
+	if (rngc->err_reg != 0) {
+		imx_rngc_irq_mask_clear(rngc);
 		return -EIO;
+	}
 
 	return 0;
 }
diff --git a/drivers/char/hw_random/ks-sa-rng.c b/drivers/char/hw_random/ks-sa-rng.c
index a67430010aa6..5c7d3dfcfdd0 100644
--- a/drivers/char/hw_random/ks-sa-rng.c
+++ b/drivers/char/hw_random/ks-sa-rng.c
@@ -208,6 +208,7 @@ static int ks_sa_rng_probe(struct platform_device *pdev)
 	ret = pm_runtime_get_sync(dev);
 	if (ret < 0) {
 		dev_err(dev, "Failed to enable SA power-domain\n");
+		pm_runtime_put_noidle(dev);
 		pm_runtime_disable(dev);
 		return ret;
 	}
diff --git a/drivers/char/hw_random/omap3-rom-rng.c b/drivers/char/hw_random/omap3-rom-rng.c
index 648e39ce6bd9..8df3cad7c97a 100644
--- a/drivers/char/hw_random/omap3-rom-rng.c
+++ b/drivers/char/hw_random/omap3-rom-rng.c
@@ -20,6 +20,8 @@
 #include <linux/workqueue.h>
 #include <linux/clk.h>
 #include <linux/err.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 
 #define RNG_RESET			0x01
@@ -86,14 +88,18 @@ static int omap3_rom_rng_read(struct hwrng *rng, void *data, size_t max, bool w)
 
 static struct hwrng omap3_rom_rng_ops = {
 	.name		= "omap3-rom",
-	.read		= omap3_rom_rng_read,
 };
 
 static int omap3_rom_rng_probe(struct platform_device *pdev)
 {
 	int ret = 0;
 
-	pr_info("initializing\n");
+	omap3_rom_rng_ops.read = of_device_get_match_data(&pdev->dev);
+	if (!omap3_rom_rng_ops.read) {
+		dev_err(&pdev->dev, "missing rom code handler\n");
+
+		return -ENODEV;
+	}
 
 	omap3_rom_rng_call = pdev->dev.platform_data;
 	if (!omap3_rom_rng_call) {
@@ -126,9 +132,16 @@ static int omap3_rom_rng_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct of_device_id omap_rom_rng_match[] = {
+	{ .compatible = "nokia,n900-rom-rng", .data = omap3_rom_rng_read, },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, omap_rom_rng_match);
+
 static struct platform_driver omap3_rom_rng_driver = {
 	.driver = {
 		.name		= "omap3-rom-rng",
+		.of_match_table = omap_rom_rng_match,
 	},
 	.probe		= omap3_rom_rng_probe,
 	.remove		= omap3_rom_rng_remove,
diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index 1a53b07e8028..7d04e7fac196 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -33,6 +33,7 @@
 #include <linux/workqueue.h>
 #include <linux/uuid.h>
 #include <linux/nospec.h>
+#include <linux/vmalloc.h>
 
 #define IPMI_DRIVER_VERSION "39.2"
 
@@ -1168,7 +1169,7 @@ static void free_user_work(struct work_struct *work)
 					      remove_work);
 
 	cleanup_srcu_struct(&user->release_barrier);
-	kfree(user);
+	vfree(user);
 }
 
 int ipmi_create_user(unsigned int          if_num,
@@ -1200,7 +1201,7 @@ int ipmi_create_user(unsigned int          if_num,
 	if (rv)
 		return rv;
 
-	new_user = kmalloc(sizeof(*new_user), GFP_KERNEL);
+	new_user = vzalloc(sizeof(*new_user));
 	if (!new_user)
 		return -ENOMEM;
 
@@ -1247,7 +1248,7 @@ int ipmi_create_user(unsigned int          if_num,
 
 out_kfree:
 	srcu_read_unlock(&ipmi_interfaces_srcu, index);
-	kfree(new_user);
+	vfree(new_user);
 	return rv;
 }
 EXPORT_SYMBOL(ipmi_create_user);
@@ -3204,8 +3205,8 @@ static void __get_guid(struct ipmi_smi *intf)
 	if (rv)
 		/* Send failed, no GUID available. */
 		bmc->dyn_guid_set = 0;
-
-	wait_event(intf->waitq, bmc->dyn_guid_set != 2);
+	else
+		wait_event(intf->waitq, bmc->dyn_guid_set != 2);
 
 	/* dyn_guid_set makes the guid data available. */
 	smp_rmb();
diff --git a/drivers/char/ipmi/ipmi_si_platform.c b/drivers/char/ipmi/ipmi_si_platform.c
index 0cd849675d99..b3c278b09247 100644
--- a/drivers/char/ipmi/ipmi_si_platform.c
+++ b/drivers/char/ipmi/ipmi_si_platform.c
@@ -194,7 +194,7 @@ static int platform_ipmi_probe(struct platform_device *pdev)
 	else
 		io.slave_addr = slave_addr;
 
-	io.irq = platform_get_irq(pdev, 0);
+	io.irq = platform_get_irq_optional(pdev, 0);
 	if (io.irq > 0)
 		io.irq_setup = ipmi_std_irq_setup;
 	else
@@ -378,7 +378,7 @@ static int acpi_ipmi_probe(struct platform_device *pdev)
 		io.irq = tmp;
 		io.irq_setup = acpi_gpe_irq_setup;
 	} else {
-		int irq = platform_get_irq(pdev, 0);
+		int irq = platform_get_irq_optional(pdev, 0);
 
 		if (irq > 0) {
 			io.irq = irq;
diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c
index 305fa5054274..2412a9baf8a2 100644
--- a/drivers/char/ipmi/ipmi_ssif.c
+++ b/drivers/char/ipmi/ipmi_ssif.c
@@ -776,10 +776,14 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result,
 	flags = ipmi_ssif_lock_cond(ssif_info, &oflags);
 	msg = ssif_info->curr_msg;
 	if (msg) {
+		if (data) {
+			if (len > IPMI_MAX_MSG_LENGTH)
+				len = IPMI_MAX_MSG_LENGTH;
+			memcpy(msg->rsp, data, len);
+		} else {
+			len = 0;
+		}
 		msg->rsp_size = len;
-		if (msg->rsp_size > IPMI_MAX_MSG_LENGTH)
-			msg->rsp_size = IPMI_MAX_MSG_LENGTH;
-		memcpy(msg->rsp, data, msg->rsp_size);
 		ssif_info->curr_msg = NULL;
 	}
 
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 5d5ea4ce1442..4d2fe922e7ed 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1330,6 +1330,7 @@ void add_interrupt_randomness(int irq, int irq_flags)
 
 	fast_mix(fast_pool);
 	add_interrupt_bench(cycles);
+	this_cpu_add(net_rand_state.s1, fast_pool->pool[cycles & 3]);
 
 	if (unlikely(crng_init == 0)) {
 		if ((fast_pool->count >= 64) &&
@@ -1687,8 +1688,9 @@ static void _warn_unseeded_randomness(const char *func_name, void *caller,
 	print_once = true;
 #endif
 	if (__ratelimit(&unseeded_warning))
-		pr_notice("random: %s called from %pS with crng_init=%d\n",
-			  func_name, caller, crng_init);
+		printk_deferred(KERN_NOTICE "random: %s called from %pS "
+				"with crng_init=%d\n", func_name, caller,
+				crng_init);
 }
 
 /*
@@ -2297,11 +2299,11 @@ struct batched_entropy {
 
 /*
  * Get a random word for internal kernel use only. The quality of the random
- * number is either as good as RDRAND or as good as /dev/urandom, with the
- * goal of being quite fast and not depleting entropy. In order to ensure
+ * number is good as /dev/urandom, but there is no backtrack protection, with
+ * the goal of being quite fast and not depleting entropy. In order to ensure
  * that the randomness provided by this function is okay, the function
- * wait_for_random_bytes() should be called and return 0 at least once
- * at any point prior.
+ * wait_for_random_bytes() should be called and return 0 at least once at any
+ * point prior.
  */
 static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u64) = {
 	.batch_lock	= __SPIN_LOCK_UNLOCKED(batched_entropy_u64.lock),
@@ -2314,15 +2316,6 @@ u64 get_random_u64(void)
 	struct batched_entropy *batch;
 	static void *previous;
 
-#if BITS_PER_LONG == 64
-	if (arch_get_random_long((unsigned long *)&ret))
-		return ret;
-#else
-	if (arch_get_random_long((unsigned long *)&ret) &&
-	    arch_get_random_long((unsigned long *)&ret + 1))
-	    return ret;
-#endif
-
 	warn_unseeded_randomness(&previous);
 
 	batch = raw_cpu_ptr(&batched_entropy_u64);
@@ -2347,9 +2340,6 @@ u32 get_random_u32(void)
 	struct batched_entropy *batch;
 	static void *previous;
 
-	if (arch_get_random_int(&ret))
-		return ret;
-
 	warn_unseeded_randomness(&previous);
 
 	batch = raw_cpu_ptr(&batched_entropy_u32);
diff --git a/drivers/char/tpm/eventlog/common.c b/drivers/char/tpm/eventlog/common.c
index 7a0fca659b6a..7460f230bae4 100644
--- a/drivers/char/tpm/eventlog/common.c
+++ b/drivers/char/tpm/eventlog/common.c
@@ -99,11 +99,8 @@ static int tpm_read_log(struct tpm_chip *chip)
  *
  * If an event log is found then the securityfs files are setup to
  * export it to userspace, otherwise nothing is done.
- *
- * Returns -ENODEV if the firmware has no event log or securityfs is not
- * supported.
  */
-int tpm_bios_log_setup(struct tpm_chip *chip)
+void tpm_bios_log_setup(struct tpm_chip *chip)
 {
 	const char *name = dev_name(&chip->dev);
 	unsigned int cnt;
@@ -112,7 +109,7 @@ int tpm_bios_log_setup(struct tpm_chip *chip)
 
 	rc = tpm_read_log(chip);
 	if (rc < 0)
-		return rc;
+		return;
 	log_version = rc;
 
 	cnt = 0;
@@ -158,13 +155,12 @@ int tpm_bios_log_setup(struct tpm_chip *chip)
 		cnt++;
 	}
 
-	return 0;
+	return;
 
 err:
-	rc = PTR_ERR(chip->bios_dir[cnt]);
 	chip->bios_dir[cnt] = NULL;
 	tpm_bios_log_teardown(chip);
-	return rc;
+	return;
 }
 
 void tpm_bios_log_teardown(struct tpm_chip *chip)
diff --git a/drivers/char/tpm/eventlog/tpm1.c b/drivers/char/tpm/eventlog/tpm1.c
index 739b1d9d16b6..2c96977ad080 100644
--- a/drivers/char/tpm/eventlog/tpm1.c
+++ b/drivers/char/tpm/eventlog/tpm1.c
@@ -115,6 +115,7 @@ static void *tpm1_bios_measurements_next(struct seq_file *m, void *v,
 	u32 converted_event_size;
 	u32 converted_event_type;
 
+	(*pos)++;
 	converted_event_size = do_endian_conversion(event->event_size);
 
 	v += sizeof(struct tcpa_event) + converted_event_size;
@@ -132,7 +133,6 @@ static void *tpm1_bios_measurements_next(struct seq_file *m, void *v,
 	    ((v + sizeof(struct tcpa_event) + converted_event_size) > limit))
 		return NULL;
 
-	(*pos)++;
 	return v;
 }
 
diff --git a/drivers/char/tpm/eventlog/tpm2.c b/drivers/char/tpm/eventlog/tpm2.c
index d506362e046f..fe86552fca1f 100644
--- a/drivers/char/tpm/eventlog/tpm2.c
+++ b/drivers/char/tpm/eventlog/tpm2.c
@@ -139,6 +139,7 @@ static void *tpm2_bios_measurements_next(struct seq_file *m, void *v,
 	size_t event_size;
 	void *marker;
 
+	(*pos)++;
 	event_header = log->bios_event_log;
 
 	if (v == SEQ_START_TOKEN) {
@@ -163,7 +164,6 @@ static void *tpm2_bios_measurements_next(struct seq_file *m, void *v,
 	if (((v + event_size) >= limit) || (event_size == 0))
 		return NULL;
 
-	(*pos)++;
 	return v;
 }
 
diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c
index 4838c6a9f0f2..61f9acc5d741 100644
--- a/drivers/char/tpm/tpm-chip.c
+++ b/drivers/char/tpm/tpm-chip.c
@@ -389,13 +389,8 @@ struct tpm_chip *tpm_chip_alloc(struct device *pdev,
 	chip->cdev.owner = THIS_MODULE;
 	chip->cdevs.owner = THIS_MODULE;
 
-	chip->work_space.context_buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!chip->work_space.context_buf) {
-		rc = -ENOMEM;
-		goto out;
-	}
-	chip->work_space.session_buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!chip->work_space.session_buf) {
+	rc = tpm2_init_space(&chip->work_space, TPM2_SPACE_BUFFER_SIZE);
+	if (rc) {
 		rc = -ENOMEM;
 		goto out;
 	}
@@ -599,9 +594,7 @@ int tpm_chip_register(struct tpm_chip *chip)
 
 	tpm_sysfs_add_device(chip);
 
-	rc = tpm_bios_log_setup(chip);
-	if (rc != 0 && rc != -ENODEV)
-		return rc;
+	tpm_bios_log_setup(chip);
 
 	tpm_add_ppi(chip);
 
diff --git a/drivers/char/tpm/tpm-dev-common.c b/drivers/char/tpm/tpm-dev-common.c
index 87f449340202..1784530b8387 100644
--- a/drivers/char/tpm/tpm-dev-common.c
+++ b/drivers/char/tpm/tpm-dev-common.c
@@ -189,15 +189,6 @@ ssize_t tpm_common_write(struct file *file, const char __user *buf,
 		goto out;
 	}
 
-	/* atomic tpm command send and result receive. We only hold the ops
-	 * lock during this period so that the tpm can be unregistered even if
-	 * the char dev is held open.
-	 */
-	if (tpm_try_get_ops(priv->chip)) {
-		ret = -EPIPE;
-		goto out;
-	}
-
 	priv->response_length = 0;
 	priv->response_read = false;
 	*off = 0;
@@ -211,11 +202,19 @@ ssize_t tpm_common_write(struct file *file, const char __user *buf,
 	if (file->f_flags & O_NONBLOCK) {
 		priv->command_enqueued = true;
 		queue_work(tpm_dev_wq, &priv->async_work);
-		tpm_put_ops(priv->chip);
 		mutex_unlock(&priv->buffer_mutex);
 		return size;
 	}
 
+	/* atomic tpm command send and result receive. We only hold the ops
+	 * lock during this period so that the tpm can be unregistered even if
+	 * the char dev is held open.
+	 */
+	if (tpm_try_get_ops(priv->chip)) {
+		ret = -EPIPE;
+		goto out;
+	}
+
 	ret = tpm_dev_transmit(priv->chip, priv->space, priv->data_buffer,
 			       sizeof(priv->data_buffer));
 	tpm_put_ops(priv->chip);
diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index d7a3888ad80f..b86ee5b18855 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -322,7 +322,7 @@ int tpm_pcr_extend(struct tpm_chip *chip, u32 pcr_idx,
 
 	for (i = 0; i < chip->nr_allocated_banks; i++) {
 		if (digests[i].alg_id != chip->allocated_banks[i].alg_id) {
-			rc = EINVAL;
+			rc = -EINVAL;
 			goto out;
 		}
 	}
diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h
index a7fea3e0ca86..37f010421a36 100644
--- a/drivers/char/tpm/tpm.h
+++ b/drivers/char/tpm/tpm.h
@@ -177,6 +177,9 @@ struct tpm_header {
 
 #define TPM_TAG_RQU_COMMAND 193
 
+/* TPM2 specific constants. */
+#define TPM2_SPACE_BUFFER_SIZE		16384 /* 16 kB */
+
 struct	stclear_flags_t {
 	__be16	tag;
 	u8	deactivated;
@@ -456,7 +459,7 @@ void tpm2_shutdown(struct tpm_chip *chip, u16 shutdown_type);
 unsigned long tpm2_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal);
 int tpm2_probe(struct tpm_chip *chip);
 int tpm2_find_cc(struct tpm_chip *chip, u32 cc);
-int tpm2_init_space(struct tpm_space *space);
+int tpm2_init_space(struct tpm_space *space, unsigned int buf_size);
 void tpm2_del_space(struct tpm_chip *chip, struct tpm_space *space);
 void tpm2_flush_space(struct tpm_chip *chip);
 int tpm2_prepare_space(struct tpm_chip *chip, struct tpm_space *space, u8 *cmd,
@@ -464,7 +467,7 @@ int tpm2_prepare_space(struct tpm_chip *chip, struct tpm_space *space, u8 *cmd,
 int tpm2_commit_space(struct tpm_chip *chip, struct tpm_space *space, void *buf,
 		      size_t *bufsiz);
 
-int tpm_bios_log_setup(struct tpm_chip *chip);
+void tpm_bios_log_setup(struct tpm_chip *chip);
 void tpm_bios_log_teardown(struct tpm_chip *chip);
 int tpm_dev_common_init(void);
 void tpm_dev_common_exit(void);
diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c
index 5817dfe5c5d2..2f8026b71933 100644
--- a/drivers/char/tpm/tpm2-cmd.c
+++ b/drivers/char/tpm/tpm2-cmd.c
@@ -831,6 +831,8 @@ static int tpm2_init_bank_info(struct tpm_chip *chip, u32 bank_index)
 		return 0;
 	}
 
+	bank->crypto_id = HASH_ALGO__LAST;
+
 	return tpm2_pcr_read(chip, 0, &digest, &bank->digest_size);
 }
 
diff --git a/drivers/char/tpm/tpm2-space.c b/drivers/char/tpm/tpm2-space.c
index 982d341d8837..784b8b3cb903 100644
--- a/drivers/char/tpm/tpm2-space.c
+++ b/drivers/char/tpm/tpm2-space.c
@@ -38,18 +38,21 @@ static void tpm2_flush_sessions(struct tpm_chip *chip, struct tpm_space *space)
 	}
 }
 
-int tpm2_init_space(struct tpm_space *space)
+int tpm2_init_space(struct tpm_space *space, unsigned int buf_size)
 {
-	space->context_buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	space->context_buf = kzalloc(buf_size, GFP_KERNEL);
 	if (!space->context_buf)
 		return -ENOMEM;
 
-	space->session_buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	space->session_buf = kzalloc(buf_size, GFP_KERNEL);
 	if (space->session_buf == NULL) {
 		kfree(space->context_buf);
+		/* Prevent caller getting a dangling pointer. */
+		space->context_buf = NULL;
 		return -ENOMEM;
 	}
 
+	space->buf_size = buf_size;
 	return 0;
 }
 
@@ -311,8 +314,10 @@ int tpm2_prepare_space(struct tpm_chip *chip, struct tpm_space *space, u8 *cmd,
 	       sizeof(space->context_tbl));
 	memcpy(&chip->work_space.session_tbl, &space->session_tbl,
 	       sizeof(space->session_tbl));
-	memcpy(chip->work_space.context_buf, space->context_buf, PAGE_SIZE);
-	memcpy(chip->work_space.session_buf, space->session_buf, PAGE_SIZE);
+	memcpy(chip->work_space.context_buf, space->context_buf,
+	       space->buf_size);
+	memcpy(chip->work_space.session_buf, space->session_buf,
+	       space->buf_size);
 
 	rc = tpm2_load_space(chip);
 	if (rc) {
@@ -492,7 +497,7 @@ static int tpm2_save_space(struct tpm_chip *chip)
 			continue;
 
 		rc = tpm2_save_context(chip, space->context_tbl[i],
-				       space->context_buf, PAGE_SIZE,
+				       space->context_buf, space->buf_size,
 				       &offset);
 		if (rc == -ENOENT) {
 			space->context_tbl[i] = 0;
@@ -509,9 +514,8 @@ static int tpm2_save_space(struct tpm_chip *chip)
 			continue;
 
 		rc = tpm2_save_context(chip, space->session_tbl[i],
-				       space->session_buf, PAGE_SIZE,
+				       space->session_buf, space->buf_size,
 				       &offset);
-
 		if (rc == -ENOENT) {
 			/* handle error saving session, just forget it */
 			space->session_tbl[i] = 0;
@@ -557,8 +561,10 @@ int tpm2_commit_space(struct tpm_chip *chip, struct tpm_space *space,
 	       sizeof(space->context_tbl));
 	memcpy(&space->session_tbl, &chip->work_space.session_tbl,
 	       sizeof(space->session_tbl));
-	memcpy(space->context_buf, chip->work_space.context_buf, PAGE_SIZE);
-	memcpy(space->session_buf, chip->work_space.session_buf, PAGE_SIZE);
+	memcpy(space->context_buf, chip->work_space.context_buf,
+	       space->buf_size);
+	memcpy(space->session_buf, chip->work_space.session_buf,
+	       space->buf_size);
 
 	return 0;
 out:
diff --git a/drivers/char/tpm/tpm_ibmvtpm.c b/drivers/char/tpm/tpm_ibmvtpm.c
index 78cc52690177..e82013d587b4 100644
--- a/drivers/char/tpm/tpm_ibmvtpm.c
+++ b/drivers/char/tpm/tpm_ibmvtpm.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2012 IBM Corporation
+ * Copyright (C) 2012-2020 IBM Corporation
  *
  * Author: Ashley Lai <ashleydlai@gmail.com>
  *
@@ -134,6 +134,64 @@ static int tpm_ibmvtpm_recv(struct tpm_chip *chip, u8 *buf, size_t count)
 }
 
 /**
+ * ibmvtpm_crq_send_init - Send a CRQ initialize message
+ * @ibmvtpm:	vtpm device struct
+ *
+ * Return:
+ *	0 on success.
+ *	Non-zero on failure.
+ */
+static int ibmvtpm_crq_send_init(struct ibmvtpm_dev *ibmvtpm)
+{
+	int rc;
+
+	rc = ibmvtpm_send_crq_word(ibmvtpm->vdev, INIT_CRQ_CMD);
+	if (rc != H_SUCCESS)
+		dev_err(ibmvtpm->dev,
+			"%s failed rc=%d\n", __func__, rc);
+
+	return rc;
+}
+
+/**
+ * tpm_ibmvtpm_resume - Resume from suspend
+ *
+ * @dev:	device struct
+ *
+ * Return: Always 0.
+ */
+static int tpm_ibmvtpm_resume(struct device *dev)
+{
+	struct tpm_chip *chip = dev_get_drvdata(dev);
+	struct ibmvtpm_dev *ibmvtpm = dev_get_drvdata(&chip->dev);
+	int rc = 0;
+
+	do {
+		if (rc)
+			msleep(100);
+		rc = plpar_hcall_norets(H_ENABLE_CRQ,
+					ibmvtpm->vdev->unit_address);
+	} while (rc == H_IN_PROGRESS || rc == H_BUSY || H_IS_LONG_BUSY(rc));
+
+	if (rc) {
+		dev_err(dev, "Error enabling ibmvtpm rc=%d\n", rc);
+		return rc;
+	}
+
+	rc = vio_enable_interrupts(ibmvtpm->vdev);
+	if (rc) {
+		dev_err(dev, "Error vio_enable_interrupts rc=%d\n", rc);
+		return rc;
+	}
+
+	rc = ibmvtpm_crq_send_init(ibmvtpm);
+	if (rc)
+		dev_err(dev, "Error send_init rc=%d\n", rc);
+
+	return rc;
+}
+
+/**
  * tpm_ibmvtpm_send() - Send a TPM command
  * @chip:	tpm chip struct
  * @buf:	buffer contains data to send
@@ -146,6 +204,7 @@ static int tpm_ibmvtpm_recv(struct tpm_chip *chip, u8 *buf, size_t count)
 static int tpm_ibmvtpm_send(struct tpm_chip *chip, u8 *buf, size_t count)
 {
 	struct ibmvtpm_dev *ibmvtpm = dev_get_drvdata(&chip->dev);
+	bool retry = true;
 	int rc, sig;
 
 	if (!ibmvtpm->rtce_buf) {
@@ -179,18 +238,27 @@ static int tpm_ibmvtpm_send(struct tpm_chip *chip, u8 *buf, size_t count)
 	 */
 	ibmvtpm->tpm_processing_cmd = true;
 
+again:
 	rc = ibmvtpm_send_crq(ibmvtpm->vdev,
 			IBMVTPM_VALID_CMD, VTPM_TPM_COMMAND,
 			count, ibmvtpm->rtce_dma_handle);
 	if (rc != H_SUCCESS) {
+		/*
+		 * H_CLOSED can be returned after LPM resume.  Call
+		 * tpm_ibmvtpm_resume() to re-enable the CRQ then retry
+		 * ibmvtpm_send_crq() once before failing.
+		 */
+		if (rc == H_CLOSED && retry) {
+			tpm_ibmvtpm_resume(ibmvtpm->dev);
+			retry = false;
+			goto again;
+		}
 		dev_err(ibmvtpm->dev, "tpm_ibmvtpm_send failed rc=%d\n", rc);
-		rc = 0;
 		ibmvtpm->tpm_processing_cmd = false;
-	} else
-		rc = 0;
+	}
 
 	spin_unlock(&ibmvtpm->rtce_lock);
-	return rc;
+	return 0;
 }
 
 static void tpm_ibmvtpm_cancel(struct tpm_chip *chip)
@@ -269,26 +337,6 @@ static int ibmvtpm_crq_send_init_complete(struct ibmvtpm_dev *ibmvtpm)
 }
 
 /**
- * ibmvtpm_crq_send_init - Send a CRQ initialize message
- * @ibmvtpm:	vtpm device struct
- *
- * Return:
- *	0 on success.
- *	Non-zero on failure.
- */
-static int ibmvtpm_crq_send_init(struct ibmvtpm_dev *ibmvtpm)
-{
-	int rc;
-
-	rc = ibmvtpm_send_crq_word(ibmvtpm->vdev, INIT_CRQ_CMD);
-	if (rc != H_SUCCESS)
-		dev_err(ibmvtpm->dev,
-			"ibmvtpm_crq_send_init failed rc=%d\n", rc);
-
-	return rc;
-}
-
-/**
  * tpm_ibmvtpm_remove - ibm vtpm remove entry point
  * @vdev:	vio device struct
  *
@@ -400,44 +448,6 @@ static int ibmvtpm_reset_crq(struct ibmvtpm_dev *ibmvtpm)
 				  ibmvtpm->crq_dma_handle, CRQ_RES_BUF_SIZE);
 }
 
-/**
- * tpm_ibmvtpm_resume - Resume from suspend
- *
- * @dev:	device struct
- *
- * Return: Always 0.
- */
-static int tpm_ibmvtpm_resume(struct device *dev)
-{
-	struct tpm_chip *chip = dev_get_drvdata(dev);
-	struct ibmvtpm_dev *ibmvtpm = dev_get_drvdata(&chip->dev);
-	int rc = 0;
-
-	do {
-		if (rc)
-			msleep(100);
-		rc = plpar_hcall_norets(H_ENABLE_CRQ,
-					ibmvtpm->vdev->unit_address);
-	} while (rc == H_IN_PROGRESS || rc == H_BUSY || H_IS_LONG_BUSY(rc));
-
-	if (rc) {
-		dev_err(dev, "Error enabling ibmvtpm rc=%d\n", rc);
-		return rc;
-	}
-
-	rc = vio_enable_interrupts(ibmvtpm->vdev);
-	if (rc) {
-		dev_err(dev, "Error vio_enable_interrupts rc=%d\n", rc);
-		return rc;
-	}
-
-	rc = ibmvtpm_crq_send_init(ibmvtpm);
-	if (rc)
-		dev_err(dev, "Error send_init rc=%d\n", rc);
-
-	return rc;
-}
-
 static bool tpm_ibmvtpm_req_canceled(struct tpm_chip *chip, u8 status)
 {
 	return (status == 0);
diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c
index e4fdde93ed4c..e7df342a317d 100644
--- a/drivers/char/tpm/tpm_tis.c
+++ b/drivers/char/tpm/tpm_tis.c
@@ -286,7 +286,7 @@ static int tpm_tis_plat_probe(struct platform_device *pdev)
 	}
 	tpm_info.res = *res;
 
-	tpm_info.irq = platform_get_irq(pdev, 0);
+	tpm_info.irq = platform_get_irq_optional(pdev, 0);
 	if (tpm_info.irq <= 0) {
 		if (pdev != force_pdev)
 			tpm_info.irq = -1;
diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c
index 270f43acbb77..e79655a05a76 100644
--- a/drivers/char/tpm/tpm_tis_core.c
+++ b/drivers/char/tpm/tpm_tis_core.c
@@ -433,6 +433,9 @@ static void disable_interrupts(struct tpm_chip *chip)
 	u32 intmask;
 	int rc;
 
+	if (priv->irq == 0)
+		return;
+
 	rc = tpm_tis_read32(priv, TPM_INT_ENABLE(priv->locality), &intmask);
 	if (rc < 0)
 		intmask = 0;
@@ -981,13 +984,15 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq,
 		}
 
 		tpm_chip_start(chip);
-		chip->flags |= TPM_CHIP_FLAG_IRQ;
 		if (irq) {
 			tpm_tis_probe_irq_single(chip, intmask, IRQF_SHARED,
 						 irq);
-			if (!(chip->flags & TPM_CHIP_FLAG_IRQ))
+			if (!(chip->flags & TPM_CHIP_FLAG_IRQ)) {
 				dev_err(&chip->dev, FW_BUG
 					"TPM interrupt not working, polling instead\n");
+
+				disable_interrupts(chip);
+			}
 		} else {
 			tpm_tis_probe_irq(chip, intmask);
 		}
@@ -1003,7 +1008,7 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq,
 
 	return 0;
 out_err:
-	if ((chip->ops != NULL) && (chip->ops->clk_enable != NULL))
+	if (chip->ops->clk_enable != NULL)
 		chip->ops->clk_enable(chip, false);
 
 	tpm_tis_remove(chip);
diff --git a/drivers/char/tpm/tpmrm-dev.c b/drivers/char/tpm/tpmrm-dev.c
index 7a0a7051a06f..eef0fb06ea83 100644
--- a/drivers/char/tpm/tpmrm-dev.c
+++ b/drivers/char/tpm/tpmrm-dev.c
@@ -21,7 +21,7 @@ static int tpmrm_open(struct inode *inode, struct file *file)
 	if (priv == NULL)
 		return -ENOMEM;
 
-	rc = tpm2_init_space(&priv->space);
+	rc = tpm2_init_space(&priv->space, TPM2_SPACE_BUFFER_SIZE);
 	if (rc) {
 		kfree(priv);
 		return -ENOMEM;
diff --git a/drivers/char/ttyprintk.c b/drivers/char/ttyprintk.c
index 4f24e46ebe7c..56db949a7b70 100644
--- a/drivers/char/ttyprintk.c
+++ b/drivers/char/ttyprintk.c
@@ -15,10 +15,11 @@
 #include <linux/serial.h>
 #include <linux/tty.h>
 #include <linux/module.h>
+#include <linux/spinlock.h>
 
 struct ttyprintk_port {
 	struct tty_port port;
-	struct mutex port_write_mutex;
+	spinlock_t spinlock;
 };
 
 static struct ttyprintk_port tpk_port;
@@ -99,11 +100,12 @@ static int tpk_open(struct tty_struct *tty, struct file *filp)
 static void tpk_close(struct tty_struct *tty, struct file *filp)
 {
 	struct ttyprintk_port *tpkp = tty->driver_data;
+	unsigned long flags;
 
-	mutex_lock(&tpkp->port_write_mutex);
+	spin_lock_irqsave(&tpkp->spinlock, flags);
 	/* flush tpk_printk buffer */
 	tpk_printk(NULL, 0);
-	mutex_unlock(&tpkp->port_write_mutex);
+	spin_unlock_irqrestore(&tpkp->spinlock, flags);
 
 	tty_port_close(&tpkp->port, tty, filp);
 }
@@ -115,13 +117,14 @@ static int tpk_write(struct tty_struct *tty,
 		const unsigned char *buf, int count)
 {
 	struct ttyprintk_port *tpkp = tty->driver_data;
+	unsigned long flags;
 	int ret;
 
 
 	/* exclusive use of tpk_printk within this tty */
-	mutex_lock(&tpkp->port_write_mutex);
+	spin_lock_irqsave(&tpkp->spinlock, flags);
 	ret = tpk_printk(buf, count);
-	mutex_unlock(&tpkp->port_write_mutex);
+	spin_unlock_irqrestore(&tpkp->spinlock, flags);
 
 	return ret;
 }
@@ -171,7 +174,7 @@ static int __init ttyprintk_init(void)
 {
 	int ret = -ENOMEM;
 
-	mutex_init(&tpk_port.port_write_mutex);
+	spin_lock_init(&tpk_port.spinlock);
 
 	ttyprintk_driver = tty_alloc_driver(1,
 			TTY_DRIVER_RESET_TERMIOS |
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 3259426f01dc..9ebce2c12c43 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -2118,6 +2118,7 @@ static struct virtio_device_id id_table[] = {
 	{ VIRTIO_ID_CONSOLE, VIRTIO_DEV_ANY_ID },
 	{ 0 },
 };
+MODULE_DEVICE_TABLE(virtio, id_table);
 
 static unsigned int features[] = {
 	VIRTIO_CONSOLE_F_SIZE,
@@ -2130,6 +2131,7 @@ static struct virtio_device_id rproc_serial_id_table[] = {
 #endif
 	{ 0 },
 };
+MODULE_DEVICE_TABLE(virtio, rproc_serial_id_table);
 
 static unsigned int rproc_serial_features[] = {
 };
@@ -2282,6 +2284,5 @@ static void __exit fini(void)
 module_init(init);
 module_exit(fini);
 
-MODULE_DEVICE_TABLE(virtio, id_table);
 MODULE_DESCRIPTION("Virtio console driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/clk/actions/owl-s500.c b/drivers/clk/actions/owl-s500.c
index e2007ac4d235..0eb83a0b70bc 100644
--- a/drivers/clk/actions/owl-s500.c
+++ b/drivers/clk/actions/owl-s500.c
@@ -183,7 +183,7 @@ static OWL_GATE(timer_clk, "timer_clk", "hosc", CMU_DEVCLKEN1, 27, 0, 0);
 static OWL_GATE(hdmi_clk, "hdmi_clk", "hosc", CMU_DEVCLKEN1, 3, 0, 0);
 
 /* divider clocks */
-static OWL_DIVIDER(h_clk, "h_clk", "ahbprevdiv_clk", CMU_BUSCLK1, 12, 2, NULL, 0, 0);
+static OWL_DIVIDER(h_clk, "h_clk", "ahbprediv_clk", CMU_BUSCLK1, 12, 2, NULL, 0, 0);
 static OWL_DIVIDER(rmii_ref_clk, "rmii_ref_clk", "ethernet_pll_clk", CMU_ETHERNETPLL, 1, 1, rmii_ref_div_table, 0, 0);
 
 /* factor clocks */
diff --git a/drivers/clk/at91/clk-usb.c b/drivers/clk/at91/clk-usb.c
index 22aede42a336..c0895c993cce 100644
--- a/drivers/clk/at91/clk-usb.c
+++ b/drivers/clk/at91/clk-usb.c
@@ -75,6 +75,9 @@ static int at91sam9x5_clk_usb_determine_rate(struct clk_hw *hw,
 			tmp_parent_rate = req->rate * div;
 			tmp_parent_rate = clk_hw_round_rate(parent,
 							   tmp_parent_rate);
+			if (!tmp_parent_rate)
+				continue;
+
 			tmp_rate = DIV_ROUND_CLOSEST(tmp_parent_rate, div);
 			if (tmp_rate < req->rate)
 				tmp_diff = req->rate - tmp_rate;
@@ -211,7 +214,7 @@ _at91sam9x5_clk_register_usb(struct regmap *regmap, const char *name,
 
 	usb->hw.init = &init;
 	usb->regmap = regmap;
-	usb->usbs_mask = SAM9X5_USBS_MASK;
+	usb->usbs_mask = usbs_mask;
 
 	hw = &usb->hw;
 	ret = clk_hw_register(NULL, &usb->hw);
diff --git a/drivers/clk/at91/sam9x60.c b/drivers/clk/at91/sam9x60.c
index 86238d5ecb4d..7338a3bc71eb 100644
--- a/drivers/clk/at91/sam9x60.c
+++ b/drivers/clk/at91/sam9x60.c
@@ -47,6 +47,7 @@ static const struct clk_programmable_layout sam9x60_programmable_layout = {
 	.pres_shift = 8,
 	.css_mask = 0x1f,
 	.have_slck_mck = 0,
+	.is_pres_direct = 1,
 };
 
 static const struct clk_pcr_layout sam9x60_pcr_layout = {
@@ -236,9 +237,8 @@ static void __init sam9x60_pmc_setup(struct device_node *np)
 
 	parent_names[0] = "pllack";
 	parent_names[1] = "upllck";
-	parent_names[2] = "mainck";
-	parent_names[3] = "mainck";
-	hw = sam9x60_clk_register_usb(regmap, "usbck", parent_names, 4);
+	parent_names[2] = "main_osc";
+	hw = sam9x60_clk_register_usb(regmap, "usbck", parent_names, 3);
 	if (IS_ERR(hw))
 		goto err_free;
 
diff --git a/drivers/clk/bcm/clk-bcm2835.c b/drivers/clk/bcm/clk-bcm2835.c
index 770bb01f523e..e11dbf787797 100644
--- a/drivers/clk/bcm/clk-bcm2835.c
+++ b/drivers/clk/bcm/clk-bcm2835.c
@@ -1438,13 +1438,13 @@ static struct clk_hw *bcm2835_register_clock(struct bcm2835_cprman *cprman,
 	return &clock->hw;
 }
 
-static struct clk *bcm2835_register_gate(struct bcm2835_cprman *cprman,
+static struct clk_hw *bcm2835_register_gate(struct bcm2835_cprman *cprman,
 					 const struct bcm2835_gate_data *data)
 {
-	return clk_register_gate(cprman->dev, data->name, data->parent,
-				 CLK_IGNORE_UNUSED | CLK_SET_RATE_GATE,
-				 cprman->regs + data->ctl_reg,
-				 CM_GATE_BIT, 0, &cprman->regs_lock);
+	return clk_hw_register_gate(cprman->dev, data->name, data->parent,
+				    CLK_IGNORE_UNUSED | CLK_SET_RATE_GATE,
+				    cprman->regs + data->ctl_reg,
+				    CM_GATE_BIT, 0, &cprman->regs_lock);
 }
 
 typedef struct clk_hw *(*bcm2835_clk_register)(struct bcm2835_cprman *cprman,
diff --git a/drivers/clk/clk-scmi.c b/drivers/clk/clk-scmi.c
index a2287c770d5c..06a47bbcf565 100644
--- a/drivers/clk/clk-scmi.c
+++ b/drivers/clk/clk-scmi.c
@@ -103,6 +103,8 @@ static const struct clk_ops scmi_clk_ops = {
 static int scmi_clk_ops_init(struct device *dev, struct scmi_clk *sclk)
 {
 	int ret;
+	unsigned long min_rate, max_rate;
+
 	struct clk_init_data init = {
 		.flags = CLK_GET_RATE_NOCACHE,
 		.num_parents = 0,
@@ -112,9 +114,23 @@ static int scmi_clk_ops_init(struct device *dev, struct scmi_clk *sclk)
 
 	sclk->hw.init = &init;
 	ret = devm_clk_hw_register(dev, &sclk->hw);
-	if (!ret)
-		clk_hw_set_rate_range(&sclk->hw, sclk->info->range.min_rate,
-				      sclk->info->range.max_rate);
+	if (ret)
+		return ret;
+
+	if (sclk->info->rate_discrete) {
+		int num_rates = sclk->info->list.num_rates;
+
+		if (num_rates <= 0)
+			return -EINVAL;
+
+		min_rate = sclk->info->list.rates[0];
+		max_rate = sclk->info->list.rates[num_rates - 1];
+	} else {
+		min_rate = sclk->info->range.min_rate;
+		max_rate = sclk->info->range.max_rate;
+	}
+
+	clk_hw_set_rate_range(&sclk->hw, min_rate, max_rate);
 	return ret;
 }
 
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 77d1d3894f8d..2eb7f8cd27a8 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -108,7 +108,11 @@ static int clk_pm_runtime_get(struct clk_core *core)
 		return 0;
 
 	ret = pm_runtime_get_sync(core->dev);
-	return ret < 0 ? ret : 0;
+	if (ret < 0) {
+		pm_runtime_put_noidle(core->dev);
+		return ret;
+	}
+	return 0;
 }
 
 static void clk_pm_runtime_put(struct clk_core *core)
@@ -2631,12 +2635,14 @@ static int clk_core_get_phase(struct clk_core *core)
 {
 	int ret;
 
-	clk_prepare_lock();
+	lockdep_assert_held(&prepare_lock);
+	if (!core->ops->get_phase)
+		return 0;
+
 	/* Always try to update cached phase if possible */
-	if (core->ops->get_phase)
-		core->phase = core->ops->get_phase(core->hw);
-	ret = core->phase;
-	clk_prepare_unlock();
+	ret = core->ops->get_phase(core->hw);
+	if (ret >= 0)
+		core->phase = ret;
 
 	return ret;
 }
@@ -2650,10 +2656,16 @@ static int clk_core_get_phase(struct clk_core *core)
  */
 int clk_get_phase(struct clk *clk)
 {
+	int ret;
+
 	if (!clk)
 		return 0;
 
-	return clk_core_get_phase(clk->core);
+	clk_prepare_lock();
+	ret = clk_core_get_phase(clk->core);
+	clk_prepare_unlock();
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(clk_get_phase);
 
@@ -2873,16 +2885,24 @@ static struct hlist_head *orphan_list[] = {
 static void clk_summary_show_one(struct seq_file *s, struct clk_core *c,
 				 int level)
 {
+	int phase;
+
 	if (!c)
 		return;
 
-	seq_printf(s, "%*s%-*s %7d %8d %8d %11lu %10lu %5d %6d\n",
+	seq_printf(s, "%*s%-*s %7d %8d %8d %11lu %10lu ",
 		   level * 3 + 1, "",
 		   30 - level * 3, c->name,
 		   c->enable_count, c->prepare_count, c->protect_count,
-		   clk_core_get_rate(c), clk_core_get_accuracy(c),
-		   clk_core_get_phase(c),
-		   clk_core_get_scaled_duty_cycle(c, 100000));
+		   clk_core_get_rate(c), clk_core_get_accuracy(c));
+
+	phase = clk_core_get_phase(c);
+	if (phase >= 0)
+		seq_printf(s, "%5d", phase);
+	else
+		seq_puts(s, "-----");
+
+	seq_printf(s, " %6d\n", clk_core_get_scaled_duty_cycle(c, 100000));
 }
 
 static void clk_summary_show_subtree(struct seq_file *s, struct clk_core *c,
@@ -2922,6 +2942,7 @@ DEFINE_SHOW_ATTRIBUTE(clk_summary);
 
 static void clk_dump_one(struct seq_file *s, struct clk_core *c, int level)
 {
+	int phase;
 	if (!c)
 		return;
 
@@ -2932,7 +2953,9 @@ static void clk_dump_one(struct seq_file *s, struct clk_core *c, int level)
 	seq_printf(s, "\"protect_count\": %d,", c->protect_count);
 	seq_printf(s, "\"rate\": %lu,", clk_core_get_rate(c));
 	seq_printf(s, "\"accuracy\": %lu,", clk_core_get_accuracy(c));
-	seq_printf(s, "\"phase\": %d,", clk_core_get_phase(c));
+	phase = clk_core_get_phase(c);
+	if (phase >= 0)
+		seq_printf(s, "\"phase\": %d,", phase);
 	seq_printf(s, "\"duty_cycle\": %u",
 		   clk_core_get_scaled_duty_cycle(c, 100000));
 }
@@ -3187,6 +3210,34 @@ static inline void clk_debug_unregister(struct clk_core *core)
 }
 #endif
 
+static void clk_core_reparent_orphans_nolock(void)
+{
+	struct clk_core *orphan;
+	struct hlist_node *tmp2;
+
+	/*
+	 * walk the list of orphan clocks and reparent any that newly finds a
+	 * parent.
+	 */
+	hlist_for_each_entry_safe(orphan, tmp2, &clk_orphan_list, child_node) {
+		struct clk_core *parent = __clk_init_parent(orphan);
+
+		/*
+		 * We need to use __clk_set_parent_before() and _after() to
+		 * to properly migrate any prepare/enable count of the orphan
+		 * clock. This is important for CLK_IS_CRITICAL clocks, which
+		 * are enabled during init but might not have a parent yet.
+		 */
+		if (parent) {
+			/* update the clk tree topology */
+			__clk_set_parent_before(orphan, parent);
+			__clk_set_parent_after(orphan, parent, NULL);
+			__clk_recalc_accuracies(orphan);
+			__clk_recalc_rates(orphan, 0);
+		}
+	}
+}
+
 /**
  * __clk_core_init - initialize the data structures in a struct clk_core
  * @core:	clk_core being initialized
@@ -3197,8 +3248,6 @@ static inline void clk_debug_unregister(struct clk_core *core)
 static int __clk_core_init(struct clk_core *core)
 {
 	int ret;
-	struct clk_core *orphan;
-	struct hlist_node *tmp2;
 	unsigned long rate;
 
 	if (!core)
@@ -3250,6 +3299,21 @@ static int __clk_core_init(struct clk_core *core)
 		goto out;
 	}
 
+	/*
+	 * optional platform-specific magic
+	 *
+	 * The .init callback is not used by any of the basic clock types, but
+	 * exists for weird hardware that must perform initialization magic.
+	 * Please consider other ways of solving initialization problems before
+	 * using this callback, as its use is discouraged.
+	 *
+	 * If it exist, this callback should called before any other callback of
+	 * the clock
+	 */
+	if (core->ops->init)
+		core->ops->init(core->hw);
+
+
 	core->parent = __clk_init_parent(core);
 
 	/*
@@ -3275,17 +3339,6 @@ static int __clk_core_init(struct clk_core *core)
 	}
 
 	/*
-	 * optional platform-specific magic
-	 *
-	 * The .init callback is not used by any of the basic clock types, but
-	 * exists for weird hardware that must perform initialization magic.
-	 * Please consider other ways of solving initialization problems before
-	 * using this callback, as its use is discouraged.
-	 */
-	if (core->ops->init)
-		core->ops->init(core->hw);
-
-	/*
 	 * Set clk's accuracy.  The preferred method is to use
 	 * .recalc_accuracy. For simple clocks and lazy developers the default
 	 * fallback is to use the parent's accuracy.  If a clock doesn't have a
@@ -3301,14 +3354,11 @@ static int __clk_core_init(struct clk_core *core)
 		core->accuracy = 0;
 
 	/*
-	 * Set clk's phase.
+	 * Set clk's phase by clk_core_get_phase() caching the phase.
 	 * Since a phase is by definition relative to its parent, just
 	 * query the current clock phase, or just assume it's in phase.
 	 */
-	if (core->ops->get_phase)
-		core->phase = core->ops->get_phase(core->hw);
-	else
-		core->phase = 0;
+	clk_core_get_phase(core);
 
 	/*
 	 * Set clk's duty cycle.
@@ -3338,39 +3388,29 @@ static int __clk_core_init(struct clk_core *core)
 	if (core->flags & CLK_IS_CRITICAL) {
 		unsigned long flags;
 
-		clk_core_prepare(core);
+		ret = clk_core_prepare(core);
+		if (ret)
+			goto out;
 
 		flags = clk_enable_lock();
-		clk_core_enable(core);
+		ret = clk_core_enable(core);
 		clk_enable_unlock(flags);
+		if (ret) {
+			clk_core_unprepare(core);
+			goto out;
+		}
 	}
 
-	/*
-	 * walk the list of orphan clocks and reparent any that newly finds a
-	 * parent.
-	 */
-	hlist_for_each_entry_safe(orphan, tmp2, &clk_orphan_list, child_node) {
-		struct clk_core *parent = __clk_init_parent(orphan);
+	clk_core_reparent_orphans_nolock();
 
-		/*
-		 * We need to use __clk_set_parent_before() and _after() to
-		 * to properly migrate any prepare/enable count of the orphan
-		 * clock. This is important for CLK_IS_CRITICAL clocks, which
-		 * are enabled during init but might not have a parent yet.
-		 */
-		if (parent) {
-			/* update the clk tree topology */
-			__clk_set_parent_before(orphan, parent);
-			__clk_set_parent_after(orphan, parent, NULL);
-			__clk_recalc_accuracies(orphan);
-			__clk_recalc_rates(orphan, 0);
-		}
-	}
 
 	kref_init(&core->ref);
 out:
 	clk_pm_runtime_put(core);
 unlock:
+	if (ret)
+		hlist_del_init(&core->child_node);
+
 	clk_prepare_unlock();
 
 	if (!ret)
@@ -3650,6 +3690,28 @@ fail_out:
 }
 
 /**
+ * dev_or_parent_of_node() - Get device node of @dev or @dev's parent
+ * @dev: Device to get device node of
+ *
+ * Return: device node pointer of @dev, or the device node pointer of
+ * @dev->parent if dev doesn't have a device node, or NULL if neither
+ * @dev or @dev->parent have a device node.
+ */
+static struct device_node *dev_or_parent_of_node(struct device *dev)
+{
+	struct device_node *np;
+
+	if (!dev)
+		return NULL;
+
+	np = dev_of_node(dev);
+	if (!np)
+		np = dev_of_node(dev->parent);
+
+	return np;
+}
+
+/**
  * clk_register - allocate a new clock, register it and return an opaque cookie
  * @dev: device that is registering this clock
  * @hw: link to hardware-specific clock data
@@ -3664,7 +3726,7 @@ fail_out:
  */
 struct clk *clk_register(struct device *dev, struct clk_hw *hw)
 {
-	return __clk_register(dev, dev_of_node(dev), hw);
+	return __clk_register(dev, dev_or_parent_of_node(dev), hw);
 }
 EXPORT_SYMBOL_GPL(clk_register);
 
@@ -3680,7 +3742,8 @@ EXPORT_SYMBOL_GPL(clk_register);
  */
 int clk_hw_register(struct device *dev, struct clk_hw *hw)
 {
-	return PTR_ERR_OR_ZERO(__clk_register(dev, dev_of_node(dev), hw));
+	return PTR_ERR_OR_ZERO(__clk_register(dev, dev_or_parent_of_node(dev),
+			       hw));
 }
 EXPORT_SYMBOL_GPL(clk_hw_register);
 
@@ -3797,6 +3860,7 @@ void clk_unregister(struct clk *clk)
 					__func__, clk->core->name);
 
 	kref_put(&clk->core->ref, __clk_release);
+	free_clk(clk);
 unlock:
 	clk_prepare_unlock();
 }
@@ -4078,6 +4142,13 @@ int clk_notifier_unregister(struct clk *clk, struct notifier_block *nb)
 EXPORT_SYMBOL_GPL(clk_notifier_unregister);
 
 #ifdef CONFIG_OF
+static void clk_core_reparent_orphans(void)
+{
+	clk_prepare_lock();
+	clk_core_reparent_orphans_nolock();
+	clk_prepare_unlock();
+}
+
 /**
  * struct of_clk_provider - Clock provider registration structure
  * @link: Entry in global list of clock providers
@@ -4172,6 +4243,8 @@ int of_clk_add_provider(struct device_node *np,
 	mutex_unlock(&of_clk_mutex);
 	pr_debug("Added clock from %pOF\n", np);
 
+	clk_core_reparent_orphans();
+
 	ret = of_clk_set_defaults(np, true);
 	if (ret < 0)
 		of_clk_del_provider(np);
@@ -4207,6 +4280,8 @@ int of_clk_add_hw_provider(struct device_node *np,
 	mutex_unlock(&of_clk_mutex);
 	pr_debug("Added clk_hw provider from %pOF\n", np);
 
+	clk_core_reparent_orphans();
+
 	ret = of_clk_set_defaults(np, true);
 	if (ret < 0)
 		of_clk_del_provider(np);
diff --git a/drivers/clk/imx/clk-imx7ulp.c b/drivers/clk/imx/clk-imx7ulp.c
index fb50b8b20c8c..65112d0e20dc 100644
--- a/drivers/clk/imx/clk-imx7ulp.c
+++ b/drivers/clk/imx/clk-imx7ulp.c
@@ -24,8 +24,8 @@ static const char * const spll_pfd_sels[]	= { "spll_pfd0", "spll_pfd1", "spll_pf
 static const char * const spll_sels[]		= { "spll", "spll_pfd_sel", };
 static const char * const apll_pfd_sels[]	= { "apll_pfd0", "apll_pfd1", "apll_pfd2", "apll_pfd3", };
 static const char * const apll_sels[]		= { "apll", "apll_pfd_sel", };
-static const char * const scs_sels[]		= { "dummy", "sosc", "sirc", "firc", "dummy", "apll_sel", "spll_sel", "upll", };
-static const char * const ddr_sels[]		= { "apll_pfd_sel", "upll", };
+static const char * const scs_sels[]		= { "dummy", "sosc", "sirc", "firc", "dummy", "apll_sel", "spll_sel", "dummy", };
+static const char * const ddr_sels[]		= { "apll_pfd_sel", "dummy", "dummy", "dummy", };
 static const char * const nic_sels[]		= { "firc", "ddr_clk", };
 static const char * const periph_plat_sels[]	= { "dummy", "nic1_bus_clk", "nic1_clk", "ddr_clk", "apll_pfd2", "apll_pfd1", "apll_pfd0", "upll", };
 static const char * const periph_bus_sels[]	= { "dummy", "sosc_bus_clk", "mpll", "firc_bus_clk", "rosc", "nic1_bus_clk", "nic1_clk", "spll_bus_clk", };
@@ -106,7 +106,7 @@ static void __init imx7ulp_clk_scg1_init(struct device_node *np)
 	clks[IMX7ULP_CLK_SYS_SEL]	= imx_clk_hw_mux2("scs_sel", base + 0x14, 24, 4, scs_sels, ARRAY_SIZE(scs_sels));
 	clks[IMX7ULP_CLK_HSRUN_SYS_SEL] = imx_clk_hw_mux2("hsrun_scs_sel", base + 0x1c, 24, 4, scs_sels, ARRAY_SIZE(scs_sels));
 	clks[IMX7ULP_CLK_NIC_SEL]	= imx_clk_hw_mux2("nic_sel", base + 0x40, 28, 1, nic_sels, ARRAY_SIZE(nic_sels));
-	clks[IMX7ULP_CLK_DDR_SEL]	= imx_clk_hw_mux_flags("ddr_sel", base + 0x30, 24, 1, ddr_sels, ARRAY_SIZE(ddr_sels), CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE);
+	clks[IMX7ULP_CLK_DDR_SEL]	= imx_clk_hw_mux_flags("ddr_sel", base + 0x30, 24, 2, ddr_sels, ARRAY_SIZE(ddr_sels), CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE);
 
 	clks[IMX7ULP_CLK_CORE_DIV]	= imx_clk_hw_divider_flags("divcore",	"scs_sel",  base + 0x14, 16, 4, CLK_SET_RATE_PARENT);
 	clks[IMX7ULP_CLK_HSRUN_CORE_DIV] = imx_clk_hw_divider_flags("hsrun_divcore", "hsrun_scs_sel", base + 0x1c, 16, 4, CLK_SET_RATE_PARENT);
diff --git a/drivers/clk/imx/clk-pll14xx.c b/drivers/clk/imx/clk-pll14xx.c
index d43b4a3c0de8..047f1d8fe323 100644
--- a/drivers/clk/imx/clk-pll14xx.c
+++ b/drivers/clk/imx/clk-pll14xx.c
@@ -112,43 +112,17 @@ static unsigned long clk_pll1443x_recalc_rate(struct clk_hw *hw,
 	return fvco;
 }
 
-static inline bool clk_pll1416x_mp_change(const struct imx_pll14xx_rate_table *rate,
+static inline bool clk_pll14xx_mp_change(const struct imx_pll14xx_rate_table *rate,
 					  u32 pll_div)
 {
 	u32 old_mdiv, old_pdiv;
 
-	old_mdiv = (pll_div >> MDIV_SHIFT) & MDIV_MASK;
-	old_pdiv = (pll_div >> PDIV_SHIFT) & PDIV_MASK;
+	old_mdiv = (pll_div & MDIV_MASK) >> MDIV_SHIFT;
+	old_pdiv = (pll_div & PDIV_MASK) >> PDIV_SHIFT;
 
 	return rate->mdiv != old_mdiv || rate->pdiv != old_pdiv;
 }
 
-static inline bool clk_pll1443x_mpk_change(const struct imx_pll14xx_rate_table *rate,
-					  u32 pll_div_ctl0, u32 pll_div_ctl1)
-{
-	u32 old_mdiv, old_pdiv, old_kdiv;
-
-	old_mdiv = (pll_div_ctl0 >> MDIV_SHIFT) & MDIV_MASK;
-	old_pdiv = (pll_div_ctl0 >> PDIV_SHIFT) & PDIV_MASK;
-	old_kdiv = (pll_div_ctl1 >> KDIV_SHIFT) & KDIV_MASK;
-
-	return rate->mdiv != old_mdiv || rate->pdiv != old_pdiv ||
-		rate->kdiv != old_kdiv;
-}
-
-static inline bool clk_pll1443x_mp_change(const struct imx_pll14xx_rate_table *rate,
-					  u32 pll_div_ctl0, u32 pll_div_ctl1)
-{
-	u32 old_mdiv, old_pdiv, old_kdiv;
-
-	old_mdiv = (pll_div_ctl0 >> MDIV_SHIFT) & MDIV_MASK;
-	old_pdiv = (pll_div_ctl0 >> PDIV_SHIFT) & PDIV_MASK;
-	old_kdiv = (pll_div_ctl1 >> KDIV_SHIFT) & KDIV_MASK;
-
-	return rate->mdiv != old_mdiv || rate->pdiv != old_pdiv ||
-		rate->kdiv != old_kdiv;
-}
-
 static int clk_pll14xx_wait_lock(struct clk_pll14xx *pll)
 {
 	u32 val;
@@ -174,7 +148,7 @@ static int clk_pll1416x_set_rate(struct clk_hw *hw, unsigned long drate,
 
 	tmp = readl_relaxed(pll->base + 4);
 
-	if (!clk_pll1416x_mp_change(rate, tmp)) {
+	if (!clk_pll14xx_mp_change(rate, tmp)) {
 		tmp &= ~(SDIV_MASK) << SDIV_SHIFT;
 		tmp |= rate->sdiv << SDIV_SHIFT;
 		writel_relaxed(tmp, pll->base + 4);
@@ -239,13 +213,15 @@ static int clk_pll1443x_set_rate(struct clk_hw *hw, unsigned long drate,
 	}
 
 	tmp = readl_relaxed(pll->base + 4);
-	div_val = readl_relaxed(pll->base + 8);
 
-	if (!clk_pll1443x_mpk_change(rate, tmp, div_val)) {
+	if (!clk_pll14xx_mp_change(rate, tmp)) {
 		tmp &= ~(SDIV_MASK) << SDIV_SHIFT;
 		tmp |= rate->sdiv << SDIV_SHIFT;
 		writel_relaxed(tmp, pll->base + 4);
 
+		tmp = rate->kdiv << KDIV_SHIFT;
+		writel_relaxed(tmp, pll->base + 8);
+
 		return 0;
 	}
 
diff --git a/drivers/clk/imx/clk-scu.c b/drivers/clk/imx/clk-scu.c
index fbef740704d0..b8b2072742a5 100644
--- a/drivers/clk/imx/clk-scu.c
+++ b/drivers/clk/imx/clk-scu.c
@@ -43,12 +43,12 @@ struct imx_sc_msg_req_set_clock_rate {
 	__le32 rate;
 	__le16 resource;
 	u8 clk;
-} __packed;
+} __packed __aligned(4);
 
 struct req_get_clock_rate {
 	__le16 resource;
 	u8 clk;
-} __packed;
+} __packed __aligned(4);
 
 struct resp_get_clock_rate {
 	__le32 rate;
@@ -84,7 +84,7 @@ struct imx_sc_msg_get_clock_parent {
 		struct req_get_clock_parent {
 			__le16 resource;
 			u8 clk;
-		} __packed req;
+		} __packed __aligned(4) req;
 		struct resp_get_clock_parent {
 			u8 parent;
 		} resp;
@@ -121,7 +121,7 @@ struct imx_sc_msg_req_clock_enable {
 	u8 clk;
 	u8 enable;
 	u8 autog;
-} __packed;
+} __packed __aligned(4);
 
 static inline struct clk_scu *to_clk_scu(struct clk_hw *hw)
 {
diff --git a/drivers/clk/ingenic/jz4770-cgu.c b/drivers/clk/ingenic/jz4770-cgu.c
index dfce740c25a8..c6f877d05af7 100644
--- a/drivers/clk/ingenic/jz4770-cgu.c
+++ b/drivers/clk/ingenic/jz4770-cgu.c
@@ -437,8 +437,10 @@ static void __init jz4770_cgu_init(struct device_node *np)
 
 	cgu = ingenic_cgu_new(jz4770_cgu_clocks,
 			      ARRAY_SIZE(jz4770_cgu_clocks), np);
-	if (!cgu)
+	if (!cgu) {
 		pr_err("%s: failed to initialise CGU\n", __func__);
+		return;
+	}
 
 	retval = ingenic_cgu_register_clocks(cgu);
 	if (retval)
diff --git a/drivers/clk/mediatek/clk-mux.c b/drivers/clk/mediatek/clk-mux.c
index 76f9cd039195..14e127e9a740 100644
--- a/drivers/clk/mediatek/clk-mux.c
+++ b/drivers/clk/mediatek/clk-mux.c
@@ -160,7 +160,7 @@ struct clk *mtk_clk_register_mux(const struct mtk_mux *mux,
 				 spinlock_t *lock)
 {
 	struct mtk_clk_mux *clk_mux;
-	struct clk_init_data init;
+	struct clk_init_data init = {};
 	struct clk *clk;
 
 	clk_mux = kzalloc(sizeof(*clk_mux), GFP_KERNEL);
diff --git a/drivers/clk/meson/axg-audio.c b/drivers/clk/meson/axg-audio.c
index db0b73d53551..c01fcddd2849 100644
--- a/drivers/clk/meson/axg-audio.c
+++ b/drivers/clk/meson/axg-audio.c
@@ -920,7 +920,7 @@ static const struct regmap_config axg_audio_regmap_cfg = {
 	.reg_bits	= 32,
 	.val_bits	= 32,
 	.reg_stride	= 4,
-	.max_register	= AUDIO_CLK_PDMIN_CTRL1,
+	.max_register	= AUDIO_CLK_SPDIFOUT_B_CTRL,
 };
 
 struct audioclk_data {
diff --git a/drivers/clk/meson/clk-pll.c b/drivers/clk/meson/clk-pll.c
index ddb1e5634739..3a5853ca98c6 100644
--- a/drivers/clk/meson/clk-pll.c
+++ b/drivers/clk/meson/clk-pll.c
@@ -77,6 +77,15 @@ static unsigned long meson_clk_pll_recalc_rate(struct clk_hw *hw,
 	unsigned int m, n, frac;
 
 	n = meson_parm_read(clk->map, &pll->n);
+
+	/*
+	 * On some HW, N is set to zero on init. This value is invalid as
+	 * it would result in a division by zero. The rate can't be
+	 * calculated in this case
+	 */
+	if (n == 0)
+		return 0;
+
 	m = meson_parm_read(clk->map, &pll->m);
 
 	frac = MESON_PARM_APPLICABLE(&pll->frac) ?
diff --git a/drivers/clk/meson/g12a.c b/drivers/clk/meson/g12a.c
index 206fafd299ea..373fd2980f2b 100644
--- a/drivers/clk/meson/g12a.c
+++ b/drivers/clk/meson/g12a.c
@@ -2819,6 +2819,7 @@ static struct clk_regmap *const g12a_clk_regmaps[] = {
 	&g12a_bt656,
 	&g12a_usb1_to_ddr,
 	&g12a_mmc_pclk,
+	&g12a_uart2,
 	&g12a_vpu_intr,
 	&g12a_gic,
 	&g12a_sd_emmc_a_clk0,
diff --git a/drivers/clk/meson/meson8b.c b/drivers/clk/meson/meson8b.c
index 62cd3a7f1f65..4ed74ec30005 100644
--- a/drivers/clk/meson/meson8b.c
+++ b/drivers/clk/meson/meson8b.c
@@ -1081,7 +1081,7 @@ static struct clk_regmap meson8b_vclk_in_en = {
 
 static struct clk_regmap meson8b_vclk_div1_gate = {
 	.data = &(struct clk_regmap_gate_data){
-		.offset = HHI_VID_CLK_DIV,
+		.offset = HHI_VID_CLK_CNTL,
 		.bit_idx = 0,
 	},
 	.hw.init = &(struct clk_init_data){
@@ -1107,7 +1107,7 @@ static struct clk_fixed_factor meson8b_vclk_div2_div = {
 
 static struct clk_regmap meson8b_vclk_div2_div_gate = {
 	.data = &(struct clk_regmap_gate_data){
-		.offset = HHI_VID_CLK_DIV,
+		.offset = HHI_VID_CLK_CNTL,
 		.bit_idx = 1,
 	},
 	.hw.init = &(struct clk_init_data){
@@ -1133,7 +1133,7 @@ static struct clk_fixed_factor meson8b_vclk_div4_div = {
 
 static struct clk_regmap meson8b_vclk_div4_div_gate = {
 	.data = &(struct clk_regmap_gate_data){
-		.offset = HHI_VID_CLK_DIV,
+		.offset = HHI_VID_CLK_CNTL,
 		.bit_idx = 2,
 	},
 	.hw.init = &(struct clk_init_data){
@@ -1159,7 +1159,7 @@ static struct clk_fixed_factor meson8b_vclk_div6_div = {
 
 static struct clk_regmap meson8b_vclk_div6_div_gate = {
 	.data = &(struct clk_regmap_gate_data){
-		.offset = HHI_VID_CLK_DIV,
+		.offset = HHI_VID_CLK_CNTL,
 		.bit_idx = 3,
 	},
 	.hw.init = &(struct clk_init_data){
@@ -1185,7 +1185,7 @@ static struct clk_fixed_factor meson8b_vclk_div12_div = {
 
 static struct clk_regmap meson8b_vclk_div12_div_gate = {
 	.data = &(struct clk_regmap_gate_data){
-		.offset = HHI_VID_CLK_DIV,
+		.offset = HHI_VID_CLK_CNTL,
 		.bit_idx = 4,
 	},
 	.hw.init = &(struct clk_init_data){
@@ -1576,8 +1576,11 @@ static struct clk_regmap meson8b_hdmi_sys = {
 
 /*
  * The MALI IP is clocked by two identical clocks (mali_0 and mali_1)
- * muxed by a glitch-free switch on Meson8b and Meson8m2. Meson8 only
- * has mali_0 and no glitch-free mux.
+ * muxed by a glitch-free switch on Meson8b and Meson8m2. The CCF can
+ * actually manage this glitch-free mux because it does top-to-bottom
+ * updates the each clock tree and switches to the "inactive" one when
+ * CLK_SET_RATE_GATE is set.
+ * Meson8 only has mali_0 and no glitch-free mux.
  */
 static const char * const meson8b_mali_0_1_parent_names[] = {
 	"xtal", "mpll2", "mpll1", "fclk_div7", "fclk_div4", "fclk_div3",
@@ -1633,7 +1636,7 @@ static struct clk_regmap meson8b_mali_0 = {
 		.ops = &clk_regmap_gate_ops,
 		.parent_names = (const char *[]){ "mali_0_div" },
 		.num_parents = 1,
-		.flags = CLK_SET_RATE_PARENT,
+		.flags = CLK_SET_RATE_GATE | CLK_SET_RATE_PARENT,
 	},
 };
 
@@ -1684,7 +1687,7 @@ static struct clk_regmap meson8b_mali_1 = {
 		.ops = &clk_regmap_gate_ops,
 		.parent_names = (const char *[]){ "mali_1_div" },
 		.num_parents = 1,
-		.flags = CLK_SET_RATE_PARENT,
+		.flags = CLK_SET_RATE_GATE | CLK_SET_RATE_PARENT,
 	},
 };
 
@@ -1703,6 +1706,13 @@ static struct clk_regmap meson8b_mali = {
 	},
 };
 
+static const struct reg_sequence meson8m2_gp_pll_init_regs[] = {
+	{ .reg = HHI_GP_PLL_CNTL2,	.def = 0x59c88000 },
+	{ .reg = HHI_GP_PLL_CNTL3,	.def = 0xca463823 },
+	{ .reg = HHI_GP_PLL_CNTL4,	.def = 0x0286a027 },
+	{ .reg = HHI_GP_PLL_CNTL5,	.def = 0x00003000 },
+};
+
 static const struct pll_params_table meson8m2_gp_pll_params_table[] = {
 	PLL_PARAMS(182, 3),
 	{ /* sentinel */ },
@@ -1736,6 +1746,8 @@ static struct clk_regmap meson8m2_gp_pll_dco = {
 			.width   = 1,
 		},
 		.table = meson8m2_gp_pll_params_table,
+		.init_regs = meson8m2_gp_pll_init_regs,
+		.init_count = ARRAY_SIZE(meson8m2_gp_pll_init_regs),
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "gp_pll_dco",
@@ -3046,54 +3058,87 @@ static struct clk_regmap *const meson8b_clk_regmaps[] = {
 static const struct meson8b_clk_reset_line {
 	u32 reg;
 	u8 bit_idx;
+	bool active_low;
 } meson8b_clk_reset_bits[] = {
 	[CLKC_RESET_L2_CACHE_SOFT_RESET] = {
-		.reg = HHI_SYS_CPU_CLK_CNTL0, .bit_idx = 30
+		.reg = HHI_SYS_CPU_CLK_CNTL0,
+		.bit_idx = 30,
+		.active_low = false,
 	},
 	[CLKC_RESET_AXI_64_TO_128_BRIDGE_A5_SOFT_RESET] = {
-		.reg = HHI_SYS_CPU_CLK_CNTL0, .bit_idx = 29
+		.reg = HHI_SYS_CPU_CLK_CNTL0,
+		.bit_idx = 29,
+		.active_low = false,
 	},
 	[CLKC_RESET_SCU_SOFT_RESET] = {
-		.reg = HHI_SYS_CPU_CLK_CNTL0, .bit_idx = 28
+		.reg = HHI_SYS_CPU_CLK_CNTL0,
+		.bit_idx = 28,
+		.active_low = false,
 	},
 	[CLKC_RESET_CPU3_SOFT_RESET] = {
-		.reg = HHI_SYS_CPU_CLK_CNTL0, .bit_idx = 27
+		.reg = HHI_SYS_CPU_CLK_CNTL0,
+		.bit_idx = 27,
+		.active_low = false,
 	},
 	[CLKC_RESET_CPU2_SOFT_RESET] = {
-		.reg = HHI_SYS_CPU_CLK_CNTL0, .bit_idx = 26
+		.reg = HHI_SYS_CPU_CLK_CNTL0,
+		.bit_idx = 26,
+		.active_low = false,
 	},
 	[CLKC_RESET_CPU1_SOFT_RESET] = {
-		.reg = HHI_SYS_CPU_CLK_CNTL0, .bit_idx = 25
+		.reg = HHI_SYS_CPU_CLK_CNTL0,
+		.bit_idx = 25,
+		.active_low = false,
 	},
 	[CLKC_RESET_CPU0_SOFT_RESET] = {
-		.reg = HHI_SYS_CPU_CLK_CNTL0, .bit_idx = 24
+		.reg = HHI_SYS_CPU_CLK_CNTL0,
+		.bit_idx = 24,
+		.active_low = false,
 	},
 	[CLKC_RESET_A5_GLOBAL_RESET] = {
-		.reg = HHI_SYS_CPU_CLK_CNTL0, .bit_idx = 18
+		.reg = HHI_SYS_CPU_CLK_CNTL0,
+		.bit_idx = 18,
+		.active_low = false,
 	},
 	[CLKC_RESET_A5_AXI_SOFT_RESET] = {
-		.reg = HHI_SYS_CPU_CLK_CNTL0, .bit_idx = 17
+		.reg = HHI_SYS_CPU_CLK_CNTL0,
+		.bit_idx = 17,
+		.active_low = false,
 	},
 	[CLKC_RESET_A5_ABP_SOFT_RESET] = {
-		.reg = HHI_SYS_CPU_CLK_CNTL0, .bit_idx = 16
+		.reg = HHI_SYS_CPU_CLK_CNTL0,
+		.bit_idx = 16,
+		.active_low = false,
 	},
 	[CLKC_RESET_AXI_64_TO_128_BRIDGE_MMC_SOFT_RESET] = {
-		.reg = HHI_SYS_CPU_CLK_CNTL1, .bit_idx = 30
+		.reg = HHI_SYS_CPU_CLK_CNTL1,
+		.bit_idx = 30,
+		.active_low = false,
 	},
 	[CLKC_RESET_VID_CLK_CNTL_SOFT_RESET] = {
-		.reg = HHI_VID_CLK_CNTL, .bit_idx = 15
+		.reg = HHI_VID_CLK_CNTL,
+		.bit_idx = 15,
+		.active_low = false,
 	},
 	[CLKC_RESET_VID_DIVIDER_CNTL_SOFT_RESET_POST] = {
-		.reg = HHI_VID_DIVIDER_CNTL, .bit_idx = 7
+		.reg = HHI_VID_DIVIDER_CNTL,
+		.bit_idx = 7,
+		.active_low = false,
 	},
 	[CLKC_RESET_VID_DIVIDER_CNTL_SOFT_RESET_PRE] = {
-		.reg = HHI_VID_DIVIDER_CNTL, .bit_idx = 3
+		.reg = HHI_VID_DIVIDER_CNTL,
+		.bit_idx = 3,
+		.active_low = false,
 	},
 	[CLKC_RESET_VID_DIVIDER_CNTL_RESET_N_POST] = {
-		.reg = HHI_VID_DIVIDER_CNTL, .bit_idx = 1
+		.reg = HHI_VID_DIVIDER_CNTL,
+		.bit_idx = 1,
+		.active_low = true,
 	},
 	[CLKC_RESET_VID_DIVIDER_CNTL_RESET_N_PRE] = {
-		.reg = HHI_VID_DIVIDER_CNTL, .bit_idx = 0
+		.reg = HHI_VID_DIVIDER_CNTL,
+		.bit_idx = 0,
+		.active_low = true,
 	},
 };
 
@@ -3102,22 +3147,22 @@ static int meson8b_clk_reset_update(struct reset_controller_dev *rcdev,
 {
 	struct meson8b_clk_reset *meson8b_clk_reset =
 		container_of(rcdev, struct meson8b_clk_reset, reset);
-	unsigned long flags;
 	const struct meson8b_clk_reset_line *reset;
+	unsigned int value = 0;
+	unsigned long flags;
 
 	if (id >= ARRAY_SIZE(meson8b_clk_reset_bits))
 		return -EINVAL;
 
 	reset = &meson8b_clk_reset_bits[id];
 
+	if (assert != reset->active_low)
+		value = BIT(reset->bit_idx);
+
 	spin_lock_irqsave(&meson_clk_lock, flags);
 
-	if (assert)
-		regmap_update_bits(meson8b_clk_reset->regmap, reset->reg,
-				   BIT(reset->bit_idx), BIT(reset->bit_idx));
-	else
-		regmap_update_bits(meson8b_clk_reset->regmap, reset->reg,
-				   BIT(reset->bit_idx), 0);
+	regmap_update_bits(meson8b_clk_reset->regmap, reset->reg,
+			   BIT(reset->bit_idx), value);
 
 	spin_unlock_irqrestore(&meson_clk_lock, flags);
 
diff --git a/drivers/clk/meson/meson8b.h b/drivers/clk/meson/meson8b.h
index ed37196187e6..64aa3e5d3538 100644
--- a/drivers/clk/meson/meson8b.h
+++ b/drivers/clk/meson/meson8b.h
@@ -20,6 +20,10 @@
  * [0] http://dn.odroid.com/S805/Datasheet/S805_Datasheet%20V0.8%2020150126.pdf
  */
 #define HHI_GP_PLL_CNTL			0x40  /* 0x10 offset in data sheet */
+#define HHI_GP_PLL_CNTL2		0x44  /* 0x11 offset in data sheet */
+#define HHI_GP_PLL_CNTL3		0x48  /* 0x12 offset in data sheet */
+#define HHI_GP_PLL_CNTL4		0x4C  /* 0x13 offset in data sheet */
+#define HHI_GP_PLL_CNTL5		0x50  /* 0x14 offset in data sheet */
 #define HHI_VIID_CLK_DIV		0x128 /* 0x4a offset in data sheet */
 #define HHI_VIID_CLK_CNTL		0x12c /* 0x4b offset in data sheet */
 #define HHI_GCLK_MPEG0			0x140 /* 0x50 offset in data sheet */
diff --git a/drivers/clk/mmp/clk-of-mmp2.c b/drivers/clk/mmp/clk-of-mmp2.c
index a60a1be937ad..b4a95cbbda98 100644
--- a/drivers/clk/mmp/clk-of-mmp2.c
+++ b/drivers/clk/mmp/clk-of-mmp2.c
@@ -134,7 +134,7 @@ static DEFINE_SPINLOCK(ssp3_lock);
 static const char *ssp_parent_names[] = {"vctcxo_4", "vctcxo_2", "vctcxo", "pll1_16"};
 
 static DEFINE_SPINLOCK(timer_lock);
-static const char *timer_parent_names[] = {"clk32", "vctcxo_2", "vctcxo_4", "vctcxo"};
+static const char *timer_parent_names[] = {"clk32", "vctcxo_4", "vctcxo_2", "vctcxo"};
 
 static DEFINE_SPINLOCK(reset_lock);
 
diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c
index 106509a27515..7a0b7271fd6f 100644
--- a/drivers/clk/qcom/clk-rcg2.c
+++ b/drivers/clk/qcom/clk-rcg2.c
@@ -217,6 +217,9 @@ static int _freq_tbl_determine_rate(struct clk_hw *hw, const struct freq_tbl *f,
 
 	clk_flags = clk_hw_get_flags(hw);
 	p = clk_hw_get_parent_by_index(hw, index);
+	if (!p)
+		return -EINVAL;
+
 	if (clk_flags & CLK_SET_RATE_PARENT) {
 		rate = f->freq;
 		if (f->pre_div) {
@@ -952,7 +955,7 @@ static void clk_rcg2_dfs_populate_freq(struct clk_hw *hw, unsigned int l,
 	struct clk_rcg2 *rcg = to_clk_rcg2(hw);
 	struct clk_hw *p;
 	unsigned long prate = 0;
-	u32 val, mask, cfg, mode;
+	u32 val, mask, cfg, mode, src;
 	int i, num_parents;
 
 	regmap_read(rcg->clkr.regmap, rcg->cmd_rcgr + SE_PERF_DFSR(l), &cfg);
@@ -962,12 +965,12 @@ static void clk_rcg2_dfs_populate_freq(struct clk_hw *hw, unsigned int l,
 	if (cfg & mask)
 		f->pre_div = cfg & mask;
 
-	cfg &= CFG_SRC_SEL_MASK;
-	cfg >>= CFG_SRC_SEL_SHIFT;
+	src = cfg & CFG_SRC_SEL_MASK;
+	src >>= CFG_SRC_SEL_SHIFT;
 
 	num_parents = clk_hw_get_num_parents(hw);
 	for (i = 0; i < num_parents; i++) {
-		if (cfg == rcg->parent_map[i].cfg) {
+		if (src == rcg->parent_map[i].cfg) {
 			f->src = rcg->parent_map[i].src;
 			p = clk_hw_get_parent_by_index(&rcg->clkr.hw, i);
 			prate = clk_hw_get_rate(p);
diff --git a/drivers/clk/qcom/clk-rpmh.c b/drivers/clk/qcom/clk-rpmh.c
index c3fd632af119..3ed9e623e32b 100644
--- a/drivers/clk/qcom/clk-rpmh.c
+++ b/drivers/clk/qcom/clk-rpmh.c
@@ -147,12 +147,22 @@ static inline bool has_state_changed(struct clk_rpmh *c, u32 state)
 		!= (c->aggr_state & BIT(state));
 }
 
+static int clk_rpmh_send(struct clk_rpmh *c, enum rpmh_state state,
+			 struct tcs_cmd *cmd, bool wait)
+{
+	if (wait)
+		return rpmh_write(c->dev, state, cmd, 1);
+
+	return rpmh_write_async(c->dev, state, cmd, 1);
+}
+
 static int clk_rpmh_send_aggregate_command(struct clk_rpmh *c)
 {
 	struct tcs_cmd cmd = { 0 };
 	u32 cmd_state, on_val;
 	enum rpmh_state state = RPMH_SLEEP_STATE;
 	int ret;
+	bool wait;
 
 	cmd.addr = c->res_addr;
 	cmd_state = c->aggr_state;
@@ -163,7 +173,8 @@ static int clk_rpmh_send_aggregate_command(struct clk_rpmh *c)
 			if (cmd_state & BIT(state))
 				cmd.data = on_val;
 
-			ret = rpmh_write_async(c->dev, state, &cmd, 1);
+			wait = cmd_state && state == RPMH_ACTIVE_ONLY_STATE;
+			ret = clk_rpmh_send(c, state, &cmd, wait);
 			if (ret) {
 				dev_err(c->dev, "set %s state of %s failed: (%d)\n",
 					!state ? "sleep" :
@@ -271,7 +282,7 @@ static int clk_rpmh_bcm_send_cmd(struct clk_rpmh *c, bool enable)
 	cmd.addr = c->res_addr;
 	cmd.data = BCM_TCS_CMD(enable, cmd_state);
 
-	ret = rpmh_write_async(c->dev, RPMH_ACTIVE_ONLY_STATE, &cmd, 1);
+	ret = clk_rpmh_send(c, RPMH_ACTIVE_ONLY_STATE, &cmd, enable);
 	if (ret) {
 		dev_err(c->dev, "set active state of %s failed: (%d)\n",
 			c->res_name, ret);
diff --git a/drivers/clk/qcom/clk-smd-rpm.c b/drivers/clk/qcom/clk-smd-rpm.c
index 930fa4a4c52a..e5c3db11bf26 100644
--- a/drivers/clk/qcom/clk-smd-rpm.c
+++ b/drivers/clk/qcom/clk-smd-rpm.c
@@ -648,6 +648,7 @@ static const struct rpm_smd_clk_desc rpm_clk_qcs404 = {
 };
 
 /* msm8998 */
+DEFINE_CLK_SMD_RPM(msm8998, bimc_clk, bimc_a_clk, QCOM_SMD_RPM_MEM_CLK, 0);
 DEFINE_CLK_SMD_RPM(msm8998, pcnoc_clk, pcnoc_a_clk, QCOM_SMD_RPM_BUS_CLK, 0);
 DEFINE_CLK_SMD_RPM(msm8998, snoc_clk, snoc_a_clk, QCOM_SMD_RPM_BUS_CLK, 1);
 DEFINE_CLK_SMD_RPM(msm8998, cnoc_clk, cnoc_a_clk, QCOM_SMD_RPM_BUS_CLK, 2);
@@ -671,6 +672,8 @@ DEFINE_CLK_SMD_RPM_XO_BUFFER_PINCTRL(msm8998, rf_clk2_pin, rf_clk2_a_pin, 5);
 DEFINE_CLK_SMD_RPM_XO_BUFFER(msm8998, rf_clk3, rf_clk3_a, 6);
 DEFINE_CLK_SMD_RPM_XO_BUFFER_PINCTRL(msm8998, rf_clk3_pin, rf_clk3_a_pin, 6);
 static struct clk_smd_rpm *msm8998_clks[] = {
+	[RPM_SMD_BIMC_CLK] = &msm8998_bimc_clk,
+	[RPM_SMD_BIMC_A_CLK] = &msm8998_bimc_a_clk,
 	[RPM_SMD_PCNOC_CLK] = &msm8998_pcnoc_clk,
 	[RPM_SMD_PCNOC_A_CLK] = &msm8998_pcnoc_a_clk,
 	[RPM_SMD_SNOC_CLK] = &msm8998_snoc_clk,
diff --git a/drivers/clk/qcom/gcc-msm8916.c b/drivers/clk/qcom/gcc-msm8916.c
index 4e329a7baf2b..17e4a5a2a9fd 100644
--- a/drivers/clk/qcom/gcc-msm8916.c
+++ b/drivers/clk/qcom/gcc-msm8916.c
@@ -260,7 +260,7 @@ static struct clk_pll gpll0 = {
 	.l_reg = 0x21004,
 	.m_reg = 0x21008,
 	.n_reg = 0x2100c,
-	.config_reg = 0x21014,
+	.config_reg = 0x21010,
 	.mode_reg = 0x21000,
 	.status_reg = 0x2101c,
 	.status_bit = 17,
@@ -287,7 +287,7 @@ static struct clk_pll gpll1 = {
 	.l_reg = 0x20004,
 	.m_reg = 0x20008,
 	.n_reg = 0x2000c,
-	.config_reg = 0x20014,
+	.config_reg = 0x20010,
 	.mode_reg = 0x20000,
 	.status_reg = 0x2001c,
 	.status_bit = 17,
@@ -314,7 +314,7 @@ static struct clk_pll gpll2 = {
 	.l_reg = 0x4a004,
 	.m_reg = 0x4a008,
 	.n_reg = 0x4a00c,
-	.config_reg = 0x4a014,
+	.config_reg = 0x4a010,
 	.mode_reg = 0x4a000,
 	.status_reg = 0x4a01c,
 	.status_bit = 17,
@@ -341,7 +341,7 @@ static struct clk_pll bimc_pll = {
 	.l_reg = 0x23004,
 	.m_reg = 0x23008,
 	.n_reg = 0x2300c,
-	.config_reg = 0x23014,
+	.config_reg = 0x23010,
 	.mode_reg = 0x23000,
 	.status_reg = 0x2301c,
 	.status_bit = 17,
diff --git a/drivers/clk/qcom/gcc-sdm660.c b/drivers/clk/qcom/gcc-sdm660.c
index 8827db23066f..e111bfcd3230 100644
--- a/drivers/clk/qcom/gcc-sdm660.c
+++ b/drivers/clk/qcom/gcc-sdm660.c
@@ -1715,6 +1715,9 @@ static struct clk_branch gcc_mss_cfg_ahb_clk = {
 
 static struct clk_branch gcc_mss_mnoc_bimc_axi_clk = {
 	.halt_reg = 0x8a004,
+	.halt_check = BRANCH_HALT,
+	.hwcg_reg = 0x8a004,
+	.hwcg_bit = 1,
 	.clkr = {
 		.enable_reg = 0x8a004,
 		.enable_mask = BIT(0),
diff --git a/drivers/clk/qcom/gcc-sdm845.c b/drivers/clk/qcom/gcc-sdm845.c
index 95be125c3bdd..56d22dd225c9 100644
--- a/drivers/clk/qcom/gcc-sdm845.c
+++ b/drivers/clk/qcom/gcc-sdm845.c
@@ -3255,6 +3255,7 @@ static struct gdsc hlos1_vote_aggre_noc_mmu_audio_tbu_gdsc = {
 		.name = "hlos1_vote_aggre_noc_mmu_audio_tbu_gdsc",
 	},
 	.pwrsts = PWRSTS_OFF_ON,
+	.flags = VOTABLE,
 };
 
 static struct gdsc hlos1_vote_aggre_noc_mmu_pcie_tbu_gdsc = {
@@ -3263,6 +3264,7 @@ static struct gdsc hlos1_vote_aggre_noc_mmu_pcie_tbu_gdsc = {
 		.name = "hlos1_vote_aggre_noc_mmu_pcie_tbu_gdsc",
 	},
 	.pwrsts = PWRSTS_OFF_ON,
+	.flags = VOTABLE,
 };
 
 static struct gdsc hlos1_vote_aggre_noc_mmu_tbu1_gdsc = {
@@ -3271,6 +3273,7 @@ static struct gdsc hlos1_vote_aggre_noc_mmu_tbu1_gdsc = {
 		.name = "hlos1_vote_aggre_noc_mmu_tbu1_gdsc",
 	},
 	.pwrsts = PWRSTS_OFF_ON,
+	.flags = VOTABLE,
 };
 
 static struct gdsc hlos1_vote_aggre_noc_mmu_tbu2_gdsc = {
@@ -3279,6 +3282,7 @@ static struct gdsc hlos1_vote_aggre_noc_mmu_tbu2_gdsc = {
 		.name = "hlos1_vote_aggre_noc_mmu_tbu2_gdsc",
 	},
 	.pwrsts = PWRSTS_OFF_ON,
+	.flags = VOTABLE,
 };
 
 static struct gdsc hlos1_vote_mmnoc_mmu_tbu_hf0_gdsc = {
@@ -3287,6 +3291,7 @@ static struct gdsc hlos1_vote_mmnoc_mmu_tbu_hf0_gdsc = {
 		.name = "hlos1_vote_mmnoc_mmu_tbu_hf0_gdsc",
 	},
 	.pwrsts = PWRSTS_OFF_ON,
+	.flags = VOTABLE,
 };
 
 static struct gdsc hlos1_vote_mmnoc_mmu_tbu_hf1_gdsc = {
@@ -3295,6 +3300,7 @@ static struct gdsc hlos1_vote_mmnoc_mmu_tbu_hf1_gdsc = {
 		.name = "hlos1_vote_mmnoc_mmu_tbu_hf1_gdsc",
 	},
 	.pwrsts = PWRSTS_OFF_ON,
+	.flags = VOTABLE,
 };
 
 static struct gdsc hlos1_vote_mmnoc_mmu_tbu_sf_gdsc = {
@@ -3303,6 +3309,7 @@ static struct gdsc hlos1_vote_mmnoc_mmu_tbu_sf_gdsc = {
 		.name = "hlos1_vote_mmnoc_mmu_tbu_sf_gdsc",
 	},
 	.pwrsts = PWRSTS_OFF_ON,
+	.flags = VOTABLE,
 };
 
 static struct clk_regmap *gcc_sdm845_clocks[] = {
diff --git a/drivers/clk/qcom/turingcc-qcs404.c b/drivers/clk/qcom/turingcc-qcs404.c
index aa859e6ec9bd..4cfbbf5bf4d9 100644
--- a/drivers/clk/qcom/turingcc-qcs404.c
+++ b/drivers/clk/qcom/turingcc-qcs404.c
@@ -96,7 +96,7 @@ static const struct regmap_config turingcc_regmap_config = {
 	.reg_bits	= 32,
 	.reg_stride	= 4,
 	.val_bits	= 32,
-	.max_register	= 0x30000,
+	.max_register	= 0x23004,
 	.fast_io	= true,
 };
 
diff --git a/drivers/clk/renesas/rcar-gen3-cpg.c b/drivers/clk/renesas/rcar-gen3-cpg.c
index d25c8ba00a65..532626946b8d 100644
--- a/drivers/clk/renesas/rcar-gen3-cpg.c
+++ b/drivers/clk/renesas/rcar-gen3-cpg.c
@@ -464,7 +464,8 @@ static struct clk * __init cpg_rpc_clk_register(const char *name,
 
 	clk = clk_register_composite(NULL, name, &parent_name, 1, NULL, NULL,
 				     &rpc->div.hw,  &clk_divider_ops,
-				     &rpc->gate.hw, &clk_gate_ops, 0);
+				     &rpc->gate.hw, &clk_gate_ops,
+				     CLK_SET_RATE_PARENT);
 	if (IS_ERR(clk)) {
 		kfree(rpc);
 		return clk;
@@ -500,7 +501,8 @@ static struct clk * __init cpg_rpcd2_clk_register(const char *name,
 
 	clk = clk_register_composite(NULL, name, &parent_name, 1, NULL, NULL,
 				     &rpcd2->fixed.hw, &clk_fixed_factor_ops,
-				     &rpcd2->gate.hw, &clk_gate_ops, 0);
+				     &rpcd2->gate.hw, &clk_gate_ops,
+				     CLK_SET_RATE_PARENT);
 	if (IS_ERR(clk))
 		kfree(rpcd2);
 
diff --git a/drivers/clk/renesas/renesas-cpg-mssr.c b/drivers/clk/renesas/renesas-cpg-mssr.c
index cbe5fb468b7f..1aa00acddde7 100644
--- a/drivers/clk/renesas/renesas-cpg-mssr.c
+++ b/drivers/clk/renesas/renesas-cpg-mssr.c
@@ -804,7 +804,8 @@ static int cpg_mssr_suspend_noirq(struct device *dev)
 	/* Save module registers with bits under our control */
 	for (reg = 0; reg < ARRAY_SIZE(priv->smstpcr_saved); reg++) {
 		if (priv->smstpcr_saved[reg].mask)
-			priv->smstpcr_saved[reg].val =
+			priv->smstpcr_saved[reg].val = priv->stbyctrl ?
+				readb(priv->base + STBCR(reg)) :
 				readl(priv->base + SMSTPCR(reg));
 	}
 
@@ -864,8 +865,9 @@ static int cpg_mssr_resume_noirq(struct device *dev)
 		}
 
 		if (!i)
-			dev_warn(dev, "Failed to enable SMSTP %p[0x%x]\n",
-				 priv->base + SMSTPCR(reg), oldval & mask);
+			dev_warn(dev, "Failed to enable %s%u[0x%x]\n",
+				 priv->stbyctrl ? "STB" : "SMSTP", reg,
+				 oldval & mask);
 	}
 
 	return 0;
diff --git a/drivers/clk/rockchip/clk-rk3228.c b/drivers/clk/rockchip/clk-rk3228.c
index bdb126321e56..d6f9502931d8 100644
--- a/drivers/clk/rockchip/clk-rk3228.c
+++ b/drivers/clk/rockchip/clk-rk3228.c
@@ -155,8 +155,6 @@ PNAME(mux_i2s_out_p)		= { "i2s1_pre", "xin12m" };
 PNAME(mux_i2s2_p)		= { "i2s2_src", "i2s2_frac", "xin12m" };
 PNAME(mux_sclk_spdif_p)		= { "sclk_spdif_src", "spdif_frac", "xin12m" };
 
-PNAME(mux_aclk_gpu_pre_p)	= { "cpll_gpu", "gpll_gpu", "hdmiphy_gpu", "usb480m_gpu" };
-
 PNAME(mux_uart0_p)		= { "uart0_src", "uart0_frac", "xin24m" };
 PNAME(mux_uart1_p)		= { "uart1_src", "uart1_frac", "xin24m" };
 PNAME(mux_uart2_p)		= { "uart2_src", "uart2_frac", "xin24m" };
@@ -467,16 +465,9 @@ static struct rockchip_clk_branch rk3228_clk_branches[] __initdata = {
 			RK2928_CLKSEL_CON(24), 6, 10, DFLAGS,
 			RK2928_CLKGATE_CON(2), 8, GFLAGS),
 
-	GATE(0, "cpll_gpu", "cpll", 0,
-			RK2928_CLKGATE_CON(3), 13, GFLAGS),
-	GATE(0, "gpll_gpu", "gpll", 0,
-			RK2928_CLKGATE_CON(3), 13, GFLAGS),
-	GATE(0, "hdmiphy_gpu", "hdmiphy", 0,
-			RK2928_CLKGATE_CON(3), 13, GFLAGS),
-	GATE(0, "usb480m_gpu", "usb480m", 0,
+	COMPOSITE(0, "aclk_gpu_pre", mux_pll_src_4plls_p, 0,
+			RK2928_CLKSEL_CON(34), 5, 2, MFLAGS, 0, 5, DFLAGS,
 			RK2928_CLKGATE_CON(3), 13, GFLAGS),
-	COMPOSITE_NOGATE(0, "aclk_gpu_pre", mux_aclk_gpu_pre_p, 0,
-			RK2928_CLKSEL_CON(34), 5, 2, MFLAGS, 0, 5, DFLAGS),
 
 	COMPOSITE(SCLK_SPI0, "sclk_spi0", mux_pll_src_2plls_p, 0,
 			RK2928_CLKSEL_CON(25), 8, 1, MFLAGS, 0, 7, DFLAGS,
@@ -581,8 +572,8 @@ static struct rockchip_clk_branch rk3228_clk_branches[] __initdata = {
 	GATE(0, "pclk_peri_noc", "pclk_peri", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(12), 2, GFLAGS),
 
 	/* PD_GPU */
-	GATE(ACLK_GPU, "aclk_gpu", "aclk_gpu_pre", 0, RK2928_CLKGATE_CON(13), 14, GFLAGS),
-	GATE(0, "aclk_gpu_noc", "aclk_gpu_pre", 0, RK2928_CLKGATE_CON(13), 15, GFLAGS),
+	GATE(ACLK_GPU, "aclk_gpu", "aclk_gpu_pre", 0, RK2928_CLKGATE_CON(7), 14, GFLAGS),
+	GATE(0, "aclk_gpu_noc", "aclk_gpu_pre", 0, RK2928_CLKGATE_CON(7), 15, GFLAGS),
 
 	/* PD_BUS */
 	GATE(0, "sclk_initmem_mbist", "aclk_cpu", 0, RK2928_CLKGATE_CON(8), 1, GFLAGS),
diff --git a/drivers/clk/samsung/clk-exynos5420.c b/drivers/clk/samsung/clk-exynos5420.c
index 94b02273a941..99cae7c07c53 100644
--- a/drivers/clk/samsung/clk-exynos5420.c
+++ b/drivers/clk/samsung/clk-exynos5420.c
@@ -164,6 +164,8 @@ static const unsigned long exynos5x_clk_regs[] __initconst = {
 	GATE_BUS_CPU,
 	GATE_SCLK_CPU,
 	CLKOUT_CMU_CPU,
+	APLL_CON0,
+	KPLL_CON0,
 	CPLL_CON0,
 	DPLL_CON0,
 	EPLL_CON0,
@@ -528,7 +530,7 @@ static const struct samsung_div_clock exynos5800_div_clks[] __initconst = {
 
 static const struct samsung_gate_clock exynos5800_gate_clks[] __initconst = {
 	GATE(CLK_ACLK550_CAM, "aclk550_cam", "mout_user_aclk550_cam",
-				GATE_BUS_TOP, 24, 0, 0),
+				GATE_BUS_TOP, 24, CLK_IS_CRITICAL, 0),
 	GATE(CLK_ACLK432_SCALER, "aclk432_scaler", "mout_user_aclk432_scaler",
 				GATE_BUS_TOP, 27, CLK_IS_CRITICAL, 0),
 };
@@ -915,25 +917,25 @@ static const struct samsung_gate_clock exynos5x_gate_clks[] __initconst = {
 	GATE(0, "aclk300_jpeg", "mout_user_aclk300_jpeg",
 			GATE_BUS_TOP, 4, CLK_IGNORE_UNUSED, 0),
 	GATE(0, "aclk333_432_isp0", "mout_user_aclk333_432_isp0",
-			GATE_BUS_TOP, 5, 0, 0),
+			GATE_BUS_TOP, 5, CLK_IS_CRITICAL, 0),
 	GATE(0, "aclk300_gscl", "mout_user_aclk300_gscl",
 			GATE_BUS_TOP, 6, CLK_IS_CRITICAL, 0),
 	GATE(0, "aclk333_432_gscl", "mout_user_aclk333_432_gscl",
 			GATE_BUS_TOP, 7, CLK_IGNORE_UNUSED, 0),
 	GATE(0, "aclk333_432_isp", "mout_user_aclk333_432_isp",
-			GATE_BUS_TOP, 8, 0, 0),
+			GATE_BUS_TOP, 8, CLK_IS_CRITICAL, 0),
 	GATE(CLK_PCLK66_GPIO, "pclk66_gpio", "mout_user_pclk66_gpio",
 			GATE_BUS_TOP, 9, CLK_IGNORE_UNUSED, 0),
 	GATE(0, "aclk66_psgen", "mout_user_aclk66_psgen",
 			GATE_BUS_TOP, 10, CLK_IGNORE_UNUSED, 0),
 	GATE(0, "aclk266_isp", "mout_user_aclk266_isp",
-			GATE_BUS_TOP, 13, 0, 0),
+			GATE_BUS_TOP, 13, CLK_IS_CRITICAL, 0),
 	GATE(0, "aclk166", "mout_user_aclk166",
 			GATE_BUS_TOP, 14, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_ACLK333, "aclk333", "mout_user_aclk333",
 			GATE_BUS_TOP, 15, CLK_IS_CRITICAL, 0),
 	GATE(0, "aclk400_isp", "mout_user_aclk400_isp",
-			GATE_BUS_TOP, 16, 0, 0),
+			GATE_BUS_TOP, 16, CLK_IS_CRITICAL, 0),
 	GATE(0, "aclk400_mscl", "mout_user_aclk400_mscl",
 			GATE_BUS_TOP, 17, CLK_IS_CRITICAL, 0),
 	GATE(0, "aclk200_disp1", "mout_user_aclk200_disp1",
@@ -1133,8 +1135,10 @@ static const struct samsung_gate_clock exynos5x_gate_clks[] __initconst = {
 			GATE_IP_GSCL1, 3, 0, 0),
 	GATE(CLK_SMMU_FIMCL1, "smmu_fimcl1", "dout_gscl_blk_333",
 			GATE_IP_GSCL1, 4, 0, 0),
-	GATE(CLK_GSCL_WA, "gscl_wa", "sclk_gscl_wa", GATE_IP_GSCL1, 12, 0, 0),
-	GATE(CLK_GSCL_WB, "gscl_wb", "sclk_gscl_wb", GATE_IP_GSCL1, 13, 0, 0),
+	GATE(CLK_GSCL_WA, "gscl_wa", "sclk_gscl_wa", GATE_IP_GSCL1, 12,
+			CLK_IS_CRITICAL, 0),
+	GATE(CLK_GSCL_WB, "gscl_wb", "sclk_gscl_wb", GATE_IP_GSCL1, 13,
+			CLK_IS_CRITICAL, 0),
 	GATE(CLK_SMMU_FIMCL3, "smmu_fimcl3,", "dout_gscl_blk_333",
 			GATE_IP_GSCL1, 16, 0, 0),
 	GATE(CLK_FIMC_LITE3, "fimc_lite3", "aclk333_432_gscl",
diff --git a/drivers/clk/samsung/clk-exynos5433.c b/drivers/clk/samsung/clk-exynos5433.c
index d49c466af143..de48588c7edf 100644
--- a/drivers/clk/samsung/clk-exynos5433.c
+++ b/drivers/clk/samsung/clk-exynos5433.c
@@ -1706,7 +1706,8 @@ static const struct samsung_gate_clock peric_gate_clks[] __initconst = {
 	GATE(CLK_SCLK_PCM1, "sclk_pcm1", "sclk_pcm1_peric",
 			ENABLE_SCLK_PERIC, 7, CLK_SET_RATE_PARENT, 0),
 	GATE(CLK_SCLK_I2S1, "sclk_i2s1", "sclk_i2s1_peric",
-			ENABLE_SCLK_PERIC, 6, CLK_SET_RATE_PARENT, 0),
+			ENABLE_SCLK_PERIC, 6,
+			CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_SCLK_SPI2, "sclk_spi2", "sclk_spi2_peric", ENABLE_SCLK_PERIC,
 			5, CLK_SET_RATE_PARENT, 0),
 	GATE(CLK_SCLK_SPI1, "sclk_spi1", "sclk_spi1_peric", ENABLE_SCLK_PERIC,
diff --git a/drivers/clk/sifive/fu540-prci.c b/drivers/clk/sifive/fu540-prci.c
index 6282ee2f361c..a8901f90a61a 100644
--- a/drivers/clk/sifive/fu540-prci.c
+++ b/drivers/clk/sifive/fu540-prci.c
@@ -586,7 +586,10 @@ static int sifive_fu540_prci_probe(struct platform_device *pdev)
 	struct __prci_data *pd;
 	int r;
 
-	pd = devm_kzalloc(dev, sizeof(*pd), GFP_KERNEL);
+	pd = devm_kzalloc(dev,
+			  struct_size(pd, hw_clks.hws,
+				      ARRAY_SIZE(__prci_init_clocks)),
+			  GFP_KERNEL);
 	if (!pd)
 		return -ENOMEM;
 
diff --git a/drivers/clk/sirf/clk-atlas6.c b/drivers/clk/sirf/clk-atlas6.c
index c84d5bab7ac2..b95483bb6a5e 100644
--- a/drivers/clk/sirf/clk-atlas6.c
+++ b/drivers/clk/sirf/clk-atlas6.c
@@ -135,7 +135,7 @@ static void __init atlas6_clk_init(struct device_node *np)
 
 	for (i = pll1; i < maxclk; i++) {
 		atlas6_clks[i] = clk_register(NULL, atlas6_clk_hw_array[i]);
-		BUG_ON(!atlas6_clks[i]);
+		BUG_ON(IS_ERR(atlas6_clks[i]));
 	}
 	clk_register_clkdev(atlas6_clks[cpu], NULL, "cpu");
 	clk_register_clkdev(atlas6_clks[io],  NULL, "io");
diff --git a/drivers/clk/sprd/common.c b/drivers/clk/sprd/common.c
index 8bdab1c3013b..c9b777592b2c 100644
--- a/drivers/clk/sprd/common.c
+++ b/drivers/clk/sprd/common.c
@@ -45,7 +45,7 @@ int sprd_clk_regmap_init(struct platform_device *pdev,
 
 	if (of_find_property(node, "sprd,syscon", NULL)) {
 		regmap = syscon_regmap_lookup_by_phandle(node, "sprd,syscon");
-		if (IS_ERR_OR_NULL(regmap)) {
+		if (IS_ERR(regmap)) {
 			pr_err("%s: failed to get syscon regmap\n", __func__);
 			return PTR_ERR(regmap);
 		}
diff --git a/drivers/clk/sprd/pll.c b/drivers/clk/sprd/pll.c
index 640270f51aa5..eb8862752c2b 100644
--- a/drivers/clk/sprd/pll.c
+++ b/drivers/clk/sprd/pll.c
@@ -105,7 +105,7 @@ static unsigned long _sprd_pll_recalc_rate(const struct sprd_pll *pll,
 
 	cfg = kcalloc(regs_num, sizeof(*cfg), GFP_KERNEL);
 	if (!cfg)
-		return -ENOMEM;
+		return parent_rate;
 
 	for (i = 0; i < regs_num; i++)
 		cfg[i] = sprd_pll_read(pll, i);
diff --git a/drivers/clk/st/clk-flexgen.c b/drivers/clk/st/clk-flexgen.c
index d18e49b4976f..5d8f25a49f8f 100644
--- a/drivers/clk/st/clk-flexgen.c
+++ b/drivers/clk/st/clk-flexgen.c
@@ -374,6 +374,7 @@ static void __init st_of_flexgen_setup(struct device_node *np)
 			break;
 		}
 
+		flex_flags &= ~CLK_IS_CRITICAL;
 		of_clk_detect_critical(np, i, &flex_flags);
 
 		/*
diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c
index 1786ee8fe8bb..d802ca251ca2 100644
--- a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c
+++ b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c
@@ -910,11 +910,26 @@ static const struct sunxi_ccu_desc sun50i_a64_ccu_desc = {
 	.num_resets	= ARRAY_SIZE(sun50i_a64_ccu_resets),
 };
 
+static struct ccu_pll_nb sun50i_a64_pll_cpu_nb = {
+	.common	= &pll_cpux_clk.common,
+	/* copy from pll_cpux_clk */
+	.enable	= BIT(31),
+	.lock	= BIT(28),
+};
+
+static struct ccu_mux_nb sun50i_a64_cpu_nb = {
+	.common		= &cpux_clk.common,
+	.cm		= &cpux_clk.mux,
+	.delay_us	= 1, /* > 8 clock cycles at 24 MHz */
+	.bypass_index	= 1, /* index of 24 MHz oscillator */
+};
+
 static int sun50i_a64_ccu_probe(struct platform_device *pdev)
 {
 	struct resource *res;
 	void __iomem *reg;
 	u32 val;
+	int ret;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	reg = devm_ioremap_resource(&pdev->dev, res);
@@ -928,7 +943,18 @@ static int sun50i_a64_ccu_probe(struct platform_device *pdev)
 
 	writel(0x515, reg + SUN50I_A64_PLL_MIPI_REG);
 
-	return sunxi_ccu_probe(pdev->dev.of_node, reg, &sun50i_a64_ccu_desc);
+	ret = sunxi_ccu_probe(pdev->dev.of_node, reg, &sun50i_a64_ccu_desc);
+	if (ret)
+		return ret;
+
+	/* Gate then ungate PLL CPU after any rate changes */
+	ccu_pll_notifier_register(&sun50i_a64_pll_cpu_nb);
+
+	/* Reparent CPU during PLL CPU rate changes */
+	ccu_mux_notifier_register(pll_cpux_clk.common.hw.clk,
+				  &sun50i_a64_cpu_nb);
+
+	return 0;
 }
 
 static const struct of_device_id sun50i_a64_ccu_ids[] = {
diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-h6-r.c b/drivers/clk/sunxi-ng/ccu-sun50i-h6-r.c
index 27554eaf6929..3f78035ff85a 100644
--- a/drivers/clk/sunxi-ng/ccu-sun50i-h6-r.c
+++ b/drivers/clk/sunxi-ng/ccu-sun50i-h6-r.c
@@ -23,9 +23,9 @@
  */
 
 static const char * const ar100_r_apb2_parents[] = { "osc24M", "osc32k",
-					     "pll-periph0", "iosc" };
+						     "iosc", "pll-periph0" };
 static const struct ccu_mux_var_prediv ar100_r_apb2_predivs[] = {
-	{ .index = 2, .shift = 0, .width = 5 },
+	{ .index = 3, .shift = 0, .width = 5 },
 };
 
 static struct ccu_div ar100_clk = {
diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-r40.c b/drivers/clk/sunxi-ng/ccu-sun8i-r40.c
index 540f5f7454fc..8a5b8fcdcc2f 100644
--- a/drivers/clk/sunxi-ng/ccu-sun8i-r40.c
+++ b/drivers/clk/sunxi-ng/ccu-sun8i-r40.c
@@ -761,7 +761,8 @@ static struct ccu_mp outa_clk = {
 		.reg		= 0x1f0,
 		.features	= CCU_FEATURE_FIXED_PREDIV,
 		.hw.init	= CLK_HW_INIT_PARENTS("outa", out_parents,
-						      &ccu_mp_ops, 0),
+						      &ccu_mp_ops,
+						      CLK_SET_RATE_PARENT),
 	}
 };
 
@@ -779,7 +780,8 @@ static struct ccu_mp outb_clk = {
 		.reg		= 0x1f4,
 		.features	= CCU_FEATURE_FIXED_PREDIV,
 		.hw.init	= CLK_HW_INIT_PARENTS("outb", out_parents,
-						      &ccu_mp_ops, 0),
+						      &ccu_mp_ops,
+						      CLK_SET_RATE_PARENT),
 	}
 };
 
diff --git a/drivers/clk/sunxi/clk-sunxi.c b/drivers/clk/sunxi/clk-sunxi.c
index 27201fd26e44..e1aa1fbac48a 100644
--- a/drivers/clk/sunxi/clk-sunxi.c
+++ b/drivers/clk/sunxi/clk-sunxi.c
@@ -90,7 +90,7 @@ static void sun6i_a31_get_pll1_factors(struct factors_request *req)
 	 * Round down the frequency to the closest multiple of either
 	 * 6 or 16
 	 */
-	u32 round_freq_6 = round_down(freq_mhz, 6);
+	u32 round_freq_6 = rounddown(freq_mhz, 6);
 	u32 round_freq_16 = round_down(freq_mhz, 16);
 
 	if (round_freq_6 > round_freq_16)
diff --git a/drivers/clk/tegra/clk-tegra-periph.c b/drivers/clk/tegra/clk-tegra-periph.c
index 1ed85f120a1b..49b9f2f85bad 100644
--- a/drivers/clk/tegra/clk-tegra-periph.c
+++ b/drivers/clk/tegra/clk-tegra-periph.c
@@ -785,7 +785,11 @@ static struct tegra_periph_init_data gate_clks[] = {
 	GATE("ahbdma", "hclk", 33, 0, tegra_clk_ahbdma, 0),
 	GATE("apbdma", "pclk", 34, 0, tegra_clk_apbdma, 0),
 	GATE("kbc", "clk_32k", 36, TEGRA_PERIPH_ON_APB | TEGRA_PERIPH_NO_RESET, tegra_clk_kbc, 0),
-	GATE("fuse", "clk_m", 39, TEGRA_PERIPH_ON_APB, tegra_clk_fuse, 0),
+	/*
+	 * Critical for RAM re-repair operation, which must occur on resume
+	 * from LP1 system suspend and as part of CCPLEX cluster switching.
+	 */
+	GATE("fuse", "clk_m", 39, TEGRA_PERIPH_ON_APB, tegra_clk_fuse, CLK_IS_CRITICAL),
 	GATE("fuse_burn", "clk_m", 39, TEGRA_PERIPH_ON_APB, tegra_clk_fuse_burn, 0),
 	GATE("kfuse", "clk_m", 40, TEGRA_PERIPH_ON_APB, tegra_clk_kfuse, 0),
 	GATE("apbif", "clk_m", 107, TEGRA_PERIPH_ON_APB, tegra_clk_apbif, 0),
diff --git a/drivers/clk/tegra/clk-tegra-pmc.c b/drivers/clk/tegra/clk-tegra-pmc.c
index bec3e008335f..5e044ba1ae36 100644
--- a/drivers/clk/tegra/clk-tegra-pmc.c
+++ b/drivers/clk/tegra/clk-tegra-pmc.c
@@ -49,16 +49,16 @@ struct pmc_clk_init_data {
 
 static DEFINE_SPINLOCK(clk_out_lock);
 
-static const char *clk_out1_parents[] = { "clk_m", "clk_m_div2",
-	"clk_m_div4", "extern1",
+static const char *clk_out1_parents[] = { "osc", "osc_div2",
+	"osc_div4", "extern1",
 };
 
-static const char *clk_out2_parents[] = { "clk_m", "clk_m_div2",
-	"clk_m_div4", "extern2",
+static const char *clk_out2_parents[] = { "osc", "osc_div2",
+	"osc_div4", "extern2",
 };
 
-static const char *clk_out3_parents[] = { "clk_m", "clk_m_div2",
-	"clk_m_div4", "extern3",
+static const char *clk_out3_parents[] = { "osc", "osc_div2",
+	"osc_div4", "extern3",
 };
 
 static struct pmc_clk_init_data pmc_clks[] = {
diff --git a/drivers/clk/ti/clk-33xx.c b/drivers/clk/ti/clk-33xx.c
index a360d3109555..73f567d8022f 100644
--- a/drivers/clk/ti/clk-33xx.c
+++ b/drivers/clk/ti/clk-33xx.c
@@ -212,7 +212,7 @@ static const struct omap_clkctrl_reg_data am3_mpu_clkctrl_regs[] __initconst = {
 };
 
 static const struct omap_clkctrl_reg_data am3_l4_rtc_clkctrl_regs[] __initconst = {
-	{ AM3_L4_RTC_RTC_CLKCTRL, NULL, CLKF_SW_SUP, "clk_32768_ck" },
+	{ AM3_L4_RTC_RTC_CLKCTRL, NULL, CLKF_SW_SUP, "clk-24mhz-clkctrl:0000:0" },
 	{ 0 },
 };
 
diff --git a/drivers/clk/ti/clk-43xx.c b/drivers/clk/ti/clk-43xx.c
index 2782d91838ac..2cca1ced913d 100644
--- a/drivers/clk/ti/clk-43xx.c
+++ b/drivers/clk/ti/clk-43xx.c
@@ -78,7 +78,7 @@ static const struct omap_clkctrl_reg_data am4_gfx_l3_clkctrl_regs[] __initconst
 };
 
 static const struct omap_clkctrl_reg_data am4_l4_rtc_clkctrl_regs[] __initconst = {
-	{ AM4_L4_RTC_RTC_CLKCTRL, NULL, CLKF_SW_SUP, "clk_32768_ck" },
+	{ AM4_L4_RTC_RTC_CLKCTRL, NULL, CLKF_SW_SUP, "clkdiv32k_ick" },
 	{ 0 },
 };
 
diff --git a/drivers/clk/ti/clk-7xx.c b/drivers/clk/ti/clk-7xx.c
index 9dd6185a4b4e..66e4b2b9ec60 100644
--- a/drivers/clk/ti/clk-7xx.c
+++ b/drivers/clk/ti/clk-7xx.c
@@ -405,7 +405,7 @@ static const struct omap_clkctrl_bit_data dra7_gmac_bit_data[] __initconst = {
 };
 
 static const struct omap_clkctrl_reg_data dra7_gmac_clkctrl_regs[] __initconst = {
-	{ DRA7_GMAC_GMAC_CLKCTRL, dra7_gmac_bit_data, CLKF_SW_SUP, "dpll_gmac_ck" },
+	{ DRA7_GMAC_GMAC_CLKCTRL, dra7_gmac_bit_data, CLKF_SW_SUP, "gmac_main_clk" },
 	{ 0 },
 };
 
diff --git a/drivers/clk/ti/composite.c b/drivers/clk/ti/composite.c
index 6a89936ba03a..eaa43575cfa5 100644
--- a/drivers/clk/ti/composite.c
+++ b/drivers/clk/ti/composite.c
@@ -196,6 +196,7 @@ cleanup:
 		if (!cclk->comp_clks[i])
 			continue;
 		list_del(&cclk->comp_clks[i]->link);
+		kfree(cclk->comp_clks[i]->parent_names);
 		kfree(cclk->comp_clks[i]);
 	}
 
diff --git a/drivers/clk/uniphier/clk-uniphier-peri.c b/drivers/clk/uniphier/clk-uniphier-peri.c
index 9caa52944b1c..3e32db9dad81 100644
--- a/drivers/clk/uniphier/clk-uniphier-peri.c
+++ b/drivers/clk/uniphier/clk-uniphier-peri.c
@@ -18,8 +18,8 @@
 #define UNIPHIER_PERI_CLK_FI2C(idx, ch)					\
 	UNIPHIER_CLK_GATE("i2c" #ch, (idx), "i2c", 0x24, 24 + (ch))
 
-#define UNIPHIER_PERI_CLK_SCSSI(idx)					\
-	UNIPHIER_CLK_GATE("scssi", (idx), "spi", 0x20, 17)
+#define UNIPHIER_PERI_CLK_SCSSI(idx, ch)				\
+	UNIPHIER_CLK_GATE("scssi" #ch, (idx), "spi", 0x20, 17 + (ch))
 
 #define UNIPHIER_PERI_CLK_MCSSI(idx)					\
 	UNIPHIER_CLK_GATE("mcssi", (idx), "spi", 0x24, 14)
@@ -35,7 +35,7 @@ const struct uniphier_clk_data uniphier_ld4_peri_clk_data[] = {
 	UNIPHIER_PERI_CLK_I2C(6, 2),
 	UNIPHIER_PERI_CLK_I2C(7, 3),
 	UNIPHIER_PERI_CLK_I2C(8, 4),
-	UNIPHIER_PERI_CLK_SCSSI(11),
+	UNIPHIER_PERI_CLK_SCSSI(11, 0),
 	{ /* sentinel */ }
 };
 
@@ -51,7 +51,10 @@ const struct uniphier_clk_data uniphier_pro4_peri_clk_data[] = {
 	UNIPHIER_PERI_CLK_FI2C(8, 4),
 	UNIPHIER_PERI_CLK_FI2C(9, 5),
 	UNIPHIER_PERI_CLK_FI2C(10, 6),
-	UNIPHIER_PERI_CLK_SCSSI(11),
-	UNIPHIER_PERI_CLK_MCSSI(12),
+	UNIPHIER_PERI_CLK_SCSSI(11, 0),
+	UNIPHIER_PERI_CLK_SCSSI(12, 1),
+	UNIPHIER_PERI_CLK_SCSSI(13, 2),
+	UNIPHIER_PERI_CLK_SCSSI(14, 3),
+	UNIPHIER_PERI_CLK_MCSSI(15),
 	{ /* sentinel */ }
 };
diff --git a/drivers/clocksource/bcm2835_timer.c b/drivers/clocksource/bcm2835_timer.c
index 2b196cbfadb6..b235f446ee50 100644
--- a/drivers/clocksource/bcm2835_timer.c
+++ b/drivers/clocksource/bcm2835_timer.c
@@ -121,7 +121,7 @@ static int __init bcm2835_timer_init(struct device_node *node)
 	ret = setup_irq(irq, &timer->act);
 	if (ret) {
 		pr_err("Can't set up timer IRQ\n");
-		goto err_iounmap;
+		goto err_timer_free;
 	}
 
 	clockevents_config_and_register(&timer->evt, freq, 0xf, 0xffffffff);
@@ -130,6 +130,9 @@ static int __init bcm2835_timer_init(struct device_node *node)
 
 	return 0;
 
+err_timer_free:
+	kfree(timer);
+
 err_iounmap:
 	iounmap(base);
 	return ret;
diff --git a/drivers/clocksource/dw_apb_timer.c b/drivers/clocksource/dw_apb_timer.c
index 654766538f93..10ce69548f1b 100644
--- a/drivers/clocksource/dw_apb_timer.c
+++ b/drivers/clocksource/dw_apb_timer.c
@@ -222,7 +222,8 @@ static int apbt_next_event(unsigned long delta,
 /**
  * dw_apb_clockevent_init() - use an APB timer as a clock_event_device
  *
- * @cpu:	The CPU the events will be targeted at.
+ * @cpu:	The CPU the events will be targeted at or -1 if CPU affiliation
+ *		isn't required.
  * @name:	The name used for the timer and the IRQ for it.
  * @rating:	The rating to give the timer.
  * @base:	I/O base for the timer registers.
@@ -257,7 +258,7 @@ dw_apb_clockevent_init(int cpu, const char *name, unsigned rating,
 	dw_ced->ced.max_delta_ticks = 0x7fffffff;
 	dw_ced->ced.min_delta_ns = clockevent_delta2ns(5000, &dw_ced->ced);
 	dw_ced->ced.min_delta_ticks = 5000;
-	dw_ced->ced.cpumask = cpumask_of(cpu);
+	dw_ced->ced.cpumask = cpu < 0 ? cpu_possible_mask : cpumask_of(cpu);
 	dw_ced->ced.features = CLOCK_EVT_FEAT_PERIODIC |
 				CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_DYNIRQ;
 	dw_ced->ced.set_state_shutdown = apbt_shutdown;
diff --git a/drivers/clocksource/dw_apb_timer_of.c b/drivers/clocksource/dw_apb_timer_of.c
index 8c28b127759f..6921b91b61ef 100644
--- a/drivers/clocksource/dw_apb_timer_of.c
+++ b/drivers/clocksource/dw_apb_timer_of.c
@@ -147,10 +147,6 @@ static int num_called;
 static int __init dw_apb_timer_init(struct device_node *timer)
 {
 	switch (num_called) {
-	case 0:
-		pr_debug("%s: found clockevent timer\n", __func__);
-		add_clockevent(timer);
-		break;
 	case 1:
 		pr_debug("%s: found clocksource timer\n", __func__);
 		add_clocksource(timer);
@@ -161,6 +157,8 @@ static int __init dw_apb_timer_init(struct device_node *timer)
 #endif
 		break;
 	default:
+		pr_debug("%s: found clockevent timer\n", __func__);
+		add_clockevent(timer);
 		break;
 	}
 
diff --git a/drivers/clocksource/sh_mtu2.c b/drivers/clocksource/sh_mtu2.c
index 354b27d14a19..62812f80b5cc 100644
--- a/drivers/clocksource/sh_mtu2.c
+++ b/drivers/clocksource/sh_mtu2.c
@@ -328,12 +328,13 @@ static int sh_mtu2_register(struct sh_mtu2_channel *ch, const char *name)
 	return 0;
 }
 
+static const unsigned int sh_mtu2_channel_offsets[] = {
+	0x300, 0x380, 0x000,
+};
+
 static int sh_mtu2_setup_channel(struct sh_mtu2_channel *ch, unsigned int index,
 				 struct sh_mtu2_device *mtu)
 {
-	static const unsigned int channel_offsets[] = {
-		0x300, 0x380, 0x000,
-	};
 	char name[6];
 	int irq;
 	int ret;
@@ -356,7 +357,7 @@ static int sh_mtu2_setup_channel(struct sh_mtu2_channel *ch, unsigned int index,
 		return ret;
 	}
 
-	ch->base = mtu->mapbase + channel_offsets[index];
+	ch->base = mtu->mapbase + sh_mtu2_channel_offsets[index];
 	ch->index = index;
 
 	return sh_mtu2_register(ch, dev_name(&mtu->pdev->dev));
@@ -408,7 +409,12 @@ static int sh_mtu2_setup(struct sh_mtu2_device *mtu,
 	}
 
 	/* Allocate and setup the channels. */
-	mtu->num_channels = 3;
+	ret = platform_irq_count(pdev);
+	if (ret < 0)
+		goto err_unmap;
+
+	mtu->num_channels = min_t(unsigned int, ret,
+				  ARRAY_SIZE(sh_mtu2_channel_offsets));
 
 	mtu->channels = kcalloc(mtu->num_channels, sizeof(*mtu->channels),
 				GFP_KERNEL);
diff --git a/drivers/clocksource/timer-riscv.c b/drivers/clocksource/timer-riscv.c
index 5e6038fbf115..47de8ed5beff 100644
--- a/drivers/clocksource/timer-riscv.c
+++ b/drivers/clocksource/timer-riscv.c
@@ -50,7 +50,7 @@ static unsigned long long riscv_clocksource_rdtime(struct clocksource *cs)
 	return get_cycles64();
 }
 
-static u64 riscv_sched_clock(void)
+static u64 notrace riscv_sched_clock(void)
 {
 	return get_cycles64();
 }
diff --git a/drivers/counter/104-quad-8.c b/drivers/counter/104-quad-8.c
index 4fa2931dcb7b..2842fe0bc222 100644
--- a/drivers/counter/104-quad-8.c
+++ b/drivers/counter/104-quad-8.c
@@ -42,6 +42,7 @@ MODULE_PARM_DESC(base, "ACCES 104-QUAD-8 base addresses");
  * @base:		base port address of the IIO device
  */
 struct quad8_iio {
+	struct mutex lock;
 	struct counter_device counter;
 	unsigned int preset[QUAD8_NUM_COUNTERS];
 	unsigned int count_mode[QUAD8_NUM_COUNTERS];
@@ -116,6 +117,8 @@ static int quad8_read_raw(struct iio_dev *indio_dev,
 		/* Borrow XOR Carry effectively doubles count range */
 		*val = (borrow ^ carry) << 24;
 
+		mutex_lock(&priv->lock);
+
 		/* Reset Byte Pointer; transfer Counter to Output Latch */
 		outb(QUAD8_CTR_RLD | QUAD8_RLD_RESET_BP | QUAD8_RLD_CNTR_OUT,
 		     base_offset + 1);
@@ -123,6 +126,8 @@ static int quad8_read_raw(struct iio_dev *indio_dev,
 		for (i = 0; i < 3; i++)
 			*val |= (unsigned int)inb(base_offset) << (8 * i);
 
+		mutex_unlock(&priv->lock);
+
 		return IIO_VAL_INT;
 	case IIO_CHAN_INFO_ENABLE:
 		*val = priv->ab_enable[chan->channel];
@@ -153,6 +158,8 @@ static int quad8_write_raw(struct iio_dev *indio_dev,
 		if ((unsigned int)val > 0xFFFFFF)
 			return -EINVAL;
 
+		mutex_lock(&priv->lock);
+
 		/* Reset Byte Pointer */
 		outb(QUAD8_CTR_RLD | QUAD8_RLD_RESET_BP, base_offset + 1);
 
@@ -176,12 +183,16 @@ static int quad8_write_raw(struct iio_dev *indio_dev,
 		/* Reset Error flag */
 		outb(QUAD8_CTR_RLD | QUAD8_RLD_RESET_E, base_offset + 1);
 
+		mutex_unlock(&priv->lock);
+
 		return 0;
 	case IIO_CHAN_INFO_ENABLE:
 		/* only boolean values accepted */
 		if (val < 0 || val > 1)
 			return -EINVAL;
 
+		mutex_lock(&priv->lock);
+
 		priv->ab_enable[chan->channel] = val;
 
 		ior_cfg = val | priv->preset_enable[chan->channel] << 1;
@@ -189,11 +200,18 @@ static int quad8_write_raw(struct iio_dev *indio_dev,
 		/* Load I/O control configuration */
 		outb(QUAD8_CTR_IOR | ior_cfg, base_offset + 1);
 
+		mutex_unlock(&priv->lock);
+
 		return 0;
 	case IIO_CHAN_INFO_SCALE:
+		mutex_lock(&priv->lock);
+
 		/* Quadrature scaling only available in quadrature mode */
-		if (!priv->quadrature_mode[chan->channel] && (val2 || val != 1))
+		if (!priv->quadrature_mode[chan->channel] &&
+				(val2 || val != 1)) {
+			mutex_unlock(&priv->lock);
 			return -EINVAL;
+		}
 
 		/* Only three gain states (1, 0.5, 0.25) */
 		if (val == 1 && !val2)
@@ -207,11 +225,15 @@ static int quad8_write_raw(struct iio_dev *indio_dev,
 				priv->quadrature_scale[chan->channel] = 2;
 				break;
 			default:
+				mutex_unlock(&priv->lock);
 				return -EINVAL;
 			}
-		else
+		else {
+			mutex_unlock(&priv->lock);
 			return -EINVAL;
+		}
 
+		mutex_unlock(&priv->lock);
 		return 0;
 	}
 
@@ -248,6 +270,8 @@ static ssize_t quad8_write_preset(struct iio_dev *indio_dev, uintptr_t private,
 	if (preset > 0xFFFFFF)
 		return -EINVAL;
 
+	mutex_lock(&priv->lock);
+
 	priv->preset[chan->channel] = preset;
 
 	/* Reset Byte Pointer */
@@ -257,6 +281,8 @@ static ssize_t quad8_write_preset(struct iio_dev *indio_dev, uintptr_t private,
 	for (i = 0; i < 3; i++)
 		outb(preset >> (8 * i), base_offset);
 
+	mutex_unlock(&priv->lock);
+
 	return len;
 }
 
@@ -286,6 +312,8 @@ static ssize_t quad8_write_set_to_preset_on_index(struct iio_dev *indio_dev,
 	/* Preset enable is active low in Input/Output Control register */
 	preset_enable = !preset_enable;
 
+	mutex_lock(&priv->lock);
+
 	priv->preset_enable[chan->channel] = preset_enable;
 
 	ior_cfg = priv->ab_enable[chan->channel] |
@@ -294,6 +322,8 @@ static ssize_t quad8_write_set_to_preset_on_index(struct iio_dev *indio_dev,
 	/* Load I/O control configuration to Input / Output Control Register */
 	outb(QUAD8_CTR_IOR | ior_cfg, base_offset);
 
+	mutex_unlock(&priv->lock);
+
 	return len;
 }
 
@@ -351,6 +381,8 @@ static int quad8_set_count_mode(struct iio_dev *indio_dev,
 	unsigned int mode_cfg = cnt_mode << 1;
 	const int base_offset = priv->base + 2 * chan->channel + 1;
 
+	mutex_lock(&priv->lock);
+
 	priv->count_mode[chan->channel] = cnt_mode;
 
 	/* Add quadrature mode configuration */
@@ -360,6 +392,8 @@ static int quad8_set_count_mode(struct iio_dev *indio_dev,
 	/* Load mode configuration to Counter Mode Register */
 	outb(QUAD8_CTR_CMR | mode_cfg, base_offset);
 
+	mutex_unlock(&priv->lock);
+
 	return 0;
 }
 
@@ -387,19 +421,26 @@ static int quad8_set_synchronous_mode(struct iio_dev *indio_dev,
 	const struct iio_chan_spec *chan, unsigned int synchronous_mode)
 {
 	struct quad8_iio *const priv = iio_priv(indio_dev);
-	const unsigned int idr_cfg = synchronous_mode |
-		priv->index_polarity[chan->channel] << 1;
 	const int base_offset = priv->base + 2 * chan->channel + 1;
+	unsigned int idr_cfg = synchronous_mode;
+
+	mutex_lock(&priv->lock);
+
+	idr_cfg |= priv->index_polarity[chan->channel] << 1;
 
 	/* Index function must be non-synchronous in non-quadrature mode */
-	if (synchronous_mode && !priv->quadrature_mode[chan->channel])
+	if (synchronous_mode && !priv->quadrature_mode[chan->channel]) {
+		mutex_unlock(&priv->lock);
 		return -EINVAL;
+	}
 
 	priv->synchronous_mode[chan->channel] = synchronous_mode;
 
 	/* Load Index Control configuration to Index Control Register */
 	outb(QUAD8_CTR_IDR | idr_cfg, base_offset);
 
+	mutex_unlock(&priv->lock);
+
 	return 0;
 }
 
@@ -427,8 +468,12 @@ static int quad8_set_quadrature_mode(struct iio_dev *indio_dev,
 	const struct iio_chan_spec *chan, unsigned int quadrature_mode)
 {
 	struct quad8_iio *const priv = iio_priv(indio_dev);
-	unsigned int mode_cfg = priv->count_mode[chan->channel] << 1;
 	const int base_offset = priv->base + 2 * chan->channel + 1;
+	unsigned int mode_cfg;
+
+	mutex_lock(&priv->lock);
+
+	mode_cfg = priv->count_mode[chan->channel] << 1;
 
 	if (quadrature_mode)
 		mode_cfg |= (priv->quadrature_scale[chan->channel] + 1) << 3;
@@ -446,6 +491,8 @@ static int quad8_set_quadrature_mode(struct iio_dev *indio_dev,
 	/* Load mode configuration to Counter Mode Register */
 	outb(QUAD8_CTR_CMR | mode_cfg, base_offset);
 
+	mutex_unlock(&priv->lock);
+
 	return 0;
 }
 
@@ -473,15 +520,20 @@ static int quad8_set_index_polarity(struct iio_dev *indio_dev,
 	const struct iio_chan_spec *chan, unsigned int index_polarity)
 {
 	struct quad8_iio *const priv = iio_priv(indio_dev);
-	const unsigned int idr_cfg = priv->synchronous_mode[chan->channel] |
-		index_polarity << 1;
 	const int base_offset = priv->base + 2 * chan->channel + 1;
+	unsigned int idr_cfg = index_polarity << 1;
+
+	mutex_lock(&priv->lock);
+
+	idr_cfg |= priv->synchronous_mode[chan->channel];
 
 	priv->index_polarity[chan->channel] = index_polarity;
 
 	/* Load Index Control configuration to Index Control Register */
 	outb(QUAD8_CTR_IDR | idr_cfg, base_offset);
 
+	mutex_unlock(&priv->lock);
+
 	return 0;
 }
 
@@ -585,7 +637,7 @@ static int quad8_signal_read(struct counter_device *counter,
 static int quad8_count_read(struct counter_device *counter,
 	struct counter_count *count, struct counter_count_read_value *val)
 {
-	const struct quad8_iio *const priv = counter->priv;
+	struct quad8_iio *const priv = counter->priv;
 	const int base_offset = priv->base + 2 * count->id;
 	unsigned int flags;
 	unsigned int borrow;
@@ -600,6 +652,8 @@ static int quad8_count_read(struct counter_device *counter,
 	/* Borrow XOR Carry effectively doubles count range */
 	position = (unsigned long)(borrow ^ carry) << 24;
 
+	mutex_lock(&priv->lock);
+
 	/* Reset Byte Pointer; transfer Counter to Output Latch */
 	outb(QUAD8_CTR_RLD | QUAD8_RLD_RESET_BP | QUAD8_RLD_CNTR_OUT,
 	     base_offset + 1);
@@ -607,6 +661,8 @@ static int quad8_count_read(struct counter_device *counter,
 	for (i = 0; i < 3; i++)
 		position |= (unsigned long)inb(base_offset) << (8 * i);
 
+	mutex_unlock(&priv->lock);
+
 	counter_count_read_value_set(val, COUNTER_COUNT_POSITION, &position);
 
 	return 0;
@@ -615,7 +671,7 @@ static int quad8_count_read(struct counter_device *counter,
 static int quad8_count_write(struct counter_device *counter,
 	struct counter_count *count, struct counter_count_write_value *val)
 {
-	const struct quad8_iio *const priv = counter->priv;
+	struct quad8_iio *const priv = counter->priv;
 	const int base_offset = priv->base + 2 * count->id;
 	int err;
 	unsigned long position;
@@ -630,6 +686,8 @@ static int quad8_count_write(struct counter_device *counter,
 	if (position > 0xFFFFFF)
 		return -EINVAL;
 
+	mutex_lock(&priv->lock);
+
 	/* Reset Byte Pointer */
 	outb(QUAD8_CTR_RLD | QUAD8_RLD_RESET_BP, base_offset + 1);
 
@@ -653,6 +711,8 @@ static int quad8_count_write(struct counter_device *counter,
 	/* Reset Error flag */
 	outb(QUAD8_CTR_RLD | QUAD8_RLD_RESET_E, base_offset + 1);
 
+	mutex_unlock(&priv->lock);
+
 	return 0;
 }
 
@@ -673,13 +733,13 @@ static enum counter_count_function quad8_count_functions_list[] = {
 static int quad8_function_get(struct counter_device *counter,
 	struct counter_count *count, size_t *function)
 {
-	const struct quad8_iio *const priv = counter->priv;
+	struct quad8_iio *const priv = counter->priv;
 	const int id = count->id;
-	const unsigned int quadrature_mode = priv->quadrature_mode[id];
-	const unsigned int scale = priv->quadrature_scale[id];
 
-	if (quadrature_mode)
-		switch (scale) {
+	mutex_lock(&priv->lock);
+
+	if (priv->quadrature_mode[id])
+		switch (priv->quadrature_scale[id]) {
 		case 0:
 			*function = QUAD8_COUNT_FUNCTION_QUADRATURE_X1;
 			break;
@@ -693,6 +753,8 @@ static int quad8_function_get(struct counter_device *counter,
 	else
 		*function = QUAD8_COUNT_FUNCTION_PULSE_DIRECTION;
 
+	mutex_unlock(&priv->lock);
+
 	return 0;
 }
 
@@ -703,10 +765,15 @@ static int quad8_function_set(struct counter_device *counter,
 	const int id = count->id;
 	unsigned int *const quadrature_mode = priv->quadrature_mode + id;
 	unsigned int *const scale = priv->quadrature_scale + id;
-	unsigned int mode_cfg = priv->count_mode[id] << 1;
 	unsigned int *const synchronous_mode = priv->synchronous_mode + id;
-	const unsigned int idr_cfg = priv->index_polarity[id] << 1;
 	const int base_offset = priv->base + 2 * id + 1;
+	unsigned int mode_cfg;
+	unsigned int idr_cfg;
+
+	mutex_lock(&priv->lock);
+
+	mode_cfg = priv->count_mode[id] << 1;
+	idr_cfg = priv->index_polarity[id] << 1;
 
 	if (function == QUAD8_COUNT_FUNCTION_PULSE_DIRECTION) {
 		*quadrature_mode = 0;
@@ -742,6 +809,8 @@ static int quad8_function_set(struct counter_device *counter,
 	/* Load mode configuration to Counter Mode Register */
 	outb(QUAD8_CTR_CMR | mode_cfg, base_offset);
 
+	mutex_unlock(&priv->lock);
+
 	return 0;
 }
 
@@ -858,15 +927,20 @@ static int quad8_index_polarity_set(struct counter_device *counter,
 {
 	struct quad8_iio *const priv = counter->priv;
 	const size_t channel_id = signal->id - 16;
-	const unsigned int idr_cfg = priv->synchronous_mode[channel_id] |
-		index_polarity << 1;
 	const int base_offset = priv->base + 2 * channel_id + 1;
+	unsigned int idr_cfg = index_polarity << 1;
+
+	mutex_lock(&priv->lock);
+
+	idr_cfg |= priv->synchronous_mode[channel_id];
 
 	priv->index_polarity[channel_id] = index_polarity;
 
 	/* Load Index Control configuration to Index Control Register */
 	outb(QUAD8_CTR_IDR | idr_cfg, base_offset);
 
+	mutex_unlock(&priv->lock);
+
 	return 0;
 }
 
@@ -893,19 +967,26 @@ static int quad8_synchronous_mode_set(struct counter_device *counter,
 {
 	struct quad8_iio *const priv = counter->priv;
 	const size_t channel_id = signal->id - 16;
-	const unsigned int idr_cfg = synchronous_mode |
-		priv->index_polarity[channel_id] << 1;
 	const int base_offset = priv->base + 2 * channel_id + 1;
+	unsigned int idr_cfg = synchronous_mode;
+
+	mutex_lock(&priv->lock);
+
+	idr_cfg |= priv->index_polarity[channel_id] << 1;
 
 	/* Index function must be non-synchronous in non-quadrature mode */
-	if (synchronous_mode && !priv->quadrature_mode[channel_id])
+	if (synchronous_mode && !priv->quadrature_mode[channel_id]) {
+		mutex_unlock(&priv->lock);
 		return -EINVAL;
+	}
 
 	priv->synchronous_mode[channel_id] = synchronous_mode;
 
 	/* Load Index Control configuration to Index Control Register */
 	outb(QUAD8_CTR_IDR | idr_cfg, base_offset);
 
+	mutex_unlock(&priv->lock);
+
 	return 0;
 }
 
@@ -970,6 +1051,8 @@ static int quad8_count_mode_set(struct counter_device *counter,
 		break;
 	}
 
+	mutex_lock(&priv->lock);
+
 	priv->count_mode[count->id] = cnt_mode;
 
 	/* Set count mode configuration value */
@@ -982,6 +1065,8 @@ static int quad8_count_mode_set(struct counter_device *counter,
 	/* Load mode configuration to Counter Mode Register */
 	outb(QUAD8_CTR_CMR | mode_cfg, base_offset);
 
+	mutex_unlock(&priv->lock);
+
 	return 0;
 }
 
@@ -1023,6 +1108,8 @@ static ssize_t quad8_count_enable_write(struct counter_device *counter,
 	if (err)
 		return err;
 
+	mutex_lock(&priv->lock);
+
 	priv->ab_enable[count->id] = ab_enable;
 
 	ior_cfg = ab_enable | priv->preset_enable[count->id] << 1;
@@ -1030,6 +1117,8 @@ static ssize_t quad8_count_enable_write(struct counter_device *counter,
 	/* Load I/O control configuration */
 	outb(QUAD8_CTR_IOR | ior_cfg, base_offset + 1);
 
+	mutex_unlock(&priv->lock);
+
 	return len;
 }
 
@@ -1058,14 +1147,28 @@ static ssize_t quad8_count_preset_read(struct counter_device *counter,
 	return sprintf(buf, "%u\n", priv->preset[count->id]);
 }
 
+static void quad8_preset_register_set(struct quad8_iio *quad8iio, int id,
+		unsigned int preset)
+{
+	const unsigned int base_offset = quad8iio->base + 2 * id;
+	int i;
+
+	quad8iio->preset[id] = preset;
+
+	/* Reset Byte Pointer */
+	outb(QUAD8_CTR_RLD | QUAD8_RLD_RESET_BP, base_offset + 1);
+
+	/* Set Preset Register */
+	for (i = 0; i < 3; i++)
+		outb(preset >> (8 * i), base_offset);
+}
+
 static ssize_t quad8_count_preset_write(struct counter_device *counter,
 	struct counter_count *count, void *private, const char *buf, size_t len)
 {
 	struct quad8_iio *const priv = counter->priv;
-	const int base_offset = priv->base + 2 * count->id;
 	unsigned int preset;
 	int ret;
-	int i;
 
 	ret = kstrtouint(buf, 0, &preset);
 	if (ret)
@@ -1075,14 +1178,11 @@ static ssize_t quad8_count_preset_write(struct counter_device *counter,
 	if (preset > 0xFFFFFF)
 		return -EINVAL;
 
-	priv->preset[count->id] = preset;
+	mutex_lock(&priv->lock);
 
-	/* Reset Byte Pointer */
-	outb(QUAD8_CTR_RLD | QUAD8_RLD_RESET_BP, base_offset + 1);
+	quad8_preset_register_set(priv, count->id, preset);
 
-	/* Set Preset Register */
-	for (i = 0; i < 3; i++)
-		outb(preset >> (8 * i), base_offset);
+	mutex_unlock(&priv->lock);
 
 	return len;
 }
@@ -1090,15 +1190,20 @@ static ssize_t quad8_count_preset_write(struct counter_device *counter,
 static ssize_t quad8_count_ceiling_read(struct counter_device *counter,
 	struct counter_count *count, void *private, char *buf)
 {
-	const struct quad8_iio *const priv = counter->priv;
+	struct quad8_iio *const priv = counter->priv;
+
+	mutex_lock(&priv->lock);
 
 	/* Range Limit and Modulo-N count modes use preset value as ceiling */
 	switch (priv->count_mode[count->id]) {
 	case 1:
 	case 3:
-		return quad8_count_preset_read(counter, count, private, buf);
+		mutex_unlock(&priv->lock);
+		return sprintf(buf, "%u\n", priv->preset[count->id]);
 	}
 
+	mutex_unlock(&priv->lock);
+
 	/* By default 0x1FFFFFF (25 bits unsigned) is maximum count */
 	return sprintf(buf, "33554431\n");
 }
@@ -1107,15 +1212,29 @@ static ssize_t quad8_count_ceiling_write(struct counter_device *counter,
 	struct counter_count *count, void *private, const char *buf, size_t len)
 {
 	struct quad8_iio *const priv = counter->priv;
+	unsigned int ceiling;
+	int ret;
+
+	ret = kstrtouint(buf, 0, &ceiling);
+	if (ret)
+		return ret;
+
+	/* Only 24-bit values are supported */
+	if (ceiling > 0xFFFFFF)
+		return -EINVAL;
+
+	mutex_lock(&priv->lock);
 
 	/* Range Limit and Modulo-N count modes use preset value as ceiling */
 	switch (priv->count_mode[count->id]) {
 	case 1:
 	case 3:
-		return quad8_count_preset_write(counter, count, private, buf,
-						len);
+		quad8_preset_register_set(priv, count->id, ceiling);
+		break;
 	}
 
+	mutex_unlock(&priv->lock);
+
 	return len;
 }
 
@@ -1143,6 +1262,8 @@ static ssize_t quad8_count_preset_enable_write(struct counter_device *counter,
 	/* Preset enable is active low in Input/Output Control register */
 	preset_enable = !preset_enable;
 
+	mutex_lock(&priv->lock);
+
 	priv->preset_enable[count->id] = preset_enable;
 
 	ior_cfg = priv->ab_enable[count->id] | (unsigned int)preset_enable << 1;
@@ -1150,6 +1271,8 @@ static ssize_t quad8_count_preset_enable_write(struct counter_device *counter,
 	/* Load I/O control configuration to Input / Output Control Register */
 	outb(QUAD8_CTR_IOR | ior_cfg, base_offset);
 
+	mutex_unlock(&priv->lock);
+
 	return len;
 }
 
@@ -1320,6 +1443,9 @@ static int quad8_probe(struct device *dev, unsigned int id)
 	quad8iio->counter.priv = quad8iio;
 	quad8iio->base = base[id];
 
+	/* Initialize mutex */
+	mutex_init(&quad8iio->lock);
+
 	/* Reset all counters and disable interrupt function */
 	outb(QUAD8_CHAN_OP_RESET_COUNTERS, base[id] + QUAD8_REG_CHAN_OP);
 	/* Set initial configuration for all counters */
diff --git a/drivers/counter/ftm-quaddec.c b/drivers/counter/ftm-quaddec.c
index c83c8875bf82..68a9b7393457 100644
--- a/drivers/counter/ftm-quaddec.c
+++ b/drivers/counter/ftm-quaddec.c
@@ -352,5 +352,5 @@ static struct platform_driver ftm_quaddec_driver = {
 module_platform_driver(ftm_quaddec_driver);
 
 MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Kjeld Flarup <kfa@deif.com");
-MODULE_AUTHOR("Patrick Havelange <patrick.havelange@essensium.com");
+MODULE_AUTHOR("Kjeld Flarup <kfa@deif.com>");
+MODULE_AUTHOR("Patrick Havelange <patrick.havelange@essensium.com>");
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index f8129edc145e..bac07ebcb29c 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -29,6 +29,7 @@ config ARM_ARMADA_37XX_CPUFREQ
 config ARM_ARMADA_8K_CPUFREQ
 	tristate "Armada 8K CPUFreq driver"
 	depends on ARCH_MVEBU && CPUFREQ_DT
+	select ARMADA_AP_CPU_CLK
 	help
 	  This enables the CPUFreq driver support for Marvell
 	  Armada8k SOCs.
diff --git a/drivers/cpufreq/armada-37xx-cpufreq.c b/drivers/cpufreq/armada-37xx-cpufreq.c
index 0df16eb1eb3c..c5f98cafc25c 100644
--- a/drivers/cpufreq/armada-37xx-cpufreq.c
+++ b/drivers/cpufreq/armada-37xx-cpufreq.c
@@ -458,6 +458,7 @@ static int __init armada37xx_cpufreq_driver_init(void)
 	/* Now that everything is setup, enable the DVFS at hardware level */
 	armada37xx_cpufreq_enable_dvfs(nb_pm_base);
 
+	memset(&pdata, 0, sizeof(pdata));
 	pdata.suspend = armada37xx_cpufreq_suspend;
 	pdata.resume = armada37xx_cpufreq_resume;
 
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index 47ccfa6b17b7..e3298ad28c4f 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -283,6 +283,9 @@ static int imx6ul_opp_check_speed_grading(struct device *dev)
 
 		np = of_find_compatible_node(NULL, NULL, "fsl,imx6ul-ocotp");
 		if (!np)
+			np = of_find_compatible_node(NULL, NULL,
+						     "fsl,imx6ull-ocotp");
+		if (!np)
 			return -ENOENT;
 
 		base = of_iomap(np, 0);
@@ -380,23 +383,24 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev)
 		goto put_reg;
 	}
 
+	/* Because we have added the OPPs here, we must free them */
+	free_opp = true;
+
 	if (of_machine_is_compatible("fsl,imx6ul") ||
 	    of_machine_is_compatible("fsl,imx6ull")) {
 		ret = imx6ul_opp_check_speed_grading(cpu_dev);
 		if (ret) {
 			if (ret == -EPROBE_DEFER)
-				goto put_node;
+				goto out_free_opp;
 
 			dev_err(cpu_dev, "failed to read ocotp: %d\n",
 				ret);
-			goto put_node;
+			goto out_free_opp;
 		}
 	} else {
 		imx6q_opp_check_speed_grading(cpu_dev);
 	}
 
-	/* Because we have added the OPPs here, we must free them */
-	free_opp = true;
 	num = dev_pm_opp_get_opp_count(cpu_dev);
 	if (num < 0) {
 		ret = num;
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 6dc359a00956..2aa28738a4ac 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1062,7 +1062,7 @@ static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b,
 
 	update_turbo_state();
 	if (global.turbo_disabled) {
-		pr_warn("Turbo disabled by BIOS or unavailable on processor\n");
+		pr_notice_once("Turbo disabled by BIOS or unavailable on processor\n");
 		mutex_unlock(&intel_pstate_limits_lock);
 		mutex_unlock(&intel_pstate_driver_lock);
 		return -EPERM;
diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index 56f4bc0d209e..1806b1da4366 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -1080,6 +1080,12 @@ free_and_return:
 
 static inline void clean_chip_info(void)
 {
+	int i;
+
+	/* flush any pending work items */
+	if (chips)
+		for (i = 0; i < nr_chips; i++)
+			cancel_work_sync(&chips[i].throttle);
 	kfree(chips);
 }
 
diff --git a/drivers/cpuidle/governors/teo.c b/drivers/cpuidle/governors/teo.c
index 9722afd1179b..f2b0e1986704 100644
--- a/drivers/cpuidle/governors/teo.c
+++ b/drivers/cpuidle/governors/teo.c
@@ -202,7 +202,7 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	 * pattern detection.
 	 */
 	cpu_data->intervals[cpu_data->interval_idx++] = measured_us;
-	if (cpu_data->interval_idx > INTERVALS)
+	if (cpu_data->interval_idx >= INTERVALS)
 		cpu_data->interval_idx = 0;
 }
 
@@ -242,7 +242,7 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu);
 	int latency_req = cpuidle_governor_latency_req(dev->cpu);
 	unsigned int duration_us, hits, misses, early_hits;
-	int max_early_idx, constraint_idx, idx, i;
+	int max_early_idx, prev_max_early_idx, constraint_idx, idx, i;
 	ktime_t delta_tick;
 
 	if (cpu_data->last_state >= 0) {
@@ -259,6 +259,7 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	misses = 0;
 	early_hits = 0;
 	max_early_idx = -1;
+	prev_max_early_idx = -1;
 	constraint_idx = drv->state_count;
 	idx = -1;
 
@@ -311,6 +312,7 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 			 */
 			if (!(tick_nohz_tick_stopped() &&
 			      drv->states[idx].target_residency < TICK_USEC)) {
+				prev_max_early_idx = max_early_idx;
 				early_hits = cpu_data->states[i].early_hits;
 				max_early_idx = idx;
 			}
@@ -337,6 +339,7 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		if (early_hits < cpu_data->states[i].early_hits &&
 		    !(tick_nohz_tick_stopped() &&
 		      drv->states[i].target_residency < TICK_USEC)) {
+			prev_max_early_idx = max_early_idx;
 			early_hits = cpu_data->states[i].early_hits;
 			max_early_idx = i;
 		}
@@ -350,9 +353,19 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	 * "early hits" metric, but if that cannot be determined, just use the
 	 * state selected so far.
 	 */
-	if (hits <= misses && max_early_idx >= 0) {
-		idx = max_early_idx;
-		duration_us = drv->states[idx].target_residency;
+	if (hits <= misses) {
+		/*
+		 * The current candidate state is not suitable, so take the one
+		 * whose "early hits" metric is the maximum for the range of
+		 * shallower states.
+		 */
+		if (idx == max_early_idx)
+			max_early_idx = prev_max_early_idx;
+
+		if (max_early_idx >= 0) {
+			idx = max_early_idx;
+			duration_us = drv->states[idx].target_residency;
+		}
 	}
 
 	/*
diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c
index eb20adb5de23..61221c97c015 100644
--- a/drivers/cpuidle/sysfs.c
+++ b/drivers/cpuidle/sysfs.c
@@ -473,7 +473,7 @@ static int cpuidle_add_state_sysfs(struct cpuidle_device *device)
 		ret = kobject_init_and_add(&kobj->kobj, &ktype_state_cpuidle,
 					   &kdev->kobj, "state%d", i);
 		if (ret) {
-			kfree(kobj);
+			kobject_put(&kobj->kobj);
 			goto error_state;
 		}
 		cpuidle_add_s2idle_attr_group(kobj);
@@ -604,7 +604,7 @@ static int cpuidle_add_driver_sysfs(struct cpuidle_device *dev)
 	ret = kobject_init_and_add(&kdrv->kobj, &ktype_driver_cpuidle,
 				   &kdev->kobj, "driver");
 	if (ret) {
-		kfree(kdrv);
+		kobject_put(&kdrv->kobj);
 		return ret;
 	}
 
@@ -698,7 +698,7 @@ int cpuidle_add_sysfs(struct cpuidle_device *dev)
 	error = kobject_init_and_add(&kdev->kobj, &ktype_cpuidle, &cpu_dev->kobj,
 				   "cpuidle");
 	if (error) {
-		kfree(kdev);
+		kobject_put(&kdev->kobj);
 		return error;
 	}
 
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 0af08081e305..4bdd761a8ca9 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -469,11 +469,9 @@ if CRYPTO_DEV_UX500
 endif # if CRYPTO_DEV_UX500
 
 config CRYPTO_DEV_ATMEL_AUTHENC
-	tristate "Support for Atmel IPSEC/SSL hw accelerator"
+	bool "Support for Atmel IPSEC/SSL hw accelerator"
 	depends on ARCH_AT91 || COMPILE_TEST
-	select CRYPTO_AUTHENC
-	select CRYPTO_DEV_ATMEL_AES
-	select CRYPTO_DEV_ATMEL_SHA
+	depends on CRYPTO_DEV_ATMEL_AES
 	help
 	  Some Atmel processors can combine the AES and SHA hw accelerators
 	  to enhance support of IPSEC/SSL.
@@ -486,6 +484,8 @@ config CRYPTO_DEV_ATMEL_AES
 	select CRYPTO_AES
 	select CRYPTO_AEAD
 	select CRYPTO_BLKCIPHER
+	select CRYPTO_AUTHENC if CRYPTO_DEV_ATMEL_AUTHENC
+	select CRYPTO_DEV_ATMEL_SHA if CRYPTO_DEV_ATMEL_AUTHENC
 	help
 	  Some Atmel processors have AES hw accelerator.
 	  Select this if you want to use the Atmel module for
@@ -700,7 +700,7 @@ source "drivers/crypto/stm32/Kconfig"
 config CRYPTO_DEV_SAFEXCEL
 	tristate "Inside Secure's SafeXcel cryptographic engine driver"
 	depends on OF
-	depends on (ARM64 && ARCH_MVEBU) || (COMPILE_TEST && 64BIT)
+	depends on (ARM64 && ARCH_MVEBU) || (COMPILE_TEST && 64BIT) && HAS_IOMEM
 	select CRYPTO_AES
 	select CRYPTO_AUTHENC
 	select CRYPTO_BLKCIPHER
diff --git a/drivers/crypto/atmel-aes.c b/drivers/crypto/atmel-aes.c
index b48b3568d9e5..35f1735b25dd 100644
--- a/drivers/crypto/atmel-aes.c
+++ b/drivers/crypto/atmel-aes.c
@@ -88,7 +88,6 @@
 struct atmel_aes_caps {
 	bool			has_dualbuff;
 	bool			has_cfb64;
-	bool			has_ctr32;
 	bool			has_gcm;
 	bool			has_xts;
 	bool			has_authenc;
@@ -1013,8 +1012,9 @@ static int atmel_aes_ctr_transfer(struct atmel_aes_dev *dd)
 	struct atmel_aes_ctr_ctx *ctx = atmel_aes_ctr_ctx_cast(dd->ctx);
 	struct ablkcipher_request *req = ablkcipher_request_cast(dd->areq);
 	struct scatterlist *src, *dst;
-	u32 ctr, blocks;
 	size_t datalen;
+	u32 ctr;
+	u16 blocks, start, end;
 	bool use_dma, fragmented = false;
 
 	/* Check for transfer completion. */
@@ -1026,27 +1026,17 @@ static int atmel_aes_ctr_transfer(struct atmel_aes_dev *dd)
 	datalen = req->nbytes - ctx->offset;
 	blocks = DIV_ROUND_UP(datalen, AES_BLOCK_SIZE);
 	ctr = be32_to_cpu(ctx->iv[3]);
-	if (dd->caps.has_ctr32) {
-		/* Check 32bit counter overflow. */
-		u32 start = ctr;
-		u32 end = start + blocks - 1;
-
-		if (end < start) {
-			ctr |= 0xffffffff;
-			datalen = AES_BLOCK_SIZE * -start;
-			fragmented = true;
-		}
-	} else {
-		/* Check 16bit counter overflow. */
-		u16 start = ctr & 0xffff;
-		u16 end = start + (u16)blocks - 1;
-
-		if (blocks >> 16 || end < start) {
-			ctr |= 0xffff;
-			datalen = AES_BLOCK_SIZE * (0x10000-start);
-			fragmented = true;
-		}
+
+	/* Check 16bit counter overflow. */
+	start = ctr & 0xffff;
+	end = start + blocks - 1;
+
+	if (blocks >> 16 || end < start) {
+		ctr |= 0xffff;
+		datalen = AES_BLOCK_SIZE * (0x10000 - start);
+		fragmented = true;
 	}
+
 	use_dma = (datalen >= ATMEL_AES_DMA_THRESHOLD);
 
 	/* Jump to offset. */
@@ -2550,7 +2540,6 @@ static void atmel_aes_get_cap(struct atmel_aes_dev *dd)
 {
 	dd->caps.has_dualbuff = 0;
 	dd->caps.has_cfb64 = 0;
-	dd->caps.has_ctr32 = 0;
 	dd->caps.has_gcm = 0;
 	dd->caps.has_xts = 0;
 	dd->caps.has_authenc = 0;
@@ -2561,7 +2550,6 @@ static void atmel_aes_get_cap(struct atmel_aes_dev *dd)
 	case 0x500:
 		dd->caps.has_dualbuff = 1;
 		dd->caps.has_cfb64 = 1;
-		dd->caps.has_ctr32 = 1;
 		dd->caps.has_gcm = 1;
 		dd->caps.has_xts = 1;
 		dd->caps.has_authenc = 1;
@@ -2570,7 +2558,6 @@ static void atmel_aes_get_cap(struct atmel_aes_dev *dd)
 	case 0x200:
 		dd->caps.has_dualbuff = 1;
 		dd->caps.has_cfb64 = 1;
-		dd->caps.has_ctr32 = 1;
 		dd->caps.has_gcm = 1;
 		dd->caps.max_burst_size = 4;
 		break;
diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c
index c3599c3f1c5d..47c291cb2aa9 100644
--- a/drivers/crypto/atmel-sha.c
+++ b/drivers/crypto/atmel-sha.c
@@ -1918,12 +1918,7 @@ static int atmel_sha_hmac_setkey(struct crypto_ahash *tfm, const u8 *key,
 {
 	struct atmel_sha_hmac_ctx *hmac = crypto_ahash_ctx(tfm);
 
-	if (atmel_sha_hmac_key_set(&hmac->hkey, key, keylen)) {
-		crypto_ahash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
-		return -EINVAL;
-	}
-
-	return 0;
+	return atmel_sha_hmac_key_set(&hmac->hkey, key, keylen);
 }
 
 static int atmel_sha_hmac_init(struct ahash_request *req)
diff --git a/drivers/crypto/axis/artpec6_crypto.c b/drivers/crypto/axis/artpec6_crypto.c
index 80fa04ef215f..5c69dcbc53c4 100644
--- a/drivers/crypto/axis/artpec6_crypto.c
+++ b/drivers/crypto/axis/artpec6_crypto.c
@@ -1251,7 +1251,7 @@ static int artpec6_crypto_aead_set_key(struct crypto_aead *tfm, const u8 *key,
 
 	if (len != 16 && len != 24 && len != 32) {
 		crypto_aead_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
-		return -1;
+		return -EINVAL;
 	}
 
 	ctx->key_length = len;
diff --git a/drivers/crypto/caam/caamalg_desc.c b/drivers/crypto/caam/caamalg_desc.c
index bb47ae5dca38..2cae1824bc06 100644
--- a/drivers/crypto/caam/caamalg_desc.c
+++ b/drivers/crypto/caam/caamalg_desc.c
@@ -1512,7 +1512,13 @@ EXPORT_SYMBOL(cnstr_shdsc_skcipher_decap);
  */
 void cnstr_shdsc_xts_skcipher_encap(u32 * const desc, struct alginfo *cdata)
 {
-	__be64 sector_size = cpu_to_be64(512);
+	/*
+	 * Set sector size to a big value, practically disabling
+	 * sector size segmentation in xts implementation. We cannot
+	 * take full advantage of this HW feature with existing
+	 * crypto API / dm-crypt SW architecture.
+	 */
+	__be64 sector_size = cpu_to_be64(BIT(15));
 	u32 *key_jump_cmd;
 
 	init_sh_desc(desc, HDR_SHARE_SERIAL | HDR_SAVECTX);
@@ -1563,7 +1569,13 @@ EXPORT_SYMBOL(cnstr_shdsc_xts_skcipher_encap);
  */
 void cnstr_shdsc_xts_skcipher_decap(u32 * const desc, struct alginfo *cdata)
 {
-	__be64 sector_size = cpu_to_be64(512);
+	/*
+	 * Set sector size to a big value, practically disabling
+	 * sector size segmentation in xts implementation. We cannot
+	 * take full advantage of this HW feature with existing
+	 * crypto API / dm-crypt SW architecture.
+	 */
+	__be64 sector_size = cpu_to_be64(BIT(15));
 	u32 *key_jump_cmd;
 
 	init_sh_desc(desc, HDR_SHARE_SERIAL | HDR_SAVECTX);
diff --git a/drivers/crypto/caam/caamalg_qi2.c b/drivers/crypto/caam/caamalg_qi2.c
index b949944c8e55..039e69d91347 100644
--- a/drivers/crypto/caam/caamalg_qi2.c
+++ b/drivers/crypto/caam/caamalg_qi2.c
@@ -2395,7 +2395,7 @@ static struct caam_aead_alg driver_aeads[] = {
 				.cra_name = "echainiv(authenc(hmac(sha256),"
 					    "cbc(des)))",
 				.cra_driver_name = "echainiv-authenc-"
-						   "hmac-sha256-cbc-desi-"
+						   "hmac-sha256-cbc-des-"
 						   "caam-qi2",
 				.cra_blocksize = DES_BLOCK_SIZE,
 			},
diff --git a/drivers/crypto/cavium/cpt/cptvf_algs.c b/drivers/crypto/cavium/cpt/cptvf_algs.c
index e9f4704494fb..10fd8f314c1c 100644
--- a/drivers/crypto/cavium/cpt/cptvf_algs.c
+++ b/drivers/crypto/cavium/cpt/cptvf_algs.c
@@ -201,6 +201,7 @@ static inline int cvm_enc_dec(struct ablkcipher_request *req, u32 enc)
 	int status;
 
 	memset(req_info, 0, sizeof(struct cpt_request_info));
+	req_info->may_sleep = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) != 0;
 	memset(fctx, 0, sizeof(struct fc_context));
 	create_input_list(req, enc, enc_iv_len);
 	create_output_list(req, enc_iv_len);
diff --git a/drivers/crypto/cavium/cpt/cptvf_reqmanager.c b/drivers/crypto/cavium/cpt/cptvf_reqmanager.c
index 7a24019356b5..e343249c8d05 100644
--- a/drivers/crypto/cavium/cpt/cptvf_reqmanager.c
+++ b/drivers/crypto/cavium/cpt/cptvf_reqmanager.c
@@ -133,7 +133,7 @@ static inline int setup_sgio_list(struct cpt_vf *cptvf,
 
 	/* Setup gather (input) components */
 	g_sz_bytes = ((req->incnt + 3) / 4) * sizeof(struct sglist_component);
-	info->gather_components = kzalloc(g_sz_bytes, GFP_KERNEL);
+	info->gather_components = kzalloc(g_sz_bytes, req->may_sleep ? GFP_KERNEL : GFP_ATOMIC);
 	if (!info->gather_components) {
 		ret = -ENOMEM;
 		goto  scatter_gather_clean;
@@ -150,7 +150,7 @@ static inline int setup_sgio_list(struct cpt_vf *cptvf,
 
 	/* Setup scatter (output) components */
 	s_sz_bytes = ((req->outcnt + 3) / 4) * sizeof(struct sglist_component);
-	info->scatter_components = kzalloc(s_sz_bytes, GFP_KERNEL);
+	info->scatter_components = kzalloc(s_sz_bytes, req->may_sleep ? GFP_KERNEL : GFP_ATOMIC);
 	if (!info->scatter_components) {
 		ret = -ENOMEM;
 		goto  scatter_gather_clean;
@@ -167,7 +167,7 @@ static inline int setup_sgio_list(struct cpt_vf *cptvf,
 
 	/* Create and initialize DPTR */
 	info->dlen = g_sz_bytes + s_sz_bytes + SG_LIST_HDR_SIZE;
-	info->in_buffer = kzalloc(info->dlen, GFP_KERNEL);
+	info->in_buffer = kzalloc(info->dlen, req->may_sleep ? GFP_KERNEL : GFP_ATOMIC);
 	if (!info->in_buffer) {
 		ret = -ENOMEM;
 		goto  scatter_gather_clean;
@@ -195,7 +195,7 @@ static inline int setup_sgio_list(struct cpt_vf *cptvf,
 	}
 
 	/* Create and initialize RPTR */
-	info->out_buffer = kzalloc(COMPLETION_CODE_SIZE, GFP_KERNEL);
+	info->out_buffer = kzalloc(COMPLETION_CODE_SIZE, req->may_sleep ? GFP_KERNEL : GFP_ATOMIC);
 	if (!info->out_buffer) {
 		ret = -ENOMEM;
 		goto scatter_gather_clean;
@@ -421,7 +421,7 @@ int process_request(struct cpt_vf *cptvf, struct cpt_request_info *req)
 	struct cpt_vq_command vq_cmd;
 	union cpt_inst_s cptinst;
 
-	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	info = kzalloc(sizeof(*info), req->may_sleep ? GFP_KERNEL : GFP_ATOMIC);
 	if (unlikely(!info)) {
 		dev_err(&pdev->dev, "Unable to allocate memory for info_buffer\n");
 		return -ENOMEM;
@@ -443,7 +443,7 @@ int process_request(struct cpt_vf *cptvf, struct cpt_request_info *req)
 	 * Get buffer for union cpt_res_s response
 	 * structure and its physical address
 	 */
-	info->completion_addr = kzalloc(sizeof(union cpt_res_s), GFP_KERNEL);
+	info->completion_addr = kzalloc(sizeof(union cpt_res_s), req->may_sleep ? GFP_KERNEL : GFP_ATOMIC);
 	if (unlikely(!info->completion_addr)) {
 		dev_err(&pdev->dev, "Unable to allocate memory for completion_addr\n");
 		ret = -ENOMEM;
diff --git a/drivers/crypto/cavium/cpt/request_manager.h b/drivers/crypto/cavium/cpt/request_manager.h
index 3514b082eca7..1e8dd9ebcc17 100644
--- a/drivers/crypto/cavium/cpt/request_manager.h
+++ b/drivers/crypto/cavium/cpt/request_manager.h
@@ -62,6 +62,8 @@ struct cpt_request_info {
 	union ctrl_info ctrl; /* User control information */
 	struct cptvf_request req; /* Request Information (Core specific) */
 
+	bool may_sleep;
+
 	struct buf_ptr in[MAX_BUF_CNT];
 	struct buf_ptr out[MAX_BUF_CNT];
 
diff --git a/drivers/crypto/cavium/nitrox/nitrox_main.c b/drivers/crypto/cavium/nitrox/nitrox_main.c
index fe825d0ef9ca..2d11795e2561 100644
--- a/drivers/crypto/cavium/nitrox/nitrox_main.c
+++ b/drivers/crypto/cavium/nitrox/nitrox_main.c
@@ -191,7 +191,7 @@ static void nitrox_remove_from_devlist(struct nitrox_device *ndev)
 
 struct nitrox_device *nitrox_get_first_device(void)
 {
-	struct nitrox_device *ndev = NULL;
+	struct nitrox_device *ndev;
 
 	mutex_lock(&devlist_lock);
 	list_for_each_entry(ndev, &ndevlist, list) {
@@ -199,7 +199,7 @@ struct nitrox_device *nitrox_get_first_device(void)
 			break;
 	}
 	mutex_unlock(&devlist_lock);
-	if (!ndev)
+	if (&ndev->list == &ndevlist)
 		return NULL;
 
 	refcount_inc(&ndev->refcnt);
diff --git a/drivers/crypto/ccp/Kconfig b/drivers/crypto/ccp/Kconfig
index 48f3edc1e3fb..f711d95277f1 100644
--- a/drivers/crypto/ccp/Kconfig
+++ b/drivers/crypto/ccp/Kconfig
@@ -10,10 +10,9 @@ config CRYPTO_DEV_CCP_DD
 config CRYPTO_DEV_SP_CCP
 	bool "Cryptographic Coprocessor device"
 	default y
-	depends on CRYPTO_DEV_CCP_DD
+	depends on CRYPTO_DEV_CCP_DD && DMADEVICES
 	select HW_RANDOM
 	select DMA_ENGINE
-	select DMADEVICES
 	select CRYPTO_SHA1
 	select CRYPTO_SHA256
 	help
diff --git a/drivers/crypto/ccp/ccp-dev-v3.c b/drivers/crypto/ccp/ccp-dev-v3.c
index 2b7d47ed5c74..490b47572278 100644
--- a/drivers/crypto/ccp/ccp-dev-v3.c
+++ b/drivers/crypto/ccp/ccp-dev-v3.c
@@ -587,6 +587,7 @@ const struct ccp_vdata ccpv3_platform = {
 	.setup = NULL,
 	.perform = &ccp3_actions,
 	.offset = 0,
+	.rsamax = CCP_RSA_MAX_WIDTH,
 };
 
 const struct ccp_vdata ccpv3 = {
diff --git a/drivers/crypto/ccp/ccp-dev.h b/drivers/crypto/ccp/ccp-dev.h
index 5e624920fd99..ee9d2ca5e651 100644
--- a/drivers/crypto/ccp/ccp-dev.h
+++ b/drivers/crypto/ccp/ccp-dev.h
@@ -468,6 +468,7 @@ struct ccp_sg_workarea {
 	unsigned int sg_used;
 
 	struct scatterlist *dma_sg;
+	struct scatterlist *dma_sg_head;
 	struct device *dma_dev;
 	unsigned int dma_count;
 	enum dma_data_direction dma_dir;
diff --git a/drivers/crypto/ccp/ccp-ops.c b/drivers/crypto/ccp/ccp-ops.c
index e12506c93a52..95d06cfb7421 100644
--- a/drivers/crypto/ccp/ccp-ops.c
+++ b/drivers/crypto/ccp/ccp-ops.c
@@ -64,7 +64,7 @@ static u32 ccp_gen_jobid(struct ccp_device *ccp)
 static void ccp_sg_free(struct ccp_sg_workarea *wa)
 {
 	if (wa->dma_count)
-		dma_unmap_sg(wa->dma_dev, wa->dma_sg, wa->nents, wa->dma_dir);
+		dma_unmap_sg(wa->dma_dev, wa->dma_sg_head, wa->nents, wa->dma_dir);
 
 	wa->dma_count = 0;
 }
@@ -93,6 +93,7 @@ static int ccp_init_sg_workarea(struct ccp_sg_workarea *wa, struct device *dev,
 		return 0;
 
 	wa->dma_sg = sg;
+	wa->dma_sg_head = sg;
 	wa->dma_dev = dev;
 	wa->dma_dir = dma_dir;
 	wa->dma_count = dma_map_sg(dev, sg, wa->nents, dma_dir);
@@ -105,14 +106,28 @@ static int ccp_init_sg_workarea(struct ccp_sg_workarea *wa, struct device *dev,
 static void ccp_update_sg_workarea(struct ccp_sg_workarea *wa, unsigned int len)
 {
 	unsigned int nbytes = min_t(u64, len, wa->bytes_left);
+	unsigned int sg_combined_len = 0;
 
 	if (!wa->sg)
 		return;
 
 	wa->sg_used += nbytes;
 	wa->bytes_left -= nbytes;
-	if (wa->sg_used == wa->sg->length) {
-		wa->sg = sg_next(wa->sg);
+	if (wa->sg_used == sg_dma_len(wa->dma_sg)) {
+		/* Advance to the next DMA scatterlist entry */
+		wa->dma_sg = sg_next(wa->dma_sg);
+
+		/* In the case that the DMA mapped scatterlist has entries
+		 * that have been merged, the non-DMA mapped scatterlist
+		 * must be advanced multiple times for each merged entry.
+		 * This ensures that the current non-DMA mapped entry
+		 * corresponds to the current DMA mapped entry.
+		 */
+		do {
+			sg_combined_len += wa->sg->length;
+			wa->sg = sg_next(wa->sg);
+		} while (wa->sg_used > sg_combined_len);
+
 		wa->sg_used = 0;
 	}
 }
@@ -301,7 +316,7 @@ static unsigned int ccp_queue_buf(struct ccp_data *data, unsigned int from)
 	/* Update the structures and generate the count */
 	buf_count = 0;
 	while (sg_wa->bytes_left && (buf_count < dm_wa->length)) {
-		nbytes = min(sg_wa->sg->length - sg_wa->sg_used,
+		nbytes = min(sg_dma_len(sg_wa->dma_sg) - sg_wa->sg_used,
 			     dm_wa->length - buf_count);
 		nbytes = min_t(u64, sg_wa->bytes_left, nbytes);
 
@@ -333,11 +348,11 @@ static void ccp_prepare_data(struct ccp_data *src, struct ccp_data *dst,
 	 * and destination. The resulting len values will always be <= UINT_MAX
 	 * because the dma length is an unsigned int.
 	 */
-	sg_src_len = sg_dma_len(src->sg_wa.sg) - src->sg_wa.sg_used;
+	sg_src_len = sg_dma_len(src->sg_wa.dma_sg) - src->sg_wa.sg_used;
 	sg_src_len = min_t(u64, src->sg_wa.bytes_left, sg_src_len);
 
 	if (dst) {
-		sg_dst_len = sg_dma_len(dst->sg_wa.sg) - dst->sg_wa.sg_used;
+		sg_dst_len = sg_dma_len(dst->sg_wa.dma_sg) - dst->sg_wa.sg_used;
 		sg_dst_len = min_t(u64, src->sg_wa.bytes_left, sg_dst_len);
 		op_len = min(sg_src_len, sg_dst_len);
 	} else {
@@ -367,7 +382,7 @@ static void ccp_prepare_data(struct ccp_data *src, struct ccp_data *dst,
 		/* Enough data in the sg element, but we need to
 		 * adjust for any previously copied data
 		 */
-		op->src.u.dma.address = sg_dma_address(src->sg_wa.sg);
+		op->src.u.dma.address = sg_dma_address(src->sg_wa.dma_sg);
 		op->src.u.dma.offset = src->sg_wa.sg_used;
 		op->src.u.dma.length = op_len & ~(block_size - 1);
 
@@ -388,7 +403,7 @@ static void ccp_prepare_data(struct ccp_data *src, struct ccp_data *dst,
 			/* Enough room in the sg element, but we need to
 			 * adjust for any previously used area
 			 */
-			op->dst.u.dma.address = sg_dma_address(dst->sg_wa.sg);
+			op->dst.u.dma.address = sg_dma_address(dst->sg_wa.dma_sg);
 			op->dst.u.dma.offset = dst->sg_wa.sg_used;
 			op->dst.u.dma.length = op->src.u.dma.length;
 		}
@@ -2040,7 +2055,7 @@ static int ccp_run_passthru_cmd(struct ccp_cmd_queue *cmd_q,
 	dst.sg_wa.sg_used = 0;
 	for (i = 1; i <= src.sg_wa.dma_count; i++) {
 		if (!dst.sg_wa.sg ||
-		    (dst.sg_wa.sg->length < src.sg_wa.sg->length)) {
+		    (sg_dma_len(dst.sg_wa.sg) < sg_dma_len(src.sg_wa.sg))) {
 			ret = -EINVAL;
 			goto e_dst;
 		}
@@ -2066,8 +2081,8 @@ static int ccp_run_passthru_cmd(struct ccp_cmd_queue *cmd_q,
 			goto e_dst;
 		}
 
-		dst.sg_wa.sg_used += src.sg_wa.sg->length;
-		if (dst.sg_wa.sg_used == dst.sg_wa.sg->length) {
+		dst.sg_wa.sg_used += sg_dma_len(src.sg_wa.sg);
+		if (dst.sg_wa.sg_used == sg_dma_len(dst.sg_wa.sg)) {
 			dst.sg_wa.sg = sg_next(dst.sg_wa.sg);
 			dst.sg_wa.sg_used = 0;
 		}
diff --git a/drivers/crypto/ccree/cc_buffer_mgr.c b/drivers/crypto/ccree/cc_buffer_mgr.c
index c81ad33f9115..b7a043178e0c 100644
--- a/drivers/crypto/ccree/cc_buffer_mgr.c
+++ b/drivers/crypto/ccree/cc_buffer_mgr.c
@@ -87,6 +87,8 @@ static unsigned int cc_get_sgl_nents(struct device *dev,
 {
 	unsigned int nents = 0;
 
+	*lbytes = 0;
+
 	while (nbytes && sg_list) {
 		nents++;
 		/* get the number of bytes in the last entry */
@@ -95,6 +97,7 @@ static unsigned int cc_get_sgl_nents(struct device *dev,
 				nbytes : sg_list->length;
 		sg_list = sg_next(sg_list);
 	}
+
 	dev_dbg(dev, "nents %d last bytes %d\n", nents, *lbytes);
 	return nents;
 }
@@ -311,37 +314,25 @@ static int cc_map_sg(struct device *dev, struct scatterlist *sg,
 		     unsigned int nbytes, int direction, u32 *nents,
 		     u32 max_sg_nents, u32 *lbytes, u32 *mapped_nents)
 {
-	if (sg_is_last(sg)) {
-		/* One entry only case -set to DLLI */
-		if (dma_map_sg(dev, sg, 1, direction) != 1) {
-			dev_err(dev, "dma_map_sg() single buffer failed\n");
-			return -ENOMEM;
-		}
-		dev_dbg(dev, "Mapped sg: dma_address=%pad page=%p addr=%pK offset=%u length=%u\n",
-			&sg_dma_address(sg), sg_page(sg), sg_virt(sg),
-			sg->offset, sg->length);
-		*lbytes = nbytes;
-		*nents = 1;
-		*mapped_nents = 1;
-	} else {  /*sg_is_last*/
-		*nents = cc_get_sgl_nents(dev, sg, nbytes, lbytes);
-		if (*nents > max_sg_nents) {
-			*nents = 0;
-			dev_err(dev, "Too many fragments. current %d max %d\n",
-				*nents, max_sg_nents);
-			return -ENOMEM;
-		}
-		/* In case of mmu the number of mapped nents might
-		 * be changed from the original sgl nents
-		 */
-		*mapped_nents = dma_map_sg(dev, sg, *nents, direction);
-		if (*mapped_nents == 0) {
-			*nents = 0;
-			dev_err(dev, "dma_map_sg() sg buffer failed\n");
-			return -ENOMEM;
-		}
+	int ret = 0;
+
+	*nents = cc_get_sgl_nents(dev, sg, nbytes, lbytes);
+	if (*nents > max_sg_nents) {
+		*nents = 0;
+		dev_err(dev, "Too many fragments. current %d max %d\n",
+			*nents, max_sg_nents);
+		return -ENOMEM;
+	}
+
+	ret = dma_map_sg(dev, sg, *nents, direction);
+	if (dma_mapping_error(dev, ret)) {
+		*nents = 0;
+		dev_err(dev, "dma_map_sg() sg buffer failed %d\n", ret);
+		return -ENOMEM;
 	}
 
+	*mapped_nents = ret;
+
 	return 0;
 }
 
@@ -576,11 +567,12 @@ void cc_unmap_aead_request(struct device *dev, struct aead_request *req)
 		sg_virt(req->src), areq_ctx->src.nents, areq_ctx->assoc.nents,
 		areq_ctx->assoclen, req->cryptlen);
 
-	dma_unmap_sg(dev, req->src, sg_nents(req->src), DMA_BIDIRECTIONAL);
+	dma_unmap_sg(dev, req->src, areq_ctx->src.mapped_nents,
+		     DMA_BIDIRECTIONAL);
 	if (req->src != req->dst) {
 		dev_dbg(dev, "Unmapping dst sgl: req->dst=%pK\n",
 			sg_virt(req->dst));
-		dma_unmap_sg(dev, req->dst, sg_nents(req->dst),
+		dma_unmap_sg(dev, req->dst, areq_ctx->dst.mapped_nents,
 			     DMA_BIDIRECTIONAL);
 	}
 	if (drvdata->coherent &&
@@ -902,7 +894,7 @@ static int cc_aead_chain_data(struct cc_drvdata *drvdata,
 					    &src_last_bytes);
 	sg_index = areq_ctx->src_sgl->length;
 	//check where the data starts
-	while (sg_index <= size_to_skip) {
+	while (src_mapped_nents && (sg_index <= size_to_skip)) {
 		src_mapped_nents--;
 		offset -= areq_ctx->src_sgl->length;
 		sgl = sg_next(areq_ctx->src_sgl);
@@ -923,13 +915,17 @@ static int cc_aead_chain_data(struct cc_drvdata *drvdata,
 
 	if (req->src != req->dst) {
 		size_for_map = areq_ctx->assoclen + req->cryptlen;
-		size_for_map += (direct == DRV_CRYPTO_DIRECTION_ENCRYPT) ?
-				authsize : 0;
+
+		if (direct == DRV_CRYPTO_DIRECTION_ENCRYPT)
+			size_for_map += authsize;
+		else
+			size_for_map -= authsize;
+
 		if (is_gcm4543)
 			size_for_map += crypto_aead_ivsize(tfm);
 
 		rc = cc_map_sg(dev, req->dst, size_for_map, DMA_BIDIRECTIONAL,
-			       &areq_ctx->dst.nents,
+			       &areq_ctx->dst.mapped_nents,
 			       LLI_MAX_NUM_OF_DATA_ENTRIES, &dst_last_bytes,
 			       &dst_mapped_nents);
 		if (rc)
@@ -942,7 +938,7 @@ static int cc_aead_chain_data(struct cc_drvdata *drvdata,
 	offset = size_to_skip;
 
 	//check where the data starts
-	while (sg_index <= size_to_skip) {
+	while (dst_mapped_nents && sg_index <= size_to_skip) {
 		dst_mapped_nents--;
 		offset -= areq_ctx->dst_sgl->length;
 		sgl = sg_next(areq_ctx->dst_sgl);
@@ -1138,13 +1134,15 @@ int cc_map_aead_request(struct cc_drvdata *drvdata, struct aead_request *req)
 	}
 
 	size_to_map = req->cryptlen + areq_ctx->assoclen;
-	if (areq_ctx->gen_ctx.op_type == DRV_CRYPTO_DIRECTION_ENCRYPT)
+	/* If we do in-place encryption, we also need the auth tag */
+	if ((areq_ctx->gen_ctx.op_type == DRV_CRYPTO_DIRECTION_ENCRYPT) &&
+	   (req->src == req->dst)) {
 		size_to_map += authsize;
-
+	}
 	if (is_gcm4543)
 		size_to_map += crypto_aead_ivsize(tfm);
 	rc = cc_map_sg(dev, req->src, size_to_map, DMA_BIDIRECTIONAL,
-		       &areq_ctx->src.nents,
+		       &areq_ctx->src.mapped_nents,
 		       (LLI_MAX_NUM_OF_ASSOC_DATA_ENTRIES +
 			LLI_MAX_NUM_OF_DATA_ENTRIES),
 		       &dummy, &mapped_nents);
diff --git a/drivers/crypto/ccree/cc_buffer_mgr.h b/drivers/crypto/ccree/cc_buffer_mgr.h
index a726016bdbc1..846b262a9029 100644
--- a/drivers/crypto/ccree/cc_buffer_mgr.h
+++ b/drivers/crypto/ccree/cc_buffer_mgr.h
@@ -25,6 +25,7 @@ enum cc_sg_cpy_direct {
 
 struct cc_mlli {
 	cc_sram_addr_t sram_addr;
+	unsigned int mapped_nents;
 	unsigned int nents; //sg nents
 	unsigned int mlli_nents; //mlli nents might be different than the above
 };
diff --git a/drivers/crypto/ccree/cc_cipher.c b/drivers/crypto/ccree/cc_cipher.c
index 5b58226ea24d..5604e188d2d4 100644
--- a/drivers/crypto/ccree/cc_cipher.c
+++ b/drivers/crypto/ccree/cc_cipher.c
@@ -167,7 +167,6 @@ static int cc_cipher_init(struct crypto_tfm *tfm)
 				     skcipher_alg.base);
 	struct device *dev = drvdata_to_dev(cc_alg->drvdata);
 	unsigned int max_key_buf_size = cc_alg->skcipher_alg.max_keysize;
-	int rc = 0;
 
 	dev_dbg(dev, "Initializing context @%p for %s\n", ctx_p,
 		crypto_tfm_alg_name(tfm));
@@ -179,10 +178,19 @@ static int cc_cipher_init(struct crypto_tfm *tfm)
 	ctx_p->flow_mode = cc_alg->flow_mode;
 	ctx_p->drvdata = cc_alg->drvdata;
 
+	if (ctx_p->cipher_mode == DRV_CIPHER_ESSIV) {
+		/* Alloc hash tfm for essiv */
+		ctx_p->shash_tfm = crypto_alloc_shash("sha256-generic", 0, 0);
+		if (IS_ERR(ctx_p->shash_tfm)) {
+			dev_err(dev, "Error allocating hash tfm for ESSIV.\n");
+			return PTR_ERR(ctx_p->shash_tfm);
+		}
+	}
+
 	/* Allocate key buffer, cache line aligned */
 	ctx_p->user.key = kmalloc(max_key_buf_size, GFP_KERNEL);
 	if (!ctx_p->user.key)
-		return -ENOMEM;
+		goto free_shash;
 
 	dev_dbg(dev, "Allocated key buffer in context. key=@%p\n",
 		ctx_p->user.key);
@@ -194,21 +202,19 @@ static int cc_cipher_init(struct crypto_tfm *tfm)
 	if (dma_mapping_error(dev, ctx_p->user.key_dma_addr)) {
 		dev_err(dev, "Mapping Key %u B at va=%pK for DMA failed\n",
 			max_key_buf_size, ctx_p->user.key);
-		return -ENOMEM;
+		goto free_key;
 	}
 	dev_dbg(dev, "Mapped key %u B at va=%pK to dma=%pad\n",
 		max_key_buf_size, ctx_p->user.key, &ctx_p->user.key_dma_addr);
 
-	if (ctx_p->cipher_mode == DRV_CIPHER_ESSIV) {
-		/* Alloc hash tfm for essiv */
-		ctx_p->shash_tfm = crypto_alloc_shash("sha256-generic", 0, 0);
-		if (IS_ERR(ctx_p->shash_tfm)) {
-			dev_err(dev, "Error allocating hash tfm for ESSIV.\n");
-			return PTR_ERR(ctx_p->shash_tfm);
-		}
-	}
+	return 0;
 
-	return rc;
+free_key:
+	kfree(ctx_p->user.key);
+free_shash:
+	crypto_free_shash(ctx_p->shash_tfm);
+
+	return -ENOMEM;
 }
 
 static void cc_cipher_exit(struct crypto_tfm *tfm)
@@ -534,6 +540,7 @@ static void cc_setup_readiv_desc(struct crypto_tfm *tfm,
 	}
 }
 
+
 static void cc_setup_state_desc(struct crypto_tfm *tfm,
 				 struct cipher_req_ctx *req_ctx,
 				 unsigned int ivsize, unsigned int nbytes,
@@ -545,8 +552,6 @@ static void cc_setup_state_desc(struct crypto_tfm *tfm,
 	int cipher_mode = ctx_p->cipher_mode;
 	int flow_mode = ctx_p->flow_mode;
 	int direction = req_ctx->gen_ctx.op_type;
-	dma_addr_t key_dma_addr = ctx_p->user.key_dma_addr;
-	unsigned int key_len = ctx_p->keylen;
 	dma_addr_t iv_dma_addr = req_ctx->gen_ctx.iv_dma_addr;
 	unsigned int du_size = nbytes;
 
@@ -582,6 +587,47 @@ static void cc_setup_state_desc(struct crypto_tfm *tfm,
 	case DRV_CIPHER_XTS:
 	case DRV_CIPHER_ESSIV:
 	case DRV_CIPHER_BITLOCKER:
+		break;
+	default:
+		dev_err(dev, "Unsupported cipher mode (%d)\n", cipher_mode);
+	}
+}
+
+
+static void cc_setup_xex_state_desc(struct crypto_tfm *tfm,
+				 struct cipher_req_ctx *req_ctx,
+				 unsigned int ivsize, unsigned int nbytes,
+				 struct cc_hw_desc desc[],
+				 unsigned int *seq_size)
+{
+	struct cc_cipher_ctx *ctx_p = crypto_tfm_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx_p->drvdata);
+	int cipher_mode = ctx_p->cipher_mode;
+	int flow_mode = ctx_p->flow_mode;
+	int direction = req_ctx->gen_ctx.op_type;
+	dma_addr_t key_dma_addr = ctx_p->user.key_dma_addr;
+	unsigned int key_len = ctx_p->keylen;
+	dma_addr_t iv_dma_addr = req_ctx->gen_ctx.iv_dma_addr;
+	unsigned int du_size = nbytes;
+
+	struct cc_crypto_alg *cc_alg =
+		container_of(tfm->__crt_alg, struct cc_crypto_alg,
+			     skcipher_alg.base);
+
+	if (cc_alg->data_unit)
+		du_size = cc_alg->data_unit;
+
+	switch (cipher_mode) {
+	case DRV_CIPHER_ECB:
+		break;
+	case DRV_CIPHER_CBC:
+	case DRV_CIPHER_CBC_CTS:
+	case DRV_CIPHER_CTR:
+	case DRV_CIPHER_OFB:
+		break;
+	case DRV_CIPHER_XTS:
+	case DRV_CIPHER_ESSIV:
+	case DRV_CIPHER_BITLOCKER:
 		/* load XEX key */
 		hw_desc_init(&desc[*seq_size]);
 		set_cipher_mode(&desc[*seq_size], cipher_mode);
@@ -892,12 +938,14 @@ static int cc_cipher_process(struct skcipher_request *req,
 
 	/* STAT_PHASE_2: Create sequence */
 
-	/* Setup IV and XEX key used */
+	/* Setup state (IV)  */
 	cc_setup_state_desc(tfm, req_ctx, ivsize, nbytes, desc, &seq_len);
 	/* Setup MLLI line, if needed */
 	cc_setup_mlli_desc(tfm, req_ctx, dst, src, nbytes, req, desc, &seq_len);
 	/* Setup key */
 	cc_setup_key_desc(tfm, req_ctx, nbytes, desc, &seq_len);
+	/* Setup state (IV and XEX key)  */
+	cc_setup_xex_state_desc(tfm, req_ctx, ivsize, nbytes, desc, &seq_len);
 	/* Data processing */
 	cc_setup_flow_desc(tfm, req_ctx, dst, src, nbytes, desc, &seq_len);
 	/* Read next IV */
diff --git a/drivers/crypto/ccree/cc_driver.h b/drivers/crypto/ccree/cc_driver.h
index b76181335c08..bfa485dce342 100644
--- a/drivers/crypto/ccree/cc_driver.h
+++ b/drivers/crypto/ccree/cc_driver.h
@@ -166,6 +166,7 @@ struct cc_drvdata {
 	int std_bodies;
 	bool sec_disabled;
 	u32 comp_mask;
+	bool pm_on;
 };
 
 struct cc_crypto_alg {
diff --git a/drivers/crypto/ccree/cc_pm.c b/drivers/crypto/ccree/cc_pm.c
index 2dad9c9543c6..759ef4d585ad 100644
--- a/drivers/crypto/ccree/cc_pm.c
+++ b/drivers/crypto/ccree/cc_pm.c
@@ -23,14 +23,8 @@ const struct dev_pm_ops ccree_pm = {
 int cc_pm_suspend(struct device *dev)
 {
 	struct cc_drvdata *drvdata = dev_get_drvdata(dev);
-	int rc;
 
 	dev_dbg(dev, "set HOST_POWER_DOWN_EN\n");
-	rc = cc_suspend_req_queue(drvdata);
-	if (rc) {
-		dev_err(dev, "cc_suspend_req_queue (%x)\n", rc);
-		return rc;
-	}
 	fini_cc_regs(drvdata);
 	cc_iowrite(drvdata, CC_REG(HOST_POWER_DOWN_EN), POWER_DOWN_ENABLE);
 	cc_clk_off(drvdata);
@@ -59,13 +53,6 @@ int cc_pm_resume(struct device *dev)
 	/* check if tee fips error occurred during power down */
 	cc_tee_handle_fips_error(drvdata);
 
-	rc = cc_resume_req_queue(drvdata);
-	if (rc) {
-		dev_err(dev, "cc_resume_req_queue (%x)\n", rc);
-		return rc;
-	}
-
-	/* must be after the queue resuming as it uses the HW queue*/
 	cc_init_hash_sram(drvdata);
 
 	cc_init_iv_sram(drvdata);
@@ -77,12 +64,10 @@ int cc_pm_get(struct device *dev)
 	int rc = 0;
 	struct cc_drvdata *drvdata = dev_get_drvdata(dev);
 
-	if (cc_req_queue_suspended(drvdata))
+	if (drvdata->pm_on)
 		rc = pm_runtime_get_sync(dev);
-	else
-		pm_runtime_get_noresume(dev);
 
-	return rc;
+	return (rc == 1 ? 0 : rc);
 }
 
 int cc_pm_put_suspend(struct device *dev)
@@ -90,14 +75,11 @@ int cc_pm_put_suspend(struct device *dev)
 	int rc = 0;
 	struct cc_drvdata *drvdata = dev_get_drvdata(dev);
 
-	if (!cc_req_queue_suspended(drvdata)) {
+	if (drvdata->pm_on) {
 		pm_runtime_mark_last_busy(dev);
 		rc = pm_runtime_put_autosuspend(dev);
-	} else {
-		/* Something wrong happens*/
-		dev_err(dev, "request to suspend already suspended queue");
-		rc = -EBUSY;
 	}
+
 	return rc;
 }
 
@@ -108,7 +90,7 @@ int cc_pm_init(struct cc_drvdata *drvdata)
 	/* must be before the enabling to avoid resdundent suspending */
 	pm_runtime_set_autosuspend_delay(dev, CC_SUSPEND_TIMEOUT);
 	pm_runtime_use_autosuspend(dev);
-	/* activate the PM module */
+	/* set us as active - note we won't do PM ops until cc_pm_go()! */
 	return pm_runtime_set_active(dev);
 }
 
@@ -116,9 +98,11 @@ int cc_pm_init(struct cc_drvdata *drvdata)
 void cc_pm_go(struct cc_drvdata *drvdata)
 {
 	pm_runtime_enable(drvdata_to_dev(drvdata));
+	drvdata->pm_on = true;
 }
 
 void cc_pm_fini(struct cc_drvdata *drvdata)
 {
 	pm_runtime_disable(drvdata_to_dev(drvdata));
+	drvdata->pm_on = false;
 }
diff --git a/drivers/crypto/ccree/cc_request_mgr.c b/drivers/crypto/ccree/cc_request_mgr.c
index 0bc6ccb0b899..31d6ccf9cb35 100644
--- a/drivers/crypto/ccree/cc_request_mgr.c
+++ b/drivers/crypto/ccree/cc_request_mgr.c
@@ -42,7 +42,6 @@ struct cc_req_mgr_handle {
 #else
 	struct tasklet_struct comptask;
 #endif
-	bool is_runtime_suspended;
 };
 
 struct cc_bl_item {
@@ -436,6 +435,7 @@ static void cc_proc_backlog(struct cc_drvdata *drvdata)
 		spin_lock(&mgr->bl_lock);
 		list_del(&bli->list);
 		--mgr->bl_len;
+		kfree(bli);
 	}
 
 	spin_unlock(&mgr->bl_lock);
@@ -712,52 +712,3 @@ static void comp_handler(unsigned long devarg)
 	cc_proc_backlog(drvdata);
 	dev_dbg(dev, "Comp. handler done.\n");
 }
-
-/*
- * resume the queue configuration - no need to take the lock as this happens
- * inside the spin lock protection
- */
-#if defined(CONFIG_PM)
-int cc_resume_req_queue(struct cc_drvdata *drvdata)
-{
-	struct cc_req_mgr_handle *request_mgr_handle =
-		drvdata->request_mgr_handle;
-
-	spin_lock_bh(&request_mgr_handle->hw_lock);
-	request_mgr_handle->is_runtime_suspended = false;
-	spin_unlock_bh(&request_mgr_handle->hw_lock);
-
-	return 0;
-}
-
-/*
- * suspend the queue configuration. Since it is used for the runtime suspend
- * only verify that the queue can be suspended.
- */
-int cc_suspend_req_queue(struct cc_drvdata *drvdata)
-{
-	struct cc_req_mgr_handle *request_mgr_handle =
-						drvdata->request_mgr_handle;
-
-	/* lock the send_request */
-	spin_lock_bh(&request_mgr_handle->hw_lock);
-	if (request_mgr_handle->req_queue_head !=
-	    request_mgr_handle->req_queue_tail) {
-		spin_unlock_bh(&request_mgr_handle->hw_lock);
-		return -EBUSY;
-	}
-	request_mgr_handle->is_runtime_suspended = true;
-	spin_unlock_bh(&request_mgr_handle->hw_lock);
-
-	return 0;
-}
-
-bool cc_req_queue_suspended(struct cc_drvdata *drvdata)
-{
-	struct cc_req_mgr_handle *request_mgr_handle =
-						drvdata->request_mgr_handle;
-
-	return	request_mgr_handle->is_runtime_suspended;
-}
-
-#endif
diff --git a/drivers/crypto/ccree/cc_request_mgr.h b/drivers/crypto/ccree/cc_request_mgr.h
index f46cf766fe4d..ff7746aaaf35 100644
--- a/drivers/crypto/ccree/cc_request_mgr.h
+++ b/drivers/crypto/ccree/cc_request_mgr.h
@@ -40,12 +40,4 @@ void complete_request(struct cc_drvdata *drvdata);
 
 void cc_req_mgr_fini(struct cc_drvdata *drvdata);
 
-#if defined(CONFIG_PM)
-int cc_resume_req_queue(struct cc_drvdata *drvdata);
-
-int cc_suspend_req_queue(struct cc_drvdata *drvdata);
-
-bool cc_req_queue_suspended(struct cc_drvdata *drvdata);
-#endif
-
 #endif /*__REQUEST_MGR_H__*/
diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c
index 177f572b9589..6c3ca14ea3f6 100644
--- a/drivers/crypto/chelsio/chcr_algo.c
+++ b/drivers/crypto/chelsio/chcr_algo.c
@@ -2830,7 +2830,7 @@ static void fill_sec_cpl_for_aead(struct cpl_tx_sec_pdu *sec_cpl,
 	unsigned int mac_mode = CHCR_SCMD_AUTH_MODE_CBCMAC;
 	unsigned int c_id = a_ctx(tfm)->tx_chan_id;
 	unsigned int ccm_xtra;
-	unsigned char tag_offset = 0, auth_offset = 0;
+	unsigned int tag_offset = 0, auth_offset = 0;
 	unsigned int assoclen;
 
 	if (get_aead_subtype(tfm) == CRYPTO_ALG_SUB_TYPE_AEAD_RFC4309)
@@ -3206,9 +3206,6 @@ static int chcr_gcm_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
 		aeadctx->mayverify = VERIFY_SW;
 		break;
 	default:
-
-		  crypto_tfm_set_flags((struct crypto_tfm *) tfm,
-			CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 	return crypto_aead_setauthsize(aeadctx->sw_cipher, authsize);
@@ -3233,8 +3230,6 @@ static int chcr_4106_4309_setauthsize(struct crypto_aead *tfm,
 		aeadctx->mayverify = VERIFY_HW;
 		break;
 	default:
-		crypto_tfm_set_flags((struct crypto_tfm *)tfm,
-				     CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 	return crypto_aead_setauthsize(aeadctx->sw_cipher, authsize);
@@ -3275,8 +3270,6 @@ static int chcr_ccm_setauthsize(struct crypto_aead *tfm,
 		aeadctx->mayverify = VERIFY_HW;
 		break;
 	default:
-		crypto_tfm_set_flags((struct crypto_tfm *)tfm,
-				     CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 	return crypto_aead_setauthsize(aeadctx->sw_cipher, authsize);
@@ -3301,8 +3294,7 @@ static int chcr_ccm_common_setkey(struct crypto_aead *aead,
 		ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_256;
 		mk_size = CHCR_KEYCTX_MAC_KEY_SIZE_256;
 	} else {
-		crypto_tfm_set_flags((struct crypto_tfm *)aead,
-				     CRYPTO_TFM_RES_BAD_KEY_LEN);
+		crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		aeadctx->enckey_len = 0;
 		return	-EINVAL;
 	}
@@ -3340,8 +3332,7 @@ static int chcr_aead_rfc4309_setkey(struct crypto_aead *aead, const u8 *key,
 	int error;
 
 	if (keylen < 3) {
-		crypto_tfm_set_flags((struct crypto_tfm *)aead,
-				     CRYPTO_TFM_RES_BAD_KEY_LEN);
+		crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		aeadctx->enckey_len = 0;
 		return	-EINVAL;
 	}
@@ -3391,8 +3382,7 @@ static int chcr_gcm_setkey(struct crypto_aead *aead, const u8 *key,
 	} else if (keylen == AES_KEYSIZE_256) {
 		ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_256;
 	} else {
-		crypto_tfm_set_flags((struct crypto_tfm *)aead,
-				     CRYPTO_TFM_RES_BAD_KEY_LEN);
+		crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		pr_err("GCM: Invalid key length %d\n", keylen);
 		ret = -EINVAL;
 		goto out;
diff --git a/drivers/crypto/chelsio/chcr_core.c b/drivers/crypto/chelsio/chcr_core.c
index 029a7354f541..5c16f368879b 100644
--- a/drivers/crypto/chelsio/chcr_core.c
+++ b/drivers/crypto/chelsio/chcr_core.c
@@ -125,8 +125,6 @@ static void chcr_dev_init(struct uld_ctx *u_ctx)
 	atomic_set(&dev->inflight, 0);
 	mutex_lock(&drv_data.drv_mutex);
 	list_add_tail(&u_ctx->entry, &drv_data.inact_dev);
-	if (!drv_data.last_dev)
-		drv_data.last_dev = u_ctx;
 	mutex_unlock(&drv_data.drv_mutex);
 }
 
diff --git a/drivers/crypto/chelsio/chtls/chtls_cm.c b/drivers/crypto/chelsio/chtls/chtls_cm.c
index aca75237bbcf..dffa2aa855fd 100644
--- a/drivers/crypto/chelsio/chtls/chtls_cm.c
+++ b/drivers/crypto/chelsio/chtls/chtls_cm.c
@@ -727,6 +727,14 @@ static int chtls_close_listsrv_rpl(struct chtls_dev *cdev, struct sk_buff *skb)
 	return 0;
 }
 
+static void chtls_purge_wr_queue(struct sock *sk)
+{
+	struct sk_buff *skb;
+
+	while ((skb = dequeue_wr(sk)) != NULL)
+		kfree_skb(skb);
+}
+
 static void chtls_release_resources(struct sock *sk)
 {
 	struct chtls_sock *csk = rcu_dereference_sk_user_data(sk);
@@ -741,6 +749,11 @@ static void chtls_release_resources(struct sock *sk)
 	kfree_skb(csk->txdata_skb_cache);
 	csk->txdata_skb_cache = NULL;
 
+	if (csk->wr_credits != csk->wr_max_credits) {
+		chtls_purge_wr_queue(sk);
+		chtls_reset_wr_list(csk);
+	}
+
 	if (csk->l2t_entry) {
 		cxgb4_l2t_release(csk->l2t_entry);
 		csk->l2t_entry = NULL;
@@ -1735,6 +1748,7 @@ static void chtls_peer_close(struct sock *sk, struct sk_buff *skb)
 		else
 			sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
 	}
+	kfree_skb(skb);
 }
 
 static void chtls_close_con_rpl(struct sock *sk, struct sk_buff *skb)
@@ -2062,19 +2076,6 @@ rel_skb:
 	return 0;
 }
 
-static struct sk_buff *dequeue_wr(struct sock *sk)
-{
-	struct chtls_sock *csk = rcu_dereference_sk_user_data(sk);
-	struct sk_buff *skb = csk->wr_skb_head;
-
-	if (likely(skb)) {
-	/* Don't bother clearing the tail */
-		csk->wr_skb_head = WR_SKB_CB(skb)->next_wr;
-		WR_SKB_CB(skb)->next_wr = NULL;
-	}
-	return skb;
-}
-
 static void chtls_rx_ack(struct sock *sk, struct sk_buff *skb)
 {
 	struct cpl_fw4_ack *hdr = cplhdr(skb) + RSS_HDR;
diff --git a/drivers/crypto/chelsio/chtls/chtls_cm.h b/drivers/crypto/chelsio/chtls/chtls_cm.h
index 129d7ac649a9..3fac0c74a41f 100644
--- a/drivers/crypto/chelsio/chtls/chtls_cm.h
+++ b/drivers/crypto/chelsio/chtls/chtls_cm.h
@@ -185,6 +185,12 @@ static inline void chtls_kfree_skb(struct sock *sk, struct sk_buff *skb)
 	kfree_skb(skb);
 }
 
+static inline void chtls_reset_wr_list(struct chtls_sock *csk)
+{
+	csk->wr_skb_head = NULL;
+	csk->wr_skb_tail = NULL;
+}
+
 static inline void enqueue_wr(struct chtls_sock *csk, struct sk_buff *skb)
 {
 	WR_SKB_CB(skb)->next_wr = NULL;
@@ -197,4 +203,19 @@ static inline void enqueue_wr(struct chtls_sock *csk, struct sk_buff *skb)
 		WR_SKB_CB(csk->wr_skb_tail)->next_wr = skb;
 	csk->wr_skb_tail = skb;
 }
+
+static inline struct sk_buff *dequeue_wr(struct sock *sk)
+{
+	struct chtls_sock *csk = rcu_dereference_sk_user_data(sk);
+	struct sk_buff *skb = NULL;
+
+	skb = csk->wr_skb_head;
+
+	if (likely(skb)) {
+	 /* Don't bother clearing the tail */
+		csk->wr_skb_head = WR_SKB_CB(skb)->next_wr;
+		WR_SKB_CB(skb)->next_wr = NULL;
+	}
+	return skb;
+}
 #endif
diff --git a/drivers/crypto/chelsio/chtls/chtls_hw.c b/drivers/crypto/chelsio/chtls/chtls_hw.c
index f2424f4c5f78..0731bae155f2 100644
--- a/drivers/crypto/chelsio/chtls/chtls_hw.c
+++ b/drivers/crypto/chelsio/chtls/chtls_hw.c
@@ -358,6 +358,7 @@ int chtls_setkey(struct chtls_sock *csk, u32 keylen, u32 optname)
 	kwr->sc_imm.cmd_more = cpu_to_be32(ULPTX_CMD_V(ULP_TX_SC_IMM));
 	kwr->sc_imm.len = cpu_to_be32(klen);
 
+	lock_sock(sk);
 	/* key info */
 	kctx = (struct _key_ctx *)(kwr + 1);
 	ret = chtls_key_info(csk, kctx, keylen, optname);
@@ -396,8 +397,10 @@ int chtls_setkey(struct chtls_sock *csk, u32 keylen, u32 optname)
 		csk->tlshws.txkey = keyid;
 	}
 
+	release_sock(sk);
 	return ret;
 out_notcb:
+	release_sock(sk);
 	free_tls_keyid(sk);
 out_nokey:
 	kfree_skb(skb);
diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/crypto/chelsio/chtls/chtls_io.c
index f382c2b23d75..9b59cea09e03 100644
--- a/drivers/crypto/chelsio/chtls/chtls_io.c
+++ b/drivers/crypto/chelsio/chtls/chtls_io.c
@@ -682,7 +682,7 @@ int chtls_push_frames(struct chtls_sock *csk, int comp)
 				make_tx_data_wr(sk, skb, immdlen, len,
 						credits_needed, completion);
 			tp->snd_nxt += len;
-			tp->lsndtime = tcp_time_stamp(tp);
+			tp->lsndtime = tcp_jiffies32;
 			if (completion)
 				ULP_SKB_CB(skb)->flags &= ~ULPCB_FLAG_NEED_HDR;
 		} else {
diff --git a/drivers/crypto/geode-aes.c b/drivers/crypto/geode-aes.c
index 940485112d15..73a899e6f837 100644
--- a/drivers/crypto/geode-aes.c
+++ b/drivers/crypto/geode-aes.c
@@ -10,7 +10,7 @@
 #include <linux/spinlock.h>
 #include <crypto/algapi.h>
 #include <crypto/aes.h>
-#include <crypto/skcipher.h>
+#include <crypto/internal/skcipher.h>
 
 #include <linux/io.h>
 #include <linux/delay.h>
@@ -24,12 +24,12 @@ static spinlock_t lock;
 
 /* Write a 128 bit field (either a writable key or IV) */
 static inline void
-_writefield(u32 offset, void *value)
+_writefield(u32 offset, const void *value)
 {
 	int i;
 
 	for (i = 0; i < 4; i++)
-		iowrite32(((u32 *) value)[i], _iobase + offset + (i * 4));
+		iowrite32(((const u32 *) value)[i], _iobase + offset + (i * 4));
 }
 
 /* Read a 128 bit field (either a writable key or IV) */
@@ -43,12 +43,12 @@ _readfield(u32 offset, void *value)
 }
 
 static int
-do_crypt(void *src, void *dst, int len, u32 flags)
+do_crypt(const void *src, void *dst, u32 len, u32 flags)
 {
 	u32 status;
 	u32 counter = AES_OP_TIMEOUT;
 
-	iowrite32(virt_to_phys(src), _iobase + AES_SOURCEA_REG);
+	iowrite32(virt_to_phys((void *)src), _iobase + AES_SOURCEA_REG);
 	iowrite32(virt_to_phys(dst), _iobase + AES_DSTA_REG);
 	iowrite32(len,  _iobase + AES_LENA_REG);
 
@@ -65,16 +65,14 @@ do_crypt(void *src, void *dst, int len, u32 flags)
 	return counter ? 0 : 1;
 }
 
-static unsigned int
-geode_aes_crypt(struct geode_aes_op *op)
+static void
+geode_aes_crypt(const struct geode_aes_tfm_ctx *tctx, const void *src,
+		void *dst, u32 len, u8 *iv, int mode, int dir)
 {
 	u32 flags = 0;
 	unsigned long iflags;
 	int ret;
 
-	if (op->len == 0)
-		return 0;
-
 	/* If the source and destination is the same, then
 	 * we need to turn on the coherent flags, otherwise
 	 * we don't need to worry
@@ -82,32 +80,28 @@ geode_aes_crypt(struct geode_aes_op *op)
 
 	flags |= (AES_CTRL_DCA | AES_CTRL_SCA);
 
-	if (op->dir == AES_DIR_ENCRYPT)
+	if (dir == AES_DIR_ENCRYPT)
 		flags |= AES_CTRL_ENCRYPT;
 
 	/* Start the critical section */
 
 	spin_lock_irqsave(&lock, iflags);
 
-	if (op->mode == AES_MODE_CBC) {
+	if (mode == AES_MODE_CBC) {
 		flags |= AES_CTRL_CBC;
-		_writefield(AES_WRITEIV0_REG, op->iv);
+		_writefield(AES_WRITEIV0_REG, iv);
 	}
 
-	if (!(op->flags & AES_FLAGS_HIDDENKEY)) {
-		flags |= AES_CTRL_WRKEY;
-		_writefield(AES_WRITEKEY0_REG, op->key);
-	}
+	flags |= AES_CTRL_WRKEY;
+	_writefield(AES_WRITEKEY0_REG, tctx->key);
 
-	ret = do_crypt(op->src, op->dst, op->len, flags);
+	ret = do_crypt(src, dst, len, flags);
 	BUG_ON(ret);
 
-	if (op->mode == AES_MODE_CBC)
-		_readfield(AES_WRITEIV0_REG, op->iv);
+	if (mode == AES_MODE_CBC)
+		_readfield(AES_WRITEIV0_REG, iv);
 
 	spin_unlock_irqrestore(&lock, iflags);
-
-	return op->len;
 }
 
 /* CRYPTO-API Functions */
@@ -115,13 +109,13 @@ geode_aes_crypt(struct geode_aes_op *op)
 static int geode_setkey_cip(struct crypto_tfm *tfm, const u8 *key,
 		unsigned int len)
 {
-	struct geode_aes_op *op = crypto_tfm_ctx(tfm);
+	struct geode_aes_tfm_ctx *tctx = crypto_tfm_ctx(tfm);
 	unsigned int ret;
 
-	op->keylen = len;
+	tctx->keylen = len;
 
 	if (len == AES_KEYSIZE_128) {
-		memcpy(op->key, key, len);
+		memcpy(tctx->key, key, len);
 		return 0;
 	}
 
@@ -134,132 +128,93 @@ static int geode_setkey_cip(struct crypto_tfm *tfm, const u8 *key,
 	/*
 	 * The requested key size is not supported by HW, do a fallback
 	 */
-	op->fallback.cip->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK;
-	op->fallback.cip->base.crt_flags |= (tfm->crt_flags & CRYPTO_TFM_REQ_MASK);
+	tctx->fallback.cip->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK;
+	tctx->fallback.cip->base.crt_flags |=
+		(tfm->crt_flags & CRYPTO_TFM_REQ_MASK);
 
-	ret = crypto_cipher_setkey(op->fallback.cip, key, len);
+	ret = crypto_cipher_setkey(tctx->fallback.cip, key, len);
 	if (ret) {
 		tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK;
-		tfm->crt_flags |= (op->fallback.cip->base.crt_flags & CRYPTO_TFM_RES_MASK);
+		tfm->crt_flags |= (tctx->fallback.cip->base.crt_flags &
+				   CRYPTO_TFM_RES_MASK);
 	}
 	return ret;
 }
 
-static int geode_setkey_blk(struct crypto_tfm *tfm, const u8 *key,
-		unsigned int len)
+static int geode_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key,
+				 unsigned int len)
 {
-	struct geode_aes_op *op = crypto_tfm_ctx(tfm);
+	struct geode_aes_tfm_ctx *tctx = crypto_skcipher_ctx(tfm);
 	unsigned int ret;
 
-	op->keylen = len;
+	tctx->keylen = len;
 
 	if (len == AES_KEYSIZE_128) {
-		memcpy(op->key, key, len);
+		memcpy(tctx->key, key, len);
 		return 0;
 	}
 
 	if (len != AES_KEYSIZE_192 && len != AES_KEYSIZE_256) {
 		/* not supported at all */
-		tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+		crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 
 	/*
 	 * The requested key size is not supported by HW, do a fallback
 	 */
-	crypto_sync_skcipher_clear_flags(op->fallback.blk, CRYPTO_TFM_REQ_MASK);
-	crypto_sync_skcipher_set_flags(op->fallback.blk,
-				       tfm->crt_flags & CRYPTO_TFM_REQ_MASK);
-
-	ret = crypto_sync_skcipher_setkey(op->fallback.blk, key, len);
-	if (ret) {
-		tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK;
-		tfm->crt_flags |= crypto_sync_skcipher_get_flags(op->fallback.blk) &
-				  CRYPTO_TFM_RES_MASK;
-	}
+	crypto_skcipher_clear_flags(tctx->fallback.skcipher,
+				    CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(tctx->fallback.skcipher,
+				  crypto_skcipher_get_flags(tfm) &
+				  CRYPTO_TFM_REQ_MASK);
+	ret = crypto_skcipher_setkey(tctx->fallback.skcipher, key, len);
+	crypto_skcipher_set_flags(tfm,
+				  crypto_skcipher_get_flags(tctx->fallback.skcipher) &
+				  CRYPTO_TFM_RES_MASK);
 	return ret;
 }
 
-static int fallback_blk_dec(struct blkcipher_desc *desc,
-		struct scatterlist *dst, struct scatterlist *src,
-		unsigned int nbytes)
-{
-	struct geode_aes_op *op = crypto_blkcipher_ctx(desc->tfm);
-	SYNC_SKCIPHER_REQUEST_ON_STACK(req, op->fallback.blk);
-
-	skcipher_request_set_sync_tfm(req, op->fallback.blk);
-	skcipher_request_set_callback(req, 0, NULL, NULL);
-	skcipher_request_set_crypt(req, src, dst, nbytes, desc->info);
-
-	return crypto_skcipher_decrypt(req);
-}
-
-static int fallback_blk_enc(struct blkcipher_desc *desc,
-		struct scatterlist *dst, struct scatterlist *src,
-		unsigned int nbytes)
-{
-	struct geode_aes_op *op = crypto_blkcipher_ctx(desc->tfm);
-	SYNC_SKCIPHER_REQUEST_ON_STACK(req, op->fallback.blk);
-
-	skcipher_request_set_sync_tfm(req, op->fallback.blk);
-	skcipher_request_set_callback(req, 0, NULL, NULL);
-	skcipher_request_set_crypt(req, src, dst, nbytes, desc->info);
-
-	return crypto_skcipher_encrypt(req);
-}
-
 static void
 geode_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
 {
-	struct geode_aes_op *op = crypto_tfm_ctx(tfm);
+	const struct geode_aes_tfm_ctx *tctx = crypto_tfm_ctx(tfm);
 
-	if (unlikely(op->keylen != AES_KEYSIZE_128)) {
-		crypto_cipher_encrypt_one(op->fallback.cip, out, in);
+	if (unlikely(tctx->keylen != AES_KEYSIZE_128)) {
+		crypto_cipher_encrypt_one(tctx->fallback.cip, out, in);
 		return;
 	}
 
-	op->src = (void *) in;
-	op->dst = (void *) out;
-	op->mode = AES_MODE_ECB;
-	op->flags = 0;
-	op->len = AES_BLOCK_SIZE;
-	op->dir = AES_DIR_ENCRYPT;
-
-	geode_aes_crypt(op);
+	geode_aes_crypt(tctx, in, out, AES_BLOCK_SIZE, NULL,
+			AES_MODE_ECB, AES_DIR_ENCRYPT);
 }
 
 
 static void
 geode_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
 {
-	struct geode_aes_op *op = crypto_tfm_ctx(tfm);
+	const struct geode_aes_tfm_ctx *tctx = crypto_tfm_ctx(tfm);
 
-	if (unlikely(op->keylen != AES_KEYSIZE_128)) {
-		crypto_cipher_decrypt_one(op->fallback.cip, out, in);
+	if (unlikely(tctx->keylen != AES_KEYSIZE_128)) {
+		crypto_cipher_decrypt_one(tctx->fallback.cip, out, in);
 		return;
 	}
 
-	op->src = (void *) in;
-	op->dst = (void *) out;
-	op->mode = AES_MODE_ECB;
-	op->flags = 0;
-	op->len = AES_BLOCK_SIZE;
-	op->dir = AES_DIR_DECRYPT;
-
-	geode_aes_crypt(op);
+	geode_aes_crypt(tctx, in, out, AES_BLOCK_SIZE, NULL,
+			AES_MODE_ECB, AES_DIR_DECRYPT);
 }
 
 static int fallback_init_cip(struct crypto_tfm *tfm)
 {
 	const char *name = crypto_tfm_alg_name(tfm);
-	struct geode_aes_op *op = crypto_tfm_ctx(tfm);
+	struct geode_aes_tfm_ctx *tctx = crypto_tfm_ctx(tfm);
 
-	op->fallback.cip = crypto_alloc_cipher(name, 0,
-					       CRYPTO_ALG_NEED_FALLBACK);
+	tctx->fallback.cip = crypto_alloc_cipher(name, 0,
+						 CRYPTO_ALG_NEED_FALLBACK);
 
-	if (IS_ERR(op->fallback.cip)) {
+	if (IS_ERR(tctx->fallback.cip)) {
 		printk(KERN_ERR "Error allocating fallback algo %s\n", name);
-		return PTR_ERR(op->fallback.cip);
+		return PTR_ERR(tctx->fallback.cip);
 	}
 
 	return 0;
@@ -267,10 +222,9 @@ static int fallback_init_cip(struct crypto_tfm *tfm)
 
 static void fallback_exit_cip(struct crypto_tfm *tfm)
 {
-	struct geode_aes_op *op = crypto_tfm_ctx(tfm);
+	struct geode_aes_tfm_ctx *tctx = crypto_tfm_ctx(tfm);
 
-	crypto_free_cipher(op->fallback.cip);
-	op->fallback.cip = NULL;
+	crypto_free_cipher(tctx->fallback.cip);
 }
 
 static struct crypto_alg geode_alg = {
@@ -283,7 +237,7 @@ static struct crypto_alg geode_alg = {
 	.cra_init			=	fallback_init_cip,
 	.cra_exit			=	fallback_exit_cip,
 	.cra_blocksize		=	AES_BLOCK_SIZE,
-	.cra_ctxsize		=	sizeof(struct geode_aes_op),
+	.cra_ctxsize		=	sizeof(struct geode_aes_tfm_ctx),
 	.cra_module			=	THIS_MODULE,
 	.cra_u				=	{
 		.cipher	=	{
@@ -296,220 +250,126 @@ static struct crypto_alg geode_alg = {
 	}
 };
 
-static int
-geode_cbc_decrypt(struct blkcipher_desc *desc,
-		  struct scatterlist *dst, struct scatterlist *src,
-		  unsigned int nbytes)
+static int geode_init_skcipher(struct crypto_skcipher *tfm)
 {
-	struct geode_aes_op *op = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-	int err, ret;
-
-	if (nbytes % AES_BLOCK_SIZE)
-		return -EINVAL;
-
-	if (unlikely(op->keylen != AES_KEYSIZE_128))
-		return fallback_blk_dec(desc, dst, src, nbytes);
+	const char *name = crypto_tfm_alg_name(&tfm->base);
+	struct geode_aes_tfm_ctx *tctx = crypto_skcipher_ctx(tfm);
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-	op->iv = walk.iv;
-
-	while ((nbytes = walk.nbytes)) {
-		op->src = walk.src.virt.addr,
-		op->dst = walk.dst.virt.addr;
-		op->mode = AES_MODE_CBC;
-		op->len = nbytes - (nbytes % AES_BLOCK_SIZE);
-		op->dir = AES_DIR_DECRYPT;
-
-		ret = geode_aes_crypt(op);
-
-		nbytes -= ret;
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+	tctx->fallback.skcipher =
+		crypto_alloc_skcipher(name, 0, CRYPTO_ALG_NEED_FALLBACK |
+				      CRYPTO_ALG_ASYNC);
+	if (IS_ERR(tctx->fallback.skcipher)) {
+		printk(KERN_ERR "Error allocating fallback algo %s\n", name);
+		return PTR_ERR(tctx->fallback.skcipher);
 	}
 
-	return err;
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct skcipher_request) +
+				    crypto_skcipher_reqsize(tctx->fallback.skcipher));
+	return 0;
 }
 
-static int
-geode_cbc_encrypt(struct blkcipher_desc *desc,
-		  struct scatterlist *dst, struct scatterlist *src,
-		  unsigned int nbytes)
+static void geode_exit_skcipher(struct crypto_skcipher *tfm)
 {
-	struct geode_aes_op *op = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-	int err, ret;
+	struct geode_aes_tfm_ctx *tctx = crypto_skcipher_ctx(tfm);
 
-	if (nbytes % AES_BLOCK_SIZE)
-		return -EINVAL;
-
-	if (unlikely(op->keylen != AES_KEYSIZE_128))
-		return fallback_blk_enc(desc, dst, src, nbytes);
+	crypto_free_skcipher(tctx->fallback.skcipher);
+}
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-	op->iv = walk.iv;
+static int geode_skcipher_crypt(struct skcipher_request *req, int mode, int dir)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct geode_aes_tfm_ctx *tctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
+	int err;
+
+	if (unlikely(tctx->keylen != AES_KEYSIZE_128)) {
+		struct skcipher_request *subreq = skcipher_request_ctx(req);
+
+		*subreq = *req;
+		skcipher_request_set_tfm(subreq, tctx->fallback.skcipher);
+		if (dir == AES_DIR_DECRYPT)
+			return crypto_skcipher_decrypt(subreq);
+		else
+			return crypto_skcipher_encrypt(subreq);
+	}
 
-	while ((nbytes = walk.nbytes)) {
-		op->src = walk.src.virt.addr,
-		op->dst = walk.dst.virt.addr;
-		op->mode = AES_MODE_CBC;
-		op->len = nbytes - (nbytes % AES_BLOCK_SIZE);
-		op->dir = AES_DIR_ENCRYPT;
+	err = skcipher_walk_virt(&walk, req, false);
 
-		ret = geode_aes_crypt(op);
-		nbytes -= ret;
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+	while ((nbytes = walk.nbytes) != 0) {
+		geode_aes_crypt(tctx, walk.src.virt.addr, walk.dst.virt.addr,
+				round_down(nbytes, AES_BLOCK_SIZE),
+				walk.iv, mode, dir);
+		err = skcipher_walk_done(&walk, nbytes % AES_BLOCK_SIZE);
 	}
 
 	return err;
 }
 
-static int fallback_init_blk(struct crypto_tfm *tfm)
+static int geode_cbc_encrypt(struct skcipher_request *req)
 {
-	const char *name = crypto_tfm_alg_name(tfm);
-	struct geode_aes_op *op = crypto_tfm_ctx(tfm);
-
-	op->fallback.blk = crypto_alloc_sync_skcipher(name, 0,
-						      CRYPTO_ALG_NEED_FALLBACK);
-	if (IS_ERR(op->fallback.blk)) {
-		printk(KERN_ERR "Error allocating fallback algo %s\n", name);
-		return PTR_ERR(op->fallback.blk);
-	}
-
-	return 0;
+	return geode_skcipher_crypt(req, AES_MODE_CBC, AES_DIR_ENCRYPT);
 }
 
-static void fallback_exit_blk(struct crypto_tfm *tfm)
+static int geode_cbc_decrypt(struct skcipher_request *req)
 {
-	struct geode_aes_op *op = crypto_tfm_ctx(tfm);
-
-	crypto_free_sync_skcipher(op->fallback.blk);
-	op->fallback.blk = NULL;
+	return geode_skcipher_crypt(req, AES_MODE_CBC, AES_DIR_DECRYPT);
 }
 
-static struct crypto_alg geode_cbc_alg = {
-	.cra_name		=	"cbc(aes)",
-	.cra_driver_name	=	"cbc-aes-geode",
-	.cra_priority		=	400,
-	.cra_flags			=	CRYPTO_ALG_TYPE_BLKCIPHER |
-						CRYPTO_ALG_KERN_DRIVER_ONLY |
-						CRYPTO_ALG_NEED_FALLBACK,
-	.cra_init			=	fallback_init_blk,
-	.cra_exit			=	fallback_exit_blk,
-	.cra_blocksize		=	AES_BLOCK_SIZE,
-	.cra_ctxsize		=	sizeof(struct geode_aes_op),
-	.cra_alignmask		=	15,
-	.cra_type			=	&crypto_blkcipher_type,
-	.cra_module			=	THIS_MODULE,
-	.cra_u				=	{
-		.blkcipher	=	{
-			.min_keysize	=	AES_MIN_KEY_SIZE,
-			.max_keysize	=	AES_MAX_KEY_SIZE,
-			.setkey			=	geode_setkey_blk,
-			.encrypt		=	geode_cbc_encrypt,
-			.decrypt		=	geode_cbc_decrypt,
-			.ivsize			=	AES_BLOCK_SIZE,
-		}
-	}
-};
-
-static int
-geode_ecb_decrypt(struct blkcipher_desc *desc,
-		  struct scatterlist *dst, struct scatterlist *src,
-		  unsigned int nbytes)
+static int geode_ecb_encrypt(struct skcipher_request *req)
 {
-	struct geode_aes_op *op = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-	int err, ret;
-
-	if (nbytes % AES_BLOCK_SIZE)
-		return -EINVAL;
-
-	if (unlikely(op->keylen != AES_KEYSIZE_128))
-		return fallback_blk_dec(desc, dst, src, nbytes);
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-
-	while ((nbytes = walk.nbytes)) {
-		op->src = walk.src.virt.addr,
-		op->dst = walk.dst.virt.addr;
-		op->mode = AES_MODE_ECB;
-		op->len = nbytes - (nbytes % AES_BLOCK_SIZE);
-		op->dir = AES_DIR_DECRYPT;
-
-		ret = geode_aes_crypt(op);
-		nbytes -= ret;
-		err = blkcipher_walk_done(desc, &walk, nbytes);
-	}
-
-	return err;
+	return geode_skcipher_crypt(req, AES_MODE_ECB, AES_DIR_ENCRYPT);
 }
 
-static int
-geode_ecb_encrypt(struct blkcipher_desc *desc,
-		  struct scatterlist *dst, struct scatterlist *src,
-		  unsigned int nbytes)
+static int geode_ecb_decrypt(struct skcipher_request *req)
 {
-	struct geode_aes_op *op = crypto_blkcipher_ctx(desc->tfm);
-	struct blkcipher_walk walk;
-	int err, ret;
-
-	if (nbytes % AES_BLOCK_SIZE)
-		return -EINVAL;
-
-	if (unlikely(op->keylen != AES_KEYSIZE_128))
-		return fallback_blk_enc(desc, dst, src, nbytes);
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-
-	while ((nbytes = walk.nbytes)) {
-		op->src = walk.src.virt.addr,
-		op->dst = walk.dst.virt.addr;
-		op->mode = AES_MODE_ECB;
-		op->len = nbytes - (nbytes % AES_BLOCK_SIZE);
-		op->dir = AES_DIR_ENCRYPT;
-
-		ret = geode_aes_crypt(op);
-		nbytes -= ret;
-		ret =  blkcipher_walk_done(desc, &walk, nbytes);
-	}
-
-	return err;
+	return geode_skcipher_crypt(req, AES_MODE_ECB, AES_DIR_DECRYPT);
 }
 
-static struct crypto_alg geode_ecb_alg = {
-	.cra_name			=	"ecb(aes)",
-	.cra_driver_name	=	"ecb-aes-geode",
-	.cra_priority		=	400,
-	.cra_flags			=	CRYPTO_ALG_TYPE_BLKCIPHER |
-						CRYPTO_ALG_KERN_DRIVER_ONLY |
-						CRYPTO_ALG_NEED_FALLBACK,
-	.cra_init			=	fallback_init_blk,
-	.cra_exit			=	fallback_exit_blk,
-	.cra_blocksize		=	AES_BLOCK_SIZE,
-	.cra_ctxsize		=	sizeof(struct geode_aes_op),
-	.cra_alignmask		=	15,
-	.cra_type			=	&crypto_blkcipher_type,
-	.cra_module			=	THIS_MODULE,
-	.cra_u				=	{
-		.blkcipher	=	{
-			.min_keysize	=	AES_MIN_KEY_SIZE,
-			.max_keysize	=	AES_MAX_KEY_SIZE,
-			.setkey			=	geode_setkey_blk,
-			.encrypt		=	geode_ecb_encrypt,
-			.decrypt		=	geode_ecb_decrypt,
-		}
-	}
+static struct skcipher_alg geode_skcipher_algs[] = {
+	{
+		.base.cra_name		= "cbc(aes)",
+		.base.cra_driver_name	= "cbc-aes-geode",
+		.base.cra_priority	= 400,
+		.base.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
+					  CRYPTO_ALG_NEED_FALLBACK,
+		.base.cra_blocksize	= AES_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct geode_aes_tfm_ctx),
+		.base.cra_alignmask	= 15,
+		.base.cra_module	= THIS_MODULE,
+		.init			= geode_init_skcipher,
+		.exit			= geode_exit_skcipher,
+		.setkey			= geode_setkey_skcipher,
+		.encrypt		= geode_cbc_encrypt,
+		.decrypt		= geode_cbc_decrypt,
+		.min_keysize		= AES_MIN_KEY_SIZE,
+		.max_keysize		= AES_MAX_KEY_SIZE,
+		.ivsize			= AES_BLOCK_SIZE,
+	}, {
+		.base.cra_name		= "ecb(aes)",
+		.base.cra_driver_name	= "ecb-aes-geode",
+		.base.cra_priority	= 400,
+		.base.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
+					  CRYPTO_ALG_NEED_FALLBACK,
+		.base.cra_blocksize	= AES_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct geode_aes_tfm_ctx),
+		.base.cra_alignmask	= 15,
+		.base.cra_module	= THIS_MODULE,
+		.init			= geode_init_skcipher,
+		.exit			= geode_exit_skcipher,
+		.setkey			= geode_setkey_skcipher,
+		.encrypt		= geode_ecb_encrypt,
+		.decrypt		= geode_ecb_decrypt,
+		.min_keysize		= AES_MIN_KEY_SIZE,
+		.max_keysize		= AES_MAX_KEY_SIZE,
+	},
 };
 
 static void geode_aes_remove(struct pci_dev *dev)
 {
 	crypto_unregister_alg(&geode_alg);
-	crypto_unregister_alg(&geode_ecb_alg);
-	crypto_unregister_alg(&geode_cbc_alg);
+	crypto_unregister_skciphers(geode_skcipher_algs,
+				    ARRAY_SIZE(geode_skcipher_algs));
 
 	pci_iounmap(dev, _iobase);
 	_iobase = NULL;
@@ -547,20 +407,14 @@ static int geode_aes_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	if (ret)
 		goto eiomap;
 
-	ret = crypto_register_alg(&geode_ecb_alg);
+	ret = crypto_register_skciphers(geode_skcipher_algs,
+					ARRAY_SIZE(geode_skcipher_algs));
 	if (ret)
 		goto ealg;
 
-	ret = crypto_register_alg(&geode_cbc_alg);
-	if (ret)
-		goto eecb;
-
 	dev_notice(&dev->dev, "GEODE AES engine enabled.\n");
 	return 0;
 
- eecb:
-	crypto_unregister_alg(&geode_ecb_alg);
-
  ealg:
 	crypto_unregister_alg(&geode_alg);
 
diff --git a/drivers/crypto/geode-aes.h b/drivers/crypto/geode-aes.h
index f8a86898ac22..6d0a0cdc7647 100644
--- a/drivers/crypto/geode-aes.h
+++ b/drivers/crypto/geode-aes.h
@@ -46,21 +46,10 @@
 
 #define AES_OP_TIMEOUT    0x50000
 
-struct geode_aes_op {
-
-	void *src;
-	void *dst;
-
-	u32 mode;
-	u32 dir;
-	u32 flags;
-	int len;
-
+struct geode_aes_tfm_ctx {
 	u8 key[AES_KEYSIZE_128];
-	u8 *iv;
-
 	union {
-		struct crypto_sync_skcipher *blk;
+		struct crypto_skcipher *skcipher;
 		struct crypto_cipher *cip;
 	} fallback;
 	u32 keylen;
diff --git a/drivers/crypto/hisilicon/sec/sec_algs.c b/drivers/crypto/hisilicon/sec/sec_algs.c
index 8c789b8671fc..9a98efc95333 100644
--- a/drivers/crypto/hisilicon/sec/sec_algs.c
+++ b/drivers/crypto/hisilicon/sec/sec_algs.c
@@ -157,7 +157,8 @@ static int sec_alloc_and_fill_hw_sgl(struct sec_hw_sgl **sec_sgl,
 				     dma_addr_t *psec_sgl,
 				     struct scatterlist *sgl,
 				     int count,
-				     struct sec_dev_info *info)
+				     struct sec_dev_info *info,
+				     gfp_t gfp)
 {
 	struct sec_hw_sgl *sgl_current = NULL;
 	struct sec_hw_sgl *sgl_next;
@@ -172,7 +173,7 @@ static int sec_alloc_and_fill_hw_sgl(struct sec_hw_sgl **sec_sgl,
 		sge_index = i % SEC_MAX_SGE_NUM;
 		if (sge_index == 0) {
 			sgl_next = dma_pool_zalloc(info->hw_sgl_pool,
-						   GFP_KERNEL, &sgl_next_dma);
+						   gfp, &sgl_next_dma);
 			if (!sgl_next) {
 				ret = -ENOMEM;
 				goto err_free_hw_sgls;
@@ -555,14 +556,14 @@ void sec_alg_callback(struct sec_bd_info *resp, void *shadow)
 }
 
 static int sec_alg_alloc_and_calc_split_sizes(int length, size_t **split_sizes,
-					      int *steps)
+					      int *steps, gfp_t gfp)
 {
 	size_t *sizes;
 	int i;
 
 	/* Split into suitable sized blocks */
 	*steps = roundup(length, SEC_REQ_LIMIT) / SEC_REQ_LIMIT;
-	sizes = kcalloc(*steps, sizeof(*sizes), GFP_KERNEL);
+	sizes = kcalloc(*steps, sizeof(*sizes), gfp);
 	if (!sizes)
 		return -ENOMEM;
 
@@ -578,7 +579,7 @@ static int sec_map_and_split_sg(struct scatterlist *sgl, size_t *split_sizes,
 				int steps, struct scatterlist ***splits,
 				int **splits_nents,
 				int sgl_len_in,
-				struct device *dev)
+				struct device *dev, gfp_t gfp)
 {
 	int ret, count;
 
@@ -586,12 +587,12 @@ static int sec_map_and_split_sg(struct scatterlist *sgl, size_t *split_sizes,
 	if (!count)
 		return -EINVAL;
 
-	*splits = kcalloc(steps, sizeof(struct scatterlist *), GFP_KERNEL);
+	*splits = kcalloc(steps, sizeof(struct scatterlist *), gfp);
 	if (!*splits) {
 		ret = -ENOMEM;
 		goto err_unmap_sg;
 	}
-	*splits_nents = kcalloc(steps, sizeof(int), GFP_KERNEL);
+	*splits_nents = kcalloc(steps, sizeof(int), gfp);
 	if (!*splits_nents) {
 		ret = -ENOMEM;
 		goto err_free_splits;
@@ -599,7 +600,7 @@ static int sec_map_and_split_sg(struct scatterlist *sgl, size_t *split_sizes,
 
 	/* output the scatter list before and after this */
 	ret = sg_split(sgl, count, 0, steps, split_sizes,
-		       *splits, *splits_nents, GFP_KERNEL);
+		       *splits, *splits_nents, gfp);
 	if (ret) {
 		ret = -ENOMEM;
 		goto err_free_splits_nents;
@@ -640,13 +641,13 @@ static struct sec_request_el
 			   int el_size, bool different_dest,
 			   struct scatterlist *sgl_in, int n_ents_in,
 			   struct scatterlist *sgl_out, int n_ents_out,
-			   struct sec_dev_info *info)
+			   struct sec_dev_info *info, gfp_t gfp)
 {
 	struct sec_request_el *el;
 	struct sec_bd_info *req;
 	int ret;
 
-	el = kzalloc(sizeof(*el), GFP_KERNEL);
+	el = kzalloc(sizeof(*el), gfp);
 	if (!el)
 		return ERR_PTR(-ENOMEM);
 	el->el_length = el_size;
@@ -678,7 +679,7 @@ static struct sec_request_el
 	el->sgl_in = sgl_in;
 
 	ret = sec_alloc_and_fill_hw_sgl(&el->in, &el->dma_in, el->sgl_in,
-					n_ents_in, info);
+					n_ents_in, info, gfp);
 	if (ret)
 		goto err_free_el;
 
@@ -689,7 +690,7 @@ static struct sec_request_el
 		el->sgl_out = sgl_out;
 		ret = sec_alloc_and_fill_hw_sgl(&el->out, &el->dma_out,
 						el->sgl_out,
-						n_ents_out, info);
+						n_ents_out, info, gfp);
 		if (ret)
 			goto err_free_hw_sgl_in;
 
@@ -730,6 +731,7 @@ static int sec_alg_skcipher_crypto(struct skcipher_request *skreq,
 	int *splits_out_nents = NULL;
 	struct sec_request_el *el, *temp;
 	bool split = skreq->src != skreq->dst;
+	gfp_t gfp = skreq->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL : GFP_ATOMIC;
 
 	mutex_init(&sec_req->lock);
 	sec_req->req_base = &skreq->base;
@@ -738,13 +740,13 @@ static int sec_alg_skcipher_crypto(struct skcipher_request *skreq,
 	sec_req->len_in = sg_nents(skreq->src);
 
 	ret = sec_alg_alloc_and_calc_split_sizes(skreq->cryptlen, &split_sizes,
-						 &steps);
+						 &steps, gfp);
 	if (ret)
 		return ret;
 	sec_req->num_elements = steps;
 	ret = sec_map_and_split_sg(skreq->src, split_sizes, steps, &splits_in,
 				   &splits_in_nents, sec_req->len_in,
-				   info->dev);
+				   info->dev, gfp);
 	if (ret)
 		goto err_free_split_sizes;
 
@@ -752,7 +754,7 @@ static int sec_alg_skcipher_crypto(struct skcipher_request *skreq,
 		sec_req->len_out = sg_nents(skreq->dst);
 		ret = sec_map_and_split_sg(skreq->dst, split_sizes, steps,
 					   &splits_out, &splits_out_nents,
-					   sec_req->len_out, info->dev);
+					   sec_req->len_out, info->dev, gfp);
 		if (ret)
 			goto err_unmap_in_sg;
 	}
@@ -785,7 +787,7 @@ static int sec_alg_skcipher_crypto(struct skcipher_request *skreq,
 					       splits_in[i], splits_in_nents[i],
 					       split ? splits_out[i] : NULL,
 					       split ? splits_out_nents[i] : 0,
-					       info);
+					       info, gfp);
 		if (IS_ERR(el)) {
 			ret = PTR_ERR(el);
 			goto err_free_elements;
diff --git a/drivers/crypto/mxs-dcp.c b/drivers/crypto/mxs-dcp.c
index bdc4c42d3ac8..c06e81802813 100644
--- a/drivers/crypto/mxs-dcp.c
+++ b/drivers/crypto/mxs-dcp.c
@@ -20,6 +20,7 @@
 #include <crypto/sha.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/skcipher.h>
+#include <crypto/scatterwalk.h>
 
 #define DCP_MAX_CHANS	4
 #define DCP_BUF_SZ	PAGE_SIZE
@@ -621,49 +622,46 @@ static int dcp_sha_req_to_buf(struct crypto_async_request *arq)
 	struct dcp_async_ctx *actx = crypto_ahash_ctx(tfm);
 	struct dcp_sha_req_ctx *rctx = ahash_request_ctx(req);
 	struct hash_alg_common *halg = crypto_hash_alg_common(tfm);
-	const int nents = sg_nents(req->src);
 
 	uint8_t *in_buf = sdcp->coh->sha_in_buf;
 	uint8_t *out_buf = sdcp->coh->sha_out_buf;
 
-	uint8_t *src_buf;
-
 	struct scatterlist *src;
 
-	unsigned int i, len, clen;
+	unsigned int i, len, clen, oft = 0;
 	int ret;
 
 	int fin = rctx->fini;
 	if (fin)
 		rctx->fini = 0;
 
-	for_each_sg(req->src, src, nents, i) {
-		src_buf = sg_virt(src);
-		len = sg_dma_len(src);
-
-		do {
-			if (actx->fill + len > DCP_BUF_SZ)
-				clen = DCP_BUF_SZ - actx->fill;
-			else
-				clen = len;
-
-			memcpy(in_buf + actx->fill, src_buf, clen);
-			len -= clen;
-			src_buf += clen;
-			actx->fill += clen;
+	src = req->src;
+	len = req->nbytes;
 
-			/*
-			 * If we filled the buffer and still have some
-			 * more data, submit the buffer.
-			 */
-			if (len && actx->fill == DCP_BUF_SZ) {
-				ret = mxs_dcp_run_sha(req);
-				if (ret)
-					return ret;
-				actx->fill = 0;
-				rctx->init = 0;
-			}
-		} while (len);
+	while (len) {
+		if (actx->fill + len > DCP_BUF_SZ)
+			clen = DCP_BUF_SZ - actx->fill;
+		else
+			clen = len;
+
+		scatterwalk_map_and_copy(in_buf + actx->fill, src, oft, clen,
+					 0);
+
+		len -= clen;
+		oft += clen;
+		actx->fill += clen;
+
+		/*
+		 * If we filled the buffer and still have some
+		 * more data, submit the buffer.
+		 */
+		if (len && actx->fill == DCP_BUF_SZ) {
+			ret = mxs_dcp_run_sha(req);
+			if (ret)
+				return ret;
+			actx->fill = 0;
+			rctx->init = 0;
+		}
 	}
 
 	if (fin) {
diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c
index e8e2907bd9f4..107cf3c579ce 100644
--- a/drivers/crypto/omap-sham.c
+++ b/drivers/crypto/omap-sham.c
@@ -165,8 +165,6 @@ struct omap_sham_hmac_ctx {
 };
 
 struct omap_sham_ctx {
-	struct omap_sham_dev	*dd;
-
 	unsigned long		flags;
 
 	/* fallback stuff */
@@ -918,27 +916,35 @@ static int omap_sham_update_dma_stop(struct omap_sham_dev *dd)
 	return 0;
 }
 
+struct omap_sham_dev *omap_sham_find_dev(struct omap_sham_reqctx *ctx)
+{
+	struct omap_sham_dev *dd;
+
+	if (ctx->dd)
+		return ctx->dd;
+
+	spin_lock_bh(&sham.lock);
+	dd = list_first_entry(&sham.dev_list, struct omap_sham_dev, list);
+	list_move_tail(&dd->list, &sham.dev_list);
+	ctx->dd = dd;
+	spin_unlock_bh(&sham.lock);
+
+	return dd;
+}
+
 static int omap_sham_init(struct ahash_request *req)
 {
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
 	struct omap_sham_ctx *tctx = crypto_ahash_ctx(tfm);
 	struct omap_sham_reqctx *ctx = ahash_request_ctx(req);
-	struct omap_sham_dev *dd = NULL, *tmp;
+	struct omap_sham_dev *dd;
 	int bs = 0;
 
-	spin_lock_bh(&sham.lock);
-	if (!tctx->dd) {
-		list_for_each_entry(tmp, &sham.dev_list, list) {
-			dd = tmp;
-			break;
-		}
-		tctx->dd = dd;
-	} else {
-		dd = tctx->dd;
-	}
-	spin_unlock_bh(&sham.lock);
+	ctx->dd = NULL;
 
-	ctx->dd = dd;
+	dd = omap_sham_find_dev(ctx);
+	if (!dd)
+		return -ENODEV;
 
 	ctx->flags = 0;
 
@@ -1187,8 +1193,7 @@ err1:
 static int omap_sham_enqueue(struct ahash_request *req, unsigned int op)
 {
 	struct omap_sham_reqctx *ctx = ahash_request_ctx(req);
-	struct omap_sham_ctx *tctx = crypto_tfm_ctx(req->base.tfm);
-	struct omap_sham_dev *dd = tctx->dd;
+	struct omap_sham_dev *dd = ctx->dd;
 
 	ctx->op = op;
 
@@ -1198,7 +1203,7 @@ static int omap_sham_enqueue(struct ahash_request *req, unsigned int op)
 static int omap_sham_update(struct ahash_request *req)
 {
 	struct omap_sham_reqctx *ctx = ahash_request_ctx(req);
-	struct omap_sham_dev *dd = ctx->dd;
+	struct omap_sham_dev *dd = omap_sham_find_dev(ctx);
 
 	if (!req->nbytes)
 		return 0;
@@ -1302,21 +1307,8 @@ static int omap_sham_setkey(struct crypto_ahash *tfm, const u8 *key,
 	struct omap_sham_hmac_ctx *bctx = tctx->base;
 	int bs = crypto_shash_blocksize(bctx->shash);
 	int ds = crypto_shash_digestsize(bctx->shash);
-	struct omap_sham_dev *dd = NULL, *tmp;
 	int err, i;
 
-	spin_lock_bh(&sham.lock);
-	if (!tctx->dd) {
-		list_for_each_entry(tmp, &sham.dev_list, list) {
-			dd = tmp;
-			break;
-		}
-		tctx->dd = dd;
-	} else {
-		dd = tctx->dd;
-	}
-	spin_unlock_bh(&sham.lock);
-
 	err = crypto_shash_setkey(tctx->fallback, key, keylen);
 	if (err)
 		return err;
@@ -1334,7 +1326,7 @@ static int omap_sham_setkey(struct crypto_ahash *tfm, const u8 *key,
 
 	memset(bctx->ipad + keylen, 0, bs - keylen);
 
-	if (!test_bit(FLAGS_AUTO_XOR, &dd->flags)) {
+	if (!test_bit(FLAGS_AUTO_XOR, &sham.flags)) {
 		memcpy(bctx->opad, bctx->ipad, bs);
 
 		for (i = 0; i < bs; i++) {
@@ -2137,6 +2129,7 @@ static int omap_sham_probe(struct platform_device *pdev)
 	}
 
 	dd->flags |= dd->pdata->flags;
+	sham.flags |= dd->pdata->flags;
 
 	pm_runtime_use_autosuspend(dev);
 	pm_runtime_set_autosuspend_delay(dev, DEFAULT_AUTOSUSPEND_DELAY);
@@ -2164,6 +2157,9 @@ static int omap_sham_probe(struct platform_device *pdev)
 	spin_unlock(&sham.lock);
 
 	for (i = 0; i < dd->pdata->algs_info_size; i++) {
+		if (dd->pdata->algs_info[i].registered)
+			break;
+
 		for (j = 0; j < dd->pdata->algs_info[i].size; j++) {
 			struct ahash_alg *alg;
 
@@ -2215,9 +2211,11 @@ static int omap_sham_remove(struct platform_device *pdev)
 	list_del(&dd->list);
 	spin_unlock(&sham.lock);
 	for (i = dd->pdata->algs_info_size - 1; i >= 0; i--)
-		for (j = dd->pdata->algs_info[i].registered - 1; j >= 0; j--)
+		for (j = dd->pdata->algs_info[i].registered - 1; j >= 0; j--) {
 			crypto_unregister_ahash(
 					&dd->pdata->algs_info[i].algs_list[j]);
+			dd->pdata->algs_info[i].registered--;
+		}
 	tasklet_kill(&dd->done_task);
 	pm_runtime_disable(&pdev->dev);
 
diff --git a/drivers/crypto/picoxcell_crypto.c b/drivers/crypto/picoxcell_crypto.c
index b985cb85c9bc..104eddfd800f 100644
--- a/drivers/crypto/picoxcell_crypto.c
+++ b/drivers/crypto/picoxcell_crypto.c
@@ -1621,6 +1621,11 @@ static const struct of_device_id spacc_of_id_table[] = {
 MODULE_DEVICE_TABLE(of, spacc_of_id_table);
 #endif /* CONFIG_OF */
 
+static void spacc_tasklet_kill(void *data)
+{
+	tasklet_kill(data);
+}
+
 static int spacc_probe(struct platform_device *pdev)
 {
 	int i, err, ret;
@@ -1664,6 +1669,14 @@ static int spacc_probe(struct platform_device *pdev)
 		return -ENXIO;
 	}
 
+	tasklet_init(&engine->complete, spacc_spacc_complete,
+		     (unsigned long)engine);
+
+	ret = devm_add_action(&pdev->dev, spacc_tasklet_kill,
+			      &engine->complete);
+	if (ret)
+		return ret;
+
 	if (devm_request_irq(&pdev->dev, irq->start, spacc_spacc_irq, 0,
 			     engine->name, engine)) {
 		dev_err(engine->dev, "failed to request IRQ\n");
@@ -1721,8 +1734,6 @@ static int spacc_probe(struct platform_device *pdev)
 	INIT_LIST_HEAD(&engine->completed);
 	INIT_LIST_HEAD(&engine->in_progress);
 	engine->in_flight = 0;
-	tasklet_init(&engine->complete, spacc_spacc_complete,
-		     (unsigned long)engine);
 
 	platform_set_drvdata(pdev, engine);
 
diff --git a/drivers/crypto/qat/qat_common/qat_uclo.c b/drivers/crypto/qat/qat_common/qat_uclo.c
index 6bd8f6a2a24f..aeb03081415c 100644
--- a/drivers/crypto/qat/qat_common/qat_uclo.c
+++ b/drivers/crypto/qat/qat_common/qat_uclo.c
@@ -332,13 +332,18 @@ static int qat_uclo_create_batch_init_list(struct icp_qat_fw_loader_handle
 	}
 	return 0;
 out_err:
+	/* Do not free the list head unless we allocated it. */
+	tail_old = tail_old->next;
+	if (flag) {
+		kfree(*init_tab_base);
+		*init_tab_base = NULL;
+	}
+
 	while (tail_old) {
 		mem_init = tail_old->next;
 		kfree(tail_old);
 		tail_old = mem_init;
 	}
-	if (flag)
-		kfree(*init_tab_base);
 	return -ENOMEM;
 }
 
diff --git a/drivers/crypto/stm32/stm32_crc32.c b/drivers/crypto/stm32/stm32_crc32.c
index 440c9f1bd006..5da7d4a8aad4 100644
--- a/drivers/crypto/stm32/stm32_crc32.c
+++ b/drivers/crypto/stm32/stm32_crc32.c
@@ -28,8 +28,10 @@
 
 /* Registers values */
 #define CRC_CR_RESET            BIT(0)
-#define CRC_CR_REVERSE          (BIT(7) | BIT(6) | BIT(5))
-#define CRC_INIT_DEFAULT        0xFFFFFFFF
+#define CRC_CR_REV_IN_WORD      (BIT(6) | BIT(5))
+#define CRC_CR_REV_IN_BYTE      BIT(5)
+#define CRC_CR_REV_OUT          BIT(7)
+#define CRC32C_INIT_DEFAULT     0xFFFFFFFF
 
 #define CRC_AUTOSUSPEND_DELAY	50
 
@@ -38,8 +40,6 @@ struct stm32_crc {
 	struct device    *dev;
 	void __iomem     *regs;
 	struct clk       *clk;
-	u8               pending_data[sizeof(u32)];
-	size_t           nb_pending_bytes;
 };
 
 struct stm32_crc_list {
@@ -59,14 +59,13 @@ struct stm32_crc_ctx {
 
 struct stm32_crc_desc_ctx {
 	u32    partial; /* crc32c: partial in first 4 bytes of that struct */
-	struct stm32_crc *crc;
 };
 
 static int stm32_crc32_cra_init(struct crypto_tfm *tfm)
 {
 	struct stm32_crc_ctx *mctx = crypto_tfm_ctx(tfm);
 
-	mctx->key = CRC_INIT_DEFAULT;
+	mctx->key = 0;
 	mctx->poly = CRC32_POLY_LE;
 	return 0;
 }
@@ -75,7 +74,7 @@ static int stm32_crc32c_cra_init(struct crypto_tfm *tfm)
 {
 	struct stm32_crc_ctx *mctx = crypto_tfm_ctx(tfm);
 
-	mctx->key = CRC_INIT_DEFAULT;
+	mctx->key = CRC32C_INIT_DEFAULT;
 	mctx->poly = CRC32C_POLY_LE;
 	return 0;
 }
@@ -94,32 +93,42 @@ static int stm32_crc_setkey(struct crypto_shash *tfm, const u8 *key,
 	return 0;
 }
 
+static struct stm32_crc *stm32_crc_get_next_crc(void)
+{
+	struct stm32_crc *crc;
+
+	spin_lock_bh(&crc_list.lock);
+	crc = list_first_entry(&crc_list.dev_list, struct stm32_crc, list);
+	if (crc)
+		list_move_tail(&crc->list, &crc_list.dev_list);
+	spin_unlock_bh(&crc_list.lock);
+
+	return crc;
+}
+
 static int stm32_crc_init(struct shash_desc *desc)
 {
 	struct stm32_crc_desc_ctx *ctx = shash_desc_ctx(desc);
 	struct stm32_crc_ctx *mctx = crypto_shash_ctx(desc->tfm);
 	struct stm32_crc *crc;
 
-	spin_lock_bh(&crc_list.lock);
-	list_for_each_entry(crc, &crc_list.dev_list, list) {
-		ctx->crc = crc;
-		break;
-	}
-	spin_unlock_bh(&crc_list.lock);
+	crc = stm32_crc_get_next_crc();
+	if (!crc)
+		return -ENODEV;
 
-	pm_runtime_get_sync(ctx->crc->dev);
+	pm_runtime_get_sync(crc->dev);
 
 	/* Reset, set key, poly and configure in bit reverse mode */
-	writel_relaxed(bitrev32(mctx->key), ctx->crc->regs + CRC_INIT);
-	writel_relaxed(bitrev32(mctx->poly), ctx->crc->regs + CRC_POL);
-	writel_relaxed(CRC_CR_RESET | CRC_CR_REVERSE, ctx->crc->regs + CRC_CR);
+	writel_relaxed(bitrev32(mctx->key), crc->regs + CRC_INIT);
+	writel_relaxed(bitrev32(mctx->poly), crc->regs + CRC_POL);
+	writel_relaxed(CRC_CR_RESET | CRC_CR_REV_IN_WORD | CRC_CR_REV_OUT,
+		       crc->regs + CRC_CR);
 
 	/* Store partial result */
-	ctx->partial = readl_relaxed(ctx->crc->regs + CRC_DR);
-	ctx->crc->nb_pending_bytes = 0;
+	ctx->partial = readl_relaxed(crc->regs + CRC_DR);
 
-	pm_runtime_mark_last_busy(ctx->crc->dev);
-	pm_runtime_put_autosuspend(ctx->crc->dev);
+	pm_runtime_mark_last_busy(crc->dev);
+	pm_runtime_put_autosuspend(crc->dev);
 
 	return 0;
 }
@@ -128,31 +137,49 @@ static int stm32_crc_update(struct shash_desc *desc, const u8 *d8,
 			    unsigned int length)
 {
 	struct stm32_crc_desc_ctx *ctx = shash_desc_ctx(desc);
-	struct stm32_crc *crc = ctx->crc;
-	u32 *d32;
-	unsigned int i;
+	struct stm32_crc_ctx *mctx = crypto_shash_ctx(desc->tfm);
+	struct stm32_crc *crc;
+
+	crc = stm32_crc_get_next_crc();
+	if (!crc)
+		return -ENODEV;
 
 	pm_runtime_get_sync(crc->dev);
 
-	if (unlikely(crc->nb_pending_bytes)) {
-		while (crc->nb_pending_bytes != sizeof(u32) && length) {
-			/* Fill in pending data */
-			crc->pending_data[crc->nb_pending_bytes++] = *(d8++);
+	/*
+	 * Restore previously calculated CRC for this context as init value
+	 * Restore polynomial configuration
+	 * Configure in register for word input data,
+	 * Configure out register in reversed bit mode data.
+	 */
+	writel_relaxed(bitrev32(ctx->partial), crc->regs + CRC_INIT);
+	writel_relaxed(bitrev32(mctx->poly), crc->regs + CRC_POL);
+	writel_relaxed(CRC_CR_RESET | CRC_CR_REV_IN_WORD | CRC_CR_REV_OUT,
+		       crc->regs + CRC_CR);
+
+	if (d8 != PTR_ALIGN(d8, sizeof(u32))) {
+		/* Configure for byte data */
+		writel_relaxed(CRC_CR_REV_IN_BYTE | CRC_CR_REV_OUT,
+			       crc->regs + CRC_CR);
+		while (d8 != PTR_ALIGN(d8, sizeof(u32)) && length) {
+			writeb_relaxed(*d8++, crc->regs + CRC_DR);
 			length--;
 		}
-
-		if (crc->nb_pending_bytes == sizeof(u32)) {
-			/* Process completed pending data */
-			writel_relaxed(*(u32 *)crc->pending_data,
-				       crc->regs + CRC_DR);
-			crc->nb_pending_bytes = 0;
-		}
+		/* Configure for word data */
+		writel_relaxed(CRC_CR_REV_IN_WORD | CRC_CR_REV_OUT,
+			       crc->regs + CRC_CR);
 	}
 
-	d32 = (u32 *)d8;
-	for (i = 0; i < length >> 2; i++)
-		/* Process 32 bits data */
-		writel_relaxed(*(d32++), crc->regs + CRC_DR);
+	for (; length >= sizeof(u32); d8 += sizeof(u32), length -= sizeof(u32))
+		writel_relaxed(*((u32 *)d8), crc->regs + CRC_DR);
+
+	if (length) {
+		/* Configure for byte data */
+		writel_relaxed(CRC_CR_REV_IN_BYTE | CRC_CR_REV_OUT,
+			       crc->regs + CRC_CR);
+		while (length--)
+			writeb_relaxed(*d8++, crc->regs + CRC_DR);
+	}
 
 	/* Store partial result */
 	ctx->partial = readl_relaxed(crc->regs + CRC_DR);
@@ -160,22 +187,6 @@ static int stm32_crc_update(struct shash_desc *desc, const u8 *d8,
 	pm_runtime_mark_last_busy(crc->dev);
 	pm_runtime_put_autosuspend(crc->dev);
 
-	/* Check for pending data (non 32 bits) */
-	length &= 3;
-	if (likely(!length))
-		return 0;
-
-	if ((crc->nb_pending_bytes + length) >= sizeof(u32)) {
-		/* Shall not happen */
-		dev_err(crc->dev, "Pending data overflow\n");
-		return -EINVAL;
-	}
-
-	d8 = (const u8 *)d32;
-	for (i = 0; i < length; i++)
-		/* Store pending data */
-		crc->pending_data[crc->nb_pending_bytes++] = *(d8++);
-
 	return 0;
 }
 
@@ -204,6 +215,8 @@ static int stm32_crc_digest(struct shash_desc *desc, const u8 *data,
 	return stm32_crc_init(desc) ?: stm32_crc_finup(desc, data, length, out);
 }
 
+static unsigned int refcnt;
+static DEFINE_MUTEX(refcnt_lock);
 static struct shash_alg algs[] = {
 	/* CRC-32 */
 	{
@@ -296,12 +309,18 @@ static int stm32_crc_probe(struct platform_device *pdev)
 	list_add(&crc->list, &crc_list.dev_list);
 	spin_unlock(&crc_list.lock);
 
-	ret = crypto_register_shashes(algs, ARRAY_SIZE(algs));
-	if (ret) {
-		dev_err(dev, "Failed to register\n");
-		clk_disable_unprepare(crc->clk);
-		return ret;
+	mutex_lock(&refcnt_lock);
+	if (!refcnt) {
+		ret = crypto_register_shashes(algs, ARRAY_SIZE(algs));
+		if (ret) {
+			mutex_unlock(&refcnt_lock);
+			dev_err(dev, "Failed to register\n");
+			clk_disable_unprepare(crc->clk);
+			return ret;
+		}
 	}
+	refcnt++;
+	mutex_unlock(&refcnt_lock);
 
 	dev_info(dev, "Initialized\n");
 
@@ -322,7 +341,10 @@ static int stm32_crc_remove(struct platform_device *pdev)
 	list_del(&crc->list);
 	spin_unlock(&crc_list.lock);
 
-	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+	mutex_lock(&refcnt_lock);
+	if (!--refcnt)
+		crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+	mutex_unlock(&refcnt_lock);
 
 	pm_runtime_disable(crc->dev);
 	pm_runtime_put_noidle(crc->dev);
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c b/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c
index ef674fefb0b5..e74ba066d002 100644
--- a/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c
+++ b/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c
@@ -12,7 +12,7 @@
  */
 #include "sun4i-ss.h"
 
-static int sun4i_ss_opti_poll(struct skcipher_request *areq)
+static int noinline_for_stack sun4i_ss_opti_poll(struct skcipher_request *areq)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(areq);
 	struct sun4i_tfm_ctx *op = crypto_skcipher_ctx(tfm);
@@ -116,6 +116,29 @@ release_ss:
 	return err;
 }
 
+
+static int noinline_for_stack sun4i_ss_cipher_poll_fallback(struct skcipher_request *areq)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(areq);
+	struct sun4i_tfm_ctx *op = crypto_skcipher_ctx(tfm);
+	struct sun4i_cipher_req_ctx *ctx = skcipher_request_ctx(areq);
+	SYNC_SKCIPHER_REQUEST_ON_STACK(subreq, op->fallback_tfm);
+	int err;
+
+	skcipher_request_set_sync_tfm(subreq, op->fallback_tfm);
+	skcipher_request_set_callback(subreq, areq->base.flags, NULL,
+				      NULL);
+	skcipher_request_set_crypt(subreq, areq->src, areq->dst,
+				   areq->cryptlen, areq->iv);
+	if (ctx->mode & SS_DECRYPTION)
+		err = crypto_skcipher_decrypt(subreq);
+	else
+		err = crypto_skcipher_encrypt(subreq);
+	skcipher_request_zero(subreq);
+
+	return err;
+}
+
 /* Generic function that support SG with size not multiple of 4 */
 static int sun4i_ss_cipher_poll(struct skcipher_request *areq)
 {
@@ -142,8 +165,6 @@ static int sun4i_ss_cipher_poll(struct skcipher_request *areq)
 	unsigned int todo;
 	struct sg_mapping_iter mi, mo;
 	unsigned int oi, oo;	/* offset for in and out */
-	char buf[4 * SS_RX_MAX];/* buffer for linearize SG src */
-	char bufo[4 * SS_TX_MAX]; /* buffer for linearize SG dst */
 	unsigned int ob = 0;	/* offset in buf */
 	unsigned int obo = 0;	/* offset in bufo*/
 	unsigned int obl = 0;	/* length of data in bufo */
@@ -180,20 +201,8 @@ static int sun4i_ss_cipher_poll(struct skcipher_request *areq)
 	if (no_chunk == 1 && !need_fallback)
 		return sun4i_ss_opti_poll(areq);
 
-	if (need_fallback) {
-		SYNC_SKCIPHER_REQUEST_ON_STACK(subreq, op->fallback_tfm);
-		skcipher_request_set_sync_tfm(subreq, op->fallback_tfm);
-		skcipher_request_set_callback(subreq, areq->base.flags, NULL,
-					      NULL);
-		skcipher_request_set_crypt(subreq, areq->src, areq->dst,
-					   areq->cryptlen, areq->iv);
-		if (ctx->mode & SS_DECRYPTION)
-			err = crypto_skcipher_decrypt(subreq);
-		else
-			err = crypto_skcipher_encrypt(subreq);
-		skcipher_request_zero(subreq);
-		return err;
-	}
+	if (need_fallback)
+		return sun4i_ss_cipher_poll_fallback(areq);
 
 	spin_lock_irqsave(&ss->slock, flags);
 
@@ -226,6 +235,8 @@ static int sun4i_ss_cipher_poll(struct skcipher_request *areq)
 
 	while (oleft) {
 		if (ileft) {
+			char buf[4 * SS_RX_MAX];/* buffer for linearize SG src */
+
 			/*
 			 * todo is the number of consecutive 4byte word that we
 			 * can read from current SG
@@ -286,6 +297,8 @@ static int sun4i_ss_cipher_poll(struct skcipher_request *areq)
 				oo = 0;
 			}
 		} else {
+			char bufo[4 * SS_TX_MAX]; /* buffer for linearize SG dst */
+
 			/*
 			 * read obl bytes in bufo, we read at maximum for
 			 * emptying the device
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-hash.c b/drivers/crypto/sunxi-ss/sun4i-ss-hash.c
index 4c0998406790..a200eadc691b 100644
--- a/drivers/crypto/sunxi-ss/sun4i-ss-hash.c
+++ b/drivers/crypto/sunxi-ss/sun4i-ss-hash.c
@@ -175,7 +175,7 @@ static int sun4i_hash(struct ahash_request *areq)
 	 */
 	unsigned int i = 0, end, fill, min_fill, nwait, nbw = 0, j = 0, todo;
 	unsigned int in_i = 0;
-	u32 spaces, rx_cnt = SS_RX_DEFAULT, bf[32] = {0}, wb = 0, v, ivmode = 0;
+	u32 spaces, rx_cnt = SS_RX_DEFAULT, bf[32] = {0}, v, ivmode = 0;
 	struct sun4i_req_ctx *op = ahash_request_ctx(areq);
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq);
 	struct sun4i_tfm_ctx *tfmctx = crypto_ahash_ctx(tfm);
@@ -184,6 +184,7 @@ static int sun4i_hash(struct ahash_request *areq)
 	struct sg_mapping_iter mi;
 	int in_r, err = 0;
 	size_t copied = 0;
+	__le32 wb = 0;
 
 	dev_dbg(ss->dev, "%s %s bc=%llu len=%u mode=%x wl=%u h0=%0x",
 		__func__, crypto_tfm_alg_name(areq->base.tfm),
@@ -395,7 +396,7 @@ hash_final:
 
 		nbw = op->len - 4 * nwait;
 		if (nbw) {
-			wb = *(u32 *)(op->buf + nwait * 4);
+			wb = cpu_to_le32(*(u32 *)(op->buf + nwait * 4));
 			wb &= GENMASK((nbw * 8) - 1, 0);
 
 			op->byte_count += nbw;
@@ -404,7 +405,7 @@ hash_final:
 
 	/* write the remaining bytes of the nbw buffer */
 	wb |= ((1 << 7) << (nbw * 8));
-	bf[j++] = wb;
+	bf[j++] = le32_to_cpu(wb);
 
 	/*
 	 * number of space to pad to obtain 64o minus 8(size) minus 4 (final 1)
@@ -423,13 +424,13 @@ hash_final:
 
 	/* write the length of data */
 	if (op->mode == SS_OP_SHA1) {
-		__be64 bits = cpu_to_be64(op->byte_count << 3);
-		bf[j++] = lower_32_bits(bits);
-		bf[j++] = upper_32_bits(bits);
+		__be64 *bits = (__be64 *)&bf[j];
+		*bits = cpu_to_be64(op->byte_count << 3);
+		j += 2;
 	} else {
-		__le64 bits = op->byte_count << 3;
-		bf[j++] = lower_32_bits(bits);
-		bf[j++] = upper_32_bits(bits);
+		__le64 *bits = (__le64 *)&bf[j];
+		*bits = cpu_to_le64(op->byte_count << 3);
+		j += 2;
 	}
 	writesl(ss->base + SS_RXFIFO, bf, j);
 
@@ -471,7 +472,7 @@ hash_final:
 		}
 	} else {
 		for (i = 0; i < 4; i++) {
-			v = readl(ss->base + SS_MD0 + i * 4);
+			v = cpu_to_le32(readl(ss->base + SS_MD0 + i * 4));
 			memcpy(areq->result + i * 4, &v, 4);
 		}
 	}
diff --git a/drivers/crypto/virtio/virtio_crypto_algs.c b/drivers/crypto/virtio/virtio_crypto_algs.c
index 963f16a6f9cf..7fbf82c0cce3 100644
--- a/drivers/crypto/virtio/virtio_crypto_algs.c
+++ b/drivers/crypto/virtio/virtio_crypto_algs.c
@@ -355,13 +355,18 @@ __virtio_crypto_ablkcipher_do_req(struct virtio_crypto_sym_request *vc_sym_req,
 	int err;
 	unsigned long flags;
 	struct scatterlist outhdr, iv_sg, status_sg, **sgs;
-	int i;
 	u64 dst_len;
 	unsigned int num_out = 0, num_in = 0;
 	int sg_total;
 	uint8_t *iv;
+	struct scatterlist *sg;
 
 	src_nents = sg_nents_for_len(req->src, req->nbytes);
+	if (src_nents < 0) {
+		pr_err("Invalid number of src SG.\n");
+		return src_nents;
+	}
+
 	dst_nents = sg_nents(req->dst);
 
 	pr_debug("virtio_crypto: Number of sgs (src_nents: %d, dst_nents: %d)\n",
@@ -437,17 +442,22 @@ __virtio_crypto_ablkcipher_do_req(struct virtio_crypto_sym_request *vc_sym_req,
 		goto free;
 	}
 	memcpy(iv, req->info, ivsize);
+	if (!vc_sym_req->encrypt)
+		scatterwalk_map_and_copy(req->info, req->src,
+					 req->nbytes - AES_BLOCK_SIZE,
+					 AES_BLOCK_SIZE, 0);
+
 	sg_init_one(&iv_sg, iv, ivsize);
 	sgs[num_out++] = &iv_sg;
 	vc_sym_req->iv = iv;
 
 	/* Source data */
-	for (i = 0; i < src_nents; i++)
-		sgs[num_out++] = &req->src[i];
+	for (sg = req->src; src_nents; sg = sg_next(sg), src_nents--)
+		sgs[num_out++] = sg;
 
 	/* Destination data */
-	for (i = 0; i < dst_nents; i++)
-		sgs[num_out + num_in++] = &req->dst[i];
+	for (sg = req->dst; sg; sg = sg_next(sg))
+		sgs[num_out + num_in++] = sg;
 
 	/* Status */
 	sg_init_one(&status_sg, &vc_req->status, sizeof(vc_req->status));
@@ -573,10 +583,15 @@ static void virtio_crypto_ablkcipher_finalize_req(
 	struct ablkcipher_request *req,
 	int err)
 {
-	crypto_finalize_ablkcipher_request(vc_sym_req->base.dataq->engine,
-					   req, err);
+	if (vc_sym_req->encrypt)
+		scatterwalk_map_and_copy(req->info, req->dst,
+					 req->nbytes - AES_BLOCK_SIZE,
+					 AES_BLOCK_SIZE, 0);
 	kzfree(vc_sym_req->iv);
 	virtcrypto_clear_request(&vc_sym_req->base);
+
+	crypto_finalize_ablkcipher_request(vc_sym_req->base.dataq->engine,
+					   req, err);
 }
 
 static struct virtio_crypto_algo virtio_crypto_algs[] = { {
diff --git a/drivers/devfreq/Kconfig b/drivers/devfreq/Kconfig
index ba98a4e3ad33..a2549db38387 100644
--- a/drivers/devfreq/Kconfig
+++ b/drivers/devfreq/Kconfig
@@ -104,7 +104,8 @@ config ARM_TEGRA_DEVFREQ
 
 config ARM_RK3399_DMC_DEVFREQ
 	tristate "ARM RK3399 DMC DEVFREQ Driver"
-	depends on ARCH_ROCKCHIP
+	depends on (ARCH_ROCKCHIP && HAVE_ARM_SMCCC) || \
+		(COMPILE_TEST && HAVE_ARM_SMCCC)
 	select DEVFREQ_EVENT_ROCKCHIP_DFI
 	select DEVFREQ_GOV_SIMPLE_ONDEMAND
 	select PM_DEVFREQ_EVENT
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index a3f0955af0f6..3b04f4c86a4c 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -551,26 +551,30 @@ static int devfreq_notifier_call(struct notifier_block *nb, unsigned long type,
 				 void *devp)
 {
 	struct devfreq *devfreq = container_of(nb, struct devfreq, nb);
-	int ret;
+	int err = -EINVAL;
 
 	mutex_lock(&devfreq->lock);
 
 	devfreq->scaling_min_freq = find_available_min_freq(devfreq);
-	if (!devfreq->scaling_min_freq) {
-		mutex_unlock(&devfreq->lock);
-		return -EINVAL;
-	}
+	if (!devfreq->scaling_min_freq)
+		goto out;
 
 	devfreq->scaling_max_freq = find_available_max_freq(devfreq);
 	if (!devfreq->scaling_max_freq) {
-		mutex_unlock(&devfreq->lock);
-		return -EINVAL;
+		devfreq->scaling_max_freq = ULONG_MAX;
+		goto out;
 	}
 
-	ret = update_devfreq(devfreq);
+	err = update_devfreq(devfreq);
+
+out:
 	mutex_unlock(&devfreq->lock);
+	if (err)
+		dev_err(devfreq->dev.parent,
+			"failed to update frequency from OPP notifier (%d)\n",
+			err);
 
-	return ret;
+	return NOTIFY_OK;
 }
 
 /**
@@ -584,11 +588,6 @@ static void devfreq_dev_release(struct device *dev)
 	struct devfreq *devfreq = to_devfreq(dev);
 
 	mutex_lock(&devfreq_list_lock);
-	if (IS_ERR(find_device_devfreq(devfreq->dev.parent))) {
-		mutex_unlock(&devfreq_list_lock);
-		dev_warn(&devfreq->dev, "releasing devfreq which doesn't exist\n");
-		return;
-	}
 	list_del(&devfreq->node);
 	mutex_unlock(&devfreq_list_lock);
 
@@ -614,7 +613,6 @@ struct devfreq *devfreq_add_device(struct device *dev,
 {
 	struct devfreq *devfreq;
 	struct devfreq_governor *governor;
-	static atomic_t devfreq_no = ATOMIC_INIT(-1);
 	int err = 0;
 
 	if (!dev || !profile || !governor_name) {
@@ -643,6 +641,7 @@ struct devfreq *devfreq_add_device(struct device *dev,
 	devfreq->dev.parent = dev;
 	devfreq->dev.class = devfreq_class;
 	devfreq->dev.release = devfreq_dev_release;
+	INIT_LIST_HEAD(&devfreq->node);
 	devfreq->profile = profile;
 	strncpy(devfreq->governor_name, governor_name, DEVFREQ_NAME_LEN);
 	devfreq->previous_freq = profile->initial_freq;
@@ -677,8 +676,7 @@ struct devfreq *devfreq_add_device(struct device *dev,
 	devfreq->suspend_freq = dev_pm_opp_get_suspend_opp_freq(dev);
 	atomic_set(&devfreq->suspend_count, 0);
 
-	dev_set_name(&devfreq->dev, "devfreq%d",
-				atomic_inc_return(&devfreq_no));
+	dev_set_name(&devfreq->dev, "%s", dev_name(dev));
 	err = device_register(&devfreq->dev);
 	if (err) {
 		mutex_unlock(&devfreq->lock);
@@ -904,7 +902,9 @@ int devfreq_suspend_device(struct devfreq *devfreq)
 	}
 
 	if (devfreq->suspend_freq) {
+		mutex_lock(&devfreq->lock);
 		ret = devfreq_set_target(devfreq, devfreq->suspend_freq, 0);
+		mutex_unlock(&devfreq->lock);
 		if (ret)
 			return ret;
 	}
@@ -932,7 +932,9 @@ int devfreq_resume_device(struct devfreq *devfreq)
 		return 0;
 
 	if (devfreq->resume_freq) {
+		mutex_lock(&devfreq->lock);
 		ret = devfreq_set_target(devfreq, devfreq->resume_freq, 0);
+		mutex_unlock(&devfreq->lock);
 		if (ret)
 			return ret;
 	}
@@ -1112,6 +1114,14 @@ err_out:
 }
 EXPORT_SYMBOL(devfreq_remove_governor);
 
+static ssize_t name_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	struct devfreq *devfreq = to_devfreq(dev);
+	return sprintf(buf, "%s\n", dev_name(devfreq->dev.parent));
+}
+static DEVICE_ATTR_RO(name);
+
 static ssize_t governor_show(struct device *dev,
 			     struct device_attribute *attr, char *buf)
 {
@@ -1196,7 +1206,7 @@ static ssize_t available_governors_show(struct device *d,
 	 * The devfreq with immutable governor (e.g., passive) shows
 	 * only own governor.
 	 */
-	if (df->governor->immutable) {
+	if (df->governor && df->governor->immutable) {
 		count = scnprintf(&buf[count], DEVFREQ_NAME_LEN,
 				  "%s ", df->governor_name);
 	/*
@@ -1440,6 +1450,7 @@ static ssize_t trans_stat_show(struct device *dev,
 static DEVICE_ATTR_RO(trans_stat);
 
 static struct attribute *devfreq_attrs[] = {
+	&dev_attr_name.attr,
 	&dev_attr_governor.attr,
 	&dev_attr_available_governors.attr,
 	&dev_attr_cur_freq.attr,
diff --git a/drivers/devfreq/event/Kconfig b/drivers/devfreq/event/Kconfig
index cef2cf5347ca..a53e0a6ffdfe 100644
--- a/drivers/devfreq/event/Kconfig
+++ b/drivers/devfreq/event/Kconfig
@@ -34,7 +34,7 @@ config DEVFREQ_EVENT_EXYNOS_PPMU
 
 config DEVFREQ_EVENT_ROCKCHIP_DFI
 	tristate "ROCKCHIP DFI DEVFREQ event Driver"
-	depends on ARCH_ROCKCHIP
+	depends on ARCH_ROCKCHIP || COMPILE_TEST
 	help
 	  This add the devfreq-event driver for Rockchip SoC. It provides DFI
 	  (DDR Monitor Module) driver to count ddr load.
diff --git a/drivers/dma-buf/dma-fence-chain.c b/drivers/dma-buf/dma-fence-chain.c
index b5089f64be2a..44a741677d25 100644
--- a/drivers/dma-buf/dma-fence-chain.c
+++ b/drivers/dma-buf/dma-fence-chain.c
@@ -178,8 +178,30 @@ static bool dma_fence_chain_signaled(struct dma_fence *fence)
 static void dma_fence_chain_release(struct dma_fence *fence)
 {
 	struct dma_fence_chain *chain = to_dma_fence_chain(fence);
+	struct dma_fence *prev;
+
+	/* Manually unlink the chain as much as possible to avoid recursion
+	 * and potential stack overflow.
+	 */
+	while ((prev = rcu_dereference_protected(chain->prev, true))) {
+		struct dma_fence_chain *prev_chain;
+
+		if (kref_read(&prev->refcount) > 1)
+		       break;
+
+		prev_chain = to_dma_fence_chain(prev);
+		if (!prev_chain)
+			break;
+
+		/* No need for atomic operations since we hold the last
+		 * reference to prev_chain.
+		 */
+		chain->prev = prev_chain->prev;
+		RCU_INIT_POINTER(prev_chain->prev, NULL);
+		dma_fence_put(prev);
+	}
+	dma_fence_put(prev);
 
-	dma_fence_put(rcu_dereference_protected(chain->prev, true));
 	dma_fence_put(chain->fence);
 	dma_fence_free(fence);
 }
diff --git a/drivers/dma/coh901318.c b/drivers/dma/coh901318.c
index 547786ac342b..8c390736b05d 100644
--- a/drivers/dma/coh901318.c
+++ b/drivers/dma/coh901318.c
@@ -1949,8 +1949,6 @@ static void dma_tc_handle(struct coh901318_chan *cohc)
 		return;
 	}
 
-	spin_lock(&cohc->lock);
-
 	/*
 	 * When we reach this point, at least one queue item
 	 * should have been moved over from cohc->queue to
@@ -1971,8 +1969,6 @@ static void dma_tc_handle(struct coh901318_chan *cohc)
 	if (coh901318_queue_start(cohc) == NULL)
 		cohc->busy = 0;
 
-	spin_unlock(&cohc->lock);
-
 	/*
 	 * This tasklet will remove items from cohc->active
 	 * and thus terminates them.
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 58cbf9fd5a46..dd22dbd0c4ea 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -179,7 +179,7 @@ __dma_device_satisfies_mask(struct dma_device *device,
 
 static struct module *dma_chan_to_owner(struct dma_chan *chan)
 {
-	return chan->device->dev->driver->owner;
+	return chan->device->owner;
 }
 
 /**
@@ -913,6 +913,8 @@ int dma_async_device_register(struct dma_device *device)
 		return -EIO;
 	}
 
+	device->owner = device->dev->driver->owner;
+
 	if (dma_has_cap(DMA_MEMCPY, device->cap_mask) && !device->device_prep_dma_memcpy) {
 		dev_err(device->dev,
 			"Device claims capability %s, but op is not defined\n",
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index d0ad46e916a6..dd1c65e61406 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -235,7 +235,7 @@ static bool is_threaded_test_run(struct dmatest_info *info)
 		struct dmatest_thread *thread;
 
 		list_for_each_entry(thread, &dtc->threads, node) {
-			if (!thread->done)
+			if (!thread->done && !thread->pending)
 				return true;
 		}
 	}
@@ -654,8 +654,8 @@ static int dmatest_func(void *data)
 	flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT;
 
 	ktime = ktime_get();
-	while (!kthread_should_stop()
-	       && !(params->iterations && total_tests >= params->iterations)) {
+	while (!(kthread_should_stop() ||
+	       (params->iterations && total_tests >= params->iterations))) {
 		struct dma_async_tx_descriptor *tx = NULL;
 		struct dmaengine_unmap_data *um;
 		dma_addr_t *dsts;
@@ -1145,10 +1145,13 @@ static int dmatest_run_set(const char *val, const struct kernel_param *kp)
 		mutex_unlock(&info->lock);
 		return ret;
 	} else if (dmatest_run) {
-		if (is_threaded_test_pending(info))
-			start_threaded_tests(info);
-		else
-			pr_info("Could not start test, no channels configured\n");
+		if (!is_threaded_test_pending(info)) {
+			pr_info("No channels configured, continue with any\n");
+			if (!is_threaded_test_run(info))
+				stop_threaded_test(info);
+			add_threaded_test(info);
+		}
+		start_threaded_tests(info);
 	} else {
 		stop_threaded_test(info);
 	}
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index 21cb2a58dbd2..a1b56f52db2f 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -118,16 +118,11 @@ static void dwc_initialize(struct dw_dma_chan *dwc)
 {
 	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
 
-	if (test_bit(DW_DMA_IS_INITIALIZED, &dwc->flags))
-		return;
-
 	dw->initialize_chan(dwc);
 
 	/* Enable interrupts */
 	channel_set_bit(dw, MASK.XFER, dwc->mask);
 	channel_set_bit(dw, MASK.ERROR, dwc->mask);
-
-	set_bit(DW_DMA_IS_INITIALIZED, &dwc->flags);
 }
 
 /*----------------------------------------------------------------------*/
@@ -954,8 +949,6 @@ static void dwc_issue_pending(struct dma_chan *chan)
 
 void do_dw_dma_off(struct dw_dma *dw)
 {
-	unsigned int i;
-
 	dma_writel(dw, CFG, 0);
 
 	channel_clear_bit(dw, MASK.XFER, dw->all_chan_mask);
@@ -966,9 +959,6 @@ void do_dw_dma_off(struct dw_dma *dw)
 
 	while (dma_readl(dw, CFG) & DW_CFG_DMA_EN)
 		cpu_relax();
-
-	for (i = 0; i < dw->dma.chancnt; i++)
-		clear_bit(DW_DMA_IS_INITIALIZED, &dw->chan[i].flags);
 }
 
 void do_dw_dma_on(struct dw_dma *dw)
@@ -1032,8 +1022,6 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
 	/* Clear custom channel configuration */
 	memset(&dwc->dws, 0, sizeof(struct dw_dma_slave));
 
-	clear_bit(DW_DMA_IS_INITIALIZED, &dwc->flags);
-
 	/* Disable interrupts */
 	channel_clear_bit(dw, MASK.XFER, dwc->mask);
 	channel_clear_bit(dw, MASK.BLOCK, dwc->mask);
diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c
index 680b2a00a953..c459c8eb96aa 100644
--- a/drivers/dma/fsl-edma-common.c
+++ b/drivers/dma/fsl-edma-common.c
@@ -320,26 +320,28 @@ static void fsl_edma_set_tcd_regs(struct fsl_edma_chan *fsl_chan,
 	/*
 	 * TCD parameters are stored in struct fsl_edma_hw_tcd in little
 	 * endian format. However, we need to load the TCD registers in
-	 * big- or little-endian obeying the eDMA engine model endian.
+	 * big- or little-endian obeying the eDMA engine model endian,
+	 * and this is performed from specific edma_write functions
 	 */
 	edma_writew(edma, 0,  &regs->tcd[ch].csr);
-	edma_writel(edma, le32_to_cpu(tcd->saddr), &regs->tcd[ch].saddr);
-	edma_writel(edma, le32_to_cpu(tcd->daddr), &regs->tcd[ch].daddr);
 
-	edma_writew(edma, le16_to_cpu(tcd->attr), &regs->tcd[ch].attr);
-	edma_writew(edma, le16_to_cpu(tcd->soff), &regs->tcd[ch].soff);
+	edma_writel(edma, (s32)tcd->saddr, &regs->tcd[ch].saddr);
+	edma_writel(edma, (s32)tcd->daddr, &regs->tcd[ch].daddr);
 
-	edma_writel(edma, le32_to_cpu(tcd->nbytes), &regs->tcd[ch].nbytes);
-	edma_writel(edma, le32_to_cpu(tcd->slast), &regs->tcd[ch].slast);
+	edma_writew(edma, (s16)tcd->attr, &regs->tcd[ch].attr);
+	edma_writew(edma, tcd->soff, &regs->tcd[ch].soff);
 
-	edma_writew(edma, le16_to_cpu(tcd->citer), &regs->tcd[ch].citer);
-	edma_writew(edma, le16_to_cpu(tcd->biter), &regs->tcd[ch].biter);
-	edma_writew(edma, le16_to_cpu(tcd->doff), &regs->tcd[ch].doff);
+	edma_writel(edma, (s32)tcd->nbytes, &regs->tcd[ch].nbytes);
+	edma_writel(edma, (s32)tcd->slast, &regs->tcd[ch].slast);
 
-	edma_writel(edma, le32_to_cpu(tcd->dlast_sga),
+	edma_writew(edma, (s16)tcd->citer, &regs->tcd[ch].citer);
+	edma_writew(edma, (s16)tcd->biter, &regs->tcd[ch].biter);
+	edma_writew(edma, (s16)tcd->doff, &regs->tcd[ch].doff);
+
+	edma_writel(edma, (s32)tcd->dlast_sga,
 			&regs->tcd[ch].dlast_sga);
 
-	edma_writew(edma, le16_to_cpu(tcd->csr), &regs->tcd[ch].csr);
+	edma_writew(edma, (s16)tcd->csr, &regs->tcd[ch].csr);
 }
 
 static inline
diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h
index c53f76eeb4d3..b434c6b9fd54 100644
--- a/drivers/dma/fsl-edma-common.h
+++ b/drivers/dma/fsl-edma-common.h
@@ -32,7 +32,7 @@
 #define EDMA_TCD_ATTR_DSIZE_16BIT	BIT(0)
 #define EDMA_TCD_ATTR_DSIZE_32BIT	BIT(1)
 #define EDMA_TCD_ATTR_DSIZE_64BIT	(BIT(0) | BIT(1))
-#define EDMA_TCD_ATTR_DSIZE_32BYTE	(BIT(3) | BIT(0))
+#define EDMA_TCD_ATTR_DSIZE_32BYTE	(BIT(2) | BIT(0))
 #define EDMA_TCD_ATTR_SSIZE_8BIT	0
 #define EDMA_TCD_ATTR_SSIZE_16BIT	(EDMA_TCD_ATTR_DSIZE_16BIT << 8)
 #define EDMA_TCD_ATTR_SSIZE_32BIT	(EDMA_TCD_ATTR_DSIZE_32BIT << 8)
diff --git a/drivers/dma/fsl-edma.c b/drivers/dma/fsl-edma.c
index 0ddad3adb761..8f03930e4691 100644
--- a/drivers/dma/fsl-edma.c
+++ b/drivers/dma/fsl-edma.c
@@ -38,6 +38,13 @@ static irqreturn_t fsl_edma_tx_handler(int irq, void *dev_id)
 			fsl_chan = &fsl_edma->chans[ch];
 
 			spin_lock(&fsl_chan->vchan.lock);
+
+			if (!fsl_chan->edesc) {
+				/* terminate_all called before */
+				spin_unlock(&fsl_chan->vchan.lock);
+				continue;
+			}
+
 			if (!fsl_chan->edesc->iscyclic) {
 				list_del(&fsl_chan->edesc->vdesc.node);
 				vchan_cookie_complete(&fsl_chan->edesc->vdesc);
diff --git a/drivers/dma/fsl-qdma.c b/drivers/dma/fsl-qdma.c
index 3582fe2a813a..de5c45f96b78 100644
--- a/drivers/dma/fsl-qdma.c
+++ b/drivers/dma/fsl-qdma.c
@@ -303,7 +303,7 @@ static void fsl_qdma_free_chan_resources(struct dma_chan *chan)
 
 	vchan_dma_desc_free_list(&fsl_chan->vchan, &head);
 
-	if (!fsl_queue->comp_pool && !fsl_queue->comp_pool)
+	if (!fsl_queue->comp_pool && !fsl_queue->desc_pool)
 		return;
 
 	list_for_each_entry_safe(comp_temp, _comp_temp,
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 3ba0e9499c37..ad2f36fa9fdf 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -1328,13 +1328,13 @@ static void sdma_free_chan_resources(struct dma_chan *chan)
 
 	sdma_channel_synchronize(chan);
 
-	if (sdmac->event_id0)
-		sdma_event_disable(sdmac, sdmac->event_id0);
+	sdma_event_disable(sdmac, sdmac->event_id0);
 	if (sdmac->event_id1)
 		sdma_event_disable(sdmac, sdmac->event_id1);
 
 	sdmac->event_id0 = 0;
 	sdmac->event_id1 = 0;
+	sdmac->context_loaded = false;
 
 	sdma_set_channel_priority(sdmac, 0);
 
@@ -1628,11 +1628,9 @@ static int sdma_config(struct dma_chan *chan,
 	memcpy(&sdmac->slave_config, dmaengine_cfg, sizeof(*dmaengine_cfg));
 
 	/* Set ENBLn earlier to make sure dma request triggered after that */
-	if (sdmac->event_id0) {
-		if (sdmac->event_id0 >= sdmac->sdma->drvdata->num_events)
-			return -EINVAL;
-		sdma_event_enable(sdmac, sdmac->event_id0);
-	}
+	if (sdmac->event_id0 >= sdmac->sdma->drvdata->num_events)
+		return -EINVAL;
+	sdma_event_enable(sdmac, sdmac->event_id0);
 
 	if (sdmac->event_id1) {
 		if (sdmac->event_id1 >= sdmac->sdma->drvdata->num_events)
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 1a422a8b43cf..8e2a4d1f0be5 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -26,6 +26,18 @@
 
 #include "../dmaengine.h"
 
+int completion_timeout = 200;
+module_param(completion_timeout, int, 0644);
+MODULE_PARM_DESC(completion_timeout,
+		"set ioat completion timeout [msec] (default 200 [msec])");
+int idle_timeout = 2000;
+module_param(idle_timeout, int, 0644);
+MODULE_PARM_DESC(idle_timeout,
+		"set ioat idel timeout [msec] (default 2000 [msec])");
+
+#define IDLE_TIMEOUT msecs_to_jiffies(idle_timeout)
+#define COMPLETION_TIMEOUT msecs_to_jiffies(completion_timeout)
+
 static char *chanerr_str[] = {
 	"DMA Transfer Source Address Error",
 	"DMA Transfer Destination Address Error",
@@ -377,10 +389,11 @@ ioat_alloc_ring(struct dma_chan *c, int order, gfp_t flags)
 
 		descs->virt = dma_alloc_coherent(to_dev(ioat_chan),
 						 SZ_2M, &descs->hw, flags);
-		if (!descs->virt && (i > 0)) {
+		if (!descs->virt) {
 			int idx;
 
 			for (idx = 0; idx < i; idx++) {
+				descs = &ioat_chan->descs[idx];
 				dma_free_coherent(to_dev(ioat_chan), SZ_2M,
 						  descs->virt, descs->hw);
 				descs->virt = NULL;
diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h
index b8e8e0b9693c..4ac9134962f3 100644
--- a/drivers/dma/ioat/dma.h
+++ b/drivers/dma/ioat/dma.h
@@ -99,8 +99,6 @@ struct ioatdma_chan {
 	#define IOAT_RUN 5
 	#define IOAT_CHAN_ACTIVE 6
 	struct timer_list timer;
-	#define COMPLETION_TIMEOUT msecs_to_jiffies(100)
-	#define IDLE_TIMEOUT msecs_to_jiffies(2000)
 	#define RESET_DELAY msecs_to_jiffies(100)
 	struct ioatdma_device *ioat_dma;
 	dma_addr_t completion_dma;
diff --git a/drivers/dma/k3dma.c b/drivers/dma/k3dma.c
index 4b36c8810517..d05471653224 100644
--- a/drivers/dma/k3dma.c
+++ b/drivers/dma/k3dma.c
@@ -229,9 +229,11 @@ static irqreturn_t k3_dma_int_handler(int irq, void *dev_id)
 			c = p->vchan;
 			if (c && (tc1 & BIT(i))) {
 				spin_lock_irqsave(&c->vc.lock, flags);
-				vchan_cookie_complete(&p->ds_run->vd);
-				p->ds_done = p->ds_run;
-				p->ds_run = NULL;
+				if (p->ds_run != NULL) {
+					vchan_cookie_complete(&p->ds_run->vd);
+					p->ds_done = p->ds_run;
+					p->ds_run = NULL;
+				}
 				spin_unlock_irqrestore(&c->vc.lock, flags);
 			}
 			if (c && (tc2 & BIT(i))) {
@@ -271,6 +273,10 @@ static int k3_dma_start_txd(struct k3_dma_chan *c)
 	if (BIT(c->phy->idx) & k3_dma_get_chan_stat(d))
 		return -EAGAIN;
 
+	/* Avoid losing track of  ds_run if a transaction is in flight */
+	if (c->phy->ds_run)
+		return -EAGAIN;
+
 	if (vd) {
 		struct k3_dma_desc_sw *ds =
 			container_of(vd, struct k3_dma_desc_sw, vd);
diff --git a/drivers/dma/mcf-edma.c b/drivers/dma/mcf-edma.c
index 7de54b2fafdb..6e3d4ab34321 100644
--- a/drivers/dma/mcf-edma.c
+++ b/drivers/dma/mcf-edma.c
@@ -35,6 +35,13 @@ static irqreturn_t mcf_edma_tx_handler(int irq, void *dev_id)
 			mcf_chan = &mcf_edma->chans[ch];
 
 			spin_lock(&mcf_chan->vchan.lock);
+
+			if (!mcf_chan->edesc) {
+				/* terminate_all called before */
+				spin_unlock(&mcf_chan->vchan.lock);
+				continue;
+			}
+
 			if (!mcf_chan->edesc->iscyclic) {
 				list_del(&mcf_chan->edesc->vdesc.node);
 				vchan_cookie_complete(&mcf_chan->edesc->vdesc);
diff --git a/drivers/dma/mmp_tdma.c b/drivers/dma/mmp_tdma.c
index bb3ccbf90a31..46d7282a6e06 100644
--- a/drivers/dma/mmp_tdma.c
+++ b/drivers/dma/mmp_tdma.c
@@ -363,6 +363,8 @@ static void mmp_tdma_free_descriptor(struct mmp_tdma_chan *tdmac)
 		gen_pool_free(gpool, (unsigned long)tdmac->desc_arr,
 				size);
 	tdmac->desc_arr = NULL;
+	if (tdmac->status == DMA_ERROR)
+		tdmac->status = DMA_COMPLETE;
 
 	return;
 }
@@ -443,7 +445,8 @@ static struct dma_async_tx_descriptor *mmp_tdma_prep_dma_cyclic(
 	if (!desc)
 		goto err_out;
 
-	mmp_tdma_config_write(chan, direction, &tdmac->slave_config);
+	if (mmp_tdma_config_write(chan, direction, &tdmac->slave_config))
+		goto err_out;
 
 	while (buf < buf_len) {
 		desc = &tdmac->desc_arr[i];
diff --git a/drivers/dma/owl-dma.c b/drivers/dma/owl-dma.c
index 90bbcef99ef8..af20e9a790a2 100644
--- a/drivers/dma/owl-dma.c
+++ b/drivers/dma/owl-dma.c
@@ -175,13 +175,11 @@ struct owl_dma_txd {
  * @id: physical index to this channel
  * @base: virtual memory base for the dma channel
  * @vchan: the virtual channel currently being served by this physical channel
- * @lock: a lock to use when altering an instance of this struct
  */
 struct owl_dma_pchan {
 	u32			id;
 	void __iomem		*base;
 	struct owl_dma_vchan	*vchan;
-	spinlock_t		lock;
 };
 
 /**
@@ -437,14 +435,14 @@ static struct owl_dma_pchan *owl_dma_get_pchan(struct owl_dma *od,
 	for (i = 0; i < od->nr_pchans; i++) {
 		pchan = &od->pchans[i];
 
-		spin_lock_irqsave(&pchan->lock, flags);
+		spin_lock_irqsave(&od->lock, flags);
 		if (!pchan->vchan) {
 			pchan->vchan = vchan;
-			spin_unlock_irqrestore(&pchan->lock, flags);
+			spin_unlock_irqrestore(&od->lock, flags);
 			break;
 		}
 
-		spin_unlock_irqrestore(&pchan->lock, flags);
+		spin_unlock_irqrestore(&od->lock, flags);
 	}
 
 	return pchan;
diff --git a/drivers/dma/pch_dma.c b/drivers/dma/pch_dma.c
index 581e7a290d98..a3b0b4c56a19 100644
--- a/drivers/dma/pch_dma.c
+++ b/drivers/dma/pch_dma.c
@@ -865,6 +865,7 @@ static int pch_dma_probe(struct pci_dev *pdev,
 	}
 
 	pci_set_master(pdev);
+	pd->dma.dev = &pdev->dev;
 
 	err = request_irq(pdev->irq, pd_irq, IRQF_SHARED, DRV_NAME, pd);
 	if (err) {
@@ -880,7 +881,6 @@ static int pch_dma_probe(struct pci_dev *pdev,
 		goto err_free_irq;
 	}
 
-	pd->dma.dev = &pdev->dev;
 
 	INIT_LIST_HEAD(&pd->dma.channels);
 
diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c
index da41bab98f5b..ef4d109e7189 100644
--- a/drivers/dma/stm32-dma.c
+++ b/drivers/dma/stm32-dma.c
@@ -1365,7 +1365,6 @@ static int stm32_dma_probe(struct platform_device *pdev)
 
 	for (i = 0; i < STM32_DMA_MAX_CHANNELS; i++) {
 		chan = &dmadev->chan[i];
-		chan->irq = platform_get_irq(pdev, i);
 		ret = platform_get_irq(pdev, i);
 		if (ret < 0)  {
 			if (ret != -EPROBE_DEFER)
diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c
index 79e9593815f1..ff256409a8c8 100644
--- a/drivers/dma/tegra20-apb-dma.c
+++ b/drivers/dma/tegra20-apb-dma.c
@@ -280,7 +280,7 @@ static struct tegra_dma_desc *tegra_dma_desc_get(
 
 	/* Do not allocate if desc are waiting for ack */
 	list_for_each_entry(dma_desc, &tdc->free_dma_desc, node) {
-		if (async_tx_test_ack(&dma_desc->txd)) {
+		if (async_tx_test_ack(&dma_desc->txd) && !dma_desc->cb_count) {
 			list_del(&dma_desc->node);
 			spin_unlock_irqrestore(&tdc->lock, flags);
 			dma_desc->txd.flags = 0;
@@ -751,10 +751,6 @@ static int tegra_dma_terminate_all(struct dma_chan *dc)
 	bool was_busy;
 
 	spin_lock_irqsave(&tdc->lock, flags);
-	if (list_empty(&tdc->pending_sg_req)) {
-		spin_unlock_irqrestore(&tdc->lock, flags);
-		return 0;
-	}
 
 	if (!tdc->busy)
 		goto skip_dma_stop;
diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c
index 0b9c96f7cdc9..4373116b579c 100644
--- a/drivers/dma/tegra210-adma.c
+++ b/drivers/dma/tegra210-adma.c
@@ -666,6 +666,7 @@ static int tegra_adma_alloc_chan_resources(struct dma_chan *dc)
 
 	ret = pm_runtime_get_sync(tdc2dev(tdc));
 	if (ret < 0) {
+		pm_runtime_put_noidle(tdc2dev(tdc));
 		free_irq(tdc->irq, tdc);
 		return ret;
 	}
@@ -877,8 +878,10 @@ static int tegra_adma_probe(struct platform_device *pdev)
 	pm_runtime_enable(&pdev->dev);
 
 	ret = pm_runtime_get_sync(&pdev->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_noidle(&pdev->dev);
 		goto rpm_disable;
+	}
 
 	ret = tegra_adma_init(tdma);
 	if (ret)
@@ -908,7 +911,7 @@ static int tegra_adma_probe(struct platform_device *pdev)
 	ret = dma_async_device_register(&tdma->dma_dev);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "ADMA registration failed: %d\n", ret);
-		goto irq_dispose;
+		goto rpm_put;
 	}
 
 	ret = of_dma_controller_register(pdev->dev.of_node,
diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c
index 982631d4e1f8..44158fa85973 100644
--- a/drivers/dma/ti/edma.c
+++ b/drivers/dma/ti/edma.c
@@ -2345,8 +2345,10 @@ static int edma_probe(struct platform_device *pdev)
 
 		ecc->tc_list = devm_kcalloc(dev, ecc->num_tc,
 					    sizeof(*ecc->tc_list), GFP_KERNEL);
-		if (!ecc->tc_list)
-			return -ENOMEM;
+		if (!ecc->tc_list) {
+			ret = -ENOMEM;
+			goto err_reg1;
+		}
 
 		for (i = 0;; i++) {
 			ret = of_parse_phandle_with_fixed_args(node, "ti,tptcs",
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 608fdab566b3..88a643aabcb0 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -265,6 +265,8 @@ static int get_scrub_rate(struct mem_ctl_info *mci)
 
 		if (pvt->model == 0x60)
 			amd64_read_pci_cfg(pvt->F2, F15H_M60H_SCRCTRL, &scrubval);
+		else
+			amd64_read_pci_cfg(pvt->F3, SCRCTRL, &scrubval);
 		break;
 
 	case 0x17:
@@ -2266,6 +2268,33 @@ static struct amd64_family_type family_types[] = {
 			.dbam_to_cs		= f17_base_addr_to_cs_size,
 		}
 	},
+	[F17_M60H_CPUS] = {
+		.ctl_name = "F17h_M60h",
+		.f0_id = PCI_DEVICE_ID_AMD_17H_M60H_DF_F0,
+		.f6_id = PCI_DEVICE_ID_AMD_17H_M60H_DF_F6,
+		.ops = {
+			.early_channel_count	= f17_early_channel_count,
+			.dbam_to_cs		= f17_base_addr_to_cs_size,
+		}
+	},
+	[F17_M70H_CPUS] = {
+		.ctl_name = "F17h_M70h",
+		.f0_id = PCI_DEVICE_ID_AMD_17H_M70H_DF_F0,
+		.f6_id = PCI_DEVICE_ID_AMD_17H_M70H_DF_F6,
+		.ops = {
+			.early_channel_count	= f17_early_channel_count,
+			.dbam_to_cs		= f17_base_addr_to_cs_size,
+		}
+	},
+	[F19_CPUS] = {
+		.ctl_name = "F19h",
+		.f0_id = PCI_DEVICE_ID_AMD_19H_DF_F0,
+		.f6_id = PCI_DEVICE_ID_AMD_19H_DF_F6,
+		.ops = {
+			.early_channel_count	= f17_early_channel_count,
+			.dbam_to_cs		= f17_base_addr_to_cs_size,
+		}
+	},
 };
 
 /*
@@ -2837,6 +2866,50 @@ static u32 get_csrow_nr_pages(struct amd64_pvt *pvt, u8 dct, int csrow_nr_orig)
 	return nr_pages;
 }
 
+static int init_csrows_df(struct mem_ctl_info *mci)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+	enum edac_type edac_mode = EDAC_NONE;
+	enum dev_type dev_type = DEV_UNKNOWN;
+	struct dimm_info *dimm;
+	int empty = 1;
+	u8 umc, cs;
+
+	if (mci->edac_ctl_cap & EDAC_FLAG_S16ECD16ED) {
+		edac_mode = EDAC_S16ECD16ED;
+		dev_type = DEV_X16;
+	} else if (mci->edac_ctl_cap & EDAC_FLAG_S8ECD8ED) {
+		edac_mode = EDAC_S8ECD8ED;
+		dev_type = DEV_X8;
+	} else if (mci->edac_ctl_cap & EDAC_FLAG_S4ECD4ED) {
+		edac_mode = EDAC_S4ECD4ED;
+		dev_type = DEV_X4;
+	} else if (mci->edac_ctl_cap & EDAC_FLAG_SECDED) {
+		edac_mode = EDAC_SECDED;
+	}
+
+	for_each_umc(umc) {
+		for_each_chip_select(cs, umc, pvt) {
+			if (!csrow_enabled(cs, umc, pvt))
+				continue;
+
+			empty = 0;
+			dimm = mci->csrows[cs]->channels[umc]->dimm;
+
+			edac_dbg(1, "MC node: %d, csrow: %d\n",
+					pvt->mc_node_id, cs);
+
+			dimm->nr_pages = get_csrow_nr_pages(pvt, umc, cs);
+			dimm->mtype = pvt->dram_type;
+			dimm->edac_mode = edac_mode;
+			dimm->dtype = dev_type;
+			dimm->grain = 64;
+		}
+	}
+
+	return empty;
+}
+
 /*
  * Initialize the array of csrow attribute instances, based on the values
  * from pci config hardware registers.
@@ -2851,15 +2924,16 @@ static int init_csrows(struct mem_ctl_info *mci)
 	int nr_pages = 0;
 	u32 val;
 
-	if (!pvt->umc) {
-		amd64_read_pci_cfg(pvt->F3, NBCFG, &val);
+	if (pvt->umc)
+		return init_csrows_df(mci);
 
-		pvt->nbcfg = val;
+	amd64_read_pci_cfg(pvt->F3, NBCFG, &val);
 
-		edac_dbg(0, "node %d, NBCFG=0x%08x[ChipKillEccCap: %d|DramEccEn: %d]\n",
-			 pvt->mc_node_id, val,
-			 !!(val & NBCFG_CHIPKILL), !!(val & NBCFG_ECC_ENABLE));
-	}
+	pvt->nbcfg = val;
+
+	edac_dbg(0, "node %d, NBCFG=0x%08x[ChipKillEccCap: %d|DramEccEn: %d]\n",
+		 pvt->mc_node_id, val,
+		 !!(val & NBCFG_CHIPKILL), !!(val & NBCFG_ECC_ENABLE));
 
 	/*
 	 * We iterate over DCT0 here but we look at DCT1 in parallel, if needed.
@@ -2896,13 +2970,7 @@ static int init_csrows(struct mem_ctl_info *mci)
 		edac_dbg(1, "Total csrow%d pages: %u\n", i, nr_pages);
 
 		/* Determine DIMM ECC mode: */
-		if (pvt->umc) {
-			if (mci->edac_ctl_cap & EDAC_FLAG_S4ECD4ED)
-				edac_mode = EDAC_S4ECD4ED;
-			else if (mci->edac_ctl_cap & EDAC_FLAG_SECDED)
-				edac_mode = EDAC_SECDED;
-
-		} else if (pvt->nbcfg & NBCFG_ECC_ENABLE) {
+		if (pvt->nbcfg & NBCFG_ECC_ENABLE) {
 			edac_mode = (pvt->nbcfg & NBCFG_CHIPKILL)
 					? EDAC_S4ECD4ED
 					: EDAC_SECDED;
@@ -2912,6 +2980,7 @@ static int init_csrows(struct mem_ctl_info *mci)
 			dimm = csrow->channels[j]->dimm;
 			dimm->mtype = pvt->dram_type;
 			dimm->edac_mode = edac_mode;
+			dimm->grain = 64;
 		}
 	}
 
@@ -3264,6 +3333,14 @@ static struct amd64_family_type *per_family_init(struct amd64_pvt *pvt)
 			fam_type = &family_types[F17_M30H_CPUS];
 			pvt->ops = &family_types[F17_M30H_CPUS].ops;
 			break;
+		} else if (pvt->model >= 0x60 && pvt->model <= 0x6f) {
+			fam_type = &family_types[F17_M60H_CPUS];
+			pvt->ops = &family_types[F17_M60H_CPUS].ops;
+			break;
+		} else if (pvt->model >= 0x70 && pvt->model <= 0x7f) {
+			fam_type = &family_types[F17_M70H_CPUS];
+			pvt->ops = &family_types[F17_M70H_CPUS].ops;
+			break;
 		}
 		/* fall through */
 	case 0x18:
@@ -3274,6 +3351,12 @@ static struct amd64_family_type *per_family_init(struct amd64_pvt *pvt)
 			family_types[F17_CPUS].ctl_name = "F18h";
 		break;
 
+	case 0x19:
+		fam_type	= &family_types[F19_CPUS];
+		pvt->ops	= &family_types[F19_CPUS].ops;
+		family_types[F19_CPUS].ctl_name = "F19h";
+		break;
+
 	default:
 		amd64_err("Unsupported family!\n");
 		return NULL;
@@ -3533,6 +3616,7 @@ static const struct x86_cpu_id amd64_cpuids[] = {
 	{ X86_VENDOR_AMD, 0x16, X86_MODEL_ANY,	X86_FEATURE_ANY, 0 },
 	{ X86_VENDOR_AMD, 0x17, X86_MODEL_ANY,	X86_FEATURE_ANY, 0 },
 	{ X86_VENDOR_HYGON, 0x18, X86_MODEL_ANY, X86_FEATURE_ANY, 0 },
+	{ X86_VENDOR_AMD, 0x19, X86_MODEL_ANY,	X86_FEATURE_ANY, 0 },
 	{ }
 };
 MODULE_DEVICE_TABLE(x86cpu, amd64_cpuids);
diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h
index 4dce6a2ac75f..2cb7431173be 100644
--- a/drivers/edac/amd64_edac.h
+++ b/drivers/edac/amd64_edac.h
@@ -120,6 +120,12 @@
 #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F6 0x15ee
 #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F0 0x1490
 #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F6 0x1496
+#define PCI_DEVICE_ID_AMD_17H_M60H_DF_F0 0x1448
+#define PCI_DEVICE_ID_AMD_17H_M60H_DF_F6 0x144e
+#define PCI_DEVICE_ID_AMD_17H_M70H_DF_F0 0x1440
+#define PCI_DEVICE_ID_AMD_17H_M70H_DF_F6 0x1446
+#define PCI_DEVICE_ID_AMD_19H_DF_F0	0x1650
+#define PCI_DEVICE_ID_AMD_19H_DF_F6	0x1656
 
 /*
  * Function 1 - Address Map
@@ -286,6 +292,9 @@ enum amd_families {
 	F17_CPUS,
 	F17_M10H_CPUS,
 	F17_M30H_CPUS,
+	F17_M60H_CPUS,
+	F17_M70H_CPUS,
+	F19_CPUS,
 	NUM_FAMILIES,
 };
 
diff --git a/drivers/edac/edac_device_sysfs.c b/drivers/edac/edac_device_sysfs.c
index 0e7ea3591b78..5e7593753799 100644
--- a/drivers/edac/edac_device_sysfs.c
+++ b/drivers/edac/edac_device_sysfs.c
@@ -275,6 +275,7 @@ int edac_device_register_sysfs_main_kobj(struct edac_device_ctl_info *edac_dev)
 
 	/* Error exit stack */
 err_kobj_reg:
+	kobject_put(&edac_dev->kobj);
 	module_put(edac_dev->owner);
 
 err_out:
diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c
index 4386ea4b9b5a..9f589acd0753 100644
--- a/drivers/edac/edac_mc_sysfs.c
+++ b/drivers/edac/edac_mc_sysfs.c
@@ -449,8 +449,7 @@ error:
 		csrow = mci->csrows[i];
 		if (!nr_pages_per_csrow(csrow))
 			continue;
-
-		device_del(&mci->csrows[i]->dev);
+		device_unregister(&mci->csrows[i]->dev);
 	}
 
 	return err;
diff --git a/drivers/edac/edac_pci_sysfs.c b/drivers/edac/edac_pci_sysfs.c
index 72c9eb9fdffb..53042af7262e 100644
--- a/drivers/edac/edac_pci_sysfs.c
+++ b/drivers/edac/edac_pci_sysfs.c
@@ -386,7 +386,7 @@ static int edac_pci_main_kobj_setup(void)
 
 	/* Error unwind statck */
 kobject_init_and_add_fail:
-	kfree(edac_pci_top_main_kobj);
+	kobject_put(edac_pci_top_main_kobj);
 
 kzalloc_fail:
 	module_put(THIS_MODULE);
diff --git a/drivers/edac/i10nm_base.c b/drivers/edac/i10nm_base.c
index 6f06aec4877c..217ba0f7fd7a 100644
--- a/drivers/edac/i10nm_base.c
+++ b/drivers/edac/i10nm_base.c
@@ -160,7 +160,7 @@ static int i10nm_get_dimm_config(struct mem_ctl_info *mci)
 				 mtr, mcddrtcfg, imc->mc, i, j);
 
 			if (IS_DIMM_PRESENT(mtr))
-				ndimms += skx_get_dimm_info(mtr, 0, dimm,
+				ndimms += skx_get_dimm_info(mtr, 0, 0, dimm,
 							    imc, i, j);
 			else if (IS_NVDIMM_PRESENT(mcddrtcfg, j))
 				ndimms += skx_get_nvdimm_info(dimm, imc, i, j,
diff --git a/drivers/edac/skx_base.c b/drivers/edac/skx_base.c
index a5c8fa3a249a..1c27e1856f0a 100644
--- a/drivers/edac/skx_base.c
+++ b/drivers/edac/skx_base.c
@@ -151,27 +151,23 @@ static const struct x86_cpu_id skx_cpuids[] = {
 };
 MODULE_DEVICE_TABLE(x86cpu, skx_cpuids);
 
-#define SKX_GET_MTMTR(dev, reg) \
-	pci_read_config_dword((dev), 0x87c, &(reg))
-
-static bool skx_check_ecc(struct pci_dev *pdev)
+static bool skx_check_ecc(u32 mcmtr)
 {
-	u32 mtmtr;
-
-	SKX_GET_MTMTR(pdev, mtmtr);
-
-	return !!GET_BITFIELD(mtmtr, 2, 2);
+	return !!GET_BITFIELD(mcmtr, 2, 2);
 }
 
 static int skx_get_dimm_config(struct mem_ctl_info *mci)
 {
 	struct skx_pvt *pvt = mci->pvt_info;
+	u32 mtr, mcmtr, amap, mcddrtcfg;
 	struct skx_imc *imc = pvt->imc;
-	u32 mtr, amap, mcddrtcfg;
 	struct dimm_info *dimm;
 	int i, j;
 	int ndimms;
 
+	/* Only the mcmtr on the first channel is effective */
+	pci_read_config_dword(imc->chan[0].cdev, 0x87c, &mcmtr);
+
 	for (i = 0; i < SKX_NUM_CHANNELS; i++) {
 		ndimms = 0;
 		pci_read_config_dword(imc->chan[i].cdev, 0x8C, &amap);
@@ -182,14 +178,14 @@ static int skx_get_dimm_config(struct mem_ctl_info *mci)
 			pci_read_config_dword(imc->chan[i].cdev,
 					      0x80 + 4 * j, &mtr);
 			if (IS_DIMM_PRESENT(mtr)) {
-				ndimms += skx_get_dimm_info(mtr, amap, dimm, imc, i, j);
+				ndimms += skx_get_dimm_info(mtr, mcmtr, amap, dimm, imc, i, j);
 			} else if (IS_NVDIMM_PRESENT(mcddrtcfg, j)) {
 				ndimms += skx_get_nvdimm_info(dimm, imc, i, j,
 							      EDAC_MOD_STR);
 				nvdimm_count++;
 			}
 		}
-		if (ndimms && !skx_check_ecc(imc->chan[0].cdev)) {
+		if (ndimms && !skx_check_ecc(mcmtr)) {
 			skx_printk(KERN_ERR, "ECC is disabled on imc %d\n", imc->mc);
 			return -ENODEV;
 		}
diff --git a/drivers/edac/skx_common.c b/drivers/edac/skx_common.c
index b0dddcfa9baa..b8b7405a5ac4 100644
--- a/drivers/edac/skx_common.c
+++ b/drivers/edac/skx_common.c
@@ -235,7 +235,7 @@ int skx_get_hi_lo(unsigned int did, int off[], u64 *tolm, u64 *tohm)
 
 	pdev = pci_get_device(PCI_VENDOR_ID_INTEL, did, NULL);
 	if (!pdev) {
-		skx_printk(KERN_ERR, "Can't get tolm/tohm\n");
+		edac_dbg(2, "Can't get tolm/tohm\n");
 		return -ENODEV;
 	}
 
@@ -283,7 +283,7 @@ static int skx_get_dimm_attr(u32 reg, int lobit, int hibit, int add,
 #define numrow(reg)	skx_get_dimm_attr(reg, 2, 4, 12, 1, 6, "rows")
 #define numcol(reg)	skx_get_dimm_attr(reg, 0, 1, 10, 0, 2, "cols")
 
-int skx_get_dimm_info(u32 mtr, u32 amap, struct dimm_info *dimm,
+int skx_get_dimm_info(u32 mtr, u32 mcmtr, u32 amap, struct dimm_info *dimm,
 		      struct skx_imc *imc, int chan, int dimmno)
 {
 	int  banks = 16, ranks, rows, cols, npages;
@@ -303,8 +303,8 @@ int skx_get_dimm_info(u32 mtr, u32 amap, struct dimm_info *dimm,
 		 imc->mc, chan, dimmno, size, npages,
 		 banks, 1 << ranks, rows, cols);
 
-	imc->chan[chan].dimms[dimmno].close_pg = GET_BITFIELD(mtr, 0, 0);
-	imc->chan[chan].dimms[dimmno].bank_xor_enable = GET_BITFIELD(mtr, 9, 9);
+	imc->chan[chan].dimms[dimmno].close_pg = GET_BITFIELD(mcmtr, 0, 0);
+	imc->chan[chan].dimms[dimmno].bank_xor_enable = GET_BITFIELD(mcmtr, 9, 9);
 	imc->chan[chan].dimms[dimmno].fine_grain_bank = GET_BITFIELD(amap, 0, 0);
 	imc->chan[chan].dimms[dimmno].rowbits = rows;
 	imc->chan[chan].dimms[dimmno].colbits = cols;
diff --git a/drivers/edac/skx_common.h b/drivers/edac/skx_common.h
index d18fa98669af..3207606ea10b 100644
--- a/drivers/edac/skx_common.h
+++ b/drivers/edac/skx_common.h
@@ -126,7 +126,7 @@ int skx_get_all_bus_mappings(unsigned int did, int off, enum type,
 
 int skx_get_hi_lo(unsigned int did, int off[], u64 *tolm, u64 *tohm);
 
-int skx_get_dimm_info(u32 mtr, u32 amap, struct dimm_info *dimm,
+int skx_get_dimm_info(u32 mtr, u32 mcmtr, u32 amap, struct dimm_info *dimm,
 		      struct skx_imc *imc, int chan, int dimmno);
 
 int skx_get_nvdimm_info(struct dimm_info *dimm, struct skx_imc *imc,
diff --git a/drivers/edac/synopsys_edac.c b/drivers/edac/synopsys_edac.c
index 2d263382d797..880ffd833718 100644
--- a/drivers/edac/synopsys_edac.c
+++ b/drivers/edac/synopsys_edac.c
@@ -479,20 +479,14 @@ static void handle_error(struct mem_ctl_info *mci, struct synps_ecc_status *p)
 		pinf = &p->ceinfo;
 		if (!priv->p_data->quirks) {
 			snprintf(priv->message, SYNPS_EDAC_MSG_SIZE,
-				 "DDR ECC error type:%s Row %d Bank %d Col %d ",
-				  "CE", pinf->row, pinf->bank, pinf->col);
-			snprintf(priv->message, SYNPS_EDAC_MSG_SIZE,
-				 "Bit Position: %d Data: 0x%08x\n",
+				 "DDR ECC error type:%s Row %d Bank %d Col %d Bit Position: %d Data: 0x%08x",
+				 "CE", pinf->row, pinf->bank, pinf->col,
 				 pinf->bitpos, pinf->data);
 		} else {
 			snprintf(priv->message, SYNPS_EDAC_MSG_SIZE,
-				 "DDR ECC error type:%s Row %d Bank %d Col %d ",
-				  "CE", pinf->row, pinf->bank, pinf->col);
-			snprintf(priv->message, SYNPS_EDAC_MSG_SIZE,
-				 "BankGroup Number %d Block Number %d ",
-				 pinf->bankgrpnr, pinf->blknr);
-			snprintf(priv->message, SYNPS_EDAC_MSG_SIZE,
-				 "Bit Position: %d Data: 0x%08x\n",
+				 "DDR ECC error type:%s Row %d Bank %d Col %d BankGroup Number %d Block Number %d Bit Position: %d Data: 0x%08x",
+				 "CE", pinf->row, pinf->bank, pinf->col,
+				 pinf->bankgrpnr, pinf->blknr,
 				 pinf->bitpos, pinf->data);
 		}
 
@@ -509,10 +503,8 @@ static void handle_error(struct mem_ctl_info *mci, struct synps_ecc_status *p)
 				"UE", pinf->row, pinf->bank, pinf->col);
 		} else {
 			snprintf(priv->message, SYNPS_EDAC_MSG_SIZE,
-				 "DDR ECC error type :%s Row %d Bank %d Col %d ",
-				 "UE", pinf->row, pinf->bank, pinf->col);
-			snprintf(priv->message, SYNPS_EDAC_MSG_SIZE,
-				 "BankGroup Number %d Block Number %d",
+				 "DDR ECC error type :%s Row %d Bank %d Col %d BankGroup Number %d Block Number %d",
+				 "UE", pinf->row, pinf->bank, pinf->col,
 				 pinf->bankgrpnr, pinf->blknr);
 		}
 
diff --git a/drivers/extcon/extcon-adc-jack.c b/drivers/extcon/extcon-adc-jack.c
index ee9b5f70bfa4..2341e7a19085 100644
--- a/drivers/extcon/extcon-adc-jack.c
+++ b/drivers/extcon/extcon-adc-jack.c
@@ -124,7 +124,7 @@ static int adc_jack_probe(struct platform_device *pdev)
 	for (i = 0; data->adc_conditions[i].id != EXTCON_NONE; i++);
 	data->num_conditions = i;
 
-	data->chan = iio_channel_get(&pdev->dev, pdata->consumer_channel);
+	data->chan = devm_iio_channel_get(&pdev->dev, pdata->consumer_channel);
 	if (IS_ERR(data->chan))
 		return PTR_ERR(data->chan);
 
@@ -166,7 +166,6 @@ static int adc_jack_remove(struct platform_device *pdev)
 
 	free_irq(data->irq, data);
 	cancel_work_sync(&data->handler.work);
-	iio_channel_release(data->chan);
 
 	return 0;
 }
diff --git a/drivers/extcon/extcon-axp288.c b/drivers/extcon/extcon-axp288.c
index 7254852e6ec0..0bd08ef4a083 100644
--- a/drivers/extcon/extcon-axp288.c
+++ b/drivers/extcon/extcon-axp288.c
@@ -421,9 +421,40 @@ static int axp288_extcon_probe(struct platform_device *pdev)
 	/* Start charger cable type detection */
 	axp288_extcon_enable(info);
 
+	device_init_wakeup(dev, true);
+	platform_set_drvdata(pdev, info);
+
+	return 0;
+}
+
+static int __maybe_unused axp288_extcon_suspend(struct device *dev)
+{
+	struct axp288_extcon_info *info = dev_get_drvdata(dev);
+
+	if (device_may_wakeup(dev))
+		enable_irq_wake(info->irq[VBUS_RISING_IRQ]);
+
 	return 0;
 }
 
+static int __maybe_unused axp288_extcon_resume(struct device *dev)
+{
+	struct axp288_extcon_info *info = dev_get_drvdata(dev);
+
+	/*
+	 * Wakeup when a charger is connected to do charger-type
+	 * connection and generate an extcon event which makes the
+	 * axp288 charger driver set the input current limit.
+	 */
+	if (device_may_wakeup(dev))
+		disable_irq_wake(info->irq[VBUS_RISING_IRQ]);
+
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(axp288_extcon_pm_ops, axp288_extcon_suspend,
+			 axp288_extcon_resume);
+
 static const struct platform_device_id axp288_extcon_table[] = {
 	{ .name = "axp288_extcon" },
 	{},
@@ -435,6 +466,7 @@ static struct platform_driver axp288_extcon_driver = {
 	.id_table = axp288_extcon_table,
 	.driver = {
 		.name = "axp288_extcon",
+		.pm = &axp288_extcon_pm_ops,
 	},
 };
 
diff --git a/drivers/extcon/extcon-intel-cht-wc.c b/drivers/extcon/extcon-intel-cht-wc.c
index 9d32150e68db..771f6f4cf92e 100644
--- a/drivers/extcon/extcon-intel-cht-wc.c
+++ b/drivers/extcon/extcon-intel-cht-wc.c
@@ -338,6 +338,7 @@ static int cht_wc_extcon_probe(struct platform_device *pdev)
 	struct intel_soc_pmic *pmic = dev_get_drvdata(pdev->dev.parent);
 	struct cht_wc_extcon_data *ext;
 	unsigned long mask = ~(CHT_WC_PWRSRC_VBUS | CHT_WC_PWRSRC_USBID_MASK);
+	int pwrsrc_sts, id;
 	int irq, ret;
 
 	irq = platform_get_irq(pdev, 0);
@@ -387,8 +388,19 @@ static int cht_wc_extcon_probe(struct platform_device *pdev)
 		goto disable_sw_control;
 	}
 
-	/* Route D+ and D- to PMIC for initial charger detection */
-	cht_wc_extcon_set_phymux(ext, MUX_SEL_PMIC);
+	ret = regmap_read(ext->regmap, CHT_WC_PWRSRC_STS, &pwrsrc_sts);
+	if (ret) {
+		dev_err(ext->dev, "Error reading pwrsrc status: %d\n", ret);
+		goto disable_sw_control;
+	}
+
+	/*
+	 * If no USB host or device connected, route D+ and D- to PMIC for
+	 * initial charger detection
+	 */
+	id = cht_wc_extcon_get_id(ext, pwrsrc_sts);
+	if (id != INTEL_USB_ID_GND)
+		cht_wc_extcon_set_phymux(ext, MUX_SEL_PMIC);
 
 	/* Get initial state */
 	cht_wc_extcon_pwrsrc_event(ext);
diff --git a/drivers/firewire/net.c b/drivers/firewire/net.c
index b132ab9ad607..715e491dfbc3 100644
--- a/drivers/firewire/net.c
+++ b/drivers/firewire/net.c
@@ -250,7 +250,11 @@ static int fwnet_header_cache(const struct neighbour *neigh,
 	h = (struct fwnet_header *)((u8 *)hh->hh_data + HH_DATA_OFF(sizeof(*h)));
 	h->h_proto = type;
 	memcpy(h->h_dest, neigh->ha, net->addr_len);
-	hh->hh_len = FWNET_HLEN;
+
+	/* Pairs with the READ_ONCE() in neigh_resolve_output(),
+	 * neigh_hh_output() and neigh_update_hhs().
+	 */
+	smp_store_release(&hh->hh_len, FWNET_HLEN);
 
 	return 0;
 }
diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c
index 92f843eaf1e0..7a30952b463d 100644
--- a/drivers/firmware/arm_scmi/bus.c
+++ b/drivers/firmware/arm_scmi/bus.c
@@ -135,8 +135,10 @@ scmi_device_create(struct device_node *np, struct device *parent, int protocol)
 		return NULL;
 
 	id = ida_simple_get(&scmi_bus_id, 1, 0, GFP_KERNEL);
-	if (id < 0)
-		goto free_mem;
+	if (id < 0) {
+		kfree(scmi_dev);
+		return NULL;
+	}
 
 	scmi_dev->id = id;
 	scmi_dev->protocol_id = protocol;
@@ -154,8 +156,6 @@ scmi_device_create(struct device_node *np, struct device *parent, int protocol)
 put_dev:
 	put_device(&scmi_dev->dev);
 	ida_simple_remove(&scmi_bus_id, id);
-free_mem:
-	kfree(scmi_dev);
 	return NULL;
 }
 
diff --git a/drivers/firmware/arm_scmi/scmi_pm_domain.c b/drivers/firmware/arm_scmi/scmi_pm_domain.c
index 87f737e01473..041f8152272b 100644
--- a/drivers/firmware/arm_scmi/scmi_pm_domain.c
+++ b/drivers/firmware/arm_scmi/scmi_pm_domain.c
@@ -85,7 +85,10 @@ static int scmi_pm_domain_probe(struct scmi_device *sdev)
 	for (i = 0; i < num_domains; i++, scmi_pd++) {
 		u32 state;
 
-		domains[i] = &scmi_pd->genpd;
+		if (handle->power_ops->state_get(handle, i, &state)) {
+			dev_warn(dev, "failed to get state for domain %d\n", i);
+			continue;
+		}
 
 		scmi_pd->domain = i;
 		scmi_pd->handle = handle;
@@ -94,13 +97,10 @@ static int scmi_pm_domain_probe(struct scmi_device *sdev)
 		scmi_pd->genpd.power_off = scmi_pd_power_off;
 		scmi_pd->genpd.power_on = scmi_pd_power_on;
 
-		if (handle->power_ops->state_get(handle, i, &state)) {
-			dev_warn(dev, "failed to get state for domain %d\n", i);
-			continue;
-		}
-
 		pm_genpd_init(&scmi_pd->genpd, NULL,
 			      state == SCMI_POWER_STATE_GENERIC_OFF);
+
+		domains[i] = &scmi_pd->genpd;
 	}
 
 	scmi_pd_data->domains = domains;
diff --git a/drivers/firmware/arm_sdei.c b/drivers/firmware/arm_sdei.c
index 9cd70d1a5622..eb2df89d4924 100644
--- a/drivers/firmware/arm_sdei.c
+++ b/drivers/firmware/arm_sdei.c
@@ -491,11 +491,6 @@ static int _sdei_event_unregister(struct sdei_event *event)
 {
 	lockdep_assert_held(&sdei_events_lock);
 
-	spin_lock(&sdei_list_lock);
-	event->reregister = false;
-	event->reenable = false;
-	spin_unlock(&sdei_list_lock);
-
 	if (event->type == SDEI_EVENT_TYPE_SHARED)
 		return sdei_api_event_unregister(event->event_num);
 
@@ -518,6 +513,11 @@ int sdei_event_unregister(u32 event_num)
 			break;
 		}
 
+		spin_lock(&sdei_list_lock);
+		event->reregister = false;
+		event->reenable = false;
+		spin_unlock(&sdei_list_lock);
+
 		err = _sdei_event_unregister(event);
 		if (err)
 			break;
@@ -585,26 +585,15 @@ static int _sdei_event_register(struct sdei_event *event)
 
 	lockdep_assert_held(&sdei_events_lock);
 
-	spin_lock(&sdei_list_lock);
-	event->reregister = true;
-	spin_unlock(&sdei_list_lock);
-
 	if (event->type == SDEI_EVENT_TYPE_SHARED)
 		return sdei_api_event_register(event->event_num,
 					       sdei_entry_point,
 					       event->registered,
 					       SDEI_EVENT_REGISTER_RM_ANY, 0);
 
-
 	err = sdei_do_cross_call(_local_event_register, event);
-	if (err) {
-		spin_lock(&sdei_list_lock);
-		event->reregister = false;
-		event->reenable = false;
-		spin_unlock(&sdei_list_lock);
-
+	if (err)
 		sdei_do_cross_call(_local_event_unregister, event);
-	}
 
 	return err;
 }
@@ -632,8 +621,17 @@ int sdei_event_register(u32 event_num, sdei_event_callback *cb, void *arg)
 			break;
 		}
 
+		spin_lock(&sdei_list_lock);
+		event->reregister = true;
+		spin_unlock(&sdei_list_lock);
+
 		err = _sdei_event_register(event);
 		if (err) {
+			spin_lock(&sdei_list_lock);
+			event->reregister = false;
+			event->reenable = false;
+			spin_unlock(&sdei_list_lock);
+
 			sdei_event_destroy(event);
 			pr_warn("Failed to register event %u: %d\n", event_num,
 				err);
diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index d4ea929e8b34..6fb498ac1aa5 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -205,3 +205,14 @@ config EFI_EARLYCON
 	depends on SERIAL_EARLYCON && !ARM && !IA64
 	select FONT_SUPPORT
 	select ARCH_USE_MEMREMAP_PROT
+
+config EFI_CUSTOM_SSDT_OVERLAYS
+	bool "Load custom ACPI SSDT overlay from an EFI variable"
+	depends on EFI_VARS && ACPI
+	default ACPI_TABLE_UPGRADE
+	help
+	  Allow loading of an ACPI SSDT overlay from an EFI variable specified
+	  by a kernel command line option.
+
+	  See Documentation/admin-guide/acpi/ssdt-overlays.rst for more
+	  information.
diff --git a/drivers/firmware/efi/earlycon.c b/drivers/firmware/efi/earlycon.c
index c9a0efca17b0..5d4f84781aa0 100644
--- a/drivers/firmware/efi/earlycon.c
+++ b/drivers/firmware/efi/earlycon.c
@@ -13,18 +13,58 @@
 
 #include <asm/early_ioremap.h>
 
+static const struct console *earlycon_console __initdata;
 static const struct font_desc *font;
 static u32 efi_x, efi_y;
 static u64 fb_base;
-static pgprot_t fb_prot;
+static bool fb_wb;
+static void *efi_fb;
+
+/*
+ * EFI earlycon needs to use early_memremap() to map the framebuffer.
+ * But early_memremap() is not usable for 'earlycon=efifb keep_bootcon',
+ * memremap() should be used instead. memremap() will be available after
+ * paging_init() which is earlier than initcall callbacks. Thus adding this
+ * early initcall function early_efi_map_fb() to map the whole EFI framebuffer.
+ */
+static int __init efi_earlycon_remap_fb(void)
+{
+	/* bail if there is no bootconsole or it has been disabled already */
+	if (!earlycon_console || !(earlycon_console->flags & CON_ENABLED))
+		return 0;
+
+	efi_fb = memremap(fb_base, screen_info.lfb_size,
+			  fb_wb ? MEMREMAP_WB : MEMREMAP_WC);
+
+	return efi_fb ? 0 : -ENOMEM;
+}
+early_initcall(efi_earlycon_remap_fb);
+
+static int __init efi_earlycon_unmap_fb(void)
+{
+	/* unmap the bootconsole fb unless keep_bootcon has left it enabled */
+	if (efi_fb && !(earlycon_console->flags & CON_ENABLED))
+		memunmap(efi_fb);
+	return 0;
+}
+late_initcall(efi_earlycon_unmap_fb);
 
 static __ref void *efi_earlycon_map(unsigned long start, unsigned long len)
 {
+	pgprot_t fb_prot;
+
+	if (efi_fb)
+		return efi_fb + start;
+
+	fb_prot = fb_wb ? PAGE_KERNEL : pgprot_writecombine(PAGE_KERNEL);
 	return early_memremap_prot(fb_base + start, len, pgprot_val(fb_prot));
 }
 
 static __ref void efi_earlycon_unmap(void *addr, unsigned long len)
 {
+	if (efi_fb)
+		return;
+
 	early_memunmap(addr, len);
 }
 
@@ -176,10 +216,7 @@ static int __init efi_earlycon_setup(struct earlycon_device *device,
 	if (screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE)
 		fb_base |= (u64)screen_info.ext_lfb_base << 32;
 
-	if (opt && !strcmp(opt, "ram"))
-		fb_prot = PAGE_KERNEL;
-	else
-		fb_prot = pgprot_writecombine(PAGE_KERNEL);
+	fb_wb = opt && !strcmp(opt, "ram");
 
 	si = &screen_info;
 	xres = si->lfb_width;
@@ -201,6 +238,7 @@ static int __init efi_earlycon_setup(struct earlycon_device *device,
 		efi_earlycon_scroll_up();
 
 	device->con->write = efi_earlycon_write;
+	earlycon_console = device->con;
 	return 0;
 }
 EARLYCON_DECLARE(efifb, efi_earlycon_setup);
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index b338e799e00d..816d773378a2 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -236,7 +236,7 @@ static void generic_ops_unregister(void)
 	efivars_unregister(&generic_efivars);
 }
 
-#if IS_ENABLED(CONFIG_ACPI)
+#ifdef CONFIG_EFI_CUSTOM_SSDT_OVERLAYS
 #define EFIVAR_SSDT_NAME_MAX	16
 static char efivar_ssdt[EFIVAR_SSDT_NAME_MAX] __initdata;
 static int __init efivar_ssdt_setup(char *str)
@@ -555,7 +555,7 @@ int __init efi_config_parse_tables(void *config_tables, int count, int sz,
 
 		seed = early_memremap(efi.rng_seed, sizeof(*seed));
 		if (seed != NULL) {
-			size = seed->size;
+			size = READ_ONCE(seed->size);
 			early_memunmap(seed, sizeof(*seed));
 		} else {
 			pr_err("Could not map UEFI random seed!\n");
@@ -565,7 +565,7 @@ int __init efi_config_parse_tables(void *config_tables, int count, int sz,
 					      sizeof(*seed) + size);
 			if (seed != NULL) {
 				pr_notice("seeding entropy pool\n");
-				add_device_randomness(seed->bits, seed->size);
+				add_device_randomness(seed->bits, size);
 				early_memunmap(seed, sizeof(*seed) + size);
 			} else {
 				pr_err("Could not map UEFI random seed!\n");
@@ -573,7 +573,7 @@ int __init efi_config_parse_tables(void *config_tables, int count, int sz,
 		}
 	}
 
-	if (efi_enabled(EFI_MEMMAP))
+	if (!IS_ENABLED(CONFIG_X86_32) && efi_enabled(EFI_MEMMAP))
 		efi_memattr_init();
 
 	efi_tpm_eventlog_init();
diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c
index 7576450c8254..d187585db97a 100644
--- a/drivers/firmware/efi/efivars.c
+++ b/drivers/firmware/efi/efivars.c
@@ -83,13 +83,16 @@ static ssize_t
 efivar_attr_read(struct efivar_entry *entry, char *buf)
 {
 	struct efi_variable *var = &entry->var;
+	unsigned long size = sizeof(var->Data);
 	char *str = buf;
+	int ret;
 
 	if (!entry || !buf)
 		return -EINVAL;
 
-	var->DataSize = 1024;
-	if (efivar_entry_get(entry, &var->Attributes, &var->DataSize, var->Data))
+	ret = efivar_entry_get(entry, &var->Attributes, &size, var->Data);
+	var->DataSize = size;
+	if (ret)
 		return -EIO;
 
 	if (var->Attributes & EFI_VARIABLE_NON_VOLATILE)
@@ -116,13 +119,16 @@ static ssize_t
 efivar_size_read(struct efivar_entry *entry, char *buf)
 {
 	struct efi_variable *var = &entry->var;
+	unsigned long size = sizeof(var->Data);
 	char *str = buf;
+	int ret;
 
 	if (!entry || !buf)
 		return -EINVAL;
 
-	var->DataSize = 1024;
-	if (efivar_entry_get(entry, &var->Attributes, &var->DataSize, var->Data))
+	ret = efivar_entry_get(entry, &var->Attributes, &size, var->Data);
+	var->DataSize = size;
+	if (ret)
 		return -EIO;
 
 	str += sprintf(str, "0x%lx\n", var->DataSize);
@@ -133,12 +139,15 @@ static ssize_t
 efivar_data_read(struct efivar_entry *entry, char *buf)
 {
 	struct efi_variable *var = &entry->var;
+	unsigned long size = sizeof(var->Data);
+	int ret;
 
 	if (!entry || !buf)
 		return -EINVAL;
 
-	var->DataSize = 1024;
-	if (efivar_entry_get(entry, &var->Attributes, &var->DataSize, var->Data))
+	ret = efivar_entry_get(entry, &var->Attributes, &size, var->Data);
+	var->DataSize = size;
+	if (ret)
 		return -EIO;
 
 	memcpy(buf, var->Data, var->DataSize);
@@ -199,6 +208,9 @@ efivar_store_raw(struct efivar_entry *entry, const char *buf, size_t count)
 	u8 *data;
 	int err;
 
+	if (!entry || !buf)
+		return -EINVAL;
+
 	if (in_compat_syscall()) {
 		struct compat_efi_variable *compat;
 
@@ -250,14 +262,16 @@ efivar_show_raw(struct efivar_entry *entry, char *buf)
 {
 	struct efi_variable *var = &entry->var;
 	struct compat_efi_variable *compat;
+	unsigned long datasize = sizeof(var->Data);
 	size_t size;
+	int ret;
 
 	if (!entry || !buf)
 		return 0;
 
-	var->DataSize = 1024;
-	if (efivar_entry_get(entry, &entry->var.Attributes,
-			     &entry->var.DataSize, entry->var.Data))
+	ret = efivar_entry_get(entry, &var->Attributes, &datasize, var->Data);
+	var->DataSize = datasize;
+	if (ret)
 		return -EIO;
 
 	if (in_compat_syscall()) {
@@ -508,8 +522,10 @@ efivar_create_sysfs_entry(struct efivar_entry *new_var)
 	ret = kobject_init_and_add(&new_var->kobj, &efivar_ktype,
 				   NULL, "%s", short_name);
 	kfree(short_name);
-	if (ret)
+	if (ret) {
+		kobject_put(&new_var->kobj);
 		return ret;
+	}
 
 	kobject_uevent(&new_var->kobj, KOBJ_ADD);
 	if (efivar_entry_add(new_var, &efivar_sysfs_list)) {
diff --git a/drivers/firmware/efi/esrt.c b/drivers/firmware/efi/esrt.c
index d6dd5f503fa2..e8f71a50ba89 100644
--- a/drivers/firmware/efi/esrt.c
+++ b/drivers/firmware/efi/esrt.c
@@ -181,7 +181,7 @@ static int esre_create_sysfs_entry(void *esre, int entry_num)
 		rc = kobject_init_and_add(&entry->kobj, &esre1_ktype, NULL,
 					  "entry%d", entry_num);
 		if (rc) {
-			kfree(entry);
+			kobject_put(&entry->kobj);
 			return rc;
 		}
 	}
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index ee0661ddb25b..8c5b5529dbc0 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -28,6 +28,7 @@ KBUILD_CFLAGS			:= $(cflags-y) -DDISABLE_BRANCH_PROFILING \
 				   -D__NO_FORTIFY \
 				   $(call cc-option,-ffreestanding) \
 				   $(call cc-option,-fno-stack-protector) \
+				   $(call cc-option,-fno-addrsig) \
 				   -D__DISABLE_EXPORTS
 
 GCOV_PROFILE			:= n
diff --git a/drivers/firmware/efi/libstub/gop.c b/drivers/firmware/efi/libstub/gop.c
index 0101ca4c13b1..b7bf1e993b8b 100644
--- a/drivers/firmware/efi/libstub/gop.c
+++ b/drivers/firmware/efi/libstub/gop.c
@@ -84,30 +84,6 @@ setup_pixel_info(struct screen_info *si, u32 pixels_per_scan_line,
 }
 
 static efi_status_t
-__gop_query32(efi_system_table_t *sys_table_arg,
-	      struct efi_graphics_output_protocol_32 *gop32,
-	      struct efi_graphics_output_mode_info **info,
-	      unsigned long *size, u64 *fb_base)
-{
-	struct efi_graphics_output_protocol_mode_32 *mode;
-	efi_graphics_output_protocol_query_mode query_mode;
-	efi_status_t status;
-	unsigned long m;
-
-	m = gop32->mode;
-	mode = (struct efi_graphics_output_protocol_mode_32 *)m;
-	query_mode = (void *)(unsigned long)gop32->query_mode;
-
-	status = __efi_call_early(query_mode, (void *)gop32, mode->mode, size,
-				  info);
-	if (status != EFI_SUCCESS)
-		return status;
-
-	*fb_base = mode->frame_buffer_base;
-	return status;
-}
-
-static efi_status_t
 setup_gop32(efi_system_table_t *sys_table_arg, struct screen_info *si,
             efi_guid_t *proto, unsigned long size, void **gop_handle)
 {
@@ -119,7 +95,7 @@ setup_gop32(efi_system_table_t *sys_table_arg, struct screen_info *si,
 	u64 fb_base;
 	struct efi_pixel_bitmask pixel_info;
 	int pixel_format;
-	efi_status_t status = EFI_NOT_FOUND;
+	efi_status_t status;
 	u32 *handles = (u32 *)(unsigned long)gop_handle;
 	int i;
 
@@ -128,6 +104,7 @@ setup_gop32(efi_system_table_t *sys_table_arg, struct screen_info *si,
 
 	nr_gops = size / sizeof(u32);
 	for (i = 0; i < nr_gops; i++) {
+		struct efi_graphics_output_protocol_mode_32 *mode;
 		struct efi_graphics_output_mode_info *info = NULL;
 		efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID;
 		bool conout_found = false;
@@ -145,9 +122,11 @@ setup_gop32(efi_system_table_t *sys_table_arg, struct screen_info *si,
 		if (status == EFI_SUCCESS)
 			conout_found = true;
 
-		status = __gop_query32(sys_table_arg, gop32, &info, &size,
-				       &current_fb_base);
-		if (status == EFI_SUCCESS && (!first_gop || conout_found) &&
+		mode = (void *)(unsigned long)gop32->mode;
+		info = (void *)(unsigned long)mode->info;
+		current_fb_base = mode->frame_buffer_base;
+
+		if ((!first_gop || conout_found) &&
 		    info->pixel_format != PIXEL_BLT_ONLY) {
 			/*
 			 * Systems that use the UEFI Console Splitter may
@@ -175,7 +154,7 @@ setup_gop32(efi_system_table_t *sys_table_arg, struct screen_info *si,
 
 	/* Did we find any GOPs? */
 	if (!first_gop)
-		goto out;
+		return EFI_NOT_FOUND;
 
 	/* EFI framebuffer */
 	si->orig_video_isVGA = VIDEO_TYPE_EFI;
@@ -197,32 +176,8 @@ setup_gop32(efi_system_table_t *sys_table_arg, struct screen_info *si,
 	si->lfb_size = si->lfb_linelength * si->lfb_height;
 
 	si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS;
-out:
-	return status;
-}
-
-static efi_status_t
-__gop_query64(efi_system_table_t *sys_table_arg,
-	      struct efi_graphics_output_protocol_64 *gop64,
-	      struct efi_graphics_output_mode_info **info,
-	      unsigned long *size, u64 *fb_base)
-{
-	struct efi_graphics_output_protocol_mode_64 *mode;
-	efi_graphics_output_protocol_query_mode query_mode;
-	efi_status_t status;
-	unsigned long m;
-
-	m = gop64->mode;
-	mode = (struct efi_graphics_output_protocol_mode_64 *)m;
-	query_mode = (void *)(unsigned long)gop64->query_mode;
-
-	status = __efi_call_early(query_mode, (void *)gop64, mode->mode, size,
-				  info);
-	if (status != EFI_SUCCESS)
-		return status;
 
-	*fb_base = mode->frame_buffer_base;
-	return status;
+	return EFI_SUCCESS;
 }
 
 static efi_status_t
@@ -237,7 +192,7 @@ setup_gop64(efi_system_table_t *sys_table_arg, struct screen_info *si,
 	u64 fb_base;
 	struct efi_pixel_bitmask pixel_info;
 	int pixel_format;
-	efi_status_t status = EFI_NOT_FOUND;
+	efi_status_t status;
 	u64 *handles = (u64 *)(unsigned long)gop_handle;
 	int i;
 
@@ -246,6 +201,7 @@ setup_gop64(efi_system_table_t *sys_table_arg, struct screen_info *si,
 
 	nr_gops = size / sizeof(u64);
 	for (i = 0; i < nr_gops; i++) {
+		struct efi_graphics_output_protocol_mode_64 *mode;
 		struct efi_graphics_output_mode_info *info = NULL;
 		efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID;
 		bool conout_found = false;
@@ -263,9 +219,11 @@ setup_gop64(efi_system_table_t *sys_table_arg, struct screen_info *si,
 		if (status == EFI_SUCCESS)
 			conout_found = true;
 
-		status = __gop_query64(sys_table_arg, gop64, &info, &size,
-				       &current_fb_base);
-		if (status == EFI_SUCCESS && (!first_gop || conout_found) &&
+		mode = (void *)(unsigned long)gop64->mode;
+		info = (void *)(unsigned long)mode->info;
+		current_fb_base = mode->frame_buffer_base;
+
+		if ((!first_gop || conout_found) &&
 		    info->pixel_format != PIXEL_BLT_ONLY) {
 			/*
 			 * Systems that use the UEFI Console Splitter may
@@ -293,7 +251,7 @@ setup_gop64(efi_system_table_t *sys_table_arg, struct screen_info *si,
 
 	/* Did we find any GOPs? */
 	if (!first_gop)
-		goto out;
+		return EFI_NOT_FOUND;
 
 	/* EFI framebuffer */
 	si->orig_video_isVGA = VIDEO_TYPE_EFI;
@@ -315,8 +273,8 @@ setup_gop64(efi_system_table_t *sys_table_arg, struct screen_info *si,
 	si->lfb_size = si->lfb_linelength * si->lfb_height;
 
 	si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS;
-out:
-	return status;
+
+	return EFI_SUCCESS;
 }
 
 /*
diff --git a/drivers/firmware/imx/imx-scu.c b/drivers/firmware/imx/imx-scu.c
index 04a24a863d6e..a3b11bc71dcb 100644
--- a/drivers/firmware/imx/imx-scu.c
+++ b/drivers/firmware/imx/imx-scu.c
@@ -29,6 +29,7 @@ struct imx_sc_chan {
 	struct mbox_client cl;
 	struct mbox_chan *ch;
 	int idx;
+	struct completion tx_done;
 };
 
 struct imx_sc_ipc {
@@ -37,6 +38,7 @@ struct imx_sc_ipc {
 	struct device *dev;
 	struct mutex lock;
 	struct completion done;
+	bool fast_ipc;
 
 	/* temporarily store the SCU msg */
 	u32 *msg;
@@ -100,12 +102,40 @@ int imx_scu_get_handle(struct imx_sc_ipc **ipc)
 }
 EXPORT_SYMBOL(imx_scu_get_handle);
 
+/* Callback called when the word of a message is ack-ed, eg read by SCU */
+static void imx_scu_tx_done(struct mbox_client *cl, void *mssg, int r)
+{
+	struct imx_sc_chan *sc_chan = container_of(cl, struct imx_sc_chan, cl);
+
+	complete(&sc_chan->tx_done);
+}
+
 static void imx_scu_rx_callback(struct mbox_client *c, void *msg)
 {
 	struct imx_sc_chan *sc_chan = container_of(c, struct imx_sc_chan, cl);
 	struct imx_sc_ipc *sc_ipc = sc_chan->sc_ipc;
 	struct imx_sc_rpc_msg *hdr;
 	u32 *data = msg;
+	int i;
+
+	if (!sc_ipc->msg) {
+		dev_warn(sc_ipc->dev, "unexpected rx idx %d 0x%08x, ignore!\n",
+				sc_chan->idx, *data);
+		return;
+	}
+
+	if (sc_ipc->fast_ipc) {
+		hdr = msg;
+		sc_ipc->rx_size = hdr->size;
+		sc_ipc->msg[0] = *data++;
+
+		for (i = 1; i < sc_ipc->rx_size; i++)
+			sc_ipc->msg[i] = *data++;
+
+		complete(&sc_ipc->done);
+
+		return;
+	}
 
 	if (sc_chan->idx == 0) {
 		hdr = msg;
@@ -128,21 +158,38 @@ static void imx_scu_rx_callback(struct mbox_client *c, void *msg)
 
 static int imx_scu_ipc_write(struct imx_sc_ipc *sc_ipc, void *msg)
 {
-	struct imx_sc_rpc_msg *hdr = msg;
+	struct imx_sc_rpc_msg hdr = *(struct imx_sc_rpc_msg *)msg;
 	struct imx_sc_chan *sc_chan;
 	u32 *data = msg;
 	int ret;
+	int size;
 	int i;
 
 	/* Check size */
-	if (hdr->size > IMX_SC_RPC_MAX_MSG)
+	if (hdr.size > IMX_SC_RPC_MAX_MSG)
 		return -EINVAL;
 
-	dev_dbg(sc_ipc->dev, "RPC SVC %u FUNC %u SIZE %u\n", hdr->svc,
-		hdr->func, hdr->size);
+	dev_dbg(sc_ipc->dev, "RPC SVC %u FUNC %u SIZE %u\n", hdr.svc,
+		hdr.func, hdr.size);
 
-	for (i = 0; i < hdr->size; i++) {
+	size = sc_ipc->fast_ipc ? 1 : hdr.size;
+	for (i = 0; i < size; i++) {
 		sc_chan = &sc_ipc->chans[i % 4];
+
+		/*
+		 * SCU requires that all messages words are written
+		 * sequentially but linux MU driver implements multiple
+		 * independent channels for each register so ordering between
+		 * different channels must be ensured by SCU API interface.
+		 *
+		 * Wait for tx_done before every send to ensure that no
+		 * queueing happens at the mailbox channel level.
+		 */
+		if (!sc_ipc->fast_ipc) {
+			wait_for_completion(&sc_chan->tx_done);
+			reinit_completion(&sc_chan->tx_done);
+		}
+
 		ret = mbox_send_message(sc_chan->ch, &data[i]);
 		if (ret < 0)
 			return ret;
@@ -165,7 +212,8 @@ int imx_scu_call_rpc(struct imx_sc_ipc *sc_ipc, void *msg, bool have_resp)
 	mutex_lock(&sc_ipc->lock);
 	reinit_completion(&sc_ipc->done);
 
-	sc_ipc->msg = msg;
+	if (have_resp)
+		sc_ipc->msg = msg;
 	sc_ipc->count = 0;
 	ret = imx_scu_ipc_write(sc_ipc, msg);
 	if (ret < 0) {
@@ -187,6 +235,7 @@ int imx_scu_call_rpc(struct imx_sc_ipc *sc_ipc, void *msg, bool have_resp)
 	}
 
 out:
+	sc_ipc->msg = NULL;
 	mutex_unlock(&sc_ipc->lock);
 
 	dev_dbg(sc_ipc->dev, "RPC SVC done\n");
@@ -202,6 +251,8 @@ static int imx_scu_probe(struct platform_device *pdev)
 	struct imx_sc_chan *sc_chan;
 	struct mbox_client *cl;
 	char *chan_name;
+	struct of_phandle_args args;
+	int num_channel;
 	int ret;
 	int i;
 
@@ -209,11 +260,20 @@ static int imx_scu_probe(struct platform_device *pdev)
 	if (!sc_ipc)
 		return -ENOMEM;
 
-	for (i = 0; i < SCU_MU_CHAN_NUM; i++) {
-		if (i < 4)
+	ret = of_parse_phandle_with_args(pdev->dev.of_node, "mboxes",
+					 "#mbox-cells", 0, &args);
+	if (ret)
+		return ret;
+
+	sc_ipc->fast_ipc = of_device_is_compatible(args.np, "fsl,imx8-mu-scu");
+
+	num_channel = sc_ipc->fast_ipc ? 2 : SCU_MU_CHAN_NUM;
+	for (i = 0; i < num_channel; i++) {
+		if (i < num_channel / 2)
 			chan_name = kasprintf(GFP_KERNEL, "tx%d", i);
 		else
-			chan_name = kasprintf(GFP_KERNEL, "rx%d", i - 4);
+			chan_name = kasprintf(GFP_KERNEL, "rx%d",
+					      i - num_channel / 2);
 
 		if (!chan_name)
 			return -ENOMEM;
@@ -225,14 +285,22 @@ static int imx_scu_probe(struct platform_device *pdev)
 		cl->knows_txdone = true;
 		cl->rx_callback = imx_scu_rx_callback;
 
+		if (!sc_ipc->fast_ipc) {
+			/* Initial tx_done completion as "done" */
+			cl->tx_done = imx_scu_tx_done;
+			init_completion(&sc_chan->tx_done);
+			complete(&sc_chan->tx_done);
+		}
+
 		sc_chan->sc_ipc = sc_ipc;
-		sc_chan->idx = i % 4;
+		sc_chan->idx = i % (num_channel / 2);
 		sc_chan->ch = mbox_request_channel_byname(cl, chan_name);
 		if (IS_ERR(sc_chan->ch)) {
 			ret = PTR_ERR(sc_chan->ch);
 			if (ret != -EPROBE_DEFER)
 				dev_err(dev, "Failed to request mbox chan %s ret %d\n",
 					chan_name, ret);
+			kfree(chan_name);
 			return ret;
 		}
 
diff --git a/drivers/firmware/imx/misc.c b/drivers/firmware/imx/misc.c
index 4b56a587dacd..d073cb3ce699 100644
--- a/drivers/firmware/imx/misc.c
+++ b/drivers/firmware/imx/misc.c
@@ -16,7 +16,7 @@ struct imx_sc_msg_req_misc_set_ctrl {
 	u32 ctrl;
 	u32 val;
 	u16 resource;
-} __packed;
+} __packed __aligned(4);
 
 struct imx_sc_msg_req_cpu_start {
 	struct imx_sc_rpc_msg hdr;
@@ -24,18 +24,18 @@ struct imx_sc_msg_req_cpu_start {
 	u32 address_lo;
 	u16 resource;
 	u8 enable;
-} __packed;
+} __packed __aligned(4);
 
 struct imx_sc_msg_req_misc_get_ctrl {
 	struct imx_sc_rpc_msg hdr;
 	u32 ctrl;
 	u16 resource;
-} __packed;
+} __packed __aligned(4);
 
 struct imx_sc_msg_resp_misc_get_ctrl {
 	struct imx_sc_rpc_msg hdr;
 	u32 val;
-} __packed;
+} __packed __aligned(4);
 
 /*
  * This function sets a miscellaneous control value.
diff --git a/drivers/firmware/imx/scu-pd.c b/drivers/firmware/imx/scu-pd.c
index 480cec69e2c9..a4f094e290da 100644
--- a/drivers/firmware/imx/scu-pd.c
+++ b/drivers/firmware/imx/scu-pd.c
@@ -61,7 +61,7 @@ struct imx_sc_msg_req_set_resource_power_mode {
 	struct imx_sc_rpc_msg hdr;
 	u16 resource;
 	u8 mode;
-} __packed;
+} __packed __aligned(4);
 
 #define IMX_SCU_PD_NAME_SIZE 20
 struct imx_sc_pm_domain {
diff --git a/drivers/firmware/psci/psci_checker.c b/drivers/firmware/psci/psci_checker.c
index f3659443f8c2..d89c0dd5159a 100644
--- a/drivers/firmware/psci/psci_checker.c
+++ b/drivers/firmware/psci/psci_checker.c
@@ -157,8 +157,10 @@ static int alloc_init_cpu_groups(cpumask_var_t **pcpu_groups)
 
 	cpu_groups = kcalloc(nb_available_cpus, sizeof(cpu_groups),
 			     GFP_KERNEL);
-	if (!cpu_groups)
+	if (!cpu_groups) {
+		free_cpumask_var(tmp);
 		return -ENOMEM;
+	}
 
 	cpumask_copy(tmp, cpu_online_mask);
 
@@ -167,6 +169,7 @@ static int alloc_init_cpu_groups(cpumask_var_t **pcpu_groups)
 			topology_core_cpumask(cpumask_any(tmp));
 
 		if (!alloc_cpumask_var(&cpu_groups[num_groups], GFP_KERNEL)) {
+			free_cpumask_var(tmp);
 			free_cpu_groups(num_groups, &cpu_groups);
 			return -ENOMEM;
 		}
diff --git a/drivers/firmware/qcom_scm.c b/drivers/firmware/qcom_scm.c
index 74b84244a0db..bcec5bab595f 100644
--- a/drivers/firmware/qcom_scm.c
+++ b/drivers/firmware/qcom_scm.c
@@ -9,7 +9,6 @@
 #include <linux/init.h>
 #include <linux/cpumask.h>
 #include <linux/export.h>
-#include <linux/dma-direct.h>
 #include <linux/dma-mapping.h>
 #include <linux/module.h>
 #include <linux/types.h>
@@ -440,8 +439,7 @@ int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz,
 	struct qcom_scm_mem_map_info *mem_to_map;
 	phys_addr_t mem_to_map_phys;
 	phys_addr_t dest_phys;
-	phys_addr_t ptr_phys;
-	dma_addr_t ptr_dma;
+	dma_addr_t ptr_phys;
 	size_t mem_to_map_sz;
 	size_t dest_sz;
 	size_t src_sz;
@@ -459,10 +457,9 @@ int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz,
 	ptr_sz = ALIGN(src_sz, SZ_64) + ALIGN(mem_to_map_sz, SZ_64) +
 			ALIGN(dest_sz, SZ_64);
 
-	ptr = dma_alloc_coherent(__scm->dev, ptr_sz, &ptr_dma, GFP_KERNEL);
+	ptr = dma_alloc_coherent(__scm->dev, ptr_sz, &ptr_phys, GFP_KERNEL);
 	if (!ptr)
 		return -ENOMEM;
-	ptr_phys = dma_to_phys(__scm->dev, ptr_dma);
 
 	/* Fill source vmid detail */
 	src = ptr;
@@ -492,7 +489,7 @@ int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz,
 
 	ret = __qcom_scm_assign_mem(__scm->dev, mem_to_map_phys, mem_to_map_sz,
 				    ptr_phys, src_sz, dest_phys, dest_sz);
-	dma_free_coherent(__scm->dev, ptr_sz, ptr, ptr_dma);
+	dma_free_coherent(__scm->dev, ptr_sz, ptr, ptr_phys);
 	if (ret) {
 		dev_err(__scm->dev,
 			"Assign memory protection call failed %d.\n", ret);
diff --git a/drivers/firmware/qemu_fw_cfg.c b/drivers/firmware/qemu_fw_cfg.c
index 039e0f91dba8..6945c3c96637 100644
--- a/drivers/firmware/qemu_fw_cfg.c
+++ b/drivers/firmware/qemu_fw_cfg.c
@@ -605,8 +605,10 @@ static int fw_cfg_register_file(const struct fw_cfg_file *f)
 	/* register entry under "/sys/firmware/qemu_fw_cfg/by_key/" */
 	err = kobject_init_and_add(&entry->kobj, &fw_cfg_sysfs_entry_ktype,
 				   fw_cfg_sel_ko, "%d", entry->select);
-	if (err)
-		goto err_register;
+	if (err) {
+		kobject_put(&entry->kobj);
+		return err;
+	}
 
 	/* add raw binary content access */
 	err = sysfs_create_bin_file(&entry->kobj, &fw_cfg_sysfs_attr_raw);
@@ -622,7 +624,6 @@ static int fw_cfg_register_file(const struct fw_cfg_file *f)
 
 err_add_raw:
 	kobject_del(&entry->kobj);
-err_register:
 	kfree(entry);
 	return err;
 }
diff --git a/drivers/fpga/dfl-afu-dma-region.c b/drivers/fpga/dfl-afu-dma-region.c
index dcd80b088c7b..652035aea7c1 100644
--- a/drivers/fpga/dfl-afu-dma-region.c
+++ b/drivers/fpga/dfl-afu-dma-region.c
@@ -106,10 +106,10 @@ static int afu_dma_pin_pages(struct dfl_feature_platform_data *pdata,
 				     region->pages);
 	if (pinned < 0) {
 		ret = pinned;
-		goto put_pages;
+		goto free_pages;
 	} else if (pinned != npages) {
 		ret = -EFAULT;
-		goto free_pages;
+		goto put_pages;
 	}
 
 	dev_dbg(dev, "%d pages pinned\n", pinned);
diff --git a/drivers/fpga/dfl-afu-main.c b/drivers/fpga/dfl-afu-main.c
index 02baa6a227c0..fc048f9a99b1 100644
--- a/drivers/fpga/dfl-afu-main.c
+++ b/drivers/fpga/dfl-afu-main.c
@@ -79,7 +79,8 @@ static int port_disable(struct platform_device *pdev)
 	 * on this port and minimum soft reset pulse width has elapsed.
 	 * Driver polls port_soft_reset_ack to determine if reset done by HW.
 	 */
-	if (readq_poll_timeout(base + PORT_HDR_CTRL, v, v & PORT_CTRL_SFTRST,
+	if (readq_poll_timeout(base + PORT_HDR_CTRL, v,
+			       v & PORT_CTRL_SFTRST_ACK,
 			       RST_POLL_INVL, RST_POLL_TIMEOUT)) {
 		dev_err(&pdev->dev, "timeout, fail to reset device\n");
 		return -ETIMEDOUT;
diff --git a/drivers/gnss/sirf.c b/drivers/gnss/sirf.c
index effed3a8d398..2ecb1d3e8eeb 100644
--- a/drivers/gnss/sirf.c
+++ b/drivers/gnss/sirf.c
@@ -439,14 +439,18 @@ static int sirf_probe(struct serdev_device *serdev)
 
 	data->on_off = devm_gpiod_get_optional(dev, "sirf,onoff",
 			GPIOD_OUT_LOW);
-	if (IS_ERR(data->on_off))
+	if (IS_ERR(data->on_off)) {
+		ret = PTR_ERR(data->on_off);
 		goto err_put_device;
+	}
 
 	if (data->on_off) {
 		data->wakeup = devm_gpiod_get_optional(dev, "sirf,wakeup",
 				GPIOD_IN);
-		if (IS_ERR(data->wakeup))
+		if (IS_ERR(data->wakeup)) {
+			ret = PTR_ERR(data->wakeup);
 			goto err_put_device;
+		}
 
 		ret = regulator_enable(data->vcc);
 		if (ret)
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 44ebb0b186f1..2d8b848279ed 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -1119,6 +1119,7 @@ config GPIO_MADERA
 config GPIO_MAX77620
 	tristate "GPIO support for PMIC MAX77620 and MAX20024"
 	depends on MFD_MAX77620
+	select GPIOLIB_IRQCHIP
 	help
 	  GPIO driver for MAX77620 and MAX20024 PMIC from Maxim Semiconductor.
 	  MAX77620 PMIC has 8 pins that can be configured as GPIOs. The
diff --git a/drivers/gpio/gpio-arizona.c b/drivers/gpio/gpio-arizona.c
index c07fad975049..6e192581495b 100644
--- a/drivers/gpio/gpio-arizona.c
+++ b/drivers/gpio/gpio-arizona.c
@@ -64,6 +64,7 @@ static int arizona_gpio_get(struct gpio_chip *chip, unsigned offset)
 		ret = pm_runtime_get_sync(chip->parent);
 		if (ret < 0) {
 			dev_err(chip->parent, "Failed to resume: %d\n", ret);
+			pm_runtime_put_autosuspend(chip->parent);
 			return ret;
 		}
 
@@ -72,12 +73,15 @@ static int arizona_gpio_get(struct gpio_chip *chip, unsigned offset)
 		if (ret < 0) {
 			dev_err(chip->parent, "Failed to drop cache: %d\n",
 				ret);
+			pm_runtime_put_autosuspend(chip->parent);
 			return ret;
 		}
 
 		ret = regmap_read(arizona->regmap, reg, &val);
-		if (ret < 0)
+		if (ret < 0) {
+			pm_runtime_put_autosuspend(chip->parent);
 			return ret;
+		}
 
 		pm_runtime_mark_last_busy(chip->parent);
 		pm_runtime_put_autosuspend(chip->parent);
@@ -106,6 +110,7 @@ static int arizona_gpio_direction_out(struct gpio_chip *chip,
 		ret = pm_runtime_get_sync(chip->parent);
 		if (ret < 0) {
 			dev_err(chip->parent, "Failed to resume: %d\n", ret);
+			pm_runtime_put(chip->parent);
 			return ret;
 		}
 	}
diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c
index 9fa6d3a967d2..100575973e1f 100644
--- a/drivers/gpio/gpio-bcm-kona.c
+++ b/drivers/gpio/gpio-bcm-kona.c
@@ -619,7 +619,7 @@ static int bcm_kona_gpio_probe(struct platform_device *pdev)
 
 	kona_gpio->reg_base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(kona_gpio->reg_base)) {
-		ret = -ENXIO;
+		ret = PTR_ERR(kona_gpio->reg_base);
 		goto err_irq_domain;
 	}
 
diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c
index 3108be5e208c..b66159748868 100644
--- a/drivers/gpio/gpio-dwapb.c
+++ b/drivers/gpio/gpio-dwapb.c
@@ -48,7 +48,9 @@
 #define GPIO_EXT_PORTC		0x58
 #define GPIO_EXT_PORTD		0x5c
 
+#define DWAPB_DRIVER_NAME	"gpio-dwapb"
 #define DWAPB_MAX_PORTS		4
+
 #define GPIO_EXT_PORT_STRIDE	0x04 /* register stride 32 bits */
 #define GPIO_SWPORT_DR_STRIDE	0x0c /* register stride 3*32 bits */
 #define GPIO_SWPORT_DDR_STRIDE	0x0c /* register stride 3*32 bits */
@@ -397,7 +399,7 @@ static void dwapb_configure_irqs(struct dwapb_gpio *gpio,
 		return;
 
 	err = irq_alloc_domain_generic_chips(gpio->domain, ngpio, 2,
-					     "gpio-dwapb", handle_level_irq,
+					     DWAPB_DRIVER_NAME, handle_level_irq,
 					     IRQ_NOREQUEST, 0,
 					     IRQ_GC_INIT_NESTED_LOCK);
 	if (err) {
@@ -454,7 +456,7 @@ static void dwapb_configure_irqs(struct dwapb_gpio *gpio,
 		 */
 		err = devm_request_irq(gpio->dev, pp->irq[0],
 				       dwapb_irq_handler_mfd,
-				       IRQF_SHARED, "gpio-dwapb-mfd", gpio);
+				       IRQF_SHARED, DWAPB_DRIVER_NAME, gpio);
 		if (err) {
 			dev_err(gpio->dev, "error requesting IRQ\n");
 			irq_domain_remove(gpio->domain);
@@ -532,26 +534,33 @@ static int dwapb_gpio_add_port(struct dwapb_gpio *gpio,
 		dwapb_configure_irqs(gpio, port, pp);
 
 	err = gpiochip_add_data(&port->gc, port);
-	if (err)
+	if (err) {
 		dev_err(gpio->dev, "failed to register gpiochip for port%d\n",
 			port->idx);
-	else
-		port->is_registered = true;
+		return err;
+	}
 
 	/* Add GPIO-signaled ACPI event support */
-	if (pp->has_irq)
-		acpi_gpiochip_request_interrupts(&port->gc);
+	acpi_gpiochip_request_interrupts(&port->gc);
 
-	return err;
+	port->is_registered = true;
+
+	return 0;
 }
 
 static void dwapb_gpio_unregister(struct dwapb_gpio *gpio)
 {
 	unsigned int m;
 
-	for (m = 0; m < gpio->nr_ports; ++m)
-		if (gpio->ports[m].is_registered)
-			gpiochip_remove(&gpio->ports[m].gc);
+	for (m = 0; m < gpio->nr_ports; ++m) {
+		struct dwapb_gpio_port *port = &gpio->ports[m];
+
+		if (!port->is_registered)
+			continue;
+
+		acpi_gpiochip_free_interrupts(&port->gc);
+		gpiochip_remove(&port->gc);
+	}
 }
 
 static struct dwapb_platform_data *
@@ -835,7 +844,7 @@ static SIMPLE_DEV_PM_OPS(dwapb_gpio_pm_ops, dwapb_gpio_suspend,
 
 static struct platform_driver dwapb_gpio_driver = {
 	.driver		= {
-		.name	= "gpio-dwapb",
+		.name	= DWAPB_DRIVER_NAME,
 		.pm	= &dwapb_gpio_pm_ops,
 		.of_match_table = of_match_ptr(dwapb_of_match),
 		.acpi_match_table = ACPI_PTR(dwapb_acpi_match),
@@ -849,3 +858,4 @@ module_platform_driver(dwapb_gpio_driver);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jamie Iles");
 MODULE_DESCRIPTION("Synopsys DesignWare APB GPIO driver");
+MODULE_ALIAS("platform:" DWAPB_DRIVER_NAME);
diff --git a/drivers/gpio/gpio-exar.c b/drivers/gpio/gpio-exar.c
index fae327d5b06e..6890d32d9f25 100644
--- a/drivers/gpio/gpio-exar.c
+++ b/drivers/gpio/gpio-exar.c
@@ -145,8 +145,10 @@ static int gpio_exar_probe(struct platform_device *pdev)
 	mutex_init(&exar_gpio->lock);
 
 	index = ida_simple_get(&ida_index, 0, 0, GFP_KERNEL);
-	if (index < 0)
-		goto err_destroy;
+	if (index < 0) {
+		ret = index;
+		goto err_mutex_destroy;
+	}
 
 	sprintf(exar_gpio->name, "exar_gpio%d", index);
 	exar_gpio->gpio_chip.label = exar_gpio->name;
@@ -173,6 +175,7 @@ static int gpio_exar_probe(struct platform_device *pdev)
 
 err_destroy:
 	ida_simple_remove(&ida_index, index);
+err_mutex_destroy:
 	mutex_destroy(&exar_gpio->lock);
 	return ret;
 }
diff --git a/drivers/gpio/gpio-grgpio.c b/drivers/gpio/gpio-grgpio.c
index 7df48e76baea..ecab6cfd1de1 100644
--- a/drivers/gpio/gpio-grgpio.c
+++ b/drivers/gpio/gpio-grgpio.c
@@ -253,17 +253,16 @@ static int grgpio_irq_map(struct irq_domain *d, unsigned int irq,
 	lirq->irq = irq;
 	uirq = &priv->uirqs[lirq->index];
 	if (uirq->refcnt == 0) {
+		spin_unlock_irqrestore(&priv->gc.bgpio_lock, flags);
 		ret = request_irq(uirq->uirq, grgpio_irq_handler, 0,
 				  dev_name(priv->dev), priv);
 		if (ret) {
 			dev_err(priv->dev,
 				"Could not request underlying irq %d\n",
 				uirq->uirq);
-
-			spin_unlock_irqrestore(&priv->gc.bgpio_lock, flags);
-
 			return ret;
 		}
+		spin_lock_irqsave(&priv->gc.bgpio_lock, flags);
 	}
 	uirq->refcnt++;
 
@@ -309,8 +308,11 @@ static void grgpio_irq_unmap(struct irq_domain *d, unsigned int irq)
 	if (index >= 0) {
 		uirq = &priv->uirqs[lirq->index];
 		uirq->refcnt--;
-		if (uirq->refcnt == 0)
+		if (uirq->refcnt == 0) {
+			spin_unlock_irqrestore(&priv->gc.bgpio_lock, flags);
 			free_irq(uirq->uirq, priv);
+			return;
+		}
 	}
 
 	spin_unlock_irqrestore(&priv->gc.bgpio_lock, flags);
diff --git a/drivers/gpio/gpio-mpc8xxx.c b/drivers/gpio/gpio-mpc8xxx.c
index 3f10f9599f2c..1899d172590b 100644
--- a/drivers/gpio/gpio-mpc8xxx.c
+++ b/drivers/gpio/gpio-mpc8xxx.c
@@ -317,6 +317,7 @@ static int mpc8xxx_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	gc = &mpc8xxx_gc->gc;
+	gc->parent = &pdev->dev;
 
 	if (of_property_read_bool(np, "little-endian")) {
 		ret = bgpio_init(gc, &pdev->dev, 4,
diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index 96d42f571a18..bf35f7f8901d 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -106,6 +106,84 @@ static const struct i2c_device_id pca953x_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, pca953x_id);
 
+#ifdef CONFIG_GPIO_PCA953X_IRQ
+
+#include <linux/dmi.h>
+#include <linux/gpio.h>
+#include <linux/list.h>
+
+static const struct dmi_system_id pca953x_dmi_acpi_irq_info[] = {
+	{
+		/*
+		 * On Intel Galileo Gen 2 board the IRQ pin of one of
+		 * the I²C GPIO expanders, which has GpioInt() resource,
+		 * is provided as an absolute number instead of being
+		 * relative. Since first controller (gpio-sch.c) and
+		 * second (gpio-dwapb.c) are at the fixed bases, we may
+		 * safely refer to the number in the global space to get
+		 * an IRQ out of it.
+		 */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_BOARD_NAME, "GalileoGen2"),
+		},
+	},
+	{}
+};
+
+#ifdef CONFIG_ACPI
+static int pca953x_acpi_get_pin(struct acpi_resource *ares, void *data)
+{
+	struct acpi_resource_gpio *agpio;
+	int *pin = data;
+
+	if (acpi_gpio_get_irq_resource(ares, &agpio))
+		*pin = agpio->pin_table[0];
+	return 1;
+}
+
+static int pca953x_acpi_find_pin(struct device *dev)
+{
+	struct acpi_device *adev = ACPI_COMPANION(dev);
+	int pin = -ENOENT, ret;
+	LIST_HEAD(r);
+
+	ret = acpi_dev_get_resources(adev, &r, pca953x_acpi_get_pin, &pin);
+	acpi_dev_free_resource_list(&r);
+	if (ret < 0)
+		return ret;
+
+	return pin;
+}
+#else
+static inline int pca953x_acpi_find_pin(struct device *dev) { return -ENXIO; }
+#endif
+
+static int pca953x_acpi_get_irq(struct device *dev)
+{
+	int pin, ret;
+
+	pin = pca953x_acpi_find_pin(dev);
+	if (pin < 0)
+		return pin;
+
+	dev_info(dev, "Applying ACPI interrupt quirk (GPIO %d)\n", pin);
+
+	if (!gpio_is_valid(pin))
+		return -EINVAL;
+
+	ret = gpio_request(pin, "pca953x interrupt");
+	if (ret)
+		return ret;
+
+	ret = gpio_to_irq(pin);
+
+	/* When pin is used as an IRQ, no need to keep it requested */
+	gpio_free(pin);
+
+	return ret;
+}
+#endif
+
 static const struct acpi_device_id pca953x_acpi_ids[] = {
 	{ "INT3491", 16 | PCA953X_TYPE | PCA_LATCH_INT, },
 	{ }
@@ -305,8 +383,23 @@ static const struct regmap_config pca953x_i2c_regmap = {
 	.volatile_reg = pca953x_volatile_register,
 
 	.cache_type = REGCACHE_RBTREE,
-	/* REVISIT: should be 0x7f but some 24 bit chips use REG_ADDR_AI */
-	.max_register = 0xff,
+	.max_register = 0x7f,
+};
+
+static const struct regmap_config pca953x_ai_i2c_regmap = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.read_flag_mask = REG_ADDR_AI,
+	.write_flag_mask = REG_ADDR_AI,
+
+	.readable_reg = pca953x_readable_register,
+	.writeable_reg = pca953x_writeable_register,
+	.volatile_reg = pca953x_volatile_register,
+
+	.disable_locking = true,
+	.cache_type = REGCACHE_RBTREE,
+	.max_register = 0x7f,
 };
 
 static u8 pca953x_recalc_addr(struct pca953x_chip *chip, int reg, int off,
@@ -317,18 +410,6 @@ static u8 pca953x_recalc_addr(struct pca953x_chip *chip, int reg, int off,
 	int pinctrl = (reg & PCAL_PINCTRL_MASK) << 1;
 	u8 regaddr = pinctrl | addr | (off / BANK_SZ);
 
-	/* Single byte read doesn't need AI bit set. */
-	if (!addrinc)
-		return regaddr;
-
-	/* Chips with 24 and more GPIOs always support Auto Increment */
-	if (write && NBANK(chip) > 2)
-		regaddr |= REG_ADDR_AI;
-
-	/* PCA9575 needs address-increment on multi-byte writes */
-	if (PCA_CHIP_TYPE(chip->driver_data) == PCA957X_TYPE)
-		regaddr |= REG_ADDR_AI;
-
 	return regaddr;
 }
 
@@ -527,7 +608,7 @@ static int pca953x_gpio_set_config(struct gpio_chip *gc, unsigned int offset,
 {
 	struct pca953x_chip *chip = gpiochip_get_data(gc);
 
-	switch (config) {
+	switch (pinconf_to_config_param(config)) {
 	case PIN_CONFIG_BIAS_PULL_UP:
 	case PIN_CONFIG_BIAS_PULL_DOWN:
 		return pca953x_gpio_set_pull_up_down(chip, offset, config);
@@ -769,6 +850,12 @@ static int pca953x_irq_setup(struct pca953x_chip *chip,
 	u8 reg_direction[MAX_BANK];
 	int ret, i;
 
+	if (dmi_first_match(pca953x_dmi_acpi_irq_info)) {
+		ret = pca953x_acpi_get_irq(&client->dev);
+		if (ret > 0)
+			client->irq = ret;
+	}
+
 	if (!client->irq)
 		return 0;
 
@@ -896,6 +983,7 @@ static int pca953x_probe(struct i2c_client *client,
 	int ret;
 	u32 invert = 0;
 	struct regulator *reg;
+	const struct regmap_config *regmap_config;
 
 	chip = devm_kzalloc(&client->dev,
 			sizeof(struct pca953x_chip), GFP_KERNEL);
@@ -963,7 +1051,17 @@ static int pca953x_probe(struct i2c_client *client,
 
 	i2c_set_clientdata(client, chip);
 
-	chip->regmap = devm_regmap_init_i2c(client, &pca953x_i2c_regmap);
+	pca953x_setup_gpio(chip, chip->driver_data & PCA_GPIO_MASK);
+
+	if (NBANK(chip) > 2 || PCA_CHIP_TYPE(chip->driver_data) == PCA957X_TYPE) {
+		dev_info(&client->dev, "using AI\n");
+		regmap_config = &pca953x_ai_i2c_regmap;
+	} else {
+		dev_info(&client->dev, "using no AI\n");
+		regmap_config = &pca953x_i2c_regmap;
+	}
+
+	chip->regmap = devm_regmap_init_i2c(client, regmap_config);
 	if (IS_ERR(chip->regmap)) {
 		ret = PTR_ERR(chip->regmap);
 		goto err_exit;
@@ -994,7 +1092,6 @@ static int pca953x_probe(struct i2c_client *client,
 	/* initialize cached registers from their original values.
 	 * we can't share this chip with another i2c master.
 	 */
-	pca953x_setup_gpio(chip, chip->driver_data & PCA_GPIO_MASK);
 
 	if (PCA_CHIP_TYPE(chip->driver_data) == PCA953X_TYPE) {
 		chip->regs = &pca953x_regs;
diff --git a/drivers/gpio/gpio-pxa.c b/drivers/gpio/gpio-pxa.c
index 9888b62f37af..432c487f77b4 100644
--- a/drivers/gpio/gpio-pxa.c
+++ b/drivers/gpio/gpio-pxa.c
@@ -663,8 +663,8 @@ static int pxa_gpio_probe(struct platform_device *pdev)
 	pchip->irq1 = irq1;
 
 	gpio_reg_base = devm_platform_ioremap_resource(pdev, 0);
-	if (!gpio_reg_base)
-		return -EINVAL;
+	if (IS_ERR(gpio_reg_base))
+		return PTR_ERR(gpio_reg_base);
 
 	clk = clk_get(&pdev->dev, NULL);
 	if (IS_ERR(clk)) {
diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c
index f57bfc07ae22..9985e8bb4624 100644
--- a/drivers/gpio/gpio-tegra.c
+++ b/drivers/gpio/gpio-tegra.c
@@ -365,6 +365,7 @@ static void tegra_gpio_irq_shutdown(struct irq_data *d)
 	struct tegra_gpio_info *tgi = bank->tgi;
 	unsigned int gpio = d->hwirq;
 
+	tegra_gpio_irq_mask(d);
 	gpiochip_unlock_as_irq(&tgi->gc, gpio);
 }
 
diff --git a/drivers/gpio/gpio-xilinx.c b/drivers/gpio/gpio-xilinx.c
index 32944eb886c1..0852d8d5c389 100644
--- a/drivers/gpio/gpio-xilinx.c
+++ b/drivers/gpio/gpio-xilinx.c
@@ -149,9 +149,10 @@ static void xgpio_set_multiple(struct gpio_chip *gc, unsigned long *mask,
 	for (i = 0; i < gc->ngpio; i++) {
 		if (*mask == 0)
 			break;
+		/* Once finished with an index write it out to the register */
 		if (index !=  xgpio_index(chip, i)) {
 			xgpio_writereg(mm_gc->regs + XGPIO_DATA_OFFSET +
-				       xgpio_regoffset(chip, i),
+				       index * XGPIO_CHANNEL_OFFSET,
 				       chip->gpio_state[index]);
 			spin_unlock_irqrestore(&chip->gpio_lock[index], flags);
 			index =  xgpio_index(chip, i);
@@ -167,7 +168,7 @@ static void xgpio_set_multiple(struct gpio_chip *gc, unsigned long *mask,
 	}
 
 	xgpio_writereg(mm_gc->regs + XGPIO_DATA_OFFSET +
-		       xgpio_regoffset(chip, i), chip->gpio_state[index]);
+		       index * XGPIO_CHANNEL_OFFSET, chip->gpio_state[index]);
 
 	spin_unlock_irqrestore(&chip->gpio_lock[index], flags);
 }
diff --git a/drivers/gpio/gpio-xtensa.c b/drivers/gpio/gpio-xtensa.c
index 43d3fa5f511a..0fb2211f9573 100644
--- a/drivers/gpio/gpio-xtensa.c
+++ b/drivers/gpio/gpio-xtensa.c
@@ -44,15 +44,14 @@ static inline unsigned long enable_cp(unsigned long *cpenable)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	RSR_CPENABLE(*cpenable);
-	WSR_CPENABLE(*cpenable | BIT(XCHAL_CP_ID_XTIOP));
-
+	*cpenable = xtensa_get_sr(cpenable);
+	xtensa_set_sr(*cpenable | BIT(XCHAL_CP_ID_XTIOP), cpenable);
 	return flags;
 }
 
 static inline void disable_cp(unsigned long flags, unsigned long cpenable)
 {
-	WSR_CPENABLE(cpenable);
+	xtensa_set_sr(cpenable, cpenable);
 	local_irq_restore(flags);
 }
 
diff --git a/drivers/gpio/gpio-zynq.c b/drivers/gpio/gpio-zynq.c
index f241b6c13dbe..211728c8ede2 100644
--- a/drivers/gpio/gpio-zynq.c
+++ b/drivers/gpio/gpio-zynq.c
@@ -681,6 +681,8 @@ static void zynq_gpio_restore_context(struct zynq_gpio *gpio)
 	unsigned int bank_num;
 
 	for (bank_num = 0; bank_num < gpio->p_data->max_bank; bank_num++) {
+		writel_relaxed(ZYNQ_GPIO_IXR_DISABLE_ALL, gpio->base_addr +
+				ZYNQ_GPIO_INTDIS_OFFSET(bank_num));
 		writel_relaxed(gpio->context.datalsw[bank_num],
 			       gpio->base_addr +
 			       ZYNQ_GPIO_DATA_LSW_OFFSET(bank_num));
@@ -690,9 +692,6 @@ static void zynq_gpio_restore_context(struct zynq_gpio *gpio)
 		writel_relaxed(gpio->context.dirm[bank_num],
 			       gpio->base_addr +
 			       ZYNQ_GPIO_DIRM_OFFSET(bank_num));
-		writel_relaxed(gpio->context.int_en[bank_num],
-			       gpio->base_addr +
-			       ZYNQ_GPIO_INTEN_OFFSET(bank_num));
 		writel_relaxed(gpio->context.int_type[bank_num],
 			       gpio->base_addr +
 			       ZYNQ_GPIO_INTTYPE_OFFSET(bank_num));
@@ -702,6 +701,9 @@ static void zynq_gpio_restore_context(struct zynq_gpio *gpio)
 		writel_relaxed(gpio->context.int_any[bank_num],
 			       gpio->base_addr +
 			       ZYNQ_GPIO_INTANY_OFFSET(bank_num));
+		writel_relaxed(~(gpio->context.int_en[bank_num]),
+			       gpio->base_addr +
+			       ZYNQ_GPIO_INTEN_OFFSET(bank_num));
 	}
 }
 
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 4d5c285c46f8..4cbe32962815 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -1295,11 +1295,28 @@ late_initcall_sync(acpi_gpio_handle_deferred_request_irqs);
 
 static const struct dmi_system_id run_edge_events_on_boot_blacklist[] = {
 	{
+		/*
+		 * The Minix Neo Z83-4 has a micro-USB-B id-pin handler for
+		 * a non existing micro-USB-B connector which puts the HDMI
+		 * DDC pins in GPIO mode, breaking HDMI support.
+		 */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "MINIX"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Z83-4"),
 		}
 	},
+	{
+		/*
+		 * The Terra Pad 1061 has a micro-USB-B id-pin handler, which
+		 * instead of controlling the actual micro-USB-B turns the 5V
+		 * boost for its USB-A connector off. The actual micro-USB-B
+		 * connector is wired for charging only.
+		 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Wortmann_AG"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "TERRA_PAD_1061"),
+		}
+	},
 	{} /* Terminating entry */
 };
 
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index c9325efc1783..4d894e004484 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -74,10 +74,6 @@ static void of_gpio_flags_quirks(struct device_node *np,
 			if (of_property_read_bool(np, "cd-inverted"))
 				*flags ^= OF_GPIO_ACTIVE_LOW;
 		}
-		if (!strcmp(propname, "wp-gpios")) {
-			if (of_property_read_bool(np, "wp-inverted"))
-				*flags ^= OF_GPIO_ACTIVE_LOW;
-		}
 	}
 	/*
 	 * Some GPIO fixed regulator quirks.
@@ -718,16 +714,13 @@ int of_gpiochip_add(struct gpio_chip *chip)
 	of_node_get(chip->of_node);
 
 	status = of_gpiochip_scan_gpios(chip);
-	if (status) {
+	if (status)
 		of_node_put(chip->of_node);
-		gpiochip_remove_pin_ranges(chip);
-	}
 
 	return status;
 }
 
 void of_gpiochip_remove(struct gpio_chip *chip)
 {
-	gpiochip_remove_pin_ranges(chip);
 	of_node_put(chip->of_node);
 }
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index e806cd9a14ba..b393dbab1844 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -218,6 +218,14 @@ int gpiod_get_direction(struct gpio_desc *desc)
 	chip = gpiod_to_chip(desc);
 	offset = gpio_chip_hwgpio(desc);
 
+	/*
+	 * Open drain emulation using input mode may incorrectly report
+	 * input here, fix that up.
+	 */
+	if (test_bit(FLAG_OPEN_DRAIN, &desc->flags) &&
+	    test_bit(FLAG_IS_OUT, &desc->flags))
+		return 0;
+
 	if (!chip->get_direction)
 		return -ENOTSUPP;
 
@@ -1444,6 +1452,7 @@ err_remove_of_chip:
 	gpiochip_free_hogs(chip);
 	of_gpiochip_remove(chip);
 err_free_gpiochip_mask:
+	gpiochip_remove_pin_ranges(chip);
 	gpiochip_free_valid_mask(chip);
 err_remove_from_list:
 	spin_lock_irqsave(&gpio_lock, flags);
@@ -1499,8 +1508,8 @@ void gpiochip_remove(struct gpio_chip *chip)
 	gdev->chip = NULL;
 	gpiochip_irqchip_remove(chip);
 	acpi_gpiochip_remove(chip);
-	gpiochip_remove_pin_ranges(chip);
 	of_gpiochip_remove(chip);
+	gpiochip_remove_pin_ranges(chip);
 	gpiochip_free_valid_mask(chip);
 	/*
 	 * We accept no more calls into the driver from this point, so
@@ -1875,9 +1884,16 @@ static void gpiochip_irq_disable(struct irq_data *d)
 {
 	struct gpio_chip *chip = irq_data_get_irq_chip_data(d);
 
+	/*
+	 * Since we override .irq_disable() we need to mimic the
+	 * behaviour of __irq_disable() in irq/chip.c.
+	 * First call .irq_disable() if it exists, else mimic the
+	 * behaviour of mask_irq() which calls .irq_mask() if
+	 * it exists.
+	 */
 	if (chip->irq.irq_disable)
 		chip->irq.irq_disable(d);
-	else
+	else if (chip->irq.chip->irq_mask)
 		chip->irq.chip->irq_mask(d);
 	gpiochip_disable_irq(chip, d->hwirq);
 }
@@ -2869,6 +2885,17 @@ int gpiod_is_active_low(const struct gpio_desc *desc)
 }
 EXPORT_SYMBOL_GPL(gpiod_is_active_low);
 
+/**
+ * gpiod_toggle_active_low - toggle whether a GPIO is active-low or not
+ * @desc: the gpio descriptor to change
+ */
+void gpiod_toggle_active_low(struct gpio_desc *desc)
+{
+	VALIDATE_DESC_VOID(desc);
+	change_bit(FLAG_ACTIVE_LOW, &desc->flags);
+}
+EXPORT_SYMBOL_GPL(gpiod_toggle_active_low);
+
 /* I/O calls are only valid after configuration completed; the relevant
  * "is this a valid GPIO" error checks should already have been done.
  *
@@ -3982,8 +4009,9 @@ static struct gpio_desc *gpiod_find(struct device *dev, const char *con_id,
 
 		if (chip->ngpio <= p->chip_hwnum) {
 			dev_err(dev,
-				"requested GPIO %d is out of range [0..%d] for chip %s\n",
-				idx, chip->ngpio, chip->label);
+				"requested GPIO %u (%u) is out of range [0..%u] for chip %s\n",
+				idx, p->chip_hwnum, chip->ngpio - 1,
+				chip->label);
 			return ERR_PTR(-EINVAL);
 		}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
index e02781b37e73..5cc4c6336d16 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
@@ -338,17 +338,9 @@ bool amdgpu_atombios_get_connector_info_from_object_table(struct amdgpu_device *
 		path_size += le16_to_cpu(path->usSize);
 
 		if (device_support & le16_to_cpu(path->usDeviceTag)) {
-			uint8_t con_obj_id, con_obj_num, con_obj_type;
-
-			con_obj_id =
+			uint8_t con_obj_id =
 			    (le16_to_cpu(path->usConnObjectId) & OBJECT_ID_MASK)
 			    >> OBJECT_ID_SHIFT;
-			con_obj_num =
-			    (le16_to_cpu(path->usConnObjectId) & ENUM_ID_MASK)
-			    >> ENUM_ID_SHIFT;
-			con_obj_type =
-			    (le16_to_cpu(path->usConnObjectId) &
-			     OBJECT_TYPE_MASK) >> OBJECT_TYPE_SHIFT;
 
 			/* Skip TV/CV support */
 			if ((le16_to_cpu(path->usDeviceTag) ==
@@ -373,15 +365,7 @@ bool amdgpu_atombios_get_connector_info_from_object_table(struct amdgpu_device *
 			router.ddc_valid = false;
 			router.cd_valid = false;
 			for (j = 0; j < ((le16_to_cpu(path->usSize) - 8) / 2); j++) {
-				uint8_t grph_obj_id, grph_obj_num, grph_obj_type;
-
-				grph_obj_id =
-				    (le16_to_cpu(path->usGraphicObjIds[j]) &
-				     OBJECT_ID_MASK) >> OBJECT_ID_SHIFT;
-				grph_obj_num =
-				    (le16_to_cpu(path->usGraphicObjIds[j]) &
-				     ENUM_ID_MASK) >> ENUM_ID_SHIFT;
-				grph_obj_type =
+				uint8_t grph_obj_type =
 				    (le16_to_cpu(path->usGraphicObjIds[j]) &
 				     OBJECT_TYPE_MASK) >> OBJECT_TYPE_SHIFT;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index f96d75c6e099..e126e02e2c49 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -139,6 +139,7 @@ int amdgpu_atomfirmware_get_vram_width(struct amdgpu_device *adev)
 			(mode_info->atom_context->bios + data_offset);
 		switch (crev) {
 		case 11:
+		case 12:
 			return igp_info->v11.umachannelnumber * 64;
 		default:
 			return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index 91bfb24f963e..9d7d47f348f4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -690,11 +690,11 @@ static ssize_t amdgpu_debugfs_gpr_read(struct file *f, char __user *buf,
 	ssize_t result = 0;
 	uint32_t offset, se, sh, cu, wave, simd, thread, bank, *data;
 
-	if (size & 3 || *pos & 3)
+	if (size > 4096 || size & 3 || *pos & 3)
 		return -EINVAL;
 
 	/* decode offset */
-	offset = *pos & GENMASK_ULL(11, 0);
+	offset = (*pos & GENMASK_ULL(11, 0)) >> 2;
 	se = (*pos & GENMASK_ULL(19, 12)) >> 12;
 	sh = (*pos & GENMASK_ULL(27, 20)) >> 20;
 	cu = (*pos & GENMASK_ULL(35, 28)) >> 28;
@@ -725,7 +725,7 @@ static ssize_t amdgpu_debugfs_gpr_read(struct file *f, char __user *buf,
 	while (size) {
 		uint32_t value;
 
-		value = data[offset++];
+		value = data[result >> 2];
 		r = put_user(value, (uint32_t *)buf);
 		if (r) {
 			result = r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index f4ac632a87b2..4ae260e268a4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2849,8 +2849,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
 		}
 	}
 
-	amdgpu_amdkfd_suspend(adev);
-
 	r = amdgpu_device_ip_suspend_phase1(adev);
 
 	/* evict vram memory */
@@ -2860,6 +2858,8 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
 
 	r = amdgpu_device_ip_suspend_phase2(adev);
 
+	amdgpu_amdkfd_suspend(adev);
+
 	/* evict remaining vram memory
 	 * This second call to evict vram is to evict the gart page table
 	 * using the CPU.
@@ -3238,8 +3238,6 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 	if (r)
 		return r;
 
-	amdgpu_amdkfd_pre_reset(adev);
-
 	/* Resume IP prior to SMC */
 	r = amdgpu_device_ip_reinit_early_sriov(adev);
 	if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 89fdb217c66f..fb168884900e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1263,7 +1263,7 @@ amdgpu_get_crtc_scanout_position(struct drm_device *dev, unsigned int pipe,
 
 static struct drm_driver kms_driver = {
 	.driver_features =
-	    DRIVER_USE_AGP | DRIVER_ATOMIC |
+	    DRIVER_ATOMIC |
 	    DRIVER_GEM |
 	    DRIVER_PRIME | DRIVER_RENDER | DRIVER_MODESET | DRIVER_SYNCOBJ,
 	.load = amdgpu_driver_load_kms,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
index bf0c61baa05c..39528260eb0f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
@@ -143,8 +143,7 @@ static int amdgpufb_create_pinned_object(struct amdgpu_fbdev *rfbdev,
 	ret = amdgpu_gem_object_create(adev, aligned_size, 0, domain,
 				       AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
 				       AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS     |
-				       AMDGPU_GEM_CREATE_VRAM_CLEARED 	     |
-				       AMDGPU_GEM_CREATE_CPU_GTT_USWC,
+				       AMDGPU_GEM_CREATE_VRAM_CLEARED,
 				       ttm_bo_type_kernel, NULL, &gobj);
 	if (ret) {
 		pr_err("failed to allocate framebuffer (%d)\n", aligned_size);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 4dee2326b29c..04ef5a264f7b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -402,7 +402,9 @@ int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
 		ring->fence_drv.gpu_addr = adev->uvd.inst[ring->me].gpu_addr + index;
 	}
 	amdgpu_fence_write(ring, atomic_read(&ring->fence_drv.last_seq));
-	amdgpu_irq_get(adev, irq_src, irq_type);
+
+	if (irq_src)
+		amdgpu_irq_get(adev, irq_src, irq_type);
 
 	ring->fence_drv.irq_src = irq_src;
 	ring->fence_drv.irq_type = irq_type;
@@ -514,8 +516,9 @@ void amdgpu_fence_driver_fini(struct amdgpu_device *adev)
 			/* no need to trigger GPU reset as we are unloading */
 			amdgpu_fence_driver_force_completion(ring);
 		}
-		amdgpu_irq_put(adev, ring->fence_drv.irq_src,
-			       ring->fence_drv.irq_type);
+		if (ring->fence_drv.irq_src)
+			amdgpu_irq_put(adev, ring->fence_drv.irq_src,
+				       ring->fence_drv.irq_type);
 		drm_sched_fini(&ring->sched);
 		del_timer_sync(&ring->fence_drv.fallback_timer);
 		for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j)
@@ -551,8 +554,9 @@ void amdgpu_fence_driver_suspend(struct amdgpu_device *adev)
 		}
 
 		/* disable the interrupt */
-		amdgpu_irq_put(adev, ring->fence_drv.irq_src,
-			       ring->fence_drv.irq_type);
+		if (ring->fence_drv.irq_src)
+			amdgpu_irq_put(adev, ring->fence_drv.irq_src,
+				       ring->fence_drv.irq_type);
 	}
 }
 
@@ -578,8 +582,9 @@ void amdgpu_fence_driver_resume(struct amdgpu_device *adev)
 			continue;
 
 		/* enable the interrupt */
-		amdgpu_irq_get(adev, ring->fence_drv.irq_src,
-			       ring->fence_drv.irq_type);
+		if (ring->fence_drv.irq_src)
+			amdgpu_irq_get(adev, ring->fence_drv.irq_src,
+				       ring->fence_drv.irq_type);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
index 071145ac67b5..f1391e612e07 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
@@ -156,6 +156,7 @@ struct amdgpu_gmc {
 	uint32_t                srbm_soft_reset;
 	bool			prt_warning;
 	uint64_t		stolen_size;
+	uint32_t		sdpif_register;
 	/* apertures */
 	u64			shared_aperture_start;
 	u64			shared_aperture_end;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index d637f0534e3b..4b8f478af867 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -36,7 +36,8 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job)
 
 	memset(&ti, 0, sizeof(struct amdgpu_task_info));
 
-	if (amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) {
+	if (amdgpu_gpu_recovery &&
+	    amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) {
 		DRM_ERROR("ring %s timeout, but soft recovered\n",
 			  s_job->sched->name);
 		return;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index b3c9ab4e4a55..fe42c6b5849d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -653,9 +653,10 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		return n ? -EFAULT : 0;
 	}
 	case AMDGPU_INFO_DEV_INFO: {
-		struct drm_amdgpu_info_device dev_info = {};
+		struct drm_amdgpu_info_device dev_info;
 		uint64_t vm_size;
 
+		memset(&dev_info, 0, sizeof(dev_info));
 		dev_info.device_id = dev->pdev->device;
 		dev_info.chip_rev = adev->rev_id;
 		dev_info.external_rev = adev->external_rev_id;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index d55519bc34e5..059f99534d77 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -75,7 +75,8 @@ void amdgpu_pm_acpi_event_handler(struct amdgpu_device *adev)
 			adev->pm.ac_power = true;
 		else
 			adev->pm.ac_power = false;
-		if (adev->powerplay.pp_funcs->enable_bapm)
+		if (adev->powerplay.pp_funcs &&
+		    adev->powerplay.pp_funcs->enable_bapm)
 			amdgpu_dpm_enable_bapm(adev, adev->pm.ac_power);
 		mutex_unlock(&adev->pm.mutex);
 	}
@@ -350,6 +351,15 @@ static ssize_t amdgpu_set_dpm_forced_performance_level(struct device *dev,
 	if (current_level == level)
 		return count;
 
+	if (adev->asic_type == CHIP_RAVEN) {
+		if (adev->rev_id < 8) {
+			if (current_level != AMD_DPM_FORCED_LEVEL_MANUAL && level == AMD_DPM_FORCED_LEVEL_MANUAL)
+				amdgpu_gfx_off_ctrl(adev, false);
+			else if (current_level == AMD_DPM_FORCED_LEVEL_MANUAL && level != AMD_DPM_FORCED_LEVEL_MANUAL)
+				amdgpu_gfx_off_ctrl(adev, true);
+		}
+	}
+
 	/* profile_exit setting is valid only when current mode is in profile mode */
 	if (!(current_level & (AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD |
 	    AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK |
@@ -405,8 +415,11 @@ static ssize_t amdgpu_get_pp_num_states(struct device *dev,
 		ret = smu_get_power_num_states(&adev->smu, &data);
 		if (ret)
 			return ret;
-	} else if (adev->powerplay.pp_funcs->get_pp_num_states)
+	} else if (adev->powerplay.pp_funcs->get_pp_num_states) {
 		amdgpu_dpm_get_pp_num_states(adev, &data);
+	} else {
+		memset(&data, 0, sizeof(data));
+	}
 
 	buf_len = snprintf(buf, PAGE_SIZE, "states: %d\n", data.nums);
 	for (i = 0; i < data.nums; i++)
@@ -1925,7 +1938,7 @@ static ssize_t amdgpu_hwmon_show_sclk(struct device *dev,
 	if (r)
 		return r;
 
-	return snprintf(buf, PAGE_SIZE, "%d\n", sclk * 10 * 1000);
+	return snprintf(buf, PAGE_SIZE, "%u\n", sclk * 10 * 1000);
 }
 
 static ssize_t amdgpu_hwmon_show_sclk_label(struct device *dev,
@@ -1960,7 +1973,7 @@ static ssize_t amdgpu_hwmon_show_mclk(struct device *dev,
 	if (r)
 		return r;
 
-	return snprintf(buf, PAGE_SIZE, "%d\n", mclk * 10 * 1000);
+	return snprintf(buf, PAGE_SIZE, "%u\n", mclk * 10 * 1000);
 }
 
 static ssize_t amdgpu_hwmon_show_mclk_label(struct device *dev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index 7d484fad3909..2adda47def64 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -386,7 +386,8 @@ static uint32_t parse_clk(char *buf, bool min)
                 if (!ptr)
                         break;
                 ptr+=2;
-                clk = simple_strtoul(ptr, NULL, 10);
+		if (kstrtou32(ptr, 10, &clk))
+			return 0;
         } while (!min);
 
         return clk * 100;
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index d42808b05971..490109be9609 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -226,7 +226,7 @@ static void cik_sdma_ring_emit_ib(struct amdgpu_ring *ring,
 	u32 extra_bits = vmid & 0xf;
 
 	/* IB packet must end on a 8 DW boundary */
-	cik_sdma_ring_insert_nop(ring, (12 - (lower_32_bits(ring->wptr) & 7)) % 8);
+	cik_sdma_ring_insert_nop(ring, (4 - lower_32_bits(ring->wptr)) & 7);
 
 	amdgpu_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_INDIRECT_BUFFER, 0, extra_bits));
 	amdgpu_ring_write(ring, ib->gpu_addr & 0xffffffe0); /* base must be 32 byte aligned */
@@ -809,7 +809,7 @@ static void cik_sdma_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib)
 	u32 pad_count;
 	int i;
 
-	pad_count = (8 - (ib->length_dw & 0x7)) % 8;
+	pad_count = (-ib->length_dw) & 7;
 	for (i = 0; i < pad_count; i++)
 		if (sdma && sdma->burst_nop && (i == 0))
 			ib->ptr[ib->length_dw++] =
diff --git a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
index d5ebe566809b..a1c941229f4b 100644
--- a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
+++ b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
@@ -75,23 +75,29 @@ static void df_v3_6_update_medium_grain_clock_gating(struct amdgpu_device *adev,
 {
 	u32 tmp;
 
-	/* Put DF on broadcast mode */
-	adev->df_funcs->enable_broadcast_mode(adev, true);
-
-	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_DF_MGCG)) {
-		tmp = RREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater);
-		tmp &= ~DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK;
-		tmp |= DF_V3_6_MGCG_ENABLE_15_CYCLE_DELAY;
-		WREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater, tmp);
-	} else {
-		tmp = RREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater);
-		tmp &= ~DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK;
-		tmp |= DF_V3_6_MGCG_DISABLE;
-		WREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater, tmp);
+	if (adev->cg_flags & AMD_CG_SUPPORT_DF_MGCG) {
+		/* Put DF on broadcast mode */
+		adev->df_funcs->enable_broadcast_mode(adev, true);
+
+		if (enable) {
+			tmp = RREG32_SOC15(DF, 0,
+					mmDF_PIE_AON0_DfGlobalClkGater);
+			tmp &= ~DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK;
+			tmp |= DF_V3_6_MGCG_ENABLE_15_CYCLE_DELAY;
+			WREG32_SOC15(DF, 0,
+					mmDF_PIE_AON0_DfGlobalClkGater, tmp);
+		} else {
+			tmp = RREG32_SOC15(DF, 0,
+					mmDF_PIE_AON0_DfGlobalClkGater);
+			tmp &= ~DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK;
+			tmp |= DF_V3_6_MGCG_DISABLE;
+			WREG32_SOC15(DF, 0,
+					mmDF_PIE_AON0_DfGlobalClkGater, tmp);
+		}
+
+		/* Exit broadcast mode */
+		adev->df_funcs->enable_broadcast_mode(adev, false);
 	}
-
-	/* Exit broadcast mode */
-	adev->df_funcs->enable_broadcast_mode(adev, false);
 }
 
 static void df_v3_6_get_clockgating_state(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index c21ef99cc590..ba9faf8e67a6 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -6157,7 +6157,23 @@ static void gfx_v8_0_ring_emit_fence_gfx(struct amdgpu_ring *ring, u64 addr,
 	bool write64bit = flags & AMDGPU_FENCE_FLAG_64BIT;
 	bool int_sel = flags & AMDGPU_FENCE_FLAG_INT;
 
-	/* EVENT_WRITE_EOP - flush caches, send int */
+	/* Workaround for cache flush problems. First send a dummy EOP
+	 * event down the pipe with seq one below.
+	 */
+	amdgpu_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE_EOP, 4));
+	amdgpu_ring_write(ring, (EOP_TCL1_ACTION_EN |
+				 EOP_TC_ACTION_EN |
+				 EOP_TC_WB_ACTION_EN |
+				 EVENT_TYPE(CACHE_FLUSH_AND_INV_TS_EVENT) |
+				 EVENT_INDEX(5)));
+	amdgpu_ring_write(ring, addr & 0xfffffffc);
+	amdgpu_ring_write(ring, (upper_32_bits(addr) & 0xffff) |
+				DATA_SEL(1) | INT_SEL(0));
+	amdgpu_ring_write(ring, lower_32_bits(seq - 1));
+	amdgpu_ring_write(ring, upper_32_bits(seq - 1));
+
+	/* Then send the real EOP event down the pipe:
+	 * EVENT_WRITE_EOP - flush caches, send int */
 	amdgpu_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE_EOP, 4));
 	amdgpu_ring_write(ring, (EOP_TCL1_ACTION_EN |
 				 EOP_TC_ACTION_EN |
@@ -6899,7 +6915,7 @@ static const struct amdgpu_ring_funcs gfx_v8_0_ring_funcs_gfx = {
 		5 +  /* COND_EXEC */
 		7 +  /* PIPELINE_SYNC */
 		VI_FLUSH_GPU_TLB_NUM_WREG * 5 + 9 + /* VM_FLUSH */
-		8 +  /* FENCE for VM_FLUSH */
+		12 +  /* FENCE for VM_FLUSH */
 		20 + /* GDS switch */
 		4 + /* double SWITCH_BUFFER,
 		       the first COND_EXEC jump to the place just
@@ -6911,7 +6927,7 @@ static const struct amdgpu_ring_funcs gfx_v8_0_ring_funcs_gfx = {
 		31 + /*	DE_META */
 		3 + /* CNTX_CTRL */
 		5 + /* HDP_INVL */
-		8 + 8 + /* FENCE x2 */
+		12 + 12 + /* FENCE x2 */
 		2, /* SWITCH_BUFFER */
 	.emit_ib_size =	4, /* gfx_v8_0_ring_emit_ib_gfx */
 	.emit_ib = gfx_v8_0_ring_emit_ib_gfx,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 8ccaf26cc29a..9ee23728d335 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -583,6 +583,8 @@ static void gfx_v9_0_check_fw_write_wait(struct amdgpu_device *adev)
 			adev->gfx.mec_fw_write_wait = true;
 		break;
 	default:
+		adev->gfx.me_fw_write_wait = true;
+		adev->gfx.mec_fw_write_wait = true;
 		break;
 	}
 }
@@ -595,17 +597,10 @@ static void gfx_v9_0_check_if_need_gfxoff(struct amdgpu_device *adev)
 	case CHIP_VEGA20:
 		break;
 	case CHIP_RAVEN:
-		/* Disable GFXOFF on original raven.  There are combinations
-		 * of sbios and platforms that are not stable.
-		 */
-		if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8))
-			adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
-		else if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8)
-			 &&((adev->gfx.rlc_fw_version != 106 &&
-			     adev->gfx.rlc_fw_version < 531) ||
-			    (adev->gfx.rlc_fw_version == 53815) ||
-			    (adev->gfx.rlc_feature_version < 1) ||
-			    !adev->gfx.rlc.is_rlc_v2_1))
+		if (!(adev->rev_id >= 0x8 ||
+		      adev->pdev->device == 0x15d8) &&
+		    (adev->pm.fw_version < 0x41e2b || /* not raven1 fresh */
+		     !adev->gfx.rlc.is_rlc_v2_1)) /* without rlc save restore ucodes */
 			adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
 
 		if (adev->pm.pp_feature & PP_GFXOFF_MASK)
@@ -2360,7 +2355,9 @@ static void gfx_v9_0_init_pg(struct amdgpu_device *adev)
 	 * And it's needed by gfxoff feature.
 	 */
 	if (adev->gfx.rlc.is_rlc_v2_1) {
-		if (adev->asic_type == CHIP_VEGA12)
+		if (adev->asic_type == CHIP_VEGA12 ||
+		    (adev->asic_type == CHIP_RAVEN &&
+		     adev->rev_id >= 8))
 			gfx_v9_1_init_rlc_save_restore_list(adev);
 		gfx_v9_0_enable_save_restore_machine(adev);
 	}
@@ -3500,11 +3497,13 @@ static uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device *adev)
 {
 	uint64_t clock;
 
+	amdgpu_gfx_off_ctrl(adev, false);
 	mutex_lock(&adev->gfx.gpu_clock_mutex);
 	WREG32_SOC15(GC, 0, mmRLC_CAPTURE_GPU_CLOCK_COUNT, 1);
 	clock = (uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_LSB) |
 		((uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_MSB) << 32ULL);
 	mutex_unlock(&adev->gfx.gpu_clock_mutex);
+	amdgpu_gfx_off_ctrl(adev, true);
 	return clock;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index c2086eb00555..c9b5086b36a9 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1120,6 +1120,19 @@ static void gmc_v9_0_init_golden_registers(struct amdgpu_device *adev)
 }
 
 /**
+ * gmc_v9_0_restore_registers - restores regs
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * This restores register values, saved at suspend.
+ */
+static void gmc_v9_0_restore_registers(struct amdgpu_device *adev)
+{
+	if (adev->asic_type == CHIP_RAVEN)
+		WREG32(mmDCHUBBUB_SDPIF_MMIO_CNTRL_0, adev->gmc.sdpif_register);
+}
+
+/**
  * gmc_v9_0_gart_enable - gart enable
  *
  * @adev: amdgpu_device pointer
@@ -1207,6 +1220,20 @@ static int gmc_v9_0_hw_init(void *handle)
 }
 
 /**
+ * gmc_v9_0_save_registers - saves regs
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * This saves potential register values that should be
+ * restored upon resume
+ */
+static void gmc_v9_0_save_registers(struct amdgpu_device *adev)
+{
+	if (adev->asic_type == CHIP_RAVEN)
+		adev->gmc.sdpif_register = RREG32(mmDCHUBBUB_SDPIF_MMIO_CNTRL_0);
+}
+
+/**
  * gmc_v9_0_gart_disable - gart disable
  *
  * @adev: amdgpu_device pointer
@@ -1239,9 +1266,16 @@ static int gmc_v9_0_hw_fini(void *handle)
 
 static int gmc_v9_0_suspend(void *handle)
 {
+	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	return gmc_v9_0_hw_fini(adev);
+	r = gmc_v9_0_hw_fini(adev);
+	if (r)
+		return r;
+
+	gmc_v9_0_save_registers(adev);
+
+	return 0;
 }
 
 static int gmc_v9_0_resume(void *handle)
@@ -1249,6 +1283,7 @@ static int gmc_v9_0_resume(void *handle)
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	gmc_v9_0_restore_registers(adev);
 	r = gmc_v9_0_hw_init(adev);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index 36196372e8db..5a68b604fd43 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -252,7 +252,7 @@ static void sdma_v2_4_ring_emit_ib(struct amdgpu_ring *ring,
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 
 	/* IB packet must end on a 8 DW boundary */
-	sdma_v2_4_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
+	sdma_v2_4_ring_insert_nop(ring, (2 - lower_32_bits(ring->wptr)) & 7);
 
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
 			  SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
@@ -747,7 +747,7 @@ static void sdma_v2_4_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib
 	u32 pad_count;
 	int i;
 
-	pad_count = (8 - (ib->length_dw & 0x7)) % 8;
+	pad_count = (-ib->length_dw) & 7;
 	for (i = 0; i < pad_count; i++)
 		if (sdma && sdma->burst_nop && (i == 0))
 			ib->ptr[ib->length_dw++] =
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 6d39544e7829..5bf5fe16b412 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -426,7 +426,7 @@ static void sdma_v3_0_ring_emit_ib(struct amdgpu_ring *ring,
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 
 	/* IB packet must end on a 8 DW boundary */
-	sdma_v3_0_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
+	sdma_v3_0_ring_insert_nop(ring, (2 - lower_32_bits(ring->wptr)) & 7);
 
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
 			  SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
@@ -1018,7 +1018,7 @@ static void sdma_v3_0_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib
 	u32 pad_count;
 	int i;
 
-	pad_count = (8 - (ib->length_dw & 0x7)) % 8;
+	pad_count = (-ib->length_dw) & 7;
 	for (i = 0; i < pad_count; i++)
 		if (sdma && sdma->burst_nop && (i == 0))
 			ib->ptr[ib->length_dw++] =
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 9c88ce513d78..6a5077ea7f1c 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -505,7 +505,7 @@ static void sdma_v4_0_ring_emit_ib(struct amdgpu_ring *ring,
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 
 	/* IB packet must end on a 8 DW boundary */
-	sdma_v4_0_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
+	sdma_v4_0_ring_insert_nop(ring, (2 - lower_32_bits(ring->wptr)) & 7);
 
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
 			  SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
@@ -1384,7 +1384,7 @@ static void sdma_v4_0_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib
 	u32 pad_count;
 	int i;
 
-	pad_count = (8 - (ib->length_dw & 0x7)) % 8;
+	pad_count = (-ib->length_dw) & 7;
 	for (i = 0; i < pad_count; i++)
 		if (sdma && sdma->burst_nop && (i == 0))
 			ib->ptr[ib->length_dw++] =
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 84c34712e39e..9b0f1871b71d 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -217,7 +217,12 @@ static u32 soc15_get_config_memsize(struct amdgpu_device *adev)
 
 static u32 soc15_get_xclk(struct amdgpu_device *adev)
 {
-	return adev->clock.spll.reference_freq;
+	u32 reference_clock = adev->clock.spll.reference_freq;
+
+	if (adev->asic_type == CHIP_RAVEN)
+		return reference_clock / 4;
+
+	return reference_clock;
 }
 
 
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15_common.h b/drivers/gpu/drm/amd/amdgpu/soc15_common.h
index 49c262540940..55cde43d9b62 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15_common.h
+++ b/drivers/gpu/drm/amd/amdgpu/soc15_common.h
@@ -52,6 +52,7 @@
 		uint32_t old_ = 0;	\
 		uint32_t tmp_ = RREG32(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg); \
 		uint32_t loop = adev->usec_timeout;		\
+		ret = 0;					\
 		while ((tmp_ & (mask)) != (expected_value)) {	\
 			if (old_ != tmp_) {			\
 				loop = adev->usec_timeout;	\
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 3dbc51f9d3b9..5f800e7ca7d4 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -1230,7 +1230,7 @@ static int vcn_v1_0_set_clockgating_state(void *handle,
 
 	if (enable) {
 		/* wait for STATUS to clear */
-		if (vcn_v1_0_is_idle(handle))
+		if (!vcn_v1_0_is_idle(handle))
 			return -EBUSY;
 		vcn_v1_0_enable_clock_gating(adev);
 	} else {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c b/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
index ab37d36d9cd6..dcc01de77926 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
@@ -109,7 +109,7 @@ void kfd_debugfs_init(void)
 				  kfd_debugfs_rls_by_device,
 				  &kfd_debugfs_fops);
 
-	ent = debugfs_create_file("hang_hws", S_IFREG | 0644, debugfs_root,
+	ent = debugfs_create_file("hang_hws", S_IFREG | 0200, debugfs_root,
 				  NULL,
 				  &kfd_debugfs_hang_hws_fops);
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 765b58a17dc7..af67c13ae386 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -1001,9 +1001,9 @@ kfd_gtt_out:
 	return 0;
 
 kfd_gtt_no_free_chunk:
-	pr_debug("Allocation failed with mem_obj = %p\n", mem_obj);
+	pr_debug("Allocation failed with mem_obj = %p\n", *mem_obj);
 	mutex_unlock(&kfd->gtt_sa_lock);
-	kfree(mem_obj);
+	kfree(*mem_obj);
 	return -ENOMEM;
 }
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 6a743aaf2669..1557bd9f0b80 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -777,9 +777,14 @@ static int dm_late_init(void *handle)
 	struct dmcu_iram_parameters params;
 	unsigned int linear_lut[16];
 	int i;
-	struct dmcu *dmcu = adev->dm.dc->res_pool->dmcu;
+	struct dmcu *dmcu = NULL;
 	bool ret;
 
+	if (!adev->dm.fw_dmcu)
+		return detect_mst_link_for_all_connectors(adev->ddev);
+
+	dmcu = adev->dm.dc->res_pool->dmcu;
+
 	for (i = 0; i < 16; i++)
 		linear_lut[i] = 0xFFFF * i / 15;
 
@@ -1263,17 +1268,22 @@ amdgpu_dm_update_connector_after_detect(struct amdgpu_dm_connector *aconnector)
 		dc_sink_retain(aconnector->dc_sink);
 		if (sink->dc_edid.length == 0) {
 			aconnector->edid = NULL;
-			drm_dp_cec_unset_edid(&aconnector->dm_dp_aux.aux);
+			if (aconnector->dc_link->aux_mode) {
+				drm_dp_cec_unset_edid(
+					&aconnector->dm_dp_aux.aux);
+			}
 		} else {
 			aconnector->edid =
-				(struct edid *) sink->dc_edid.raw_edid;
-
+				(struct edid *)sink->dc_edid.raw_edid;
 
 			drm_connector_update_edid_property(connector,
-					aconnector->edid);
-			drm_dp_cec_set_edid(&aconnector->dm_dp_aux.aux,
-					    aconnector->edid);
+							   aconnector->edid);
+
+			if (aconnector->dc_link->aux_mode)
+				drm_dp_cec_set_edid(&aconnector->dm_dp_aux.aux,
+						    aconnector->edid);
 		}
+
 		amdgpu_dm_update_freesync_caps(connector, aconnector->edid);
 
 	} else {
@@ -2511,7 +2521,8 @@ fill_plane_dcc_attributes(struct amdgpu_device *adev,
 			  const union dc_tiling_info *tiling_info,
 			  const uint64_t info,
 			  struct dc_plane_dcc_param *dcc,
-			  struct dc_plane_address *address)
+			  struct dc_plane_address *address,
+			  bool force_disable_dcc)
 {
 	struct dc *dc = adev->dm.dc;
 	struct dc_dcc_surface_param input;
@@ -2523,6 +2534,9 @@ fill_plane_dcc_attributes(struct amdgpu_device *adev,
 	memset(&input, 0, sizeof(input));
 	memset(&output, 0, sizeof(output));
 
+	if (force_disable_dcc)
+		return 0;
+
 	if (!offset)
 		return 0;
 
@@ -2572,7 +2586,8 @@ fill_plane_buffer_attributes(struct amdgpu_device *adev,
 			     union dc_tiling_info *tiling_info,
 			     union plane_size *plane_size,
 			     struct dc_plane_dcc_param *dcc,
-			     struct dc_plane_address *address)
+			     struct dc_plane_address *address,
+			     bool force_disable_dcc)
 {
 	const struct drm_framebuffer *fb = &afb->base;
 	int ret;
@@ -2674,7 +2689,8 @@ fill_plane_buffer_attributes(struct amdgpu_device *adev,
 
 		ret = fill_plane_dcc_attributes(adev, afb, format, rotation,
 						plane_size, tiling_info,
-						tiling_flags, dcc, address);
+						tiling_flags, dcc, address,
+						force_disable_dcc);
 		if (ret)
 			return ret;
 	}
@@ -2766,7 +2782,8 @@ fill_dc_plane_info_and_addr(struct amdgpu_device *adev,
 			    const struct drm_plane_state *plane_state,
 			    const uint64_t tiling_flags,
 			    struct dc_plane_info *plane_info,
-			    struct dc_plane_address *address)
+			    struct dc_plane_address *address,
+			    bool force_disable_dcc)
 {
 	const struct drm_framebuffer *fb = plane_state->fb;
 	const struct amdgpu_framebuffer *afb =
@@ -2843,7 +2860,8 @@ fill_dc_plane_info_and_addr(struct amdgpu_device *adev,
 					   plane_info->rotation, tiling_flags,
 					   &plane_info->tiling_info,
 					   &plane_info->plane_size,
-					   &plane_info->dcc, address);
+					   &plane_info->dcc, address,
+					   force_disable_dcc);
 	if (ret)
 		return ret;
 
@@ -2865,6 +2883,7 @@ static int fill_dc_plane_attributes(struct amdgpu_device *adev,
 	struct dc_plane_info plane_info;
 	uint64_t tiling_flags;
 	int ret;
+	bool force_disable_dcc = false;
 
 	ret = fill_dc_scaling_info(plane_state, &scaling_info);
 	if (ret)
@@ -2879,9 +2898,11 @@ static int fill_dc_plane_attributes(struct amdgpu_device *adev,
 	if (ret)
 		return ret;
 
+	force_disable_dcc = adev->asic_type == CHIP_RAVEN && adev->in_suspend;
 	ret = fill_dc_plane_info_and_addr(adev, plane_state, tiling_flags,
 					  &plane_info,
-					  &dc_plane_state->address);
+					  &dc_plane_state->address,
+					  force_disable_dcc);
 	if (ret)
 		return ret;
 
@@ -3054,27 +3075,21 @@ get_output_color_space(const struct dc_crtc_timing *dc_crtc_timing)
 	return color_space;
 }
 
-static void reduce_mode_colour_depth(struct dc_crtc_timing *timing_out)
-{
-	if (timing_out->display_color_depth <= COLOR_DEPTH_888)
-		return;
-
-	timing_out->display_color_depth--;
-}
-
-static void adjust_colour_depth_from_display_info(struct dc_crtc_timing *timing_out,
-						const struct drm_display_info *info)
+static bool adjust_colour_depth_from_display_info(
+	struct dc_crtc_timing *timing_out,
+	const struct drm_display_info *info)
 {
+	enum dc_color_depth depth = timing_out->display_color_depth;
 	int normalized_clk;
-	if (timing_out->display_color_depth <= COLOR_DEPTH_888)
-		return;
 	do {
 		normalized_clk = timing_out->pix_clk_100hz / 10;
 		/* YCbCr 4:2:0 requires additional adjustment of 1/2 */
 		if (timing_out->pixel_encoding == PIXEL_ENCODING_YCBCR420)
 			normalized_clk /= 2;
 		/* Adjusting pix clock following on HDMI spec based on colour depth */
-		switch (timing_out->display_color_depth) {
+		switch (depth) {
+		case COLOR_DEPTH_888:
+			break;
 		case COLOR_DEPTH_101010:
 			normalized_clk = (normalized_clk * 30) / 24;
 			break;
@@ -3085,14 +3100,15 @@ static void adjust_colour_depth_from_display_info(struct dc_crtc_timing *timing_
 			normalized_clk = (normalized_clk * 48) / 24;
 			break;
 		default:
-			return;
+			/* The above depths are the only ones valid for HDMI. */
+			return false;
 		}
-		if (normalized_clk <= info->max_tmds_clock)
-			return;
-		reduce_mode_colour_depth(timing_out);
-
-	} while (timing_out->display_color_depth > COLOR_DEPTH_888);
-
+		if (normalized_clk <= info->max_tmds_clock) {
+			timing_out->display_color_depth = depth;
+			return true;
+		}
+	} while (--depth > COLOR_DEPTH_666);
+	return false;
 }
 
 static void
@@ -3157,8 +3173,14 @@ fill_stream_properties_from_drm_display_mode(struct dc_stream_state *stream,
 
 	stream->out_transfer_func->type = TF_TYPE_PREDEFINED;
 	stream->out_transfer_func->tf = TRANSFER_FUNCTION_SRGB;
-	if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A)
-		adjust_colour_depth_from_display_info(timing_out, info);
+	if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A) {
+		if (!adjust_colour_depth_from_display_info(timing_out, info) &&
+		    drm_mode_is_420_also(info, mode_in) &&
+		    timing_out->pixel_encoding != PIXEL_ENCODING_YCBCR420) {
+			timing_out->pixel_encoding = PIXEL_ENCODING_YCBCR420;
+			adjust_colour_depth_from_display_info(timing_out, info);
+		}
+	}
 }
 
 static void fill_audio_info(struct audio_info *audio_info,
@@ -4102,6 +4124,7 @@ static int dm_plane_helper_prepare_fb(struct drm_plane *plane,
 	uint64_t tiling_flags;
 	uint32_t domain;
 	int r;
+	bool force_disable_dcc = false;
 
 	dm_plane_state_old = to_dm_plane_state(plane->state);
 	dm_plane_state_new = to_dm_plane_state(new_state);
@@ -4152,11 +4175,13 @@ static int dm_plane_helper_prepare_fb(struct drm_plane *plane,
 			dm_plane_state_old->dc_state != dm_plane_state_new->dc_state) {
 		struct dc_plane_state *plane_state = dm_plane_state_new->dc_state;
 
+		force_disable_dcc = adev->asic_type == CHIP_RAVEN && adev->in_suspend;
 		fill_plane_buffer_attributes(
 			adev, afb, plane_state->format, plane_state->rotation,
 			tiling_flags, &plane_state->tiling_info,
 			&plane_state->plane_size, &plane_state->dcc,
-			&plane_state->address);
+			&plane_state->address,
+			force_disable_dcc);
 	}
 
 	return 0;
@@ -5362,7 +5387,12 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 		fill_dc_plane_info_and_addr(
 			dm->adev, new_plane_state, tiling_flags,
 			&bundle->plane_infos[planes_count],
-			&bundle->flip_addrs[planes_count].address);
+			&bundle->flip_addrs[planes_count].address,
+			false);
+
+		DRM_DEBUG_DRIVER("plane: id=%d dcc_en=%d\n",
+				 new_plane_state->plane->index,
+				 bundle->plane_infos[planes_count].dcc.enable);
 
 		bundle->surface_updates[planes_count].plane_info =
 			&bundle->plane_infos[planes_count];
@@ -6375,6 +6405,7 @@ static int dm_update_plane_state(struct dc *dc,
 	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
 	struct dm_crtc_state *dm_new_crtc_state, *dm_old_crtc_state;
 	struct dm_plane_state *dm_new_plane_state, *dm_old_plane_state;
+	struct amdgpu_crtc *new_acrtc;
 	bool needs_reset;
 	int ret = 0;
 
@@ -6384,9 +6415,23 @@ static int dm_update_plane_state(struct dc *dc,
 	dm_new_plane_state = to_dm_plane_state(new_plane_state);
 	dm_old_plane_state = to_dm_plane_state(old_plane_state);
 
-	/*TODO Implement atomic check for cursor plane */
-	if (plane->type == DRM_PLANE_TYPE_CURSOR)
+	/*TODO Implement better atomic check for cursor plane */
+	if (plane->type == DRM_PLANE_TYPE_CURSOR) {
+		if (!enable || !new_plane_crtc ||
+			drm_atomic_plane_disabling(plane->state, new_plane_state))
+			return 0;
+
+		new_acrtc = to_amdgpu_crtc(new_plane_crtc);
+
+		if ((new_plane_state->crtc_w > new_acrtc->max_cursor_width) ||
+			(new_plane_state->crtc_h > new_acrtc->max_cursor_height)) {
+			DRM_DEBUG_ATOMIC("Bad cursor size %d x %d\n",
+							 new_plane_state->crtc_w, new_plane_state->crtc_h);
+			return -EINVAL;
+		}
+
 		return 0;
+	}
 
 	needs_reset = should_reset_plane(state, plane, old_plane_state,
 					 new_plane_state);
@@ -6552,6 +6597,12 @@ dm_determine_update_type_for_commit(struct amdgpu_display_manager *dm,
 			continue;
 
 		for_each_oldnew_plane_in_state(state, plane, old_plane_state, new_plane_state, j) {
+			const struct amdgpu_framebuffer *amdgpu_fb =
+				to_amdgpu_framebuffer(new_plane_state->fb);
+			struct dc_plane_info plane_info;
+			struct dc_flip_addrs flip_addr;
+			uint64_t tiling_flags;
+
 			new_plane_crtc = new_plane_state->crtc;
 			old_plane_crtc = old_plane_state->crtc;
 			new_dm_plane_state = to_dm_plane_state(new_plane_state);
@@ -6593,6 +6644,25 @@ dm_determine_update_type_for_commit(struct amdgpu_display_manager *dm,
 
 			updates[num_plane].scaling_info = &scaling_info;
 
+			if (amdgpu_fb) {
+				ret = get_fb_info(amdgpu_fb, &tiling_flags);
+				if (ret)
+					goto cleanup;
+
+				memset(&flip_addr, 0, sizeof(flip_addr));
+
+				ret = fill_dc_plane_info_and_addr(
+					dm->adev, new_plane_state, tiling_flags,
+					&plane_info,
+					&flip_addr.address,
+					false);
+				if (ret)
+					goto cleanup;
+
+				updates[num_plane].plane_info = &plane_info;
+				updates[num_plane].flip_addr = &flip_addr;
+			}
+
 			num_plane++;
 		}
 
@@ -6869,20 +6939,38 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 		 * the same resource. If we have a new DC context as part of
 		 * the DM atomic state from validation we need to free it and
 		 * retain the existing one instead.
+		 *
+		 * Furthermore, since the DM atomic state only contains the DC
+		 * context and can safely be annulled, we can free the state
+		 * and clear the associated private object now to free
+		 * some memory and avoid a possible use-after-free later.
 		 */
-		struct dm_atomic_state *new_dm_state, *old_dm_state;
 
-		new_dm_state = dm_atomic_get_new_state(state);
-		old_dm_state = dm_atomic_get_old_state(state);
+		for (i = 0; i < state->num_private_objs; i++) {
+			struct drm_private_obj *obj = state->private_objs[i].ptr;
 
-		if (new_dm_state && old_dm_state) {
-			if (new_dm_state->context)
-				dc_release_state(new_dm_state->context);
+			if (obj->funcs == adev->dm.atomic_obj.funcs) {
+				int j = state->num_private_objs-1;
 
-			new_dm_state->context = old_dm_state->context;
+				dm_atomic_destroy_state(obj,
+						state->private_objs[i].state);
 
-			if (old_dm_state->context)
-				dc_retain_state(old_dm_state->context);
+				/* If i is not at the end of the array then the
+				 * last element needs to be moved to where i was
+				 * before the array can safely be truncated.
+				 */
+				if (i != j)
+					state->private_objs[i] =
+						state->private_objs[j];
+
+				state->private_objs[j].ptr = NULL;
+				state->private_objs[j].state = NULL;
+				state->private_objs[j].old_state = NULL;
+				state->private_objs[j].new_state = NULL;
+
+				state->num_private_objs = j;
+				break;
+			}
 		}
 	}
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index e6cd67342df8..415ae97ef87c 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -248,7 +248,8 @@ bool dm_helpers_dp_mst_write_payload_allocation_table(
 		drm_dp_mst_reset_vcpi_slots(mst_mgr, mst_port);
 	}
 
-	ret = drm_dp_update_payload_part1(mst_mgr);
+	/* It's OK for this to fail */
+	drm_dp_update_payload_part1(mst_mgr);
 
 	/* mst_mgr->->payloads are VC payload notify MST branch using DPCD or
 	 * AUX message. The sequence is slot 1-63 allocated sequence for each
@@ -257,9 +258,6 @@ bool dm_helpers_dp_mst_write_payload_allocation_table(
 
 	get_payload_table(aconnector, proposed_table);
 
-	if (ret)
-		return false;
-
 	return true;
 }
 
@@ -317,7 +315,6 @@ bool dm_helpers_dp_mst_send_payload_allocation(
 	struct amdgpu_dm_connector *aconnector;
 	struct drm_dp_mst_topology_mgr *mst_mgr;
 	struct drm_dp_mst_port *mst_port;
-	int ret;
 
 	aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context;
 
@@ -331,10 +328,8 @@ bool dm_helpers_dp_mst_send_payload_allocation(
 	if (!mst_mgr->mst_state)
 		return false;
 
-	ret = drm_dp_update_payload_part2(mst_mgr);
-
-	if (ret)
-		return false;
+	/* It's OK for this to fail */
+	drm_dp_update_payload_part2(mst_mgr);
 
 	if (!enable)
 		drm_dp_mst_deallocate_vcpi(mst_mgr, mst_port);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 6e205ee36ac3..b528acababbd 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -357,6 +357,7 @@ static void dm_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 					   aconnector->dc_sink);
 		dc_sink_release(aconnector->dc_sink);
 		aconnector->dc_sink = NULL;
+		aconnector->dc_link->cur_link_settings.lane_count = 0;
 	}
 
 	drm_connector_unregister(connector);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
index 37893145e712..b7ab878f3932 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
@@ -500,6 +500,8 @@ bool dm_pp_get_static_clocks(
 			&pp_clk_info);
 	else if (adev->smu.funcs)
 		ret = smu_get_current_clocks(&adev->smu, &pp_clk_info);
+	else
+		return false;
 	if (ret)
 		return false;
 
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
index a4c97d32e751..57c27c3848f3 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
@@ -2541,7 +2541,6 @@ static enum bp_result construct_integrated_info(
 
 	/* Sort voltage table from low to high*/
 	if (result == BP_RESULT_OK) {
-		struct clock_voltage_caps temp = {0, 0};
 		uint32_t i;
 		uint32_t j;
 
@@ -2551,10 +2550,8 @@ static enum bp_result construct_integrated_info(
 						info->disp_clk_voltage[j].max_supported_clk <
 						info->disp_clk_voltage[j-1].max_supported_clk) {
 					/* swap j and j - 1*/
-					temp = info->disp_clk_voltage[j-1];
-					info->disp_clk_voltage[j-1] =
-							info->disp_clk_voltage[j];
-					info->disp_clk_voltage[j] = temp;
+					swap(info->disp_clk_voltage[j - 1],
+					     info->disp_clk_voltage[j]);
 				}
 			}
 		}
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index fd5266a58297..2c97c042807b 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -1605,8 +1605,6 @@ static enum bp_result construct_integrated_info(
 
 	struct atom_common_table_header *header;
 	struct atom_data_revision revision;
-
-	struct clock_voltage_caps temp = {0, 0};
 	uint32_t i;
 	uint32_t j;
 
@@ -1636,10 +1634,8 @@ static enum bp_result construct_integrated_info(
 				info->disp_clk_voltage[j-1].max_supported_clk
 				) {
 				/* swap j and j - 1*/
-				temp = info->disp_clk_voltage[j-1];
-				info->disp_clk_voltage[j-1] =
-					info->disp_clk_voltage[j];
-				info->disp_clk_voltage[j] = temp;
+				swap(info->disp_clk_voltage[j - 1],
+				     info->disp_clk_voltage[j]);
 			}
 		}
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
index 1b4b51657f5e..78c4bc573c69 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
@@ -1375,6 +1375,7 @@ void dcn_bw_update_from_pplib(struct dc *dc)
 	struct dc_context *ctx = dc->ctx;
 	struct dm_pp_clock_levels_with_voltage fclks = {0}, dcfclks = {0};
 	bool res;
+	unsigned vmin0p65_idx, vmid0p72_idx, vnom0p8_idx, vmax0p9_idx;
 
 	/* TODO: This is not the proper way to obtain fabric_and_dram_bandwidth, should be min(fclk, memclk) */
 	res = dm_pp_get_clock_levels_by_type_with_voltage(
@@ -1386,17 +1387,28 @@ void dcn_bw_update_from_pplib(struct dc *dc)
 		res = verify_clock_values(&fclks);
 
 	if (res) {
-		ASSERT(fclks.num_levels >= 3);
-		dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 = 32 * (fclks.data[0].clocks_in_khz / 1000.0) / 1000.0;
-		dc->dcn_soc->fabric_and_dram_bandwidth_vmid0p72 = dc->dcn_soc->number_of_channels *
-				(fclks.data[fclks.num_levels - (fclks.num_levels > 2 ? 3 : 2)].clocks_in_khz / 1000.0)
-				* ddr4_dram_factor_single_Channel / 1000.0;
-		dc->dcn_soc->fabric_and_dram_bandwidth_vnom0p8 = dc->dcn_soc->number_of_channels *
-				(fclks.data[fclks.num_levels - 2].clocks_in_khz / 1000.0)
-				* ddr4_dram_factor_single_Channel / 1000.0;
-		dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = dc->dcn_soc->number_of_channels *
-				(fclks.data[fclks.num_levels - 1].clocks_in_khz / 1000.0)
-				* ddr4_dram_factor_single_Channel / 1000.0;
+		ASSERT(fclks.num_levels);
+
+		vmin0p65_idx = 0;
+		vmid0p72_idx = fclks.num_levels -
+			(fclks.num_levels > 2 ? 3 : (fclks.num_levels > 1 ? 2 : 1));
+		vnom0p8_idx = fclks.num_levels - (fclks.num_levels > 1 ? 2 : 1);
+		vmax0p9_idx = fclks.num_levels - 1;
+
+		dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 =
+			32 * (fclks.data[vmin0p65_idx].clocks_in_khz / 1000.0) / 1000.0;
+		dc->dcn_soc->fabric_and_dram_bandwidth_vmid0p72 =
+			dc->dcn_soc->number_of_channels *
+			(fclks.data[vmid0p72_idx].clocks_in_khz / 1000.0)
+			* ddr4_dram_factor_single_Channel / 1000.0;
+		dc->dcn_soc->fabric_and_dram_bandwidth_vnom0p8 =
+			dc->dcn_soc->number_of_channels *
+			(fclks.data[vnom0p8_idx].clocks_in_khz / 1000.0)
+			* ddr4_dram_factor_single_Channel / 1000.0;
+		dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 =
+			dc->dcn_soc->number_of_channels *
+			(fclks.data[vmax0p9_idx].clocks_in_khz / 1000.0)
+			* ddr4_dram_factor_single_Channel / 1000.0;
 	} else
 		BREAK_TO_DEBUGGER();
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 191f5757ded1..3b4afaaadf96 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -254,6 +254,8 @@ bool dc_stream_adjust_vmin_vmax(struct dc *dc,
 	int i = 0;
 	bool ret = false;
 
+	stream->adjust = *adjust;
+
 	for (i = 0; i < MAX_PIPES; i++) {
 		struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i];
 
@@ -947,15 +949,11 @@ static void program_timing_sync(
 
 		/* set first pipe with plane as master */
 		for (j = 0; j < group_size; j++) {
-			struct pipe_ctx *temp;
-
 			if (pipe_set[j]->plane_state) {
 				if (j == 0)
 					break;
 
-				temp = pipe_set[0];
-				pipe_set[0] = pipe_set[j];
-				pipe_set[j] = temp;
+				swap(pipe_set[0], pipe_set[j]);
 				break;
 			}
 		}
@@ -1216,6 +1214,26 @@ bool dc_commit_state(struct dc *dc, struct dc_state *context)
 	return (result == DC_OK);
 }
 
+static bool is_flip_pending_in_pipes(struct dc *dc, struct dc_state *context)
+{
+	int i;
+	struct pipe_ctx *pipe;
+
+	for (i = 0; i < MAX_PIPES; i++) {
+		pipe = &context->res_ctx.pipe_ctx[i];
+
+		if (!pipe->plane_state)
+			continue;
+
+		/* Must set to false to start with, due to OR in update function */
+		pipe->plane_state->status.is_flip_pending = false;
+		dc->hwss.update_pending_status(pipe);
+		if (pipe->plane_state->status.is_flip_pending)
+			return true;
+	}
+	return false;
+}
+
 bool dc_post_update_surfaces_to_stream(struct dc *dc)
 {
 	int i;
@@ -1226,6 +1244,9 @@ bool dc_post_update_surfaces_to_stream(struct dc *dc)
 
 	post_surface_trace(dc);
 
+	if (is_flip_pending_in_pipes(dc, context))
+		return true;
+
 	for (i = 0; i < dc->res_pool->pipe_count; i++)
 		if (context->res_ctx.pipe_ctx[i].stream == NULL ||
 		    context->res_ctx.pipe_ctx[i].plane_state == NULL) {
@@ -1937,6 +1958,14 @@ void dc_commit_updates_for_stream(struct dc *dc,
 		}
 	}
 
+	if (update_type > UPDATE_TYPE_FAST) {
+		if (!dc->res_pool->funcs->validate_bandwidth(dc, context, false)) {
+			DC_ERROR("Mode validation failed for stream update!\n");
+			dc_release_state(context);
+			return;
+		}
+	}
+
 	commit_planes_for_stream(
 				dc,
 				srf_updates,
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 8090202171ec..a68175ac7c1a 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -367,7 +367,7 @@ bool dc_link_is_dp_sink_present(struct dc_link *link)
 
 	if (GPIO_RESULT_OK != dal_ddc_open(
 		ddc, GPIO_MODE_INPUT, GPIO_DDC_CONFIG_TYPE_MODE_I2C)) {
-		dal_gpio_destroy_ddc(&ddc);
+		dal_ddc_close(ddc);
 
 		return present;
 	}
@@ -871,8 +871,7 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
 			same_edid = is_same_edid(&prev_sink->dc_edid, &sink->dc_edid);
 
 		if (link->connector_signal == SIGNAL_TYPE_DISPLAY_PORT &&
-			sink_caps.transaction_type == DDC_TRANSACTION_TYPE_I2C_OVER_AUX &&
-			reason != DETECT_REASON_HPDRX) {
+			sink_caps.transaction_type == DDC_TRANSACTION_TYPE_I2C_OVER_AUX) {
 			/*
 			 * TODO debug why Dell 2413 doesn't like
 			 *  two link trainings
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 02d7e16ffeb4..1e0917c04b77 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -2523,6 +2523,17 @@ static bool retrieve_link_cap(struct dc_link *link)
 		sink_id.ieee_device_id,
 		sizeof(sink_id.ieee_device_id));
 
+	/* Quirk Apple MBP 2017 15" Retina panel: Wrong DP_MAX_LINK_RATE */
+	{
+		uint8_t str_mbp_2017[] = { 101, 68, 21, 101, 98, 97 };
+
+		if ((link->dpcd_caps.sink_dev_id == 0x0010fa) &&
+		    !memcmp(link->dpcd_caps.sink_dev_id_str, str_mbp_2017,
+			    sizeof(str_mbp_2017))) {
+			link->reported_link_cap.link_rate = 0x0c;
+		}
+	}
+
 	core_link_read_dpcd(
 		link,
 		DP_SINK_HW_REVISION_START,
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
index bd33c47183fc..850b78af9fe6 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
@@ -380,7 +380,7 @@ static bool acquire(
 {
 	enum gpio_result result;
 
-	if (!is_engine_available(engine))
+	if ((engine == NULL) || !is_engine_available(engine))
 		return false;
 
 	result = dal_ddc_open(ddc, GPIO_MODE_HARDWARE,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
index 0db2a6e96fc0..8725e6d54ac9 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
@@ -779,8 +779,8 @@ static void hubbub1_det_request_size(
 
 	hubbub1_get_blk256_size(&blk256_width, &blk256_height, bpe);
 
-	swath_bytes_horz_wc = height * blk256_height * bpe;
-	swath_bytes_vert_wc = width * blk256_width * bpe;
+	swath_bytes_horz_wc = width * blk256_height * bpe;
+	swath_bytes_vert_wc = height * blk256_width * bpe;
 
 	*req128_horz_wc = (2 * swath_bytes_horz_wc <= detile_buf_size) ?
 			false : /* full 256B request */
diff --git a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
index 31f867bb5afe..0d1a096848d9 100644
--- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
+++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
@@ -1756,7 +1756,7 @@ bool calculate_user_regamma_ramp(struct dc_transfer_func *output_tf,
 
 	kfree(rgb_regamma);
 rgb_regamma_alloc_fail:
-	kvfree(rgb_user);
+	kfree(rgb_user);
 rgb_user_alloc_fail:
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
index 471135a5439d..19826b9f2583 100644
--- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
+++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
@@ -963,6 +963,7 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync,
 			2 * in_out_vrr->min_refresh_in_uhz)
 		in_out_vrr->btr.btr_enabled = false;
 
+	in_out_vrr->fixed.fixed_active = false;
 	in_out_vrr->btr.btr_active = false;
 	in_out_vrr->btr.inserted_duration_in_us = 0;
 	in_out_vrr->btr.frames_to_insert = 0;
@@ -982,6 +983,7 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync,
 		in_out_vrr->adjust.v_total_max = stream->timing.v_total;
 	} else if (in_out_vrr->state == VRR_STATE_ACTIVE_VARIABLE &&
 			refresh_range >= MIN_REFRESH_RANGE_IN_US) {
+
 		in_out_vrr->adjust.v_total_min =
 			calc_v_total_from_refresh(stream,
 				in_out_vrr->max_refresh_in_uhz);
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h
index b6f74bf4af02..27bb8c1ab858 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h
@@ -7376,6 +7376,8 @@
 #define mmCRTC4_CRTC_DRR_CONTROL                                                                       0x0f3e
 #define mmCRTC4_CRTC_DRR_CONTROL_BASE_IDX                                                              2
 
+#define mmDCHUBBUB_SDPIF_MMIO_CNTRL_0                                                                  0x395d
+#define mmDCHUBBUB_SDPIF_MMIO_CNTRL_0_BASE_IDX                                                         2
 
 // addressBlock: dce_dc_fmt4_dispdec
 // base address: 0x2000
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index bea1587d352d..593146f1edbc 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -320,12 +320,12 @@ static void pp_dpm_en_umd_pstate(struct pp_hwmgr  *hwmgr,
 		if (*level & profile_mode_mask) {
 			hwmgr->saved_dpm_level = hwmgr->dpm_level;
 			hwmgr->en_umd_pstate = true;
-			amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
-						AMD_IP_BLOCK_TYPE_GFX,
-						AMD_CG_STATE_UNGATE);
 			amdgpu_device_ip_set_powergating_state(hwmgr->adev,
 					AMD_IP_BLOCK_TYPE_GFX,
 					AMD_PG_STATE_UNGATE);
+			amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
+						AMD_IP_BLOCK_TYPE_GFX,
+						AMD_CG_STATE_UNGATE);
 		}
 	} else {
 		/* exit umd pstate, restore level, enable gfx cg*/
@@ -1408,10 +1408,12 @@ static int pp_get_asic_baco_capability(void *handle, bool *cap)
 {
 	struct pp_hwmgr *hwmgr = handle;
 
+	*cap = false;
 	if (!hwmgr)
 		return -EINVAL;
 
-	if (!hwmgr->pm_en || !hwmgr->hwmgr_func->get_asic_baco_capability)
+	if (!(hwmgr->not_vf && amdgpu_dpm) ||
+		!hwmgr->hwmgr_func->get_asic_baco_capability)
 		return 0;
 
 	mutex_lock(&hwmgr->smu_lock);
@@ -1445,7 +1447,8 @@ static int pp_set_asic_baco_state(void *handle, int state)
 	if (!hwmgr)
 		return -EINVAL;
 
-	if (!hwmgr->pm_en || !hwmgr->hwmgr_func->set_asic_baco_state)
+	if (!(hwmgr->not_vf && amdgpu_dpm) ||
+		!hwmgr->hwmgr_func->set_asic_baco_state)
 		return 0;
 
 	mutex_lock(&hwmgr->smu_lock);
diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index 61a6d183c153..25fc055168ac 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -1092,12 +1092,12 @@ static int smu_enable_umd_pstate(void *handle,
 		if (*level & profile_mode_mask) {
 			smu_dpm_ctx->saved_dpm_level = smu_dpm_ctx->dpm_level;
 			smu_dpm_ctx->enable_umd_pstate = true;
-			amdgpu_device_ip_set_clockgating_state(smu->adev,
-							       AMD_IP_BLOCK_TYPE_GFX,
-							       AMD_CG_STATE_UNGATE);
 			amdgpu_device_ip_set_powergating_state(smu->adev,
 							       AMD_IP_BLOCK_TYPE_GFX,
 							       AMD_PG_STATE_UNGATE);
+			amdgpu_device_ip_set_clockgating_state(smu->adev,
+							       AMD_IP_BLOCK_TYPE_GFX,
+							       AMD_CG_STATE_UNGATE);
 		}
 	} else {
 		/* exit umd pstate, restore level, enable gfx cg*/
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c
index 77c14671866c..719597c5d27d 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c
@@ -984,6 +984,32 @@ static int init_thermal_controller(
 			struct pp_hwmgr *hwmgr,
 			const ATOM_PPLIB_POWERPLAYTABLE *powerplay_table)
 {
+	hwmgr->thermal_controller.ucType =
+			powerplay_table->sThermalController.ucType;
+	hwmgr->thermal_controller.ucI2cLine =
+			powerplay_table->sThermalController.ucI2cLine;
+	hwmgr->thermal_controller.ucI2cAddress =
+			powerplay_table->sThermalController.ucI2cAddress;
+
+	hwmgr->thermal_controller.fanInfo.bNoFan =
+		(0 != (powerplay_table->sThermalController.ucFanParameters &
+			ATOM_PP_FANPARAMETERS_NOFAN));
+
+	hwmgr->thermal_controller.fanInfo.ucTachometerPulsesPerRevolution =
+		powerplay_table->sThermalController.ucFanParameters &
+		ATOM_PP_FANPARAMETERS_TACHOMETER_PULSES_PER_REVOLUTION_MASK;
+
+	hwmgr->thermal_controller.fanInfo.ulMinRPM
+		= powerplay_table->sThermalController.ucFanMinRPM * 100UL;
+	hwmgr->thermal_controller.fanInfo.ulMaxRPM
+		= powerplay_table->sThermalController.ucFanMaxRPM * 100UL;
+
+	set_hw_cap(hwmgr,
+		   ATOM_PP_THERMALCONTROLLER_NONE != hwmgr->thermal_controller.ucType,
+		   PHM_PlatformCaps_ThermalController);
+
+	hwmgr->thermal_controller.use_hw_fan_control = 1;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
index e32ae9d3373c..61e5a5006bbb 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
@@ -1026,12 +1026,15 @@ static int smu10_get_clock_by_type_with_latency(struct pp_hwmgr *hwmgr,
 
 	clocks->num_levels = 0;
 	for (i = 0; i < pclk_vol_table->count; i++) {
-		clocks->data[i].clocks_in_khz = pclk_vol_table->entries[i].clk * 10;
-		clocks->data[i].latency_in_us = latency_required ?
-						smu10_get_mem_latency(hwmgr,
-						pclk_vol_table->entries[i].clk) :
-						0;
-		clocks->num_levels++;
+		if (pclk_vol_table->entries[i].clk) {
+			clocks->data[clocks->num_levels].clocks_in_khz =
+				pclk_vol_table->entries[i].clk * 10;
+			clocks->data[clocks->num_levels].latency_in_us = latency_required ?
+				smu10_get_mem_latency(hwmgr,
+						      pclk_vol_table->entries[i].clk) :
+				0;
+			clocks->num_levels++;
+		}
 	}
 
 	return 0;
@@ -1077,9 +1080,11 @@ static int smu10_get_clock_by_type_with_voltage(struct pp_hwmgr *hwmgr,
 
 	clocks->num_levels = 0;
 	for (i = 0; i < pclk_vol_table->count; i++) {
-		clocks->data[i].clocks_in_khz = pclk_vol_table->entries[i].clk  * 10;
-		clocks->data[i].voltage_in_mv = pclk_vol_table->entries[i].vol;
-		clocks->num_levels++;
+		if (pclk_vol_table->entries[i].clk) {
+			clocks->data[clocks->num_levels].clocks_in_khz = pclk_vol_table->entries[i].clk  * 10;
+			clocks->data[clocks->num_levels].voltage_in_mv = pclk_vol_table->entries[i].vol;
+			clocks->num_levels++;
+		}
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
index fc01e20a5242..16fc8b857b0a 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
@@ -3800,9 +3800,12 @@ static int smu7_trim_single_dpm_states(struct pp_hwmgr *hwmgr,
 {
 	uint32_t i;
 
+	/* force the trim if mclk_switching is disabled to prevent flicker */
+	bool force_trim = (low_limit == high_limit);
 	for (i = 0; i < dpm_table->count; i++) {
 	/*skip the trim if od is enabled*/
-		if (!hwmgr->od_enabled && (dpm_table->dpm_levels[i].value < low_limit
+		if ((!hwmgr->od_enabled || force_trim)
+			&& (dpm_table->dpm_levels[i].value < low_limit
 			|| dpm_table->dpm_levels[i].value > high_limit))
 			dpm_table->dpm_levels[i].enabled = false;
 		else
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
index 92903a4cc4d8..50e5ab5a0be1 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
@@ -166,7 +166,8 @@ static int smu_v11_0_init_microcode(struct smu_context *smu)
 		chip_name = "vega20";
 		break;
 	default:
-		BUG();
+		dev_err(adev->dev, "Unsupported ASIC type %d\n", adev->asic_type);
+		return -EINVAL;
 	}
 
 	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_smc.bin", chip_name);
@@ -841,8 +842,12 @@ static int smu_v11_0_init_max_sustainable_clocks(struct smu_context *smu)
 	struct smu_11_0_max_sustainable_clocks *max_sustainable_clocks;
 	int ret = 0;
 
-	max_sustainable_clocks = kzalloc(sizeof(struct smu_11_0_max_sustainable_clocks),
+	if (!smu->smu_table.max_sustainable_clocks)
+		max_sustainable_clocks = kzalloc(sizeof(struct smu_11_0_max_sustainable_clocks),
 					 GFP_KERNEL);
+	else
+		max_sustainable_clocks = smu->smu_table.max_sustainable_clocks;
+
 	smu->smu_table.max_sustainable_clocks = (void *)max_sustainable_clocks;
 
 	max_sustainable_clocks->uclock = smu->smu_table.boot_values.uclk / 100;
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
index 669bd0c2a16c..4de562758436 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
@@ -238,7 +238,7 @@ static void ci_initialize_power_tune_defaults(struct pp_hwmgr *hwmgr)
 
 	switch (dev_id) {
 	case 0x67BA:
-	case 0x66B1:
+	case 0x67B1:
 		smu_data->power_tune_defaults = &defaults_hawaii_pro;
 		break;
 	case 0x67B8:
@@ -2724,7 +2724,10 @@ static int ci_initialize_mc_reg_table(struct pp_hwmgr *hwmgr)
 
 static bool ci_is_dpm_running(struct pp_hwmgr *hwmgr)
 {
-	return ci_is_smc_ram_running(hwmgr);
+	return (1 == PHM_READ_INDIRECT_FIELD(hwmgr->device,
+					     CGS_IND_REG__SMC, FEATURE_STATUS,
+					     VOLTAGE_CONTROLLER_ON))
+		? true : false;
 }
 
 static int ci_smu_init(struct pp_hwmgr *hwmgr)
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
index 1e69300f6175..d33ae5ba8fbf 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
@@ -642,9 +642,6 @@ static int vegam_get_dependency_volt_by_clk(struct pp_hwmgr *hwmgr,
 
 	/* sclk is bigger than max sclk in the dependence table */
 	*voltage |= (dep_table->entries[i - 1].vddc * VOLTAGE_SCALE) << VDDC_SHIFT;
-	vddci = phm_find_closest_vddci(&(data->vddci_voltage_table),
-			(dep_table->entries[i - 1].vddc -
-					(uint16_t)VDDC_VDDCI_DELTA));
 
 	if (SMU7_VOLTAGE_CONTROL_NONE == data->vddci_control)
 		*voltage |= (data->vbios_boot_state.vddci_bootup_value *
@@ -652,8 +649,13 @@ static int vegam_get_dependency_volt_by_clk(struct pp_hwmgr *hwmgr,
 	else if (dep_table->entries[i - 1].vddci)
 		*voltage |= (dep_table->entries[i - 1].vddci *
 				VOLTAGE_SCALE) << VDDC_SHIFT;
-	else
+	else {
+		vddci = phm_find_closest_vddci(&(data->vddci_voltage_table),
+				(dep_table->entries[i - 1].vddc -
+						(uint16_t)VDDC_VDDCI_DELTA));
+
 		*voltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT;
+	}
 
 	if (SMU7_VOLTAGE_CONTROL_NONE == data->mvdd_control)
 		*mvdd = data->vbios_boot_state.mvdd_bootup_value * VOLTAGE_SCALE;
diff --git a/drivers/gpu/drm/arm/malidp_mw.c b/drivers/gpu/drm/arm/malidp_mw.c
index 5f102bdaf841..cc1e731b2485 100644
--- a/drivers/gpu/drm/arm/malidp_mw.c
+++ b/drivers/gpu/drm/arm/malidp_mw.c
@@ -55,7 +55,7 @@ malidp_mw_connector_mode_valid(struct drm_connector *connector,
 	return MODE_OK;
 }
 
-const struct drm_connector_helper_funcs malidp_mw_connector_helper_funcs = {
+static const struct drm_connector_helper_funcs malidp_mw_connector_helper_funcs = {
 	.get_modes = malidp_mw_connector_get_modes,
 	.mode_valid = malidp_mw_connector_mode_valid,
 };
diff --git a/drivers/gpu/drm/arm/malidp_planes.c b/drivers/gpu/drm/arm/malidp_planes.c
index 062e88e238dd..2631e76bac7c 100644
--- a/drivers/gpu/drm/arm/malidp_planes.c
+++ b/drivers/gpu/drm/arm/malidp_planes.c
@@ -928,7 +928,7 @@ int malidp_de_planes_init(struct drm_device *drm)
 	const struct malidp_hw_regmap *map = &malidp->dev->hw->map;
 	struct malidp_plane *plane = NULL;
 	enum drm_plane_type plane_type;
-	unsigned long crtcs = 1 << drm->mode_config.num_crtc;
+	unsigned long crtcs = BIT(drm->mode_config.num_crtc);
 	unsigned long flags = DRM_MODE_ROTATE_0 | DRM_MODE_ROTATE_90 | DRM_MODE_ROTATE_180 |
 			      DRM_MODE_ROTATE_270 | DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y;
 	unsigned int blend_caps = BIT(DRM_MODE_BLEND_PIXEL_NONE) |
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
index a128400593a9..ea14f363b81e 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
@@ -68,7 +68,11 @@ static void atmel_hlcdc_crtc_mode_set_nofb(struct drm_crtc *c)
 	struct videomode vm;
 	unsigned long prate;
 	unsigned int cfg;
-	int div;
+	int div, ret;
+
+	ret = clk_prepare_enable(crtc->dc->hlcdc->sys_clk);
+	if (ret)
+		return;
 
 	vm.vfront_porch = adj->crtc_vsync_start - adj->crtc_vdisplay;
 	vm.vback_porch = adj->crtc_vtotal - adj->crtc_vsync_end;
@@ -109,8 +113,8 @@ static void atmel_hlcdc_crtc_mode_set_nofb(struct drm_crtc *c)
 		int div_low = prate / mode_rate;
 
 		if (div_low >= 2 &&
-		    ((prate / div_low - mode_rate) <
-		     10 * (mode_rate - prate / div)))
+		    (10 * (prate / div_low - mode_rate) <
+		     (mode_rate - prate / div)))
 			/*
 			 * At least 10 times better when using a higher
 			 * frequency than requested, instead of a lower.
@@ -143,6 +147,8 @@ static void atmel_hlcdc_crtc_mode_set_nofb(struct drm_crtc *c)
 			   ATMEL_HLCDC_VSPSU | ATMEL_HLCDC_VSPHO |
 			   ATMEL_HLCDC_GUARDTIME_MASK | ATMEL_HLCDC_MODE_MASK,
 			   cfg);
+
+	clk_disable_unprepare(crtc->dc->hlcdc->sys_clk);
 }
 
 static enum drm_mode_status
diff --git a/drivers/gpu/drm/bochs/bochs_hw.c b/drivers/gpu/drm/bochs/bochs_hw.c
index 791ab2f79947..1fdf1cd7aedf 100644
--- a/drivers/gpu/drm/bochs/bochs_hw.c
+++ b/drivers/gpu/drm/bochs/bochs_hw.c
@@ -152,10 +152,8 @@ int bochs_hw_init(struct drm_device *dev)
 		size = min(size, mem);
 	}
 
-	if (pci_request_region(pdev, 0, "bochs-drm") != 0) {
-		DRM_ERROR("Cannot request framebuffer\n");
-		return -EBUSY;
-	}
+	if (pci_request_region(pdev, 0, "bochs-drm") != 0)
+		DRM_WARN("Cannot request framebuffer, boot fb still active?\n");
 
 	bochs->fb_map = ioremap(addr, size);
 	if (bochs->fb_map == NULL) {
diff --git a/drivers/gpu/drm/bochs/bochs_kms.c b/drivers/gpu/drm/bochs/bochs_kms.c
index 37e515221ad8..6f42db56c20c 100644
--- a/drivers/gpu/drm/bochs/bochs_kms.c
+++ b/drivers/gpu/drm/bochs/bochs_kms.c
@@ -190,6 +190,7 @@ int bochs_kms_init(struct bochs_device *bochs)
 	bochs->dev->mode_config.fb_base = bochs->fb_base;
 	bochs->dev->mode_config.preferred_depth = 24;
 	bochs->dev->mode_config.prefer_shadow = 0;
+	bochs->dev->mode_config.fbdev_use_iomem = true;
 	bochs->dev->mode_config.quirk_addfb_prefer_host_byte_order = true;
 
 	bochs->dev->mode_config.funcs = &bochs_mode_funcs;
diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c b/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c
index a428185be2c1..d05b3033b510 100644
--- a/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c
+++ b/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c
@@ -19,13 +19,15 @@ static void adv7511_calc_cts_n(unsigned int f_tmds, unsigned int fs,
 {
 	switch (fs) {
 	case 32000:
-		*n = 4096;
+	case 48000:
+	case 96000:
+	case 192000:
+		*n = fs * 128 / 1000;
 		break;
 	case 44100:
-		*n = 6272;
-		break;
-	case 48000:
-		*n = 6144;
+	case 88200:
+	case 176400:
+		*n = fs * 128 / 900;
 		break;
 	}
 
diff --git a/drivers/gpu/drm/bridge/sil-sii8620.c b/drivers/gpu/drm/bridge/sil-sii8620.c
index bd3165ee5354..04431dbac4a4 100644
--- a/drivers/gpu/drm/bridge/sil-sii8620.c
+++ b/drivers/gpu/drm/bridge/sil-sii8620.c
@@ -177,7 +177,7 @@ static void sii8620_read_buf(struct sii8620 *ctx, u16 addr, u8 *buf, int len)
 
 static u8 sii8620_readb(struct sii8620 *ctx, u16 addr)
 {
-	u8 ret;
+	u8 ret = 0;
 
 	sii8620_read_buf(ctx, addr, &ret, 1);
 	return ret;
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
index 90f462c1555d..3781a4bbb296 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
@@ -1449,28 +1449,34 @@ static void hdmi_config_AVI(struct dw_hdmi *hdmi, struct drm_display_mode *mode)
 		frame.colorspace = HDMI_COLORSPACE_RGB;
 
 	/* Set up colorimetry */
-	switch (hdmi->hdmi_data.enc_out_encoding) {
-	case V4L2_YCBCR_ENC_601:
-		if (hdmi->hdmi_data.enc_in_encoding == V4L2_YCBCR_ENC_XV601)
-			frame.colorimetry = HDMI_COLORIMETRY_EXTENDED;
-		else
+	if (!hdmi_bus_fmt_is_rgb(hdmi->hdmi_data.enc_out_bus_format)) {
+		switch (hdmi->hdmi_data.enc_out_encoding) {
+		case V4L2_YCBCR_ENC_601:
+			if (hdmi->hdmi_data.enc_in_encoding == V4L2_YCBCR_ENC_XV601)
+				frame.colorimetry = HDMI_COLORIMETRY_EXTENDED;
+			else
+				frame.colorimetry = HDMI_COLORIMETRY_ITU_601;
+			frame.extended_colorimetry =
+					HDMI_EXTENDED_COLORIMETRY_XV_YCC_601;
+			break;
+		case V4L2_YCBCR_ENC_709:
+			if (hdmi->hdmi_data.enc_in_encoding == V4L2_YCBCR_ENC_XV709)
+				frame.colorimetry = HDMI_COLORIMETRY_EXTENDED;
+			else
+				frame.colorimetry = HDMI_COLORIMETRY_ITU_709;
+			frame.extended_colorimetry =
+					HDMI_EXTENDED_COLORIMETRY_XV_YCC_709;
+			break;
+		default: /* Carries no data */
 			frame.colorimetry = HDMI_COLORIMETRY_ITU_601;
+			frame.extended_colorimetry =
+					HDMI_EXTENDED_COLORIMETRY_XV_YCC_601;
+			break;
+		}
+	} else {
+		frame.colorimetry = HDMI_COLORIMETRY_NONE;
 		frame.extended_colorimetry =
-				HDMI_EXTENDED_COLORIMETRY_XV_YCC_601;
-		break;
-	case V4L2_YCBCR_ENC_709:
-		if (hdmi->hdmi_data.enc_in_encoding == V4L2_YCBCR_ENC_XV709)
-			frame.colorimetry = HDMI_COLORIMETRY_EXTENDED;
-		else
-			frame.colorimetry = HDMI_COLORIMETRY_ITU_709;
-		frame.extended_colorimetry =
-				HDMI_EXTENDED_COLORIMETRY_XV_YCC_709;
-		break;
-	default: /* Carries no data */
-		frame.colorimetry = HDMI_COLORIMETRY_ITU_601;
-		frame.extended_colorimetry =
-				HDMI_EXTENDED_COLORIMETRY_XV_YCC_601;
-		break;
+			HDMI_EXTENDED_COLORIMETRY_XV_YCC_601;
 	}
 
 	frame.scan_mode = HDMI_SCAN_MODE_NONE;
diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
index f72ee137e5f1..638fd14e0858 100644
--- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c
+++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
@@ -607,6 +607,12 @@ static ssize_t ti_sn_aux_transfer(struct drm_dp_aux *aux,
 				     buf[i]);
 	}
 
+	/* Clear old status bits before start so we don't get confused */
+	regmap_write(pdata->regmap, SN_AUX_CMD_STATUS_REG,
+		     AUX_IRQ_STATUS_NAT_I2C_FAIL |
+		     AUX_IRQ_STATUS_AUX_RPLY_TOUT |
+		     AUX_IRQ_STATUS_AUX_SHORT);
+
 	regmap_write(pdata->regmap, SN_AUX_CMD_REG, request_val | AUX_CMD_SEND);
 
 	ret = regmap_read_poll_timeout(pdata->regmap, SN_AUX_CMD_REG, val,
diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index b34c3d38bf15..4b728a5cbf6b 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -27,6 +27,7 @@
 #include <drm/drm_print.h>
 #include <drm/drm_drv.h>
 #include <drm/drm_file.h>
+#include <drm/drm_sysfs.h>
 
 #include <linux/uaccess.h>
 
@@ -478,6 +479,10 @@ int drm_connector_register(struct drm_connector *connector)
 	drm_mode_object_register(connector->dev, &connector->base);
 
 	connector->registration_state = DRM_CONNECTOR_REGISTERED;
+
+	/* Let userspace know we have a new connector */
+	drm_sysfs_hotplug_event(connector->dev);
+
 	goto unlock;
 
 err_debugfs:
diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c
index f8468eae0503..b531649e4ee2 100644
--- a/drivers/gpu/drm/drm_debugfs.c
+++ b/drivers/gpu/drm/drm_debugfs.c
@@ -354,13 +354,13 @@ static ssize_t connector_write(struct file *file, const char __user *ubuf,
 
 	buf[len] = '\0';
 
-	if (!strcmp(buf, "on"))
+	if (sysfs_streq(buf, "on"))
 		connector->force = DRM_FORCE_ON;
-	else if (!strcmp(buf, "digital"))
+	else if (sysfs_streq(buf, "digital"))
 		connector->force = DRM_FORCE_ON_DIGITAL;
-	else if (!strcmp(buf, "off"))
+	else if (sysfs_streq(buf, "off"))
 		connector->force = DRM_FORCE_OFF;
-	else if (!strcmp(buf, "unspecified"))
+	else if (sysfs_streq(buf, "unspecified"))
 		connector->force = DRM_FORCE_UNSPECIFIED;
 	else
 		return -EINVAL;
diff --git a/drivers/gpu/drm/drm_debugfs_crc.c b/drivers/gpu/drm/drm_debugfs_crc.c
index fde298d9f510..0496cf1ab28b 100644
--- a/drivers/gpu/drm/drm_debugfs_crc.c
+++ b/drivers/gpu/drm/drm_debugfs_crc.c
@@ -124,8 +124,8 @@ static ssize_t crc_control_write(struct file *file, const char __user *ubuf,
 	if (IS_ERR(source))
 		return PTR_ERR(source);
 
-	if (source[len] == '\n')
-		source[len] = '\0';
+	if (source[len - 1] == '\n')
+		source[len - 1] = '\0';
 
 	ret = crtc->funcs->verify_crc_source(crtc, source, &values_cnt);
 	if (ret)
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index fbfb685e4d2b..aa6e6d88f30b 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -333,7 +333,7 @@ static void drm_dp_encode_sideband_req(struct drm_dp_sideband_msg_req_body *req,
 			memcpy(&buf[idx], req->u.i2c_read.transactions[i].bytes, req->u.i2c_read.transactions[i].num_bytes);
 			idx += req->u.i2c_read.transactions[i].num_bytes;
 
-			buf[idx] = (req->u.i2c_read.transactions[i].no_stop_bit & 0x1) << 5;
+			buf[idx] = (req->u.i2c_read.transactions[i].no_stop_bit & 0x1) << 4;
 			buf[idx] |= (req->u.i2c_read.transactions[i].i2c_transaction_delay & 0xf);
 			idx++;
 		}
@@ -2569,6 +2569,7 @@ int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool ms
 	int ret = 0;
 	struct drm_dp_mst_branch *mstb = NULL;
 
+	mutex_lock(&mgr->payload_lock);
 	mutex_lock(&mgr->lock);
 	if (mst_state == mgr->mst_state)
 		goto out_unlock;
@@ -2627,7 +2628,10 @@ int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool ms
 		/* this can fail if the device is gone */
 		drm_dp_dpcd_writeb(mgr->aux, DP_MSTM_CTRL, 0);
 		ret = 0;
-		memset(mgr->payloads, 0, mgr->max_payloads * sizeof(struct drm_dp_payload));
+		memset(mgr->payloads, 0,
+		       mgr->max_payloads * sizeof(mgr->payloads[0]));
+		memset(mgr->proposed_vcpis, 0,
+		       mgr->max_payloads * sizeof(mgr->proposed_vcpis[0]));
 		mgr->payload_mask = 0;
 		set_bit(0, &mgr->payload_mask);
 		mgr->vcpi_mask = 0;
@@ -2635,6 +2639,7 @@ int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool ms
 
 out_unlock:
 	mutex_unlock(&mgr->lock);
+	mutex_unlock(&mgr->payload_lock);
 	if (mstb)
 		drm_dp_mst_topology_put_mstb(mstb);
 	return ret;
@@ -3236,11 +3241,11 @@ bool drm_dp_mst_allocate_vcpi(struct drm_dp_mst_topology_mgr *mgr,
 {
 	int ret;
 
-	port = drm_dp_mst_topology_get_port_validated(mgr, port);
-	if (!port)
+	if (slots < 0)
 		return false;
 
-	if (slots < 0)
+	port = drm_dp_mst_topology_get_port_validated(mgr, port);
+	if (!port)
 		return false;
 
 	if (port->vcpi.vcpi > 0) {
@@ -3256,6 +3261,7 @@ bool drm_dp_mst_allocate_vcpi(struct drm_dp_mst_topology_mgr *mgr,
 	if (ret) {
 		DRM_DEBUG_KMS("failed to init vcpi slots=%d max=63 ret=%d\n",
 			      DIV_ROUND_UP(pbn, mgr->pbn_div), ret);
+		drm_dp_mst_topology_put_port(port);
 		goto out;
 	}
 	DRM_DEBUG_KMS("initing vcpi for pbn=%d slots=%d\n",
@@ -3375,33 +3381,31 @@ fail:
  */
 int drm_dp_check_act_status(struct drm_dp_mst_topology_mgr *mgr)
 {
+	int count = 0, ret;
 	u8 status;
-	int ret;
-	int count = 0;
 
 	do {
-		ret = drm_dp_dpcd_readb(mgr->aux, DP_PAYLOAD_TABLE_UPDATE_STATUS, &status);
-
+		ret = drm_dp_dpcd_readb(mgr->aux,
+					DP_PAYLOAD_TABLE_UPDATE_STATUS,
+					&status);
 		if (ret < 0) {
-			DRM_DEBUG_KMS("failed to read payload table status %d\n", ret);
-			goto fail;
+			DRM_DEBUG_KMS("failed to read payload table status %d\n",
+				      ret);
+			return ret;
 		}
 
 		if (status & DP_PAYLOAD_ACT_HANDLED)
 			break;
 		count++;
 		udelay(100);
-
 	} while (count < 30);
 
 	if (!(status & DP_PAYLOAD_ACT_HANDLED)) {
-		DRM_DEBUG_KMS("failed to get ACT bit %d after %d retries\n", status, count);
-		ret = -EINVAL;
-		goto fail;
+		DRM_DEBUG_KMS("failed to get ACT bit %d after %d retries\n",
+			      status, count);
+		return -EINVAL;
 	}
 	return 0;
-fail:
-	return ret;
 }
 EXPORT_SYMBOL(drm_dp_check_act_status);
 
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 10ad140f1916..c597b89b161b 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -188,10 +188,11 @@ static const struct edid_quirk {
 	{ "HVR", 0xaa01, EDID_QUIRK_NON_DESKTOP },
 	{ "HVR", 0xaa02, EDID_QUIRK_NON_DESKTOP },
 
-	/* Oculus Rift DK1, DK2, and CV1 VR Headsets */
+	/* Oculus Rift DK1, DK2, CV1 and Rift S VR Headsets */
 	{ "OVR", 0x0001, EDID_QUIRK_NON_DESKTOP },
 	{ "OVR", 0x0003, EDID_QUIRK_NON_DESKTOP },
 	{ "OVR", 0x0004, EDID_QUIRK_NON_DESKTOP },
+	{ "OVR", 0x0012, EDID_QUIRK_NON_DESKTOP },
 
 	/* Windows Mixed Reality Headsets */
 	{ "ACR", 0x7fce, EDID_QUIRK_NON_DESKTOP },
@@ -4688,7 +4689,7 @@ static struct drm_display_mode *drm_mode_displayid_detailed(struct drm_device *d
 	struct drm_display_mode *mode;
 	unsigned pixel_clock = (timings->pixel_clock[0] |
 				(timings->pixel_clock[1] << 8) |
-				(timings->pixel_clock[2] << 16));
+				(timings->pixel_clock[2] << 16)) + 1;
 	unsigned hactive = (timings->hactive[0] | timings->hactive[1] << 8) + 1;
 	unsigned hblank = (timings->hblank[0] | timings->hblank[1] << 8) + 1;
 	unsigned hsync = (timings->hsync[0] | (timings->hsync[1] & 0x7f) << 8) + 1;
diff --git a/drivers/gpu/drm/drm_encoder_slave.c b/drivers/gpu/drm/drm_encoder_slave.c
index cf804389f5ec..d50a7884e69e 100644
--- a/drivers/gpu/drm/drm_encoder_slave.c
+++ b/drivers/gpu/drm/drm_encoder_slave.c
@@ -84,7 +84,7 @@ int drm_i2c_encoder_init(struct drm_device *dev,
 
 	err = encoder_drv->encoder_init(client, dev, encoder);
 	if (err)
-		goto fail_unregister;
+		goto fail_module_put;
 
 	if (info->platform_data)
 		encoder->slave_funcs->set_config(&encoder->base,
@@ -92,9 +92,10 @@ int drm_i2c_encoder_init(struct drm_device *dev,
 
 	return 0;
 
+fail_module_put:
+	module_put(module);
 fail_unregister:
 	i2c_unregister_device(client);
-	module_put(module);
 fail:
 	return err;
 }
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 498f95c3e81d..1124be028ff5 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -775,7 +775,11 @@ static void drm_fb_helper_dirty_blit_real(struct drm_fb_helper *fb_helper,
 	unsigned int y;
 
 	for (y = clip->y1; y < clip->y2; y++) {
-		memcpy(dst, src, len);
+		if (!fb_helper->dev->mode_config.fbdev_use_iomem)
+			memcpy(dst, src, len);
+		else
+			memcpy_toio((void __iomem *)dst, src, len);
+
 		src += fb->pitches[0];
 		dst += fb->pitches[0];
 	}
@@ -1706,7 +1710,7 @@ int drm_fb_helper_check_var(struct fb_var_screeninfo *var,
 	 * Changes struct fb_var_screeninfo are currently not pushed back
 	 * to KMS, hence fail if different settings are requested.
 	 */
-	if (var->bits_per_pixel != fb->format->cpp[0] * 8 ||
+	if (var->bits_per_pixel > fb->format->cpp[0] * 8 ||
 	    var->xres > fb->width || var->yres > fb->height ||
 	    var->xres_virtual > fb->width || var->yres_virtual > fb->height) {
 		DRM_DEBUG("fb requested width/height/bpp can't fit in current fb "
@@ -1732,6 +1736,11 @@ int drm_fb_helper_check_var(struct fb_var_screeninfo *var,
 	}
 
 	/*
+	 * Likewise, bits_per_pixel should be rounded up to a supported value.
+	 */
+	var->bits_per_pixel = fb->format->cpp[0] * 8;
+
+	/*
 	 * drm fbdev emulation doesn't support changing the pixel format at all,
 	 * so reject all pixel format changing requests.
 	 */
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 50de138c89e0..dbab035203ee 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -703,6 +703,8 @@ int drm_gem_objects_lookup(struct drm_file *filp, void __user *bo_handles,
 	if (!objs)
 		return -ENOMEM;
 
+	*objs_out = objs;
+
 	handles = kvmalloc_array(count, sizeof(u32), GFP_KERNEL);
 	if (!handles) {
 		ret = -ENOMEM;
@@ -716,8 +718,6 @@ int drm_gem_objects_lookup(struct drm_file *filp, void __user *bo_handles,
 	}
 
 	ret = objects_lookup(filp, handles, count, objs);
-	*objs_out = objs;
-
 out:
 	kvfree(handles);
 	return ret;
@@ -865,9 +865,6 @@ err:
  * @file_priv: drm file-private structure
  *
  * Open an object using the global name, returning a handle and the size.
- *
- * This handle (of course) holds a reference to the object, so the object
- * will not go away until the handle is deleted.
  */
 int
 drm_gem_open_ioctl(struct drm_device *dev, void *data,
@@ -892,14 +889,15 @@ drm_gem_open_ioctl(struct drm_device *dev, void *data,
 
 	/* drm_gem_handle_create_tail unlocks dev->object_name_lock. */
 	ret = drm_gem_handle_create_tail(file_priv, obj, &handle);
-	drm_gem_object_put_unlocked(obj);
 	if (ret)
-		return ret;
+		goto err;
 
 	args->handle = handle;
 	args->size = obj->size;
 
-	return 0;
+err:
+	drm_gem_object_put_unlocked(obj);
+	return ret;
 }
 
 /**
diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c
index e8a5e3b13b2a..f668238e47bf 100644
--- a/drivers/gpu/drm/drm_lease.c
+++ b/drivers/gpu/drm/drm_lease.c
@@ -537,10 +537,12 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev,
 	}
 
 	DRM_DEBUG_LEASE("Creating lease\n");
+	/* lessee will take the ownership of leases */
 	lessee = drm_lease_create(lessor, &leases);
 
 	if (IS_ERR(lessee)) {
 		ret = PTR_ERR(lessee);
+		idr_destroy(&leases);
 		goto out_leases;
 	}
 
@@ -575,7 +577,6 @@ out_lessee:
 
 out_leases:
 	put_unused_fd(fd);
-	idr_destroy(&leases);
 
 	DRM_DEBUG_LEASE("drm_mode_create_lease_ioctl failed: %d\n", ret);
 	return ret;
diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c
index 80b75501f5c6..7ed8e510565e 100644
--- a/drivers/gpu/drm/drm_mipi_dsi.c
+++ b/drivers/gpu/drm/drm_mipi_dsi.c
@@ -1034,11 +1034,11 @@ EXPORT_SYMBOL(mipi_dsi_dcs_set_pixel_format);
  */
 int mipi_dsi_dcs_set_tear_scanline(struct mipi_dsi_device *dsi, u16 scanline)
 {
-	u8 payload[3] = { MIPI_DCS_SET_TEAR_SCANLINE, scanline >> 8,
-			  scanline & 0xff };
+	u8 payload[2] = { scanline >> 8, scanline & 0xff };
 	ssize_t err;
 
-	err = mipi_dsi_generic_write(dsi, payload, sizeof(payload));
+	err = mipi_dsi_dcs_write(dsi, MIPI_DCS_SET_TEAR_SCANLINE, payload,
+				 sizeof(payload));
 	if (err < 0)
 		return err;
 
diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c
index ffd95bfeaa94..58f5dc2f6dd5 100644
--- a/drivers/gpu/drm/drm_panel_orientation_quirks.c
+++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c
@@ -30,12 +30,6 @@ struct drm_dmi_panel_orientation_data {
 	int orientation;
 };
 
-static const struct drm_dmi_panel_orientation_data acer_s1003 = {
-	.width = 800,
-	.height = 1280,
-	.orientation = DRM_MODE_PANEL_ORIENTATION_RIGHT_UP,
-};
-
 static const struct drm_dmi_panel_orientation_data asus_t100ha = {
 	.width = 800,
 	.height = 1280,
@@ -114,13 +108,25 @@ static const struct dmi_system_id orientation_data[] = {
 		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Acer"),
 		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "One S1003"),
 		},
-		.driver_data = (void *)&acer_s1003,
+		.driver_data = (void *)&lcd800x1280_rightside_up,
 	}, {	/* Asus T100HA */
 		.matches = {
 		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
 		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100HAN"),
 		},
 		.driver_data = (void *)&asus_t100ha,
+	}, {	/* Asus T101HA */
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T101HA"),
+		},
+		.driver_data = (void *)&lcd800x1280_rightside_up,
+	}, {	/* Asus T103HAF */
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T103HAF"),
+		},
+		.driver_data = (void *)&lcd800x1280_rightside_up,
 	}, {	/* GPD MicroPC (generic strings, also match on bios date) */
 		.matches = {
 		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Default string"),
diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c
index 693748ad8b88..18f070634170 100644
--- a/drivers/gpu/drm/drm_pci.c
+++ b/drivers/gpu/drm/drm_pci.c
@@ -46,8 +46,6 @@
 drm_dma_handle_t *drm_pci_alloc(struct drm_device * dev, size_t size, size_t align)
 {
 	drm_dma_handle_t *dmah;
-	unsigned long addr;
-	size_t sz;
 
 	/* pci_alloc_consistent only guarantees alignment to the smallest
 	 * PAGE_SIZE order which is greater than or equal to the requested size.
@@ -63,20 +61,13 @@ drm_dma_handle_t *drm_pci_alloc(struct drm_device * dev, size_t size, size_t ali
 	dmah->size = size;
 	dmah->vaddr = dma_alloc_coherent(&dev->pdev->dev, size,
 					 &dmah->busaddr,
-					 GFP_KERNEL | __GFP_COMP);
+					 GFP_KERNEL);
 
 	if (dmah->vaddr == NULL) {
 		kfree(dmah);
 		return NULL;
 	}
 
-	/* XXX - Is virt_to_page() legal for consistent mem? */
-	/* Reserve */
-	for (addr = (unsigned long)dmah->vaddr, sz = size;
-	     sz > 0; addr += PAGE_SIZE, sz -= PAGE_SIZE) {
-		SetPageReserved(virt_to_page((void *)addr));
-	}
-
 	return dmah;
 }
 
@@ -89,19 +80,9 @@ EXPORT_SYMBOL(drm_pci_alloc);
  */
 void __drm_legacy_pci_free(struct drm_device * dev, drm_dma_handle_t * dmah)
 {
-	unsigned long addr;
-	size_t sz;
-
-	if (dmah->vaddr) {
-		/* XXX - Is virt_to_page() legal for consistent mem? */
-		/* Unreserve */
-		for (addr = (unsigned long)dmah->vaddr, sz = dmah->size;
-		     sz > 0; addr += PAGE_SIZE, sz -= PAGE_SIZE) {
-			ClearPageReserved(virt_to_page((void *)addr));
-		}
+	if (dmah->vaddr)
 		dma_free_coherent(&dev->pdev->dev, dmah->size, dmah->vaddr,
 				  dmah->busaddr);
-	}
 }
 
 /**
diff --git a/drivers/gpu/drm/drm_rect.c b/drivers/gpu/drm/drm_rect.c
index 66c41b12719c..70f0dc83d1d7 100644
--- a/drivers/gpu/drm/drm_rect.c
+++ b/drivers/gpu/drm/drm_rect.c
@@ -52,7 +52,12 @@ EXPORT_SYMBOL(drm_rect_intersect);
 
 static u32 clip_scaled(u32 src, u32 dst, u32 clip)
 {
-	u64 tmp = mul_u32_u32(src, dst - clip);
+	u64 tmp;
+
+	if (dst == 0)
+		return 0;
+
+	tmp = mul_u32_u32(src, dst - clip);
 
 	/*
 	 * Round toward 1.0 when clipping so that we don't accidentally
diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index 3d400905100b..cecff2e447b1 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -1292,14 +1292,14 @@ int drm_syncobj_query_ioctl(struct drm_device *dev, void *data,
 			struct dma_fence *iter, *last_signaled = NULL;
 
 			dma_fence_chain_for_each(iter, fence) {
-				if (!iter)
-					break;
-				dma_fence_put(last_signaled);
-				last_signaled = dma_fence_get(iter);
-				if (!to_dma_fence_chain(last_signaled)->prev_seqno)
+				if (iter->context != fence->context) {
+					dma_fence_put(iter);
 					/* It is most likely that timeline has
 					 * unorder points. */
 					break;
+				}
+				dma_fence_put(last_signaled);
+				last_signaled = dma_fence_get(iter);
 			}
 			point = dma_fence_is_signaled(last_signaled) ?
 				last_signaled->seqno :
diff --git a/drivers/gpu/drm/drm_sysfs.c b/drivers/gpu/drm/drm_sysfs.c
index 74857fafb0b8..04ae7f0d5ae2 100644
--- a/drivers/gpu/drm/drm_sysfs.c
+++ b/drivers/gpu/drm/drm_sysfs.c
@@ -282,9 +282,6 @@ int drm_sysfs_connector_add(struct drm_connector *connector)
 		return PTR_ERR(connector->kdev);
 	}
 
-	/* Let userspace know we have a new connector */
-	drm_sysfs_hotplug_event(dev);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
index 5418a1a87b2c..517d87175fed 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
@@ -694,7 +694,7 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu)
 	ret = pm_runtime_get_sync(gpu->dev);
 	if (ret < 0) {
 		dev_err(gpu->dev, "Failed to enable GPU power domain\n");
-		return ret;
+		goto pm_put;
 	}
 
 	etnaviv_hw_identify(gpu);
@@ -808,6 +808,7 @@ destroy_iommu:
 	gpu->mmu = NULL;
 fail:
 	pm_runtime_mark_last_busy(gpu->dev);
+pm_put:
 	pm_runtime_put_autosuspend(gpu->dev);
 
 	return ret;
@@ -848,7 +849,7 @@ int etnaviv_gpu_debugfs(struct etnaviv_gpu *gpu, struct seq_file *m)
 
 	ret = pm_runtime_get_sync(gpu->dev);
 	if (ret < 0)
-		return ret;
+		goto pm_put;
 
 	dma_lo = gpu_read(gpu, VIVS_FE_DMA_LOW);
 	dma_hi = gpu_read(gpu, VIVS_FE_DMA_HIGH);
@@ -971,6 +972,7 @@ int etnaviv_gpu_debugfs(struct etnaviv_gpu *gpu, struct seq_file *m)
 	ret = 0;
 
 	pm_runtime_mark_last_busy(gpu->dev);
+pm_put:
 	pm_runtime_put_autosuspend(gpu->dev);
 
 	return ret;
@@ -984,7 +986,7 @@ void etnaviv_gpu_recover_hang(struct etnaviv_gpu *gpu)
 	dev_err(gpu->dev, "recover hung GPU!\n");
 
 	if (pm_runtime_get_sync(gpu->dev) < 0)
-		return;
+		goto pm_put;
 
 	mutex_lock(&gpu->lock);
 
@@ -1002,6 +1004,7 @@ void etnaviv_gpu_recover_hang(struct etnaviv_gpu *gpu)
 
 	mutex_unlock(&gpu->lock);
 	pm_runtime_mark_last_busy(gpu->dev);
+pm_put:
 	pm_runtime_put_autosuspend(gpu->dev);
 }
 
@@ -1274,8 +1277,10 @@ struct dma_fence *etnaviv_gpu_submit(struct etnaviv_gem_submit *submit)
 
 	if (!submit->runtime_resumed) {
 		ret = pm_runtime_get_sync(gpu->dev);
-		if (ret < 0)
+		if (ret < 0) {
+			pm_runtime_put_noidle(gpu->dev);
 			return NULL;
+		}
 		submit->runtime_resumed = true;
 	}
 
@@ -1292,6 +1297,7 @@ struct dma_fence *etnaviv_gpu_submit(struct etnaviv_gem_submit *submit)
 	ret = event_alloc(gpu, nr_events, event);
 	if (ret) {
 		DRM_ERROR("no free events\n");
+		pm_runtime_put_noidle(gpu->dev);
 		return NULL;
 	}
 
@@ -1453,7 +1459,7 @@ static int etnaviv_gpu_clk_enable(struct etnaviv_gpu *gpu)
 	if (gpu->clk_bus) {
 		ret = clk_prepare_enable(gpu->clk_bus);
 		if (ret)
-			return ret;
+			goto disable_clk_reg;
 	}
 
 	if (gpu->clk_core) {
@@ -1476,6 +1482,9 @@ disable_clk_core:
 disable_clk_bus:
 	if (gpu->clk_bus)
 		clk_disable_unprepare(gpu->clk_bus);
+disable_clk_reg:
+	if (gpu->clk_reg)
+		clk_disable_unprepare(gpu->clk_reg);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_perfmon.c b/drivers/gpu/drm/etnaviv/etnaviv_perfmon.c
index 4227a4006c34..b3464d2dc2b4 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_perfmon.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_perfmon.c
@@ -4,6 +4,7 @@
  * Copyright (C) 2017 Zodiac Inflight Innovations
  */
 
+#include "common.xml.h"
 #include "etnaviv_gpu.h"
 #include "etnaviv_perfmon.h"
 #include "state_hi.xml.h"
@@ -31,17 +32,11 @@ struct etnaviv_pm_domain {
 };
 
 struct etnaviv_pm_domain_meta {
+	unsigned int feature;
 	const struct etnaviv_pm_domain *domains;
 	u32 nr_domains;
 };
 
-static u32 simple_reg_read(struct etnaviv_gpu *gpu,
-	const struct etnaviv_pm_domain *domain,
-	const struct etnaviv_pm_signal *signal)
-{
-	return gpu_read(gpu, signal->data);
-}
-
 static u32 perf_reg_read(struct etnaviv_gpu *gpu,
 	const struct etnaviv_pm_domain *domain,
 	const struct etnaviv_pm_signal *signal)
@@ -75,6 +70,34 @@ static u32 pipe_reg_read(struct etnaviv_gpu *gpu,
 	return value;
 }
 
+static u32 hi_total_cycle_read(struct etnaviv_gpu *gpu,
+	const struct etnaviv_pm_domain *domain,
+	const struct etnaviv_pm_signal *signal)
+{
+	u32 reg = VIVS_HI_PROFILE_TOTAL_CYCLES;
+
+	if (gpu->identity.model == chipModel_GC880 ||
+		gpu->identity.model == chipModel_GC2000 ||
+		gpu->identity.model == chipModel_GC2100)
+		reg = VIVS_MC_PROFILE_CYCLE_COUNTER;
+
+	return gpu_read(gpu, reg);
+}
+
+static u32 hi_total_idle_cycle_read(struct etnaviv_gpu *gpu,
+	const struct etnaviv_pm_domain *domain,
+	const struct etnaviv_pm_signal *signal)
+{
+	u32 reg = VIVS_HI_PROFILE_IDLE_CYCLES;
+
+	if (gpu->identity.model == chipModel_GC880 ||
+		gpu->identity.model == chipModel_GC2000 ||
+		gpu->identity.model == chipModel_GC2100)
+		reg = VIVS_HI_PROFILE_TOTAL_CYCLES;
+
+	return gpu_read(gpu, reg);
+}
+
 static const struct etnaviv_pm_domain doms_3d[] = {
 	{
 		.name = "HI",
@@ -84,13 +107,13 @@ static const struct etnaviv_pm_domain doms_3d[] = {
 		.signal = (const struct etnaviv_pm_signal[]) {
 			{
 				"TOTAL_CYCLES",
-				VIVS_HI_PROFILE_TOTAL_CYCLES,
-				&simple_reg_read
+				0,
+				&hi_total_cycle_read
 			},
 			{
 				"IDLE_CYCLES",
-				VIVS_HI_PROFILE_IDLE_CYCLES,
-				&simple_reg_read
+				0,
+				&hi_total_idle_cycle_read
 			},
 			{
 				"AXI_CYCLES_READ_REQUEST_STALLED",
@@ -388,36 +411,78 @@ static const struct etnaviv_pm_domain doms_vg[] = {
 
 static const struct etnaviv_pm_domain_meta doms_meta[] = {
 	{
+		.feature = chipFeatures_PIPE_3D,
 		.nr_domains = ARRAY_SIZE(doms_3d),
 		.domains = &doms_3d[0]
 	},
 	{
+		.feature = chipFeatures_PIPE_2D,
 		.nr_domains = ARRAY_SIZE(doms_2d),
 		.domains = &doms_2d[0]
 	},
 	{
+		.feature = chipFeatures_PIPE_VG,
 		.nr_domains = ARRAY_SIZE(doms_vg),
 		.domains = &doms_vg[0]
 	}
 };
 
+static unsigned int num_pm_domains(const struct etnaviv_gpu *gpu)
+{
+	unsigned int num = 0, i;
+
+	for (i = 0; i < ARRAY_SIZE(doms_meta); i++) {
+		const struct etnaviv_pm_domain_meta *meta = &doms_meta[i];
+
+		if (gpu->identity.features & meta->feature)
+			num += meta->nr_domains;
+	}
+
+	return num;
+}
+
+static const struct etnaviv_pm_domain *pm_domain(const struct etnaviv_gpu *gpu,
+	unsigned int index)
+{
+	const struct etnaviv_pm_domain *domain = NULL;
+	unsigned int offset = 0, i;
+
+	for (i = 0; i < ARRAY_SIZE(doms_meta); i++) {
+		const struct etnaviv_pm_domain_meta *meta = &doms_meta[i];
+
+		if (!(gpu->identity.features & meta->feature))
+			continue;
+
+		if (index - offset >= meta->nr_domains) {
+			offset += meta->nr_domains;
+			continue;
+		}
+
+		domain = meta->domains + (index - offset);
+	}
+
+	return domain;
+}
+
 int etnaviv_pm_query_dom(struct etnaviv_gpu *gpu,
 	struct drm_etnaviv_pm_domain *domain)
 {
-	const struct etnaviv_pm_domain_meta *meta = &doms_meta[domain->pipe];
+	const unsigned int nr_domains = num_pm_domains(gpu);
 	const struct etnaviv_pm_domain *dom;
 
-	if (domain->iter >= meta->nr_domains)
+	if (domain->iter >= nr_domains)
 		return -EINVAL;
 
-	dom = meta->domains + domain->iter;
+	dom = pm_domain(gpu, domain->iter);
+	if (!dom)
+		return -EINVAL;
 
 	domain->id = domain->iter;
 	domain->nr_signals = dom->nr_signals;
 	strncpy(domain->name, dom->name, sizeof(domain->name));
 
 	domain->iter++;
-	if (domain->iter == meta->nr_domains)
+	if (domain->iter == nr_domains)
 		domain->iter = 0xff;
 
 	return 0;
@@ -426,14 +491,16 @@ int etnaviv_pm_query_dom(struct etnaviv_gpu *gpu,
 int etnaviv_pm_query_sig(struct etnaviv_gpu *gpu,
 	struct drm_etnaviv_pm_signal *signal)
 {
-	const struct etnaviv_pm_domain_meta *meta = &doms_meta[signal->pipe];
+	const unsigned int nr_domains = num_pm_domains(gpu);
 	const struct etnaviv_pm_domain *dom;
 	const struct etnaviv_pm_signal *sig;
 
-	if (signal->domain >= meta->nr_domains)
+	if (signal->domain >= nr_domains)
 		return -EINVAL;
 
-	dom = meta->domains + signal->domain;
+	dom = pm_domain(gpu, signal->domain);
+	if (!dom)
+		return -EINVAL;
 
 	if (signal->iter >= dom->nr_signals)
 		return -EINVAL;
diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
index 0650b619de24..debfdbdc45fb 100644
--- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
@@ -52,6 +52,7 @@ static const char * const decon_clks_name[] = {
 struct decon_context {
 	struct device			*dev;
 	struct drm_device		*drm_dev;
+	void				*dma_priv;
 	struct exynos_drm_crtc		*crtc;
 	struct exynos_drm_plane		planes[WINDOWS_NR];
 	struct exynos_drm_plane_config	configs[WINDOWS_NR];
@@ -641,7 +642,7 @@ static int decon_bind(struct device *dev, struct device *master, void *data)
 
 	decon_clear_channels(ctx->crtc);
 
-	return exynos_drm_register_dma(drm_dev, dev);
+	return exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv);
 }
 
 static void decon_unbind(struct device *dev, struct device *master, void *data)
@@ -651,7 +652,7 @@ static void decon_unbind(struct device *dev, struct device *master, void *data)
 	decon_disable(ctx->crtc);
 
 	/* detach this sub driver from iommu mapping if supported. */
-	exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev);
+	exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev, &ctx->dma_priv);
 }
 
 static const struct component_ops decon_component_ops = {
diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
index 13509ca8aa35..a46e26da7397 100644
--- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
@@ -38,6 +38,7 @@
 struct decon_context {
 	struct device			*dev;
 	struct drm_device		*drm_dev;
+	void				*dma_priv;
 	struct exynos_drm_crtc		*crtc;
 	struct exynos_drm_plane		planes[WINDOWS_NR];
 	struct exynos_drm_plane_config	configs[WINDOWS_NR];
@@ -125,13 +126,13 @@ static int decon_ctx_initialize(struct decon_context *ctx,
 
 	decon_clear_channels(ctx->crtc);
 
-	return exynos_drm_register_dma(drm_dev, ctx->dev);
+	return exynos_drm_register_dma(drm_dev, ctx->dev, &ctx->dma_priv);
 }
 
 static void decon_ctx_remove(struct decon_context *ctx)
 {
 	/* detach this sub driver from iommu mapping if supported. */
-	exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev);
+	exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev, &ctx->dma_priv);
 }
 
 static u32 decon_calc_clkdiv(struct decon_context *ctx,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dma.c b/drivers/gpu/drm/exynos/exynos_drm_dma.c
index bef8bc3c8e00..38f7e9dc9485 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dma.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dma.c
@@ -56,10 +56,10 @@ static inline void clear_dma_max_seg_size(struct device *dev)
  * mapping.
  */
 static int drm_iommu_attach_device(struct drm_device *drm_dev,
-				struct device *subdrv_dev)
+				struct device *subdrv_dev, void **dma_priv)
 {
 	struct exynos_drm_private *priv = drm_dev->dev_private;
-	int ret;
+	int ret = 0;
 
 	if (get_dma_ops(priv->dma_dev) != get_dma_ops(subdrv_dev)) {
 		DRM_DEV_ERROR(subdrv_dev, "Device %s lacks support for IOMMU\n",
@@ -72,7 +72,14 @@ static int drm_iommu_attach_device(struct drm_device *drm_dev,
 		return ret;
 
 	if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)) {
-		if (to_dma_iommu_mapping(subdrv_dev))
+		/*
+		 * Keep the original DMA mapping of the sub-device and
+		 * restore it on Exynos DRM detach, otherwise the DMA
+		 * framework considers it as IOMMU-less during the next
+		 * probe (in case of deferred probe or modular build)
+		 */
+		*dma_priv = to_dma_iommu_mapping(subdrv_dev);
+		if (*dma_priv)
 			arm_iommu_detach_device(subdrv_dev);
 
 		ret = arm_iommu_attach_device(subdrv_dev, priv->mapping);
@@ -83,7 +90,7 @@ static int drm_iommu_attach_device(struct drm_device *drm_dev,
 	if (ret)
 		clear_dma_max_seg_size(subdrv_dev);
 
-	return 0;
+	return ret;
 }
 
 /*
@@ -96,19 +103,21 @@ static int drm_iommu_attach_device(struct drm_device *drm_dev,
  * mapping
  */
 static void drm_iommu_detach_device(struct drm_device *drm_dev,
-				struct device *subdrv_dev)
+				    struct device *subdrv_dev, void **dma_priv)
 {
 	struct exynos_drm_private *priv = drm_dev->dev_private;
 
-	if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU))
+	if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)) {
 		arm_iommu_detach_device(subdrv_dev);
-	else if (IS_ENABLED(CONFIG_IOMMU_DMA))
+		arm_iommu_attach_device(subdrv_dev, *dma_priv);
+	} else if (IS_ENABLED(CONFIG_IOMMU_DMA))
 		iommu_detach_device(priv->mapping, subdrv_dev);
 
 	clear_dma_max_seg_size(subdrv_dev);
 }
 
-int exynos_drm_register_dma(struct drm_device *drm, struct device *dev)
+int exynos_drm_register_dma(struct drm_device *drm, struct device *dev,
+			    void **dma_priv)
 {
 	struct exynos_drm_private *priv = drm->dev_private;
 
@@ -135,13 +144,14 @@ int exynos_drm_register_dma(struct drm_device *drm, struct device *dev)
 		priv->mapping = mapping;
 	}
 
-	return drm_iommu_attach_device(drm, dev);
+	return drm_iommu_attach_device(drm, dev, dma_priv);
 }
 
-void exynos_drm_unregister_dma(struct drm_device *drm, struct device *dev)
+void exynos_drm_unregister_dma(struct drm_device *drm, struct device *dev,
+			       void **dma_priv)
 {
 	if (IS_ENABLED(CONFIG_EXYNOS_IOMMU))
-		drm_iommu_detach_device(drm, dev);
+		drm_iommu_detach_device(drm, dev, dma_priv);
 }
 
 void exynos_drm_cleanup_dma(struct drm_device *drm)
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h
index 18b03b83f8a3..5e6762e76a04 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h
@@ -217,8 +217,10 @@ static inline bool is_drm_iommu_supported(struct drm_device *drm_dev)
 	return priv->mapping ? true : false;
 }
 
-int exynos_drm_register_dma(struct drm_device *drm, struct device *dev);
-void exynos_drm_unregister_dma(struct drm_device *drm, struct device *dev);
+int exynos_drm_register_dma(struct drm_device *drm, struct device *dev,
+			    void **dma_priv);
+void exynos_drm_unregister_dma(struct drm_device *drm, struct device *dev,
+			       void **dma_priv);
 void exynos_drm_cleanup_dma(struct drm_device *drm);
 
 #ifdef CONFIG_DRM_EXYNOS_DPI
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
index 8f62581e2d0f..fa8f10fa366e 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
@@ -1749,8 +1749,9 @@ static int exynos_dsi_probe(struct platform_device *pdev)
 	ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(dsi->supplies),
 				      dsi->supplies);
 	if (ret) {
-		dev_info(dev, "failed to get regulators: %d\n", ret);
-		return -EPROBE_DEFER;
+		if (ret != -EPROBE_DEFER)
+			dev_info(dev, "failed to get regulators: %d\n", ret);
+		return ret;
 	}
 
 	dsi->clks = devm_kcalloc(dev,
@@ -1763,9 +1764,10 @@ static int exynos_dsi_probe(struct platform_device *pdev)
 		dsi->clks[i] = devm_clk_get(dev, clk_names[i]);
 		if (IS_ERR(dsi->clks[i])) {
 			if (strcmp(clk_names[i], "sclk_mipi") == 0) {
-				strcpy(clk_names[i], OLD_SCLK_MIPI_CLK_NAME);
-				i--;
-				continue;
+				dsi->clks[i] = devm_clk_get(dev,
+							OLD_SCLK_MIPI_CLK_NAME);
+				if (!IS_ERR(dsi->clks[i]))
+					continue;
 			}
 
 			dev_info(dev, "failed to get the clock: %s\n",
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
index 0db29690ede3..2257e5091f26 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
@@ -94,6 +94,7 @@ struct fimc_scaler {
 struct fimc_context {
 	struct exynos_drm_ipp ipp;
 	struct drm_device *drm_dev;
+	void		*dma_priv;
 	struct device	*dev;
 	struct exynos_drm_ipp_task	*task;
 	struct exynos_drm_ipp_formats	*formats;
@@ -1130,7 +1131,7 @@ static int fimc_bind(struct device *dev, struct device *master, void *data)
 
 	ctx->drm_dev = drm_dev;
 	ipp->drm_dev = drm_dev;
-	exynos_drm_register_dma(drm_dev, dev);
+	exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv);
 
 	exynos_drm_ipp_register(dev, ipp, &ipp_funcs,
 			DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE |
@@ -1150,7 +1151,7 @@ static void fimc_unbind(struct device *dev, struct device *master,
 	struct exynos_drm_ipp *ipp = &ctx->ipp;
 
 	exynos_drm_ipp_unregister(dev, ipp);
-	exynos_drm_unregister_dma(drm_dev, dev);
+	exynos_drm_unregister_dma(drm_dev, dev, &ctx->dma_priv);
 }
 
 static const struct component_ops fimc_component_ops = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index e9106b1f4a50..8666ad4e7e7c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -165,6 +165,7 @@ static struct fimd_driver_data exynos5420_fimd_driver_data = {
 struct fimd_context {
 	struct device			*dev;
 	struct drm_device		*drm_dev;
+	void				*dma_priv;
 	struct exynos_drm_crtc		*crtc;
 	struct exynos_drm_plane		planes[WINDOWS_NR];
 	struct exynos_drm_plane_config	configs[WINDOWS_NR];
@@ -1088,7 +1089,7 @@ static int fimd_bind(struct device *dev, struct device *master, void *data)
 	if (is_drm_iommu_supported(drm_dev))
 		fimd_clear_channels(ctx->crtc);
 
-	return exynos_drm_register_dma(drm_dev, dev);
+	return exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv);
 }
 
 static void fimd_unbind(struct device *dev, struct device *master,
@@ -1098,7 +1099,7 @@ static void fimd_unbind(struct device *dev, struct device *master,
 
 	fimd_disable(ctx->crtc);
 
-	exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev);
+	exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev, &ctx->dma_priv);
 
 	if (ctx->encoder)
 		exynos_dpi_remove(ctx->encoder);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index 2e4b9434245b..fa32ebeff722 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -229,6 +229,7 @@ struct g2d_runqueue_node {
 
 struct g2d_data {
 	struct device			*dev;
+	void				*dma_priv;
 	struct clk			*gate_clk;
 	void __iomem			*regs;
 	int				irq;
@@ -1406,7 +1407,7 @@ static int g2d_bind(struct device *dev, struct device *master, void *data)
 		return ret;
 	}
 
-	ret = exynos_drm_register_dma(drm_dev, dev);
+	ret = exynos_drm_register_dma(drm_dev, dev, &g2d->dma_priv);
 	if (ret < 0) {
 		dev_err(dev, "failed to enable iommu.\n");
 		g2d_fini_cmdlist(g2d);
@@ -1431,7 +1432,7 @@ static void g2d_unbind(struct device *dev, struct device *master, void *data)
 	priv->g2d_dev = NULL;
 
 	cancel_work_sync(&g2d->runqueue_work);
-	exynos_drm_unregister_dma(g2d->drm_dev, dev);
+	exynos_drm_unregister_dma(g2d->drm_dev, dev, &g2d->dma_priv);
 }
 
 static const struct component_ops g2d_component_ops = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
index 05b0fe21b81e..668ac13b712d 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
@@ -94,6 +94,7 @@ struct gsc_scaler {
 struct gsc_context {
 	struct exynos_drm_ipp ipp;
 	struct drm_device *drm_dev;
+	void		*dma_priv;
 	struct device	*dev;
 	struct exynos_drm_ipp_task	*task;
 	struct exynos_drm_ipp_formats	*formats;
@@ -1166,7 +1167,7 @@ static int gsc_bind(struct device *dev, struct device *master, void *data)
 
 	ctx->drm_dev = drm_dev;
 	ctx->drm_dev = drm_dev;
-	exynos_drm_register_dma(drm_dev, dev);
+	exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv);
 
 	exynos_drm_ipp_register(dev, ipp, &ipp_funcs,
 			DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE |
@@ -1186,7 +1187,7 @@ static void gsc_unbind(struct device *dev, struct device *master,
 	struct exynos_drm_ipp *ipp = &ctx->ipp;
 
 	exynos_drm_ipp_unregister(dev, ipp);
-	exynos_drm_unregister_dma(drm_dev, dev);
+	exynos_drm_unregister_dma(drm_dev, dev, &ctx->dma_priv);
 }
 
 static const struct component_ops gsc_component_ops = {
@@ -1310,6 +1311,7 @@ static int gsc_remove(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 
+	component_del(dev, &gsc_component_ops);
 	pm_runtime_dont_use_autosuspend(dev);
 	pm_runtime_disable(dev);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_mic.c b/drivers/gpu/drm/exynos/exynos_drm_mic.c
index 8363cb40daed..08e5e45eaf0e 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_mic.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_mic.c
@@ -266,8 +266,10 @@ static void mic_pre_enable(struct drm_bridge *bridge)
 		goto unlock;
 
 	ret = pm_runtime_get_sync(mic->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_noidle(mic->dev);
 		goto unlock;
+	}
 
 	mic_set_path(mic, 1);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
index 85e30cb6c23f..330631167d3a 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
@@ -54,6 +54,7 @@ struct rot_variant {
 struct rot_context {
 	struct exynos_drm_ipp ipp;
 	struct drm_device *drm_dev;
+	void		*dma_priv;
 	struct device	*dev;
 	void __iomem	*regs;
 	struct clk	*clock;
@@ -241,7 +242,7 @@ static int rotator_bind(struct device *dev, struct device *master, void *data)
 
 	rot->drm_dev = drm_dev;
 	ipp->drm_dev = drm_dev;
-	exynos_drm_register_dma(drm_dev, dev);
+	exynos_drm_register_dma(drm_dev, dev, &rot->dma_priv);
 
 	exynos_drm_ipp_register(dev, ipp, &ipp_funcs,
 			   DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE,
@@ -259,7 +260,7 @@ static void rotator_unbind(struct device *dev, struct device *master,
 	struct exynos_drm_ipp *ipp = &rot->ipp;
 
 	exynos_drm_ipp_unregister(dev, ipp);
-	exynos_drm_unregister_dma(rot->drm_dev, rot->dev);
+	exynos_drm_unregister_dma(rot->drm_dev, rot->dev, &rot->dma_priv);
 }
 
 static const struct component_ops rotator_component_ops = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_scaler.c b/drivers/gpu/drm/exynos/exynos_drm_scaler.c
index 8989f8af716b..d78c6529b11d 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_scaler.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_scaler.c
@@ -38,6 +38,7 @@ struct scaler_data {
 struct scaler_context {
 	struct exynos_drm_ipp		ipp;
 	struct drm_device		*drm_dev;
+	void				*dma_priv;
 	struct device			*dev;
 	void __iomem			*regs;
 	struct clk			*clock[SCALER_MAX_CLK];
@@ -449,7 +450,7 @@ static int scaler_bind(struct device *dev, struct device *master, void *data)
 
 	scaler->drm_dev = drm_dev;
 	ipp->drm_dev = drm_dev;
-	exynos_drm_register_dma(drm_dev, dev);
+	exynos_drm_register_dma(drm_dev, dev, &scaler->dma_priv);
 
 	exynos_drm_ipp_register(dev, ipp, &ipp_funcs,
 			DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE |
@@ -469,7 +470,8 @@ static void scaler_unbind(struct device *dev, struct device *master,
 	struct exynos_drm_ipp *ipp = &scaler->ipp;
 
 	exynos_drm_ipp_unregister(dev, ipp);
-	exynos_drm_unregister_dma(scaler->drm_dev, scaler->dev);
+	exynos_drm_unregister_dma(scaler->drm_dev, scaler->dev,
+				  &scaler->dma_priv);
 }
 
 static const struct component_ops scaler_component_ops = {
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index 894a99793633..086600c7b724 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -1789,18 +1789,10 @@ static int hdmi_resources_init(struct hdmi_context *hdata)
 
 	hdata->reg_hdmi_en = devm_regulator_get_optional(dev, "hdmi-en");
 
-	if (PTR_ERR(hdata->reg_hdmi_en) != -ENODEV) {
+	if (PTR_ERR(hdata->reg_hdmi_en) != -ENODEV)
 		if (IS_ERR(hdata->reg_hdmi_en))
 			return PTR_ERR(hdata->reg_hdmi_en);
 
-		ret = regulator_enable(hdata->reg_hdmi_en);
-		if (ret) {
-			DRM_DEV_ERROR(dev,
-				      "failed to enable hdmi-en regulator\n");
-			return ret;
-		}
-	}
-
 	return hdmi_bridge_init(hdata);
 }
 
@@ -2013,6 +2005,15 @@ static int hdmi_probe(struct platform_device *pdev)
 		goto err_hdmiphy;
 	}
 
+	if (!IS_ERR(hdata->reg_hdmi_en)) {
+		ret = regulator_enable(hdata->reg_hdmi_en);
+		if (ret) {
+			DRM_DEV_ERROR(dev,
+			      "failed to enable hdmi-en regulator\n");
+			goto err_hdmiphy;
+		}
+	}
+
 	pm_runtime_enable(dev);
 
 	audio_infoframe = &hdata->audio.infoframe;
@@ -2038,7 +2039,8 @@ err_unregister_audio:
 err_notifier_put:
 	cec_notifier_put(hdata->notifier);
 	pm_runtime_disable(dev);
-
+	if (!IS_ERR(hdata->reg_hdmi_en))
+		regulator_disable(hdata->reg_hdmi_en);
 err_hdmiphy:
 	if (hdata->hdmiphy_port)
 		put_device(&hdata->hdmiphy_port->dev);
diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c
index db0b698ea8ea..3eeb04b1fcd8 100644
--- a/drivers/gpu/drm/exynos/exynos_mixer.c
+++ b/drivers/gpu/drm/exynos/exynos_mixer.c
@@ -95,6 +95,7 @@ struct mixer_context {
 	struct platform_device *pdev;
 	struct device		*dev;
 	struct drm_device	*drm_dev;
+	void			*dma_priv;
 	struct exynos_drm_crtc	*crtc;
 	struct exynos_drm_plane	planes[MIXER_WIN_NR];
 	unsigned long		flags;
@@ -895,12 +896,14 @@ static int mixer_initialize(struct mixer_context *mixer_ctx,
 		}
 	}
 
-	return exynos_drm_register_dma(drm_dev, mixer_ctx->dev);
+	return exynos_drm_register_dma(drm_dev, mixer_ctx->dev,
+				       &mixer_ctx->dma_priv);
 }
 
 static void mixer_ctx_remove(struct mixer_context *mixer_ctx)
 {
-	exynos_drm_unregister_dma(mixer_ctx->drm_dev, mixer_ctx->dev);
+	exynos_drm_unregister_dma(mixer_ctx->drm_dev, mixer_ctx->dev,
+				  &mixer_ctx->dma_priv);
 }
 
 static int mixer_enable_vblank(struct exynos_drm_crtc *crtc)
diff --git a/drivers/gpu/drm/gma500/framebuffer.c b/drivers/gpu/drm/gma500/framebuffer.c
index 45c3db50ee1a..4924bc56b954 100644
--- a/drivers/gpu/drm/gma500/framebuffer.c
+++ b/drivers/gpu/drm/gma500/framebuffer.c
@@ -462,6 +462,7 @@ static int psbfb_probe(struct drm_fb_helper *helper,
 		container_of(helper, struct psb_fbdev, psb_fb_helper);
 	struct drm_device *dev = psb_fbdev->psb_fb_helper.dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
+	unsigned int fb_size;
 	int bytespp;
 
 	bytespp = sizes->surface_bpp / 8;
@@ -471,8 +472,11 @@ static int psbfb_probe(struct drm_fb_helper *helper,
 	/* If the mode will not fit in 32bit then switch to 16bit to get
 	   a console on full resolution. The X mode setting server will
 	   allocate its own 32bit GEM framebuffer */
-	if (ALIGN(sizes->fb_width * bytespp, 64) * sizes->fb_height >
-	                dev_priv->vram_stolen_size) {
+	fb_size = ALIGN(sizes->surface_width * bytespp, 64) *
+		  sizes->surface_height;
+	fb_size = ALIGN(fb_size, PAGE_SIZE);
+
+	if (fb_size > dev_priv->vram_stolen_size) {
                 sizes->surface_bpp = 16;
                 sizes->surface_depth = 16;
         }
diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index e1c313da6c00..59aa5e64acb0 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -207,14 +207,41 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 				SKL_FUSE_PG_DIST_STATUS(SKL_PG0) |
 				SKL_FUSE_PG_DIST_STATUS(SKL_PG1) |
 				SKL_FUSE_PG_DIST_STATUS(SKL_PG2);
-		vgpu_vreg_t(vgpu, LCPLL1_CTL) |=
-				LCPLL_PLL_ENABLE |
-				LCPLL_PLL_LOCK;
-		vgpu_vreg_t(vgpu, LCPLL2_CTL) |= LCPLL_PLL_ENABLE;
-
+		/*
+		 * Only 1 PIPE enabled in current vGPU display and PIPE_A is
+		 *  tied to TRANSCODER_A in HW, so it's safe to assume PIPE_A,
+		 *   TRANSCODER_A can be enabled. PORT_x depends on the input of
+		 *   setup_virtual_dp_monitor, we can bind DPLL0 to any PORT_x
+		 *   so we fixed to DPLL0 here.
+		 * Setup DPLL0: DP link clk 1620 MHz, non SSC, DP Mode
+		 */
+		vgpu_vreg_t(vgpu, DPLL_CTRL1) =
+			DPLL_CTRL1_OVERRIDE(DPLL_ID_SKL_DPLL0);
+		vgpu_vreg_t(vgpu, DPLL_CTRL1) |=
+			DPLL_CTRL1_LINK_RATE(DPLL_CTRL1_LINK_RATE_1620, DPLL_ID_SKL_DPLL0);
+		vgpu_vreg_t(vgpu, LCPLL1_CTL) =
+			LCPLL_PLL_ENABLE | LCPLL_PLL_LOCK;
+		vgpu_vreg_t(vgpu, DPLL_STATUS) = DPLL_LOCK(DPLL_ID_SKL_DPLL0);
+		/*
+		 * Golden M/N are calculated based on:
+		 *   24 bpp, 4 lanes, 154000 pixel clk (from virtual EDID),
+		 *   DP link clk 1620 MHz and non-constant_n.
+		 * TODO: calculate DP link symbol clk and stream clk m/n.
+		 */
+		vgpu_vreg_t(vgpu, PIPE_DATA_M1(TRANSCODER_A)) = 63 << TU_SIZE_SHIFT;
+		vgpu_vreg_t(vgpu, PIPE_DATA_M1(TRANSCODER_A)) |= 0x5b425e;
+		vgpu_vreg_t(vgpu, PIPE_DATA_N1(TRANSCODER_A)) = 0x800000;
+		vgpu_vreg_t(vgpu, PIPE_LINK_M1(TRANSCODER_A)) = 0x3cd6e;
+		vgpu_vreg_t(vgpu, PIPE_LINK_N1(TRANSCODER_A)) = 0x80000;
 	}
 
 	if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) {
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) &=
+			~DPLL_CTRL2_DDI_CLK_OFF(PORT_B);
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) |=
+			DPLL_CTRL2_DDI_CLK_SEL(DPLL_ID_SKL_DPLL0, PORT_B);
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) |=
+			DPLL_CTRL2_DDI_SEL_OVERRIDE(PORT_B);
 		vgpu_vreg_t(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDIB_DETECTED;
 		vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) &=
 			~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK |
@@ -235,6 +262,12 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 	}
 
 	if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) {
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) &=
+			~DPLL_CTRL2_DDI_CLK_OFF(PORT_C);
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) |=
+			DPLL_CTRL2_DDI_CLK_SEL(DPLL_ID_SKL_DPLL0, PORT_C);
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) |=
+			DPLL_CTRL2_DDI_SEL_OVERRIDE(PORT_C);
 		vgpu_vreg_t(vgpu, SDEISR) |= SDE_PORTC_HOTPLUG_CPT;
 		vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) &=
 			~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK |
@@ -255,6 +288,12 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 	}
 
 	if (intel_vgpu_has_monitor_on_port(vgpu, PORT_D)) {
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) &=
+			~DPLL_CTRL2_DDI_CLK_OFF(PORT_D);
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) |=
+			DPLL_CTRL2_DDI_CLK_SEL(DPLL_ID_SKL_DPLL0, PORT_D);
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) |=
+			DPLL_CTRL2_DDI_SEL_OVERRIDE(PORT_D);
 		vgpu_vreg_t(vgpu, SDEISR) |= SDE_PORTD_HOTPLUG_CPT;
 		vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) &=
 			~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK |
@@ -457,7 +496,8 @@ void intel_vgpu_emulate_hotplug(struct intel_vgpu *vgpu, bool connected)
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 
 	/* TODO: add more platforms support */
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
+	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv) ||
+		IS_COFFEELAKE(dev_priv)) {
 		if (connected) {
 			vgpu_vreg_t(vgpu, SFUSE_STRAP) |=
 				SFUSE_STRAP_DDID_DETECTED;
diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c
index 41c8ebc60c63..cd951b8ca513 100644
--- a/drivers/gpu/drm/i915/gvt/dmabuf.c
+++ b/drivers/gpu/drm/i915/gvt/dmabuf.c
@@ -96,12 +96,12 @@ static void dmabuf_gem_object_free(struct kref *kref)
 			dmabuf_obj = container_of(pos,
 					struct intel_vgpu_dmabuf_obj, list);
 			if (dmabuf_obj == obj) {
+				list_del(pos);
 				intel_gvt_hypervisor_put_vfio_device(vgpu);
 				idr_remove(&vgpu->object_idr,
 					   dmabuf_obj->dmabuf_id);
 				kfree(dmabuf_obj->info);
 				kfree(dmabuf_obj);
-				list_del(pos);
 				break;
 			}
 		}
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 53115bdae12b..03ffc5ebf8be 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -1956,7 +1956,11 @@ void _intel_vgpu_mm_release(struct kref *mm_ref)
 
 	if (mm->type == INTEL_GVT_MM_PPGTT) {
 		list_del(&mm->ppgtt_mm.list);
+
+		mutex_lock(&mm->vgpu->gvt->gtt.ppgtt_mm_lock);
 		list_del(&mm->ppgtt_mm.lru_list);
+		mutex_unlock(&mm->vgpu->gvt->gtt.ppgtt_mm_lock);
+
 		invalidate_ppgtt_mm(mm);
 	} else {
 		vfree(mm->ggtt_mm.virtual_ggtt);
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 25f78196b964..689b07bc91c4 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -3103,8 +3103,8 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 	MMIO_DFH(GEN9_WM_CHICKEN3, D_SKL_PLUS, F_MODE_MASK | F_CMD_ACCESS,
 		 NULL, NULL);
 
-	MMIO_D(GAMT_CHKN_BIT_REG, D_KBL);
-	MMIO_D(GEN9_CTX_PREEMPT_REG, D_KBL | D_SKL);
+	MMIO_D(GAMT_CHKN_BIT_REG, D_KBL | D_CFL);
+	MMIO_D(GEN9_CTX_PREEMPT_REG, D_SKL_PLUS);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 754c1debd7b0..bfea2239ccbd 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -369,6 +369,11 @@ static int set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload,
 		px_dma(&ppgtt->pml4) = mm->ppgtt_mm.shadow_pdps[0];
 	} else {
 		for (i = 0; i < GVT_RING_CTX_NR_PDPS; i++) {
+			/* skip now as current i915 ppgtt alloc won't allocate
+			   top level pdp for non 4-level table, won't impact
+			   shadow ppgtt. */
+			if (!ppgtt->pdp.page_directory[i])
+				break;
 			px_dma(ppgtt->pdp.page_directory[i]) =
 				mm->ppgtt_mm.shadow_pdps[i];
 		}
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index 44ce3c2b9ac1..e9e9547ffb1e 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -272,10 +272,17 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu)
 {
 	struct intel_gvt *gvt = vgpu->gvt;
 
-	mutex_lock(&vgpu->vgpu_lock);
-
 	WARN(vgpu->active, "vGPU is still active!\n");
 
+	/*
+	 * remove idr first so later clean can judge if need to stop
+	 * service if no active vgpu.
+	 */
+	mutex_lock(&gvt->lock);
+	idr_remove(&gvt->vgpu_idr, vgpu->id);
+	mutex_unlock(&gvt->lock);
+
+	mutex_lock(&vgpu->vgpu_lock);
 	intel_gvt_debugfs_remove_vgpu(vgpu);
 	intel_vgpu_clean_sched_policy(vgpu);
 	intel_vgpu_clean_submission(vgpu);
@@ -290,7 +297,6 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu)
 	mutex_unlock(&vgpu->vgpu_lock);
 
 	mutex_lock(&gvt->lock);
-	idr_remove(&gvt->vgpu_idr, vgpu->id);
 	if (idr_is_empty(&gvt->vgpu_idr))
 		intel_gvt_clean_irq(gvt);
 	intel_gvt_update_vgpu_types(gvt);
@@ -562,9 +568,9 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
 
 		intel_vgpu_reset_mmio(vgpu, dmlr);
 		populate_pvinfo_page(vgpu);
-		intel_vgpu_reset_display(vgpu);
 
 		if (dmlr) {
+			intel_vgpu_reset_display(vgpu);
 			intel_vgpu_reset_cfg_space(vgpu);
 			/* only reset the failsafe mode when dmlr reset */
 			vgpu->failsafe = false;
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index d485d49c473b..1b0410f0b38a 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -196,6 +196,7 @@ intel_pch_type(const struct drm_i915_private *dev_priv, unsigned short id)
 		WARN_ON(!IS_CANNONLAKE(dev_priv) && !IS_COFFEELAKE(dev_priv));
 		return PCH_CNP;
 	case INTEL_PCH_CMP_DEVICE_ID_TYPE:
+	case INTEL_PCH_CMP2_DEVICE_ID_TYPE:
 		DRM_DEBUG_KMS("Found Comet Lake PCH (CMP)\n");
 		WARN_ON(!IS_COFFEELAKE(dev_priv));
 		/* CometPoint is CNP Compatible */
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 066fd2a12851..8038b33097a9 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2627,6 +2627,7 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define INTEL_PCH_CNP_DEVICE_ID_TYPE		0xA300
 #define INTEL_PCH_CNP_LP_DEVICE_ID_TYPE		0x9D80
 #define INTEL_PCH_CMP_DEVICE_ID_TYPE		0x0280
+#define INTEL_PCH_CMP2_DEVICE_ID_TYPE		0x0680
 #define INTEL_PCH_ICP_DEVICE_ID_TYPE		0x3480
 #define INTEL_PCH_P2X_DEVICE_ID_TYPE		0x7100
 #define INTEL_PCH_P3X_DEVICE_ID_TYPE		0x7000
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index dd728b26b5aa..094d6c0a1a99 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -1539,8 +1539,7 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 	ext_data.fpriv = file->driver_priv;
 	if (client_is_banned(ext_data.fpriv)) {
 		DRM_DEBUG("client %s[%d] banned from creating ctx\n",
-			  current->comm,
-			  pid_nr(get_task_pid(current, PIDTYPE_PID)));
+			  current->comm, task_pid_nr(current));
 		return -EIO;
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index c83d2a195d15..a5e5425b018c 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -451,7 +451,8 @@ eb_validate_vma(struct i915_execbuffer *eb,
 	if (unlikely(entry->flags & eb->invalid_flags))
 		return -EINVAL;
 
-	if (unlikely(entry->alignment && !is_power_of_2(entry->alignment)))
+	if (unlikely(entry->alignment &&
+		     !is_power_of_2_u64(entry->alignment)))
 		return -EINVAL;
 
 	/*
@@ -999,11 +1000,13 @@ static inline struct i915_ggtt *cache_to_ggtt(struct reloc_cache *cache)
 
 static void reloc_gpu_flush(struct reloc_cache *cache)
 {
-	GEM_BUG_ON(cache->rq_size >= cache->rq->batch->obj->base.size / sizeof(u32));
+	struct drm_i915_gem_object *obj = cache->rq->batch->obj;
+
+	GEM_BUG_ON(cache->rq_size >= obj->base.size / sizeof(u32));
 	cache->rq_cmd[cache->rq_size] = MI_BATCH_BUFFER_END;
 
-	__i915_gem_object_flush_map(cache->rq->batch->obj, 0, cache->rq_size);
-	i915_gem_object_unpin_map(cache->rq->batch->obj);
+	__i915_gem_object_flush_map(obj, 0, sizeof(u32) * (cache->rq_size + 1));
+	i915_gem_object_unpin_map(obj);
 
 	i915_gem_chipset_flush(cache->rq->i915);
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 8f460cc4cc1f..04c084508435 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -988,6 +988,7 @@ gen8_ppgtt_insert_pte_entries(struct i915_hw_ppgtt *ppgtt,
 	pd = pdp->page_directory[idx->pdpe];
 	vaddr = kmap_atomic_px(pd->page_table[idx->pde]);
 	do {
+		GEM_BUG_ON(iter->sg->length < I915_GTT_PAGE_SIZE);
 		vaddr[idx->pte] = pte_encode | iter->dma;
 
 		iter->dma += I915_GTT_PAGE_SIZE;
@@ -1718,6 +1719,7 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 
 	vaddr = kmap_atomic_px(ppgtt->pd.page_table[act_pt]);
 	do {
+		GEM_BUG_ON(iter.sg->length < I915_GTT_PAGE_SIZE);
 		vaddr[act_pte] = pte_encode | GEN6_PTE_ADDR_ENCODE(iter.dma);
 
 		iter.dma += I915_GTT_PAGE_SIZE;
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index c91ae67a39c3..2e200e832ac8 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -441,7 +441,7 @@ struct get_pages_work {
 
 static struct sg_table *
 __i915_gem_userptr_alloc_pages(struct drm_i915_gem_object *obj,
-			       struct page **pvec, int num_pages)
+			       struct page **pvec, unsigned long num_pages)
 {
 	unsigned int max_segment = i915_sg_segment_size();
 	struct sg_table *st;
@@ -487,9 +487,10 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 {
 	struct get_pages_work *work = container_of(_work, typeof(*work), work);
 	struct drm_i915_gem_object *obj = work->obj;
-	const int npages = obj->base.size >> PAGE_SHIFT;
+	const unsigned long npages = obj->base.size >> PAGE_SHIFT;
+	unsigned long pinned;
 	struct page **pvec;
-	int pinned, ret;
+	int ret;
 
 	ret = -ENOMEM;
 	pinned = 0;
@@ -592,7 +593,7 @@ __i915_gem_userptr_get_pages_schedule(struct drm_i915_gem_object *obj)
 
 static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
 {
-	const int num_pages = obj->base.size >> PAGE_SHIFT;
+	const unsigned long num_pages = obj->base.size >> PAGE_SHIFT;
 	struct mm_struct *mm = obj->userptr.mm->mm;
 	struct page **pvec;
 	struct sg_table *pages;
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index b92cfd69134b..e5ca3c11c202 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -3749,6 +3749,7 @@ static void gen11_hpd_irq_setup(struct drm_i915_private *dev_priv)
 
 	val = I915_READ(GEN11_DE_HPD_IMR);
 	val &= ~hotplug_irqs;
+	val |= ~enabled_irqs & hotplug_irqs;
 	I915_WRITE(GEN11_DE_HPD_IMR, val);
 	POSTING_READ(GEN11_DE_HPD_IMR);
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index cf748b80e640..ed902a47fcc8 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4077,7 +4077,13 @@ enum {
 #define  GWUNIT_CLKGATE_DIS		(1 << 16)
 
 #define UNSLICE_UNIT_LEVEL_CLKGATE	_MMIO(0x9434)
-#define  VFUNIT_CLKGATE_DIS		(1 << 20)
+#define   VFUNIT_CLKGATE_DIS		REG_BIT(20)
+#define   HSUNIT_CLKGATE_DIS		REG_BIT(8)
+#define   VSUNIT_CLKGATE_DIS		REG_BIT(3)
+
+#define UNSLICE_UNIT_LEVEL_CLKGATE2	_MMIO(0x94e4)
+#define   VSUNIT_CLKGATE_DIS_TGL	REG_BIT(19)
+#define   PSDUNIT_CLKGATE_DIS		REG_BIT(5)
 
 #define INF_UNIT_LEVEL_CLKGATE		_MMIO(0x9560)
 #define   CGPSF_CLKGATE_DIS		(1 << 3)
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 81b48e273cbd..c87e0d584308 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -565,19 +565,31 @@ submit_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
 	return NOTIFY_DONE;
 }
 
+static void irq_semaphore_cb(struct irq_work *wrk)
+{
+	struct i915_request *rq =
+		container_of(wrk, typeof(*rq), semaphore_work);
+
+	i915_schedule_bump_priority(rq, I915_PRIORITY_NOSEMAPHORE);
+	i915_request_put(rq);
+}
+
 static int __i915_sw_fence_call
 semaphore_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
 {
-	struct i915_request *request =
-		container_of(fence, typeof(*request), semaphore);
+	struct i915_request *rq = container_of(fence, typeof(*rq), semaphore);
 
 	switch (state) {
 	case FENCE_COMPLETE:
-		i915_schedule_bump_priority(request, I915_PRIORITY_NOSEMAPHORE);
+		if (!(READ_ONCE(rq->sched.attr.priority) & I915_PRIORITY_NOSEMAPHORE)) {
+			i915_request_get(rq);
+			init_irq_work(&rq->semaphore_work, irq_semaphore_cb);
+			irq_work_queue(&rq->semaphore_work);
+		}
 		break;
 
 	case FENCE_FREE:
-		i915_request_put(request);
+		i915_request_put(rq);
 		break;
 	}
 
@@ -1194,7 +1206,6 @@ void i915_request_add(struct i915_request *request)
 	 * run at the earliest possible convenience.
 	 */
 	local_bh_disable();
-	i915_sw_fence_commit(&request->semaphore);
 	rcu_read_lock(); /* RCU serialisation for set-wedged protection */
 	if (engine->schedule) {
 		struct i915_sched_attr attr = request->gem_context->sched;
@@ -1226,6 +1237,7 @@ void i915_request_add(struct i915_request *request)
 		engine->schedule(request, &attr);
 	}
 	rcu_read_unlock();
+	i915_sw_fence_commit(&request->semaphore);
 	i915_sw_fence_commit(&request->submit);
 	local_bh_enable(); /* Kick the execlists tasklet if just scheduled */
 
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index a982664618c2..e544b497ed3f 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -26,6 +26,7 @@
 #define I915_REQUEST_H
 
 #include <linux/dma-fence.h>
+#include <linux/irq_work.h>
 #include <linux/lockdep.h>
 
 #include "i915_gem.h"
@@ -144,6 +145,7 @@ struct i915_request {
 	};
 	struct list_head execute_cb;
 	struct i915_sw_fence semaphore;
+	struct irq_work semaphore_work;
 
 	/*
 	 * A list of everyone we wait upon, and everyone who waits upon us.
diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h
index 2dbe8933b50a..cb41d0dee889 100644
--- a/drivers/gpu/drm/i915/i915_utils.h
+++ b/drivers/gpu/drm/i915/i915_utils.h
@@ -154,6 +154,11 @@ static inline u64 ptr_to_u64(const void *ptr)
 
 #include <linux/list.h>
 
+static inline bool is_power_of_2_u64(u64 n)
+{
+	return (n != 0 && ((n & (n - 1)) == 0));
+}
+
 static inline void __list_del_many(struct list_head *head,
 				   struct list_head *first)
 {
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 75105a2c59ea..9b2129031f79 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -16333,8 +16333,11 @@ get_encoder_power_domains(struct drm_i915_private *dev_priv)
 
 static void intel_early_display_was(struct drm_i915_private *dev_priv)
 {
-	/* Display WA #1185 WaDisableDARBFClkGating:cnl,glk */
-	if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv))
+	/*
+	 * Display WA #1185 WaDisableDARBFClkGating:cnl,glk,icl,ehl,tgl
+	 * Also known as Wa_14010480278.
+	 */
+	if (IS_GEN_RANGE(dev_priv, 10, 12) || IS_GEMINILAKE(dev_priv))
 		I915_WRITE(GEN9_CLKGATE_DIS_0, I915_READ(GEN9_CLKGATE_DIS_0) |
 			   DARBF_GATING_DIS);
 
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 560274d1c50b..abb25d6226bb 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -7235,11 +7235,8 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 		intel_connector->get_hw_state = intel_connector_get_hw_state;
 
 	/* init MST on ports that can support it */
-	if (HAS_DP_MST(dev_priv) && !intel_dp_is_edp(intel_dp) &&
-	    (port == PORT_B || port == PORT_C ||
-	     port == PORT_D || port == PORT_F))
-		intel_dp_mst_encoder_init(intel_dig_port,
-					  intel_connector->base.base.id);
+	intel_dp_mst_encoder_init(intel_dig_port,
+				  intel_connector->base.base.id);
 
 	if (!intel_edp_init_connector(intel_dp, intel_connector)) {
 		intel_dp_aux_fini(intel_dp);
diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c
index 8e6a7b8dffca..5b72ac7f1bd6 100644
--- a/drivers/gpu/drm/i915/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/intel_dp_mst.c
@@ -646,21 +646,31 @@ intel_dp_create_fake_mst_encoders(struct intel_digital_port *intel_dig_port)
 int
 intel_dp_mst_encoder_init(struct intel_digital_port *intel_dig_port, int conn_base_id)
 {
+	struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev);
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
-	struct drm_device *dev = intel_dig_port->base.base.dev;
+	enum port port = intel_dig_port->base.port;
 	int ret;
 
-	intel_dp->can_mst = true;
+	if (!HAS_DP_MST(i915) || intel_dp_is_edp(intel_dp))
+		return 0;
+
+	if (INTEL_GEN(i915) < 12 && port == PORT_A)
+		return 0;
+
+	if (INTEL_GEN(i915) < 11 && port == PORT_E)
+		return 0;
+
 	intel_dp->mst_mgr.cbs = &mst_cbs;
 
 	/* create encoders */
 	intel_dp_create_fake_mst_encoders(intel_dig_port);
-	ret = drm_dp_mst_topology_mgr_init(&intel_dp->mst_mgr, dev,
+	ret = drm_dp_mst_topology_mgr_init(&intel_dp->mst_mgr, &i915->drm,
 					   &intel_dp->aux, 16, 3, conn_base_id);
-	if (ret) {
-		intel_dp->can_mst = false;
+	if (ret)
 		return ret;
-	}
+
+	intel_dp->can_mst = true;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index 4044a739894f..f7c89b638914 100644
--- a/drivers/gpu/drm/i915/intel_fbc.c
+++ b/drivers/gpu/drm/i915/intel_fbc.c
@@ -501,8 +501,7 @@ static int intel_fbc_alloc_cfb(struct intel_crtc *crtc)
 	if (!ret)
 		goto err_llb;
 	else if (ret > 1) {
-		DRM_INFO("Reducing the compressed framebuffer size. This may lead to less power savings than a non-reduced-size. Try to increase stolen memory size if available in BIOS.\n");
-
+		DRM_INFO_ONCE("Reducing the compressed framebuffer size. This may lead to less power savings than a non-reduced-size. Try to increase stolen memory size if available in BIOS.\n");
 	}
 
 	fbc->threshold = ret;
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 11e5a86610bf..f37d22592f0e 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1579,6 +1579,15 @@ static u32 *gen9_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch)
 	/* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt,glk */
 	batch = gen8_emit_flush_coherentl3_wa(engine, batch);
 
+	/* WaClearSlmSpaceAtContextSwitch:skl,bxt,kbl,glk,cfl */
+	batch = gen8_emit_pipe_control(batch,
+				       PIPE_CONTROL_FLUSH_L3 |
+				       PIPE_CONTROL_GLOBAL_GTT_IVB |
+				       PIPE_CONTROL_CS_STALL |
+				       PIPE_CONTROL_QW_WRITE,
+				       i915_scratch_offset(engine->i915) +
+				       2 * CACHELINE_BYTES);
+
 	batch = emit_lri(batch, lri, ARRAY_SIZE(lri));
 
 	/* WaMediaPoolStateCmdInWABB:bxt,glk */
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 44be676fabd6..5854bcc91cd5 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -9045,6 +9045,17 @@ static void icl_init_clock_gating(struct drm_i915_private *dev_priv)
 	/* WaEnable32PlaneMode:icl */
 	I915_WRITE(GEN9_CSFE_CHICKEN1_RCS,
 		   _MASKED_BIT_ENABLE(GEN11_ENABLE_32_PLANE_MODE));
+
+	/*
+	 * Wa_1408615072:icl,ehl  (vsunit)
+	 * Wa_1407596294:icl,ehl  (hsunit)
+	 */
+	intel_uncore_rmw(&dev_priv->uncore, UNSLICE_UNIT_LEVEL_CLKGATE,
+			 0, VSUNIT_CLKGATE_DIS | HSUNIT_CLKGATE_DIS);
+
+	/* Wa_1407352427:icl,ehl */
+	intel_uncore_rmw(&dev_priv->uncore, UNSLICE_UNIT_LEVEL_CLKGATE2,
+			 0, PSDUNIT_CLKGATE_DIS);
 }
 
 static void cnp_init_clock_gating(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index 6150e35bf7b5..75af48d56614 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -3599,13 +3599,19 @@ static void icl_dbuf_disable(struct drm_i915_private *dev_priv)
 
 static void icl_mbus_init(struct drm_i915_private *dev_priv)
 {
-	u32 val;
+	u32 mask, val;
 
-	val = MBUS_ABOX_BT_CREDIT_POOL1(16) |
-	      MBUS_ABOX_BT_CREDIT_POOL2(16) |
-	      MBUS_ABOX_B_CREDIT(1) |
-	      MBUS_ABOX_BW_CREDIT(1);
+	mask = MBUS_ABOX_BT_CREDIT_POOL1_MASK |
+		MBUS_ABOX_BT_CREDIT_POOL2_MASK |
+		MBUS_ABOX_B_CREDIT_MASK |
+		MBUS_ABOX_BW_CREDIT_MASK;
 
+	val = I915_READ(MBUS_ABOX_CTL);
+	val &= ~mask;
+	val |= MBUS_ABOX_BT_CREDIT_POOL1(16) |
+		MBUS_ABOX_BT_CREDIT_POOL2(16) |
+		MBUS_ABOX_B_CREDIT(1) |
+		MBUS_ABOX_BW_CREDIT(1);
 	I915_WRITE(MBUS_ABOX_CTL, val);
 }
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
index 971148fbe6f5..54ddd86e45cf 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
@@ -493,7 +493,7 @@ static bool assert_mmap_offset(struct drm_i915_private *i915,
 
 	obj = i915_gem_object_create_internal(i915, size);
 	if (IS_ERR(obj))
-		return PTR_ERR(obj);
+		return false;
 
 	err = i915_gem_object_create_mmap_offset(obj);
 	i915_gem_object_put(obj);
diff --git a/drivers/gpu/drm/i915/selftests/i915_random.h b/drivers/gpu/drm/i915/selftests/i915_random.h
index 8e1ff9c105b6..22335cee2203 100644
--- a/drivers/gpu/drm/i915/selftests/i915_random.h
+++ b/drivers/gpu/drm/i915/selftests/i915_random.h
@@ -25,6 +25,7 @@
 #ifndef __I915_SELFTESTS_RANDOM_H__
 #define __I915_SELFTESTS_RANDOM_H__
 
+#include <linux/math64.h>
 #include <linux/random.h>
 
 #include "../i915_selftest.h"
diff --git a/drivers/gpu/drm/imx/dw_hdmi-imx.c b/drivers/gpu/drm/imx/dw_hdmi-imx.c
index 06393cd1067d..fb86fb6c67e7 100644
--- a/drivers/gpu/drm/imx/dw_hdmi-imx.c
+++ b/drivers/gpu/drm/imx/dw_hdmi-imx.c
@@ -210,9 +210,8 @@ static int dw_hdmi_imx_bind(struct device *dev, struct device *master,
 	if (!pdev->dev.of_node)
 		return -ENODEV;
 
-	hdmi = devm_kzalloc(&pdev->dev, sizeof(*hdmi), GFP_KERNEL);
-	if (!hdmi)
-		return -ENOMEM;
+	hdmi = dev_get_drvdata(dev);
+	memset(hdmi, 0, sizeof(*hdmi));
 
 	match = of_match_node(dw_hdmi_imx_dt_ids, pdev->dev.of_node);
 	plat_data = match->data;
@@ -237,8 +236,6 @@ static int dw_hdmi_imx_bind(struct device *dev, struct device *master,
 	drm_encoder_init(drm, encoder, &dw_hdmi_imx_encoder_funcs,
 			 DRM_MODE_ENCODER_TMDS, NULL);
 
-	platform_set_drvdata(pdev, hdmi);
-
 	hdmi->hdmi = dw_hdmi_bind(pdev, encoder, plat_data);
 
 	/*
@@ -268,6 +265,14 @@ static const struct component_ops dw_hdmi_imx_ops = {
 
 static int dw_hdmi_imx_probe(struct platform_device *pdev)
 {
+	struct imx_hdmi *hdmi;
+
+	hdmi = devm_kzalloc(&pdev->dev, sizeof(*hdmi), GFP_KERNEL);
+	if (!hdmi)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, hdmi);
+
 	return component_add(&pdev->dev, &dw_hdmi_imx_ops);
 }
 
diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c
index 3e8bece620df..97b78e384183 100644
--- a/drivers/gpu/drm/imx/imx-drm-core.c
+++ b/drivers/gpu/drm/imx/imx-drm-core.c
@@ -280,9 +280,10 @@ static void imx_drm_unbind(struct device *dev)
 
 	drm_kms_helper_poll_fini(drm);
 
+	component_unbind_all(drm->dev, drm);
+
 	drm_mode_config_cleanup(drm);
 
-	component_unbind_all(drm->dev, drm);
 	dev_set_drvdata(dev, NULL);
 
 	drm_dev_put(drm);
diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c
index 383733302280..c92a5149ae4e 100644
--- a/drivers/gpu/drm/imx/imx-ldb.c
+++ b/drivers/gpu/drm/imx/imx-ldb.c
@@ -303,18 +303,19 @@ static void imx_ldb_encoder_disable(struct drm_encoder *encoder)
 {
 	struct imx_ldb_channel *imx_ldb_ch = enc_to_imx_ldb_ch(encoder);
 	struct imx_ldb *ldb = imx_ldb_ch->ldb;
+	int dual = ldb->ldb_ctrl & LDB_SPLIT_MODE_EN;
 	int mux, ret;
 
 	drm_panel_disable(imx_ldb_ch->panel);
 
-	if (imx_ldb_ch == &ldb->channel[0])
+	if (imx_ldb_ch == &ldb->channel[0] || dual)
 		ldb->ldb_ctrl &= ~LDB_CH0_MODE_EN_MASK;
-	else if (imx_ldb_ch == &ldb->channel[1])
+	if (imx_ldb_ch == &ldb->channel[1] || dual)
 		ldb->ldb_ctrl &= ~LDB_CH1_MODE_EN_MASK;
 
 	regmap_write(ldb->regmap, IOMUXC_GPR2, ldb->ldb_ctrl);
 
-	if (ldb->ldb_ctrl & LDB_SPLIT_MODE_EN) {
+	if (dual) {
 		clk_disable_unprepare(ldb->clk[0]);
 		clk_disable_unprepare(ldb->clk[1]);
 	}
@@ -593,9 +594,8 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data)
 	int ret;
 	int i;
 
-	imx_ldb = devm_kzalloc(dev, sizeof(*imx_ldb), GFP_KERNEL);
-	if (!imx_ldb)
-		return -ENOMEM;
+	imx_ldb = dev_get_drvdata(dev);
+	memset(imx_ldb, 0, sizeof(*imx_ldb));
 
 	imx_ldb->regmap = syscon_regmap_lookup_by_phandle(np, "gpr");
 	if (IS_ERR(imx_ldb->regmap)) {
@@ -703,8 +703,6 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data)
 		}
 	}
 
-	dev_set_drvdata(dev, imx_ldb);
-
 	return 0;
 
 free_child:
@@ -736,6 +734,14 @@ static const struct component_ops imx_ldb_ops = {
 
 static int imx_ldb_probe(struct platform_device *pdev)
 {
+	struct imx_ldb *imx_ldb;
+
+	imx_ldb = devm_kzalloc(&pdev->dev, sizeof(*imx_ldb), GFP_KERNEL);
+	if (!imx_ldb)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, imx_ldb);
+
 	return component_add(&pdev->dev, &imx_ldb_ops);
 }
 
diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c
index e725af8a0025..527e2659d99c 100644
--- a/drivers/gpu/drm/imx/imx-tve.c
+++ b/drivers/gpu/drm/imx/imx-tve.c
@@ -490,6 +490,13 @@ static int imx_tve_register(struct drm_device *drm, struct imx_tve *tve)
 	return 0;
 }
 
+static void imx_tve_disable_regulator(void *data)
+{
+	struct imx_tve *tve = data;
+
+	regulator_disable(tve->dac_reg);
+}
+
 static bool imx_tve_readable_reg(struct device *dev, unsigned int reg)
 {
 	return (reg % 4 == 0) && (reg <= 0xdc);
@@ -542,9 +549,8 @@ static int imx_tve_bind(struct device *dev, struct device *master, void *data)
 	int irq;
 	int ret;
 
-	tve = devm_kzalloc(dev, sizeof(*tve), GFP_KERNEL);
-	if (!tve)
-		return -ENOMEM;
+	tve = dev_get_drvdata(dev);
+	memset(tve, 0, sizeof(*tve));
 
 	tve->dev = dev;
 	spin_lock_init(&tve->lock);
@@ -614,6 +620,9 @@ static int imx_tve_bind(struct device *dev, struct device *master, void *data)
 		ret = regulator_enable(tve->dac_reg);
 		if (ret)
 			return ret;
+		ret = devm_add_action_or_reset(dev, imx_tve_disable_regulator, tve);
+		if (ret)
+			return ret;
 	}
 
 	tve->clk = devm_clk_get(dev, "tve");
@@ -655,27 +664,23 @@ static int imx_tve_bind(struct device *dev, struct device *master, void *data)
 	if (ret)
 		return ret;
 
-	dev_set_drvdata(dev, tve);
-
 	return 0;
 }
 
-static void imx_tve_unbind(struct device *dev, struct device *master,
-	void *data)
-{
-	struct imx_tve *tve = dev_get_drvdata(dev);
-
-	if (!IS_ERR(tve->dac_reg))
-		regulator_disable(tve->dac_reg);
-}
-
 static const struct component_ops imx_tve_ops = {
 	.bind	= imx_tve_bind,
-	.unbind	= imx_tve_unbind,
 };
 
 static int imx_tve_probe(struct platform_device *pdev)
 {
+	struct imx_tve *tve;
+
+	tve = devm_kzalloc(&pdev->dev, sizeof(*tve), GFP_KERNEL);
+	if (!tve)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, tve);
+
 	return component_add(&pdev->dev, &imx_tve_ops);
 }
 
diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c
index c436a28d50e4..f3df21880140 100644
--- a/drivers/gpu/drm/imx/ipuv3-crtc.c
+++ b/drivers/gpu/drm/imx/ipuv3-crtc.c
@@ -434,21 +434,13 @@ static int ipu_drm_bind(struct device *dev, struct device *master, void *data)
 	struct ipu_client_platformdata *pdata = dev->platform_data;
 	struct drm_device *drm = data;
 	struct ipu_crtc *ipu_crtc;
-	int ret;
 
-	ipu_crtc = devm_kzalloc(dev, sizeof(*ipu_crtc), GFP_KERNEL);
-	if (!ipu_crtc)
-		return -ENOMEM;
+	ipu_crtc = dev_get_drvdata(dev);
+	memset(ipu_crtc, 0, sizeof(*ipu_crtc));
 
 	ipu_crtc->dev = dev;
 
-	ret = ipu_crtc_init(ipu_crtc, pdata, drm);
-	if (ret)
-		return ret;
-
-	dev_set_drvdata(dev, ipu_crtc);
-
-	return 0;
+	return ipu_crtc_init(ipu_crtc, pdata, drm);
 }
 
 static void ipu_drm_unbind(struct device *dev, struct device *master,
@@ -470,6 +462,7 @@ static const struct component_ops ipu_crtc_ops = {
 static int ipu_drm_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
+	struct ipu_crtc *ipu_crtc;
 	int ret;
 
 	if (!dev->platform_data)
@@ -479,6 +472,12 @@ static int ipu_drm_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	ipu_crtc = devm_kzalloc(dev, sizeof(*ipu_crtc), GFP_KERNEL);
+	if (!ipu_crtc)
+		return -ENOMEM;
+
+	dev_set_drvdata(dev, ipu_crtc);
+
 	return component_add(dev, &ipu_crtc_ops);
 }
 
diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c
index 1a76de1e8e7b..487ba3b176d3 100644
--- a/drivers/gpu/drm/imx/parallel-display.c
+++ b/drivers/gpu/drm/imx/parallel-display.c
@@ -205,9 +205,8 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data)
 	u32 bus_format = 0;
 	const char *fmt;
 
-	imxpd = devm_kzalloc(dev, sizeof(*imxpd), GFP_KERNEL);
-	if (!imxpd)
-		return -ENOMEM;
+	imxpd = dev_get_drvdata(dev);
+	memset(imxpd, 0, sizeof(*imxpd));
 
 	edidp = of_get_property(np, "edid", &imxpd->edid_len);
 	if (edidp)
@@ -237,8 +236,6 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data)
 	if (ret)
 		return ret;
 
-	dev_set_drvdata(dev, imxpd);
-
 	return 0;
 }
 
@@ -260,6 +257,14 @@ static const struct component_ops imx_pd_ops = {
 
 static int imx_pd_probe(struct platform_device *pdev)
 {
+	struct imx_parallel_display *imxpd;
+
+	imxpd = devm_kzalloc(&pdev->dev, sizeof(*imxpd), GFP_KERNEL);
+	if (!imxpd)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, imxpd);
+
 	return component_add(&pdev->dev, &imx_pd_ops);
 }
 
diff --git a/drivers/gpu/drm/lima/lima_device.c b/drivers/gpu/drm/lima/lima_device.c
index 570d0e93f9a9..bb2eaa4f370e 100644
--- a/drivers/gpu/drm/lima/lima_device.c
+++ b/drivers/gpu/drm/lima/lima_device.c
@@ -80,7 +80,6 @@ const char *lima_ip_name(struct lima_ip *ip)
 static int lima_clk_init(struct lima_device *dev)
 {
 	int err;
-	unsigned long bus_rate, gpu_rate;
 
 	dev->clk_bus = devm_clk_get(dev->dev, "bus");
 	if (IS_ERR(dev->clk_bus)) {
@@ -94,12 +93,6 @@ static int lima_clk_init(struct lima_device *dev)
 		return PTR_ERR(dev->clk_gpu);
 	}
 
-	bus_rate = clk_get_rate(dev->clk_bus);
-	dev_info(dev->dev, "bus rate = %lu\n", bus_rate);
-
-	gpu_rate = clk_get_rate(dev->clk_gpu);
-	dev_info(dev->dev, "mod rate = %lu", gpu_rate);
-
 	err = clk_prepare_enable(dev->clk_bus);
 	if (err)
 		return err;
@@ -145,7 +138,8 @@ static int lima_regulator_init(struct lima_device *dev)
 		dev->regulator = NULL;
 		if (ret == -ENODEV)
 			return 0;
-		dev_err(dev->dev, "failed to get regulator: %d\n", ret);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev->dev, "failed to get regulator: %d\n", ret);
 		return ret;
 	}
 
@@ -297,10 +291,8 @@ int lima_device_init(struct lima_device *ldev)
 	}
 
 	err = lima_regulator_init(ldev);
-	if (err) {
-		dev_err(ldev->dev, "regulator init fail %d\n", err);
+	if (err)
 		goto err_out0;
-	}
 
 	ldev->empty_vm = lima_vm_create(ldev);
 	if (!ldev->empty_vm) {
@@ -343,6 +335,9 @@ int lima_device_init(struct lima_device *ldev)
 	if (err)
 		goto err_out5;
 
+	dev_info(ldev->dev, "bus rate = %lu\n", clk_get_rate(ldev->clk_bus));
+	dev_info(ldev->dev, "mod rate = %lu", clk_get_rate(ldev->clk_gpu));
+
 	return 0;
 
 err_out5:
diff --git a/drivers/gpu/drm/lima/lima_drv.c b/drivers/gpu/drm/lima/lima_drv.c
index f9a281a62083..e2a922e2c8fa 100644
--- a/drivers/gpu/drm/lima/lima_drv.c
+++ b/drivers/gpu/drm/lima/lima_drv.c
@@ -307,10 +307,8 @@ static int lima_pdev_probe(struct platform_device *pdev)
 	ldev->ddev = ddev;
 
 	err = lima_device_init(ldev);
-	if (err) {
-		dev_err(&pdev->dev, "Fatal error during GPU init\n");
+	if (err)
 		goto err_out1;
-	}
 
 	/*
 	 * Register the DRM device with the core and the connectors with
diff --git a/drivers/gpu/drm/lima/lima_vm.h b/drivers/gpu/drm/lima/lima_vm.h
index caee2f8a29b4..e0bdedcf14dd 100644
--- a/drivers/gpu/drm/lima/lima_vm.h
+++ b/drivers/gpu/drm/lima/lima_vm.h
@@ -15,9 +15,9 @@
 #define LIMA_VM_NUM_PT_PER_BT (1 << LIMA_VM_NUM_PT_PER_BT_SHIFT)
 #define LIMA_VM_NUM_BT (LIMA_PAGE_ENT_NUM >> LIMA_VM_NUM_PT_PER_BT_SHIFT)
 
-#define LIMA_VA_RESERVE_START  0xFFF00000
+#define LIMA_VA_RESERVE_START  0x0FFF00000ULL
 #define LIMA_VA_RESERVE_DLBU   LIMA_VA_RESERVE_START
-#define LIMA_VA_RESERVE_END    0x100000000
+#define LIMA_VA_RESERVE_END    0x100000000ULL
 
 struct lima_device;
 
diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c
index bacd989cc9aa..9fd366d711af 100644
--- a/drivers/gpu/drm/mediatek/mtk_dpi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dpi.c
@@ -12,7 +12,9 @@
 #include <linux/platform_device.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/of_gpio.h>
 #include <linux/of_graph.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/interrupt.h>
 #include <linux/types.h>
 #include <linux/clk.h>
@@ -71,6 +73,9 @@ struct mtk_dpi {
 	enum mtk_dpi_out_yc_map yc_map;
 	enum mtk_dpi_out_bit_num bit_num;
 	enum mtk_dpi_out_channel_swap channel_swap;
+	struct pinctrl *pinctrl;
+	struct pinctrl_state *pins_gpio;
+	struct pinctrl_state *pins_dpi;
 	int refcount;
 };
 
@@ -376,6 +381,9 @@ static void mtk_dpi_power_off(struct mtk_dpi *dpi)
 	if (--dpi->refcount != 0)
 		return;
 
+	if (dpi->pinctrl && dpi->pins_gpio)
+		pinctrl_select_state(dpi->pinctrl, dpi->pins_gpio);
+
 	mtk_dpi_disable(dpi);
 	clk_disable_unprepare(dpi->pixel_clk);
 	clk_disable_unprepare(dpi->engine_clk);
@@ -400,6 +408,9 @@ static int mtk_dpi_power_on(struct mtk_dpi *dpi)
 		goto err_pixel;
 	}
 
+	if (dpi->pinctrl && dpi->pins_dpi)
+		pinctrl_select_state(dpi->pinctrl, dpi->pins_dpi);
+
 	mtk_dpi_enable(dpi);
 	return 0;
 
@@ -687,6 +698,26 @@ static int mtk_dpi_probe(struct platform_device *pdev)
 	dpi->dev = dev;
 	dpi->conf = (struct mtk_dpi_conf *)of_device_get_match_data(dev);
 
+	dpi->pinctrl = devm_pinctrl_get(&pdev->dev);
+	if (IS_ERR(dpi->pinctrl)) {
+		dpi->pinctrl = NULL;
+		dev_dbg(&pdev->dev, "Cannot find pinctrl!\n");
+	}
+	if (dpi->pinctrl) {
+		dpi->pins_gpio = pinctrl_lookup_state(dpi->pinctrl, "sleep");
+		if (IS_ERR(dpi->pins_gpio)) {
+			dpi->pins_gpio = NULL;
+			dev_dbg(&pdev->dev, "Cannot find pinctrl idle!\n");
+		}
+		if (dpi->pins_gpio)
+			pinctrl_select_state(dpi->pinctrl, dpi->pins_gpio);
+
+		dpi->pins_dpi = pinctrl_lookup_state(dpi->pinctrl, "default");
+		if (IS_ERR(dpi->pins_dpi)) {
+			dpi->pins_dpi = NULL;
+			dev_dbg(&pdev->dev, "Cannot find pinctrl active!\n");
+		}
+	}
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	dpi->regs = devm_ioremap_resource(dev, mem);
 	if (IS_ERR(dpi->regs)) {
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
index a9007210dda1..3e288935695e 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
@@ -296,6 +296,7 @@ err_pm_runtime_put:
 static void mtk_crtc_ddp_hw_fini(struct mtk_drm_crtc *mtk_crtc)
 {
 	struct drm_device *drm = mtk_crtc->base.dev;
+	struct drm_crtc *crtc = &mtk_crtc->base;
 	int i;
 
 	DRM_DEBUG_DRIVER("%s\n", __func__);
@@ -317,6 +318,13 @@ static void mtk_crtc_ddp_hw_fini(struct mtk_drm_crtc *mtk_crtc)
 	mtk_disp_mutex_unprepare(mtk_crtc->mutex);
 
 	pm_runtime_put(drm->dev);
+
+	if (crtc->state->event && !crtc->state->active) {
+		spin_lock_irq(&crtc->dev->event_lock);
+		drm_crtc_send_vblank_event(crtc, crtc->state->event);
+		crtc->state->event = NULL;
+		spin_unlock_irq(&crtc->dev->event_lock);
+	}
 }
 
 static void mtk_crtc_ddp_config(struct drm_crtc *crtc)
@@ -486,10 +494,18 @@ static const struct drm_crtc_helper_funcs mtk_crtc_helper_funcs = {
 
 static int mtk_drm_crtc_init(struct drm_device *drm,
 			     struct mtk_drm_crtc *mtk_crtc,
-			     struct drm_plane *primary,
-			     struct drm_plane *cursor, unsigned int pipe)
+			     unsigned int pipe)
 {
-	int ret;
+	struct drm_plane *primary = NULL;
+	struct drm_plane *cursor = NULL;
+	int i, ret;
+
+	for (i = 0; i < mtk_crtc->layer_nr; i++) {
+		if (mtk_crtc->planes[i].type == DRM_PLANE_TYPE_PRIMARY)
+			primary = &mtk_crtc->planes[i];
+		else if (mtk_crtc->planes[i].type == DRM_PLANE_TYPE_CURSOR)
+			cursor = &mtk_crtc->planes[i];
+	}
 
 	ret = drm_crtc_init_with_planes(drm, &mtk_crtc->base, primary, cursor,
 					&mtk_crtc_funcs, NULL);
@@ -527,6 +543,7 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 	int pipe = priv->num_pipes;
 	int ret;
 	int i;
+	uint gamma_lut_size = 0;
 
 	if (!path)
 		return 0;
@@ -577,6 +594,9 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 		}
 
 		mtk_crtc->ddp_comp[i] = comp;
+
+		if (comp->funcs && comp->funcs->gamma_set)
+			gamma_lut_size = MTK_LUT_SIZE;
 	}
 
 	mtk_crtc->layer_nr = mtk_ddp_comp_layer_nr(mtk_crtc->ddp_comp[0]);
@@ -594,13 +614,13 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 			return ret;
 	}
 
-	ret = mtk_drm_crtc_init(drm_dev, mtk_crtc, &mtk_crtc->planes[0],
-				mtk_crtc->layer_nr > 1 ? &mtk_crtc->planes[1] :
-				NULL, pipe);
+	ret = mtk_drm_crtc_init(drm_dev, mtk_crtc, pipe);
 	if (ret < 0)
 		return ret;
-	drm_mode_crtc_set_gamma_size(&mtk_crtc->base, MTK_LUT_SIZE);
-	drm_crtc_enable_color_mgmt(&mtk_crtc->base, 0, false, MTK_LUT_SIZE);
+
+	if (gamma_lut_size)
+		drm_mode_crtc_set_gamma_size(&mtk_crtc->base, gamma_lut_size);
+	drm_crtc_enable_color_mgmt(&mtk_crtc->base, 0, false, gamma_lut_size);
 	priv->num_pipes++;
 
 	return 0;
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.c b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
index f2ef83aed6f9..876921429991 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_plane.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
@@ -100,6 +100,16 @@ static int mtk_plane_atomic_check(struct drm_plane *plane,
 						   true, true);
 }
 
+static void mtk_plane_atomic_disable(struct drm_plane *plane,
+				     struct drm_plane_state *old_state)
+{
+	struct mtk_plane_state *state = to_mtk_plane_state(plane->state);
+
+	state->pending.enable = false;
+	wmb(); /* Make sure the above parameter is set before update */
+	state->pending.dirty = true;
+}
+
 static void mtk_plane_atomic_update(struct drm_plane *plane,
 				    struct drm_plane_state *old_state)
 {
@@ -114,6 +124,11 @@ static void mtk_plane_atomic_update(struct drm_plane *plane,
 	if (!crtc || WARN_ON(!fb))
 		return;
 
+	if (!plane->state->visible) {
+		mtk_plane_atomic_disable(plane, old_state);
+		return;
+	}
+
 	gem = fb->obj[0];
 	mtk_gem = to_mtk_gem_obj(gem);
 	addr = mtk_gem->dma_addr;
@@ -135,16 +150,6 @@ static void mtk_plane_atomic_update(struct drm_plane *plane,
 	state->pending.dirty = true;
 }
 
-static void mtk_plane_atomic_disable(struct drm_plane *plane,
-				     struct drm_plane_state *old_state)
-{
-	struct mtk_plane_state *state = to_mtk_plane_state(plane->state);
-
-	state->pending.enable = false;
-	wmb(); /* Make sure the above parameter is set before update */
-	state->pending.dirty = true;
-}
-
 static const struct drm_plane_helper_funcs mtk_plane_helper_funcs = {
 	.atomic_check = mtk_plane_atomic_check,
 	.atomic_update = mtk_plane_atomic_update,
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index a3c778df23a8..1471676b8b84 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -686,11 +686,18 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 		gpu->funcs->flush(gpu, gpu->rb[0]);
 		if (!a5xx_idle(gpu, gpu->rb[0]))
 			return -EINVAL;
-	} else {
-		/* Print a warning so if we die, we know why */
+	} else if (ret == -ENODEV) {
+		/*
+		 * This device does not use zap shader (but print a warning
+		 * just in case someone got their dt wrong.. hopefully they
+		 * have a debug UART to realize the error of their ways...
+		 * if you mess this up you are about to crash horribly)
+		 */
 		dev_warn_once(gpu->dev->dev,
 			"Zap shader not enabled - using SECVID_TRUST_CNTL instead\n");
 		gpu_write(gpu, REG_A5XX_RBBM_SECVID_TRUST_CNTL, 0x0);
+	} else {
+		return ret;
 	}
 
 	/* Last step - yield the ringbuffer */
@@ -1312,6 +1319,10 @@ static unsigned long a5xx_gpu_busy(struct msm_gpu *gpu)
 {
 	u64 busy_cycles, busy_time;
 
+	/* Only read the gpu busy if the hardware is already active */
+	if (pm_runtime_get_if_in_use(&gpu->pdev->dev) == 0)
+		return 0;
+
 	busy_cycles = gpu_read64(gpu, REG_A5XX_RBBM_PERFCTR_RBBM_0_LO,
 			REG_A5XX_RBBM_PERFCTR_RBBM_0_HI);
 
@@ -1320,6 +1331,8 @@ static unsigned long a5xx_gpu_busy(struct msm_gpu *gpu)
 
 	gpu->devfreq.busy_cycles = busy_cycles;
 
+	pm_runtime_put(&gpu->pdev->dev);
+
 	if (WARN_ON(busy_time > ~0LU))
 		return ~0LU;
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index 6910d0468e3c..862ec6a96406 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -107,6 +107,13 @@ static void __a6xx_gmu_set_freq(struct a6xx_gmu *gmu, int index)
 	struct msm_gpu *gpu = &adreno_gpu->base;
 	int ret;
 
+	/*
+	 * This can get called from devfreq while the hardware is idle. Don't
+	 * bring up the power if it isn't already active
+	 */
+	if (pm_runtime_get_if_in_use(gmu->dev) == 0)
+		return;
+
 	gmu_write(gmu, REG_A6XX_GMU_DCVS_ACK_OPTION, 0);
 
 	gmu_write(gmu, REG_A6XX_GMU_DCVS_PERF_SETTING,
@@ -133,6 +140,7 @@ static void __a6xx_gmu_set_freq(struct a6xx_gmu *gmu, int index)
 	 * for now leave it at max so that the performance is nominal.
 	 */
 	icc_set_bw(gpu->icc_path, 0, MBps_to_icc(7216));
+	pm_runtime_put(gmu->dev);
 }
 
 void a6xx_gmu_set_freq(struct msm_gpu *gpu, unsigned long freq)
@@ -705,10 +713,19 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 	/* Turn on the resources */
 	pm_runtime_get_sync(gmu->dev);
 
+	/*
+	 * "enable" the GX power domain which won't actually do anything but it
+	 * will make sure that the refcounting is correct in case we need to
+	 * bring down the GX after a GMU failure
+	 */
+	if (!IS_ERR_OR_NULL(gmu->gxpd))
+		pm_runtime_get_sync(gmu->gxpd);
+
 	/* Use a known rate to bring up the GMU */
 	clk_set_rate(gmu->core_clk, 200000000);
 	ret = clk_bulk_prepare_enable(gmu->nr_clocks, gmu->clocks);
 	if (ret) {
+		pm_runtime_put(gmu->gxpd);
 		pm_runtime_put(gmu->dev);
 		return ret;
 	}
@@ -744,19 +761,12 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 	/* Set the GPU to the highest power frequency */
 	__a6xx_gmu_set_freq(gmu, gmu->nr_gpu_freqs - 1);
 
-	/*
-	 * "enable" the GX power domain which won't actually do anything but it
-	 * will make sure that the refcounting is correct in case we need to
-	 * bring down the GX after a GMU failure
-	 */
-	if (!IS_ERR_OR_NULL(gmu->gxpd))
-		pm_runtime_get(gmu->gxpd);
-
 out:
 	/* On failure, shut down the GMU to leave it in a good state */
 	if (ret) {
 		disable_irq(gmu->gmu_irq);
 		a6xx_rpmh_stop(gmu);
+		pm_runtime_put(gmu->gxpd);
 		pm_runtime_put(gmu->dev);
 	}
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index e74dce474250..b17b09f7abbc 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -522,12 +522,19 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 		a6xx_flush(gpu, gpu->rb[0]);
 		if (!a6xx_idle(gpu, gpu->rb[0]))
 			return -EINVAL;
-	} else {
-		/* Print a warning so if we die, we know why */
+	} else if (ret == -ENODEV) {
+		/*
+		 * This device does not use zap shader (but print a warning
+		 * just in case someone got their dt wrong.. hopefully they
+		 * have a debug UART to realize the error of their ways...
+		 * if you mess this up you are about to crash horribly)
+		 */
 		dev_warn_once(gpu->dev->dev,
 			"Zap shader not enabled - using SECVID_TRUST_CNTL instead\n");
 		gpu_write(gpu, REG_A6XX_RBBM_SECVID_TRUST_CNTL, 0x0);
 		ret = 0;
+	} else {
+		return ret;
 	}
 
 out:
@@ -781,6 +788,11 @@ static unsigned long a6xx_gpu_busy(struct msm_gpu *gpu)
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
 	u64 busy_cycles, busy_time;
 
+
+	/* Only read the gpu busy if the hardware is already active */
+	if (pm_runtime_get_if_in_use(a6xx_gpu->gmu.dev) == 0)
+		return 0;
+
 	busy_cycles = gmu_read64(&a6xx_gpu->gmu,
 			REG_A6XX_GMU_CX_GMU_POWER_COUNTER_XOCLK_0_L,
 			REG_A6XX_GMU_CX_GMU_POWER_COUNTER_XOCLK_0_H);
@@ -790,6 +802,8 @@ static unsigned long a6xx_gpu_busy(struct msm_gpu *gpu)
 
 	gpu->devfreq.busy_cycles = busy_cycles;
 
+	pm_runtime_put(a6xx_gpu->gmu.dev);
+
 	if (WARN_ON(busy_time > ~0LU))
 		return ~0LU;
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
index ccc298711bae..b97a541079ec 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -397,7 +397,7 @@ static void dpu_crtc_frame_event_cb(void *data, u32 event)
 	spin_unlock_irqrestore(&dpu_crtc->spin_lock, flags);
 
 	if (!fevent) {
-		DRM_ERROR("crtc%d event %d overflow\n", crtc->base.id, event);
+		DRM_ERROR_RATELIMITED("crtc%d event %d overflow\n", crtc->base.id, event);
 		return;
 	}
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index c62f7abcf509..8fcfee5e6e85 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -2221,7 +2221,6 @@ int dpu_encoder_setup(struct drm_device *dev, struct drm_encoder *enc,
 
 	dpu_enc = to_dpu_encoder_virt(enc);
 
-	mutex_init(&dpu_enc->enc_lock);
 	ret = dpu_encoder_setup_display(dpu_enc, dpu_kms, disp_info);
 	if (ret)
 		goto fail;
@@ -2236,7 +2235,6 @@ int dpu_encoder_setup(struct drm_device *dev, struct drm_encoder *enc,
 				0);
 
 
-	mutex_init(&dpu_enc->rc_lock);
 	INIT_DELAYED_WORK(&dpu_enc->delayed_off_work,
 			dpu_encoder_off_work);
 	dpu_enc->idle_timeout = IDLE_TIMEOUT;
@@ -2268,7 +2266,7 @@ struct drm_encoder *dpu_encoder_init(struct drm_device *dev,
 
 	dpu_enc = devm_kzalloc(dev->dev, sizeof(*dpu_enc), GFP_KERNEL);
 	if (!dpu_enc)
-		return ERR_PTR(ENOMEM);
+		return ERR_PTR(-ENOMEM);
 
 	rc = drm_encoder_init(dev, &dpu_enc->base, &dpu_encoder_funcs,
 			drm_enc_mode, NULL);
@@ -2281,6 +2279,8 @@ struct drm_encoder *dpu_encoder_init(struct drm_device *dev,
 
 	spin_lock_init(&dpu_enc->enc_spinlock);
 	dpu_enc->enabled = false;
+	mutex_init(&dpu_enc->enc_lock);
+	mutex_init(&dpu_enc->rc_lock);
 
 	return &dpu_enc->base;
 }
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
index 0440696b5bad..8cc18e3540fc 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
@@ -255,13 +255,13 @@ static const struct dpu_format dpu_format_map[] = {
 
 	INTERLEAVED_RGB_FMT(RGB565,
 		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
-		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3,
 		false, 2, 0,
 		DPU_FETCH_LINEAR, 1),
 
 	INTERLEAVED_RGB_FMT(BGR565,
 		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
-		C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
 		false, 2, 0,
 		DPU_FETCH_LINEAR, 1),
 
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_dsi_encoder.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_dsi_encoder.c
index 772f0753ed38..aaf2f26f8505 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_dsi_encoder.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_dsi_encoder.c
@@ -121,7 +121,7 @@ static void mdp4_dsi_encoder_enable(struct drm_encoder *encoder)
 	if (mdp4_dsi_encoder->enabled)
 		return;
 
-	 mdp4_crtc_set_config(encoder->crtc,
+	mdp4_crtc_set_config(encoder->crtc,
 			MDP4_DMA_CONFIG_PACK_ALIGN_MSB |
 			MDP4_DMA_CONFIG_DEFLKR_EN |
 			MDP4_DMA_CONFIG_DITHER_EN |
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
index fe7cdb3fe887..602b19d92205 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
@@ -1100,8 +1100,8 @@ static void mdp5_crtc_wait_for_pp_done(struct drm_crtc *crtc)
 	ret = wait_for_completion_timeout(&mdp5_crtc->pp_completion,
 						msecs_to_jiffies(50));
 	if (ret == 0)
-		dev_warn(dev->dev, "pp done time out, lm=%d\n",
-			 mdp5_cstate->pipeline.mixer->lm);
+		dev_warn_ratelimited(dev->dev, "pp done time out, lm=%d\n",
+				     mdp5_cstate->pipeline.mixer->lm);
 }
 
 static void mdp5_crtc_wait_for_flush_done(struct drm_crtc *crtc)
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
index 901009e1f219..6dcfa97d3d54 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
@@ -1010,7 +1010,8 @@ static int mdp5_init(struct platform_device *pdev, struct drm_device *dev)
 
 	return 0;
 fail:
-	mdp5_destroy(pdev);
+	if (mdp5_kms)
+		mdp5_destroy(pdev);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c
index ec6cb0f7f206..969c4b64a110 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_manager.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c
@@ -320,7 +320,7 @@ static int dsi_mgr_connector_get_modes(struct drm_connector *connector)
 	return num;
 }
 
-static int dsi_mgr_connector_mode_valid(struct drm_connector *connector,
+static enum drm_mode_status dsi_mgr_connector_mode_valid(struct drm_connector *connector,
 				struct drm_display_mode *mode)
 {
 	int id = dsi_mgr_connector_get_id(connector);
@@ -463,6 +463,7 @@ static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge)
 	struct msm_dsi *msm_dsi1 = dsi_mgr_get_dsi(DSI_1);
 	struct mipi_dsi_host *host = msm_dsi->host;
 	struct drm_panel *panel = msm_dsi->panel;
+	struct msm_dsi_pll *src_pll;
 	bool is_dual_dsi = IS_DUAL_DSI();
 	int ret;
 
@@ -503,6 +504,10 @@ static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge)
 								id, ret);
 	}
 
+	/* Save PLL status if it is a clock source */
+	src_pll = msm_dsi_phy_get_pll(msm_dsi->phy);
+	msm_dsi_pll_save_state(src_pll);
+
 	ret = msm_dsi_host_power_off(host);
 	if (ret)
 		pr_err("%s: host %d power off failed,%d\n", __func__, id, ret);
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
index bc6f64b202f3..1b7c1bcb3140 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
@@ -718,10 +718,6 @@ void msm_dsi_phy_disable(struct msm_dsi_phy *phy)
 	if (!phy || !phy->cfg->ops.disable)
 		return;
 
-	/* Save PLL status if it is a clock source */
-	if (phy->usecase != MSM_DSI_PHY_SLAVE)
-		msm_dsi_pll_save_state(phy->pll);
-
 	phy->cfg->ops.disable(phy);
 
 	dsi_phy_regulator_disable(phy);
diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
index aabab6311043..dd63ef7f9dd2 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
@@ -406,6 +406,12 @@ static int dsi_pll_10nm_vco_prepare(struct clk_hw *hw)
 	if (pll_10nm->slave)
 		dsi_pll_enable_pll_bias(pll_10nm->slave);
 
+	rc = dsi_pll_10nm_vco_set_rate(hw,pll_10nm->vco_current_rate, 0);
+	if (rc) {
+		pr_err("vco_set_rate failed, rc=%d\n", rc);
+		return rc;
+	}
+
 	/* Start PLL */
 	pll_write(pll_10nm->phy_cmn_mmio + REG_DSI_10nm_PHY_CMN_PLL_CNTRL,
 		  0x01);
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index a56eef3cfee7..49048eaffb05 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -463,6 +463,14 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 	if (ret)
 		goto err_msm_uninit;
 
+	if (!dev->dma_parms) {
+		dev->dma_parms = devm_kzalloc(dev, sizeof(*dev->dma_parms),
+					      GFP_KERNEL);
+		if (!dev->dma_parms)
+			return -ENOMEM;
+	}
+	dma_set_max_seg_size(dev, DMA_BIT_MASK(32));
+
 	msm_gem_shrinker_init(ddev);
 
 	switch (get_mdp_ver(pdev)) {
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 49a019939ccd..bba6291b58a2 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -937,10 +937,8 @@ int msm_gem_new_handle(struct drm_device *dev, struct drm_file *file,
 static int msm_gem_new_impl(struct drm_device *dev,
 		uint32_t size, uint32_t flags,
 		struct reservation_object *resv,
-		struct drm_gem_object **obj,
-		bool struct_mutex_locked)
+		struct drm_gem_object **obj)
 {
-	struct msm_drm_private *priv = dev->dev_private;
 	struct msm_gem_object *msm_obj;
 
 	switch (flags & MSM_BO_CACHE_MASK) {
@@ -969,15 +967,6 @@ static int msm_gem_new_impl(struct drm_device *dev,
 	INIT_LIST_HEAD(&msm_obj->submit_entry);
 	INIT_LIST_HEAD(&msm_obj->vmas);
 
-	if (struct_mutex_locked) {
-		WARN_ON(!mutex_is_locked(&dev->struct_mutex));
-		list_add_tail(&msm_obj->mm_list, &priv->inactive_list);
-	} else {
-		mutex_lock(&dev->struct_mutex);
-		list_add_tail(&msm_obj->mm_list, &priv->inactive_list);
-		mutex_unlock(&dev->struct_mutex);
-	}
-
 	*obj = &msm_obj->base;
 
 	return 0;
@@ -987,6 +976,7 @@ static struct drm_gem_object *_msm_gem_new(struct drm_device *dev,
 		uint32_t size, uint32_t flags, bool struct_mutex_locked)
 {
 	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_gem_object *msm_obj;
 	struct drm_gem_object *obj = NULL;
 	bool use_vram = false;
 	int ret;
@@ -1007,14 +997,15 @@ static struct drm_gem_object *_msm_gem_new(struct drm_device *dev,
 	if (size == 0)
 		return ERR_PTR(-EINVAL);
 
-	ret = msm_gem_new_impl(dev, size, flags, NULL, &obj, struct_mutex_locked);
+	ret = msm_gem_new_impl(dev, size, flags, NULL, &obj);
 	if (ret)
 		goto fail;
 
+	msm_obj = to_msm_bo(obj);
+
 	if (use_vram) {
 		struct msm_gem_vma *vma;
 		struct page **pages;
-		struct msm_gem_object *msm_obj = to_msm_bo(obj);
 
 		mutex_lock(&msm_obj->lock);
 
@@ -1049,6 +1040,15 @@ static struct drm_gem_object *_msm_gem_new(struct drm_device *dev,
 		mapping_set_gfp_mask(obj->filp->f_mapping, GFP_HIGHUSER);
 	}
 
+	if (struct_mutex_locked) {
+		WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+		list_add_tail(&msm_obj->mm_list, &priv->inactive_list);
+	} else {
+		mutex_lock(&dev->struct_mutex);
+		list_add_tail(&msm_obj->mm_list, &priv->inactive_list);
+		mutex_unlock(&dev->struct_mutex);
+	}
+
 	return obj;
 
 fail:
@@ -1071,6 +1071,7 @@ struct drm_gem_object *msm_gem_new(struct drm_device *dev,
 struct drm_gem_object *msm_gem_import(struct drm_device *dev,
 		struct dma_buf *dmabuf, struct sg_table *sgt)
 {
+	struct msm_drm_private *priv = dev->dev_private;
 	struct msm_gem_object *msm_obj;
 	struct drm_gem_object *obj;
 	uint32_t size;
@@ -1084,7 +1085,7 @@ struct drm_gem_object *msm_gem_import(struct drm_device *dev,
 
 	size = PAGE_ALIGN(dmabuf->size);
 
-	ret = msm_gem_new_impl(dev, size, MSM_BO_WC, dmabuf->resv, &obj, false);
+	ret = msm_gem_new_impl(dev, size, MSM_BO_WC, dmabuf->resv, &obj);
 	if (ret)
 		goto fail;
 
@@ -1109,6 +1110,11 @@ struct drm_gem_object *msm_gem_import(struct drm_device *dev,
 	}
 
 	mutex_unlock(&msm_obj->lock);
+
+	mutex_lock(&dev->struct_mutex);
+	list_add_tail(&msm_obj->mm_list, &priv->inactive_list);
+	mutex_unlock(&dev->struct_mutex);
+
 	return obj;
 
 fail:
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index b2a8411c2d84..ed4f89aeeca1 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -16,6 +16,7 @@
 #include <linux/pm_opp.h>
 #include <linux/devfreq.h>
 #include <linux/devcoredump.h>
+#include <linux/sched/task.h>
 
 /*
  * Power Management:
diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c
index c70e00e22c4c..5ae5a465d28a 100644
--- a/drivers/gpu/drm/msm/msm_submitqueue.c
+++ b/drivers/gpu/drm/msm/msm_submitqueue.c
@@ -69,8 +69,10 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx,
 	queue->flags = flags;
 
 	if (priv->gpu) {
-		if (prio >= priv->gpu->nr_rings)
+		if (prio >= priv->gpu->nr_rings) {
+			kfree(queue);
 			return -EINVAL;
+		}
 
 		queue->prio = prio;
 	}
diff --git a/drivers/gpu/drm/nouveau/Kbuild b/drivers/gpu/drm/nouveau/Kbuild
index b0f53f4f71bf..7a62fa04272d 100644
--- a/drivers/gpu/drm/nouveau/Kbuild
+++ b/drivers/gpu/drm/nouveau/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 ccflags-y += -I $(srctree)/$(src)/include
 ccflags-y += -I $(srctree)/$(src)/include/nvkm
 ccflags-y += -I $(srctree)/$(src)/nvkm
diff --git a/drivers/gpu/drm/nouveau/dispnv04/Kbuild b/drivers/gpu/drm/nouveau/dispnv04/Kbuild
index 65a3990b4e16..975c4e226936 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/Kbuild
+++ b/drivers/gpu/drm/nouveau/dispnv04/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nouveau-y += dispnv04/arb.o
 nouveau-y += dispnv04/crtc.o
 nouveau-y += dispnv04/cursor.o
diff --git a/drivers/gpu/drm/nouveau/dispnv50/Kbuild b/drivers/gpu/drm/nouveau/dispnv50/Kbuild
index 475c630308d1..e0c435eae664 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/Kbuild
+++ b/drivers/gpu/drm/nouveau/dispnv50/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nouveau-y += dispnv50/disp.o
 nouveau-y += dispnv50/lut.o
 
diff --git a/drivers/gpu/drm/nouveau/dispnv50/head.c b/drivers/gpu/drm/nouveau/dispnv50/head.c
index 4497f07935cd..ec639d055595 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/head.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/head.c
@@ -83,18 +83,20 @@ nv50_head_atomic_check_dither(struct nv50_head_atom *armh,
 {
 	u32 mode = 0x00;
 
-	if (asyc->dither.mode == DITHERING_MODE_AUTO) {
-		if (asyh->base.depth > asyh->or.bpc * 3)
-			mode = DITHERING_MODE_DYNAMIC2X2;
-	} else {
-		mode = asyc->dither.mode;
-	}
+	if (asyc->dither.mode) {
+		if (asyc->dither.mode == DITHERING_MODE_AUTO) {
+			if (asyh->base.depth > asyh->or.bpc * 3)
+				mode = DITHERING_MODE_DYNAMIC2X2;
+		} else {
+			mode = asyc->dither.mode;
+		}
 
-	if (asyc->dither.depth == DITHERING_DEPTH_AUTO) {
-		if (asyh->or.bpc >= 8)
-			mode |= DITHERING_DEPTH_8BPC;
-	} else {
-		mode |= asyc->dither.depth;
+		if (asyc->dither.depth == DITHERING_DEPTH_AUTO) {
+			if (asyh->or.bpc >= 8)
+				mode |= DITHERING_DEPTH_8BPC;
+		} else {
+			mode |= asyc->dither.depth;
+		}
 	}
 
 	asyh->dither.enable = mode;
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
index 50303ec194bb..dbb1444ab4e9 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
@@ -334,6 +334,8 @@ nv50_wndw_atomic_check_lut(struct nv50_wndw *wndw,
 		asyw->xlut.handle = wndw->wndw.vram.handle;
 		asyw->xlut.i.buffer = !asyw->xlut.i.buffer;
 		asyw->set.xlut = true;
+	} else {
+		asyw->clr.xlut = armw->xlut.handle != 0;
 	}
 
 	/* Handle setting base SET_OUTPUT_LUT_LO_ENABLE_USE_CORE_LUT. */
@@ -410,6 +412,8 @@ nv50_wndw_atomic_check(struct drm_plane *plane, struct drm_plane_state *state)
 		asyw->clr.ntfy = armw->ntfy.handle != 0;
 		asyw->clr.sema = armw->sema.handle != 0;
 		asyw->clr.xlut = armw->xlut.handle != 0;
+		if (asyw->clr.xlut && asyw->visible)
+			asyw->set.xlut = asyw->xlut.handle != 0;
 		if (wndw->func->image_clr)
 			asyw->clr.image = armw->image.handle[0] != 0;
 	}
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index 3a14365e3d23..6bd9f55a3f0b 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -246,14 +246,22 @@ nouveau_conn_atomic_duplicate_state(struct drm_connector *connector)
 void
 nouveau_conn_reset(struct drm_connector *connector)
 {
+	struct nouveau_connector *nv_connector = nouveau_connector(connector);
 	struct nouveau_conn_atom *asyc;
 
-	if (WARN_ON(!(asyc = kzalloc(sizeof(*asyc), GFP_KERNEL))))
-		return;
+	if (drm_drv_uses_atomic_modeset(connector->dev)) {
+		if (WARN_ON(!(asyc = kzalloc(sizeof(*asyc), GFP_KERNEL))))
+			return;
+
+		if (connector->state)
+			nouveau_conn_atomic_destroy_state(connector,
+							  connector->state);
+
+		__drm_atomic_helper_connector_reset(connector, &asyc->state);
+	} else {
+		asyc = &nv_connector->properties_state;
+	}
 
-	if (connector->state)
-		nouveau_conn_atomic_destroy_state(connector, connector->state);
-	__drm_atomic_helper_connector_reset(connector, &asyc->state);
 	asyc->dither.mode = DITHERING_MODE_AUTO;
 	asyc->dither.depth = DITHERING_DEPTH_AUTO;
 	asyc->scaler.mode = DRM_MODE_SCALE_NONE;
@@ -277,8 +285,14 @@ void
 nouveau_conn_attach_properties(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
-	struct nouveau_conn_atom *armc = nouveau_conn_atom(connector->state);
 	struct nouveau_display *disp = nouveau_display(dev);
+	struct nouveau_connector *nv_connector = nouveau_connector(connector);
+	struct nouveau_conn_atom *armc;
+
+	if (drm_drv_uses_atomic_modeset(connector->dev))
+		armc = nouveau_conn_atom(connector->state);
+	else
+		armc = &nv_connector->properties_state;
 
 	/* Init DVI-I specific properties. */
 	if (connector->connector_type == DRM_MODE_CONNECTOR_DVII)
@@ -750,9 +764,9 @@ static int
 nouveau_connector_set_property(struct drm_connector *connector,
 			       struct drm_property *property, uint64_t value)
 {
-	struct nouveau_conn_atom *asyc = nouveau_conn_atom(connector->state);
 	struct nouveau_connector *nv_connector = nouveau_connector(connector);
 	struct nouveau_encoder *nv_encoder = nv_connector->detected_encoder;
+	struct nouveau_conn_atom *asyc = &nv_connector->properties_state;
 	struct drm_encoder *encoder = to_drm_encoder(nv_encoder);
 	int ret;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.h b/drivers/gpu/drm/nouveau/nouveau_connector.h
index f43a8d63aef8..de84fb4708c7 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.h
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.h
@@ -29,6 +29,7 @@
 
 #include <nvif/notify.h>
 
+#include <drm/drm_crtc.h>
 #include <drm/drm_edid.h>
 #include <drm/drm_encoder.h>
 #include <drm/drm_dp_helper.h>
@@ -44,6 +45,60 @@ struct dcb_output;
 struct nouveau_backlight;
 #endif
 
+#define nouveau_conn_atom(p)                                                   \
+	container_of((p), struct nouveau_conn_atom, state)
+
+struct nouveau_conn_atom {
+	struct drm_connector_state state;
+
+	struct {
+		/* The enum values specifically defined here match nv50/gf119
+		 * hw values, and the code relies on this.
+		 */
+		enum {
+			DITHERING_MODE_OFF = 0x00,
+			DITHERING_MODE_ON = 0x01,
+			DITHERING_MODE_DYNAMIC2X2 = 0x10 | DITHERING_MODE_ON,
+			DITHERING_MODE_STATIC2X2 = 0x18 | DITHERING_MODE_ON,
+			DITHERING_MODE_TEMPORAL = 0x20 | DITHERING_MODE_ON,
+			DITHERING_MODE_AUTO
+		} mode;
+		enum {
+			DITHERING_DEPTH_6BPC = 0x00,
+			DITHERING_DEPTH_8BPC = 0x02,
+			DITHERING_DEPTH_AUTO
+		} depth;
+	} dither;
+
+	struct {
+		int mode;	/* DRM_MODE_SCALE_* */
+		struct {
+			enum {
+				UNDERSCAN_OFF,
+				UNDERSCAN_ON,
+				UNDERSCAN_AUTO,
+			} mode;
+			u32 hborder;
+			u32 vborder;
+		} underscan;
+		bool full;
+	} scaler;
+
+	struct {
+		int color_vibrance;
+		int vibrant_hue;
+	} procamp;
+
+	union {
+		struct {
+			bool dither:1;
+			bool scaler:1;
+			bool procamp:1;
+		};
+		u8 mask;
+	} set;
+};
+
 struct nouveau_connector {
 	struct drm_connector base;
 	enum dcb_connector_type type;
@@ -63,6 +118,12 @@ struct nouveau_connector {
 #ifdef CONFIG_DRM_NOUVEAU_BACKLIGHT
 	struct nouveau_backlight *backlight;
 #endif
+	/*
+	 * Our connector property code expects a nouveau_conn_atom struct
+	 * even on pre-nv50 where we do not support atomic. This embedded
+	 * version gets used in the non atomic modeset case.
+	 */
+	struct nouveau_conn_atom properties_state;
 };
 
 static inline struct nouveau_connector *nouveau_connector(
@@ -121,61 +182,6 @@ extern int nouveau_ignorelid;
 extern int nouveau_duallink;
 extern int nouveau_hdmimhz;
 
-#include <drm/drm_crtc.h>
-#define nouveau_conn_atom(p)                                                   \
-	container_of((p), struct nouveau_conn_atom, state)
-
-struct nouveau_conn_atom {
-	struct drm_connector_state state;
-
-	struct {
-		/* The enum values specifically defined here match nv50/gf119
-		 * hw values, and the code relies on this.
-		 */
-		enum {
-			DITHERING_MODE_OFF = 0x00,
-			DITHERING_MODE_ON = 0x01,
-			DITHERING_MODE_DYNAMIC2X2 = 0x10 | DITHERING_MODE_ON,
-			DITHERING_MODE_STATIC2X2 = 0x18 | DITHERING_MODE_ON,
-			DITHERING_MODE_TEMPORAL = 0x20 | DITHERING_MODE_ON,
-			DITHERING_MODE_AUTO
-		} mode;
-		enum {
-			DITHERING_DEPTH_6BPC = 0x00,
-			DITHERING_DEPTH_8BPC = 0x02,
-			DITHERING_DEPTH_AUTO
-		} depth;
-	} dither;
-
-	struct {
-		int mode;	/* DRM_MODE_SCALE_* */
-		struct {
-			enum {
-				UNDERSCAN_OFF,
-				UNDERSCAN_ON,
-				UNDERSCAN_AUTO,
-			} mode;
-			u32 hborder;
-			u32 vborder;
-		} underscan;
-		bool full;
-	} scaler;
-
-	struct {
-		int color_vibrance;
-		int vibrant_hue;
-	} procamp;
-
-	union {
-		struct {
-			bool dither:1;
-			bool scaler:1;
-			bool procamp:1;
-		};
-		u8 mask;
-	} set;
-};
-
 void nouveau_conn_attach_properties(struct drm_connector *);
 void nouveau_conn_reset(struct drm_connector *);
 struct drm_connector_state *
diff --git a/drivers/gpu/drm/nouveau/nouveau_debugfs.c b/drivers/gpu/drm/nouveau/nouveau_debugfs.c
index 7dfbbbc1beea..5c314f135dd1 100644
--- a/drivers/gpu/drm/nouveau/nouveau_debugfs.c
+++ b/drivers/gpu/drm/nouveau/nouveau_debugfs.c
@@ -54,8 +54,10 @@ nouveau_debugfs_strap_peek(struct seq_file *m, void *data)
 	int ret;
 
 	ret = pm_runtime_get_sync(drm->dev->dev);
-	if (ret < 0 && ret != -EACCES)
+	if (ret < 0 && ret != -EACCES) {
+		pm_runtime_put_autosuspend(drm->dev->dev);
 		return ret;
+	}
 
 	seq_printf(m, "0x%08x\n",
 		   nvif_rd32(&drm->client.device.object, 0x101000));
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 7c2fcaba42d6..425fe54da1f5 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -616,6 +616,64 @@ nouveau_drm_device_fini(struct drm_device *dev)
 	kfree(drm);
 }
 
+/*
+ * On some Intel PCIe bridge controllers doing a
+ * D0 -> D3hot -> D3cold -> D0 sequence causes Nvidia GPUs to not reappear.
+ * Skipping the intermediate D3hot step seems to make it work again. This is
+ * probably caused by not meeting the expectation the involved AML code has
+ * when the GPU is put into D3hot state before invoking it.
+ *
+ * This leads to various manifestations of this issue:
+ *  - AML code execution to power on the GPU hits an infinite loop (as the
+ *    code waits on device memory to change).
+ *  - kernel crashes, as all PCI reads return -1, which most code isn't able
+ *    to handle well enough.
+ *
+ * In all cases dmesg will contain at least one line like this:
+ * 'nouveau 0000:01:00.0: Refused to change power state, currently in D3'
+ * followed by a lot of nouveau timeouts.
+ *
+ * In the \_SB.PCI0.PEG0.PG00._OFF code deeper down writes bit 0x80 to the not
+ * documented PCI config space register 0x248 of the Intel PCIe bridge
+ * controller (0x1901) in order to change the state of the PCIe link between
+ * the PCIe port and the GPU. There are alternative code paths using other
+ * registers, which seem to work fine (executed pre Windows 8):
+ *  - 0xbc bit 0x20 (publicly available documentation claims 'reserved')
+ *  - 0xb0 bit 0x10 (link disable)
+ * Changing the conditions inside the firmware by poking into the relevant
+ * addresses does resolve the issue, but it seemed to be ACPI private memory
+ * and not any device accessible memory at all, so there is no portable way of
+ * changing the conditions.
+ * On a XPS 9560 that means bits [0,3] on \CPEX need to be cleared.
+ *
+ * The only systems where this behavior can be seen are hybrid graphics laptops
+ * with a secondary Nvidia Maxwell, Pascal or Turing GPU. It's unclear whether
+ * this issue only occurs in combination with listed Intel PCIe bridge
+ * controllers and the mentioned GPUs or other devices as well.
+ *
+ * documentation on the PCIe bridge controller can be found in the
+ * "7th Generation Intel® Processor Families for H Platforms Datasheet Volume 2"
+ * Section "12 PCI Express* Controller (x16) Registers"
+ */
+
+static void quirk_broken_nv_runpm(struct pci_dev *pdev)
+{
+	struct drm_device *dev = pci_get_drvdata(pdev);
+	struct nouveau_drm *drm = nouveau_drm(dev);
+	struct pci_dev *bridge = pci_upstream_bridge(pdev);
+
+	if (!bridge || bridge->vendor != PCI_VENDOR_ID_INTEL)
+		return;
+
+	switch (bridge->device) {
+	case 0x1901:
+		drm->old_pm_cap = pdev->pm_cap;
+		pdev->pm_cap = 0;
+		NV_INFO(drm, "Disabling PCI power management to avoid bug\n");
+		break;
+	}
+}
+
 static int nouveau_drm_probe(struct pci_dev *pdev,
 			     const struct pci_device_id *pent)
 {
@@ -697,6 +755,7 @@ static int nouveau_drm_probe(struct pci_dev *pdev,
 	if (ret)
 		goto fail_drm_dev_init;
 
+	quirk_broken_nv_runpm(pdev);
 	return 0;
 
 fail_drm_dev_init:
@@ -734,7 +793,11 @@ static void
 nouveau_drm_remove(struct pci_dev *pdev)
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
+	struct nouveau_drm *drm = nouveau_drm(dev);
 
+	/* revert our workaround */
+	if (drm->old_pm_cap)
+		pdev->pm_cap = drm->old_pm_cap;
 	nouveau_drm_device_remove(dev);
 }
 
@@ -987,8 +1050,10 @@ nouveau_drm_open(struct drm_device *dev, struct drm_file *fpriv)
 
 	/* need to bring up power immediately if opening device */
 	ret = pm_runtime_get_sync(dev->dev);
-	if (ret < 0 && ret != -EACCES)
+	if (ret < 0 && ret != -EACCES) {
+		pm_runtime_put_autosuspend(dev->dev);
 		return ret;
+	}
 
 	get_task_comm(tmpname, current);
 	snprintf(name, sizeof(name), "%s[%d]", tmpname, pid_nr(fpriv->pid));
@@ -1070,8 +1135,10 @@ nouveau_drm_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	long ret;
 
 	ret = pm_runtime_get_sync(dev->dev);
-	if (ret < 0 && ret != -EACCES)
+	if (ret < 0 && ret != -EACCES) {
+		pm_runtime_put_autosuspend(dev->dev);
 		return ret;
+	}
 
 	switch (_IOC_NR(cmd) - DRM_COMMAND_BASE) {
 	case DRM_NOUVEAU_NVIF:
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index 35ff0ca01a3b..607b7d899295 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -136,6 +136,8 @@ struct nouveau_drm {
 
 	struct list_head clients;
 
+	u8 old_pm_cap;
+
 	struct {
 		struct agp_bridge_data *bridge;
 		u32 base;
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index 73cc3217068a..d323b7e99def 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -315,7 +315,7 @@ nouveau_fbcon_create(struct drm_fb_helper *helper,
 	struct nouveau_framebuffer *fb;
 	struct nouveau_channel *chan;
 	struct nouveau_bo *nvbo;
-	struct drm_mode_fb_cmd2 mode_cmd;
+	struct drm_mode_fb_cmd2 mode_cmd = {};
 	int ret;
 
 	mode_cmd.width = sizes->surface_width;
@@ -592,6 +592,7 @@ fini:
 	drm_fb_helper_fini(&fbcon->helper);
 free:
 	kfree(fbcon);
+	drm->fbcon = NULL;
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index d4964f3397a1..91286d0125ac 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -157,7 +157,7 @@ nouveau_fence_wait_uevent_handler(struct nvif_notify *notify)
 
 		fence = list_entry(fctx->pending.next, typeof(*fence), head);
 		chan = rcu_dereference_protected(fence->channel, lockdep_is_held(&fctx->lock));
-		if (nouveau_fence_update(fence->channel, fctx))
+		if (nouveau_fence_update(chan, fctx))
 			ret = NVIF_NOTIFY_DROP;
 	}
 	spin_unlock_irqrestore(&fctx->lock, flags);
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index b4bda716564d..0f96beec66ac 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -45,8 +45,10 @@ nouveau_gem_object_del(struct drm_gem_object *gem)
 	int ret;
 
 	ret = pm_runtime_get_sync(dev);
-	if (WARN_ON(ret < 0 && ret != -EACCES))
+	if (WARN_ON(ret < 0 && ret != -EACCES)) {
+		pm_runtime_put_autosuspend(dev);
 		return;
+	}
 
 	if (gem->import_attach)
 		drm_prime_gem_destroy(gem, nvbo->bo.sg);
diff --git a/drivers/gpu/drm/nouveau/nouveau_sgdma.c b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
index 8ebdc74cc0ad..326948b65542 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sgdma.c
+++ b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
@@ -96,12 +96,9 @@ nouveau_sgdma_create_ttm(struct ttm_buffer_object *bo, uint32_t page_flags)
 	else
 		nvbe->ttm.ttm.func = &nv50_sgdma_backend;
 
-	if (ttm_dma_tt_init(&nvbe->ttm, bo, page_flags))
-		/*
-		 * A failing ttm_dma_tt_init() will call ttm_tt_destroy()
-		 * and thus our nouveau_sgdma_destroy() hook, so we don't need
-		 * to free nvbe here.
-		 */
+	if (ttm_dma_tt_init(&nvbe->ttm, bo, page_flags)) {
+		kfree(nvbe);
 		return NULL;
+	}
 	return &nvbe->ttm.ttm;
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c
index 93ed43c413f0..fd10499329bf 100644
--- a/drivers/gpu/drm/nouveau/nouveau_svm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_svm.c
@@ -173,6 +173,11 @@ nouveau_svmm_bind(struct drm_device *dev, void *data,
 	mm = get_task_mm(current);
 	down_read(&mm->mmap_sem);
 
+	if (!cli->svm.svmm) {
+		up_read(&mm->mmap_sem);
+		return -EINVAL;
+	}
+
 	for (addr = args->va_start, end = args->va_start + size; addr < end;) {
 		struct vm_area_struct *vma;
 		unsigned long next;
@@ -181,6 +186,7 @@ nouveau_svmm_bind(struct drm_device *dev, void *data,
 		if (!vma)
 			break;
 
+		addr = max(addr, vma->vm_start);
 		next = min(vma->vm_end, end);
 		/* This is a best effort so we ignore errors */
 		nouveau_dmem_migrate_vma(cli->drm, vma, addr, next);
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index f0daf958e03a..621d28f094bc 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -63,14 +63,12 @@ nouveau_vram_manager_new(struct ttm_mem_type_manager *man,
 {
 	struct nouveau_bo *nvbo = nouveau_bo(bo);
 	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
-	struct nouveau_mem *mem;
 	int ret;
 
 	if (drm->client.device.info.ram_size == 0)
 		return -ENOMEM;
 
 	ret = nouveau_mem_new(&drm->master, nvbo->kind, nvbo->comp, reg);
-	mem = nouveau_mem(reg);
 	if (ret)
 		return ret;
 
@@ -103,11 +101,9 @@ nouveau_gart_manager_new(struct ttm_mem_type_manager *man,
 {
 	struct nouveau_bo *nvbo = nouveau_bo(bo);
 	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
-	struct nouveau_mem *mem;
 	int ret;
 
 	ret = nouveau_mem_new(&drm->master, nvbo->kind, nvbo->comp, reg);
-	mem = nouveau_mem(reg);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/nouveau/nvif/Kbuild b/drivers/gpu/drm/nouveau/nvif/Kbuild
index 7eebd7d18b6d..50d583d63807 100644
--- a/drivers/gpu/drm/nouveau/nvif/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvif/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvif-y := nvif/object.o
 nvif-y += nvif/client.o
 nvif-y += nvif/device.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/Kbuild b/drivers/gpu/drm/nouveau/nvkm/Kbuild
index a8ec75cf02dc..b53de9ba8c73 100644
--- a/drivers/gpu/drm/nouveau/nvkm/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 include $(src)/nvkm/core/Kbuild
 include $(src)/nvkm/falcon/Kbuild
 include $(src)/nvkm/subdev/Kbuild
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/Kbuild b/drivers/gpu/drm/nouveau/nvkm/core/Kbuild
index 01de22144259..2b471ab585b4 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/core/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y := nvkm/core/client.o
 nvkm-y += nvkm/core/engine.o
 nvkm-y += nvkm/core/enum.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/memory.c b/drivers/gpu/drm/nouveau/nvkm/core/memory.c
index e85a08ecd9da..4cc186262d34 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/memory.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/memory.c
@@ -91,8 +91,8 @@ nvkm_memory_tags_get(struct nvkm_memory *memory, struct nvkm_device *device,
 	}
 
 	refcount_set(&tags->refcount, 1);
+	*ptags = memory->tags = tags;
 	mutex_unlock(&fb->subdev.mutex);
-	*ptags = tags;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/Kbuild
index 5a43bcfb3622..c6dfed18f35b 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/engine/falcon.o
 nvkm-y += nvkm/engine/xtensa.o
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/bsp/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/bsp/Kbuild
index ad1bcfa6fc6c..b596b990519c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/bsp/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/bsp/Kbuild
@@ -1,2 +1,2 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/engine/bsp/g84.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/ce/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/ce/Kbuild
index 157a70721629..ba88613e1e46 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/ce/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/ce/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/engine/ce/gt215.o
 nvkm-y += nvkm/engine/ce/gf100.o
 nvkm-y += nvkm/engine/ce/gk104.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/cipher/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/cipher/Kbuild
index 95708b59496c..ffad341f42bc 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/cipher/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/cipher/Kbuild
@@ -1,2 +1,2 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/engine/cipher/g84.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/device/Kbuild
index 206163da52e1..293c57678dab 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/engine/device/acpi.o
 nvkm-y += nvkm/engine/device/base.o
 nvkm-y += nvkm/engine/device/ctrl.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
index dbfda73cfea6..0d584d0da59c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/engine/disp/base.o
 nvkm-y += nvkm/engine/disp/nv04.o
 nvkm-y += nvkm/engine/disp/nv50.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
index bcf32d92ee5a..50e3539f33d2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
@@ -74,6 +74,8 @@ nv50_disp_chan_mthd(struct nv50_disp_chan *chan, int debug)
 
 	if (debug > subdev->debug)
 		return;
+	if (!mthd)
+		return;
 
 	for (i = 0; (list = mthd->data[i].mthd) != NULL; i++) {
 		u32 base = chan->head * mthd->addr;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdmigm200.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdmigm200.c
index 9b16a08eb4d9..bf6d41fb0c9f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdmigm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdmigm200.c
@@ -27,10 +27,10 @@ void
 gm200_hdmi_scdc(struct nvkm_ior *ior, int head, u8 scdc)
 {
 	struct nvkm_device *device = ior->disp->engine.subdev.device;
-	const u32 hoff = head * 0x800;
+	const u32 soff = nv50_ior_base(ior);
 	const u32 ctrl = scdc & 0x3;
 
-	nvkm_mask(device, 0x61c5bc + hoff, 0x00000003, ctrl);
+	nvkm_mask(device, 0x61c5bc + soff, 0x00000003, ctrl);
 
 	ior->tmds.high_speed = !!(scdc & 0x2);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/dma/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/dma/Kbuild
index 3e2680cbe370..a0e551b92c8d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/dma/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/dma/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/engine/dma/base.o
 nvkm-y += nvkm/engine/dma/nv04.o
 nvkm-y += nvkm/engine/dma/nv50.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/Kbuild
index 1f0eddacc9b7..90e9a0972a44 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/engine/fifo/base.o
 nvkm-y += nvkm/engine/fifo/nv04.o
 nvkm-y += nvkm/engine/fifo/nv10.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/gr/Kbuild
index 50bd9830694f..73724a8cb861 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/engine/gr/base.o
 nvkm-y += nvkm/engine/gr/nv04.o
 nvkm-y += nvkm/engine/gr/nv10.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
index c578deb5867a..c71606a45d1d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
@@ -1988,8 +1988,34 @@ gf100_gr_init_(struct nvkm_gr *base)
 {
 	struct gf100_gr *gr = gf100_gr(base);
 	struct nvkm_subdev *subdev = &base->engine.subdev;
+	struct nvkm_device *device = subdev->device;
+	bool reset = device->chipset == 0x137 || device->chipset == 0x138;
 	u32 ret;
 
+	/* On certain GP107/GP108 boards, we trigger a weird issue where
+	 * GR will stop responding to PRI accesses after we've asked the
+	 * SEC2 RTOS to boot the GR falcons.  This happens with far more
+	 * frequency when cold-booting a board (ie. returning from D3).
+	 *
+	 * The root cause for this is not known and has proven difficult
+	 * to isolate, with many avenues being dead-ends.
+	 *
+	 * A workaround was discovered by Karol, whereby putting GR into
+	 * reset for an extended period right before initialisation
+	 * prevents the problem from occuring.
+	 *
+	 * XXX: As RM does not require any such workaround, this is more
+	 *      of a hack than a true fix.
+	 */
+	reset = nvkm_boolopt(device->cfgopt, "NvGrResetWar", reset);
+	if (reset) {
+		nvkm_mask(device, 0x000200, 0x00001000, 0x00000000);
+		nvkm_rd32(device, 0x000200);
+		msleep(50);
+		nvkm_mask(device, 0x000200, 0x00001000, 0x00001000);
+		nvkm_rd32(device, 0x000200);
+	}
+
 	nvkm_pmu_pgob(gr->base.engine.subdev.device->pmu, false);
 
 	ret = nvkm_falcon_get(gr->fecs.falcon, subdev);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk20a.c
index 500cb08dd608..b57ab5cea9a1 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk20a.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk20a.c
@@ -143,23 +143,24 @@ gk20a_gr_av_to_method(struct gf100_gr *gr, const char *fw_name,
 
 	nent = (fuc.size / sizeof(struct gk20a_fw_av));
 
-	pack = vzalloc((sizeof(*pack) * max_classes) +
-		       (sizeof(*init) * (nent + 1)));
+	pack = vzalloc((sizeof(*pack) * (max_classes + 1)) +
+		       (sizeof(*init) * (nent + max_classes + 1)));
 	if (!pack) {
 		ret = -ENOMEM;
 		goto end;
 	}
 
-	init = (void *)(pack + max_classes);
+	init = (void *)(pack + max_classes + 1);
 
-	for (i = 0; i < nent; i++) {
-		struct gf100_gr_init *ent = &init[i];
+	for (i = 0; i < nent; i++, init++) {
 		struct gk20a_fw_av *av = &((struct gk20a_fw_av *)fuc.data)[i];
 		u32 class = av->addr & 0xffff;
 		u32 addr = (av->addr & 0xffff0000) >> 14;
 
 		if (prevclass != class) {
-			pack[classidx].init = ent;
+			if (prevclass) /* Add terminator to the method list. */
+				init++;
+			pack[classidx].init = init;
 			pack[classidx].type = class;
 			prevclass = class;
 			if (++classidx >= max_classes) {
@@ -169,10 +170,10 @@ gk20a_gr_av_to_method(struct gf100_gr *gr, const char *fw_name,
 			}
 		}
 
-		ent->addr = addr;
-		ent->data = av->data;
-		ent->count = 1;
-		ent->pitch = 1;
+		init->addr = addr;
+		init->data = av->data;
+		init->count = 1;
+		init->pitch = 1;
 	}
 
 	*ppack = pack;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/Kbuild
index 651270137268..8d2d9eae5604 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/engine/mpeg/nv31.o
 nvkm-y += nvkm/engine/mpeg/nv40.o
 nvkm-y += nvkm/engine/mpeg/nv44.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/msenc/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/msenc/Kbuild
index b808d9e9c964..4bf033ff4d41 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/msenc/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/msenc/Kbuild
@@ -1,2 +1,2 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 #nvkm-y += nvkm/engine/msenc/base.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/mspdec/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/mspdec/Kbuild
index df50010e5f2c..0cd957d72593 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/mspdec/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/mspdec/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/engine/mspdec/base.o
 nvkm-y += nvkm/engine/mspdec/g98.o
 nvkm-y += nvkm/engine/mspdec/gt215.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/msppp/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/msppp/Kbuild
index 322e3470b2f1..788ce7255b61 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/msppp/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/msppp/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/engine/msppp/base.o
 nvkm-y += nvkm/engine/msppp/g98.o
 nvkm-y += nvkm/engine/msppp/gt215.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/msvld/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/msvld/Kbuild
index beddd82f5755..d68b4431cd80 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/msvld/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/msvld/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/engine/msvld/base.o
 nvkm-y += nvkm/engine/msvld/g98.o
 nvkm-y += nvkm/engine/msvld/gt215.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/nvdec/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/nvdec/Kbuild
index 29d7ddb56f0e..cdf631822282 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/nvdec/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/nvdec/Kbuild
@@ -1,3 +1,3 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/engine/nvdec/base.o
 nvkm-y += nvkm/engine/nvdec/gp102.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/nvenc/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/nvenc/Kbuild
index 85725b11200b..f316de8d45a8 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/nvenc/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/nvenc/Kbuild
@@ -1,2 +1,2 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 #nvkm-y += nvkm/engine/nvenc/base.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/pm/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/pm/Kbuild
index ceb7302e292f..2cc8a5f6fe0c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/pm/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/pm/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/engine/pm/base.o
 nvkm-y += nvkm/engine/pm/nv40.o
 nvkm-y += nvkm/engine/pm/nv50.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/sec/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/sec/Kbuild
index f72ee558f8e8..b6e02ceb1c5a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/sec/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/sec/Kbuild
@@ -1,2 +1,2 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/engine/sec/g98.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/Kbuild
index 9a2f4f669291..97c4696171f0 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/engine/sec2/base.o
 nvkm-y += nvkm/engine/sec2/gp102.o
 nvkm-y += nvkm/engine/sec2/tu102.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/sw/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/sw/Kbuild
index 91cf08084bc1..94fe25964f51 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/sw/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/sw/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/engine/sw/base.o
 nvkm-y += nvkm/engine/sw/nv04.o
 nvkm-y += nvkm/engine/sw/nv10.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/vic/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/vic/Kbuild
index 9281c82ea99c..70164f482cc5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/vic/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/vic/Kbuild
@@ -1,2 +1,2 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 #nvkm-y += nvkm/engine/vic/base.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/vp/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/vp/Kbuild
index 456e43fd1f6c..d48ea0fd1d27 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/vp/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/vp/Kbuild
@@ -1,2 +1,2 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/engine/vp/g84.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/Kbuild b/drivers/gpu/drm/nouveau/nvkm/falcon/Kbuild
index 8afbf0f9bc86..b5665ada850a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/falcon/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/falcon/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/falcon/base.o
 nvkm-y += nvkm/falcon/v1.o
 nvkm-y += nvkm/falcon/msgqueue.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/Kbuild
index d8c287173f4c..4e136f3d7c28 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 include $(src)/nvkm/subdev/bar/Kbuild
 include $(src)/nvkm/subdev/bios/Kbuild
 include $(src)/nvkm/subdev/bus/Kbuild
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bar/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/bar/Kbuild
index 8210bf9c52a5..8faee3317a74 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bar/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bar/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/subdev/bar/base.o
 nvkm-y += nvkm/subdev/bar/nv50.o
 nvkm-y += nvkm/subdev/bar/g84.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/Kbuild
index bb4759cc38a6..5a970fb8f7ee 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/subdev/bios/base.o
 nvkm-y += nvkm/subdev/bios/bit.o
 nvkm-y += nvkm/subdev/bios/boost.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bus/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/bus/Kbuild
index 409137fbdddf..01d737989d00 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bus/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bus/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/subdev/bus/base.o
 nvkm-y += nvkm/subdev/bus/hwsq.o
 nvkm-y += nvkm/subdev/bus/nv04.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/Kbuild
index 0a8a7072bcbc..dcecd499d8df 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/subdev/clk/base.o
 nvkm-y += nvkm/subdev/clk/nv04.o
 nvkm-y += nvkm/subdev/clk/nv40.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/Kbuild
index f054c44acab2..b3429371ed82 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/subdev/devinit/base.o
 nvkm-y += nvkm/subdev/devinit/nv04.o
 nvkm-y += nvkm/subdev/devinit/nv05.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/Kbuild
index c9bcf3744e5c..53b9d638f2c8 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/subdev/fault/base.o
 nvkm-y += nvkm/subdev/fault/user.o
 nvkm-y += nvkm/subdev/fault/gp100.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c
index ca251560d3e0..bb4a4266897c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c
@@ -146,6 +146,7 @@ nvkm_fault_dtor(struct nvkm_subdev *subdev)
 	struct nvkm_fault *fault = nvkm_fault(subdev);
 	int i;
 
+	nvkm_notify_fini(&fault->nrpfb);
 	nvkm_event_fini(&fault->event);
 
 	for (i = 0; i < fault->buffer_nr; i++) {
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild
index 88b1668929ba..43a42159a3d0 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/subdev/fb/base.o
 nvkm-y += nvkm/subdev/fb/nv04.o
 nvkm-y += nvkm/subdev/fb/nv10.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fuse/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/fuse/Kbuild
index 9626715768c8..8e7cd9d27f23 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fuse/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fuse/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/subdev/fuse/base.o
 nvkm-y += nvkm/subdev/fuse/nv50.o
 nvkm-y += nvkm/subdev/fuse/gf100.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/Kbuild
index 0169fc30a2f9..b2ad5922a1c2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/subdev/gpio/base.o
 nvkm-y += nvkm/subdev/gpio/nv10.o
 nvkm-y += nvkm/subdev/gpio/nv50.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/Kbuild
index fa566ea6cb95..e7c4f068936e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/Kbuild
@@ -1,2 +1,2 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/subdev/gsp/gv100.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/Kbuild
index 69f341e11d70..723d0284caef 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/subdev/i2c/base.o
 nvkm-y += nvkm/subdev/i2c/nv04.o
 nvkm-y += nvkm/subdev/i2c/nv4e.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c
index c8ab1b5741a3..db7769cb33eb 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c
@@ -118,10 +118,10 @@ g94_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
 		if (retries)
 			udelay(400);
 
-		/* transaction request, wait up to 1ms for it to complete */
+		/* transaction request, wait up to 2ms for it to complete */
 		nvkm_wr32(device, 0x00e4e4 + base, 0x00010000 | ctrl);
 
-		timeout = 1000;
+		timeout = 2000;
 		do {
 			ctrl = nvkm_rd32(device, 0x00e4e4 + base);
 			udelay(1);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c
index 7ef60895f43a..edb6148cbca0 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c
@@ -118,10 +118,10 @@ gm200_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
 		if (retries)
 			udelay(400);
 
-		/* transaction request, wait up to 1ms for it to complete */
+		/* transaction request, wait up to 2ms for it to complete */
 		nvkm_wr32(device, 0x00d954 + base, 0x00010000 | ctrl);
 
-		timeout = 1000;
+		timeout = 2000;
 		do {
 			ctrl = nvkm_rd32(device, 0x00d954 + base);
 			udelay(1);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/Kbuild
index 557530355064..127efb51f67d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/subdev/ibus/gf100.o
 nvkm-y += nvkm/subdev/ibus/gf117.o
 nvkm-y += nvkm/subdev/ibus/gk104.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/iccsense/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/iccsense/Kbuild
index 52eb0746c750..6634bcdc5eeb 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/iccsense/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/iccsense/Kbuild
@@ -1,3 +1,3 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/subdev/iccsense/base.o
 nvkm-y += nvkm/subdev/iccsense/gf100.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/Kbuild
index e0031b5c06b1..06cbe19ce376 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/subdev/instmem/base.o
 nvkm-y += nvkm/subdev/instmem/nv04.o
 nvkm-y += nvkm/subdev/instmem/nv40.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/Kbuild
index 61f655c2de0c..2b6d36ea7067 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/subdev/ltc/base.o
 nvkm-y += nvkm/subdev/ltc/gf100.o
 nvkm-y += nvkm/subdev/ltc/gk104.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/Kbuild
index 15da199d2fca..2585ef07532a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/subdev/mc/base.o
 nvkm-y += nvkm/subdev/mc/nv04.o
 nvkm-y += nvkm/subdev/mc/nv11.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/Kbuild
index 697dc22c937c..a602b0cb5b31 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/subdev/mmu/base.o
 nvkm-y += nvkm/subdev/mmu/nv04.o
 nvkm-y += nvkm/subdev/mmu/nv41.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mxm/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/mxm/Kbuild
index 7a549386e675..5124a0c41367 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mxm/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mxm/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/subdev/mxm/base.o
 nvkm-y += nvkm/subdev/mxm/mxms.o
 nvkm-y += nvkm/subdev/mxm/nv50.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pci/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/pci/Kbuild
index 6fbd008d6f10..174bdf995271 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pci/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pci/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/subdev/pci/agp.o
 nvkm-y += nvkm/subdev/pci/base.o
 nvkm-y += nvkm/subdev/pci/pcie.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/Kbuild
index 132ae3341d55..e37b6e45eaa2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/subdev/pmu/base.o
 nvkm-y += nvkm/subdev/pmu/memx.o
 nvkm-y += nvkm/subdev/pmu/gt215.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/Kbuild
index 51b33799cfdb..f3dee2693c79 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/subdev/secboot/base.o
 nvkm-y += nvkm/subdev/secboot/hs_ucode.o
 nvkm-y += nvkm/subdev/secboot/ls_ucode_gr.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c
index df8b919dcf09..ace6fefba428 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c
@@ -108,6 +108,7 @@ gm20b_secboot_new(struct nvkm_device *device, int index,
 	struct gm200_secboot *gsb;
 	struct nvkm_acr *acr;
 
+	*psb = NULL;
 	acr = acr_r352_new(BIT(NVKM_SECBOOT_FALCON_FECS) |
 			   BIT(NVKM_SECBOOT_FALCON_PMU));
 	if (IS_ERR(acr))
@@ -116,10 +117,8 @@ gm20b_secboot_new(struct nvkm_device *device, int index,
 	acr->optional_falcons = BIT(NVKM_SECBOOT_FALCON_PMU);
 
 	gsb = kzalloc(sizeof(*gsb), GFP_KERNEL);
-	if (!gsb) {
-		psb = NULL;
+	if (!gsb)
 		return -ENOMEM;
-	}
 	*psb = &gsb->base;
 
 	ret = nvkm_secboot_ctor(&gm20b_secboot, acr, device, index, &gsb->base);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/Kbuild
index 0cc1439d863b..9aa76a2befa8 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/subdev/therm/base.o
 nvkm-y += nvkm/subdev/therm/fan.o
 nvkm-y += nvkm/subdev/therm/fannil.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/timer/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/timer/Kbuild
index a4aa8e621eb2..f710da4427cf 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/timer/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/timer/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/subdev/timer/base.o
 nvkm-y += nvkm/subdev/timer/nv04.o
 nvkm-y += nvkm/subdev/timer/nv40.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/top/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/top/Kbuild
index e0b27242eeea..438d9d78ab52 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/top/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/top/Kbuild
@@ -1,3 +1,3 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/subdev/top/base.o
 nvkm-y += nvkm/subdev/top/gk104.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/volt/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/volt/Kbuild
index e80bc64b638a..523a7cd155a6 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/volt/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/volt/Kbuild
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: MIT
 nvkm-y += nvkm/subdev/volt/base.o
 nvkm-y += nvkm/subdev/volt/gpio.o
 nvkm-y += nvkm/subdev/volt/nv40.o
diff --git a/drivers/gpu/drm/panel/panel-lvds.c b/drivers/gpu/drm/panel/panel-lvds.c
index 3f6550e6b6a4..f69b9b290113 100644
--- a/drivers/gpu/drm/panel/panel-lvds.c
+++ b/drivers/gpu/drm/panel/panel-lvds.c
@@ -195,7 +195,6 @@ static int panel_lvds_parse_dt(struct panel_lvds *lvds)
 static int panel_lvds_probe(struct platform_device *pdev)
 {
 	struct panel_lvds *lvds;
-	struct device_node *np;
 	int ret;
 
 	lvds = devm_kzalloc(&pdev->dev, sizeof(*lvds), GFP_KERNEL);
@@ -241,14 +240,9 @@ static int panel_lvds_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	np = of_parse_phandle(lvds->dev->of_node, "backlight", 0);
-	if (np) {
-		lvds->backlight = of_find_backlight_by_node(np);
-		of_node_put(np);
-
-		if (!lvds->backlight)
-			return -EPROBE_DEFER;
-	}
+	lvds->backlight = devm_of_find_backlight(lvds->dev);
+	if (IS_ERR(lvds->backlight))
+		return PTR_ERR(lvds->backlight);
 
 	/*
 	 * TODO: Handle all power supplies specified in the DT node in a generic
@@ -264,14 +258,10 @@ static int panel_lvds_probe(struct platform_device *pdev)
 
 	ret = drm_panel_add(&lvds->panel);
 	if (ret < 0)
-		goto error;
+		return ret;
 
 	dev_set_drvdata(lvds->dev, lvds);
 	return 0;
-
-error:
-	put_device(&lvds->backlight->dev);
-	return ret;
 }
 
 static int panel_lvds_remove(struct platform_device *pdev)
@@ -282,9 +272,6 @@ static int panel_lvds_remove(struct platform_device *pdev)
 
 	panel_lvds_disable(&lvds->panel);
 
-	if (lvds->backlight)
-		put_device(&lvds->backlight->dev);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 95e430f9fea4..3a7410057c92 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -1663,7 +1663,7 @@ static const struct drm_display_mode lg_lb070wv8_mode = {
 static const struct panel_desc lg_lb070wv8 = {
 	.modes = &lg_lb070wv8_mode,
 	.num_modes = 1,
-	.bpc = 16,
+	.bpc = 8,
 	.size = {
 		.width = 151,
 		.height = 91,
@@ -1776,6 +1776,40 @@ static const struct drm_display_mode mitsubishi_aa070mc01_mode = {
 	.flags = DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC,
 };
 
+static const struct drm_display_mode logicpd_type_28_mode = {
+	.clock = 9000,
+	.hdisplay = 480,
+	.hsync_start = 480 + 3,
+	.hsync_end = 480 + 3 + 42,
+	.htotal = 480 + 3 + 42 + 2,
+
+	.vdisplay = 272,
+	.vsync_start = 272 + 2,
+	.vsync_end = 272 + 2 + 11,
+	.vtotal = 272 + 2 + 11 + 3,
+	.vrefresh = 60,
+	.flags = DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC,
+};
+
+static const struct panel_desc logicpd_type_28 = {
+	.modes = &logicpd_type_28_mode,
+	.num_modes = 1,
+	.bpc = 8,
+	.size = {
+		.width = 105,
+		.height = 67,
+	},
+	.delay = {
+		.prepare = 200,
+		.enable = 200,
+		.unprepare = 200,
+		.disable = 200,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_POSEDGE |
+		     DRM_BUS_FLAG_SYNC_DRIVE_NEGEDGE,
+};
+
 static const struct panel_desc mitsubishi_aa070mc01 = {
 	.modes = &mitsubishi_aa070mc01_mode,
 	.num_modes = 1,
@@ -2759,6 +2793,9 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "lg,lp129qe",
 		.data = &lg_lp129qe,
 	}, {
+		.compatible = "logicpd,type28",
+		.data = &logicpd_type_28,
+	}, {
 		.compatible = "mitsubishi,aa070mc01-ca1",
 		.data = &mitsubishi_aa070mc01,
 	}, {
diff --git a/drivers/gpu/drm/qxl/qxl_cmd.c b/drivers/gpu/drm/qxl/qxl_cmd.c
index 0a2e51af1230..b7acf19cea8c 100644
--- a/drivers/gpu/drm/qxl/qxl_cmd.c
+++ b/drivers/gpu/drm/qxl/qxl_cmd.c
@@ -478,9 +478,10 @@ int qxl_hw_surface_alloc(struct qxl_device *qdev,
 		return ret;
 
 	ret = qxl_release_reserve_list(release, true);
-	if (ret)
+	if (ret) {
+		qxl_release_free(qdev, release);
 		return ret;
-
+	}
 	cmd = (struct qxl_surface_cmd *)qxl_release_map(qdev, release);
 	cmd->type = QXL_SURFACE_CMD_CREATE;
 	cmd->flags = QXL_SURF_FLAG_KEEP_DATA;
@@ -497,8 +498,8 @@ int qxl_hw_surface_alloc(struct qxl_device *qdev,
 	/* no need to add a release to the fence for this surface bo,
 	   since it is only released when we ask to destroy the surface
 	   and it would never signal otherwise */
-	qxl_push_command_ring_release(qdev, release, QXL_CMD_SURFACE, false);
 	qxl_release_fence_buffer_objects(release);
+	qxl_push_command_ring_release(qdev, release, QXL_CMD_SURFACE, false);
 
 	surf->hw_surf_alloc = true;
 	spin_lock(&qdev->surf_id_idr_lock);
@@ -540,9 +541,8 @@ int qxl_hw_surface_dealloc(struct qxl_device *qdev,
 	cmd->surface_id = id;
 	qxl_release_unmap(qdev, release, &cmd->release_info);
 
-	qxl_push_command_ring_release(qdev, release, QXL_CMD_SURFACE, false);
-
 	qxl_release_fence_buffer_objects(release);
+	qxl_push_command_ring_release(qdev, release, QXL_CMD_SURFACE, false);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index 8b319ebbb0fb..a2152cef3ca2 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -520,8 +520,8 @@ static int qxl_primary_apply_cursor(struct drm_plane *plane)
 	cmd->u.set.visible = 1;
 	qxl_release_unmap(qdev, release, &cmd->release_info);
 
-	qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false);
 	qxl_release_fence_buffer_objects(release);
+	qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false);
 
 	return ret;
 
@@ -662,8 +662,8 @@ static void qxl_cursor_atomic_update(struct drm_plane *plane,
 	cmd->u.position.y = plane->state->crtc_y + fb->hot_y;
 
 	qxl_release_unmap(qdev, release, &cmd->release_info);
-	qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false);
 	qxl_release_fence_buffer_objects(release);
+	qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false);
 
 	if (old_cursor_bo != NULL)
 		qxl_bo_unpin(old_cursor_bo);
@@ -710,8 +710,8 @@ static void qxl_cursor_atomic_disable(struct drm_plane *plane,
 	cmd->type = QXL_CURSOR_HIDE;
 	qxl_release_unmap(qdev, release, &cmd->release_info);
 
-	qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false);
 	qxl_release_fence_buffer_objects(release);
+	qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false);
 }
 
 static void qxl_update_dumb_head(struct qxl_device *qdev,
diff --git a/drivers/gpu/drm/qxl/qxl_draw.c b/drivers/gpu/drm/qxl/qxl_draw.c
index 97c3f1a95a32..e31843add572 100644
--- a/drivers/gpu/drm/qxl/qxl_draw.c
+++ b/drivers/gpu/drm/qxl/qxl_draw.c
@@ -207,9 +207,10 @@ void qxl_draw_dirty_fb(struct qxl_device *qdev,
 		goto out_release_backoff;
 
 	rects = drawable_set_clipping(qdev, num_clips, clips_bo);
-	if (!rects)
+	if (!rects) {
+		ret = -EINVAL;
 		goto out_release_backoff;
-
+	}
 	drawable = (struct qxl_drawable *)qxl_release_map(qdev, release);
 
 	drawable->clip.type = SPICE_CLIP_TYPE_RECTS;
@@ -240,8 +241,8 @@ void qxl_draw_dirty_fb(struct qxl_device *qdev,
 	}
 	qxl_bo_kunmap(clips_bo);
 
-	qxl_push_command_ring_release(qdev, release, QXL_CMD_DRAW, false);
 	qxl_release_fence_buffer_objects(release);
+	qxl_push_command_ring_release(qdev, release, QXL_CMD_DRAW, false);
 
 out_release_backoff:
 	if (ret)
diff --git a/drivers/gpu/drm/qxl/qxl_image.c b/drivers/gpu/drm/qxl/qxl_image.c
index 43688ecdd8a0..60ab7151b84d 100644
--- a/drivers/gpu/drm/qxl/qxl_image.c
+++ b/drivers/gpu/drm/qxl/qxl_image.c
@@ -212,7 +212,8 @@ qxl_image_init_helper(struct qxl_device *qdev,
 		break;
 	default:
 		DRM_ERROR("unsupported image bit depth\n");
-		return -EINVAL; /* TODO: cleanup */
+		qxl_bo_kunmap_atomic_page(qdev, image_bo, ptr);
+		return -EINVAL;
 	}
 	image->u.bitmap.flags = QXL_BITMAP_TOP_DOWN;
 	image->u.bitmap.x = width;
diff --git a/drivers/gpu/drm/qxl/qxl_ioctl.c b/drivers/gpu/drm/qxl/qxl_ioctl.c
index d410e2925162..0fc0995e50b5 100644
--- a/drivers/gpu/drm/qxl/qxl_ioctl.c
+++ b/drivers/gpu/drm/qxl/qxl_ioctl.c
@@ -258,11 +258,8 @@ static int qxl_process_single_command(struct qxl_device *qdev,
 			apply_surf_reloc(qdev, &reloc_info[i]);
 	}
 
+	qxl_release_fence_buffer_objects(release);
 	ret = qxl_push_command_ring_release(qdev, release, cmd->type, true);
-	if (ret)
-		qxl_release_backoff_reserve_list(release);
-	else
-		qxl_release_fence_buffer_objects(release);
 
 out_free_bos:
 out_free_release:
diff --git a/drivers/gpu/drm/qxl/qxl_kms.c b/drivers/gpu/drm/qxl/qxl_kms.c
index bee61fa2c9bc..5d2e7ddc83e5 100644
--- a/drivers/gpu/drm/qxl/qxl_kms.c
+++ b/drivers/gpu/drm/qxl/qxl_kms.c
@@ -181,7 +181,7 @@ int qxl_device_init(struct qxl_device *qdev,
 
 	if (!qxl_check_device(qdev)) {
 		r = -ENODEV;
-		goto surface_mapping_free;
+		goto rom_unmap;
 	}
 
 	r = qxl_bo_init(qdev);
@@ -215,7 +215,7 @@ int qxl_device_init(struct qxl_device *qdev,
 				&(qdev->ram_header->cursor_ring_hdr),
 				sizeof(struct qxl_command),
 				QXL_CURSOR_RING_SIZE,
-				qdev->io_base + QXL_IO_NOTIFY_CMD,
+				qdev->io_base + QXL_IO_NOTIFY_CURSOR,
 				false,
 				&qdev->cursor_event);
 
diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index a12439266bb0..0f9d7945ae09 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -4364,7 +4364,7 @@ static int ci_set_mc_special_registers(struct radeon_device *rdev,
 					table->mc_reg_table_entry[k].mc_data[j] |= 0x100;
 			}
 			j++;
-			if (j > SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE)
+			if (j >= SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE)
 				return -EINVAL;
 
 			if (!pi->mem_gddr5) {
@@ -5576,6 +5576,7 @@ static int ci_parse_power_table(struct radeon_device *rdev)
 	if (!rdev->pm.dpm.ps)
 		return -ENOMEM;
 	power_state_offset = (u8 *)state_array->states;
+	rdev->pm.dpm.num_ps = 0;
 	for (i = 0; i < state_array->ucNumEntries; i++) {
 		u8 *idx;
 		power_state = (union pplib_power_state *)power_state_offset;
@@ -5585,10 +5586,8 @@ static int ci_parse_power_table(struct radeon_device *rdev)
 		if (!rdev->pm.power_state[i].clock_info)
 			return -EINVAL;
 		ps = kzalloc(sizeof(struct ci_ps), GFP_KERNEL);
-		if (ps == NULL) {
-			kfree(rdev->pm.dpm.ps);
+		if (ps == NULL)
 			return -ENOMEM;
-		}
 		rdev->pm.dpm.ps[i].ps_priv = ps;
 		ci_parse_pplib_non_clock_info(rdev, &rdev->pm.dpm.ps[i],
 					      non_clock_info,
@@ -5610,8 +5609,8 @@ static int ci_parse_power_table(struct radeon_device *rdev)
 			k++;
 		}
 		power_state_offset += 2 + power_state->v2.ucNumDPMLevels;
+		rdev->pm.dpm.num_ps = i + 1;
 	}
-	rdev->pm.dpm.num_ps = state_array->ucNumEntries;
 
 	/* fill in the vce power states */
 	for (i = 0; i < RADEON_MAX_VCE_LEVELS; i++) {
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index ab7b4e2ffcd2..947b97a390ae 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -6965,8 +6965,8 @@ static int cik_irq_init(struct radeon_device *rdev)
 	}
 
 	/* setup interrupt control */
-	/* XXX this should actually be a bus address, not an MC address. same on older asics */
-	WREG32(INTERRUPT_CNTL2, rdev->ih.gpu_addr >> 8);
+	/* set dummy read address to dummy page address */
+	WREG32(INTERRUPT_CNTL2, rdev->dummy_page.addr >> 8);
 	interrupt_cntl = RREG32(INTERRUPT_CNTL);
 	/* IH_DUMMY_RD_OVERRIDE=0 - dummy read disabled with msi, enabled without msi
 	 * IH_DUMMY_RD_OVERRIDE=1 - dummy read controlled by IH_DUMMY_RD_EN
diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c
index 0fd8d6ba9828..f86ca163dcf3 100644
--- a/drivers/gpu/drm/radeon/ni_dpm.c
+++ b/drivers/gpu/drm/radeon/ni_dpm.c
@@ -2126,7 +2126,7 @@ static int ni_init_smc_spll_table(struct radeon_device *rdev)
 		if (clk_s & ~(SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_MASK >> SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_SHIFT))
 			ret = -EINVAL;
 
-		if (clk_s & ~(SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_MASK >> SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_SHIFT))
+		if (fb_div & ~(SMC_NISLANDS_SPLL_DIV_TABLE_FBDIV_MASK >> SMC_NISLANDS_SPLL_DIV_TABLE_FBDIV_SHIFT))
 			ret = -EINVAL;
 
 		if (clk_v & ~(SMC_NISLANDS_SPLL_DIV_TABLE_CLKV_MASK >> SMC_NISLANDS_SPLL_DIV_TABLE_CLKV_SHIFT))
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index e06e2d8feab3..a724bb87cfad 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -3690,8 +3690,8 @@ int r600_irq_init(struct radeon_device *rdev)
 	}
 
 	/* setup interrupt control */
-	/* set dummy read address to ring address */
-	WREG32(INTERRUPT_CNTL2, rdev->ih.gpu_addr >> 8);
+	/* set dummy read address to dummy page address */
+	WREG32(INTERRUPT_CNTL2, rdev->dummy_page.addr >> 8);
 	interrupt_cntl = RREG32(INTERRUPT_CNTL);
 	/* IH_DUMMY_RD_OVERRIDE=0 - dummy read disabled with msi, enabled without msi
 	 * IH_DUMMY_RD_OVERRIDE=1 - dummy read controlled by IH_DUMMY_RD_EN
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 433df7036f96..b1efbef8107f 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -122,6 +122,8 @@ static void dce5_crtc_load_lut(struct drm_crtc *crtc)
 
 	DRM_DEBUG_KMS("%d\n", radeon_crtc->crtc_id);
 
+	msleep(10);
+
 	WREG32(NI_INPUT_CSC_CONTROL + radeon_crtc->crtc_offset,
 	       (NI_INPUT_CSC_GRPH_MODE(NI_INPUT_CSC_BYPASS) |
 		NI_INPUT_CSC_OVL_MODE(NI_INPUT_CSC_BYPASS)));
@@ -624,8 +626,10 @@ radeon_crtc_set_config(struct drm_mode_set *set,
 	dev = set->crtc->dev;
 
 	ret = pm_runtime_get_sync(dev->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_autosuspend(dev->dev);
 		return ret;
+	}
 
 	ret = drm_crtc_helper_set_config(set, ctx);
 
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 5502e3428868..ab1bc6fcfd0b 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -42,6 +42,7 @@
 #include <drm/drm_gem.h>
 #include <drm/drm_fb_helper.h>
 
+#include <drm/drm_agpsupport.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_probe_helper.h>
 
@@ -169,12 +170,7 @@ int radeon_no_wb;
 int radeon_modeset = -1;
 int radeon_dynclks = -1;
 int radeon_r4xx_atom = 0;
-#ifdef __powerpc__
-/* Default to PCI on PowerPC (fdo #95017) */
 int radeon_agpmode = -1;
-#else
-int radeon_agpmode = 0;
-#endif
 int radeon_vram_limit = 0;
 int radeon_gart_size = -1; /* auto */
 int radeon_benchmarking = 0;
@@ -321,6 +317,7 @@ static int radeon_pci_probe(struct pci_dev *pdev,
 			    const struct pci_device_id *ent)
 {
 	unsigned long flags = 0;
+	struct drm_device *dev;
 	int ret;
 
 	if (!ent)
@@ -361,7 +358,44 @@ static int radeon_pci_probe(struct pci_dev *pdev,
 	if (ret)
 		return ret;
 
-	return drm_get_pci_dev(pdev, ent, &kms_driver);
+	dev = drm_dev_alloc(&kms_driver, &pdev->dev);
+	if (IS_ERR(dev))
+		return PTR_ERR(dev);
+
+	ret = pci_enable_device(pdev);
+	if (ret)
+		goto err_free;
+
+	dev->pdev = pdev;
+#ifdef __alpha__
+	dev->hose = pdev->sysdata;
+#endif
+
+	pci_set_drvdata(pdev, dev);
+
+	if (pci_find_capability(dev->pdev, PCI_CAP_ID_AGP))
+		dev->agp = drm_agp_init(dev);
+	if (dev->agp) {
+		dev->agp->agp_mtrr = arch_phys_wc_add(
+			dev->agp->agp_info.aper_base,
+			dev->agp->agp_info.aper_size *
+			1024 * 1024);
+	}
+
+	ret = drm_dev_register(dev, ent->driver_data);
+	if (ret)
+		goto err_agp;
+
+	return 0;
+
+err_agp:
+	if (dev->agp)
+		arch_phys_wc_del(dev->agp->agp_mtrr);
+	kfree(dev->agp);
+	pci_disable_device(pdev);
+err_free:
+	drm_dev_put(dev);
+	return ret;
 }
 
 static void
@@ -503,8 +537,10 @@ long radeon_drm_ioctl(struct file *filp,
 	long ret;
 	dev = file_priv->minor->dev;
 	ret = pm_runtime_get_sync(dev->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_autosuspend(dev->dev);
 		return ret;
+	}
 
 	ret = drm_ioctl(filp, cmd, arg);
 	
@@ -565,7 +601,7 @@ radeon_get_crtc_scanout_position(struct drm_device *dev, unsigned int pipe,
 
 static struct drm_driver kms_driver = {
 	.driver_features =
-	    DRIVER_USE_AGP | DRIVER_GEM | DRIVER_PRIME | DRIVER_RENDER,
+	    DRIVER_GEM | DRIVER_PRIME | DRIVER_RENDER,
 	.load = radeon_driver_load_kms,
 	.open = radeon_driver_open_kms,
 	.postclose = radeon_driver_postclose_kms,
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 3ff835767ac5..44901fba0dbf 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -26,6 +26,7 @@
  *          Jerome Glisse
  */
 #include <drm/drmP.h>
+#include <drm/drm_agpsupport.h>
 #include <drm/drm_fb_helper.h>
 #include "radeon.h"
 #include <drm/radeon_drm.h>
@@ -72,6 +73,11 @@ void radeon_driver_unload_kms(struct drm_device *dev)
 	radeon_modeset_fini(rdev);
 	radeon_device_fini(rdev);
 
+	if (dev->agp)
+		arch_phys_wc_del(dev->agp->agp_mtrr);
+	kfree(dev->agp);
+	dev->agp = NULL;
+
 done_free:
 	kfree(rdev);
 	dev->dev_private = NULL;
@@ -627,8 +633,10 @@ int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 	file_priv->driver_priv = NULL;
 
 	r = pm_runtime_get_sync(dev->dev);
-	if (r < 0)
+	if (r < 0) {
+		pm_runtime_put_autosuspend(dev->dev);
 		return r;
+	}
 
 	/* new gpu have virtual address space support */
 	if (rdev->family >= CHIP_CAYMAN) {
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 841bc8bc333d..c181ac082c23 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -5993,8 +5993,8 @@ static int si_irq_init(struct radeon_device *rdev)
 	}
 
 	/* setup interrupt control */
-	/* set dummy read address to ring address */
-	WREG32(INTERRUPT_CNTL2, rdev->ih.gpu_addr >> 8);
+	/* set dummy read address to dummy page address */
+	WREG32(INTERRUPT_CNTL2, rdev->dummy_page.addr >> 8);
 	interrupt_cntl = RREG32(INTERRUPT_CNTL);
 	/* IH_DUMMY_RD_OVERRIDE=0 - dummy read disabled with msi, enabled without msi
 	 * IH_DUMMY_RD_OVERRIDE=1 - dummy read controlled by IH_DUMMY_RD_EN
diff --git a/drivers/gpu/drm/rcar-du/Kconfig b/drivers/gpu/drm/rcar-du/Kconfig
index 1529849e217e..7cdba77b1420 100644
--- a/drivers/gpu/drm/rcar-du/Kconfig
+++ b/drivers/gpu/drm/rcar-du/Kconfig
@@ -23,6 +23,7 @@ config DRM_RCAR_DW_HDMI
 config DRM_RCAR_LVDS
 	tristate "R-Car DU LVDS Encoder Support"
 	depends on DRM && DRM_BRIDGE && OF
+	select DRM_KMS_HELPER
 	select DRM_PANEL
 	select OF_FLATTREE
 	select OF_OVERLAY
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_plane.c b/drivers/gpu/drm/rcar-du/rcar_du_plane.c
index c6430027169f..a0021fc25b27 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_plane.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_plane.c
@@ -785,13 +785,15 @@ int rcar_du_planes_init(struct rcar_du_group *rgrp)
 
 		drm_plane_create_alpha_property(&plane->plane);
 
-		if (type == DRM_PLANE_TYPE_PRIMARY)
-			continue;
-
-		drm_object_attach_property(&plane->plane.base,
-					   rcdu->props.colorkey,
-					   RCAR_DU_COLORKEY_NONE);
-		drm_plane_create_zpos_property(&plane->plane, 1, 1, 7);
+		if (type == DRM_PLANE_TYPE_PRIMARY) {
+			drm_plane_create_zpos_immutable_property(&plane->plane,
+								 0);
+		} else {
+			drm_object_attach_property(&plane->plane.base,
+						   rcdu->props.colorkey,
+						   RCAR_DU_COLORKEY_NONE);
+			drm_plane_create_zpos_property(&plane->plane, 1, 1, 7);
+		}
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
index 5e4faf258c31..f1a81c9b184d 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c
@@ -392,12 +392,14 @@ int rcar_du_vsp_init(struct rcar_du_vsp *vsp, struct device_node *np,
 		drm_plane_helper_add(&plane->plane,
 				     &rcar_du_vsp_plane_helper_funcs);
 
-		if (type == DRM_PLANE_TYPE_PRIMARY)
-			continue;
-
-		drm_plane_create_alpha_property(&plane->plane);
-		drm_plane_create_zpos_property(&plane->plane, 1, 1,
-					       vsp->num_planes - 1);
+		if (type == DRM_PLANE_TYPE_PRIMARY) {
+			drm_plane_create_zpos_immutable_property(&plane->plane,
+								 0);
+		} else {
+			drm_plane_create_alpha_property(&plane->plane);
+			drm_plane_create_zpos_property(&plane->plane, 1, 1,
+						       vsp->num_planes - 1);
+		}
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/rcar-du/rcar_lvds.c b/drivers/gpu/drm/rcar-du/rcar_lvds.c
index 620b51aab291..6b623310f36a 100644
--- a/drivers/gpu/drm/rcar-du/rcar_lvds.c
+++ b/drivers/gpu/drm/rcar-du/rcar_lvds.c
@@ -16,6 +16,7 @@
 #include <linux/of_graph.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
+#include <linux/sys_soc.h>
 
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
@@ -779,8 +780,23 @@ static int rcar_lvds_get_clocks(struct rcar_lvds *lvds)
 	return 0;
 }
 
+static const struct rcar_lvds_device_info rcar_lvds_r8a7790es1_info = {
+	.gen = 2,
+	.quirks = RCAR_LVDS_QUIRK_LANES,
+	.pll_setup = rcar_lvds_pll_setup_gen2,
+};
+
+static const struct soc_device_attribute lvds_quirk_matches[] = {
+	{
+		.soc_id = "r8a7790", .revision = "ES1.*",
+		.data = &rcar_lvds_r8a7790es1_info,
+	},
+	{ /* sentinel */ }
+};
+
 static int rcar_lvds_probe(struct platform_device *pdev)
 {
+	const struct soc_device_attribute *attr;
 	struct rcar_lvds *lvds;
 	struct resource *mem;
 	int ret;
@@ -795,6 +811,10 @@ static int rcar_lvds_probe(struct platform_device *pdev)
 	lvds->info = of_device_get_match_data(&pdev->dev);
 	lvds->enabled = false;
 
+	attr = soc_device_match(lvds_quirk_matches);
+	if (attr)
+		lvds->info = attr->data;
+
 	ret = rcar_lvds_parse_dt(lvds);
 	if (ret < 0)
 		return ret;
@@ -831,12 +851,6 @@ static const struct rcar_lvds_device_info rcar_lvds_gen2_info = {
 	.pll_setup = rcar_lvds_pll_setup_gen2,
 };
 
-static const struct rcar_lvds_device_info rcar_lvds_r8a7790_info = {
-	.gen = 2,
-	.quirks = RCAR_LVDS_QUIRK_LANES,
-	.pll_setup = rcar_lvds_pll_setup_gen2,
-};
-
 static const struct rcar_lvds_device_info rcar_lvds_gen3_info = {
 	.gen = 3,
 	.quirks = RCAR_LVDS_QUIRK_PWD,
@@ -867,7 +881,7 @@ static const struct of_device_id rcar_lvds_of_table[] = {
 	{ .compatible = "renesas,r8a7743-lvds", .data = &rcar_lvds_gen2_info },
 	{ .compatible = "renesas,r8a7744-lvds", .data = &rcar_lvds_gen2_info },
 	{ .compatible = "renesas,r8a774c0-lvds", .data = &rcar_lvds_r8a77990_info },
-	{ .compatible = "renesas,r8a7790-lvds", .data = &rcar_lvds_r8a7790_info },
+	{ .compatible = "renesas,r8a7790-lvds", .data = &rcar_lvds_gen2_info },
 	{ .compatible = "renesas,r8a7791-lvds", .data = &rcar_lvds_gen2_info },
 	{ .compatible = "renesas,r8a7793-lvds", .data = &rcar_lvds_gen2_info },
 	{ .compatible = "renesas,r8a7795-lvds", .data = &rcar_lvds_gen3_info },
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index 09046135e720..f66bdfce1a62 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -1009,10 +1009,41 @@ static bool vop_crtc_mode_fixup(struct drm_crtc *crtc,
 				struct drm_display_mode *adjusted_mode)
 {
 	struct vop *vop = to_vop(crtc);
+	unsigned long rate;
 
-	adjusted_mode->clock =
-		DIV_ROUND_UP(clk_round_rate(vop->dclk, mode->clock * 1000),
-			     1000);
+	/*
+	 * Clock craziness.
+	 *
+	 * Key points:
+	 *
+	 * - DRM works in in kHz.
+	 * - Clock framework works in Hz.
+	 * - Rockchip's clock driver picks the clock rate that is the
+	 *   same _OR LOWER_ than the one requested.
+	 *
+	 * Action plan:
+	 *
+	 * 1. When DRM gives us a mode, we should add 999 Hz to it.  That way
+	 *    if the clock we need is 60000001 Hz (~60 MHz) and DRM tells us to
+	 *    make 60000 kHz then the clock framework will actually give us
+	 *    the right clock.
+	 *
+	 *    NOTE: if the PLL (maybe through a divider) could actually make
+	 *    a clock rate 999 Hz higher instead of the one we want then this
+	 *    could be a problem.  Unfortunately there's not much we can do
+	 *    since it's baked into DRM to use kHz.  It shouldn't matter in
+	 *    practice since Rockchip PLLs are controlled by tables and
+	 *    even if there is a divider in the middle I wouldn't expect PLL
+	 *    rates in the table that are just a few kHz different.
+	 *
+	 * 2. Get the clock framework to round the rate for us to tell us
+	 *    what it will actually make.
+	 *
+	 * 3. Store the rounded up rate so that we don't need to worry about
+	 *    this in the actual clk_set_rate().
+	 */
+	rate = clk_round_rate(vop->dclk, adjusted_mode->clock * 1000 + 999);
+	adjusted_mode->clock = DIV_ROUND_UP(rate, 1000);
 
 	return true;
 }
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index a3688a5c166a..eba7731ce681 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -618,7 +618,9 @@ static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb)
 	list_del_init(&s_job->node);
 	spin_unlock_irqrestore(&sched->job_list_lock, flags);
 
+	dma_fence_get(&s_fence->finished);
 	drm_sched_fence_finished(s_fence);
+	dma_fence_put(&s_fence->finished);
 
 	trace_drm_sched_process_job(s_fence);
 	wake_up_interruptible(&sched->wake_up_worker);
diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c
index 3ff73998d841..344e6a29ef17 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.c
@@ -96,7 +96,6 @@ static int sun4i_drv_bind(struct device *dev)
 	}
 
 	drm_mode_config_init(drm);
-	drm->mode_config.allow_fb_modifiers = true;
 
 	ret = component_bind_all(drm->dev, drm);
 	if (ret) {
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi.h b/drivers/gpu/drm/sun4i/sun4i_hdmi.h
index 7ad3f06c127e..00ca35f07ba5 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi.h
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi.h
@@ -148,7 +148,7 @@
 #define SUN4I_HDMI_DDC_CMD_IMPLICIT_WRITE	3
 
 #define SUN4I_HDMI_DDC_CLK_REG		0x528
-#define SUN4I_HDMI_DDC_CLK_M(m)			(((m) & 0x7) << 3)
+#define SUN4I_HDMI_DDC_CLK_M(m)			(((m) & 0xf) << 3)
 #define SUN4I_HDMI_DDC_CLK_N(n)			((n) & 0x7)
 
 #define SUN4I_HDMI_DDC_LINE_CTRL_REG	0x540
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_ddc_clk.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_ddc_clk.c
index 2ff780114106..12430b9d4e93 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi_ddc_clk.c
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_ddc_clk.c
@@ -33,7 +33,7 @@ static unsigned long sun4i_ddc_calc_divider(unsigned long rate,
 	unsigned long best_rate = 0;
 	u8 best_m = 0, best_n = 0, _m, _n;
 
-	for (_m = 0; _m < 8; _m++) {
+	for (_m = 0; _m < 16; _m++) {
 		for (_n = 0; _n < 8; _n++) {
 			unsigned long tmp_rate;
 
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
index 9c3f99339b82..68328feea192 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
@@ -261,9 +261,8 @@ sun4i_hdmi_connector_detect(struct drm_connector *connector, bool force)
 	struct sun4i_hdmi *hdmi = drm_connector_to_sun4i_hdmi(connector);
 	unsigned long reg;
 
-	if (readl_poll_timeout(hdmi->base + SUN4I_HDMI_HPD_REG, reg,
-			       reg & SUN4I_HDMI_HPD_HIGH,
-			       0, 500000)) {
+	reg = readl(hdmi->base + SUN4I_HDMI_HPD_REG);
+	if (!(reg & SUN4I_HDMI_HPD_HIGH)) {
 		cec_phys_addr_invalidate(hdmi->cec_adap);
 		return connector_status_disconnected;
 	}
@@ -681,8 +680,6 @@ static void sun4i_hdmi_unbind(struct device *dev, struct device *master,
 	struct sun4i_hdmi *hdmi = dev_get_drvdata(dev);
 
 	cec_unregister_adapter(hdmi->cec_adap);
-	drm_connector_cleanup(&hdmi->connector);
-	drm_encoder_cleanup(&hdmi->encoder);
 	i2c_del_adapter(hdmi->i2c);
 	i2c_put_adapter(hdmi->ddc_i2c);
 	clk_disable_unprepare(hdmi->mod_clk);
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index 7774824bf04c..9ecd0a604c19 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -1501,6 +1501,8 @@ const struct of_device_id sun4i_tcon_of_table[] = {
 	{ .compatible = "allwinner,sun6i-a31-tcon", .data = &sun6i_a31_quirks },
 	{ .compatible = "allwinner,sun6i-a31s-tcon", .data = &sun6i_a31s_quirks },
 	{ .compatible = "allwinner,sun7i-a20-tcon", .data = &sun7i_a20_quirks },
+	{ .compatible = "allwinner,sun7i-a20-tcon0", .data = &sun7i_a20_quirks },
+	{ .compatible = "allwinner,sun7i-a20-tcon1", .data = &sun7i_a20_quirks },
 	{ .compatible = "allwinner,sun8i-a23-tcon", .data = &sun8i_a33_quirks },
 	{ .compatible = "allwinner,sun8i-a33-tcon", .data = &sun8i_a33_quirks },
 	{ .compatible = "allwinner,sun8i-a83t-tcon-lcd", .data = &sun8i_a83t_lcd_quirks },
diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
index 5f3a9d37bc9c..858499da27c2 100644
--- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
+++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
@@ -717,7 +717,7 @@ static void sun6i_dsi_encoder_enable(struct drm_encoder *encoder)
 	struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode;
 	struct sun6i_dsi *dsi = encoder_to_sun6i_dsi(encoder);
 	struct mipi_dsi_device *device = dsi->device;
-	union phy_configure_opts opts = { 0 };
+	union phy_configure_opts opts = { };
 	struct phy_configure_opts_mipi_dphy *cfg = &opts.mipi_dphy;
 	u16 delay;
 
diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.c b/drivers/gpu/drm/sun4i/sun8i_mixer.c
index c2eedf58bf4b..dd40ed238537 100644
--- a/drivers/gpu/drm/sun4i/sun8i_mixer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_mixer.c
@@ -107,48 +107,128 @@ static const struct de2_fmt_info de2_formats[] = {
 		.csc = SUN8I_CSC_MODE_OFF,
 	},
 	{
+		/* for DE2 VI layer which ignores alpha */
+		.drm_fmt = DRM_FORMAT_XRGB4444,
+		.de2_fmt = SUN8I_MIXER_FBFMT_ARGB4444,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
 		.drm_fmt = DRM_FORMAT_ABGR4444,
 		.de2_fmt = SUN8I_MIXER_FBFMT_ABGR4444,
 		.rgb = true,
 		.csc = SUN8I_CSC_MODE_OFF,
 	},
 	{
+		/* for DE2 VI layer which ignores alpha */
+		.drm_fmt = DRM_FORMAT_XBGR4444,
+		.de2_fmt = SUN8I_MIXER_FBFMT_ABGR4444,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
 		.drm_fmt = DRM_FORMAT_RGBA4444,
 		.de2_fmt = SUN8I_MIXER_FBFMT_RGBA4444,
 		.rgb = true,
 		.csc = SUN8I_CSC_MODE_OFF,
 	},
 	{
+		/* for DE2 VI layer which ignores alpha */
+		.drm_fmt = DRM_FORMAT_RGBX4444,
+		.de2_fmt = SUN8I_MIXER_FBFMT_RGBA4444,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
 		.drm_fmt = DRM_FORMAT_BGRA4444,
 		.de2_fmt = SUN8I_MIXER_FBFMT_BGRA4444,
 		.rgb = true,
 		.csc = SUN8I_CSC_MODE_OFF,
 	},
 	{
+		/* for DE2 VI layer which ignores alpha */
+		.drm_fmt = DRM_FORMAT_BGRX4444,
+		.de2_fmt = SUN8I_MIXER_FBFMT_BGRA4444,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
 		.drm_fmt = DRM_FORMAT_ARGB1555,
 		.de2_fmt = SUN8I_MIXER_FBFMT_ARGB1555,
 		.rgb = true,
 		.csc = SUN8I_CSC_MODE_OFF,
 	},
 	{
+		/* for DE2 VI layer which ignores alpha */
+		.drm_fmt = DRM_FORMAT_XRGB1555,
+		.de2_fmt = SUN8I_MIXER_FBFMT_ARGB1555,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
 		.drm_fmt = DRM_FORMAT_ABGR1555,
 		.de2_fmt = SUN8I_MIXER_FBFMT_ABGR1555,
 		.rgb = true,
 		.csc = SUN8I_CSC_MODE_OFF,
 	},
 	{
+		/* for DE2 VI layer which ignores alpha */
+		.drm_fmt = DRM_FORMAT_XBGR1555,
+		.de2_fmt = SUN8I_MIXER_FBFMT_ABGR1555,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
 		.drm_fmt = DRM_FORMAT_RGBA5551,
 		.de2_fmt = SUN8I_MIXER_FBFMT_RGBA5551,
 		.rgb = true,
 		.csc = SUN8I_CSC_MODE_OFF,
 	},
 	{
+		/* for DE2 VI layer which ignores alpha */
+		.drm_fmt = DRM_FORMAT_RGBX5551,
+		.de2_fmt = SUN8I_MIXER_FBFMT_RGBA5551,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
 		.drm_fmt = DRM_FORMAT_BGRA5551,
 		.de2_fmt = SUN8I_MIXER_FBFMT_BGRA5551,
 		.rgb = true,
 		.csc = SUN8I_CSC_MODE_OFF,
 	},
 	{
+		/* for DE2 VI layer which ignores alpha */
+		.drm_fmt = DRM_FORMAT_BGRX5551,
+		.de2_fmt = SUN8I_MIXER_FBFMT_BGRA5551,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
+		.drm_fmt = DRM_FORMAT_ARGB2101010,
+		.de2_fmt = SUN8I_MIXER_FBFMT_ARGB2101010,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
+		.drm_fmt = DRM_FORMAT_ABGR2101010,
+		.de2_fmt = SUN8I_MIXER_FBFMT_ABGR2101010,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
+		.drm_fmt = DRM_FORMAT_RGBA1010102,
+		.de2_fmt = SUN8I_MIXER_FBFMT_RGBA1010102,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
+		.drm_fmt = DRM_FORMAT_BGRA1010102,
+		.de2_fmt = SUN8I_MIXER_FBFMT_BGRA1010102,
+		.rgb = true,
+		.csc = SUN8I_CSC_MODE_OFF,
+	},
+	{
 		.drm_fmt = DRM_FORMAT_UYVY,
 		.de2_fmt = SUN8I_MIXER_FBFMT_UYVY,
 		.rgb = false,
@@ -197,12 +277,6 @@ static const struct de2_fmt_info de2_formats[] = {
 		.csc = SUN8I_CSC_MODE_YUV2RGB,
 	},
 	{
-		.drm_fmt = DRM_FORMAT_YUV444,
-		.de2_fmt = SUN8I_MIXER_FBFMT_RGB888,
-		.rgb = true,
-		.csc = SUN8I_CSC_MODE_YUV2RGB,
-	},
-	{
 		.drm_fmt = DRM_FORMAT_YUV422,
 		.de2_fmt = SUN8I_MIXER_FBFMT_YUV422,
 		.rgb = false,
@@ -221,12 +295,6 @@ static const struct de2_fmt_info de2_formats[] = {
 		.csc = SUN8I_CSC_MODE_YUV2RGB,
 	},
 	{
-		.drm_fmt = DRM_FORMAT_YVU444,
-		.de2_fmt = SUN8I_MIXER_FBFMT_RGB888,
-		.rgb = true,
-		.csc = SUN8I_CSC_MODE_YVU2RGB,
-	},
-	{
 		.drm_fmt = DRM_FORMAT_YVU422,
 		.de2_fmt = SUN8I_MIXER_FBFMT_YUV422,
 		.rgb = false,
@@ -244,6 +312,18 @@ static const struct de2_fmt_info de2_formats[] = {
 		.rgb = false,
 		.csc = SUN8I_CSC_MODE_YVU2RGB,
 	},
+	{
+		.drm_fmt = DRM_FORMAT_P010,
+		.de2_fmt = SUN8I_MIXER_FBFMT_P010_YUV,
+		.rgb = false,
+		.csc = SUN8I_CSC_MODE_YUV2RGB,
+	},
+	{
+		.drm_fmt = DRM_FORMAT_P210,
+		.de2_fmt = SUN8I_MIXER_FBFMT_P210_YUV,
+		.rgb = false,
+		.csc = SUN8I_CSC_MODE_YUV2RGB,
+	},
 };
 
 const struct de2_fmt_info *sun8i_mixer_format_info(u32 format)
diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.h b/drivers/gpu/drm/sun4i/sun8i_mixer.h
index c6cc94057faf..345b28b0a80a 100644
--- a/drivers/gpu/drm/sun4i/sun8i_mixer.h
+++ b/drivers/gpu/drm/sun4i/sun8i_mixer.h
@@ -93,6 +93,10 @@
 #define SUN8I_MIXER_FBFMT_ABGR1555	17
 #define SUN8I_MIXER_FBFMT_RGBA5551	18
 #define SUN8I_MIXER_FBFMT_BGRA5551	19
+#define SUN8I_MIXER_FBFMT_ARGB2101010	20
+#define SUN8I_MIXER_FBFMT_ABGR2101010	21
+#define SUN8I_MIXER_FBFMT_RGBA1010102	22
+#define SUN8I_MIXER_FBFMT_BGRA1010102	23
 
 #define SUN8I_MIXER_FBFMT_YUYV		0
 #define SUN8I_MIXER_FBFMT_UYVY		1
@@ -109,6 +113,13 @@
 /* format 12 is semi-planar YUV411 UVUV */
 /* format 13 is semi-planar YUV411 VUVU */
 #define SUN8I_MIXER_FBFMT_YUV411	14
+/* format 15 doesn't exist */
+/* format 16 is P010 YVU */
+#define SUN8I_MIXER_FBFMT_P010_YUV	17
+/* format 18 is P210 YVU */
+#define SUN8I_MIXER_FBFMT_P210_YUV	19
+/* format 20 is packed YVU444 10-bit */
+/* format 21 is packed YUV444 10-bit */
 
 /*
  * Sub-engines listed bellow are unused for now. The EN registers are here only
diff --git a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
index bd0e6a52d1d8..ec4c17a8a498 100644
--- a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
@@ -397,24 +397,66 @@ static const struct drm_plane_funcs sun8i_vi_layer_funcs = {
 };
 
 /*
- * While all RGB formats are supported, VI planes don't support
- * alpha blending, so there is no point having formats with alpha
- * channel if their opaque analog exist.
+ * While DE2 VI layer supports same RGB formats as UI layer, alpha
+ * channel is ignored. This structure lists all unique variants
+ * where alpha channel is replaced with "don't care" (X) channel.
  */
 static const u32 sun8i_vi_layer_formats[] = {
+	DRM_FORMAT_BGR565,
+	DRM_FORMAT_BGR888,
+	DRM_FORMAT_BGRX4444,
+	DRM_FORMAT_BGRX5551,
+	DRM_FORMAT_BGRX8888,
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_RGB888,
+	DRM_FORMAT_RGBX4444,
+	DRM_FORMAT_RGBX5551,
+	DRM_FORMAT_RGBX8888,
+	DRM_FORMAT_XBGR1555,
+	DRM_FORMAT_XBGR4444,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_XRGB1555,
+	DRM_FORMAT_XRGB4444,
+	DRM_FORMAT_XRGB8888,
+
+	DRM_FORMAT_NV16,
+	DRM_FORMAT_NV12,
+	DRM_FORMAT_NV21,
+	DRM_FORMAT_NV61,
+	DRM_FORMAT_UYVY,
+	DRM_FORMAT_VYUY,
+	DRM_FORMAT_YUYV,
+	DRM_FORMAT_YVYU,
+	DRM_FORMAT_YUV411,
+	DRM_FORMAT_YUV420,
+	DRM_FORMAT_YUV422,
+	DRM_FORMAT_YVU411,
+	DRM_FORMAT_YVU420,
+	DRM_FORMAT_YVU422,
+};
+
+static const u32 sun8i_vi_layer_de3_formats[] = {
 	DRM_FORMAT_ABGR1555,
+	DRM_FORMAT_ABGR2101010,
 	DRM_FORMAT_ABGR4444,
+	DRM_FORMAT_ABGR8888,
 	DRM_FORMAT_ARGB1555,
+	DRM_FORMAT_ARGB2101010,
 	DRM_FORMAT_ARGB4444,
+	DRM_FORMAT_ARGB8888,
 	DRM_FORMAT_BGR565,
 	DRM_FORMAT_BGR888,
+	DRM_FORMAT_BGRA1010102,
 	DRM_FORMAT_BGRA5551,
 	DRM_FORMAT_BGRA4444,
+	DRM_FORMAT_BGRA8888,
 	DRM_FORMAT_BGRX8888,
 	DRM_FORMAT_RGB565,
 	DRM_FORMAT_RGB888,
+	DRM_FORMAT_RGBA1010102,
 	DRM_FORMAT_RGBA4444,
 	DRM_FORMAT_RGBA5551,
+	DRM_FORMAT_RGBA8888,
 	DRM_FORMAT_RGBX8888,
 	DRM_FORMAT_XBGR8888,
 	DRM_FORMAT_XRGB8888,
@@ -423,6 +465,8 @@ static const u32 sun8i_vi_layer_formats[] = {
 	DRM_FORMAT_NV12,
 	DRM_FORMAT_NV21,
 	DRM_FORMAT_NV61,
+	DRM_FORMAT_P010,
+	DRM_FORMAT_P210,
 	DRM_FORMAT_UYVY,
 	DRM_FORMAT_VYUY,
 	DRM_FORMAT_YUYV,
@@ -430,30 +474,36 @@ static const u32 sun8i_vi_layer_formats[] = {
 	DRM_FORMAT_YUV411,
 	DRM_FORMAT_YUV420,
 	DRM_FORMAT_YUV422,
-	DRM_FORMAT_YUV444,
 	DRM_FORMAT_YVU411,
 	DRM_FORMAT_YVU420,
 	DRM_FORMAT_YVU422,
-	DRM_FORMAT_YVU444,
 };
 
 struct sun8i_vi_layer *sun8i_vi_layer_init_one(struct drm_device *drm,
 					       struct sun8i_mixer *mixer,
 					       int index)
 {
+	unsigned int plane_cnt, format_count;
 	struct sun8i_vi_layer *layer;
-	unsigned int plane_cnt;
+	const u32 *formats;
 	int ret;
 
 	layer = devm_kzalloc(drm->dev, sizeof(*layer), GFP_KERNEL);
 	if (!layer)
 		return ERR_PTR(-ENOMEM);
 
+	if (mixer->cfg->is_de3) {
+		formats = sun8i_vi_layer_de3_formats;
+		format_count = ARRAY_SIZE(sun8i_vi_layer_de3_formats);
+	} else {
+		formats = sun8i_vi_layer_formats;
+		format_count = ARRAY_SIZE(sun8i_vi_layer_formats);
+	}
+
 	/* possible crtcs are set later */
 	ret = drm_universal_plane_init(drm, &layer->plane, 0,
 				       &sun8i_vi_layer_funcs,
-				       sun8i_vi_layer_formats,
-				       ARRAY_SIZE(sun8i_vi_layer_formats),
+				       formats, format_count,
 				       NULL, DRM_PLANE_TYPE_OVERLAY, NULL);
 	if (ret) {
 		dev_err(drm->dev, "Couldn't initialize layer\n");
diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index ddb802bce0a3..ac0164c6d3f1 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -193,19 +193,19 @@ hub:
 	if (tegra->hub)
 		tegra_display_hub_cleanup(tegra->hub);
 device:
-	host1x_device_exit(device);
-fbdev:
-	drm_kms_helper_poll_fini(drm);
-	tegra_drm_fb_free(drm);
-config:
-	drm_mode_config_cleanup(drm);
-
 	if (tegra->domain) {
 		mutex_destroy(&tegra->mm_lock);
 		drm_mm_takedown(&tegra->mm);
 		put_iova_domain(&tegra->carveout.domain);
 		iova_cache_put();
 	}
+
+	host1x_device_exit(device);
+fbdev:
+	drm_kms_helper_poll_fini(drm);
+	tegra_drm_fb_free(drm);
+config:
+	drm_mode_config_cleanup(drm);
 domain:
 	if (tegra->domain)
 		iommu_domain_free(tegra->domain);
diff --git a/drivers/gpu/drm/tegra/drm.h b/drivers/gpu/drm/tegra/drm.h
index 3844c402ff03..86daa19fcf24 100644
--- a/drivers/gpu/drm/tegra/drm.h
+++ b/drivers/gpu/drm/tegra/drm.h
@@ -124,8 +124,7 @@ struct tegra_output {
 	const struct edid *edid;
 	struct cec_notifier *cec;
 	unsigned int hpd_irq;
-	int hpd_gpio;
-	enum of_gpio_flags hpd_gpio_flags;
+	struct gpio_desc *hpd_gpio;
 
 	struct drm_encoder encoder;
 	struct drm_connector connector;
diff --git a/drivers/gpu/drm/tegra/hub.c b/drivers/gpu/drm/tegra/hub.c
index 92f202ec0577..706a494e1389 100644
--- a/drivers/gpu/drm/tegra/hub.c
+++ b/drivers/gpu/drm/tegra/hub.c
@@ -140,7 +140,9 @@ int tegra_display_hub_prepare(struct tegra_display_hub *hub)
 	for (i = 0; i < hub->soc->num_wgrps; i++) {
 		struct tegra_windowgroup *wgrp = &hub->wgrps[i];
 
-		tegra_windowgroup_enable(wgrp);
+		/* Skip orphaned window group whose parent DC is disabled */
+		if (wgrp->parent)
+			tegra_windowgroup_enable(wgrp);
 	}
 
 	return 0;
@@ -157,7 +159,9 @@ void tegra_display_hub_cleanup(struct tegra_display_hub *hub)
 	for (i = 0; i < hub->soc->num_wgrps; i++) {
 		struct tegra_windowgroup *wgrp = &hub->wgrps[i];
 
-		tegra_windowgroup_disable(wgrp);
+		/* Skip orphaned window group whose parent DC is disabled */
+		if (wgrp->parent)
+			tegra_windowgroup_disable(wgrp);
 	}
 }
 
diff --git a/drivers/gpu/drm/tegra/output.c b/drivers/gpu/drm/tegra/output.c
index 4d450ce8aa86..bdcaa4c7168c 100644
--- a/drivers/gpu/drm/tegra/output.c
+++ b/drivers/gpu/drm/tegra/output.c
@@ -50,18 +50,11 @@ tegra_output_connector_detect(struct drm_connector *connector, bool force)
 	struct tegra_output *output = connector_to_output(connector);
 	enum drm_connector_status status = connector_status_unknown;
 
-	if (gpio_is_valid(output->hpd_gpio)) {
-		if (output->hpd_gpio_flags & OF_GPIO_ACTIVE_LOW) {
-			if (gpio_get_value(output->hpd_gpio) != 0)
-				status = connector_status_disconnected;
-			else
-				status = connector_status_connected;
-		} else {
-			if (gpio_get_value(output->hpd_gpio) == 0)
-				status = connector_status_disconnected;
-			else
-				status = connector_status_connected;
-		}
+	if (output->hpd_gpio) {
+		if (gpiod_get_value(output->hpd_gpio) == 0)
+			status = connector_status_disconnected;
+		else
+			status = connector_status_connected;
 	} else {
 		if (!output->panel)
 			status = connector_status_disconnected;
@@ -99,6 +92,7 @@ static irqreturn_t hpd_irq(int irq, void *data)
 int tegra_output_probe(struct tegra_output *output)
 {
 	struct device_node *ddc, *panel;
+	unsigned long flags;
 	int err, size;
 
 	if (!output->of_node)
@@ -127,23 +121,22 @@ int tegra_output_probe(struct tegra_output *output)
 		of_node_put(ddc);
 	}
 
-	output->hpd_gpio = of_get_named_gpio_flags(output->of_node,
-						   "nvidia,hpd-gpio", 0,
-						   &output->hpd_gpio_flags);
-	if (gpio_is_valid(output->hpd_gpio)) {
-		unsigned long flags;
+	output->hpd_gpio = devm_gpiod_get_from_of_node(output->dev,
+						       output->of_node,
+						       "nvidia,hpd-gpio", 0,
+						       GPIOD_IN,
+						       "HDMI hotplug detect");
+	if (IS_ERR(output->hpd_gpio)) {
+		if (PTR_ERR(output->hpd_gpio) != -ENOENT)
+			return PTR_ERR(output->hpd_gpio);
 
-		err = gpio_request_one(output->hpd_gpio, GPIOF_DIR_IN,
-				       "HDMI hotplug detect");
-		if (err < 0) {
-			dev_err(output->dev, "gpio_request_one(): %d\n", err);
-			return err;
-		}
+		output->hpd_gpio = NULL;
+	}
 
-		err = gpio_to_irq(output->hpd_gpio);
+	if (output->hpd_gpio) {
+		err = gpiod_to_irq(output->hpd_gpio);
 		if (err < 0) {
-			dev_err(output->dev, "gpio_to_irq(): %d\n", err);
-			gpio_free(output->hpd_gpio);
+			dev_err(output->dev, "gpiod_to_irq(): %d\n", err);
 			return err;
 		}
 
@@ -157,7 +150,6 @@ int tegra_output_probe(struct tegra_output *output)
 		if (err < 0) {
 			dev_err(output->dev, "failed to request IRQ#%u: %d\n",
 				output->hpd_irq, err);
-			gpio_free(output->hpd_gpio);
 			return err;
 		}
 
@@ -183,10 +175,8 @@ void tegra_output_remove(struct tegra_output *output)
 	if (output->cec)
 		cec_notifier_put(output->cec);
 
-	if (gpio_is_valid(output->hpd_gpio)) {
+	if (output->hpd_gpio)
 		free_irq(output->hpd_irq, output);
-		gpio_free(output->hpd_gpio);
-	}
 
 	if (output->ddc)
 		put_device(&output->ddc->dev);
@@ -206,7 +196,7 @@ int tegra_output_init(struct drm_device *drm, struct tegra_output *output)
 	 * The connector is now registered and ready to receive hotplug events
 	 * so the hotplug interrupt can be enabled.
 	 */
-	if (gpio_is_valid(output->hpd_gpio))
+	if (output->hpd_gpio)
 		enable_irq(output->hpd_irq);
 
 	return 0;
@@ -218,7 +208,7 @@ void tegra_output_exit(struct tegra_output *output)
 	 * The connector is going away, so the interrupt must be disabled to
 	 * prevent the hotplug interrupt handler from potentially crashing.
 	 */
-	if (gpio_is_valid(output->hpd_gpio))
+	if (output->hpd_gpio)
 		disable_irq(output->hpd_irq);
 
 	if (output->panel)
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_panel.c b/drivers/gpu/drm/tilcdc/tilcdc_panel.c
index 22b100d2e174..199fc2ecbb19 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_panel.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_panel.c
@@ -140,12 +140,16 @@ static int panel_connector_get_modes(struct drm_connector *connector)
 	int i;
 
 	for (i = 0; i < timings->num_timings; i++) {
-		struct drm_display_mode *mode = drm_mode_create(dev);
+		struct drm_display_mode *mode;
 		struct videomode vm;
 
 		if (videomode_from_timings(timings, &vm, i))
 			break;
 
+		mode = drm_mode_create(dev);
+		if (!mode)
+			break;
+
 		drm_display_mode_from_videomode(&vm, mode);
 
 		mode->type = DRM_MODE_TYPE_DRIVER;
diff --git a/drivers/gpu/drm/tinydrm/mipi-dbi.c b/drivers/gpu/drm/tinydrm/mipi-dbi.c
index e33b309ba016..379b3bf31b1d 100644
--- a/drivers/gpu/drm/tinydrm/mipi-dbi.c
+++ b/drivers/gpu/drm/tinydrm/mipi-dbi.c
@@ -362,9 +362,9 @@ static void mipi_dbi_blank(struct mipi_dbi *mipi)
 	memset(mipi->tx_buf, 0, len);
 
 	mipi_dbi_command(mipi, MIPI_DCS_SET_COLUMN_ADDRESS, 0, 0,
-			 (width >> 8) & 0xFF, (width - 1) & 0xFF);
+			 ((width - 1) >> 8) & 0xFF, (width - 1) & 0xFF);
 	mipi_dbi_command(mipi, MIPI_DCS_SET_PAGE_ADDRESS, 0, 0,
-			 (height >> 8) & 0xFF, (height - 1) & 0xFF);
+			 ((height - 1) >> 8) & 0xFF, (height - 1) & 0xFF);
 	mipi_dbi_command_buf(mipi, MIPI_DCS_WRITE_MEMORY_START,
 			     (u8 *)mipi->tx_buf, len);
 
@@ -820,7 +820,7 @@ static int mipi_dbi_spi1_transfer(struct mipi_dbi *mipi, int dc,
 			}
 		}
 
-		tr.len = chunk;
+		tr.len = chunk * 2;
 		len -= chunk;
 
 		tinydrm_dbg_spi_message(spi, &m);
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 2845fceb2fbd..720cc129369e 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -508,8 +508,10 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 
 		reservation_object_unlock(bo->resv);
 	}
-	if (bo->resv != &bo->ttm_resv)
+	if (bo->resv != &bo->ttm_resv) {
+		ttm_bo_flush_all_fences(bo);
 		reservation_object_unlock(&bo->ttm_resv);
+	}
 
 error:
 	kref_get(&bo->list_kref);
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index e3a0691582ff..68cfa25674e5 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -241,7 +241,6 @@ int ttm_tt_init(struct ttm_tt *ttm, struct ttm_buffer_object *bo,
 	ttm_tt_init_fields(ttm, bo, page_flags);
 
 	if (ttm_tt_alloc_page_directory(ttm)) {
-		ttm_tt_destroy(ttm);
 		pr_err("Failed allocating page table\n");
 		return -ENOMEM;
 	}
@@ -265,7 +264,6 @@ int ttm_dma_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_buffer_object *bo,
 
 	INIT_LIST_HEAD(&ttm_dma->pages_list);
 	if (ttm_dma_tt_alloc_page_directory(ttm_dma)) {
-		ttm_tt_destroy(ttm);
 		pr_err("Failed allocating page table\n");
 		return -ENOMEM;
 	}
@@ -287,7 +285,6 @@ int ttm_sg_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_buffer_object *bo,
 	else
 		ret = ttm_dma_tt_alloc_page_directory(ttm_dma);
 	if (ret) {
-		ttm_tt_destroy(ttm);
 		pr_err("Failed allocating page table\n");
 		return -ENOMEM;
 	}
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index 718b26276dbd..152a6ecba1e3 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -672,11 +672,23 @@ static enum drm_mode_status
 vc4_hdmi_encoder_mode_valid(struct drm_encoder *crtc,
 			    const struct drm_display_mode *mode)
 {
-	/* HSM clock must be 108% of the pixel clock.  Additionally,
-	 * the AXI clock needs to be at least 25% of pixel clock, but
-	 * HSM ends up being the limiting factor.
+	/*
+	 * As stated in RPi's vc4 firmware "HDMI state machine (HSM) clock must
+	 * be faster than pixel clock, infinitesimally faster, tested in
+	 * simulation. Otherwise, exact value is unimportant for HDMI
+	 * operation." This conflicts with bcm2835's vc4 documentation, which
+	 * states HSM's clock has to be at least 108% of the pixel clock.
+	 *
+	 * Real life tests reveal that vc4's firmware statement holds up, and
+	 * users are able to use pixel clocks closer to HSM's, namely for
+	 * 1920x1200@60Hz. So it was decided to have leave a 1% margin between
+	 * both clocks. Which, for RPi0-3 implies a maximum pixel clock of
+	 * 162MHz.
+	 *
+	 * Additionally, the AXI clock needs to be at least 25% of
+	 * pixel clock, but HSM ends up being the limiting factor.
 	 */
-	if (mode->clock > HSM_CLOCK_FREQ / (1000 * 108 / 100))
+	if (mode->clock > HSM_CLOCK_FREQ / (1000 * 101 / 100))
 		return MODE_CLOCK_HIGH;
 
 	return MODE_OK;
diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c
index 11a8f99ba18c..19d9ac82b62a 100644
--- a/drivers/gpu/drm/vgem/vgem_drv.c
+++ b/drivers/gpu/drm/vgem/vgem_drv.c
@@ -189,9 +189,10 @@ static struct drm_gem_object *vgem_gem_create(struct drm_device *dev,
 		return ERR_CAST(obj);
 
 	ret = drm_gem_handle_create(file, &obj->base, handle);
-	drm_gem_object_put_unlocked(&obj->base);
-	if (ret)
+	if (ret) {
+		drm_gem_object_put_unlocked(&obj->base);
 		return ERR_PTR(ret);
+	}
 
 	return &obj->base;
 }
@@ -214,7 +215,9 @@ static int vgem_gem_dumb_create(struct drm_file *file, struct drm_device *dev,
 	args->size = gem_object->size;
 	args->pitch = pitch;
 
-	DRM_DEBUG_DRIVER("Created object of size %lld\n", size);
+	drm_gem_object_put_unlocked(gem_object);
+
+	DRM_DEBUG_DRIVER("Created object of size %llu\n", args->size);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c
index 09b526518f5a..8de93ccacaac 100644
--- a/drivers/gpu/drm/virtio/virtgpu_object.c
+++ b/drivers/gpu/drm/virtio/virtgpu_object.c
@@ -23,38 +23,44 @@
  * WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
  */
 
+#include <linux/moduleparam.h>
+
 #include <drm/ttm/ttm_execbuf_util.h>
 
 #include "virtgpu_drv.h"
 
+static int virtio_gpu_virglrenderer_workaround = 1;
+module_param_named(virglhack, virtio_gpu_virglrenderer_workaround, int, 0400);
+
 static int virtio_gpu_resource_id_get(struct virtio_gpu_device *vgdev,
 				       uint32_t *resid)
 {
-#if 0
-	int handle = ida_alloc(&vgdev->resource_ida, GFP_KERNEL);
-
-	if (handle < 0)
-		return handle;
-#else
-	static int handle;
-
-	/*
-	 * FIXME: dirty hack to avoid re-using IDs, virglrenderer
-	 * can't deal with that.  Needs fixing in virglrenderer, also
-	 * should figure a better way to handle that in the guest.
-	 */
-	handle++;
-#endif
-
-	*resid = handle + 1;
+	if (virtio_gpu_virglrenderer_workaround) {
+		/*
+		 * Hack to avoid re-using resource IDs.
+		 *
+		 * virglrenderer versions up to (and including) 0.7.0
+		 * can't deal with that.  virglrenderer commit
+		 * "f91a9dd35715 Fix unlinking resources from hash
+		 * table." (Feb 2019) fixes the bug.
+		 */
+		static atomic_t seqno = ATOMIC_INIT(0);
+		int handle = atomic_inc_return(&seqno);
+		*resid = handle + 1;
+	} else {
+		int handle = ida_alloc(&vgdev->resource_ida, GFP_KERNEL);
+		if (handle < 0)
+			return handle;
+		*resid = handle + 1;
+	}
 	return 0;
 }
 
 static void virtio_gpu_resource_id_put(struct virtio_gpu_device *vgdev, uint32_t id)
 {
-#if 0
-	ida_free(&vgdev->resource_ida, id - 1);
-#endif
+	if (!virtio_gpu_virglrenderer_workaround) {
+		ida_free(&vgdev->resource_ida, id - 1);
+	}
 }
 
 static void virtio_gpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
diff --git a/drivers/gpu/drm/vkms/vkms_drv.h b/drivers/gpu/drm/vkms/vkms_drv.h
index a0adcc86079f..939ebe84a4a9 100644
--- a/drivers/gpu/drm/vkms/vkms_drv.h
+++ b/drivers/gpu/drm/vkms/vkms_drv.h
@@ -121,11 +121,6 @@ struct drm_plane *vkms_plane_init(struct vkms_device *vkmsdev,
 				  enum drm_plane_type type, int index);
 
 /* Gem stuff */
-struct drm_gem_object *vkms_gem_create(struct drm_device *dev,
-				       struct drm_file *file,
-				       u32 *handle,
-				       u64 size);
-
 vm_fault_t vkms_gem_fault(struct vm_fault *vmf);
 
 int vkms_dumb_create(struct drm_file *file, struct drm_device *dev,
diff --git a/drivers/gpu/drm/vkms/vkms_gem.c b/drivers/gpu/drm/vkms/vkms_gem.c
index 69048e73377d..431c401f44c0 100644
--- a/drivers/gpu/drm/vkms/vkms_gem.c
+++ b/drivers/gpu/drm/vkms/vkms_gem.c
@@ -94,10 +94,10 @@ vm_fault_t vkms_gem_fault(struct vm_fault *vmf)
 	return ret;
 }
 
-struct drm_gem_object *vkms_gem_create(struct drm_device *dev,
-				       struct drm_file *file,
-				       u32 *handle,
-				       u64 size)
+static struct drm_gem_object *vkms_gem_create(struct drm_device *dev,
+					      struct drm_file *file,
+					      u32 *handle,
+					      u64 size)
 {
 	struct vkms_gem_object *obj;
 	int ret;
@@ -110,7 +110,6 @@ struct drm_gem_object *vkms_gem_create(struct drm_device *dev,
 		return ERR_CAST(obj);
 
 	ret = drm_gem_handle_create(file, &obj->gem, handle);
-	drm_gem_object_put_unlocked(&obj->gem);
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -139,6 +138,8 @@ int vkms_dumb_create(struct drm_file *file, struct drm_device *dev,
 	args->size = gem_obj->size;
 	args->pitch = pitch;
 
+	drm_gem_object_put_unlocked(gem_obj);
+
 	DRM_DEBUG_DRIVER("Created object of size %lld\n", size);
 
 	return 0;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c
index 4ac55fc2bf97..44d858ce4ce7 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c
@@ -209,8 +209,10 @@ int vmw_cmdbuf_res_add(struct vmw_cmdbuf_res_manager *man,
 
 	cres->hash.key = user_key | (res_type << 24);
 	ret = drm_ht_insert_item(&man->resources, &cres->hash);
-	if (unlikely(ret != 0))
+	if (unlikely(ret != 0)) {
+		kfree(cres);
 		goto out_invalid_key;
+	}
 
 	cres->state = VMW_CMDBUF_RES_ADD;
 	cres->res = vmw_resource_reference(res);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index b97bc8e5944b..e9f7c67a5499 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -2657,7 +2657,7 @@ int vmw_kms_fbdev_init_data(struct vmw_private *dev_priv,
 		++i;
 	}
 
-	if (i != unit) {
+	if (&con->head == &dev_priv->dev->mode_config.connector_list) {
 		DRM_ERROR("Could not find initial display unit.\n");
 		ret = -EINVAL;
 		goto out_unlock;
@@ -2681,13 +2681,13 @@ int vmw_kms_fbdev_init_data(struct vmw_private *dev_priv,
 			break;
 	}
 
-	if (mode->type & DRM_MODE_TYPE_PREFERRED)
-		*p_mode = mode;
-	else {
+	if (&mode->head == &con->modes) {
 		WARN_ONCE(true, "Could not find initial preferred mode.\n");
 		*p_mode = list_first_entry(&con->modes,
 					   struct drm_display_mode,
 					   head);
+	} else {
+		*p_mode = mode;
 	}
 
  out_unlock:
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
index 25e6343bcf21..9fa16361ee2a 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
@@ -79,7 +79,7 @@ static int vmw_ldu_commit_list(struct vmw_private *dev_priv)
 	struct vmw_legacy_display_unit *entry;
 	struct drm_framebuffer *fb = NULL;
 	struct drm_crtc *crtc = NULL;
-	int i = 0;
+	int i;
 
 	/* If there is no display topology the host just assumes
 	 * that the guest will set the same layout as the host.
@@ -90,12 +90,11 @@ static int vmw_ldu_commit_list(struct vmw_private *dev_priv)
 			crtc = &entry->base.crtc;
 			w = max(w, crtc->x + crtc->mode.hdisplay);
 			h = max(h, crtc->y + crtc->mode.vdisplay);
-			i++;
 		}
 
 		if (crtc == NULL)
 			return 0;
-		fb = entry->base.crtc.primary->state->fb;
+		fb = crtc->primary->state->fb;
 
 		return vmw_kms_write_svga(dev_priv, w, h, fb->pitches[0],
 					  fb->format->cpp[0] * 8,
diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c
index 6387302c1245..148af90cefc6 100644
--- a/drivers/gpu/host1x/bus.c
+++ b/drivers/gpu/host1x/bus.c
@@ -656,8 +656,17 @@ EXPORT_SYMBOL(host1x_driver_register_full);
  */
 void host1x_driver_unregister(struct host1x_driver *driver)
 {
+	struct host1x *host1x;
+
 	driver_unregister(&driver->driver);
 
+	mutex_lock(&devices_lock);
+
+	list_for_each_entry(host1x, &devices, list)
+		host1x_detach_driver(host1x, driver);
+
+	mutex_unlock(&devices_lock);
+
 	mutex_lock(&drivers_lock);
 	list_del_init(&driver->list);
 	mutex_unlock(&drivers_lock);
diff --git a/drivers/gpu/host1x/debug.c b/drivers/gpu/host1x/debug.c
index 070b30f72947..277696029f3e 100644
--- a/drivers/gpu/host1x/debug.c
+++ b/drivers/gpu/host1x/debug.c
@@ -16,6 +16,8 @@
 #include "debug.h"
 #include "channel.h"
 
+static DEFINE_MUTEX(debug_lock);
+
 unsigned int host1x_debug_trace_cmdbuf;
 
 static pid_t host1x_debug_force_timeout_pid;
@@ -52,12 +54,14 @@ static int show_channel(struct host1x_channel *ch, void *data, bool show_fifo)
 	struct output *o = data;
 
 	mutex_lock(&ch->cdma.lock);
+	mutex_lock(&debug_lock);
 
 	if (show_fifo)
 		host1x_hw_show_channel_fifo(m, ch, o);
 
 	host1x_hw_show_channel_cdma(m, ch, o);
 
+	mutex_unlock(&debug_lock);
 	mutex_unlock(&ch->cdma.lock);
 
 	return 0;
diff --git a/drivers/gpu/ipu-v3/ipu-image-convert.c b/drivers/gpu/ipu-v3/ipu-image-convert.c
index e744f3527ce1..9d3b965b128e 100644
--- a/drivers/gpu/ipu-v3/ipu-image-convert.c
+++ b/drivers/gpu/ipu-v3/ipu-image-convert.c
@@ -137,6 +137,17 @@ struct ipu_image_convert_ctx;
 struct ipu_image_convert_chan;
 struct ipu_image_convert_priv;
 
+enum eof_irq_mask {
+	EOF_IRQ_IN      = BIT(0),
+	EOF_IRQ_ROT_IN  = BIT(1),
+	EOF_IRQ_OUT     = BIT(2),
+	EOF_IRQ_ROT_OUT = BIT(3),
+};
+
+#define EOF_IRQ_COMPLETE (EOF_IRQ_IN | EOF_IRQ_OUT)
+#define EOF_IRQ_ROT_COMPLETE (EOF_IRQ_IN | EOF_IRQ_OUT |	\
+			      EOF_IRQ_ROT_IN | EOF_IRQ_ROT_OUT)
+
 struct ipu_image_convert_ctx {
 	struct ipu_image_convert_chan *chan;
 
@@ -172,6 +183,9 @@ struct ipu_image_convert_ctx {
 	/* where to place converted tile in dest image */
 	unsigned int out_tile_map[MAX_TILES];
 
+	/* mask of completed EOF irqs at every tile conversion */
+	enum eof_irq_mask eof_mask;
+
 	struct list_head list;
 };
 
@@ -188,6 +202,8 @@ struct ipu_image_convert_chan {
 	struct ipuv3_channel *rotation_out_chan;
 
 	/* the IPU end-of-frame irqs */
+	int in_eof_irq;
+	int rot_in_eof_irq;
 	int out_eof_irq;
 	int rot_out_eof_irq;
 
@@ -1361,6 +1377,9 @@ static int convert_start(struct ipu_image_convert_run *run, unsigned int tile)
 	init_idmac_channel(ctx, chan->in_chan, s_image,
 			   IPU_ROTATE_NONE, false, tile);
 
+	/* clear EOF irq mask */
+	ctx->eof_mask = 0;
+
 	if (ipu_rot_mode_is_irt(ctx->rot_mode)) {
 		/* init the IC PP-->MEM IDMAC channel */
 		init_idmac_channel(ctx, chan->out_chan, d_image,
@@ -1559,7 +1578,7 @@ static bool ic_settings_changed(struct ipu_image_convert_ctx *ctx)
 }
 
 /* hold irqlock when calling */
-static irqreturn_t do_irq(struct ipu_image_convert_run *run)
+static irqreturn_t do_tile_complete(struct ipu_image_convert_run *run)
 {
 	struct ipu_image_convert_ctx *ctx = run->ctx;
 	struct ipu_image_convert_chan *chan = ctx->chan;
@@ -1644,6 +1663,7 @@ static irqreturn_t do_irq(struct ipu_image_convert_run *run)
 		ctx->cur_buf_num ^= 1;
 	}
 
+	ctx->eof_mask = 0; /* clear EOF irq mask for next tile */
 	ctx->next_tile++;
 	return IRQ_HANDLED;
 done:
@@ -1653,13 +1673,15 @@ done:
 	return IRQ_WAKE_THREAD;
 }
 
-static irqreturn_t norotate_irq(int irq, void *data)
+static irqreturn_t eof_irq(int irq, void *data)
 {
 	struct ipu_image_convert_chan *chan = data;
+	struct ipu_image_convert_priv *priv = chan->priv;
 	struct ipu_image_convert_ctx *ctx;
 	struct ipu_image_convert_run *run;
+	irqreturn_t ret = IRQ_HANDLED;
+	bool tile_complete = false;
 	unsigned long flags;
-	irqreturn_t ret;
 
 	spin_lock_irqsave(&chan->irqlock, flags);
 
@@ -1672,46 +1694,33 @@ static irqreturn_t norotate_irq(int irq, void *data)
 
 	ctx = run->ctx;
 
-	if (ipu_rot_mode_is_irt(ctx->rot_mode)) {
-		/* this is a rotation operation, just ignore */
-		spin_unlock_irqrestore(&chan->irqlock, flags);
-		return IRQ_HANDLED;
-	}
-
-	ret = do_irq(run);
-out:
-	spin_unlock_irqrestore(&chan->irqlock, flags);
-	return ret;
-}
-
-static irqreturn_t rotate_irq(int irq, void *data)
-{
-	struct ipu_image_convert_chan *chan = data;
-	struct ipu_image_convert_priv *priv = chan->priv;
-	struct ipu_image_convert_ctx *ctx;
-	struct ipu_image_convert_run *run;
-	unsigned long flags;
-	irqreturn_t ret;
-
-	spin_lock_irqsave(&chan->irqlock, flags);
-
-	/* get current run and its context */
-	run = chan->current_run;
-	if (!run) {
+	if (irq == chan->in_eof_irq) {
+		ctx->eof_mask |= EOF_IRQ_IN;
+	} else if (irq == chan->out_eof_irq) {
+		ctx->eof_mask |= EOF_IRQ_OUT;
+	} else if (irq == chan->rot_in_eof_irq ||
+		   irq == chan->rot_out_eof_irq) {
+		if (!ipu_rot_mode_is_irt(ctx->rot_mode)) {
+			/* this was NOT a rotation op, shouldn't happen */
+			dev_err(priv->ipu->dev,
+				"Unexpected rotation interrupt\n");
+			goto out;
+		}
+		ctx->eof_mask |= (irq == chan->rot_in_eof_irq) ?
+			EOF_IRQ_ROT_IN : EOF_IRQ_ROT_OUT;
+	} else {
+		dev_err(priv->ipu->dev, "Received unknown irq %d\n", irq);
 		ret = IRQ_NONE;
 		goto out;
 	}
 
-	ctx = run->ctx;
-
-	if (!ipu_rot_mode_is_irt(ctx->rot_mode)) {
-		/* this was NOT a rotation operation, shouldn't happen */
-		dev_err(priv->ipu->dev, "Unexpected rotation interrupt\n");
-		spin_unlock_irqrestore(&chan->irqlock, flags);
-		return IRQ_HANDLED;
-	}
+	if (ipu_rot_mode_is_irt(ctx->rot_mode))
+		tile_complete =	(ctx->eof_mask == EOF_IRQ_ROT_COMPLETE);
+	else
+		tile_complete = (ctx->eof_mask == EOF_IRQ_COMPLETE);
 
-	ret = do_irq(run);
+	if (tile_complete)
+		ret = do_tile_complete(run);
 out:
 	spin_unlock_irqrestore(&chan->irqlock, flags);
 	return ret;
@@ -1745,6 +1754,10 @@ static void force_abort(struct ipu_image_convert_ctx *ctx)
 
 static void release_ipu_resources(struct ipu_image_convert_chan *chan)
 {
+	if (chan->in_eof_irq >= 0)
+		free_irq(chan->in_eof_irq, chan);
+	if (chan->rot_in_eof_irq >= 0)
+		free_irq(chan->rot_in_eof_irq, chan);
 	if (chan->out_eof_irq >= 0)
 		free_irq(chan->out_eof_irq, chan);
 	if (chan->rot_out_eof_irq >= 0)
@@ -1763,7 +1776,27 @@ static void release_ipu_resources(struct ipu_image_convert_chan *chan)
 
 	chan->in_chan = chan->out_chan = chan->rotation_in_chan =
 		chan->rotation_out_chan = NULL;
-	chan->out_eof_irq = chan->rot_out_eof_irq = -1;
+	chan->in_eof_irq = -1;
+	chan->rot_in_eof_irq = -1;
+	chan->out_eof_irq = -1;
+	chan->rot_out_eof_irq = -1;
+}
+
+static int get_eof_irq(struct ipu_image_convert_chan *chan,
+		       struct ipuv3_channel *channel)
+{
+	struct ipu_image_convert_priv *priv = chan->priv;
+	int ret, irq;
+
+	irq = ipu_idmac_channel_irq(priv->ipu, channel, IPU_IRQ_EOF);
+
+	ret = request_threaded_irq(irq, eof_irq, do_bh, 0, "ipu-ic", chan);
+	if (ret < 0) {
+		dev_err(priv->ipu->dev, "could not acquire irq %d\n", irq);
+		return ret;
+	}
+
+	return irq;
 }
 
 static int get_ipu_resources(struct ipu_image_convert_chan *chan)
@@ -1799,31 +1832,33 @@ static int get_ipu_resources(struct ipu_image_convert_chan *chan)
 	}
 
 	/* acquire the EOF interrupts */
-	chan->out_eof_irq = ipu_idmac_channel_irq(priv->ipu,
-						  chan->out_chan,
-						  IPU_IRQ_EOF);
+	ret = get_eof_irq(chan, chan->in_chan);
+	if (ret < 0) {
+		chan->in_eof_irq = -1;
+		goto err;
+	}
+	chan->in_eof_irq = ret;
 
-	ret = request_threaded_irq(chan->out_eof_irq, norotate_irq, do_bh,
-				   0, "ipu-ic", chan);
+	ret = get_eof_irq(chan, chan->rotation_in_chan);
 	if (ret < 0) {
-		dev_err(priv->ipu->dev, "could not acquire irq %d\n",
-			 chan->out_eof_irq);
-		chan->out_eof_irq = -1;
+		chan->rot_in_eof_irq = -1;
 		goto err;
 	}
+	chan->rot_in_eof_irq = ret;
 
-	chan->rot_out_eof_irq = ipu_idmac_channel_irq(priv->ipu,
-						     chan->rotation_out_chan,
-						     IPU_IRQ_EOF);
+	ret = get_eof_irq(chan, chan->out_chan);
+	if (ret < 0) {
+		chan->out_eof_irq = -1;
+		goto err;
+	}
+	chan->out_eof_irq = ret;
 
-	ret = request_threaded_irq(chan->rot_out_eof_irq, rotate_irq, do_bh,
-				   0, "ipu-ic", chan);
+	ret = get_eof_irq(chan, chan->rotation_out_chan);
 	if (ret < 0) {
-		dev_err(priv->ipu->dev, "could not acquire irq %d\n",
-			chan->rot_out_eof_irq);
 		chan->rot_out_eof_irq = -1;
 		goto err;
 	}
+	chan->rot_out_eof_irq = ret;
 
 	return 0;
 err:
@@ -2389,6 +2424,8 @@ int ipu_image_convert_init(struct ipu_soc *ipu, struct device *dev)
 		chan->ic_task = i;
 		chan->priv = priv;
 		chan->dma_ch = &image_convert_dma_chan[i];
+		chan->in_eof_irq = -1;
+		chan->rot_in_eof_irq = -1;
 		chan->out_eof_irq = -1;
 		chan->rot_out_eof_irq = -1;
 
diff --git a/drivers/hid/hid-alps.c b/drivers/hid/hid-alps.c
index ae79a7c66737..d33f5abc8f64 100644
--- a/drivers/hid/hid-alps.c
+++ b/drivers/hid/hid-alps.c
@@ -25,6 +25,7 @@
 
 #define U1_MOUSE_REPORT_ID			0x01 /* Mouse data ReportID */
 #define U1_ABSOLUTE_REPORT_ID		0x03 /* Absolute data ReportID */
+#define U1_ABSOLUTE_REPORT_ID_SECD  0x02 /* FW-PTP Absolute data ReportID */
 #define U1_FEATURE_REPORT_ID		0x05 /* Feature ReportID */
 #define U1_SP_ABSOLUTE_REPORT_ID	0x06 /* Feature ReportID */
 
@@ -368,6 +369,7 @@ static int u1_raw_event(struct alps_dev *hdata, u8 *data, int size)
 	case U1_FEATURE_REPORT_ID:
 		break;
 	case U1_ABSOLUTE_REPORT_ID:
+	case U1_ABSOLUTE_REPORT_ID_SECD:
 		for (i = 0; i < hdata->max_fingers; i++) {
 			u8 *contact = &data[i * 5];
 
@@ -730,7 +732,7 @@ static int alps_input_configured(struct hid_device *hdev, struct hid_input *hi)
 	if (data->has_sp) {
 		input2 = input_allocate_device();
 		if (!input2) {
-			input_free_device(input2);
+			ret = -ENOMEM;
 			goto exit;
 		}
 
@@ -802,6 +804,7 @@ static int alps_probe(struct hid_device *hdev, const struct hid_device_id *id)
 		break;
 	case HID_DEVICE_ID_ALPS_U1_DUAL:
 	case HID_DEVICE_ID_ALPS_U1:
+	case HID_DEVICE_ID_ALPS_U1_UNICORN_LEGACY:
 		data->dev_type = U1;
 		break;
 	default:
diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c
index 6ac8becc2372..6909c045fece 100644
--- a/drivers/hid/hid-apple.c
+++ b/drivers/hid/hid-apple.c
@@ -54,6 +54,7 @@ MODULE_PARM_DESC(swap_opt_cmd, "Swap the Option (\"Alt\") and Command (\"Flag\")
 struct apple_sc {
 	unsigned long quirks;
 	unsigned int fn_on;
+	unsigned int fn_found;
 	DECLARE_BITMAP(pressed_numlock, KEY_CNT);
 };
 
@@ -339,11 +340,15 @@ static int apple_input_mapping(struct hid_device *hdev, struct hid_input *hi,
 		struct hid_field *field, struct hid_usage *usage,
 		unsigned long **bit, int *max)
 {
+	struct apple_sc *asc = hid_get_drvdata(hdev);
+
 	if (usage->hid == (HID_UP_CUSTOM | 0x0003) ||
-			usage->hid == (HID_UP_MSVENDOR | 0x0003)) {
+			usage->hid == (HID_UP_MSVENDOR | 0x0003) ||
+			usage->hid == (HID_UP_HPVENDOR2 | 0x0003)) {
 		/* The fn key on Apple USB keyboards */
 		set_bit(EV_REP, hi->input->evbit);
 		hid_map_usage_clear(hi, usage, bit, max, EV_KEY, KEY_FN);
+		asc->fn_found = true;
 		apple_setup_input(hi->input);
 		return 1;
 	}
@@ -370,6 +375,19 @@ static int apple_input_mapped(struct hid_device *hdev, struct hid_input *hi,
 	return 0;
 }
 
+static int apple_input_configured(struct hid_device *hdev,
+		struct hid_input *hidinput)
+{
+	struct apple_sc *asc = hid_get_drvdata(hdev);
+
+	if ((asc->quirks & APPLE_HAS_FN) && !asc->fn_found) {
+		hid_info(hdev, "Fn key not found (Apple Wireless Keyboard clone?), disabling Fn key handling\n");
+		asc->quirks = 0;
+	}
+
+	return 0;
+}
+
 static int apple_probe(struct hid_device *hdev,
 		const struct hid_device_id *id)
 {
@@ -584,6 +602,7 @@ static struct hid_driver apple_driver = {
 	.event = apple_event,
 	.input_mapping = apple_input_mapping,
 	.input_mapped = apple_input_mapped,
+	.input_configured = apple_input_configured,
 };
 module_hid_driver(apple_driver);
 
diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c
index 5b37c570f611..03e92a5db37f 100644
--- a/drivers/hid/hid-asus.c
+++ b/drivers/hid/hid-asus.c
@@ -261,7 +261,8 @@ static int asus_event(struct hid_device *hdev, struct hid_field *field,
 		      struct hid_usage *usage, __s32 value)
 {
 	if ((usage->hid & HID_USAGE_PAGE) == 0xff310000 &&
-	    (usage->hid & HID_USAGE) != 0x00 && !usage->type) {
+	    (usage->hid & HID_USAGE) != 0x00 &&
+	    (usage->hid & HID_USAGE) != 0xff && !usage->type) {
 		hid_warn(hdev, "Unmapped Asus vendor usagepage code 0x%02x\n",
 			 usage->hid & HID_USAGE);
 	}
diff --git a/drivers/hid/hid-bigbenff.c b/drivers/hid/hid-bigbenff.c
index 3f6abd190df4..db6da21ade06 100644
--- a/drivers/hid/hid-bigbenff.c
+++ b/drivers/hid/hid-bigbenff.c
@@ -174,6 +174,7 @@ static __u8 pid0902_rdesc_fixed[] = {
 struct bigben_device {
 	struct hid_device *hid;
 	struct hid_report *report;
+	bool removed;
 	u8 led_state;         /* LED1 = 1 .. LED4 = 8 */
 	u8 right_motor_on;    /* right motor off/on 0/1 */
 	u8 left_motor_force;  /* left motor force 0-255 */
@@ -190,6 +191,9 @@ static void bigben_worker(struct work_struct *work)
 		struct bigben_device, worker);
 	struct hid_field *report_field = bigben->report->field[0];
 
+	if (bigben->removed)
+		return;
+
 	if (bigben->work_led) {
 		bigben->work_led = false;
 		report_field->value[0] = 0x01; /* 1 = led message */
@@ -220,10 +224,16 @@ static void bigben_worker(struct work_struct *work)
 static int hid_bigben_play_effect(struct input_dev *dev, void *data,
 			 struct ff_effect *effect)
 {
-	struct bigben_device *bigben = data;
+	struct hid_device *hid = input_get_drvdata(dev);
+	struct bigben_device *bigben = hid_get_drvdata(hid);
 	u8 right_motor_on;
 	u8 left_motor_force;
 
+	if (!bigben) {
+		hid_err(hid, "no device data\n");
+		return 0;
+	}
+
 	if (effect->type != FF_RUMBLE)
 		return 0;
 
@@ -298,8 +308,8 @@ static void bigben_remove(struct hid_device *hid)
 {
 	struct bigben_device *bigben = hid_get_drvdata(hid);
 
+	bigben->removed = true;
 	cancel_work_sync(&bigben->worker);
-	hid_hw_close(hid);
 	hid_hw_stop(hid);
 }
 
@@ -319,6 +329,7 @@ static int bigben_probe(struct hid_device *hid,
 		return -ENOMEM;
 	hid_set_drvdata(hid, bigben);
 	bigben->hid = hid;
+	bigben->removed = false;
 
 	error = hid_parse(hid);
 	if (error) {
@@ -341,10 +352,10 @@ static int bigben_probe(struct hid_device *hid,
 
 	INIT_WORK(&bigben->worker, bigben_worker);
 
-	error = input_ff_create_memless(hidinput->input, bigben,
+	error = input_ff_create_memless(hidinput->input, NULL,
 		hid_bigben_play_effect);
 	if (error)
-		return error;
+		goto error_hw_stop;
 
 	name_sz = strlen(dev_name(&hid->dev)) + strlen(":red:bigben#") + 1;
 
@@ -354,8 +365,10 @@ static int bigben_probe(struct hid_device *hid,
 			sizeof(struct led_classdev) + name_sz,
 			GFP_KERNEL
 		);
-		if (!led)
-			return -ENOMEM;
+		if (!led) {
+			error = -ENOMEM;
+			goto error_hw_stop;
+		}
 		name = (void *)(&led[1]);
 		snprintf(name, name_sz,
 			"%s:red:bigben%d",
@@ -369,7 +382,7 @@ static int bigben_probe(struct hid_device *hid,
 		bigben->leds[n] = led;
 		error = devm_led_classdev_register(&hid->dev, led);
 		if (error)
-			return error;
+			goto error_hw_stop;
 	}
 
 	/* initial state: LED1 is on, no rumble effect */
@@ -383,6 +396,10 @@ static int bigben_probe(struct hid_device *hid,
 	hid_info(hid, "LED and force feedback support for BigBen gamepad\n");
 
 	return 0;
+
+error_hw_stop:
+	hid_hw_stop(hid);
+	return error;
 }
 
 static __u8 *bigben_report_fixup(struct hid_device *hid, __u8 *rdesc,
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index dea1f9139b5c..ea13f7f10ad5 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -288,6 +288,12 @@ static int hid_add_field(struct hid_parser *parser, unsigned report_type, unsign
 	offset = report->size;
 	report->size += parser->global.report_size * parser->global.report_count;
 
+	/* Total size check: Allow for possible report index byte */
+	if (report->size > (HID_MAX_BUFFER_SIZE - 1) << 3) {
+		hid_err(parser->device, "report is too long\n");
+		return -1;
+	}
+
 	if (!parser->local.usage_index) /* Ignore padding fields */
 		return 0;
 
@@ -1735,7 +1741,9 @@ int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size,
 
 	rsize = ((report->size - 1) >> 3) + 1;
 
-	if (rsize > HID_MAX_BUFFER_SIZE)
+	if (report_enum->numbered && rsize >= HID_MAX_BUFFER_SIZE)
+		rsize = HID_MAX_BUFFER_SIZE - 1;
+	else if (rsize > HID_MAX_BUFFER_SIZE)
 		rsize = HID_MAX_BUFFER_SIZE;
 
 	if (csize < rsize) {
diff --git a/drivers/hid/hid-google-hammer.c b/drivers/hid/hid-google-hammer.c
index 154f1ce771d5..d52112da1f8e 100644
--- a/drivers/hid/hid-google-hammer.c
+++ b/drivers/hid/hid-google-hammer.c
@@ -474,6 +474,8 @@ static const struct hid_device_id hammer_devices[] = {
 	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
 		     USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_MASTERBALL) },
 	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
+		     USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_MOONBALL) },
+	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
 		     USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_STAFF) },
 	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
 		     USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_WAND) },
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index a8af282ef75c..e253e3a7a169 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -79,10 +79,10 @@
 #define HID_DEVICE_ID_ALPS_U1_DUAL_PTP	0x121F
 #define HID_DEVICE_ID_ALPS_U1_DUAL_3BTN_PTP	0x1220
 #define HID_DEVICE_ID_ALPS_U1		0x1215
+#define HID_DEVICE_ID_ALPS_U1_UNICORN_LEGACY         0x121E
 #define HID_DEVICE_ID_ALPS_T4_BTNLESS	0x120C
 #define HID_DEVICE_ID_ALPS_1222		0x1222
 
-
 #define USB_VENDOR_ID_AMI		0x046b
 #define USB_DEVICE_ID_AMI_VIRT_KEYBOARD_AND_MOUSE	0xff10
 
@@ -384,6 +384,7 @@
 #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_7349	0x7349
 #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_73F7	0x73f7
 #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_A001	0xa001
+#define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_C002	0xc002
 
 #define USB_VENDOR_ID_ELAN		0x04f3
 #define USB_DEVICE_ID_TOSHIBA_CLICK_L9W	0x0401
@@ -477,6 +478,7 @@
 #define USB_DEVICE_ID_GOOGLE_WHISKERS	0x5030
 #define USB_DEVICE_ID_GOOGLE_MASTERBALL	0x503c
 #define USB_DEVICE_ID_GOOGLE_MAGNEMITE	0x503d
+#define USB_DEVICE_ID_GOOGLE_MOONBALL	0x5044
 
 #define USB_VENDOR_ID_GOTOP		0x08f2
 #define USB_DEVICE_ID_SUPER_Q2		0x007f
@@ -617,6 +619,7 @@
 #define USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A081	0xa081
 #define USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A0C2	0xa0c2
 #define USB_DEVICE_ID_HOLTEK_ALT_KEYBOARD_A096	0xa096
+#define USB_DEVICE_ID_HOLTEK_ALT_KEYBOARD_A293	0xa293
 
 #define USB_VENDOR_ID_IMATION		0x0718
 #define USB_DEVICE_ID_DISC_STAKKA	0xd000
@@ -630,6 +633,7 @@
 #define USB_VENDOR_ID_ITE               0x048d
 #define USB_DEVICE_ID_ITE_LENOVO_YOGA   0x8386
 #define USB_DEVICE_ID_ITE_LENOVO_YOGA2  0x8350
+#define I2C_DEVICE_ID_ITE_LENOVO_LEGION_Y720	0x837a
 #define USB_DEVICE_ID_ITE_LENOVO_YOGA900	0x8396
 #define USB_DEVICE_ID_ITE8595		0x8595
 
@@ -724,11 +728,13 @@
 #define USB_DEVICE_ID_LENOVO_X1_COVER	0x6085
 #define USB_DEVICE_ID_LENOVO_X1_TAB	0x60a3
 #define USB_DEVICE_ID_LENOVO_X1_TAB3	0x60b5
+#define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_608D	0x608d
 
 #define USB_VENDOR_ID_LG		0x1fd2
 #define USB_DEVICE_ID_LG_MULTITOUCH	0x0064
 #define USB_DEVICE_ID_LG_MELFAS_MT	0x6007
 #define I2C_DEVICE_ID_LG_8001		0x8001
+#define I2C_DEVICE_ID_LG_7010		0x7010
 
 #define USB_VENDOR_ID_LOGITECH		0x046d
 #define USB_DEVICE_ID_LOGITECH_AUDIOHUB 0x0a0e
@@ -987,6 +993,8 @@
 #define USB_DEVICE_ID_ROCCAT_RYOS_MK_PRO	0x3232
 #define USB_DEVICE_ID_ROCCAT_SAVU	0x2d5a
 
+#define USB_VENDOR_ID_SAI		0x17dd
+
 #define USB_VENDOR_ID_SAITEK		0x06a3
 #define USB_DEVICE_ID_SAITEK_RUMBLEPAD	0xff17
 #define USB_DEVICE_ID_SAITEK_PS1000	0x0621
@@ -1081,6 +1089,9 @@
 #define USB_DEVICE_ID_SYMBOL_SCANNER_2	0x1300
 #define USB_DEVICE_ID_SYMBOL_SCANNER_3	0x1200
 
+#define I2C_VENDOR_ID_SYNAPTICS     0x06cb
+#define I2C_PRODUCT_ID_SYNAPTICS_SYNA2393   0x7a13
+
 #define USB_VENDOR_ID_SYNAPTICS		0x06cb
 #define USB_DEVICE_ID_SYNAPTICS_TP	0x0001
 #define USB_DEVICE_ID_SYNAPTICS_INT_TP	0x0002
@@ -1095,6 +1106,8 @@
 #define USB_DEVICE_ID_SYNAPTICS_LTS2	0x1d10
 #define USB_DEVICE_ID_SYNAPTICS_HD	0x0ac3
 #define USB_DEVICE_ID_SYNAPTICS_QUAD_HD	0x1ac3
+#define USB_DEVICE_ID_SYNAPTICS_DELL_K12A	0x2819
+#define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012	0x2968
 #define USB_DEVICE_ID_SYNAPTICS_TP_V103	0x5710
 #define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5	0x81a7
 
@@ -1134,6 +1147,9 @@
 #define USB_DEVICE_ID_TPV_OPTICAL_TOUCHSCREEN_8882	0x8882
 #define USB_DEVICE_ID_TPV_OPTICAL_TOUCHSCREEN_8883	0x8883
 
+#define USB_VENDOR_ID_TRUST             0x145f
+#define USB_DEVICE_ID_TRUST_PANORA_TABLET   0x0212
+
 #define USB_VENDOR_ID_TURBOX		0x062a
 #define USB_DEVICE_ID_TURBOX_KEYBOARD	0x0201
 #define USB_DEVICE_ID_ASUS_MD_5110	0x5110
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 63855f275a38..e8641ce677e4 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -350,13 +350,13 @@ static int hidinput_query_battery_capacity(struct hid_device *dev)
 	u8 *buf;
 	int ret;
 
-	buf = kmalloc(2, GFP_KERNEL);
+	buf = kmalloc(4, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
-	ret = hid_hw_raw_request(dev, dev->battery_report_id, buf, 2,
+	ret = hid_hw_raw_request(dev, dev->battery_report_id, buf, 4,
 				 dev->battery_report_type, HID_REQ_GET_REPORT);
-	if (ret != 2) {
+	if (ret < 2) {
 		kfree(buf);
 		return -ENODATA;
 	}
@@ -1132,9 +1132,15 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel
 	}
 
 mapped:
-	if (device->driver->input_mapped && device->driver->input_mapped(device,
-				hidinput, field, usage, &bit, &max) < 0)
-		goto ignore;
+	if (device->driver->input_mapped &&
+	    device->driver->input_mapped(device, hidinput, field, usage,
+					 &bit, &max) < 0) {
+		/*
+		 * The driver indicated that no further generic handling
+		 * of the usage is desired.
+		 */
+		return;
+	}
 
 	set_bit(usage->type, input->evbit);
 
@@ -1215,9 +1221,11 @@ mapped:
 		set_bit(MSC_SCAN, input->mscbit);
 	}
 
-ignore:
 	return;
 
+ignore:
+	usage->type = 0;
+	usage->code = 0;
 }
 
 static void hidinput_handle_scroll(struct hid_usage *usage,
diff --git a/drivers/hid/hid-ite.c b/drivers/hid/hid-ite.c
index a45f2352618d..6c55682c5974 100644
--- a/drivers/hid/hid-ite.c
+++ b/drivers/hid/hid-ite.c
@@ -40,6 +40,10 @@ static int ite_event(struct hid_device *hdev, struct hid_field *field,
 static const struct hid_device_id ite_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ITE, USB_DEVICE_ID_ITE8595) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_258A, USB_DEVICE_ID_258A_6A88) },
+	/* ITE8595 USB kbd ctlr, with Synaptics touchpad connected to it. */
+	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
+		     USB_VENDOR_ID_SYNAPTICS,
+		     USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012) },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, ite_devices);
diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c
index 0af0fb304c0c..09ee227b1a35 100644
--- a/drivers/hid/hid-logitech-dj.c
+++ b/drivers/hid/hid-logitech-dj.c
@@ -1123,7 +1123,7 @@ static int logi_dj_recv_query_hidpp_devices(struct dj_receiver_dev *djrcv_dev)
 				    HID_REQ_SET_REPORT);
 
 	kfree(hidpp_report);
-	return 0;
+	return (retval < 0) ? retval : 0;
 }
 
 static int logi_dj_recv_query_paired_devices(struct dj_receiver_dev *djrcv_dev)
diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c
index f97913974983..e994403f7650 100644
--- a/drivers/hid/hid-logitech-hidpp.c
+++ b/drivers/hid/hid-logitech-hidpp.c
@@ -2964,7 +2964,7 @@ static int hi_res_scroll_enable(struct hidpp_device *hidpp)
 		multiplier = 1;
 
 	hidpp->vertical_wheel_counter.wheel_multiplier = multiplier;
-	hid_info(hidpp->hid_dev, "multiplier = %d\n", multiplier);
+	hid_dbg(hidpp->hid_dev, "wheel multiplier = %d\n", multiplier);
 	return 0;
 }
 
diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c
index 34138667f8af..abd86903875f 100644
--- a/drivers/hid/hid-magicmouse.c
+++ b/drivers/hid/hid-magicmouse.c
@@ -535,6 +535,12 @@ static int magicmouse_setup_input(struct input_dev *input, struct hid_device *hd
 		__set_bit(MSC_RAW, input->mscbit);
 	}
 
+	/*
+	 * hid-input may mark device as using autorepeat, but neither
+	 * the trackpad, nor the mouse actually want it.
+	 */
+	__clear_bit(EV_REP, input->evbit);
+
 	return 0;
 }
 
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index b603c14d043b..95ed0adb6c25 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -68,6 +68,8 @@ MODULE_LICENSE("GPL");
 #define MT_QUIRK_STICKY_FINGERS		BIT(16)
 #define MT_QUIRK_ASUS_CUSTOM_UP		BIT(17)
 #define MT_QUIRK_WIN8_PTP_BUTTONS	BIT(18)
+#define MT_QUIRK_SEPARATE_APP_REPORT	BIT(19)
+#define MT_QUIRK_FORCE_MULTI_INPUT	BIT(20)
 
 #define MT_INPUTMODE_TOUCHSCREEN	0x02
 #define MT_INPUTMODE_TOUCHPAD		0x03
@@ -103,6 +105,7 @@ struct mt_usages {
 struct mt_application {
 	struct list_head list;
 	unsigned int application;
+	unsigned int report_id;
 	struct list_head mt_usages;	/* mt usages list */
 
 	__s32 quirks;
@@ -187,6 +190,7 @@ static void mt_post_parse(struct mt_device *td, struct mt_application *app);
 #define MT_CLS_WIN_8				0x0012
 #define MT_CLS_EXPORT_ALL_INPUTS		0x0013
 #define MT_CLS_WIN_8_DUAL			0x0014
+#define MT_CLS_WIN_8_FORCE_MULTI_INPUT		0x0015
 
 /* vendor specific classes */
 #define MT_CLS_3M				0x0101
@@ -203,6 +207,7 @@ static void mt_post_parse(struct mt_device *td, struct mt_application *app);
 #define MT_CLS_VTL				0x0110
 #define MT_CLS_GOOGLE				0x0111
 #define MT_CLS_RAZER_BLADE_STEALTH		0x0112
+#define MT_CLS_SMART_TECH			0x0113
 
 #define MT_DEFAULT_MAXCONTACT	10
 #define MT_MAX_MAXCONTACT	250
@@ -275,6 +280,15 @@ static const struct mt_class mt_classes[] = {
 			MT_QUIRK_CONTACT_CNT_ACCURATE |
 			MT_QUIRK_WIN8_PTP_BUTTONS,
 		.export_all_inputs = true },
+	{ .name = MT_CLS_WIN_8_FORCE_MULTI_INPUT,
+		.quirks = MT_QUIRK_ALWAYS_VALID |
+			MT_QUIRK_IGNORE_DUPLICATES |
+			MT_QUIRK_HOVERING |
+			MT_QUIRK_CONTACT_CNT_ACCURATE |
+			MT_QUIRK_STICKY_FINGERS |
+			MT_QUIRK_WIN8_PTP_BUTTONS |
+			MT_QUIRK_FORCE_MULTI_INPUT,
+		.export_all_inputs = true },
 
 	/*
 	 * vendor specific classes
@@ -353,6 +367,12 @@ static const struct mt_class mt_classes[] = {
 			MT_QUIRK_CONTACT_CNT_ACCURATE |
 			MT_QUIRK_WIN8_PTP_BUTTONS,
 	},
+	{ .name = MT_CLS_SMART_TECH,
+		.quirks = MT_QUIRK_ALWAYS_VALID |
+			MT_QUIRK_IGNORE_DUPLICATES |
+			MT_QUIRK_CONTACT_CNT_ACCURATE |
+			MT_QUIRK_SEPARATE_APP_REPORT,
+	},
 	{ }
 };
 
@@ -509,8 +529,9 @@ static struct mt_usages *mt_allocate_usage(struct hid_device *hdev,
 }
 
 static struct mt_application *mt_allocate_application(struct mt_device *td,
-						      unsigned int application)
+						      struct hid_report *report)
 {
+	unsigned int application = report->application;
 	struct mt_application *mt_application;
 
 	mt_application = devm_kzalloc(&td->hdev->dev, sizeof(*mt_application),
@@ -535,6 +556,7 @@ static struct mt_application *mt_allocate_application(struct mt_device *td,
 	mt_application->scantime = DEFAULT_ZERO;
 	mt_application->raw_cc = DEFAULT_ZERO;
 	mt_application->quirks = td->mtclass.quirks;
+	mt_application->report_id = report->id;
 
 	list_add_tail(&mt_application->list, &td->applications);
 
@@ -542,19 +564,23 @@ static struct mt_application *mt_allocate_application(struct mt_device *td,
 }
 
 static struct mt_application *mt_find_application(struct mt_device *td,
-						  unsigned int application)
+						  struct hid_report *report)
 {
+	unsigned int application = report->application;
 	struct mt_application *tmp, *mt_application = NULL;
 
 	list_for_each_entry(tmp, &td->applications, list) {
 		if (application == tmp->application) {
-			mt_application = tmp;
-			break;
+			if (!(td->mtclass.quirks & MT_QUIRK_SEPARATE_APP_REPORT) ||
+			    tmp->report_id == report->id) {
+				mt_application = tmp;
+				break;
+			}
 		}
 	}
 
 	if (!mt_application)
-		mt_application = mt_allocate_application(td, application);
+		mt_application = mt_allocate_application(td, report);
 
 	return mt_application;
 }
@@ -571,7 +597,7 @@ static struct mt_report_data *mt_allocate_report_data(struct mt_device *td,
 		return NULL;
 
 	rdata->report = report;
-	rdata->application = mt_find_application(td, report->application);
+	rdata->application = mt_find_application(td, report);
 
 	if (!rdata->application) {
 		devm_kfree(&td->hdev->dev, rdata);
@@ -1003,7 +1029,7 @@ static int mt_process_slot(struct mt_device *td, struct input_dev *input,
 		tool = MT_TOOL_DIAL;
 	else if (unlikely(!confidence_state)) {
 		tool = MT_TOOL_PALM;
-		if (!active &&
+		if (!active && mt &&
 		    input_mt_is_active(&mt->slots[slotnum])) {
 			/*
 			 * The non-confidence was reported for
@@ -1561,6 +1587,9 @@ static int mt_input_configured(struct hid_device *hdev, struct hid_input *hi)
 	case HID_VD_ASUS_CUSTOM_MEDIA_KEYS:
 		suffix = "Custom Media Keys";
 		break;
+	case HID_DG_PEN:
+		suffix = "Stylus";
+		break;
 	default:
 		suffix = "UNKNOWN";
 		break;
@@ -1695,6 +1724,11 @@ static int mt_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	if (id->group != HID_GROUP_MULTITOUCH_WIN_8)
 		hdev->quirks |= HID_QUIRK_MULTI_INPUT;
 
+	if (mtclass->quirks & MT_QUIRK_FORCE_MULTI_INPUT) {
+		hdev->quirks &= ~HID_QUIRK_INPUT_PER_APP;
+		hdev->quirks |= HID_QUIRK_MULTI_INPUT;
+	}
+
 	timer_setup(&td->release_timer, mt_expired_timeout, 0);
 
 	ret = hid_parse(hdev);
@@ -1903,6 +1937,14 @@ static const struct hid_device_id mt_devices[] = {
 	{ .driver_data = MT_CLS_EGALAX_SERIAL,
 		MT_USB_DEVICE(USB_VENDOR_ID_DWAV,
 			USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_A001) },
+	{ .driver_data = MT_CLS_EGALAX,
+		MT_USB_DEVICE(USB_VENDOR_ID_DWAV,
+			USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_C002) },
+
+	/* Elan devices */
+	{ .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT,
+		HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8,
+			USB_VENDOR_ID_ELAN, 0x313a) },
 
 	/* Elitegroup panel */
 	{ .driver_data = MT_CLS_SERIAL,
@@ -1966,6 +2008,9 @@ static const struct hid_device_id mt_devices[] = {
 	{ .driver_data = MT_CLS_LG,
 		HID_USB_DEVICE(USB_VENDOR_ID_LG,
 			USB_DEVICE_ID_LG_MELFAS_MT) },
+	{ .driver_data = MT_CLS_LG,
+		HID_DEVICE(BUS_I2C, HID_GROUP_GENERIC,
+			USB_VENDOR_ID_LG, I2C_DEVICE_ID_LG_7010) },
 
 	/* MosArt panels */
 	{ .driver_data = MT_CLS_CONFIDENCE_MINUS_ONE,
@@ -2022,11 +2067,20 @@ static const struct hid_device_id mt_devices[] = {
 		HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8,
 			USB_VENDOR_ID_SYNAPTICS, 0x8323) },
 
+	/* Smart Tech panels */
+	{ .driver_data = MT_CLS_SMART_TECH,
+		MT_USB_DEVICE(0x0b8c, 0x0092)},
+
 	/* Stantum panels */
 	{ .driver_data = MT_CLS_CONFIDENCE,
 		MT_USB_DEVICE(USB_VENDOR_ID_STANTUM_STM,
 			USB_DEVICE_ID_MTP_STM)},
 
+	/* Synaptics devices */
+	{ .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT,
+		HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8,
+			USB_VENDOR_ID_SYNAPTICS, 0xce08) },
+
 	/* TopSeed panels */
 	{ .driver_data = MT_CLS_TOPSEED,
 		MT_USB_DEVICE(USB_VENDOR_ID_TOPSEED2,
diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c
index 3b64e297bfc9..affcd54c08e0 100644
--- a/drivers/hid/hid-quirks.c
+++ b/drivers/hid/hid-quirks.c
@@ -87,6 +87,7 @@ static const struct hid_device_id hid_quirks[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_HAPP, USB_DEVICE_ID_UGCI_FIGHTING), HID_QUIRK_BADPAD | HID_QUIRK_MULTI_INPUT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_HAPP, USB_DEVICE_ID_UGCI_FLYING), HID_QUIRK_BADPAD | HID_QUIRK_MULTI_INPUT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_KEYBOARD_A096), HID_QUIRK_NO_INIT_REPORTS },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_KEYBOARD_A293), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_LOGITECH_OEM_USB_OPTICAL_MOUSE_0A4A), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_LOGITECH_OEM_USB_OPTICAL_MOUSE_0B4A), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE), HID_QUIRK_ALWAYS_POLL },
@@ -102,6 +103,7 @@ static const struct hid_device_id hid_quirks[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_PENSKETCH_M912), HID_QUIRK_MULTI_INPUT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M406XE), HID_QUIRK_MULTI_INPUT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_PIXART_USB_OPTICAL_MOUSE_ID2), HID_QUIRK_ALWAYS_POLL },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_608D), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_C007), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_C077), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_KEYBOARD_G710_PLUS), HID_QUIRK_NOGET },
@@ -161,10 +163,12 @@ static const struct hid_device_id hid_quirks[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_LTS2), HID_QUIRK_NO_INIT_REPORTS },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_QUAD_HD), HID_QUIRK_NO_INIT_REPORTS },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_TP_V103), HID_QUIRK_NO_INIT_REPORTS },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_DELL_K12A), HID_QUIRK_NO_INIT_REPORTS },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_TOPMAX, USB_DEVICE_ID_TOPMAX_COBRAPAD), HID_QUIRK_BADPAD },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_TOUCHPACK, USB_DEVICE_ID_TOUCHPACK_RTS), HID_QUIRK_MULTI_INPUT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_TPV, USB_DEVICE_ID_TPV_OPTICAL_TOUCHSCREEN_8882), HID_QUIRK_NOGET },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_TPV, USB_DEVICE_ID_TPV_OPTICAL_TOUCHSCREEN_8883), HID_QUIRK_NOGET },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_TRUST, USB_DEVICE_ID_TRUST_PANORA_TABLET), HID_QUIRK_MULTI_INPUT | HID_QUIRK_HIDINPUT_FORCE },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_TURBOX, USB_DEVICE_ID_TURBOX_KEYBOARD), HID_QUIRK_NOGET },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UCLOGIC_TABLET_KNA5), HID_QUIRK_MULTI_INPUT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UCLOGIC_TABLET_TWA60), HID_QUIRK_MULTI_INPUT },
@@ -173,6 +177,7 @@ static const struct hid_device_id hid_quirks[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WALTOP, USB_DEVICE_ID_WALTOP_SIRIUS_BATTERY_FREE_TABLET), HID_QUIRK_MULTI_INPUT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP_LTD2, USB_DEVICE_ID_SMARTJOY_DUAL_PLUS), HID_QUIRK_NOGET | HID_QUIRK_MULTI_INPUT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP, USB_DEVICE_ID_QUAD_USB_JOYPAD), HID_QUIRK_NOGET | HID_QUIRK_MULTI_INPUT },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_XIN_MO, USB_DEVICE_ID_XIN_MO_DUAL_ARCADE), HID_QUIRK_MULTI_INPUT },
 
 	{ 0 }
 };
@@ -395,9 +400,6 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A081) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A0C2) },
 #endif
-#if IS_ENABLED(CONFIG_HID_ITE)
-	{ HID_USB_DEVICE(USB_VENDOR_ID_ITE, USB_DEVICE_ID_ITE8595) },
-#endif
 #if IS_ENABLED(CONFIG_HID_ICADE)
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ION, USB_DEVICE_ID_ICADE) },
 #endif
@@ -837,6 +839,7 @@ static const struct hid_device_id hid_ignore_list[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_PETZL, USB_DEVICE_ID_PETZL_HEADLAMP) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_PHILIPS, USB_DEVICE_ID_PHILIPS_IEEE802154_DONGLE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_POWERCOM, USB_DEVICE_ID_POWERCOM_UPS) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_SAI, USB_DEVICE_ID_CYPRESS_HIDCOM) },
 #if IS_ENABLED(CONFIG_MOUSE_SYNAPTICS_USB)
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_TP) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_INT_TP) },
diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c
index 4c6ed6ef31f1..2f073f536070 100644
--- a/drivers/hid/hid-sony.c
+++ b/drivers/hid/hid-sony.c
@@ -867,6 +867,23 @@ static u8 *sony_report_fixup(struct hid_device *hdev, u8 *rdesc,
 	if (sc->quirks & PS3REMOTE)
 		return ps3remote_fixup(hdev, rdesc, rsize);
 
+	/*
+	 * Some knock-off USB dongles incorrectly report their button count
+	 * as 13 instead of 16 causing three non-functional buttons.
+	 */
+	if ((sc->quirks & SIXAXIS_CONTROLLER_USB) && *rsize >= 45 &&
+		/* Report Count (13) */
+		rdesc[23] == 0x95 && rdesc[24] == 0x0D &&
+		/* Usage Maximum (13) */
+		rdesc[37] == 0x29 && rdesc[38] == 0x0D &&
+		/* Report Count (3) */
+		rdesc[43] == 0x95 && rdesc[44] == 0x03) {
+		hid_info(hdev, "Fixing up USB dongle report descriptor\n");
+		rdesc[24] = 0x10;
+		rdesc[38] = 0x10;
+		rdesc[44] = 0x00;
+	}
+
 	return rdesc;
 }
 
diff --git a/drivers/hid/hid-steam.c b/drivers/hid/hid-steam.c
index 8dae0f9b819e..a3b151b29bd7 100644
--- a/drivers/hid/hid-steam.c
+++ b/drivers/hid/hid-steam.c
@@ -526,7 +526,8 @@ static int steam_register(struct steam_device *steam)
 			steam_battery_register(steam);
 
 		mutex_lock(&steam_devices_lock);
-		list_add(&steam->list, &steam_devices);
+		if (list_empty(&steam->list))
+			list_add(&steam->list, &steam_devices);
 		mutex_unlock(&steam_devices_lock);
 	}
 
@@ -552,7 +553,7 @@ static void steam_unregister(struct steam_device *steam)
 		hid_info(steam->hdev, "Steam Controller '%s' disconnected",
 				steam->serial_no);
 		mutex_lock(&steam_devices_lock);
-		list_del(&steam->list);
+		list_del_init(&steam->list);
 		mutex_unlock(&steam_devices_lock);
 		steam->serial_no[0] = 0;
 	}
@@ -738,6 +739,7 @@ static int steam_probe(struct hid_device *hdev,
 	mutex_init(&steam->mutex);
 	steam->quirks = id->driver_data;
 	INIT_WORK(&steam->work_connect, steam_work_connect_cb);
+	INIT_LIST_HEAD(&steam->list);
 
 	steam->client_hdev = steam_create_client_hid(hdev);
 	if (IS_ERR(steam->client_hdev)) {
@@ -768,8 +770,12 @@ static int steam_probe(struct hid_device *hdev,
 
 	if (steam->quirks & STEAM_QUIRK_WIRELESS) {
 		hid_info(hdev, "Steam wireless receiver connected");
+		/* If using a wireless adaptor ask for connection status */
+		steam->connected = false;
 		steam_request_conn_status(steam);
 	} else {
+		/* A wired connection is always present */
+		steam->connected = true;
 		ret = steam_register(steam);
 		if (ret) {
 			hid_err(hdev,
diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c
index 62ef47a730b0..b382c6bf2c5c 100644
--- a/drivers/hid/hidraw.c
+++ b/drivers/hid/hidraw.c
@@ -249,13 +249,14 @@ out:
 static __poll_t hidraw_poll(struct file *file, poll_table *wait)
 {
 	struct hidraw_list *list = file->private_data;
+	__poll_t mask = EPOLLOUT | EPOLLWRNORM; /* hidraw is always writable */
 
 	poll_wait(file, &list->hidraw->wait, wait);
 	if (list->head != list->tail)
-		return EPOLLIN | EPOLLRDNORM;
+		mask |= EPOLLIN | EPOLLRDNORM;
 	if (!list->hidraw->exist)
-		return EPOLLERR | EPOLLHUP;
-	return 0;
+		mask |= EPOLLERR | EPOLLHUP;
+	return mask;
 }
 
 static int hidraw_open(struct inode *inode, struct file *file)
diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c
index 7df445a6da1f..9ebb0881f7d6 100644
--- a/drivers/hid/i2c-hid/i2c-hid-core.c
+++ b/drivers/hid/i2c-hid/i2c-hid-core.c
@@ -51,6 +51,9 @@
 #define I2C_HID_QUIRK_NO_RUNTIME_PM		BIT(2)
 #define I2C_HID_QUIRK_DELAY_AFTER_SLEEP		BIT(3)
 #define I2C_HID_QUIRK_BOGUS_IRQ			BIT(4)
+#define I2C_HID_QUIRK_RESET_ON_RESUME		BIT(5)
+#define I2C_HID_QUIRK_BAD_INPUT_SIZE		BIT(6)
+
 
 /* flags */
 #define I2C_HID_STARTED		0
@@ -186,6 +189,12 @@ static const struct i2c_hid_quirks {
 		I2C_HID_QUIRK_NO_IRQ_AFTER_RESET },
 	{ USB_VENDOR_ID_ELAN, HID_ANY_ID,
 		 I2C_HID_QUIRK_BOGUS_IRQ },
+	{ USB_VENDOR_ID_ALPS_JP, HID_ANY_ID,
+		 I2C_HID_QUIRK_RESET_ON_RESUME },
+	{ I2C_VENDOR_ID_SYNAPTICS, I2C_PRODUCT_ID_SYNAPTICS_SYNA2393,
+		 I2C_HID_QUIRK_RESET_ON_RESUME },
+	{ USB_VENDOR_ID_ITE, I2C_DEVICE_ID_ITE_LENOVO_LEGION_Y720,
+		I2C_HID_QUIRK_BAD_INPUT_SIZE },
 	{ 0, 0 }
 };
 
@@ -517,9 +526,15 @@ static void i2c_hid_get_input(struct i2c_hid *ihid)
 	}
 
 	if ((ret_size > size) || (ret_size < 2)) {
-		dev_err(&ihid->client->dev, "%s: incomplete report (%d/%d)\n",
-			__func__, size, ret_size);
-		return;
+		if (ihid->quirks & I2C_HID_QUIRK_BAD_INPUT_SIZE) {
+			ihid->inbuf[0] = size & 0xff;
+			ihid->inbuf[1] = size >> 8;
+			ret_size = size;
+		} else {
+			dev_err(&ihid->client->dev, "%s: incomplete report (%d/%d)\n",
+				__func__, size, ret_size);
+			return;
+		}
 	}
 
 	i2c_hid_dbg(ihid, "input: %*ph\n", ret_size, ihid->inbuf);
@@ -1294,8 +1309,15 @@ static int i2c_hid_resume(struct device *dev)
 	 * solves "incomplete reports" on Raydium devices 2386:3118 and
 	 * 2386:4B33 and fixes various SIS touchscreens no longer sending
 	 * data after a suspend/resume.
+	 *
+	 * However some ALPS touchpads generate IRQ storm without reset, so
+	 * let's still reset them here.
 	 */
-	ret = i2c_hid_set_power(client, I2C_HID_PWR_ON);
+	if (ihid->quirks & I2C_HID_QUIRK_RESET_ON_RESUME)
+		ret = i2c_hid_hwreset(client);
+	else
+		ret = i2c_hid_set_power(client, I2C_HID_PWR_ON);
+
 	if (ret)
 		return ret;
 
diff --git a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c
index d31ea82b84c1..35f3bfc3e6f5 100644
--- a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c
+++ b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c
@@ -342,6 +342,14 @@ static const struct dmi_system_id i2c_hid_dmi_desc_override_table[] = {
 		.driver_data = (void *)&sipodev_desc
 	},
 	{
+		.ident = "Trekstor SURFBOOK E11B",
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "TREKSTOR"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "SURFBOOK E11B"),
+		},
+		.driver_data = (void *)&sipodev_desc
+	},
+	{
 		.ident = "Direkt-Tek DTLAPY116-2",
 		.matches = {
 			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Direkt-Tek"),
@@ -366,6 +374,14 @@ static const struct dmi_system_id i2c_hid_dmi_desc_override_table[] = {
 		.driver_data = (void *)&sipodev_desc
 	},
 	{
+		.ident = "Mediacom FlexBook edge 13",
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "MEDIACOM"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "FlexBook_edge13-M-FBE13"),
+		},
+		.driver_data = (void *)&sipodev_desc
+	},
+	{
 		.ident = "Odys Winbook 13",
 		.matches = {
 			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "AXDIA International GmbH"),
@@ -381,6 +397,14 @@ static const struct dmi_system_id i2c_hid_dmi_desc_override_table[] = {
 		},
 		.driver_data = (void *)&sipodev_desc
 	},
+	{
+		.ident = "Schneider SCL142ALM",
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "SCHNEIDER"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "SCL142ALM"),
+		},
+		.driver_data = (void *)&sipodev_desc
+	},
 	{ }	/* Terminate list */
 };
 
diff --git a/drivers/hid/intel-ish-hid/ipc/hw-ish.h b/drivers/hid/intel-ish-hid/ipc/hw-ish.h
index 5792a104000a..a576a9428e43 100644
--- a/drivers/hid/intel-ish-hid/ipc/hw-ish.h
+++ b/drivers/hid/intel-ish-hid/ipc/hw-ish.h
@@ -24,7 +24,9 @@
 #define ICL_MOBILE_DEVICE_ID	0x34FC
 #define SPT_H_DEVICE_ID		0xA135
 #define CML_LP_DEVICE_ID	0x02FC
+#define CMP_H_DEVICE_ID		0x06FC
 #define EHL_Ax_DEVICE_ID	0x4BB3
+#define TGL_LP_DEVICE_ID	0xA0FC
 
 #define	REVISION_ID_CHT_A0	0x6
 #define	REVISION_ID_CHT_Ax_SI	0x0
diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
index 8cce3cfe28e0..e4929facc12a 100644
--- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c
+++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
@@ -33,7 +33,9 @@ static const struct pci_device_id ish_pci_tbl[] = {
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, ICL_MOBILE_DEVICE_ID)},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, SPT_H_DEVICE_ID)},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, CML_LP_DEVICE_ID)},
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, CMP_H_DEVICE_ID)},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, EHL_Ax_DEVICE_ID)},
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, TGL_LP_DEVICE_ID)},
 	{0, }
 };
 MODULE_DEVICE_TABLE(pci, ish_pci_tbl);
diff --git a/drivers/hid/intel-ish-hid/ishtp-fw-loader.c b/drivers/hid/intel-ish-hid/ishtp-fw-loader.c
index aa2dbed30fc3..6cf59fd26ad7 100644
--- a/drivers/hid/intel-ish-hid/ishtp-fw-loader.c
+++ b/drivers/hid/intel-ish-hid/ishtp-fw-loader.c
@@ -480,6 +480,7 @@ static int ish_query_loader_prop(struct ishtp_cl_data *client_data,
 			    sizeof(ldr_xfer_query_resp));
 	if (rv < 0) {
 		client_data->flag_retry = true;
+		*fw_info = (struct shim_fw_info){};
 		return rv;
 	}
 
@@ -489,6 +490,7 @@ static int ish_query_loader_prop(struct ishtp_cl_data *client_data,
 			"data size %d is not equal to size of loader_xfer_query_response %zu\n",
 			rv, sizeof(struct loader_xfer_query_response));
 		client_data->flag_retry = true;
+		*fw_info = (struct shim_fw_info){};
 		return -EMSGSIZE;
 	}
 
diff --git a/drivers/hid/uhid.c b/drivers/hid/uhid.c
index fa0cc0899827..8fe3efcb8327 100644
--- a/drivers/hid/uhid.c
+++ b/drivers/hid/uhid.c
@@ -766,13 +766,14 @@ unlock:
 static __poll_t uhid_char_poll(struct file *file, poll_table *wait)
 {
 	struct uhid_device *uhid = file->private_data;
+	__poll_t mask = EPOLLOUT | EPOLLWRNORM; /* uhid is always writable */
 
 	poll_wait(file, &uhid->waitq, wait);
 
 	if (uhid->head != uhid->tail)
-		return EPOLLIN | EPOLLRDNORM;
+		mask |= EPOLLIN | EPOLLRDNORM;
 
-	return 0;
+	return mask;
 }
 
 static const struct file_operations uhid_fops = {
diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
index c7bc9db5b192..17a638f15082 100644
--- a/drivers/hid/usbhid/hid-core.c
+++ b/drivers/hid/usbhid/hid-core.c
@@ -682,16 +682,21 @@ static int usbhid_open(struct hid_device *hid)
 	struct usbhid_device *usbhid = hid->driver_data;
 	int res;
 
+	mutex_lock(&usbhid->mutex);
+
 	set_bit(HID_OPENED, &usbhid->iofl);
 
-	if (hid->quirks & HID_QUIRK_ALWAYS_POLL)
-		return 0;
+	if (hid->quirks & HID_QUIRK_ALWAYS_POLL) {
+		res = 0;
+		goto Done;
+	}
 
 	res = usb_autopm_get_interface(usbhid->intf);
 	/* the device must be awake to reliably request remote wakeup */
 	if (res < 0) {
 		clear_bit(HID_OPENED, &usbhid->iofl);
-		return -EIO;
+		res = -EIO;
+		goto Done;
 	}
 
 	usbhid->intf->needs_remote_wakeup = 1;
@@ -725,6 +730,9 @@ static int usbhid_open(struct hid_device *hid)
 		msleep(50);
 
 	clear_bit(HID_RESUME_RUNNING, &usbhid->iofl);
+
+ Done:
+	mutex_unlock(&usbhid->mutex);
 	return res;
 }
 
@@ -732,6 +740,8 @@ static void usbhid_close(struct hid_device *hid)
 {
 	struct usbhid_device *usbhid = hid->driver_data;
 
+	mutex_lock(&usbhid->mutex);
+
 	/*
 	 * Make sure we don't restart data acquisition due to
 	 * a resumption we no longer care about by avoiding racing
@@ -743,12 +753,13 @@ static void usbhid_close(struct hid_device *hid)
 		clear_bit(HID_IN_POLLING, &usbhid->iofl);
 	spin_unlock_irq(&usbhid->lock);
 
-	if (hid->quirks & HID_QUIRK_ALWAYS_POLL)
-		return;
+	if (!(hid->quirks & HID_QUIRK_ALWAYS_POLL)) {
+		hid_cancel_delayed_stuff(usbhid);
+		usb_kill_urb(usbhid->urbin);
+		usbhid->intf->needs_remote_wakeup = 0;
+	}
 
-	hid_cancel_delayed_stuff(usbhid);
-	usb_kill_urb(usbhid->urbin);
-	usbhid->intf->needs_remote_wakeup = 0;
+	mutex_unlock(&usbhid->mutex);
 }
 
 /*
@@ -1057,6 +1068,8 @@ static int usbhid_start(struct hid_device *hid)
 	unsigned int n, insize = 0;
 	int ret;
 
+	mutex_lock(&usbhid->mutex);
+
 	clear_bit(HID_DISCONNECTED, &usbhid->iofl);
 
 	usbhid->bufsize = HID_MIN_BUFFER_SIZE;
@@ -1177,6 +1190,8 @@ static int usbhid_start(struct hid_device *hid)
 		usbhid_set_leds(hid);
 		device_set_wakeup_enable(&dev->dev, 1);
 	}
+
+	mutex_unlock(&usbhid->mutex);
 	return 0;
 
 fail:
@@ -1187,6 +1202,7 @@ fail:
 	usbhid->urbout = NULL;
 	usbhid->urbctrl = NULL;
 	hid_free_buffers(dev, hid);
+	mutex_unlock(&usbhid->mutex);
 	return ret;
 }
 
@@ -1202,6 +1218,8 @@ static void usbhid_stop(struct hid_device *hid)
 		usbhid->intf->needs_remote_wakeup = 0;
 	}
 
+	mutex_lock(&usbhid->mutex);
+
 	clear_bit(HID_STARTED, &usbhid->iofl);
 	spin_lock_irq(&usbhid->lock);	/* Sync with error and led handlers */
 	set_bit(HID_DISCONNECTED, &usbhid->iofl);
@@ -1222,6 +1240,8 @@ static void usbhid_stop(struct hid_device *hid)
 	usbhid->urbout = NULL;
 
 	hid_free_buffers(hid_to_usb_dev(hid), hid);
+
+	mutex_unlock(&usbhid->mutex);
 }
 
 static int usbhid_power(struct hid_device *hid, int lvl)
@@ -1382,6 +1402,7 @@ static int usbhid_probe(struct usb_interface *intf, const struct usb_device_id *
 	INIT_WORK(&usbhid->reset_work, hid_reset);
 	timer_setup(&usbhid->io_retry, hid_retry_timeout, 0);
 	spin_lock_init(&usbhid->lock);
+	mutex_init(&usbhid->mutex);
 
 	ret = hid_add_device(hid);
 	if (ret) {
diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c
index 4e11cc6fc34b..86759ba04452 100644
--- a/drivers/hid/usbhid/hiddev.c
+++ b/drivers/hid/usbhid/hiddev.c
@@ -241,12 +241,51 @@ static int hiddev_release(struct inode * inode, struct file * file)
 	return 0;
 }
 
+static int __hiddev_open(struct hiddev *hiddev, struct file *file)
+{
+	struct hiddev_list *list;
+	int error;
+
+	lockdep_assert_held(&hiddev->existancelock);
+
+	list = vzalloc(sizeof(*list));
+	if (!list)
+		return -ENOMEM;
+
+	mutex_init(&list->thread_lock);
+	list->hiddev = hiddev;
+
+	if (!hiddev->open++) {
+		error = hid_hw_power(hiddev->hid, PM_HINT_FULLON);
+		if (error < 0)
+			goto err_drop_count;
+
+		error = hid_hw_open(hiddev->hid);
+		if (error < 0)
+			goto err_normal_power;
+	}
+
+	spin_lock_irq(&hiddev->list_lock);
+	list_add_tail(&list->node, &hiddev->list);
+	spin_unlock_irq(&hiddev->list_lock);
+
+	file->private_data = list;
+
+	return 0;
+
+err_normal_power:
+	hid_hw_power(hiddev->hid, PM_HINT_NORMAL);
+err_drop_count:
+	hiddev->open--;
+	vfree(list);
+	return error;
+}
+
 /*
  * open file op
  */
 static int hiddev_open(struct inode *inode, struct file *file)
 {
-	struct hiddev_list *list;
 	struct usb_interface *intf;
 	struct hid_device *hid;
 	struct hiddev *hiddev;
@@ -255,66 +294,14 @@ static int hiddev_open(struct inode *inode, struct file *file)
 	intf = usbhid_find_interface(iminor(inode));
 	if (!intf)
 		return -ENODEV;
+
 	hid = usb_get_intfdata(intf);
 	hiddev = hid->hiddev;
 
-	if (!(list = vzalloc(sizeof(struct hiddev_list))))
-		return -ENOMEM;
-	mutex_init(&list->thread_lock);
-	list->hiddev = hiddev;
-	file->private_data = list;
-
-	/*
-	 * no need for locking because the USB major number
-	 * is shared which usbcore guards against disconnect
-	 */
-	if (list->hiddev->exist) {
-		if (!list->hiddev->open++) {
-			res = hid_hw_open(hiddev->hid);
-			if (res < 0)
-				goto bail;
-		}
-	} else {
-		res = -ENODEV;
-		goto bail;
-	}
-
-	spin_lock_irq(&list->hiddev->list_lock);
-	list_add_tail(&list->node, &hiddev->list);
-	spin_unlock_irq(&list->hiddev->list_lock);
-
 	mutex_lock(&hiddev->existancelock);
-	/*
-	 * recheck exist with existance lock held to
-	 * avoid opening a disconnected device
-	 */
-	if (!list->hiddev->exist) {
-		res = -ENODEV;
-		goto bail_unlock;
-	}
-	if (!list->hiddev->open++)
-		if (list->hiddev->exist) {
-			struct hid_device *hid = hiddev->hid;
-			res = hid_hw_power(hid, PM_HINT_FULLON);
-			if (res < 0)
-				goto bail_unlock;
-			res = hid_hw_open(hid);
-			if (res < 0)
-				goto bail_normal_power;
-		}
-	mutex_unlock(&hiddev->existancelock);
-	return 0;
-bail_normal_power:
-	hid_hw_power(hid, PM_HINT_NORMAL);
-bail_unlock:
+	res = hiddev->exist ? __hiddev_open(hiddev, file) : -ENODEV;
 	mutex_unlock(&hiddev->existancelock);
 
-	spin_lock_irq(&list->hiddev->list_lock);
-	list_del(&list->node);
-	spin_unlock_irq(&list->hiddev->list_lock);
-bail:
-	file->private_data = NULL;
-	vfree(list);
 	return res;
 }
 
@@ -954,9 +941,9 @@ void hiddev_disconnect(struct hid_device *hid)
 	hiddev->exist = 0;
 
 	if (hiddev->open) {
-		mutex_unlock(&hiddev->existancelock);
 		hid_hw_close(hiddev->hid);
 		wake_up_interruptible(&hiddev->wait);
+		mutex_unlock(&hiddev->existancelock);
 	} else {
 		mutex_unlock(&hiddev->existancelock);
 		kfree(hiddev);
diff --git a/drivers/hid/usbhid/usbhid.h b/drivers/hid/usbhid/usbhid.h
index 8620408bd7af..75fe85d3d27a 100644
--- a/drivers/hid/usbhid/usbhid.h
+++ b/drivers/hid/usbhid/usbhid.h
@@ -80,6 +80,7 @@ struct usbhid_device {
 	dma_addr_t outbuf_dma;                                          /* Output buffer dma */
 	unsigned long last_out;							/* record of last output for timeouts */
 
+	struct mutex mutex;						/* start/stop/open/close */
 	spinlock_t lock;						/* fifo spinlock */
 	unsigned long iofl;                                             /* I/O flags (CTRL_RUNNING, OUT_RUNNING) */
 	struct timer_list io_retry;                                     /* Retry timer */
diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index 602219a8710d..0dbaf68ea291 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -319,9 +319,11 @@ static void wacom_feature_mapping(struct hid_device *hdev,
 			data[0] = field->report->id;
 			ret = wacom_get_report(hdev, HID_FEATURE_REPORT,
 					       data, n, WAC_CMD_RETRIES);
-			if (ret == n) {
+			if (ret == n && features->type == HID_GENERIC) {
 				ret = hid_report_raw_event(hdev,
 					HID_FEATURE_REPORT, data, n, 0);
+			} else if (ret == 2 && features->type != HID_GENERIC) {
+				features->touch_max = data[1];
 			} else {
 				features->touch_max = 16;
 				hid_warn(hdev, "wacom_feature_mapping: "
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index c42f2e114d43..d89e8dbd5128 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -2043,12 +2043,18 @@ static void wacom_wac_pad_event(struct hid_device *hdev, struct hid_field *field
 		 */
 		if (hdev->vendor == 0x56a &&
 		    (hdev->product == 0x34d || hdev->product == 0x34e ||  /* MobileStudio Pro */
-		     hdev->product == 0x357 || hdev->product == 0x358)) { /* Intuos Pro 2 */
+		     hdev->product == 0x357 || hdev->product == 0x358 ||  /* Intuos Pro 2 */
+		     hdev->product == 0x392 ||				  /* Intuos Pro 2 */
+		     hdev->product == 0x398 || hdev->product == 0x399 ||  /* MobileStudio Pro */
+		     hdev->product == 0x3AA)) {				  /* MobileStudio Pro */
 			value = (field->logical_maximum - value);
 
-			if (hdev->product == 0x357 || hdev->product == 0x358)
+			if (hdev->product == 0x357 || hdev->product == 0x358 ||
+			    hdev->product == 0x392)
 				value = wacom_offset_rotation(input, usage, value, 3, 16);
-			else if (hdev->product == 0x34d || hdev->product == 0x34e)
+			else if (hdev->product == 0x34d || hdev->product == 0x34e ||
+				 hdev->product == 0x398 || hdev->product == 0x399 ||
+				 hdev->product == 0x3AA)
 				value = wacom_offset_rotation(input, usage, value, 1, 2);
 		}
 		else {
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index addcef50df7a..a8fca0279013 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -827,6 +827,9 @@ void vmbus_initiate_unload(bool crash)
 {
 	struct vmbus_channel_message_header hdr;
 
+	if (xchg(&vmbus_connection.conn_state, DISCONNECTED) == DISCONNECTED)
+		return;
+
 	/* Pre-Win2012R2 hosts don't support reconnect */
 	if (vmbus_proto_version < VERSION_WIN8_1)
 		return;
@@ -1224,6 +1227,8 @@ channel_message_table[CHANNELMSG_COUNT] = {
 	{ CHANNELMSG_19,			0, NULL },
 	{ CHANNELMSG_20,			0, NULL },
 	{ CHANNELMSG_TL_CONNECT_REQUEST,	0, NULL },
+	{ CHANNELMSG_22,			0, NULL },
+	{ CHANNELMSG_TL_CONNECT_RESULT,		0, NULL },
 };
 
 /*
@@ -1235,25 +1240,16 @@ void vmbus_onmessage(void *context)
 {
 	struct hv_message *msg = context;
 	struct vmbus_channel_message_header *hdr;
-	int size;
 
 	hdr = (struct vmbus_channel_message_header *)msg->u.payload;
-	size = msg->header.payload_size;
 
 	trace_vmbus_on_message(hdr);
 
-	if (hdr->msgtype >= CHANNELMSG_COUNT) {
-		pr_err("Received invalid channel message type %d size %d\n",
-			   hdr->msgtype, size);
-		print_hex_dump_bytes("", DUMP_PREFIX_NONE,
-				     (unsigned char *)msg->u.payload, size);
-		return;
-	}
-
-	if (channel_message_table[hdr->msgtype].message_handler)
-		channel_message_table[hdr->msgtype].message_handler(hdr);
-	else
-		pr_err("Unhandled channel message type %d\n", hdr->msgtype);
+	/*
+	 * vmbus_on_msg_dpc() makes sure the hdr->msgtype here can not go
+	 * out of bound and the message_handler pointer can not be NULL.
+	 */
+	channel_message_table[hdr->msgtype].message_handler(hdr);
 }
 
 /*
diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c
index 6fb4ea5f0304..5803fb328a5a 100644
--- a/drivers/hv/hv_balloon.c
+++ b/drivers/hv/hv_balloon.c
@@ -1213,10 +1213,7 @@ static unsigned int alloc_balloon_pages(struct hv_dynmem_device *dm,
 	unsigned int i, j;
 	struct page *pg;
 
-	if (num_pages < alloc_unit)
-		return 0;
-
-	for (i = 0; (i * alloc_unit) < num_pages; i++) {
+	for (i = 0; i < num_pages / alloc_unit; i++) {
 		if (bl_resp->hdr.size + sizeof(union dm_mem_page_range) >
 			PAGE_SIZE)
 			return i * alloc_unit;
@@ -1254,7 +1251,7 @@ static unsigned int alloc_balloon_pages(struct hv_dynmem_device *dm,
 
 	}
 
-	return num_pages;
+	return i * alloc_unit;
 }
 
 static void balloon_up(struct work_struct *dummy)
@@ -1269,9 +1266,6 @@ static void balloon_up(struct work_struct *dummy)
 	long avail_pages;
 	unsigned long floor;
 
-	/* The host balloons pages in 2M granularity. */
-	WARN_ON_ONCE(num_pages % PAGES_IN_2M != 0);
-
 	/*
 	 * We will attempt 2M allocations. However, if we fail to
 	 * allocate 2M chunks, we will go back to 4k allocations.
@@ -1281,14 +1275,13 @@ static void balloon_up(struct work_struct *dummy)
 	avail_pages = si_mem_available();
 	floor = compute_balloon_floor();
 
-	/* Refuse to balloon below the floor, keep the 2M granularity. */
+	/* Refuse to balloon below the floor. */
 	if (avail_pages < num_pages || avail_pages - num_pages < floor) {
 		pr_warn("Balloon request will be partially fulfilled. %s\n",
 			avail_pages < num_pages ? "Not enough memory." :
 			"Balloon floor reached.");
 
 		num_pages = avail_pages > floor ? (avail_pages - floor) : 0;
-		num_pages -= num_pages % PAGES_IN_2M;
 	}
 
 	while (!done) {
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 92b1874b3eb3..8342028bc005 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -15,6 +15,7 @@
 #include <linux/interrupt.h>
 #include <linux/sysctl.h>
 #include <linux/slab.h>
+#include <linux/kernel.h>
 #include <linux/acpi.h>
 #include <linux/completion.h>
 #include <linux/hyperv.h>
@@ -45,14 +46,35 @@ static int hyperv_cpuhp_online;
 
 static void *hv_panic_page;
 
+/*
+ * Boolean to control whether to report panic messages over Hyper-V.
+ *
+ * It can be set via /proc/sys/kernel/hyperv/record_panic_msg
+ */
+static int sysctl_record_panic_msg = 1;
+
+static int hyperv_report_reg(void)
+{
+	return !sysctl_record_panic_msg || !hv_panic_page;
+}
+
 static int hyperv_panic_event(struct notifier_block *nb, unsigned long val,
 			      void *args)
 {
 	struct pt_regs *regs;
 
-	regs = current_pt_regs();
+	vmbus_initiate_unload(true);
 
-	hyperv_report_panic(regs, val);
+	/*
+	 * Hyper-V should be notified only once about a panic.  If we will be
+	 * doing hyperv_report_panic_msg() later with kmsg data, don't do
+	 * the notification here.
+	 */
+	if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE
+	    && hyperv_report_reg()) {
+		regs = current_pt_regs();
+		hyperv_report_panic(regs, val, false);
+	}
 	return NOTIFY_DONE;
 }
 
@@ -62,7 +84,13 @@ static int hyperv_die_event(struct notifier_block *nb, unsigned long val,
 	struct die_args *die = (struct die_args *)args;
 	struct pt_regs *regs = die->regs;
 
-	hyperv_report_panic(regs, val);
+	/*
+	 * Hyper-V should be notified only once about a panic.  If we will be
+	 * doing hyperv_report_panic_msg() later with kmsg data, don't do
+	 * the notification here.
+	 */
+	if (hyperv_report_reg())
+		hyperv_report_panic(regs, val, true);
 	return NOTIFY_DONE;
 }
 
@@ -991,6 +1019,10 @@ void vmbus_on_msg_dpc(unsigned long data)
 	}
 
 	entry = &channel_message_table[hdr->msgtype];
+
+	if (!entry->message_handler)
+		goto msg_handled;
+
 	if (entry->handler_type	== VMHT_BLOCKING) {
 		ctx = kmalloc(sizeof(*ctx), GFP_ATOMIC);
 		if (ctx == NULL)
@@ -1169,13 +1201,6 @@ static void vmbus_isr(void)
 }
 
 /*
- * Boolean to control whether to report panic messages over Hyper-V.
- *
- * It can be set via /proc/sys/kernel/hyperv/record_panic_msg
- */
-static int sysctl_record_panic_msg = 1;
-
-/*
  * Callback from kmsg_dump. Grab as much as possible from the end of the kmsg
  * buffer and call into Hyper-V to transfer the data.
  */
@@ -1299,19 +1324,28 @@ static int vmbus_bus_init(void)
 			hv_panic_page = (void *)get_zeroed_page(GFP_KERNEL);
 			if (hv_panic_page) {
 				ret = kmsg_dump_register(&hv_kmsg_dumper);
-				if (ret)
+				if (ret) {
 					pr_err("Hyper-V: kmsg dump register "
 						"error 0x%x\n", ret);
+					free_page((unsigned long)hv_panic_page);
+					hv_panic_page = NULL;
+				}
 			} else
 				pr_err("Hyper-V: panic message page memory "
 					"allocation failed");
 		}
 
 		register_die_notifier(&hyperv_die_block);
-		atomic_notifier_chain_register(&panic_notifier_list,
-					       &hyperv_panic_block);
 	}
 
+	/*
+	 * Always register the panic notifier because we need to unload
+	 * the VMbus channel connection to prevent any VMbus
+	 * activity after the VM panics.
+	 */
+	atomic_notifier_chain_register(&panic_notifier_list,
+			       &hyperv_panic_block);
+
 	vmbus_request_offers();
 
 	return 0;
@@ -1323,7 +1357,6 @@ err_alloc:
 	hv_remove_vmbus_irq();
 
 	bus_unregister(&hv_bus);
-	free_page((unsigned long)hv_panic_page);
 	unregister_sysctl_table(hv_ctl_table_hdr);
 	hv_ctl_table_hdr = NULL;
 	return ret;
@@ -2066,7 +2099,6 @@ static void hv_kexec_handler(void)
 {
 	hv_synic_clockevents_cleanup();
 	vmbus_initiate_unload(false);
-	vmbus_connection.conn_state = DISCONNECTED;
 	/* Make sure conn_state is set as hv_synic_cleanup checks for it */
 	mb();
 	cpuhp_remove_state(hyperv_cpuhp_online);
@@ -2081,7 +2113,6 @@ static void hv_crash_handler(struct pt_regs *regs)
 	 * doing the cleanup for current CPU only. This should be sufficient
 	 * for kdump.
 	 */
-	vmbus_connection.conn_state = DISCONNECTED;
 	hv_synic_cleanup(smp_processor_id());
 	hyperv_cleanup();
 };
diff --git a/drivers/hwmon/acpi_power_meter.c b/drivers/hwmon/acpi_power_meter.c
index 4cf25458f0b9..740ac0a1b726 100644
--- a/drivers/hwmon/acpi_power_meter.c
+++ b/drivers/hwmon/acpi_power_meter.c
@@ -883,7 +883,7 @@ static int acpi_power_meter_add(struct acpi_device *device)
 
 	res = setup_attrs(resource);
 	if (res)
-		goto exit_free;
+		goto exit_free_capability;
 
 	resource->hwmon_dev = hwmon_device_register(&device->dev);
 	if (IS_ERR(resource->hwmon_dev)) {
@@ -896,6 +896,8 @@ static int acpi_power_meter_add(struct acpi_device *device)
 
 exit_remove:
 	remove_attrs(resource);
+exit_free_capability:
+	free_capabilities(resource);
 exit_free:
 	kfree(resource);
 exit:
diff --git a/drivers/hwmon/adt7462.c b/drivers/hwmon/adt7462.c
index 9632e2e3c4bb..319a0519ebdb 100644
--- a/drivers/hwmon/adt7462.c
+++ b/drivers/hwmon/adt7462.c
@@ -413,7 +413,7 @@ static int ADT7462_REG_VOLT(struct adt7462_data *data, int which)
 			return 0x95;
 		break;
 	}
-	return -ENODEV;
+	return 0;
 }
 
 /* Provide labels for sysfs */
diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c
index c3c6031a7285..e3831086bac5 100644
--- a/drivers/hwmon/adt7475.c
+++ b/drivers/hwmon/adt7475.c
@@ -293,9 +293,10 @@ static inline u16 volt2reg(int channel, long volt, u8 bypass_attn)
 	long reg;
 
 	if (bypass_attn & (1 << channel))
-		reg = (volt * 1024) / 2250;
+		reg = DIV_ROUND_CLOSEST(volt * 1024, 2250);
 	else
-		reg = (volt * r[1] * 1024) / ((r[0] + r[1]) * 2250);
+		reg = DIV_ROUND_CLOSEST(volt * r[1] * 1024,
+					(r[0] + r[1]) * 2250);
 	return clamp_val(reg, 0, 1023) & (0xff << 2);
 }
 
diff --git a/drivers/hwmon/aspeed-pwm-tacho.c b/drivers/hwmon/aspeed-pwm-tacho.c
index 40c489be62ea..40f3139f1e02 100644
--- a/drivers/hwmon/aspeed-pwm-tacho.c
+++ b/drivers/hwmon/aspeed-pwm-tacho.c
@@ -851,6 +851,8 @@ static int aspeed_create_fan(struct device *dev,
 	ret = of_property_read_u32(child, "reg", &pwm_port);
 	if (ret)
 		return ret;
+	if (pwm_port >= ARRAY_SIZE(pwm_port_params))
+		return -EINVAL;
 	aspeed_create_pwm_port(priv, (u8)pwm_port);
 
 	ret = of_property_count_u8_elems(child, "cooling-levels");
diff --git a/drivers/hwmon/da9052-hwmon.c b/drivers/hwmon/da9052-hwmon.c
index 53b517dbe7e6..4af2fc309c28 100644
--- a/drivers/hwmon/da9052-hwmon.c
+++ b/drivers/hwmon/da9052-hwmon.c
@@ -244,9 +244,9 @@ static ssize_t da9052_tsi_show(struct device *dev,
 	int channel = to_sensor_dev_attr(devattr)->index;
 	int ret;
 
-	mutex_lock(&hwmon->hwmon_lock);
+	mutex_lock(&hwmon->da9052->auxadc_lock);
 	ret = __da9052_read_tsi(dev, channel);
-	mutex_unlock(&hwmon->hwmon_lock);
+	mutex_unlock(&hwmon->da9052->auxadc_lock);
 
 	if (ret < 0)
 		return ret;
diff --git a/drivers/hwmon/emc2103.c b/drivers/hwmon/emc2103.c
index 491a570e8e50..924c02c1631d 100644
--- a/drivers/hwmon/emc2103.c
+++ b/drivers/hwmon/emc2103.c
@@ -443,7 +443,7 @@ static ssize_t pwm1_enable_store(struct device *dev,
 	}
 
 	result = read_u8_from_i2c(client, REG_FAN_CONF1, &conf_reg);
-	if (result) {
+	if (result < 0) {
 		count = result;
 		goto err;
 	}
diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c
index 84753680a4e8..54c27e683ee1 100644
--- a/drivers/hwmon/gpio-fan.c
+++ b/drivers/hwmon/gpio-fan.c
@@ -524,7 +524,9 @@ static int gpio_fan_probe(struct platform_device *pdev)
 		err = fan_ctrl_init(fan_data);
 		if (err)
 			return err;
-		devm_add_action_or_reset(dev, gpio_fan_stop, fan_data);
+		err = devm_add_action_or_reset(dev, gpio_fan_stop, fan_data);
+		if (err)
+			return err;
 	}
 
 	/* Make this driver part of hwmon class. */
diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c
index 05e120e01cb4..7dfb9c524b58 100644
--- a/drivers/hwmon/hwmon.c
+++ b/drivers/hwmon/hwmon.c
@@ -51,6 +51,7 @@ struct hwmon_device_attribute {
 
 #define to_hwmon_attr(d) \
 	container_of(d, struct hwmon_device_attribute, dev_attr)
+#define to_dev_attr(a) container_of(a, struct device_attribute, attr)
 
 /*
  * Thermal zone information
@@ -58,7 +59,7 @@ struct hwmon_device_attribute {
  * also provides the sensor index.
  */
 struct hwmon_thermal_data {
-	struct hwmon_device *hwdev;	/* Reference to hwmon device */
+	struct device *dev;		/* Reference to hwmon device */
 	int index;			/* sensor index */
 };
 
@@ -95,9 +96,27 @@ static const struct attribute_group *hwmon_dev_attr_groups[] = {
 	NULL
 };
 
+static void hwmon_free_attrs(struct attribute **attrs)
+{
+	int i;
+
+	for (i = 0; attrs[i]; i++) {
+		struct device_attribute *dattr = to_dev_attr(attrs[i]);
+		struct hwmon_device_attribute *hattr = to_hwmon_attr(dattr);
+
+		kfree(hattr);
+	}
+	kfree(attrs);
+}
+
 static void hwmon_dev_release(struct device *dev)
 {
-	kfree(to_hwmon_device(dev));
+	struct hwmon_device *hwdev = to_hwmon_device(dev);
+
+	if (hwdev->group.attrs)
+		hwmon_free_attrs(hwdev->group.attrs);
+	kfree(hwdev->groups);
+	kfree(hwdev);
 }
 
 static struct class hwmon_class = {
@@ -119,11 +138,11 @@ static DEFINE_IDA(hwmon_ida);
 static int hwmon_thermal_get_temp(void *data, int *temp)
 {
 	struct hwmon_thermal_data *tdata = data;
-	struct hwmon_device *hwdev = tdata->hwdev;
+	struct hwmon_device *hwdev = to_hwmon_device(tdata->dev);
 	int ret;
 	long t;
 
-	ret = hwdev->chip->ops->read(&hwdev->dev, hwmon_temp, hwmon_temp_input,
+	ret = hwdev->chip->ops->read(tdata->dev, hwmon_temp, hwmon_temp_input,
 				     tdata->index, &t);
 	if (ret < 0)
 		return ret;
@@ -137,8 +156,7 @@ static const struct thermal_zone_of_device_ops hwmon_thermal_ops = {
 	.get_temp = hwmon_thermal_get_temp,
 };
 
-static int hwmon_thermal_add_sensor(struct device *dev,
-				    struct hwmon_device *hwdev, int index)
+static int hwmon_thermal_add_sensor(struct device *dev, int index)
 {
 	struct hwmon_thermal_data *tdata;
 	struct thermal_zone_device *tzd;
@@ -147,10 +165,10 @@ static int hwmon_thermal_add_sensor(struct device *dev,
 	if (!tdata)
 		return -ENOMEM;
 
-	tdata->hwdev = hwdev;
+	tdata->dev = dev;
 	tdata->index = index;
 
-	tzd = devm_thermal_zone_of_sensor_register(&hwdev->dev, index, tdata,
+	tzd = devm_thermal_zone_of_sensor_register(dev, index, tdata,
 						   &hwmon_thermal_ops);
 	/*
 	 * If CONFIG_THERMAL_OF is disabled, this returns -ENODEV,
@@ -162,8 +180,7 @@ static int hwmon_thermal_add_sensor(struct device *dev,
 	return 0;
 }
 #else
-static int hwmon_thermal_add_sensor(struct device *dev,
-				    struct hwmon_device *hwdev, int index)
+static int hwmon_thermal_add_sensor(struct device *dev, int index)
 {
 	return 0;
 }
@@ -250,8 +267,7 @@ static bool is_string_attr(enum hwmon_sensor_types type, u32 attr)
 	       (type == hwmon_fan && attr == hwmon_fan_label);
 }
 
-static struct attribute *hwmon_genattr(struct device *dev,
-				       const void *drvdata,
+static struct attribute *hwmon_genattr(const void *drvdata,
 				       enum hwmon_sensor_types type,
 				       u32 attr,
 				       int index,
@@ -279,7 +295,7 @@ static struct attribute *hwmon_genattr(struct device *dev,
 	if ((mode & 0222) && !ops->write)
 		return ERR_PTR(-EINVAL);
 
-	hattr = devm_kzalloc(dev, sizeof(*hattr), GFP_KERNEL);
+	hattr = kzalloc(sizeof(*hattr), GFP_KERNEL);
 	if (!hattr)
 		return ERR_PTR(-ENOMEM);
 
@@ -492,8 +508,7 @@ static int hwmon_num_channel_attrs(const struct hwmon_channel_info *info)
 	return n;
 }
 
-static int hwmon_genattrs(struct device *dev,
-			  const void *drvdata,
+static int hwmon_genattrs(const void *drvdata,
 			  struct attribute **attrs,
 			  const struct hwmon_ops *ops,
 			  const struct hwmon_channel_info *info)
@@ -519,7 +534,7 @@ static int hwmon_genattrs(struct device *dev,
 			attr_mask &= ~BIT(attr);
 			if (attr >= template_size)
 				return -EINVAL;
-			a = hwmon_genattr(dev, drvdata, info->type, attr, i,
+			a = hwmon_genattr(drvdata, info->type, attr, i,
 					  templates[attr], ops);
 			if (IS_ERR(a)) {
 				if (PTR_ERR(a) != -ENOENT)
@@ -533,8 +548,7 @@ static int hwmon_genattrs(struct device *dev,
 }
 
 static struct attribute **
-__hwmon_create_attrs(struct device *dev, const void *drvdata,
-		     const struct hwmon_chip_info *chip)
+__hwmon_create_attrs(const void *drvdata, const struct hwmon_chip_info *chip)
 {
 	int ret, i, aindex = 0, nattrs = 0;
 	struct attribute **attrs;
@@ -545,15 +559,17 @@ __hwmon_create_attrs(struct device *dev, const void *drvdata,
 	if (nattrs == 0)
 		return ERR_PTR(-EINVAL);
 
-	attrs = devm_kcalloc(dev, nattrs + 1, sizeof(*attrs), GFP_KERNEL);
+	attrs = kcalloc(nattrs + 1, sizeof(*attrs), GFP_KERNEL);
 	if (!attrs)
 		return ERR_PTR(-ENOMEM);
 
 	for (i = 0; chip->info[i]; i++) {
-		ret = hwmon_genattrs(dev, drvdata, &attrs[aindex], chip->ops,
+		ret = hwmon_genattrs(drvdata, &attrs[aindex], chip->ops,
 				     chip->info[i]);
-		if (ret < 0)
+		if (ret < 0) {
+			hwmon_free_attrs(attrs);
 			return ERR_PTR(ret);
+		}
 		aindex += ret;
 	}
 
@@ -595,14 +611,13 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata,
 			for (i = 0; groups[i]; i++)
 				ngroups++;
 
-		hwdev->groups = devm_kcalloc(dev, ngroups, sizeof(*groups),
-					     GFP_KERNEL);
+		hwdev->groups = kcalloc(ngroups, sizeof(*groups), GFP_KERNEL);
 		if (!hwdev->groups) {
 			err = -ENOMEM;
 			goto free_hwmon;
 		}
 
-		attrs = __hwmon_create_attrs(dev, drvdata, chip);
+		attrs = __hwmon_create_attrs(drvdata, chip);
 		if (IS_ERR(attrs)) {
 			err = PTR_ERR(attrs);
 			goto free_hwmon;
@@ -647,8 +662,7 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata,
 							   hwmon_temp_input, j))
 					continue;
 				if (info[i]->config[j] & HWMON_T_INPUT) {
-					err = hwmon_thermal_add_sensor(dev,
-								hwdev, j);
+					err = hwmon_thermal_add_sensor(hdev, j);
 					if (err) {
 						device_unregister(hdev);
 						goto ida_remove;
@@ -661,7 +675,7 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata,
 	return hdev;
 
 free_hwmon:
-	kfree(hwdev);
+	hwmon_dev_release(hdev);
 ida_remove:
 	ida_simple_remove(&hwmon_ida, id);
 	return ERR_PTR(err);
diff --git a/drivers/hwmon/jc42.c b/drivers/hwmon/jc42.c
index f2d81b0558e5..e3f1ebee7130 100644
--- a/drivers/hwmon/jc42.c
+++ b/drivers/hwmon/jc42.c
@@ -506,7 +506,7 @@ static int jc42_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	}
 	data->config = config;
 
-	hwmon_dev = devm_hwmon_device_register_with_info(dev, client->name,
+	hwmon_dev = devm_hwmon_device_register_with_info(dev, "jc42",
 							 data, &jc42_chip_info,
 							 NULL);
 	return PTR_ERR_OR_ZERO(hwmon_dev);
diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c
index 5c1dddde193c..f96fd8efb45a 100644
--- a/drivers/hwmon/k10temp.c
+++ b/drivers/hwmon/k10temp.c
@@ -349,6 +349,7 @@ static const struct pci_device_id k10temp_id_table[] = {
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F3) },
+	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_M60H_DF_F3) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) },
 	{ PCI_VDEVICE(HYGON, PCI_DEVICE_ID_AMD_17H_DF_F3) },
 	{}
diff --git a/drivers/hwmon/max6697.c b/drivers/hwmon/max6697.c
index 743752a2467a..64122eb38060 100644
--- a/drivers/hwmon/max6697.c
+++ b/drivers/hwmon/max6697.c
@@ -38,8 +38,9 @@ static const u8 MAX6697_REG_CRIT[] = {
  * Map device tree / platform data register bit map to chip bit map.
  * Applies to alert register and over-temperature register.
  */
-#define MAX6697_MAP_BITS(reg)	((((reg) & 0x7e) >> 1) | \
+#define MAX6697_ALERT_MAP_BITS(reg)	((((reg) & 0x7e) >> 1) | \
 				 (((reg) & 0x01) << 6) | ((reg) & 0x80))
+#define MAX6697_OVERT_MAP_BITS(reg) (((reg) >> 1) | (((reg) & 0x01) << 7))
 
 #define MAX6697_REG_STAT(n)		(0x44 + (n))
 
@@ -562,12 +563,12 @@ static int max6697_init_chip(struct max6697_data *data,
 		return ret;
 
 	ret = i2c_smbus_write_byte_data(client, MAX6697_REG_ALERT_MASK,
-					MAX6697_MAP_BITS(pdata->alert_mask));
+				MAX6697_ALERT_MAP_BITS(pdata->alert_mask));
 	if (ret < 0)
 		return ret;
 
 	ret = i2c_smbus_write_byte_data(client, MAX6697_REG_OVERT_MASK,
-				MAX6697_MAP_BITS(pdata->over_temperature_mask));
+			MAX6697_OVERT_MAP_BITS(pdata->over_temperature_mask));
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c
index d42bc0883a32..c6b7d6f72520 100644
--- a/drivers/hwmon/nct6775.c
+++ b/drivers/hwmon/nct6775.c
@@ -782,13 +782,13 @@ static const char *const nct6798_temp_label[] = {
 	"Agent1 Dimm1",
 	"BYTE_TEMP0",
 	"BYTE_TEMP1",
-	"",
-	"",
+	"PECI Agent 0 Calibration",	/* undocumented */
+	"PECI Agent 1 Calibration",	/* undocumented */
 	"",
 	"Virtual_TEMP"
 };
 
-#define NCT6798_TEMP_MASK	0x8fff0ffe
+#define NCT6798_TEMP_MASK	0xbfff0ffe
 #define NCT6798_VIRT_TEMP_MASK	0x80000c00
 
 /* NCT6102D/NCT6106D specific data */
diff --git a/drivers/hwmon/nct7802.c b/drivers/hwmon/nct7802.c
index f3dd2a17bd42..2e97e56c72c7 100644
--- a/drivers/hwmon/nct7802.c
+++ b/drivers/hwmon/nct7802.c
@@ -23,8 +23,8 @@
 static const u8 REG_VOLTAGE[5] = { 0x09, 0x0a, 0x0c, 0x0d, 0x0e };
 
 static const u8 REG_VOLTAGE_LIMIT_LSB[2][5] = {
-	{ 0x40, 0x00, 0x42, 0x44, 0x46 },
-	{ 0x3f, 0x00, 0x41, 0x43, 0x45 },
+	{ 0x46, 0x00, 0x40, 0x42, 0x44 },
+	{ 0x45, 0x00, 0x3f, 0x41, 0x43 },
 };
 
 static const u8 REG_VOLTAGE_LIMIT_MSB[5] = { 0x48, 0x00, 0x47, 0x47, 0x48 };
@@ -58,6 +58,8 @@ static const u8 REG_VOLTAGE_LIMIT_MSB_SHIFT[2][5] = {
 struct nct7802_data {
 	struct regmap *regmap;
 	struct mutex access_lock; /* for multi-byte read and write operations */
+	u8 in_status;
+	struct mutex in_alarm_lock;
 };
 
 static ssize_t temp_type_show(struct device *dev,
@@ -368,6 +370,66 @@ static ssize_t in_store(struct device *dev, struct device_attribute *attr,
 	return err ? : count;
 }
 
+static ssize_t in_alarm_show(struct device *dev, struct device_attribute *attr,
+			     char *buf)
+{
+	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
+	struct nct7802_data *data = dev_get_drvdata(dev);
+	int volt, min, max, ret;
+	unsigned int val;
+
+	mutex_lock(&data->in_alarm_lock);
+
+	/*
+	 * The SMI Voltage status register is the only register giving a status
+	 * for voltages. A bit is set for each input crossing a threshold, in
+	 * both direction, but the "inside" or "outside" limits info is not
+	 * available. Also this register is cleared on read.
+	 * Note: this is not explicitly spelled out in the datasheet, but
+	 * from experiment.
+	 * To deal with this we use a status cache with one validity bit and
+	 * one status bit for each input. Validity is cleared at startup and
+	 * each time the register reports a change, and the status is processed
+	 * by software based on current input value and limits.
+	 */
+	ret = regmap_read(data->regmap, 0x1e, &val); /* SMI Voltage status */
+	if (ret < 0)
+		goto abort;
+
+	/* invalidate cached status for all inputs crossing a threshold */
+	data->in_status &= ~((val & 0x0f) << 4);
+
+	/* if cached status for requested input is invalid, update it */
+	if (!(data->in_status & (0x10 << sattr->index))) {
+		ret = nct7802_read_voltage(data, sattr->nr, 0);
+		if (ret < 0)
+			goto abort;
+		volt = ret;
+
+		ret = nct7802_read_voltage(data, sattr->nr, 1);
+		if (ret < 0)
+			goto abort;
+		min = ret;
+
+		ret = nct7802_read_voltage(data, sattr->nr, 2);
+		if (ret < 0)
+			goto abort;
+		max = ret;
+
+		if (volt < min || volt > max)
+			data->in_status |= (1 << sattr->index);
+		else
+			data->in_status &= ~(1 << sattr->index);
+
+		data->in_status |= 0x10 << sattr->index;
+	}
+
+	ret = sprintf(buf, "%u\n", !!(data->in_status & (1 << sattr->index)));
+abort:
+	mutex_unlock(&data->in_alarm_lock);
+	return ret;
+}
+
 static ssize_t temp_show(struct device *dev, struct device_attribute *attr,
 			 char *buf)
 {
@@ -660,7 +722,7 @@ static const struct attribute_group nct7802_temp_group = {
 static SENSOR_DEVICE_ATTR_2_RO(in0_input, in, 0, 0);
 static SENSOR_DEVICE_ATTR_2_RW(in0_min, in, 0, 1);
 static SENSOR_DEVICE_ATTR_2_RW(in0_max, in, 0, 2);
-static SENSOR_DEVICE_ATTR_2_RO(in0_alarm, alarm, 0x1e, 3);
+static SENSOR_DEVICE_ATTR_2_RO(in0_alarm, in_alarm, 0, 3);
 static SENSOR_DEVICE_ATTR_2_RW(in0_beep, beep, 0x5a, 3);
 
 static SENSOR_DEVICE_ATTR_2_RO(in1_input, in, 1, 0);
@@ -668,19 +730,19 @@ static SENSOR_DEVICE_ATTR_2_RO(in1_input, in, 1, 0);
 static SENSOR_DEVICE_ATTR_2_RO(in2_input, in, 2, 0);
 static SENSOR_DEVICE_ATTR_2_RW(in2_min, in, 2, 1);
 static SENSOR_DEVICE_ATTR_2_RW(in2_max, in, 2, 2);
-static SENSOR_DEVICE_ATTR_2_RO(in2_alarm, alarm, 0x1e, 0);
+static SENSOR_DEVICE_ATTR_2_RO(in2_alarm, in_alarm, 2, 0);
 static SENSOR_DEVICE_ATTR_2_RW(in2_beep, beep, 0x5a, 0);
 
 static SENSOR_DEVICE_ATTR_2_RO(in3_input, in, 3, 0);
 static SENSOR_DEVICE_ATTR_2_RW(in3_min, in, 3, 1);
 static SENSOR_DEVICE_ATTR_2_RW(in3_max, in, 3, 2);
-static SENSOR_DEVICE_ATTR_2_RO(in3_alarm, alarm, 0x1e, 1);
+static SENSOR_DEVICE_ATTR_2_RO(in3_alarm, in_alarm, 3, 1);
 static SENSOR_DEVICE_ATTR_2_RW(in3_beep, beep, 0x5a, 1);
 
 static SENSOR_DEVICE_ATTR_2_RO(in4_input, in, 4, 0);
 static SENSOR_DEVICE_ATTR_2_RW(in4_min, in, 4, 1);
 static SENSOR_DEVICE_ATTR_2_RW(in4_max, in, 4, 2);
-static SENSOR_DEVICE_ATTR_2_RO(in4_alarm, alarm, 0x1e, 2);
+static SENSOR_DEVICE_ATTR_2_RO(in4_alarm, in_alarm, 4, 2);
 static SENSOR_DEVICE_ATTR_2_RW(in4_beep, beep, 0x5a, 2);
 
 static struct attribute *nct7802_in_attrs[] = {
@@ -1011,6 +1073,7 @@ static int nct7802_probe(struct i2c_client *client,
 		return PTR_ERR(data->regmap);
 
 	mutex_init(&data->access_lock);
+	mutex_init(&data->in_alarm_lock);
 
 	ret = nct7802_init_chip(data);
 	if (ret < 0)
diff --git a/drivers/hwmon/pmbus/adm1275.c b/drivers/hwmon/pmbus/adm1275.c
index 82052b6611c9..8104d8ad6086 100644
--- a/drivers/hwmon/pmbus/adm1275.c
+++ b/drivers/hwmon/pmbus/adm1275.c
@@ -355,6 +355,7 @@ MODULE_DEVICE_TABLE(i2c, adm1275_id);
 static int adm1275_probe(struct i2c_client *client,
 			 const struct i2c_device_id *id)
 {
+	s32 (*config_read_fn)(const struct i2c_client *client, u8 reg);
 	u8 block_buffer[I2C_SMBUS_BLOCK_MAX + 1];
 	int config, device_config;
 	int ret;
@@ -400,11 +401,16 @@ static int adm1275_probe(struct i2c_client *client,
 			   "Device mismatch: Configured %s, detected %s\n",
 			   id->name, mid->name);
 
-	config = i2c_smbus_read_byte_data(client, ADM1275_PMON_CONFIG);
+	if (mid->driver_data == adm1272 || mid->driver_data == adm1278 ||
+	    mid->driver_data == adm1293 || mid->driver_data == adm1294)
+		config_read_fn = i2c_smbus_read_word_data;
+	else
+		config_read_fn = i2c_smbus_read_byte_data;
+	config = config_read_fn(client, ADM1275_PMON_CONFIG);
 	if (config < 0)
 		return config;
 
-	device_config = i2c_smbus_read_byte_data(client, ADM1275_DEVICE_CONFIG);
+	device_config = config_read_fn(client, ADM1275_DEVICE_CONFIG);
 	if (device_config < 0)
 		return device_config;
 
diff --git a/drivers/hwmon/pmbus/ibm-cffps.c b/drivers/hwmon/pmbus/ibm-cffps.c
index ee2ee9e3ffd7..5a6e9b5a228b 100644
--- a/drivers/hwmon/pmbus/ibm-cffps.c
+++ b/drivers/hwmon/pmbus/ibm-cffps.c
@@ -37,9 +37,13 @@
 #define CFFPS_MFR_VAUX_FAULT			BIT(6)
 #define CFFPS_MFR_CURRENT_SHARE_WARNING		BIT(7)
 
+/*
+ * LED off state actually relinquishes LED control to PSU firmware, so it can
+ * turn on the LED for faults.
+ */
+#define CFFPS_LED_OFF				0
 #define CFFPS_LED_BLINK				BIT(0)
 #define CFFPS_LED_ON				BIT(1)
-#define CFFPS_LED_OFF				BIT(2)
 #define CFFPS_BLINK_RATE_MS			250
 
 enum {
@@ -265,26 +269,36 @@ static int ibm_cffps_read_word_data(struct i2c_client *client, int page,
 	return rc;
 }
 
-static void ibm_cffps_led_brightness_set(struct led_classdev *led_cdev,
-					 enum led_brightness brightness)
+static int ibm_cffps_led_brightness_set(struct led_classdev *led_cdev,
+					enum led_brightness brightness)
 {
 	int rc;
+	u8 next_led_state;
 	struct ibm_cffps *psu = container_of(led_cdev, struct ibm_cffps, led);
 
 	if (brightness == LED_OFF) {
-		psu->led_state = CFFPS_LED_OFF;
+		next_led_state = CFFPS_LED_OFF;
 	} else {
 		brightness = LED_FULL;
+
 		if (psu->led_state != CFFPS_LED_BLINK)
-			psu->led_state = CFFPS_LED_ON;
+			next_led_state = CFFPS_LED_ON;
+		else
+			next_led_state = CFFPS_LED_BLINK;
 	}
 
+	dev_dbg(&psu->client->dev, "LED brightness set: %d. Command: %d.\n",
+		brightness, next_led_state);
+
 	rc = i2c_smbus_write_byte_data(psu->client, CFFPS_SYS_CONFIG_CMD,
-				       psu->led_state);
+				       next_led_state);
 	if (rc < 0)
-		return;
+		return rc;
 
+	psu->led_state = next_led_state;
 	led_cdev->brightness = brightness;
+
+	return 0;
 }
 
 static int ibm_cffps_led_blink_set(struct led_classdev *led_cdev,
@@ -294,16 +308,15 @@ static int ibm_cffps_led_blink_set(struct led_classdev *led_cdev,
 	int rc;
 	struct ibm_cffps *psu = container_of(led_cdev, struct ibm_cffps, led);
 
-	psu->led_state = CFFPS_LED_BLINK;
-
-	if (led_cdev->brightness == LED_OFF)
-		return 0;
+	dev_dbg(&psu->client->dev, "LED blink set.\n");
 
 	rc = i2c_smbus_write_byte_data(psu->client, CFFPS_SYS_CONFIG_CMD,
 				       CFFPS_LED_BLINK);
 	if (rc < 0)
 		return rc;
 
+	psu->led_state = CFFPS_LED_BLINK;
+	led_cdev->brightness = LED_FULL;
 	*delay_on = CFFPS_BLINK_RATE_MS;
 	*delay_off = CFFPS_BLINK_RATE_MS;
 
@@ -320,7 +333,7 @@ static void ibm_cffps_create_led_class(struct ibm_cffps *psu)
 		 client->addr);
 	psu->led.name = psu->led_name;
 	psu->led.max_brightness = LED_FULL;
-	psu->led.brightness_set = ibm_cffps_led_brightness_set;
+	psu->led.brightness_set_blocking = ibm_cffps_led_brightness_set;
 	psu->led.blink_set = ibm_cffps_led_blink_set;
 
 	rc = devm_led_classdev_register(dev, &psu->led);
diff --git a/drivers/hwmon/pmbus/ltc2978.c b/drivers/hwmon/pmbus/ltc2978.c
index f01f4887fb2e..a91ed01abb68 100644
--- a/drivers/hwmon/pmbus/ltc2978.c
+++ b/drivers/hwmon/pmbus/ltc2978.c
@@ -82,8 +82,8 @@ enum chips { ltc2974, ltc2975, ltc2977, ltc2978, ltc2980, ltc3880, ltc3882,
 
 #define LTC_POLL_TIMEOUT		100	/* in milli-seconds */
 
-#define LTC_NOT_BUSY			BIT(5)
-#define LTC_NOT_PENDING			BIT(4)
+#define LTC_NOT_BUSY			BIT(6)
+#define LTC_NOT_PENDING			BIT(5)
 
 /*
  * LTC2978 clears peak data whenever the CLEAR_FAULTS command is executed, which
diff --git a/drivers/hwmon/pwm-fan.c b/drivers/hwmon/pwm-fan.c
index 08c9b9f1c16e..54c0ff00d67f 100644
--- a/drivers/hwmon/pwm-fan.c
+++ b/drivers/hwmon/pwm-fan.c
@@ -320,8 +320,10 @@ static int pwm_fan_probe(struct platform_device *pdev)
 			dev_err(dev, "Failed to enable fan supply: %d\n", ret);
 			return ret;
 		}
-		devm_add_action_or_reset(dev, pwm_fan_regulator_disable,
-					 ctx->reg_en);
+		ret = devm_add_action_or_reset(dev, pwm_fan_regulator_disable,
+					       ctx->reg_en);
+		if (ret)
+			return ret;
 	}
 
 	ctx->pwm_value = MAX_PWM;
@@ -337,7 +339,9 @@ static int pwm_fan_probe(struct platform_device *pdev)
 		return ret;
 	}
 	timer_setup(&ctx->rpm_timer, sample_timer, 0);
-	devm_add_action_or_reset(dev, pwm_fan_pwm_disable, ctx);
+	ret = devm_add_action_or_reset(dev, pwm_fan_pwm_disable, ctx);
+	if (ret)
+		return ret;
 
 	of_property_read_u32(dev->of_node, "pulses-per-revolution", &ppr);
 	ctx->pulses_per_revolution = ppr;
diff --git a/drivers/hwmon/scmi-hwmon.c b/drivers/hwmon/scmi-hwmon.c
index a80183a488c5..8c70f6250241 100644
--- a/drivers/hwmon/scmi-hwmon.c
+++ b/drivers/hwmon/scmi-hwmon.c
@@ -99,7 +99,7 @@ static enum hwmon_sensor_types scmi_types[] = {
 	[ENERGY] = hwmon_energy,
 };
 
-static u32 hwmon_attributes[] = {
+static u32 hwmon_attributes[hwmon_max] = {
 	[hwmon_chip] = HWMON_C_REGISTER_TZ,
 	[hwmon_temp] = HWMON_T_INPUT | HWMON_T_LABEL,
 	[hwmon_in] = HWMON_I_INPUT | HWMON_I_LABEL,
diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c
index 8de109de171f..e43e9ef0617c 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-etf.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c
@@ -592,13 +592,6 @@ int tmc_read_prepare_etb(struct tmc_drvdata *drvdata)
 		goto out;
 	}
 
-	/* There is no point in reading a TMC in HW FIFO mode */
-	mode = readl_relaxed(drvdata->base + TMC_MODE);
-	if (mode != TMC_MODE_CIRCULAR_BUFFER) {
-		ret = -EINVAL;
-		goto out;
-	}
-
 	/* Don't interfere if operated from Perf */
 	if (drvdata->mode == CS_MODE_PERF) {
 		ret = -EINVAL;
@@ -612,8 +605,15 @@ int tmc_read_prepare_etb(struct tmc_drvdata *drvdata)
 	}
 
 	/* Disable the TMC if need be */
-	if (drvdata->mode == CS_MODE_SYSFS)
+	if (drvdata->mode == CS_MODE_SYSFS) {
+		/* There is no point in reading a TMC in HW FIFO mode */
+		mode = readl_relaxed(drvdata->base + TMC_MODE);
+		if (mode != TMC_MODE_CIRCULAR_BUFFER) {
+			ret = -EINVAL;
+			goto out;
+		}
 		__tmc_etb_disable_hw(drvdata);
+	}
 
 	drvdata->reading = true;
 out:
@@ -635,15 +635,14 @@ int tmc_read_unprepare_etb(struct tmc_drvdata *drvdata)
 
 	spin_lock_irqsave(&drvdata->spinlock, flags);
 
-	/* There is no point in reading a TMC in HW FIFO mode */
-	mode = readl_relaxed(drvdata->base + TMC_MODE);
-	if (mode != TMC_MODE_CIRCULAR_BUFFER) {
-		spin_unlock_irqrestore(&drvdata->spinlock, flags);
-		return -EINVAL;
-	}
-
 	/* Re-enable the TMC if need be */
 	if (drvdata->mode == CS_MODE_SYSFS) {
+		/* There is no point in reading a TMC in HW FIFO mode */
+		mode = readl_relaxed(drvdata->base + TMC_MODE);
+		if (mode != TMC_MODE_CIRCULAR_BUFFER) {
+			spin_unlock_irqrestore(&drvdata->spinlock, flags);
+			return -EINVAL;
+		}
 		/*
 		 * The trace run will continue with the same allocated trace
 		 * buffer. As such zero-out the buffer so that we don't end
diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c
index 3fe7967efa51..1ed2ea51f222 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-etr.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c
@@ -1525,7 +1525,7 @@ tmc_update_etr_buffer(struct coresight_device *csdev,
 		goto out;
 	}
 
-	if (WARN_ON(drvdata->perf_data != etr_perf)) {
+	if (WARN_ON(drvdata->perf_buf != etr_buf)) {
 		lost = true;
 		spin_unlock_irqrestore(&drvdata->spinlock, flags);
 		goto out;
@@ -1537,8 +1537,6 @@ tmc_update_etr_buffer(struct coresight_device *csdev,
 	tmc_sync_etr_buf(drvdata);
 
 	CS_LOCK(drvdata->base);
-	/* Reset perf specific data */
-	drvdata->perf_data = NULL;
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
 	size = etr_buf->len;
@@ -1592,7 +1590,6 @@ static int tmc_enable_etr_sink_perf(struct coresight_device *csdev, void *data)
 	}
 
 	etr_perf->head = PERF_IDX2OFF(handle->head, etr_perf);
-	drvdata->perf_data = etr_perf;
 
 	/*
 	 * No HW configuration is needed if the sink is already in
@@ -1608,6 +1605,7 @@ static int tmc_enable_etr_sink_perf(struct coresight_device *csdev, void *data)
 		/* Associate with monitored process. */
 		drvdata->pid = pid;
 		drvdata->mode = CS_MODE_PERF;
+		drvdata->perf_buf = etr_perf->etr_buf;
 		atomic_inc(csdev->refcnt);
 	}
 
@@ -1653,6 +1651,8 @@ static int tmc_disable_etr_sink(struct coresight_device *csdev)
 	/* Dissociate from monitored process. */
 	drvdata->pid = -1;
 	drvdata->mode = CS_MODE_DISABLED;
+	/* Reset perf specific data */
+	drvdata->perf_buf = NULL;
 
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
diff --git a/drivers/hwtracing/coresight/coresight-tmc.h b/drivers/hwtracing/coresight/coresight-tmc.h
index b66c82d271fa..46118e93f1a9 100644
--- a/drivers/hwtracing/coresight/coresight-tmc.h
+++ b/drivers/hwtracing/coresight/coresight-tmc.h
@@ -213,8 +213,8 @@ struct etr_buf {
  *		device configuration register (DEVID)
  * @idr:	Holds etr_bufs allocated for this ETR.
  * @idr_mutex:	Access serialisation for idr.
- * @perf_data:	PERF buffer for ETR.
- * @sysfs_data:	SYSFS buffer for ETR.
+ * @sysfs_buf:	SYSFS buffer for ETR.
+ * @perf_buf:	PERF buffer for ETR.
  * @etr_options: Bitmask of options to manage Silicon issues
  * @cpu:	CPU id this component is associated with
  */
@@ -245,6 +245,7 @@ struct tmc_drvdata {
 	void			*perf_data;
 	u32			etr_options;
 	int			cpu;
+	struct etr_buf		*perf_buf;
 };
 
 struct etr_buf_operations {
diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c
index 52f000d37bac..9ea1d8f54465 100644
--- a/drivers/hwtracing/intel_th/core.c
+++ b/drivers/hwtracing/intel_th/core.c
@@ -1030,15 +1030,30 @@ int intel_th_set_output(struct intel_th_device *thdev,
 {
 	struct intel_th_device *hub = to_intel_th_hub(thdev);
 	struct intel_th_driver *hubdrv = to_intel_th_driver(hub->dev.driver);
+	int ret;
 
 	/* In host mode, this is up to the external debugger, do nothing. */
 	if (hub->host_mode)
 		return 0;
 
-	if (!hubdrv->set_output)
-		return -ENOTSUPP;
+	/*
+	 * hub is instantiated together with the source device that
+	 * calls here, so guaranteed to be present.
+	 */
+	hubdrv = to_intel_th_driver(hub->dev.driver);
+	if (!hubdrv || !try_module_get(hubdrv->driver.owner))
+		return -EINVAL;
+
+	if (!hubdrv->set_output) {
+		ret = -ENOTSUPP;
+		goto out;
+	}
+
+	ret = hubdrv->set_output(hub, master);
 
-	return hubdrv->set_output(hub, master);
+out:
+	module_put(hubdrv->driver.owner);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(intel_th_set_output);
 
diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c
index cfd48c81b9d9..e73ed7ac0cea 100644
--- a/drivers/hwtracing/intel_th/msu.c
+++ b/drivers/hwtracing/intel_th/msu.c
@@ -535,7 +535,7 @@ static int msc_configure(struct msc *msc)
 	lockdep_assert_held(&msc->buf_mutex);
 
 	if (msc->mode > MSC_MODE_MULTI)
-		return -ENOTSUPP;
+		return -EINVAL;
 
 	if (msc->mode == MSC_MODE_MULTI)
 		msc_buffer_clear_hw_header(msc);
@@ -1029,7 +1029,7 @@ static int msc_buffer_alloc(struct msc *msc, unsigned long *nr_pages,
 	} else if (msc->mode == MSC_MODE_MULTI) {
 		ret = msc_buffer_multi_alloc(msc, nr_pages, nr_wins);
 	} else {
-		ret = -ENOTSUPP;
+		ret = -EINVAL;
 	}
 
 	if (!ret) {
@@ -1252,7 +1252,7 @@ static ssize_t intel_th_msc_read(struct file *file, char __user *buf,
 		if (ret >= 0)
 			*ppos = iter->offset;
 	} else {
-		ret = -ENOTSUPP;
+		ret = -EINVAL;
 	}
 
 put_count:
diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c
index e9d90b53bbc4..0d26484d6795 100644
--- a/drivers/hwtracing/intel_th/pci.c
+++ b/drivers/hwtracing/intel_th/pci.c
@@ -230,15 +230,35 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
 	},
 	{
+		/* Tiger Lake PCH-H */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x43a6),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
+	{
 		/* Jasper Lake PCH */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4da6),
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
 	},
 	{
+		/* Jasper Lake CPU */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4e29),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
+	{
+		/* Elkhart Lake CPU */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4529),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
+	{
 		/* Elkhart Lake */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4b26),
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
 	},
+	{
+		/* Emmitsburg PCH */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x1bcc),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
 	{ 0 },
 };
 
diff --git a/drivers/hwtracing/intel_th/sth.c b/drivers/hwtracing/intel_th/sth.c
index 3a1f4e650378..a1529f571491 100644
--- a/drivers/hwtracing/intel_th/sth.c
+++ b/drivers/hwtracing/intel_th/sth.c
@@ -161,9 +161,7 @@ static int sth_stm_link(struct stm_data *stm_data, unsigned int master,
 {
 	struct sth_device *sth = container_of(stm_data, struct sth_device, stm);
 
-	intel_th_set_output(to_intel_th_device(sth->dev), master);
-
-	return 0;
+	return intel_th_set_output(to_intel_th_device(sth->dev), master);
 }
 
 static int intel_th_sw_init(struct sth_device *sth)
diff --git a/drivers/hwtracing/stm/p_sys-t.c b/drivers/hwtracing/stm/p_sys-t.c
index b178a5495b67..360b5c03df95 100644
--- a/drivers/hwtracing/stm/p_sys-t.c
+++ b/drivers/hwtracing/stm/p_sys-t.c
@@ -238,7 +238,7 @@ static struct configfs_attribute *sys_t_policy_attrs[] = {
 static inline bool sys_t_need_ts(struct sys_t_output *op)
 {
 	if (op->node.ts_interval &&
-	    time_after(op->ts_jiffies + op->node.ts_interval, jiffies)) {
+	    time_after(jiffies, op->ts_jiffies + op->node.ts_interval)) {
 		op->ts_jiffies = jiffies;
 
 		return true;
@@ -250,8 +250,8 @@ static inline bool sys_t_need_ts(struct sys_t_output *op)
 static bool sys_t_need_clock_sync(struct sys_t_output *op)
 {
 	if (op->node.clocksync_interval &&
-	    time_after(op->clocksync_jiffies + op->node.clocksync_interval,
-		       jiffies)) {
+	    time_after(jiffies,
+		       op->clocksync_jiffies + op->node.clocksync_interval)) {
 		op->clocksync_jiffies = jiffies;
 
 		return true;
diff --git a/drivers/i2c/algos/i2c-algo-pca.c b/drivers/i2c/algos/i2c-algo-pca.c
index 5ac93f41bfec..8ea850eed18f 100644
--- a/drivers/i2c/algos/i2c-algo-pca.c
+++ b/drivers/i2c/algos/i2c-algo-pca.c
@@ -314,7 +314,8 @@ static int pca_xfer(struct i2c_adapter *i2c_adap,
 			DEB2("BUS ERROR - SDA Stuck low\n");
 			pca_reset(adap);
 			goto out;
-		case 0x90: /* Bus error - SCL stuck low */
+		case 0x78: /* Bus error - SCL stuck low (PCA9665) */
+		case 0x90: /* Bus error - SCL stuck low (PCA9564) */
 			DEB2("BUS ERROR - SCL Stuck low\n");
 			pca_reset(adap);
 			goto out;
diff --git a/drivers/i2c/busses/i2c-altera.c b/drivers/i2c/busses/i2c-altera.c
index 5255d3755411..a60042431370 100644
--- a/drivers/i2c/busses/i2c-altera.c
+++ b/drivers/i2c/busses/i2c-altera.c
@@ -70,6 +70,7 @@
  * @isr_mask: cached copy of local ISR enables.
  * @isr_status: cached copy of local ISR status.
  * @lock: spinlock for IRQ synchronization.
+ * @isr_mutex: mutex for IRQ thread.
  */
 struct altr_i2c_dev {
 	void __iomem *base;
@@ -86,6 +87,7 @@ struct altr_i2c_dev {
 	u32 isr_mask;
 	u32 isr_status;
 	spinlock_t lock;	/* IRQ synchronization */
+	struct mutex isr_mutex;
 };
 
 static void
@@ -171,7 +173,7 @@ static void altr_i2c_init(struct altr_i2c_dev *idev)
 	/* SCL Low Time */
 	writel(t_low, idev->base + ALTR_I2C_SCL_LOW);
 	/* SDA Hold Time, 300ns */
-	writel(div_u64(300 * clk_mhz, 1000), idev->base + ALTR_I2C_SDA_HOLD);
+	writel(3 * clk_mhz / 10, idev->base + ALTR_I2C_SDA_HOLD);
 
 	/* Mask all master interrupt bits */
 	altr_i2c_int_enable(idev, ALTR_I2C_ALL_IRQ, false);
@@ -245,10 +247,11 @@ static irqreturn_t altr_i2c_isr(int irq, void *_dev)
 	struct altr_i2c_dev *idev = _dev;
 	u32 status = idev->isr_status;
 
+	mutex_lock(&idev->isr_mutex);
 	if (!idev->msg) {
 		dev_warn(idev->dev, "unexpected interrupt\n");
 		altr_i2c_int_clear(idev, ALTR_I2C_ALL_IRQ);
-		return IRQ_HANDLED;
+		goto out;
 	}
 	read = (idev->msg->flags & I2C_M_RD) != 0;
 
@@ -301,6 +304,8 @@ static irqreturn_t altr_i2c_isr(int irq, void *_dev)
 		complete(&idev->msg_complete);
 		dev_dbg(idev->dev, "Message Complete\n");
 	}
+out:
+	mutex_unlock(&idev->isr_mutex);
 
 	return IRQ_HANDLED;
 }
@@ -312,6 +317,7 @@ static int altr_i2c_xfer_msg(struct altr_i2c_dev *idev, struct i2c_msg *msg)
 	u32 value;
 	u8 addr = i2c_8bit_addr_from_msg(msg);
 
+	mutex_lock(&idev->isr_mutex);
 	idev->msg = msg;
 	idev->msg_len = msg->len;
 	idev->buf = msg->buf;
@@ -336,6 +342,7 @@ static int altr_i2c_xfer_msg(struct altr_i2c_dev *idev, struct i2c_msg *msg)
 		altr_i2c_int_enable(idev, imask, true);
 		altr_i2c_fill_tx_fifo(idev);
 	}
+	mutex_unlock(&idev->isr_mutex);
 
 	time_left = wait_for_completion_timeout(&idev->msg_complete,
 						ALTR_I2C_XFER_TIMEOUT);
@@ -384,7 +391,6 @@ static int altr_i2c_probe(struct platform_device *pdev)
 	struct altr_i2c_dev *idev = NULL;
 	struct resource *res;
 	int irq, ret;
-	u32 val;
 
 	idev = devm_kzalloc(&pdev->dev, sizeof(*idev), GFP_KERNEL);
 	if (!idev)
@@ -410,18 +416,19 @@ static int altr_i2c_probe(struct platform_device *pdev)
 	idev->dev = &pdev->dev;
 	init_completion(&idev->msg_complete);
 	spin_lock_init(&idev->lock);
+	mutex_init(&idev->isr_mutex);
 
-	val = device_property_read_u32(idev->dev, "fifo-size",
+	ret = device_property_read_u32(idev->dev, "fifo-size",
 				       &idev->fifo_size);
-	if (val) {
+	if (ret) {
 		dev_err(&pdev->dev, "FIFO size set to default of %d\n",
 			ALTR_I2C_DFLT_FIFO_SZ);
 		idev->fifo_size = ALTR_I2C_DFLT_FIFO_SZ;
 	}
 
-	val = device_property_read_u32(idev->dev, "clock-frequency",
+	ret = device_property_read_u32(idev->dev, "clock-frequency",
 				       &idev->bus_clk_rate);
-	if (val) {
+	if (ret) {
 		dev_err(&pdev->dev, "Default to 100kHz\n");
 		idev->bus_clk_rate = 100000;	/* default clock rate */
 	}
diff --git a/drivers/i2c/busses/i2c-amd-mp2-pci.c b/drivers/i2c/busses/i2c-amd-mp2-pci.c
index 455e1f36a2a3..2441682269b3 100644
--- a/drivers/i2c/busses/i2c-amd-mp2-pci.c
+++ b/drivers/i2c/busses/i2c-amd-mp2-pci.c
@@ -349,12 +349,12 @@ static int amd_mp2_pci_probe(struct pci_dev *pci_dev,
 	if (!privdata)
 		return -ENOMEM;
 
+	privdata->pci_dev = pci_dev;
 	rc = amd_mp2_pci_init(privdata, pci_dev);
 	if (rc)
 		return rc;
 
 	mutex_init(&privdata->c2p_lock);
-	privdata->pci_dev = pci_dev;
 
 	pm_runtime_set_autosuspend_delay(&pci_dev->dev, 1000);
 	pm_runtime_use_autosuspend(&pci_dev->dev);
diff --git a/drivers/i2c/busses/i2c-aspeed.c b/drivers/i2c/busses/i2c-aspeed.c
index 7b098ff5f5dd..dad6e432de89 100644
--- a/drivers/i2c/busses/i2c-aspeed.c
+++ b/drivers/i2c/busses/i2c-aspeed.c
@@ -603,6 +603,7 @@ static irqreturn_t aspeed_i2c_bus_irq(int irq, void *dev_id)
 	/* Ack all interrupts except for Rx done */
 	writel(irq_received & ~ASPEED_I2CD_INTR_RX_DONE,
 	       bus->base + ASPEED_I2C_INTR_STS_REG);
+	readl(bus->base + ASPEED_I2C_INTR_STS_REG);
 	irq_remaining = irq_received;
 
 #if IS_ENABLED(CONFIG_I2C_SLAVE)
@@ -645,9 +646,11 @@ static irqreturn_t aspeed_i2c_bus_irq(int irq, void *dev_id)
 			irq_received, irq_handled);
 
 	/* Ack Rx done */
-	if (irq_received & ASPEED_I2CD_INTR_RX_DONE)
+	if (irq_received & ASPEED_I2CD_INTR_RX_DONE) {
 		writel(ASPEED_I2CD_INTR_RX_DONE,
 		       bus->base + ASPEED_I2C_INTR_STS_REG);
+		readl(bus->base + ASPEED_I2C_INTR_STS_REG);
+	}
 	spin_unlock(&bus->lock);
 	return irq_remaining ? IRQ_NONE : IRQ_HANDLED;
 }
diff --git a/drivers/i2c/busses/i2c-cadence.c b/drivers/i2c/busses/i2c-cadence.c
index 9d71ce15db05..a51d3b795770 100644
--- a/drivers/i2c/busses/i2c-cadence.c
+++ b/drivers/i2c/busses/i2c-cadence.c
@@ -377,10 +377,8 @@ static void cdns_i2c_mrecv(struct cdns_i2c *id)
 	 * Check for the message size against FIFO depth and set the
 	 * 'hold bus' bit if it is greater than FIFO depth.
 	 */
-	if ((id->recv_count > CDNS_I2C_FIFO_DEPTH)  || id->bus_hold_flag)
+	if (id->recv_count > CDNS_I2C_FIFO_DEPTH)
 		ctrl_reg |= CDNS_I2C_CR_HOLD;
-	else
-		ctrl_reg = ctrl_reg & ~CDNS_I2C_CR_HOLD;
 
 	cdns_i2c_writereg(ctrl_reg, CDNS_I2C_CR_OFFSET);
 
@@ -437,11 +435,8 @@ static void cdns_i2c_msend(struct cdns_i2c *id)
 	 * Check for the message size against FIFO depth and set the
 	 * 'hold bus' bit if it is greater than FIFO depth.
 	 */
-	if ((id->send_count > CDNS_I2C_FIFO_DEPTH) || id->bus_hold_flag)
+	if (id->send_count > CDNS_I2C_FIFO_DEPTH)
 		ctrl_reg |= CDNS_I2C_CR_HOLD;
-	else
-		ctrl_reg = ctrl_reg & ~CDNS_I2C_CR_HOLD;
-
 	cdns_i2c_writereg(ctrl_reg, CDNS_I2C_CR_OFFSET);
 
 	/* Clear the interrupts in interrupt status register. */
diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c
index ddfb81872906..e138c159dbbc 100644
--- a/drivers/i2c/busses/i2c-designware-platdrv.c
+++ b/drivers/i2c/busses/i2c-designware-platdrv.c
@@ -346,8 +346,10 @@ static int dw_i2c_plat_probe(struct platform_device *pdev)
 
 	/* Optional interface clock */
 	dev->pclk = devm_clk_get_optional(&pdev->dev, "pclk");
-	if (IS_ERR(dev->pclk))
-		return PTR_ERR(dev->pclk);
+	if (IS_ERR(dev->pclk)) {
+		ret = PTR_ERR(dev->pclk);
+		goto exit_reset;
+	}
 
 	dev->clk = devm_clk_get(&pdev->dev, NULL);
 	if (!i2c_dw_prepare_clk(dev, true)) {
@@ -370,10 +372,16 @@ static int dw_i2c_plat_probe(struct platform_device *pdev)
 	adap->dev.of_node = pdev->dev.of_node;
 	adap->nr = -1;
 
-	dev_pm_set_driver_flags(&pdev->dev,
-				DPM_FLAG_SMART_PREPARE |
-				DPM_FLAG_SMART_SUSPEND |
-				DPM_FLAG_LEAVE_SUSPENDED);
+	if (dev->flags & ACCESS_NO_IRQ_SUSPEND) {
+		dev_pm_set_driver_flags(&pdev->dev,
+					DPM_FLAG_SMART_PREPARE |
+					DPM_FLAG_LEAVE_SUSPENDED);
+	} else {
+		dev_pm_set_driver_flags(&pdev->dev,
+					DPM_FLAG_SMART_PREPARE |
+					DPM_FLAG_SMART_SUSPEND |
+					DPM_FLAG_LEAVE_SUSPENDED);
+	}
 
 	/* The code below assumes runtime PM to be disabled. */
 	WARN_ON(pm_runtime_enabled(&pdev->dev));
diff --git a/drivers/i2c/busses/i2c-eg20t.c b/drivers/i2c/busses/i2c-eg20t.c
index bb810dee8fb5..73f139690e4e 100644
--- a/drivers/i2c/busses/i2c-eg20t.c
+++ b/drivers/i2c/busses/i2c-eg20t.c
@@ -180,6 +180,7 @@ static const struct pci_device_id pch_pcidev_id[] = {
 	{ PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ML7831_I2C), 1, },
 	{0,}
 };
+MODULE_DEVICE_TABLE(pci, pch_pcidev_id);
 
 static irqreturn_t pch_i2c_handler(int irq, void *pData);
 
diff --git a/drivers/i2c/busses/i2c-fsi.c b/drivers/i2c/busses/i2c-fsi.c
index 1e2be2219a60..46aef609fb70 100644
--- a/drivers/i2c/busses/i2c-fsi.c
+++ b/drivers/i2c/busses/i2c-fsi.c
@@ -98,7 +98,7 @@
 #define I2C_STAT_DAT_REQ	BIT(25)
 #define I2C_STAT_CMD_COMP	BIT(24)
 #define I2C_STAT_STOP_ERR	BIT(23)
-#define I2C_STAT_MAX_PORT	GENMASK(19, 16)
+#define I2C_STAT_MAX_PORT	GENMASK(22, 16)
 #define I2C_STAT_ANY_INT	BIT(15)
 #define I2C_STAT_SCL_IN		BIT(11)
 #define I2C_STAT_SDA_IN		BIT(10)
diff --git a/drivers/i2c/busses/i2c-gpio.c b/drivers/i2c/busses/i2c-gpio.c
index 3a9e840a3546..a4a6825c8758 100644
--- a/drivers/i2c/busses/i2c-gpio.c
+++ b/drivers/i2c/busses/i2c-gpio.c
@@ -348,7 +348,7 @@ static struct gpio_desc *i2c_gpio_get_desc(struct device *dev,
 	if (ret == -ENOENT)
 		retdesc = ERR_PTR(-EPROBE_DEFER);
 
-	if (ret != -EPROBE_DEFER)
+	if (PTR_ERR(retdesc) != -EPROBE_DEFER)
 		dev_err(dev, "error trying to get descriptor: %d\n", ret);
 
 	return retdesc;
diff --git a/drivers/i2c/busses/i2c-hix5hd2.c b/drivers/i2c/busses/i2c-hix5hd2.c
index 4df1434b3597..16cbf1ebd03d 100644
--- a/drivers/i2c/busses/i2c-hix5hd2.c
+++ b/drivers/i2c/busses/i2c-hix5hd2.c
@@ -478,6 +478,7 @@ static int hix5hd2_i2c_remove(struct platform_device *pdev)
 	i2c_del_adapter(&priv->adap);
 	pm_runtime_disable(priv->dev);
 	pm_runtime_set_suspended(priv->dev);
+	clk_disable_unprepare(priv->clk);
 
 	return 0;
 }
diff --git a/drivers/i2c/busses/i2c-jz4780.c b/drivers/i2c/busses/i2c-jz4780.c
index 25dcd73acd63..8f0e1f802f2d 100644
--- a/drivers/i2c/busses/i2c-jz4780.c
+++ b/drivers/i2c/busses/i2c-jz4780.c
@@ -73,25 +73,6 @@
 #define JZ4780_I2C_STA_TFNF		BIT(1)
 #define JZ4780_I2C_STA_ACT		BIT(0)
 
-static const char * const jz4780_i2c_abrt_src[] = {
-	"ABRT_7B_ADDR_NOACK",
-	"ABRT_10ADDR1_NOACK",
-	"ABRT_10ADDR2_NOACK",
-	"ABRT_XDATA_NOACK",
-	"ABRT_GCALL_NOACK",
-	"ABRT_GCALL_READ",
-	"ABRT_HS_ACKD",
-	"SBYTE_ACKDET",
-	"ABRT_HS_NORSTRT",
-	"SBYTE_NORSTRT",
-	"ABRT_10B_RD_NORSTRT",
-	"ABRT_MASTER_DIS",
-	"ARB_LOST",
-	"SLVFLUSH_TXFIFO",
-	"SLV_ARBLOST",
-	"SLVRD_INTX",
-};
-
 #define JZ4780_I2C_INTST_IGC		BIT(11)
 #define JZ4780_I2C_INTST_ISTT		BIT(10)
 #define JZ4780_I2C_INTST_ISTP		BIT(9)
@@ -529,21 +510,8 @@ done:
 
 static void jz4780_i2c_txabrt(struct jz4780_i2c *i2c, int src)
 {
-	int i;
-
-	dev_err(&i2c->adap.dev, "txabrt: 0x%08x\n", src);
-	dev_err(&i2c->adap.dev, "device addr=%x\n",
-		jz4780_i2c_readw(i2c, JZ4780_I2C_TAR));
-	dev_err(&i2c->adap.dev, "send cmd count:%d  %d\n",
-		i2c->cmd, i2c->cmd_buf[i2c->cmd]);
-	dev_err(&i2c->adap.dev, "receive data count:%d  %d\n",
-		i2c->cmd, i2c->data_buf[i2c->cmd]);
-
-	for (i = 0; i < 16; i++) {
-		if (src & BIT(i))
-			dev_dbg(&i2c->adap.dev, "I2C TXABRT[%d]=%s\n",
-				i, jz4780_i2c_abrt_src[i]);
-	}
+	dev_dbg(&i2c->adap.dev, "txabrt: 0x%08x, cmd: %d, send: %d, recv: %d\n",
+		src, i2c->cmd, i2c->cmd_buf[i2c->cmd], i2c->data_buf[i2c->cmd]);
 }
 
 static inline int jz4780_i2c_xfer_read(struct jz4780_i2c *i2c,
diff --git a/drivers/i2c/busses/i2c-mlxcpld.c b/drivers/i2c/busses/i2c-mlxcpld.c
index 2fd717d8dd30..71d7bae2cbca 100644
--- a/drivers/i2c/busses/i2c-mlxcpld.c
+++ b/drivers/i2c/busses/i2c-mlxcpld.c
@@ -337,9 +337,9 @@ static int mlxcpld_i2c_wait_for_tc(struct mlxcpld_i2c_priv *priv)
 		if (priv->smbus_block && (val & MLXCPLD_I2C_SMBUS_BLK_BIT)) {
 			mlxcpld_i2c_read_comm(priv, MLXCPLD_LPCI2C_NUM_DAT_REG,
 					      &datalen, 1);
-			if (unlikely(datalen > (I2C_SMBUS_BLOCK_MAX + 1))) {
+			if (unlikely(datalen > I2C_SMBUS_BLOCK_MAX)) {
 				dev_err(priv->dev, "Incorrect smbus block read message len\n");
-				return -E2BIG;
+				return -EPROTO;
 			}
 		} else {
 			datalen = priv->xfer.data_len;
diff --git a/drivers/i2c/busses/i2c-nvidia-gpu.c b/drivers/i2c/busses/i2c-nvidia-gpu.c
index ee2412b7459c..78c5fcc0406c 100644
--- a/drivers/i2c/busses/i2c-nvidia-gpu.c
+++ b/drivers/i2c/busses/i2c-nvidia-gpu.c
@@ -8,6 +8,7 @@
 #include <linux/delay.h>
 #include <linux/i2c.h>
 #include <linux/interrupt.h>
+#include <linux/iopoll.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/platform_device.h>
@@ -75,20 +76,15 @@ static void gpu_enable_i2c_bus(struct gpu_i2c_dev *i2cd)
 
 static int gpu_i2c_check_status(struct gpu_i2c_dev *i2cd)
 {
-	unsigned long target = jiffies + msecs_to_jiffies(1000);
 	u32 val;
+	int ret;
 
-	do {
-		val = readl(i2cd->regs + I2C_MST_CNTL);
-		if (!(val & I2C_MST_CNTL_CYCLE_TRIGGER))
-			break;
-		if ((val & I2C_MST_CNTL_STATUS) !=
-				I2C_MST_CNTL_STATUS_BUS_BUSY)
-			break;
-		usleep_range(500, 600);
-	} while (time_is_after_jiffies(target));
-
-	if (time_is_before_jiffies(target)) {
+	ret = readl_poll_timeout(i2cd->regs + I2C_MST_CNTL, val,
+				 !(val & I2C_MST_CNTL_CYCLE_TRIGGER) ||
+				 (val & I2C_MST_CNTL_STATUS) != I2C_MST_CNTL_STATUS_BUS_BUSY,
+				 500, 1000 * USEC_PER_MSEC);
+
+	if (ret) {
 		dev_err(i2cd->dev, "i2c timeout error %x\n", val);
 		return -ETIMEDOUT;
 	}
diff --git a/drivers/i2c/busses/i2c-pca-platform.c b/drivers/i2c/busses/i2c-pca-platform.c
index a7a81846d5b1..635dd697ac0b 100644
--- a/drivers/i2c/busses/i2c-pca-platform.c
+++ b/drivers/i2c/busses/i2c-pca-platform.c
@@ -140,7 +140,7 @@ static int i2c_pca_pf_probe(struct platform_device *pdev)
 	int ret = 0;
 	int irq;
 
-	irq = platform_get_irq(pdev, 0);
+	irq = platform_get_irq_optional(pdev, 0);
 	/* If irq is 0, we do polling. */
 	if (irq < 0)
 		irq = 0;
diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c
index cba325eb852f..2f1ff472aa78 100644
--- a/drivers/i2c/busses/i2c-piix4.c
+++ b/drivers/i2c/busses/i2c-piix4.c
@@ -957,7 +957,8 @@ static int piix4_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	}
 
 	if (dev->vendor == PCI_VENDOR_ID_AMD &&
-	    dev->device == PCI_DEVICE_ID_AMD_HUDSON2_SMBUS) {
+	    (dev->device == PCI_DEVICE_ID_AMD_HUDSON2_SMBUS ||
+	     dev->device == PCI_DEVICE_ID_AMD_KERNCZ_SMBUS)) {
 		retval = piix4_setup_sb800(dev, id, 1);
 	}
 
diff --git a/drivers/i2c/busses/i2c-pxa.c b/drivers/i2c/busses/i2c-pxa.c
index 2c3c3d6935c0..d0c557c8d80f 100644
--- a/drivers/i2c/busses/i2c-pxa.c
+++ b/drivers/i2c/busses/i2c-pxa.c
@@ -312,11 +312,10 @@ static void i2c_pxa_scream_blue_murder(struct pxa_i2c *i2c, const char *why)
 	dev_err(dev, "IBMR: %08x IDBR: %08x ICR: %08x ISR: %08x\n",
 		readl(_IBMR(i2c)), readl(_IDBR(i2c)), readl(_ICR(i2c)),
 		readl(_ISR(i2c)));
-	dev_dbg(dev, "log: ");
+	dev_err(dev, "log:");
 	for (i = 0; i < i2c->irqlogidx; i++)
-		pr_debug("[%08x:%08x] ", i2c->isrlog[i], i2c->icrlog[i]);
-
-	pr_debug("\n");
+		pr_cont(" [%03x:%05x]", i2c->isrlog[i], i2c->icrlog[i]);
+	pr_cont("\n");
 }
 
 #else /* ifdef DEBUG */
@@ -706,11 +705,9 @@ static inline void i2c_pxa_stop_message(struct pxa_i2c *i2c)
 {
 	u32 icr;
 
-	/*
-	 * Clear the STOP and ACK flags
-	 */
+	/* Clear the START, STOP, ACK, TB and MA flags */
 	icr = readl(_ICR(i2c));
-	icr &= ~(ICR_STOP | ICR_ACKNAK);
+	icr &= ~(ICR_START | ICR_STOP | ICR_ACKNAK | ICR_TB | ICR_MA);
 	writel(icr, _ICR(i2c));
 }
 
diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c
index 715ddc5d0eac..509fd583de89 100644
--- a/drivers/i2c/busses/i2c-qcom-geni.c
+++ b/drivers/i2c/busses/i2c-qcom-geni.c
@@ -367,7 +367,6 @@ static int geni_i2c_rx_one_msg(struct geni_i2c_dev *gi2c, struct i2c_msg *msg,
 		geni_se_select_mode(se, GENI_SE_FIFO);
 
 	writel_relaxed(len, se->base + SE_I2C_RX_TRANS_LEN);
-	geni_se_setup_m_cmd(se, I2C_READ, m_param);
 
 	if (dma_buf && geni_se_rx_dma_prep(se, dma_buf, len, &rx_dma)) {
 		geni_se_select_mode(se, GENI_SE_FIFO);
@@ -375,6 +374,8 @@ static int geni_i2c_rx_one_msg(struct geni_i2c_dev *gi2c, struct i2c_msg *msg,
 		dma_buf = NULL;
 	}
 
+	geni_se_setup_m_cmd(se, I2C_READ, m_param);
+
 	time_left = wait_for_completion_timeout(&gi2c->done, XFER_TIMEOUT);
 	if (!time_left)
 		geni_i2c_abort_xfer(gi2c);
@@ -408,7 +409,6 @@ static int geni_i2c_tx_one_msg(struct geni_i2c_dev *gi2c, struct i2c_msg *msg,
 		geni_se_select_mode(se, GENI_SE_FIFO);
 
 	writel_relaxed(len, se->base + SE_I2C_TX_TRANS_LEN);
-	geni_se_setup_m_cmd(se, I2C_WRITE, m_param);
 
 	if (dma_buf && geni_se_tx_dma_prep(se, dma_buf, len, &tx_dma)) {
 		geni_se_select_mode(se, GENI_SE_FIFO);
@@ -416,6 +416,8 @@ static int geni_i2c_tx_one_msg(struct geni_i2c_dev *gi2c, struct i2c_msg *msg,
 		dma_buf = NULL;
 	}
 
+	geni_se_setup_m_cmd(se, I2C_WRITE, m_param);
+
 	if (!dma_buf) /* Get FIFO IRQ */
 		writel_relaxed(1, se->base + SE_GENI_TX_WATERMARK_REG);
 
diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c
index 531c01100b56..0b90aa0318df 100644
--- a/drivers/i2c/busses/i2c-rcar.c
+++ b/drivers/i2c/busses/i2c-rcar.c
@@ -580,13 +580,14 @@ static bool rcar_i2c_slave_irq(struct rcar_i2c_priv *priv)
 			rcar_i2c_write(priv, ICSIER, SDR | SSR | SAR);
 		}
 
-		rcar_i2c_write(priv, ICSSR, ~SAR & 0xff);
+		/* Clear SSR, too, because of old STOPs to other clients than us */
+		rcar_i2c_write(priv, ICSSR, ~(SAR | SSR) & 0xff);
 	}
 
 	/* master sent stop */
 	if (ssr_filtered & SSR) {
 		i2c_slave_event(priv->slave, I2C_SLAVE_STOP, &value);
-		rcar_i2c_write(priv, ICSIER, SAR | SSR);
+		rcar_i2c_write(priv, ICSIER, SAR);
 		rcar_i2c_write(priv, ICSSR, ~SSR & 0xff);
 	}
 
@@ -850,7 +851,7 @@ static int rcar_reg_slave(struct i2c_client *slave)
 	priv->slave = slave;
 	rcar_i2c_write(priv, ICSAR, slave->addr);
 	rcar_i2c_write(priv, ICSSR, 0);
-	rcar_i2c_write(priv, ICSIER, SAR | SSR);
+	rcar_i2c_write(priv, ICSIER, SAR);
 	rcar_i2c_write(priv, ICSCR, SIE | SDBS);
 
 	return 0;
@@ -862,11 +863,14 @@ static int rcar_unreg_slave(struct i2c_client *slave)
 
 	WARN_ON(!priv->slave);
 
-	/* disable irqs and ensure none is running before clearing ptr */
+	/* ensure no irq is running before clearing ptr */
+	disable_irq(priv->irq);
 	rcar_i2c_write(priv, ICSIER, 0);
-	rcar_i2c_write(priv, ICSCR, 0);
+	rcar_i2c_write(priv, ICSSR, 0);
+	enable_irq(priv->irq);
+	rcar_i2c_write(priv, ICSCR, SDBS);
+	rcar_i2c_write(priv, ICSAR, 0); /* Gen2: must be 0 if not using slave */
 
-	synchronize_irq(priv->irq);
 	priv->slave = NULL;
 
 	pm_runtime_put(rcar_i2c_priv_to_dev(priv));
@@ -971,6 +975,8 @@ static int rcar_i2c_probe(struct platform_device *pdev)
 	if (ret < 0)
 		goto out_pm_put;
 
+	rcar_i2c_write(priv, ICSAR, 0); /* Gen2: must be 0 if not using slave */
+
 	if (priv->devtype == I2C_RCAR_GEN3) {
 		priv->rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL);
 		if (!IS_ERR(priv->rstc)) {
diff --git a/drivers/i2c/busses/i2c-st.c b/drivers/i2c/busses/i2c-st.c
index 54e1fc8a495e..f7f7b5b64720 100644
--- a/drivers/i2c/busses/i2c-st.c
+++ b/drivers/i2c/busses/i2c-st.c
@@ -434,6 +434,7 @@ static void st_i2c_wr_fill_tx_fifo(struct st_i2c_dev *i2c_dev)
 /**
  * st_i2c_rd_fill_tx_fifo() - Fill the Tx FIFO in read mode
  * @i2c_dev: Controller's private data
+ * @max: Maximum amount of data to fill into the Tx FIFO
  *
  * This functions fills the Tx FIFO with fixed pattern when
  * in read mode to trigger clock.
diff --git a/drivers/i2c/busses/i2c-stm32.c b/drivers/i2c/busses/i2c-stm32.c
index 07d5dfce68d4..1da347e6a358 100644
--- a/drivers/i2c/busses/i2c-stm32.c
+++ b/drivers/i2c/busses/i2c-stm32.c
@@ -20,13 +20,13 @@ struct stm32_i2c_dma *stm32_i2c_dma_request(struct device *dev,
 
 	dma = devm_kzalloc(dev, sizeof(*dma), GFP_KERNEL);
 	if (!dma)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	/* Request and configure I2C TX dma channel */
-	dma->chan_tx = dma_request_slave_channel(dev, "tx");
-	if (!dma->chan_tx) {
+	dma->chan_tx = dma_request_chan(dev, "tx");
+	if (IS_ERR(dma->chan_tx)) {
 		dev_dbg(dev, "can't request DMA tx channel\n");
-		ret = -EINVAL;
+		ret = PTR_ERR(dma->chan_tx);
 		goto fail_al;
 	}
 
@@ -42,10 +42,10 @@ struct stm32_i2c_dma *stm32_i2c_dma_request(struct device *dev,
 	}
 
 	/* Request and configure I2C RX dma channel */
-	dma->chan_rx = dma_request_slave_channel(dev, "rx");
-	if (!dma->chan_rx) {
+	dma->chan_rx = dma_request_chan(dev, "rx");
+	if (IS_ERR(dma->chan_rx)) {
 		dev_err(dev, "can't request DMA rx channel\n");
-		ret = -EINVAL;
+		ret = PTR_ERR(dma->chan_rx);
 		goto fail_tx;
 	}
 
@@ -75,7 +75,7 @@ fail_al:
 	devm_kfree(dev, dma);
 	dev_info(dev, "can't use DMA\n");
 
-	return NULL;
+	return ERR_PTR(ret);
 }
 
 void stm32_i2c_dma_free(struct stm32_i2c_dma *dma)
diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c
index 3fa0711bc77c..c2ac212ce70c 100644
--- a/drivers/i2c/busses/i2c-stm32f7.c
+++ b/drivers/i2c/busses/i2c-stm32f7.c
@@ -1264,8 +1264,8 @@ static int stm32f7_i2c_get_free_slave_id(struct stm32f7_i2c_dev *i2c_dev,
 	 * slave[0] supports 7-bit and 10-bit slave address
 	 * slave[1] supports 7-bit slave address only
 	 */
-	for (i = 0; i < STM32F7_I2C_MAX_SLAVE; i++) {
-		if (i == 1 && (slave->flags & I2C_CLIENT_PEC))
+	for (i = STM32F7_I2C_MAX_SLAVE - 1; i >= 0; i--) {
+		if (i == 1 && (slave->flags & I2C_CLIENT_TEN))
 			continue;
 		if (!i2c_dev->slave[i]) {
 			*id = i;
@@ -1951,6 +1951,15 @@ static int stm32f7_i2c_probe(struct platform_device *pdev)
 	i2c_dev->dma = stm32_i2c_dma_request(i2c_dev->dev, phy_addr,
 					     STM32F7_I2C_TXDR,
 					     STM32F7_I2C_RXDR);
+	if (PTR_ERR(i2c_dev->dma) == -ENODEV)
+		i2c_dev->dma = NULL;
+	else if (IS_ERR(i2c_dev->dma)) {
+		ret = PTR_ERR(i2c_dev->dma);
+		if (ret != -EPROBE_DEFER)
+			dev_err(&pdev->dev,
+				"Failed to request dma error %i\n", ret);
+		goto clk_free;
+	}
 
 	platform_set_drvdata(pdev, i2c_dev);
 
diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c
index 9a3bcfcad35f..ac5150ee0803 100644
--- a/drivers/i2c/i2c-core-acpi.c
+++ b/drivers/i2c/i2c-core-acpi.c
@@ -371,10 +371,18 @@ static struct i2c_adapter *i2c_acpi_find_adapter_by_handle(acpi_handle handle)
 static struct i2c_client *i2c_acpi_find_client_by_adev(struct acpi_device *adev)
 {
 	struct device *dev;
+	struct i2c_client *client;
 
 	dev = bus_find_device(&i2c_bus_type, NULL, adev,
 			      i2c_acpi_find_match_device);
-	return dev ? i2c_verify_client(dev) : NULL;
+	if (!dev)
+		return NULL;
+
+	client = i2c_verify_client(dev);
+	if (!client)
+		put_device(dev);
+
+	return client;
 }
 
 static int i2c_acpi_notify(struct notifier_block *nb, unsigned long value,
diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index 9e43508d4567..d46ae60fd8d0 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -186,10 +186,11 @@ int i2c_generic_scl_recovery(struct i2c_adapter *adap)
 	 * If we can set SDA, we will always create a STOP to ensure additional
 	 * pulses will do no harm. This is achieved by letting SDA follow SCL
 	 * half a cycle later. Check the 'incomplete_write_byte' fault injector
-	 * for details.
+	 * for details. Note that we must honour tsu:sto, 4us, but lets use 5us
+	 * here for simplicity.
 	 */
 	bri->set_scl(adap, scl);
-	ndelay(RECOVERY_NDELAY / 2);
+	ndelay(RECOVERY_NDELAY);
 	if (bri->set_sda)
 		bri->set_sda(adap, scl);
 	ndelay(RECOVERY_NDELAY / 2);
@@ -211,7 +212,13 @@ int i2c_generic_scl_recovery(struct i2c_adapter *adap)
 		scl = !scl;
 		bri->set_scl(adap, scl);
 		/* Creating STOP again, see above */
-		ndelay(RECOVERY_NDELAY / 2);
+		if (scl)  {
+			/* Honour minimum tsu:sto */
+			ndelay(RECOVERY_NDELAY);
+		} else {
+			/* Honour minimum tf and thd:dat */
+			ndelay(RECOVERY_NDELAY / 2);
+		}
 		if (bri->set_sda)
 			bri->set_sda(adap, scl);
 		ndelay(RECOVERY_NDELAY / 2);
@@ -329,8 +336,10 @@ static int i2c_device_probe(struct device *dev)
 		} else if (ACPI_COMPANION(dev)) {
 			irq = acpi_dev_gpio_irq_get(ACPI_COMPANION(dev), 0);
 		}
-		if (irq == -EPROBE_DEFER)
-			return irq;
+		if (irq == -EPROBE_DEFER) {
+			status = irq;
+			goto put_sync_adapter;
+		}
 
 		if (irq < 0)
 			irq = 0;
@@ -344,16 +353,20 @@ static int i2c_device_probe(struct device *dev)
 	 */
 	if (!driver->id_table &&
 	    !i2c_acpi_match_device(dev->driver->acpi_match_table, client) &&
-	    !i2c_of_match_device(dev->driver->of_match_table, client))
-		return -ENODEV;
+	    !i2c_of_match_device(dev->driver->of_match_table, client)) {
+		status = -ENODEV;
+		goto put_sync_adapter;
+	}
 
 	if (client->flags & I2C_CLIENT_WAKE) {
 		int wakeirq = -ENOENT;
 
 		if (dev->of_node) {
 			wakeirq = of_irq_get_byname(dev->of_node, "wakeup");
-			if (wakeirq == -EPROBE_DEFER)
-				return wakeirq;
+			if (wakeirq == -EPROBE_DEFER) {
+				status = wakeirq;
+				goto put_sync_adapter;
+			}
 		}
 
 		device_init_wakeup(&client->dev, true);
@@ -401,6 +414,10 @@ err_detach_pm_domain:
 err_clear_wakeup_irq:
 	dev_pm_clear_wake_irq(&client->dev);
 	device_init_wakeup(&client->dev, false);
+put_sync_adapter:
+	if (client->flags & I2C_CLIENT_HOST_NOTIFY)
+		pm_runtime_put_sync(&client->adapter->dev);
+
 	return status;
 }
 
@@ -721,7 +738,7 @@ static int i2c_dev_irq_from_resources(const struct resource *resources,
  * This returns the new i2c client, which may be saved for later use with
  * i2c_unregister_device(); or an ERR_PTR to describe the error.
  */
-static struct i2c_client *
+struct i2c_client *
 i2c_new_client_device(struct i2c_adapter *adap, struct i2c_board_info const *info)
 {
 	struct i2c_client	*client;
@@ -887,8 +904,7 @@ static struct i2c_driver dummy_driver = {
  * This returns the new i2c client, which should be saved for later use with
  * i2c_unregister_device(); or an ERR_PTR to describe the error.
  */
-static struct i2c_client *
-i2c_new_dummy_device(struct i2c_adapter *adapter, u16 address)
+struct i2c_client *i2c_new_dummy_device(struct i2c_adapter *adapter, u16 address)
 {
 	struct i2c_board_info info = {
 		I2C_BOARD_INFO("dummy", address),
diff --git a/drivers/i2c/i2c-core-slave.c b/drivers/i2c/i2c-core-slave.c
index 5427f047faf0..1589179d5eb9 100644
--- a/drivers/i2c/i2c-core-slave.c
+++ b/drivers/i2c/i2c-core-slave.c
@@ -18,10 +18,8 @@ int i2c_slave_register(struct i2c_client *client, i2c_slave_cb_t slave_cb)
 {
 	int ret;
 
-	if (!client || !slave_cb) {
-		WARN(1, "insufficient data\n");
+	if (WARN(IS_ERR_OR_NULL(client) || !slave_cb, "insufficient data\n"))
 		return -EINVAL;
-	}
 
 	if (!(client->flags & I2C_CLIENT_SLAVE))
 		dev_warn(&client->dev, "%s: client slave flag not set. You might see address collisions\n",
@@ -60,6 +58,9 @@ int i2c_slave_unregister(struct i2c_client *client)
 {
 	int ret;
 
+	if (IS_ERR_OR_NULL(client))
+		return -EINVAL;
+
 	if (!client->adapter->algo->unreg_slave) {
 		dev_err(&client->dev, "%s: not supported by adapter\n", __func__);
 		return -EOPNOTSUPP;
diff --git a/drivers/i2c/i2c-core-smbus.c b/drivers/i2c/i2c-core-smbus.c
index 3ac426a8ab5a..c2ae8c8cd429 100644
--- a/drivers/i2c/i2c-core-smbus.c
+++ b/drivers/i2c/i2c-core-smbus.c
@@ -495,6 +495,13 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr,
 			break;
 		case I2C_SMBUS_BLOCK_DATA:
 		case I2C_SMBUS_BLOCK_PROC_CALL:
+			if (msg[1].buf[0] > I2C_SMBUS_BLOCK_MAX) {
+				dev_err(&adapter->dev,
+					"Invalid block size returned: %d\n",
+					msg[1].buf[0]);
+				status = -EPROTO;
+				goto cleanup;
+			}
 			for (i = 0; i < msg[1].buf[0] + 1; i++)
 				data->block[i] = msg[1].buf[i];
 			break;
diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c
index 2ea4585d18c5..94beacc41302 100644
--- a/drivers/i2c/i2c-dev.c
+++ b/drivers/i2c/i2c-dev.c
@@ -40,7 +40,7 @@
 struct i2c_dev {
 	struct list_head list;
 	struct i2c_adapter *adap;
-	struct device *dev;
+	struct device dev;
 	struct cdev cdev;
 };
 
@@ -84,12 +84,14 @@ static struct i2c_dev *get_free_i2c_dev(struct i2c_adapter *adap)
 	return i2c_dev;
 }
 
-static void put_i2c_dev(struct i2c_dev *i2c_dev)
+static void put_i2c_dev(struct i2c_dev *i2c_dev, bool del_cdev)
 {
 	spin_lock(&i2c_dev_list_lock);
 	list_del(&i2c_dev->list);
 	spin_unlock(&i2c_dev_list_lock);
-	kfree(i2c_dev);
+	if (del_cdev)
+		cdev_device_del(&i2c_dev->cdev, &i2c_dev->dev);
+	put_device(&i2c_dev->dev);
 }
 
 static ssize_t name_show(struct device *dev,
@@ -628,6 +630,14 @@ static const struct file_operations i2cdev_fops = {
 
 static struct class *i2c_dev_class;
 
+static void i2cdev_dev_release(struct device *dev)
+{
+	struct i2c_dev *i2c_dev;
+
+	i2c_dev = container_of(dev, struct i2c_dev, dev);
+	kfree(i2c_dev);
+}
+
 static int i2cdev_attach_adapter(struct device *dev, void *dummy)
 {
 	struct i2c_adapter *adap;
@@ -644,27 +654,23 @@ static int i2cdev_attach_adapter(struct device *dev, void *dummy)
 
 	cdev_init(&i2c_dev->cdev, &i2cdev_fops);
 	i2c_dev->cdev.owner = THIS_MODULE;
-	res = cdev_add(&i2c_dev->cdev, MKDEV(I2C_MAJOR, adap->nr), 1);
-	if (res)
-		goto error_cdev;
-
-	/* register this i2c device with the driver core */
-	i2c_dev->dev = device_create(i2c_dev_class, &adap->dev,
-				     MKDEV(I2C_MAJOR, adap->nr), NULL,
-				     "i2c-%d", adap->nr);
-	if (IS_ERR(i2c_dev->dev)) {
-		res = PTR_ERR(i2c_dev->dev);
-		goto error;
+
+	device_initialize(&i2c_dev->dev);
+	i2c_dev->dev.devt = MKDEV(I2C_MAJOR, adap->nr);
+	i2c_dev->dev.class = i2c_dev_class;
+	i2c_dev->dev.parent = &adap->dev;
+	i2c_dev->dev.release = i2cdev_dev_release;
+	dev_set_name(&i2c_dev->dev, "i2c-%d", adap->nr);
+
+	res = cdev_device_add(&i2c_dev->cdev, &i2c_dev->dev);
+	if (res) {
+		put_i2c_dev(i2c_dev, false);
+		return res;
 	}
 
 	pr_debug("i2c-dev: adapter [%s] registered as minor %d\n",
 		 adap->name, adap->nr);
 	return 0;
-error:
-	cdev_del(&i2c_dev->cdev);
-error_cdev:
-	put_i2c_dev(i2c_dev);
-	return res;
 }
 
 static int i2cdev_detach_adapter(struct device *dev, void *dummy)
@@ -680,9 +686,7 @@ static int i2cdev_detach_adapter(struct device *dev, void *dummy)
 	if (!i2c_dev) /* attach_adapter must have failed */
 		return 0;
 
-	cdev_del(&i2c_dev->cdev);
-	put_i2c_dev(i2c_dev);
-	device_destroy(i2c_dev_class, MKDEV(I2C_MAJOR, adap->nr));
+	put_i2c_dev(i2c_dev, true);
 
 	pr_debug("i2c-dev: adapter [%s] unregistered\n", adap->name);
 	return 0;
diff --git a/drivers/i2c/muxes/i2c-demux-pinctrl.c b/drivers/i2c/muxes/i2c-demux-pinctrl.c
index 0e16490eb3a1..5365199a31f4 100644
--- a/drivers/i2c/muxes/i2c-demux-pinctrl.c
+++ b/drivers/i2c/muxes/i2c-demux-pinctrl.c
@@ -272,6 +272,7 @@ static int i2c_demux_pinctrl_probe(struct platform_device *pdev)
 err_rollback_available:
 	device_remove_file(&pdev->dev, &dev_attr_available_masters);
 err_rollback:
+	i2c_demux_deactivate_master(priv);
 	for (j = 0; j < i; j++) {
 		of_node_put(priv->chan[j].parent_np);
 		of_changeset_destroy(&priv->chan[j].chgset);
diff --git a/drivers/ide/cmd64x.c b/drivers/ide/cmd64x.c
index a1898e11b04e..943bf944bf72 100644
--- a/drivers/ide/cmd64x.c
+++ b/drivers/ide/cmd64x.c
@@ -66,6 +66,9 @@ static void cmd64x_program_timings(ide_drive_t *drive, u8 mode)
 	struct ide_timing t;
 	u8 arttim = 0;
 
+	if (drive->dn >= ARRAY_SIZE(drwtim_regs))
+		return;
+
 	ide_timing_compute(drive, mode, &t, T, 0);
 
 	/*
diff --git a/drivers/ide/serverworks.c b/drivers/ide/serverworks.c
index ac6fc3fffa0d..458e72e034b0 100644
--- a/drivers/ide/serverworks.c
+++ b/drivers/ide/serverworks.c
@@ -115,6 +115,9 @@ static void svwks_set_pio_mode(ide_hwif_t *hwif, ide_drive_t *drive)
 	struct pci_dev *dev = to_pci_dev(hwif->dev);
 	const u8 pio = drive->pio_mode - XFER_PIO_0;
 
+	if (drive->dn >= ARRAY_SIZE(drive_pci))
+		return;
+
 	pci_write_config_byte(dev, drive_pci[drive->dn], pio_modes[pio]);
 
 	if (svwks_csb_check(dev)) {
@@ -141,6 +144,9 @@ static void svwks_set_dma_mode(ide_hwif_t *hwif, ide_drive_t *drive)
 
 	u8 ultra_enable	 = 0, ultra_timing = 0, dma_timing = 0;
 
+	if (drive->dn >= ARRAY_SIZE(drive_pci2))
+		return;
+
 	pci_read_config_byte(dev, (0x56|hwif->channel), &ultra_timing);
 	pci_read_config_byte(dev, 0x54, &ultra_enable);
 
diff --git a/drivers/iio/accel/adxl372.c b/drivers/iio/accel/adxl372.c
index 67b8817995c0..60daf04ce188 100644
--- a/drivers/iio/accel/adxl372.c
+++ b/drivers/iio/accel/adxl372.c
@@ -237,6 +237,7 @@ static const struct adxl372_axis_lookup adxl372_axis_lookup_table[] = {
 		.realbits = 12,						\
 		.storagebits = 16,					\
 		.shift = 4,						\
+		.endianness = IIO_BE,					\
 	},								\
 }
 
diff --git a/drivers/iio/accel/mma8452.c b/drivers/iio/accel/mma8452.c
index 00e100fc845a..813bca7cfc3e 100644
--- a/drivers/iio/accel/mma8452.c
+++ b/drivers/iio/accel/mma8452.c
@@ -1685,10 +1685,13 @@ static int mma8452_probe(struct i2c_client *client,
 
 	ret = mma8452_set_freefall_mode(data, false);
 	if (ret < 0)
-		goto buffer_cleanup;
+		goto unregister_device;
 
 	return 0;
 
+unregister_device:
+	iio_device_unregister(indio_dev);
+
 buffer_cleanup:
 	iio_triggered_buffer_cleanup(indio_dev);
 
diff --git a/drivers/iio/accel/sca3000.c b/drivers/iio/accel/sca3000.c
index 274ce2f8bddf..76ea3bb1752d 100644
--- a/drivers/iio/accel/sca3000.c
+++ b/drivers/iio/accel/sca3000.c
@@ -979,7 +979,7 @@ static int sca3000_read_data(struct sca3000_state *st,
 	st->tx[0] = SCA3000_READ_REG(reg_address_high);
 	ret = spi_sync_transfer(st->us, xfer, ARRAY_SIZE(xfer));
 	if (ret) {
-		dev_err(get_device(&st->us->dev), "problem reading register");
+		dev_err(&st->us->dev, "problem reading register\n");
 		return ret;
 	}
 
diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c
index e02b79931979..9e4d00a20359 100644
--- a/drivers/iio/accel/st_accel_core.c
+++ b/drivers/iio/accel/st_accel_core.c
@@ -994,6 +994,7 @@ static const struct iio_trigger_ops st_accel_trigger_ops = {
 #define ST_ACCEL_TRIGGER_OPS NULL
 #endif
 
+#ifdef CONFIG_ACPI
 static const struct iio_mount_matrix *
 get_mount_matrix(const struct iio_dev *indio_dev,
 		 const struct iio_chan_spec *chan)
@@ -1014,7 +1015,6 @@ static const struct iio_chan_spec_ext_info mount_matrix_ext_info[] = {
 static int apply_acpi_orientation(struct iio_dev *indio_dev,
 				  struct iio_chan_spec *channels)
 {
-#ifdef CONFIG_ACPI
 	struct st_sensor_data *adata = iio_priv(indio_dev);
 	struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
 	struct acpi_device *adev;
@@ -1142,10 +1142,14 @@ static int apply_acpi_orientation(struct iio_dev *indio_dev,
 out:
 	kfree(buffer.pointer);
 	return ret;
+}
 #else /* !CONFIG_ACPI */
+static int apply_acpi_orientation(struct iio_dev *indio_dev,
+				  struct iio_chan_spec *channels)
+{
 	return 0;
-#endif
 }
+#endif
 
 int st_accel_common_probe(struct iio_dev *indio_dev)
 {
diff --git a/drivers/iio/accel/st_accel_i2c.c b/drivers/iio/accel/st_accel_i2c.c
index c3c8f2e73c2a..f13f7fd8c914 100644
--- a/drivers/iio/accel/st_accel_i2c.c
+++ b/drivers/iio/accel/st_accel_i2c.c
@@ -114,7 +114,7 @@ MODULE_DEVICE_TABLE(of, st_accel_of_match);
 
 #ifdef CONFIG_ACPI
 static const struct acpi_device_id st_accel_acpi_match[] = {
-	{"SMO8840", (kernel_ulong_t)LNG2DM_ACCEL_DEV_NAME},
+	{"SMO8840", (kernel_ulong_t)LIS2DH12_ACCEL_DEV_NAME},
 	{"SMO8A90", (kernel_ulong_t)LNG2DM_ACCEL_DEV_NAME},
 	{ },
 };
diff --git a/drivers/iio/adc/ad7124.c b/drivers/iio/adc/ad7124.c
index 5262d34ebea8..2d662dd09e6b 100644
--- a/drivers/iio/adc/ad7124.c
+++ b/drivers/iio/adc/ad7124.c
@@ -485,13 +485,11 @@ static int ad7124_of_parse_channel_config(struct iio_dev *indio_dev,
 		else
 			st->channel_config[channel].refsel = tmp;
 
-		*chan = ad7124_channel_template;
-		chan->address = channel;
-		chan->scan_index = channel;
-		chan->channel = ain[0];
-		chan->channel2 = ain[1];
-
-		chan++;
+		chan[channel] = ad7124_channel_template;
+		chan[channel].address = channel;
+		chan[channel].scan_index = channel;
+		chan[channel].channel = ain[0];
+		chan[channel].channel2 = ain[1];
 	}
 
 	return 0;
diff --git a/drivers/iio/adc/ad7606_par.c b/drivers/iio/adc/ad7606_par.c
index 1b08028facde..f732b3ac7878 100644
--- a/drivers/iio/adc/ad7606_par.c
+++ b/drivers/iio/adc/ad7606_par.c
@@ -53,10 +53,8 @@ static int ad7606_par_probe(struct platform_device *pdev)
 	int irq;
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(&pdev->dev, "no irq: %d\n", irq);
+	if (irq < 0)
 		return irq;
-	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	addr = devm_ioremap_resource(&pdev->dev, res);
diff --git a/drivers/iio/adc/ad7780.c b/drivers/iio/adc/ad7780.c
index 217a5a5c3c6d..7e741294de7b 100644
--- a/drivers/iio/adc/ad7780.c
+++ b/drivers/iio/adc/ad7780.c
@@ -309,7 +309,7 @@ static int ad7780_probe(struct spi_device *spi)
 
 	ret = ad7780_init_gpios(&spi->dev, st);
 	if (ret)
-		goto error_cleanup_buffer_and_trigger;
+		return ret;
 
 	st->reg = devm_regulator_get(&spi->dev, "avdd");
 	if (IS_ERR(st->reg))
diff --git a/drivers/iio/adc/ad7793.c b/drivers/iio/adc/ad7793.c
index bbc41ecf0d2f..6ed6d1410201 100644
--- a/drivers/iio/adc/ad7793.c
+++ b/drivers/iio/adc/ad7793.c
@@ -541,7 +541,7 @@ static const struct iio_info ad7797_info = {
 	.read_raw = &ad7793_read_raw,
 	.write_raw = &ad7793_write_raw,
 	.write_raw_get_fmt = &ad7793_write_raw_get_fmt,
-	.attrs = &ad7793_attribute_group,
+	.attrs = &ad7797_attribute_group,
 	.validate_trigger = ad_sd_validate_trigger,
 };
 
diff --git a/drivers/iio/adc/at91-sama5d2_adc.c b/drivers/iio/adc/at91-sama5d2_adc.c
index d384cf0250ff..5759534886a6 100644
--- a/drivers/iio/adc/at91-sama5d2_adc.c
+++ b/drivers/iio/adc/at91-sama5d2_adc.c
@@ -723,6 +723,7 @@ static int at91_adc_configure_trigger(struct iio_trigger *trig, bool state)
 
 	for_each_set_bit(bit, indio->active_scan_mask, indio->num_channels) {
 		struct iio_chan_spec const *chan = at91_adc_chan_get(indio, bit);
+		u32 cor;
 
 		if (!chan)
 			continue;
@@ -732,6 +733,20 @@ static int at91_adc_configure_trigger(struct iio_trigger *trig, bool state)
 			continue;
 
 		if (state) {
+			cor = at91_adc_readl(st, AT91_SAMA5D2_COR);
+
+			if (chan->differential)
+				cor |= (BIT(chan->channel) |
+					BIT(chan->channel2)) <<
+					AT91_SAMA5D2_COR_DIFF_OFFSET;
+			else
+				cor &= ~(BIT(chan->channel) <<
+				       AT91_SAMA5D2_COR_DIFF_OFFSET);
+
+			at91_adc_writel(st, AT91_SAMA5D2_COR, cor);
+		}
+
+		if (state) {
 			at91_adc_writel(st, AT91_SAMA5D2_CHER,
 					BIT(chan->channel));
 			/* enable irq only if not using DMA */
diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c
index d23709ed9049..303193024854 100644
--- a/drivers/iio/adc/at91_adc.c
+++ b/drivers/iio/adc/at91_adc.c
@@ -1179,10 +1179,8 @@ static int at91_adc_probe(struct platform_device *pdev)
 	idev->info = &at91_adc_info;
 
 	st->irq = platform_get_irq(pdev, 0);
-	if (st->irq < 0) {
-		dev_err(&pdev->dev, "No IRQ ID is designated\n");
+	if (st->irq < 0)
 		return -ENODEV;
-	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 
diff --git a/drivers/iio/adc/axp288_adc.c b/drivers/iio/adc/axp288_adc.c
index 85d08e68b34f..8ea2aed6d6f5 100644
--- a/drivers/iio/adc/axp288_adc.c
+++ b/drivers/iio/adc/axp288_adc.c
@@ -257,10 +257,8 @@ static int axp288_adc_probe(struct platform_device *pdev)
 
 	info = iio_priv(indio_dev);
 	info->irq = platform_get_irq(pdev, 0);
-	if (info->irq < 0) {
-		dev_err(&pdev->dev, "no irq resource?\n");
+	if (info->irq < 0)
 		return info->irq;
-	}
 	platform_set_drvdata(pdev, indio_dev);
 	info->regmap = axp20x->regmap;
 	/*
diff --git a/drivers/iio/adc/bcm_iproc_adc.c b/drivers/iio/adc/bcm_iproc_adc.c
index c46c0aa15376..646ebdc0a8b4 100644
--- a/drivers/iio/adc/bcm_iproc_adc.c
+++ b/drivers/iio/adc/bcm_iproc_adc.c
@@ -540,11 +540,8 @@ static int iproc_adc_probe(struct platform_device *pdev)
 	}
 
 	adc_priv->irqno = platform_get_irq(pdev, 0);
-	if (adc_priv->irqno <= 0) {
-		dev_err(&pdev->dev, "platform_get_irq failed\n");
-		ret = -ENODEV;
-		return ret;
-	}
+	if (adc_priv->irqno <= 0)
+		return -ENODEV;
 
 	ret = regmap_update_bits(adc_priv->regmap, IPROC_REGCTL2,
 				IPROC_ADC_AUXIN_SCAN_ENA, 0);
diff --git a/drivers/iio/adc/da9150-gpadc.c b/drivers/iio/adc/da9150-gpadc.c
index 354433996101..ae8bcc32f63d 100644
--- a/drivers/iio/adc/da9150-gpadc.c
+++ b/drivers/iio/adc/da9150-gpadc.c
@@ -337,10 +337,8 @@ static int da9150_gpadc_probe(struct platform_device *pdev)
 	init_completion(&gpadc->complete);
 
 	irq = platform_get_irq_byname(pdev, "GPADC");
-	if (irq < 0) {
-		dev_err(dev, "Failed to get IRQ: %d\n", irq);
+	if (irq < 0)
 		return irq;
-	}
 
 	ret = devm_request_threaded_irq(dev, irq, NULL, da9150_gpadc_irq,
 					IRQF_ONESHOT, "GPADC", gpadc);
diff --git a/drivers/iio/adc/envelope-detector.c b/drivers/iio/adc/envelope-detector.c
index 2f2b563c1162..28f3d6758eb5 100644
--- a/drivers/iio/adc/envelope-detector.c
+++ b/drivers/iio/adc/envelope-detector.c
@@ -357,11 +357,8 @@ static int envelope_detector_probe(struct platform_device *pdev)
 	}
 
 	env->comp_irq = platform_get_irq_byname(pdev, "comp");
-	if (env->comp_irq < 0) {
-		if (env->comp_irq != -EPROBE_DEFER)
-			dev_err(dev, "failed to get compare interrupt\n");
+	if (env->comp_irq < 0)
 		return env->comp_irq;
-	}
 
 	ret = devm_request_irq(dev, env->comp_irq, envelope_detector_comp_isr,
 			       0, "envelope-detector", env);
diff --git a/drivers/iio/adc/exynos_adc.c b/drivers/iio/adc/exynos_adc.c
index d4c3ece21679..42a3ced11fbd 100644
--- a/drivers/iio/adc/exynos_adc.c
+++ b/drivers/iio/adc/exynos_adc.c
@@ -805,10 +805,8 @@ static int exynos_adc_probe(struct platform_device *pdev)
 	}
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(&pdev->dev, "no irq resource?\n");
+	if (irq < 0)
 		return irq;
-	}
 	info->irq = irq;
 
 	irq = platform_get_irq(pdev, 1);
diff --git a/drivers/iio/adc/fsl-imx25-gcq.c b/drivers/iio/adc/fsl-imx25-gcq.c
index df19ecae52f7..fa71489195c6 100644
--- a/drivers/iio/adc/fsl-imx25-gcq.c
+++ b/drivers/iio/adc/fsl-imx25-gcq.c
@@ -340,7 +340,6 @@ static int mx25_gcq_probe(struct platform_device *pdev)
 
 	priv->irq = platform_get_irq(pdev, 0);
 	if (priv->irq <= 0) {
-		dev_err(dev, "Failed to get IRQ\n");
 		ret = priv->irq;
 		if (!ret)
 			ret = -ENXIO;
diff --git a/drivers/iio/adc/imx7d_adc.c b/drivers/iio/adc/imx7d_adc.c
index 4fe97c2a0f43..e4c3f11654d9 100644
--- a/drivers/iio/adc/imx7d_adc.c
+++ b/drivers/iio/adc/imx7d_adc.c
@@ -500,10 +500,8 @@ static int imx7d_adc_probe(struct platform_device *pdev)
 	}
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(dev, "No irq resource?\n");
+	if (irq < 0)
 		return irq;
-	}
 
 	info->clk = devm_clk_get(dev, "adc");
 	if (IS_ERR(info->clk)) {
diff --git a/drivers/iio/adc/lpc32xx_adc.c b/drivers/iio/adc/lpc32xx_adc.c
index a6ee1c3a9064..b896f7ff4572 100644
--- a/drivers/iio/adc/lpc32xx_adc.c
+++ b/drivers/iio/adc/lpc32xx_adc.c
@@ -172,10 +172,8 @@ static int lpc32xx_adc_probe(struct platform_device *pdev)
 	}
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq <= 0) {
-		dev_err(&pdev->dev, "failed getting interrupt resource\n");
+	if (irq <= 0)
 		return -ENXIO;
-	}
 
 	retval = devm_request_irq(&pdev->dev, irq, lpc32xx_adc_isr, 0,
 				  LPC32XXAD_NAME, st);
diff --git a/drivers/iio/adc/max9611.c b/drivers/iio/adc/max9611.c
index da073d72f649..e480529b3f04 100644
--- a/drivers/iio/adc/max9611.c
+++ b/drivers/iio/adc/max9611.c
@@ -89,6 +89,12 @@
 #define MAX9611_TEMP_SCALE_NUM		1000000
 #define MAX9611_TEMP_SCALE_DIV		2083
 
+/*
+ * Conversion time is 2 ms (typically) at Ta=25 degreeC
+ * No maximum value is known, so play it safe.
+ */
+#define MAX9611_CONV_TIME_US_RANGE	3000, 3300
+
 struct max9611_dev {
 	struct device *dev;
 	struct i2c_client *i2c_client;
@@ -236,11 +242,9 @@ static int max9611_read_single(struct max9611_dev *max9611,
 		return ret;
 	}
 
-	/*
-	 * need a delay here to make register configuration
-	 * stabilize. 1 msec at least, from empirical testing.
-	 */
-	usleep_range(1000, 2000);
+	/* need a delay here to make register configuration stabilize. */
+
+	usleep_range(MAX9611_CONV_TIME_US_RANGE);
 
 	ret = i2c_smbus_read_word_swapped(max9611->i2c_client, reg_addr);
 	if (ret < 0) {
@@ -507,7 +511,7 @@ static int max9611_init(struct max9611_dev *max9611)
 			MAX9611_REG_CTRL2, 0);
 		return ret;
 	}
-	usleep_range(1000, 2000);
+	usleep_range(MAX9611_CONV_TIME_US_RANGE);
 
 	return 0;
 }
diff --git a/drivers/iio/adc/npcm_adc.c b/drivers/iio/adc/npcm_adc.c
index 193b3b81de4d..910f3585fa54 100644
--- a/drivers/iio/adc/npcm_adc.c
+++ b/drivers/iio/adc/npcm_adc.c
@@ -225,7 +225,6 @@ static int npcm_adc_probe(struct platform_device *pdev)
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq <= 0) {
-		dev_err(dev, "failed getting interrupt resource\n");
 		ret = -EINVAL;
 		goto err_disable_clk;
 	}
diff --git a/drivers/iio/adc/rockchip_saradc.c b/drivers/iio/adc/rockchip_saradc.c
index dd8299831e09..582ba047c4a6 100644
--- a/drivers/iio/adc/rockchip_saradc.c
+++ b/drivers/iio/adc/rockchip_saradc.c
@@ -244,10 +244,8 @@ static int rockchip_saradc_probe(struct platform_device *pdev)
 	init_completion(&info->completion);
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(&pdev->dev, "no irq resource?\n");
+	if (irq < 0)
 		return irq;
-	}
 
 	ret = devm_request_irq(&pdev->dev, irq, rockchip_saradc_isr,
 			       0, dev_name(&pdev->dev), info);
diff --git a/drivers/iio/adc/sc27xx_adc.c b/drivers/iio/adc/sc27xx_adc.c
index f7f7a18904b4..bb616aa01f4f 100644
--- a/drivers/iio/adc/sc27xx_adc.c
+++ b/drivers/iio/adc/sc27xx_adc.c
@@ -528,10 +528,8 @@ static int sc27xx_adc_probe(struct platform_device *pdev)
 	}
 
 	sc27xx_data->irq = platform_get_irq(pdev, 0);
-	if (sc27xx_data->irq < 0) {
-		dev_err(&pdev->dev, "failed to get ADC irq number\n");
+	if (sc27xx_data->irq < 0)
 		return sc27xx_data->irq;
-	}
 
 	ret = of_hwspin_lock_get_id(np, 0);
 	if (ret < 0) {
diff --git a/drivers/iio/adc/spear_adc.c b/drivers/iio/adc/spear_adc.c
index a33d0a4cc088..592b97c464da 100644
--- a/drivers/iio/adc/spear_adc.c
+++ b/drivers/iio/adc/spear_adc.c
@@ -301,7 +301,6 @@ static int spear_adc_probe(struct platform_device *pdev)
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq <= 0) {
-		dev_err(dev, "failed getting interrupt resource\n");
 		ret = -EINVAL;
 		goto errout2;
 	}
diff --git a/drivers/iio/adc/stm32-adc-core.c b/drivers/iio/adc/stm32-adc-core.c
index 6016a864d6d6..5b995bf4b3ee 100644
--- a/drivers/iio/adc/stm32-adc-core.c
+++ b/drivers/iio/adc/stm32-adc-core.c
@@ -51,11 +51,13 @@ struct stm32_adc_priv;
  * @regs:	common registers for all instances
  * @clk_sel:	clock selection routine
  * @max_clk_rate_hz: maximum analog clock rate (Hz, from datasheet)
+ * @num_irqs:	number of interrupt lines
  */
 struct stm32_adc_priv_cfg {
 	const struct stm32_adc_common_regs *regs;
 	int (*clk_sel)(struct platform_device *, struct stm32_adc_priv *);
 	u32 max_clk_rate_hz;
+	unsigned int num_irqs;
 };
 
 /**
@@ -347,22 +349,15 @@ static int stm32_adc_irq_probe(struct platform_device *pdev,
 	struct device_node *np = pdev->dev.of_node;
 	unsigned int i;
 
-	for (i = 0; i < STM32_ADC_MAX_ADCS; i++) {
+	/*
+	 * Interrupt(s) must be provided, depending on the compatible:
+	 * - stm32f4/h7 shares a common interrupt line.
+	 * - stm32mp1, has one line per ADC
+	 */
+	for (i = 0; i < priv->cfg->num_irqs; i++) {
 		priv->irq[i] = platform_get_irq(pdev, i);
-		if (priv->irq[i] < 0) {
-			/*
-			 * At least one interrupt must be provided, make others
-			 * optional:
-			 * - stm32f4/h7 shares a common interrupt.
-			 * - stm32mp1, has one line per ADC (either for ADC1,
-			 *   ADC2 or both).
-			 */
-			if (i && priv->irq[i] == -ENXIO)
-				continue;
-			dev_err(&pdev->dev, "failed to get irq\n");
-
+		if (priv->irq[i] < 0)
 			return priv->irq[i];
-		}
 	}
 
 	priv->domain = irq_domain_add_simple(np, STM32_ADC_MAX_ADCS, 0,
@@ -373,9 +368,7 @@ static int stm32_adc_irq_probe(struct platform_device *pdev,
 		return -ENOMEM;
 	}
 
-	for (i = 0; i < STM32_ADC_MAX_ADCS; i++) {
-		if (priv->irq[i] < 0)
-			continue;
+	for (i = 0; i < priv->cfg->num_irqs; i++) {
 		irq_set_chained_handler(priv->irq[i], stm32_adc_irq_handler);
 		irq_set_handler_data(priv->irq[i], priv);
 	}
@@ -393,11 +386,8 @@ static void stm32_adc_irq_remove(struct platform_device *pdev,
 		irq_dispose_mapping(irq_find_mapping(priv->domain, hwirq));
 	irq_domain_remove(priv->domain);
 
-	for (i = 0; i < STM32_ADC_MAX_ADCS; i++) {
-		if (priv->irq[i] < 0)
-			continue;
+	for (i = 0; i < priv->cfg->num_irqs; i++)
 		irq_set_chained_handler(priv->irq[i], NULL);
-	}
 }
 
 static int stm32_adc_core_hw_start(struct device *dev)
@@ -615,18 +605,21 @@ static const struct stm32_adc_priv_cfg stm32f4_adc_priv_cfg = {
 	.regs = &stm32f4_adc_common_regs,
 	.clk_sel = stm32f4_adc_clk_sel,
 	.max_clk_rate_hz = 36000000,
+	.num_irqs = 1,
 };
 
 static const struct stm32_adc_priv_cfg stm32h7_adc_priv_cfg = {
 	.regs = &stm32h7_adc_common_regs,
 	.clk_sel = stm32h7_adc_clk_sel,
 	.max_clk_rate_hz = 36000000,
+	.num_irqs = 1,
 };
 
 static const struct stm32_adc_priv_cfg stm32mp1_adc_priv_cfg = {
 	.regs = &stm32h7_adc_common_regs,
 	.clk_sel = stm32h7_adc_clk_sel,
 	.max_clk_rate_hz = 40000000,
+	.num_irqs = 2,
 };
 
 static const struct of_device_id stm32_adc_of_match[] = {
diff --git a/drivers/iio/adc/stm32-adc.c b/drivers/iio/adc/stm32-adc.c
index 755627e4ab9e..94fde39d9ff7 100644
--- a/drivers/iio/adc/stm32-adc.c
+++ b/drivers/iio/adc/stm32-adc.c
@@ -1367,8 +1367,30 @@ static unsigned int stm32_adc_dma_residue(struct stm32_adc *adc)
 static void stm32_adc_dma_buffer_done(void *data)
 {
 	struct iio_dev *indio_dev = data;
+	struct stm32_adc *adc = iio_priv(indio_dev);
+	int residue = stm32_adc_dma_residue(adc);
+
+	/*
+	 * In DMA mode the trigger services of IIO are not used
+	 * (e.g. no call to iio_trigger_poll).
+	 * Calling irq handler associated to the hardware trigger is not
+	 * relevant as the conversions have already been done. Data
+	 * transfers are performed directly in DMA callback instead.
+	 * This implementation avoids to call trigger irq handler that
+	 * may sleep, in an atomic context (DMA irq handler context).
+	 */
+	dev_dbg(&indio_dev->dev, "%s bufi=%d\n", __func__, adc->bufi);
+
+	while (residue >= indio_dev->scan_bytes) {
+		u16 *buffer = (u16 *)&adc->rx_buf[adc->bufi];
 
-	iio_trigger_poll_chained(indio_dev->trig);
+		iio_push_to_buffers(indio_dev, buffer);
+
+		residue -= indio_dev->scan_bytes;
+		adc->bufi += indio_dev->scan_bytes;
+		if (adc->bufi >= adc->rx_buf_sz)
+			adc->bufi = 0;
+	}
 }
 
 static int stm32_adc_dma_start(struct iio_dev *indio_dev)
@@ -1735,15 +1757,27 @@ static int stm32_adc_chan_of_init(struct iio_dev *indio_dev)
 	return 0;
 }
 
-static int stm32_adc_dma_request(struct iio_dev *indio_dev)
+static int stm32_adc_dma_request(struct device *dev, struct iio_dev *indio_dev)
 {
 	struct stm32_adc *adc = iio_priv(indio_dev);
 	struct dma_slave_config config;
 	int ret;
 
-	adc->dma_chan = dma_request_slave_channel(&indio_dev->dev, "rx");
-	if (!adc->dma_chan)
+	adc->dma_chan = dma_request_chan(dev, "rx");
+	if (IS_ERR(adc->dma_chan)) {
+		ret = PTR_ERR(adc->dma_chan);
+		if (ret != -ENODEV) {
+			if (ret != -EPROBE_DEFER)
+				dev_err(dev,
+					"DMA channel request failed with %d\n",
+					ret);
+			return ret;
+		}
+
+		/* DMA is optional: fall back to IRQ mode */
+		adc->dma_chan = NULL;
 		return 0;
+	}
 
 	adc->rx_buf = dma_alloc_coherent(adc->dma_chan->device->dev,
 					 STM32_DMA_BUFFER_SIZE,
@@ -1778,6 +1812,7 @@ static int stm32_adc_probe(struct platform_device *pdev)
 {
 	struct iio_dev *indio_dev;
 	struct device *dev = &pdev->dev;
+	irqreturn_t (*handler)(int irq, void *p) = NULL;
 	struct stm32_adc *adc;
 	int ret;
 
@@ -1810,10 +1845,8 @@ static int stm32_adc_probe(struct platform_device *pdev)
 	}
 
 	adc->irq = platform_get_irq(pdev, 0);
-	if (adc->irq < 0) {
-		dev_err(&pdev->dev, "failed to get irq\n");
+	if (adc->irq < 0)
 		return adc->irq;
-	}
 
 	ret = devm_request_irq(&pdev->dev, adc->irq, stm32_adc_isr,
 			       0, pdev->name, adc);
@@ -1841,13 +1874,15 @@ static int stm32_adc_probe(struct platform_device *pdev)
 	if (ret < 0)
 		return ret;
 
-	ret = stm32_adc_dma_request(indio_dev);
+	ret = stm32_adc_dma_request(dev, indio_dev);
 	if (ret < 0)
 		return ret;
 
+	if (!adc->dma_chan)
+		handler = &stm32_adc_trigger_handler;
+
 	ret = iio_triggered_buffer_setup(indio_dev,
-					 &iio_pollfunc_store_time,
-					 &stm32_adc_trigger_handler,
+					 &iio_pollfunc_store_time, handler,
 					 &stm32_adc_buffer_setup_ops);
 	if (ret) {
 		dev_err(&pdev->dev, "buffer setup failed\n");
diff --git a/drivers/iio/adc/stm32-dfsdm-adc.c b/drivers/iio/adc/stm32-dfsdm-adc.c
index 6b90a40882f2..89a5e24bd057 100644
--- a/drivers/iio/adc/stm32-dfsdm-adc.c
+++ b/drivers/iio/adc/stm32-dfsdm-adc.c
@@ -62,7 +62,7 @@ enum sd_converter_type {
 
 struct stm32_dfsdm_dev_data {
 	int type;
-	int (*init)(struct iio_dev *indio_dev);
+	int (*init)(struct device *dev, struct iio_dev *indio_dev);
 	unsigned int num_channels;
 	const struct regmap_config *regmap_cfg;
 };
@@ -779,29 +779,6 @@ static unsigned int stm32_dfsdm_adc_dma_residue(struct stm32_dfsdm_adc *adc)
 	return 0;
 }
 
-static irqreturn_t stm32_dfsdm_adc_trigger_handler(int irq, void *p)
-{
-	struct iio_poll_func *pf = p;
-	struct iio_dev *indio_dev = pf->indio_dev;
-	struct stm32_dfsdm_adc *adc = iio_priv(indio_dev);
-	int available = stm32_dfsdm_adc_dma_residue(adc);
-
-	while (available >= indio_dev->scan_bytes) {
-		u32 *buffer = (u32 *)&adc->rx_buf[adc->bufi];
-
-		iio_push_to_buffers_with_timestamp(indio_dev, buffer,
-						   pf->timestamp);
-		available -= indio_dev->scan_bytes;
-		adc->bufi += indio_dev->scan_bytes;
-		if (adc->bufi >= adc->buf_sz)
-			adc->bufi = 0;
-	}
-
-	iio_trigger_notify_done(indio_dev->trig);
-
-	return IRQ_HANDLED;
-}
-
 static void stm32_dfsdm_dma_buffer_done(void *data)
 {
 	struct iio_dev *indio_dev = data;
@@ -811,11 +788,6 @@ static void stm32_dfsdm_dma_buffer_done(void *data)
 	int available = stm32_dfsdm_adc_dma_residue(adc);
 	size_t old_pos;
 
-	if (indio_dev->currentmode & INDIO_BUFFER_TRIGGERED) {
-		iio_trigger_poll_chained(indio_dev->trig);
-		return;
-	}
-
 	/*
 	 * FIXME: In Kernel interface does not support cyclic DMA buffer,and
 	 * offers only an interface to push data samples per samples.
@@ -852,7 +824,15 @@ static void stm32_dfsdm_dma_buffer_done(void *data)
 			adc->bufi = 0;
 			old_pos = 0;
 		}
-		/* regular iio buffer without trigger */
+		/*
+		 * In DMA mode the trigger services of IIO are not used
+		 * (e.g. no call to iio_trigger_poll).
+		 * Calling irq handler associated to the hardware trigger is not
+		 * relevant as the conversions have already been done. Data
+		 * transfers are performed directly in DMA callback instead.
+		 * This implementation avoids to call trigger irq handler that
+		 * may sleep, in an atomic context (DMA irq handler context).
+		 */
 		if (adc->dev_data->type == DFSDM_IIO)
 			iio_push_to_buffers(indio_dev, buffer);
 	}
@@ -1321,13 +1301,18 @@ static void stm32_dfsdm_dma_release(struct iio_dev *indio_dev)
 	}
 }
 
-static int stm32_dfsdm_dma_request(struct iio_dev *indio_dev)
+static int stm32_dfsdm_dma_request(struct device *dev,
+				   struct iio_dev *indio_dev)
 {
 	struct stm32_dfsdm_adc *adc = iio_priv(indio_dev);
 
-	adc->dma_chan = dma_request_slave_channel(&indio_dev->dev, "rx");
-	if (!adc->dma_chan)
-		return -EINVAL;
+	adc->dma_chan = dma_request_chan(dev, "rx");
+	if (IS_ERR(adc->dma_chan)) {
+		int ret = PTR_ERR(adc->dma_chan);
+
+		adc->dma_chan = NULL;
+		return ret;
+	}
 
 	adc->rx_buf = dma_alloc_coherent(adc->dma_chan->device->dev,
 					 DFSDM_DMA_BUFFER_SIZE,
@@ -1377,7 +1362,7 @@ static int stm32_dfsdm_adc_chan_init_one(struct iio_dev *indio_dev,
 					  &adc->dfsdm->ch_list[ch->channel]);
 }
 
-static int stm32_dfsdm_audio_init(struct iio_dev *indio_dev)
+static int stm32_dfsdm_audio_init(struct device *dev, struct iio_dev *indio_dev)
 {
 	struct iio_chan_spec *ch;
 	struct stm32_dfsdm_adc *adc = iio_priv(indio_dev);
@@ -1404,10 +1389,10 @@ static int stm32_dfsdm_audio_init(struct iio_dev *indio_dev)
 	indio_dev->num_channels = 1;
 	indio_dev->channels = ch;
 
-	return stm32_dfsdm_dma_request(indio_dev);
+	return stm32_dfsdm_dma_request(dev, indio_dev);
 }
 
-static int stm32_dfsdm_adc_init(struct iio_dev *indio_dev)
+static int stm32_dfsdm_adc_init(struct device *dev, struct iio_dev *indio_dev)
 {
 	struct iio_chan_spec *ch;
 	struct stm32_dfsdm_adc *adc = iio_priv(indio_dev);
@@ -1452,14 +1437,22 @@ static int stm32_dfsdm_adc_init(struct iio_dev *indio_dev)
 	init_completion(&adc->completion);
 
 	/* Optionally request DMA */
-	if (stm32_dfsdm_dma_request(indio_dev)) {
-		dev_dbg(&indio_dev->dev, "No DMA support\n");
+	ret = stm32_dfsdm_dma_request(dev, indio_dev);
+	if (ret) {
+		if (ret != -ENODEV) {
+			if (ret != -EPROBE_DEFER)
+				dev_err(dev,
+					"DMA channel request failed with %d\n",
+					ret);
+			return ret;
+		}
+
+		dev_dbg(dev, "No DMA support\n");
 		return 0;
 	}
 
 	ret = iio_triggered_buffer_setup(indio_dev,
-					 &iio_pollfunc_store_time,
-					 &stm32_dfsdm_adc_trigger_handler,
+					 &iio_pollfunc_store_time, NULL,
 					 &stm32_dfsdm_buffer_setup_ops);
 	if (ret) {
 		stm32_dfsdm_dma_release(indio_dev);
@@ -1544,11 +1537,8 @@ static int stm32_dfsdm_adc_probe(struct platform_device *pdev)
 	 * So IRQ associated to filter instance 0 is dedicated to the Filter 0.
 	 */
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		if (irq != -EPROBE_DEFER)
-			dev_err(dev, "Failed to get IRQ: %d\n", irq);
+	if (irq < 0)
 		return irq;
-	}
 
 	ret = devm_request_irq(dev, irq, stm32_dfsdm_irq,
 			       0, pdev->name, adc);
@@ -1570,7 +1560,7 @@ static int stm32_dfsdm_adc_probe(struct platform_device *pdev)
 		adc->dfsdm->fl_list[adc->fl_id].sync_mode = val;
 
 	adc->dev_data = dev_data;
-	ret = dev_data->init(iio);
+	ret = dev_data->init(dev, iio);
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/iio/adc/sun4i-gpadc-iio.c b/drivers/iio/adc/sun4i-gpadc-iio.c
index a09e7f5dd8f7..292e0ac73d6f 100644
--- a/drivers/iio/adc/sun4i-gpadc-iio.c
+++ b/drivers/iio/adc/sun4i-gpadc-iio.c
@@ -460,10 +460,8 @@ static int sun4i_irq_init(struct platform_device *pdev, const char *name,
 	atomic_set(atomic, 1);
 
 	ret = platform_get_irq_byname(pdev, name);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "no %s interrupt registered\n", name);
+	if (ret < 0)
 		return ret;
-	}
 
 	ret = regmap_irq_get_virq(mfd_dev->regmap_irqc, ret);
 	if (ret < 0) {
diff --git a/drivers/iio/adc/ti-ads8344.c b/drivers/iio/adc/ti-ads8344.c
index 9a460807d46d..8a8792010c20 100644
--- a/drivers/iio/adc/ti-ads8344.c
+++ b/drivers/iio/adc/ti-ads8344.c
@@ -29,19 +29,20 @@ struct ads8344 {
 	struct mutex lock;
 
 	u8 tx_buf ____cacheline_aligned;
-	u16 rx_buf;
+	u8 rx_buf[3];
 };
 
-#define ADS8344_VOLTAGE_CHANNEL(chan, si)				\
+#define ADS8344_VOLTAGE_CHANNEL(chan, addr)				\
 	{								\
 		.type = IIO_VOLTAGE,					\
 		.indexed = 1,						\
 		.channel = chan,					\
 		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),		\
 		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),	\
+		.address = addr,					\
 	}
 
-#define ADS8344_VOLTAGE_CHANNEL_DIFF(chan1, chan2, si)			\
+#define ADS8344_VOLTAGE_CHANNEL_DIFF(chan1, chan2, addr)		\
 	{								\
 		.type = IIO_VOLTAGE,					\
 		.indexed = 1,						\
@@ -50,6 +51,7 @@ struct ads8344 {
 		.differential = 1,					\
 		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),		\
 		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),	\
+		.address = addr,					\
 	}
 
 static const struct iio_chan_spec ads8344_channels[] = {
@@ -89,11 +91,11 @@ static int ads8344_adc_conversion(struct ads8344 *adc, int channel,
 
 	udelay(9);
 
-	ret = spi_read(spi, &adc->rx_buf, 2);
+	ret = spi_read(spi, adc->rx_buf, sizeof(adc->rx_buf));
 	if (ret)
 		return ret;
 
-	return adc->rx_buf;
+	return adc->rx_buf[0] << 9 | adc->rx_buf[1] << 1 | adc->rx_buf[2] >> 7;
 }
 
 static int ads8344_read_raw(struct iio_dev *iio,
@@ -105,7 +107,7 @@ static int ads8344_read_raw(struct iio_dev *iio,
 	switch (mask) {
 	case IIO_CHAN_INFO_RAW:
 		mutex_lock(&adc->lock);
-		*value = ads8344_adc_conversion(adc, channel->scan_index,
+		*value = ads8344_adc_conversion(adc, channel->address,
 						channel->differential);
 		mutex_unlock(&adc->lock);
 		if (*value < 0)
diff --git a/drivers/iio/adc/twl6030-gpadc.c b/drivers/iio/adc/twl6030-gpadc.c
index 2fa6ec83bb13..f24148bd15de 100644
--- a/drivers/iio/adc/twl6030-gpadc.c
+++ b/drivers/iio/adc/twl6030-gpadc.c
@@ -905,10 +905,8 @@ static int twl6030_gpadc_probe(struct platform_device *pdev)
 	}
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(&pdev->dev, "failed to get irq\n");
+	if (irq < 0)
 		return irq;
-	}
 
 	ret = devm_request_threaded_irq(dev, irq, NULL,
 				twl6030_gpadc_irq_handler,
diff --git a/drivers/iio/adc/vf610_adc.c b/drivers/iio/adc/vf610_adc.c
index 41d3621c4787..98b30475bbc6 100644
--- a/drivers/iio/adc/vf610_adc.c
+++ b/drivers/iio/adc/vf610_adc.c
@@ -821,10 +821,8 @@ static int vf610_adc_probe(struct platform_device *pdev)
 		return PTR_ERR(info->regs);
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(&pdev->dev, "no irq resource?\n");
+	if (irq < 0)
 		return irq;
-	}
 
 	ret = devm_request_irq(info->dev, irq,
 				vf610_adc_isr, 0,
diff --git a/drivers/iio/adc/xilinx-xadc-core.c b/drivers/iio/adc/xilinx-xadc-core.c
index 4fd389678dba..3f0b88b13dd3 100644
--- a/drivers/iio/adc/xilinx-xadc-core.c
+++ b/drivers/iio/adc/xilinx-xadc-core.c
@@ -102,6 +102,16 @@ static const unsigned int XADC_ZYNQ_UNMASK_TIMEOUT = 500;
 
 #define XADC_FLAGS_BUFFERED BIT(0)
 
+/*
+ * The XADC hardware supports a samplerate of up to 1MSPS. Unfortunately it does
+ * not have a hardware FIFO. Which means an interrupt is generated for each
+ * conversion sequence. At 1MSPS sample rate the CPU in ZYNQ7000 is completely
+ * overloaded by the interrupts that it soft-lockups. For this reason the driver
+ * limits the maximum samplerate 150kSPS. At this rate the CPU is fairly busy,
+ * but still responsive.
+ */
+#define XADC_MAX_SAMPLERATE 150000
+
 static void xadc_write_reg(struct xadc *xadc, unsigned int reg,
 	uint32_t val)
 {
@@ -674,7 +684,7 @@ static int xadc_trigger_set_state(struct iio_trigger *trigger, bool state)
 
 	spin_lock_irqsave(&xadc->lock, flags);
 	xadc_read_reg(xadc, XADC_AXI_REG_IPIER, &val);
-	xadc_write_reg(xadc, XADC_AXI_REG_IPISR, val & XADC_AXI_INT_EOS);
+	xadc_write_reg(xadc, XADC_AXI_REG_IPISR, XADC_AXI_INT_EOS);
 	if (state)
 		val |= XADC_AXI_INT_EOS;
 	else
@@ -722,13 +732,14 @@ static int xadc_power_adc_b(struct xadc *xadc, unsigned int seq_mode)
 {
 	uint16_t val;
 
+	/* Powerdown the ADC-B when it is not needed. */
 	switch (seq_mode) {
 	case XADC_CONF1_SEQ_SIMULTANEOUS:
 	case XADC_CONF1_SEQ_INDEPENDENT:
-		val = XADC_CONF2_PD_ADC_B;
+		val = 0;
 		break;
 	default:
-		val = 0;
+		val = XADC_CONF2_PD_ADC_B;
 		break;
 	}
 
@@ -797,6 +808,16 @@ static int xadc_preenable(struct iio_dev *indio_dev)
 	if (ret)
 		goto err;
 
+	/*
+	 * In simultaneous mode the upper and lower aux channels are samples at
+	 * the same time. In this mode the upper 8 bits in the sequencer
+	 * register are don't care and the lower 8 bits control two channels
+	 * each. As such we must set the bit if either the channel in the lower
+	 * group or the upper group is enabled.
+	 */
+	if (seq_mode == XADC_CONF1_SEQ_SIMULTANEOUS)
+		scan_mask = ((scan_mask >> 8) | scan_mask) & 0xff0000;
+
 	ret = xadc_write_adc_reg(xadc, XADC_REG_SEQ(1), scan_mask >> 16);
 	if (ret)
 		goto err;
@@ -823,11 +844,27 @@ static const struct iio_buffer_setup_ops xadc_buffer_ops = {
 	.postdisable = &xadc_postdisable,
 };
 
+static int xadc_read_samplerate(struct xadc *xadc)
+{
+	unsigned int div;
+	uint16_t val16;
+	int ret;
+
+	ret = xadc_read_adc_reg(xadc, XADC_REG_CONF2, &val16);
+	if (ret)
+		return ret;
+
+	div = (val16 & XADC_CONF2_DIV_MASK) >> XADC_CONF2_DIV_OFFSET;
+	if (div < 2)
+		div = 2;
+
+	return xadc_get_dclk_rate(xadc) / div / 26;
+}
+
 static int xadc_read_raw(struct iio_dev *indio_dev,
 	struct iio_chan_spec const *chan, int *val, int *val2, long info)
 {
 	struct xadc *xadc = iio_priv(indio_dev);
-	unsigned int div;
 	uint16_t val16;
 	int ret;
 
@@ -880,41 +917,31 @@ static int xadc_read_raw(struct iio_dev *indio_dev,
 		*val = -((273150 << 12) / 503975);
 		return IIO_VAL_INT;
 	case IIO_CHAN_INFO_SAMP_FREQ:
-		ret = xadc_read_adc_reg(xadc, XADC_REG_CONF2, &val16);
-		if (ret)
+		ret = xadc_read_samplerate(xadc);
+		if (ret < 0)
 			return ret;
 
-		div = (val16 & XADC_CONF2_DIV_MASK) >> XADC_CONF2_DIV_OFFSET;
-		if (div < 2)
-			div = 2;
-
-		*val = xadc_get_dclk_rate(xadc) / div / 26;
-
+		*val = ret;
 		return IIO_VAL_INT;
 	default:
 		return -EINVAL;
 	}
 }
 
-static int xadc_write_raw(struct iio_dev *indio_dev,
-	struct iio_chan_spec const *chan, int val, int val2, long info)
+static int xadc_write_samplerate(struct xadc *xadc, int val)
 {
-	struct xadc *xadc = iio_priv(indio_dev);
 	unsigned long clk_rate = xadc_get_dclk_rate(xadc);
 	unsigned int div;
 
 	if (!clk_rate)
 		return -EINVAL;
 
-	if (info != IIO_CHAN_INFO_SAMP_FREQ)
-		return -EINVAL;
-
 	if (val <= 0)
 		return -EINVAL;
 
 	/* Max. 150 kSPS */
-	if (val > 150000)
-		val = 150000;
+	if (val > XADC_MAX_SAMPLERATE)
+		val = XADC_MAX_SAMPLERATE;
 
 	val *= 26;
 
@@ -927,7 +954,7 @@ static int xadc_write_raw(struct iio_dev *indio_dev,
 	 * limit.
 	 */
 	div = clk_rate / val;
-	if (clk_rate / div / 26 > 150000)
+	if (clk_rate / div / 26 > XADC_MAX_SAMPLERATE)
 		div++;
 	if (div < 2)
 		div = 2;
@@ -938,6 +965,17 @@ static int xadc_write_raw(struct iio_dev *indio_dev,
 		div << XADC_CONF2_DIV_OFFSET);
 }
 
+static int xadc_write_raw(struct iio_dev *indio_dev,
+	struct iio_chan_spec const *chan, int val, int val2, long info)
+{
+	struct xadc *xadc = iio_priv(indio_dev);
+
+	if (info != IIO_CHAN_INFO_SAMP_FREQ)
+		return -EINVAL;
+
+	return xadc_write_samplerate(xadc, val);
+}
+
 static const struct iio_event_spec xadc_temp_events[] = {
 	{
 		.type = IIO_EV_TYPE_THRESH,
@@ -1225,6 +1263,21 @@ static int xadc_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_free_samplerate_trigger;
 
+	/*
+	 * Make sure not to exceed the maximum samplerate since otherwise the
+	 * resulting interrupt storm will soft-lock the system.
+	 */
+	if (xadc->ops->flags & XADC_FLAGS_BUFFERED) {
+		ret = xadc_read_samplerate(xadc);
+		if (ret < 0)
+			goto err_free_samplerate_trigger;
+		if (ret > XADC_MAX_SAMPLERATE) {
+			ret = xadc_write_samplerate(xadc, XADC_MAX_SAMPLERATE);
+			if (ret < 0)
+				goto err_free_samplerate_trigger;
+		}
+	}
+
 	ret = request_irq(xadc->irq, xadc->ops->interrupt_handler, 0,
 			dev_name(&pdev->dev), indio_dev);
 	if (ret)
diff --git a/drivers/iio/chemical/Kconfig b/drivers/iio/chemical/Kconfig
index fa4586037bb8..a7e65a59bf42 100644
--- a/drivers/iio/chemical/Kconfig
+++ b/drivers/iio/chemical/Kconfig
@@ -65,6 +65,7 @@ config IAQCORE
 config PMS7003
 	tristate "Plantower PMS7003 particulate matter sensor"
 	depends on SERIAL_DEV_BUS
+	select IIO_BUFFER
 	select IIO_TRIGGERED_BUFFER
 	help
 	  Say Y here to build support for the Plantower PMS7003 particulate
@@ -90,6 +91,8 @@ config SPS30
 	tristate "SPS30 particulate matter sensor"
 	depends on I2C
 	select CRC8
+	select IIO_BUFFER
+	select IIO_TRIGGERED_BUFFER
 	help
 	  Say Y here to build support for the Sensirion SPS30 particulate
 	  matter sensor.
diff --git a/drivers/iio/chemical/pms7003.c b/drivers/iio/chemical/pms7003.c
index 23c9ab252470..07bb90d72434 100644
--- a/drivers/iio/chemical/pms7003.c
+++ b/drivers/iio/chemical/pms7003.c
@@ -73,6 +73,11 @@ struct pms7003_state {
 	struct pms7003_frame frame;
 	struct completion frame_ready;
 	struct mutex lock; /* must be held whenever state gets touched */
+	/* Used to construct scan to push to the IIO buffer */
+	struct {
+		u16 data[3]; /* PM1, PM2P5, PM10 */
+		s64 ts;
+	} scan;
 };
 
 static int pms7003_do_cmd(struct pms7003_state *state, enum pms7003_cmd cmd)
@@ -104,7 +109,6 @@ static irqreturn_t pms7003_trigger_handler(int irq, void *p)
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct pms7003_state *state = iio_priv(indio_dev);
 	struct pms7003_frame *frame = &state->frame;
-	u16 data[3 + 1 + 4]; /* PM1, PM2P5, PM10, padding, timestamp */
 	int ret;
 
 	mutex_lock(&state->lock);
@@ -114,12 +118,15 @@ static irqreturn_t pms7003_trigger_handler(int irq, void *p)
 		goto err;
 	}
 
-	data[PM1] = pms7003_get_pm(frame->data + PMS7003_PM1_OFFSET);
-	data[PM2P5] = pms7003_get_pm(frame->data + PMS7003_PM2P5_OFFSET);
-	data[PM10] = pms7003_get_pm(frame->data + PMS7003_PM10_OFFSET);
+	state->scan.data[PM1] =
+		pms7003_get_pm(frame->data + PMS7003_PM1_OFFSET);
+	state->scan.data[PM2P5] =
+		pms7003_get_pm(frame->data + PMS7003_PM2P5_OFFSET);
+	state->scan.data[PM10] =
+		pms7003_get_pm(frame->data + PMS7003_PM10_OFFSET);
 	mutex_unlock(&state->lock);
 
-	iio_push_to_buffers_with_timestamp(indio_dev, data,
+	iio_push_to_buffers_with_timestamp(indio_dev, &state->scan,
 					   iio_get_time_ns(indio_dev));
 err:
 	iio_trigger_notify_done(indio_dev->trig);
diff --git a/drivers/iio/chemical/sps30.c b/drivers/iio/chemical/sps30.c
index edbb956e81e8..c0845d892faa 100644
--- a/drivers/iio/chemical/sps30.c
+++ b/drivers/iio/chemical/sps30.c
@@ -230,15 +230,18 @@ static irqreturn_t sps30_trigger_handler(int irq, void *p)
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct sps30_state *state = iio_priv(indio_dev);
 	int ret;
-	s32 data[4 + 2]; /* PM1, PM2P5, PM4, PM10, timestamp */
+	struct {
+		s32 data[4]; /* PM1, PM2P5, PM4, PM10 */
+		s64 ts;
+	} scan;
 
 	mutex_lock(&state->lock);
-	ret = sps30_do_meas(state, data, 4);
+	ret = sps30_do_meas(state, scan.data, ARRAY_SIZE(scan.data));
 	mutex_unlock(&state->lock);
 	if (ret)
 		goto err;
 
-	iio_push_to_buffers_with_timestamp(indio_dev, data,
+	iio_push_to_buffers_with_timestamp(indio_dev, &scan,
 					   iio_get_time_ns(indio_dev));
 err:
 	iio_trigger_notify_done(indio_dev->trig);
diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c
index 8b22dc241482..4136fe8a4f91 100644
--- a/drivers/iio/common/st_sensors/st_sensors_core.c
+++ b/drivers/iio/common/st_sensors/st_sensors_core.c
@@ -92,7 +92,7 @@ int st_sensors_set_odr(struct iio_dev *indio_dev, unsigned int odr)
 	struct st_sensor_odr_avl odr_out = {0, 0};
 	struct st_sensor_data *sdata = iio_priv(indio_dev);
 
-	if (!sdata->sensor_settings->odr.addr)
+	if (!sdata->sensor_settings->odr.mask)
 		return 0;
 
 	err = st_sensors_match_odr(sdata->sensor_settings, odr, &odr_out);
diff --git a/drivers/iio/dac/ad5592r-base.c b/drivers/iio/dac/ad5592r-base.c
index 2d897e64c6a9..424922cad1e3 100644
--- a/drivers/iio/dac/ad5592r-base.c
+++ b/drivers/iio/dac/ad5592r-base.c
@@ -416,7 +416,7 @@ static int ad5592r_read_raw(struct iio_dev *iio_dev,
 			s64 tmp = *val * (3767897513LL / 25LL);
 			*val = div_s64_rem(tmp, 1000000000LL, val2);
 
-			ret = IIO_VAL_INT_PLUS_MICRO;
+			return IIO_VAL_INT_PLUS_MICRO;
 		} else {
 			int mult;
 
@@ -447,7 +447,7 @@ static int ad5592r_read_raw(struct iio_dev *iio_dev,
 		ret =  IIO_VAL_INT;
 		break;
 	default:
-		ret = -EINVAL;
+		return -EINVAL;
 	}
 
 unlock:
diff --git a/drivers/iio/dac/vf610_dac.c b/drivers/iio/dac/vf610_dac.c
index 0ec4d2609ef9..364925d703db 100644
--- a/drivers/iio/dac/vf610_dac.c
+++ b/drivers/iio/dac/vf610_dac.c
@@ -225,6 +225,7 @@ static int vf610_dac_probe(struct platform_device *pdev)
 	return 0;
 
 error_iio_device_register:
+	vf610_dac_exit(info);
 	clk_disable_unprepare(info->clk);
 
 	return ret;
diff --git a/drivers/iio/gyro/st_gyro_core.c b/drivers/iio/gyro/st_gyro_core.c
index e995dc77e30e..6c4e47ff4e3c 100644
--- a/drivers/iio/gyro/st_gyro_core.c
+++ b/drivers/iio/gyro/st_gyro_core.c
@@ -140,7 +140,6 @@ static const struct st_sensor_settings st_gyro_sensors_settings[] = {
 			[2] = LSM330DLC_GYRO_DEV_NAME,
 			[3] = L3G4IS_GYRO_DEV_NAME,
 			[4] = LSM330_GYRO_DEV_NAME,
-			[5] = LSM9DS0_GYRO_DEV_NAME,
 		},
 		.ch = (struct iio_chan_spec *)st_gyro_16bit_channels,
 		.odr = {
@@ -211,6 +210,80 @@ static const struct st_sensor_settings st_gyro_sensors_settings[] = {
 		.bootime = 2,
 	},
 	{
+		.wai = 0xd4,
+		.wai_addr = ST_SENSORS_DEFAULT_WAI_ADDRESS,
+		.sensors_supported = {
+			[0] = LSM9DS0_GYRO_DEV_NAME,
+		},
+		.ch = (struct iio_chan_spec *)st_gyro_16bit_channels,
+		.odr = {
+			.addr = 0x20,
+			.mask = GENMASK(7, 6),
+			.odr_avl = {
+				{ .hz = 95, .value = 0x00, },
+				{ .hz = 190, .value = 0x01, },
+				{ .hz = 380, .value = 0x02, },
+				{ .hz = 760, .value = 0x03, },
+			},
+		},
+		.pw = {
+			.addr = 0x20,
+			.mask = BIT(3),
+			.value_on = ST_SENSORS_DEFAULT_POWER_ON_VALUE,
+			.value_off = ST_SENSORS_DEFAULT_POWER_OFF_VALUE,
+		},
+		.enable_axis = {
+			.addr = ST_SENSORS_DEFAULT_AXIS_ADDR,
+			.mask = ST_SENSORS_DEFAULT_AXIS_MASK,
+		},
+		.fs = {
+			.addr = 0x23,
+			.mask = GENMASK(5, 4),
+			.fs_avl = {
+				[0] = {
+					.num = ST_GYRO_FS_AVL_245DPS,
+					.value = 0x00,
+					.gain = IIO_DEGREE_TO_RAD(8750),
+				},
+				[1] = {
+					.num = ST_GYRO_FS_AVL_500DPS,
+					.value = 0x01,
+					.gain = IIO_DEGREE_TO_RAD(17500),
+				},
+				[2] = {
+					.num = ST_GYRO_FS_AVL_2000DPS,
+					.value = 0x02,
+					.gain = IIO_DEGREE_TO_RAD(70000),
+				},
+			},
+		},
+		.bdu = {
+			.addr = 0x23,
+			.mask = BIT(7),
+		},
+		.drdy_irq = {
+			.int2 = {
+				.addr = 0x22,
+				.mask = BIT(3),
+			},
+			/*
+			 * The sensor has IHL (active low) and open
+			 * drain settings, but only for INT1 and not
+			 * for the DRDY line on INT2.
+			 */
+			.stat_drdy = {
+				.addr = ST_SENSORS_DEFAULT_STAT_ADDR,
+				.mask = GENMASK(2, 0),
+			},
+		},
+		.sim = {
+			.addr = 0x23,
+			.value = BIT(0),
+		},
+		.multi_read_bit = true,
+		.bootime = 2,
+	},
+	{
 		.wai = 0xd7,
 		.wai_addr = ST_SENSORS_DEFAULT_WAI_ADDRESS,
 		.sensors_supported = {
diff --git a/drivers/iio/health/afe4403.c b/drivers/iio/health/afe4403.c
index dc22dc363a99..a3507624b30f 100644
--- a/drivers/iio/health/afe4403.c
+++ b/drivers/iio/health/afe4403.c
@@ -23,6 +23,8 @@
 #include <linux/iio/triggered_buffer.h>
 #include <linux/iio/trigger_consumer.h>
 
+#include <asm/unaligned.h>
+
 #include "afe440x.h"
 
 #define AFE4403_DRIVER_NAME		"afe4403"
@@ -63,6 +65,7 @@ static const struct reg_field afe4403_reg_fields[] = {
  * @regulator: Pointer to the regulator for the IC
  * @trig: IIO trigger for this device
  * @irq: ADC_RDY line interrupt number
+ * @buffer: Used to construct data layout to push into IIO buffer.
  */
 struct afe4403_data {
 	struct device *dev;
@@ -72,6 +75,8 @@ struct afe4403_data {
 	struct regulator *regulator;
 	struct iio_trigger *trig;
 	int irq;
+	/* Ensure suitable alignment for timestamp */
+	s32 buffer[8] __aligned(8);
 };
 
 enum afe4403_chan_id {
@@ -220,13 +225,11 @@ static int afe4403_read(struct afe4403_data *afe, unsigned int reg, u32 *val)
 	if (ret)
 		return ret;
 
-	ret = spi_write_then_read(afe->spi, &reg, 1, rx, 3);
+	ret = spi_write_then_read(afe->spi, &reg, 1, rx, sizeof(rx));
 	if (ret)
 		return ret;
 
-	*val = (rx[0] << 16) |
-		(rx[1] << 8) |
-		(rx[2]);
+	*val = get_unaligned_be24(&rx[0]);
 
 	/* Disable reading from the device */
 	tx[3] = AFE440X_CONTROL0_WRITE;
@@ -309,7 +312,6 @@ static irqreturn_t afe4403_trigger_handler(int irq, void *private)
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct afe4403_data *afe = iio_priv(indio_dev);
 	int ret, bit, i = 0;
-	s32 buffer[8];
 	u8 tx[4] = {AFE440X_CONTROL0, 0x0, 0x0, AFE440X_CONTROL0_READ};
 	u8 rx[3];
 
@@ -322,13 +324,11 @@ static irqreturn_t afe4403_trigger_handler(int irq, void *private)
 			 indio_dev->masklength) {
 		ret = spi_write_then_read(afe->spi,
 					  &afe4403_channel_values[bit], 1,
-					  rx, 3);
+					  rx, sizeof(rx));
 		if (ret)
 			goto err;
 
-		buffer[i++] = (rx[0] << 16) |
-				(rx[1] << 8) |
-				(rx[2]);
+		afe->buffer[i++] = get_unaligned_be24(&rx[0]);
 	}
 
 	/* Disable reading from the device */
@@ -337,7 +337,8 @@ static irqreturn_t afe4403_trigger_handler(int irq, void *private)
 	if (ret)
 		goto err;
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buffer, pf->timestamp);
+	iio_push_to_buffers_with_timestamp(indio_dev, afe->buffer,
+					   pf->timestamp);
 err:
 	iio_trigger_notify_done(indio_dev->trig);
 
diff --git a/drivers/iio/health/afe4404.c b/drivers/iio/health/afe4404.c
index e728bbb21ca8..cebb1fd4d0b1 100644
--- a/drivers/iio/health/afe4404.c
+++ b/drivers/iio/health/afe4404.c
@@ -83,6 +83,7 @@ static const struct reg_field afe4404_reg_fields[] = {
  * @regulator: Pointer to the regulator for the IC
  * @trig: IIO trigger for this device
  * @irq: ADC_RDY line interrupt number
+ * @buffer: Used to construct a scan to push to the iio buffer.
  */
 struct afe4404_data {
 	struct device *dev;
@@ -91,6 +92,7 @@ struct afe4404_data {
 	struct regulator *regulator;
 	struct iio_trigger *trig;
 	int irq;
+	s32 buffer[10] __aligned(8);
 };
 
 enum afe4404_chan_id {
@@ -328,17 +330,17 @@ static irqreturn_t afe4404_trigger_handler(int irq, void *private)
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct afe4404_data *afe = iio_priv(indio_dev);
 	int ret, bit, i = 0;
-	s32 buffer[10];
 
 	for_each_set_bit(bit, indio_dev->active_scan_mask,
 			 indio_dev->masklength) {
 		ret = regmap_read(afe->regmap, afe4404_channel_values[bit],
-				  &buffer[i++]);
+				  &afe->buffer[i++]);
 		if (ret)
 			goto err;
 	}
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buffer, pf->timestamp);
+	iio_push_to_buffers_with_timestamp(indio_dev, afe->buffer,
+					   pf->timestamp);
 err:
 	iio_trigger_notify_done(indio_dev->trig);
 
diff --git a/drivers/iio/humidity/hdc100x.c b/drivers/iio/humidity/hdc100x.c
index ff6666ac5d68..0fcaa2c0b2f4 100644
--- a/drivers/iio/humidity/hdc100x.c
+++ b/drivers/iio/humidity/hdc100x.c
@@ -38,6 +38,11 @@ struct hdc100x_data {
 
 	/* integration time of the sensor */
 	int adc_int_us[2];
+	/* Ensure natural alignment of timestamp */
+	struct {
+		__be16 channels[2];
+		s64 ts __aligned(8);
+	} scan;
 };
 
 /* integration time in us */
@@ -319,7 +324,6 @@ static irqreturn_t hdc100x_trigger_handler(int irq, void *p)
 	struct i2c_client *client = data->client;
 	int delay = data->adc_int_us[0] + data->adc_int_us[1];
 	int ret;
-	s16 buf[8];  /* 2x s16 + padding + 8 byte timestamp */
 
 	/* dual read starts at temp register */
 	mutex_lock(&data->lock);
@@ -330,13 +334,13 @@ static irqreturn_t hdc100x_trigger_handler(int irq, void *p)
 	}
 	usleep_range(delay, delay + 1000);
 
-	ret = i2c_master_recv(client, (u8 *)buf, 4);
+	ret = i2c_master_recv(client, (u8 *)data->scan.channels, 4);
 	if (ret < 0) {
 		dev_err(&client->dev, "cannot read sensor data\n");
 		goto err;
 	}
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buf,
+	iio_push_to_buffers_with_timestamp(indio_dev, &data->scan,
 					   iio_get_time_ns(indio_dev));
 err:
 	mutex_unlock(&data->lock);
diff --git a/drivers/iio/humidity/hts221.h b/drivers/iio/humidity/hts221.h
index 7d6771f7cf47..b2eb5abeaccd 100644
--- a/drivers/iio/humidity/hts221.h
+++ b/drivers/iio/humidity/hts221.h
@@ -14,8 +14,6 @@
 
 #include <linux/iio/iio.h>
 
-#define HTS221_DATA_SIZE	2
-
 enum hts221_sensor_type {
 	HTS221_SENSOR_H,
 	HTS221_SENSOR_T,
@@ -39,6 +37,11 @@ struct hts221_hw {
 
 	bool enabled;
 	u8 odr;
+	/* Ensure natural alignment of timestamp */
+	struct {
+		__le16 channels[2];
+		s64 ts __aligned(8);
+	} scan;
 };
 
 extern const struct dev_pm_ops hts221_pm_ops;
diff --git a/drivers/iio/humidity/hts221_buffer.c b/drivers/iio/humidity/hts221_buffer.c
index 81d50a861c22..49dcd36d8838 100644
--- a/drivers/iio/humidity/hts221_buffer.c
+++ b/drivers/iio/humidity/hts221_buffer.c
@@ -162,7 +162,6 @@ static const struct iio_buffer_setup_ops hts221_buffer_ops = {
 
 static irqreturn_t hts221_buffer_handler_thread(int irq, void *p)
 {
-	u8 buffer[ALIGN(2 * HTS221_DATA_SIZE, sizeof(s64)) + sizeof(s64)];
 	struct iio_poll_func *pf = p;
 	struct iio_dev *iio_dev = pf->indio_dev;
 	struct hts221_hw *hw = iio_priv(iio_dev);
@@ -172,18 +171,20 @@ static irqreturn_t hts221_buffer_handler_thread(int irq, void *p)
 	/* humidity data */
 	ch = &iio_dev->channels[HTS221_SENSOR_H];
 	err = regmap_bulk_read(hw->regmap, ch->address,
-			       buffer, HTS221_DATA_SIZE);
+			       &hw->scan.channels[0],
+			       sizeof(hw->scan.channels[0]));
 	if (err < 0)
 		goto out;
 
 	/* temperature data */
 	ch = &iio_dev->channels[HTS221_SENSOR_T];
 	err = regmap_bulk_read(hw->regmap, ch->address,
-			       buffer + HTS221_DATA_SIZE, HTS221_DATA_SIZE);
+			       &hw->scan.channels[1],
+			       sizeof(hw->scan.channels[1]));
 	if (err < 0)
 		goto out;
 
-	iio_push_to_buffers_with_timestamp(iio_dev, buffer,
+	iio_push_to_buffers_with_timestamp(iio_dev, &hw->scan,
 					   iio_get_time_ns(iio_dev));
 
 out:
diff --git a/drivers/iio/imu/adis16480.c b/drivers/iio/imu/adis16480.c
index 7b966a41d623..cf7b59d97802 100644
--- a/drivers/iio/imu/adis16480.c
+++ b/drivers/iio/imu/adis16480.c
@@ -454,12 +454,14 @@ static int adis16480_get_calibbias(struct iio_dev *indio_dev,
 	case IIO_MAGN:
 	case IIO_PRESSURE:
 		ret = adis_read_reg_16(&st->adis, reg, &val16);
-		*bias = sign_extend32(val16, 15);
+		if (ret == 0)
+			*bias = sign_extend32(val16, 15);
 		break;
 	case IIO_ANGL_VEL:
 	case IIO_ACCEL:
 		ret = adis_read_reg_32(&st->adis, reg, &val32);
-		*bias = sign_extend32(val32, 31);
+		if (ret == 0)
+			*bias = sign_extend32(val32, 31);
 		break;
 	default:
 			ret = -EINVAL;
diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
index c193d64e5217..112225c0e486 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -566,7 +566,7 @@ static int iio_compute_scan_bytes(struct iio_dev *indio_dev,
 				const unsigned long *mask, bool timestamp)
 {
 	unsigned bytes = 0;
-	int length, i;
+	int length, i, largest = 0;
 
 	/* How much space will the demuxed element take? */
 	for_each_set_bit(i, mask,
@@ -574,13 +574,17 @@ static int iio_compute_scan_bytes(struct iio_dev *indio_dev,
 		length = iio_storage_bytes_for_si(indio_dev, i);
 		bytes = ALIGN(bytes, length);
 		bytes += length;
+		largest = max(largest, length);
 	}
 
 	if (timestamp) {
 		length = iio_storage_bytes_for_timestamp(indio_dev);
 		bytes = ALIGN(bytes, length);
 		bytes += length;
+		largest = max(largest, length);
 	}
+
+	bytes = ALIGN(bytes, largest);
 	return bytes;
 }
 
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 245b5844028d..393bafc91331 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -130,6 +130,8 @@ static const char * const iio_modifier_names[] = {
 	[IIO_MOD_PM2P5] = "pm2p5",
 	[IIO_MOD_PM4] = "pm4",
 	[IIO_MOD_PM10] = "pm10",
+	[IIO_MOD_ETHANOL] = "ethanol",
+	[IIO_MOD_H2] = "h2",
 };
 
 /* relies on pairs of these shared then separate */
diff --git a/drivers/iio/light/si1133.c b/drivers/iio/light/si1133.c
index 015a21f0c2ef..9174ab928880 100644
--- a/drivers/iio/light/si1133.c
+++ b/drivers/iio/light/si1133.c
@@ -102,6 +102,9 @@
 #define SI1133_INPUT_FRACTION_LOW	15
 #define SI1133_LUX_OUTPUT_FRACTION	12
 #define SI1133_LUX_BUFFER_SIZE		9
+#define SI1133_MEASURE_BUFFER_SIZE	3
+
+#define SI1133_SIGN_BIT_INDEX 23
 
 static const int si1133_scale_available[] = {
 	1, 2, 4, 8, 16, 32, 64, 128};
@@ -234,13 +237,13 @@ static const struct si1133_lux_coeff lux_coeff = {
 	}
 };
 
-static int si1133_calculate_polynomial_inner(u32 input, u8 fraction, u16 mag,
+static int si1133_calculate_polynomial_inner(s32 input, u8 fraction, u16 mag,
 					     s8 shift)
 {
 	return ((input << fraction) / mag) << shift;
 }
 
-static int si1133_calculate_output(u32 x, u32 y, u8 x_order, u8 y_order,
+static int si1133_calculate_output(s32 x, s32 y, u8 x_order, u8 y_order,
 				   u8 input_fraction, s8 sign,
 				   const struct si1133_coeff *coeffs)
 {
@@ -276,7 +279,7 @@ static int si1133_calculate_output(u32 x, u32 y, u8 x_order, u8 y_order,
  * The algorithm is from:
  * https://siliconlabs.github.io/Gecko_SDK_Doc/efm32zg/html/si1133_8c_source.html#l00716
  */
-static int si1133_calc_polynomial(u32 x, u32 y, u8 input_fraction, u8 num_coeff,
+static int si1133_calc_polynomial(s32 x, s32 y, u8 input_fraction, u8 num_coeff,
 				  const struct si1133_coeff *coeffs)
 {
 	u8 x_order, y_order;
@@ -614,7 +617,7 @@ static int si1133_measure(struct si1133_data *data,
 {
 	int err;
 
-	__be16 resp;
+	u8 buffer[SI1133_MEASURE_BUFFER_SIZE];
 
 	err = si1133_set_adcmux(data, 0, chan->channel);
 	if (err)
@@ -625,12 +628,13 @@ static int si1133_measure(struct si1133_data *data,
 	if (err)
 		return err;
 
-	err = si1133_bulk_read(data, SI1133_REG_HOSTOUT(0), sizeof(resp),
-			       (u8 *)&resp);
+	err = si1133_bulk_read(data, SI1133_REG_HOSTOUT(0), sizeof(buffer),
+			       buffer);
 	if (err)
 		return err;
 
-	*val = be16_to_cpu(resp);
+	*val = sign_extend32((buffer[0] << 16) | (buffer[1] << 8) | buffer[2],
+			     SI1133_SIGN_BIT_INDEX);
 
 	return err;
 }
@@ -704,9 +708,9 @@ static int si1133_get_lux(struct si1133_data *data, int *val)
 {
 	int err;
 	int lux;
-	u32 high_vis;
-	u32 low_vis;
-	u32 ir;
+	s32 high_vis;
+	s32 low_vis;
+	s32 ir;
 	u8 buffer[SI1133_LUX_BUFFER_SIZE];
 
 	/* Activate lux channels */
@@ -719,9 +723,16 @@ static int si1133_get_lux(struct si1133_data *data, int *val)
 	if (err)
 		return err;
 
-	high_vis = (buffer[0] << 16) | (buffer[1] << 8) | buffer[2];
-	low_vis = (buffer[3] << 16) | (buffer[4] << 8) | buffer[5];
-	ir = (buffer[6] << 16) | (buffer[7] << 8) | buffer[8];
+	high_vis =
+		sign_extend32((buffer[0] << 16) | (buffer[1] << 8) | buffer[2],
+			      SI1133_SIGN_BIT_INDEX);
+
+	low_vis =
+		sign_extend32((buffer[3] << 16) | (buffer[4] << 8) | buffer[5],
+			      SI1133_SIGN_BIT_INDEX);
+
+	ir = sign_extend32((buffer[6] << 16) | (buffer[7] << 8) | buffer[8],
+			   SI1133_SIGN_BIT_INDEX);
 
 	if (high_vis > SI1133_ADC_THRESHOLD || ir > SI1133_ADC_THRESHOLD)
 		lux = si1133_calc_polynomial(high_vis, ir,
diff --git a/drivers/iio/light/vcnl4000.c b/drivers/iio/light/vcnl4000.c
index 51421ac32517..7384a3ffcac4 100644
--- a/drivers/iio/light/vcnl4000.c
+++ b/drivers/iio/light/vcnl4000.c
@@ -163,20 +163,22 @@ static int vcnl4200_init(struct vcnl4000_data *data)
 	if (ret < 0)
 		return ret;
 
-	data->al_scale = 24000;
 	data->vcnl4200_al.reg = VCNL4200_AL_DATA;
 	data->vcnl4200_ps.reg = VCNL4200_PS_DATA;
 	switch (id) {
 	case VCNL4200_PROD_ID:
-		/* Integration time is 50ms, but the experiments */
-		/* show 54ms in total. */
-		data->vcnl4200_al.sampling_rate = ktime_set(0, 54000 * 1000);
-		data->vcnl4200_ps.sampling_rate = ktime_set(0, 4200 * 1000);
+		/* Default wait time is 50ms, add 20% tolerance. */
+		data->vcnl4200_al.sampling_rate = ktime_set(0, 60000 * 1000);
+		/* Default wait time is 4.8ms, add 20% tolerance. */
+		data->vcnl4200_ps.sampling_rate = ktime_set(0, 5760 * 1000);
+		data->al_scale = 24000;
 		break;
 	case VCNL4040_PROD_ID:
-		/* Integration time is 80ms, add 10ms. */
-		data->vcnl4200_al.sampling_rate = ktime_set(0, 100000 * 1000);
-		data->vcnl4200_ps.sampling_rate = ktime_set(0, 100000 * 1000);
+		/* Default wait time is 80ms, add 20% tolerance. */
+		data->vcnl4200_al.sampling_rate = ktime_set(0, 96000 * 1000);
+		/* Default wait time is 5ms, add 20% tolerance. */
+		data->vcnl4200_ps.sampling_rate = ktime_set(0, 6000 * 1000);
+		data->al_scale = 120000;
 		break;
 	}
 	data->vcnl4200_al.last_measurement = ktime_set(0, 0);
@@ -191,7 +193,6 @@ static int vcnl4000_measure(struct vcnl4000_data *data, u8 req_mask,
 				u8 rdy_mask, u8 data_reg, int *val)
 {
 	int tries = 20;
-	__be16 buf;
 	int ret;
 
 	mutex_lock(&data->vcnl4000_lock);
@@ -218,13 +219,12 @@ static int vcnl4000_measure(struct vcnl4000_data *data, u8 req_mask,
 		goto fail;
 	}
 
-	ret = i2c_smbus_read_i2c_block_data(data->client,
-		data_reg, sizeof(buf), (u8 *) &buf);
+	ret = i2c_smbus_read_word_swapped(data->client, data_reg);
 	if (ret < 0)
 		goto fail;
 
 	mutex_unlock(&data->vcnl4000_lock);
-	*val = be16_to_cpu(buf);
+	*val = ret;
 
 	return 0;
 
@@ -398,19 +398,23 @@ static int vcnl4000_probe(struct i2c_client *client,
 static const struct of_device_id vcnl_4000_of_match[] = {
 	{
 		.compatible = "vishay,vcnl4000",
-		.data = "VCNL4000",
+		.data = (void *)VCNL4000,
 	},
 	{
 		.compatible = "vishay,vcnl4010",
-		.data = "VCNL4010",
+		.data = (void *)VCNL4010,
 	},
 	{
-		.compatible = "vishay,vcnl4010",
-		.data = "VCNL4020",
+		.compatible = "vishay,vcnl4020",
+		.data = (void *)VCNL4010,
+	},
+	{
+		.compatible = "vishay,vcnl4040",
+		.data = (void *)VCNL4040,
 	},
 	{
 		.compatible = "vishay,vcnl4200",
-		.data = "VCNL4200",
+		.data = (void *)VCNL4200,
 	},
 	{},
 };
diff --git a/drivers/iio/magnetometer/ak8974.c b/drivers/iio/magnetometer/ak8974.c
index fc7e910f8e8b..87c15a63c1a4 100644
--- a/drivers/iio/magnetometer/ak8974.c
+++ b/drivers/iio/magnetometer/ak8974.c
@@ -185,6 +185,11 @@ struct ak8974 {
 	bool drdy_irq;
 	struct completion drdy_complete;
 	bool drdy_active_low;
+	/* Ensure timestamp is naturally aligned */
+	struct {
+		__le16 channels[3];
+		s64 ts __aligned(8);
+	} scan;
 };
 
 static const char ak8974_reg_avdd[] = "avdd";
@@ -564,7 +569,7 @@ static int ak8974_read_raw(struct iio_dev *indio_dev,
 		 * We read all axes and discard all but one, for optimized
 		 * reading, use the triggered buffer.
 		 */
-		*val = le16_to_cpu(hw_values[chan->address]);
+		*val = (s16)le16_to_cpu(hw_values[chan->address]);
 
 		ret = IIO_VAL_INT;
 	}
@@ -581,7 +586,6 @@ static void ak8974_fill_buffer(struct iio_dev *indio_dev)
 {
 	struct ak8974 *ak8974 = iio_priv(indio_dev);
 	int ret;
-	__le16 hw_values[8]; /* Three axes + 64bit padding */
 
 	pm_runtime_get_sync(&ak8974->i2c->dev);
 	mutex_lock(&ak8974->lock);
@@ -591,13 +595,13 @@ static void ak8974_fill_buffer(struct iio_dev *indio_dev)
 		dev_err(&ak8974->i2c->dev, "error triggering measure\n");
 		goto out_unlock;
 	}
-	ret = ak8974_getresult(ak8974, hw_values);
+	ret = ak8974_getresult(ak8974, ak8974->scan.channels);
 	if (ret) {
 		dev_err(&ak8974->i2c->dev, "error getting measures\n");
 		goto out_unlock;
 	}
 
-	iio_push_to_buffers_with_timestamp(indio_dev, hw_values,
+	iio_push_to_buffers_with_timestamp(indio_dev, &ak8974->scan,
 					   iio_get_time_ns(indio_dev));
 
  out_unlock:
@@ -764,19 +768,21 @@ static int ak8974_probe(struct i2c_client *i2c,
 	ak8974->map = devm_regmap_init_i2c(i2c, &ak8974_regmap_config);
 	if (IS_ERR(ak8974->map)) {
 		dev_err(&i2c->dev, "failed to allocate register map\n");
+		pm_runtime_put_noidle(&i2c->dev);
+		pm_runtime_disable(&i2c->dev);
 		return PTR_ERR(ak8974->map);
 	}
 
 	ret = ak8974_set_power(ak8974, AK8974_PWR_ON);
 	if (ret) {
 		dev_err(&i2c->dev, "could not power on\n");
-		goto power_off;
+		goto disable_pm;
 	}
 
 	ret = ak8974_detect(ak8974);
 	if (ret) {
 		dev_err(&i2c->dev, "neither AK8974 nor AMI30x found\n");
-		goto power_off;
+		goto disable_pm;
 	}
 
 	ret = ak8974_selftest(ak8974);
@@ -786,14 +792,9 @@ static int ak8974_probe(struct i2c_client *i2c,
 	ret = ak8974_reset(ak8974);
 	if (ret) {
 		dev_err(&i2c->dev, "AK8974 reset failed\n");
-		goto power_off;
+		goto disable_pm;
 	}
 
-	pm_runtime_set_autosuspend_delay(&i2c->dev,
-					 AK8974_AUTOSUSPEND_DELAY);
-	pm_runtime_use_autosuspend(&i2c->dev);
-	pm_runtime_put(&i2c->dev);
-
 	indio_dev->dev.parent = &i2c->dev;
 	indio_dev->channels = ak8974_channels;
 	indio_dev->num_channels = ARRAY_SIZE(ak8974_channels);
@@ -846,6 +847,11 @@ no_irq:
 		goto cleanup_buffer;
 	}
 
+	pm_runtime_set_autosuspend_delay(&i2c->dev,
+					 AK8974_AUTOSUSPEND_DELAY);
+	pm_runtime_use_autosuspend(&i2c->dev);
+	pm_runtime_put(&i2c->dev);
+
 	return 0;
 
 cleanup_buffer:
@@ -854,7 +860,6 @@ disable_pm:
 	pm_runtime_put_noidle(&i2c->dev);
 	pm_runtime_disable(&i2c->dev);
 	ak8974_set_power(ak8974, AK8974_PWR_OFF);
-power_off:
 	regulator_bulk_disable(ARRAY_SIZE(ak8974->regs), ak8974->regs);
 
 	return ret;
diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c
index 8d0f15f27dc5..0a95afaa48fe 100644
--- a/drivers/iio/pressure/bmp280-core.c
+++ b/drivers/iio/pressure/bmp280-core.c
@@ -264,6 +264,8 @@ static u32 bmp280_compensate_humidity(struct bmp280_data *data,
 		+ (s32)2097152) * calib->H2 + 8192) >> 14);
 	var -= ((((var >> 15) * (var >> 15)) >> 7) * (s32)calib->H1) >> 4;
 
+	var = clamp_val(var, 0, 419430400);
+
 	return var >> 12;
 };
 
@@ -706,7 +708,7 @@ static int bmp180_measure(struct bmp280_data *data, u8 ctrl_meas)
 	unsigned int ctrl;
 
 	if (data->use_eoc)
-		init_completion(&data->done);
+		reinit_completion(&data->done);
 
 	ret = regmap_write(data->regmap, BMP280_REG_CTRL_MEAS, ctrl_meas);
 	if (ret)
@@ -962,6 +964,9 @@ static int bmp085_fetch_eoc_irq(struct device *dev,
 			"trying to enforce it\n");
 		irq_trig = IRQF_TRIGGER_RISING;
 	}
+
+	init_completion(&data->done);
+
 	ret = devm_request_threaded_irq(dev,
 			irq,
 			bmp085_eoc_irq,
diff --git a/drivers/iio/pressure/ms5611_core.c b/drivers/iio/pressure/ms5611_core.c
index 2f598ad91621..f5db9fa086f3 100644
--- a/drivers/iio/pressure/ms5611_core.c
+++ b/drivers/iio/pressure/ms5611_core.c
@@ -212,16 +212,21 @@ static irqreturn_t ms5611_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct ms5611_state *st = iio_priv(indio_dev);
-	s32 buf[4]; /* s32 (pressure) + s32 (temp) + 2 * s32 (timestamp) */
+	/* Ensure buffer elements are naturally aligned */
+	struct {
+		s32 channels[2];
+		s64 ts __aligned(8);
+	} scan;
 	int ret;
 
 	mutex_lock(&st->lock);
-	ret = ms5611_read_temp_and_pressure(indio_dev, &buf[1], &buf[0]);
+	ret = ms5611_read_temp_and_pressure(indio_dev, &scan.channels[1],
+					    &scan.channels[0]);
 	mutex_unlock(&st->lock);
 	if (ret < 0)
 		goto err;
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buf,
+	iio_push_to_buffers_with_timestamp(indio_dev, &scan,
 					   iio_get_time_ns(indio_dev));
 
 err:
diff --git a/drivers/iio/pressure/zpa2326.c b/drivers/iio/pressure/zpa2326.c
index 9d0d07930236..7f2e5a8942a4 100644
--- a/drivers/iio/pressure/zpa2326.c
+++ b/drivers/iio/pressure/zpa2326.c
@@ -664,8 +664,10 @@ static int zpa2326_resume(const struct iio_dev *indio_dev)
 	int err;
 
 	err = pm_runtime_get_sync(indio_dev->dev.parent);
-	if (err < 0)
+	if (err < 0) {
+		pm_runtime_put(indio_dev->dev.parent);
 		return err;
+	}
 
 	if (err > 0) {
 		/*
diff --git a/drivers/iio/trigger/stm32-timer-trigger.c b/drivers/iio/trigger/stm32-timer-trigger.c
index ccf1ce653b25..7722745e101f 100644
--- a/drivers/iio/trigger/stm32-timer-trigger.c
+++ b/drivers/iio/trigger/stm32-timer-trigger.c
@@ -161,7 +161,8 @@ static int stm32_timer_start(struct stm32_timer_trigger *priv,
 	return 0;
 }
 
-static void stm32_timer_stop(struct stm32_timer_trigger *priv)
+static void stm32_timer_stop(struct stm32_timer_trigger *priv,
+			     struct iio_trigger *trig)
 {
 	u32 ccer, cr1;
 
@@ -179,6 +180,12 @@ static void stm32_timer_stop(struct stm32_timer_trigger *priv)
 	regmap_write(priv->regmap, TIM_PSC, 0);
 	regmap_write(priv->regmap, TIM_ARR, 0);
 
+	/* Force disable master mode */
+	if (stm32_timer_is_trgo2_name(trig->name))
+		regmap_update_bits(priv->regmap, TIM_CR2, TIM_CR2_MMS2, 0);
+	else
+		regmap_update_bits(priv->regmap, TIM_CR2, TIM_CR2_MMS, 0);
+
 	/* Make sure that registers are updated */
 	regmap_update_bits(priv->regmap, TIM_EGR, TIM_EGR_UG, TIM_EGR_UG);
 }
@@ -197,7 +204,7 @@ static ssize_t stm32_tt_store_frequency(struct device *dev,
 		return ret;
 
 	if (freq == 0) {
-		stm32_timer_stop(priv);
+		stm32_timer_stop(priv, trig);
 	} else {
 		ret = stm32_timer_start(priv, trig, freq);
 		if (ret)
diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index fca5025d5a1a..152b3069588a 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -139,7 +139,7 @@ int ib_nl_handle_ip_res_resp(struct sk_buff *skb,
 	if (ib_nl_is_good_ip_resp(nlh))
 		ib_nl_process_good_ip_rsep(nlh);
 
-	return skb->len;
+	return 0;
 }
 
 static int ib_nl_ip_send_msg(struct rdma_dev_addr *dev_addr,
diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c
index 18e476b3ced0..bac02a44cc23 100644
--- a/drivers/infiniband/core/cache.c
+++ b/drivers/infiniband/core/cache.c
@@ -51,9 +51,8 @@ struct ib_pkey_cache {
 
 struct ib_update_work {
 	struct work_struct work;
-	struct ib_device  *device;
-	u8                 port_num;
-	bool		   enforce_security;
+	struct ib_event event;
+	bool enforce_security;
 };
 
 union ib_gid zgid;
@@ -130,7 +129,7 @@ static void dispatch_gid_change_event(struct ib_device *ib_dev, u8 port)
 	event.element.port_num	= port;
 	event.event		= IB_EVENT_GID_CHANGE;
 
-	ib_dispatch_event(&event);
+	ib_dispatch_event_clients(&event);
 }
 
 static const char * const gid_type_str[] = {
@@ -1386,9 +1385,8 @@ err:
 	return ret;
 }
 
-static void ib_cache_update(struct ib_device *device,
-			    u8                port,
-			    bool	      enforce_security)
+static int
+ib_cache_update(struct ib_device *device, u8 port, bool enforce_security)
 {
 	struct ib_port_attr       *tprops = NULL;
 	struct ib_pkey_cache      *pkey_cache = NULL, *old_pkey_cache;
@@ -1396,11 +1394,11 @@ static void ib_cache_update(struct ib_device *device,
 	int                        ret;
 
 	if (!rdma_is_port_valid(device, port))
-		return;
+		return -EINVAL;
 
 	tprops = kmalloc(sizeof *tprops, GFP_KERNEL);
 	if (!tprops)
-		return;
+		return -ENOMEM;
 
 	ret = ib_query_port(device, port, tprops);
 	if (ret) {
@@ -1418,8 +1416,10 @@ static void ib_cache_update(struct ib_device *device,
 	pkey_cache = kmalloc(struct_size(pkey_cache, table,
 					 tprops->pkey_tbl_len),
 			     GFP_KERNEL);
-	if (!pkey_cache)
+	if (!pkey_cache) {
+		ret = -ENOMEM;
 		goto err;
+	}
 
 	pkey_cache->table_len = tprops->pkey_tbl_len;
 
@@ -1451,50 +1451,84 @@ static void ib_cache_update(struct ib_device *device,
 
 	kfree(old_pkey_cache);
 	kfree(tprops);
-	return;
+	return 0;
 
 err:
 	kfree(pkey_cache);
 	kfree(tprops);
+	return ret;
+}
+
+static void ib_cache_event_task(struct work_struct *_work)
+{
+	struct ib_update_work *work =
+		container_of(_work, struct ib_update_work, work);
+	int ret;
+
+	/* Before distributing the cache update event, first sync
+	 * the cache.
+	 */
+	ret = ib_cache_update(work->event.device, work->event.element.port_num,
+			      work->enforce_security);
+
+	/* GID event is notified already for individual GID entries by
+	 * dispatch_gid_change_event(). Hence, notifiy for rest of the
+	 * events.
+	 */
+	if (!ret && work->event.event != IB_EVENT_GID_CHANGE)
+		ib_dispatch_event_clients(&work->event);
+
+	kfree(work);
 }
 
-static void ib_cache_task(struct work_struct *_work)
+static void ib_generic_event_task(struct work_struct *_work)
 {
 	struct ib_update_work *work =
 		container_of(_work, struct ib_update_work, work);
 
-	ib_cache_update(work->device,
-			work->port_num,
-			work->enforce_security);
+	ib_dispatch_event_clients(&work->event);
 	kfree(work);
 }
 
-static void ib_cache_event(struct ib_event_handler *handler,
-			   struct ib_event *event)
+static bool is_cache_update_event(const struct ib_event *event)
+{
+	return (event->event == IB_EVENT_PORT_ERR    ||
+		event->event == IB_EVENT_PORT_ACTIVE ||
+		event->event == IB_EVENT_LID_CHANGE  ||
+		event->event == IB_EVENT_PKEY_CHANGE ||
+		event->event == IB_EVENT_CLIENT_REREGISTER ||
+		event->event == IB_EVENT_GID_CHANGE);
+}
+
+/**
+ * ib_dispatch_event - Dispatch an asynchronous event
+ * @event:Event to dispatch
+ *
+ * Low-level drivers must call ib_dispatch_event() to dispatch the
+ * event to all registered event handlers when an asynchronous event
+ * occurs.
+ */
+void ib_dispatch_event(const struct ib_event *event)
 {
 	struct ib_update_work *work;
 
-	if (event->event == IB_EVENT_PORT_ERR    ||
-	    event->event == IB_EVENT_PORT_ACTIVE ||
-	    event->event == IB_EVENT_LID_CHANGE  ||
-	    event->event == IB_EVENT_PKEY_CHANGE ||
-	    event->event == IB_EVENT_CLIENT_REREGISTER ||
-	    event->event == IB_EVENT_GID_CHANGE) {
-		work = kmalloc(sizeof *work, GFP_ATOMIC);
-		if (work) {
-			INIT_WORK(&work->work, ib_cache_task);
-			work->device   = event->device;
-			work->port_num = event->element.port_num;
-			if (event->event == IB_EVENT_PKEY_CHANGE ||
-			    event->event == IB_EVENT_GID_CHANGE)
-				work->enforce_security = true;
-			else
-				work->enforce_security = false;
-
-			queue_work(ib_wq, &work->work);
-		}
-	}
+	work = kzalloc(sizeof(*work), GFP_ATOMIC);
+	if (!work)
+		return;
+
+	if (is_cache_update_event(event))
+		INIT_WORK(&work->work, ib_cache_event_task);
+	else
+		INIT_WORK(&work->work, ib_generic_event_task);
+
+	work->event = *event;
+	if (event->event == IB_EVENT_PKEY_CHANGE ||
+	    event->event == IB_EVENT_GID_CHANGE)
+		work->enforce_security = true;
+
+	queue_work(ib_wq, &work->work);
 }
+EXPORT_SYMBOL(ib_dispatch_event);
 
 int ib_cache_setup_one(struct ib_device *device)
 {
@@ -1507,12 +1541,12 @@ int ib_cache_setup_one(struct ib_device *device)
 	if (err)
 		return err;
 
-	rdma_for_each_port (device, p)
-		ib_cache_update(device, p, true);
+	rdma_for_each_port (device, p) {
+		err = ib_cache_update(device, p, true);
+		if (err)
+			return err;
+	}
 
-	INIT_IB_EVENT_HANDLER(&device->cache.event_handler,
-			      device, ib_cache_event);
-	ib_register_event_handler(&device->cache.event_handler);
 	return 0;
 }
 
@@ -1534,14 +1568,12 @@ void ib_cache_release_one(struct ib_device *device)
 
 void ib_cache_cleanup_one(struct ib_device *device)
 {
-	/* The cleanup function unregisters the event handler,
-	 * waits for all in-progress workqueue elements and cleans
-	 * up the GID cache. This function should be called after
-	 * the device was removed from the devices list and all
-	 * clients were removed, so the cache exists but is
+	/* The cleanup function waits for all in-progress workqueue
+	 * elements and cleans up the GID cache. This function should be
+	 * called after the device was removed from the devices list and
+	 * all clients were removed, so the cache exists but is
 	 * non-functional and shouldn't be updated anymore.
 	 */
-	ib_unregister_event_handler(&device->cache.event_handler);
 	flush_workqueue(ib_wq);
 	gid_table_cleanup_one(device);
 
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 5920c0085d35..09af96ec41dd 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -597,18 +597,6 @@ static int cm_init_av_by_path(struct sa_path_rec *path,
 	return 0;
 }
 
-static int cm_alloc_id(struct cm_id_private *cm_id_priv)
-{
-	int err;
-	u32 id;
-
-	err = xa_alloc_cyclic_irq(&cm.local_id_table, &id, cm_id_priv,
-			xa_limit_32b, &cm.local_id_next, GFP_KERNEL);
-
-	cm_id_priv->id.local_id = (__force __be32)id ^ cm.random_id_operand;
-	return err;
-}
-
 static u32 cm_local_id(__be32 local_id)
 {
 	return (__force u32) (local_id ^ cm.random_id_operand);
@@ -862,6 +850,7 @@ struct ib_cm_id *ib_create_cm_id(struct ib_device *device,
 				 void *context)
 {
 	struct cm_id_private *cm_id_priv;
+	u32 id;
 	int ret;
 
 	cm_id_priv = kzalloc(sizeof *cm_id_priv, GFP_KERNEL);
@@ -873,9 +862,6 @@ struct ib_cm_id *ib_create_cm_id(struct ib_device *device,
 	cm_id_priv->id.cm_handler = cm_handler;
 	cm_id_priv->id.context = context;
 	cm_id_priv->id.remote_cm_qpn = 1;
-	ret = cm_alloc_id(cm_id_priv);
-	if (ret)
-		goto error;
 
 	spin_lock_init(&cm_id_priv->lock);
 	init_completion(&cm_id_priv->comp);
@@ -884,11 +870,20 @@ struct ib_cm_id *ib_create_cm_id(struct ib_device *device,
 	INIT_LIST_HEAD(&cm_id_priv->altr_list);
 	atomic_set(&cm_id_priv->work_count, -1);
 	atomic_set(&cm_id_priv->refcount, 1);
+
+	ret = xa_alloc_cyclic_irq(&cm.local_id_table, &id, NULL, xa_limit_32b,
+				  &cm.local_id_next, GFP_KERNEL);
+	if (ret < 0)
+		goto error;
+	cm_id_priv->id.local_id = (__force __be32)id ^ cm.random_id_operand;
+	xa_store_irq(&cm.local_id_table, cm_local_id(cm_id_priv->id.local_id),
+		     cm_id_priv, GFP_KERNEL);
+
 	return &cm_id_priv->id;
 
 error:
 	kfree(cm_id_priv);
-	return ERR_PTR(-ENOMEM);
+	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL(ib_create_cm_id);
 
@@ -1228,6 +1223,7 @@ struct ib_cm_id *ib_cm_insert_listen(struct ib_device *device,
 			/* Sharing an ib_cm_id with different handlers is not
 			 * supported */
 			spin_unlock_irqrestore(&cm.lock, flags);
+			ib_destroy_cm_id(cm_id);
 			return ERR_PTR(-EINVAL);
 		}
 		atomic_inc(&cm_id_priv->refcount);
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 2e48b59926c1..08d6d7b2d635 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -1631,6 +1631,8 @@ static struct rdma_id_private *cma_find_listener(
 {
 	struct rdma_id_private *id_priv, *id_priv_dev;
 
+	lockdep_assert_held(&lock);
+
 	if (!bind_list)
 		return ERR_PTR(-EINVAL);
 
@@ -1677,6 +1679,7 @@ cma_ib_id_from_event(struct ib_cm_id *cm_id,
 		}
 	}
 
+	mutex_lock(&lock);
 	/*
 	 * Net namespace might be getting deleted while route lookup,
 	 * cm_id lookup is in progress. Therefore, perform netdevice
@@ -1718,6 +1721,7 @@ cma_ib_id_from_event(struct ib_cm_id *cm_id,
 	id_priv = cma_find_listener(bind_list, cm_id, ib_event, req, *net_dev);
 err:
 	rcu_read_unlock();
+	mutex_unlock(&lock);
 	if (IS_ERR(id_priv) && *net_dev) {
 		dev_put(*net_dev);
 		*net_dev = NULL;
@@ -2473,6 +2477,8 @@ static void cma_listen_on_dev(struct rdma_id_private *id_priv,
 	struct net *net = id_priv->id.route.addr.dev_addr.net;
 	int ret;
 
+	lockdep_assert_held(&lock);
+
 	if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cma_dev->device, 1))
 		return;
 
@@ -2911,6 +2917,7 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
 err2:
 	kfree(route->path_rec);
 	route->path_rec = NULL;
+	route->num_paths = 0;
 err1:
 	kfree(work);
 	return ret;
@@ -3091,6 +3098,7 @@ static int cma_resolve_loopback(struct rdma_id_private *id_priv)
 	rdma_addr_get_sgid(&id_priv->id.route.addr.dev_addr, &gid);
 	rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, &gid);
 
+	atomic_inc(&id_priv->refcount);
 	cma_init_resolve_addr_work(work, id_priv);
 	queue_work(cma_wq, &work->work);
 	return 0;
@@ -3117,6 +3125,7 @@ static int cma_resolve_ib_addr(struct rdma_id_private *id_priv)
 	rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, (union ib_gid *)
 		&(((struct sockaddr_ib *) &id_priv->id.route.addr.dst_addr)->sib_addr));
 
+	atomic_inc(&id_priv->refcount);
 	cma_init_resolve_addr_work(work, id_priv);
 	queue_work(cma_wq, &work->work);
 	return 0;
@@ -3153,19 +3162,26 @@ int rdma_resolve_addr(struct rdma_cm_id *id, struct sockaddr *src_addr,
 	int ret;
 
 	id_priv = container_of(id, struct rdma_id_private, id);
+	memcpy(cma_dst_addr(id_priv), dst_addr, rdma_addr_size(dst_addr));
 	if (id_priv->state == RDMA_CM_IDLE) {
 		ret = cma_bind_addr(id, src_addr, dst_addr);
-		if (ret)
+		if (ret) {
+			memset(cma_dst_addr(id_priv), 0,
+			       rdma_addr_size(dst_addr));
 			return ret;
+		}
 	}
 
-	if (cma_family(id_priv) != dst_addr->sa_family)
+	if (cma_family(id_priv) != dst_addr->sa_family) {
+		memset(cma_dst_addr(id_priv), 0, rdma_addr_size(dst_addr));
 		return -EINVAL;
+	}
 
-	if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDR_QUERY))
+	if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDR_QUERY)) {
+		memset(cma_dst_addr(id_priv), 0, rdma_addr_size(dst_addr));
 		return -EINVAL;
+	}
 
-	memcpy(cma_dst_addr(id_priv), dst_addr, rdma_addr_size(dst_addr));
 	if (cma_any_addr(dst_addr)) {
 		ret = cma_resolve_loopback(id_priv);
 	} else {
@@ -3235,6 +3251,8 @@ static void cma_bind_port(struct rdma_bind_list *bind_list,
 	u64 sid, mask;
 	__be16 port;
 
+	lockdep_assert_held(&lock);
+
 	addr = cma_src_addr(id_priv);
 	port = htons(bind_list->port);
 
@@ -3263,6 +3281,8 @@ static int cma_alloc_port(enum rdma_ucm_port_space ps,
 	struct rdma_bind_list *bind_list;
 	int ret;
 
+	lockdep_assert_held(&lock);
+
 	bind_list = kzalloc(sizeof *bind_list, GFP_KERNEL);
 	if (!bind_list)
 		return -ENOMEM;
@@ -3289,6 +3309,8 @@ static int cma_port_is_unique(struct rdma_bind_list *bind_list,
 	struct sockaddr  *saddr = cma_src_addr(id_priv);
 	__be16 dport = cma_port(daddr);
 
+	lockdep_assert_held(&lock);
+
 	hlist_for_each_entry(cur_id, &bind_list->owners, node) {
 		struct sockaddr  *cur_daddr = cma_dst_addr(cur_id);
 		struct sockaddr  *cur_saddr = cma_src_addr(cur_id);
@@ -3328,6 +3350,8 @@ static int cma_alloc_any_port(enum rdma_ucm_port_space ps,
 	unsigned int rover;
 	struct net *net = id_priv->id.route.addr.dev_addr.net;
 
+	lockdep_assert_held(&lock);
+
 	inet_get_local_port_range(net, &low, &high);
 	remaining = (high - low) + 1;
 	rover = prandom_u32() % remaining + low;
@@ -3375,6 +3399,8 @@ static int cma_check_port(struct rdma_bind_list *bind_list,
 	struct rdma_id_private *cur_id;
 	struct sockaddr *addr, *cur_addr;
 
+	lockdep_assert_held(&lock);
+
 	addr = cma_src_addr(id_priv);
 	hlist_for_each_entry(cur_id, &bind_list->owners, node) {
 		if (id_priv == cur_id)
@@ -3405,6 +3431,8 @@ static int cma_use_port(enum rdma_ucm_port_space ps,
 	unsigned short snum;
 	int ret;
 
+	lockdep_assert_held(&lock);
+
 	snum = ntohs(cma_port(cma_src_addr(id_priv)));
 	if (snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE))
 		return -EACCES;
@@ -4710,6 +4738,19 @@ static int __init cma_init(void)
 {
 	int ret;
 
+	/*
+	 * There is a rare lock ordering dependency in cma_netdev_callback()
+	 * that only happens when bonding is enabled. Teach lockdep that rtnl
+	 * must never be nested under lock so it can find these without having
+	 * to test with bonding.
+	 */
+	if (IS_ENABLED(CONFIG_LOCKDEP)) {
+		rtnl_lock();
+		mutex_lock(&lock);
+		mutex_unlock(&lock);
+		rtnl_unlock();
+	}
+
 	cma_wq = alloc_ordered_workqueue("rdma_cm", WQ_MEM_RECLAIM);
 	if (!cma_wq)
 		return -ENOMEM;
@@ -4736,6 +4777,7 @@ err_ib:
 err:
 	unregister_netdevice_notifier(&cma_nb);
 	ib_sa_unregister_client(&sa_client);
+	unregister_pernet_subsys(&cma_pernet_operations);
 err_wq:
 	destroy_workqueue(cma_wq);
 	return ret;
diff --git a/drivers/infiniband/core/cma_configfs.c b/drivers/infiniband/core/cma_configfs.c
index 3ec2c415bb70..6b3f5b25b6ff 100644
--- a/drivers/infiniband/core/cma_configfs.c
+++ b/drivers/infiniband/core/cma_configfs.c
@@ -322,8 +322,21 @@ fail:
 	return ERR_PTR(err);
 }
 
+static void drop_cma_dev(struct config_group *cgroup, struct config_item *item)
+{
+	struct config_group *group =
+		container_of(item, struct config_group, cg_item);
+	struct cma_dev_group *cma_dev_group =
+		container_of(group, struct cma_dev_group, device_group);
+
+	configfs_remove_default_groups(&cma_dev_group->ports_group);
+	configfs_remove_default_groups(&cma_dev_group->device_group);
+	config_item_put(item);
+}
+
 static struct configfs_group_operations cma_subsys_group_ops = {
 	.make_group	= make_cma_dev,
+	.drop_item	= drop_cma_dev,
 };
 
 static const struct config_item_type cma_subsys_type = {
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index ff9e0d7fb4f3..4c9193d2f894 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -119,6 +119,7 @@ unsigned long roce_gid_type_mask_support(struct ib_device *ib_dev, u8 port);
 int ib_cache_setup_one(struct ib_device *device);
 void ib_cache_cleanup_one(struct ib_device *device);
 void ib_cache_release_one(struct ib_device *device);
+void ib_dispatch_event_clients(struct ib_event *event);
 
 #ifdef CONFIG_CGROUP_RDMA
 void ib_device_register_rdmacg(struct ib_device *device);
@@ -307,6 +308,21 @@ static inline struct ib_qp *_ib_create_qp(struct ib_device *dev,
 	qp->pd = pd;
 	qp->uobject = uobj;
 	qp->real_qp = qp;
+
+	qp->qp_type = attr->qp_type;
+	qp->rwq_ind_tbl = attr->rwq_ind_tbl;
+	qp->send_cq = attr->send_cq;
+	qp->recv_cq = attr->recv_cq;
+	qp->srq = attr->srq;
+	qp->rwq_ind_tbl = attr->rwq_ind_tbl;
+	qp->event_handler = attr->event_handler;
+	qp->qp_context	  = attr->qp_context;
+
+	atomic_set(&qp->usecnt, 0);
+	spin_lock_init(&qp->mr_lock);
+	INIT_LIST_HEAD(&qp->rdma_mrs);
+	INIT_LIST_HEAD(&qp->sig_mrs);
+
 	/*
 	 * We don't track XRC QPs for now, because they don't have PD
 	 * and more importantly they are created internaly by driver,
diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c
index a24c900fbdf6..d17e7af352fd 100644
--- a/drivers/infiniband/core/cq.c
+++ b/drivers/infiniband/core/cq.c
@@ -113,7 +113,7 @@ static void ib_cq_completion_workqueue(struct ib_cq *cq, void *private)
 }
 
 /**
- * __ib_alloc_cq - allocate a completion queue
+ * __ib_alloc_cq_user - allocate a completion queue
  * @dev:		device to allocate the CQ for
  * @private:		driver private data, accessible from cq->cq_context
  * @nr_cqe:		number of CQEs to allocate
@@ -193,7 +193,7 @@ out_destroy_cq:
 EXPORT_SYMBOL(__ib_alloc_cq_user);
 
 /**
- * ib_free_cq - free a completion queue
+ * ib_free_cq_user - free a completion queue
  * @cq:		completion queue to free.
  * @udata:	User data or NULL for kernel object
  */
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 862cda8d4f46..80a1e20a95ae 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -589,6 +589,7 @@ struct ib_device *_ib_alloc_device(size_t size)
 
 	INIT_LIST_HEAD(&device->event_handler_list);
 	spin_lock_init(&device->event_handler_lock);
+	init_rwsem(&device->event_handler_rwsem);
 	mutex_init(&device->unregistration_lock);
 	/*
 	 * client_data needs to be alloc because we don't want our mark to be
@@ -896,7 +897,9 @@ static int add_one_compat_dev(struct ib_device *device,
 	cdev->dev.parent = device->dev.parent;
 	rdma_init_coredev(cdev, device, read_pnet(&rnet->net));
 	cdev->dev.release = compatdev_release;
-	dev_set_name(&cdev->dev, "%s", dev_name(&device->dev));
+	ret = dev_set_name(&cdev->dev, "%s", dev_name(&device->dev));
+	if (ret)
+		goto add_err;
 
 	ret = device_add(&cdev->dev);
 	if (ret)
@@ -1312,6 +1315,10 @@ out:
 	return ret;
 }
 
+static void prevent_dealloc_device(struct ib_device *ib_dev)
+{
+}
+
 /**
  * ib_register_device - Register an IB device with IB core
  * @device:Device to register
@@ -1377,11 +1384,11 @@ int ib_register_device(struct ib_device *device, const char *name)
 		 * possibility for a parallel unregistration along with this
 		 * error flow. Since we have a refcount here we know any
 		 * parallel flow is stopped in disable_device and will see the
-		 * NULL pointers, causing the responsibility to
+		 * special dealloc_driver pointer, causing the responsibility to
 		 * ib_dealloc_device() to revert back to this thread.
 		 */
 		dealloc_fn = device->ops.dealloc_driver;
-		device->ops.dealloc_driver = NULL;
+		device->ops.dealloc_driver = prevent_dealloc_device;
 		ib_device_put(device);
 		__ib_unregister_device(device);
 		device->ops.dealloc_driver = dealloc_fn;
@@ -1429,7 +1436,8 @@ static void __ib_unregister_device(struct ib_device *ib_dev)
 	 * Drivers using the new flow may not call ib_dealloc_device except
 	 * in error unwind prior to registration success.
 	 */
-	if (ib_dev->ops.dealloc_driver) {
+	if (ib_dev->ops.dealloc_driver &&
+	    ib_dev->ops.dealloc_driver != prevent_dealloc_device) {
 		WARN_ON(kref_read(&ib_dev->dev.kobj.kref) <= 1);
 		ib_dealloc_device(ib_dev);
 	}
@@ -1820,17 +1828,15 @@ EXPORT_SYMBOL(ib_set_client_data);
  *
  * ib_register_event_handler() registers an event handler that will be
  * called back when asynchronous IB events occur (as defined in
- * chapter 11 of the InfiniBand Architecture Specification).  This
- * callback may occur in interrupt context.
+ * chapter 11 of the InfiniBand Architecture Specification). This
+ * callback occurs in workqueue context.
  */
 void ib_register_event_handler(struct ib_event_handler *event_handler)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&event_handler->device->event_handler_lock, flags);
+	down_write(&event_handler->device->event_handler_rwsem);
 	list_add_tail(&event_handler->list,
 		      &event_handler->device->event_handler_list);
-	spin_unlock_irqrestore(&event_handler->device->event_handler_lock, flags);
+	up_write(&event_handler->device->event_handler_rwsem);
 }
 EXPORT_SYMBOL(ib_register_event_handler);
 
@@ -1843,35 +1849,23 @@ EXPORT_SYMBOL(ib_register_event_handler);
  */
 void ib_unregister_event_handler(struct ib_event_handler *event_handler)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&event_handler->device->event_handler_lock, flags);
+	down_write(&event_handler->device->event_handler_rwsem);
 	list_del(&event_handler->list);
-	spin_unlock_irqrestore(&event_handler->device->event_handler_lock, flags);
+	up_write(&event_handler->device->event_handler_rwsem);
 }
 EXPORT_SYMBOL(ib_unregister_event_handler);
 
-/**
- * ib_dispatch_event - Dispatch an asynchronous event
- * @event:Event to dispatch
- *
- * Low-level drivers must call ib_dispatch_event() to dispatch the
- * event to all registered event handlers when an asynchronous event
- * occurs.
- */
-void ib_dispatch_event(struct ib_event *event)
+void ib_dispatch_event_clients(struct ib_event *event)
 {
-	unsigned long flags;
 	struct ib_event_handler *handler;
 
-	spin_lock_irqsave(&event->device->event_handler_lock, flags);
+	down_read(&event->device->event_handler_rwsem);
 
 	list_for_each_entry(handler, &event->device->event_handler_list, list)
 		handler->handler(handler, event);
 
-	spin_unlock_irqrestore(&event->device->event_handler_lock, flags);
+	up_read(&event->device->event_handler_rwsem);
 }
-EXPORT_SYMBOL(ib_dispatch_event);
 
 /**
  * ib_query_port - Query IB port attributes
diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c
index 72141c5b7c95..570dc526a942 100644
--- a/drivers/infiniband/core/iwcm.c
+++ b/drivers/infiniband/core/iwcm.c
@@ -159,8 +159,10 @@ static void dealloc_work_entries(struct iwcm_id_private *cm_id_priv)
 {
 	struct list_head *e, *tmp;
 
-	list_for_each_safe(e, tmp, &cm_id_priv->work_free_list)
+	list_for_each_safe(e, tmp, &cm_id_priv->work_free_list) {
+		list_del(e);
 		kfree(list_entry(e, struct iwcm_work, free_list));
+	}
 }
 
 static int alloc_work_entries(struct iwcm_id_private *cm_id_priv, int count)
diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
index 9947d16edef2..2284930b5f91 100644
--- a/drivers/infiniband/core/mad.c
+++ b/drivers/infiniband/core/mad.c
@@ -639,10 +639,10 @@ static void unregister_mad_agent(struct ib_mad_agent_private *mad_agent_priv)
 	xa_erase(&ib_mad_clients, mad_agent_priv->agent.hi_tid);
 
 	flush_workqueue(port_priv->wq);
-	ib_cancel_rmpp_recvs(mad_agent_priv);
 
 	deref_mad_agent(mad_agent_priv);
 	wait_for_completion(&mad_agent_priv->comp);
+	ib_cancel_rmpp_recvs(mad_agent_priv);
 
 	ib_mad_agent_security_cleanup(&mad_agent_priv->agent);
 
@@ -2960,6 +2960,7 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info,
 						 DMA_FROM_DEVICE);
 		if (unlikely(ib_dma_mapping_error(qp_info->port_priv->device,
 						  sg_list.addr))) {
+			kfree(mad_priv);
 			ret = -ENOMEM;
 			break;
 		}
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 5e53f5ef6a74..6123780f9602 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -692,6 +692,10 @@ static int nldev_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 		nla_strlcpy(name, tb[RDMA_NLDEV_ATTR_DEV_NAME],
 			    IB_DEVICE_NAME_MAX);
+		if (strlen(name) == 0) {
+			err = -EINVAL;
+			goto done;
+		}
 		err = ib_device_rename(device, name);
 		goto done;
 	}
@@ -1069,10 +1073,10 @@ static int res_get_common_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	has_cap_net_admin = netlink_capable(skb, CAP_NET_ADMIN);
 	ret = fe->fill_res_func(msg, has_cap_net_admin, res, port);
-	rdma_restrack_put(res);
 	if (ret)
 		goto err_free;
 
+	rdma_restrack_put(res);
 	nlmsg_end(msg, nlh);
 	ib_device_put(device);
 	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
@@ -1292,7 +1296,7 @@ static int nldev_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	nla_strlcpy(ibdev_name, tb[RDMA_NLDEV_ATTR_DEV_NAME],
 		    sizeof(ibdev_name));
-	if (strchr(ibdev_name, '%'))
+	if (strchr(ibdev_name, '%') || strlen(ibdev_name) == 0)
 		return -EINVAL;
 
 	nla_strlcpy(type, tb[RDMA_NLDEV_ATTR_LINK_TYPE], sizeof(type));
diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c
index ccf4d069c25c..d0580eed3bcb 100644
--- a/drivers/infiniband/core/rdma_core.c
+++ b/drivers/infiniband/core/rdma_core.c
@@ -160,9 +160,9 @@ static int uverbs_destroy_uobject(struct ib_uobject *uobj,
 	uobj->context = NULL;
 
 	/*
-	 * For DESTROY the usecnt is held write locked, the caller is expected
-	 * to put it unlock and put the object when done with it. Only DESTROY
-	 * can remove the IDR handle.
+	 * For DESTROY the usecnt is not changed, the caller is expected to
+	 * manage it via uobj_put_destroy(). Only DESTROY can remove the IDR
+	 * handle.
 	 */
 	if (reason != RDMA_REMOVE_DESTROY)
 		atomic_set(&uobj->usecnt, 0);
@@ -194,7 +194,7 @@ static int uverbs_destroy_uobject(struct ib_uobject *uobj,
 /*
  * This calls uverbs_destroy_uobject() using the RDMA_REMOVE_DESTROY
  * sequence. It should only be used from command callbacks. On success the
- * caller must pair this with rdma_lookup_put_uobject(LOOKUP_WRITE). This
+ * caller must pair this with uobj_put_destroy(). This
  * version requires the caller to have already obtained an
  * LOOKUP_DESTROY uobject kref.
  */
@@ -205,6 +205,13 @@ int uobj_destroy(struct ib_uobject *uobj, struct uverbs_attr_bundle *attrs)
 
 	down_read(&ufile->hw_destroy_rwsem);
 
+	/*
+	 * Once the uobject is destroyed by RDMA_REMOVE_DESTROY then it is left
+	 * write locked as the callers put it back with UVERBS_LOOKUP_DESTROY.
+	 * This is because any other concurrent thread can still see the object
+	 * in the xarray due to RCU. Leaving it locked ensures nothing else will
+	 * touch it.
+	 */
 	ret = uverbs_try_lock_object(uobj, UVERBS_LOOKUP_WRITE);
 	if (ret)
 		goto out_unlock;
@@ -223,7 +230,7 @@ out_unlock:
 /*
  * uobj_get_destroy destroys the HW object and returns a handle to the uobj
  * with a NULL object pointer. The caller must pair this with
- * uverbs_put_destroy.
+ * uobj_put_destroy().
  */
 struct ib_uobject *__uobj_get_destroy(const struct uverbs_api_object *obj,
 				      u32 id, struct uverbs_attr_bundle *attrs)
@@ -257,8 +264,7 @@ int __uobj_perform_destroy(const struct uverbs_api_object *obj, u32 id,
 	uobj = __uobj_get_destroy(obj, id, attrs);
 	if (IS_ERR(uobj))
 		return PTR_ERR(uobj);
-
-	rdma_lookup_put_uobject(uobj, UVERBS_LOOKUP_WRITE);
+	uobj_put_destroy(uobj);
 	return 0;
 }
 
@@ -362,7 +368,7 @@ lookup_get_fd_uobject(const struct uverbs_api_object *obj,
 	 * and the caller is expected to ensure that uverbs_close_fd is never
 	 * done while a call top lookup is possible.
 	 */
-	if (f->f_op != fd_type->fops) {
+	if (f->f_op != fd_type->fops || uobject->ufile != ufile) {
 		fput(f);
 		return ERR_PTR(-EBADF);
 	}
@@ -689,7 +695,6 @@ void rdma_lookup_put_uobject(struct ib_uobject *uobj,
 			     enum rdma_lookup_mode mode)
 {
 	assert_uverbs_usecnt(uobj, mode);
-	uobj->uapi_object->type_class->lookup_put(uobj, mode);
 	/*
 	 * In order to unlock an object, either decrease its usecnt for
 	 * read access or zero it in case of exclusive access. See
@@ -706,6 +711,7 @@ void rdma_lookup_put_uobject(struct ib_uobject *uobj,
 		break;
 	}
 
+	uobj->uapi_object->type_class->lookup_put(uobj, mode);
 	/* Pairs with the kref obtained by type->lookup_get */
 	uverbs_uobject_put(uobj);
 }
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 7d8071c7e564..e3058b9e814b 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -829,13 +829,20 @@ static int ib_nl_get_path_rec_attrs_len(ib_sa_comp_mask comp_mask)
 	return len;
 }
 
-static int ib_nl_send_msg(struct ib_sa_query *query, gfp_t gfp_mask)
+static int ib_nl_make_request(struct ib_sa_query *query, gfp_t gfp_mask)
 {
 	struct sk_buff *skb = NULL;
 	struct nlmsghdr *nlh;
 	void *data;
 	struct ib_sa_mad *mad;
 	int len;
+	unsigned long flags;
+	unsigned long delay;
+	gfp_t gfp_flag;
+	int ret;
+
+	INIT_LIST_HEAD(&query->list);
+	query->seq = (u32)atomic_inc_return(&ib_nl_sa_request_seq);
 
 	mad = query->mad_buf->mad;
 	len = ib_nl_get_path_rec_attrs_len(mad->sa_hdr.comp_mask);
@@ -860,36 +867,25 @@ static int ib_nl_send_msg(struct ib_sa_query *query, gfp_t gfp_mask)
 	/* Repair the nlmsg header length */
 	nlmsg_end(skb, nlh);
 
-	return rdma_nl_multicast(skb, RDMA_NL_GROUP_LS, gfp_mask);
-}
+	gfp_flag = ((gfp_mask & GFP_ATOMIC) == GFP_ATOMIC) ? GFP_ATOMIC :
+		GFP_NOWAIT;
 
-static int ib_nl_make_request(struct ib_sa_query *query, gfp_t gfp_mask)
-{
-	unsigned long flags;
-	unsigned long delay;
-	int ret;
+	spin_lock_irqsave(&ib_nl_request_lock, flags);
+	ret = rdma_nl_multicast(skb, RDMA_NL_GROUP_LS, gfp_flag);
 
-	INIT_LIST_HEAD(&query->list);
-	query->seq = (u32)atomic_inc_return(&ib_nl_sa_request_seq);
+	if (ret)
+		goto out;
 
-	/* Put the request on the list first.*/
-	spin_lock_irqsave(&ib_nl_request_lock, flags);
+	/* Put the request on the list.*/
 	delay = msecs_to_jiffies(sa_local_svc_timeout_ms);
 	query->timeout = delay + jiffies;
 	list_add_tail(&query->list, &ib_nl_request_list);
 	/* Start the timeout if this is the only request */
 	if (ib_nl_request_list.next == &query->list)
 		queue_delayed_work(ib_nl_wq, &ib_nl_timed_work, delay);
-	spin_unlock_irqrestore(&ib_nl_request_lock, flags);
 
-	ret = ib_nl_send_msg(query, gfp_mask);
-	if (ret) {
-		ret = -EIO;
-		/* Remove the request */
-		spin_lock_irqsave(&ib_nl_request_lock, flags);
-		list_del(&query->list);
-		spin_unlock_irqrestore(&ib_nl_request_lock, flags);
-	}
+out:
+	spin_unlock_irqrestore(&ib_nl_request_lock, flags);
 
 	return ret;
 }
@@ -1068,7 +1064,7 @@ int ib_nl_handle_set_timeout(struct sk_buff *skb,
 	}
 
 settimeout_out:
-	return skb->len;
+	return 0;
 }
 
 static inline int ib_nl_is_good_resolve_resp(const struct nlmsghdr *nlh)
@@ -1139,7 +1135,7 @@ int ib_nl_handle_resolve_resp(struct sk_buff *skb,
 	}
 
 resp_out:
-	return skb->len;
+	return 0;
 }
 
 static void free_sm_ah(struct kref *kref)
diff --git a/drivers/infiniband/core/security.c b/drivers/infiniband/core/security.c
index 6eb6d2717ca5..75e7ec017836 100644
--- a/drivers/infiniband/core/security.c
+++ b/drivers/infiniband/core/security.c
@@ -339,27 +339,20 @@ static struct ib_ports_pkeys *get_new_pps(const struct ib_qp *qp,
 	if (!new_pps)
 		return NULL;
 
-	if (qp_attr_mask & (IB_QP_PKEY_INDEX | IB_QP_PORT)) {
-		if (!qp_pps) {
-			new_pps->main.port_num = qp_attr->port_num;
-			new_pps->main.pkey_index = qp_attr->pkey_index;
-		} else {
-			new_pps->main.port_num = (qp_attr_mask & IB_QP_PORT) ?
-						  qp_attr->port_num :
-						  qp_pps->main.port_num;
-
-			new_pps->main.pkey_index =
-					(qp_attr_mask & IB_QP_PKEY_INDEX) ?
-					 qp_attr->pkey_index :
-					 qp_pps->main.pkey_index;
-		}
-		new_pps->main.state = IB_PORT_PKEY_VALID;
-	} else if (qp_pps) {
+	if (qp_attr_mask & IB_QP_PORT)
+		new_pps->main.port_num = qp_attr->port_num;
+	else if (qp_pps)
 		new_pps->main.port_num = qp_pps->main.port_num;
+
+	if (qp_attr_mask & IB_QP_PKEY_INDEX)
+		new_pps->main.pkey_index = qp_attr->pkey_index;
+	else if (qp_pps)
 		new_pps->main.pkey_index = qp_pps->main.pkey_index;
-		if (qp_pps->main.state != IB_PORT_PKEY_NOT_VALID)
-			new_pps->main.state = IB_PORT_PKEY_VALID;
-	}
+
+	if (((qp_attr_mask & IB_QP_PKEY_INDEX) &&
+	     (qp_attr_mask & IB_QP_PORT)) ||
+	    (qp_pps && qp_pps->main.state != IB_PORT_PKEY_NOT_VALID))
+		new_pps->main.state = IB_PORT_PKEY_VALID;
 
 	if (qp_attr_mask & IB_QP_ALT_PATH) {
 		new_pps->alt.port_num = qp_attr->alt_port_num;
diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index c78d0c9646ae..2b9991b37bc8 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -1044,8 +1044,7 @@ static int add_port(struct ib_core_device *coredev, int port_num)
 				   coredev->ports_kobj,
 				   "%d", port_num);
 	if (ret) {
-		kfree(p);
-		return ret;
+		goto err_put;
 	}
 
 	p->gid_attr_group = kzalloc(sizeof(*p->gid_attr_group), GFP_KERNEL);
@@ -1058,8 +1057,7 @@ static int add_port(struct ib_core_device *coredev, int port_num)
 	ret = kobject_init_and_add(&p->gid_attr_group->kobj, &gid_attr_type,
 				   &p->kobj, "gid_attrs");
 	if (ret) {
-		kfree(p->gid_attr_group);
-		goto err_put;
+		goto err_put_gid_attrs;
 	}
 
 	if (device->ops.process_mad && is_full_dev) {
@@ -1386,8 +1384,10 @@ int ib_port_register_module_stat(struct ib_device *device, u8 port_num,
 
 		ret = kobject_init_and_add(kobj, ktype, &port->kobj, "%s",
 					   name);
-		if (ret)
+		if (ret) {
+			kobject_put(kobj);
 			return ret;
+		}
 	}
 
 	return 0;
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 140a338a135f..176738311020 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -89,6 +89,7 @@ struct ucma_context {
 
 	struct ucma_file	*file;
 	struct rdma_cm_id	*cm_id;
+	struct mutex		mutex;
 	u64			uid;
 
 	struct list_head	list;
@@ -215,6 +216,7 @@ static struct ucma_context *ucma_alloc_ctx(struct ucma_file *file)
 	init_completion(&ctx->comp);
 	INIT_LIST_HEAD(&ctx->mc_list);
 	ctx->file = file;
+	mutex_init(&ctx->mutex);
 
 	mutex_lock(&mut);
 	ctx->id = idr_alloc(&ctx_idr, ctx, 0, 0, GFP_KERNEL);
@@ -596,6 +598,7 @@ static int ucma_free_ctx(struct ucma_context *ctx)
 	}
 
 	events_reported = ctx->events_reported;
+	mutex_destroy(&ctx->mutex);
 	kfree(ctx);
 	return events_reported;
 }
@@ -665,7 +668,10 @@ static ssize_t ucma_bind_ip(struct ucma_file *file, const char __user *inbuf,
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
+	mutex_lock(&ctx->mutex);
 	ret = rdma_bind_addr(ctx->cm_id, (struct sockaddr *) &cmd.addr);
+	mutex_unlock(&ctx->mutex);
+
 	ucma_put_ctx(ctx);
 	return ret;
 }
@@ -688,7 +694,9 @@ static ssize_t ucma_bind(struct ucma_file *file, const char __user *inbuf,
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
+	mutex_lock(&ctx->mutex);
 	ret = rdma_bind_addr(ctx->cm_id, (struct sockaddr *) &cmd.addr);
+	mutex_unlock(&ctx->mutex);
 	ucma_put_ctx(ctx);
 	return ret;
 }
@@ -712,8 +720,10 @@ static ssize_t ucma_resolve_ip(struct ucma_file *file,
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
+	mutex_lock(&ctx->mutex);
 	ret = rdma_resolve_addr(ctx->cm_id, (struct sockaddr *) &cmd.src_addr,
 				(struct sockaddr *) &cmd.dst_addr, cmd.timeout_ms);
+	mutex_unlock(&ctx->mutex);
 	ucma_put_ctx(ctx);
 	return ret;
 }
@@ -738,8 +748,10 @@ static ssize_t ucma_resolve_addr(struct ucma_file *file,
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
+	mutex_lock(&ctx->mutex);
 	ret = rdma_resolve_addr(ctx->cm_id, (struct sockaddr *) &cmd.src_addr,
 				(struct sockaddr *) &cmd.dst_addr, cmd.timeout_ms);
+	mutex_unlock(&ctx->mutex);
 	ucma_put_ctx(ctx);
 	return ret;
 }
@@ -759,7 +771,9 @@ static ssize_t ucma_resolve_route(struct ucma_file *file,
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
+	mutex_lock(&ctx->mutex);
 	ret = rdma_resolve_route(ctx->cm_id, cmd.timeout_ms);
+	mutex_unlock(&ctx->mutex);
 	ucma_put_ctx(ctx);
 	return ret;
 }
@@ -848,6 +862,7 @@ static ssize_t ucma_query_route(struct ucma_file *file,
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
+	mutex_lock(&ctx->mutex);
 	memset(&resp, 0, sizeof resp);
 	addr = (struct sockaddr *) &ctx->cm_id->route.addr.src_addr;
 	memcpy(&resp.src_addr, addr, addr->sa_family == AF_INET ?
@@ -871,6 +886,7 @@ static ssize_t ucma_query_route(struct ucma_file *file,
 		ucma_copy_iw_route(&resp, &ctx->cm_id->route);
 
 out:
+	mutex_unlock(&ctx->mutex);
 	if (copy_to_user(u64_to_user_ptr(cmd.response),
 			 &resp, sizeof(resp)))
 		ret = -EFAULT;
@@ -1022,6 +1038,7 @@ static ssize_t ucma_query(struct ucma_file *file,
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
+	mutex_lock(&ctx->mutex);
 	switch (cmd.option) {
 	case RDMA_USER_CM_QUERY_ADDR:
 		ret = ucma_query_addr(ctx, response, out_len);
@@ -1036,6 +1053,7 @@ static ssize_t ucma_query(struct ucma_file *file,
 		ret = -ENOSYS;
 		break;
 	}
+	mutex_unlock(&ctx->mutex);
 
 	ucma_put_ctx(ctx);
 	return ret;
@@ -1076,7 +1094,9 @@ static ssize_t ucma_connect(struct ucma_file *file, const char __user *inbuf,
 		return PTR_ERR(ctx);
 
 	ucma_copy_conn_param(ctx->cm_id, &conn_param, &cmd.conn_param);
+	mutex_lock(&ctx->mutex);
 	ret = rdma_connect(ctx->cm_id, &conn_param);
+	mutex_unlock(&ctx->mutex);
 	ucma_put_ctx(ctx);
 	return ret;
 }
@@ -1097,7 +1117,9 @@ static ssize_t ucma_listen(struct ucma_file *file, const char __user *inbuf,
 
 	ctx->backlog = cmd.backlog > 0 && cmd.backlog < max_backlog ?
 		       cmd.backlog : max_backlog;
+	mutex_lock(&ctx->mutex);
 	ret = rdma_listen(ctx->cm_id, ctx->backlog);
+	mutex_unlock(&ctx->mutex);
 	ucma_put_ctx(ctx);
 	return ret;
 }
@@ -1120,13 +1142,17 @@ static ssize_t ucma_accept(struct ucma_file *file, const char __user *inbuf,
 	if (cmd.conn_param.valid) {
 		ucma_copy_conn_param(ctx->cm_id, &conn_param, &cmd.conn_param);
 		mutex_lock(&file->mut);
+		mutex_lock(&ctx->mutex);
 		ret = __rdma_accept(ctx->cm_id, &conn_param, NULL);
+		mutex_unlock(&ctx->mutex);
 		if (!ret)
 			ctx->uid = cmd.uid;
 		mutex_unlock(&file->mut);
-	} else
+	} else {
+		mutex_lock(&ctx->mutex);
 		ret = __rdma_accept(ctx->cm_id, NULL, NULL);
-
+		mutex_unlock(&ctx->mutex);
+	}
 	ucma_put_ctx(ctx);
 	return ret;
 }
@@ -1145,7 +1171,9 @@ static ssize_t ucma_reject(struct ucma_file *file, const char __user *inbuf,
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
+	mutex_lock(&ctx->mutex);
 	ret = rdma_reject(ctx->cm_id, cmd.private_data, cmd.private_data_len);
+	mutex_unlock(&ctx->mutex);
 	ucma_put_ctx(ctx);
 	return ret;
 }
@@ -1164,7 +1192,9 @@ static ssize_t ucma_disconnect(struct ucma_file *file, const char __user *inbuf,
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
+	mutex_lock(&ctx->mutex);
 	ret = rdma_disconnect(ctx->cm_id);
+	mutex_unlock(&ctx->mutex);
 	ucma_put_ctx(ctx);
 	return ret;
 }
@@ -1195,7 +1225,9 @@ static ssize_t ucma_init_qp_attr(struct ucma_file *file,
 	resp.qp_attr_mask = 0;
 	memset(&qp_attr, 0, sizeof qp_attr);
 	qp_attr.qp_state = cmd.qp_state;
+	mutex_lock(&ctx->mutex);
 	ret = rdma_init_qp_attr(ctx->cm_id, &qp_attr, &resp.qp_attr_mask);
+	mutex_unlock(&ctx->mutex);
 	if (ret)
 		goto out;
 
@@ -1281,9 +1313,13 @@ static int ucma_set_ib_path(struct ucma_context *ctx,
 		struct sa_path_rec opa;
 
 		sa_convert_path_ib_to_opa(&opa, &sa_path);
+		mutex_lock(&ctx->mutex);
 		ret = rdma_set_ib_path(ctx->cm_id, &opa);
+		mutex_unlock(&ctx->mutex);
 	} else {
+		mutex_lock(&ctx->mutex);
 		ret = rdma_set_ib_path(ctx->cm_id, &sa_path);
+		mutex_unlock(&ctx->mutex);
 	}
 	if (ret)
 		return ret;
@@ -1316,7 +1352,9 @@ static int ucma_set_option_level(struct ucma_context *ctx, int level,
 
 	switch (level) {
 	case RDMA_OPTION_ID:
+		mutex_lock(&ctx->mutex);
 		ret = ucma_set_option_id(ctx, optname, optval, optlen);
+		mutex_unlock(&ctx->mutex);
 		break;
 	case RDMA_OPTION_IB:
 		ret = ucma_set_option_ib(ctx, optname, optval, optlen);
@@ -1376,8 +1414,10 @@ static ssize_t ucma_notify(struct ucma_file *file, const char __user *inbuf,
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
+	mutex_lock(&ctx->mutex);
 	if (ctx->cm_id->device)
 		ret = rdma_notify(ctx->cm_id, (enum ib_event_type)cmd.event);
+	mutex_unlock(&ctx->mutex);
 
 	ucma_put_ctx(ctx);
 	return ret;
@@ -1420,8 +1460,10 @@ static ssize_t ucma_process_join(struct ucma_file *file,
 	mc->join_state = join_state;
 	mc->uid = cmd->uid;
 	memcpy(&mc->addr, addr, cmd->addr_size);
+	mutex_lock(&ctx->mutex);
 	ret = rdma_join_multicast(ctx->cm_id, (struct sockaddr *)&mc->addr,
 				  join_state, mc);
+	mutex_unlock(&ctx->mutex);
 	if (ret)
 		goto err2;
 
@@ -1525,7 +1567,10 @@ static ssize_t ucma_leave_multicast(struct ucma_file *file,
 		goto out;
 	}
 
+	mutex_lock(&mc->ctx->mutex);
 	rdma_leave_multicast(mc->ctx->cm_id, (struct sockaddr *) &mc->addr);
+	mutex_unlock(&mc->ctx->mutex);
+
 	mutex_lock(&mc->ctx->file->mut);
 	ucma_cleanup_mc_events(mc);
 	list_del(&mc->list);
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index e7ea819fcb11..b9f1dfb2a37a 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -168,10 +168,13 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem,
 		 * for any address.
 		 */
 		mask |= (sg_dma_address(sg) + pgoff) ^ va;
-		if (i && i != (umem->nmap - 1))
-			/* restrict by length as well for interior SGEs */
-			mask |= sg_dma_len(sg);
 		va += sg_dma_len(sg) - pgoff;
+		/* Except for the last entry, the ending iova alignment sets
+		 * the maximum possible page size as the low bits of the iova
+		 * must be zero when starting the next chunk.
+		 */
+		if (i != (umem->nmap - 1))
+			mask |= va;
 		pgoff = 0;
 	}
 	best_pg_bit = rdma_find_pg_bit(mask, pgsz_bitmap);
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index 5e5f7dd82c50..bab412516b07 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -626,7 +626,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt,
 
 	while (bcnt > 0) {
 		const size_t gup_num_pages = min_t(size_t,
-				(bcnt + BIT(page_shift) - 1) >> page_shift,
+				ALIGN(bcnt, PAGE_SIZE) / PAGE_SIZE,
 				PAGE_SIZE / sizeof(struct page *));
 
 		down_read(&owning_mm->mmap_sem);
diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c
index 025b6d86a61f..9b9fa953595b 100644
--- a/drivers/infiniband/core/user_mad.c
+++ b/drivers/infiniband/core/user_mad.c
@@ -1274,6 +1274,9 @@ static void ib_umad_kill_port(struct ib_umad_port *port)
 	struct ib_umad_file *file;
 	int id;
 
+	cdev_device_del(&port->sm_cdev, &port->sm_dev);
+	cdev_device_del(&port->cdev, &port->dev);
+
 	mutex_lock(&port->file_mutex);
 
 	/* Mark ib_dev NULL and block ioctl or other file ops to progress
@@ -1293,8 +1296,6 @@ static void ib_umad_kill_port(struct ib_umad_port *port)
 
 	mutex_unlock(&port->file_mutex);
 
-	cdev_device_del(&port->sm_cdev, &port->sm_dev);
-	cdev_device_del(&port->cdev, &port->dev);
 	ida_free(&umad_ida, port->dev_num);
 
 	/* balances device_initialize() */
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index df8e8ac2c16b..6273d2430736 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -760,6 +760,7 @@ static int ib_uverbs_reg_mr(struct uverbs_attr_bundle *attrs)
 	mr->uobject = uobj;
 	atomic_inc(&pd->usecnt);
 	mr->res.type = RDMA_RESTRACK_MR;
+	mr->iova = cmd.hca_va;
 	rdma_restrack_uadd(&mr->res);
 
 	uobj->object = mr;
@@ -850,6 +851,9 @@ static int ib_uverbs_rereg_mr(struct uverbs_attr_bundle *attrs)
 		atomic_dec(&old_pd->usecnt);
 	}
 
+	if (cmd.flags & IB_MR_REREG_TRANS)
+		mr->iova = cmd.hca_va;
+
 	memset(&resp, 0, sizeof(resp));
 	resp.lkey      = mr->lkey;
 	resp.rkey      = mr->rkey;
@@ -1429,17 +1433,7 @@ static int create_qp(struct uverbs_attr_bundle *attrs,
 		if (ret)
 			goto err_cb;
 
-		qp->pd		  = pd;
-		qp->send_cq	  = attr.send_cq;
-		qp->recv_cq	  = attr.recv_cq;
-		qp->srq		  = attr.srq;
-		qp->rwq_ind_tbl	  = ind_tbl;
-		qp->event_handler = attr.event_handler;
-		qp->qp_context	  = attr.qp_context;
-		qp->qp_type	  = attr.qp_type;
-		atomic_set(&qp->usecnt, 0);
 		atomic_inc(&pd->usecnt);
-		qp->port = 0;
 		if (attr.send_cq)
 			atomic_inc(&attr.send_cq->usecnt);
 		if (attr.recv_cq)
@@ -2716,12 +2710,6 @@ static int kern_spec_to_ib_spec_action(struct uverbs_attr_bundle *attrs,
 	return 0;
 }
 
-static size_t kern_spec_filter_sz(const struct ib_uverbs_flow_spec_hdr *spec)
-{
-	/* Returns user space filter size, includes padding */
-	return (spec->size - sizeof(struct ib_uverbs_flow_spec_hdr)) / 2;
-}
-
 static ssize_t spec_filter_size(const void *kern_spec_filter, u16 kern_filter_size,
 				u16 ib_real_filter_sz)
 {
@@ -2865,11 +2853,16 @@ int ib_uverbs_kern_spec_to_ib_spec_filter(enum ib_flow_spec_type type,
 static int kern_spec_to_ib_spec_filter(struct ib_uverbs_flow_spec *kern_spec,
 				       union ib_flow_spec *ib_spec)
 {
-	ssize_t kern_filter_sz;
+	size_t kern_filter_sz;
 	void *kern_spec_mask;
 	void *kern_spec_val;
 
-	kern_filter_sz = kern_spec_filter_sz(&kern_spec->hdr);
+	if (check_sub_overflow((size_t)kern_spec->hdr.size,
+			       sizeof(struct ib_uverbs_flow_spec_hdr),
+			       &kern_filter_sz))
+		return -EINVAL;
+
+	kern_filter_sz /= 2;
 
 	kern_spec_val = (void *)kern_spec +
 		sizeof(struct ib_uverbs_flow_spec_hdr);
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 84a5e9a6d483..5b7f9d33dd80 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -215,7 +215,6 @@ void ib_uverbs_release_file(struct kref *ref)
 }
 
 static ssize_t ib_uverbs_event_read(struct ib_uverbs_event_queue *ev_queue,
-				    struct ib_uverbs_file *uverbs_file,
 				    struct file *filp, char __user *buf,
 				    size_t count, loff_t *pos,
 				    size_t eventsz)
@@ -233,19 +232,16 @@ static ssize_t ib_uverbs_event_read(struct ib_uverbs_event_queue *ev_queue,
 
 		if (wait_event_interruptible(ev_queue->poll_wait,
 					     (!list_empty(&ev_queue->event_list) ||
-			/* The barriers built into wait_event_interruptible()
-			 * and wake_up() guarentee this will see the null set
-			 * without using RCU
-			 */
-					     !uverbs_file->device->ib_dev)))
+					      ev_queue->is_closed)))
 			return -ERESTARTSYS;
 
+		spin_lock_irq(&ev_queue->lock);
+
 		/* If device was disassociated and no event exists set an error */
-		if (list_empty(&ev_queue->event_list) &&
-		    !uverbs_file->device->ib_dev)
+		if (list_empty(&ev_queue->event_list) && ev_queue->is_closed) {
+			spin_unlock_irq(&ev_queue->lock);
 			return -EIO;
-
-		spin_lock_irq(&ev_queue->lock);
+		}
 	}
 
 	event = list_entry(ev_queue->event_list.next, struct ib_uverbs_event, list);
@@ -280,8 +276,7 @@ static ssize_t ib_uverbs_async_event_read(struct file *filp, char __user *buf,
 {
 	struct ib_uverbs_async_event_file *file = filp->private_data;
 
-	return ib_uverbs_event_read(&file->ev_queue, file->uverbs_file, filp,
-				    buf, count, pos,
+	return ib_uverbs_event_read(&file->ev_queue, filp, buf, count, pos,
 				    sizeof(struct ib_uverbs_async_event_desc));
 }
 
@@ -291,9 +286,8 @@ static ssize_t ib_uverbs_comp_event_read(struct file *filp, char __user *buf,
 	struct ib_uverbs_completion_event_file *comp_ev_file =
 		filp->private_data;
 
-	return ib_uverbs_event_read(&comp_ev_file->ev_queue,
-				    comp_ev_file->uobj.ufile, filp,
-				    buf, count, pos,
+	return ib_uverbs_event_read(&comp_ev_file->ev_queue, filp, buf, count,
+				    pos,
 				    sizeof(struct ib_uverbs_comp_event_desc));
 }
 
@@ -308,6 +302,8 @@ static __poll_t ib_uverbs_event_poll(struct ib_uverbs_event_queue *ev_queue,
 	spin_lock_irq(&ev_queue->lock);
 	if (!list_empty(&ev_queue->event_list))
 		pollflags = EPOLLIN | EPOLLRDNORM;
+	else if (ev_queue->is_closed)
+		pollflags = EPOLLERR;
 	spin_unlock_irq(&ev_queue->lock);
 
 	return pollflags;
@@ -316,7 +312,9 @@ static __poll_t ib_uverbs_event_poll(struct ib_uverbs_event_queue *ev_queue,
 static __poll_t ib_uverbs_async_event_poll(struct file *filp,
 					       struct poll_table_struct *wait)
 {
-	return ib_uverbs_event_poll(filp->private_data, filp, wait);
+	struct ib_uverbs_async_event_file *file = filp->private_data;
+
+	return ib_uverbs_event_poll(&file->ev_queue, filp, wait);
 }
 
 static __poll_t ib_uverbs_comp_event_poll(struct file *filp,
@@ -330,9 +328,9 @@ static __poll_t ib_uverbs_comp_event_poll(struct file *filp,
 
 static int ib_uverbs_async_event_fasync(int fd, struct file *filp, int on)
 {
-	struct ib_uverbs_event_queue *ev_queue = filp->private_data;
+	struct ib_uverbs_async_event_file *file = filp->private_data;
 
-	return fasync_helper(fd, filp, on, &ev_queue->async_queue);
+	return fasync_helper(fd, filp, on, &file->ev_queue.async_queue);
 }
 
 static int ib_uverbs_comp_event_fasync(int fd, struct file *filp, int on)
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 10a0e49b70a0..41caf36575df 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -316,7 +316,7 @@ struct ib_pd *__ib_alloc_pd(struct ib_device *device, unsigned int flags,
 EXPORT_SYMBOL(__ib_alloc_pd);
 
 /**
- * ib_dealloc_pd - Deallocates a protection domain.
+ * ib_dealloc_pd_user - Deallocates a protection domain.
  * @pd: The protection domain to deallocate.
  * @udata: Valid user data or NULL for kernel object
  *
@@ -1175,16 +1175,6 @@ struct ib_qp *ib_create_qp_user(struct ib_pd *pd,
 	if (ret)
 		goto err;
 
-	qp->qp_type    = qp_init_attr->qp_type;
-	qp->rwq_ind_tbl = qp_init_attr->rwq_ind_tbl;
-
-	atomic_set(&qp->usecnt, 0);
-	qp->mrs_used = 0;
-	spin_lock_init(&qp->mr_lock);
-	INIT_LIST_HEAD(&qp->rdma_mrs);
-	INIT_LIST_HEAD(&qp->sig_mrs);
-	qp->port = 0;
-
 	if (qp_init_attr->qp_type == IB_QPT_XRC_TGT) {
 		struct ib_qp *xrc_qp =
 			create_xrc_qp_user(qp, qp_init_attr, udata);
@@ -1651,7 +1641,7 @@ static int _ib_modify_qp(struct ib_qp *qp, struct ib_qp_attr *attr,
 		if (!(rdma_protocol_ib(qp->device,
 				       attr->alt_ah_attr.port_num) &&
 		      rdma_protocol_ib(qp->device, port))) {
-			ret = EINVAL;
+			ret = -EINVAL;
 			goto out;
 		}
 	}
@@ -1982,7 +1972,7 @@ int ib_dereg_mr_user(struct ib_mr *mr, struct ib_udata *udata)
 EXPORT_SYMBOL(ib_dereg_mr_user);
 
 /**
- * ib_alloc_mr() - Allocates a memory region
+ * ib_alloc_mr_user() - Allocates a memory region
  * @pd:            protection domain associated with the region
  * @mr_type:       memory region type
  * @max_num_sg:    maximum sg entries available for registration.
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 94559169924f..7d9f44434562 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -3346,8 +3346,10 @@ int bnxt_re_dereg_mr(struct ib_mr *ib_mr, struct ib_udata *udata)
 	int rc;
 
 	rc = bnxt_qplib_free_mrw(&rdev->qplib_res, &mr->qplib_mr);
-	if (rc)
+	if (rc) {
 		dev_err(rdev_to_dev(rdev), "Dereg MR failed: %#x\n", rc);
+		return rc;
+	}
 
 	if (mr->pages) {
 		rc = bnxt_qplib_free_fast_reg_page_list(&rdev->qplib_res,
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index 958c1ff9c515..4d07d22bfa7b 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -2283,13 +2283,13 @@ static int bnxt_qplib_cq_process_req(struct bnxt_qplib_cq *cq,
 			/* Add qp to flush list of the CQ */
 			bnxt_qplib_add_flush_qp(qp);
 		} else {
+			/* Before we complete, do WA 9060 */
+			if (do_wa9060(qp, cq, cq_cons, sw_sq_cons,
+				      cqe_sq_cons)) {
+				*lib_qp = qp;
+				goto out;
+			}
 			if (swq->flags & SQ_SEND_FLAGS_SIGNAL_COMP) {
-				/* Before we complete, do WA 9060 */
-				if (do_wa9060(qp, cq, cq_cons, sw_sq_cons,
-					      cqe_sq_cons)) {
-					*lib_qp = qp;
-					goto out;
-				}
 				cqe->status = CQ_REQ_STATUS_OK;
 				cqe++;
 				(*budget)--;
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 216c69325659..69d5fc3eba45 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -2888,8 +2888,7 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb)
 			srqidx = ABORT_RSS_SRQIDX_G(
 					be32_to_cpu(req->srqidx_status));
 			if (srqidx) {
-				complete_cached_srq_buffers(ep,
-							    req->srqidx_status);
+				complete_cached_srq_buffers(ep, srqidx);
 			} else {
 				/* Hold ep ref until finish_peer_abort() */
 				c4iw_get_ep(&ep->com);
@@ -3033,6 +3032,10 @@ static int terminate(struct c4iw_dev *dev, struct sk_buff *skb)
 				       C4IW_QP_ATTR_NEXT_STATE, &attrs, 1);
 		}
 
+		/* As per draft-hilland-iwarp-verbs-v1.0, sec 6.2.3,
+		 * when entering the TERM state the RNIC MUST initiate a CLOSE.
+		 */
+		c4iw_ep_disconnect(ep, 1, GFP_KERNEL);
 		c4iw_put_ep(&ep->com);
 	} else
 		pr_warn("TERM received tid %u no ep/qp\n", tid);
@@ -3866,8 +3869,8 @@ static int read_tcb_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 		return 0;
 	}
 
-	ep->srqe_idx = t4_tcb_get_field32(tcb, TCB_RQ_START_W, TCB_RQ_START_W,
-			TCB_RQ_START_S);
+	ep->srqe_idx = t4_tcb_get_field32(tcb, TCB_RQ_START_W, TCB_RQ_START_M,
+					  TCB_RQ_START_S);
 cleanup:
 	pr_debug("ep %p tid %u %016x\n", ep, ep->hwtid, ep->srqe_idx);
 
diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c
index 570aa1ff49b3..1e6f38dea488 100644
--- a/drivers/infiniband/hw/cxgb4/device.c
+++ b/drivers/infiniband/hw/cxgb4/device.c
@@ -953,6 +953,7 @@ void c4iw_dealloc(struct uld_ctx *ctx)
 static void c4iw_remove(struct uld_ctx *ctx)
 {
 	pr_debug("c4iw_dev %p\n", ctx->dev);
+	debugfs_remove_recursive(ctx->dev->debugfs_root);
 	c4iw_unregister_device(ctx->dev);
 	c4iw_dealloc(ctx);
 }
diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c
index 69b287d025f7..7af958b3318e 100644
--- a/drivers/infiniband/hw/cxgb4/mem.c
+++ b/drivers/infiniband/hw/cxgb4/mem.c
@@ -398,7 +398,6 @@ static int finish_mem_reg(struct c4iw_mr *mhp, u32 stag)
 	mmid = stag >> 8;
 	mhp->ibmr.rkey = mhp->ibmr.lkey = stag;
 	mhp->ibmr.length = mhp->attr.len;
-	mhp->ibmr.iova = mhp->attr.va_fbo;
 	mhp->ibmr.page_size = 1U << (mhp->attr.page_size + 12);
 	pr_debug("mmid 0x%x mhp %p\n", mmid, mhp);
 	return xa_insert_irq(&mhp->rhp->mrs, mmid, mhp, GFP_KERNEL);
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index 752c65268b0e..8b587cb2aa55 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -1976,10 +1976,10 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 			qhp->attr.layer_etype = attrs->layer_etype;
 			qhp->attr.ecode = attrs->ecode;
 			ep = qhp->ep;
-			c4iw_get_ep(&ep->com);
-			disconnect = 1;
 			if (!internal) {
+				c4iw_get_ep(&ep->com);
 				terminate = 1;
+				disconnect = 1;
 			} else {
 				terminate = qhp->attr.send_term;
 				ret = rdma_fini(rhp, qhp, ep);
diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c
index 4fe662c3bbc1..39c0067fe66a 100644
--- a/drivers/infiniband/hw/hfi1/affinity.c
+++ b/drivers/infiniband/hw/hfi1/affinity.c
@@ -479,6 +479,8 @@ static int _dev_comp_vect_mappings_create(struct hfi1_devdata *dd,
 			  rvt_get_ibdev_name(&(dd)->verbs_dev.rdi), i, cpu);
 	}
 
+	free_cpumask_var(available_cpus);
+	free_cpumask_var(non_intr_cpus);
 	return 0;
 
 fail:
diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index 67052dc3100c..e510f019d712 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -1685,6 +1685,14 @@ static u64 access_sw_pio_drain(const struct cntr_entry *entry,
 	return dd->verbs_dev.n_piodrain;
 }
 
+static u64 access_sw_ctx0_seq_drop(const struct cntr_entry *entry,
+				   void *context, int vl, int mode, u64 data)
+{
+	struct hfi1_devdata *dd = context;
+
+	return dd->ctx0_seq_drop;
+}
+
 static u64 access_sw_vtx_wait(const struct cntr_entry *entry,
 			      void *context, int vl, int mode, u64 data)
 {
@@ -4105,6 +4113,7 @@ def_access_ibp_counter(seq_naks);
 static struct cntr_entry dev_cntrs[DEV_CNTR_LAST] = {
 [C_RCV_OVF] = RXE32_DEV_CNTR_ELEM(RcvOverflow, RCV_BUF_OVFL_CNT, CNTR_SYNTH),
 [C_RX_LEN_ERR] = RXE32_DEV_CNTR_ELEM(RxLenErr, RCV_LENGTH_ERR_CNT, CNTR_SYNTH),
+[C_RX_SHORT_ERR] = RXE32_DEV_CNTR_ELEM(RxShrErr, RCV_SHORT_ERR_CNT, CNTR_SYNTH),
 [C_RX_ICRC_ERR] = RXE32_DEV_CNTR_ELEM(RxICrcErr, RCV_ICRC_ERR_CNT, CNTR_SYNTH),
 [C_RX_EBP] = RXE32_DEV_CNTR_ELEM(RxEbpCnt, RCV_EBP_CNT, CNTR_SYNTH),
 [C_RX_TID_FULL] = RXE32_DEV_CNTR_ELEM(RxTIDFullEr, RCV_TID_FULL_ERR_CNT,
@@ -4248,6 +4257,8 @@ static struct cntr_entry dev_cntrs[DEV_CNTR_LAST] = {
 			    access_sw_cpu_intr),
 [C_SW_CPU_RCV_LIM] = CNTR_ELEM("RcvLimit", 0, 0, CNTR_NORMAL,
 			    access_sw_cpu_rcv_limit),
+[C_SW_CTX0_SEQ_DROP] = CNTR_ELEM("SeqDrop0", 0, 0, CNTR_NORMAL,
+			    access_sw_ctx0_seq_drop),
 [C_SW_VTX_WAIT] = CNTR_ELEM("vTxWait", 0, 0, CNTR_NORMAL,
 			    access_sw_vtx_wait),
 [C_SW_PIO_WAIT] = CNTR_ELEM("PioWait", 0, 0, CNTR_NORMAL,
diff --git a/drivers/infiniband/hw/hfi1/chip.h b/drivers/infiniband/hw/hfi1/chip.h
index b76cf81f927f..39a57c35af22 100644
--- a/drivers/infiniband/hw/hfi1/chip.h
+++ b/drivers/infiniband/hw/hfi1/chip.h
@@ -859,6 +859,7 @@ static inline int idx_from_vl(int vl)
 enum {
 	C_RCV_OVF = 0,
 	C_RX_LEN_ERR,
+	C_RX_SHORT_ERR,
 	C_RX_ICRC_ERR,
 	C_RX_EBP,
 	C_RX_TID_FULL,
@@ -926,6 +927,7 @@ enum {
 	C_DC_PG_STS_TX_MBE_CNT,
 	C_SW_CPU_INTR,
 	C_SW_CPU_RCV_LIM,
+	C_SW_CTX0_SEQ_DROP,
 	C_SW_VTX_WAIT,
 	C_SW_PIO_WAIT,
 	C_SW_PIO_DRAIN,
diff --git a/drivers/infiniband/hw/hfi1/chip_registers.h b/drivers/infiniband/hw/hfi1/chip_registers.h
index ab3589d17aee..fb3ec9bff7a2 100644
--- a/drivers/infiniband/hw/hfi1/chip_registers.h
+++ b/drivers/infiniband/hw/hfi1/chip_registers.h
@@ -381,6 +381,7 @@
 #define DC_LCB_STS_LINK_TRANSFER_ACTIVE (DC_LCB_CSRS + 0x000000000468)
 #define DC_LCB_STS_ROUND_TRIP_LTP_CNT (DC_LCB_CSRS + 0x0000000004B0)
 #define RCV_LENGTH_ERR_CNT 0
+#define RCV_SHORT_ERR_CNT 2
 #define RCV_ICRC_ERR_CNT 6
 #define RCV_EBP_CNT 9
 #define RCV_BUF_OVFL_CNT 10
diff --git a/drivers/infiniband/hw/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c
index 01aa1f132f55..941b465244ab 100644
--- a/drivers/infiniband/hw/hfi1/driver.c
+++ b/drivers/infiniband/hw/hfi1/driver.c
@@ -734,6 +734,7 @@ static noinline int skip_rcv_packet(struct hfi1_packet *packet, int thread)
 {
 	int ret;
 
+	packet->rcd->dd->ctx0_seq_drop++;
 	/* Set up for the next packet */
 	packet->rhqoff += packet->rsize;
 	if (packet->rhqoff >= packet->maxcnt)
diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c
index f9a7e9d29c8b..89e1dfd07a1b 100644
--- a/drivers/infiniband/hw/hfi1/file_ops.c
+++ b/drivers/infiniband/hw/hfi1/file_ops.c
@@ -200,23 +200,24 @@ static int hfi1_file_open(struct inode *inode, struct file *fp)
 
 	fd = kzalloc(sizeof(*fd), GFP_KERNEL);
 
-	if (fd) {
-		fd->rec_cpu_num = -1; /* no cpu affinity by default */
-		fd->mm = current->mm;
-		mmgrab(fd->mm);
-		fd->dd = dd;
-		kobject_get(&fd->dd->kobj);
-		fp->private_data = fd;
-	} else {
-		fp->private_data = NULL;
-
-		if (atomic_dec_and_test(&dd->user_refcount))
-			complete(&dd->user_comp);
-
-		return -ENOMEM;
-	}
-
+	if (!fd || init_srcu_struct(&fd->pq_srcu))
+		goto nomem;
+	spin_lock_init(&fd->pq_rcu_lock);
+	spin_lock_init(&fd->tid_lock);
+	spin_lock_init(&fd->invalid_lock);
+	fd->rec_cpu_num = -1; /* no cpu affinity by default */
+	fd->mm = current->mm;
+	mmgrab(fd->mm);
+	fd->dd = dd;
+	kobject_get(&fd->dd->kobj);
+	fp->private_data = fd;
 	return 0;
+nomem:
+	kfree(fd);
+	fp->private_data = NULL;
+	if (atomic_dec_and_test(&dd->user_refcount))
+		complete(&dd->user_comp);
+	return -ENOMEM;
 }
 
 static long hfi1_file_ioctl(struct file *fp, unsigned int cmd,
@@ -301,21 +302,30 @@ static long hfi1_file_ioctl(struct file *fp, unsigned int cmd,
 static ssize_t hfi1_write_iter(struct kiocb *kiocb, struct iov_iter *from)
 {
 	struct hfi1_filedata *fd = kiocb->ki_filp->private_data;
-	struct hfi1_user_sdma_pkt_q *pq = fd->pq;
+	struct hfi1_user_sdma_pkt_q *pq;
 	struct hfi1_user_sdma_comp_q *cq = fd->cq;
 	int done = 0, reqs = 0;
 	unsigned long dim = from->nr_segs;
+	int idx;
 
-	if (!cq || !pq)
+	idx = srcu_read_lock(&fd->pq_srcu);
+	pq = srcu_dereference(fd->pq, &fd->pq_srcu);
+	if (!cq || !pq) {
+		srcu_read_unlock(&fd->pq_srcu, idx);
 		return -EIO;
+	}
 
-	if (!iter_is_iovec(from) || !dim)
+	if (!iter_is_iovec(from) || !dim) {
+		srcu_read_unlock(&fd->pq_srcu, idx);
 		return -EINVAL;
+	}
 
 	trace_hfi1_sdma_request(fd->dd, fd->uctxt->ctxt, fd->subctxt, dim);
 
-	if (atomic_read(&pq->n_reqs) == pq->n_max_reqs)
+	if (atomic_read(&pq->n_reqs) == pq->n_max_reqs) {
+		srcu_read_unlock(&fd->pq_srcu, idx);
 		return -ENOSPC;
+	}
 
 	while (dim) {
 		int ret;
@@ -333,6 +343,7 @@ static ssize_t hfi1_write_iter(struct kiocb *kiocb, struct iov_iter *from)
 		reqs++;
 	}
 
+	srcu_read_unlock(&fd->pq_srcu, idx);
 	return reqs;
 }
 
@@ -707,6 +718,7 @@ done:
 	if (atomic_dec_and_test(&dd->user_refcount))
 		complete(&dd->user_comp);
 
+	cleanup_srcu_struct(&fdata->pq_srcu);
 	kfree(fdata);
 	return 0;
 }
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index fa45350a9a1d..b79931cc74ab 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -1153,6 +1153,8 @@ struct hfi1_devdata {
 
 	char *boardname; /* human readable board info */
 
+	u64 ctx0_seq_drop;
+
 	/* reset value */
 	u64 z_int_counter;
 	u64 z_rcv_limit;
@@ -1436,10 +1438,13 @@ struct mmu_rb_handler;
 
 /* Private data for file operations */
 struct hfi1_filedata {
+	struct srcu_struct pq_srcu;
 	struct hfi1_devdata *dd;
 	struct hfi1_ctxtdata *uctxt;
 	struct hfi1_user_sdma_comp_q *cq;
-	struct hfi1_user_sdma_pkt_q *pq;
+	/* update side lock for SRCU */
+	spinlock_t pq_rcu_lock;
+	struct hfi1_user_sdma_pkt_q __rcu *pq;
 	u16 subctxt;
 	/* for cpu affinity; -1 if none */
 	int rec_cpu_num;
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 26b792bb1027..fbff6b2f00e7 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -845,6 +845,29 @@ wq_error:
 }
 
 /**
+ * destroy_workqueues - destroy per port workqueues
+ * @dd: the hfi1_ib device
+ */
+static void destroy_workqueues(struct hfi1_devdata *dd)
+{
+	int pidx;
+	struct hfi1_pportdata *ppd;
+
+	for (pidx = 0; pidx < dd->num_pports; ++pidx) {
+		ppd = dd->pport + pidx;
+
+		if (ppd->hfi1_wq) {
+			destroy_workqueue(ppd->hfi1_wq);
+			ppd->hfi1_wq = NULL;
+		}
+		if (ppd->link_wq) {
+			destroy_workqueue(ppd->link_wq);
+			ppd->link_wq = NULL;
+		}
+	}
+}
+
+/**
  * enable_general_intr() - Enable the IRQs that will be handled by the
  * general interrupt handler.
  * @dd: valid devdata
@@ -1117,15 +1140,10 @@ static void shutdown_device(struct hfi1_devdata *dd)
 		 * We can't count on interrupts since we are stopping.
 		 */
 		hfi1_quiet_serdes(ppd);
-
-		if (ppd->hfi1_wq) {
-			destroy_workqueue(ppd->hfi1_wq);
-			ppd->hfi1_wq = NULL;
-		}
-		if (ppd->link_wq) {
-			destroy_workqueue(ppd->link_wq);
-			ppd->link_wq = NULL;
-		}
+		if (ppd->hfi1_wq)
+			flush_workqueue(ppd->hfi1_wq);
+		if (ppd->link_wq)
+			flush_workqueue(ppd->link_wq);
 	}
 	sdma_exit(dd);
 }
@@ -1814,6 +1832,7 @@ static void remove_one(struct pci_dev *pdev)
 	 * clear dma engines, etc.
 	 */
 	shutdown_device(dd);
+	destroy_workqueues(dd);
 
 	stop_timers(dd);
 
diff --git a/drivers/infiniband/hw/hfi1/iowait.c b/drivers/infiniband/hw/hfi1/iowait.c
index adb4a1ba921b..5836fe7b2817 100644
--- a/drivers/infiniband/hw/hfi1/iowait.c
+++ b/drivers/infiniband/hw/hfi1/iowait.c
@@ -81,7 +81,9 @@ void iowait_init(struct iowait *wait, u32 tx_limit,
 void iowait_cancel_work(struct iowait *w)
 {
 	cancel_work_sync(&iowait_get_ib_work(w)->iowork);
-	cancel_work_sync(&iowait_get_tid_work(w)->iowork);
+	/* Make sure that the iowork for TID RDMA is used */
+	if (iowait_get_tid_work(w)->iowork.func)
+		cancel_work_sync(&iowait_get_tid_work(w)->iowork);
 }
 
 /**
diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c
index 4e5c2d1b8cfa..79126b2b14ab 100644
--- a/drivers/infiniband/hw/hfi1/pio.c
+++ b/drivers/infiniband/hw/hfi1/pio.c
@@ -1594,9 +1594,8 @@ void hfi1_sc_wantpiobuf_intr(struct send_context *sc, u32 needint)
 	else
 		sc_del_credit_return_intr(sc);
 	trace_hfi1_wantpiointr(sc, needint, sc->credit_ctrl);
-	if (needint) {
+	if (needint)
 		sc_return_credits(sc);
-	}
 }
 
 /**
diff --git a/drivers/infiniband/hw/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c
index 4e0e9fc0a777..30ba09b510fa 100644
--- a/drivers/infiniband/hw/hfi1/qp.c
+++ b/drivers/infiniband/hw/hfi1/qp.c
@@ -381,7 +381,10 @@ bool _hfi1_schedule_send(struct rvt_qp *qp)
 	struct hfi1_ibport *ibp =
 		to_iport(qp->ibqp.device, qp->port_num);
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
-	struct hfi1_devdata *dd = dd_from_ibdev(qp->ibqp.device);
+	struct hfi1_devdata *dd = ppd->dd;
+
+	if (dd->flags & HFI1_SHUTDOWN)
+		return true;
 
 	return iowait_schedule(&priv->s_iowait, ppd->hfi1_wq,
 			       priv->s_sde ?
diff --git a/drivers/infiniband/hw/hfi1/sysfs.c b/drivers/infiniband/hw/hfi1/sysfs.c
index 90f62c4bddba..074ec71772d2 100644
--- a/drivers/infiniband/hw/hfi1/sysfs.c
+++ b/drivers/infiniband/hw/hfi1/sysfs.c
@@ -674,7 +674,11 @@ int hfi1_create_port_files(struct ib_device *ibdev, u8 port_num,
 		dd_dev_err(dd,
 			   "Skipping sc2vl sysfs info, (err %d) port %u\n",
 			   ret, port_num);
-		goto bail;
+		/*
+		 * Based on the documentation for kobject_init_and_add(), the
+		 * caller should call kobject_put even if this call fails.
+		 */
+		goto bail_sc2vl;
 	}
 	kobject_uevent(&ppd->sc2vl_kobj, KOBJ_ADD);
 
@@ -684,7 +688,7 @@ int hfi1_create_port_files(struct ib_device *ibdev, u8 port_num,
 		dd_dev_err(dd,
 			   "Skipping sl2sc sysfs info, (err %d) port %u\n",
 			   ret, port_num);
-		goto bail_sc2vl;
+		goto bail_sl2sc;
 	}
 	kobject_uevent(&ppd->sl2sc_kobj, KOBJ_ADD);
 
@@ -694,7 +698,7 @@ int hfi1_create_port_files(struct ib_device *ibdev, u8 port_num,
 		dd_dev_err(dd,
 			   "Skipping vl2mtu sysfs info, (err %d) port %u\n",
 			   ret, port_num);
-		goto bail_sl2sc;
+		goto bail_vl2mtu;
 	}
 	kobject_uevent(&ppd->vl2mtu_kobj, KOBJ_ADD);
 
@@ -704,7 +708,7 @@ int hfi1_create_port_files(struct ib_device *ibdev, u8 port_num,
 		dd_dev_err(dd,
 			   "Skipping Congestion Control sysfs info, (err %d) port %u\n",
 			   ret, port_num);
-		goto bail_vl2mtu;
+		goto bail_cc;
 	}
 
 	kobject_uevent(&ppd->pport_cc_kobj, KOBJ_ADD);
@@ -742,7 +746,6 @@ bail_sl2sc:
 	kobject_put(&ppd->sl2sc_kobj);
 bail_sc2vl:
 	kobject_put(&ppd->sc2vl_kobj);
-bail:
 	return ret;
 }
 
@@ -853,8 +856,13 @@ int hfi1_verbs_register_sysfs(struct hfi1_devdata *dd)
 
 	return 0;
 bail:
-	for (i = 0; i < dd->num_sdma; i++)
-		kobject_del(&dd->per_sdma[i].kobj);
+	/*
+	 * The function kobject_put() will call kobject_del() if the kobject
+	 * has been added successfully. The sysfs files created under the
+	 * kobject directory will also be removed during the process.
+	 */
+	for (; i >= 0; i--)
+		kobject_put(&dd->per_sdma[i].kobj);
 
 	return ret;
 }
@@ -867,6 +875,10 @@ void hfi1_verbs_unregister_sysfs(struct hfi1_devdata *dd)
 	struct hfi1_pportdata *ppd;
 	int i;
 
+	/* Unwind operations in hfi1_verbs_register_sysfs() */
+	for (i = 0; i < dd->num_sdma; i++)
+		kobject_put(&dd->per_sdma[i].kobj);
+
 	for (i = 0; i < dd->num_pports; i++) {
 		ppd = &dd->pport[i];
 
diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c
index 50ddb6d3aefa..b5bc41e10e22 100644
--- a/drivers/infiniband/hw/hfi1/tid_rdma.c
+++ b/drivers/infiniband/hw/hfi1/tid_rdma.c
@@ -4627,6 +4627,15 @@ void hfi1_rc_rcv_tid_rdma_ack(struct hfi1_packet *packet)
 			 */
 			fpsn = full_flow_psn(flow, flow->flow_state.spsn);
 			req->r_ack_psn = psn;
+			/*
+			 * If resync_psn points to the last flow PSN for a
+			 * segment and the new segment (likely from a new
+			 * request) starts with a new generation number, we
+			 * need to adjust resync_psn accordingly.
+			 */
+			if (flow->flow_state.generation !=
+			    (resync_psn >> HFI1_KDETH_BTH_SEQ_SHIFT))
+				resync_psn = mask_psn(fpsn - 1);
 			flow->resync_npkts +=
 				delta_psn(mask_psn(resync_psn + 1), fpsn);
 			/*
@@ -5391,7 +5400,10 @@ static bool _hfi1_schedule_tid_send(struct rvt_qp *qp)
 	struct hfi1_ibport *ibp =
 		to_iport(qp->ibqp.device, qp->port_num);
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
-	struct hfi1_devdata *dd = dd_from_ibdev(qp->ibqp.device);
+	struct hfi1_devdata *dd = ppd->dd;
+
+	if ((dd->flags & HFI1_SHUTDOWN))
+		return true;
 
 	return iowait_tid_schedule(&priv->s_iowait, ppd->hfi1_wq,
 				   priv->s_sde ?
diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c
index 3592a9ec155e..4d732353379d 100644
--- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c
+++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c
@@ -90,9 +90,6 @@ int hfi1_user_exp_rcv_init(struct hfi1_filedata *fd,
 	struct hfi1_devdata *dd = uctxt->dd;
 	int ret = 0;
 
-	spin_lock_init(&fd->tid_lock);
-	spin_lock_init(&fd->invalid_lock);
-
 	fd->entry_to_rb = kcalloc(uctxt->expected_count,
 				  sizeof(struct rb_node *),
 				  GFP_KERNEL);
@@ -165,10 +162,12 @@ void hfi1_user_exp_rcv_free(struct hfi1_filedata *fd)
 	if (fd->handler) {
 		hfi1_mmu_rb_unregister(fd->handler);
 	} else {
+		mutex_lock(&uctxt->exp_mutex);
 		if (!EXP_TID_SET_EMPTY(uctxt->tid_full_list))
 			unlock_exp_tids(uctxt, &uctxt->tid_full_list, fd);
 		if (!EXP_TID_SET_EMPTY(uctxt->tid_used_list))
 			unlock_exp_tids(uctxt, &uctxt->tid_used_list, fd);
+		mutex_unlock(&uctxt->exp_mutex);
 	}
 
 	kfree(fd->invalid_tids);
diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c
index fd754a16475a..a92346e88628 100644
--- a/drivers/infiniband/hw/hfi1/user_sdma.c
+++ b/drivers/infiniband/hw/hfi1/user_sdma.c
@@ -141,6 +141,7 @@ static int defer_packet_queue(
 	 */
 	xchg(&pq->state, SDMA_PKT_Q_DEFERRED);
 	if (list_empty(&pq->busy.list)) {
+		pq->busy.lock = &sde->waitlock;
 		iowait_get_priority(&pq->busy);
 		iowait_queue(pkts_sent, &pq->busy, &sde->dmawait);
 	}
@@ -155,6 +156,7 @@ static void activate_packet_queue(struct iowait *wait, int reason)
 {
 	struct hfi1_user_sdma_pkt_q *pq =
 		container_of(wait, struct hfi1_user_sdma_pkt_q, busy);
+	pq->busy.lock = NULL;
 	xchg(&pq->state, SDMA_PKT_Q_ACTIVE);
 	wake_up(&wait->wait_dma);
 };
@@ -179,7 +181,6 @@ int hfi1_user_sdma_alloc_queues(struct hfi1_ctxtdata *uctxt,
 	pq = kzalloc(sizeof(*pq), GFP_KERNEL);
 	if (!pq)
 		return -ENOMEM;
-
 	pq->dd = dd;
 	pq->ctxt = uctxt->ctxt;
 	pq->subctxt = fd->subctxt;
@@ -236,7 +237,7 @@ int hfi1_user_sdma_alloc_queues(struct hfi1_ctxtdata *uctxt,
 		goto pq_mmu_fail;
 	}
 
-	fd->pq = pq;
+	rcu_assign_pointer(fd->pq, pq);
 	fd->cq = cq;
 
 	return 0;
@@ -257,6 +258,21 @@ pq_reqs_nomem:
 	return ret;
 }
 
+static void flush_pq_iowait(struct hfi1_user_sdma_pkt_q *pq)
+{
+	unsigned long flags;
+	seqlock_t *lock = pq->busy.lock;
+
+	if (!lock)
+		return;
+	write_seqlock_irqsave(lock, flags);
+	if (!list_empty(&pq->busy.list)) {
+		list_del_init(&pq->busy.list);
+		pq->busy.lock = NULL;
+	}
+	write_sequnlock_irqrestore(lock, flags);
+}
+
 int hfi1_user_sdma_free_queues(struct hfi1_filedata *fd,
 			       struct hfi1_ctxtdata *uctxt)
 {
@@ -264,8 +280,14 @@ int hfi1_user_sdma_free_queues(struct hfi1_filedata *fd,
 
 	trace_hfi1_sdma_user_free_queues(uctxt->dd, uctxt->ctxt, fd->subctxt);
 
-	pq = fd->pq;
+	spin_lock(&fd->pq_rcu_lock);
+	pq = srcu_dereference_check(fd->pq, &fd->pq_srcu,
+				    lockdep_is_held(&fd->pq_rcu_lock));
 	if (pq) {
+		rcu_assign_pointer(fd->pq, NULL);
+		spin_unlock(&fd->pq_rcu_lock);
+		synchronize_srcu(&fd->pq_srcu);
+		/* at this point there can be no more new requests */
 		if (pq->handler)
 			hfi1_mmu_rb_unregister(pq->handler);
 		iowait_sdma_drain(&pq->busy);
@@ -276,8 +298,10 @@ int hfi1_user_sdma_free_queues(struct hfi1_filedata *fd,
 		kfree(pq->reqs);
 		kfree(pq->req_in_use);
 		kmem_cache_destroy(pq->txreq_cache);
+		flush_pq_iowait(pq);
 		kfree(pq);
-		fd->pq = NULL;
+	} else {
+		spin_unlock(&fd->pq_rcu_lock);
 	}
 	if (fd->cq) {
 		vfree(fd->cq->comps);
@@ -321,7 +345,8 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd,
 {
 	int ret = 0, i;
 	struct hfi1_ctxtdata *uctxt = fd->uctxt;
-	struct hfi1_user_sdma_pkt_q *pq = fd->pq;
+	struct hfi1_user_sdma_pkt_q *pq =
+		srcu_dereference(fd->pq, &fd->pq_srcu);
 	struct hfi1_user_sdma_comp_q *cq = fd->cq;
 	struct hfi1_devdata *dd = pq->dd;
 	unsigned long idx = 0;
@@ -564,10 +589,6 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd,
 
 	set_comp_state(pq, cq, info.comp_idx, QUEUED, 0);
 	pq->state = SDMA_PKT_Q_ACTIVE;
-	/* Send the first N packets in the request to buy us some time */
-	ret = user_sdma_send_pkts(req, pcount);
-	if (unlikely(ret < 0 && ret != -EBUSY))
-		goto free_req;
 
 	/*
 	 * This is a somewhat blocking send implementation.
@@ -580,11 +601,12 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd,
 		if (ret < 0) {
 			if (ret != -EBUSY)
 				goto free_req;
-			wait_event_interruptible_timeout(
+			if (wait_event_interruptible_timeout(
 				pq->busy.wait_dma,
-				(pq->state == SDMA_PKT_Q_ACTIVE),
+				pq->state == SDMA_PKT_Q_ACTIVE,
 				msecs_to_jiffies(
-					SDMA_IOWAIT_TIMEOUT));
+					SDMA_IOWAIT_TIMEOUT)) <= 0)
+				flush_pq_iowait(pq);
 		}
 	}
 	*count += idx;
diff --git a/drivers/infiniband/hw/hfi1/user_sdma.h b/drivers/infiniband/hw/hfi1/user_sdma.h
index 4d8510b0fc38..9972e0e6545e 100644
--- a/drivers/infiniband/hw/hfi1/user_sdma.h
+++ b/drivers/infiniband/hw/hfi1/user_sdma.h
@@ -110,12 +110,6 @@ enum pkt_q_sdma_state {
 	SDMA_PKT_Q_DEFERRED,
 };
 
-/*
- * Maximum retry attempts to submit a TX request
- * before putting the process to sleep.
- */
-#define MAX_DEFER_RETRY_COUNT 1
-
 #define SDMA_IOWAIT_TIMEOUT 1000 /* in milliseconds */
 
 #define SDMA_DBG(req, fmt, ...)				     \
diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c
index e02ee5af0303..53dd30fd2d56 100644
--- a/drivers/infiniband/hw/hfi1/verbs.c
+++ b/drivers/infiniband/hw/hfi1/verbs.c
@@ -515,10 +515,11 @@ static inline void hfi1_handle_packet(struct hfi1_packet *packet,
 				       opa_get_lid(packet->dlid, 9B));
 		if (!mcast)
 			goto drop;
+		rcu_read_lock();
 		list_for_each_entry_rcu(p, &mcast->qp_list, list) {
 			packet->qp = p->qp;
 			if (hfi1_do_pkey_check(packet))
-				goto drop;
+				goto unlock_drop;
 			spin_lock_irqsave(&packet->qp->r_lock, flags);
 			packet_handler = qp_ok(packet);
 			if (likely(packet_handler))
@@ -527,6 +528,7 @@ static inline void hfi1_handle_packet(struct hfi1_packet *packet,
 				ibp->rvp.n_pkt_drops++;
 			spin_unlock_irqrestore(&packet->qp->r_lock, flags);
 		}
+		rcu_read_unlock();
 		/*
 		 * Notify rvt_multicast_detach() if it is waiting for us
 		 * to finish.
diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index 563cf39df6d5..9cc2e72093be 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -381,7 +381,7 @@ struct hns_roce_mr_table {
 struct hns_roce_wq {
 	u64		*wrid;     /* Work request ID */
 	spinlock_t	lock;
-	int		wqe_cnt;  /* WQE num */
+	u32		wqe_cnt;  /* WQE num */
 	u32		max_post;
 	int		max_gs;
 	int		offset;
@@ -613,7 +613,6 @@ struct hns_roce_qp {
 	u8			sdb_en;
 	u32			doorbell_qpn;
 	__le32			sq_signal_bits;
-	u32			sq_next_wqe;
 	int			sq_max_wqes_per_wr;
 	int			sq_spare_wqes;
 	struct hns_roce_wq	sq;
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
index 9496c69fff3a..902e74555654 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
@@ -74,8 +74,8 @@ static int hns_roce_v1_post_send(struct ib_qp *ibqp,
 	unsigned long flags = 0;
 	void *wqe = NULL;
 	u32 doorbell[2];
+	u32 wqe_idx = 0;
 	int nreq = 0;
-	u32 ind = 0;
 	int ret = 0;
 	u8 *smac;
 	int loopback;
@@ -88,7 +88,7 @@ static int hns_roce_v1_post_send(struct ib_qp *ibqp,
 	}
 
 	spin_lock_irqsave(&qp->sq.lock, flags);
-	ind = qp->sq_next_wqe;
+
 	for (nreq = 0; wr; ++nreq, wr = wr->next) {
 		if (hns_roce_wq_overflow(&qp->sq, nreq, qp->ibqp.send_cq)) {
 			ret = -ENOMEM;
@@ -96,6 +96,8 @@ static int hns_roce_v1_post_send(struct ib_qp *ibqp,
 			goto out;
 		}
 
+		wqe_idx = (qp->sq.head + nreq) & (qp->sq.wqe_cnt - 1);
+
 		if (unlikely(wr->num_sge > qp->sq.max_gs)) {
 			dev_err(dev, "num_sge=%d > qp->sq.max_gs=%d\n",
 				wr->num_sge, qp->sq.max_gs);
@@ -104,9 +106,8 @@ static int hns_roce_v1_post_send(struct ib_qp *ibqp,
 			goto out;
 		}
 
-		wqe = get_send_wqe(qp, ind & (qp->sq.wqe_cnt - 1));
-		qp->sq.wrid[(qp->sq.head + nreq) & (qp->sq.wqe_cnt - 1)] =
-								      wr->wr_id;
+		wqe = get_send_wqe(qp, wqe_idx);
+		qp->sq.wrid[wqe_idx] = wr->wr_id;
 
 		/* Corresponding to the RC and RD type wqe process separately */
 		if (ibqp->qp_type == IB_QPT_GSI) {
@@ -213,7 +214,6 @@ static int hns_roce_v1_post_send(struct ib_qp *ibqp,
 				       cpu_to_le32((wr->sg_list[1].addr) >> 32);
 			ud_sq_wqe->l_key1 =
 				       cpu_to_le32(wr->sg_list[1].lkey);
-			ind++;
 		} else if (ibqp->qp_type == IB_QPT_RC) {
 			u32 tmp_len = 0;
 
@@ -311,7 +311,6 @@ static int hns_roce_v1_post_send(struct ib_qp *ibqp,
 				ctrl->flag |= cpu_to_le32(wr->num_sge <<
 					      HNS_ROCE_WQE_SGE_NUM_BIT);
 			}
-			ind++;
 		}
 	}
 
@@ -339,7 +338,6 @@ out:
 		doorbell[1] = le32_to_cpu(sq_db.u32_8);
 
 		hns_roce_write64_k((__le32 *)doorbell, qp->sq.db_reg_l);
-		qp->sq_next_wqe = ind;
 	}
 
 	spin_unlock_irqrestore(&qp->sq.lock, flags);
@@ -351,12 +349,6 @@ static int hns_roce_v1_post_recv(struct ib_qp *ibqp,
 				 const struct ib_recv_wr *wr,
 				 const struct ib_recv_wr **bad_wr)
 {
-	int ret = 0;
-	int nreq = 0;
-	int ind = 0;
-	int i = 0;
-	u32 reg_val;
-	unsigned long flags = 0;
 	struct hns_roce_rq_wqe_ctrl *ctrl = NULL;
 	struct hns_roce_wqe_data_seg *scat = NULL;
 	struct hns_roce_qp *hr_qp = to_hr_qp(ibqp);
@@ -364,9 +356,14 @@ static int hns_roce_v1_post_recv(struct ib_qp *ibqp,
 	struct device *dev = &hr_dev->pdev->dev;
 	struct hns_roce_rq_db rq_db;
 	uint32_t doorbell[2] = {0};
+	unsigned long flags = 0;
+	unsigned int wqe_idx;
+	int ret = 0;
+	int nreq = 0;
+	int i = 0;
+	u32 reg_val;
 
 	spin_lock_irqsave(&hr_qp->rq.lock, flags);
-	ind = hr_qp->rq.head & (hr_qp->rq.wqe_cnt - 1);
 
 	for (nreq = 0; wr; ++nreq, wr = wr->next) {
 		if (hns_roce_wq_overflow(&hr_qp->rq, nreq,
@@ -376,6 +373,8 @@ static int hns_roce_v1_post_recv(struct ib_qp *ibqp,
 			goto out;
 		}
 
+		wqe_idx = (hr_qp->rq.head + nreq) & (hr_qp->rq.wqe_cnt - 1);
+
 		if (unlikely(wr->num_sge > hr_qp->rq.max_gs)) {
 			dev_err(dev, "rq:num_sge=%d > qp->sq.max_gs=%d\n",
 				wr->num_sge, hr_qp->rq.max_gs);
@@ -384,7 +383,7 @@ static int hns_roce_v1_post_recv(struct ib_qp *ibqp,
 			goto out;
 		}
 
-		ctrl = get_recv_wqe(hr_qp, ind);
+		ctrl = get_recv_wqe(hr_qp, wqe_idx);
 
 		roce_set_field(ctrl->rwqe_byte_12,
 			       RQ_WQE_CTRL_RWQE_BYTE_12_RWQE_SGE_NUM_M,
@@ -396,9 +395,7 @@ static int hns_roce_v1_post_recv(struct ib_qp *ibqp,
 		for (i = 0; i < wr->num_sge; i++)
 			set_data_seg(scat + i, wr->sg_list + i);
 
-		hr_qp->rq.wrid[ind] = wr->wr_id;
-
-		ind = (ind + 1) & (hr_qp->rq.wqe_cnt - 1);
+		hr_qp->rq.wrid[wqe_idx] = wr->wr_id;
 	}
 
 out:
@@ -2701,7 +2698,6 @@ static int hns_roce_v1_m_sqp(struct ib_qp *ibqp, const struct ib_qp_attr *attr,
 		hr_qp->rq.tail = 0;
 		hr_qp->sq.head = 0;
 		hr_qp->sq.tail = 0;
-		hr_qp->sq_next_wqe = 0;
 	}
 
 	kfree(context);
@@ -3315,7 +3311,6 @@ static int hns_roce_v1_m_qp(struct ib_qp *ibqp, const struct ib_qp_attr *attr,
 		hr_qp->rq.tail = 0;
 		hr_qp->sq.head = 0;
 		hr_qp->sq.tail = 0;
-		hr_qp->sq_next_wqe = 0;
 	}
 out:
 	kfree(context);
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index cfa9e4403a85..ff0e5a3df724 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -110,7 +110,7 @@ static void set_atomic_seg(struct hns_roce_wqe_atomic_seg *aseg,
 }
 
 static void set_extend_sge(struct hns_roce_qp *qp, const struct ib_send_wr *wr,
-			   unsigned int *sge_ind)
+			   unsigned int *sge_ind, int valid_num_sge)
 {
 	struct hns_roce_v2_wqe_data_seg *dseg;
 	struct ib_sge *sg;
@@ -123,7 +123,7 @@ static void set_extend_sge(struct hns_roce_qp *qp, const struct ib_send_wr *wr,
 
 	if (qp->ibqp.qp_type == IB_QPT_RC || qp->ibqp.qp_type == IB_QPT_UC)
 		num_in_wqe = HNS_ROCE_V2_UC_RC_SGE_NUM_IN_WQE;
-	extend_sge_num = wr->num_sge - num_in_wqe;
+	extend_sge_num = valid_num_sge - num_in_wqe;
 	sg = wr->sg_list + num_in_wqe;
 	shift = qp->hr_buf.page_shift;
 
@@ -159,14 +159,16 @@ static void set_extend_sge(struct hns_roce_qp *qp, const struct ib_send_wr *wr,
 static int set_rwqe_data_seg(struct ib_qp *ibqp, const struct ib_send_wr *wr,
 			     struct hns_roce_v2_rc_send_wqe *rc_sq_wqe,
 			     void *wqe, unsigned int *sge_ind,
+			     int valid_num_sge,
 			     const struct ib_send_wr **bad_wr)
 {
 	struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device);
 	struct hns_roce_v2_wqe_data_seg *dseg = wqe;
 	struct hns_roce_qp *qp = to_hr_qp(ibqp);
+	int j = 0;
 	int i;
 
-	if (wr->send_flags & IB_SEND_INLINE && wr->num_sge) {
+	if (wr->send_flags & IB_SEND_INLINE && valid_num_sge) {
 		if (le32_to_cpu(rc_sq_wqe->msg_len) >
 		    hr_dev->caps.max_sq_inline) {
 			*bad_wr = wr;
@@ -190,7 +192,7 @@ static int set_rwqe_data_seg(struct ib_qp *ibqp, const struct ib_send_wr *wr,
 		roce_set_bit(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_INLINE_S,
 			     1);
 	} else {
-		if (wr->num_sge <= HNS_ROCE_V2_UC_RC_SGE_NUM_IN_WQE) {
+		if (valid_num_sge <= HNS_ROCE_V2_UC_RC_SGE_NUM_IN_WQE) {
 			for (i = 0; i < wr->num_sge; i++) {
 				if (likely(wr->sg_list[i].length)) {
 					set_data_seg_v2(dseg, wr->sg_list + i);
@@ -203,19 +205,21 @@ static int set_rwqe_data_seg(struct ib_qp *ibqp, const struct ib_send_wr *wr,
 				     V2_RC_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_S,
 				     (*sge_ind) & (qp->sge.sge_cnt - 1));
 
-			for (i = 0; i < HNS_ROCE_V2_UC_RC_SGE_NUM_IN_WQE; i++) {
+			for (i = 0; i < wr->num_sge &&
+			     j < HNS_ROCE_V2_UC_RC_SGE_NUM_IN_WQE; i++) {
 				if (likely(wr->sg_list[i].length)) {
 					set_data_seg_v2(dseg, wr->sg_list + i);
 					dseg++;
+					j++;
 				}
 			}
 
-			set_extend_sge(qp, wr, sge_ind);
+			set_extend_sge(qp, wr, sge_ind, valid_num_sge);
 		}
 
 		roce_set_field(rc_sq_wqe->byte_16,
 			       V2_RC_SEND_WQE_BYTE_16_SGE_NUM_M,
-			       V2_RC_SEND_WQE_BYTE_16_SGE_NUM_S, wr->num_sge);
+			       V2_RC_SEND_WQE_BYTE_16_SGE_NUM_S, valid_num_sge);
 	}
 
 	return 0;
@@ -239,10 +243,11 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp,
 	struct device *dev = hr_dev->dev;
 	struct hns_roce_v2_db sq_db;
 	struct ib_qp_attr attr;
-	unsigned int sge_ind = 0;
 	unsigned int owner_bit;
+	unsigned int sge_idx;
+	unsigned int wqe_idx;
 	unsigned long flags;
-	unsigned int ind;
+	int valid_num_sge;
 	void *wqe = NULL;
 	bool loopback;
 	int attr_mask;
@@ -269,8 +274,7 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp,
 	}
 
 	spin_lock_irqsave(&qp->sq.lock, flags);
-	ind = qp->sq_next_wqe;
-	sge_ind = qp->next_sge;
+	sge_idx = qp->next_sge;
 
 	for (nreq = 0; wr; ++nreq, wr = wr->next) {
 		if (hns_roce_wq_overflow(&qp->sq, nreq, qp->ibqp.send_cq)) {
@@ -279,6 +283,8 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp,
 			goto out;
 		}
 
+		wqe_idx = (qp->sq.head + nreq) & (qp->sq.wqe_cnt - 1);
+
 		if (unlikely(wr->num_sge > qp->sq.max_gs)) {
 			dev_err(dev, "num_sge=%d > qp->sq.max_gs=%d\n",
 				wr->num_sge, qp->sq.max_gs);
@@ -287,14 +293,20 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp,
 			goto out;
 		}
 
-		wqe = get_send_wqe(qp, ind & (qp->sq.wqe_cnt - 1));
-		qp->sq.wrid[(qp->sq.head + nreq) & (qp->sq.wqe_cnt - 1)] =
-								      wr->wr_id;
-
+		wqe = get_send_wqe(qp, wqe_idx);
+		qp->sq.wrid[wqe_idx] = wr->wr_id;
 		owner_bit =
 		       ~(((qp->sq.head + nreq) >> ilog2(qp->sq.wqe_cnt)) & 0x1);
+		valid_num_sge = 0;
 		tmp_len = 0;
 
+		for (i = 0; i < wr->num_sge; i++) {
+			if (likely(wr->sg_list[i].length)) {
+				tmp_len += wr->sg_list[i].length;
+				valid_num_sge++;
+			}
+		}
+
 		/* Corresponding to the QP type, wqe process separately */
 		if (ibqp->qp_type == IB_QPT_GSI) {
 			ud_sq_wqe = wqe;
@@ -330,9 +342,6 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp,
 				       V2_UD_SEND_WQE_BYTE_4_OPCODE_S,
 				       HNS_ROCE_V2_WQE_OP_SEND);
 
-			for (i = 0; i < wr->num_sge; i++)
-				tmp_len += wr->sg_list[i].length;
-
 			ud_sq_wqe->msg_len =
 			 cpu_to_le32(le32_to_cpu(ud_sq_wqe->msg_len) + tmp_len);
 
@@ -368,12 +377,12 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp,
 			roce_set_field(ud_sq_wqe->byte_16,
 				       V2_UD_SEND_WQE_BYTE_16_SGE_NUM_M,
 				       V2_UD_SEND_WQE_BYTE_16_SGE_NUM_S,
-				       wr->num_sge);
+				       valid_num_sge);
 
 			roce_set_field(ud_sq_wqe->byte_20,
 				     V2_UD_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_M,
 				     V2_UD_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_S,
-				     sge_ind & (qp->sge.sge_cnt - 1));
+				     sge_idx & (qp->sge.sge_cnt - 1));
 
 			roce_set_field(ud_sq_wqe->byte_24,
 				       V2_UD_SEND_WQE_BYTE_24_UDPSPN_M,
@@ -426,13 +435,10 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp,
 			memcpy(&ud_sq_wqe->dgid[0], &ah->av.dgid[0],
 			       GID_LEN_V2);
 
-			set_extend_sge(qp, wr, &sge_ind);
-			ind++;
+			set_extend_sge(qp, wr, &sge_idx, valid_num_sge);
 		} else if (ibqp->qp_type == IB_QPT_RC) {
 			rc_sq_wqe = wqe;
 			memset(rc_sq_wqe, 0, sizeof(*rc_sq_wqe));
-			for (i = 0; i < wr->num_sge; i++)
-				tmp_len += wr->sg_list[i].length;
 
 			rc_sq_wqe->msg_len =
 			 cpu_to_le32(le32_to_cpu(rc_sq_wqe->msg_len) + tmp_len);
@@ -553,15 +559,14 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp,
 				roce_set_field(rc_sq_wqe->byte_16,
 					       V2_RC_SEND_WQE_BYTE_16_SGE_NUM_M,
 					       V2_RC_SEND_WQE_BYTE_16_SGE_NUM_S,
-					       wr->num_sge);
+					       valid_num_sge);
 			} else if (wr->opcode != IB_WR_REG_MR) {
 				ret = set_rwqe_data_seg(ibqp, wr, rc_sq_wqe,
-							wqe, &sge_ind, bad_wr);
+							wqe, &sge_idx,
+							valid_num_sge, bad_wr);
 				if (ret)
 					goto out;
 			}
-
-			ind++;
 		} else {
 			dev_err(dev, "Illegal qp_type(0x%x)\n", ibqp->qp_type);
 			spin_unlock_irqrestore(&qp->sq.lock, flags);
@@ -591,8 +596,7 @@ out:
 
 		hns_roce_write64(hr_dev, (__le32 *)&sq_db, qp->sq.db_reg_l);
 
-		qp->sq_next_wqe = ind;
-		qp->next_sge = sge_ind;
+		qp->next_sge = sge_idx;
 
 		if (qp->state == IB_QPS_ERR) {
 			attr_mask = IB_QP_STATE;
@@ -626,13 +630,12 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp,
 	unsigned long flags;
 	void *wqe = NULL;
 	int attr_mask;
+	u32 wqe_idx;
 	int ret = 0;
 	int nreq;
-	int ind;
 	int i;
 
 	spin_lock_irqsave(&hr_qp->rq.lock, flags);
-	ind = hr_qp->rq.head & (hr_qp->rq.wqe_cnt - 1);
 
 	if (hr_qp->state == IB_QPS_RESET) {
 		spin_unlock_irqrestore(&hr_qp->rq.lock, flags);
@@ -648,6 +651,8 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp,
 			goto out;
 		}
 
+		wqe_idx = (hr_qp->rq.head + nreq) & (hr_qp->rq.wqe_cnt - 1);
+
 		if (unlikely(wr->num_sge > hr_qp->rq.max_gs)) {
 			dev_err(dev, "rq:num_sge=%d > qp->sq.max_gs=%d\n",
 				wr->num_sge, hr_qp->rq.max_gs);
@@ -656,7 +661,7 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp,
 			goto out;
 		}
 
-		wqe = get_recv_wqe(hr_qp, ind);
+		wqe = get_recv_wqe(hr_qp, wqe_idx);
 		dseg = (struct hns_roce_v2_wqe_data_seg *)wqe;
 		for (i = 0; i < wr->num_sge; i++) {
 			if (!wr->sg_list[i].length)
@@ -672,8 +677,8 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp,
 
 		/* rq support inline data */
 		if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_RQ_INLINE) {
-			sge_list = hr_qp->rq_inl_buf.wqe_list[ind].sg_list;
-			hr_qp->rq_inl_buf.wqe_list[ind].sge_cnt =
+			sge_list = hr_qp->rq_inl_buf.wqe_list[wqe_idx].sg_list;
+			hr_qp->rq_inl_buf.wqe_list[wqe_idx].sge_cnt =
 							       (u32)wr->num_sge;
 			for (i = 0; i < wr->num_sge; i++) {
 				sge_list[i].addr =
@@ -682,9 +687,7 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp,
 			}
 		}
 
-		hr_qp->rq.wrid[ind] = wr->wr_id;
-
-		ind = (ind + 1) & (hr_qp->rq.wqe_cnt - 1);
+		hr_qp->rq.wrid[wqe_idx] = wr->wr_id;
 	}
 
 out:
@@ -1218,34 +1221,26 @@ static int hns_roce_query_pf_resource(struct hns_roce_dev *hr_dev)
 static int hns_roce_query_pf_timer_resource(struct hns_roce_dev *hr_dev)
 {
 	struct hns_roce_pf_timer_res_a *req_a;
-	struct hns_roce_cmq_desc desc[2];
-	int ret, i;
-
-	for (i = 0; i < 2; i++) {
-		hns_roce_cmq_setup_basic_desc(&desc[i],
-					      HNS_ROCE_OPC_QUERY_PF_TIMER_RES,
-					      true);
+	struct hns_roce_cmq_desc desc;
+	int ret;
 
-		if (i == 0)
-			desc[i].flag |= cpu_to_le16(HNS_ROCE_CMD_FLAG_NEXT);
-		else
-			desc[i].flag &= ~cpu_to_le16(HNS_ROCE_CMD_FLAG_NEXT);
-	}
+	hns_roce_cmq_setup_basic_desc(&desc, HNS_ROCE_OPC_QUERY_PF_TIMER_RES,
+				      true);
 
-	ret = hns_roce_cmq_send(hr_dev, desc, 2);
+	ret = hns_roce_cmq_send(hr_dev, &desc, 1);
 	if (ret)
 		return ret;
 
-	req_a = (struct hns_roce_pf_timer_res_a *)desc[0].data;
+	req_a = (struct hns_roce_pf_timer_res_a *)desc.data;
 
 	hr_dev->caps.qpc_timer_bt_num =
-				roce_get_field(req_a->qpc_timer_bt_idx_num,
-					PF_RES_DATA_1_PF_QPC_TIMER_BT_NUM_M,
-					PF_RES_DATA_1_PF_QPC_TIMER_BT_NUM_S);
+		roce_get_field(req_a->qpc_timer_bt_idx_num,
+			       PF_RES_DATA_1_PF_QPC_TIMER_BT_NUM_M,
+			       PF_RES_DATA_1_PF_QPC_TIMER_BT_NUM_S);
 	hr_dev->caps.cqc_timer_bt_num =
-				roce_get_field(req_a->cqc_timer_bt_idx_num,
-					PF_RES_DATA_2_PF_CQC_TIMER_BT_NUM_M,
-					PF_RES_DATA_2_PF_CQC_TIMER_BT_NUM_S);
+		roce_get_field(req_a->cqc_timer_bt_idx_num,
+			       PF_RES_DATA_2_PF_CQC_TIMER_BT_NUM_M,
+			       PF_RES_DATA_2_PF_CQC_TIMER_BT_NUM_S);
 
 	return 0;
 }
@@ -4260,7 +4255,6 @@ static int hns_roce_v2_modify_qp(struct ib_qp *ibqp,
 		hr_qp->rq.tail = 0;
 		hr_qp->sq.head = 0;
 		hr_qp->sq.tail = 0;
-		hr_qp->sq_next_wqe = 0;
 		hr_qp->next_sge = 0;
 		if (hr_qp->rq.wqe_cnt)
 			*hr_qp->rdb.db_record = 0;
@@ -4362,7 +4356,7 @@ static int hns_roce_v2_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr,
 	qp_attr->path_mig_state = IB_MIG_ARMED;
 	qp_attr->ah_attr.type   = RDMA_AH_ATTR_TYPE_ROCE;
 	if (hr_qp->ibqp.qp_type == IB_QPT_UD)
-		qp_attr->qkey = V2_QKEY_VAL;
+		qp_attr->qkey = le32_to_cpu(context->qkey_xrcd);
 
 	qp_attr->rq_psn = roce_get_field(context->byte_108_rx_reqepsn,
 					 V2_QPC_BYTE_108_RX_REQ_EPSN_M,
@@ -5860,11 +5854,11 @@ static void hns_roce_v2_write_srqc(struct hns_roce_dev *hr_dev,
 	roce_set_field(srq_context->byte_44_idxbufpgsz_addr,
 		       SRQC_BYTE_44_SRQ_IDX_BA_PG_SZ_M,
 		       SRQC_BYTE_44_SRQ_IDX_BA_PG_SZ_S,
-		       hr_dev->caps.idx_ba_pg_sz);
+		       hr_dev->caps.idx_ba_pg_sz + PG_SHIFT_OFFSET);
 	roce_set_field(srq_context->byte_44_idxbufpgsz_addr,
 		       SRQC_BYTE_44_SRQ_IDX_BUF_PG_SZ_M,
 		       SRQC_BYTE_44_SRQ_IDX_BUF_PG_SZ_S,
-		       hr_dev->caps.idx_buf_pg_sz);
+		       hr_dev->caps.idx_buf_pg_sz + PG_SHIFT_OFFSET);
 
 	srq_context->idx_nxt_blk_addr = (u32)(mtts_idx[1] >> PAGE_ADDR_SHIFT);
 	srq_context->idx_nxt_blk_addr =
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
index edfdbe2ce0db..4211a982a8e0 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
@@ -87,8 +87,8 @@
 #define HNS_ROCE_V2_MTT_ENTRY_SZ		64
 #define HNS_ROCE_V2_CQE_ENTRY_SIZE		32
 #define HNS_ROCE_V2_SCCC_ENTRY_SZ		32
-#define HNS_ROCE_V2_QPC_TIMER_ENTRY_SZ		4096
-#define HNS_ROCE_V2_CQC_TIMER_ENTRY_SZ		4096
+#define HNS_ROCE_V2_QPC_TIMER_ENTRY_SZ		PAGE_SIZE
+#define HNS_ROCE_V2_CQC_TIMER_ENTRY_SZ		PAGE_SIZE
 #define HNS_ROCE_V2_PAGE_SIZE_SUPPORTED		0xFFFFF000
 #define HNS_ROCE_V2_MAX_INNER_MTPT_NUM		2
 #define HNS_ROCE_INVALID_LKEY			0x100
diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c
index 6110ec408626..c68527f77418 100644
--- a/drivers/infiniband/hw/hns/hns_roce_mr.c
+++ b/drivers/infiniband/hw/hns/hns_roce_mr.c
@@ -1018,8 +1018,8 @@ int hns_roce_ib_umem_write_mtt(struct hns_roce_dev *hr_dev,
 		if (!(npage % (1 << (mtt->page_shift - PAGE_SHIFT)))) {
 			if (page_addr & ((1 << mtt->page_shift) - 1)) {
 				dev_err(dev,
-					"page_addr 0x%llx is not page_shift %d alignment!\n",
-					page_addr, mtt->page_shift);
+					"page_addr is not page_shift %d alignment!\n",
+					mtt->page_shift);
 				ret = -EINVAL;
 				goto out;
 			}
diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c
index 8233f5a4e623..47d7be972d34 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_cm.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c
@@ -1984,7 +1984,6 @@ static int i40iw_addr_resolve_neigh(struct i40iw_device *iwdev,
 	struct rtable *rt;
 	struct neighbour *neigh;
 	int rc = arpindex;
-	struct net_device *netdev = iwdev->netdev;
 	__be32 dst_ipaddr = htonl(dst_ip);
 	__be32 src_ipaddr = htonl(src_ip);
 
@@ -1994,9 +1993,6 @@ static int i40iw_addr_resolve_neigh(struct i40iw_device *iwdev,
 		return rc;
 	}
 
-	if (netif_is_bond_slave(netdev))
-		netdev = netdev_master_upper_dev_get(netdev);
-
 	neigh = dst_neigh_lookup(&rt->dst, &dst_ipaddr);
 
 	rcu_read_lock();
@@ -2062,7 +2058,6 @@ static int i40iw_addr_resolve_neigh_ipv6(struct i40iw_device *iwdev,
 {
 	struct neighbour *neigh;
 	int rc = arpindex;
-	struct net_device *netdev = iwdev->netdev;
 	struct dst_entry *dst;
 	struct sockaddr_in6 dst_addr;
 	struct sockaddr_in6 src_addr;
@@ -2083,9 +2078,6 @@ static int i40iw_addr_resolve_neigh_ipv6(struct i40iw_device *iwdev,
 		return rc;
 	}
 
-	if (netif_is_bond_slave(netdev))
-		netdev = netdev_master_upper_dev_get(netdev);
-
 	neigh = dst_neigh_lookup(dst, dst_addr.sin6_addr.in6_u.u6_addr32);
 
 	rcu_read_lock();
diff --git a/drivers/infiniband/hw/i40iw/i40iw_hw.c b/drivers/infiniband/hw/i40iw/i40iw_hw.c
index 55a1fbf0e670..ae8b97c30665 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_hw.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_hw.c
@@ -534,7 +534,7 @@ void i40iw_manage_arp_cache(struct i40iw_device *iwdev,
 	int arp_index;
 
 	arp_index = i40iw_arp_table(iwdev, ip_addr, ipv4, mac_addr, action);
-	if (arp_index == -1)
+	if (arp_index < 0)
 		return;
 	cqp_request = i40iw_get_cqp_request(&iwdev->cqp, false);
 	if (!cqp_request)
diff --git a/drivers/infiniband/hw/i40iw/i40iw_main.c b/drivers/infiniband/hw/i40iw/i40iw_main.c
index 10932baee279..7749d680017a 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_main.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_main.c
@@ -1223,6 +1223,8 @@ static void i40iw_add_ipv4_addr(struct i40iw_device *iwdev)
 		      (rdma_vlan_dev_real_dev(dev) == iwdev->netdev)) ||
 		    (dev == iwdev->netdev)) && (dev->flags & IFF_UP)) {
 			idev = in_dev_get(dev);
+			if (!idev)
+				continue;
 			for_ifa(idev) {
 				i40iw_debug(&iwdev->sc_dev, I40IW_DEBUG_CM,
 					    "IP=%pI4, vlan_id=%d, MAC=%pM\n", &ifa->ifa_address,
diff --git a/drivers/infiniband/hw/mlx4/cm.c b/drivers/infiniband/hw/mlx4/cm.c
index ecd6cadd529a..b591861934b3 100644
--- a/drivers/infiniband/hw/mlx4/cm.c
+++ b/drivers/infiniband/hw/mlx4/cm.c
@@ -186,23 +186,6 @@ out:
 	kfree(ent);
 }
 
-static void id_map_find_del(struct ib_device *ibdev, int pv_cm_id)
-{
-	struct mlx4_ib_sriov *sriov = &to_mdev(ibdev)->sriov;
-	struct rb_root *sl_id_map = &sriov->sl_id_map;
-	struct id_map_entry *ent, *found_ent;
-
-	spin_lock(&sriov->id_map_lock);
-	ent = xa_erase(&sriov->pv_id_table, pv_cm_id);
-	if (!ent)
-		goto out;
-	found_ent = id_map_find_by_sl_id(ibdev, ent->slave_id, ent->sl_cm_id);
-	if (found_ent && found_ent == ent)
-		rb_erase(&found_ent->node, sl_id_map);
-out:
-	spin_unlock(&sriov->id_map_lock);
-}
-
 static void sl_id_map_add(struct ib_device *ibdev, struct id_map_entry *new)
 {
 	struct rb_root *sl_id_map = &to_mdev(ibdev)->sriov.sl_id_map;
@@ -294,7 +277,7 @@ static void schedule_delayed(struct ib_device *ibdev, struct id_map_entry *id)
 	spin_lock(&sriov->id_map_lock);
 	spin_lock_irqsave(&sriov->going_down_lock, flags);
 	/*make sure that there is no schedule inside the scheduled work.*/
-	if (!sriov->is_going_down) {
+	if (!sriov->is_going_down && !id->scheduled_delete) {
 		id->scheduled_delete = 1;
 		schedule_delayed_work(&id->timeout, CM_CLEANUP_CACHE_TIMEOUT);
 	}
@@ -341,9 +324,6 @@ cont:
 
 	if (mad->mad_hdr.attr_id == CM_DREQ_ATTR_ID)
 		schedule_delayed(ibdev, id);
-	else if (mad->mad_hdr.attr_id == CM_DREP_ATTR_ID)
-		id_map_find_del(ibdev, pv_cm_id);
-
 	return 0;
 }
 
@@ -382,12 +362,9 @@ int mlx4_ib_demux_cm_handler(struct ib_device *ibdev, int port, int *slave,
 		*slave = id->slave_id;
 	set_remote_comm_id(mad, id->sl_cm_id);
 
-	if (mad->mad_hdr.attr_id == CM_DREQ_ATTR_ID)
+	if (mad->mad_hdr.attr_id == CM_DREQ_ATTR_ID ||
+	    mad->mad_hdr.attr_id == CM_REJ_ATTR_ID)
 		schedule_delayed(ibdev, id);
-	else if (mad->mad_hdr.attr_id == CM_REJ_ATTR_ID ||
-			mad->mad_hdr.attr_id == CM_DREP_ATTR_ID) {
-		id_map_find_del(ibdev, (int) pv_cm_id);
-	}
 
 	return 0;
 }
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 25d09d53b51c..4aa439a7ce61 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -246,6 +246,13 @@ static int mlx4_ib_update_gids(struct gid_entry *gids,
 	return mlx4_ib_update_gids_v1(gids, ibdev, port_num);
 }
 
+static void free_gid_entry(struct gid_entry *entry)
+{
+	memset(&entry->gid, 0, sizeof(entry->gid));
+	kfree(entry->ctx);
+	entry->ctx = NULL;
+}
+
 static int mlx4_ib_add_gid(const struct ib_gid_attr *attr, void **context)
 {
 	struct mlx4_ib_dev *ibdev = to_mdev(attr->device);
@@ -306,6 +313,8 @@ static int mlx4_ib_add_gid(const struct ib_gid_attr *attr, void **context)
 				     GFP_ATOMIC);
 		if (!gids) {
 			ret = -ENOMEM;
+			*context = NULL;
+			free_gid_entry(&port_gid_table->gids[free]);
 		} else {
 			for (i = 0; i < MLX4_MAX_PORT_GIDS; i++) {
 				memcpy(&gids[i].gid, &port_gid_table->gids[i].gid, sizeof(union ib_gid));
@@ -317,6 +326,12 @@ static int mlx4_ib_add_gid(const struct ib_gid_attr *attr, void **context)
 
 	if (!ret && hw_update) {
 		ret = mlx4_ib_update_gids(gids, ibdev, attr->port_num);
+		if (ret) {
+			spin_lock_bh(&iboe->lock);
+			*context = NULL;
+			free_gid_entry(&port_gid_table->gids[free]);
+			spin_unlock_bh(&iboe->lock);
+		}
 		kfree(gids);
 	}
 
@@ -346,10 +361,7 @@ static int mlx4_ib_del_gid(const struct ib_gid_attr *attr, void **context)
 		if (!ctx->refcount) {
 			unsigned int real_index = ctx->real_index;
 
-			memset(&port_gid_table->gids[real_index].gid, 0,
-			       sizeof(port_gid_table->gids[real_index].gid));
-			kfree(port_gid_table->gids[real_index].ctx);
-			port_gid_table->gids[real_index].ctx = NULL;
+			free_gid_entry(&port_gid_table->gids[real_index]);
 			hw_update = 1;
 		}
 	}
@@ -768,7 +780,8 @@ static int eth_link_query_port(struct ib_device *ibdev, u8 port,
 	props->ip_gids = true;
 	props->gid_tbl_len	= mdev->dev->caps.gid_table_len[port];
 	props->max_msg_sz	= mdev->dev->caps.max_msg_sz;
-	props->pkey_tbl_len	= 1;
+	if (mdev->dev->caps.pkey_table_len[port])
+		props->pkey_tbl_len = 1;
 	props->max_mtu		= IB_MTU_4096;
 	props->max_vl_num	= 2;
 	props->state		= IB_PORT_DOWN;
@@ -1478,8 +1491,9 @@ static int __mlx4_ib_create_default_rules(
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(pdefault_rules->rules_create_list); i++) {
+		union ib_flow_spec ib_spec = {};
 		int ret;
-		union ib_flow_spec ib_spec;
+
 		switch (pdefault_rules->rules_create_list[i]) {
 		case 0:
 			/* no rule */
@@ -3004,16 +3018,17 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr)
 	ibdev->ib_active = false;
 	flush_workqueue(wq);
 
-	mlx4_ib_close_sriov(ibdev);
-	mlx4_ib_mad_cleanup(ibdev);
-	ib_unregister_device(&ibdev->ib_dev);
-	mlx4_ib_diag_cleanup(ibdev);
 	if (ibdev->iboe.nb.notifier_call) {
 		if (unregister_netdevice_notifier(&ibdev->iboe.nb))
 			pr_warn("failure unregistering notifier\n");
 		ibdev->iboe.nb.notifier_call = NULL;
 	}
 
+	mlx4_ib_close_sriov(ibdev);
+	mlx4_ib_mad_cleanup(ibdev);
+	ib_unregister_device(&ibdev->ib_dev);
+	mlx4_ib_diag_cleanup(ibdev);
+
 	mlx4_qp_release_range(dev, ibdev->steer_qpn_base,
 			      ibdev->steer_qpn_count);
 	kfree(ibdev->ib_uc_qpns_bitmap);
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index 355205a28544..6fd661076ade 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -440,7 +440,6 @@ struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 
 	mr->ibmr.rkey = mr->ibmr.lkey = mr->mmr.key;
 	mr->ibmr.length = length;
-	mr->ibmr.iova = virt_addr;
 	mr->ibmr.page_size = 1U << shift;
 
 	return &mr->ibmr;
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 5221c0794d1d..89c2038f50da 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -2817,6 +2817,7 @@ static int build_sriov_qp0_header(struct mlx4_ib_sqp *sqp,
 	int send_size;
 	int header_size;
 	int spc;
+	int err;
 	int i;
 
 	if (wr->wr.opcode != IB_WR_SEND)
@@ -2851,7 +2852,9 @@ static int build_sriov_qp0_header(struct mlx4_ib_sqp *sqp,
 
 	sqp->ud_header.lrh.virtual_lane    = 0;
 	sqp->ud_header.bth.solicited_event = !!(wr->wr.send_flags & IB_SEND_SOLICITED);
-	ib_get_cached_pkey(ib_dev, sqp->qp.port, 0, &pkey);
+	err = ib_get_cached_pkey(ib_dev, sqp->qp.port, 0, &pkey);
+	if (err)
+		return err;
 	sqp->ud_header.bth.pkey = cpu_to_be16(pkey);
 	if (sqp->qp.mlx4_ib_qp_type == MLX4_IB_QPT_TUN_SMI_OWNER)
 		sqp->ud_header.bth.destination_qpn = cpu_to_be32(wr->remote_qpn);
@@ -3138,9 +3141,14 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, const struct ib_ud_wr *wr,
 	}
 	sqp->ud_header.bth.solicited_event = !!(wr->wr.send_flags & IB_SEND_SOLICITED);
 	if (!sqp->qp.ibqp.qp_num)
-		ib_get_cached_pkey(ib_dev, sqp->qp.port, sqp->pkey_index, &pkey);
+		err = ib_get_cached_pkey(ib_dev, sqp->qp.port, sqp->pkey_index,
+					 &pkey);
 	else
-		ib_get_cached_pkey(ib_dev, sqp->qp.port, wr->pkey_index, &pkey);
+		err = ib_get_cached_pkey(ib_dev, sqp->qp.port, wr->pkey_index,
+					 &pkey);
+	if (err)
+		return err;
+
 	sqp->ud_header.bth.pkey = cpu_to_be16(pkey);
 	sqp->ud_header.bth.destination_qpn = cpu_to_be32(wr->remote_qpn);
 	sqp->ud_header.bth.psn = cpu_to_be32((sqp->send_psn++) & ((1 << 24) - 1));
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 2e2e65f00257..347a563736e3 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -330,6 +330,22 @@ static void mlx5_handle_error_cqe(struct mlx5_ib_dev *dev,
 		dump_cqe(dev, cqe);
 }
 
+static void handle_atomics(struct mlx5_ib_qp *qp, struct mlx5_cqe64 *cqe64,
+			   u16 tail, u16 head)
+{
+	u16 idx;
+
+	do {
+		idx = tail & (qp->sq.wqe_cnt - 1);
+		if (idx == head)
+			break;
+
+		tail = qp->sq.w_list[idx].next;
+	} while (1);
+	tail = qp->sq.w_list[idx].next;
+	qp->sq.last_poll = tail;
+}
+
 static void free_cq_buf(struct mlx5_ib_dev *dev, struct mlx5_ib_cq_buf *buf)
 {
 	mlx5_frag_buf_free(dev->mdev, &buf->frag_buf);
@@ -368,7 +384,7 @@ static void get_sig_err_item(struct mlx5_sig_err_cqe *cqe,
 }
 
 static void sw_comp(struct mlx5_ib_qp *qp, int num_entries, struct ib_wc *wc,
-		    int *npolled, int is_send)
+		    int *npolled, bool is_send)
 {
 	struct mlx5_ib_wq *wq;
 	unsigned int cur;
@@ -383,10 +399,16 @@ static void sw_comp(struct mlx5_ib_qp *qp, int num_entries, struct ib_wc *wc,
 		return;
 
 	for (i = 0;  i < cur && np < num_entries; i++) {
-		wc->wr_id = wq->wrid[wq->tail & (wq->wqe_cnt - 1)];
+		unsigned int idx;
+
+		idx = (is_send) ? wq->last_poll : wq->tail;
+		idx &= (wq->wqe_cnt - 1);
+		wc->wr_id = wq->wrid[idx];
 		wc->status = IB_WC_WR_FLUSH_ERR;
 		wc->vendor_err = MLX5_CQE_SYNDROME_WR_FLUSH_ERR;
 		wq->tail++;
+		if (is_send)
+			wq->last_poll = wq->w_list[idx].next;
 		np++;
 		wc->qp = &qp->ibqp;
 		wc++;
@@ -476,6 +498,7 @@ repoll:
 		wqe_ctr = be16_to_cpu(cqe64->wqe_counter);
 		idx = wqe_ctr & (wq->wqe_cnt - 1);
 		handle_good_req(wc, cqe64, wq, idx);
+		handle_atomics(*cur_qp, cqe64, wq->last_poll, idx);
 		wc->wr_id = wq->wrid[idx];
 		wq->tail = wq->wqe_head[idx] + 1;
 		wc->status = IB_WC_SUCCESS;
diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index 80b42d069328..4c1f4fe5eb02 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -306,6 +306,10 @@ static u64 devx_get_obj_id(const void *in)
 		obj_id = get_enc_obj_id(MLX5_CMD_OP_CREATE_QP,
 					MLX5_GET(rst2init_qp_in, in, qpn));
 		break;
+	case MLX5_CMD_OP_INIT2INIT_QP:
+		obj_id = get_enc_obj_id(MLX5_CMD_OP_CREATE_QP,
+					MLX5_GET(init2init_qp_in, in, qpn));
+		break;
 	case MLX5_CMD_OP_INIT2RTR_QP:
 		obj_id = get_enc_obj_id(MLX5_CMD_OP_CREATE_QP,
 					MLX5_GET(init2rtr_qp_in, in, qpn));
@@ -621,6 +625,7 @@ static bool devx_is_obj_modify_cmd(const void *in)
 	case MLX5_CMD_OP_SET_L2_TABLE_ENTRY:
 	case MLX5_CMD_OP_RST2INIT_QP:
 	case MLX5_CMD_OP_INIT2RTR_QP:
+	case MLX5_CMD_OP_INIT2INIT_QP:
 	case MLX5_CMD_OP_RTR2RTS_QP:
 	case MLX5_CMD_OP_RTS2RTS_QP:
 	case MLX5_CMD_OP_SQERR2RTS_QP:
diff --git a/drivers/infiniband/hw/mlx5/gsi.c b/drivers/infiniband/hw/mlx5/gsi.c
index 4950df3f71b6..5c73c0a790fa 100644
--- a/drivers/infiniband/hw/mlx5/gsi.c
+++ b/drivers/infiniband/hw/mlx5/gsi.c
@@ -507,8 +507,7 @@ int mlx5_ib_gsi_post_send(struct ib_qp *qp, const struct ib_send_wr *wr,
 		ret = ib_post_send(tx_qp, &cur_wr.wr, bad_wr);
 		if (ret) {
 			/* Undo the effect of adding the outstanding wr */
-			gsi->outstanding_pi = (gsi->outstanding_pi - 1) %
-					      gsi->cap.max_send_wr;
+			gsi->outstanding_pi--;
 			goto err;
 		}
 		spin_unlock_irqrestore(&gsi->lock, flags);
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index ff6a2b1fa8b6..660310d54ff6 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -516,7 +516,7 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
 					   mdev_port_num);
 	if (err)
 		goto out;
-	ext = MLX5_CAP_PCAM_FEATURE(dev->mdev, ptys_extended_ethernet);
+	ext = !!MLX5_GET_ETH_PROTO(ptys_reg, out, true, eth_proto_capability);
 	eth_prot_oper = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, eth_proto_oper);
 
 	props->active_width     = IB_WIDTH_4X;
@@ -828,6 +828,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 				struct ib_device_attr *props,
 				struct ib_udata *uhw)
 {
+	size_t uhw_outlen = (uhw) ? uhw->outlen : 0;
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
 	struct mlx5_core_dev *mdev = dev->mdev;
 	int err = -ENOMEM;
@@ -841,12 +842,12 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 	u64 max_tso;
 
 	resp_len = sizeof(resp.comp_mask) + sizeof(resp.response_length);
-	if (uhw->outlen && uhw->outlen < resp_len)
+	if (uhw_outlen && uhw_outlen < resp_len)
 		return -EINVAL;
 	else
 		resp.response_length = resp_len;
 
-	if (uhw->inlen && !ib_is_udata_cleared(uhw, 0, uhw->inlen))
+	if (uhw && uhw->inlen && !ib_is_udata_cleared(uhw, 0, uhw->inlen))
 		return -EINVAL;
 
 	memset(props, 0, sizeof(*props));
@@ -910,7 +911,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 			props->raw_packet_caps |=
 				IB_RAW_PACKET_CAP_CVLAN_STRIPPING;
 
-		if (field_avail(typeof(resp), tso_caps, uhw->outlen)) {
+		if (field_avail(typeof(resp), tso_caps, uhw_outlen)) {
 			max_tso = MLX5_CAP_ETH(mdev, max_lso_cap);
 			if (max_tso) {
 				resp.tso_caps.max_tso = 1 << max_tso;
@@ -920,7 +921,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 			}
 		}
 
-		if (field_avail(typeof(resp), rss_caps, uhw->outlen)) {
+		if (field_avail(typeof(resp), rss_caps, uhw_outlen)) {
 			resp.rss_caps.rx_hash_function =
 						MLX5_RX_HASH_FUNC_TOEPLITZ;
 			resp.rss_caps.rx_hash_fields_mask =
@@ -940,9 +941,9 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 			resp.response_length += sizeof(resp.rss_caps);
 		}
 	} else {
-		if (field_avail(typeof(resp), tso_caps, uhw->outlen))
+		if (field_avail(typeof(resp), tso_caps, uhw_outlen))
 			resp.response_length += sizeof(resp.tso_caps);
-		if (field_avail(typeof(resp), rss_caps, uhw->outlen))
+		if (field_avail(typeof(resp), rss_caps, uhw_outlen))
 			resp.response_length += sizeof(resp.rss_caps);
 	}
 
@@ -1063,7 +1064,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 						MLX5_MAX_CQ_PERIOD;
 	}
 
-	if (field_avail(typeof(resp), cqe_comp_caps, uhw->outlen)) {
+	if (field_avail(typeof(resp), cqe_comp_caps, uhw_outlen)) {
 		resp.response_length += sizeof(resp.cqe_comp_caps);
 
 		if (MLX5_CAP_GEN(dev->mdev, cqe_compression)) {
@@ -1081,7 +1082,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		}
 	}
 
-	if (field_avail(typeof(resp), packet_pacing_caps, uhw->outlen) &&
+	if (field_avail(typeof(resp), packet_pacing_caps, uhw_outlen) &&
 	    raw_support) {
 		if (MLX5_CAP_QOS(mdev, packet_pacing) &&
 		    MLX5_CAP_GEN(mdev, qos)) {
@@ -1100,7 +1101,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 	}
 
 	if (field_avail(typeof(resp), mlx5_ib_support_multi_pkt_send_wqes,
-			uhw->outlen)) {
+			uhw_outlen)) {
 		if (MLX5_CAP_ETH(mdev, multi_pkt_send_wqe))
 			resp.mlx5_ib_support_multi_pkt_send_wqes =
 				MLX5_IB_ALLOW_MPW;
@@ -1113,7 +1114,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 			sizeof(resp.mlx5_ib_support_multi_pkt_send_wqes);
 	}
 
-	if (field_avail(typeof(resp), flags, uhw->outlen)) {
+	if (field_avail(typeof(resp), flags, uhw_outlen)) {
 		resp.response_length += sizeof(resp.flags);
 
 		if (MLX5_CAP_GEN(mdev, cqe_compression_128))
@@ -1129,8 +1130,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		resp.flags |= MLX5_IB_QUERY_DEV_RESP_FLAGS_SCAT2CQE_DCT;
 	}
 
-	if (field_avail(typeof(resp), sw_parsing_caps,
-			uhw->outlen)) {
+	if (field_avail(typeof(resp), sw_parsing_caps, uhw_outlen)) {
 		resp.response_length += sizeof(resp.sw_parsing_caps);
 		if (MLX5_CAP_ETH(mdev, swp)) {
 			resp.sw_parsing_caps.sw_parsing_offloads |=
@@ -1150,7 +1150,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		}
 	}
 
-	if (field_avail(typeof(resp), striding_rq_caps, uhw->outlen) &&
+	if (field_avail(typeof(resp), striding_rq_caps, uhw_outlen) &&
 	    raw_support) {
 		resp.response_length += sizeof(resp.striding_rq_caps);
 		if (MLX5_CAP_GEN(mdev, striding_rq)) {
@@ -1167,8 +1167,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		}
 	}
 
-	if (field_avail(typeof(resp), tunnel_offloads_caps,
-			uhw->outlen)) {
+	if (field_avail(typeof(resp), tunnel_offloads_caps, uhw_outlen)) {
 		resp.response_length += sizeof(resp.tunnel_offloads_caps);
 		if (MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan))
 			resp.tunnel_offloads_caps |=
@@ -1179,17 +1178,15 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		if (MLX5_CAP_ETH(mdev, tunnel_stateless_gre))
 			resp.tunnel_offloads_caps |=
 				MLX5_IB_TUNNELED_OFFLOADS_GRE;
-		if (MLX5_CAP_GEN(mdev, flex_parser_protocols) &
-		    MLX5_FLEX_PROTO_CW_MPLS_GRE)
+		if (MLX5_CAP_ETH(mdev, tunnel_stateless_mpls_over_gre))
 			resp.tunnel_offloads_caps |=
 				MLX5_IB_TUNNELED_OFFLOADS_MPLS_GRE;
-		if (MLX5_CAP_GEN(mdev, flex_parser_protocols) &
-		    MLX5_FLEX_PROTO_CW_MPLS_UDP)
+		if (MLX5_CAP_ETH(mdev, tunnel_stateless_mpls_over_udp))
 			resp.tunnel_offloads_caps |=
 				MLX5_IB_TUNNELED_OFFLOADS_MPLS_UDP;
 	}
 
-	if (uhw->outlen) {
+	if (uhw_outlen) {
 		err = ib_copy_to_udata(uhw, &resp, resp.response_length);
 
 		if (err)
@@ -3502,10 +3499,6 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
 	}
 
 	INIT_LIST_HEAD(&handler->list);
-	if (dst) {
-		memcpy(&dest_arr[0], dst, sizeof(*dst));
-		dest_num++;
-	}
 
 	for (spec_index = 0; spec_index < flow_attr->num_of_specs; spec_index++) {
 		err = parse_flow_attr(dev->mdev, spec->match_criteria,
@@ -3519,6 +3512,11 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
 		ib_flow += ((union ib_flow_spec *)ib_flow)->size;
 	}
 
+	if (dst && !(flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DROP)) {
+		memcpy(&dest_arr[0], dst, sizeof(*dst));
+		dest_num++;
+	}
+
 	if (!flow_is_multicast_only(flow_attr))
 		set_underlay_qp(dev, spec, underlay_qpn);
 
@@ -3563,10 +3561,8 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
 	}
 
 	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DROP) {
-		if (!(flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT)) {
+		if (!dest_num)
 			rule_dst = NULL;
-			dest_num = 0;
-		}
 	} else {
 		if (is_egress)
 			flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_ALLOW;
@@ -4678,7 +4674,6 @@ static int __get_port_caps(struct mlx5_ib_dev *dev, u8 port)
 	struct ib_device_attr *dprops = NULL;
 	struct ib_port_attr *pprops = NULL;
 	int err = -ENOMEM;
-	struct ib_udata uhw = {.inlen = 0, .outlen = 0};
 
 	pprops = kmalloc(sizeof(*pprops), GFP_KERNEL);
 	if (!pprops)
@@ -4688,7 +4683,7 @@ static int __get_port_caps(struct mlx5_ib_dev *dev, u8 port)
 	if (!dprops)
 		goto out;
 
-	err = mlx5_ib_query_device(&dev->ib_dev, dprops, &uhw);
+	err = mlx5_ib_query_device(&dev->ib_dev, dprops, NULL);
 	if (err) {
 		mlx5_ib_warn(dev, "query_device failed %d\n", err);
 		goto out;
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index f52b845f2f7b..3b11ed0d95ad 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -282,6 +282,7 @@ struct mlx5_ib_wq {
 	unsigned		head;
 	unsigned		tail;
 	u16			cur_post;
+	u16			last_poll;
 	void			*cur_edge;
 };
 
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 1bbcd80c0ca5..eaab3e5b785b 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -454,7 +454,7 @@ struct mlx5_ib_mr *mlx5_mr_cache_alloc(struct mlx5_ib_dev *dev, int entry)
 
 	if (entry < 0 || entry >= MAX_MR_CACHE_ENTRIES) {
 		mlx5_ib_err(dev, "cache entry %d is out of range\n", entry);
-		return NULL;
+		return ERR_PTR(-EINVAL);
 	}
 
 	ent = &cache->ent[entry];
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index fda3dfd6f87b..e0ecb540c67e 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -1205,7 +1205,7 @@ static void mlx5_ib_mr_wqe_pfault_handler(struct mlx5_ib_dev *dev,
 {
 	bool sq = pfault->type & MLX5_PFAULT_REQUESTOR;
 	u16 wqe_index = pfault->wqe.wqe_index;
-	void *wqe = NULL, *wqe_end = NULL;
+	void *wqe, *wqe_start = NULL, *wqe_end = NULL;
 	u32 bytes_mapped, total_wqe_bytes;
 	struct mlx5_core_rsc_common *res;
 	int resume_with_error = 1;
@@ -1226,12 +1226,13 @@ static void mlx5_ib_mr_wqe_pfault_handler(struct mlx5_ib_dev *dev,
 		goto resolve_page_fault;
 	}
 
-	wqe = (void *)__get_free_page(GFP_KERNEL);
-	if (!wqe) {
+	wqe_start = (void *)__get_free_page(GFP_KERNEL);
+	if (!wqe_start) {
 		mlx5_ib_err(dev, "Error allocating memory for IO page fault handling.\n");
 		goto resolve_page_fault;
 	}
 
+	wqe = wqe_start;
 	qp = (res->res == MLX5_RES_QP) ? res_to_qp(res) : NULL;
 	if (qp && sq) {
 		ret = mlx5_ib_read_user_wqe_sq(qp, wqe_index, wqe, PAGE_SIZE,
@@ -1286,7 +1287,7 @@ resolve_page_fault:
 		    pfault->wqe.wq_num, resume_with_error,
 		    pfault->type);
 	mlx5_core_res_put(res);
-	free_page((unsigned long)wqe);
+	free_page((unsigned long)wqe_start);
 }
 
 static int pages_in_range(u64 address, u32 length)
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 62e70c4b3ed0..b19e580939ac 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -1468,6 +1468,8 @@ static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	u16 uid = to_mpd(pd)->uid;
 	u32 out[MLX5_ST_SZ_DW(create_tir_out)] = {};
 
+	if (!qp->sq.wqe_cnt && !qp->rq.wqe_cnt)
+		return -EINVAL;
 	if (qp->sq.wqe_cnt) {
 		err = create_raw_packet_qp_tis(dev, qp, sq, tdn, pd);
 		if (err)
@@ -3704,6 +3706,7 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 		qp->sq.cur_post = 0;
 		if (qp->sq.wqe_cnt)
 			qp->sq.cur_edge = get_sq_edge(&qp->sq, 0);
+		qp->sq.last_poll = 0;
 		qp->db.db[MLX5_RCV_DBR] = 0;
 		qp->db.db[MLX5_SND_DBR] = 0;
 	}
@@ -5374,7 +5377,9 @@ static void to_rdma_ah_attr(struct mlx5_ib_dev *ibdev,
 	rdma_ah_set_path_bits(ah_attr, path->grh_mlid & 0x7f);
 	rdma_ah_set_static_rate(ah_attr,
 				path->static_rate ? path->static_rate - 5 : 0);
-	if (path->grh_mlid & (1 << 7)) {
+
+	if (path->grh_mlid & (1 << 7) ||
+	    ah_attr->type == RDMA_AH_ATTR_TYPE_ROCE) {
 		u32 tc_fl = be32_to_cpu(path->tclass_flowlabel);
 
 		rdma_ah_set_grh(ah_attr, NULL,
@@ -6010,6 +6015,10 @@ struct ib_wq *mlx5_ib_create_wq(struct ib_pd *pd,
 	if (udata->outlen && udata->outlen < min_resp_len)
 		return ERR_PTR(-EINVAL);
 
+	if (!capable(CAP_SYS_RAWIO) &&
+	    init_attr->create_flags & IB_WQ_FLAGS_DELAY_DROP)
+		return ERR_PTR(-EPERM);
+
 	dev = to_mdev(pd->device);
 	switch (init_attr->wq_type) {
 	case IB_WQT_RQ:
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index 4e7fde86c96b..c29c1f7da4a1 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -310,12 +310,18 @@ int mlx5_ib_create_srq(struct ib_srq *ib_srq,
 	srq->msrq.event = mlx5_ib_srq_event;
 	srq->ibsrq.ext.xrc.srq_num = srq->msrq.srqn;
 
-	if (udata)
-		if (ib_copy_to_udata(udata, &srq->msrq.srqn, sizeof(__u32))) {
+	if (udata) {
+		struct mlx5_ib_create_srq_resp resp = {
+			.srqn = srq->msrq.srqn,
+		};
+
+		if (ib_copy_to_udata(udata, &resp, min(udata->outlen,
+				     sizeof(resp)))) {
 			mlx5_ib_dbg(dev, "copy to user failed\n");
 			err = -EFAULT;
 			goto err_core;
 		}
+	}
 
 	init_attr->attr.max_wr = srq->msrq.max - 1;
 
diff --git a/drivers/infiniband/hw/mlx5/srq_cmd.c b/drivers/infiniband/hw/mlx5/srq_cmd.c
index b0d0687c7a68..2e8fa8767fd7 100644
--- a/drivers/infiniband/hw/mlx5/srq_cmd.c
+++ b/drivers/infiniband/hw/mlx5/srq_cmd.c
@@ -83,11 +83,11 @@ struct mlx5_core_srq *mlx5_cmd_get_srq(struct mlx5_ib_dev *dev, u32 srqn)
 	struct mlx5_srq_table *table = &dev->srq_table;
 	struct mlx5_core_srq *srq;
 
-	xa_lock(&table->array);
+	xa_lock_irq(&table->array);
 	srq = xa_load(&table->array, srqn);
 	if (srq)
 		atomic_inc(&srq->common.refcount);
-	xa_unlock(&table->array);
+	xa_unlock_irq(&table->array);
 
 	return srq;
 }
diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c
index 51173d9046a8..a37fb659c54e 100644
--- a/drivers/infiniband/hw/qedr/main.c
+++ b/drivers/infiniband/hw/qedr/main.c
@@ -357,7 +357,7 @@ static int qedr_alloc_resources(struct qedr_dev *dev)
 	xa_init_flags(&dev->srqs, XA_FLAGS_LOCK_IRQ);
 
 	if (IS_IWARP(dev)) {
-		xa_init_flags(&dev->qps, XA_FLAGS_LOCK_IRQ);
+		xa_init(&dev->qps);
 		dev->iwarp_wq = create_singlethread_workqueue("qedr_iwarpq");
 	}
 
diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h
index 6175d1e98717..bbf72944b720 100644
--- a/drivers/infiniband/hw/qedr/qedr.h
+++ b/drivers/infiniband/hw/qedr/qedr.h
@@ -40,6 +40,7 @@
 #include <linux/qed/qed_rdma_if.h>
 #include <linux/qed/qede_rdma.h>
 #include <linux/qed/roce_common.h>
+#include <linux/completion.h>
 #include "qedr_hsi_rdma.h"
 
 #define QEDR_NODE_DESC "QLogic 579xx RoCE HCA"
@@ -346,10 +347,10 @@ struct qedr_srq_hwq_info {
 	u32 wqe_prod;
 	u32 sge_prod;
 	u32 wr_prod_cnt;
-	u32 wr_cons_cnt;
+	atomic_t wr_cons_cnt;
 	u32 num_elems;
 
-	u32 *virt_prod_pair_addr;
+	struct rdma_srq_producers *virt_prod_pair_addr;
 	dma_addr_t phy_prod_pair_addr;
 };
 
@@ -375,10 +376,20 @@ enum qedr_qp_err_bitmap {
 	QEDR_QP_ERR_RQ_PBL_FULL = 32,
 };
 
+enum qedr_qp_create_type {
+	QEDR_QP_CREATE_NONE,
+	QEDR_QP_CREATE_USER,
+	QEDR_QP_CREATE_KERNEL,
+};
+
+enum qedr_iwarp_cm_flags {
+	QEDR_IWARP_CM_WAIT_FOR_CONNECT    = BIT(0),
+	QEDR_IWARP_CM_WAIT_FOR_DISCONNECT = BIT(1),
+};
+
 struct qedr_qp {
 	struct ib_qp ibqp;	/* must be first */
 	struct qedr_dev *dev;
-	struct qedr_iw_ep *ep;
 	struct qedr_qp_hwq_info sq;
 	struct qedr_qp_hwq_info rq;
 
@@ -393,6 +404,7 @@ struct qedr_qp {
 	u32 id;
 	struct qedr_pd *pd;
 	enum ib_qp_type qp_type;
+	enum qedr_qp_create_type create_type;
 	struct qed_rdma_qp *qed_qp;
 	u32 qp_id;
 	u16 icid;
@@ -435,8 +447,11 @@ struct qedr_qp {
 	/* Relevant to qps created from user space only (applications) */
 	struct qedr_userq usq;
 	struct qedr_userq urq;
-	atomic_t refcnt;
-	bool destroyed;
+
+	/* synchronization objects used with iwarp ep */
+	struct kref refcnt;
+	struct completion iwarp_cm_comp;
+	unsigned long iwarp_cm_flags; /* enum iwarp_cm_flags */
 };
 
 struct qedr_ah {
@@ -529,7 +544,7 @@ struct qedr_iw_ep {
 	struct iw_cm_id	*cm_id;
 	struct qedr_qp	*qp;
 	void		*qed_context;
-	u8		during_connect;
+	struct kref	refcnt;
 };
 
 static inline
diff --git a/drivers/infiniband/hw/qedr/qedr_iw_cm.c b/drivers/infiniband/hw/qedr/qedr_iw_cm.c
index 22881d4442b9..180f26794f28 100644
--- a/drivers/infiniband/hw/qedr/qedr_iw_cm.c
+++ b/drivers/infiniband/hw/qedr/qedr_iw_cm.c
@@ -79,6 +79,27 @@ qedr_fill_sockaddr6(const struct qed_iwarp_cm_info *cm_info,
 	}
 }
 
+static void qedr_iw_free_qp(struct kref *ref)
+{
+	struct qedr_qp *qp = container_of(ref, struct qedr_qp, refcnt);
+
+	kfree(qp);
+}
+
+static void
+qedr_iw_free_ep(struct kref *ref)
+{
+	struct qedr_iw_ep *ep = container_of(ref, struct qedr_iw_ep, refcnt);
+
+	if (ep->qp)
+		kref_put(&ep->qp->refcnt, qedr_iw_free_qp);
+
+	if (ep->cm_id)
+		ep->cm_id->rem_ref(ep->cm_id);
+
+	kfree(ep);
+}
+
 static void
 qedr_iw_mpa_request(void *context, struct qed_iwarp_cm_event_params *params)
 {
@@ -93,6 +114,7 @@ qedr_iw_mpa_request(void *context, struct qed_iwarp_cm_event_params *params)
 
 	ep->dev = dev;
 	ep->qed_context = params->ep_context;
+	kref_init(&ep->refcnt);
 
 	memset(&event, 0, sizeof(event));
 	event.event = IW_CM_EVENT_CONNECT_REQUEST;
@@ -128,8 +150,17 @@ qedr_iw_issue_event(void *context,
 	if (params->cm_info) {
 		event.ird = params->cm_info->ird;
 		event.ord = params->cm_info->ord;
-		event.private_data_len = params->cm_info->private_data_len;
-		event.private_data = (void *)params->cm_info->private_data;
+		/* Only connect_request and reply have valid private data
+		 * the rest of the events this may be left overs from
+		 * connection establishment. CONNECT_REQUEST is issued via
+		 * qedr_iw_mpa_request
+		 */
+		if (event_type == IW_CM_EVENT_CONNECT_REPLY) {
+			event.private_data_len =
+				params->cm_info->private_data_len;
+			event.private_data =
+				(void *)params->cm_info->private_data;
+		}
 	}
 
 	if (ep->cm_id)
@@ -141,12 +172,10 @@ qedr_iw_close_event(void *context, struct qed_iwarp_cm_event_params *params)
 {
 	struct qedr_iw_ep *ep = (struct qedr_iw_ep *)context;
 
-	if (ep->cm_id) {
+	if (ep->cm_id)
 		qedr_iw_issue_event(context, params, IW_CM_EVENT_CLOSE);
 
-		ep->cm_id->rem_ref(ep->cm_id);
-		ep->cm_id = NULL;
-	}
+	kref_put(&ep->refcnt, qedr_iw_free_ep);
 }
 
 static void
@@ -186,11 +215,13 @@ static void qedr_iw_disconnect_worker(struct work_struct *work)
 	struct qedr_qp *qp = ep->qp;
 	struct iw_cm_event event;
 
-	if (qp->destroyed) {
-		kfree(dwork);
-		qedr_iw_qp_rem_ref(&qp->ibqp);
-		return;
-	}
+	/* The qp won't be released until we release the ep.
+	 * the ep's refcnt was increased before calling this
+	 * function, therefore it is safe to access qp
+	 */
+	if (test_and_set_bit(QEDR_IWARP_CM_WAIT_FOR_DISCONNECT,
+			     &qp->iwarp_cm_flags))
+		goto out;
 
 	memset(&event, 0, sizeof(event));
 	event.status = dwork->status;
@@ -204,7 +235,6 @@ static void qedr_iw_disconnect_worker(struct work_struct *work)
 	else
 		qp_params.new_state = QED_ROCE_QP_STATE_SQD;
 
-	kfree(dwork);
 
 	if (ep->cm_id)
 		ep->cm_id->event_handler(ep->cm_id, &event);
@@ -214,7 +244,10 @@ static void qedr_iw_disconnect_worker(struct work_struct *work)
 
 	dev->ops->rdma_modify_qp(dev->rdma_ctx, qp->qed_qp, &qp_params);
 
-	qedr_iw_qp_rem_ref(&qp->ibqp);
+	complete(&ep->qp->iwarp_cm_comp);
+out:
+	kfree(dwork);
+	kref_put(&ep->refcnt, qedr_iw_free_ep);
 }
 
 static void
@@ -224,13 +257,17 @@ qedr_iw_disconnect_event(void *context,
 	struct qedr_discon_work *work;
 	struct qedr_iw_ep *ep = (struct qedr_iw_ep *)context;
 	struct qedr_dev *dev = ep->dev;
-	struct qedr_qp *qp = ep->qp;
 
 	work = kzalloc(sizeof(*work), GFP_ATOMIC);
 	if (!work)
 		return;
 
-	qedr_iw_qp_add_ref(&qp->ibqp);
+	/* We can't get a close event before disconnect, but since
+	 * we're scheduling a work queue we need to make sure close
+	 * won't delete the ep, so we increase the refcnt
+	 */
+	kref_get(&ep->refcnt);
+
 	work->ep = ep;
 	work->event = params->event;
 	work->status = params->status;
@@ -252,16 +289,30 @@ qedr_iw_passive_complete(void *context,
 	if ((params->status == -ECONNREFUSED) && (!ep->qp)) {
 		DP_DEBUG(dev, QEDR_MSG_IWARP,
 			 "PASSIVE connection refused releasing ep...\n");
-		kfree(ep);
+		kref_put(&ep->refcnt, qedr_iw_free_ep);
 		return;
 	}
 
+	complete(&ep->qp->iwarp_cm_comp);
 	qedr_iw_issue_event(context, params, IW_CM_EVENT_ESTABLISHED);
 
 	if (params->status < 0)
 		qedr_iw_close_event(context, params);
 }
 
+static void
+qedr_iw_active_complete(void *context,
+			struct qed_iwarp_cm_event_params *params)
+{
+	struct qedr_iw_ep *ep = (struct qedr_iw_ep *)context;
+
+	complete(&ep->qp->iwarp_cm_comp);
+	qedr_iw_issue_event(context, params, IW_CM_EVENT_CONNECT_REPLY);
+
+	if (params->status < 0)
+		kref_put(&ep->refcnt, qedr_iw_free_ep);
+}
+
 static int
 qedr_iw_mpa_reply(void *context, struct qed_iwarp_cm_event_params *params)
 {
@@ -288,27 +339,15 @@ qedr_iw_event_handler(void *context, struct qed_iwarp_cm_event_params *params)
 		qedr_iw_mpa_reply(context, params);
 		break;
 	case QED_IWARP_EVENT_PASSIVE_COMPLETE:
-		ep->during_connect = 0;
 		qedr_iw_passive_complete(context, params);
 		break;
-
 	case QED_IWARP_EVENT_ACTIVE_COMPLETE:
-		ep->during_connect = 0;
-		qedr_iw_issue_event(context,
-				    params,
-				    IW_CM_EVENT_CONNECT_REPLY);
-		if (params->status < 0) {
-			struct qedr_iw_ep *ep = (struct qedr_iw_ep *)context;
-
-			ep->cm_id->rem_ref(ep->cm_id);
-			ep->cm_id = NULL;
-		}
+		qedr_iw_active_complete(context, params);
 		break;
 	case QED_IWARP_EVENT_DISCONNECT:
 		qedr_iw_disconnect_event(context, params);
 		break;
 	case QED_IWARP_EVENT_CLOSE:
-		ep->during_connect = 0;
 		qedr_iw_close_event(context, params);
 		break;
 	case QED_IWARP_EVENT_RQ_EMPTY:
@@ -476,6 +515,19 @@ qedr_addr6_resolve(struct qedr_dev *dev,
 	return rc;
 }
 
+static struct qedr_qp *qedr_iw_load_qp(struct qedr_dev *dev, u32 qpn)
+{
+	struct qedr_qp *qp;
+
+	xa_lock(&dev->qps);
+	qp = xa_load(&dev->qps, qpn);
+	if (qp)
+		kref_get(&qp->refcnt);
+	xa_unlock(&dev->qps);
+
+	return qp;
+}
+
 int qedr_iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 {
 	struct qedr_dev *dev = get_qedr_dev(cm_id->device);
@@ -491,10 +543,6 @@ int qedr_iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 	int rc = 0;
 	int i;
 
-	qp = xa_load(&dev->qps, conn_param->qpn);
-	if (unlikely(!qp))
-		return -EINVAL;
-
 	laddr = (struct sockaddr_in *)&cm_id->m_local_addr;
 	raddr = (struct sockaddr_in *)&cm_id->m_remote_addr;
 	laddr6 = (struct sockaddr_in6 *)&cm_id->m_local_addr;
@@ -516,8 +564,15 @@ int qedr_iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 		return -ENOMEM;
 
 	ep->dev = dev;
+	kref_init(&ep->refcnt);
+
+	qp = qedr_iw_load_qp(dev, conn_param->qpn);
+	if (!qp) {
+		rc = -EINVAL;
+		goto err;
+	}
+
 	ep->qp = qp;
-	qp->ep = ep;
 	cm_id->add_ref(cm_id);
 	ep->cm_id = cm_id;
 
@@ -580,16 +635,20 @@ int qedr_iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 	in_params.qp = qp->qed_qp;
 	memcpy(in_params.local_mac_addr, dev->ndev->dev_addr, ETH_ALEN);
 
-	ep->during_connect = 1;
+	if (test_and_set_bit(QEDR_IWARP_CM_WAIT_FOR_CONNECT,
+			     &qp->iwarp_cm_flags))
+		goto err; /* QP already being destroyed */
+
 	rc = dev->ops->iwarp_connect(dev->rdma_ctx, &in_params, &out_params);
-	if (rc)
+	if (rc) {
+		complete(&qp->iwarp_cm_comp);
 		goto err;
+	}
 
 	return rc;
 
 err:
-	cm_id->rem_ref(cm_id);
-	kfree(ep);
+	kref_put(&ep->refcnt, qedr_iw_free_ep);
 	return rc;
 }
 
@@ -677,18 +736,17 @@ int qedr_iw_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 	struct qedr_dev *dev = ep->dev;
 	struct qedr_qp *qp;
 	struct qed_iwarp_accept_in params;
-	int rc;
+	int rc = 0;
 
 	DP_DEBUG(dev, QEDR_MSG_IWARP, "Accept on qpid=%d\n", conn_param->qpn);
 
-	qp = xa_load(&dev->qps, conn_param->qpn);
+	qp = qedr_iw_load_qp(dev, conn_param->qpn);
 	if (!qp) {
 		DP_ERR(dev, "Invalid QP number %d\n", conn_param->qpn);
 		return -EINVAL;
 	}
 
 	ep->qp = qp;
-	qp->ep = ep;
 	cm_id->add_ref(cm_id);
 	ep->cm_id = cm_id;
 
@@ -700,15 +758,21 @@ int qedr_iw_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 	params.ird = conn_param->ird;
 	params.ord = conn_param->ord;
 
-	ep->during_connect = 1;
+	if (test_and_set_bit(QEDR_IWARP_CM_WAIT_FOR_CONNECT,
+			     &qp->iwarp_cm_flags))
+		goto err; /* QP already destroyed */
+
 	rc = dev->ops->iwarp_accept(dev->rdma_ctx, &params);
-	if (rc)
+	if (rc) {
+		complete(&qp->iwarp_cm_comp);
 		goto err;
+	}
 
 	return rc;
+
 err:
-	ep->during_connect = 0;
-	cm_id->rem_ref(cm_id);
+	kref_put(&ep->refcnt, qedr_iw_free_ep);
+
 	return rc;
 }
 
@@ -731,17 +795,14 @@ void qedr_iw_qp_add_ref(struct ib_qp *ibqp)
 {
 	struct qedr_qp *qp = get_qedr_qp(ibqp);
 
-	atomic_inc(&qp->refcnt);
+	kref_get(&qp->refcnt);
 }
 
 void qedr_iw_qp_rem_ref(struct ib_qp *ibqp)
 {
 	struct qedr_qp *qp = get_qedr_qp(ibqp);
 
-	if (atomic_dec_and_test(&qp->refcnt)) {
-		xa_erase_irq(&qp->dev->qps, qp->qp_id);
-		kfree(qp);
-	}
+	kref_put(&qp->refcnt, qedr_iw_free_qp);
 }
 
 struct ib_qp *qedr_iw_get_qp(struct ib_device *ibdev, int qpn)
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 84301beb13b9..9d3204410ead 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -51,6 +51,7 @@
 #include "verbs.h"
 #include <rdma/qedr-abi.h>
 #include "qedr_roce_cm.h"
+#include "qedr_iw_cm.h"
 
 #define QEDR_SRQ_WQE_ELEM_SIZE	sizeof(union rdma_srq_elm)
 #define	RDMA_MAX_SGE_PER_SRQ	(4)
@@ -1226,7 +1227,10 @@ static void qedr_set_common_qp_params(struct qedr_dev *dev,
 				      struct ib_qp_init_attr *attrs)
 {
 	spin_lock_init(&qp->q_lock);
-	atomic_set(&qp->refcnt, 1);
+	if (rdma_protocol_iwarp(&dev->ibdev, 1)) {
+		kref_init(&qp->refcnt);
+		init_completion(&qp->iwarp_cm_comp);
+	}
 	qp->pd = pd;
 	qp->qp_type = attrs->qp_type;
 	qp->max_inline_data = attrs->cap.max_inline_data;
@@ -1635,6 +1639,7 @@ static int qedr_create_user_qp(struct qedr_dev *dev,
 	int alloc_and_init = rdma_protocol_roce(&dev->ibdev, 1);
 	int rc = -EINVAL;
 
+	qp->create_type = QEDR_QP_CREATE_USER;
 	memset(&ureq, 0, sizeof(ureq));
 	rc = ib_copy_from_udata(&ureq, udata, sizeof(ureq));
 	if (rc) {
@@ -1848,6 +1853,7 @@ static int qedr_create_kernel_qp(struct qedr_dev *dev,
 	u32 n_sq_entries;
 
 	memset(&in_params, 0, sizeof(in_params));
+	qp->create_type = QEDR_QP_CREATE_KERNEL;
 
 	/* A single work request may take up to QEDR_MAX_SQ_WQE_SIZE elements in
 	 * the ring. The ring should allow at least a single WR, even if the
@@ -1961,7 +1967,7 @@ struct ib_qp *qedr_create_qp(struct ib_pd *ibpd,
 	qp->ibqp.qp_num = qp->qp_id;
 
 	if (rdma_protocol_iwarp(&dev->ibdev, 1)) {
-		rc = xa_insert_irq(&dev->qps, qp->qp_id, qp, GFP_KERNEL);
+		rc = xa_insert(&dev->qps, qp->qp_id, qp, GFP_KERNEL);
 		if (rc)
 			goto err;
 	}
@@ -2480,7 +2486,7 @@ static int qedr_free_qp_resources(struct qedr_dev *dev, struct qedr_qp *qp,
 			return rc;
 	}
 
-	if (udata)
+	if (qp->create_type == QEDR_QP_CREATE_USER)
 		qedr_cleanup_user(dev, qp);
 	else
 		qedr_cleanup_kernel(dev, qp);
@@ -2511,34 +2517,44 @@ int qedr_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata)
 			qedr_modify_qp(ibqp, &attr, attr_mask, NULL);
 		}
 	} else {
-		/* Wait for the connect/accept to complete */
-		if (qp->ep) {
-			int wait_count = 1;
-
-			while (qp->ep->during_connect) {
-				DP_DEBUG(dev, QEDR_MSG_QP,
-					 "Still in during connect/accept\n");
-
-				msleep(100);
-				if (wait_count++ > 200) {
-					DP_NOTICE(dev,
-						  "during connect timeout\n");
-					break;
-				}
-			}
-		}
+		/* If connection establishment started the WAIT_FOR_CONNECT
+		 * bit will be on and we need to Wait for the establishment
+		 * to complete before destroying the qp.
+		 */
+		if (test_and_set_bit(QEDR_IWARP_CM_WAIT_FOR_CONNECT,
+				     &qp->iwarp_cm_flags))
+			wait_for_completion(&qp->iwarp_cm_comp);
+
+		/* If graceful disconnect started, the WAIT_FOR_DISCONNECT
+		 * bit will be on, and we need to wait for the disconnect to
+		 * complete before continuing. We can use the same completion,
+		 * iwarp_cm_comp, since this is the only place that waits for
+		 * this completion and it is sequential. In addition,
+		 * disconnect can't occur before the connection is fully
+		 * established, therefore if WAIT_FOR_DISCONNECT is on it
+		 * means WAIT_FOR_CONNECT is also on and the completion for
+		 * CONNECT already occurred.
+		 */
+		if (test_and_set_bit(QEDR_IWARP_CM_WAIT_FOR_DISCONNECT,
+				     &qp->iwarp_cm_flags))
+			wait_for_completion(&qp->iwarp_cm_comp);
 	}
 
 	if (qp->qp_type == IB_QPT_GSI)
 		qedr_destroy_gsi_qp(dev);
 
+	/* We need to remove the entry from the xarray before we release the
+	 * qp_id to avoid a race of the qp_id being reallocated and failing
+	 * on xa_insert
+	 */
+	if (rdma_protocol_iwarp(&dev->ibdev, 1))
+		xa_erase(&dev->qps, qp->qp_id);
+
 	qedr_free_qp_resources(dev, qp, udata);
 
-	if (atomic_dec_and_test(&qp->refcnt) &&
-	    rdma_protocol_iwarp(&dev->ibdev, 1)) {
-		xa_erase_irq(&dev->qps, qp->qp_id);
-		kfree(qp);
-	}
+	if (rdma_protocol_iwarp(&dev->ibdev, 1))
+		qedr_iw_qp_rem_ref(&qp->ibqp);
+
 	return rc;
 }
 
@@ -3481,7 +3497,7 @@ static u32 qedr_srq_elem_left(struct qedr_srq_hwq_info *hw_srq)
 	 * count and consumer count and subtract it from max
 	 * work request supported so that we get elements left.
 	 */
-	used = hw_srq->wr_prod_cnt - hw_srq->wr_cons_cnt;
+	used = hw_srq->wr_prod_cnt - (u32)atomic_read(&hw_srq->wr_cons_cnt);
 
 	return hw_srq->max_wr - used;
 }
@@ -3496,7 +3512,6 @@ int qedr_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr,
 	unsigned long flags;
 	int status = 0;
 	u32 num_sge;
-	u32 offset;
 
 	spin_lock_irqsave(&srq->lock, flags);
 
@@ -3509,7 +3524,8 @@ int qedr_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr,
 		if (!qedr_srq_elem_left(hw_srq) ||
 		    wr->num_sge > srq->hw_srq.max_sges) {
 			DP_ERR(dev, "Can't post WR  (%d,%d) || (%d > %d)\n",
-			       hw_srq->wr_prod_cnt, hw_srq->wr_cons_cnt,
+			       hw_srq->wr_prod_cnt,
+			       atomic_read(&hw_srq->wr_cons_cnt),
 			       wr->num_sge, srq->hw_srq.max_sges);
 			status = -ENOMEM;
 			*bad_wr = wr;
@@ -3543,22 +3559,20 @@ int qedr_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr,
 			hw_srq->sge_prod++;
 		}
 
-		/* Flush WQE and SGE information before
+		/* Update WQE and SGE information before
 		 * updating producer.
 		 */
-		wmb();
+		dma_wmb();
 
 		/* SRQ producer is 8 bytes. Need to update SGE producer index
 		 * in first 4 bytes and need to update WQE producer in
 		 * next 4 bytes.
 		 */
-		*srq->hw_srq.virt_prod_pair_addr = hw_srq->sge_prod;
-		offset = offsetof(struct rdma_srq_producers, wqe_prod);
-		*((u8 *)srq->hw_srq.virt_prod_pair_addr + offset) =
-			hw_srq->wqe_prod;
+		srq->hw_srq.virt_prod_pair_addr->sge_prod = hw_srq->sge_prod;
+		/* Make sure sge producer is updated first */
+		dma_wmb();
+		srq->hw_srq.virt_prod_pair_addr->wqe_prod = hw_srq->wqe_prod;
 
-		/* Flush producer after updating it. */
-		wmb();
 		wr = wr->next;
 	}
 
@@ -3977,7 +3991,7 @@ static int process_resp_one_srq(struct qedr_dev *dev, struct qedr_qp *qp,
 	} else {
 		__process_resp_one(dev, qp, cq, wc, resp, wr_id);
 	}
-	srq->hw_srq.wr_cons_cnt++;
+	atomic_inc(&srq->hw_srq.wr_cons_cnt);
 
 	return 1;
 }
diff --git a/drivers/infiniband/hw/qib/qib_sysfs.c b/drivers/infiniband/hw/qib/qib_sysfs.c
index d4f5e8cd438d..d7d74dda3aee 100644
--- a/drivers/infiniband/hw/qib/qib_sysfs.c
+++ b/drivers/infiniband/hw/qib/qib_sysfs.c
@@ -758,7 +758,7 @@ int qib_create_port_files(struct ib_device *ibdev, u8 port_num,
 		qib_dev_err(dd,
 			"Skipping linkcontrol sysfs info, (err %d) port %u\n",
 			ret, port_num);
-		goto bail;
+		goto bail_link;
 	}
 	kobject_uevent(&ppd->pport_kobj, KOBJ_ADD);
 
@@ -768,7 +768,7 @@ int qib_create_port_files(struct ib_device *ibdev, u8 port_num,
 		qib_dev_err(dd,
 			"Skipping sl2vl sysfs info, (err %d) port %u\n",
 			ret, port_num);
-		goto bail_link;
+		goto bail_sl;
 	}
 	kobject_uevent(&ppd->sl2vl_kobj, KOBJ_ADD);
 
@@ -778,7 +778,7 @@ int qib_create_port_files(struct ib_device *ibdev, u8 port_num,
 		qib_dev_err(dd,
 			"Skipping diag_counters sysfs info, (err %d) port %u\n",
 			ret, port_num);
-		goto bail_sl;
+		goto bail_diagc;
 	}
 	kobject_uevent(&ppd->diagc_kobj, KOBJ_ADD);
 
@@ -791,7 +791,7 @@ int qib_create_port_files(struct ib_device *ibdev, u8 port_num,
 		qib_dev_err(dd,
 		 "Skipping Congestion Control sysfs info, (err %d) port %u\n",
 		 ret, port_num);
-		goto bail_diagc;
+		goto bail_cc;
 	}
 
 	kobject_uevent(&ppd->pport_cc_kobj, KOBJ_ADD);
@@ -852,6 +852,7 @@ void qib_verbs_unregister_sysfs(struct qib_devdata *dd)
 				&cc_table_bin_attr);
 			kobject_put(&ppd->pport_cc_kobj);
 		}
+		kobject_put(&ppd->diagc_kobj);
 		kobject_put(&ppd->sl2vl_kobj);
 		kobject_put(&ppd->pport_kobj);
 	}
diff --git a/drivers/infiniband/hw/qib/qib_verbs.c b/drivers/infiniband/hw/qib/qib_verbs.c
index 2c4e569ce438..12c8ec59e657 100644
--- a/drivers/infiniband/hw/qib/qib_verbs.c
+++ b/drivers/infiniband/hw/qib/qib_verbs.c
@@ -329,8 +329,10 @@ void qib_ib_rcv(struct qib_ctxtdata *rcd, void *rhdr, void *data, u32 tlen)
 		if (mcast == NULL)
 			goto drop;
 		this_cpu_inc(ibp->pmastats->n_multicast_rcv);
+		rcu_read_lock();
 		list_for_each_entry_rcu(p, &mcast->qp_list, list)
 			qib_qp_rcv(rcd, hdr, 1, data, tlen, p->qp);
+		rcu_read_unlock();
 		/*
 		 * Notify rvt_multicast_detach() if it is waiting for us
 		 * to finish.
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
index 40182297f87f..6f38dc7c6a07 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
@@ -827,7 +827,7 @@ static int pvrdma_pci_probe(struct pci_dev *pdev,
 	    !(pci_resource_flags(pdev, 1) & IORESOURCE_MEM)) {
 		dev_err(&pdev->dev, "PCI BAR region not MMIO\n");
 		ret = -ENOMEM;
-		goto err_free_device;
+		goto err_disable_pdev;
 	}
 
 	ret = pci_request_regions(pdev, DRV_NAME);
diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c
index cb9e171d7e7b..78809766fc5f 100644
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -59,6 +59,8 @@
 #include "trace.h"
 
 static void rvt_rc_timeout(struct timer_list *t);
+static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp,
+			 enum ib_qp_type type);
 
 /*
  * Convert the AETH RNR timeout code into the number of microseconds.
@@ -450,40 +452,41 @@ no_qp_table:
 }
 
 /**
- * free_all_qps - check for QPs still in use
+ * rvt_free_qp_cb - callback function to reset a qp
+ * @qp: the qp to reset
+ * @v: a 64-bit value
+ *
+ * This function resets the qp and removes it from the
+ * qp hash table.
+ */
+static void rvt_free_qp_cb(struct rvt_qp *qp, u64 v)
+{
+	unsigned int *qp_inuse = (unsigned int *)v;
+	struct rvt_dev_info *rdi = ib_to_rvt(qp->ibqp.device);
+
+	/* Reset the qp and remove it from the qp hash list */
+	rvt_reset_qp(rdi, qp, qp->ibqp.qp_type);
+
+	/* Increment the qp_inuse count */
+	(*qp_inuse)++;
+}
+
+/**
+ * rvt_free_all_qps - check for QPs still in use
  * @rdi: rvt device info structure
  *
  * There should not be any QPs still in use.
  * Free memory for table.
+ * Return the number of QPs still in use.
  */
 static unsigned rvt_free_all_qps(struct rvt_dev_info *rdi)
 {
-	unsigned long flags;
-	struct rvt_qp *qp;
-	unsigned n, qp_inuse = 0;
-	spinlock_t *ql; /* work around too long line below */
-
-	if (rdi->driver_f.free_all_qps)
-		qp_inuse = rdi->driver_f.free_all_qps(rdi);
+	unsigned int qp_inuse = 0;
 
 	qp_inuse += rvt_mcast_tree_empty(rdi);
 
-	if (!rdi->qp_dev)
-		return qp_inuse;
+	rvt_qp_iter(rdi, (u64)&qp_inuse, rvt_free_qp_cb);
 
-	ql = &rdi->qp_dev->qpt_lock;
-	spin_lock_irqsave(ql, flags);
-	for (n = 0; n < rdi->qp_dev->qp_table_size; n++) {
-		qp = rcu_dereference_protected(rdi->qp_dev->qp_table[n],
-					       lockdep_is_held(ql));
-		RCU_INIT_POINTER(rdi->qp_dev->qp_table[n], NULL);
-
-		for (; qp; qp = rcu_dereference_protected(qp->next,
-							  lockdep_is_held(ql)))
-			qp_inuse++;
-	}
-	spin_unlock_irqrestore(ql, flags);
-	synchronize_rcu();
 	return qp_inuse;
 }
 
@@ -861,14 +864,14 @@ static void rvt_init_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp,
 }
 
 /**
- * rvt_reset_qp - initialize the QP state to the reset state
+ * _rvt_reset_qp - initialize the QP state to the reset state
  * @qp: the QP to reset
  * @type: the QP type
  *
  * r_lock, s_hlock, and s_lock are required to be held by the caller
  */
-static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp,
-			 enum ib_qp_type type)
+static void _rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp,
+			  enum ib_qp_type type)
 	__must_hold(&qp->s_lock)
 	__must_hold(&qp->s_hlock)
 	__must_hold(&qp->r_lock)
@@ -914,6 +917,27 @@ static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp,
 	lockdep_assert_held(&qp->s_lock);
 }
 
+/**
+ * rvt_reset_qp - initialize the QP state to the reset state
+ * @rdi: the device info
+ * @qp: the QP to reset
+ * @type: the QP type
+ *
+ * This is the wrapper function to acquire the r_lock, s_hlock, and s_lock
+ * before calling _rvt_reset_qp().
+ */
+static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp,
+			 enum ib_qp_type type)
+{
+	spin_lock_irq(&qp->r_lock);
+	spin_lock(&qp->s_hlock);
+	spin_lock(&qp->s_lock);
+	_rvt_reset_qp(rdi, qp, type);
+	spin_unlock(&qp->s_lock);
+	spin_unlock(&qp->s_hlock);
+	spin_unlock_irq(&qp->r_lock);
+}
+
 /** rvt_free_qpn - Free a qpn from the bit map
  * @qpt: QP table
  * @qpn: queue pair number to free
@@ -1465,7 +1489,7 @@ int rvt_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	switch (new_state) {
 	case IB_QPS_RESET:
 		if (qp->state != IB_QPS_RESET)
-			rvt_reset_qp(rdi, qp, ibqp->qp_type);
+			_rvt_reset_qp(rdi, qp, ibqp->qp_type);
 		break;
 
 	case IB_QPS_RTR:
@@ -1614,13 +1638,7 @@ int rvt_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata)
 	struct rvt_qp *qp = ibqp_to_rvtqp(ibqp);
 	struct rvt_dev_info *rdi = ib_to_rvt(ibqp->device);
 
-	spin_lock_irq(&qp->r_lock);
-	spin_lock(&qp->s_hlock);
-	spin_lock(&qp->s_lock);
 	rvt_reset_qp(rdi, qp, ibqp->qp_type);
-	spin_unlock(&qp->s_lock);
-	spin_unlock(&qp->s_hlock);
-	spin_unlock_irq(&qp->r_lock);
 
 	wait_event(qp->wait, !atomic_read(&qp->refcount));
 	/* qpn is now available for use again */
diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c
index 00eb99d3df86..7c5999ada61d 100644
--- a/drivers/infiniband/sw/rxe/rxe_comp.c
+++ b/drivers/infiniband/sw/rxe/rxe_comp.c
@@ -329,7 +329,7 @@ static inline enum comp_state check_ack(struct rxe_qp *qp,
 					qp->comp.psn = pkt->psn;
 					if (qp->req.wait_psn) {
 						qp->req.wait_psn = 0;
-						rxe_run_task(&qp->req.task, 1);
+						rxe_run_task(&qp->req.task, 0);
 					}
 				}
 				return COMPST_ERROR_RETRY;
@@ -463,7 +463,7 @@ static void do_complete(struct rxe_qp *qp, struct rxe_send_wqe *wqe)
 	 */
 	if (qp->req.wait_fence) {
 		qp->req.wait_fence = 0;
-		rxe_run_task(&qp->req.task, 1);
+		rxe_run_task(&qp->req.task, 0);
 	}
 }
 
@@ -479,7 +479,7 @@ static inline enum comp_state complete_ack(struct rxe_qp *qp,
 		if (qp->req.need_rd_atomic) {
 			qp->comp.timeout_retry = 0;
 			qp->req.need_rd_atomic = 0;
-			rxe_run_task(&qp->req.task, 1);
+			rxe_run_task(&qp->req.task, 0);
 		}
 	}
 
@@ -725,7 +725,7 @@ int rxe_completer(void *arg)
 							RXE_CNT_COMP_RETRY);
 					qp->req.need_retry = 1;
 					qp->comp.started_retry = 1;
-					rxe_run_task(&qp->req.task, 1);
+					rxe_run_task(&qp->req.task, 0);
 				}
 
 				if (pkt) {
diff --git a/drivers/infiniband/sw/rxe/rxe_recv.c b/drivers/infiniband/sw/rxe/rxe_recv.c
index f9a492ed900b..46e111c218fd 100644
--- a/drivers/infiniband/sw/rxe/rxe_recv.c
+++ b/drivers/infiniband/sw/rxe/rxe_recv.c
@@ -330,10 +330,14 @@ err1:
 
 static int rxe_match_dgid(struct rxe_dev *rxe, struct sk_buff *skb)
 {
+	struct rxe_pkt_info *pkt = SKB_TO_PKT(skb);
 	const struct ib_gid_attr *gid_attr;
 	union ib_gid dgid;
 	union ib_gid *pdgid;
 
+	if (pkt->mask & RXE_LOOPBACK_MASK)
+		return 0;
+
 	if (skb->protocol == htons(ETH_P_IP)) {
 		ipv6_addr_set_v4mapped(ip_hdr(skb)->daddr,
 				       (struct in6_addr *)&dgid);
@@ -366,7 +370,7 @@ void rxe_rcv(struct sk_buff *skb)
 	if (unlikely(skb->len < pkt->offset + RXE_BTH_BYTES))
 		goto drop;
 
-	if (unlikely(rxe_match_dgid(rxe, skb) < 0)) {
+	if (rxe_match_dgid(rxe, skb) < 0) {
 		pr_warn_ratelimited("failed matching dgid\n");
 		goto drop;
 	}
@@ -389,7 +393,7 @@ void rxe_rcv(struct sk_buff *skb)
 
 	calc_icrc = rxe_icrc_hdr(pkt, skb);
 	calc_icrc = rxe_crc32(rxe, calc_icrc, (u8 *)payload_addr(pkt),
-			      payload_size(pkt));
+			      payload_size(pkt) + bth_pad(pkt));
 	calc_icrc = (__force u32)cpu_to_be32(~calc_icrc);
 	if (unlikely(calc_icrc != pack_icrc)) {
 		if (skb->protocol == htons(ETH_P_IPV6))
diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
index c5d9b558fa90..e5031172c019 100644
--- a/drivers/infiniband/sw/rxe/rxe_req.c
+++ b/drivers/infiniband/sw/rxe/rxe_req.c
@@ -500,6 +500,12 @@ static int fill_packet(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
 			if (err)
 				return err;
 		}
+		if (bth_pad(pkt)) {
+			u8 *pad = payload_addr(pkt) + paylen;
+
+			memset(pad, 0, bth_pad(pkt));
+			crc = rxe_crc32(rxe, crc, pad, bth_pad(pkt));
+		}
 	}
 	p = payload_addr(pkt) + paylen + bth_pad(pkt);
 
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index 1cbfbd98eb22..c4a8195bf670 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -732,6 +732,13 @@ static enum resp_states read_reply(struct rxe_qp *qp,
 	if (err)
 		pr_err("Failed copying memory\n");
 
+	if (bth_pad(&ack_pkt)) {
+		struct rxe_dev *rxe = to_rdev(qp->ibqp.device);
+		u8 *pad = payload_addr(&ack_pkt) + payload;
+
+		memset(pad, 0, bth_pad(&ack_pkt));
+		icrc = rxe_crc32(rxe, icrc, pad, bth_pad(&ack_pkt));
+	}
 	p = payload_addr(&ack_pkt) + payload + bth_pad(&ack_pkt);
 	*p = ~icrc;
 
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index 8c3e2a18cfe4..75a41f99a23a 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -679,6 +679,7 @@ static int rxe_post_send_kernel(struct rxe_qp *qp, const struct ib_send_wr *wr,
 	unsigned int mask;
 	unsigned int length = 0;
 	int i;
+	struct ib_send_wr *next;
 
 	while (wr) {
 		mask = wr_opcode_mask(wr->opcode, qp);
@@ -695,6 +696,8 @@ static int rxe_post_send_kernel(struct rxe_qp *qp, const struct ib_send_wr *wr,
 			break;
 		}
 
+		next = wr->next;
+
 		length = 0;
 		for (i = 0; i < wr->num_sge; i++)
 			length += wr->sg_list[i].length;
@@ -705,7 +708,7 @@ static int rxe_post_send_kernel(struct rxe_qp *qp, const struct ib_send_wr *wr,
 			*bad_wr = wr;
 			break;
 		}
-		wr = wr->next;
+		wr = next;
 	}
 
 	rxe_run_task(&qp->req.task, 1);
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h
index 28bfb3ece104..3536ab43eed3 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.h
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.h
@@ -407,7 +407,7 @@ struct rxe_dev {
 	struct list_head	pending_mmaps;
 
 	spinlock_t		mmap_offset_lock; /* guard mmap_offset */
-	int			mmap_offset;
+	u64			mmap_offset;
 
 	atomic64_t		stats_counters[RXE_NUM_OF_COUNTERS];
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index 2aa3457a30ce..50a355738609 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -377,8 +377,12 @@ struct ipoib_dev_priv {
 	struct ipoib_rx_buf *rx_ring;
 
 	struct ipoib_tx_buf *tx_ring;
+	/* cyclic ring variables for managing tx_ring, for UD only */
 	unsigned int	     tx_head;
 	unsigned int	     tx_tail;
+	/* cyclic ring variables for counting overall outstanding send WRs */
+	unsigned int	     global_tx_head;
+	unsigned int	     global_tx_tail;
 	struct ib_sge	     tx_sge[MAX_SKB_FRAGS + 1];
 	struct ib_ud_wr      tx_wr;
 	struct ib_wc	     send_wc[MAX_SEND_CQE];
@@ -511,7 +515,7 @@ void ipoib_ib_dev_cleanup(struct net_device *dev);
 
 int ipoib_ib_dev_open_default(struct net_device *dev);
 int ipoib_ib_dev_open(struct net_device *dev);
-int ipoib_ib_dev_stop(struct net_device *dev);
+void ipoib_ib_dev_stop(struct net_device *dev);
 void ipoib_ib_dev_up(struct net_device *dev);
 void ipoib_ib_dev_down(struct net_device *dev);
 int ipoib_ib_dev_stop_default(struct net_device *dev);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index aa9dcfc36cd3..196f1e6b5396 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -756,7 +756,8 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_
 		return;
 	}
 
-	if ((priv->tx_head - priv->tx_tail) == ipoib_sendq_size - 1) {
+	if ((priv->global_tx_head - priv->global_tx_tail) ==
+	    ipoib_sendq_size - 1) {
 		ipoib_dbg(priv, "TX ring 0x%x full, stopping kernel net queue\n",
 			  tx->qp->qp_num);
 		netif_stop_queue(dev);
@@ -786,7 +787,7 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_
 	} else {
 		netif_trans_update(dev);
 		++tx->tx_head;
-		++priv->tx_head;
+		++priv->global_tx_head;
 	}
 }
 
@@ -820,10 +821,11 @@ void ipoib_cm_handle_tx_wc(struct net_device *dev, struct ib_wc *wc)
 	netif_tx_lock(dev);
 
 	++tx->tx_tail;
-	++priv->tx_tail;
+	++priv->global_tx_tail;
 
 	if (unlikely(netif_queue_stopped(dev) &&
-		     (priv->tx_head - priv->tx_tail) <= ipoib_sendq_size >> 1 &&
+		     ((priv->global_tx_head - priv->global_tx_tail) <=
+		      ipoib_sendq_size >> 1) &&
 		     test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)))
 		netif_wake_queue(dev);
 
@@ -1233,8 +1235,9 @@ timeout:
 		dev_kfree_skb_any(tx_req->skb);
 		netif_tx_lock_bh(p->dev);
 		++p->tx_tail;
-		++priv->tx_tail;
-		if (unlikely(priv->tx_head - priv->tx_tail == ipoib_sendq_size >> 1) &&
+		++priv->global_tx_tail;
+		if (unlikely((priv->global_tx_head - priv->global_tx_tail) <=
+			     ipoib_sendq_size >> 1) &&
 		    netif_queue_stopped(p->dev) &&
 		    test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags))
 			netif_wake_queue(p->dev);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 78fa777c87b1..7b598b66f235 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -406,9 +406,11 @@ static void ipoib_ib_handle_tx_wc(struct net_device *dev, struct ib_wc *wc)
 	dev_kfree_skb_any(tx_req->skb);
 
 	++priv->tx_tail;
+	++priv->global_tx_tail;
 
 	if (unlikely(netif_queue_stopped(dev) &&
-		     ((priv->tx_head - priv->tx_tail) <= ipoib_sendq_size >> 1) &&
+		     ((priv->global_tx_head - priv->global_tx_tail) <=
+		      ipoib_sendq_size >> 1) &&
 		     test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)))
 		netif_wake_queue(dev);
 
@@ -633,7 +635,8 @@ int ipoib_send(struct net_device *dev, struct sk_buff *skb,
 	else
 		priv->tx_wr.wr.send_flags &= ~IB_SEND_IP_CSUM;
 	/* increase the tx_head after send success, but use it for queue state */
-	if (priv->tx_head - priv->tx_tail == ipoib_sendq_size - 1) {
+	if ((priv->global_tx_head - priv->global_tx_tail) ==
+	    ipoib_sendq_size - 1) {
 		ipoib_dbg(priv, "TX ring full, stopping kernel net queue\n");
 		netif_stop_queue(dev);
 	}
@@ -661,17 +664,17 @@ int ipoib_send(struct net_device *dev, struct sk_buff *skb,
 
 		rc = priv->tx_head;
 		++priv->tx_head;
+		++priv->global_tx_head;
 	}
 	return rc;
 }
 
-static void __ipoib_reap_ah(struct net_device *dev)
+static void ipoib_reap_dead_ahs(struct ipoib_dev_priv *priv)
 {
-	struct ipoib_dev_priv *priv = ipoib_priv(dev);
 	struct ipoib_ah *ah, *tah;
 	unsigned long flags;
 
-	netif_tx_lock_bh(dev);
+	netif_tx_lock_bh(priv->dev);
 	spin_lock_irqsave(&priv->lock, flags);
 
 	list_for_each_entry_safe(ah, tah, &priv->dead_ahs, list)
@@ -682,37 +685,37 @@ static void __ipoib_reap_ah(struct net_device *dev)
 		}
 
 	spin_unlock_irqrestore(&priv->lock, flags);
-	netif_tx_unlock_bh(dev);
+	netif_tx_unlock_bh(priv->dev);
 }
 
 void ipoib_reap_ah(struct work_struct *work)
 {
 	struct ipoib_dev_priv *priv =
 		container_of(work, struct ipoib_dev_priv, ah_reap_task.work);
-	struct net_device *dev = priv->dev;
 
-	__ipoib_reap_ah(dev);
+	ipoib_reap_dead_ahs(priv);
 
 	if (!test_bit(IPOIB_STOP_REAPER, &priv->flags))
 		queue_delayed_work(priv->wq, &priv->ah_reap_task,
 				   round_jiffies_relative(HZ));
 }
 
-static void ipoib_flush_ah(struct net_device *dev)
+static void ipoib_start_ah_reaper(struct ipoib_dev_priv *priv)
 {
-	struct ipoib_dev_priv *priv = ipoib_priv(dev);
-
-	cancel_delayed_work(&priv->ah_reap_task);
-	flush_workqueue(priv->wq);
-	ipoib_reap_ah(&priv->ah_reap_task.work);
+	clear_bit(IPOIB_STOP_REAPER, &priv->flags);
+	queue_delayed_work(priv->wq, &priv->ah_reap_task,
+			   round_jiffies_relative(HZ));
 }
 
-static void ipoib_stop_ah(struct net_device *dev)
+static void ipoib_stop_ah_reaper(struct ipoib_dev_priv *priv)
 {
-	struct ipoib_dev_priv *priv = ipoib_priv(dev);
-
 	set_bit(IPOIB_STOP_REAPER, &priv->flags);
-	ipoib_flush_ah(dev);
+	cancel_delayed_work(&priv->ah_reap_task);
+	/*
+	 * After ipoib_stop_ah_reaper() we always go through
+	 * ipoib_reap_dead_ahs() which ensures the work is really stopped and
+	 * does a final flush out of the dead_ah's list
+	 */
 }
 
 static int recvs_pending(struct net_device *dev)
@@ -806,6 +809,7 @@ int ipoib_ib_dev_stop_default(struct net_device *dev)
 				ipoib_dma_unmap_tx(priv, tx_req);
 				dev_kfree_skb_any(tx_req->skb);
 				++priv->tx_tail;
+				++priv->global_tx_tail;
 			}
 
 			for (i = 0; i < ipoib_recvq_size; ++i) {
@@ -840,18 +844,6 @@ timeout:
 	return 0;
 }
 
-int ipoib_ib_dev_stop(struct net_device *dev)
-{
-	struct ipoib_dev_priv *priv = ipoib_priv(dev);
-
-	priv->rn_ops->ndo_stop(dev);
-
-	clear_bit(IPOIB_FLAG_INITIALIZED, &priv->flags);
-	ipoib_flush_ah(dev);
-
-	return 0;
-}
-
 int ipoib_ib_dev_open_default(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
@@ -895,10 +887,7 @@ int ipoib_ib_dev_open(struct net_device *dev)
 		return -1;
 	}
 
-	clear_bit(IPOIB_STOP_REAPER, &priv->flags);
-	queue_delayed_work(priv->wq, &priv->ah_reap_task,
-			   round_jiffies_relative(HZ));
-
+	ipoib_start_ah_reaper(priv);
 	if (priv->rn_ops->ndo_open(dev)) {
 		pr_warn("%s: Failed to open dev\n", dev->name);
 		goto dev_stop;
@@ -909,13 +898,20 @@ int ipoib_ib_dev_open(struct net_device *dev)
 	return 0;
 
 dev_stop:
-	set_bit(IPOIB_STOP_REAPER, &priv->flags);
-	cancel_delayed_work(&priv->ah_reap_task);
-	set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags);
-	ipoib_ib_dev_stop(dev);
+	ipoib_stop_ah_reaper(priv);
 	return -1;
 }
 
+void ipoib_ib_dev_stop(struct net_device *dev)
+{
+	struct ipoib_dev_priv *priv = ipoib_priv(dev);
+
+	priv->rn_ops->ndo_stop(dev);
+
+	clear_bit(IPOIB_FLAG_INITIALIZED, &priv->flags);
+	ipoib_stop_ah_reaper(priv);
+}
+
 void ipoib_pkey_dev_check_presence(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
@@ -1226,7 +1222,7 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
 		ipoib_mcast_dev_flush(dev);
 		if (oper_up)
 			set_bit(IPOIB_FLAG_OPER_UP, &priv->flags);
-		ipoib_flush_ah(dev);
+		ipoib_reap_dead_ahs(priv);
 	}
 
 	if (level >= IPOIB_FLUSH_NORMAL)
@@ -1301,7 +1297,7 @@ void ipoib_ib_dev_cleanup(struct net_device *dev)
 	 * the neighbor garbage collection is stopped and reaped.
 	 * That should all be done now, so make a final ah flush.
 	 */
-	ipoib_stop_ah(dev);
+	ipoib_reap_dead_ahs(priv);
 
 	clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index ac0583ff280d..044bcacad6e4 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -1188,9 +1188,11 @@ static void ipoib_timeout(struct net_device *dev)
 
 	ipoib_warn(priv, "transmit timeout: latency %d msecs\n",
 		   jiffies_to_msecs(jiffies - dev_trans_start(dev)));
-	ipoib_warn(priv, "queue stopped %d, tx_head %u, tx_tail %u\n",
-		   netif_queue_stopped(dev),
-		   priv->tx_head, priv->tx_tail);
+	ipoib_warn(priv,
+		   "queue stopped %d, tx_head %u, tx_tail %u, global_tx_head %u, global_tx_tail %u\n",
+		   netif_queue_stopped(dev), priv->tx_head, priv->tx_tail,
+		   priv->global_tx_head, priv->global_tx_tail);
+
 	/* XXX reset QP, etc. */
 }
 
@@ -1705,7 +1707,7 @@ static int ipoib_dev_init_default(struct net_device *dev)
 		goto out_rx_ring_cleanup;
 	}
 
-	/* priv->tx_head, tx_tail & tx_outstanding are already 0 */
+	/* priv->tx_head, tx_tail and global_tx_tail/head are already 0 */
 
 	if (ipoib_transport_dev_init(dev, priv->ca)) {
 		pr_warn("%s: ipoib_transport_dev_init failed\n",
@@ -1977,6 +1979,8 @@ static void ipoib_ndo_uninit(struct net_device *dev)
 
 	/* no more works over the priv->wq */
 	if (priv->wq) {
+		/* See ipoib_mcast_carrier_on_task() */
+		WARN_ON(test_bit(IPOIB_FLAG_OPER_UP, &priv->flags));
 		flush_workqueue(priv->wq);
 		destroy_workqueue(priv->wq);
 		priv->wq = NULL;
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 0b09d0cd9b3c..19b6cebfed19 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -2553,7 +2553,8 @@ static void srp_cm_rep_handler(struct ib_cm_id *cm_id,
 	if (lrsp->opcode == SRP_LOGIN_RSP) {
 		ch->max_ti_iu_len = be32_to_cpu(lrsp->max_ti_iu_len);
 		ch->req_lim       = be32_to_cpu(lrsp->req_lim_delta);
-		ch->use_imm_data  = lrsp->rsp_flags & SRP_LOGIN_RSP_IMMED_SUPP;
+		ch->use_imm_data  = srp_use_imm_data &&
+			(lrsp->rsp_flags & SRP_LOGIN_RSP_IMMED_SUPP);
 		ch->max_it_iu_len = srp_max_it_iu_len(target->cmd_sg_cnt,
 						      ch->use_imm_data);
 		WARN_ON_ONCE(ch->max_it_iu_len >
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 1a039f16d315..7b9ff07d9118 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -1364,9 +1364,11 @@ static int srpt_build_cmd_rsp(struct srpt_rdma_ch *ch,
 			      struct srpt_send_ioctx *ioctx, u64 tag,
 			      int status)
 {
+	struct se_cmd *cmd = &ioctx->cmd;
 	struct srp_rsp *srp_rsp;
 	const u8 *sense_data;
 	int sense_data_len, max_sense_len;
+	u32 resid = cmd->residual_count;
 
 	/*
 	 * The lowest bit of all SAM-3 status codes is zero (see also
@@ -1388,6 +1390,28 @@ static int srpt_build_cmd_rsp(struct srpt_rdma_ch *ch,
 	srp_rsp->tag = tag;
 	srp_rsp->status = status;
 
+	if (cmd->se_cmd_flags & SCF_UNDERFLOW_BIT) {
+		if (cmd->data_direction == DMA_TO_DEVICE) {
+			/* residual data from an underflow write */
+			srp_rsp->flags = SRP_RSP_FLAG_DOUNDER;
+			srp_rsp->data_out_res_cnt = cpu_to_be32(resid);
+		} else if (cmd->data_direction == DMA_FROM_DEVICE) {
+			/* residual data from an underflow read */
+			srp_rsp->flags = SRP_RSP_FLAG_DIUNDER;
+			srp_rsp->data_in_res_cnt = cpu_to_be32(resid);
+		}
+	} else if (cmd->se_cmd_flags & SCF_OVERFLOW_BIT) {
+		if (cmd->data_direction == DMA_TO_DEVICE) {
+			/* residual data from an overflow write */
+			srp_rsp->flags = SRP_RSP_FLAG_DOOVER;
+			srp_rsp->data_out_res_cnt = cpu_to_be32(resid);
+		} else if (cmd->data_direction == DMA_FROM_DEVICE) {
+			/* residual data from an overflow read */
+			srp_rsp->flags = SRP_RSP_FLAG_DIOVER;
+			srp_rsp->data_in_res_cnt = cpu_to_be32(resid);
+		}
+	}
+
 	if (sense_data_len) {
 		BUILD_BUG_ON(MIN_MAX_RSP_SIZE <= sizeof(*srp_rsp));
 		max_sense_len = ch->max_ti_iu_len - sizeof(*srp_rsp);
diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c
index 867c2cfd0038..3a933b9d3adf 100644
--- a/drivers/input/evdev.c
+++ b/drivers/input/evdev.c
@@ -238,13 +238,13 @@ static void __pass_event(struct evdev_client *client,
 		 */
 		client->tail = (client->head - 2) & (client->bufsize - 1);
 
-		client->buffer[client->tail].input_event_sec =
-						event->input_event_sec;
-		client->buffer[client->tail].input_event_usec =
-						event->input_event_usec;
-		client->buffer[client->tail].type = EV_SYN;
-		client->buffer[client->tail].code = SYN_DROPPED;
-		client->buffer[client->tail].value = 0;
+		client->buffer[client->tail] = (struct input_event) {
+			.input_event_sec = event->input_event_sec,
+			.input_event_usec = event->input_event_usec,
+			.type = EV_SYN,
+			.code = SYN_DROPPED,
+			.value = 0,
+		};
 
 		client->packet_head = client->tail;
 	}
@@ -345,20 +345,6 @@ static int evdev_fasync(int fd, struct file *file, int on)
 	return fasync_helper(fd, file, on, &client->fasync);
 }
 
-static int evdev_flush(struct file *file, fl_owner_t id)
-{
-	struct evdev_client *client = file->private_data;
-	struct evdev *evdev = client->evdev;
-
-	mutex_lock(&evdev->mutex);
-
-	if (evdev->exist && !client->revoked)
-		input_flush_device(&evdev->handle, file);
-
-	mutex_unlock(&evdev->mutex);
-	return 0;
-}
-
 static void evdev_free(struct device *dev)
 {
 	struct evdev *evdev = container_of(dev, struct evdev, dev);
@@ -472,6 +458,10 @@ static int evdev_release(struct inode *inode, struct file *file)
 	unsigned int i;
 
 	mutex_lock(&evdev->mutex);
+
+	if (evdev->exist && !client->revoked)
+		input_flush_device(&evdev->handle, file);
+
 	evdev_ungrab(evdev, client);
 	mutex_unlock(&evdev->mutex);
 
@@ -503,10 +493,7 @@ static int evdev_open(struct inode *inode, struct file *file)
 	struct evdev_client *client;
 	int error;
 
-	client = kzalloc(struct_size(client, buffer, bufsize),
-			 GFP_KERNEL | __GFP_NOWARN);
-	if (!client)
-		client = vzalloc(struct_size(client, buffer, bufsize));
+	client = kvzalloc(struct_size(client, buffer, bufsize), GFP_KERNEL);
 	if (!client)
 		return -ENOMEM;
 
@@ -1332,7 +1319,6 @@ static const struct file_operations evdev_fops = {
 	.compat_ioctl	= evdev_ioctl_compat,
 #endif
 	.fasync		= evdev_fasync,
-	.flush		= evdev_flush,
 	.llseek		= no_llseek,
 };
 
diff --git a/drivers/input/input.c b/drivers/input/input.c
index 7f3c5fcb9ed6..33e6ac2f565d 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -854,16 +854,18 @@ static int input_default_setkeycode(struct input_dev *dev,
 		}
 	}
 
-	__clear_bit(*old_keycode, dev->keybit);
-	__set_bit(ke->keycode, dev->keybit);
-
-	for (i = 0; i < dev->keycodemax; i++) {
-		if (input_fetch_keycode(dev, i) == *old_keycode) {
-			__set_bit(*old_keycode, dev->keybit);
-			break; /* Setting the bit twice is useless, so break */
+	if (*old_keycode <= KEY_MAX) {
+		__clear_bit(*old_keycode, dev->keybit);
+		for (i = 0; i < dev->keycodemax; i++) {
+			if (input_fetch_keycode(dev, i) == *old_keycode) {
+				__set_bit(*old_keycode, dev->keybit);
+				/* Setting the bit twice is useless, so break */
+				break;
+			}
 		}
 	}
 
+	__set_bit(ke->keycode, dev->keybit);
 	return 0;
 }
 
@@ -919,9 +921,13 @@ int input_set_keycode(struct input_dev *dev,
 	 * Simulate keyup event if keycode is not present
 	 * in the keymap anymore
 	 */
-	if (test_bit(EV_KEY, dev->evbit) &&
-	    !is_event_supported(old_keycode, dev->keybit, KEY_MAX) &&
-	    __test_and_clear_bit(old_keycode, dev->key)) {
+	if (old_keycode > KEY_MAX) {
+		dev_warn(dev->dev.parent ?: &dev->dev,
+			 "%s: got too big old keycode %#x\n",
+			 __func__, old_keycode);
+	} else if (test_bit(EV_KEY, dev->evbit) &&
+		   !is_event_supported(old_keycode, dev->keybit, KEY_MAX) &&
+		   __test_and_clear_bit(old_keycode, dev->key)) {
 		struct input_value vals[] =  {
 			{ EV_KEY, old_keycode, 0 },
 			input_value_sync
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 6b40a1c68f9f..c77cdb3b62b5 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -459,6 +459,16 @@ static const u8 xboxone_fw2015_init[] = {
 };
 
 /*
+ * This packet is required for Xbox One S (0x045e:0x02ea)
+ * and Xbox One Elite Series 2 (0x045e:0x0b00) pads to
+ * initialize the controller that was previously used in
+ * Bluetooth mode.
+ */
+static const u8 xboxone_s_init[] = {
+	0x05, 0x20, 0x00, 0x0f, 0x06
+};
+
+/*
  * This packet is required for the Titanfall 2 Xbox One pads
  * (0x0e6f:0x0165) to finish initialization and for Hori pads
  * (0x0f0d:0x0067) to make the analog sticks work.
@@ -516,6 +526,8 @@ static const struct xboxone_init_packet xboxone_init_packets[] = {
 	XBOXONE_INIT_PKT(0x0e6f, 0x0165, xboxone_hori_init),
 	XBOXONE_INIT_PKT(0x0f0d, 0x0067, xboxone_hori_init),
 	XBOXONE_INIT_PKT(0x0000, 0x0000, xboxone_fw2015_init),
+	XBOXONE_INIT_PKT(0x045e, 0x02ea, xboxone_s_init),
+	XBOXONE_INIT_PKT(0x045e, 0x0b00, xboxone_s_init),
 	XBOXONE_INIT_PKT(0x0e6f, 0x0000, xboxone_pdp_init1),
 	XBOXONE_INIT_PKT(0x0e6f, 0x0000, xboxone_pdp_init2),
 	XBOXONE_INIT_PKT(0x24c6, 0x541a, xboxone_rumblebegin_init),
diff --git a/drivers/input/keyboard/dlink-dir685-touchkeys.c b/drivers/input/keyboard/dlink-dir685-touchkeys.c
index b0ead7199c40..a69dcc3bd30c 100644
--- a/drivers/input/keyboard/dlink-dir685-touchkeys.c
+++ b/drivers/input/keyboard/dlink-dir685-touchkeys.c
@@ -143,7 +143,7 @@ MODULE_DEVICE_TABLE(of, dir685_tk_of_match);
 
 static struct i2c_driver dir685_tk_i2c_driver = {
 	.driver = {
-		.name	= "dlin-dir685-touchkeys",
+		.name	= "dlink-dir685-touchkeys",
 		.of_match_table = of_match_ptr(dir685_tk_of_match),
 	},
 	.probe		= dir685_tk_probe,
diff --git a/drivers/input/keyboard/tm2-touchkey.c b/drivers/input/keyboard/tm2-touchkey.c
index 14b55bacdd0f..fb078e049413 100644
--- a/drivers/input/keyboard/tm2-touchkey.c
+++ b/drivers/input/keyboard/tm2-touchkey.c
@@ -75,6 +75,14 @@ static struct touchkey_variant aries_touchkey_variant = {
 	.cmd_led_off = ARIES_TOUCHKEY_CMD_LED_OFF,
 };
 
+static const struct touchkey_variant tc360_touchkey_variant = {
+	.keycode_reg = 0x00,
+	.base_reg = 0x00,
+	.fixed_regulator = true,
+	.cmd_led_on = TM2_TOUCHKEY_CMD_LED_ON,
+	.cmd_led_off = TM2_TOUCHKEY_CMD_LED_OFF,
+};
+
 static int tm2_touchkey_led_brightness_set(struct led_classdev *led_dev,
 					    enum led_brightness brightness)
 {
@@ -327,6 +335,9 @@ static const struct of_device_id tm2_touchkey_of_match[] = {
 	}, {
 		.compatible = "cypress,aries-touchkey",
 		.data = &aries_touchkey_variant,
+	}, {
+		.compatible = "coreriver,tc360-touchkey",
+		.data = &tc360_touchkey_variant,
 	},
 	{ },
 };
diff --git a/drivers/input/misc/keyspan_remote.c b/drivers/input/misc/keyspan_remote.c
index 83368f1e7c4e..4650f4a94989 100644
--- a/drivers/input/misc/keyspan_remote.c
+++ b/drivers/input/misc/keyspan_remote.c
@@ -336,7 +336,8 @@ static int keyspan_setup(struct usb_device* dev)
 	int retval = 0;
 
 	retval = usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
-				 0x11, 0x40, 0x5601, 0x0, NULL, 0, 0);
+				 0x11, 0x40, 0x5601, 0x0, NULL, 0,
+				 USB_CTRL_SET_TIMEOUT);
 	if (retval) {
 		dev_dbg(&dev->dev, "%s - failed to set bit rate due to error: %d\n",
 			__func__, retval);
@@ -344,7 +345,8 @@ static int keyspan_setup(struct usb_device* dev)
 	}
 
 	retval = usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
-				 0x44, 0x40, 0x0, 0x0, NULL, 0, 0);
+				 0x44, 0x40, 0x0, 0x0, NULL, 0,
+				 USB_CTRL_SET_TIMEOUT);
 	if (retval) {
 		dev_dbg(&dev->dev, "%s - failed to set resume sensitivity due to error: %d\n",
 			__func__, retval);
@@ -352,7 +354,8 @@ static int keyspan_setup(struct usb_device* dev)
 	}
 
 	retval = usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
-				 0x22, 0x40, 0x0, 0x0, NULL, 0, 0);
+				 0x22, 0x40, 0x0, 0x0, NULL, 0,
+				 USB_CTRL_SET_TIMEOUT);
 	if (retval) {
 		dev_dbg(&dev->dev, "%s - failed to turn receive on due to error: %d\n",
 			__func__, retval);
diff --git a/drivers/input/misc/max77650-onkey.c b/drivers/input/misc/max77650-onkey.c
index fbf6caab7217..04ad7024141c 100644
--- a/drivers/input/misc/max77650-onkey.c
+++ b/drivers/input/misc/max77650-onkey.c
@@ -108,9 +108,16 @@ static int max77650_onkey_probe(struct platform_device *pdev)
 	return input_register_device(onkey->input);
 }
 
+static const struct of_device_id max77650_onkey_of_match[] = {
+	{ .compatible = "maxim,max77650-onkey" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, max77650_onkey_of_match);
+
 static struct platform_driver max77650_onkey_driver = {
 	.driver = {
 		.name = "max77650-onkey",
+		.of_match_table = max77650_onkey_of_match,
 	},
 	.probe = max77650_onkey_probe,
 };
diff --git a/drivers/input/misc/pm8xxx-vibrator.c b/drivers/input/misc/pm8xxx-vibrator.c
index ecd762f93732..53ad25eaf1a2 100644
--- a/drivers/input/misc/pm8xxx-vibrator.c
+++ b/drivers/input/misc/pm8xxx-vibrator.c
@@ -90,7 +90,7 @@ static int pm8xxx_vib_set(struct pm8xxx_vib *vib, bool on)
 
 	if (regs->enable_mask)
 		rc = regmap_update_bits(vib->regmap, regs->enable_addr,
-					on ? regs->enable_mask : 0, val);
+					regs->enable_mask, on ? ~0 : 0);
 
 	return rc;
 }
diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c
index 84051f20b18a..002654ec7040 100644
--- a/drivers/input/misc/uinput.c
+++ b/drivers/input/misc/uinput.c
@@ -74,12 +74,16 @@ static int uinput_dev_event(struct input_dev *dev,
 	struct uinput_device	*udev = input_get_drvdata(dev);
 	struct timespec64	ts;
 
-	udev->buff[udev->head].type = type;
-	udev->buff[udev->head].code = code;
-	udev->buff[udev->head].value = value;
 	ktime_get_ts64(&ts);
-	udev->buff[udev->head].input_event_sec = ts.tv_sec;
-	udev->buff[udev->head].input_event_usec = ts.tv_nsec / NSEC_PER_USEC;
+
+	udev->buff[udev->head] = (struct input_event) {
+		.input_event_sec = ts.tv_sec,
+		.input_event_usec = ts.tv_nsec / NSEC_PER_USEC,
+		.type = type,
+		.code = code,
+		.value = value,
+	};
+
 	udev->head = (udev->head + 1) % UINPUT_BUFFER_SIZE;
 
 	wake_up_interruptible(&udev->waitq);
diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c
index e78c20d7df41..6b3b5d5ad721 100644
--- a/drivers/input/mouse/elan_i2c_core.c
+++ b/drivers/input/mouse/elan_i2c_core.c
@@ -914,6 +914,8 @@ static void elan_report_absolute(struct elan_tp_data *data, u8 *packet)
 	u8 hover_info = packet[ETP_HOVER_INFO_OFFSET];
 	bool contact_valid, hover_event;
 
+	pm_wakeup_event(&data->client->dev, 0);
+
 	hover_event = hover_info & 0x40;
 	for (i = 0; i < ETP_MAX_FINGERS; i++) {
 		contact_valid = tp_info & (1U << (3 + i));
@@ -936,6 +938,8 @@ static void elan_report_trackpoint(struct elan_tp_data *data, u8 *report)
 	u8 *packet = &report[ETP_REPORT_ID_OFFSET + 1];
 	int x, y;
 
+	pm_wakeup_event(&data->client->dev, 0);
+
 	if (!data->tp_input) {
 		dev_warn_once(&data->client->dev,
 			      "received a trackpoint report while no trackpoint device has been created. Please report upstream.\n");
@@ -960,7 +964,6 @@ static void elan_report_trackpoint(struct elan_tp_data *data, u8 *report)
 static irqreturn_t elan_isr(int irq, void *dev_id)
 {
 	struct elan_tp_data *data = dev_id;
-	struct device *dev = &data->client->dev;
 	int error;
 	u8 report[ETP_MAX_REPORT_LEN];
 
@@ -978,8 +981,6 @@ static irqreturn_t elan_isr(int irq, void *dev_id)
 	if (error)
 		goto out;
 
-	pm_wakeup_event(dev, 0);
-
 	switch (report[ETP_REPORT_ID_OFFSET]) {
 	case ETP_REPORT_ID:
 		elan_report_absolute(data, report);
@@ -988,7 +989,7 @@ static irqreturn_t elan_isr(int irq, void *dev_id)
 		elan_report_trackpoint(data, report);
 		break;
 	default:
-		dev_err(dev, "invalid report id data (%x)\n",
+		dev_err(&data->client->dev, "invalid report id data (%x)\n",
 			report[ETP_REPORT_ID_OFFSET]);
 	}
 
@@ -1376,8 +1377,15 @@ static const struct acpi_device_id elan_acpi_id[] = {
 	{ "ELAN062B", 0 },
 	{ "ELAN062C", 0 },
 	{ "ELAN062D", 0 },
+	{ "ELAN062E", 0 }, /* Lenovo V340 Whiskey Lake U */
+	{ "ELAN062F", 0 }, /* Lenovo V340 Comet Lake U */
 	{ "ELAN0631", 0 },
 	{ "ELAN0632", 0 },
+	{ "ELAN0633", 0 }, /* Lenovo S145 */
+	{ "ELAN0634", 0 }, /* Lenovo V340 Ice lake */
+	{ "ELAN0635", 0 }, /* Lenovo V1415-IIL */
+	{ "ELAN0636", 0 }, /* Lenovo V1415-Dali */
+	{ "ELAN0637", 0 }, /* Lenovo V1415-IGLR */
 	{ "ELAN1000", 0 },
 	{ }
 };
diff --git a/drivers/input/mouse/sentelic.c b/drivers/input/mouse/sentelic.c
index e99d9bf1a267..e78c4c7eda34 100644
--- a/drivers/input/mouse/sentelic.c
+++ b/drivers/input/mouse/sentelic.c
@@ -441,7 +441,7 @@ static ssize_t fsp_attr_set_setreg(struct psmouse *psmouse, void *data,
 
 	fsp_reg_write_enable(psmouse, false);
 
-	return count;
+	return retval;
 }
 
 PSMOUSE_DEFINE_WO_ATTR(setreg, S_IWUSR, NULL, fsp_attr_set_setreg);
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 49f9654d6617..9e7ff6fdad78 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -146,7 +146,6 @@ static const char * const topbuttonpad_pnp_ids[] = {
 	"LEN0042", /* Yoga */
 	"LEN0045",
 	"LEN0047",
-	"LEN0049",
 	"LEN2000", /* S540 */
 	"LEN2001", /* Edge E431 */
 	"LEN2002", /* Edge E531 */
@@ -166,9 +165,12 @@ static const char * const smbus_pnp_ids[] = {
 	/* all of the topbuttonpad_pnp_ids are valid, we just add some extras */
 	"LEN0048", /* X1 Carbon 3 */
 	"LEN0046", /* X250 */
+	"LEN0049", /* Yoga 11e */
 	"LEN004a", /* W541 */
 	"LEN005b", /* P50 */
 	"LEN005e", /* T560 */
+	"LEN006c", /* T470s */
+	"LEN007a", /* T470s */
 	"LEN0071", /* T480 */
 	"LEN0072", /* X1 Carbon Gen 5 (2017) - Elan/ALPS trackpoint */
 	"LEN0073", /* X1 Carbon G5 (Elantech) */
@@ -177,13 +179,16 @@ static const char * const smbus_pnp_ids[] = {
 	"LEN0093", /* T480 */
 	"LEN0096", /* X280 */
 	"LEN0097", /* X280 -> ALPS trackpoint */
+	"LEN0099", /* X1 Extreme 1st */
 	"LEN009b", /* T580 */
 	"LEN200f", /* T450s */
+	"LEN2044", /* L470  */
 	"LEN2054", /* E480 */
 	"LEN2055", /* E580 */
 	"SYN3052", /* HP EliteBook 840 G4 */
 	"SYN3221", /* HP 15-ay000 */
 	"SYN323d", /* HP Spectre X360 13-w013dx */
+	"SYN3257", /* HP Envy 13-ad105ng */
 	NULL
 };
 
diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c
index 190b9974526b..258d5fe3d395 100644
--- a/drivers/input/rmi4/rmi_driver.c
+++ b/drivers/input/rmi4/rmi_driver.c
@@ -205,7 +205,7 @@ static irqreturn_t rmi_irq_fn(int irq, void *dev_id)
 
 	if (count) {
 		kfree(attn_data.data);
-		attn_data.data = NULL;
+		drvdata->attn_data.data = NULL;
 	}
 
 	if (!kfifo_is_empty(&drvdata->attn_fifo))
@@ -1210,7 +1210,8 @@ static int rmi_driver_probe(struct device *dev)
 	if (data->input) {
 		rmi_driver_set_input_name(rmi_dev, data->input);
 		if (!rmi_dev->xport->input) {
-			if (input_register_device(data->input)) {
+			retval = input_register_device(data->input);
+			if (retval) {
 				dev_err(dev, "%s: Failed to register input device.\n",
 					__func__);
 				goto err_destroy_functions;
diff --git a/drivers/input/rmi4/rmi_smbus.c b/drivers/input/rmi4/rmi_smbus.c
index b313c579914f..2407ea43de59 100644
--- a/drivers/input/rmi4/rmi_smbus.c
+++ b/drivers/input/rmi4/rmi_smbus.c
@@ -163,6 +163,7 @@ static int rmi_smb_write_block(struct rmi_transport_dev *xport, u16 rmiaddr,
 		/* prepare to write next block of bytes */
 		cur_len -= SMB_MAX_COUNT;
 		databuff += SMB_MAX_COUNT;
+		rmiaddr += SMB_MAX_COUNT;
 	}
 exit:
 	mutex_unlock(&rmi_smb->page_mutex);
@@ -214,6 +215,7 @@ static int rmi_smb_read_block(struct rmi_transport_dev *xport, u16 rmiaddr,
 		/* prepare to read next block of bytes */
 		cur_len -= SMB_MAX_COUNT;
 		databuff += SMB_MAX_COUNT;
+		rmiaddr += SMB_MAX_COUNT;
 	}
 
 	retval = 0;
diff --git a/drivers/input/serio/i8042-ppcio.h b/drivers/input/serio/i8042-ppcio.h
deleted file mode 100644
index 391f94d9e47d..000000000000
--- a/drivers/input/serio/i8042-ppcio.h
+++ /dev/null
@@ -1,57 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-#ifndef _I8042_PPCIO_H
-#define _I8042_PPCIO_H
-
-
-#if defined(CONFIG_WALNUT)
-
-#define I8042_KBD_IRQ 25
-#define I8042_AUX_IRQ 26
-
-#define I8042_KBD_PHYS_DESC "walnutps2/serio0"
-#define I8042_AUX_PHYS_DESC "walnutps2/serio1"
-#define I8042_MUX_PHYS_DESC "walnutps2/serio%d"
-
-extern void *kb_cs;
-extern void *kb_data;
-
-#define I8042_COMMAND_REG (*(int *)kb_cs)
-#define I8042_DATA_REG (*(int *)kb_data)
-
-static inline int i8042_read_data(void)
-{
-	return readb(kb_data);
-}
-
-static inline int i8042_read_status(void)
-{
-	return readb(kb_cs);
-}
-
-static inline void i8042_write_data(int val)
-{
-	writeb(val, kb_data);
-}
-
-static inline void i8042_write_command(int val)
-{
-	writeb(val, kb_cs);
-}
-
-static inline int i8042_platform_init(void)
-{
-	i8042_reset = I8042_RESET_ALWAYS;
-	return 0;
-}
-
-static inline void i8042_platform_exit(void)
-{
-}
-
-#else
-
-#include "i8042-io.h"
-
-#endif
-
-#endif /* _I8042_PPCIO_H */
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index dc974c288e88..858a26302198 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -426,6 +426,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = {
 		},
 	},
 	{
+		/* Lenovo XiaoXin Air 12 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "80UN"),
+		},
+	},
+	{
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 1360"),
@@ -530,6 +537,17 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = {
 			DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo LaVie Z"),
 		},
 	},
+	{
+		/*
+		 * Acer Aspire 5738z
+		 * Touchpad stops working in mux mode when dis- + re-enabled
+		 * with the touchpad enable/disable toggle hotkey
+		 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5738"),
+		},
+	},
 	{ }
 };
 
@@ -651,6 +669,13 @@ static const struct dmi_system_id __initconst i8042_dmi_reset_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "P65xRP"),
 		},
 	},
+	{
+		/* Lenovo ThinkPad Twist S230u */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "33474HU"),
+		},
+	},
 	{ }
 };
 
diff --git a/drivers/input/serio/i8042.h b/drivers/input/serio/i8042.h
index 38dc27ad3c18..eb376700dfff 100644
--- a/drivers/input/serio/i8042.h
+++ b/drivers/input/serio/i8042.h
@@ -17,8 +17,6 @@
 #include "i8042-ip22io.h"
 #elif defined(CONFIG_SNI_RM)
 #include "i8042-snirm.h"
-#elif defined(CONFIG_PPC)
-#include "i8042-ppcio.h"
 #elif defined(CONFIG_SPARC)
 #include "i8042-sparcio.h"
 #elif defined(CONFIG_X86) || defined(CONFIG_IA64)
diff --git a/drivers/input/tablet/aiptek.c b/drivers/input/tablet/aiptek.c
index 2ca586fb914f..06d0ffef4a17 100644
--- a/drivers/input/tablet/aiptek.c
+++ b/drivers/input/tablet/aiptek.c
@@ -1802,14 +1802,14 @@ aiptek_probe(struct usb_interface *intf, const struct usb_device_id *id)
 	input_set_abs_params(inputdev, ABS_WHEEL, AIPTEK_WHEEL_MIN, AIPTEK_WHEEL_MAX - 1, 0, 0);
 
 	/* Verify that a device really has an endpoint */
-	if (intf->altsetting[0].desc.bNumEndpoints < 1) {
+	if (intf->cur_altsetting->desc.bNumEndpoints < 1) {
 		dev_err(&intf->dev,
 			"interface has %d endpoints, but must have minimum 1\n",
-			intf->altsetting[0].desc.bNumEndpoints);
+			intf->cur_altsetting->desc.bNumEndpoints);
 		err = -EINVAL;
 		goto fail3;
 	}
-	endpoint = &intf->altsetting[0].endpoint[0].desc;
+	endpoint = &intf->cur_altsetting->endpoint[0].desc;
 
 	/* Go set up our URB, which is called when the tablet receives
 	 * input.
diff --git a/drivers/input/tablet/gtco.c b/drivers/input/tablet/gtco.c
index 35031228a6d0..799c94dda651 100644
--- a/drivers/input/tablet/gtco.c
+++ b/drivers/input/tablet/gtco.c
@@ -875,18 +875,14 @@ static int gtco_probe(struct usb_interface *usbinterface,
 	}
 
 	/* Sanity check that a device has an endpoint */
-	if (usbinterface->altsetting[0].desc.bNumEndpoints < 1) {
+	if (usbinterface->cur_altsetting->desc.bNumEndpoints < 1) {
 		dev_err(&usbinterface->dev,
 			"Invalid number of endpoints\n");
 		error = -EINVAL;
 		goto err_free_urb;
 	}
 
-	/*
-	 * The endpoint is always altsetting 0, we know this since we know
-	 * this device only has one interrupt endpoint
-	 */
-	endpoint = &usbinterface->altsetting[0].endpoint[0].desc;
+	endpoint = &usbinterface->cur_altsetting->endpoint[0].desc;
 
 	/* Some debug */
 	dev_dbg(&usbinterface->dev, "gtco # interfaces: %d\n", usbinterface->num_altsetting);
@@ -973,7 +969,7 @@ static int gtco_probe(struct usb_interface *usbinterface,
 	input_dev->dev.parent = &usbinterface->dev;
 
 	/* Setup the URB, it will be posted later on open of input device */
-	endpoint = &usbinterface->altsetting[0].endpoint[0].desc;
+	endpoint = &usbinterface->cur_altsetting->endpoint[0].desc;
 
 	usb_fill_int_urb(gtco->urbinfo,
 			 udev,
diff --git a/drivers/input/tablet/pegasus_notetaker.c b/drivers/input/tablet/pegasus_notetaker.c
index a1f3a0cb197e..38f087404f7a 100644
--- a/drivers/input/tablet/pegasus_notetaker.c
+++ b/drivers/input/tablet/pegasus_notetaker.c
@@ -275,7 +275,7 @@ static int pegasus_probe(struct usb_interface *intf,
 		return -ENODEV;
 
 	/* Sanity check that the device has an endpoint */
-	if (intf->altsetting[0].desc.bNumEndpoints < 1) {
+	if (intf->cur_altsetting->desc.bNumEndpoints < 1) {
 		dev_err(&intf->dev, "Invalid number of endpoints\n");
 		return -EINVAL;
 	}
diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c
index c639ebce914c..d123bd56b657 100644
--- a/drivers/input/touchscreen/edt-ft5x06.c
+++ b/drivers/input/touchscreen/edt-ft5x06.c
@@ -941,19 +941,25 @@ static void edt_ft5x06_ts_get_defaults(struct device *dev,
 
 	error = device_property_read_u32(dev, "offset", &val);
 	if (!error) {
-		edt_ft5x06_register_write(tsdata, reg_addr->reg_offset, val);
+		if (reg_addr->reg_offset != NO_REGISTER)
+			edt_ft5x06_register_write(tsdata,
+						  reg_addr->reg_offset, val);
 		tsdata->offset = val;
 	}
 
 	error = device_property_read_u32(dev, "offset-x", &val);
 	if (!error) {
-		edt_ft5x06_register_write(tsdata, reg_addr->reg_offset_x, val);
+		if (reg_addr->reg_offset_x != NO_REGISTER)
+			edt_ft5x06_register_write(tsdata,
+						  reg_addr->reg_offset_x, val);
 		tsdata->offset_x = val;
 	}
 
 	error = device_property_read_u32(dev, "offset-y", &val);
 	if (!error) {
-		edt_ft5x06_register_write(tsdata, reg_addr->reg_offset_y, val);
+		if (reg_addr->reg_offset_y != NO_REGISTER)
+			edt_ft5x06_register_write(tsdata,
+						  reg_addr->reg_offset_y, val);
 		tsdata->offset_y = val;
 	}
 }
@@ -1047,6 +1053,7 @@ static int edt_ft5x06_ts_probe(struct i2c_client *client,
 {
 	const struct edt_i2c_chip_data *chip_data;
 	struct edt_ft5x06_ts_data *tsdata;
+	u8 buf[2] = { 0xfc, 0x00 };
 	struct input_dev *input;
 	unsigned long irq_flags;
 	int error;
@@ -1116,6 +1123,12 @@ static int edt_ft5x06_ts_probe(struct i2c_client *client,
 		return error;
 	}
 
+	/*
+	 * Dummy read access. EP0700MLP1 returns bogus data on the first
+	 * register read access and ignores writes.
+	 */
+	edt_ft5x06_ts_readwrite(tsdata->client, 2, buf, 2, buf);
+
 	edt_ft5x06_ts_set_regs(tsdata);
 	edt_ft5x06_ts_get_defaults(&client->dev, tsdata);
 	edt_ft5x06_ts_get_parameters(tsdata);
diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c
index b99ace9b9a0e..ab18cc298d76 100644
--- a/drivers/input/touchscreen/goodix.c
+++ b/drivers/input/touchscreen/goodix.c
@@ -153,6 +153,22 @@ static const struct dmi_system_id rotated_screen[] = {
 	{}
 };
 
+/*
+ * Those tablets have their x coordinate inverted
+ */
+static const struct dmi_system_id inverted_x_screen[] = {
+#if defined(CONFIG_DMI) && defined(CONFIG_X86)
+	{
+		.ident = "Cube I15-TC",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Cube"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "I15-TC")
+		},
+	},
+#endif
+	{}
+};
+
 /**
  * goodix_i2c_read - read data from a register of the i2c slave device.
  *
@@ -739,6 +755,12 @@ static int goodix_configure_dev(struct goodix_ts_data *ts)
 			"Applying '180 degrees rotated screen' quirk\n");
 	}
 
+	if (dmi_check_system(inverted_x_screen)) {
+		ts->prop.invert_x = true;
+		dev_dbg(&ts->client->dev,
+			"Applying 'inverted x screen' quirk\n");
+	}
+
 	error = input_mt_init_slots(ts->input_dev, ts->max_touch_num,
 				    INPUT_MT_DIRECT | INPUT_MT_DROP_UNUSED);
 	if (error) {
diff --git a/drivers/input/touchscreen/mms114.c b/drivers/input/touchscreen/mms114.c
index a5ab774da4cc..fb28fd2d6f1c 100644
--- a/drivers/input/touchscreen/mms114.c
+++ b/drivers/input/touchscreen/mms114.c
@@ -54,6 +54,7 @@
 enum mms_type {
 	TYPE_MMS114	= 114,
 	TYPE_MMS152	= 152,
+	TYPE_MMS345L	= 345,
 };
 
 struct mms114_data {
@@ -91,15 +92,15 @@ static int __mms114_read_reg(struct mms114_data *data, unsigned int reg,
 	if (reg <= MMS114_MODE_CONTROL && reg + len > MMS114_MODE_CONTROL)
 		BUG();
 
-	/* Write register: use repeated start */
+	/* Write register */
 	xfer[0].addr = client->addr;
-	xfer[0].flags = I2C_M_TEN | I2C_M_NOSTART;
+	xfer[0].flags = client->flags & I2C_M_TEN;
 	xfer[0].len = 1;
 	xfer[0].buf = &buf;
 
 	/* Read data */
 	xfer[1].addr = client->addr;
-	xfer[1].flags = I2C_M_RD;
+	xfer[1].flags = (client->flags & I2C_M_TEN) | I2C_M_RD;
 	xfer[1].len = len;
 	xfer[1].buf = val;
 
@@ -250,6 +251,15 @@ static int mms114_get_version(struct mms114_data *data)
 	int error;
 
 	switch (data->type) {
+	case TYPE_MMS345L:
+		error = __mms114_read_reg(data, MMS152_FW_REV, 3, buf);
+		if (error)
+			return error;
+
+		dev_info(dev, "TSP FW Rev: bootloader 0x%x / core 0x%x / config 0x%x\n",
+			 buf[0], buf[1], buf[2]);
+		break;
+
 	case TYPE_MMS152:
 		error = __mms114_read_reg(data, MMS152_FW_REV, 3, buf);
 		if (error)
@@ -287,8 +297,8 @@ static int mms114_setup_regs(struct mms114_data *data)
 	if (error < 0)
 		return error;
 
-	/* MMS152 has no configuration or power on registers */
-	if (data->type == TYPE_MMS152)
+	/* Only MMS114 has configuration and power on registers */
+	if (data->type != TYPE_MMS114)
 		return 0;
 
 	error = mms114_set_active(data, true);
@@ -428,10 +438,8 @@ static int mms114_probe(struct i2c_client *client,
 	const void *match_data;
 	int error;
 
-	if (!i2c_check_functionality(client->adapter,
-				I2C_FUNC_PROTOCOL_MANGLING)) {
-		dev_err(&client->dev,
-			"Need i2c bus that supports protocol mangling\n");
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
+		dev_err(&client->dev, "Not supported I2C adapter\n");
 		return -ENODEV;
 	}
 
@@ -600,6 +608,9 @@ static const struct of_device_id mms114_dt_match[] = {
 	}, {
 		.compatible = "melfas,mms152",
 		.data = (void *)TYPE_MMS152,
+	}, {
+		.compatible = "melfas,mms345l",
+		.data = (void *)TYPE_MMS345L,
 	},
 	{ }
 };
diff --git a/drivers/input/touchscreen/raydium_i2c_ts.c b/drivers/input/touchscreen/raydium_i2c_ts.c
index 6ed9f22e6401..fe245439adee 100644
--- a/drivers/input/touchscreen/raydium_i2c_ts.c
+++ b/drivers/input/touchscreen/raydium_i2c_ts.c
@@ -432,7 +432,7 @@ static int raydium_i2c_write_object(struct i2c_client *client,
 	return 0;
 }
 
-static bool raydium_i2c_boot_trigger(struct i2c_client *client)
+static int raydium_i2c_boot_trigger(struct i2c_client *client)
 {
 	static const u8 cmd[7][6] = {
 		{ 0x08, 0x0C, 0x09, 0x00, 0x50, 0xD7 },
@@ -457,10 +457,10 @@ static bool raydium_i2c_boot_trigger(struct i2c_client *client)
 		}
 	}
 
-	return false;
+	return 0;
 }
 
-static bool raydium_i2c_fw_trigger(struct i2c_client *client)
+static int raydium_i2c_fw_trigger(struct i2c_client *client)
 {
 	static const u8 cmd[5][11] = {
 		{ 0, 0x09, 0x71, 0x0C, 0x09, 0x00, 0x50, 0xD7, 0, 0, 0 },
@@ -483,7 +483,7 @@ static bool raydium_i2c_fw_trigger(struct i2c_client *client)
 		}
 	}
 
-	return false;
+	return 0;
 }
 
 static int raydium_i2c_check_path(struct i2c_client *client)
diff --git a/drivers/input/touchscreen/sun4i-ts.c b/drivers/input/touchscreen/sun4i-ts.c
index 92f6e1ae23a2..b328066bed9a 100644
--- a/drivers/input/touchscreen/sun4i-ts.c
+++ b/drivers/input/touchscreen/sun4i-ts.c
@@ -237,6 +237,7 @@ static int sun4i_ts_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
 	struct device *hwmon;
+	struct thermal_zone_device *thermal;
 	int error;
 	u32 reg;
 	bool ts_attached;
@@ -356,7 +357,10 @@ static int sun4i_ts_probe(struct platform_device *pdev)
 	if (IS_ERR(hwmon))
 		return PTR_ERR(hwmon);
 
-	devm_thermal_zone_of_sensor_register(ts->dev, 0, ts, &sun4i_ts_tz_ops);
+	thermal = devm_thermal_zone_of_sensor_register(ts->dev, 0, ts,
+						       &sun4i_ts_tz_ops);
+	if (IS_ERR(thermal))
+		return PTR_ERR(thermal);
 
 	writel(TEMP_IRQ_EN(1), ts->base + TP_INT_FIFOC);
 
diff --git a/drivers/input/touchscreen/sur40.c b/drivers/input/touchscreen/sur40.c
index 8c8ac4dff0d5..fb252b3ad4ed 100644
--- a/drivers/input/touchscreen/sur40.c
+++ b/drivers/input/touchscreen/sur40.c
@@ -653,7 +653,7 @@ static int sur40_probe(struct usb_interface *interface,
 	int error;
 
 	/* Check if we really have the right interface. */
-	iface_desc = &interface->altsetting[0];
+	iface_desc = interface->cur_altsetting;
 	if (iface_desc->desc.bInterfaceClass != 0xFF)
 		return -ENODEV;
 
diff --git a/drivers/input/touchscreen/usbtouchscreen.c b/drivers/input/touchscreen/usbtouchscreen.c
index 16d70201de4a..397cb1d3f481 100644
--- a/drivers/input/touchscreen/usbtouchscreen.c
+++ b/drivers/input/touchscreen/usbtouchscreen.c
@@ -182,6 +182,7 @@ static const struct usb_device_id usbtouch_devices[] = {
 #endif
 
 #ifdef CONFIG_TOUCHSCREEN_USB_IRTOUCH
+	{USB_DEVICE(0x255e, 0x0001), .driver_info = DEVTYPE_IRTOUCH},
 	{USB_DEVICE(0x595a, 0x0001), .driver_info = DEVTYPE_IRTOUCH},
 	{USB_DEVICE(0x6615, 0x0001), .driver_info = DEVTYPE_IRTOUCH},
 	{USB_DEVICE(0x6615, 0x0012), .driver_info = DEVTYPE_IRTOUCH_HIRES},
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 83664db5221d..c255fc8c7f8a 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -204,7 +204,7 @@ config INTEL_IOMMU_DEBUGFS
 
 config INTEL_IOMMU_SVM
 	bool "Support for Shared Virtual Memory with Intel IOMMU"
-	depends on INTEL_IOMMU && X86
+	depends on INTEL_IOMMU && X86_64
 	select PCI_PASID
 	select MMU_NOTIFIER
 	help
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 909a97da6595..78bd2eb3c422 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -226,71 +226,58 @@ static struct iommu_dev_data *search_dev_data(u16 devid)
 	return NULL;
 }
 
-static int __last_alias(struct pci_dev *pdev, u16 alias, void *data)
+static int clone_alias(struct pci_dev *pdev, u16 alias, void *data)
 {
-	*(u16 *)data = alias;
-	return 0;
-}
-
-static u16 get_alias(struct device *dev)
-{
-	struct pci_dev *pdev = to_pci_dev(dev);
-	u16 devid, ivrs_alias, pci_alias;
-
-	/* The callers make sure that get_device_id() does not fail here */
-	devid = get_device_id(dev);
+	u16 devid = pci_dev_id(pdev);
 
-	/* For ACPI HID devices, we simply return the devid as such */
-	if (!dev_is_pci(dev))
-		return devid;
+	if (devid == alias)
+		return 0;
 
-	ivrs_alias = amd_iommu_alias_table[devid];
+	amd_iommu_rlookup_table[alias] =
+		amd_iommu_rlookup_table[devid];
+	memcpy(amd_iommu_dev_table[alias].data,
+	       amd_iommu_dev_table[devid].data,
+	       sizeof(amd_iommu_dev_table[alias].data));
 
-	pci_for_each_dma_alias(pdev, __last_alias, &pci_alias);
+	return 0;
+}
 
-	if (ivrs_alias == pci_alias)
-		return ivrs_alias;
+static void clone_aliases(struct pci_dev *pdev)
+{
+	if (!pdev)
+		return;
 
 	/*
-	 * DMA alias showdown
-	 *
-	 * The IVRS is fairly reliable in telling us about aliases, but it
-	 * can't know about every screwy device.  If we don't have an IVRS
-	 * reported alias, use the PCI reported alias.  In that case we may
-	 * still need to initialize the rlookup and dev_table entries if the
-	 * alias is to a non-existent device.
+	 * The IVRS alias stored in the alias table may not be
+	 * part of the PCI DMA aliases if it's bus differs
+	 * from the original device.
 	 */
-	if (ivrs_alias == devid) {
-		if (!amd_iommu_rlookup_table[pci_alias]) {
-			amd_iommu_rlookup_table[pci_alias] =
-				amd_iommu_rlookup_table[devid];
-			memcpy(amd_iommu_dev_table[pci_alias].data,
-			       amd_iommu_dev_table[devid].data,
-			       sizeof(amd_iommu_dev_table[pci_alias].data));
-		}
+	clone_alias(pdev, amd_iommu_alias_table[pci_dev_id(pdev)], NULL);
 
-		return pci_alias;
-	}
+	pci_for_each_dma_alias(pdev, clone_alias, NULL);
+}
+
+static struct pci_dev *setup_aliases(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	u16 ivrs_alias;
 
-	pci_info(pdev, "Using IVRS reported alias %02x:%02x.%d "
-		"for device [%04x:%04x], kernel reported alias "
-		"%02x:%02x.%d\n", PCI_BUS_NUM(ivrs_alias), PCI_SLOT(ivrs_alias),
-		PCI_FUNC(ivrs_alias), pdev->vendor, pdev->device,
-		PCI_BUS_NUM(pci_alias), PCI_SLOT(pci_alias),
-		PCI_FUNC(pci_alias));
+	/* For ACPI HID devices, there are no aliases */
+	if (!dev_is_pci(dev))
+		return NULL;
 
 	/*
-	 * If we don't have a PCI DMA alias and the IVRS alias is on the same
-	 * bus, then the IVRS table may know about a quirk that we don't.
+	 * Add the IVRS alias to the pci aliases if it is on the same
+	 * bus. The IVRS table may know about a quirk that we don't.
 	 */
-	if (pci_alias == devid &&
-	    PCI_BUS_NUM(ivrs_alias) == pdev->bus->number) {
-		pci_add_dma_alias(pdev, ivrs_alias & 0xff);
-		pci_info(pdev, "Added PCI DMA alias %02x.%d\n",
-			PCI_SLOT(ivrs_alias), PCI_FUNC(ivrs_alias));
-	}
+	ivrs_alias = amd_iommu_alias_table[pci_dev_id(pdev)];
+	if (ivrs_alias != pci_dev_id(pdev) &&
+	    PCI_BUS_NUM(ivrs_alias) == pdev->bus->number)
+		pci_add_dma_alias(pdev, ivrs_alias & 0xff, 1);
 
-	return ivrs_alias;
+	clone_aliases(pdev);
+
+	return pdev;
 }
 
 static struct iommu_dev_data *find_dev_data(u16 devid)
@@ -428,7 +415,7 @@ static int iommu_init_device(struct device *dev)
 	if (!dev_data)
 		return -ENOMEM;
 
-	dev_data->alias = get_alias(dev);
+	dev_data->pdev = setup_aliases(dev);
 
 	/*
 	 * By default we use passthrough mode for IOMMUv2 capable device.
@@ -453,20 +440,16 @@ static int iommu_init_device(struct device *dev)
 
 static void iommu_ignore_device(struct device *dev)
 {
-	u16 alias;
 	int devid;
 
 	devid = get_device_id(dev);
 	if (devid < 0)
 		return;
 
-	alias = get_alias(dev);
-
+	amd_iommu_rlookup_table[devid] = NULL;
 	memset(&amd_iommu_dev_table[devid], 0, sizeof(struct dev_table_entry));
-	memset(&amd_iommu_dev_table[alias], 0, sizeof(struct dev_table_entry));
 
-	amd_iommu_rlookup_table[devid] = NULL;
-	amd_iommu_rlookup_table[alias] = NULL;
+	setup_aliases(dev);
 }
 
 static void iommu_uninit_device(struct device *dev)
@@ -1212,6 +1195,13 @@ static int device_flush_iotlb(struct iommu_dev_data *dev_data,
 	return iommu_queue_command(iommu, &cmd);
 }
 
+static int device_flush_dte_alias(struct pci_dev *pdev, u16 alias, void *data)
+{
+	struct amd_iommu *iommu = data;
+
+	return iommu_flush_dte(iommu, alias);
+}
+
 /*
  * Command send function for invalidating a device table entry
  */
@@ -1222,14 +1212,22 @@ static int device_flush_dte(struct iommu_dev_data *dev_data)
 	int ret;
 
 	iommu = amd_iommu_rlookup_table[dev_data->devid];
-	alias = dev_data->alias;
 
-	ret = iommu_flush_dte(iommu, dev_data->devid);
-	if (!ret && alias != dev_data->devid)
-		ret = iommu_flush_dte(iommu, alias);
+	if (dev_data->pdev)
+		ret = pci_for_each_dma_alias(dev_data->pdev,
+					     device_flush_dte_alias, iommu);
+	else
+		ret = iommu_flush_dte(iommu, dev_data->devid);
 	if (ret)
 		return ret;
 
+	alias = amd_iommu_alias_table[dev_data->devid];
+	if (alias != dev_data->devid) {
+		ret = iommu_flush_dte(iommu, alias);
+		if (ret)
+			return ret;
+	}
+
 	if (dev_data->ats.enabled)
 		ret = device_flush_iotlb(dev_data, 0, ~0UL);
 
@@ -1426,6 +1424,7 @@ static void free_pagetable(struct protection_domain *domain)
  * to 64 bits.
  */
 static void increase_address_space(struct protection_domain *domain,
+				   unsigned long address,
 				   gfp_t gfp)
 {
 	unsigned long flags;
@@ -1433,8 +1432,8 @@ static void increase_address_space(struct protection_domain *domain,
 
 	spin_lock_irqsave(&domain->lock, flags);
 
-	if (WARN_ON_ONCE(domain->mode == PAGE_MODE_6_LEVEL))
-		/* address space already 64 bit large */
+	if (address <= PM_LEVEL_SIZE(domain->mode) ||
+	    WARN_ON_ONCE(domain->mode == PAGE_MODE_6_LEVEL))
 		goto out;
 
 	pte = (void *)get_zeroed_page(gfp);
@@ -1465,7 +1464,7 @@ static u64 *alloc_pte(struct protection_domain *domain,
 	BUG_ON(!is_power_of_2(page_size));
 
 	while (address > PM_LEVEL_SIZE(domain->mode))
-		increase_address_space(domain, gfp);
+		increase_address_space(domain, address, gfp);
 
 	level   = domain->mode - 1;
 	pte     = &domain->pt_root[PM_LEVEL_INDEX(level, address)];
@@ -1960,11 +1959,9 @@ static void do_attach(struct iommu_dev_data *dev_data,
 		      struct protection_domain *domain)
 {
 	struct amd_iommu *iommu;
-	u16 alias;
 	bool ats;
 
 	iommu = amd_iommu_rlookup_table[dev_data->devid];
-	alias = dev_data->alias;
 	ats   = dev_data->ats.enabled;
 
 	/* Update data structures */
@@ -1977,8 +1974,7 @@ static void do_attach(struct iommu_dev_data *dev_data,
 
 	/* Update device table */
 	set_dte_entry(dev_data->devid, domain, ats, dev_data->iommu_v2);
-	if (alias != dev_data->devid)
-		set_dte_entry(alias, domain, ats, dev_data->iommu_v2);
+	clone_aliases(dev_data->pdev);
 
 	device_flush_dte(dev_data);
 }
@@ -1987,17 +1983,14 @@ static void do_detach(struct iommu_dev_data *dev_data)
 {
 	struct protection_domain *domain = dev_data->domain;
 	struct amd_iommu *iommu;
-	u16 alias;
 
 	iommu = amd_iommu_rlookup_table[dev_data->devid];
-	alias = dev_data->alias;
 
 	/* Update data structures */
 	dev_data->domain = NULL;
 	list_del(&dev_data->list);
 	clear_dte_entry(dev_data->devid);
-	if (alias != dev_data->devid)
-		clear_dte_entry(alias);
+	clone_aliases(dev_data->pdev);
 
 	/* Flush the DTE entry */
 	device_flush_dte(dev_data);
@@ -2333,13 +2326,7 @@ static void update_device_table(struct protection_domain *domain)
 	list_for_each_entry(dev_data, &domain->dev_list, list) {
 		set_dte_entry(dev_data->devid, domain, dev_data->ats.enabled,
 			      dev_data->iommu_v2);
-
-		if (dev_data->devid == dev_data->alias)
-			continue;
-
-		/* There is an alias, update device table entry for it */
-		set_dte_entry(dev_data->alias, domain, dev_data->ats.enabled,
-			      dev_data->iommu_v2);
+		clone_aliases(dev_data->pdev);
 	}
 }
 
@@ -2354,6 +2341,7 @@ static void update_domain(struct protection_domain *domain)
 	domain_flush_tlb_pde(domain);
 
 	domain->updated = false;
+	domain_flush_complete(domain);
 }
 
 static int dir2prot(enum dma_data_direction direction)
@@ -3693,7 +3681,20 @@ static void set_remap_table_entry(struct amd_iommu *iommu, u16 devid,
 	iommu_flush_dte(iommu, devid);
 }
 
-static struct irq_remap_table *alloc_irq_table(u16 devid)
+static int set_remap_table_entry_alias(struct pci_dev *pdev, u16 alias,
+				       void *data)
+{
+	struct irq_remap_table *table = data;
+
+	irq_lookup_table[alias] = table;
+	set_dte_irq_entry(alias, table);
+
+	iommu_flush_dte(amd_iommu_rlookup_table[alias], alias);
+
+	return 0;
+}
+
+static struct irq_remap_table *alloc_irq_table(u16 devid, struct pci_dev *pdev)
 {
 	struct irq_remap_table *table = NULL;
 	struct irq_remap_table *new_table = NULL;
@@ -3739,7 +3740,12 @@ static struct irq_remap_table *alloc_irq_table(u16 devid)
 	table = new_table;
 	new_table = NULL;
 
-	set_remap_table_entry(iommu, devid, table);
+	if (pdev)
+		pci_for_each_dma_alias(pdev, set_remap_table_entry_alias,
+				       table);
+	else
+		set_remap_table_entry(iommu, devid, table);
+
 	if (devid != alias)
 		set_remap_table_entry(iommu, alias, table);
 
@@ -3756,7 +3762,8 @@ out_unlock:
 	return table;
 }
 
-static int alloc_irq_index(u16 devid, int count, bool align)
+static int alloc_irq_index(u16 devid, int count, bool align,
+			   struct pci_dev *pdev)
 {
 	struct irq_remap_table *table;
 	int index, c, alignment = 1;
@@ -3766,7 +3773,7 @@ static int alloc_irq_index(u16 devid, int count, bool align)
 	if (!iommu)
 		return -ENODEV;
 
-	table = alloc_irq_table(devid);
+	table = alloc_irq_table(devid, pdev);
 	if (!table)
 		return -ENODEV;
 
@@ -4199,7 +4206,7 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
 		struct irq_remap_table *table;
 		struct amd_iommu *iommu;
 
-		table = alloc_irq_table(devid);
+		table = alloc_irq_table(devid, NULL);
 		if (table) {
 			if (!table->min_index) {
 				/*
@@ -4216,11 +4223,15 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
 		} else {
 			index = -ENOMEM;
 		}
-	} else {
+	} else if (info->type == X86_IRQ_ALLOC_TYPE_MSI ||
+		   info->type == X86_IRQ_ALLOC_TYPE_MSIX) {
 		bool align = (info->type == X86_IRQ_ALLOC_TYPE_MSI);
 
-		index = alloc_irq_index(devid, nr_irqs, align);
+		index = alloc_irq_index(devid, nr_irqs, align, info->msi_dev);
+	} else {
+		index = alloc_irq_index(devid, nr_irqs, false, NULL);
 	}
+
 	if (index < 0) {
 		pr_warn("Failed to allocate IRTE\n");
 		ret = index;
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 6469f5128242..248e5dcb25a9 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -1326,8 +1326,8 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu,
 		}
 		case IVHD_DEV_ACPI_HID: {
 			u16 devid;
-			u8 hid[ACPIHID_HID_LEN] = {0};
-			u8 uid[ACPIHID_UID_LEN] = {0};
+			u8 hid[ACPIHID_HID_LEN];
+			u8 uid[ACPIHID_UID_LEN];
 			int ret;
 
 			if (h->type != 0x40) {
@@ -1344,6 +1344,7 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu,
 				break;
 			}
 
+			uid[0] = '\0';
 			switch (e->uidf) {
 			case UID_NOT_PRESENT:
 
@@ -1358,8 +1359,8 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu,
 				break;
 			case UID_IS_CHARACTER:
 
-				memcpy(uid, (u8 *)(&e->uid), ACPIHID_UID_LEN - 1);
-				uid[ACPIHID_UID_LEN - 1] = '\0';
+				memcpy(uid, &e->uid, e->uidl);
+				uid[e->uidl] = '\0';
 
 				break;
 			default:
@@ -1650,27 +1651,39 @@ static int iommu_pc_get_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
 static void init_iommu_perf_ctr(struct amd_iommu *iommu)
 {
 	struct pci_dev *pdev = iommu->dev;
-	u64 val = 0xabcd, val2 = 0;
+	u64 val = 0xabcd, val2 = 0, save_reg = 0;
 
 	if (!iommu_feature(iommu, FEATURE_PC))
 		return;
 
 	amd_iommu_pc_present = true;
 
+	/* save the value to restore, if writable */
+	if (iommu_pc_get_set_reg(iommu, 0, 0, 0, &save_reg, false))
+		goto pc_false;
+
 	/* Check if the performance counters can be written to */
 	if ((iommu_pc_get_set_reg(iommu, 0, 0, 0, &val, true)) ||
 	    (iommu_pc_get_set_reg(iommu, 0, 0, 0, &val2, false)) ||
-	    (val != val2)) {
-		pci_err(pdev, "Unable to write to IOMMU perf counter.\n");
-		amd_iommu_pc_present = false;
-		return;
-	}
+	    (val != val2))
+		goto pc_false;
+
+	/* restore */
+	if (iommu_pc_get_set_reg(iommu, 0, 0, 0, &save_reg, true))
+		goto pc_false;
 
 	pci_info(pdev, "IOMMU performance counters supported\n");
 
 	val = readl(iommu->mmio_base + MMIO_CNTR_CONF_OFFSET);
 	iommu->max_banks = (u8) ((val >> 12) & 0x3f);
 	iommu->max_counters = (u8) ((val >> 7) & 0xf);
+
+	return;
+
+pc_false:
+	pci_err(pdev, "Unable to read/write to IOMMU perf counter.\n");
+	amd_iommu_pc_present = false;
+	return;
 }
 
 static ssize_t amd_iommu_show_cap(struct device *dev,
@@ -2432,6 +2445,7 @@ static int __init early_amd_iommu_init(void)
 	struct acpi_table_header *ivrs_base;
 	acpi_status status;
 	int i, remap_cache_sz, ret = 0;
+	u32 pci_id;
 
 	if (!amd_iommu_detected)
 		return -ENODEV;
@@ -2519,6 +2533,16 @@ static int __init early_amd_iommu_init(void)
 	if (ret)
 		goto out;
 
+	/* Disable IOMMU if there's Stoney Ridge graphics */
+	for (i = 0; i < 32; i++) {
+		pci_id = read_pci_config(0, i, 0, 0);
+		if ((pci_id & 0xffff) == 0x1002 && (pci_id >> 16) == 0x98e4) {
+			pr_info("Disable IOMMU on Stoney Ridge\n");
+			amd_iommu_disabled = true;
+			break;
+		}
+	}
+
 	/* Disable any previously enabled IOMMUs */
 	if (!is_kdump_kernel() || amd_iommu_disabled)
 		disable_iommus();
@@ -2627,7 +2651,7 @@ static int __init state_next(void)
 		ret = early_amd_iommu_init();
 		init_state = ret ? IOMMU_INIT_ERROR : IOMMU_ACPI_FINISHED;
 		if (init_state == IOMMU_ACPI_FINISHED && amd_iommu_disabled) {
-			pr_info("AMD IOMMU disabled on kernel command-line\n");
+			pr_info("AMD IOMMU disabled\n");
 			free_dma_resources();
 			free_iommu_resources();
 			init_state = IOMMU_CMDLINE_DISABLED;
@@ -2825,7 +2849,7 @@ static int __init parse_amd_iommu_intr(char *str)
 {
 	for (; *str; ++str) {
 		if (strncmp(str, "legacy", 6) == 0) {
-			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY;
+			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY_GA;
 			break;
 		}
 		if (strncmp(str, "vapic", 5) == 0) {
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index 52c35d557fad..e8cb05dcb612 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -341,7 +341,7 @@
 
 #define DTE_GCR3_VAL_A(x)	(((x) >> 12) & 0x00007ULL)
 #define DTE_GCR3_VAL_B(x)	(((x) >> 15) & 0x0ffffULL)
-#define DTE_GCR3_VAL_C(x)	(((x) >> 31) & 0xfffffULL)
+#define DTE_GCR3_VAL_C(x)	(((x) >> 31) & 0x1fffffULL)
 
 #define DTE_GCR3_INDEX_A	0
 #define DTE_GCR3_INDEX_B	1
@@ -628,8 +628,8 @@ struct iommu_dev_data {
 	struct list_head list;		  /* For domain->dev_list */
 	struct llist_node dev_data_list;  /* For global dev_data_list */
 	struct protection_domain *domain; /* Domain the device is bound to */
+	struct pci_dev *pdev;
 	u16 devid;			  /* PCI Device ID */
-	u16 alias;			  /* Alias Device ID */
 	bool iommu_v2;			  /* Device can make use of IOMMUv2 */
 	bool passthrough;		  /* Device is identity mapped */
 	struct {
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index be788aee14e7..ec146b1ff699 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -826,6 +826,7 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
 		cmd[1] |= FIELD_PREP(CMDQ_CFGI_1_RANGE, 31);
 		break;
 	case CMDQ_OP_TLBI_NH_VA:
+		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid);
 		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_ASID, ent->tlbi.asid);
 		cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_LEAF, ent->tlbi.leaf);
 		cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_VA_MASK;
@@ -1256,7 +1257,8 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 						 STRTAB_STE_1_EATS_TRANS));
 
 	arm_smmu_sync_ste_for_sid(smmu, sid);
-	dst[0] = cpu_to_le64(val);
+	/* See comment in arm_smmu_write_ctx_desc() */
+	WRITE_ONCE(dst[0], cpu_to_le64(val));
 	arm_smmu_sync_ste_for_sid(smmu, sid);
 
 	/* It's likely that we'll want to use the new STE soon */
@@ -3118,19 +3120,19 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 
 	/* Interrupt lines */
 
-	irq = platform_get_irq_byname(pdev, "combined");
+	irq = platform_get_irq_byname_optional(pdev, "combined");
 	if (irq > 0)
 		smmu->combined_irq = irq;
 	else {
-		irq = platform_get_irq_byname(pdev, "eventq");
+		irq = platform_get_irq_byname_optional(pdev, "eventq");
 		if (irq > 0)
 			smmu->evtq.q.irq = irq;
 
-		irq = platform_get_irq_byname(pdev, "priq");
+		irq = platform_get_irq_byname_optional(pdev, "priq");
 		if (irq > 0)
 			smmu->priq.q.irq = irq;
 
-		irq = platform_get_irq_byname(pdev, "gerror");
+		irq = platform_get_irq_byname_optional(pdev, "gerror");
 		if (irq > 0)
 			smmu->gerr_irq = irq;
 	}
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 586dd5a46d9f..cdb7bc788a37 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -2226,10 +2226,8 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 	for (i = 0; i < num_irqs; ++i) {
 		int irq = platform_get_irq(pdev, i);
 
-		if (irq < 0) {
-			dev_err(dev, "failed to get irq index %d\n", i);
+		if (irq < 0)
 			return -ENODEV;
-		}
 		smmu->irqs[i] = irq;
 	}
 
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 8c02d2283d64..53f7cfe9b0a9 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -17,6 +17,7 @@
 #include <linux/iova.h>
 #include <linux/irq.h>
 #include <linux/mm.h>
+#include <linux/mutex.h>
 #include <linux/pci.h>
 #include <linux/scatterlist.h>
 #include <linux/vmalloc.h>
@@ -41,7 +42,6 @@ struct iommu_dma_cookie {
 		dma_addr_t		msi_iova;
 	};
 	struct list_head		msi_page_list;
-	spinlock_t			msi_lock;
 
 	/* Domain for flush queue callback; NULL if flush queue not in use */
 	struct iommu_domain		*fq_domain;
@@ -60,7 +60,6 @@ static struct iommu_dma_cookie *cookie_alloc(enum iommu_dma_cookie_type type)
 
 	cookie = kzalloc(sizeof(*cookie), GFP_KERNEL);
 	if (cookie) {
-		spin_lock_init(&cookie->msi_lock);
 		INIT_LIST_HEAD(&cookie->msi_page_list);
 		cookie->type = type;
 	}
@@ -180,15 +179,15 @@ static int cookie_init_hw_msi_region(struct iommu_dma_cookie *cookie,
 	start -= iova_offset(iovad, start);
 	num_pages = iova_align(iovad, end - start) >> iova_shift(iovad);
 
-	msi_page = kcalloc(num_pages, sizeof(*msi_page), GFP_KERNEL);
-	if (!msi_page)
-		return -ENOMEM;
-
 	for (i = 0; i < num_pages; i++) {
-		msi_page[i].phys = start;
-		msi_page[i].iova = start;
-		INIT_LIST_HEAD(&msi_page[i].list);
-		list_add(&msi_page[i].list, &cookie->msi_page_list);
+		msi_page = kmalloc(sizeof(*msi_page), GFP_KERNEL);
+		if (!msi_page)
+			return -ENOMEM;
+
+		msi_page->phys = start;
+		msi_page->iova = start;
+		INIT_LIST_HEAD(&msi_page->list);
+		list_add(&msi_page->list, &cookie->msi_page_list);
 		start += iovad->granule;
 	}
 
@@ -229,8 +228,8 @@ resv_iova:
 		start = window->res->end - window->offset + 1;
 		/* If window is last entry */
 		if (window->node.next == &bridge->dma_ranges &&
-		    end != ~(dma_addr_t)0) {
-			end = ~(dma_addr_t)0;
+		    end != ~(phys_addr_t)0) {
+			end = ~(phys_addr_t)0;
 			goto resv_iova;
 		}
 	}
@@ -877,7 +876,7 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
 		if (msi_page->phys == msi_addr)
 			return msi_page;
 
-	msi_page = kzalloc(sizeof(*msi_page), GFP_ATOMIC);
+	msi_page = kzalloc(sizeof(*msi_page), GFP_KERNEL);
 	if (!msi_page)
 		return NULL;
 
@@ -900,25 +899,22 @@ int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr)
 {
 	struct device *dev = msi_desc_to_dev(desc);
 	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
-	struct iommu_dma_cookie *cookie;
 	struct iommu_dma_msi_page *msi_page;
-	unsigned long flags;
+	static DEFINE_MUTEX(msi_prepare_lock); /* see below */
 
 	if (!domain || !domain->iova_cookie) {
 		desc->iommu_cookie = NULL;
 		return 0;
 	}
 
-	cookie = domain->iova_cookie;
-
 	/*
-	 * We disable IRQs to rule out a possible inversion against
-	 * irq_desc_lock if, say, someone tries to retarget the affinity
-	 * of an MSI from within an IPI handler.
+	 * In fact the whole prepare operation should already be serialised by
+	 * irq_domain_mutex further up the callchain, but that's pretty subtle
+	 * on its own, so consider this locking as failsafe documentation...
 	 */
-	spin_lock_irqsave(&cookie->msi_lock, flags);
+	mutex_lock(&msi_prepare_lock);
 	msi_page = iommu_dma_get_msi_page(dev, msi_addr, domain);
-	spin_unlock_irqrestore(&cookie->msi_lock, flags);
+	mutex_unlock(&msi_prepare_lock);
 
 	msi_desc_set_iommu_cookie(desc, msi_page);
 
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 5d0754ed5fa0..d6c28e96d691 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -28,6 +28,7 @@
 #include <linux/slab.h>
 #include <linux/iommu.h>
 #include <linux/numa.h>
+#include <linux/limits.h>
 #include <asm/irq_remapping.h>
 #include <asm/iommu_table.h>
 
@@ -128,6 +129,13 @@ dmar_alloc_pci_notify_info(struct pci_dev *dev, unsigned long event)
 
 	BUG_ON(dev->is_virtfn);
 
+	/*
+	 * Ignore devices that have a domain number higher than what can
+	 * be looked up in DMAR, e.g. VMD subdevices with domain 0x10000
+	 */
+	if (pci_domain_nr(dev->bus) > U16_MAX)
+		return NULL;
+
 	/* Only generate path[] for device addition event */
 	if (event == BUS_NOTIFY_ADD_DEVICE)
 		for (tmp = dev; tmp; tmp = tmp->bus->self)
@@ -363,7 +371,8 @@ dmar_find_dmaru(struct acpi_dmar_hardware_unit *drhd)
 {
 	struct dmar_drhd_unit *dmaru;
 
-	list_for_each_entry_rcu(dmaru, &dmar_drhd_units, list)
+	list_for_each_entry_rcu(dmaru, &dmar_drhd_units, list,
+				dmar_rcu_check())
 		if (dmaru->segment == drhd->segment &&
 		    dmaru->reg_base_addr == drhd->address)
 			return dmaru;
@@ -440,12 +449,13 @@ static int __init dmar_parse_one_andd(struct acpi_dmar_header *header,
 
 	/* Check for NUL termination within the designated length */
 	if (strnlen(andd->device_name, header->length - 8) == header->length - 8) {
-		WARN_TAINT(1, TAINT_FIRMWARE_WORKAROUND,
+		pr_warn(FW_BUG
 			   "Your BIOS is broken; ANDD object name is not NUL-terminated\n"
 			   "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
 			   dmi_get_system_info(DMI_BIOS_VENDOR),
 			   dmi_get_system_info(DMI_BIOS_VERSION),
 			   dmi_get_system_info(DMI_PRODUCT_VERSION));
+		add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
 		return -EINVAL;
 	}
 	pr_info("ANDD device: %x name: %s\n", andd->device_number,
@@ -471,14 +481,14 @@ static int dmar_parse_one_rhsa(struct acpi_dmar_header *header, void *arg)
 			return 0;
 		}
 	}
-	WARN_TAINT(
-		1, TAINT_FIRMWARE_WORKAROUND,
+	pr_warn(FW_BUG
 		"Your BIOS is broken; RHSA refers to non-existent DMAR unit at %llx\n"
 		"BIOS vendor: %s; Ver: %s; Product Version: %s\n",
-		drhd->reg_base_addr,
+		rhsa->base_address,
 		dmi_get_system_info(DMI_BIOS_VENDOR),
 		dmi_get_system_info(DMI_BIOS_VERSION),
 		dmi_get_system_info(DMI_PRODUCT_VERSION));
+	add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
 
 	return 0;
 }
@@ -827,14 +837,14 @@ int __init dmar_table_init(void)
 
 static void warn_invalid_dmar(u64 addr, const char *message)
 {
-	WARN_TAINT_ONCE(
-		1, TAINT_FIRMWARE_WORKAROUND,
+	pr_warn_once(FW_BUG
 		"Your BIOS is broken; DMAR reported at address %llx%s!\n"
 		"BIOS vendor: %s; Ver: %s; Product Version: %s\n",
 		addr, message,
 		dmi_get_system_info(DMI_BIOS_VENDOR),
 		dmi_get_system_info(DMI_BIOS_VERSION),
 		dmi_get_system_info(DMI_PRODUCT_VERSION));
+	add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
 }
 
 static int __ref
@@ -888,7 +898,8 @@ int __init detect_intel_iommu(void)
 	if (!ret)
 		ret = dmar_walk_dmar_table((struct acpi_table_dmar *)dmar_tbl,
 					   &validate_drhd_cb);
-	if (!ret && !no_iommu && !iommu_detected && !dmar_disabled) {
+	if (!ret && !no_iommu && !iommu_detected &&
+	    (!dmar_disabled || dmar_platform_optin())) {
 		iommu_detected = 1;
 		/* Make sure ACS will be enabled */
 		pci_request_acs();
@@ -1351,7 +1362,6 @@ void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid,
 	struct qi_desc desc;
 
 	if (mask) {
-		WARN_ON_ONCE(addr & ((1ULL << (VTD_PAGE_SHIFT + mask)) - 1));
 		addr |= (1ULL << (VTD_PAGE_SHIFT + mask - 1)) - 1;
 		desc.qw1 = QI_DEV_IOTLB_ADDR(addr) | QI_DEV_IOTLB_SIZE;
 	} else
diff --git a/drivers/iommu/intel-iommu-debugfs.c b/drivers/iommu/intel-iommu-debugfs.c
index 7fabf9b1c2dc..e077ceb0aae0 100644
--- a/drivers/iommu/intel-iommu-debugfs.c
+++ b/drivers/iommu/intel-iommu-debugfs.c
@@ -21,38 +21,42 @@ struct iommu_regset {
 
 #define IOMMU_REGSET_ENTRY(_reg_)					\
 	{ DMAR_##_reg_##_REG, __stringify(_reg_) }
-static const struct iommu_regset iommu_regs[] = {
+
+static const struct iommu_regset iommu_regs_32[] = {
 	IOMMU_REGSET_ENTRY(VER),
-	IOMMU_REGSET_ENTRY(CAP),
-	IOMMU_REGSET_ENTRY(ECAP),
 	IOMMU_REGSET_ENTRY(GCMD),
 	IOMMU_REGSET_ENTRY(GSTS),
-	IOMMU_REGSET_ENTRY(RTADDR),
-	IOMMU_REGSET_ENTRY(CCMD),
 	IOMMU_REGSET_ENTRY(FSTS),
 	IOMMU_REGSET_ENTRY(FECTL),
 	IOMMU_REGSET_ENTRY(FEDATA),
 	IOMMU_REGSET_ENTRY(FEADDR),
 	IOMMU_REGSET_ENTRY(FEUADDR),
-	IOMMU_REGSET_ENTRY(AFLOG),
 	IOMMU_REGSET_ENTRY(PMEN),
 	IOMMU_REGSET_ENTRY(PLMBASE),
 	IOMMU_REGSET_ENTRY(PLMLIMIT),
+	IOMMU_REGSET_ENTRY(ICS),
+	IOMMU_REGSET_ENTRY(PRS),
+	IOMMU_REGSET_ENTRY(PECTL),
+	IOMMU_REGSET_ENTRY(PEDATA),
+	IOMMU_REGSET_ENTRY(PEADDR),
+	IOMMU_REGSET_ENTRY(PEUADDR),
+};
+
+static const struct iommu_regset iommu_regs_64[] = {
+	IOMMU_REGSET_ENTRY(CAP),
+	IOMMU_REGSET_ENTRY(ECAP),
+	IOMMU_REGSET_ENTRY(RTADDR),
+	IOMMU_REGSET_ENTRY(CCMD),
+	IOMMU_REGSET_ENTRY(AFLOG),
 	IOMMU_REGSET_ENTRY(PHMBASE),
 	IOMMU_REGSET_ENTRY(PHMLIMIT),
 	IOMMU_REGSET_ENTRY(IQH),
 	IOMMU_REGSET_ENTRY(IQT),
 	IOMMU_REGSET_ENTRY(IQA),
-	IOMMU_REGSET_ENTRY(ICS),
 	IOMMU_REGSET_ENTRY(IRTA),
 	IOMMU_REGSET_ENTRY(PQH),
 	IOMMU_REGSET_ENTRY(PQT),
 	IOMMU_REGSET_ENTRY(PQA),
-	IOMMU_REGSET_ENTRY(PRS),
-	IOMMU_REGSET_ENTRY(PECTL),
-	IOMMU_REGSET_ENTRY(PEDATA),
-	IOMMU_REGSET_ENTRY(PEADDR),
-	IOMMU_REGSET_ENTRY(PEUADDR),
 	IOMMU_REGSET_ENTRY(MTRRCAP),
 	IOMMU_REGSET_ENTRY(MTRRDEF),
 	IOMMU_REGSET_ENTRY(MTRR_FIX64K_00000),
@@ -115,10 +119,16 @@ static int iommu_regset_show(struct seq_file *m, void *unused)
 		 * by adding the offset to the pointer (virtual address).
 		 */
 		raw_spin_lock_irqsave(&iommu->register_lock, flag);
-		for (i = 0 ; i < ARRAY_SIZE(iommu_regs); i++) {
-			value = dmar_readq(iommu->reg + iommu_regs[i].offset);
+		for (i = 0 ; i < ARRAY_SIZE(iommu_regs_32); i++) {
+			value = dmar_readl(iommu->reg + iommu_regs_32[i].offset);
+			seq_printf(m, "%-16s\t0x%02x\t\t0x%016llx\n",
+				   iommu_regs_32[i].regs, iommu_regs_32[i].offset,
+				   value);
+		}
+		for (i = 0 ; i < ARRAY_SIZE(iommu_regs_64); i++) {
+			value = dmar_readq(iommu->reg + iommu_regs_64[i].offset);
 			seq_printf(m, "%-16s\t0x%02x\t\t0x%016llx\n",
-				   iommu_regs[i].regs, iommu_regs[i].offset,
+				   iommu_regs_64[i].regs, iommu_regs_64[i].offset,
 				   value);
 		}
 		raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
@@ -182,9 +192,16 @@ static int dmar_translation_struct_show(struct seq_file *m, void *unused)
 {
 	struct dmar_drhd_unit *drhd;
 	struct intel_iommu *iommu;
+	u32 sts;
 
 	rcu_read_lock();
 	for_each_active_iommu(iommu, drhd) {
+		sts = dmar_readl(iommu->reg + DMAR_GSTS_REG);
+		if (!(sts & DMA_GSTS_TES)) {
+			seq_printf(m, "DMA Remapping is not enabled on %s\n",
+				   iommu->name);
+			continue;
+		}
 		root_tbl_entry_show(m, iommu);
 		seq_putc(m, '\n');
 	}
@@ -254,6 +271,7 @@ static int ir_translation_struct_show(struct seq_file *m, void *unused)
 	struct dmar_drhd_unit *drhd;
 	struct intel_iommu *iommu;
 	u64 irta;
+	u32 sts;
 
 	rcu_read_lock();
 	for_each_active_iommu(iommu, drhd) {
@@ -263,7 +281,8 @@ static int ir_translation_struct_show(struct seq_file *m, void *unused)
 		seq_printf(m, "Remapped Interrupt supported on IOMMU: %s\n",
 			   iommu->name);
 
-		if (iommu->ir_table) {
+		sts = dmar_readl(iommu->reg + DMAR_GSTS_REG);
+		if (iommu->ir_table && (sts & DMA_GSTS_IRES)) {
 			irta = virt_to_phys(iommu->ir_table->base);
 			seq_printf(m, " IR table address:%llx\n", irta);
 			ir_tbl_remap_entry_show(m, iommu);
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 1ad24367373f..f3685493a724 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -608,6 +608,12 @@ struct intel_iommu *domain_get_iommu(struct dmar_domain *domain)
 	return g_iommus[iommu_id];
 }
 
+static inline bool iommu_paging_structure_coherency(struct intel_iommu *iommu)
+{
+	return sm_supported(iommu) ?
+			ecap_smpwc(iommu->ecap) : ecap_coherent(iommu->ecap);
+}
+
 static void domain_update_iommu_coherency(struct dmar_domain *domain)
 {
 	struct dmar_drhd_unit *drhd;
@@ -619,7 +625,7 @@ static void domain_update_iommu_coherency(struct dmar_domain *domain)
 
 	for_each_domain_iommu(i, domain) {
 		found = true;
-		if (!ecap_coherent(g_iommus[i]->ecap)) {
+		if (!iommu_paging_structure_coherency(g_iommus[i])) {
 			domain->iommu_coherency = 0;
 			break;
 		}
@@ -630,7 +636,7 @@ static void domain_update_iommu_coherency(struct dmar_domain *domain)
 	/* No hardware attached; use lowest common denominator */
 	rcu_read_lock();
 	for_each_active_iommu(iommu, drhd) {
-		if (!ecap_coherent(iommu->ecap)) {
+		if (!iommu_paging_structure_coherency(iommu)) {
 			domain->iommu_coherency = 0;
 			break;
 		}
@@ -2089,7 +2095,8 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
 
 	context_set_fault_enable(context);
 	context_set_present(context);
-	domain_flush_cache(domain, context, sizeof(*context));
+	if (!ecap_coherent(iommu->ecap))
+		clflush_cache_range(context, sizeof(*context));
 
 	/*
 	 * It's a non-present to present mapping. If hardware doesn't cache
@@ -3558,7 +3565,8 @@ static unsigned long intel_alloc_iova(struct device *dev,
 	iova_pfn = alloc_iova_fast(&domain->iovad, nrpages,
 				   IOVA_PFN(dma_mask), true);
 	if (unlikely(!iova_pfn)) {
-		dev_err(dev, "Allocating %ld-page iova failed", nrpages);
+		dev_err_once(dev, "Allocating %ld-page iova failed\n",
+			     nrpages);
 		return 0;
 	}
 
@@ -4015,10 +4023,11 @@ static void quirk_ioat_snb_local_iommu(struct pci_dev *pdev)
 
 	/* we know that the this iommu should be at offset 0xa000 from vtbar */
 	drhd = dmar_find_matched_drhd_unit(pdev);
-	if (WARN_TAINT_ONCE(!drhd || drhd->reg_base_addr - vtbar != 0xa000,
-			    TAINT_FIRMWARE_WORKAROUND,
-			    "BIOS assigned incorrect VT-d unit for Intel(R) QuickData Technology device\n"))
+	if (!drhd || drhd->reg_base_addr - vtbar != 0xa000) {
+		pr_warn_once(FW_BUG "BIOS assigned incorrect VT-d unit for Intel(R) QuickData Technology device\n");
+		add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
 		pdev->dev.archdata.iommu = DUMMY_DEVICE_DOMAIN_INFO;
+	}
 }
 DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB, quirk_ioat_snb_local_iommu);
 
@@ -4242,7 +4251,8 @@ static struct dmar_atsr_unit *dmar_find_atsr(struct acpi_dmar_atsr *atsr)
 	struct dmar_atsr_unit *atsru;
 	struct acpi_dmar_atsr *tmp;
 
-	list_for_each_entry_rcu(atsru, &dmar_atsr_units, list) {
+	list_for_each_entry_rcu(atsru, &dmar_atsr_units, list,
+				dmar_rcu_check()) {
 		tmp = (struct acpi_dmar_atsr *)atsru->hdr;
 		if (atsr->segment != tmp->segment)
 			continue;
@@ -4856,6 +4866,9 @@ int __init intel_iommu_init(void)
 
 	down_write(&dmar_global_lock);
 
+	if (!no_iommu)
+		intel_iommu_debugfs_init();
+
 	if (no_iommu || dmar_disabled) {
 		/*
 		 * We exit the function here to ensure IOMMU's remapping and
@@ -4928,7 +4941,6 @@ int __init intel_iommu_init(void)
 	cpuhp_setup_state(CPUHP_IOMMU_INTEL_DEAD, "iommu/intel:dead", NULL,
 			  intel_iommu_cpu_dead);
 	intel_iommu_enabled = 1;
-	intel_iommu_debugfs_init();
 
 	return 0;
 
@@ -5376,8 +5388,10 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
 	u64 phys = 0;
 
 	pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level);
-	if (pte)
-		phys = dma_pte_addr(pte);
+	if (pte && dma_pte_present(pte))
+		phys = dma_pte_addr(pte) +
+			(iova & (BIT_MASK(level_to_offset_bits(level) +
+						VTD_PAGE_SHIFT) - 1));
 
 	return phys;
 }
@@ -5702,6 +5716,23 @@ intel_iommu_aux_get_pasid(struct iommu_domain *domain, struct device *dev)
 			dmar_domain->default_pasid : -EINVAL;
 }
 
+/*
+ * Check that the device does not live on an external facing PCI port that is
+ * marked as untrusted. Such devices should not be able to apply quirks and
+ * thus not be able to bypass the IOMMU restrictions.
+ */
+static bool risky_device(struct pci_dev *pdev)
+{
+	if (pdev->untrusted) {
+		pci_info(pdev,
+			 "Skipping IOMMU quirk for dev [%04X:%04X] on untrusted PCI link\n",
+			 pdev->vendor, pdev->device);
+		pci_info(pdev, "Please check with your BIOS/Platform vendor about this\n");
+		return true;
+	}
+	return false;
+}
+
 const struct iommu_ops intel_iommu_ops = {
 	.capable		= intel_iommu_capable,
 	.domain_alloc		= intel_iommu_domain_alloc,
@@ -5743,6 +5774,9 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e90, quirk_iommu_g4x_gfx);
 
 static void quirk_iommu_rwbf(struct pci_dev *dev)
 {
+	if (risky_device(dev))
+		return;
+
 	/*
 	 * Mobile 4 Series Chipset neglects to set RWBF capability,
 	 * but needs it. Same seems to hold for the desktop versions.
@@ -5773,6 +5807,9 @@ static void quirk_calpella_no_shadow_gtt(struct pci_dev *dev)
 {
 	unsigned short ggc;
 
+	if (risky_device(dev))
+		return;
+
 	if (pci_read_config_word(dev, GGC, &ggc))
 		return;
 
@@ -5806,6 +5843,12 @@ static void __init check_tylersburg_isoch(void)
 	pdev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x3a3e, NULL);
 	if (!pdev)
 		return;
+
+	if (risky_device(pdev)) {
+		pci_dev_put(pdev);
+		return;
+	}
+
 	pci_dev_put(pdev);
 
 	/* System Management Registers. Might be hidden, in which case
@@ -5815,6 +5858,11 @@ static void __init check_tylersburg_isoch(void)
 	if (!pdev)
 		return;
 
+	if (risky_device(pdev)) {
+		pci_dev_put(pdev);
+		return;
+	}
+
 	if (pci_read_config_dword(pdev, 0x188, &vtisochctrl)) {
 		pci_dev_put(pdev);
 		return;
diff --git a/drivers/iommu/intel-pasid.c b/drivers/iommu/intel-pasid.c
index fe51d8af457f..9328471d0d01 100644
--- a/drivers/iommu/intel-pasid.c
+++ b/drivers/iommu/intel-pasid.c
@@ -516,8 +516,16 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu,
 	}
 
 #ifdef CONFIG_X86
-	if (cpu_feature_enabled(X86_FEATURE_LA57))
-		pasid_set_flpm(pte, 1);
+	/* Both CPU and IOMMU paging mode need to match */
+	if (cpu_feature_enabled(X86_FEATURE_LA57)) {
+		if (cap_5lp_support(iommu->cap)) {
+			pasid_set_flpm(pte, 1);
+		} else {
+			pr_err("VT-d has no 5-level paging support for CPU\n");
+			pasid_clear_entry(pte);
+			return -EINVAL;
+		}
+	}
 #endif /* CONFIG_X86 */
 
 	pasid_set_domain_id(pte, did);
diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index 641dc223c97b..7f9a8de9ce6b 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -104,11 +104,7 @@ static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_d
 {
 	struct qi_desc desc;
 
-	/*
-	 * Do PASID granu IOTLB invalidation if page selective capability is
-	 * not available.
-	 */
-	if (pages == -1 || !cap_pgsel_inv(svm->iommu->cap)) {
+	if (pages == -1) {
 		desc.qw0 = QI_EIOTLB_PASID(svm->pasid) |
 			QI_EIOTLB_DID(sdev->did) |
 			QI_EIOTLB_GRAN(QI_GRAN_NONG_PASID) |
@@ -321,7 +317,7 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
 		/* Do not use PASID 0 in caching mode (virtualised IOMMU) */
 		ret = intel_pasid_alloc_id(svm,
 					   !!cap_caching_mode(iommu->cap),
-					   pasid_max - 1, GFP_KERNEL);
+					   pasid_max, GFP_KERNEL);
 		if (ret < 0) {
 			kfree(svm);
 			kfree(sdev);
@@ -491,7 +487,7 @@ struct page_req_dsc {
 	u64 priv_data[2];
 };
 
-#define PRQ_RING_MASK ((0x1000 << PRQ_ORDER) - 0x10)
+#define PRQ_RING_MASK	((0x1000 << PRQ_ORDER) - 0x20)
 
 static bool access_error(struct vm_area_struct *vma, struct page_req_dsc *req)
 {
@@ -572,14 +568,15 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 		 * any faults on kernel addresses. */
 		if (!svm->mm)
 			goto bad_req;
-		/* If the mm is already defunct, don't handle faults. */
-		if (!mmget_not_zero(svm->mm))
-			goto bad_req;
 
 		/* If address is not canonical, return invalid response */
 		if (!is_canonical_address(address))
 			goto bad_req;
 
+		/* If the mm is already defunct, don't handle faults. */
+		if (!mmget_not_zero(svm->mm))
+			goto bad_req;
+
 		down_read(&svm->mm->mmap_sem);
 		vma = find_extend_vma(svm->mm, address);
 		if (!vma || address < vma->vm_start)
@@ -643,11 +640,10 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 			if (req->priv_data_present)
 				memcpy(&resp.qw2, req->priv_data,
 				       sizeof(req->priv_data));
+			resp.qw2 = 0;
+			resp.qw3 = 0;
+			qi_submit_sync(&resp, iommu);
 		}
-		resp.qw2 = 0;
-		resp.qw3 = 0;
-		qi_submit_sync(&resp, iommu);
-
 		head = (head + sizeof(*req)) & PRQ_RING_MASK;
 	}
 
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 4b6b2f3150a9..1446c800a1dd 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -165,6 +165,9 @@
 #define ARM_MALI_LPAE_TTBR_READ_INNER	BIT(2)
 #define ARM_MALI_LPAE_TTBR_SHARE_OUTER	BIT(4)
 
+#define ARM_MALI_LPAE_MEMATTR_IMP_DEF	0x88ULL
+#define ARM_MALI_LPAE_MEMATTR_WRITE_ALLOC 0x8DULL
+
 /* IOPTE accessors */
 #define iopte_deref(pte,d) __va(iopte_to_paddr(pte, d))
 
@@ -1003,27 +1006,56 @@ arm_32_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 static struct io_pgtable *
 arm_mali_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
 {
-	struct io_pgtable *iop;
+	struct arm_lpae_io_pgtable *data;
 
-	if (cfg->ias != 48 || cfg->oas > 40)
+	/* No quirks for Mali (hopefully) */
+	if (cfg->quirks)
+		return NULL;
+
+	if (cfg->ias > 48 || cfg->oas > 40)
 		return NULL;
 
 	cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
-	iop = arm_64_lpae_alloc_pgtable_s1(cfg, cookie);
-	if (iop) {
-		u64 mair, ttbr;
 
-		/* Copy values as union fields overlap */
-		mair = cfg->arm_lpae_s1_cfg.mair[0];
-		ttbr = cfg->arm_lpae_s1_cfg.ttbr[0];
+	data = arm_lpae_alloc_pgtable(cfg);
+	if (!data)
+		return NULL;
 
-		cfg->arm_mali_lpae_cfg.memattr = mair;
-		cfg->arm_mali_lpae_cfg.transtab = ttbr |
-			ARM_MALI_LPAE_TTBR_READ_INNER |
-			ARM_MALI_LPAE_TTBR_ADRMODE_TABLE;
+	/* Mali seems to need a full 4-level table regardless of IAS */
+	if (data->levels < ARM_LPAE_MAX_LEVELS) {
+		data->levels = ARM_LPAE_MAX_LEVELS;
+		data->pgd_size = sizeof(arm_lpae_iopte);
 	}
+	/*
+	 * MEMATTR: Mali has no actual notion of a non-cacheable type, so the
+	 * best we can do is mimic the out-of-tree driver and hope that the
+	 * "implementation-defined caching policy" is good enough. Similarly,
+	 * we'll use it for the sake of a valid attribute for our 'device'
+	 * index, although callers should never request that in practice.
+	 */
+	cfg->arm_mali_lpae_cfg.memattr =
+		(ARM_MALI_LPAE_MEMATTR_IMP_DEF
+		 << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_NC)) |
+		(ARM_MALI_LPAE_MEMATTR_WRITE_ALLOC
+		 << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_CACHE)) |
+		(ARM_MALI_LPAE_MEMATTR_IMP_DEF
+		 << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_DEV));
 
-	return iop;
+	data->pgd = __arm_lpae_alloc_pages(data->pgd_size, GFP_KERNEL, cfg);
+	if (!data->pgd)
+		goto out_free_data;
+
+	/* Ensure the empty pgd is visible before TRANSTAB can be written */
+	wmb();
+
+	cfg->arm_mali_lpae_cfg.transtab = virt_to_phys(data->pgd) |
+					  ARM_MALI_LPAE_TTBR_READ_INNER |
+					  ARM_MALI_LPAE_TTBR_ADRMODE_TABLE;
+	return &data->iop;
+
+out_free_data:
+	kfree(data);
+	return NULL;
 }
 
 struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s1_init_fns = {
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 30db41e9f15c..86a0b0259df4 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -406,7 +406,7 @@ struct iommu_group *iommu_group_alloc(void)
 				   NULL, "%d", group->id);
 	if (ret) {
 		ida_simple_remove(&iommu_group_ida, group->id);
-		kfree(group);
+		kobject_put(&group->kobj);
 		return ERR_PTR(ret);
 	}
 
@@ -664,6 +664,7 @@ err_put_group:
 	mutex_unlock(&group->mutex);
 	dev->iommu_group = NULL;
 	kobject_put(group->devices_kobj);
+	sysfs_remove_link(group->devices_kobj, device->name);
 err_free_name:
 	kfree(device->name);
 err_remove_link:
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index c7a914b9bbbc..0e6a9536eca6 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -233,7 +233,7 @@ static DEFINE_MUTEX(iova_cache_mutex);
 
 struct iova *alloc_iova_mem(void)
 {
-	return kmem_cache_zalloc(iova_cache, GFP_ATOMIC);
+	return kmem_cache_zalloc(iova_cache, GFP_ATOMIC | __GFP_NOWARN);
 }
 EXPORT_SYMBOL(alloc_iova_mem);
 
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index 9a380c10655e..1e620f7ee08a 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -1050,8 +1050,6 @@ static int ipmmu_probe(struct platform_device *pdev)
 	mmu->num_ctx = min_t(unsigned int, IPMMU_CTX_MAX,
 			     mmu->features->number_of_contexts);
 
-	irq = platform_get_irq(pdev, 0);
-
 	/*
 	 * Determine if this IPMMU instance is a root device by checking for
 	 * the lack of has_cache_leaf_nodes flag or renesas,ipmmu-main property.
@@ -1070,6 +1068,7 @@ static int ipmmu_probe(struct platform_device *pdev)
 
 	/* Root devices have mandatory IRQs */
 	if (ipmmu_is_root(mmu)) {
+		irq = platform_get_irq(pdev, 0);
 		if (irq < 0) {
 			dev_err(&pdev->dev, "no IRQ found\n");
 			return irq;
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 82e4be4dfdaf..0faaa6697678 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -386,7 +386,7 @@ static size_t mtk_iommu_unmap(struct iommu_domain *domain,
 
 static void mtk_iommu_iotlb_sync(struct iommu_domain *domain)
 {
-	mtk_iommu_tlb_sync(mtk_iommu_get_m4u_data());
+	mtk_iommu_tlb_flush_all(mtk_iommu_get_m4u_data());
 }
 
 static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
diff --git a/drivers/iommu/omap-iommu-debug.c b/drivers/iommu/omap-iommu-debug.c
index ff31bddba60a..02e8156b6a75 100644
--- a/drivers/iommu/omap-iommu-debug.c
+++ b/drivers/iommu/omap-iommu-debug.c
@@ -98,8 +98,11 @@ static ssize_t debug_read_regs(struct file *file, char __user *userbuf,
 	mutex_lock(&iommu_debug_lock);
 
 	bytes = omap_iommu_dump_ctx(obj, p, count);
+	if (bytes < 0)
+		goto err;
 	bytes = simple_read_from_buffer(userbuf, count, ppos, buf, bytes);
 
+err:
 	mutex_unlock(&iommu_debug_lock);
 	kfree(buf);
 
diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c
index 34d0b9783b3e..ccd291b0b64b 100644
--- a/drivers/iommu/qcom_iommu.c
+++ b/drivers/iommu/qcom_iommu.c
@@ -322,21 +322,19 @@ static void qcom_iommu_domain_free(struct iommu_domain *domain)
 {
 	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
 
-	if (WARN_ON(qcom_domain->iommu))    /* forgot to detach? */
-		return;
-
 	iommu_put_dma_cookie(domain);
 
-	/* NOTE: unmap can be called after client device is powered off,
-	 * for example, with GPUs or anything involving dma-buf.  So we
-	 * cannot rely on the device_link.  Make sure the IOMMU is on to
-	 * avoid unclocked accesses in the TLB inv path:
-	 */
-	pm_runtime_get_sync(qcom_domain->iommu->dev);
-
-	free_io_pgtable_ops(qcom_domain->pgtbl_ops);
-
-	pm_runtime_put_sync(qcom_domain->iommu->dev);
+	if (qcom_domain->iommu) {
+		/*
+		 * NOTE: unmap can be called after client device is powered
+		 * off, for example, with GPUs or anything involving dma-buf.
+		 * So we cannot rely on the device_link.  Make sure the IOMMU
+		 * is on to avoid unclocked accesses in the TLB inv path:
+		 */
+		pm_runtime_get_sync(qcom_domain->iommu->dev);
+		free_io_pgtable_ops(qcom_domain->pgtbl_ops);
+		pm_runtime_put_sync(qcom_domain->iommu->dev);
+	}
 
 	kfree(qcom_domain);
 }
@@ -382,7 +380,7 @@ static void qcom_iommu_detach_dev(struct iommu_domain *domain, struct device *de
 	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
 	unsigned i;
 
-	if (!qcom_domain->iommu)
+	if (WARN_ON(!qcom_domain->iommu))
 		return;
 
 	pm_runtime_get_sync(qcom_iommu->dev);
@@ -395,8 +393,6 @@ static void qcom_iommu_detach_dev(struct iommu_domain *domain, struct device *de
 		ctx->domain = NULL;
 	}
 	pm_runtime_put_sync(qcom_iommu->dev);
-
-	qcom_domain->iommu = NULL;
 }
 
 static int qcom_iommu_map(struct iommu_domain *domain, unsigned long iova,
@@ -792,8 +788,11 @@ static int qcom_iommu_device_probe(struct platform_device *pdev)
 	qcom_iommu->dev = dev;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (res)
+	if (res) {
 		qcom_iommu->local_base = devm_ioremap_resource(dev, res);
+		if (IS_ERR(qcom_iommu->local_base))
+			return PTR_ERR(qcom_iommu->local_base);
+	}
 
 	qcom_iommu->iface_clk = devm_clk_get(dev, "iface");
 	if (IS_ERR(qcom_iommu->iface_clk)) {
diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c
index 16e056d1407c..9a94af7bfd0f 100644
--- a/drivers/iommu/rockchip-iommu.c
+++ b/drivers/iommu/rockchip-iommu.c
@@ -100,6 +100,7 @@ struct rk_iommu {
 	struct device *dev;
 	void __iomem **bases;
 	int num_mmu;
+	int num_irq;
 	struct clk_bulk_data *clocks;
 	int num_clocks;
 	bool reset_disabled;
@@ -1139,7 +1140,7 @@ static int rk_iommu_probe(struct platform_device *pdev)
 	struct rk_iommu *iommu;
 	struct resource *res;
 	int num_res = pdev->num_resources;
-	int err, i, irq;
+	int err, i;
 
 	iommu = devm_kzalloc(dev, sizeof(*iommu), GFP_KERNEL);
 	if (!iommu)
@@ -1166,6 +1167,10 @@ static int rk_iommu_probe(struct platform_device *pdev)
 	if (iommu->num_mmu == 0)
 		return PTR_ERR(iommu->bases[0]);
 
+	iommu->num_irq = platform_irq_count(pdev);
+	if (iommu->num_irq < 0)
+		return iommu->num_irq;
+
 	iommu->reset_disabled = device_property_read_bool(dev,
 					"rockchip,disable-mmu-reset");
 
@@ -1222,8 +1227,9 @@ static int rk_iommu_probe(struct platform_device *pdev)
 
 	pm_runtime_enable(dev);
 
-	i = 0;
-	while ((irq = platform_get_irq(pdev, i++)) != -ENXIO) {
+	for (i = 0; i < iommu->num_irq; i++) {
+		int irq = platform_get_irq(pdev, i);
+
 		if (irq < 0)
 			return irq;
 
@@ -1248,10 +1254,13 @@ err_unprepare_clocks:
 static void rk_iommu_shutdown(struct platform_device *pdev)
 {
 	struct rk_iommu *iommu = platform_get_drvdata(pdev);
-	int i = 0, irq;
+	int i;
+
+	for (i = 0; i < iommu->num_irq; i++) {
+		int irq = platform_get_irq(pdev, i);
 
-	while ((irq = platform_get_irq(pdev, i++)) != -ENXIO)
 		devm_free_irq(iommu->dev, irq, iommu);
+	}
 
 	pm_runtime_force_suspend(&pdev->dev);
 }
diff --git a/drivers/ipack/carriers/tpci200.c b/drivers/ipack/carriers/tpci200.c
index d246d74ec3a5..fdcf2bcae164 100644
--- a/drivers/ipack/carriers/tpci200.c
+++ b/drivers/ipack/carriers/tpci200.c
@@ -306,6 +306,7 @@ static int tpci200_register(struct tpci200_board *tpci200)
 			"(bn 0x%X, sn 0x%X) failed to map driver user space!",
 			tpci200->info->pdev->bus->number,
 			tpci200->info->pdev->devfn);
+		res = -ENOMEM;
 		goto out_release_mem8_space;
 	}
 
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 659c5e0fb835..65366ec59087 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -447,8 +447,6 @@ config TI_SCI_INTA_IRQCHIP
 	  If you wish to use interrupt aggregator irq resources managed by the
 	  TI System Controller, say Y here. Otherwise, say N.
 
-endmenu
-
 config SIFIVE_PLIC
 	bool "SiFive Platform-Level Interrupt Controller"
 	depends on RISCV
@@ -460,3 +458,5 @@ config SIFIVE_PLIC
 	   interrupt sources are subordinate to the PLIC.
 
 	   If you don't know what to do here, say Y.
+
+endmenu
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index d70badb3ab14..0e8c08ce2cd6 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -571,7 +571,7 @@ static struct its_collection *its_build_invall_cmd(struct its_node *its,
 						   struct its_cmd_desc *desc)
 {
 	its_encode_cmd(cmd, GITS_CMD_INVALL);
-	its_encode_collection(cmd, desc->its_mapc_cmd.col->col_id);
+	its_encode_collection(cmd, desc->its_invall_cmd.col->col_id);
 
 	its_fixup_cmd(cmd);
 
@@ -2581,6 +2581,7 @@ static int its_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 	msi_alloc_info_t *info = args;
 	struct its_device *its_dev = info->scratchpad[0].ptr;
 	struct its_node *its = its_dev->its;
+	struct irq_data *irqd;
 	irq_hw_number_t hwirq;
 	int err;
 	int i;
@@ -2600,7 +2601,9 @@ static int its_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 
 		irq_domain_set_hwirq_and_chip(domain, virq + i,
 					      hwirq + i, &its_irq_chip, its_dev);
-		irqd_set_single_target(irq_desc_get_irq_data(irq_to_desc(virq + i)));
+		irqd = irq_get_irq_data(virq + i);
+		irqd_set_single_target(irqd);
+		irqd_set_affinity_on_activate(irqd);
 		pr_debug("ID:%d pID:%d vID:%d\n",
 			 (int)(hwirq + i - its_dev->event_map.lpi_base),
 			 (int)(hwirq + i), virq + i);
@@ -2985,12 +2988,18 @@ static int its_vpe_set_irqchip_state(struct irq_data *d,
 	return 0;
 }
 
+static int its_vpe_retrigger(struct irq_data *d)
+{
+	return !its_vpe_set_irqchip_state(d, IRQCHIP_STATE_PENDING, true);
+}
+
 static struct irq_chip its_vpe_irq_chip = {
 	.name			= "GICv4-vpe",
 	.irq_mask		= its_vpe_mask_irq,
 	.irq_unmask		= its_vpe_unmask_irq,
 	.irq_eoi		= irq_chip_eoi_parent,
 	.irq_set_affinity	= its_vpe_set_affinity,
+	.irq_retrigger		= its_vpe_retrigger,
 	.irq_set_irqchip_state	= its_vpe_set_irqchip_state,
 	.irq_set_vcpu_affinity	= its_vpe_set_vcpu_affinity,
 };
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index f3e44d6d9255..c09c1eea3319 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -1572,6 +1572,7 @@ static struct
 	struct redist_region *redist_regs;
 	u32 nr_redist_regions;
 	bool single_redist;
+	int enabled_rdists;
 	u32 maint_irq;
 	int maint_irq_mode;
 	phys_addr_t vcpu_base;
@@ -1666,8 +1667,10 @@ static int __init gic_acpi_match_gicc(union acpi_subtable_headers *header,
 	 * If GICC is enabled and has valid gicr base address, then it means
 	 * GICR base is presented via GICC
 	 */
-	if ((gicc->flags & ACPI_MADT_ENABLED) && gicc->gicr_base_address)
+	if ((gicc->flags & ACPI_MADT_ENABLED) && gicc->gicr_base_address) {
+		acpi_data.enabled_rdists++;
 		return 0;
+	}
 
 	/*
 	 * It's perfectly valid firmware can pass disabled GICC entry, driver
@@ -1697,8 +1700,10 @@ static int __init gic_acpi_count_gicr_regions(void)
 
 	count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT,
 				      gic_acpi_match_gicc, 0);
-	if (count > 0)
+	if (count > 0) {
 		acpi_data.single_redist = true;
+		count = acpi_data.enabled_rdists;
+	}
 
 	return count;
 }
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index e45f45e68720..50b9ca69e6a2 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -321,10 +321,8 @@ static int gic_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu)
 static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 			    bool force)
 {
-	void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + (gic_irq(d) & ~3);
-	unsigned int cpu, shift = (gic_irq(d) % 4) * 8;
-	u32 val, mask, bit;
-	unsigned long flags;
+	void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + gic_irq(d);
+	unsigned int cpu;
 
 	if (!force)
 		cpu = cpumask_any_and(mask_val, cpu_online_mask);
@@ -334,13 +332,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 	if (cpu >= NR_GIC_CPU_IF || cpu >= nr_cpu_ids)
 		return -EINVAL;
 
-	gic_lock_irqsave(flags);
-	mask = 0xff << shift;
-	bit = gic_cpu_map[cpu] << shift;
-	val = readl_relaxed(reg) & ~mask;
-	writel_relaxed(val | bit, reg);
-	gic_unlock_irqrestore(flags);
-
+	writeb_relaxed(gic_cpu_map[cpu], reg);
 	irq_data_update_effective_affinity(d, cpumask_of(cpu));
 
 	return IRQ_SET_MASK_OK_DONE;
diff --git a/drivers/irqchip/irq-mbigen.c b/drivers/irqchip/irq-mbigen.c
index a89c693d5b90..cad4e07880cf 100644
--- a/drivers/irqchip/irq-mbigen.c
+++ b/drivers/irqchip/irq-mbigen.c
@@ -220,10 +220,16 @@ static int mbigen_irq_domain_alloc(struct irq_domain *domain,
 	return 0;
 }
 
+static void mbigen_irq_domain_free(struct irq_domain *domain, unsigned int virq,
+				   unsigned int nr_irqs)
+{
+	platform_msi_domain_free(domain, virq, nr_irqs);
+}
+
 static const struct irq_domain_ops mbigen_domain_ops = {
 	.translate	= mbigen_domain_translate,
 	.alloc		= mbigen_irq_domain_alloc,
-	.free		= irq_domain_free_irqs_common,
+	.free		= mbigen_irq_domain_free,
 };
 
 static int mbigen_of_create_domain(struct platform_device *pdev,
@@ -370,6 +376,7 @@ static struct platform_driver mbigen_platform_driver = {
 		.name		= "Hisilicon MBIGEN-V2",
 		.of_match_table	= mbigen_of_match,
 		.acpi_match_table = ACPI_PTR(mbigen_acpi_match),
+		.suppress_bind_attrs = true,
 	},
 	.probe			= mbigen_device_probe,
 };
diff --git a/drivers/irqchip/irq-mtk-sysirq.c b/drivers/irqchip/irq-mtk-sysirq.c
index 73eae5966a40..6ff98b87e5c0 100644
--- a/drivers/irqchip/irq-mtk-sysirq.c
+++ b/drivers/irqchip/irq-mtk-sysirq.c
@@ -15,7 +15,7 @@
 #include <linux/spinlock.h>
 
 struct mtk_sysirq_chip_data {
-	spinlock_t lock;
+	raw_spinlock_t lock;
 	u32 nr_intpol_bases;
 	void __iomem **intpol_bases;
 	u32 *intpol_words;
@@ -37,7 +37,7 @@ static int mtk_sysirq_set_type(struct irq_data *data, unsigned int type)
 	reg_index = chip_data->which_word[hwirq];
 	offset = hwirq & 0x1f;
 
-	spin_lock_irqsave(&chip_data->lock, flags);
+	raw_spin_lock_irqsave(&chip_data->lock, flags);
 	value = readl_relaxed(base + reg_index * 4);
 	if (type == IRQ_TYPE_LEVEL_LOW || type == IRQ_TYPE_EDGE_FALLING) {
 		if (type == IRQ_TYPE_LEVEL_LOW)
@@ -53,7 +53,7 @@ static int mtk_sysirq_set_type(struct irq_data *data, unsigned int type)
 
 	data = data->parent_data;
 	ret = data->chip->irq_set_type(data, type);
-	spin_unlock_irqrestore(&chip_data->lock, flags);
+	raw_spin_unlock_irqrestore(&chip_data->lock, flags);
 	return ret;
 }
 
@@ -212,7 +212,7 @@ static int __init mtk_sysirq_of_init(struct device_node *node,
 		ret = -ENOMEM;
 		goto out_free_which_word;
 	}
-	spin_lock_init(&chip_data->lock);
+	raw_spin_lock_init(&chip_data->lock);
 
 	return 0;
 
diff --git a/drivers/irqchip/irq-ti-sci-inta.c b/drivers/irqchip/irq-ti-sci-inta.c
index ef4d625d2d80..0a35499c4672 100644
--- a/drivers/irqchip/irq-ti-sci-inta.c
+++ b/drivers/irqchip/irq-ti-sci-inta.c
@@ -37,6 +37,7 @@
 #define VINT_ENABLE_SET_OFFSET	0x0
 #define VINT_ENABLE_CLR_OFFSET	0x8
 #define VINT_STATUS_OFFSET	0x18
+#define VINT_STATUS_MASKED_OFFSET	0x20
 
 /**
  * struct ti_sci_inta_event_desc - Description of an event coming to
@@ -116,7 +117,7 @@ static void ti_sci_inta_irq_handler(struct irq_desc *desc)
 	chained_irq_enter(irq_desc_get_chip(desc), desc);
 
 	val = readq_relaxed(inta->base + vint_desc->vint_id * 0x1000 +
-			    VINT_STATUS_OFFSET);
+			    VINT_STATUS_MASKED_OFFSET);
 
 	for_each_set_bit(bit, &val, MAX_EVENTS_PER_VINT) {
 		virq = irq_find_mapping(domain, vint_desc->events[bit].hwirq);
@@ -570,7 +571,7 @@ static int ti_sci_inta_irq_domain_probe(struct platform_device *pdev)
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	inta->base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(inta->base))
-		return -ENODEV;
+		return PTR_ERR(inta->base);
 
 	domain = irq_domain_add_linear(dev_of_node(dev),
 				       ti_sci_get_num_resources(inta->vint),
diff --git a/drivers/irqchip/irq-versatile-fpga.c b/drivers/irqchip/irq-versatile-fpga.c
index 928858dada75..f1386733d3bc 100644
--- a/drivers/irqchip/irq-versatile-fpga.c
+++ b/drivers/irqchip/irq-versatile-fpga.c
@@ -6,6 +6,7 @@
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/irqchip.h>
+#include <linux/irqchip/chained_irq.h>
 #include <linux/irqchip/versatile-fpga.h>
 #include <linux/irqdomain.h>
 #include <linux/module.h>
@@ -68,12 +69,16 @@ static void fpga_irq_unmask(struct irq_data *d)
 
 static void fpga_irq_handle(struct irq_desc *desc)
 {
+	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct fpga_irq_data *f = irq_desc_get_handler_data(desc);
-	u32 status = readl(f->base + IRQ_STATUS);
+	u32 status;
+
+	chained_irq_enter(chip, desc);
 
+	status = readl(f->base + IRQ_STATUS);
 	if (status == 0) {
 		do_bad_IRQ(desc);
-		return;
+		goto out;
 	}
 
 	do {
@@ -82,6 +87,9 @@ static void fpga_irq_handle(struct irq_desc *desc)
 		status &= ~(1 << irq);
 		generic_handle_irq(irq_find_mapping(f->domain, irq));
 	} while (status);
+
+out:
+	chained_irq_exit(chip, desc);
 }
 
 /*
@@ -204,6 +212,9 @@ int __init fpga_irq_of_init(struct device_node *node,
 	if (of_property_read_u32(node, "valid-mask", &valid_mask))
 		valid_mask = 0;
 
+	writel(clear_mask, base + IRQ_ENABLE_CLEAR);
+	writel(clear_mask, base + FIQ_ENABLE_CLEAR);
+
 	/* Some chips are cascaded from a parent IRQ */
 	parent_irq = irq_of_parse_and_map(node, 0);
 	if (!parent_irq) {
@@ -213,9 +224,6 @@ int __init fpga_irq_of_init(struct device_node *node,
 
 	fpga_irq_init(base, node->name, 0, parent_irq, valid_mask, node);
 
-	writel(clear_mask, base + IRQ_ENABLE_CLEAR);
-	writel(clear_mask, base + FIQ_ENABLE_CLEAR);
-
 	/*
 	 * On Versatile AB/PB, some secondary interrupts have a direct
 	 * pass-thru to the primary controller for IRQs 20 and 22-31 which need
diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c
index 4793e77808e2..930158dcfb6e 100644
--- a/drivers/leds/led-class.c
+++ b/drivers/leds/led-class.c
@@ -171,6 +171,7 @@ void led_classdev_suspend(struct led_classdev *led_cdev)
 {
 	led_cdev->flags |= LED_SUSPENDED;
 	led_set_brightness_nopm(led_cdev, 0);
+	flush_work(&led_cdev->set_brightness_work);
 }
 EXPORT_SYMBOL_GPL(led_classdev_suspend);
 
diff --git a/drivers/leds/leds-88pm860x.c b/drivers/leds/leds-88pm860x.c
index b3044c9a8120..465c3755cf2e 100644
--- a/drivers/leds/leds-88pm860x.c
+++ b/drivers/leds/leds-88pm860x.c
@@ -203,21 +203,33 @@ static int pm860x_led_probe(struct platform_device *pdev)
 	data->cdev.brightness_set_blocking = pm860x_led_set;
 	mutex_init(&data->lock);
 
-	ret = devm_led_classdev_register(chip->dev, &data->cdev);
+	ret = led_classdev_register(chip->dev, &data->cdev);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "Failed to register LED: %d\n", ret);
 		return ret;
 	}
 	pm860x_led_set(&data->cdev, 0);
+
+	platform_set_drvdata(pdev, data);
+
 	return 0;
 }
 
+static int pm860x_led_remove(struct platform_device *pdev)
+{
+	struct pm860x_led *data = platform_get_drvdata(pdev);
+
+	led_classdev_unregister(&data->cdev);
+
+	return 0;
+}
 
 static struct platform_driver pm860x_led_driver = {
 	.driver	= {
 		.name	= "88pm860x-led",
 	},
 	.probe	= pm860x_led_probe,
+	.remove	= pm860x_led_remove,
 };
 
 module_platform_driver(pm860x_led_driver);
diff --git a/drivers/leds/leds-da903x.c b/drivers/leds/leds-da903x.c
index ed1b303f699f..2b5fb00438a2 100644
--- a/drivers/leds/leds-da903x.c
+++ b/drivers/leds/leds-da903x.c
@@ -110,12 +110,23 @@ static int da903x_led_probe(struct platform_device *pdev)
 	led->flags = pdata->flags;
 	led->master = pdev->dev.parent;
 
-	ret = devm_led_classdev_register(led->master, &led->cdev);
+	ret = led_classdev_register(led->master, &led->cdev);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to register LED %d\n", id);
 		return ret;
 	}
 
+	platform_set_drvdata(pdev, led);
+
+	return 0;
+}
+
+static int da903x_led_remove(struct platform_device *pdev)
+{
+	struct da903x_led *led = platform_get_drvdata(pdev);
+
+	led_classdev_unregister(&led->cdev);
+
 	return 0;
 }
 
@@ -124,6 +135,7 @@ static struct platform_driver da903x_led_driver = {
 		.name	= "da903x-led",
 	},
 	.probe		= da903x_led_probe,
+	.remove		= da903x_led_remove,
 };
 
 module_platform_driver(da903x_led_driver);
diff --git a/drivers/leds/leds-lm3532.c b/drivers/leds/leds-lm3532.c
index e55a64847fe2..1631cf2de3d6 100644
--- a/drivers/leds/leds-lm3532.c
+++ b/drivers/leds/leds-lm3532.c
@@ -38,6 +38,9 @@
 #define LM3532_REG_ZN_2_LO	0x65
 #define LM3532_REG_ZN_3_HI	0x66
 #define LM3532_REG_ZN_3_LO	0x67
+#define LM3532_REG_ZONE_TRGT_A	0x70
+#define LM3532_REG_ZONE_TRGT_B	0x75
+#define LM3532_REG_ZONE_TRGT_C	0x7a
 #define LM3532_REG_MAX		0x7e
 
 /* Control Enable */
@@ -116,6 +119,7 @@ struct lm3532_als_data {
  * @priv - Pointer the device data structure
  * @control_bank - Control bank the LED is associated to
  * @mode - Mode of the LED string
+ * @ctrl_brt_pointer - Zone target register that controls the sink
  * @num_leds - Number of LED strings are supported in this array
  * @led_strings - The LED strings supported in this array
  * @label - LED label
@@ -126,6 +130,7 @@ struct lm3532_led {
 
 	int control_bank;
 	int mode;
+	int ctrl_brt_pointer;
 	int num_leds;
 	u32 led_strings[LM3532_MAX_CONTROL_BANKS];
 	char label[LED_MAX_NAME_SIZE];
@@ -339,8 +344,8 @@ static int lm3532_brightness_set(struct led_classdev *led_cdev,
 	if (ret)
 		goto unlock;
 
-	brightness_reg = LM3532_REG_CTRL_A_BRT + led->control_bank * 2;
-	brt_val = brt_val / LM3532_BRT_VAL_ADJUST;
+	brightness_reg = LM3532_REG_ZONE_TRGT_A + led->control_bank * 5 +
+			 (led->ctrl_brt_pointer >> 2);
 
 	ret = regmap_write(led->priv->regmap, brightness_reg, brt_val);
 
@@ -356,8 +361,30 @@ static int lm3532_init_registers(struct lm3532_led *led)
 	unsigned int output_cfg_val = 0;
 	unsigned int output_cfg_shift = 0;
 	unsigned int output_cfg_mask = 0;
+	unsigned int brightness_config_reg;
+	unsigned int brightness_config_val;
 	int ret, i;
 
+	if (drvdata->enable_gpio)
+		gpiod_direction_output(drvdata->enable_gpio, 1);
+
+	brightness_config_reg = LM3532_REG_ZONE_CFG_A + led->control_bank * 2;
+	/*
+	 * This could be hard coded to the default value but the control
+	 * brightness register may have changed during boot.
+	 */
+	ret = regmap_read(drvdata->regmap, brightness_config_reg,
+			  &led->ctrl_brt_pointer);
+	if (ret)
+		return ret;
+
+	led->ctrl_brt_pointer &= LM3532_ZONE_MASK;
+	brightness_config_val = led->ctrl_brt_pointer | led->mode;
+	ret = regmap_write(drvdata->regmap, brightness_config_reg,
+			   brightness_config_val);
+	if (ret)
+		return ret;
+
 	for (i = 0; i < led->num_leds; i++) {
 		output_cfg_shift = led->led_strings[i] * 2;
 		output_cfg_val |= (led->control_bank << output_cfg_shift);
@@ -382,7 +409,6 @@ static int lm3532_als_configure(struct lm3532_data *priv,
 	struct lm3532_als_data *als = priv->als_data;
 	u32 als_vmin, als_vmax, als_vstep;
 	int zone_reg = LM3532_REG_ZN_0_HI;
-	int brightnes_config_reg;
 	int ret;
 	int i;
 
@@ -411,14 +437,7 @@ static int lm3532_als_configure(struct lm3532_data *priv,
 	als->config = (als->als_avrg_time | (LM3532_ENABLE_ALS) |
 		(als->als_input_mode << LM3532_ALS_SEL_SHIFT));
 
-	ret = regmap_write(priv->regmap, LM3532_ALS_CONFIG, als->config);
-	if (ret)
-		return ret;
-
-	brightnes_config_reg = LM3532_REG_ZONE_CFG_A + led->control_bank * 2;
-
-	return regmap_update_bits(priv->regmap, brightnes_config_reg,
-				  LM3532_I2C_CTRL, LM3532_ALS_CTRL);
+	return regmap_write(priv->regmap, LM3532_ALS_CONFIG, als->config);
 }
 
 static int lm3532_parse_als(struct lm3532_data *priv)
@@ -646,9 +665,6 @@ static int lm3532_probe(struct i2c_client *client,
 		return ret;
 	}
 
-	if (drvdata->enable_gpio)
-		gpiod_direction_output(drvdata->enable_gpio, 1);
-
 	return ret;
 }
 
diff --git a/drivers/leds/leds-lm3533.c b/drivers/leds/leds-lm3533.c
index 9504ad405aef..b3edee703193 100644
--- a/drivers/leds/leds-lm3533.c
+++ b/drivers/leds/leds-lm3533.c
@@ -694,7 +694,7 @@ static int lm3533_led_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, led);
 
-	ret = devm_led_classdev_register(pdev->dev.parent, &led->cdev);
+	ret = led_classdev_register(pdev->dev.parent, &led->cdev);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to register LED %d\n", pdev->id);
 		return ret;
@@ -704,13 +704,18 @@ static int lm3533_led_probe(struct platform_device *pdev)
 
 	ret = lm3533_led_setup(led, pdata);
 	if (ret)
-		return ret;
+		goto err_deregister;
 
 	ret = lm3533_ctrlbank_enable(&led->cb);
 	if (ret)
-		return ret;
+		goto err_deregister;
 
 	return 0;
+
+err_deregister:
+	led_classdev_unregister(&led->cdev);
+
+	return ret;
 }
 
 static int lm3533_led_remove(struct platform_device *pdev)
@@ -720,6 +725,7 @@ static int lm3533_led_remove(struct platform_device *pdev)
 	dev_dbg(&pdev->dev, "%s\n", __func__);
 
 	lm3533_ctrlbank_disable(&led->cb);
+	led_classdev_unregister(&led->cdev);
 
 	return 0;
 }
diff --git a/drivers/leds/leds-lm355x.c b/drivers/leds/leds-lm355x.c
index a5abb499574b..129f475aebf2 100644
--- a/drivers/leds/leds-lm355x.c
+++ b/drivers/leds/leds-lm355x.c
@@ -165,18 +165,19 @@ static int lm355x_chip_init(struct lm355x_chip_data *chip)
 	/* input and output pins configuration */
 	switch (chip->type) {
 	case CHIP_LM3554:
-		reg_val = pdata->pin_tx2 | pdata->ntc_pin;
+		reg_val = (u32)pdata->pin_tx2 | (u32)pdata->ntc_pin;
 		ret = regmap_update_bits(chip->regmap, 0xE0, 0x28, reg_val);
 		if (ret < 0)
 			goto out;
-		reg_val = pdata->pass_mode;
+		reg_val = (u32)pdata->pass_mode;
 		ret = regmap_update_bits(chip->regmap, 0xA0, 0x04, reg_val);
 		if (ret < 0)
 			goto out;
 		break;
 
 	case CHIP_LM3556:
-		reg_val = pdata->pin_tx2 | pdata->ntc_pin | pdata->pass_mode;
+		reg_val = (u32)pdata->pin_tx2 | (u32)pdata->ntc_pin |
+		          (u32)pdata->pass_mode;
 		ret = regmap_update_bits(chip->regmap, 0x0A, 0xC4, reg_val);
 		if (ret < 0)
 			goto out;
diff --git a/drivers/leds/leds-max77650.c b/drivers/leds/leds-max77650.c
index 6b74ce9cac12..9f830b6c85fb 100644
--- a/drivers/leds/leds-max77650.c
+++ b/drivers/leds/leds-max77650.c
@@ -134,9 +134,16 @@ static int max77650_led_probe(struct platform_device *pdev)
 			    MAX77650_LED_TOP_DEFAULT);
 }
 
+static const struct of_device_id max77650_led_of_match[] = {
+	{ .compatible = "maxim,max77650-led" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, max77650_led_of_match);
+
 static struct platform_driver max77650_led_driver = {
 	.driver = {
 		.name = "max77650-led",
+		.of_match_table = max77650_led_of_match,
 	},
 	.probe = max77650_led_probe,
 };
diff --git a/drivers/leds/leds-pca963x.c b/drivers/leds/leds-pca963x.c
index 4afc317901a8..66cdc003b8f4 100644
--- a/drivers/leds/leds-pca963x.c
+++ b/drivers/leds/leds-pca963x.c
@@ -40,6 +40,8 @@
 #define PCA963X_LED_PWM		0x2	/* Controlled through PWM */
 #define PCA963X_LED_GRP_PWM	0x3	/* Controlled through PWM/GRPPWM */
 
+#define PCA963X_MODE2_OUTDRV	0x04	/* Open-drain or totem pole */
+#define PCA963X_MODE2_INVRT	0x10	/* Normal or inverted direction */
 #define PCA963X_MODE2_DMBLNK	0x20	/* Enable blinking */
 
 #define PCA963X_MODE1		0x00
@@ -438,12 +440,12 @@ static int pca963x_probe(struct i2c_client *client,
 						    PCA963X_MODE2);
 		/* Configure output: open-drain or totem pole (push-pull) */
 		if (pdata->outdrv == PCA963X_OPEN_DRAIN)
-			mode2 |= 0x01;
+			mode2 &= ~PCA963X_MODE2_OUTDRV;
 		else
-			mode2 |= 0x05;
+			mode2 |= PCA963X_MODE2_OUTDRV;
 		/* Configure direction: normal or inverted */
 		if (pdata->dir == PCA963X_INVERTED)
-			mode2 |= 0x10;
+			mode2 |= PCA963X_MODE2_INVRT;
 		i2c_smbus_write_byte_data(pca963x->chip->client, PCA963X_MODE2,
 					  mode2);
 	}
diff --git a/drivers/leds/leds-tlc591xx.c b/drivers/leds/leds-tlc591xx.c
index 59ff088c7d75..9feaec3c8329 100644
--- a/drivers/leds/leds-tlc591xx.c
+++ b/drivers/leds/leds-tlc591xx.c
@@ -13,6 +13,7 @@
 #include <linux/slab.h>
 
 #define TLC591XX_MAX_LEDS	16
+#define TLC591XX_MAX_BRIGHTNESS	256
 
 #define TLC591XX_REG_MODE1	0x00
 #define MODE1_RESPON_ADDR_MASK	0xF0
@@ -112,11 +113,11 @@ tlc591xx_brightness_set(struct led_classdev *led_cdev,
 	struct tlc591xx_priv *priv = led->priv;
 	int err;
 
-	switch (brightness) {
+	switch ((int)brightness) {
 	case 0:
 		err = tlc591xx_set_ledout(priv, led, LEDOUT_OFF);
 		break;
-	case LED_FULL:
+	case TLC591XX_MAX_BRIGHTNESS:
 		err = tlc591xx_set_ledout(priv, led, LEDOUT_ON);
 		break;
 	default:
@@ -157,7 +158,7 @@ tlc591xx_configure(struct device *dev,
 		led->priv = priv;
 		led->led_no = i;
 		led->ldev.brightness_set_blocking = tlc591xx_brightness_set;
-		led->ldev.max_brightness = LED_FULL;
+		led->ldev.max_brightness = TLC591XX_MAX_BRIGHTNESS;
 		err = led_classdev_register(dev, &led->ldev);
 		if (err < 0) {
 			dev_err(dev, "couldn't register LED %s\n",
diff --git a/drivers/leds/leds-wm831x-status.c b/drivers/leds/leds-wm831x-status.c
index 082df7f1dd90..67f4235cb28a 100644
--- a/drivers/leds/leds-wm831x-status.c
+++ b/drivers/leds/leds-wm831x-status.c
@@ -269,12 +269,23 @@ static int wm831x_status_probe(struct platform_device *pdev)
 	drvdata->cdev.blink_set = wm831x_status_blink_set;
 	drvdata->cdev.groups = wm831x_status_groups;
 
-	ret = devm_led_classdev_register(wm831x->dev, &drvdata->cdev);
+	ret = led_classdev_register(wm831x->dev, &drvdata->cdev);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "Failed to register LED: %d\n", ret);
 		return ret;
 	}
 
+	platform_set_drvdata(pdev, drvdata);
+
+	return 0;
+}
+
+static int wm831x_status_remove(struct platform_device *pdev)
+{
+	struct wm831x_status *drvdata = platform_get_drvdata(pdev);
+
+	led_classdev_unregister(&drvdata->cdev);
+
 	return 0;
 }
 
@@ -283,6 +294,7 @@ static struct platform_driver wm831x_status_driver = {
 		   .name = "wm831x-status",
 		   },
 	.probe = wm831x_status_probe,
+	.remove = wm831x_status_remove,
 };
 
 module_platform_driver(wm831x_status_driver);
diff --git a/drivers/macintosh/therm_windtunnel.c b/drivers/macintosh/therm_windtunnel.c
index 8c744578122a..a0d87ed9da69 100644
--- a/drivers/macintosh/therm_windtunnel.c
+++ b/drivers/macintosh/therm_windtunnel.c
@@ -300,9 +300,11 @@ static int control_loop(void *dummy)
 /*	i2c probing and setup						*/
 /************************************************************************/
 
-static int
-do_attach( struct i2c_adapter *adapter )
+static void do_attach(struct i2c_adapter *adapter)
 {
+	struct i2c_board_info info = { };
+	struct device_node *np;
+
 	/* scan 0x48-0x4f (DS1775) and 0x2c-2x2f (ADM1030) */
 	static const unsigned short scan_ds1775[] = {
 		0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f,
@@ -313,25 +315,24 @@ do_attach( struct i2c_adapter *adapter )
 		I2C_CLIENT_END
 	};
 
-	if( strncmp(adapter->name, "uni-n", 5) )
-		return 0;
-
-	if( !x.running ) {
-		struct i2c_board_info info;
+	if (x.running || strncmp(adapter->name, "uni-n", 5))
+		return;
 
-		memset(&info, 0, sizeof(struct i2c_board_info));
-		strlcpy(info.type, "therm_ds1775", I2C_NAME_SIZE);
+	np = of_find_compatible_node(adapter->dev.of_node, NULL, "MAC,ds1775");
+	if (np) {
+		of_node_put(np);
+	} else {
+		strlcpy(info.type, "MAC,ds1775", I2C_NAME_SIZE);
 		i2c_new_probed_device(adapter, &info, scan_ds1775, NULL);
+	}
 
-		strlcpy(info.type, "therm_adm1030", I2C_NAME_SIZE);
+	np = of_find_compatible_node(adapter->dev.of_node, NULL, "MAC,adm1030");
+	if (np) {
+		of_node_put(np);
+	} else {
+		strlcpy(info.type, "MAC,adm1030", I2C_NAME_SIZE);
 		i2c_new_probed_device(adapter, &info, scan_adm1030, NULL);
-
-		if( x.thermostat && x.fan ) {
-			x.running = 1;
-			x.poll_task = kthread_run(control_loop, NULL, "g4fand");
-		}
 	}
-	return 0;
 }
 
 static int
@@ -404,8 +405,8 @@ out:
 enum chip { ds1775, adm1030 };
 
 static const struct i2c_device_id therm_windtunnel_id[] = {
-	{ "therm_ds1775", ds1775 },
-	{ "therm_adm1030", adm1030 },
+	{ "MAC,ds1775", ds1775 },
+	{ "MAC,adm1030", adm1030 },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, therm_windtunnel_id);
@@ -414,6 +415,7 @@ static int
 do_probe(struct i2c_client *cl, const struct i2c_device_id *id)
 {
 	struct i2c_adapter *adapter = cl->adapter;
+	int ret = 0;
 
 	if( !i2c_check_functionality(adapter, I2C_FUNC_SMBUS_WORD_DATA
 				     | I2C_FUNC_SMBUS_WRITE_BYTE) )
@@ -421,11 +423,19 @@ do_probe(struct i2c_client *cl, const struct i2c_device_id *id)
 
 	switch (id->driver_data) {
 	case adm1030:
-		return attach_fan( cl );
+		ret = attach_fan(cl);
+		break;
 	case ds1775:
-		return attach_thermostat(cl);
+		ret = attach_thermostat(cl);
+		break;
 	}
-	return 0;
+
+	if (!x.running && x.thermostat && x.fan) {
+		x.running = 1;
+		x.poll_task = kthread_run(control_loop, NULL, "g4fand");
+	}
+
+	return ret;
 }
 
 static struct i2c_driver g4fan_driver = {
diff --git a/drivers/macintosh/via-macii.c b/drivers/macintosh/via-macii.c
index ac824d7b2dcf..6aa903529570 100644
--- a/drivers/macintosh/via-macii.c
+++ b/drivers/macintosh/via-macii.c
@@ -270,15 +270,12 @@ static int macii_autopoll(int devs)
 	unsigned long flags;
 	int err = 0;
 
+	local_irq_save(flags);
+
 	/* bit 1 == device 1, and so on. */
 	autopoll_devs = devs & 0xFFFE;
 
-	if (!autopoll_devs)
-		return 0;
-
-	local_irq_save(flags);
-
-	if (current_req == NULL) {
+	if (autopoll_devs && !current_req) {
 		/* Send a Talk Reg 0. The controller will repeatedly transmit
 		 * this as long as it is idle.
 		 */
diff --git a/drivers/macintosh/windfarm_ad7417_sensor.c b/drivers/macintosh/windfarm_ad7417_sensor.c
index 125605987b44..e7dec328c7cf 100644
--- a/drivers/macintosh/windfarm_ad7417_sensor.c
+++ b/drivers/macintosh/windfarm_ad7417_sensor.c
@@ -312,9 +312,16 @@ static const struct i2c_device_id wf_ad7417_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, wf_ad7417_id);
 
+static const struct of_device_id wf_ad7417_of_id[] = {
+	{ .compatible = "ad7417", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, wf_ad7417_of_id);
+
 static struct i2c_driver wf_ad7417_driver = {
 	.driver = {
 		.name	= "wf_ad7417",
+		.of_match_table = wf_ad7417_of_id,
 	},
 	.probe		= wf_ad7417_probe,
 	.remove		= wf_ad7417_remove,
diff --git a/drivers/macintosh/windfarm_fcu_controls.c b/drivers/macintosh/windfarm_fcu_controls.c
index 3c971297b6dc..89b48e8ac6ef 100644
--- a/drivers/macintosh/windfarm_fcu_controls.c
+++ b/drivers/macintosh/windfarm_fcu_controls.c
@@ -582,9 +582,16 @@ static const struct i2c_device_id wf_fcu_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, wf_fcu_id);
 
+static const struct of_device_id wf_fcu_of_id[] = {
+	{ .compatible = "fcu", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, wf_fcu_of_id);
+
 static struct i2c_driver wf_fcu_driver = {
 	.driver = {
 		.name	= "wf_fcu",
+		.of_match_table = wf_fcu_of_id,
 	},
 	.probe		= wf_fcu_probe,
 	.remove		= wf_fcu_remove,
diff --git a/drivers/macintosh/windfarm_lm75_sensor.c b/drivers/macintosh/windfarm_lm75_sensor.c
index 282c28a17ea1..1e5fa09845e7 100644
--- a/drivers/macintosh/windfarm_lm75_sensor.c
+++ b/drivers/macintosh/windfarm_lm75_sensor.c
@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/wait.h>
 #include <linux/i2c.h>
+#include <linux/of_device.h>
 #include <asm/prom.h>
 #include <asm/machdep.h>
 #include <asm/io.h>
@@ -91,9 +92,14 @@ static int wf_lm75_probe(struct i2c_client *client,
 			 const struct i2c_device_id *id)
 {	
 	struct wf_lm75_sensor *lm;
-	int rc, ds1775 = id->driver_data;
+	int rc, ds1775;
 	const char *name, *loc;
 
+	if (id)
+		ds1775 = id->driver_data;
+	else
+		ds1775 = !!of_device_get_match_data(&client->dev);
+
 	DBG("wf_lm75: creating  %s device at address 0x%02x\n",
 	    ds1775 ? "ds1775" : "lm75", client->addr);
 
@@ -164,9 +170,17 @@ static const struct i2c_device_id wf_lm75_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, wf_lm75_id);
 
+static const struct of_device_id wf_lm75_of_id[] = {
+	{ .compatible = "lm75", .data = (void *)0},
+	{ .compatible = "ds1775", .data = (void *)1 },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, wf_lm75_of_id);
+
 static struct i2c_driver wf_lm75_driver = {
 	.driver = {
 		.name	= "wf_lm75",
+		.of_match_table = wf_lm75_of_id,
 	},
 	.probe		= wf_lm75_probe,
 	.remove		= wf_lm75_remove,
diff --git a/drivers/macintosh/windfarm_lm87_sensor.c b/drivers/macintosh/windfarm_lm87_sensor.c
index e44525b19071..1a1f8f3f0abc 100644
--- a/drivers/macintosh/windfarm_lm87_sensor.c
+++ b/drivers/macintosh/windfarm_lm87_sensor.c
@@ -166,9 +166,16 @@ static const struct i2c_device_id wf_lm87_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, wf_lm87_id);
 
+static const struct of_device_id wf_lm87_of_id[] = {
+	{ .compatible = "lm87cimt", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, wf_lm87_of_id);
+
 static struct i2c_driver wf_lm87_driver = {
 	.driver = {
 		.name	= "wf_lm87",
+		.of_match_table = wf_lm87_of_id,
 	},
 	.probe		= wf_lm87_probe,
 	.remove		= wf_lm87_remove,
diff --git a/drivers/macintosh/windfarm_max6690_sensor.c b/drivers/macintosh/windfarm_max6690_sensor.c
index e666cc020683..1e7b03d44ad9 100644
--- a/drivers/macintosh/windfarm_max6690_sensor.c
+++ b/drivers/macintosh/windfarm_max6690_sensor.c
@@ -120,9 +120,16 @@ static const struct i2c_device_id wf_max6690_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, wf_max6690_id);
 
+static const struct of_device_id wf_max6690_of_id[] = {
+	{ .compatible = "max6690", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, wf_max6690_of_id);
+
 static struct i2c_driver wf_max6690_driver = {
 	.driver = {
 		.name		= "wf_max6690",
+		.of_match_table = wf_max6690_of_id,
 	},
 	.probe		= wf_max6690_probe,
 	.remove		= wf_max6690_remove,
diff --git a/drivers/macintosh/windfarm_pm112.c b/drivers/macintosh/windfarm_pm112.c
index 4150301a89a5..e8377ce0a95a 100644
--- a/drivers/macintosh/windfarm_pm112.c
+++ b/drivers/macintosh/windfarm_pm112.c
@@ -132,14 +132,6 @@ static int create_cpu_loop(int cpu)
 	s32 tmax;
 	int fmin;
 
-	/* Get PID params from the appropriate SAT */
-	hdr = smu_sat_get_sdb_partition(chip, 0xC8 + core, NULL);
-	if (hdr == NULL) {
-		printk(KERN_WARNING"windfarm: can't get CPU PID fan config\n");
-		return -EINVAL;
-	}
-	piddata = (struct smu_sdbp_cpupiddata *)&hdr[1];
-
 	/* Get FVT params to get Tmax; if not found, assume default */
 	hdr = smu_sat_get_sdb_partition(chip, 0xC4 + core, NULL);
 	if (hdr) {
@@ -152,6 +144,16 @@ static int create_cpu_loop(int cpu)
 	if (tmax < cpu_all_tmax)
 		cpu_all_tmax = tmax;
 
+	kfree(hdr);
+
+	/* Get PID params from the appropriate SAT */
+	hdr = smu_sat_get_sdb_partition(chip, 0xC8 + core, NULL);
+	if (hdr == NULL) {
+		printk(KERN_WARNING"windfarm: can't get CPU PID fan config\n");
+		return -EINVAL;
+	}
+	piddata = (struct smu_sdbp_cpupiddata *)&hdr[1];
+
 	/*
 	 * Darwin has a minimum fan speed of 1000 rpm for the 4-way and
 	 * 515 for the 2-way.  That appears to be overkill, so for now,
@@ -174,6 +176,9 @@ static int create_cpu_loop(int cpu)
 		pid.min = fmin;
 
 	wf_cpu_pid_init(&cpu_pid[cpu], &pid);
+
+	kfree(hdr);
+
 	return 0;
 }
 
diff --git a/drivers/macintosh/windfarm_smu_sat.c b/drivers/macintosh/windfarm_smu_sat.c
index c84ec49c3741..cb75dc035616 100644
--- a/drivers/macintosh/windfarm_smu_sat.c
+++ b/drivers/macintosh/windfarm_smu_sat.c
@@ -341,9 +341,16 @@ static const struct i2c_device_id wf_sat_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, wf_sat_id);
 
+static const struct of_device_id wf_sat_of_id[] = {
+	{ .compatible = "smu-sat", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, wf_sat_of_id);
+
 static struct i2c_driver wf_sat_driver = {
 	.driver = {
 		.name		= "wf_smu_sat",
+		.of_match_table = wf_sat_of_id,
 	},
 	.probe		= wf_sat_probe,
 	.remove		= wf_sat_remove,
diff --git a/drivers/mailbox/zynqmp-ipi-mailbox.c b/drivers/mailbox/zynqmp-ipi-mailbox.c
index 86887c9a349a..f9cc674ba9b7 100644
--- a/drivers/mailbox/zynqmp-ipi-mailbox.c
+++ b/drivers/mailbox/zynqmp-ipi-mailbox.c
@@ -504,10 +504,9 @@ static int zynqmp_ipi_mbox_probe(struct zynqmp_ipi_mbox *ipi_mbox,
 		mchan->req_buf_size = resource_size(&res);
 		mchan->req_buf = devm_ioremap(mdev, res.start,
 					      mchan->req_buf_size);
-		if (IS_ERR(mchan->req_buf)) {
+		if (!mchan->req_buf) {
 			dev_err(mdev, "Unable to map IPI buffer I/O memory\n");
-			ret = PTR_ERR(mchan->req_buf);
-			return ret;
+			return -ENOMEM;
 		}
 	} else if (ret != -ENODEV) {
 		dev_err(mdev, "Unmatched resource %s, %d.\n", name, ret);
@@ -520,10 +519,9 @@ static int zynqmp_ipi_mbox_probe(struct zynqmp_ipi_mbox *ipi_mbox,
 		mchan->resp_buf_size = resource_size(&res);
 		mchan->resp_buf = devm_ioremap(mdev, res.start,
 					       mchan->resp_buf_size);
-		if (IS_ERR(mchan->resp_buf)) {
+		if (!mchan->resp_buf) {
 			dev_err(mdev, "Unable to map IPI buffer I/O memory\n");
-			ret = PTR_ERR(mchan->resp_buf);
-			return ret;
+			return -ENOMEM;
 		}
 	} else if (ret != -ENODEV) {
 		dev_err(mdev, "Unmatched resource %s.\n", name);
@@ -543,10 +541,9 @@ static int zynqmp_ipi_mbox_probe(struct zynqmp_ipi_mbox *ipi_mbox,
 		mchan->req_buf_size = resource_size(&res);
 		mchan->req_buf = devm_ioremap(mdev, res.start,
 					      mchan->req_buf_size);
-		if (IS_ERR(mchan->req_buf)) {
+		if (!mchan->req_buf) {
 			dev_err(mdev, "Unable to map IPI buffer I/O memory\n");
-			ret = PTR_ERR(mchan->req_buf);
-			return ret;
+			return -ENOMEM;
 		}
 	} else if (ret != -ENODEV) {
 		dev_err(mdev, "Unmatched resource %s.\n", name);
@@ -559,10 +556,9 @@ static int zynqmp_ipi_mbox_probe(struct zynqmp_ipi_mbox *ipi_mbox,
 		mchan->resp_buf_size = resource_size(&res);
 		mchan->resp_buf = devm_ioremap(mdev, res.start,
 					       mchan->resp_buf_size);
-		if (IS_ERR(mchan->resp_buf)) {
+		if (!mchan->resp_buf) {
 			dev_err(mdev, "Unable to map IPI buffer I/O memory\n");
-			ret = PTR_ERR(mchan->resp_buf);
-			return ret;
+			return -ENOMEM;
 		}
 	} else if (ret != -ENODEV) {
 		dev_err(mdev, "Unmatched resource %s.\n", name);
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index a45c2f91ec2b..2e396954b39d 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -264,7 +264,7 @@ struct bcache_device {
 #define BCACHE_DEV_UNLINK_DONE		2
 #define BCACHE_DEV_WB_RUNNING		3
 #define BCACHE_DEV_RATE_DW_RUNNING	4
-	unsigned int		nr_stripes;
+	int			nr_stripes;
 	unsigned int		stripe_size;
 	atomic_t		*stripe_sectors_dirty;
 	unsigned long		*full_dirty_stripes;
@@ -329,6 +329,9 @@ struct cached_dev {
 	 */
 	atomic_t		has_dirty;
 
+#define BCH_CACHE_READA_ALL		0
+#define BCH_CACHE_READA_META_ONLY	1
+	unsigned int		cache_readahead_policy;
 	struct bch_ratelimit	writeback_rate;
 	struct delayed_work	writeback_rate_update;
 
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index 268f1b685084..ec48cf86cab6 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -321,7 +321,7 @@ int bch_btree_keys_alloc(struct btree_keys *b,
 
 	b->page_order = page_order;
 
-	t->data = (void *) __get_free_pages(gfp, b->page_order);
+	t->data = (void *) __get_free_pages(__GFP_COMP|gfp, b->page_order);
 	if (!t->data)
 		goto err;
 
diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h
index c71365e7c1fa..a50dcfda656f 100644
--- a/drivers/md/bcache/bset.h
+++ b/drivers/md/bcache/bset.h
@@ -397,7 +397,8 @@ void bch_btree_keys_stats(struct btree_keys *b, struct bset_stats *state);
 
 /* Bkey utility code */
 
-#define bset_bkey_last(i)	bkey_idx((struct bkey *) (i)->d, (i)->keys)
+#define bset_bkey_last(i)	bkey_idx((struct bkey *) (i)->d, \
+					 (unsigned int)(i)->keys)
 
 static inline struct bkey *bset_bkey_idx(struct bset *i, unsigned int idx)
 {
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index d307c65d90fc..b60cb7a99b18 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -836,7 +836,7 @@ int bch_btree_cache_alloc(struct cache_set *c)
 	mutex_init(&c->verify_lock);
 
 	c->verify_ondisk = (void *)
-		__get_free_pages(GFP_KERNEL, ilog2(bucket_pages(c)));
+		__get_free_pages(GFP_KERNEL|__GFP_COMP, ilog2(bucket_pages(c)));
 
 	c->verify_data = mca_bucket_alloc(c, &ZERO_KEY, GFP_KERNEL);
 
@@ -1438,7 +1438,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op,
 			if (__set_blocks(n1, n1->keys + n2->keys,
 					 block_bytes(b->c)) >
 			    btree_blocks(new_nodes[i]))
-				goto out_nocoalesce;
+				goto out_unlock_nocoalesce;
 
 			keys = n2->keys;
 			/* Take the key of the node we're getting rid of */
@@ -1467,7 +1467,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op,
 
 		if (__bch_keylist_realloc(&keylist,
 					  bkey_u64s(&new_nodes[i]->key)))
-			goto out_nocoalesce;
+			goto out_unlock_nocoalesce;
 
 		bch_btree_node_write(new_nodes[i], &cl);
 		bch_keylist_add(&keylist, &new_nodes[i]->key);
@@ -1513,6 +1513,10 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op,
 	/* Invalidated our iterator */
 	return -EINTR;
 
+out_unlock_nocoalesce:
+	for (i = 0; i < nodes; i++)
+		mutex_unlock(&new_nodes[i]->write_lock);
+
 out_nocoalesce:
 	closure_sync(&cl);
 
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 33556acdcf9c..e145c2b1e2c9 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -865,8 +865,8 @@ int bch_journal_alloc(struct cache_set *c)
 	j->w[1].c = c;
 
 	if (!(init_fifo(&j->pin, JOURNAL_PIN, GFP_KERNEL)) ||
-	    !(j->w[0].data = (void *) __get_free_pages(GFP_KERNEL, JSET_BITS)) ||
-	    !(j->w[1].data = (void *) __get_free_pages(GFP_KERNEL, JSET_BITS)))
+	    !(j->w[0].data = (void *) __get_free_pages(GFP_KERNEL|__GFP_COMP, JSET_BITS)) ||
+	    !(j->w[1].data = (void *) __get_free_pages(GFP_KERNEL|__GFP_COMP, JSET_BITS)))
 		return -ENOMEM;
 
 	return 0;
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 41adcd1546f1..4045ae748f17 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -391,13 +391,20 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio)
 		goto skip;
 
 	/*
-	 * Flag for bypass if the IO is for read-ahead or background,
-	 * unless the read-ahead request is for metadata
+	 * If the bio is for read-ahead or background IO, bypass it or
+	 * not depends on the following situations,
+	 * - If the IO is for meta data, always cache it and no bypass
+	 * - If the IO is not meta data, check dc->cache_reada_policy,
+	 *      BCH_CACHE_READA_ALL: cache it and not bypass
+	 *      BCH_CACHE_READA_META_ONLY: not cache it and bypass
+	 * That is, read-ahead request for metadata always get cached
 	 * (eg, for gfs2 or xfs).
 	 */
-	if (bio->bi_opf & (REQ_RAHEAD|REQ_BACKGROUND) &&
-	    !(bio->bi_opf & (REQ_META|REQ_PRIO)))
-		goto skip;
+	if ((bio->bi_opf & (REQ_RAHEAD|REQ_BACKGROUND))) {
+		if (!(bio->bi_opf & (REQ_META|REQ_PRIO)) &&
+		    (dc->cache_readahead_policy != BCH_CACHE_READA_ALL))
+			goto skip;
+	}
 
 	if (bio->bi_iter.bi_sector & (c->sb.block_size - 1) ||
 	    bio_sectors(bio) & (c->sb.block_size - 1)) {
diff --git a/drivers/md/bcache/stats.c b/drivers/md/bcache/stats.c
index ba1c93791d8d..503aafe188dc 100644
--- a/drivers/md/bcache/stats.c
+++ b/drivers/md/bcache/stats.c
@@ -109,9 +109,13 @@ int bch_cache_accounting_add_kobjs(struct cache_accounting *acc,
 
 void bch_cache_accounting_clear(struct cache_accounting *acc)
 {
-	memset(&acc->total.cache_hits,
-	       0,
-	       sizeof(struct cache_stats));
+	acc->total.cache_hits = 0;
+	acc->total.cache_misses = 0;
+	acc->total.cache_bypass_hits = 0;
+	acc->total.cache_bypass_misses = 0;
+	acc->total.cache_readaheads = 0;
+	acc->total.cache_miss_collisions = 0;
+	acc->total.sectors_bypassed = 0;
 }
 
 void bch_cache_accounting_destroy(struct cache_accounting *acc)
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 7415ce647479..5248bca5e2ed 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -782,7 +782,9 @@ static void bcache_device_free(struct bcache_device *d)
 		bcache_device_detach(d);
 
 	if (disk) {
-		if (disk->flags & GENHD_FL_UP)
+		bool disk_added = (disk->flags & GENHD_FL_UP) != 0;
+
+		if (disk_added)
 			del_gendisk(disk);
 
 		if (disk->queue)
@@ -790,7 +792,8 @@ static void bcache_device_free(struct bcache_device *d)
 
 		ida_simple_remove(&bcache_device_idx,
 				  first_minor_to_idx(disk->first_minor));
-		put_disk(disk);
+		if (disk_added)
+			put_disk(disk);
 	}
 
 	bioset_exit(&d->bio_split);
@@ -1232,6 +1235,9 @@ static void cached_dev_free(struct closure *cl)
 
 	mutex_unlock(&bch_register_lock);
 
+	if (dc->sb_bio.bi_inline_vecs[0].bv_page)
+		put_page(bio_first_page_all(&dc->sb_bio));
+
 	if (!IS_ERR_OR_NULL(dc->bdev))
 		blkdev_put(dc->bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
 
@@ -1697,7 +1703,7 @@ void bch_cache_set_unregister(struct cache_set *c)
 }
 
 #define alloc_bucket_pages(gfp, c)			\
-	((void *) __get_free_pages(__GFP_ZERO|gfp, ilog2(bucket_pages(c))))
+	((void *) __get_free_pages(__GFP_ZERO|__GFP_COMP|gfp, ilog2(bucket_pages(c))))
 
 struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 {
@@ -2017,7 +2023,14 @@ found:
 	    sysfs_create_link(&c->kobj, &ca->kobj, buf))
 		goto err;
 
-	if (ca->sb.seq > c->sb.seq) {
+	/*
+	 * A special case is both ca->sb.seq and c->sb.seq are 0,
+	 * such condition happens on a new created cache device whose
+	 * super block is never flushed yet. In this case c->sb.version
+	 * and other members should be updated too, otherwise we will
+	 * have a mistaken super block version in cache set.
+	 */
+	if (ca->sb.seq > c->sb.seq || c->sb.seq == 0) {
 		c->sb.version		= ca->sb.version;
 		memcpy(c->sb.set_uuid, ca->sb.set_uuid, 16);
 		c->sb.flags             = ca->sb.flags;
@@ -2297,29 +2310,35 @@ static bool bch_is_open(struct block_device *bdev)
 static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 			       const char *buffer, size_t size)
 {
-	ssize_t ret = -EINVAL;
-	const char *err = "cannot allocate memory";
+	const char *err;
 	char *path = NULL;
-	struct cache_sb *sb = NULL;
+	struct cache_sb *sb;
 	struct block_device *bdev = NULL;
-	struct page *sb_page = NULL;
+	struct page *sb_page;
+	ssize_t ret;
 
+	ret = -EBUSY;
+	err = "failed to reference bcache module";
 	if (!try_module_get(THIS_MODULE))
-		return -EBUSY;
+		goto out;
 
 	/* For latest state of bcache_is_reboot */
 	smp_mb();
+	err = "bcache is in reboot";
 	if (bcache_is_reboot)
-		return -EBUSY;
+		goto out_module_put;
 
+	ret = -ENOMEM;
+	err = "cannot allocate memory";
 	path = kstrndup(buffer, size, GFP_KERNEL);
 	if (!path)
-		goto err;
+		goto out_module_put;
 
 	sb = kmalloc(sizeof(struct cache_sb), GFP_KERNEL);
 	if (!sb)
-		goto err;
+		goto out_free_path;
 
+	ret = -EINVAL;
 	err = "failed to open device";
 	bdev = blkdev_get_by_path(strim(path),
 				  FMODE_READ|FMODE_WRITE|FMODE_EXCL,
@@ -2336,57 +2355,69 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 			if (!IS_ERR(bdev))
 				bdput(bdev);
 			if (attr == &ksysfs_register_quiet)
-				goto quiet_out;
+				goto done;
 		}
-		goto err;
+		goto out_free_sb;
 	}
 
 	err = "failed to set blocksize";
 	if (set_blocksize(bdev, 4096))
-		goto err_close;
+		goto out_blkdev_put;
 
 	err = read_super(sb, bdev, &sb_page);
 	if (err)
-		goto err_close;
+		goto out_blkdev_put;
 
 	err = "failed to register device";
 	if (SB_IS_BDEV(sb)) {
 		struct cached_dev *dc = kzalloc(sizeof(*dc), GFP_KERNEL);
 
 		if (!dc)
-			goto err_close;
+			goto out_put_sb_page;
 
 		mutex_lock(&bch_register_lock);
 		ret = register_bdev(sb, sb_page, bdev, dc);
 		mutex_unlock(&bch_register_lock);
 		/* blkdev_put() will be called in cached_dev_free() */
-		if (ret < 0)
-			goto err;
+		if (ret < 0) {
+			bdev = NULL;
+			goto out_put_sb_page;
+		}
 	} else {
 		struct cache *ca = kzalloc(sizeof(*ca), GFP_KERNEL);
 
 		if (!ca)
-			goto err_close;
+			goto out_put_sb_page;
 
 		/* blkdev_put() will be called in bch_cache_release() */
-		if (register_cache(sb, sb_page, bdev, ca) != 0)
-			goto err;
+		if (register_cache(sb, sb_page, bdev, ca) != 0) {
+			bdev = NULL;
+			goto out_put_sb_page;
+		}
 	}
-quiet_out:
-	ret = size;
-out:
-	if (sb_page)
-		put_page(sb_page);
+
+	put_page(sb_page);
+done:
 	kfree(sb);
 	kfree(path);
 	module_put(THIS_MODULE);
+	return size;
+
+out_put_sb_page:
+	put_page(sb_page);
+out_blkdev_put:
+	if (bdev)
+		blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
+out_free_sb:
+	kfree(sb);
+out_free_path:
+	kfree(path);
+	path = NULL;
+out_module_put:
+	module_put(THIS_MODULE);
+out:
+	pr_info("error %s: %s", path?path:"", err);
 	return ret;
-
-err_close:
-	blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
-err:
-	pr_info("error %s: %s", path, err);
-	goto out;
 }
 
 static int bcache_reboot(struct notifier_block *n, unsigned long code, void *x)
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 54cd1727d20c..9d5cc9fc8d65 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -27,6 +27,12 @@ static const char * const bch_cache_modes[] = {
 	NULL
 };
 
+static const char * const bch_reada_cache_policies[] = {
+	"all",
+	"meta-only",
+	NULL
+};
+
 /* Default is 0 ("auto") */
 static const char * const bch_stop_on_failure_modes[] = {
 	"auto",
@@ -100,6 +106,7 @@ rw_attribute(congested_write_threshold_us);
 rw_attribute(sequential_cutoff);
 rw_attribute(data_csum);
 rw_attribute(cache_mode);
+rw_attribute(readahead_cache_policy);
 rw_attribute(stop_when_cache_set_failed);
 rw_attribute(writeback_metadata);
 rw_attribute(writeback_running);
@@ -167,6 +174,11 @@ SHOW(__bch_cached_dev)
 					       bch_cache_modes,
 					       BDEV_CACHE_MODE(&dc->sb));
 
+	if (attr == &sysfs_readahead_cache_policy)
+		return bch_snprint_string_list(buf, PAGE_SIZE,
+					      bch_reada_cache_policies,
+					      dc->cache_readahead_policy);
+
 	if (attr == &sysfs_stop_when_cache_set_failed)
 		return bch_snprint_string_list(buf, PAGE_SIZE,
 					       bch_stop_on_failure_modes,
@@ -349,6 +361,15 @@ STORE(__cached_dev)
 		}
 	}
 
+	if (attr == &sysfs_readahead_cache_policy) {
+		v = __sysfs_match_string(bch_reada_cache_policies, -1, buf);
+		if (v < 0)
+			return v;
+
+		if ((unsigned int) v != dc->cache_readahead_policy)
+			dc->cache_readahead_policy = v;
+	}
+
 	if (attr == &sysfs_stop_when_cache_set_failed) {
 		v = __sysfs_match_string(bch_stop_on_failure_modes, -1, buf);
 		if (v < 0)
@@ -463,6 +484,7 @@ static struct attribute *bch_cached_dev_files[] = {
 	&sysfs_data_csum,
 #endif
 	&sysfs_cache_mode,
+	&sysfs_readahead_cache_policy,
 	&sysfs_stop_when_cache_set_failed,
 	&sysfs_writeback_metadata,
 	&sysfs_writeback_running,
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index e9ffcea1ca50..58bedd51e11b 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -516,15 +516,19 @@ void bcache_dev_sectors_dirty_add(struct cache_set *c, unsigned int inode,
 				  uint64_t offset, int nr_sectors)
 {
 	struct bcache_device *d = c->devices[inode];
-	unsigned int stripe_offset, stripe, sectors_dirty;
+	unsigned int stripe_offset, sectors_dirty;
+	int stripe;
 
 	if (!d)
 		return;
 
+	stripe = offset_to_stripe(d, offset);
+	if (stripe < 0)
+		return;
+
 	if (UUID_FLASH_ONLY(&c->uuids[inode]))
 		atomic_long_add(nr_sectors, &c->flash_dev_dirty_sectors);
 
-	stripe = offset_to_stripe(d, offset);
 	stripe_offset = offset & (d->stripe_size - 1);
 
 	while (nr_sectors) {
@@ -564,12 +568,12 @@ static bool dirty_pred(struct keybuf *buf, struct bkey *k)
 static void refill_full_stripes(struct cached_dev *dc)
 {
 	struct keybuf *buf = &dc->writeback_keys;
-	unsigned int start_stripe, stripe, next_stripe;
+	unsigned int start_stripe, next_stripe;
+	int stripe;
 	bool wrapped = false;
 
 	stripe = offset_to_stripe(&dc->disk, KEY_OFFSET(&buf->last_scanned));
-
-	if (stripe >= dc->disk.nr_stripes)
+	if (stripe < 0)
 		stripe = 0;
 
 	start_stripe = stripe;
diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h
index 4e4c6810dc3c..c4ff76037227 100644
--- a/drivers/md/bcache/writeback.h
+++ b/drivers/md/bcache/writeback.h
@@ -33,10 +33,22 @@ static inline uint64_t bcache_dev_sectors_dirty(struct bcache_device *d)
 	return ret;
 }
 
-static inline unsigned int offset_to_stripe(struct bcache_device *d,
+static inline int offset_to_stripe(struct bcache_device *d,
 					uint64_t offset)
 {
 	do_div(offset, d->stripe_size);
+
+	/* d->nr_stripes is in range [1, INT_MAX] */
+	if (unlikely(offset >= d->nr_stripes)) {
+		pr_err("Invalid stripe %llu (>= nr_stripes %d).\n",
+			offset, d->nr_stripes);
+		return -EINVAL;
+	}
+
+	/*
+	 * Here offset is definitly smaller than INT_MAX,
+	 * return it as int will never overflow.
+	 */
 	return offset;
 }
 
@@ -44,7 +56,10 @@ static inline bool bcache_dev_stripe_dirty(struct cached_dev *dc,
 					   uint64_t offset,
 					   unsigned int nr_sectors)
 {
-	unsigned int stripe = offset_to_stripe(&dc->disk, offset);
+	int stripe = offset_to_stripe(&dc->disk, offset);
+
+	if (stripe < 0)
+		return false;
 
 	while (1) {
 		if (atomic_read(dc->disk.stripe_sectors_dirty + stripe))
diff --git a/drivers/md/dm-bio-record.h b/drivers/md/dm-bio-record.h
index c82578af56a5..2ea0360108e1 100644
--- a/drivers/md/dm-bio-record.h
+++ b/drivers/md/dm-bio-record.h
@@ -20,8 +20,13 @@
 struct dm_bio_details {
 	struct gendisk *bi_disk;
 	u8 bi_partno;
+	int __bi_remaining;
 	unsigned long bi_flags;
 	struct bvec_iter bi_iter;
+	bio_end_io_t *bi_end_io;
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+	struct bio_integrity_payload *bi_integrity;
+#endif
 };
 
 static inline void dm_bio_record(struct dm_bio_details *bd, struct bio *bio)
@@ -30,6 +35,11 @@ static inline void dm_bio_record(struct dm_bio_details *bd, struct bio *bio)
 	bd->bi_partno = bio->bi_partno;
 	bd->bi_flags = bio->bi_flags;
 	bd->bi_iter = bio->bi_iter;
+	bd->__bi_remaining = atomic_read(&bio->__bi_remaining);
+	bd->bi_end_io = bio->bi_end_io;
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+	bd->bi_integrity = bio_integrity(bio);
+#endif
 }
 
 static inline void dm_bio_restore(struct dm_bio_details *bd, struct bio *bio)
@@ -38,6 +48,11 @@ static inline void dm_bio_restore(struct dm_bio_details *bd, struct bio *bio)
 	bio->bi_partno = bd->bi_partno;
 	bio->bi_flags = bd->bi_flags;
 	bio->bi_iter = bd->bi_iter;
+	atomic_set(&bio->__bi_remaining, bd->__bi_remaining);
+	bio->bi_end_io = bd->bi_end_io;
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+	bio->bi_integrity = bd->bi_integrity;
+#endif
 }
 
 #endif
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 8346e6d1816c..f595e9867cbe 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -2867,8 +2867,8 @@ static void cache_postsuspend(struct dm_target *ti)
 	prevent_background_work(cache);
 	BUG_ON(atomic_read(&cache->nr_io_migrations));
 
-	cancel_delayed_work(&cache->waker);
-	flush_workqueue(cache->wq);
+	cancel_delayed_work_sync(&cache->waker);
+	drain_workqueue(cache->wq);
 	WARN_ON(cache->tracker.in_flight);
 
 	/*
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index e78e4d3d3352..47f6065a31e8 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -481,8 +481,14 @@ static int crypt_iv_essiv_gen(struct crypt_config *cc, u8 *iv,
 static int crypt_iv_benbi_ctr(struct crypt_config *cc, struct dm_target *ti,
 			      const char *opts)
 {
-	unsigned bs = crypto_skcipher_blocksize(any_tfm(cc));
-	int log = ilog2(bs);
+	unsigned bs;
+	int log;
+
+	if (test_bit(CRYPT_MODE_INTEGRITY_AEAD, &cc->cipher_flags))
+		bs = crypto_aead_blocksize(any_tfm_aead(cc));
+	else
+		bs = crypto_skcipher_blocksize(any_tfm(cc));
+	log = ilog2(bs);
 
 	/* we need to calculate how far we must shift the sector count
 	 * to get the cipher block count, we use this shift in _gen */
@@ -3083,7 +3089,7 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits)
 	limits->max_segment_size = PAGE_SIZE;
 
 	limits->logical_block_size =
-		max_t(unsigned short, limits->logical_block_size, cc->sector_size);
+		max_t(unsigned, limits->logical_block_size, cc->sector_size);
 	limits->physical_block_size =
 		max_t(unsigned, limits->physical_block_size, cc->sector_size);
 	limits->io_min = max_t(unsigned, limits->io_min, cc->sector_size);
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 29a5e5b4c63c..382b8694be50 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -6,6 +6,8 @@
  * This file is released under the GPL.
  */
 
+#include "dm-bio-record.h"
+
 #include <linux/compiler.h>
 #include <linux/module.h>
 #include <linux/device-mapper.h>
@@ -199,17 +201,19 @@ struct dm_integrity_c {
 	__u8 log2_blocks_per_bitmap_bit;
 
 	unsigned char mode;
-	int suspending;
 
 	int failed;
 
 	struct crypto_shash *internal_hash;
 
+	struct dm_target *ti;
+
 	/* these variables are locked with endio_wait.lock */
 	struct rb_root in_progress;
 	struct list_head wait_list;
 	wait_queue_head_t endio_wait;
 	struct workqueue_struct *wait_wq;
+	struct workqueue_struct *offload_wq;
 
 	unsigned char commit_seq;
 	commit_id_t commit_ids[N_COMMIT_IDS];
@@ -290,11 +294,7 @@ struct dm_integrity_io {
 
 	struct completion *completion;
 
-	struct gendisk *orig_bi_disk;
-	u8 orig_bi_partno;
-	bio_end_io_t *orig_bi_end_io;
-	struct bio_integrity_payload *orig_bi_integrity;
-	struct bvec_iter orig_bi_iter;
+	struct dm_bio_details bio_details;
 };
 
 struct journal_completion {
@@ -1421,7 +1421,7 @@ static void dec_in_flight(struct dm_integrity_io *dio)
 			dio->range.logical_sector += dio->range.n_sectors;
 			bio_advance(bio, dio->range.n_sectors << SECTOR_SHIFT);
 			INIT_WORK(&dio->work, integrity_bio_wait);
-			queue_work(ic->wait_wq, &dio->work);
+			queue_work(ic->offload_wq, &dio->work);
 			return;
 		}
 		do_endio_flush(ic, dio);
@@ -1432,14 +1432,9 @@ static void integrity_end_io(struct bio *bio)
 {
 	struct dm_integrity_io *dio = dm_per_bio_data(bio, sizeof(struct dm_integrity_io));
 
-	bio->bi_iter = dio->orig_bi_iter;
-	bio->bi_disk = dio->orig_bi_disk;
-	bio->bi_partno = dio->orig_bi_partno;
-	if (dio->orig_bi_integrity) {
-		bio->bi_integrity = dio->orig_bi_integrity;
+	dm_bio_restore(&dio->bio_details, bio);
+	if (bio->bi_integrity)
 		bio->bi_opf |= REQ_INTEGRITY;
-	}
-	bio->bi_end_io = dio->orig_bi_end_io;
 
 	if (dio->completion)
 		complete(dio->completion);
@@ -1506,7 +1501,7 @@ static void integrity_metadata(struct work_struct *w)
 		struct bio *bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io));
 		char *checksums;
 		unsigned extra_space = unlikely(digest_size > ic->tag_size) ? digest_size - ic->tag_size : 0;
-		char checksums_onstack[HASH_MAX_DIGESTSIZE];
+		char checksums_onstack[max((size_t)HASH_MAX_DIGESTSIZE, MAX_TAG_SIZE)];
 		unsigned sectors_to_process = dio->range.n_sectors;
 		sector_t sector = dio->range.logical_sector;
 
@@ -1524,7 +1519,7 @@ static void integrity_metadata(struct work_struct *w)
 			}
 		}
 
-		__bio_for_each_segment(bv, bio, iter, dio->orig_bi_iter) {
+		__bio_for_each_segment(bv, bio, iter, dio->bio_details.bi_iter) {
 			unsigned pos;
 			char *mem, *checksums_ptr;
 
@@ -1568,7 +1563,7 @@ again:
 		if (likely(checksums != checksums_onstack))
 			kfree(checksums);
 	} else {
-		struct bio_integrity_payload *bip = dio->orig_bi_integrity;
+		struct bio_integrity_payload *bip = dio->bio_details.bi_integrity;
 
 		if (bip) {
 			struct bio_vec biv;
@@ -1735,7 +1730,7 @@ retry_kmap:
 				} while (++s < ic->sectors_per_block);
 #ifdef INTERNAL_VERIFY
 				if (ic->internal_hash) {
-					char checksums_onstack[max(HASH_MAX_DIGESTSIZE, MAX_TAG_SIZE)];
+					char checksums_onstack[max((size_t)HASH_MAX_DIGESTSIZE, MAX_TAG_SIZE)];
 
 					integrity_sector_checksum(ic, logical_sector, mem + bv.bv_offset, checksums_onstack);
 					if (unlikely(memcmp(checksums_onstack, journal_entry_tag(ic, je), ic->tag_size))) {
@@ -1847,7 +1842,7 @@ static void dm_integrity_map_continue(struct dm_integrity_io *dio, bool from_map
 
 	if (need_sync_io && from_map) {
 		INIT_WORK(&dio->work, integrity_bio_wait);
-		queue_work(ic->metadata_wq, &dio->work);
+		queue_work(ic->offload_wq, &dio->work);
 		return;
 	}
 
@@ -1987,20 +1982,13 @@ offload_to_thread:
 	} else
 		dio->completion = NULL;
 
-	dio->orig_bi_iter = bio->bi_iter;
-
-	dio->orig_bi_disk = bio->bi_disk;
-	dio->orig_bi_partno = bio->bi_partno;
+	dm_bio_record(&dio->bio_details, bio);
 	bio_set_dev(bio, ic->dev->bdev);
-
-	dio->orig_bi_integrity = bio_integrity(bio);
 	bio->bi_integrity = NULL;
 	bio->bi_opf &= ~REQ_INTEGRITY;
-
-	dio->orig_bi_end_io = bio->bi_end_io;
 	bio->bi_end_io = integrity_end_io;
-
 	bio->bi_iter.bi_size = dio->range.n_sectors << SECTOR_SHIFT;
+
 	generic_make_request(bio);
 
 	if (need_sync_io) {
@@ -2297,7 +2285,7 @@ static void integrity_writer(struct work_struct *w)
 	unsigned prev_free_sectors;
 
 	/* the following test is not needed, but it tests the replay code */
-	if (READ_ONCE(ic->suspending) && !ic->meta_dev)
+	if (unlikely(dm_post_suspending(ic->ti)) && !ic->meta_dev)
 		return;
 
 	spin_lock_irq(&ic->endio_wait.lock);
@@ -2359,7 +2347,7 @@ static void integrity_recalc(struct work_struct *w)
 
 next_chunk:
 
-	if (unlikely(READ_ONCE(ic->suspending)))
+	if (unlikely(dm_post_suspending(ic->ti)))
 		goto unlock_ret;
 
 	range.logical_sector = le64_to_cpu(ic->sb->recalc_sector);
@@ -2484,7 +2472,7 @@ static void bitmap_block_work(struct work_struct *w)
 				    dio->range.n_sectors, BITMAP_OP_TEST_ALL_SET)) {
 			remove_range(ic, &dio->range);
 			INIT_WORK(&dio->work, integrity_bio_wait);
-			queue_work(ic->wait_wq, &dio->work);
+			queue_work(ic->offload_wq, &dio->work);
 		} else {
 			block_bitmap_op(ic, ic->journal, dio->range.logical_sector,
 					dio->range.n_sectors, BITMAP_OP_SET);
@@ -2507,7 +2495,7 @@ static void bitmap_block_work(struct work_struct *w)
 
 		remove_range(ic, &dio->range);
 		INIT_WORK(&dio->work, integrity_bio_wait);
-		queue_work(ic->wait_wq, &dio->work);
+		queue_work(ic->offload_wq, &dio->work);
 	}
 
 	queue_delayed_work(ic->commit_wq, &ic->bitmap_flush_work, ic->bitmap_flush_interval);
@@ -2787,8 +2775,6 @@ static void dm_integrity_postsuspend(struct dm_target *ti)
 
 	del_timer_sync(&ic->autocommit_timer);
 
-	WRITE_ONCE(ic->suspending, 1);
-
 	if (ic->recalc_wq)
 		drain_workqueue(ic->recalc_wq);
 
@@ -2817,8 +2803,6 @@ static void dm_integrity_postsuspend(struct dm_target *ti)
 #endif
 	}
 
-	WRITE_ONCE(ic->suspending, 0);
-
 	BUG_ON(!RB_EMPTY_ROOT(&ic->in_progress));
 
 	ic->journal_uptodate = true;
@@ -2871,17 +2855,24 @@ static void dm_integrity_resume(struct dm_target *ti)
 	} else {
 		replay_journal(ic);
 		if (ic->mode == 'B') {
-			int mode;
 			ic->sb->flags |= cpu_to_le32(SB_FLAG_DIRTY_BITMAP);
 			ic->sb->log2_blocks_per_bitmap_bit = ic->log2_blocks_per_bitmap_bit;
 			r = sync_rw_sb(ic, REQ_OP_WRITE, REQ_FUA);
 			if (unlikely(r))
 				dm_integrity_io_error(ic, "writing superblock", r);
 
-			mode = ic->recalculate_flag ? BITMAP_OP_SET : BITMAP_OP_CLEAR;
-			block_bitmap_op(ic, ic->journal, 0, ic->provided_data_sectors, mode);
-			block_bitmap_op(ic, ic->recalc_bitmap, 0, ic->provided_data_sectors, mode);
-			block_bitmap_op(ic, ic->may_write_bitmap, 0, ic->provided_data_sectors, mode);
+			block_bitmap_op(ic, ic->journal, 0, ic->provided_data_sectors, BITMAP_OP_CLEAR);
+			block_bitmap_op(ic, ic->recalc_bitmap, 0, ic->provided_data_sectors, BITMAP_OP_CLEAR);
+			block_bitmap_op(ic, ic->may_write_bitmap, 0, ic->provided_data_sectors, BITMAP_OP_CLEAR);
+			if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING) &&
+			    le64_to_cpu(ic->sb->recalc_sector) < ic->provided_data_sectors) {
+				block_bitmap_op(ic, ic->journal, le64_to_cpu(ic->sb->recalc_sector),
+						ic->provided_data_sectors - le64_to_cpu(ic->sb->recalc_sector), BITMAP_OP_SET);
+				block_bitmap_op(ic, ic->recalc_bitmap, le64_to_cpu(ic->sb->recalc_sector),
+						ic->provided_data_sectors - le64_to_cpu(ic->sb->recalc_sector), BITMAP_OP_SET);
+				block_bitmap_op(ic, ic->may_write_bitmap, le64_to_cpu(ic->sb->recalc_sector),
+						ic->provided_data_sectors - le64_to_cpu(ic->sb->recalc_sector), BITMAP_OP_SET);
+			}
 			rw_journal_sectors(ic, REQ_OP_WRITE, REQ_FUA | REQ_SYNC, 0,
 					   ic->n_bitmap_blocks * (BITMAP_BLOCK_SIZE >> SECTOR_SHIFT), NULL);
 		}
@@ -2949,7 +2940,7 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type,
 			DMEMIT(" meta_device:%s", ic->meta_dev->name);
 		if (ic->sectors_per_block != 1)
 			DMEMIT(" block_size:%u", ic->sectors_per_block << SECTOR_SHIFT);
-		if (ic->recalculate_flag)
+		if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING))
 			DMEMIT(" recalculate");
 		DMEMIT(" journal_sectors:%u", ic->initial_sectors - SB_SECTORS);
 		DMEMIT(" interleave_sectors:%u", 1U << ic->sb->log2_interleave_sectors);
@@ -3596,6 +3587,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	}
 	ti->private = ic;
 	ti->per_io_data_size = sizeof(struct dm_integrity_io);
+	ic->ti = ti;
 
 	ic->in_progress = RB_ROOT;
 	INIT_LIST_HEAD(&ic->wait_list);
@@ -3807,6 +3799,14 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv)
 		goto bad;
 	}
 
+	ic->offload_wq = alloc_workqueue("dm-integrity-offload", WQ_MEM_RECLAIM,
+					  METADATA_WORKQUEUE_MAX_ACTIVE);
+	if (!ic->offload_wq) {
+		ti->error = "Cannot allocate workqueue";
+		r = -ENOMEM;
+		goto bad;
+	}
+
 	ic->commit_wq = alloc_workqueue("dm-integrity-commit", WQ_MEM_RECLAIM, 1);
 	if (!ic->commit_wq) {
 		ti->error = "Cannot allocate workqueue";
@@ -4111,6 +4111,8 @@ static void dm_integrity_dtr(struct dm_target *ti)
 		destroy_workqueue(ic->metadata_wq);
 	if (ic->wait_wq)
 		destroy_workqueue(ic->wait_wq);
+	if (ic->offload_wq)
+		destroy_workqueue(ic->offload_wq);
 	if (ic->commit_wq)
 		destroy_workqueue(ic->commit_wq);
 	if (ic->writer_wq)
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index e0c32793c248..f2de4c73cc8f 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -576,10 +576,12 @@ static struct pgpath *__map_bio(struct multipath *m, struct bio *bio)
 
 	/* Do we need to select a new pgpath? */
 	pgpath = READ_ONCE(m->current_pgpath);
-	queue_io = test_bit(MPATHF_QUEUE_IO, &m->flags);
-	if (!pgpath || !queue_io)
+	if (!pgpath || !test_bit(MPATHF_QUEUE_IO, &m->flags))
 		pgpath = choose_pgpath(m, bio->bi_iter.bi_size);
 
+	/* MPATHF_QUEUE_IO might have been cleared by choose_pgpath. */
+	queue_io = test_bit(MPATHF_QUEUE_IO, &m->flags);
+
 	if ((pgpath && queue_io) ||
 	    (!pgpath && test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))) {
 		/* Queue for the daemon to resubmit */
@@ -1854,7 +1856,7 @@ static int multipath_prepare_ioctl(struct dm_target *ti,
 	int r;
 
 	current_pgpath = READ_ONCE(m->current_pgpath);
-	if (!current_pgpath)
+	if (!current_pgpath || !test_bit(MPATHF_QUEUE_IO, &m->flags))
 		current_pgpath = choose_pgpath(m, 0);
 
 	if (current_pgpath) {
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index b41ecb451c78..99784f16cb56 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -70,9 +70,6 @@ void dm_start_queue(struct request_queue *q)
 
 void dm_stop_queue(struct request_queue *q)
 {
-	if (blk_mq_queue_stopped(q))
-		return;
-
 	blk_mq_quiesce_queue(q);
 }
 
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index 3c50c4e4da8f..963d3774c93e 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -17,7 +17,7 @@
 #include <linux/dm-bufio.h>
 
 #define DM_MSG_PREFIX "persistent snapshot"
-#define DM_CHUNK_SIZE_DEFAULT_SECTORS 32	/* 16KB */
+#define DM_CHUNK_SIZE_DEFAULT_SECTORS 32U	/* 16KB */
 
 #define DM_PREFETCH_CHUNKS		12
 
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index b88d6d701f5b..4cd8868f8004 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -387,16 +387,15 @@ static int subtree_equal(void *context, const void *value1_le, const void *value
  * Variant that is used for in-core only changes or code that
  * shouldn't put the pool in service on its own (e.g. commit).
  */
-static inline void __pmd_write_lock(struct dm_pool_metadata *pmd)
+static inline void pmd_write_lock_in_core(struct dm_pool_metadata *pmd)
 	__acquires(pmd->root_lock)
 {
 	down_write(&pmd->root_lock);
 }
-#define pmd_write_lock_in_core(pmd) __pmd_write_lock((pmd))
 
 static inline void pmd_write_lock(struct dm_pool_metadata *pmd)
 {
-	__pmd_write_lock(pmd);
+	pmd_write_lock_in_core(pmd);
 	if (unlikely(!pmd->in_service))
 		pmd->in_service = true;
 }
@@ -831,6 +830,7 @@ static int __commit_transaction(struct dm_pool_metadata *pmd)
 	 * We need to know if the thin_disk_superblock exceeds a 512-byte sector.
 	 */
 	BUILD_BUG_ON(sizeof(struct thin_disk_superblock) > 512);
+	BUG_ON(!rwsem_is_locked(&pmd->root_lock));
 
 	if (unlikely(!pmd->in_service))
 		return 0;
@@ -953,12 +953,14 @@ int dm_pool_metadata_close(struct dm_pool_metadata *pmd)
 		return -EBUSY;
 	}
 
+	pmd_write_lock_in_core(pmd);
 	if (!dm_bm_is_read_only(pmd->bm) && !pmd->fail_io) {
 		r = __commit_transaction(pmd);
 		if (r < 0)
 			DMWARN("%s: __commit_transaction() failed, error = %d",
 			       __func__, r);
 	}
+	pmd_write_unlock(pmd);
 	if (!pmd->fail_io)
 		__destroy_persistent_data_objects(pmd);
 
@@ -1841,7 +1843,7 @@ int dm_pool_commit_metadata(struct dm_pool_metadata *pmd)
 	 * Care is taken to not have commit be what
 	 * triggers putting the thin-pool in-service.
 	 */
-	__pmd_write_lock(pmd);
+	pmd_write_lock_in_core(pmd);
 	if (pmd->fail_io)
 		goto out;
 
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 69201bdf7f4c..1b2c98b43519 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -231,6 +231,7 @@ struct pool {
 	struct dm_target *ti;	/* Only set if a pool target is bound */
 
 	struct mapped_device *pool_md;
+	struct block_device *data_dev;
 	struct block_device *md_dev;
 	struct dm_pool_metadata *pmd;
 
@@ -2945,6 +2946,7 @@ static struct kmem_cache *_new_mapping_cache;
 
 static struct pool *pool_create(struct mapped_device *pool_md,
 				struct block_device *metadata_dev,
+				struct block_device *data_dev,
 				unsigned long block_size,
 				int read_only, char **error)
 {
@@ -3052,6 +3054,7 @@ static struct pool *pool_create(struct mapped_device *pool_md,
 	pool->last_commit_jiffies = jiffies;
 	pool->pool_md = pool_md;
 	pool->md_dev = metadata_dev;
+	pool->data_dev = data_dev;
 	__pool_table_insert(pool);
 
 	return pool;
@@ -3093,6 +3096,7 @@ static void __pool_dec(struct pool *pool)
 
 static struct pool *__pool_find(struct mapped_device *pool_md,
 				struct block_device *metadata_dev,
+				struct block_device *data_dev,
 				unsigned long block_size, int read_only,
 				char **error, int *created)
 {
@@ -3103,19 +3107,23 @@ static struct pool *__pool_find(struct mapped_device *pool_md,
 			*error = "metadata device already in use by a pool";
 			return ERR_PTR(-EBUSY);
 		}
+		if (pool->data_dev != data_dev) {
+			*error = "data device already in use by a pool";
+			return ERR_PTR(-EBUSY);
+		}
 		__pool_inc(pool);
 
 	} else {
 		pool = __pool_table_lookup(pool_md);
 		if (pool) {
-			if (pool->md_dev != metadata_dev) {
+			if (pool->md_dev != metadata_dev || pool->data_dev != data_dev) {
 				*error = "different pool cannot replace a pool";
 				return ERR_PTR(-EINVAL);
 			}
 			__pool_inc(pool);
 
 		} else {
-			pool = pool_create(pool_md, metadata_dev, block_size, read_only, error);
+			pool = pool_create(pool_md, metadata_dev, data_dev, block_size, read_only, error);
 			*created = 1;
 		}
 	}
@@ -3368,7 +3376,7 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
 		goto out;
 	}
 
-	pool = __pool_find(dm_table_get_md(ti->table), metadata_dev->bdev,
+	pool = __pool_find(dm_table_get_md(ti->table), metadata_dev->bdev, data_dev->bdev,
 			   block_size, pf.mode == PM_READ_ONLY, &ti->error, &pool_created);
 	if (IS_ERR(pool)) {
 		r = PTR_ERR(pool);
@@ -4114,7 +4122,7 @@ static struct target_type pool_target = {
 	.name = "thin-pool",
 	.features = DM_TARGET_SINGLETON | DM_TARGET_ALWAYS_WRITEABLE |
 		    DM_TARGET_IMMUTABLE,
-	.version = {1, 21, 0},
+	.version = {1, 22, 0},
 	.module = THIS_MODULE,
 	.ctr = pool_ctr,
 	.dtr = pool_dtr,
@@ -4493,7 +4501,7 @@ static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 static struct target_type thin_target = {
 	.name = "thin",
-	.version = {1, 21, 0},
+	.version = {1, 22, 0},
 	.module	= THIS_MODULE,
 	.ctr = thin_ctr,
 	.dtr = thin_dtr,
diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c
index 3ceeb6b404ed..fb41b4f23c48 100644
--- a/drivers/md/dm-verity-fec.c
+++ b/drivers/md/dm-verity-fec.c
@@ -435,7 +435,7 @@ int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io,
 	fio->level++;
 
 	if (type == DM_VERITY_BLOCK_TYPE_METADATA)
-		block += v->data_blocks;
+		block = block - v->hash_start + v->data_blocks;
 
 	/*
 	 * For RS(M, N), the continuous FEC data is divided into blocks of N
@@ -551,6 +551,7 @@ void verity_fec_dtr(struct dm_verity *v)
 	mempool_exit(&f->rs_pool);
 	mempool_exit(&f->prealloc_pool);
 	mempool_exit(&f->extra_pool);
+	mempool_exit(&f->output_pool);
 	kmem_cache_destroy(f->cache);
 
 	if (f->data_bufio)
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 598e5fafbeed..2727a525b5bb 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -280,6 +280,8 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 			while (daa-- && i < p) {
 				pages[i++] = pfn_t_to_page(pfn);
 				pfn.val++;
+				if (!(i & 15))
+					cond_resched();
 			}
 		} while (i < p);
 		wc->memory_map = vmap(pages, p, VM_MAP, PAGE_KERNEL);
@@ -443,7 +445,13 @@ static void writecache_notify_io(unsigned long error, void *context)
 		complete(&endio->c);
 }
 
-static void ssd_commit_flushed(struct dm_writecache *wc)
+static void writecache_wait_for_ios(struct dm_writecache *wc, int direction)
+{
+	wait_event(wc->bio_in_progress_wait[direction],
+		   !atomic_read(&wc->bio_in_progress[direction]));
+}
+
+static void ssd_commit_flushed(struct dm_writecache *wc, bool wait_for_ios)
 {
 	struct dm_io_region region;
 	struct dm_io_request req;
@@ -489,17 +497,20 @@ static void ssd_commit_flushed(struct dm_writecache *wc)
 	writecache_notify_io(0, &endio);
 	wait_for_completion_io(&endio.c);
 
+	if (wait_for_ios)
+		writecache_wait_for_ios(wc, WRITE);
+
 	writecache_disk_flush(wc, wc->ssd_dev);
 
 	memset(wc->dirty_bitmap, 0, wc->dirty_bitmap_size);
 }
 
-static void writecache_commit_flushed(struct dm_writecache *wc)
+static void writecache_commit_flushed(struct dm_writecache *wc, bool wait_for_ios)
 {
 	if (WC_MODE_PMEM(wc))
 		wmb();
 	else
-		ssd_commit_flushed(wc);
+		ssd_commit_flushed(wc, wait_for_ios);
 }
 
 static void writecache_disk_flush(struct dm_writecache *wc, struct dm_dev *dev)
@@ -523,12 +534,6 @@ static void writecache_disk_flush(struct dm_writecache *wc, struct dm_dev *dev)
 		writecache_error(wc, r, "error flushing metadata: %d", r);
 }
 
-static void writecache_wait_for_ios(struct dm_writecache *wc, int direction)
-{
-	wait_event(wc->bio_in_progress_wait[direction],
-		   !atomic_read(&wc->bio_in_progress[direction]));
-}
-
 #define WFE_RETURN_FOLLOWING	1
 #define WFE_LOWEST_SEQ		2
 
@@ -623,6 +628,12 @@ static void writecache_add_to_freelist(struct dm_writecache *wc, struct wc_entry
 	wc->freelist_size++;
 }
 
+static inline void writecache_verify_watermark(struct dm_writecache *wc)
+{
+	if (unlikely(wc->freelist_size + wc->writeback_size <= wc->freelist_high_watermark))
+		queue_work(wc->writeback_wq, &wc->writeback_work);
+}
+
 static struct wc_entry *writecache_pop_from_freelist(struct dm_writecache *wc)
 {
 	struct wc_entry *e;
@@ -644,8 +655,8 @@ static struct wc_entry *writecache_pop_from_freelist(struct dm_writecache *wc)
 		list_del(&e->lru);
 	}
 	wc->freelist_size--;
-	if (unlikely(wc->freelist_size + wc->writeback_size <= wc->freelist_high_watermark))
-		queue_work(wc->writeback_wq, &wc->writeback_work);
+
+	writecache_verify_watermark(wc);
 
 	return e;
 }
@@ -725,14 +736,12 @@ static void writecache_flush(struct dm_writecache *wc)
 		e = e2;
 		cond_resched();
 	}
-	writecache_commit_flushed(wc);
-
-	writecache_wait_for_ios(wc, WRITE);
+	writecache_commit_flushed(wc, true);
 
 	wc->seq_count++;
 	pmem_assign(sb(wc)->seq_count, cpu_to_le64(wc->seq_count));
 	writecache_flush_region(wc, &sb(wc)->seq_count, sizeof sb(wc)->seq_count);
-	writecache_commit_flushed(wc);
+	writecache_commit_flushed(wc, false);
 
 	wc->overwrote_committed = false;
 
@@ -756,7 +765,7 @@ static void writecache_flush(struct dm_writecache *wc)
 	}
 
 	if (need_flush_after_free)
-		writecache_commit_flushed(wc);
+		writecache_commit_flushed(wc, false);
 }
 
 static void writecache_flush_work(struct work_struct *work)
@@ -799,6 +808,8 @@ static void writecache_discard(struct dm_writecache *wc, sector_t start, sector_
 				writecache_wait_for_ios(wc, WRITE);
 				discarded_something = true;
 			}
+			if (!writecache_entry_is_committed(wc, e))
+				wc->uncommitted_blocks--;
 			writecache_free_entry(wc, e);
 		}
 
@@ -809,7 +820,7 @@ static void writecache_discard(struct dm_writecache *wc, sector_t start, sector_
 	}
 
 	if (discarded_something)
-		writecache_commit_flushed(wc);
+		writecache_commit_flushed(wc, false);
 }
 
 static bool writecache_wait_for_writeback(struct dm_writecache *wc)
@@ -838,7 +849,7 @@ static void writecache_suspend(struct dm_target *ti)
 	}
 	wc_unlock(wc);
 
-	flush_workqueue(wc->writeback_wq);
+	drain_workqueue(wc->writeback_wq);
 
 	wc_lock(wc);
 	if (flush_on_suspend)
@@ -866,11 +877,30 @@ static int writecache_alloc_entries(struct dm_writecache *wc)
 		struct wc_entry *e = &wc->entries[b];
 		e->index = b;
 		e->write_in_progress = false;
+		cond_resched();
 	}
 
 	return 0;
 }
 
+static int writecache_read_metadata(struct dm_writecache *wc, sector_t n_sectors)
+{
+	struct dm_io_region region;
+	struct dm_io_request req;
+
+	region.bdev = wc->ssd_dev->bdev;
+	region.sector = wc->start_sector;
+	region.count = n_sectors;
+	req.bi_op = REQ_OP_READ;
+	req.bi_op_flags = REQ_SYNC;
+	req.mem.type = DM_IO_VMA;
+	req.mem.ptr.vma = (char *)wc->memory_map;
+	req.client = wc->dm_io;
+	req.notify.fn = NULL;
+
+	return dm_io(&req, 1, &region, NULL);
+}
+
 static void writecache_resume(struct dm_target *ti)
 {
 	struct dm_writecache *wc = ti->private;
@@ -881,8 +911,18 @@ static void writecache_resume(struct dm_target *ti)
 
 	wc_lock(wc);
 
-	if (WC_MODE_PMEM(wc))
+	if (WC_MODE_PMEM(wc)) {
 		persistent_memory_invalidate_cache(wc->memory_map, wc->memory_map_size);
+	} else {
+		r = writecache_read_metadata(wc, wc->metadata_sectors);
+		if (r) {
+			size_t sb_entries_offset;
+			writecache_error(wc, r, "unable to read metadata: %d", r);
+			sb_entries_offset = offsetof(struct wc_memory_superblock, entries);
+			memset((char *)wc->memory_map + sb_entries_offset, -1,
+			       (wc->metadata_sectors << SECTOR_SHIFT) - sb_entries_offset);
+		}
+	}
 
 	wc->tree = RB_ROOT;
 	INIT_LIST_HEAD(&wc->lru);
@@ -920,6 +960,7 @@ static void writecache_resume(struct dm_target *ti)
 			e->original_sector = le64_to_cpu(wme.original_sector);
 			e->seq_count = le64_to_cpu(wme.seq_count);
 		}
+		cond_resched();
 	}
 #endif
 	for (b = 0; b < wc->n_blocks; b++) {
@@ -958,9 +999,11 @@ erase_this:
 
 	if (need_flush) {
 		writecache_flush_all_metadata(wc);
-		writecache_commit_flushed(wc);
+		writecache_commit_flushed(wc, false);
 	}
 
+	writecache_verify_watermark(wc);
+
 	wc_unlock(wc);
 }
 
@@ -1342,7 +1385,7 @@ static void __writecache_endio_pmem(struct dm_writecache *wc, struct list_head *
 			wc->writeback_size--;
 			n_walked++;
 			if (unlikely(n_walked >= ENDIO_LATENCY)) {
-				writecache_commit_flushed(wc);
+				writecache_commit_flushed(wc, false);
 				wc_unlock(wc);
 				wc_lock(wc);
 				n_walked = 0;
@@ -1423,7 +1466,7 @@ pop_from_list:
 			writecache_wait_for_ios(wc, READ);
 		}
 
-		writecache_commit_flushed(wc);
+		writecache_commit_flushed(wc, false);
 
 		wc_unlock(wc);
 	}
@@ -1749,14 +1792,16 @@ static int init_memory(struct dm_writecache *wc)
 	pmem_assign(sb(wc)->n_blocks, cpu_to_le64(wc->n_blocks));
 	pmem_assign(sb(wc)->seq_count, cpu_to_le64(0));
 
-	for (b = 0; b < wc->n_blocks; b++)
+	for (b = 0; b < wc->n_blocks; b++) {
 		write_original_sector_seq_count(wc, &wc->entries[b], -1, -1);
+		cond_resched();
+	}
 
 	writecache_flush_all_metadata(wc);
-	writecache_commit_flushed(wc);
+	writecache_commit_flushed(wc, false);
 	pmem_assign(sb(wc)->magic, cpu_to_le32(MEMORY_SUPERBLOCK_MAGIC));
 	writecache_flush_region(wc, &sb(wc)->magic, sizeof sb(wc)->magic);
-	writecache_commit_flushed(wc);
+	writecache_commit_flushed(wc, false);
 
 	return 0;
 }
@@ -1959,6 +2004,12 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv)
 		ti->error = "Invalid block size";
 		goto bad;
 	}
+	if (wc->block_size < bdev_logical_block_size(wc->dev->bdev) ||
+	    wc->block_size < bdev_logical_block_size(wc->ssd_dev->bdev)) {
+		r = -EINVAL;
+		ti->error = "Block size is smaller than device logical block size";
+		goto bad;
+	}
 	wc->block_size_bits = __ffs(wc->block_size);
 
 	wc->max_writeback_jobs = MAX_WRITEBACK_JOBS;
@@ -2047,8 +2098,6 @@ invalid_optional:
 			goto bad;
 		}
 	} else {
-		struct dm_io_region region;
-		struct dm_io_request req;
 		size_t n_blocks, n_metadata_blocks;
 		uint64_t n_bitmap_bits;
 
@@ -2105,19 +2154,9 @@ invalid_optional:
 			goto bad;
 		}
 
-		region.bdev = wc->ssd_dev->bdev;
-		region.sector = wc->start_sector;
-		region.count = wc->metadata_sectors;
-		req.bi_op = REQ_OP_READ;
-		req.bi_op_flags = REQ_SYNC;
-		req.mem.type = DM_IO_VMA;
-		req.mem.ptr.vma = (char *)wc->memory_map;
-		req.client = wc->dm_io;
-		req.notify.fn = NULL;
-
-		r = dm_io(&req, 1, &region, NULL);
+		r = writecache_read_metadata(wc, wc->block_size >> SECTOR_SHIFT);
 		if (r) {
-			ti->error = "Unable to read metadata";
+			ti->error = "Unable to read first block of metadata";
 			goto bad;
 		}
 	}
diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c
index c2c17149d968..5c2bbdf67f25 100644
--- a/drivers/md/dm-zoned-metadata.c
+++ b/drivers/md/dm-zoned-metadata.c
@@ -132,6 +132,7 @@ struct dmz_metadata {
 
 	sector_t		zone_bitmap_size;
 	unsigned int		zone_nr_bitmap_blocks;
+	unsigned int		zone_bits_per_mblk;
 
 	unsigned int		nr_bitmap_blocks;
 	unsigned int		nr_map_blocks;
@@ -1104,7 +1105,6 @@ static int dmz_init_zone(struct dmz_metadata *zmd, struct dm_zone *zone,
 
 	if (blkz->type == BLK_ZONE_TYPE_CONVENTIONAL) {
 		set_bit(DMZ_RND, &zone->flags);
-		zmd->nr_rnd_zones++;
 	} else if (blkz->type == BLK_ZONE_TYPE_SEQWRITE_REQ ||
 		   blkz->type == BLK_ZONE_TYPE_SEQWRITE_PREF) {
 		set_bit(DMZ_SEQ, &zone->flags);
@@ -1165,7 +1165,10 @@ static int dmz_init_zones(struct dmz_metadata *zmd)
 
 	/* Init */
 	zmd->zone_bitmap_size = dev->zone_nr_blocks >> 3;
-	zmd->zone_nr_bitmap_blocks = zmd->zone_bitmap_size >> DMZ_BLOCK_SHIFT;
+	zmd->zone_nr_bitmap_blocks =
+		max_t(sector_t, 1, zmd->zone_bitmap_size >> DMZ_BLOCK_SHIFT);
+	zmd->zone_bits_per_mblk = min_t(sector_t, dev->zone_nr_blocks,
+					DMZ_BLOCK_SIZE_BITS);
 
 	/* Allocate zone array */
 	zmd->zones = kcalloc(dev->nr_zones, sizeof(struct dm_zone), GFP_KERNEL);
@@ -1577,7 +1580,7 @@ static struct dm_zone *dmz_get_rnd_zone_for_reclaim(struct dmz_metadata *zmd)
 			return dzone;
 	}
 
-	return ERR_PTR(-EBUSY);
+	return NULL;
 }
 
 /*
@@ -1597,7 +1600,7 @@ static struct dm_zone *dmz_get_seq_zone_for_reclaim(struct dmz_metadata *zmd)
 			return zone;
 	}
 
-	return ERR_PTR(-EBUSY);
+	return NULL;
 }
 
 /*
@@ -1982,7 +1985,7 @@ int dmz_copy_valid_blocks(struct dmz_metadata *zmd, struct dm_zone *from_zone,
 		dmz_release_mblock(zmd, to_mblk);
 		dmz_release_mblock(zmd, from_mblk);
 
-		chunk_block += DMZ_BLOCK_SIZE_BITS;
+		chunk_block += zmd->zone_bits_per_mblk;
 	}
 
 	to_zone->weight = from_zone->weight;
@@ -2043,7 +2046,7 @@ int dmz_validate_blocks(struct dmz_metadata *zmd, struct dm_zone *zone,
 
 		/* Set bits */
 		bit = chunk_block & DMZ_BLOCK_MASK_BITS;
-		nr_bits = min(nr_blocks, DMZ_BLOCK_SIZE_BITS - bit);
+		nr_bits = min(nr_blocks, zmd->zone_bits_per_mblk - bit);
 
 		count = dmz_set_bits((unsigned long *)mblk->data, bit, nr_bits);
 		if (count) {
@@ -2122,7 +2125,7 @@ int dmz_invalidate_blocks(struct dmz_metadata *zmd, struct dm_zone *zone,
 
 		/* Clear bits */
 		bit = chunk_block & DMZ_BLOCK_MASK_BITS;
-		nr_bits = min(nr_blocks, DMZ_BLOCK_SIZE_BITS - bit);
+		nr_bits = min(nr_blocks, zmd->zone_bits_per_mblk - bit);
 
 		count = dmz_clear_bits((unsigned long *)mblk->data,
 				       bit, nr_bits);
@@ -2182,6 +2185,7 @@ static int dmz_to_next_set_block(struct dmz_metadata *zmd, struct dm_zone *zone,
 {
 	struct dmz_mblock *mblk;
 	unsigned int bit, set_bit, nr_bits;
+	unsigned int zone_bits = zmd->zone_bits_per_mblk;
 	unsigned long *bitmap;
 	int n = 0;
 
@@ -2196,15 +2200,15 @@ static int dmz_to_next_set_block(struct dmz_metadata *zmd, struct dm_zone *zone,
 		/* Get offset */
 		bitmap = (unsigned long *) mblk->data;
 		bit = chunk_block & DMZ_BLOCK_MASK_BITS;
-		nr_bits = min(nr_blocks, DMZ_BLOCK_SIZE_BITS - bit);
+		nr_bits = min(nr_blocks, zone_bits - bit);
 		if (set)
-			set_bit = find_next_bit(bitmap, DMZ_BLOCK_SIZE_BITS, bit);
+			set_bit = find_next_bit(bitmap, zone_bits, bit);
 		else
-			set_bit = find_next_zero_bit(bitmap, DMZ_BLOCK_SIZE_BITS, bit);
+			set_bit = find_next_zero_bit(bitmap, zone_bits, bit);
 		dmz_release_mblock(zmd, mblk);
 
 		n += set_bit - bit;
-		if (set_bit < DMZ_BLOCK_SIZE_BITS)
+		if (set_bit < zone_bits)
 			break;
 
 		nr_blocks -= nr_bits;
@@ -2307,7 +2311,7 @@ static void dmz_get_zone_weight(struct dmz_metadata *zmd, struct dm_zone *zone)
 		/* Count bits in this block */
 		bitmap = mblk->data;
 		bit = chunk_block & DMZ_BLOCK_MASK_BITS;
-		nr_bits = min(nr_blocks, DMZ_BLOCK_SIZE_BITS - bit);
+		nr_bits = min(nr_blocks, zmd->zone_bits_per_mblk - bit);
 		n += dmz_count_bits(bitmap, bit, nr_bits);
 
 		dmz_release_mblock(zmd, mblk);
diff --git a/drivers/md/dm-zoned-reclaim.c b/drivers/md/dm-zoned-reclaim.c
index 84ac671acd2e..879848aad97a 100644
--- a/drivers/md/dm-zoned-reclaim.c
+++ b/drivers/md/dm-zoned-reclaim.c
@@ -348,8 +348,8 @@ static int dmz_do_reclaim(struct dmz_reclaim *zrc)
 
 	/* Get a data zone */
 	dzone = dmz_get_zone_for_reclaim(zmd);
-	if (IS_ERR(dzone))
-		return PTR_ERR(dzone);
+	if (!dzone)
+		return -EBUSY;
 
 	start = jiffies;
 
diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index 775b890bd736..159d27aa712b 100644
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -789,7 +789,7 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	}
 
 	/* Set target (no write same support) */
-	ti->max_io_len = dev->zone_nr_sectors << 9;
+	ti->max_io_len = dev->zone_nr_sectors;
 	ti->num_flush_bios = 1;
 	ti->num_discard_bios = 1;
 	ti->num_write_zeroes_bios = 1;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 5475081dcbd6..9e7765ea73a9 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/sched/mm.h>
 #include <linux/sched/signal.h>
 #include <linux/blkpg.h>
 #include <linux/bio.h>
@@ -140,6 +141,7 @@ EXPORT_SYMBOL_GPL(dm_bio_get_target_bio_nr);
 #define DMF_NOFLUSH_SUSPENDING 5
 #define DMF_DEFERRED_REMOVE 6
 #define DMF_SUSPENDED_INTERNALLY 7
+#define DMF_POST_SUSPENDING 8
 
 #define DM_NUMA_NODE NUMA_NO_NODE
 static int dm_numa_node = DM_NUMA_NODE;
@@ -1438,9 +1440,6 @@ static int __send_empty_flush(struct clone_info *ci)
 	BUG_ON(bio_has_data(ci->bio));
 	while ((ti = dm_table_get_target(ci->map, target_nr++)))
 		__send_duplicate_bios(ci, ti, ti->num_flush_bios, NULL);
-
-	bio_disassociate_blkg(ci->bio);
-
 	return 0;
 }
 
@@ -1628,6 +1627,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
 		ci.bio = &flush_bio;
 		ci.sector_count = 0;
 		error = __send_empty_flush(&ci);
+		bio_uninit(ci.bio);
 		/* dec_pending submits any data associated with flush */
 	} else if (bio_op(bio) == REQ_OP_ZONE_RESET) {
 		ci.bio = bio;
@@ -1702,6 +1702,7 @@ static blk_qc_t __process_bio(struct mapped_device *md, struct dm_table *map,
 		ci.bio = &flush_bio;
 		ci.sector_count = 0;
 		error = __send_empty_flush(&ci);
+		bio_uninit(ci.bio);
 		/* dec_pending submits any data associated with flush */
 	} else {
 		struct dm_target_io *tio;
@@ -1762,8 +1763,9 @@ static blk_qc_t dm_process_bio(struct mapped_device *md,
 	 * won't be imposed.
 	 */
 	if (current->bio_list) {
-		blk_queue_split(md->queue, &bio);
-		if (!is_abnormal_io(bio))
+		if (is_abnormal_io(bio))
+			blk_queue_split(md->queue, &bio);
+		else
 			dm_queue_split(md, ti, &bio);
 	}
 
@@ -1811,7 +1813,8 @@ static int dm_any_congested(void *congested_data, int bdi_bits)
 			 * With request-based DM we only need to check the
 			 * top-level queue for congestion.
 			 */
-			r = md->queue->backing_dev_info->wb.state & bdi_bits;
+			struct backing_dev_info *bdi = md->queue->backing_dev_info;
+			r = bdi->wb.congested->state & bdi_bits;
 		} else {
 			map = dm_get_live_table_fast(md);
 			if (map)
@@ -1877,14 +1880,6 @@ static const struct dax_operations dm_dax_ops;
 
 static void dm_wq_work(struct work_struct *work);
 
-static void dm_init_normal_md_queue(struct mapped_device *md)
-{
-	/*
-	 * Initialize aspects of queue that aren't relevant for blk-mq
-	 */
-	md->queue->backing_dev_info->congested_fn = dm_any_congested;
-}
-
 static void cleanup_mapped_device(struct mapped_device *md)
 {
 	if (md->wq)
@@ -1972,7 +1967,12 @@ static struct mapped_device *alloc_dev(int minor)
 	if (!md->queue)
 		goto bad;
 	md->queue->queuedata = md;
-	md->queue->backing_dev_info->congested_data = md;
+	/*
+	 * default to bio-based required ->make_request_fn until DM
+	 * table is loaded and md->type established. If request-based
+	 * table is loaded: blk-mq will override accordingly.
+	 */
+	blk_queue_make_request(md->queue, dm_make_request);
 
 	md->disk = alloc_disk_node(1, md->numa_node_id);
 	if (!md->disk)
@@ -2265,6 +2265,12 @@ struct queue_limits *dm_get_queue_limits(struct mapped_device *md)
 }
 EXPORT_SYMBOL_GPL(dm_get_queue_limits);
 
+static void dm_init_congested_fn(struct mapped_device *md)
+{
+	md->queue->backing_dev_info->congested_data = md;
+	md->queue->backing_dev_info->congested_fn = dm_any_congested;
+}
+
 /*
  * Setup the DM device's queue based on md's type
  */
@@ -2281,12 +2287,12 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
 			DMERR("Cannot initialize queue for request-based dm-mq mapped device");
 			return r;
 		}
+		dm_init_congested_fn(md);
 		break;
 	case DM_TYPE_BIO_BASED:
 	case DM_TYPE_DAX_BIO_BASED:
 	case DM_TYPE_NVME_BIO_BASED:
-		dm_init_normal_md_queue(md);
-		blk_queue_make_request(md->queue, dm_make_request);
+		dm_init_congested_fn(md);
 		break;
 	case DM_TYPE_NONE:
 		WARN_ON_ONCE(true);
@@ -2385,6 +2391,8 @@ static void __dm_destroy(struct mapped_device *md, bool wait)
 	map = dm_get_live_table(md, &srcu_idx);
 	if (!dm_suspended_md(md)) {
 		dm_table_presuspend_targets(map);
+		set_bit(DMF_SUSPENDED, &md->flags);
+		set_bit(DMF_POST_SUSPENDING, &md->flags);
 		dm_table_postsuspend_targets(map);
 	}
 	/* dm_put_live_table must be before msleep, otherwise deadlock is possible */
@@ -2707,7 +2715,9 @@ retry:
 	if (r)
 		goto out_unlock;
 
+	set_bit(DMF_POST_SUSPENDING, &md->flags);
 	dm_table_postsuspend_targets(map);
+	clear_bit(DMF_POST_SUSPENDING, &md->flags);
 
 out_unlock:
 	mutex_unlock(&md->suspend_lock);
@@ -2804,7 +2814,9 @@ static void __dm_internal_suspend(struct mapped_device *md, unsigned suspend_fla
 	(void) __dm_suspend(md, map, suspend_flags, TASK_UNINTERRUPTIBLE,
 			    DMF_SUSPENDED_INTERNALLY);
 
+	set_bit(DMF_POST_SUSPENDING, &md->flags);
 	dm_table_postsuspend_targets(map);
+	clear_bit(DMF_POST_SUSPENDING, &md->flags);
 }
 
 static void __dm_internal_resume(struct mapped_device *md)
@@ -2881,17 +2893,25 @@ EXPORT_SYMBOL_GPL(dm_internal_resume_fast);
 int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action,
 		       unsigned cookie)
 {
+	int r;
+	unsigned noio_flag;
 	char udev_cookie[DM_COOKIE_LENGTH];
 	char *envp[] = { udev_cookie, NULL };
 
+	noio_flag = memalloc_noio_save();
+
 	if (!cookie)
-		return kobject_uevent(&disk_to_dev(md->disk)->kobj, action);
+		r = kobject_uevent(&disk_to_dev(md->disk)->kobj, action);
 	else {
 		snprintf(udev_cookie, DM_COOKIE_LENGTH, "%s=%u",
 			 DM_COOKIE_ENV_VAR_NAME, cookie);
-		return kobject_uevent_env(&disk_to_dev(md->disk)->kobj,
-					  action, envp);
+		r = kobject_uevent_env(&disk_to_dev(md->disk)->kobj,
+				       action, envp);
 	}
+
+	memalloc_noio_restore(noio_flag);
+
+	return r;
 }
 
 uint32_t dm_next_uevent_seq(struct mapped_device *md)
@@ -2957,6 +2977,11 @@ int dm_suspended_md(struct mapped_device *md)
 	return test_bit(DMF_SUSPENDED, &md->flags);
 }
 
+static int dm_post_suspending_md(struct mapped_device *md)
+{
+	return test_bit(DMF_POST_SUSPENDING, &md->flags);
+}
+
 int dm_suspended_internally_md(struct mapped_device *md)
 {
 	return test_bit(DMF_SUSPENDED_INTERNALLY, &md->flags);
@@ -2973,6 +2998,12 @@ int dm_suspended(struct dm_target *ti)
 }
 EXPORT_SYMBOL_GPL(dm_suspended);
 
+int dm_post_suspending(struct dm_target *ti)
+{
+	return dm_post_suspending_md(dm_table_get_md(ti->table));
+}
+EXPORT_SYMBOL_GPL(dm_post_suspending);
+
 int dm_noflush_suspending(struct dm_target *ti)
 {
 	return __noflush_suspending(dm_table_get_md(ti->table));
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 813a99ffa86f..d50737ec4039 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -1139,6 +1139,7 @@ static int resize_bitmaps(struct mddev *mddev, sector_t newsize, sector_t oldsiz
 		bitmap = get_bitmap_from_slot(mddev, i);
 		if (IS_ERR(bitmap)) {
 			pr_err("can't get bitmap from slot %d\n", i);
+			bitmap = NULL;
 			goto out;
 		}
 		counts = &bitmap->counts;
@@ -1518,6 +1519,7 @@ static void unlock_all_bitmaps(struct mddev *mddev)
 			}
 		}
 		kfree(cinfo->other_bitmap_lockres);
+		cinfo->other_bitmap_lockres = NULL;
 	}
 }
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index dc44de8f228a..1dbfe8213575 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1180,6 +1180,8 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev)
 			mddev->new_layout = mddev->layout;
 			mddev->new_chunk_sectors = mddev->chunk_sectors;
 		}
+		if (mddev->level == 0)
+			mddev->layout = -1;
 
 		if (sb->state & (1<<MD_SB_CLEAN))
 			mddev->recovery_cp = MaxSector;
@@ -1596,6 +1598,10 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 		rdev->ppl.sector = rdev->sb_start + rdev->ppl.offset;
 	}
 
+	if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_RAID0_LAYOUT) &&
+	    sb->level != 0)
+		return -EINVAL;
+
 	/* not spare disk, or LEVEL_MULTIPATH */
 	if (sb->level == cpu_to_le32(LEVEL_MULTIPATH) ||
 		(rdev->desc_nr >= 0 &&
@@ -1717,6 +1723,10 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
 			mddev->new_chunk_sectors = mddev->chunk_sectors;
 		}
 
+		if (mddev->level == 0 &&
+		    !(le32_to_cpu(sb->feature_map) & MD_FEATURE_RAID0_LAYOUT))
+			mddev->layout = -1;
+
 		if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL)
 			set_bit(MD_HAS_JOURNAL, &mddev->flags);
 
@@ -5891,7 +5901,7 @@ EXPORT_SYMBOL_GPL(md_stop_writes);
 static void mddev_detach(struct mddev *mddev)
 {
 	md_bitmap_wait_behind_writes(mddev);
-	if (mddev->pers && mddev->pers->quiesce) {
+	if (mddev->pers && mddev->pers->quiesce && !mddev->suspended) {
 		mddev->pers->quiesce(mddev, 1);
 		mddev->pers->quiesce(mddev, 0);
 	}
@@ -6801,6 +6811,9 @@ static int set_array_info(struct mddev *mddev, mdu_array_info_t *info)
 	mddev->external	     = 0;
 
 	mddev->layout        = info->layout;
+	if (mddev->level == 0)
+		/* Cannot trust RAID0 layout info here */
+		mddev->layout = -1;
 	mddev->chunk_sectors = info->chunk_size >> 9;
 
 	if (mddev->persistent) {
@@ -7455,7 +7468,8 @@ static int md_open(struct block_device *bdev, fmode_t mode)
 		 */
 		mddev_put(mddev);
 		/* Wait until bdev->bd_disk is definitely gone */
-		flush_workqueue(md_misc_wq);
+		if (work_pending(&mddev->del_work))
+			flush_workqueue(md_misc_wq);
 		/* Then retry the open from the top */
 		return -ERESTARTSYS;
 	}
diff --git a/drivers/md/persistent-data/dm-space-map-common.c b/drivers/md/persistent-data/dm-space-map-common.c
index b8a62188f6be..f4fffe5e4f20 100644
--- a/drivers/md/persistent-data/dm-space-map-common.c
+++ b/drivers/md/persistent-data/dm-space-map-common.c
@@ -384,6 +384,33 @@ int sm_ll_find_free_block(struct ll_disk *ll, dm_block_t begin,
 	return -ENOSPC;
 }
 
+int sm_ll_find_common_free_block(struct ll_disk *old_ll, struct ll_disk *new_ll,
+	                         dm_block_t begin, dm_block_t end, dm_block_t *b)
+{
+	int r;
+	uint32_t count;
+
+	do {
+		r = sm_ll_find_free_block(new_ll, begin, new_ll->nr_blocks, b);
+		if (r)
+			break;
+
+		/* double check this block wasn't used in the old transaction */
+		if (*b >= old_ll->nr_blocks)
+			count = 0;
+		else {
+			r = sm_ll_lookup(old_ll, *b, &count);
+			if (r)
+				break;
+
+			if (count)
+				begin = *b + 1;
+		}
+	} while (count);
+
+	return r;
+}
+
 static int sm_ll_mutate(struct ll_disk *ll, dm_block_t b,
 			int (*mutator)(void *context, uint32_t old, uint32_t *new),
 			void *context, enum allocation_event *ev)
diff --git a/drivers/md/persistent-data/dm-space-map-common.h b/drivers/md/persistent-data/dm-space-map-common.h
index b3078d5eda0c..8de63ce39bdd 100644
--- a/drivers/md/persistent-data/dm-space-map-common.h
+++ b/drivers/md/persistent-data/dm-space-map-common.h
@@ -109,6 +109,8 @@ int sm_ll_lookup_bitmap(struct ll_disk *ll, dm_block_t b, uint32_t *result);
 int sm_ll_lookup(struct ll_disk *ll, dm_block_t b, uint32_t *result);
 int sm_ll_find_free_block(struct ll_disk *ll, dm_block_t begin,
 			  dm_block_t end, dm_block_t *result);
+int sm_ll_find_common_free_block(struct ll_disk *old_ll, struct ll_disk *new_ll,
+	                         dm_block_t begin, dm_block_t end, dm_block_t *result);
 int sm_ll_insert(struct ll_disk *ll, dm_block_t b, uint32_t ref_count, enum allocation_event *ev);
 int sm_ll_inc(struct ll_disk *ll, dm_block_t b, enum allocation_event *ev);
 int sm_ll_dec(struct ll_disk *ll, dm_block_t b, enum allocation_event *ev);
diff --git a/drivers/md/persistent-data/dm-space-map-disk.c b/drivers/md/persistent-data/dm-space-map-disk.c
index 32adf6b4a9c7..bf4c5e2ccb6f 100644
--- a/drivers/md/persistent-data/dm-space-map-disk.c
+++ b/drivers/md/persistent-data/dm-space-map-disk.c
@@ -167,8 +167,10 @@ static int sm_disk_new_block(struct dm_space_map *sm, dm_block_t *b)
 	enum allocation_event ev;
 	struct sm_disk *smd = container_of(sm, struct sm_disk, sm);
 
-	/* FIXME: we should loop round a couple of times */
-	r = sm_ll_find_free_block(&smd->old_ll, smd->begin, smd->old_ll.nr_blocks, b);
+	/*
+	 * Any block we allocate has to be free in both the old and current ll.
+	 */
+	r = sm_ll_find_common_free_block(&smd->old_ll, &smd->ll, smd->begin, smd->ll.nr_blocks, b);
 	if (r)
 		return r;
 
diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c
index 25328582cc48..9e3c64ec2026 100644
--- a/drivers/md/persistent-data/dm-space-map-metadata.c
+++ b/drivers/md/persistent-data/dm-space-map-metadata.c
@@ -448,7 +448,10 @@ static int sm_metadata_new_block_(struct dm_space_map *sm, dm_block_t *b)
 	enum allocation_event ev;
 	struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
 
-	r = sm_ll_find_free_block(&smm->old_ll, smm->begin, smm->old_ll.nr_blocks, b);
+	/*
+	 * Any block we allocate has to be free in both the old and current ll.
+	 */
+	r = sm_ll_find_common_free_block(&smm->old_ll, &smm->ll, smm->begin, smm->ll.nr_blocks, b);
 	if (r)
 		return r;
 
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 8f4046d5789d..02dc6b9c16f9 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -87,7 +87,7 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 	char b[BDEVNAME_SIZE];
 	char b2[BDEVNAME_SIZE];
 	struct r0conf *conf = kzalloc(sizeof(*conf), GFP_KERNEL);
-	unsigned short blksize = 512;
+	unsigned blksize = 512;
 
 	*private_conf = ERR_PTR(-ENOMEM);
 	if (!conf)
@@ -145,6 +145,9 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 
 	if (conf->nr_strip_zones == 1) {
 		conf->layout = RAID0_ORIG_LAYOUT;
+	} else if (mddev->layout == RAID0_ORIG_LAYOUT ||
+		   mddev->layout == RAID0_ALT_MULTIZONE_LAYOUT) {
+		conf->layout = mddev->layout;
 	} else if (default_layout == RAID0_ORIG_LAYOUT ||
 		   default_layout == RAID0_ALT_MULTIZONE_LAYOUT) {
 		conf->layout = default_layout;
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index c0ba5503106e..7ad019202caf 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -2747,7 +2747,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 				write_targets++;
 			}
 		}
-		if (bio->bi_end_io) {
+		if (rdev && bio->bi_end_io) {
 			atomic_inc(&rdev->nr_pending);
 			bio->bi_iter.bi_sector = sector_nr + rdev->data_offset;
 			bio_set_dev(bio, rdev->bdev);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 37b0d8e31ab8..d0af52da65af 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2228,14 +2228,19 @@ static int grow_stripes(struct r5conf *conf, int num)
  * of the P and Q blocks.
  */
 static int scribble_alloc(struct raid5_percpu *percpu,
-			  int num, int cnt, gfp_t flags)
+			  int num, int cnt)
 {
 	size_t obj_size =
 		sizeof(struct page *) * (num+2) +
 		sizeof(addr_conv_t) * (num+2);
 	void *scribble;
 
-	scribble = kvmalloc_array(cnt, obj_size, flags);
+	/*
+	 * If here is in raid array suspend context, it is in memalloc noio
+	 * context as well, there is no potential recursive memory reclaim
+	 * I/Os with the GFP_KERNEL flag.
+	 */
+	scribble = kvmalloc_array(cnt, obj_size, GFP_KERNEL);
 	if (!scribble)
 		return -ENOMEM;
 
@@ -2267,8 +2272,7 @@ static int resize_chunks(struct r5conf *conf, int new_disks, int new_sectors)
 
 		percpu = per_cpu_ptr(conf->percpu, cpu);
 		err = scribble_alloc(percpu, new_disks,
-				     new_sectors / STRIPE_SECTORS,
-				     GFP_NOIO);
+				     new_sectors / STRIPE_SECTORS);
 		if (err)
 			break;
 	}
@@ -3594,6 +3598,7 @@ static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s,
 	 * is missing/faulty, then we need to read everything we can.
 	 */
 	if (sh->raid_conf->level != 6 &&
+	    sh->raid_conf->rmw_level != PARITY_DISABLE_RMW &&
 	    sh->sector < sh->raid_conf->mddev->recovery_cp)
 		/* reconstruct-write isn't being forced */
 		return 0;
@@ -4830,7 +4835,7 @@ static void handle_stripe(struct stripe_head *sh)
 	 * or to load a block that is being partially written.
 	 */
 	if (s.to_read || s.non_overwrite
-	    || (conf->level == 6 && s.to_write && s.failed)
+	    || (s.to_write && s.failed)
 	    || (s.syncing && (s.uptodate + s.compute < disks))
 	    || s.replacing
 	    || s.expanding)
@@ -6761,8 +6766,7 @@ static int alloc_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu
 			       conf->previous_raid_disks),
 			   max(conf->chunk_sectors,
 			       conf->prev_chunk_sectors)
-			   / STRIPE_SECTORS,
-			   GFP_KERNEL)) {
+			   / STRIPE_SECTORS)) {
 		free_scratch_buffer(conf, percpu);
 		return -ENOMEM;
 	}
diff --git a/drivers/media/cec/cec-adap.c b/drivers/media/cec/cec-adap.c
index f1261cc2b6fa..72bc84f1be12 100644
--- a/drivers/media/cec/cec-adap.c
+++ b/drivers/media/cec/cec-adap.c
@@ -365,7 +365,8 @@ static void cec_data_cancel(struct cec_data *data, u8 tx_status)
 	} else {
 		list_del_init(&data->list);
 		if (!(data->msg.tx_status & CEC_TX_STATUS_OK))
-			data->adap->transmit_queue_sz--;
+			if (!WARN_ON(!data->adap->transmit_queue_sz))
+				data->adap->transmit_queue_sz--;
 	}
 
 	if (data->msg.tx_status & CEC_TX_STATUS_OK) {
@@ -417,6 +418,14 @@ static void cec_flush(struct cec_adapter *adap)
 		 * need to do anything special in that case.
 		 */
 	}
+	/*
+	 * If something went wrong and this counter isn't what it should
+	 * be, then this will reset it back to 0. Warn if it is not 0,
+	 * since it indicates a bug, either in this framework or in a
+	 * CEC driver.
+	 */
+	if (WARN_ON(adap->transmit_queue_sz))
+		adap->transmit_queue_sz = 0;
 }
 
 /*
@@ -441,7 +450,7 @@ int cec_thread_func(void *_adap)
 		bool timeout = false;
 		u8 attempts;
 
-		if (adap->transmitting) {
+		if (adap->transmit_in_progress) {
 			int err;
 
 			/*
@@ -476,7 +485,7 @@ int cec_thread_func(void *_adap)
 			goto unlock;
 		}
 
-		if (adap->transmitting && timeout) {
+		if (adap->transmit_in_progress && timeout) {
 			/*
 			 * If we timeout, then log that. Normally this does
 			 * not happen and it is an indication of a faulty CEC
@@ -485,14 +494,18 @@ int cec_thread_func(void *_adap)
 			 * so much traffic on the bus that the adapter was
 			 * unable to transmit for CEC_XFER_TIMEOUT_MS (2.1s).
 			 */
-			pr_warn("cec-%s: message %*ph timed out\n", adap->name,
-				adap->transmitting->msg.len,
-				adap->transmitting->msg.msg);
+			if (adap->transmitting) {
+				pr_warn("cec-%s: message %*ph timed out\n", adap->name,
+					adap->transmitting->msg.len,
+					adap->transmitting->msg.msg);
+				/* Just give up on this. */
+				cec_data_cancel(adap->transmitting,
+						CEC_TX_STATUS_TIMEOUT);
+			} else {
+				pr_warn("cec-%s: transmit timed out\n", adap->name);
+			}
 			adap->transmit_in_progress = false;
 			adap->tx_timeouts++;
-			/* Just give up on this. */
-			cec_data_cancel(adap->transmitting,
-					CEC_TX_STATUS_TIMEOUT);
 			goto unlock;
 		}
 
@@ -507,7 +520,8 @@ int cec_thread_func(void *_adap)
 		data = list_first_entry(&adap->transmit_queue,
 					struct cec_data, list);
 		list_del_init(&data->list);
-		adap->transmit_queue_sz--;
+		if (!WARN_ON(!data->adap->transmit_queue_sz))
+			adap->transmit_queue_sz--;
 
 		/* Make this the current transmitting message */
 		adap->transmitting = data;
@@ -1038,11 +1052,11 @@ void cec_received_msg_ts(struct cec_adapter *adap,
 			valid_la = false;
 		else if (!cec_msg_is_broadcast(msg) && !(dir_fl & DIRECTED))
 			valid_la = false;
-		else if (cec_msg_is_broadcast(msg) && !(dir_fl & BCAST1_4))
+		else if (cec_msg_is_broadcast(msg) && !(dir_fl & BCAST))
 			valid_la = false;
 		else if (cec_msg_is_broadcast(msg) &&
-			 adap->log_addrs.cec_version >= CEC_OP_CEC_VERSION_2_0 &&
-			 !(dir_fl & BCAST2_0))
+			 adap->log_addrs.cec_version < CEC_OP_CEC_VERSION_2_0 &&
+			 !(dir_fl & BCAST1_4))
 			valid_la = false;
 	}
 	if (valid_la && min_len) {
@@ -1654,6 +1668,10 @@ int __cec_s_log_addrs(struct cec_adapter *adap,
 		unsigned j;
 
 		log_addrs->log_addr[i] = CEC_LOG_ADDR_INVALID;
+		if (log_addrs->log_addr_type[i] > CEC_LOG_ADDR_TYPE_UNREGISTERED) {
+			dprintk(1, "unknown logical address type\n");
+			return -EINVAL;
+		}
 		if (type_mask & (1 << log_addrs->log_addr_type[i])) {
 			dprintk(1, "duplicate logical address type\n");
 			return -EINVAL;
@@ -1674,10 +1692,6 @@ int __cec_s_log_addrs(struct cec_adapter *adap,
 			dprintk(1, "invalid primary device type\n");
 			return -EINVAL;
 		}
-		if (log_addrs->log_addr_type[i] > CEC_LOG_ADDR_TYPE_UNREGISTERED) {
-			dprintk(1, "unknown logical address type\n");
-			return -EINVAL;
-		}
 		for (j = 0; j < feature_sz; j++) {
 			if ((features[j] & 0x80) == 0) {
 				if (op_is_dev_features)
diff --git a/drivers/media/dvb-core/dvbdev.c b/drivers/media/dvb-core/dvbdev.c
index 7557fbf9d306..075dc4f8e25a 100644
--- a/drivers/media/dvb-core/dvbdev.c
+++ b/drivers/media/dvb-core/dvbdev.c
@@ -708,9 +708,10 @@ int dvb_create_media_graph(struct dvb_adapter *adap,
 	}
 
 	if (ntuner && ndemod) {
-		pad_source = media_get_pad_index(tuner, true,
+		/* NOTE: first found tuner source pad presumed correct */
+		pad_source = media_get_pad_index(tuner, false,
 						 PAD_SIGNAL_ANALOG);
-		if (pad_source)
+		if (pad_source < 0)
 			return -EINVAL;
 		ret = media_create_pad_links(mdev,
 					     MEDIA_ENT_F_TUNER,
diff --git a/drivers/media/dvb-frontends/si2168.c b/drivers/media/dvb-frontends/si2168.c
index 5dae571e2f62..328fdc824848 100644
--- a/drivers/media/dvb-frontends/si2168.c
+++ b/drivers/media/dvb-frontends/si2168.c
@@ -82,8 +82,19 @@ static int si2168_ts_bus_ctrl(struct dvb_frontend *fe, int acquire)
 
 	dev_dbg(&client->dev, "%s acquire: %d\n", __func__, acquire);
 
+	/* set manual value */
+	if (dev->ts_mode & SI2168_TS_CLK_MANUAL) {
+		memcpy(cmd.args, "\x14\x00\x0d\x10\xe8\x03", 6);
+		cmd.wlen = 6;
+		cmd.rlen = 4;
+		ret = si2168_cmd_execute(client, &cmd);
+		if (ret)
+			return ret;
+	}
 	/* set TS_MODE property */
 	memcpy(cmd.args, "\x14\x00\x01\x10\x10\x00", 6);
+	if (dev->ts_mode & SI2168_TS_CLK_MANUAL)
+		cmd.args[4] = SI2168_TS_CLK_MANUAL;
 	if (acquire)
 		cmd.args[4] |= dev->ts_mode;
 	else
diff --git a/drivers/media/dvb-frontends/si2168.h b/drivers/media/dvb-frontends/si2168.h
index 3b04f84272d9..50dccb394efa 100644
--- a/drivers/media/dvb-frontends/si2168.h
+++ b/drivers/media/dvb-frontends/si2168.h
@@ -30,6 +30,7 @@ struct si2168_config {
 #define SI2168_TS_PARALLEL	0x06
 #define SI2168_TS_SERIAL	0x03
 #define SI2168_TS_TRISTATE	0x00
+#define SI2168_TS_CLK_MANUAL	0x20
 	u8 ts_mode;
 
 	/* TS clock inverted */
diff --git a/drivers/media/firewire/firedtv-fw.c b/drivers/media/firewire/firedtv-fw.c
index 97144734eb05..3f1ca40b9b98 100644
--- a/drivers/media/firewire/firedtv-fw.c
+++ b/drivers/media/firewire/firedtv-fw.c
@@ -272,6 +272,8 @@ static int node_probe(struct fw_unit *unit, const struct ieee1394_device_id *id)
 
 	name_len = fw_csr_string(unit->directory, CSR_MODEL,
 				 name, sizeof(name));
+	if (name_len < 0)
+		return name_len;
 	for (i = ARRAY_SIZE(model_names); --i; )
 		if (strlen(model_names[i]) <= name_len &&
 		    strncmp(name, model_names[i], name_len) == 0)
diff --git a/drivers/media/i2c/adv748x/adv748x.h b/drivers/media/i2c/adv748x/adv748x.h
index 5042f9e94aee..fccb388ce179 100644
--- a/drivers/media/i2c/adv748x/adv748x.h
+++ b/drivers/media/i2c/adv748x/adv748x.h
@@ -394,10 +394,10 @@ int adv748x_write_block(struct adv748x_state *state, int client_page,
 
 #define io_read(s, r) adv748x_read(s, ADV748X_PAGE_IO, r)
 #define io_write(s, r, v) adv748x_write(s, ADV748X_PAGE_IO, r, v)
-#define io_clrset(s, r, m, v) io_write(s, r, (io_read(s, r) & ~m) | v)
+#define io_clrset(s, r, m, v) io_write(s, r, (io_read(s, r) & ~(m)) | (v))
 
 #define hdmi_read(s, r) adv748x_read(s, ADV748X_PAGE_HDMI, r)
-#define hdmi_read16(s, r, m) (((hdmi_read(s, r) << 8) | hdmi_read(s, r+1)) & m)
+#define hdmi_read16(s, r, m) (((hdmi_read(s, r) << 8) | hdmi_read(s, (r)+1)) & (m))
 #define hdmi_write(s, r, v) adv748x_write(s, ADV748X_PAGE_HDMI, r, v)
 
 #define repeater_read(s, r) adv748x_read(s, ADV748X_PAGE_REPEATER, r)
@@ -405,11 +405,11 @@ int adv748x_write_block(struct adv748x_state *state, int client_page,
 
 #define sdp_read(s, r) adv748x_read(s, ADV748X_PAGE_SDP, r)
 #define sdp_write(s, r, v) adv748x_write(s, ADV748X_PAGE_SDP, r, v)
-#define sdp_clrset(s, r, m, v) sdp_write(s, r, (sdp_read(s, r) & ~m) | v)
+#define sdp_clrset(s, r, m, v) sdp_write(s, r, (sdp_read(s, r) & ~(m)) | (v))
 
 #define cp_read(s, r) adv748x_read(s, ADV748X_PAGE_CP, r)
 #define cp_write(s, r, v) adv748x_write(s, ADV748X_PAGE_CP, r, v)
-#define cp_clrset(s, r, m, v) cp_write(s, r, (cp_read(s, r) & ~m) | v)
+#define cp_clrset(s, r, m, v) cp_write(s, r, (cp_read(s, r) & ~(m)) | (v))
 
 #define tx_read(t, r) adv748x_read(t->state, t->page, r)
 #define tx_write(t, r, v) adv748x_write(t->state, t->page, r, v)
diff --git a/drivers/media/i2c/mt9v032.c b/drivers/media/i2c/mt9v032.c
index 4b9b98cf6674..5bd3ae82992f 100644
--- a/drivers/media/i2c/mt9v032.c
+++ b/drivers/media/i2c/mt9v032.c
@@ -428,10 +428,12 @@ static int mt9v032_enum_mbus_code(struct v4l2_subdev *subdev,
 				  struct v4l2_subdev_pad_config *cfg,
 				  struct v4l2_subdev_mbus_code_enum *code)
 {
+	struct mt9v032 *mt9v032 = to_mt9v032(subdev);
+
 	if (code->index > 0)
 		return -EINVAL;
 
-	code->code = MEDIA_BUS_FMT_SGRBG10_1X10;
+	code->code = mt9v032->format.code;
 	return 0;
 }
 
@@ -439,7 +441,11 @@ static int mt9v032_enum_frame_size(struct v4l2_subdev *subdev,
 				   struct v4l2_subdev_pad_config *cfg,
 				   struct v4l2_subdev_frame_size_enum *fse)
 {
-	if (fse->index >= 3 || fse->code != MEDIA_BUS_FMT_SGRBG10_1X10)
+	struct mt9v032 *mt9v032 = to_mt9v032(subdev);
+
+	if (fse->index >= 3)
+		return -EINVAL;
+	if (mt9v032->format.code != fse->code)
 		return -EINVAL;
 
 	fse->min_width = MT9V032_WINDOW_WIDTH_DEF / (1 << fse->index);
diff --git a/drivers/media/i2c/ov5640.c b/drivers/media/i2c/ov5640.c
index 75b7cfeaf0eb..7fb8cd22101e 100644
--- a/drivers/media/i2c/ov5640.c
+++ b/drivers/media/i2c/ov5640.c
@@ -874,7 +874,7 @@ static unsigned long ov5640_calc_sys_clk(struct ov5640_dev *sensor,
 			 * We have reached the maximum allowed PLL1 output,
 			 * increase sysdiv.
 			 */
-			if (!rate)
+			if (!_rate)
 				break;
 
 			/*
@@ -3069,8 +3069,8 @@ static int ov5640_probe(struct i2c_client *client,
 free_ctrls:
 	v4l2_ctrl_handler_free(&sensor->ctrls.handler);
 entity_cleanup:
-	mutex_destroy(&sensor->lock);
 	media_entity_cleanup(&sensor->sd.entity);
+	mutex_destroy(&sensor->lock);
 	return ret;
 }
 
@@ -3080,9 +3080,9 @@ static int ov5640_remove(struct i2c_client *client)
 	struct ov5640_dev *sensor = to_ov5640_dev(sd);
 
 	v4l2_async_unregister_subdev(&sensor->sd);
-	mutex_destroy(&sensor->lock);
 	media_entity_cleanup(&sensor->sd.entity);
 	v4l2_ctrl_handler_free(&sensor->ctrls.handler);
+	mutex_destroy(&sensor->lock);
 
 	return 0;
 }
diff --git a/drivers/media/i2c/ov5695.c b/drivers/media/i2c/ov5695.c
index 5d107c53364d..be242bb8fefc 100644
--- a/drivers/media/i2c/ov5695.c
+++ b/drivers/media/i2c/ov5695.c
@@ -974,16 +974,9 @@ unlock_and_return:
 	return ret;
 }
 
-/* Calculate the delay in us by clock rate and clock cycles */
-static inline u32 ov5695_cal_delay(u32 cycles)
-{
-	return DIV_ROUND_UP(cycles, OV5695_XVCLK_FREQ / 1000 / 1000);
-}
-
 static int __ov5695_power_on(struct ov5695 *ov5695)
 {
-	int ret;
-	u32 delay_us;
+	int i, ret;
 	struct device *dev = &ov5695->client->dev;
 
 	ret = clk_prepare_enable(ov5695->xvclk);
@@ -994,21 +987,28 @@ static int __ov5695_power_on(struct ov5695 *ov5695)
 
 	gpiod_set_value_cansleep(ov5695->reset_gpio, 1);
 
-	ret = regulator_bulk_enable(OV5695_NUM_SUPPLIES, ov5695->supplies);
-	if (ret < 0) {
-		dev_err(dev, "Failed to enable regulators\n");
-		goto disable_clk;
+	/*
+	 * The hardware requires the regulators to be powered on in order,
+	 * so enable them one by one.
+	 */
+	for (i = 0; i < OV5695_NUM_SUPPLIES; i++) {
+		ret = regulator_enable(ov5695->supplies[i].consumer);
+		if (ret) {
+			dev_err(dev, "Failed to enable %s: %d\n",
+				ov5695->supplies[i].supply, ret);
+			goto disable_reg_clk;
+		}
 	}
 
 	gpiod_set_value_cansleep(ov5695->reset_gpio, 0);
 
-	/* 8192 cycles prior to first SCCB transaction */
-	delay_us = ov5695_cal_delay(8192);
-	usleep_range(delay_us, delay_us * 2);
+	usleep_range(1000, 1200);
 
 	return 0;
 
-disable_clk:
+disable_reg_clk:
+	for (--i; i >= 0; i--)
+		regulator_disable(ov5695->supplies[i].consumer);
 	clk_disable_unprepare(ov5695->xvclk);
 
 	return ret;
@@ -1016,9 +1016,22 @@ disable_clk:
 
 static void __ov5695_power_off(struct ov5695 *ov5695)
 {
+	struct device *dev = &ov5695->client->dev;
+	int i, ret;
+
 	clk_disable_unprepare(ov5695->xvclk);
 	gpiod_set_value_cansleep(ov5695->reset_gpio, 1);
-	regulator_bulk_disable(OV5695_NUM_SUPPLIES, ov5695->supplies);
+
+	/*
+	 * The hardware requires the regulators to be powered off in order,
+	 * so disable them one by one.
+	 */
+	for (i = OV5695_NUM_SUPPLIES - 1; i >= 0; i--) {
+		ret = regulator_disable(ov5695->supplies[i].consumer);
+		if (ret)
+			dev_err(dev, "Failed to disable %s: %d\n",
+				ov5695->supplies[i].supply, ret);
+	}
 }
 
 static int __maybe_unused ov5695_runtime_resume(struct device *dev)
@@ -1288,7 +1301,7 @@ static int ov5695_probe(struct i2c_client *client,
 	if (clk_get_rate(ov5695->xvclk) != OV5695_XVCLK_FREQ)
 		dev_warn(dev, "xvclk mismatched, modes are based on 24MHz\n");
 
-	ov5695->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW);
+	ov5695->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH);
 	if (IS_ERR(ov5695->reset_gpio)) {
 		dev_err(dev, "Failed to get reset-gpios\n");
 		return -EINVAL;
diff --git a/drivers/media/i2c/ov6650.c b/drivers/media/i2c/ov6650.c
index ba37c8331c65..af482620f94a 100644
--- a/drivers/media/i2c/ov6650.c
+++ b/drivers/media/i2c/ov6650.c
@@ -201,7 +201,6 @@ struct ov6650 {
 	unsigned long		pclk_max;	/* from resolution and format */
 	struct v4l2_fract	tpf;		/* as requested with s_frame_interval */
 	u32 code;
-	enum v4l2_colorspace	colorspace;
 };
 
 
@@ -214,6 +213,17 @@ static u32 ov6650_codes[] = {
 	MEDIA_BUS_FMT_Y8_1X8,
 };
 
+static const struct v4l2_mbus_framefmt ov6650_def_fmt = {
+	.width		= W_CIF,
+	.height		= H_CIF,
+	.code		= MEDIA_BUS_FMT_SBGGR8_1X8,
+	.colorspace	= V4L2_COLORSPACE_SRGB,
+	.field		= V4L2_FIELD_NONE,
+	.ycbcr_enc	= V4L2_YCBCR_ENC_DEFAULT,
+	.quantization	= V4L2_QUANTIZATION_DEFAULT,
+	.xfer_func	= V4L2_XFER_FUNC_DEFAULT,
+};
+
 /* read a register */
 static int ov6650_reg_read(struct i2c_client *client, u8 reg, u8 *val)
 {
@@ -514,12 +524,20 @@ static int ov6650_get_fmt(struct v4l2_subdev *sd,
 	if (format->pad)
 		return -EINVAL;
 
-	mf->width	= priv->rect.width >> priv->half_scale;
-	mf->height	= priv->rect.height >> priv->half_scale;
-	mf->code	= priv->code;
-	mf->colorspace	= priv->colorspace;
-	mf->field	= V4L2_FIELD_NONE;
+	/* initialize response with default media bus frame format */
+	*mf = ov6650_def_fmt;
+
+	/* update media bus format code and frame size */
+	if (format->which == V4L2_SUBDEV_FORMAT_TRY) {
+		mf->width = cfg->try_fmt.width;
+		mf->height = cfg->try_fmt.height;
+		mf->code = cfg->try_fmt.code;
 
+	} else {
+		mf->width = priv->rect.width >> priv->half_scale;
+		mf->height = priv->rect.height >> priv->half_scale;
+		mf->code = priv->code;
+	}
 	return 0;
 }
 
@@ -624,11 +642,6 @@ static int ov6650_s_fmt(struct v4l2_subdev *sd, struct v4l2_mbus_framefmt *mf)
 		priv->pclk_max = 8000000;
 	}
 
-	if (code == MEDIA_BUS_FMT_SBGGR8_1X8)
-		priv->colorspace = V4L2_COLORSPACE_SRGB;
-	else if (code != 0)
-		priv->colorspace = V4L2_COLORSPACE_JPEG;
-
 	if (half_scale) {
 		dev_dbg(&client->dev, "max resolution: QCIF\n");
 		coma_set |= COMA_QCIF;
@@ -662,11 +675,6 @@ static int ov6650_s_fmt(struct v4l2_subdev *sd, struct v4l2_mbus_framefmt *mf)
 	if (!ret)
 		priv->code = code;
 
-	if (!ret) {
-		mf->colorspace	= priv->colorspace;
-		mf->width = priv->rect.width >> half_scale;
-		mf->height = priv->rect.height >> half_scale;
-	}
 	return ret;
 }
 
@@ -685,8 +693,6 @@ static int ov6650_set_fmt(struct v4l2_subdev *sd,
 		v4l_bound_align_image(&mf->width, 2, W_CIF, 1,
 				&mf->height, 2, H_CIF, 1, 0);
 
-	mf->field = V4L2_FIELD_NONE;
-
 	switch (mf->code) {
 	case MEDIA_BUS_FMT_Y10_1X10:
 		mf->code = MEDIA_BUS_FMT_Y8_1X8;
@@ -696,20 +702,39 @@ static int ov6650_set_fmt(struct v4l2_subdev *sd,
 	case MEDIA_BUS_FMT_YUYV8_2X8:
 	case MEDIA_BUS_FMT_VYUY8_2X8:
 	case MEDIA_BUS_FMT_UYVY8_2X8:
-		mf->colorspace = V4L2_COLORSPACE_JPEG;
 		break;
 	default:
 		mf->code = MEDIA_BUS_FMT_SBGGR8_1X8;
 		/* fall through */
 	case MEDIA_BUS_FMT_SBGGR8_1X8:
-		mf->colorspace = V4L2_COLORSPACE_SRGB;
 		break;
 	}
 
-	if (format->which == V4L2_SUBDEV_FORMAT_ACTIVE)
-		return ov6650_s_fmt(sd, mf);
-	cfg->try_fmt = *mf;
+	if (format->which == V4L2_SUBDEV_FORMAT_TRY) {
+		/* store media bus format code and frame size in pad config */
+		cfg->try_fmt.width = mf->width;
+		cfg->try_fmt.height = mf->height;
+		cfg->try_fmt.code = mf->code;
 
+		/* return default mbus frame format updated with pad config */
+		*mf = ov6650_def_fmt;
+		mf->width = cfg->try_fmt.width;
+		mf->height = cfg->try_fmt.height;
+		mf->code = cfg->try_fmt.code;
+
+	} else {
+		/* apply new media bus format code and frame size */
+		int ret = ov6650_s_fmt(sd, mf);
+
+		if (ret)
+			return ret;
+
+		/* return default format updated with active size and code */
+		*mf = ov6650_def_fmt;
+		mf->width = priv->rect.width >> priv->half_scale;
+		mf->height = priv->rect.height >> priv->half_scale;
+		mf->code = priv->code;
+	}
 	return 0;
 }
 
@@ -852,6 +877,11 @@ static int ov6650_video_probe(struct v4l2_subdev *sd)
 	ret = ov6650_reset(client);
 	if (!ret)
 		ret = ov6650_prog_dflt(client);
+	if (!ret) {
+		struct v4l2_mbus_framefmt mf = ov6650_def_fmt;
+
+		ret = ov6650_s_fmt(sd, &mf);
+	}
 	if (!ret)
 		ret = v4l2_ctrl_handler_setup(&priv->hdl);
 
@@ -1006,16 +1036,12 @@ static int ov6650_probe(struct i2c_client *client,
 	priv->rect.top	  = DEF_VSTRT << 1;
 	priv->rect.width  = W_CIF;
 	priv->rect.height = H_CIF;
-	priv->half_scale  = false;
-	priv->code	  = MEDIA_BUS_FMT_YUYV8_2X8;
-	priv->colorspace  = V4L2_COLORSPACE_JPEG;
 
 	/* Hardware default frame interval */
 	priv->tpf.numerator   = GET_CLKRC_DIV(DEF_CLKRC);
 	priv->tpf.denominator = FRAME_RATE_MAX;
 
 	priv->subdev.internal_ops = &ov6650_internal_ops;
-	priv->subdev.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 
 	ret = v4l2_async_register_subdev(&priv->subdev);
 	if (!ret)
diff --git a/drivers/media/i2c/video-i2c.c b/drivers/media/i2c/video-i2c.c
index abd3152df7d0..4844f4ebb9d6 100644
--- a/drivers/media/i2c/video-i2c.c
+++ b/drivers/media/i2c/video-i2c.c
@@ -259,7 +259,7 @@ static int amg88xx_set_power(struct video_i2c_data *data, bool on)
 	return amg88xx_set_power_off(data);
 }
 
-#if IS_ENABLED(CONFIG_HWMON)
+#if IS_REACHABLE(CONFIG_HWMON)
 
 static const u32 amg88xx_temp_config[] = {
 	HWMON_T_INPUT,
diff --git a/drivers/media/media-request.c b/drivers/media/media-request.c
index e3fca436c75b..c0782fd96c59 100644
--- a/drivers/media/media-request.c
+++ b/drivers/media/media-request.c
@@ -296,9 +296,18 @@ int media_request_alloc(struct media_device *mdev, int *alloc_fd)
 	if (WARN_ON(!mdev->ops->req_alloc ^ !mdev->ops->req_free))
 		return -ENOMEM;
 
+	if (mdev->ops->req_alloc)
+		req = mdev->ops->req_alloc(mdev);
+	else
+		req = kzalloc(sizeof(*req), GFP_KERNEL);
+	if (!req)
+		return -ENOMEM;
+
 	fd = get_unused_fd_flags(O_CLOEXEC);
-	if (fd < 0)
-		return fd;
+	if (fd < 0) {
+		ret = fd;
+		goto err_free_req;
+	}
 
 	filp = anon_inode_getfile("request", &request_fops, NULL, O_CLOEXEC);
 	if (IS_ERR(filp)) {
@@ -306,15 +315,6 @@ int media_request_alloc(struct media_device *mdev, int *alloc_fd)
 		goto err_put_fd;
 	}
 
-	if (mdev->ops->req_alloc)
-		req = mdev->ops->req_alloc(mdev);
-	else
-		req = kzalloc(sizeof(*req), GFP_KERNEL);
-	if (!req) {
-		ret = -ENOMEM;
-		goto err_fput;
-	}
-
 	filp->private_data = req;
 	req->mdev = mdev;
 	req->state = MEDIA_REQUEST_STATE_IDLE;
@@ -336,12 +336,15 @@ int media_request_alloc(struct media_device *mdev, int *alloc_fd)
 
 	return 0;
 
-err_fput:
-	fput(filp);
-
 err_put_fd:
 	put_unused_fd(fd);
 
+err_free_req:
+	if (mdev->ops->req_free)
+		mdev->ops->req_free(req);
+	else
+		kfree(req);
+
 	return ret;
 }
 
diff --git a/drivers/media/pci/cx23885/cx23885-cards.c b/drivers/media/pci/cx23885/cx23885-cards.c
index 8644205d3cd3..8e5a2c580821 100644
--- a/drivers/media/pci/cx23885/cx23885-cards.c
+++ b/drivers/media/pci/cx23885/cx23885-cards.c
@@ -801,6 +801,25 @@ struct cx23885_board cx23885_boards[] = {
 		.name		= "Hauppauge WinTV-Starburst2",
 		.portb		= CX23885_MPEG_DVB,
 	},
+	[CX23885_BOARD_AVERMEDIA_CE310B] = {
+		.name		= "AVerMedia CE310B",
+		.porta		= CX23885_ANALOG_VIDEO,
+		.force_bff	= 1,
+		.input          = {{
+			.type   = CX23885_VMUX_COMPOSITE1,
+			.vmux   = CX25840_VIN1_CH1 |
+				  CX25840_NONE_CH2 |
+				  CX25840_NONE0_CH3,
+			.amux   = CX25840_AUDIO7,
+		}, {
+			.type   = CX23885_VMUX_SVIDEO,
+			.vmux   = CX25840_VIN8_CH1 |
+				  CX25840_NONE_CH2 |
+				  CX25840_VIN7_CH3 |
+				  CX25840_SVIDEO_ON,
+			.amux   = CX25840_AUDIO7,
+		} },
+	},
 };
 const unsigned int cx23885_bcount = ARRAY_SIZE(cx23885_boards);
 
@@ -1124,6 +1143,10 @@ struct cx23885_subid cx23885_subids[] = {
 		.subvendor = 0x0070,
 		.subdevice = 0xf02a,
 		.card      = CX23885_BOARD_HAUPPAUGE_STARBURST2,
+	}, {
+		.subvendor = 0x1461,
+		.subdevice = 0x3100,
+		.card      = CX23885_BOARD_AVERMEDIA_CE310B,
 	},
 };
 const unsigned int cx23885_idcount = ARRAY_SIZE(cx23885_subids);
@@ -2348,6 +2371,7 @@ void cx23885_card_setup(struct cx23885_dev *dev)
 	case CX23885_BOARD_DVBSKY_T982:
 	case CX23885_BOARD_VIEWCAST_260E:
 	case CX23885_BOARD_VIEWCAST_460E:
+	case CX23885_BOARD_AVERMEDIA_CE310B:
 		dev->sd_cx25840 = v4l2_i2c_new_subdev(&dev->v4l2_dev,
 				&dev->i2c_bus[2].i2c_adap,
 				"cx25840", 0x88 >> 1, NULL);
diff --git a/drivers/media/pci/cx23885/cx23885-video.c b/drivers/media/pci/cx23885/cx23885-video.c
index 0c59ecccc38a..ba3431d4b3ce 100644
--- a/drivers/media/pci/cx23885/cx23885-video.c
+++ b/drivers/media/pci/cx23885/cx23885-video.c
@@ -258,7 +258,8 @@ static int cx23885_video_mux(struct cx23885_dev *dev, unsigned int input)
 		(dev->board == CX23885_BOARD_MYGICA_X8507) ||
 		(dev->board == CX23885_BOARD_AVERMEDIA_HC81R) ||
 		(dev->board == CX23885_BOARD_VIEWCAST_260E) ||
-		(dev->board == CX23885_BOARD_VIEWCAST_460E)) {
+		(dev->board == CX23885_BOARD_VIEWCAST_460E) ||
+		(dev->board == CX23885_BOARD_AVERMEDIA_CE310B)) {
 		/* Configure audio routing */
 		v4l2_subdev_call(dev->sd_cx25840, audio, s_routing,
 			INPUT(input)->amux, 0, 0);
diff --git a/drivers/media/pci/cx23885/cx23885.h b/drivers/media/pci/cx23885/cx23885.h
index 9da66fdd5a0d..930ea4b12d3c 100644
--- a/drivers/media/pci/cx23885/cx23885.h
+++ b/drivers/media/pci/cx23885/cx23885.h
@@ -101,6 +101,7 @@
 #define CX23885_BOARD_HAUPPAUGE_STARBURST2     59
 #define CX23885_BOARD_HAUPPAUGE_QUADHD_DVB_885 60
 #define CX23885_BOARD_HAUPPAUGE_QUADHD_ATSC_885 61
+#define CX23885_BOARD_AVERMEDIA_CE310B         62
 
 #define GPIO_0 0x00000001
 #define GPIO_1 0x00000002
diff --git a/drivers/media/platform/aspeed-video.c b/drivers/media/platform/aspeed-video.c
index 3c6c15d5d6be..3573270c8bbd 100644
--- a/drivers/media/platform/aspeed-video.c
+++ b/drivers/media/platform/aspeed-video.c
@@ -1648,7 +1648,8 @@ static int aspeed_video_probe(struct platform_device *pdev)
 {
 	int rc;
 	struct resource *res;
-	struct aspeed_video *video = kzalloc(sizeof(*video), GFP_KERNEL);
+	struct aspeed_video *video =
+		devm_kzalloc(&pdev->dev, sizeof(*video), GFP_KERNEL);
 
 	if (!video)
 		return -ENOMEM;
diff --git a/drivers/media/platform/cadence/cdns-csi2rx.c b/drivers/media/platform/cadence/cdns-csi2rx.c
index 31ace114eda1..be9ec59774d6 100644
--- a/drivers/media/platform/cadence/cdns-csi2rx.c
+++ b/drivers/media/platform/cadence/cdns-csi2rx.c
@@ -129,7 +129,7 @@ static int csi2rx_start(struct csi2rx_priv *csi2rx)
 	 */
 	for (i = csi2rx->num_lanes; i < csi2rx->max_lanes; i++) {
 		unsigned int idx = find_first_zero_bit(&lanes_used,
-						       sizeof(lanes_used));
+						       csi2rx->max_lanes);
 		set_bit(idx, &lanes_used);
 		reg |= CSI2RX_STATIC_CFG_DLANE_MAP(i, i + 1);
 	}
diff --git a/drivers/media/platform/cros-ec-cec/cros-ec-cec.c b/drivers/media/platform/cros-ec-cec/cros-ec-cec.c
index 068df9888dbf..e49ca6e726e1 100644
--- a/drivers/media/platform/cros-ec-cec/cros-ec-cec.c
+++ b/drivers/media/platform/cros-ec-cec/cros-ec-cec.c
@@ -276,11 +276,7 @@ static int cros_ec_cec_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	ret = device_init_wakeup(&pdev->dev, 1);
-	if (ret) {
-		dev_err(&pdev->dev, "failed to initialize wakeup\n");
-		return ret;
-	}
+	device_init_wakeup(&pdev->dev, 1);
 
 	cros_ec_cec->adap = cec_allocate_adapter(&cros_ec_cec_ops, cros_ec_cec,
 						 DRV_NAME, CEC_CAP_DEFAULTS, 1);
diff --git a/drivers/media/platform/exynos4-is/fimc-isp-video.c b/drivers/media/platform/exynos4-is/fimc-isp-video.c
index 8900559e1813..900b88f5584e 100644
--- a/drivers/media/platform/exynos4-is/fimc-isp-video.c
+++ b/drivers/media/platform/exynos4-is/fimc-isp-video.c
@@ -313,7 +313,7 @@ static int isp_video_release(struct file *file)
 		ivc->streaming = 0;
 	}
 
-	vb2_fop_release(file);
+	_vb2_fop_release(file, NULL);
 
 	if (v4l2_fh_is_singular_file(file)) {
 		fimc_pipeline_call(&ivc->ve, close);
diff --git a/drivers/media/platform/exynos4-is/media-dev.c b/drivers/media/platform/exynos4-is/media-dev.c
index 594e4807e45b..0ed62d11389a 100644
--- a/drivers/media/platform/exynos4-is/media-dev.c
+++ b/drivers/media/platform/exynos4-is/media-dev.c
@@ -1266,6 +1266,9 @@ static int fimc_md_get_pinctrl(struct fimc_md *fmd)
 
 	pctl->state_idle = pinctrl_lookup_state(pctl->pinctrl,
 					PINCTRL_STATE_IDLE);
+	if (IS_ERR(pctl->state_idle))
+		return PTR_ERR(pctl->state_idle);
+
 	return 0;
 }
 
diff --git a/drivers/media/platform/meson/ao-cec-g12a.c b/drivers/media/platform/meson/ao-cec-g12a.c
index ddfd060625da..fb52e5dd044a 100644
--- a/drivers/media/platform/meson/ao-cec-g12a.c
+++ b/drivers/media/platform/meson/ao-cec-g12a.c
@@ -365,28 +365,22 @@ static int meson_ao_cec_g12a_read(void *context, unsigned int addr,
 {
 	struct meson_ao_cec_g12a_device *ao_cec = context;
 	u32 reg = FIELD_PREP(CECB_RW_ADDR, addr);
-	unsigned long flags;
 	int ret = 0;
 
-	spin_lock_irqsave(&ao_cec->cec_reg_lock, flags);
-
 	ret = regmap_write(ao_cec->regmap, CECB_RW_REG, reg);
 	if (ret)
-		goto read_out;
+		return ret;
 
 	ret = regmap_read_poll_timeout(ao_cec->regmap, CECB_RW_REG, reg,
 				       !(reg & CECB_RW_BUS_BUSY),
 				       5, 1000);
 	if (ret)
-		goto read_out;
+		return ret;
 
 	ret = regmap_read(ao_cec->regmap, CECB_RW_REG, &reg);
 
 	*data = FIELD_GET(CECB_RW_RD_DATA, reg);
 
-read_out:
-	spin_unlock_irqrestore(&ao_cec->cec_reg_lock, flags);
-
 	return ret;
 }
 
@@ -394,19 +388,11 @@ static int meson_ao_cec_g12a_write(void *context, unsigned int addr,
 				   unsigned int data)
 {
 	struct meson_ao_cec_g12a_device *ao_cec = context;
-	unsigned long flags;
 	u32 reg = FIELD_PREP(CECB_RW_ADDR, addr) |
 		  FIELD_PREP(CECB_RW_WR_DATA, data) |
 		  CECB_RW_WRITE_EN;
-	int ret = 0;
 
-	spin_lock_irqsave(&ao_cec->cec_reg_lock, flags);
-
-	ret = regmap_write(ao_cec->regmap, CECB_RW_REG, reg);
-
-	spin_unlock_irqrestore(&ao_cec->cec_reg_lock, flags);
-
-	return ret;
+	return regmap_write(ao_cec->regmap, CECB_RW_REG, reg);
 }
 
 static const struct regmap_config meson_ao_cec_g12a_cec_regmap_conf = {
diff --git a/drivers/media/platform/omap3isp/isppreview.c b/drivers/media/platform/omap3isp/isppreview.c
index 97d660606d98..b8c2b8bba826 100644
--- a/drivers/media/platform/omap3isp/isppreview.c
+++ b/drivers/media/platform/omap3isp/isppreview.c
@@ -2287,7 +2287,7 @@ static int preview_init_entities(struct isp_prev_device *prev)
 	me->ops = &preview_media_ops;
 	ret = media_entity_pads_init(me, PREV_PADS_NUM, pads);
 	if (ret < 0)
-		return ret;
+		goto error_handler_free;
 
 	preview_init_formats(sd, NULL);
 
@@ -2320,6 +2320,8 @@ error_video_out:
 	omap3isp_video_cleanup(&prev->video_in);
 error_video_in:
 	media_entity_cleanup(&prev->subdev.entity);
+error_handler_free:
+	v4l2_ctrl_handler_free(&prev->ctrls);
 	return ret;
 }
 
diff --git a/drivers/media/platform/qcom/venus/firmware.c b/drivers/media/platform/qcom/venus/firmware.c
index d3d1748a7ef6..33f70e1def94 100644
--- a/drivers/media/platform/qcom/venus/firmware.c
+++ b/drivers/media/platform/qcom/venus/firmware.c
@@ -44,8 +44,14 @@ static void venus_reset_cpu(struct venus_core *core)
 
 int venus_set_hw_state(struct venus_core *core, bool resume)
 {
-	if (core->use_tz)
-		return qcom_scm_set_remote_state(resume, 0);
+	int ret;
+
+	if (core->use_tz) {
+		ret = qcom_scm_set_remote_state(resume, 0);
+		if (resume && ret == -EINVAL)
+			ret = 0;
+		return ret;
+	}
 
 	if (resume)
 		venus_reset_cpu(core);
diff --git a/drivers/media/platform/qcom/venus/hfi_parser.c b/drivers/media/platform/qcom/venus/hfi_parser.c
index 2293d936e49c..7f515a4b9bd1 100644
--- a/drivers/media/platform/qcom/venus/hfi_parser.c
+++ b/drivers/media/platform/qcom/venus/hfi_parser.c
@@ -181,6 +181,7 @@ static void parse_codecs(struct venus_core *core, void *data)
 	if (IS_V1(core)) {
 		core->dec_codecs &= ~HFI_VIDEO_CODEC_HEVC;
 		core->dec_codecs &= ~HFI_VIDEO_CODEC_SPARK;
+		core->enc_codecs &= ~HFI_VIDEO_CODEC_HEVC;
 	}
 }
 
diff --git a/drivers/media/platform/rcar-fcp.c b/drivers/media/platform/rcar-fcp.c
index 43c78620c9d8..5c6b00737fe7 100644
--- a/drivers/media/platform/rcar-fcp.c
+++ b/drivers/media/platform/rcar-fcp.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/device.h>
+#include <linux/dma-mapping.h>
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/mod_devicetable.h>
@@ -21,6 +22,7 @@
 struct rcar_fcp_device {
 	struct list_head list;
 	struct device *dev;
+	struct device_dma_parameters dma_parms;
 };
 
 static LIST_HEAD(fcp_devices);
@@ -136,6 +138,9 @@ static int rcar_fcp_probe(struct platform_device *pdev)
 
 	fcp->dev = &pdev->dev;
 
+	fcp->dev->dma_parms = &fcp->dma_parms;
+	dma_set_max_seg_size(fcp->dev, DMA_BIT_MASK(32));
+
 	pm_runtime_enable(&pdev->dev);
 
 	mutex_lock(&fcp_lock);
diff --git a/drivers/media/platform/rcar-vin/rcar-v4l2.c b/drivers/media/platform/rcar-vin/rcar-v4l2.c
index 7cbdcbf9b090..b4fb72daeb73 100644
--- a/drivers/media/platform/rcar-vin/rcar-v4l2.c
+++ b/drivers/media/platform/rcar-vin/rcar-v4l2.c
@@ -196,6 +196,7 @@ static int rvin_try_format(struct rvin_dev *vin, u32 which,
 	ret = v4l2_subdev_call(sd, pad, set_fmt, pad_cfg, &format);
 	if (ret < 0 && ret != -ENOIOCTLCMD)
 		goto done;
+	ret = 0;
 
 	v4l2_fill_pix_format(pix, &format.format);
 
@@ -230,7 +231,7 @@ static int rvin_try_format(struct rvin_dev *vin, u32 which,
 done:
 	v4l2_subdev_free_pad_config(pad_cfg);
 
-	return 0;
+	return ret;
 }
 
 static int rvin_querycap(struct file *file, void *priv,
diff --git a/drivers/media/platform/rcar_fdp1.c b/drivers/media/platform/rcar_fdp1.c
index 6ca2cb15291f..66768fdf0242 100644
--- a/drivers/media/platform/rcar_fdp1.c
+++ b/drivers/media/platform/rcar_fdp1.c
@@ -2368,7 +2368,7 @@ static int fdp1_probe(struct platform_device *pdev)
 		dprintk(fdp1, "FDP1 Version R-Car H3\n");
 		break;
 	case FD1_IP_M3N:
-		dprintk(fdp1, "FDP1 Version R-Car M3N\n");
+		dprintk(fdp1, "FDP1 Version R-Car M3-N\n");
 		break;
 	case FD1_IP_E3:
 		dprintk(fdp1, "FDP1 Version R-Car E3\n");
diff --git a/drivers/media/platform/rockchip/rga/rga-hw.c b/drivers/media/platform/rockchip/rga/rga-hw.c
index 4be6dcf292ff..aaa96f256356 100644
--- a/drivers/media/platform/rockchip/rga/rga-hw.c
+++ b/drivers/media/platform/rockchip/rga/rga-hw.c
@@ -200,22 +200,25 @@ static void rga_cmd_set_trans_info(struct rga_ctx *ctx)
 	dst_info.data.format = ctx->out.fmt->hw_format;
 	dst_info.data.swap = ctx->out.fmt->color_swap;
 
-	if (ctx->in.fmt->hw_format >= RGA_COLOR_FMT_YUV422SP) {
-		if (ctx->out.fmt->hw_format < RGA_COLOR_FMT_YUV422SP) {
-			switch (ctx->in.colorspace) {
-			case V4L2_COLORSPACE_REC709:
-				src_info.data.csc_mode =
-					RGA_SRC_CSC_MODE_BT709_R0;
-				break;
-			default:
-				src_info.data.csc_mode =
-					RGA_SRC_CSC_MODE_BT601_R0;
-				break;
-			}
+	/*
+	 * CSC mode must only be set when the colorspace families differ between
+	 * input and output. It must remain unset (zeroed) if both are the same.
+	 */
+
+	if (RGA_COLOR_FMT_IS_YUV(ctx->in.fmt->hw_format) &&
+	    RGA_COLOR_FMT_IS_RGB(ctx->out.fmt->hw_format)) {
+		switch (ctx->in.colorspace) {
+		case V4L2_COLORSPACE_REC709:
+			src_info.data.csc_mode = RGA_SRC_CSC_MODE_BT709_R0;
+			break;
+		default:
+			src_info.data.csc_mode = RGA_SRC_CSC_MODE_BT601_R0;
+			break;
 		}
 	}
 
-	if (ctx->out.fmt->hw_format >= RGA_COLOR_FMT_YUV422SP) {
+	if (RGA_COLOR_FMT_IS_RGB(ctx->in.fmt->hw_format) &&
+	    RGA_COLOR_FMT_IS_YUV(ctx->out.fmt->hw_format)) {
 		switch (ctx->out.colorspace) {
 		case V4L2_COLORSPACE_REC709:
 			dst_info.data.csc_mode = RGA_SRC_CSC_MODE_BT709_R0;
diff --git a/drivers/media/platform/rockchip/rga/rga-hw.h b/drivers/media/platform/rockchip/rga/rga-hw.h
index 96cb0314dfa7..e8917e5630a4 100644
--- a/drivers/media/platform/rockchip/rga/rga-hw.h
+++ b/drivers/media/platform/rockchip/rga/rga-hw.h
@@ -95,6 +95,11 @@
 #define RGA_COLOR_FMT_CP_8BPP 15
 #define RGA_COLOR_FMT_MASK 15
 
+#define RGA_COLOR_FMT_IS_YUV(fmt) \
+	(((fmt) >= RGA_COLOR_FMT_YUV422SP) && ((fmt) < RGA_COLOR_FMT_CP_1BPP))
+#define RGA_COLOR_FMT_IS_RGB(fmt) \
+	((fmt) < RGA_COLOR_FMT_YUV422SP)
+
 #define RGA_COLOR_NONE_SWAP 0
 #define RGA_COLOR_RB_SWAP 1
 #define RGA_COLOR_ALPHA_SWAP 2
diff --git a/drivers/media/platform/sti/bdisp/bdisp-hw.c b/drivers/media/platform/sti/bdisp/bdisp-hw.c
index 4372abbb5950..a74e9fd65238 100644
--- a/drivers/media/platform/sti/bdisp/bdisp-hw.c
+++ b/drivers/media/platform/sti/bdisp/bdisp-hw.c
@@ -14,8 +14,8 @@
 #define MAX_SRC_WIDTH           2048
 
 /* Reset & boot poll config */
-#define POLL_RST_MAX            50
-#define POLL_RST_DELAY_MS       20
+#define POLL_RST_MAX            500
+#define POLL_RST_DELAY_MS       2
 
 enum bdisp_target_plan {
 	BDISP_RGB,
@@ -382,7 +382,7 @@ int bdisp_hw_reset(struct bdisp_dev *bdisp)
 	for (i = 0; i < POLL_RST_MAX; i++) {
 		if (readl(bdisp->regs + BLT_STA1) & BLT_STA1_IDLE)
 			break;
-		msleep(POLL_RST_DELAY_MS);
+		udelay(POLL_RST_DELAY_MS * 1000);
 	}
 	if (i == POLL_RST_MAX)
 		dev_err(bdisp->dev, "Reset timeout\n");
diff --git a/drivers/media/platform/ti-vpe/cal.c b/drivers/media/platform/ti-vpe/cal.c
index 9e86d761546b..92311461cc59 100644
--- a/drivers/media/platform/ti-vpe/cal.c
+++ b/drivers/media/platform/ti-vpe/cal.c
@@ -266,8 +266,6 @@ struct cal_ctx {
 	struct v4l2_subdev	*sensor;
 	struct v4l2_fwnode_endpoint	endpoint;
 
-	struct v4l2_async_subdev asd;
-
 	struct v4l2_fh		fh;
 	struct cal_dev		*dev;
 	struct cc_data		*cc;
@@ -537,16 +535,16 @@ static void enable_irqs(struct cal_ctx *ctx)
 
 static void disable_irqs(struct cal_ctx *ctx)
 {
+	u32 val;
+
 	/* Disable IRQ_WDMA_END 0/1 */
-	reg_write_field(ctx->dev,
-			CAL_HL_IRQENABLE_CLR(2),
-			CAL_HL_IRQ_CLEAR,
-			CAL_HL_IRQ_MASK(ctx->csi2_port));
+	val = 0;
+	set_field(&val, CAL_HL_IRQ_CLEAR, CAL_HL_IRQ_MASK(ctx->csi2_port));
+	reg_write(ctx->dev, CAL_HL_IRQENABLE_CLR(2), val);
 	/* Disable IRQ_WDMA_START 0/1 */
-	reg_write_field(ctx->dev,
-			CAL_HL_IRQENABLE_CLR(3),
-			CAL_HL_IRQ_CLEAR,
-			CAL_HL_IRQ_MASK(ctx->csi2_port));
+	val = 0;
+	set_field(&val, CAL_HL_IRQ_CLEAR, CAL_HL_IRQ_MASK(ctx->csi2_port));
+	reg_write(ctx->dev, CAL_HL_IRQENABLE_CLR(3), val);
 	/* Todo: Add VC_IRQ and CSI2_COMPLEXIO_IRQ handling */
 	reg_write(ctx->dev, CAL_CSI2_VC_IRQENABLE(1), 0);
 }
@@ -1648,7 +1646,6 @@ static int of_cal_create_instance(struct cal_ctx *ctx, int inst)
 
 	parent = pdev->dev.of_node;
 
-	asd = &ctx->asd;
 	endpoint = &ctx->endpoint;
 
 	ep_node = NULL;
@@ -1695,8 +1692,6 @@ static int of_cal_create_instance(struct cal_ctx *ctx, int inst)
 		ctx_dbg(3, ctx, "can't get remote parent\n");
 		goto cleanup_exit;
 	}
-	asd->match_type = V4L2_ASYNC_MATCH_FWNODE;
-	asd->match.fwnode = of_fwnode_handle(sensor_node);
 
 	v4l2_fwnode_endpoint_parse(of_fwnode_handle(ep_node), endpoint);
 
@@ -1726,9 +1721,17 @@ static int of_cal_create_instance(struct cal_ctx *ctx, int inst)
 
 	v4l2_async_notifier_init(&ctx->notifier);
 
+	asd = kzalloc(sizeof(*asd), GFP_KERNEL);
+	if (!asd)
+		goto cleanup_exit;
+
+	asd->match_type = V4L2_ASYNC_MATCH_FWNODE;
+	asd->match.fwnode = of_fwnode_handle(sensor_node);
+
 	ret = v4l2_async_notifier_add_subdev(&ctx->notifier, asd);
 	if (ret) {
 		ctx_err(ctx, "Error adding asd\n");
+		kfree(asd);
 		goto cleanup_exit;
 	}
 
diff --git a/drivers/media/platform/vicodec/vicodec-core.c b/drivers/media/platform/vicodec/vicodec-core.c
index bd01a9206aa6..7bd1af067194 100644
--- a/drivers/media/platform/vicodec/vicodec-core.c
+++ b/drivers/media/platform/vicodec/vicodec-core.c
@@ -2038,16 +2038,19 @@ static int vicodec_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, dev);
 
-	if (register_instance(dev, &dev->stateful_enc,
-			      "stateful-encoder", true))
+	ret = register_instance(dev, &dev->stateful_enc, "stateful-encoder",
+				true);
+	if (ret)
 		goto unreg_dev;
 
-	if (register_instance(dev, &dev->stateful_dec,
-			      "stateful-decoder", false))
+	ret = register_instance(dev, &dev->stateful_dec, "stateful-decoder",
+				false);
+	if (ret)
 		goto unreg_sf_enc;
 
-	if (register_instance(dev, &dev->stateless_dec,
-			      "stateless-decoder", false))
+	ret = register_instance(dev, &dev->stateless_dec, "stateless-decoder",
+				false);
+	if (ret)
 		goto unreg_sf_dec;
 
 #ifdef CONFIG_MEDIA_CONTROLLER
diff --git a/drivers/media/platform/vsp1/vsp1_dl.c b/drivers/media/platform/vsp1/vsp1_dl.c
index d7b43037e500..e07b135613eb 100644
--- a/drivers/media/platform/vsp1/vsp1_dl.c
+++ b/drivers/media/platform/vsp1/vsp1_dl.c
@@ -431,6 +431,8 @@ vsp1_dl_cmd_pool_create(struct vsp1_device *vsp1, enum vsp1_extcmd_type type,
 	if (!pool)
 		return NULL;
 
+	pool->vsp1 = vsp1;
+
 	spin_lock_init(&pool->lock);
 	INIT_LIST_HEAD(&pool->free);
 
diff --git a/drivers/media/rc/iguanair.c b/drivers/media/rc/iguanair.c
index 872d6441e512..a7deca1fefb7 100644
--- a/drivers/media/rc/iguanair.c
+++ b/drivers/media/rc/iguanair.c
@@ -413,7 +413,7 @@ static int iguanair_probe(struct usb_interface *intf,
 	int ret, pipein, pipeout;
 	struct usb_host_interface *idesc;
 
-	idesc = intf->altsetting;
+	idesc = intf->cur_altsetting;
 	if (idesc->desc.bNumEndpoints < 2)
 		return -ENODEV;
 
diff --git a/drivers/media/rc/keymaps/Makefile b/drivers/media/rc/keymaps/Makefile
index 5b1399af6b3a..27d9f1538cb1 100644
--- a/drivers/media/rc/keymaps/Makefile
+++ b/drivers/media/rc/keymaps/Makefile
@@ -113,6 +113,7 @@ obj-$(CONFIG_RC_MAP) += rc-adstech-dvb-t-pci.o \
 			rc-videomate-m1f.o \
 			rc-videomate-s350.o \
 			rc-videomate-tv-pvr.o \
+			rc-videostrong-kii-pro.o \
 			rc-winfast.o \
 			rc-winfast-usbii-deluxe.o \
 			rc-su3000.o \
diff --git a/drivers/media/rc/keymaps/rc-videostrong-kii-pro.c b/drivers/media/rc/keymaps/rc-videostrong-kii-pro.c
new file mode 100644
index 000000000000..414d4d231e7e
--- /dev/null
+++ b/drivers/media/rc/keymaps/rc-videostrong-kii-pro.c
@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (C) 2019 Mohammad Rasim <mohammad.rasim96@gmail.com>
+
+#include <media/rc-map.h>
+#include <linux/module.h>
+
+//
+// Keytable for the Videostrong KII Pro STB remote control
+//
+
+static struct rc_map_table kii_pro[] = {
+	{ 0x59, KEY_POWER },
+	{ 0x19, KEY_MUTE },
+	{ 0x42, KEY_RED },
+	{ 0x40, KEY_GREEN },
+	{ 0x00, KEY_YELLOW },
+	{ 0x03, KEY_BLUE },
+	{ 0x4a, KEY_BACK },
+	{ 0x48, KEY_FORWARD },
+	{ 0x08, KEY_PREVIOUSSONG},
+	{ 0x0b, KEY_NEXTSONG},
+	{ 0x46, KEY_PLAYPAUSE },
+	{ 0x44, KEY_STOP },
+	{ 0x1f, KEY_FAVORITES},	//KEY_F5?
+	{ 0x04, KEY_PVR },
+	{ 0x4d, KEY_EPG },
+	{ 0x02, KEY_INFO },
+	{ 0x09, KEY_SUBTITLE },
+	{ 0x01, KEY_AUDIO },
+	{ 0x0d, KEY_HOMEPAGE },
+	{ 0x11, KEY_TV },	// DTV ?
+	{ 0x06, KEY_UP },
+	{ 0x5a, KEY_LEFT },
+	{ 0x1a, KEY_ENTER },	// KEY_OK ?
+	{ 0x1b, KEY_RIGHT },
+	{ 0x16, KEY_DOWN },
+	{ 0x45, KEY_MENU },
+	{ 0x05, KEY_ESC },
+	{ 0x13, KEY_VOLUMEUP },
+	{ 0x17, KEY_VOLUMEDOWN },
+	{ 0x58, KEY_APPSELECT },
+	{ 0x12, KEY_VENDOR },	// mouse
+	{ 0x55, KEY_PAGEUP },	// KEY_CHANNELUP ?
+	{ 0x15, KEY_PAGEDOWN },	// KEY_CHANNELDOWN ?
+	{ 0x52, KEY_1 },
+	{ 0x50, KEY_2 },
+	{ 0x10, KEY_3 },
+	{ 0x56, KEY_4 },
+	{ 0x54, KEY_5 },
+	{ 0x14, KEY_6 },
+	{ 0x4e, KEY_7 },
+	{ 0x4c, KEY_8 },
+	{ 0x0c, KEY_9 },
+	{ 0x18, KEY_WWW },	// KEY_F7
+	{ 0x0f, KEY_0 },
+	{ 0x51, KEY_BACKSPACE },
+};
+
+static struct rc_map_list kii_pro_map = {
+	.map = {
+		.scan     = kii_pro,
+		.size     = ARRAY_SIZE(kii_pro),
+		.rc_proto = RC_PROTO_NEC,
+		.name     = RC_MAP_KII_PRO,
+	}
+};
+
+static int __init init_rc_map_kii_pro(void)
+{
+	return rc_map_register(&kii_pro_map);
+}
+
+static void __exit exit_rc_map_kii_pro(void)
+{
+	rc_map_unregister(&kii_pro_map);
+}
+
+module_init(init_rc_map_kii_pro)
+module_exit(exit_rc_map_kii_pro)
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Mohammad Rasim <mohammad.rasim96@gmail.com>");
diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c
index 3290a249eb3c..777876904afc 100644
--- a/drivers/media/rc/rc-main.c
+++ b/drivers/media/rc/rc-main.c
@@ -1893,23 +1893,28 @@ int rc_register_device(struct rc_dev *dev)
 
 	dev->registered = true;
 
-	if (dev->driver_type != RC_DRIVER_IR_RAW_TX) {
-		rc = rc_setup_rx_device(dev);
-		if (rc)
-			goto out_dev;
-	}
-
-	/* Ensure that the lirc kfifo is setup before we start the thread */
+	/*
+	 * once the the input device is registered in rc_setup_rx_device,
+	 * userspace can open the input device and rc_open() will be called
+	 * as a result. This results in driver code being allowed to submit
+	 * keycodes with rc_keydown, so lirc must be registered first.
+	 */
 	if (dev->allowed_protocols != RC_PROTO_BIT_CEC) {
 		rc = ir_lirc_register(dev);
 		if (rc < 0)
-			goto out_rx;
+			goto out_dev;
+	}
+
+	if (dev->driver_type != RC_DRIVER_IR_RAW_TX) {
+		rc = rc_setup_rx_device(dev);
+		if (rc)
+			goto out_lirc;
 	}
 
 	if (dev->driver_type == RC_DRIVER_IR_RAW) {
 		rc = ir_raw_event_register(dev);
 		if (rc < 0)
-			goto out_lirc;
+			goto out_rx;
 	}
 
 	dev_dbg(&dev->dev, "Registered rc%u (driver: %s)\n", dev->minor,
@@ -1917,11 +1922,11 @@ int rc_register_device(struct rc_dev *dev)
 
 	return 0;
 
+out_rx:
+	rc_free_rx_device(dev);
 out_lirc:
 	if (dev->allowed_protocols != RC_PROTO_BIT_CEC)
 		ir_lirc_unregister(dev);
-out_rx:
-	rc_free_rx_device(dev);
 out_dev:
 	device_del(&dev->dev);
 out_rx_free:
diff --git a/drivers/media/tuners/si2157.c b/drivers/media/tuners/si2157.c
index 7be893def190..06bbc80df314 100644
--- a/drivers/media/tuners/si2157.c
+++ b/drivers/media/tuners/si2157.c
@@ -75,24 +75,23 @@ static int si2157_init(struct dvb_frontend *fe)
 	struct si2157_cmd cmd;
 	const struct firmware *fw;
 	const char *fw_name;
-	unsigned int uitmp, chip_id;
+	unsigned int chip_id, xtal_trim;
 
 	dev_dbg(&client->dev, "\n");
 
-	/* Returned IF frequency is garbage when firmware is not running */
-	memcpy(cmd.args, "\x15\x00\x06\x07", 4);
+	/* Try to get Xtal trim property, to verify tuner still running */
+	memcpy(cmd.args, "\x15\x00\x04\x02", 4);
 	cmd.wlen = 4;
 	cmd.rlen = 4;
 	ret = si2157_cmd_execute(client, &cmd);
-	if (ret)
-		goto err;
 
-	uitmp = cmd.args[2] << 0 | cmd.args[3] << 8;
-	dev_dbg(&client->dev, "if_frequency kHz=%u\n", uitmp);
+	xtal_trim = cmd.args[2] | (cmd.args[3] << 8);
 
-	if (uitmp == dev->if_frequency / 1000)
+	if (ret == 0 && xtal_trim < 16)
 		goto warm;
 
+	dev->if_frequency = 0; /* we no longer know current tuner state */
+
 	/* power up */
 	if (dev->chiptype == SI2157_CHIPTYPE_SI2146) {
 		memcpy(cmd.args, "\xc0\x05\x01\x00\x00\x0b\x00\x00\x01", 9);
diff --git a/drivers/media/usb/b2c2/flexcop-usb.c b/drivers/media/usb/b2c2/flexcop-usb.c
index d1331f828108..198ddfb8d2b1 100644
--- a/drivers/media/usb/b2c2/flexcop-usb.c
+++ b/drivers/media/usb/b2c2/flexcop-usb.c
@@ -295,7 +295,7 @@ static int flexcop_usb_i2c_req(struct flexcop_i2c_adapter *i2c,
 
 	mutex_unlock(&fc_usb->data_mutex);
 
-	return 0;
+	return ret;
 }
 
 /* actual bus specific access functions,
@@ -511,6 +511,9 @@ static int flexcop_usb_init(struct flexcop_usb *fc_usb)
 		return ret;
 	}
 
+	if (fc_usb->uintf->cur_altsetting->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	switch (fc_usb->udev->speed) {
 	case USB_SPEED_LOW:
 		err("cannot handle USB speed because it is too slow.");
@@ -544,9 +547,6 @@ static int flexcop_usb_probe(struct usb_interface *intf,
 	struct flexcop_device *fc = NULL;
 	int ret;
 
-	if (intf->cur_altsetting->desc.bNumEndpoints < 1)
-		return -ENODEV;
-
 	if ((fc = flexcop_device_kmalloc(sizeof(struct flexcop_usb))) == NULL) {
 		err("out of memory\n");
 		return -ENOMEM;
diff --git a/drivers/media/usb/dvb-usb-v2/dvbsky.c b/drivers/media/usb/dvb-usb-v2/dvbsky.c
index c41e10bd6ef7..3b035d5f21dd 100644
--- a/drivers/media/usb/dvb-usb-v2/dvbsky.c
+++ b/drivers/media/usb/dvb-usb-v2/dvbsky.c
@@ -551,6 +551,8 @@ static int dvbsky_mygica_t230c_attach(struct dvb_usb_adapter *adap)
 	si2168_config.i2c_adapter = &i2c_adapter;
 	si2168_config.fe = &adap->fe[0];
 	si2168_config.ts_mode = SI2168_TS_PARALLEL;
+	if (le16_to_cpu(d->udev->descriptor.idProduct) == USB_PID_MYGICA_T230C2)
+		si2168_config.ts_mode |= SI2168_TS_CLK_MANUAL;
 	si2168_config.ts_clock_inv = 1;
 
 	state->i2c_client_demod = dvb_module_probe("si2168", NULL,
@@ -790,6 +792,12 @@ static const struct usb_device_id dvbsky_id_table[] = {
 	{ DVB_USB_DEVICE(USB_VID_CONEXANT, USB_PID_MYGICA_T230C,
 		&mygica_t230c_props, "MyGica Mini DVB-T2 USB Stick T230C",
 		RC_MAP_TOTAL_MEDIA_IN_HAND_02) },
+	{ DVB_USB_DEVICE(USB_VID_CONEXANT, USB_PID_MYGICA_T230C_LITE,
+		&mygica_t230c_props, "MyGica Mini DVB-T2 USB Stick T230C Lite",
+		NULL) },
+	{ DVB_USB_DEVICE(USB_VID_CONEXANT, USB_PID_MYGICA_T230C2,
+		&mygica_t230c_props, "MyGica Mini DVB-T2 USB Stick T230C v2",
+		RC_MAP_TOTAL_MEDIA_IN_HAND_02) },
 	{ }
 };
 MODULE_DEVICE_TABLE(usb, dvbsky_id_table);
diff --git a/drivers/media/usb/dvb-usb/af9005.c b/drivers/media/usb/dvb-usb/af9005.c
index ac93e88d7038..89b4b5d84cdf 100644
--- a/drivers/media/usb/dvb-usb/af9005.c
+++ b/drivers/media/usb/dvb-usb/af9005.c
@@ -554,7 +554,7 @@ static int af9005_boot_packet(struct usb_device *udev, int type, u8 *reply,
 			      u8 *buf, int size)
 {
 	u16 checksum;
-	int act_len, i, ret;
+	int act_len = 0, i, ret;
 
 	memset(buf, 0, size);
 	buf[0] = (u8) (FW_BULKOUT_SIZE & 0xff);
diff --git a/drivers/media/usb/dvb-usb/dib0700_core.c b/drivers/media/usb/dvb-usb/dib0700_core.c
index e53c58ab6488..ef62dd6c5ae4 100644
--- a/drivers/media/usb/dvb-usb/dib0700_core.c
+++ b/drivers/media/usb/dvb-usb/dib0700_core.c
@@ -818,7 +818,7 @@ int dib0700_rc_setup(struct dvb_usb_device *d, struct usb_interface *intf)
 
 	/* Starting in firmware 1.20, the RC info is provided on a bulk pipe */
 
-	if (intf->altsetting[0].desc.bNumEndpoints < rc_ep + 1)
+	if (intf->cur_altsetting->desc.bNumEndpoints < rc_ep + 1)
 		return -ENODEV;
 
 	purb = usb_alloc_urb(0, GFP_KERNEL);
@@ -838,7 +838,7 @@ int dib0700_rc_setup(struct dvb_usb_device *d, struct usb_interface *intf)
 	 * Some devices like the Hauppauge NovaTD model 52009 use an interrupt
 	 * endpoint, while others use a bulk one.
 	 */
-	e = &intf->altsetting[0].endpoint[rc_ep].desc;
+	e = &intf->cur_altsetting->endpoint[rc_ep].desc;
 	if (usb_endpoint_dir_in(e)) {
 		if (usb_endpoint_xfer_bulk(e)) {
 			pipe = usb_rcvbulkpipe(d->udev, rc_ep);
diff --git a/drivers/media/usb/dvb-usb/dibusb-mb.c b/drivers/media/usb/dvb-usb/dibusb-mb.c
index d4ea72bf09c5..5131c8d4c632 100644
--- a/drivers/media/usb/dvb-usb/dibusb-mb.c
+++ b/drivers/media/usb/dvb-usb/dibusb-mb.c
@@ -81,7 +81,7 @@ static int dibusb_tuner_probe_and_attach(struct dvb_usb_adapter *adap)
 
 	if (i2c_transfer(&adap->dev->i2c_adap, msg, 2) != 2) {
 		err("tuner i2c write failed.");
-		ret = -EREMOTEIO;
+		return -EREMOTEIO;
 	}
 
 	if (adap->fe_adap[0].fe->ops.i2c_gate_ctrl)
diff --git a/drivers/media/usb/dvb-usb/digitv.c b/drivers/media/usb/dvb-usb/digitv.c
index dd5bb230cec1..99a39339d45d 100644
--- a/drivers/media/usb/dvb-usb/digitv.c
+++ b/drivers/media/usb/dvb-usb/digitv.c
@@ -230,18 +230,22 @@ static struct rc_map_table rc_map_digitv_table[] = {
 
 static int digitv_rc_query(struct dvb_usb_device *d, u32 *event, int *state)
 {
-	int i;
+	int ret, i;
 	u8 key[5];
 	u8 b[4] = { 0 };
 
 	*event = 0;
 	*state = REMOTE_NO_KEY_PRESSED;
 
-	digitv_ctrl_msg(d,USB_READ_REMOTE,0,NULL,0,&key[1],4);
+	ret = digitv_ctrl_msg(d, USB_READ_REMOTE, 0, NULL, 0, &key[1], 4);
+	if (ret)
+		return ret;
 
 	/* Tell the device we've read the remote. Not sure how necessary
 	   this is, but the Nebula SDK does it. */
-	digitv_ctrl_msg(d,USB_WRITE_REMOTE,0,b,4,NULL,0);
+	ret = digitv_ctrl_msg(d, USB_WRITE_REMOTE, 0, b, 4, NULL, 0);
+	if (ret)
+		return ret;
 
 	/* if something is inside the buffer, simulate key press */
 	if (key[1] != 0)
diff --git a/drivers/media/usb/dvb-usb/dvb-usb-urb.c b/drivers/media/usb/dvb-usb/dvb-usb-urb.c
index c1b4e94a37f8..2aabf90d8697 100644
--- a/drivers/media/usb/dvb-usb/dvb-usb-urb.c
+++ b/drivers/media/usb/dvb-usb/dvb-usb-urb.c
@@ -12,7 +12,7 @@
 int dvb_usb_generic_rw(struct dvb_usb_device *d, u8 *wbuf, u16 wlen, u8 *rbuf,
 	u16 rlen, int delay_ms)
 {
-	int actlen,ret = -ENOMEM;
+	int actlen = 0, ret = -ENOMEM;
 
 	if (!d || wbuf == NULL || wlen == 0)
 		return -EINVAL;
diff --git a/drivers/media/usb/dvb-usb/vp7045.c b/drivers/media/usb/dvb-usb/vp7045.c
index 80c1cf05384b..2baf57216d19 100644
--- a/drivers/media/usb/dvb-usb/vp7045.c
+++ b/drivers/media/usb/dvb-usb/vp7045.c
@@ -96,10 +96,14 @@ static int vp7045_power_ctrl(struct dvb_usb_device *d, int onoff)
 
 static int vp7045_rc_query(struct dvb_usb_device *d)
 {
+	int ret;
 	u8 key;
-	vp7045_usb_op(d,RC_VAL_READ,NULL,0,&key,1,20);
 
-	deb_rc("remote query key: %x %d\n",key,key);
+	ret = vp7045_usb_op(d, RC_VAL_READ, NULL, 0, &key, 1, 20);
+	if (ret)
+		return ret;
+
+	deb_rc("remote query key: %x\n", key);
 
 	if (key != 0x44) {
 		/*
@@ -115,15 +119,18 @@ static int vp7045_rc_query(struct dvb_usb_device *d)
 
 static int vp7045_read_eeprom(struct dvb_usb_device *d,u8 *buf, int len, int offset)
 {
-	int i = 0;
-	u8 v,br[2];
+	int i, ret;
+	u8 v, br[2];
 	for (i=0; i < len; i++) {
 		v = offset + i;
-		vp7045_usb_op(d,GET_EE_VALUE,&v,1,br,2,5);
+		ret = vp7045_usb_op(d, GET_EE_VALUE, &v, 1, br, 2, 5);
+		if (ret)
+			return ret;
+
 		buf[i] = br[1];
 	}
-	deb_info("VP7045 EEPROM read (offs: %d, len: %d) : ",offset, i);
-	debug_dump(buf,i,deb_info);
+	deb_info("VP7045 EEPROM read (offs: %d, len: %d) : ", offset, i);
+	debug_dump(buf, i, deb_info);
 	return 0;
 }
 
diff --git a/drivers/media/usb/go7007/snd-go7007.c b/drivers/media/usb/go7007/snd-go7007.c
index 4a449c62fc32..e8de12372e25 100644
--- a/drivers/media/usb/go7007/snd-go7007.c
+++ b/drivers/media/usb/go7007/snd-go7007.c
@@ -236,22 +236,18 @@ int go7007_snd_init(struct go7007 *go)
 	gosnd->capturing = 0;
 	ret = snd_card_new(go->dev, index[dev], id[dev], THIS_MODULE, 0,
 			   &gosnd->card);
-	if (ret < 0) {
-		kfree(gosnd);
-		return ret;
-	}
+	if (ret < 0)
+		goto free_snd;
+
 	ret = snd_device_new(gosnd->card, SNDRV_DEV_LOWLEVEL, go,
 			&go7007_snd_device_ops);
-	if (ret < 0) {
-		kfree(gosnd);
-		return ret;
-	}
+	if (ret < 0)
+		goto free_card;
+
 	ret = snd_pcm_new(gosnd->card, "go7007", 0, 0, 1, &gosnd->pcm);
-	if (ret < 0) {
-		snd_card_free(gosnd->card);
-		kfree(gosnd);
-		return ret;
-	}
+	if (ret < 0)
+		goto free_card;
+
 	strscpy(gosnd->card->driver, "go7007", sizeof(gosnd->card->driver));
 	strscpy(gosnd->card->shortname, go->name, sizeof(gosnd->card->driver));
 	strscpy(gosnd->card->longname, gosnd->card->shortname,
@@ -262,11 +258,8 @@ int go7007_snd_init(struct go7007 *go)
 			&go7007_snd_capture_ops);
 
 	ret = snd_card_register(gosnd->card);
-	if (ret < 0) {
-		snd_card_free(gosnd->card);
-		kfree(gosnd);
-		return ret;
-	}
+	if (ret < 0)
+		goto free_card;
 
 	gosnd->substream = NULL;
 	go->snd_context = gosnd;
@@ -274,6 +267,12 @@ int go7007_snd_init(struct go7007 *go)
 	++dev;
 
 	return 0;
+
+free_card:
+	snd_card_free(gosnd->card);
+free_snd:
+	kfree(gosnd);
+	return ret;
 }
 EXPORT_SYMBOL(go7007_snd_init);
 
diff --git a/drivers/media/usb/gspca/gspca.c b/drivers/media/usb/gspca/gspca.c
index a7ed5257cdba..9d14a58a4fad 100644
--- a/drivers/media/usb/gspca/gspca.c
+++ b/drivers/media/usb/gspca/gspca.c
@@ -1472,7 +1472,7 @@ int gspca_dev_probe2(struct usb_interface *intf,
 		pr_err("couldn't kzalloc gspca struct\n");
 		return -ENOMEM;
 	}
-	gspca_dev->usb_buf = kmalloc(USB_BUF_SZ, GFP_KERNEL);
+	gspca_dev->usb_buf = kzalloc(USB_BUF_SZ, GFP_KERNEL);
 	if (!gspca_dev->usb_buf) {
 		pr_err("out of memory\n");
 		ret = -ENOMEM;
diff --git a/drivers/media/usb/gspca/ov519.c b/drivers/media/usb/gspca/ov519.c
index f417dfc0b872..0afe70a3f9a2 100644
--- a/drivers/media/usb/gspca/ov519.c
+++ b/drivers/media/usb/gspca/ov519.c
@@ -3477,6 +3477,11 @@ static void ov511_mode_init_regs(struct sd *sd)
 		return;
 	}
 
+	if (alt->desc.bNumEndpoints < 1) {
+		sd->gspca_dev.usb_err = -ENODEV;
+		return;
+	}
+
 	packet_size = le16_to_cpu(alt->endpoint[0].desc.wMaxPacketSize);
 	reg_w(sd, R51x_FIFO_PSIZE, packet_size >> 5);
 
@@ -3603,6 +3608,11 @@ static void ov518_mode_init_regs(struct sd *sd)
 		return;
 	}
 
+	if (alt->desc.bNumEndpoints < 1) {
+		sd->gspca_dev.usb_err = -ENODEV;
+		return;
+	}
+
 	packet_size = le16_to_cpu(alt->endpoint[0].desc.wMaxPacketSize);
 	ov518_reg_w32(sd, R51x_FIFO_PSIZE, packet_size & ~7, 2);
 
diff --git a/drivers/media/usb/gspca/stv06xx/stv06xx.c b/drivers/media/usb/gspca/stv06xx/stv06xx.c
index 79653d409951..95673fc0a99c 100644
--- a/drivers/media/usb/gspca/stv06xx/stv06xx.c
+++ b/drivers/media/usb/gspca/stv06xx/stv06xx.c
@@ -282,6 +282,9 @@ static int stv06xx_start(struct gspca_dev *gspca_dev)
 		return -EIO;
 	}
 
+	if (alt->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	packet_size = le16_to_cpu(alt->endpoint[0].desc.wMaxPacketSize);
 	err = stv06xx_write_bridge(sd, STV_ISO_SIZE_L, packet_size);
 	if (err < 0)
@@ -306,11 +309,21 @@ out:
 
 static int stv06xx_isoc_init(struct gspca_dev *gspca_dev)
 {
+	struct usb_interface_cache *intfc;
 	struct usb_host_interface *alt;
 	struct sd *sd = (struct sd *) gspca_dev;
 
+	intfc = gspca_dev->dev->actconfig->intf_cache[0];
+
+	if (intfc->num_altsetting < 2)
+		return -ENODEV;
+
+	alt = &intfc->altsetting[1];
+
+	if (alt->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	/* Start isoc bandwidth "negotiation" at max isoc bandwidth */
-	alt = &gspca_dev->dev->actconfig->intf_cache[0]->altsetting[1];
 	alt->endpoint[0].desc.wMaxPacketSize =
 		cpu_to_le16(sd->sensor->max_packet_size[gspca_dev->curr_mode]);
 
@@ -323,6 +336,10 @@ static int stv06xx_isoc_nego(struct gspca_dev *gspca_dev)
 	struct usb_host_interface *alt;
 	struct sd *sd = (struct sd *) gspca_dev;
 
+	/*
+	 * Existence of altsetting and endpoint was verified in
+	 * stv06xx_isoc_init()
+	 */
 	alt = &gspca_dev->dev->actconfig->intf_cache[0]->altsetting[1];
 	packet_size = le16_to_cpu(alt->endpoint[0].desc.wMaxPacketSize);
 	min_packet_size = sd->sensor->min_packet_size[gspca_dev->curr_mode];
diff --git a/drivers/media/usb/gspca/stv06xx/stv06xx_pb0100.c b/drivers/media/usb/gspca/stv06xx/stv06xx_pb0100.c
index 6d1007715ff7..ae382b3b5f7f 100644
--- a/drivers/media/usb/gspca/stv06xx/stv06xx_pb0100.c
+++ b/drivers/media/usb/gspca/stv06xx/stv06xx_pb0100.c
@@ -185,6 +185,10 @@ static int pb0100_start(struct sd *sd)
 	alt = usb_altnum_to_altsetting(intf, sd->gspca_dev.alt);
 	if (!alt)
 		return -ENODEV;
+
+	if (alt->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	packet_size = le16_to_cpu(alt->endpoint[0].desc.wMaxPacketSize);
 
 	/* If we don't have enough bandwidth use a lower framerate */
diff --git a/drivers/media/usb/gspca/xirlink_cit.c b/drivers/media/usb/gspca/xirlink_cit.c
index 934a90bd78c2..c579b100f066 100644
--- a/drivers/media/usb/gspca/xirlink_cit.c
+++ b/drivers/media/usb/gspca/xirlink_cit.c
@@ -1442,6 +1442,9 @@ static int cit_get_packet_size(struct gspca_dev *gspca_dev)
 		return -EIO;
 	}
 
+	if (alt->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	return le16_to_cpu(alt->endpoint[0].desc.wMaxPacketSize);
 }
 
@@ -2626,6 +2629,7 @@ static int sd_start(struct gspca_dev *gspca_dev)
 
 static int sd_isoc_init(struct gspca_dev *gspca_dev)
 {
+	struct usb_interface_cache *intfc;
 	struct usb_host_interface *alt;
 	int max_packet_size;
 
@@ -2641,8 +2645,17 @@ static int sd_isoc_init(struct gspca_dev *gspca_dev)
 		break;
 	}
 
+	intfc = gspca_dev->dev->actconfig->intf_cache[0];
+
+	if (intfc->num_altsetting < 2)
+		return -ENODEV;
+
+	alt = &intfc->altsetting[1];
+
+	if (alt->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	/* Start isoc bandwidth "negotiation" at max isoc bandwidth */
-	alt = &gspca_dev->dev->actconfig->intf_cache[0]->altsetting[1];
 	alt->endpoint[0].desc.wMaxPacketSize = cpu_to_le16(max_packet_size);
 
 	return 0;
@@ -2665,6 +2678,9 @@ static int sd_isoc_nego(struct gspca_dev *gspca_dev)
 		break;
 	}
 
+	/*
+	 * Existence of altsetting and endpoint was verified in sd_isoc_init()
+	 */
 	alt = &gspca_dev->dev->actconfig->intf_cache[0]->altsetting[1];
 	packet_size = le16_to_cpu(alt->endpoint[0].desc.wMaxPacketSize);
 	if (packet_size <= min_packet_size)
diff --git a/drivers/media/usb/pulse8-cec/pulse8-cec.c b/drivers/media/usb/pulse8-cec/pulse8-cec.c
index ac88ade94cda..59609556d969 100644
--- a/drivers/media/usb/pulse8-cec/pulse8-cec.c
+++ b/drivers/media/usb/pulse8-cec/pulse8-cec.c
@@ -116,6 +116,7 @@ struct pulse8 {
 	unsigned int vers;
 	struct completion cmd_done;
 	struct work_struct work;
+	u8 work_result;
 	struct delayed_work ping_eeprom_work;
 	struct cec_msg rx_msg;
 	u8 data[DATA_SIZE];
@@ -137,8 +138,10 @@ static void pulse8_irq_work_handler(struct work_struct *work)
 {
 	struct pulse8 *pulse8 =
 		container_of(work, struct pulse8, work);
+	u8 result = pulse8->work_result;
 
-	switch (pulse8->data[0] & 0x3f) {
+	pulse8->work_result = 0;
+	switch (result & 0x3f) {
 	case MSGCODE_FRAME_DATA:
 		cec_received_msg(pulse8->adap, &pulse8->rx_msg);
 		break;
@@ -172,12 +175,12 @@ static irqreturn_t pulse8_interrupt(struct serio *serio, unsigned char data,
 		pulse8->escape = false;
 	} else if (data == MSGEND) {
 		struct cec_msg *msg = &pulse8->rx_msg;
+		u8 msgcode = pulse8->buf[0];
 
 		if (debug)
 			dev_info(pulse8->dev, "received: %*ph\n",
 				 pulse8->idx, pulse8->buf);
-		pulse8->data[0] = pulse8->buf[0];
-		switch (pulse8->buf[0] & 0x3f) {
+		switch (msgcode & 0x3f) {
 		case MSGCODE_FRAME_START:
 			msg->len = 1;
 			msg->msg[0] = pulse8->buf[1];
@@ -186,14 +189,20 @@ static irqreturn_t pulse8_interrupt(struct serio *serio, unsigned char data,
 			if (msg->len == CEC_MAX_MSG_SIZE)
 				break;
 			msg->msg[msg->len++] = pulse8->buf[1];
-			if (pulse8->buf[0] & MSGCODE_FRAME_EOM)
+			if (msgcode & MSGCODE_FRAME_EOM) {
+				WARN_ON(pulse8->work_result);
+				pulse8->work_result = msgcode;
 				schedule_work(&pulse8->work);
+				break;
+			}
 			break;
 		case MSGCODE_TRANSMIT_SUCCEEDED:
 		case MSGCODE_TRANSMIT_FAILED_LINE:
 		case MSGCODE_TRANSMIT_FAILED_ACK:
 		case MSGCODE_TRANSMIT_FAILED_TIMEOUT_DATA:
 		case MSGCODE_TRANSMIT_FAILED_TIMEOUT_LINE:
+			WARN_ON(pulse8->work_result);
+			pulse8->work_result = msgcode;
 			schedule_work(&pulse8->work);
 			break;
 		case MSGCODE_HIGH_ERROR:
diff --git a/drivers/media/usb/usbtv/usbtv-core.c b/drivers/media/usb/usbtv/usbtv-core.c
index 5095c380b2c1..ee9c656d121f 100644
--- a/drivers/media/usb/usbtv/usbtv-core.c
+++ b/drivers/media/usb/usbtv/usbtv-core.c
@@ -56,7 +56,7 @@ int usbtv_set_regs(struct usbtv *usbtv, const u16 regs[][2], int size)
 
 		ret = usb_control_msg(usbtv->udev, pipe, USBTV_REQUEST_REG,
 			USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
-			value, index, NULL, 0, 0);
+			value, index, NULL, 0, USB_CTRL_GET_TIMEOUT);
 		if (ret < 0)
 			return ret;
 	}
diff --git a/drivers/media/usb/usbtv/usbtv-video.c b/drivers/media/usb/usbtv/usbtv-video.c
index 4a1eab711bdc..646747a2c387 100644
--- a/drivers/media/usb/usbtv/usbtv-video.c
+++ b/drivers/media/usb/usbtv/usbtv-video.c
@@ -805,7 +805,8 @@ static int usbtv_s_ctrl(struct v4l2_ctrl *ctrl)
 		ret = usb_control_msg(usbtv->udev,
 			usb_rcvctrlpipe(usbtv->udev, 0), USBTV_CONTROL_REG,
 			USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
-			0, USBTV_BASE + 0x0244, (void *)data, 3, 0);
+			0, USBTV_BASE + 0x0244, (void *)data, 3,
+			USB_CTRL_GET_TIMEOUT);
 		if (ret < 0)
 			goto error;
 	}
@@ -856,7 +857,7 @@ static int usbtv_s_ctrl(struct v4l2_ctrl *ctrl)
 	ret = usb_control_msg(usbtv->udev, usb_sndctrlpipe(usbtv->udev, 0),
 			USBTV_CONTROL_REG,
 			USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
-			0, index, (void *)data, size, 0);
+			0, index, (void *)data, size, USB_CTRL_SET_TIMEOUT);
 
 error:
 	if (ret < 0)
diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c
index 428235ca2635..99883550375e 100644
--- a/drivers/media/usb/uvc/uvc_driver.c
+++ b/drivers/media/usb/uvc/uvc_driver.c
@@ -497,6 +497,22 @@ static int uvc_parse_format(struct uvc_device *dev,
 			}
 		}
 
+		/* Some devices report bpp that doesn't match the format. */
+		if (dev->quirks & UVC_QUIRK_FORCE_BPP) {
+			const struct v4l2_format_info *info =
+				v4l2_format_info(format->fcc);
+
+			if (info) {
+				unsigned int div = info->hdiv * info->vdiv;
+
+				n = info->bpp[0] * div;
+				for (i = 1; i < info->comp_planes; i++)
+					n += info->bpp[i];
+
+				format->bpp = DIV_ROUND_UP(8 * n, div);
+			}
+		}
+
 		if (buffer[2] == UVC_VS_FORMAT_UNCOMPRESSED) {
 			ftype = UVC_VS_FRAME_UNCOMPRESSED;
 		} else {
@@ -1493,6 +1509,11 @@ static int uvc_scan_chain_forward(struct uvc_video_chain *chain,
 			break;
 		if (forward == prev)
 			continue;
+		if (forward->chain.next || forward->chain.prev) {
+			uvc_trace(UVC_TRACE_DESCR, "Found reference to "
+				"entity %d already in chain.\n", forward->id);
+			return -EINVAL;
+		}
 
 		switch (UVC_ENTITY_TYPE(forward)) {
 		case UVC_VC_EXTENSION_UNIT:
@@ -1574,6 +1595,13 @@ static int uvc_scan_chain_backward(struct uvc_video_chain *chain,
 				return -1;
 			}
 
+			if (term->chain.next || term->chain.prev) {
+				uvc_trace(UVC_TRACE_DESCR, "Found reference to "
+					"entity %d already in chain.\n",
+					term->id);
+				return -EINVAL;
+			}
+
 			if (uvc_trace_param & UVC_TRACE_PROBE)
 				printk(KERN_CONT " %d", term->id);
 
@@ -2862,6 +2890,15 @@ static const struct usb_device_id uvc_ids[] = {
 	  .bInterfaceSubClass	= 1,
 	  .bInterfaceProtocol	= 0,
 	  .driver_info		= (kernel_ulong_t)&uvc_quirk_force_y8 },
+	/* GEO Semiconductor GC6500 */
+	{ .match_flags		= USB_DEVICE_ID_MATCH_DEVICE
+				| USB_DEVICE_ID_MATCH_INT_INFO,
+	  .idVendor		= 0x29fe,
+	  .idProduct		= 0x4d53,
+	  .bInterfaceClass	= USB_CLASS_VIDEO,
+	  .bInterfaceSubClass	= 1,
+	  .bInterfaceProtocol	= 0,
+	  .driver_info		= UVC_INFO_QUIRK(UVC_QUIRK_FORCE_BPP) },
 	/* Intel RealSense D4M */
 	{ .match_flags		= USB_DEVICE_ID_MATCH_DEVICE
 				| USB_DEVICE_ID_MATCH_INT_INFO,
diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h
index c7c1baa90dea..24e3d8c647e7 100644
--- a/drivers/media/usb/uvc/uvcvideo.h
+++ b/drivers/media/usb/uvc/uvcvideo.h
@@ -198,6 +198,7 @@
 #define UVC_QUIRK_RESTRICT_FRAME_RATE	0x00000200
 #define UVC_QUIRK_RESTORE_CTRLS_ON_INIT	0x00000400
 #define UVC_QUIRK_FORCE_Y8		0x00000800
+#define UVC_QUIRK_FORCE_BPP		0x00001000
 
 /* Format flags */
 #define UVC_FMT_FLAG_COMPRESSED		0x00000001
diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
index e1eaf1135c7f..7ad6db8dd9f6 100644
--- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
+++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
@@ -1183,36 +1183,38 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 	u32 aux_space;
 	int compatible_arg = 1;
 	long err = 0;
+	unsigned int ncmd;
 
 	/*
 	 * 1. When struct size is different, converts the command.
 	 */
 	switch (cmd) {
-	case VIDIOC_G_FMT32: cmd = VIDIOC_G_FMT; break;
-	case VIDIOC_S_FMT32: cmd = VIDIOC_S_FMT; break;
-	case VIDIOC_QUERYBUF32: cmd = VIDIOC_QUERYBUF; break;
-	case VIDIOC_G_FBUF32: cmd = VIDIOC_G_FBUF; break;
-	case VIDIOC_S_FBUF32: cmd = VIDIOC_S_FBUF; break;
-	case VIDIOC_QBUF32: cmd = VIDIOC_QBUF; break;
-	case VIDIOC_DQBUF32: cmd = VIDIOC_DQBUF; break;
-	case VIDIOC_ENUMSTD32: cmd = VIDIOC_ENUMSTD; break;
-	case VIDIOC_ENUMINPUT32: cmd = VIDIOC_ENUMINPUT; break;
-	case VIDIOC_TRY_FMT32: cmd = VIDIOC_TRY_FMT; break;
-	case VIDIOC_G_EXT_CTRLS32: cmd = VIDIOC_G_EXT_CTRLS; break;
-	case VIDIOC_S_EXT_CTRLS32: cmd = VIDIOC_S_EXT_CTRLS; break;
-	case VIDIOC_TRY_EXT_CTRLS32: cmd = VIDIOC_TRY_EXT_CTRLS; break;
-	case VIDIOC_DQEVENT32: cmd = VIDIOC_DQEVENT; break;
-	case VIDIOC_OVERLAY32: cmd = VIDIOC_OVERLAY; break;
-	case VIDIOC_STREAMON32: cmd = VIDIOC_STREAMON; break;
-	case VIDIOC_STREAMOFF32: cmd = VIDIOC_STREAMOFF; break;
-	case VIDIOC_G_INPUT32: cmd = VIDIOC_G_INPUT; break;
-	case VIDIOC_S_INPUT32: cmd = VIDIOC_S_INPUT; break;
-	case VIDIOC_G_OUTPUT32: cmd = VIDIOC_G_OUTPUT; break;
-	case VIDIOC_S_OUTPUT32: cmd = VIDIOC_S_OUTPUT; break;
-	case VIDIOC_CREATE_BUFS32: cmd = VIDIOC_CREATE_BUFS; break;
-	case VIDIOC_PREPARE_BUF32: cmd = VIDIOC_PREPARE_BUF; break;
-	case VIDIOC_G_EDID32: cmd = VIDIOC_G_EDID; break;
-	case VIDIOC_S_EDID32: cmd = VIDIOC_S_EDID; break;
+	case VIDIOC_G_FMT32: ncmd = VIDIOC_G_FMT; break;
+	case VIDIOC_S_FMT32: ncmd = VIDIOC_S_FMT; break;
+	case VIDIOC_QUERYBUF32: ncmd = VIDIOC_QUERYBUF; break;
+	case VIDIOC_G_FBUF32: ncmd = VIDIOC_G_FBUF; break;
+	case VIDIOC_S_FBUF32: ncmd = VIDIOC_S_FBUF; break;
+	case VIDIOC_QBUF32: ncmd = VIDIOC_QBUF; break;
+	case VIDIOC_DQBUF32: ncmd = VIDIOC_DQBUF; break;
+	case VIDIOC_ENUMSTD32: ncmd = VIDIOC_ENUMSTD; break;
+	case VIDIOC_ENUMINPUT32: ncmd = VIDIOC_ENUMINPUT; break;
+	case VIDIOC_TRY_FMT32: ncmd = VIDIOC_TRY_FMT; break;
+	case VIDIOC_G_EXT_CTRLS32: ncmd = VIDIOC_G_EXT_CTRLS; break;
+	case VIDIOC_S_EXT_CTRLS32: ncmd = VIDIOC_S_EXT_CTRLS; break;
+	case VIDIOC_TRY_EXT_CTRLS32: ncmd = VIDIOC_TRY_EXT_CTRLS; break;
+	case VIDIOC_DQEVENT32: ncmd = VIDIOC_DQEVENT; break;
+	case VIDIOC_OVERLAY32: ncmd = VIDIOC_OVERLAY; break;
+	case VIDIOC_STREAMON32: ncmd = VIDIOC_STREAMON; break;
+	case VIDIOC_STREAMOFF32: ncmd = VIDIOC_STREAMOFF; break;
+	case VIDIOC_G_INPUT32: ncmd = VIDIOC_G_INPUT; break;
+	case VIDIOC_S_INPUT32: ncmd = VIDIOC_S_INPUT; break;
+	case VIDIOC_G_OUTPUT32: ncmd = VIDIOC_G_OUTPUT; break;
+	case VIDIOC_S_OUTPUT32: ncmd = VIDIOC_S_OUTPUT; break;
+	case VIDIOC_CREATE_BUFS32: ncmd = VIDIOC_CREATE_BUFS; break;
+	case VIDIOC_PREPARE_BUF32: ncmd = VIDIOC_PREPARE_BUF; break;
+	case VIDIOC_G_EDID32: ncmd = VIDIOC_G_EDID; break;
+	case VIDIOC_S_EDID32: ncmd = VIDIOC_S_EDID; break;
+	default: ncmd = cmd; break;
 	}
 
 	/*
@@ -1221,11 +1223,11 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 	 * argument into it.
 	 */
 	switch (cmd) {
-	case VIDIOC_OVERLAY:
-	case VIDIOC_STREAMON:
-	case VIDIOC_STREAMOFF:
-	case VIDIOC_S_INPUT:
-	case VIDIOC_S_OUTPUT:
+	case VIDIOC_OVERLAY32:
+	case VIDIOC_STREAMON32:
+	case VIDIOC_STREAMOFF32:
+	case VIDIOC_S_INPUT32:
+	case VIDIOC_S_OUTPUT32:
 		err = alloc_userspace(sizeof(unsigned int), 0, &new_p64);
 		if (!err && assign_in_user((unsigned int __user *)new_p64,
 					   (compat_uint_t __user *)p32))
@@ -1233,23 +1235,23 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 		compatible_arg = 0;
 		break;
 
-	case VIDIOC_G_INPUT:
-	case VIDIOC_G_OUTPUT:
+	case VIDIOC_G_INPUT32:
+	case VIDIOC_G_OUTPUT32:
 		err = alloc_userspace(sizeof(unsigned int), 0, &new_p64);
 		compatible_arg = 0;
 		break;
 
-	case VIDIOC_G_EDID:
-	case VIDIOC_S_EDID:
+	case VIDIOC_G_EDID32:
+	case VIDIOC_S_EDID32:
 		err = alloc_userspace(sizeof(struct v4l2_edid), 0, &new_p64);
 		if (!err)
 			err = get_v4l2_edid32(new_p64, p32);
 		compatible_arg = 0;
 		break;
 
-	case VIDIOC_G_FMT:
-	case VIDIOC_S_FMT:
-	case VIDIOC_TRY_FMT:
+	case VIDIOC_G_FMT32:
+	case VIDIOC_S_FMT32:
+	case VIDIOC_TRY_FMT32:
 		err = bufsize_v4l2_format(p32, &aux_space);
 		if (!err)
 			err = alloc_userspace(sizeof(struct v4l2_format),
@@ -1262,7 +1264,7 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 		compatible_arg = 0;
 		break;
 
-	case VIDIOC_CREATE_BUFS:
+	case VIDIOC_CREATE_BUFS32:
 		err = bufsize_v4l2_create(p32, &aux_space);
 		if (!err)
 			err = alloc_userspace(sizeof(struct v4l2_create_buffers),
@@ -1275,10 +1277,10 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 		compatible_arg = 0;
 		break;
 
-	case VIDIOC_PREPARE_BUF:
-	case VIDIOC_QUERYBUF:
-	case VIDIOC_QBUF:
-	case VIDIOC_DQBUF:
+	case VIDIOC_PREPARE_BUF32:
+	case VIDIOC_QUERYBUF32:
+	case VIDIOC_QBUF32:
+	case VIDIOC_DQBUF32:
 		err = bufsize_v4l2_buffer(p32, &aux_space);
 		if (!err)
 			err = alloc_userspace(sizeof(struct v4l2_buffer),
@@ -1291,7 +1293,7 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 		compatible_arg = 0;
 		break;
 
-	case VIDIOC_S_FBUF:
+	case VIDIOC_S_FBUF32:
 		err = alloc_userspace(sizeof(struct v4l2_framebuffer), 0,
 				      &new_p64);
 		if (!err)
@@ -1299,13 +1301,13 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 		compatible_arg = 0;
 		break;
 
-	case VIDIOC_G_FBUF:
+	case VIDIOC_G_FBUF32:
 		err = alloc_userspace(sizeof(struct v4l2_framebuffer), 0,
 				      &new_p64);
 		compatible_arg = 0;
 		break;
 
-	case VIDIOC_ENUMSTD:
+	case VIDIOC_ENUMSTD32:
 		err = alloc_userspace(sizeof(struct v4l2_standard), 0,
 				      &new_p64);
 		if (!err)
@@ -1313,16 +1315,16 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 		compatible_arg = 0;
 		break;
 
-	case VIDIOC_ENUMINPUT:
+	case VIDIOC_ENUMINPUT32:
 		err = alloc_userspace(sizeof(struct v4l2_input), 0, &new_p64);
 		if (!err)
 			err = get_v4l2_input32(new_p64, p32);
 		compatible_arg = 0;
 		break;
 
-	case VIDIOC_G_EXT_CTRLS:
-	case VIDIOC_S_EXT_CTRLS:
-	case VIDIOC_TRY_EXT_CTRLS:
+	case VIDIOC_G_EXT_CTRLS32:
+	case VIDIOC_S_EXT_CTRLS32:
+	case VIDIOC_TRY_EXT_CTRLS32:
 		err = bufsize_v4l2_ext_controls(p32, &aux_space);
 		if (!err)
 			err = alloc_userspace(sizeof(struct v4l2_ext_controls),
@@ -1334,7 +1336,7 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 		}
 		compatible_arg = 0;
 		break;
-	case VIDIOC_DQEVENT:
+	case VIDIOC_DQEVENT32:
 		err = alloc_userspace(sizeof(struct v4l2_event), 0, &new_p64);
 		compatible_arg = 0;
 		break;
@@ -1352,9 +1354,9 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 	 * Otherwise, it will pass the newly allocated @new_p64 argument.
 	 */
 	if (compatible_arg)
-		err = native_ioctl(file, cmd, (unsigned long)p32);
+		err = native_ioctl(file, ncmd, (unsigned long)p32);
 	else
-		err = native_ioctl(file, cmd, (unsigned long)new_p64);
+		err = native_ioctl(file, ncmd, (unsigned long)new_p64);
 
 	if (err == -ENOTTY)
 		return err;
@@ -1370,13 +1372,13 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 	 * the blocks to maximum allowed value.
 	 */
 	switch (cmd) {
-	case VIDIOC_G_EXT_CTRLS:
-	case VIDIOC_S_EXT_CTRLS:
-	case VIDIOC_TRY_EXT_CTRLS:
+	case VIDIOC_G_EXT_CTRLS32:
+	case VIDIOC_S_EXT_CTRLS32:
+	case VIDIOC_TRY_EXT_CTRLS32:
 		if (put_v4l2_ext_controls32(file, new_p64, p32))
 			err = -EFAULT;
 		break;
-	case VIDIOC_S_EDID:
+	case VIDIOC_S_EDID32:
 		if (put_v4l2_edid32(new_p64, p32))
 			err = -EFAULT;
 		break;
@@ -1389,49 +1391,49 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 	 * the original 32 bits structure.
 	 */
 	switch (cmd) {
-	case VIDIOC_S_INPUT:
-	case VIDIOC_S_OUTPUT:
-	case VIDIOC_G_INPUT:
-	case VIDIOC_G_OUTPUT:
+	case VIDIOC_S_INPUT32:
+	case VIDIOC_S_OUTPUT32:
+	case VIDIOC_G_INPUT32:
+	case VIDIOC_G_OUTPUT32:
 		if (assign_in_user((compat_uint_t __user *)p32,
 				   ((unsigned int __user *)new_p64)))
 			err = -EFAULT;
 		break;
 
-	case VIDIOC_G_FBUF:
+	case VIDIOC_G_FBUF32:
 		err = put_v4l2_framebuffer32(new_p64, p32);
 		break;
 
-	case VIDIOC_DQEVENT:
+	case VIDIOC_DQEVENT32:
 		err = put_v4l2_event32(new_p64, p32);
 		break;
 
-	case VIDIOC_G_EDID:
+	case VIDIOC_G_EDID32:
 		err = put_v4l2_edid32(new_p64, p32);
 		break;
 
-	case VIDIOC_G_FMT:
-	case VIDIOC_S_FMT:
-	case VIDIOC_TRY_FMT:
+	case VIDIOC_G_FMT32:
+	case VIDIOC_S_FMT32:
+	case VIDIOC_TRY_FMT32:
 		err = put_v4l2_format32(new_p64, p32);
 		break;
 
-	case VIDIOC_CREATE_BUFS:
+	case VIDIOC_CREATE_BUFS32:
 		err = put_v4l2_create32(new_p64, p32);
 		break;
 
-	case VIDIOC_PREPARE_BUF:
-	case VIDIOC_QUERYBUF:
-	case VIDIOC_QBUF:
-	case VIDIOC_DQBUF:
+	case VIDIOC_PREPARE_BUF32:
+	case VIDIOC_QUERYBUF32:
+	case VIDIOC_QBUF32:
+	case VIDIOC_DQBUF32:
 		err = put_v4l2_buffer32(new_p64, p32);
 		break;
 
-	case VIDIOC_ENUMSTD:
+	case VIDIOC_ENUMSTD32:
 		err = put_v4l2_standard32(new_p64, p32);
 		break;
 
-	case VIDIOC_ENUMINPUT:
+	case VIDIOC_ENUMINPUT32:
 		err = put_v4l2_input32(new_p64, p32);
 		break;
 	}
diff --git a/drivers/media/v4l2-core/v4l2-device.c b/drivers/media/v4l2-core/v4l2-device.c
index aa277f5bc862..7fd8f2facc94 100644
--- a/drivers/media/v4l2-core/v4l2-device.c
+++ b/drivers/media/v4l2-core/v4l2-device.c
@@ -210,6 +210,7 @@ static void v4l2_subdev_release(struct v4l2_subdev *sd)
 
 	if (sd->internal_ops && sd->internal_ops->release)
 		sd->internal_ops->release(sd);
+	sd->devnode = NULL;
 	module_put(owner);
 }
 
diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index 85bf87d20908..1f261eac4e0b 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -1575,12 +1575,12 @@ static int v4l_s_fmt(const struct v4l2_ioctl_ops *ops,
 	case V4L2_BUF_TYPE_VBI_CAPTURE:
 		if (unlikely(!ops->vidioc_s_fmt_vbi_cap))
 			break;
-		CLEAR_AFTER_FIELD(p, fmt.vbi);
+		CLEAR_AFTER_FIELD(p, fmt.vbi.flags);
 		return ops->vidioc_s_fmt_vbi_cap(file, fh, arg);
 	case V4L2_BUF_TYPE_SLICED_VBI_CAPTURE:
 		if (unlikely(!ops->vidioc_s_fmt_sliced_vbi_cap))
 			break;
-		CLEAR_AFTER_FIELD(p, fmt.sliced);
+		CLEAR_AFTER_FIELD(p, fmt.sliced.io_size);
 		return ops->vidioc_s_fmt_sliced_vbi_cap(file, fh, arg);
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
 		if (unlikely(!ops->vidioc_s_fmt_vid_out))
@@ -1606,22 +1606,22 @@ static int v4l_s_fmt(const struct v4l2_ioctl_ops *ops,
 	case V4L2_BUF_TYPE_VBI_OUTPUT:
 		if (unlikely(!ops->vidioc_s_fmt_vbi_out))
 			break;
-		CLEAR_AFTER_FIELD(p, fmt.vbi);
+		CLEAR_AFTER_FIELD(p, fmt.vbi.flags);
 		return ops->vidioc_s_fmt_vbi_out(file, fh, arg);
 	case V4L2_BUF_TYPE_SLICED_VBI_OUTPUT:
 		if (unlikely(!ops->vidioc_s_fmt_sliced_vbi_out))
 			break;
-		CLEAR_AFTER_FIELD(p, fmt.sliced);
+		CLEAR_AFTER_FIELD(p, fmt.sliced.io_size);
 		return ops->vidioc_s_fmt_sliced_vbi_out(file, fh, arg);
 	case V4L2_BUF_TYPE_SDR_CAPTURE:
 		if (unlikely(!ops->vidioc_s_fmt_sdr_cap))
 			break;
-		CLEAR_AFTER_FIELD(p, fmt.sdr);
+		CLEAR_AFTER_FIELD(p, fmt.sdr.buffersize);
 		return ops->vidioc_s_fmt_sdr_cap(file, fh, arg);
 	case V4L2_BUF_TYPE_SDR_OUTPUT:
 		if (unlikely(!ops->vidioc_s_fmt_sdr_out))
 			break;
-		CLEAR_AFTER_FIELD(p, fmt.sdr);
+		CLEAR_AFTER_FIELD(p, fmt.sdr.buffersize);
 		return ops->vidioc_s_fmt_sdr_out(file, fh, arg);
 	case V4L2_BUF_TYPE_META_CAPTURE:
 		if (unlikely(!ops->vidioc_s_fmt_meta_cap))
@@ -1674,12 +1674,12 @@ static int v4l_try_fmt(const struct v4l2_ioctl_ops *ops,
 	case V4L2_BUF_TYPE_VBI_CAPTURE:
 		if (unlikely(!ops->vidioc_try_fmt_vbi_cap))
 			break;
-		CLEAR_AFTER_FIELD(p, fmt.vbi);
+		CLEAR_AFTER_FIELD(p, fmt.vbi.flags);
 		return ops->vidioc_try_fmt_vbi_cap(file, fh, arg);
 	case V4L2_BUF_TYPE_SLICED_VBI_CAPTURE:
 		if (unlikely(!ops->vidioc_try_fmt_sliced_vbi_cap))
 			break;
-		CLEAR_AFTER_FIELD(p, fmt.sliced);
+		CLEAR_AFTER_FIELD(p, fmt.sliced.io_size);
 		return ops->vidioc_try_fmt_sliced_vbi_cap(file, fh, arg);
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
 		if (unlikely(!ops->vidioc_try_fmt_vid_out))
@@ -1705,22 +1705,22 @@ static int v4l_try_fmt(const struct v4l2_ioctl_ops *ops,
 	case V4L2_BUF_TYPE_VBI_OUTPUT:
 		if (unlikely(!ops->vidioc_try_fmt_vbi_out))
 			break;
-		CLEAR_AFTER_FIELD(p, fmt.vbi);
+		CLEAR_AFTER_FIELD(p, fmt.vbi.flags);
 		return ops->vidioc_try_fmt_vbi_out(file, fh, arg);
 	case V4L2_BUF_TYPE_SLICED_VBI_OUTPUT:
 		if (unlikely(!ops->vidioc_try_fmt_sliced_vbi_out))
 			break;
-		CLEAR_AFTER_FIELD(p, fmt.sliced);
+		CLEAR_AFTER_FIELD(p, fmt.sliced.io_size);
 		return ops->vidioc_try_fmt_sliced_vbi_out(file, fh, arg);
 	case V4L2_BUF_TYPE_SDR_CAPTURE:
 		if (unlikely(!ops->vidioc_try_fmt_sdr_cap))
 			break;
-		CLEAR_AFTER_FIELD(p, fmt.sdr);
+		CLEAR_AFTER_FIELD(p, fmt.sdr.buffersize);
 		return ops->vidioc_try_fmt_sdr_cap(file, fh, arg);
 	case V4L2_BUF_TYPE_SDR_OUTPUT:
 		if (unlikely(!ops->vidioc_try_fmt_sdr_out))
 			break;
-		CLEAR_AFTER_FIELD(p, fmt.sdr);
+		CLEAR_AFTER_FIELD(p, fmt.sdr.buffersize);
 		return ops->vidioc_try_fmt_sdr_out(file, fh, arg);
 	case V4L2_BUF_TYPE_META_CAPTURE:
 		if (unlikely(!ops->vidioc_try_fmt_meta_cap))
diff --git a/drivers/media/v4l2-core/v4l2-mem2mem.c b/drivers/media/v4l2-core/v4l2-mem2mem.c
index fd96df98c780..24c9a8707e7b 100644
--- a/drivers/media/v4l2-core/v4l2-mem2mem.c
+++ b/drivers/media/v4l2-core/v4l2-mem2mem.c
@@ -802,12 +802,12 @@ int v4l2_m2m_register_media_controller(struct v4l2_m2m_dev *m2m_dev,
 		goto err_rel_entity1;
 
 	/* Connect the three entities */
-	ret = media_create_pad_link(m2m_dev->source, 0, &m2m_dev->proc, 1,
+	ret = media_create_pad_link(m2m_dev->source, 0, &m2m_dev->proc, 0,
 			MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED);
 	if (ret)
 		goto err_rel_entity2;
 
-	ret = media_create_pad_link(&m2m_dev->proc, 0, &m2m_dev->sink, 0,
+	ret = media_create_pad_link(&m2m_dev->proc, 1, &m2m_dev->sink, 0,
 			MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED);
 	if (ret)
 		goto err_rm_links0;
diff --git a/drivers/media/v4l2-core/videobuf-dma-sg.c b/drivers/media/v4l2-core/videobuf-dma-sg.c
index 66a6c6c236a7..28262190c3ab 100644
--- a/drivers/media/v4l2-core/videobuf-dma-sg.c
+++ b/drivers/media/v4l2-core/videobuf-dma-sg.c
@@ -349,8 +349,11 @@ int videobuf_dma_free(struct videobuf_dmabuf *dma)
 	BUG_ON(dma->sglen);
 
 	if (dma->pages) {
-		for (i = 0; i < dma->nr_pages; i++)
+		for (i = 0; i < dma->nr_pages; i++) {
+			if (dma->direction == DMA_FROM_DEVICE)
+				set_page_dirty_lock(dma->pages[i]);
 			put_page(dma->pages[i]);
+		}
 		kfree(dma->pages);
 		dma->pages = NULL;
 	}
diff --git a/drivers/message/fusion/mptctl.c b/drivers/message/fusion/mptctl.c
index f9ac22413000..1074b882c57c 100644
--- a/drivers/message/fusion/mptctl.c
+++ b/drivers/message/fusion/mptctl.c
@@ -100,19 +100,19 @@ struct buflist {
  * Function prototypes. Called from OS entry point mptctl_ioctl.
  * arg contents specific to function.
  */
-static int mptctl_fw_download(unsigned long arg);
-static int mptctl_getiocinfo(unsigned long arg, unsigned int cmd);
-static int mptctl_gettargetinfo(unsigned long arg);
-static int mptctl_readtest(unsigned long arg);
-static int mptctl_mpt_command(unsigned long arg);
-static int mptctl_eventquery(unsigned long arg);
-static int mptctl_eventenable(unsigned long arg);
-static int mptctl_eventreport(unsigned long arg);
-static int mptctl_replace_fw(unsigned long arg);
-
-static int mptctl_do_reset(unsigned long arg);
-static int mptctl_hp_hostinfo(unsigned long arg, unsigned int cmd);
-static int mptctl_hp_targetinfo(unsigned long arg);
+static int mptctl_fw_download(MPT_ADAPTER *iocp, unsigned long arg);
+static int mptctl_getiocinfo(MPT_ADAPTER *iocp, unsigned long arg, unsigned int cmd);
+static int mptctl_gettargetinfo(MPT_ADAPTER *iocp, unsigned long arg);
+static int mptctl_readtest(MPT_ADAPTER *iocp, unsigned long arg);
+static int mptctl_mpt_command(MPT_ADAPTER *iocp, unsigned long arg);
+static int mptctl_eventquery(MPT_ADAPTER *iocp, unsigned long arg);
+static int mptctl_eventenable(MPT_ADAPTER *iocp, unsigned long arg);
+static int mptctl_eventreport(MPT_ADAPTER *iocp, unsigned long arg);
+static int mptctl_replace_fw(MPT_ADAPTER *iocp, unsigned long arg);
+
+static int mptctl_do_reset(MPT_ADAPTER *iocp, unsigned long arg);
+static int mptctl_hp_hostinfo(MPT_ADAPTER *iocp, unsigned long arg, unsigned int cmd);
+static int mptctl_hp_targetinfo(MPT_ADAPTER *iocp, unsigned long arg);
 
 static int  mptctl_probe(struct pci_dev *, const struct pci_device_id *);
 static void mptctl_remove(struct pci_dev *);
@@ -123,8 +123,8 @@ static long compat_mpctl_ioctl(struct file *f, unsigned cmd, unsigned long arg);
 /*
  * Private function calls.
  */
-static int mptctl_do_mpt_command(struct mpt_ioctl_command karg, void __user *mfPtr);
-static int mptctl_do_fw_download(int ioc, char __user *ufwbuf, size_t fwlen);
+static int mptctl_do_mpt_command(MPT_ADAPTER *iocp, struct mpt_ioctl_command karg, void __user *mfPtr);
+static int mptctl_do_fw_download(MPT_ADAPTER *iocp, char __user *ufwbuf, size_t fwlen);
 static MptSge_t *kbuf_alloc_2_sgl(int bytes, u32 dir, int sge_offset, int *frags,
 		struct buflist **blp, dma_addr_t *sglbuf_dma, MPT_ADAPTER *ioc);
 static void kfree_sgl(MptSge_t *sgl, dma_addr_t sgl_dma,
@@ -656,19 +656,19 @@ __mptctl_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	 * by TM and FW reloads.
 	 */
 	if ((cmd & ~IOCSIZE_MASK) == (MPTIOCINFO & ~IOCSIZE_MASK)) {
-		return mptctl_getiocinfo(arg, _IOC_SIZE(cmd));
+		return mptctl_getiocinfo(iocp, arg, _IOC_SIZE(cmd));
 	} else if (cmd == MPTTARGETINFO) {
-		return mptctl_gettargetinfo(arg);
+		return mptctl_gettargetinfo(iocp, arg);
 	} else if (cmd == MPTTEST) {
-		return mptctl_readtest(arg);
+		return mptctl_readtest(iocp, arg);
 	} else if (cmd == MPTEVENTQUERY) {
-		return mptctl_eventquery(arg);
+		return mptctl_eventquery(iocp, arg);
 	} else if (cmd == MPTEVENTENABLE) {
-		return mptctl_eventenable(arg);
+		return mptctl_eventenable(iocp, arg);
 	} else if (cmd == MPTEVENTREPORT) {
-		return mptctl_eventreport(arg);
+		return mptctl_eventreport(iocp, arg);
 	} else if (cmd == MPTFWREPLACE) {
-		return mptctl_replace_fw(arg);
+		return mptctl_replace_fw(iocp, arg);
 	}
 
 	/* All of these commands require an interrupt or
@@ -678,15 +678,15 @@ __mptctl_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		return ret;
 
 	if (cmd == MPTFWDOWNLOAD)
-		ret = mptctl_fw_download(arg);
+		ret = mptctl_fw_download(iocp, arg);
 	else if (cmd == MPTCOMMAND)
-		ret = mptctl_mpt_command(arg);
+		ret = mptctl_mpt_command(iocp, arg);
 	else if (cmd == MPTHARDRESET)
-		ret = mptctl_do_reset(arg);
+		ret = mptctl_do_reset(iocp, arg);
 	else if ((cmd & ~IOCSIZE_MASK) == (HP_GETHOSTINFO & ~IOCSIZE_MASK))
-		ret = mptctl_hp_hostinfo(arg, _IOC_SIZE(cmd));
+		ret = mptctl_hp_hostinfo(iocp, arg, _IOC_SIZE(cmd));
 	else if (cmd == HP_GETTARGETINFO)
-		ret = mptctl_hp_targetinfo(arg);
+		ret = mptctl_hp_targetinfo(iocp, arg);
 	else
 		ret = -EINVAL;
 
@@ -705,11 +705,10 @@ mptctl_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	return ret;
 }
 
-static int mptctl_do_reset(unsigned long arg)
+static int mptctl_do_reset(MPT_ADAPTER *iocp, unsigned long arg)
 {
 	struct mpt_ioctl_diag_reset __user *urinfo = (void __user *) arg;
 	struct mpt_ioctl_diag_reset krinfo;
-	MPT_ADAPTER		*iocp;
 
 	if (copy_from_user(&krinfo, urinfo, sizeof(struct mpt_ioctl_diag_reset))) {
 		printk(KERN_ERR MYNAM "%s@%d::mptctl_do_reset - "
@@ -718,12 +717,6 @@ static int mptctl_do_reset(unsigned long arg)
 		return -EFAULT;
 	}
 
-	if (mpt_verify_adapter(krinfo.hdr.iocnum, &iocp) < 0) {
-		printk(KERN_DEBUG MYNAM "%s@%d::mptctl_do_reset - ioc%d not found!\n",
-				__FILE__, __LINE__, krinfo.hdr.iocnum);
-		return -ENODEV; /* (-6) No such device or address */
-	}
-
 	dctlprintk(iocp, printk(MYIOC_s_DEBUG_FMT "mptctl_do_reset called.\n",
 	    iocp->name));
 
@@ -754,7 +747,7 @@ static int mptctl_do_reset(unsigned long arg)
  *		-ENOMSG if FW upload returned bad status
  */
 static int
-mptctl_fw_download(unsigned long arg)
+mptctl_fw_download(MPT_ADAPTER *iocp, unsigned long arg)
 {
 	struct mpt_fw_xfer __user *ufwdl = (void __user *) arg;
 	struct mpt_fw_xfer	 kfwdl;
@@ -766,7 +759,7 @@ mptctl_fw_download(unsigned long arg)
 		return -EFAULT;
 	}
 
-	return mptctl_do_fw_download(kfwdl.iocnum, kfwdl.bufp, kfwdl.fwlen);
+	return mptctl_do_fw_download(iocp, kfwdl.bufp, kfwdl.fwlen);
 }
 
 /*=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=*/
@@ -784,11 +777,10 @@ mptctl_fw_download(unsigned long arg)
  *		-ENOMSG if FW upload returned bad status
  */
 static int
-mptctl_do_fw_download(int ioc, char __user *ufwbuf, size_t fwlen)
+mptctl_do_fw_download(MPT_ADAPTER *iocp, char __user *ufwbuf, size_t fwlen)
 {
 	FWDownload_t		*dlmsg;
 	MPT_FRAME_HDR		*mf;
-	MPT_ADAPTER		*iocp;
 	FWDownloadTCSGE_t	*ptsge;
 	MptSge_t		*sgl, *sgIn;
 	char			*sgOut;
@@ -808,17 +800,10 @@ mptctl_do_fw_download(int ioc, char __user *ufwbuf, size_t fwlen)
 	pFWDownloadReply_t	 ReplyMsg = NULL;
 	unsigned long		 timeleft;
 
-	if (mpt_verify_adapter(ioc, &iocp) < 0) {
-		printk(KERN_DEBUG MYNAM "ioctl_fwdl - ioc%d not found!\n",
-				 ioc);
-		return -ENODEV; /* (-6) No such device or address */
-	} else {
-
-		/*  Valid device. Get a message frame and construct the FW download message.
-	 	*/
-		if ((mf = mpt_get_msg_frame(mptctl_id, iocp)) == NULL)
-			return -EAGAIN;
-	}
+	/*  Valid device. Get a message frame and construct the FW download message.
+	*/
+	if ((mf = mpt_get_msg_frame(mptctl_id, iocp)) == NULL)
+		return -EAGAIN;
 
 	dctlprintk(iocp, printk(MYIOC_s_DEBUG_FMT
 	    "mptctl_do_fwdl called. mptctl_id = %xh.\n", iocp->name, mptctl_id));
@@ -826,8 +811,6 @@ mptctl_do_fw_download(int ioc, char __user *ufwbuf, size_t fwlen)
 	    iocp->name, ufwbuf));
 	dctlprintk(iocp, printk(MYIOC_s_DEBUG_FMT "DbG: kfwdl.fwlen = %d\n",
 	    iocp->name, (int)fwlen));
-	dctlprintk(iocp, printk(MYIOC_s_DEBUG_FMT "DbG: kfwdl.ioc   = %04xh\n",
-	    iocp->name, ioc));
 
 	dlmsg = (FWDownload_t*) mf;
 	ptsge = (FWDownloadTCSGE_t *) &dlmsg->SGL;
@@ -1238,13 +1221,11 @@ kfree_sgl(MptSge_t *sgl, dma_addr_t sgl_dma, struct buflist *buflist, MPT_ADAPTE
  *		-ENODEV  if no such device/adapter
  */
 static int
-mptctl_getiocinfo (unsigned long arg, unsigned int data_size)
+mptctl_getiocinfo (MPT_ADAPTER *ioc, unsigned long arg, unsigned int data_size)
 {
 	struct mpt_ioctl_iocinfo __user *uarg = (void __user *) arg;
 	struct mpt_ioctl_iocinfo *karg;
-	MPT_ADAPTER		*ioc;
 	struct pci_dev		*pdev;
-	int			iocnum;
 	unsigned int		port;
 	int			cim_rev;
 	struct scsi_device 	*sdev;
@@ -1272,14 +1253,6 @@ mptctl_getiocinfo (unsigned long arg, unsigned int data_size)
 		return PTR_ERR(karg);
 	}
 
-	if (((iocnum = mpt_verify_adapter(karg->hdr.iocnum, &ioc)) < 0) ||
-	    (ioc == NULL)) {
-		printk(KERN_DEBUG MYNAM "%s::mptctl_getiocinfo() @%d - ioc%d not found!\n",
-				__FILE__, __LINE__, iocnum);
-		kfree(karg);
-		return -ENODEV;
-	}
-
 	/* Verify the data transfer size is correct. */
 	if (karg->hdr.maxDataSize != data_size) {
 		printk(MYIOC_s_ERR_FMT "%s@%d::mptctl_getiocinfo - "
@@ -1385,15 +1358,13 @@ mptctl_getiocinfo (unsigned long arg, unsigned int data_size)
  *		-ENODEV  if no such device/adapter
  */
 static int
-mptctl_gettargetinfo (unsigned long arg)
+mptctl_gettargetinfo (MPT_ADAPTER *ioc, unsigned long arg)
 {
 	struct mpt_ioctl_targetinfo __user *uarg = (void __user *) arg;
 	struct mpt_ioctl_targetinfo karg;
-	MPT_ADAPTER		*ioc;
 	VirtDevice		*vdevice;
 	char			*pmem;
 	int			*pdata;
-	int			iocnum;
 	int			numDevices = 0;
 	int			lun;
 	int			maxWordsLeft;
@@ -1408,13 +1379,6 @@ mptctl_gettargetinfo (unsigned long arg)
 		return -EFAULT;
 	}
 
-	if (((iocnum = mpt_verify_adapter(karg.hdr.iocnum, &ioc)) < 0) ||
-	    (ioc == NULL)) {
-		printk(KERN_DEBUG MYNAM "%s::mptctl_gettargetinfo() @%d - ioc%d not found!\n",
-				__FILE__, __LINE__, iocnum);
-		return -ENODEV;
-	}
-
 	dctlprintk(ioc, printk(MYIOC_s_DEBUG_FMT "mptctl_gettargetinfo called.\n",
 	    ioc->name));
 	/* Get the port number and set the maximum number of bytes
@@ -1510,12 +1474,10 @@ mptctl_gettargetinfo (unsigned long arg)
  *		-ENODEV  if no such device/adapter
  */
 static int
-mptctl_readtest (unsigned long arg)
+mptctl_readtest (MPT_ADAPTER *ioc, unsigned long arg)
 {
 	struct mpt_ioctl_test __user *uarg = (void __user *) arg;
 	struct mpt_ioctl_test	 karg;
-	MPT_ADAPTER *ioc;
-	int iocnum;
 
 	if (copy_from_user(&karg, uarg, sizeof(struct mpt_ioctl_test))) {
 		printk(KERN_ERR MYNAM "%s@%d::mptctl_readtest - "
@@ -1524,13 +1486,6 @@ mptctl_readtest (unsigned long arg)
 		return -EFAULT;
 	}
 
-	if (((iocnum = mpt_verify_adapter(karg.hdr.iocnum, &ioc)) < 0) ||
-	    (ioc == NULL)) {
-		printk(KERN_DEBUG MYNAM "%s::mptctl_readtest() @%d - ioc%d not found!\n",
-				__FILE__, __LINE__, iocnum);
-		return -ENODEV;
-	}
-
 	dctlprintk(ioc, printk(MYIOC_s_DEBUG_FMT "mptctl_readtest called.\n",
 	    ioc->name));
 	/* Fill in the data and return the structure to the calling
@@ -1571,12 +1526,10 @@ mptctl_readtest (unsigned long arg)
  *		-ENODEV  if no such device/adapter
  */
 static int
-mptctl_eventquery (unsigned long arg)
+mptctl_eventquery (MPT_ADAPTER *ioc, unsigned long arg)
 {
 	struct mpt_ioctl_eventquery __user *uarg = (void __user *) arg;
 	struct mpt_ioctl_eventquery	 karg;
-	MPT_ADAPTER *ioc;
-	int iocnum;
 
 	if (copy_from_user(&karg, uarg, sizeof(struct mpt_ioctl_eventquery))) {
 		printk(KERN_ERR MYNAM "%s@%d::mptctl_eventquery - "
@@ -1585,13 +1538,6 @@ mptctl_eventquery (unsigned long arg)
 		return -EFAULT;
 	}
 
-	if (((iocnum = mpt_verify_adapter(karg.hdr.iocnum, &ioc)) < 0) ||
-	    (ioc == NULL)) {
-		printk(KERN_DEBUG MYNAM "%s::mptctl_eventquery() @%d - ioc%d not found!\n",
-				__FILE__, __LINE__, iocnum);
-		return -ENODEV;
-	}
-
 	dctlprintk(ioc, printk(MYIOC_s_DEBUG_FMT "mptctl_eventquery called.\n",
 	    ioc->name));
 	karg.eventEntries = MPTCTL_EVENT_LOG_SIZE;
@@ -1610,12 +1556,10 @@ mptctl_eventquery (unsigned long arg)
 
 /*=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=*/
 static int
-mptctl_eventenable (unsigned long arg)
+mptctl_eventenable (MPT_ADAPTER *ioc, unsigned long arg)
 {
 	struct mpt_ioctl_eventenable __user *uarg = (void __user *) arg;
 	struct mpt_ioctl_eventenable	 karg;
-	MPT_ADAPTER *ioc;
-	int iocnum;
 
 	if (copy_from_user(&karg, uarg, sizeof(struct mpt_ioctl_eventenable))) {
 		printk(KERN_ERR MYNAM "%s@%d::mptctl_eventenable - "
@@ -1624,13 +1568,6 @@ mptctl_eventenable (unsigned long arg)
 		return -EFAULT;
 	}
 
-	if (((iocnum = mpt_verify_adapter(karg.hdr.iocnum, &ioc)) < 0) ||
-	    (ioc == NULL)) {
-		printk(KERN_DEBUG MYNAM "%s::mptctl_eventenable() @%d - ioc%d not found!\n",
-				__FILE__, __LINE__, iocnum);
-		return -ENODEV;
-	}
-
 	dctlprintk(ioc, printk(MYIOC_s_DEBUG_FMT "mptctl_eventenable called.\n",
 	    ioc->name));
 	if (ioc->events == NULL) {
@@ -1658,12 +1595,10 @@ mptctl_eventenable (unsigned long arg)
 
 /*=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=*/
 static int
-mptctl_eventreport (unsigned long arg)
+mptctl_eventreport (MPT_ADAPTER *ioc, unsigned long arg)
 {
 	struct mpt_ioctl_eventreport __user *uarg = (void __user *) arg;
 	struct mpt_ioctl_eventreport	 karg;
-	MPT_ADAPTER		 *ioc;
-	int			 iocnum;
 	int			 numBytes, maxEvents, max;
 
 	if (copy_from_user(&karg, uarg, sizeof(struct mpt_ioctl_eventreport))) {
@@ -1673,12 +1608,6 @@ mptctl_eventreport (unsigned long arg)
 		return -EFAULT;
 	}
 
-	if (((iocnum = mpt_verify_adapter(karg.hdr.iocnum, &ioc)) < 0) ||
-	    (ioc == NULL)) {
-		printk(KERN_DEBUG MYNAM "%s::mptctl_eventreport() @%d - ioc%d not found!\n",
-				__FILE__, __LINE__, iocnum);
-		return -ENODEV;
-	}
 	dctlprintk(ioc, printk(MYIOC_s_DEBUG_FMT "mptctl_eventreport called.\n",
 	    ioc->name));
 
@@ -1712,12 +1641,10 @@ mptctl_eventreport (unsigned long arg)
 
 /*=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=*/
 static int
-mptctl_replace_fw (unsigned long arg)
+mptctl_replace_fw (MPT_ADAPTER *ioc, unsigned long arg)
 {
 	struct mpt_ioctl_replace_fw __user *uarg = (void __user *) arg;
 	struct mpt_ioctl_replace_fw	 karg;
-	MPT_ADAPTER		 *ioc;
-	int			 iocnum;
 	int			 newFwSize;
 
 	if (copy_from_user(&karg, uarg, sizeof(struct mpt_ioctl_replace_fw))) {
@@ -1727,13 +1654,6 @@ mptctl_replace_fw (unsigned long arg)
 		return -EFAULT;
 	}
 
-	if (((iocnum = mpt_verify_adapter(karg.hdr.iocnum, &ioc)) < 0) ||
-	    (ioc == NULL)) {
-		printk(KERN_DEBUG MYNAM "%s::mptctl_replace_fw() @%d - ioc%d not found!\n",
-				__FILE__, __LINE__, iocnum);
-		return -ENODEV;
-	}
-
 	dctlprintk(ioc, printk(MYIOC_s_DEBUG_FMT "mptctl_replace_fw called.\n",
 	    ioc->name));
 	/* If caching FW, Free the old FW image
@@ -1780,12 +1700,10 @@ mptctl_replace_fw (unsigned long arg)
  *		-ENOMEM if memory allocation error
  */
 static int
-mptctl_mpt_command (unsigned long arg)
+mptctl_mpt_command (MPT_ADAPTER *ioc, unsigned long arg)
 {
 	struct mpt_ioctl_command __user *uarg = (void __user *) arg;
 	struct mpt_ioctl_command  karg;
-	MPT_ADAPTER	*ioc;
-	int		iocnum;
 	int		rc;
 
 
@@ -1796,14 +1714,7 @@ mptctl_mpt_command (unsigned long arg)
 		return -EFAULT;
 	}
 
-	if (((iocnum = mpt_verify_adapter(karg.hdr.iocnum, &ioc)) < 0) ||
-	    (ioc == NULL)) {
-		printk(KERN_DEBUG MYNAM "%s::mptctl_mpt_command() @%d - ioc%d not found!\n",
-				__FILE__, __LINE__, iocnum);
-		return -ENODEV;
-	}
-
-	rc = mptctl_do_mpt_command (karg, &uarg->MF);
+	rc = mptctl_do_mpt_command (ioc, karg, &uarg->MF);
 
 	return rc;
 }
@@ -1821,9 +1732,8 @@ mptctl_mpt_command (unsigned long arg)
  *		-EPERM if SCSI I/O and target is untagged
  */
 static int
-mptctl_do_mpt_command (struct mpt_ioctl_command karg, void __user *mfPtr)
+mptctl_do_mpt_command (MPT_ADAPTER *ioc, struct mpt_ioctl_command karg, void __user *mfPtr)
 {
-	MPT_ADAPTER	*ioc;
 	MPT_FRAME_HDR	*mf = NULL;
 	MPIHeader_t	*hdr;
 	char		*psge;
@@ -1832,7 +1742,7 @@ mptctl_do_mpt_command (struct mpt_ioctl_command karg, void __user *mfPtr)
 	dma_addr_t	dma_addr_in;
 	dma_addr_t	dma_addr_out;
 	int		sgSize = 0;	/* Num SG elements */
-	int		iocnum, flagsLength;
+	int		flagsLength;
 	int		sz, rc = 0;
 	int		msgContext;
 	u16		req_idx;
@@ -1847,13 +1757,6 @@ mptctl_do_mpt_command (struct mpt_ioctl_command karg, void __user *mfPtr)
 	bufIn.kptr = bufOut.kptr = NULL;
 	bufIn.len = bufOut.len = 0;
 
-	if (((iocnum = mpt_verify_adapter(karg.hdr.iocnum, &ioc)) < 0) ||
-	    (ioc == NULL)) {
-		printk(KERN_DEBUG MYNAM "%s::mptctl_do_mpt_command() @%d - ioc%d not found!\n",
-				__FILE__, __LINE__, iocnum);
-		return -ENODEV;
-	}
-
 	spin_lock_irqsave(&ioc->taskmgmt_lock, flags);
 	if (ioc->ioc_reset_in_progress) {
 		spin_unlock_irqrestore(&ioc->taskmgmt_lock, flags);
@@ -2418,17 +2321,15 @@ done_free_mem:
  *		-ENOMEM if memory allocation error
  */
 static int
-mptctl_hp_hostinfo(unsigned long arg, unsigned int data_size)
+mptctl_hp_hostinfo(MPT_ADAPTER *ioc, unsigned long arg, unsigned int data_size)
 {
 	hp_host_info_t	__user *uarg = (void __user *) arg;
-	MPT_ADAPTER		*ioc;
 	struct pci_dev		*pdev;
 	char                    *pbuf=NULL;
 	dma_addr_t		buf_dma;
 	hp_host_info_t		karg;
 	CONFIGPARMS		cfg;
 	ConfigPageHeader_t	hdr;
-	int			iocnum;
 	int			rc, cim_rev;
 	ToolboxIstwiReadWriteRequest_t	*IstwiRWRequest;
 	MPT_FRAME_HDR		*mf = NULL;
@@ -2452,12 +2353,6 @@ mptctl_hp_hostinfo(unsigned long arg, unsigned int data_size)
 		return -EFAULT;
 	}
 
-	if (((iocnum = mpt_verify_adapter(karg.hdr.iocnum, &ioc)) < 0) ||
-	    (ioc == NULL)) {
-		printk(KERN_DEBUG MYNAM "%s::mptctl_hp_hostinfo() @%d - ioc%d not found!\n",
-				__FILE__, __LINE__, iocnum);
-		return -ENODEV;
-	}
 	dctlprintk(ioc, printk(MYIOC_s_DEBUG_FMT ": mptctl_hp_hostinfo called.\n",
 	    ioc->name));
 
@@ -2659,15 +2554,13 @@ retry_wait:
  *		-ENOMEM if memory allocation error
  */
 static int
-mptctl_hp_targetinfo(unsigned long arg)
+mptctl_hp_targetinfo(MPT_ADAPTER *ioc, unsigned long arg)
 {
 	hp_target_info_t __user *uarg = (void __user *) arg;
 	SCSIDevicePage0_t	*pg0_alloc;
 	SCSIDevicePage3_t	*pg3_alloc;
-	MPT_ADAPTER		*ioc;
 	MPT_SCSI_HOST 		*hd = NULL;
 	hp_target_info_t	karg;
-	int			iocnum;
 	int			data_sz;
 	dma_addr_t		page_dma;
 	CONFIGPARMS	 	cfg;
@@ -2681,12 +2574,6 @@ mptctl_hp_targetinfo(unsigned long arg)
 		return -EFAULT;
 	}
 
-	if (((iocnum = mpt_verify_adapter(karg.hdr.iocnum, &ioc)) < 0) ||
-		(ioc == NULL)) {
-		printk(KERN_DEBUG MYNAM "%s::mptctl_hp_targetinfo() @%d - ioc%d not found!\n",
-				__FILE__, __LINE__, iocnum);
-		return -ENODEV;
-	}
 	if (karg.hdr.id >= MPT_MAX_FC_DEVICES)
 		return -EINVAL;
 	dctlprintk(ioc, printk(MYIOC_s_DEBUG_FMT "mptctl_hp_targetinfo called.\n",
@@ -2854,7 +2741,7 @@ compat_mptfwxfer_ioctl(struct file *filp, unsigned int cmd,
 	kfw.fwlen = kfw32.fwlen;
 	kfw.bufp = compat_ptr(kfw32.bufp);
 
-	ret = mptctl_do_fw_download(kfw.iocnum, kfw.bufp, kfw.fwlen);
+	ret = mptctl_do_fw_download(iocp, kfw.bufp, kfw.fwlen);
 
 	mutex_unlock(&iocp->ioctl_cmds.mutex);
 
@@ -2908,7 +2795,7 @@ compat_mpt_command(struct file *filp, unsigned int cmd,
 
 	/* Pass new structure to do_mpt_command
 	 */
-	ret = mptctl_do_mpt_command (karg, &uarg->MF);
+	ret = mptctl_do_mpt_command (iocp, karg, &uarg->MF);
 
 	mutex_unlock(&iocp->ioctl_cmds.mutex);
 
diff --git a/drivers/message/fusion/mptscsih.c b/drivers/message/fusion/mptscsih.c
index f0737c57ed5f..1491561d2e5c 100644
--- a/drivers/message/fusion/mptscsih.c
+++ b/drivers/message/fusion/mptscsih.c
@@ -118,8 +118,6 @@ int 		mptscsih_suspend(struct pci_dev *pdev, pm_message_t state);
 int 		mptscsih_resume(struct pci_dev *pdev);
 #endif
 
-#define SNS_LEN(scp)	SCSI_SENSE_BUFFERSIZE
-
 
 /*=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=*/
 /*
@@ -2422,7 +2420,7 @@ mptscsih_copy_sense_data(struct scsi_cmnd *sc, MPT_SCSI_HOST *hd, MPT_FRAME_HDR
 		/* Copy the sense received into the scsi command block. */
 		req_index = le16_to_cpu(mf->u.frame.hwhdr.msgctxu.fld.req_idx);
 		sense_data = ((u8 *)ioc->sense_buf_pool + (req_index * MPT_SENSE_BUFFER_ALLOC));
-		memcpy(sc->sense_buffer, sense_data, SNS_LEN(sc));
+		memcpy(sc->sense_buffer, sense_data, MPT_SENSE_BUFFER_ALLOC);
 
 		/* Log SMART data (asc = 0x5D, non-IM case only) if required.
 		 */
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index a17d275bf1d4..6610aa81da51 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -750,6 +750,7 @@ config MFD_MAX77650
 	depends on OF || COMPILE_TEST
 	select MFD_CORE
 	select REGMAP_I2C
+	select REGMAP_IRQ
 	help
 	  Say Y here to add support for Maxim Semiconductor MAX77650 and
 	  MAX77651 Power Management ICs. This is the core multifunction
diff --git a/drivers/mfd/arizona-core.c b/drivers/mfd/arizona-core.c
index 4a31907a4525..3ff872c205ee 100644
--- a/drivers/mfd/arizona-core.c
+++ b/drivers/mfd/arizona-core.c
@@ -1430,6 +1430,15 @@ err_irq:
 	arizona_irq_exit(arizona);
 err_pm:
 	pm_runtime_disable(arizona->dev);
+
+	switch (arizona->pdata.clk32k_src) {
+	case ARIZONA_32KZ_MCLK1:
+	case ARIZONA_32KZ_MCLK2:
+		arizona_clk32k_disable(arizona);
+		break;
+	default:
+		break;
+	}
 err_reset:
 	arizona_enable_reset(arizona);
 	regulator_disable(arizona->dcvdd);
@@ -1452,6 +1461,15 @@ int arizona_dev_exit(struct arizona *arizona)
 	regulator_disable(arizona->dcvdd);
 	regulator_put(arizona->dcvdd);
 
+	switch (arizona->pdata.clk32k_src) {
+	case ARIZONA_32KZ_MCLK1:
+	case ARIZONA_32KZ_MCLK2:
+		arizona_clk32k_disable(arizona);
+		break;
+	default:
+		break;
+	}
+
 	mfd_remove_devices(arizona->dev);
 	arizona_free_irq(arizona, ARIZONA_IRQ_UNDERCLOCKED, arizona);
 	arizona_free_irq(arizona, ARIZONA_IRQ_OVERCLOCKED, arizona);
diff --git a/drivers/mfd/axp20x.c b/drivers/mfd/axp20x.c
index a4aaadaa0cb0..aa59496e4376 100644
--- a/drivers/mfd/axp20x.c
+++ b/drivers/mfd/axp20x.c
@@ -126,7 +126,7 @@ static const struct regmap_range axp288_writeable_ranges[] = {
 static const struct regmap_range axp288_volatile_ranges[] = {
 	regmap_reg_range(AXP20X_PWR_INPUT_STATUS, AXP288_POWER_REASON),
 	regmap_reg_range(AXP288_BC_GLOBAL, AXP288_BC_GLOBAL),
-	regmap_reg_range(AXP288_BC_DET_STAT, AXP288_BC_DET_STAT),
+	regmap_reg_range(AXP288_BC_DET_STAT, AXP20X_VBUS_IPSOUT_MGMT),
 	regmap_reg_range(AXP20X_CHRG_BAK_CTRL, AXP20X_CHRG_BAK_CTRL),
 	regmap_reg_range(AXP20X_IRQ1_EN, AXP20X_IPSOUT_V_HIGH_L),
 	regmap_reg_range(AXP20X_TIMER_CTRL, AXP20X_TIMER_CTRL),
diff --git a/drivers/mfd/da9062-core.c b/drivers/mfd/da9062-core.c
index e69626867c26..9143de7b77b8 100644
--- a/drivers/mfd/da9062-core.c
+++ b/drivers/mfd/da9062-core.c
@@ -248,7 +248,7 @@ static const struct mfd_cell da9062_devs[] = {
 		.name		= "da9062-watchdog",
 		.num_resources	= ARRAY_SIZE(da9062_wdt_resources),
 		.resources	= da9062_wdt_resources,
-		.of_compatible  = "dlg,da9062-wdt",
+		.of_compatible  = "dlg,da9062-watchdog",
 	},
 	{
 		.name		= "da9062-thermal",
diff --git a/drivers/mfd/dln2.c b/drivers/mfd/dln2.c
index 381593fbe50f..707f4287ab4a 100644
--- a/drivers/mfd/dln2.c
+++ b/drivers/mfd/dln2.c
@@ -90,6 +90,11 @@ struct dln2_mod_rx_slots {
 	spinlock_t lock;
 };
 
+enum dln2_endpoint {
+	DLN2_EP_OUT	= 0,
+	DLN2_EP_IN	= 1,
+};
+
 struct dln2_dev {
 	struct usb_device *usb_dev;
 	struct usb_interface *interface;
@@ -282,7 +287,11 @@ static void dln2_rx(struct urb *urb)
 	len = urb->actual_length - sizeof(struct dln2_header);
 
 	if (handle == DLN2_HANDLE_EVENT) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&dln2->event_cb_lock, flags);
 		dln2_run_event_callbacks(dln2, id, echo, data, len);
+		spin_unlock_irqrestore(&dln2->event_cb_lock, flags);
 	} else {
 		/* URB will be re-submitted in _dln2_transfer (free_rx_slot) */
 		if (dln2_transfer_complete(dln2, urb, handle, echo))
@@ -722,6 +731,8 @@ static int dln2_probe(struct usb_interface *interface,
 		      const struct usb_device_id *usb_id)
 {
 	struct usb_host_interface *hostif = interface->cur_altsetting;
+	struct usb_endpoint_descriptor *epin;
+	struct usb_endpoint_descriptor *epout;
 	struct device *dev = &interface->dev;
 	struct dln2_dev *dln2;
 	int ret;
@@ -731,12 +742,19 @@ static int dln2_probe(struct usb_interface *interface,
 	    hostif->desc.bNumEndpoints < 2)
 		return -ENODEV;
 
+	epout = &hostif->endpoint[DLN2_EP_OUT].desc;
+	if (!usb_endpoint_is_bulk_out(epout))
+		return -ENODEV;
+	epin = &hostif->endpoint[DLN2_EP_IN].desc;
+	if (!usb_endpoint_is_bulk_in(epin))
+		return -ENODEV;
+
 	dln2 = kzalloc(sizeof(*dln2), GFP_KERNEL);
 	if (!dln2)
 		return -ENOMEM;
 
-	dln2->ep_out = hostif->endpoint[0].desc.bEndpointAddress;
-	dln2->ep_in = hostif->endpoint[1].desc.bEndpointAddress;
+	dln2->ep_out = epout->bEndpointAddress;
+	dln2->ep_in = epin->bEndpointAddress;
 	dln2->usb_dev = usb_get_dev(interface_to_usbdev(interface));
 	dln2->interface = interface;
 	usb_set_intfdata(interface, dln2);
diff --git a/drivers/mfd/intel-lpss-pci.c b/drivers/mfd/intel-lpss-pci.c
index 3c271b14e7c6..9ca78d4f7f3b 100644
--- a/drivers/mfd/intel-lpss-pci.c
+++ b/drivers/mfd/intel-lpss-pci.c
@@ -122,13 +122,25 @@ static const struct intel_lpss_platform_info apl_i2c_info = {
 	.properties = apl_i2c_properties,
 };
 
+static struct property_entry glk_i2c_properties[] = {
+	PROPERTY_ENTRY_U32("i2c-sda-hold-time-ns", 313),
+	PROPERTY_ENTRY_U32("i2c-sda-falling-time-ns", 171),
+	PROPERTY_ENTRY_U32("i2c-scl-falling-time-ns", 290),
+	{ },
+};
+
+static const struct intel_lpss_platform_info glk_i2c_info = {
+	.clk_rate = 133000000,
+	.properties = glk_i2c_properties,
+};
+
 static const struct intel_lpss_platform_info cnl_i2c_info = {
 	.clk_rate = 216000000,
 	.properties = spt_i2c_properties,
 };
 
 static const struct pci_device_id intel_lpss_pci_ids[] = {
-	/* CML */
+	/* CML-LP */
 	{ PCI_VDEVICE(INTEL, 0x02a8), (kernel_ulong_t)&spt_uart_info },
 	{ PCI_VDEVICE(INTEL, 0x02a9), (kernel_ulong_t)&spt_uart_info },
 	{ PCI_VDEVICE(INTEL, 0x02aa), (kernel_ulong_t)&spt_info },
@@ -141,6 +153,17 @@ static const struct pci_device_id intel_lpss_pci_ids[] = {
 	{ PCI_VDEVICE(INTEL, 0x02ea), (kernel_ulong_t)&cnl_i2c_info },
 	{ PCI_VDEVICE(INTEL, 0x02eb), (kernel_ulong_t)&cnl_i2c_info },
 	{ PCI_VDEVICE(INTEL, 0x02fb), (kernel_ulong_t)&spt_info },
+	/* CML-H */
+	{ PCI_VDEVICE(INTEL, 0x06a8), (kernel_ulong_t)&spt_uart_info },
+	{ PCI_VDEVICE(INTEL, 0x06a9), (kernel_ulong_t)&spt_uart_info },
+	{ PCI_VDEVICE(INTEL, 0x06aa), (kernel_ulong_t)&spt_info },
+	{ PCI_VDEVICE(INTEL, 0x06ab), (kernel_ulong_t)&spt_info },
+	{ PCI_VDEVICE(INTEL, 0x06c7), (kernel_ulong_t)&spt_uart_info },
+	{ PCI_VDEVICE(INTEL, 0x06e8), (kernel_ulong_t)&cnl_i2c_info },
+	{ PCI_VDEVICE(INTEL, 0x06e9), (kernel_ulong_t)&cnl_i2c_info },
+	{ PCI_VDEVICE(INTEL, 0x06ea), (kernel_ulong_t)&cnl_i2c_info },
+	{ PCI_VDEVICE(INTEL, 0x06eb), (kernel_ulong_t)&cnl_i2c_info },
+	{ PCI_VDEVICE(INTEL, 0x06fb), (kernel_ulong_t)&spt_info },
 	/* BXT A-Step */
 	{ PCI_VDEVICE(INTEL, 0x0aac), (kernel_ulong_t)&bxt_i2c_info },
 	{ PCI_VDEVICE(INTEL, 0x0aae), (kernel_ulong_t)&bxt_i2c_info },
@@ -174,14 +197,14 @@ static const struct pci_device_id intel_lpss_pci_ids[] = {
 	{ PCI_VDEVICE(INTEL, 0x1ac6), (kernel_ulong_t)&bxt_info },
 	{ PCI_VDEVICE(INTEL, 0x1aee), (kernel_ulong_t)&bxt_uart_info },
 	/* GLK */
-	{ PCI_VDEVICE(INTEL, 0x31ac), (kernel_ulong_t)&bxt_i2c_info },
-	{ PCI_VDEVICE(INTEL, 0x31ae), (kernel_ulong_t)&bxt_i2c_info },
-	{ PCI_VDEVICE(INTEL, 0x31b0), (kernel_ulong_t)&bxt_i2c_info },
-	{ PCI_VDEVICE(INTEL, 0x31b2), (kernel_ulong_t)&bxt_i2c_info },
-	{ PCI_VDEVICE(INTEL, 0x31b4), (kernel_ulong_t)&bxt_i2c_info },
-	{ PCI_VDEVICE(INTEL, 0x31b6), (kernel_ulong_t)&bxt_i2c_info },
-	{ PCI_VDEVICE(INTEL, 0x31b8), (kernel_ulong_t)&bxt_i2c_info },
-	{ PCI_VDEVICE(INTEL, 0x31ba), (kernel_ulong_t)&bxt_i2c_info },
+	{ PCI_VDEVICE(INTEL, 0x31ac), (kernel_ulong_t)&glk_i2c_info },
+	{ PCI_VDEVICE(INTEL, 0x31ae), (kernel_ulong_t)&glk_i2c_info },
+	{ PCI_VDEVICE(INTEL, 0x31b0), (kernel_ulong_t)&glk_i2c_info },
+	{ PCI_VDEVICE(INTEL, 0x31b2), (kernel_ulong_t)&glk_i2c_info },
+	{ PCI_VDEVICE(INTEL, 0x31b4), (kernel_ulong_t)&glk_i2c_info },
+	{ PCI_VDEVICE(INTEL, 0x31b6), (kernel_ulong_t)&glk_i2c_info },
+	{ PCI_VDEVICE(INTEL, 0x31b8), (kernel_ulong_t)&glk_i2c_info },
+	{ PCI_VDEVICE(INTEL, 0x31ba), (kernel_ulong_t)&glk_i2c_info },
 	{ PCI_VDEVICE(INTEL, 0x31bc), (kernel_ulong_t)&bxt_uart_info },
 	{ PCI_VDEVICE(INTEL, 0x31be), (kernel_ulong_t)&bxt_uart_info },
 	{ PCI_VDEVICE(INTEL, 0x31c0), (kernel_ulong_t)&bxt_uart_info },
diff --git a/drivers/mfd/intel-lpss.c b/drivers/mfd/intel-lpss.c
index a475cbd2b9ef..4afc1a0d1e78 100644
--- a/drivers/mfd/intel-lpss.c
+++ b/drivers/mfd/intel-lpss.c
@@ -395,7 +395,7 @@ int intel_lpss_probe(struct device *dev,
 	if (!lpss)
 		return -ENOMEM;
 
-	lpss->priv = devm_ioremap(dev, info->mem->start + LPSS_PRIV_OFFSET,
+	lpss->priv = devm_ioremap_uc(dev, info->mem->start + LPSS_PRIV_OFFSET,
 				  LPSS_PRIV_SIZE);
 	if (!lpss->priv)
 		return -ENOMEM;
diff --git a/drivers/mfd/rn5t618.c b/drivers/mfd/rn5t618.c
index da5cd9c92a59..ead2e79036a9 100644
--- a/drivers/mfd/rn5t618.c
+++ b/drivers/mfd/rn5t618.c
@@ -26,6 +26,7 @@ static bool rn5t618_volatile_reg(struct device *dev, unsigned int reg)
 	case RN5T618_WATCHDOGCNT:
 	case RN5T618_DCIRQ:
 	case RN5T618_ILIMDATAH ... RN5T618_AIN0DATAL:
+	case RN5T618_ADCCNT3:
 	case RN5T618_IR_ADC1 ... RN5T618_IR_ADC3:
 	case RN5T618_IR_GPR:
 	case RN5T618_IR_GPF:
diff --git a/drivers/mfd/stmfx.c b/drivers/mfd/stmfx.c
index 857991cb3cbb..711979afd90a 100644
--- a/drivers/mfd/stmfx.c
+++ b/drivers/mfd/stmfx.c
@@ -287,14 +287,21 @@ static int stmfx_irq_init(struct i2c_client *client)
 
 	ret = regmap_write(stmfx->map, STMFX_REG_IRQ_OUT_PIN, irqoutpin);
 	if (ret)
-		return ret;
+		goto irq_exit;
 
 	ret = devm_request_threaded_irq(stmfx->dev, client->irq,
 					NULL, stmfx_irq_handler,
 					irqtrigger | IRQF_ONESHOT,
 					"stmfx", stmfx);
 	if (ret)
-		stmfx_irq_exit(client);
+		goto irq_exit;
+
+	stmfx->irq = client->irq;
+
+	return 0;
+
+irq_exit:
+	stmfx_irq_exit(client);
 
 	return ret;
 }
@@ -481,6 +488,8 @@ static int stmfx_suspend(struct device *dev)
 	if (ret)
 		return ret;
 
+	disable_irq(stmfx->irq);
+
 	if (stmfx->vdd)
 		return regulator_disable(stmfx->vdd);
 
@@ -501,6 +510,13 @@ static int stmfx_resume(struct device *dev)
 		}
 	}
 
+	/* Reset STMFX - supply has been stopped during suspend */
+	ret = stmfx_chip_reset(stmfx);
+	if (ret) {
+		dev_err(stmfx->dev, "Failed to reset chip: %d\n", ret);
+		return ret;
+	}
+
 	ret = regmap_raw_write(stmfx->map, STMFX_REG_SYS_CTRL,
 			       &stmfx->bkp_sysctrl, sizeof(stmfx->bkp_sysctrl));
 	if (ret)
@@ -517,6 +533,8 @@ static int stmfx_resume(struct device *dev)
 	if (ret)
 		return ret;
 
+	enable_irq(stmfx->irq);
+
 	return 0;
 }
 #endif
diff --git a/drivers/mfd/wm8994-core.c b/drivers/mfd/wm8994-core.c
index 1e9fe7d92597..737dede4a95c 100644
--- a/drivers/mfd/wm8994-core.c
+++ b/drivers/mfd/wm8994-core.c
@@ -690,3 +690,4 @@ module_i2c_driver(wm8994_i2c_driver);
 MODULE_DESCRIPTION("Core support for the WM8994 audio CODEC");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Mark Brown <broonie@opensource.wolfsonmicro.com>");
+MODULE_SOFTDEP("pre: wm8994_regulator");
diff --git a/drivers/misc/altera-stapl/altera.c b/drivers/misc/altera-stapl/altera.c
index 25e5f24b3fec..5bdf57472314 100644
--- a/drivers/misc/altera-stapl/altera.c
+++ b/drivers/misc/altera-stapl/altera.c
@@ -2112,8 +2112,8 @@ exit_done:
 	return status;
 }
 
-static int altera_get_note(u8 *p, s32 program_size,
-			s32 *offset, char *key, char *value, int length)
+static int altera_get_note(u8 *p, s32 program_size, s32 *offset,
+			   char *key, char *value, int keylen, int vallen)
 /*
  * Gets key and value of NOTE fields in the JBC file.
  * Can be called in two modes:  if offset pointer is NULL,
@@ -2170,7 +2170,7 @@ static int altera_get_note(u8 *p, s32 program_size,
 						&p[note_table + (8 * i) + 4])];
 
 				if (value != NULL)
-					strlcpy(value, value_ptr, length);
+					strlcpy(value, value_ptr, vallen);
 
 			}
 		}
@@ -2189,13 +2189,13 @@ static int altera_get_note(u8 *p, s32 program_size,
 				strlcpy(key, &p[note_strings +
 						get_unaligned_be32(
 						&p[note_table + (8 * i)])],
-					length);
+					keylen);
 
 			if (value != NULL)
 				strlcpy(value, &p[note_strings +
 						get_unaligned_be32(
 						&p[note_table + (8 * i) + 4])],
-					length);
+					vallen);
 
 			*offset = i + 1;
 		}
@@ -2449,7 +2449,7 @@ int altera_init(struct altera_config *config, const struct firmware *fw)
 			__func__, (format_version == 2) ? "Jam STAPL" :
 						"pre-standardized Jam 1.1");
 		while (altera_get_note((u8 *)fw->data, fw->size,
-					&offset, key, value, 256) == 0)
+					&offset, key, value, 32, 256) == 0)
 			printk(KERN_INFO "%s: NOTE \"%s\" = \"%s\"\n",
 					__func__, key, value);
 	}
diff --git a/drivers/misc/atmel-ssc.c b/drivers/misc/atmel-ssc.c
index ab4144ea1f11..d6cd5537126c 100644
--- a/drivers/misc/atmel-ssc.c
+++ b/drivers/misc/atmel-ssc.c
@@ -10,7 +10,7 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/io.h>
-#include <linux/spinlock.h>
+#include <linux/mutex.h>
 #include <linux/atmel-ssc.h>
 #include <linux/slab.h>
 #include <linux/module.h>
@@ -20,7 +20,7 @@
 #include "../../sound/soc/atmel/atmel_ssc_dai.h"
 
 /* Serialize access to ssc_list and user count */
-static DEFINE_SPINLOCK(user_lock);
+static DEFINE_MUTEX(user_lock);
 static LIST_HEAD(ssc_list);
 
 struct ssc_device *ssc_request(unsigned int ssc_num)
@@ -28,7 +28,7 @@ struct ssc_device *ssc_request(unsigned int ssc_num)
 	int ssc_valid = 0;
 	struct ssc_device *ssc;
 
-	spin_lock(&user_lock);
+	mutex_lock(&user_lock);
 	list_for_each_entry(ssc, &ssc_list, list) {
 		if (ssc->pdev->dev.of_node) {
 			if (of_alias_get_id(ssc->pdev->dev.of_node, "ssc")
@@ -44,18 +44,18 @@ struct ssc_device *ssc_request(unsigned int ssc_num)
 	}
 
 	if (!ssc_valid) {
-		spin_unlock(&user_lock);
+		mutex_unlock(&user_lock);
 		pr_err("ssc: ssc%d platform device is missing\n", ssc_num);
 		return ERR_PTR(-ENODEV);
 	}
 
 	if (ssc->user) {
-		spin_unlock(&user_lock);
+		mutex_unlock(&user_lock);
 		dev_dbg(&ssc->pdev->dev, "module busy\n");
 		return ERR_PTR(-EBUSY);
 	}
 	ssc->user++;
-	spin_unlock(&user_lock);
+	mutex_unlock(&user_lock);
 
 	clk_prepare(ssc->clk);
 
@@ -67,14 +67,14 @@ void ssc_free(struct ssc_device *ssc)
 {
 	bool disable_clk = true;
 
-	spin_lock(&user_lock);
+	mutex_lock(&user_lock);
 	if (ssc->user)
 		ssc->user--;
 	else {
 		disable_clk = false;
 		dev_dbg(&ssc->pdev->dev, "device already free\n");
 	}
-	spin_unlock(&user_lock);
+	mutex_unlock(&user_lock);
 
 	if (disable_clk)
 		clk_unprepare(ssc->clk);
@@ -237,9 +237,9 @@ static int ssc_probe(struct platform_device *pdev)
 		return -ENXIO;
 	}
 
-	spin_lock(&user_lock);
+	mutex_lock(&user_lock);
 	list_add_tail(&ssc->list, &ssc_list);
-	spin_unlock(&user_lock);
+	mutex_unlock(&user_lock);
 
 	platform_set_drvdata(pdev, ssc);
 
@@ -258,9 +258,9 @@ static int ssc_remove(struct platform_device *pdev)
 
 	ssc_sound_dai_remove(ssc);
 
-	spin_lock(&user_lock);
+	mutex_lock(&user_lock);
 	list_del(&ssc->list);
-	spin_unlock(&user_lock);
+	mutex_unlock(&user_lock);
 
 	return 0;
 }
diff --git a/drivers/misc/cardreader/rts5227.c b/drivers/misc/cardreader/rts5227.c
index 4feed296a327..9d8fe08dbc75 100644
--- a/drivers/misc/cardreader/rts5227.c
+++ b/drivers/misc/cardreader/rts5227.c
@@ -395,6 +395,7 @@ void rts522a_init_params(struct rtsx_pcr *pcr)
 {
 	rts5227_init_params(pcr);
 
+	pcr->ops = &rts522a_pcr_ops;
 	pcr->reg_pm_ctrl3 = RTS522A_PM_CTRL3;
 
 	pcr->option.ocp_en = 1;
diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c
index b4a66b64f742..1958833b3b74 100644
--- a/drivers/misc/cardreader/rtsx_pcr.c
+++ b/drivers/misc/cardreader/rtsx_pcr.c
@@ -143,6 +143,9 @@ static void rtsx_comm_pm_full_on(struct rtsx_pcr *pcr)
 
 	rtsx_disable_aspm(pcr);
 
+	/* Fixes DMA transfer timout issue after disabling ASPM on RTS5260 */
+	msleep(1);
+
 	if (option->ltr_enabled)
 		rtsx_set_ltr_latency(pcr, option->ltr_active_latency);
 
diff --git a/drivers/misc/cxl/sysfs.c b/drivers/misc/cxl/sysfs.c
index f0263d1a1fdf..d97a243ad30c 100644
--- a/drivers/misc/cxl/sysfs.c
+++ b/drivers/misc/cxl/sysfs.c
@@ -624,7 +624,7 @@ static struct afu_config_record *cxl_sysfs_afu_new_cr(struct cxl_afu *afu, int c
 	rc = kobject_init_and_add(&cr->kobj, &afu_config_record_type,
 				  &afu->dev.kobj, "cr%i", cr->cr);
 	if (rc)
-		goto err;
+		goto err1;
 
 	rc = sysfs_create_bin_file(&cr->kobj, &cr->config_attr);
 	if (rc)
diff --git a/drivers/misc/enclosure.c b/drivers/misc/enclosure.c
index 6d27ccfe0680..3c2d405bc79b 100644
--- a/drivers/misc/enclosure.c
+++ b/drivers/misc/enclosure.c
@@ -406,10 +406,9 @@ int enclosure_remove_device(struct enclosure_device *edev, struct device *dev)
 		cdev = &edev->component[i];
 		if (cdev->dev == dev) {
 			enclosure_remove_links(cdev);
-			device_del(&cdev->cdev);
 			put_device(dev);
 			cdev->dev = NULL;
-			return device_add(&cdev->cdev);
+			return 0;
 		}
 	}
 	return -ENODEV;
diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index 90c7e59e461d..8e10b4aa60d0 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -857,6 +857,7 @@ static int fastrpc_invoke_send(struct fastrpc_session_ctx *sctx,
 	struct fastrpc_channel_ctx *cctx;
 	struct fastrpc_user *fl = ctx->fl;
 	struct fastrpc_msg *msg = &ctx->msg;
+	int ret;
 
 	cctx = fl->cctx;
 	msg->pid = fl->tgid;
@@ -872,7 +873,13 @@ static int fastrpc_invoke_send(struct fastrpc_session_ctx *sctx,
 	msg->size = roundup(ctx->msg_sz, PAGE_SIZE);
 	fastrpc_context_get(ctx);
 
-	return rpmsg_send(cctx->rpdev->ept, (void *)msg, sizeof(*msg));
+	ret = rpmsg_send(cctx->rpdev->ept, (void *)msg, sizeof(*msg));
+
+	if (ret)
+		fastrpc_context_put(ctx);
+
+	return ret;
+
 }
 
 static int fastrpc_internal_invoke(struct fastrpc_user *fl,  u32 kernel,
diff --git a/drivers/misc/habanalabs/command_submission.c b/drivers/misc/habanalabs/command_submission.c
index 6fe785e26859..52fd0229c4f7 100644
--- a/drivers/misc/habanalabs/command_submission.c
+++ b/drivers/misc/habanalabs/command_submission.c
@@ -764,8 +764,9 @@ int hl_cs_wait_ioctl(struct hl_fpriv *hpriv, void *data)
 	memset(args, 0, sizeof(*args));
 
 	if (rc < 0) {
-		dev_err(hdev->dev, "Error %ld on waiting for CS handle %llu\n",
-			rc, seq);
+		dev_err_ratelimited(hdev->dev,
+				"Error %ld on waiting for CS handle %llu\n",
+				rc, seq);
 		if (rc == -ERESTARTSYS) {
 			args->out.status = HL_WAIT_CS_STATUS_INTERRUPTED;
 			rc = -EINTR;
diff --git a/drivers/misc/habanalabs/context.c b/drivers/misc/habanalabs/context.c
index f4c92f110a72..4d5a0454208e 100644
--- a/drivers/misc/habanalabs/context.c
+++ b/drivers/misc/habanalabs/context.c
@@ -159,7 +159,7 @@ struct dma_fence *hl_ctx_get_fence(struct hl_ctx *ctx, u64 seq)
 	spin_lock(&ctx->cs_lock);
 
 	if (seq >= ctx->cs_sequence) {
-		dev_notice(hdev->dev,
+		dev_notice_ratelimited(hdev->dev,
 			"Can't wait on seq %llu because current CS is at seq %llu\n",
 			seq, ctx->cs_sequence);
 		spin_unlock(&ctx->cs_lock);
diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c
index 0b19d3eefb98..065cb7f127fb 100644
--- a/drivers/misc/habanalabs/device.c
+++ b/drivers/misc/habanalabs/device.c
@@ -934,6 +934,7 @@ int hl_device_init(struct hl_device *hdev, struct class *hclass)
 	if (hdev->asic_funcs->get_hw_state(hdev) == HL_DEVICE_HW_STATE_DIRTY) {
 		dev_info(hdev->dev,
 			"H/W state is dirty, must reset before initializing\n");
+		hdev->asic_funcs->halt_engines(hdev, true);
 		hdev->asic_funcs->hw_fini(hdev, true);
 	}
 
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index ac6b252a1ddc..86f7b6dcfa76 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -826,6 +826,11 @@ void goya_init_dma_qmans(struct hl_device *hdev)
  */
 static void goya_disable_external_queues(struct hl_device *hdev)
 {
+	struct goya_device *goya = hdev->asic_specific;
+
+	if (!(goya->hw_cap_initialized & HW_CAP_DMA))
+		return;
+
 	WREG32(mmDMA_QM_0_GLBL_CFG0, 0);
 	WREG32(mmDMA_QM_1_GLBL_CFG0, 0);
 	WREG32(mmDMA_QM_2_GLBL_CFG0, 0);
@@ -887,6 +892,11 @@ static int goya_stop_external_queues(struct hl_device *hdev)
 {
 	int rc, retval = 0;
 
+	struct goya_device *goya = hdev->asic_specific;
+
+	if (!(goya->hw_cap_initialized & HW_CAP_DMA))
+		return retval;
+
 	rc = goya_stop_queue(hdev,
 			mmDMA_QM_0_GLBL_CFG1,
 			mmDMA_QM_0_CP_STS,
@@ -1678,9 +1688,18 @@ void goya_init_tpc_qmans(struct hl_device *hdev)
  */
 static void goya_disable_internal_queues(struct hl_device *hdev)
 {
+	struct goya_device *goya = hdev->asic_specific;
+
+	if (!(goya->hw_cap_initialized & HW_CAP_MME))
+		goto disable_tpc;
+
 	WREG32(mmMME_QM_GLBL_CFG0, 0);
 	WREG32(mmMME_CMDQ_GLBL_CFG0, 0);
 
+disable_tpc:
+	if (!(goya->hw_cap_initialized & HW_CAP_TPC))
+		return;
+
 	WREG32(mmTPC0_QM_GLBL_CFG0, 0);
 	WREG32(mmTPC0_CMDQ_GLBL_CFG0, 0);
 
@@ -1716,8 +1735,12 @@ static void goya_disable_internal_queues(struct hl_device *hdev)
  */
 static int goya_stop_internal_queues(struct hl_device *hdev)
 {
+	struct goya_device *goya = hdev->asic_specific;
 	int rc, retval = 0;
 
+	if (!(goya->hw_cap_initialized & HW_CAP_MME))
+		goto stop_tpc;
+
 	/*
 	 * Each queue (QMAN) is a separate H/W logic. That means that each
 	 * QMAN can be stopped independently and failure to stop one does NOT
@@ -1744,6 +1767,10 @@ static int goya_stop_internal_queues(struct hl_device *hdev)
 		retval = -EIO;
 	}
 
+stop_tpc:
+	if (!(goya->hw_cap_initialized & HW_CAP_TPC))
+		return retval;
+
 	rc = goya_stop_queue(hdev,
 			mmTPC0_QM_GLBL_CFG1,
 			mmTPC0_QM_CP_STS,
@@ -1909,6 +1936,11 @@ static int goya_stop_internal_queues(struct hl_device *hdev)
 
 static void goya_dma_stall(struct hl_device *hdev)
 {
+	struct goya_device *goya = hdev->asic_specific;
+
+	if (!(goya->hw_cap_initialized & HW_CAP_DMA))
+		return;
+
 	WREG32(mmDMA_QM_0_GLBL_CFG1, 1 << DMA_QM_0_GLBL_CFG1_DMA_STOP_SHIFT);
 	WREG32(mmDMA_QM_1_GLBL_CFG1, 1 << DMA_QM_1_GLBL_CFG1_DMA_STOP_SHIFT);
 	WREG32(mmDMA_QM_2_GLBL_CFG1, 1 << DMA_QM_2_GLBL_CFG1_DMA_STOP_SHIFT);
@@ -1918,6 +1950,11 @@ static void goya_dma_stall(struct hl_device *hdev)
 
 static void goya_tpc_stall(struct hl_device *hdev)
 {
+	struct goya_device *goya = hdev->asic_specific;
+
+	if (!(goya->hw_cap_initialized & HW_CAP_TPC))
+		return;
+
 	WREG32(mmTPC0_CFG_TPC_STALL, 1 << TPC0_CFG_TPC_STALL_V_SHIFT);
 	WREG32(mmTPC1_CFG_TPC_STALL, 1 << TPC1_CFG_TPC_STALL_V_SHIFT);
 	WREG32(mmTPC2_CFG_TPC_STALL, 1 << TPC2_CFG_TPC_STALL_V_SHIFT);
@@ -1930,6 +1967,11 @@ static void goya_tpc_stall(struct hl_device *hdev)
 
 static void goya_mme_stall(struct hl_device *hdev)
 {
+	struct goya_device *goya = hdev->asic_specific;
+
+	if (!(goya->hw_cap_initialized & HW_CAP_MME))
+		return;
+
 	WREG32(mmMME_STALL, 0xFFFFFFFF);
 }
 
@@ -2107,7 +2149,7 @@ static int goya_push_linux_to_device(struct hl_device *hdev)
 
 static int goya_pldm_init_cpu(struct hl_device *hdev)
 {
-	u32 val, unit_rst_val;
+	u32 unit_rst_val;
 	int rc;
 
 	/* Must initialize SRAM scrambler before pushing u-boot to SRAM */
@@ -2115,14 +2157,14 @@ static int goya_pldm_init_cpu(struct hl_device *hdev)
 
 	/* Put ARM cores into reset */
 	WREG32(mmCPU_CA53_CFG_ARM_RST_CONTROL, CPU_RESET_ASSERT);
-	val = RREG32(mmCPU_CA53_CFG_ARM_RST_CONTROL);
+	RREG32(mmCPU_CA53_CFG_ARM_RST_CONTROL);
 
 	/* Reset the CA53 MACRO */
 	unit_rst_val = RREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N);
 	WREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N, CA53_RESET);
-	val = RREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N);
+	RREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N);
 	WREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N, unit_rst_val);
-	val = RREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N);
+	RREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N);
 
 	rc = goya_push_uboot_to_device(hdev);
 	if (rc)
@@ -2143,7 +2185,7 @@ static int goya_pldm_init_cpu(struct hl_device *hdev)
 	/* Release ARM core 0 from reset */
 	WREG32(mmCPU_CA53_CFG_ARM_RST_CONTROL,
 					CPU_RESET_CORE0_DEASSERT);
-	val = RREG32(mmCPU_CA53_CFG_ARM_RST_CONTROL);
+	RREG32(mmCPU_CA53_CFG_ARM_RST_CONTROL);
 
 	return 0;
 }
@@ -2411,13 +2453,12 @@ err:
 static int goya_hw_init(struct hl_device *hdev)
 {
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
-	u32 val;
 	int rc;
 
 	dev_info(hdev->dev, "Starting initialization of H/W\n");
 
 	/* Perform read from the device to make sure device is up */
-	val = RREG32(mmPCIE_DBI_DEVICE_ID_VENDOR_ID_REG);
+	RREG32(mmPCIE_DBI_DEVICE_ID_VENDOR_ID_REG);
 
 	/*
 	 * Let's mark in the H/W that we have reached this point. We check
@@ -2486,7 +2527,7 @@ static int goya_hw_init(struct hl_device *hdev)
 	}
 
 	/* Perform read from the device to flush all MSI-X configuration */
-	val = RREG32(mmPCIE_DBI_DEVICE_ID_VENDOR_ID_REG);
+	RREG32(mmPCIE_DBI_DEVICE_ID_VENDOR_ID_REG);
 
 	return 0;
 
@@ -4491,8 +4532,6 @@ static int goya_memset_device_memory(struct hl_device *hdev, u64 addr, u32 size,
 
 	rc = goya_send_job_on_qman0(hdev, job);
 
-	hl_cb_put(job->patched_cb);
-
 	hl_debugfs_remove_job(hdev, job);
 	kfree(job);
 	cb->cs_cnt--;
diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h
index d56ab65d5b2a..43fef59d1bce 100644
--- a/drivers/misc/habanalabs/habanalabs.h
+++ b/drivers/misc/habanalabs/habanalabs.h
@@ -23,7 +23,7 @@
 
 #define HL_MMAP_CB_MASK			(0x8000000000000000ull >> PAGE_SHIFT)
 
-#define HL_PENDING_RESET_PER_SEC	5
+#define HL_PENDING_RESET_PER_SEC	30
 
 #define HL_DEVICE_TIMEOUT_USEC		1000000 /* 1 s */
 
diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c
index 53bb394ccba6..cef97a7eb8b6 100644
--- a/drivers/misc/mei/bus.c
+++ b/drivers/misc/mei/bus.c
@@ -745,9 +745,8 @@ static int mei_cl_device_remove(struct device *dev)
 
 	mei_cl_bus_module_put(cldev);
 	module_put(THIS_MODULE);
-	dev->driver = NULL;
-	return ret;
 
+	return ret;
 }
 
 static ssize_t name_show(struct device *dev, struct device_attribute *a,
diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c
index 1e3edbbacb1e..c6b163060c76 100644
--- a/drivers/misc/mei/client.c
+++ b/drivers/misc/mei/client.c
@@ -266,6 +266,7 @@ void mei_me_cl_rm_by_uuid(struct mei_device *dev, const uuid_le *uuid)
 	down_write(&dev->me_clients_rwsem);
 	me_cl = __mei_me_cl_by_uuid(dev, uuid);
 	__mei_me_cl_del(dev, me_cl);
+	mei_me_cl_put(me_cl);
 	up_write(&dev->me_clients_rwsem);
 }
 
@@ -287,6 +288,7 @@ void mei_me_cl_rm_by_uuid_id(struct mei_device *dev, const uuid_le *uuid, u8 id)
 	down_write(&dev->me_clients_rwsem);
 	me_cl = __mei_me_cl_by_uuid_id(dev, uuid, id);
 	__mei_me_cl_del(dev, me_cl);
+	mei_me_cl_put(me_cl);
 	up_write(&dev->me_clients_rwsem);
 }
 
diff --git a/drivers/misc/mei/hdcp/mei_hdcp.c b/drivers/misc/mei/hdcp/mei_hdcp.c
index b07000202d4a..778f9c4f3281 100644
--- a/drivers/misc/mei/hdcp/mei_hdcp.c
+++ b/drivers/misc/mei/hdcp/mei_hdcp.c
@@ -761,11 +761,38 @@ static const struct component_master_ops mei_component_master_ops = {
 	.unbind = mei_component_master_unbind,
 };
 
+/**
+ * mei_hdcp_component_match - compare function for matching mei hdcp.
+ *
+ *    The function checks if the driver is i915, the subcomponent is HDCP
+ *    and the grand parent of hdcp and the parent of i915 are the same
+ *    PCH device.
+ *
+ * @dev: master device
+ * @subcomponent: subcomponent to match (I915_COMPONENT_HDCP)
+ * @data: compare data (mei hdcp device)
+ *
+ * Return:
+ * * 1 - if components match
+ * * 0 - otherwise
+ */
 static int mei_hdcp_component_match(struct device *dev, int subcomponent,
 				    void *data)
 {
-	return !strcmp(dev->driver->name, "i915") &&
-	       subcomponent == I915_COMPONENT_HDCP;
+	struct device *base = data;
+
+	if (strcmp(dev->driver->name, "i915") ||
+	    subcomponent != I915_COMPONENT_HDCP)
+		return 0;
+
+	base = base->parent;
+	if (!base)
+		return 0;
+
+	base = base->parent;
+	dev = dev->parent;
+
+	return (base && dev && dev == base);
 }
 
 static int mei_hdcp_probe(struct mei_cl_device *cldev,
@@ -789,7 +816,7 @@ static int mei_hdcp_probe(struct mei_cl_device *cldev,
 
 	master_match = NULL;
 	component_match_add_typed(&cldev->dev, &master_match,
-				  mei_hdcp_component_match, comp_master);
+				  mei_hdcp_component_match, &cldev->dev);
 	if (IS_ERR_OR_NULL(master_match)) {
 		ret = -ENOMEM;
 		goto err_exit;
diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h
index b359f06f05e7..e56dc4754064 100644
--- a/drivers/misc/mei/hw-me-regs.h
+++ b/drivers/misc/mei/hw-me-regs.h
@@ -81,8 +81,14 @@
 
 #define MEI_DEV_ID_CMP_LP     0x02e0  /* Comet Point LP */
 #define MEI_DEV_ID_CMP_LP_3   0x02e4  /* Comet Point LP 3 (iTouch) */
+
 #define MEI_DEV_ID_CMP_V      0xA3BA  /* Comet Point Lake V */
 
+#define MEI_DEV_ID_CMP_H      0x06e0  /* Comet Lake H */
+#define MEI_DEV_ID_CMP_H_3    0x06e4  /* Comet Lake H 3 (iTouch) */
+
+#define MEI_DEV_ID_CDF        0x18D3  /* Cedar Fork */
+
 #define MEI_DEV_ID_ICP_LP     0x34E0  /* Ice Lake Point LP */
 
 #define MEI_DEV_ID_TGP_LP     0xA0E0  /* Tiger Lake Point LP */
diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c
index b1c518abc10e..3c2cbc1c114e 100644
--- a/drivers/misc/mei/pci-me.c
+++ b/drivers/misc/mei/pci-me.c
@@ -99,6 +99,8 @@ static const struct pci_device_id mei_me_pci_tbl[] = {
 	{MEI_PCI_DEVICE(MEI_DEV_ID_CMP_LP, MEI_ME_PCH12_CFG)},
 	{MEI_PCI_DEVICE(MEI_DEV_ID_CMP_LP_3, MEI_ME_PCH8_CFG)},
 	{MEI_PCI_DEVICE(MEI_DEV_ID_CMP_V, MEI_ME_PCH12_CFG)},
+	{MEI_PCI_DEVICE(MEI_DEV_ID_CMP_H, MEI_ME_PCH12_CFG)},
+	{MEI_PCI_DEVICE(MEI_DEV_ID_CMP_H_3, MEI_ME_PCH8_CFG)},
 
 	{MEI_PCI_DEVICE(MEI_DEV_ID_ICP_LP, MEI_ME_PCH12_CFG)},
 
@@ -107,6 +109,8 @@ static const struct pci_device_id mei_me_pci_tbl[] = {
 	{MEI_PCI_DEVICE(MEI_DEV_ID_MCC, MEI_ME_PCH12_CFG)},
 	{MEI_PCI_DEVICE(MEI_DEV_ID_MCC_4, MEI_ME_PCH8_CFG)},
 
+	{MEI_PCI_DEVICE(MEI_DEV_ID_CDF, MEI_ME_PCH8_CFG)},
+
 	/* required last entry */
 	{0, }
 };
diff --git a/drivers/misc/ocxl/context.c b/drivers/misc/ocxl/context.c
index bab9c9364184..425bec7b140c 100644
--- a/drivers/misc/ocxl/context.c
+++ b/drivers/misc/ocxl/context.c
@@ -10,18 +10,17 @@ int ocxl_context_alloc(struct ocxl_context **context, struct ocxl_afu *afu,
 	int pasid;
 	struct ocxl_context *ctx;
 
-	*context = kzalloc(sizeof(struct ocxl_context), GFP_KERNEL);
-	if (!*context)
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
 		return -ENOMEM;
 
-	ctx = *context;
-
 	ctx->afu = afu;
 	mutex_lock(&afu->contexts_lock);
 	pasid = idr_alloc(&afu->contexts_idr, ctx, afu->pasid_base,
 			afu->pasid_base + afu->pasid_max, GFP_KERNEL);
 	if (pasid < 0) {
 		mutex_unlock(&afu->contexts_lock);
+		kfree(ctx);
 		return pasid;
 	}
 	afu->pasid_count++;
@@ -43,6 +42,7 @@ int ocxl_context_alloc(struct ocxl_context **context, struct ocxl_afu *afu,
 	 * duration of the life of the context
 	 */
 	ocxl_afu_get(afu);
+	*context = ctx;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ocxl_context_alloc);
diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c
index 6765f10837ac..ca946d149851 100644
--- a/drivers/misc/pci_endpoint_test.c
+++ b/drivers/misc/pci_endpoint_test.c
@@ -98,6 +98,7 @@ struct pci_endpoint_test {
 	struct completion irq_raised;
 	int		last_irq;
 	int		num_irqs;
+	int		irq_type;
 	/* mutex to protect the ioctls */
 	struct mutex	mutex;
 	struct miscdevice miscdev;
@@ -157,6 +158,7 @@ static void pci_endpoint_test_free_irq_vectors(struct pci_endpoint_test *test)
 	struct pci_dev *pdev = test->pdev;
 
 	pci_free_irq_vectors(pdev);
+	test->irq_type = IRQ_TYPE_UNDEFINED;
 }
 
 static bool pci_endpoint_test_alloc_irq_vectors(struct pci_endpoint_test *test,
@@ -191,6 +193,8 @@ static bool pci_endpoint_test_alloc_irq_vectors(struct pci_endpoint_test *test,
 		irq = 0;
 		res = false;
 	}
+
+	test->irq_type = type;
 	test->num_irqs = irq;
 
 	return res;
@@ -330,6 +334,7 @@ static bool pci_endpoint_test_copy(struct pci_endpoint_test *test, size_t size)
 	dma_addr_t orig_dst_phys_addr;
 	size_t offset;
 	size_t alignment = test->alignment;
+	int irq_type = test->irq_type;
 	u32 src_crc32;
 	u32 dst_crc32;
 
@@ -426,6 +431,7 @@ static bool pci_endpoint_test_write(struct pci_endpoint_test *test, size_t size)
 	dma_addr_t orig_phys_addr;
 	size_t offset;
 	size_t alignment = test->alignment;
+	int irq_type = test->irq_type;
 	u32 crc32;
 
 	if (size > SIZE_MAX - alignment)
@@ -494,6 +500,7 @@ static bool pci_endpoint_test_read(struct pci_endpoint_test *test, size_t size)
 	dma_addr_t orig_phys_addr;
 	size_t offset;
 	size_t alignment = test->alignment;
+	int irq_type = test->irq_type;
 	u32 crc32;
 
 	if (size > SIZE_MAX - alignment)
@@ -555,7 +562,7 @@ static bool pci_endpoint_test_set_irq(struct pci_endpoint_test *test,
 		return false;
 	}
 
-	if (irq_type == req_irq_type)
+	if (test->irq_type == req_irq_type)
 		return true;
 
 	pci_endpoint_test_release_irq(test);
@@ -567,12 +574,10 @@ static bool pci_endpoint_test_set_irq(struct pci_endpoint_test *test,
 	if (!pci_endpoint_test_request_irq(test))
 		goto err;
 
-	irq_type = req_irq_type;
 	return true;
 
 err:
 	pci_endpoint_test_free_irq_vectors(test);
-	irq_type = IRQ_TYPE_UNDEFINED;
 	return false;
 }
 
@@ -633,7 +638,7 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
 {
 	int err;
 	int id;
-	char name[20];
+	char name[24];
 	enum pci_barno bar;
 	void __iomem *base;
 	struct device *dev = &pdev->dev;
@@ -652,6 +657,7 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
 	test->test_reg_bar = 0;
 	test->alignment = 0;
 	test->pdev = pdev;
+	test->irq_type = IRQ_TYPE_UNDEFINED;
 
 	if (no_msi)
 		irq_type = IRQ_TYPE_LEGACY;
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 95b41c0891d0..7f480c6b1981 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -1417,6 +1417,7 @@ static void mmc_blk_cqe_complete_rq(struct mmc_queue *mq, struct request *req)
 	struct mmc_request *mrq = &mqrq->brq.mrq;
 	struct request_queue *q = req->q;
 	struct mmc_host *host = mq->card->host;
+	enum mmc_issue_type issue_type = mmc_issue_type(mq, req);
 	unsigned long flags;
 	bool put_card;
 	int err;
@@ -1446,7 +1447,7 @@ static void mmc_blk_cqe_complete_rq(struct mmc_queue *mq, struct request *req)
 
 	spin_lock_irqsave(&mq->lock, flags);
 
-	mq->in_flight[mmc_issue_type(mq, req)] -= 1;
+	mq->in_flight[issue_type] -= 1;
 
 	put_card = (mmc_tot_in_flight(mq) == 0);
 
@@ -2474,8 +2475,8 @@ static int mmc_rpmb_chrdev_release(struct inode *inode, struct file *filp)
 	struct mmc_rpmb_data *rpmb = container_of(inode->i_cdev,
 						  struct mmc_rpmb_data, chrdev);
 
-	put_device(&rpmb->dev);
 	mmc_blk_put(rpmb->md);
+	put_device(&rpmb->dev);
 
 	return 0;
 }
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 221127324709..6db0efde7429 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -1733,8 +1733,11 @@ static int mmc_do_erase(struct mmc_card *card, unsigned int from,
 	 * the erase operation does not exceed the max_busy_timeout, we should
 	 * use R1B response. Or we need to prevent the host from doing hw busy
 	 * detection, which is done by converting to a R1 response instead.
+	 * Note, some hosts requires R1B, which also means they are on their own
+	 * when it comes to deal with the busy timeout.
 	 */
-	if (card->host->max_busy_timeout &&
+	if (!(card->host->caps & MMC_CAP_NEED_RSP_BUSY) &&
+	    card->host->max_busy_timeout &&
 	    busy_timeout > card->host->max_busy_timeout) {
 		cmd.flags = MMC_RSP_SPI_R1 | MMC_RSP_R1 | MMC_CMD_AC;
 	} else {
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index 105b7a7c0251..b3484def0a8b 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -176,7 +176,6 @@ int mmc_of_parse(struct mmc_host *host)
 	u32 bus_width, drv_type, cd_debounce_delay_ms;
 	int ret;
 	bool cd_cap_invert, cd_gpio_invert = false;
-	bool ro_cap_invert, ro_gpio_invert = false;
 
 	if (!dev || !dev_fwnode(dev))
 		return 0;
@@ -255,9 +254,11 @@ int mmc_of_parse(struct mmc_host *host)
 	}
 
 	/* Parse Write Protection */
-	ro_cap_invert = device_property_read_bool(dev, "wp-inverted");
 
-	ret = mmc_gpiod_request_ro(host, "wp", 0, 0, &ro_gpio_invert);
+	if (device_property_read_bool(dev, "wp-inverted"))
+		host->caps2 |= MMC_CAP2_RO_ACTIVE_HIGH;
+
+	ret = mmc_gpiod_request_ro(host, "wp", 0, 0, NULL);
 	if (!ret)
 		dev_info(host->parent, "Got WP GPIO\n");
 	else if (ret != -ENOENT && ret != -ENOSYS)
@@ -266,10 +267,6 @@ int mmc_of_parse(struct mmc_host *host)
 	if (device_property_read_bool(dev, "disable-wp"))
 		host->caps2 |= MMC_CAP2_NO_WRITE_PROTECT;
 
-	/* See the comment on CD inversion above */
-	if (ro_cap_invert ^ ro_gpio_invert)
-		host->caps2 |= MMC_CAP2_RO_ACTIVE_HIGH;
-
 	if (device_property_read_bool(dev, "cap-sd-highspeed"))
 		host->caps |= MMC_CAP_SD_HIGHSPEED;
 	if (device_property_read_bool(dev, "cap-mmc-highspeed"))
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index c8804895595f..b7159e243323 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1911,9 +1911,12 @@ static int mmc_sleep(struct mmc_host *host)
 	 * If the max_busy_timeout of the host is specified, validate it against
 	 * the sleep cmd timeout. A failure means we need to prevent the host
 	 * from doing hw busy detection, which is done by converting to a R1
-	 * response instead of a R1B.
+	 * response instead of a R1B. Note, some hosts requires R1B, which also
+	 * means they are on their own when it comes to deal with the busy
+	 * timeout.
 	 */
-	if (host->max_busy_timeout && (timeout_ms > host->max_busy_timeout)) {
+	if (!(host->caps & MMC_CAP_NEED_RSP_BUSY) && host->max_busy_timeout &&
+	    (timeout_ms > host->max_busy_timeout)) {
 		cmd.flags = MMC_RSP_R1 | MMC_CMD_AC;
 	} else {
 		cmd.flags = MMC_RSP_R1B | MMC_CMD_AC;
diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c
index 09113b9ad679..18a7afb2a5b2 100644
--- a/drivers/mmc/core/mmc_ops.c
+++ b/drivers/mmc/core/mmc_ops.c
@@ -538,10 +538,12 @@ int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 	 * If the cmd timeout and the max_busy_timeout of the host are both
 	 * specified, let's validate them. A failure means we need to prevent
 	 * the host from doing hw busy detection, which is done by converting
-	 * to a R1 response instead of a R1B.
+	 * to a R1 response instead of a R1B. Note, some hosts requires R1B,
+	 * which also means they are on their own when it comes to deal with the
+	 * busy timeout.
 	 */
-	if (timeout_ms && host->max_busy_timeout &&
-		(timeout_ms > host->max_busy_timeout))
+	if (!(host->caps & MMC_CAP_NEED_RSP_BUSY) && timeout_ms &&
+	    host->max_busy_timeout && (timeout_ms > host->max_busy_timeout))
 		use_r1b_resp = false;
 
 	cmd.opcode = MMC_SWITCH;
diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
index 245a6fd668c8..15c76ba035fc 100644
--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -105,11 +105,10 @@ static enum blk_eh_timer_return mmc_cqe_timed_out(struct request *req)
 	case MMC_ISSUE_DCMD:
 		if (host->cqe_ops->cqe_timeout(host, mrq, &recovery_needed)) {
 			if (recovery_needed)
-				__mmc_cqe_recovery_notifier(mq);
+				mmc_cqe_recovery_notifier(mrq);
 			return BLK_EH_RESET_TIMER;
 		}
-		/* No timeout (XXX: huh? comment doesn't make much sense) */
-		blk_mq_complete_request(req);
+		/* The request has gone already */
 		return BLK_EH_DONE;
 	default:
 		/* Timeout is handled by mmc core */
@@ -123,18 +122,13 @@ static enum blk_eh_timer_return mmc_mq_timed_out(struct request *req,
 	struct request_queue *q = req->q;
 	struct mmc_queue *mq = q->queuedata;
 	unsigned long flags;
-	int ret;
+	bool ignore_tout;
 
 	spin_lock_irqsave(&mq->lock, flags);
-
-	if (mq->recovery_needed || !mq->use_cqe)
-		ret = BLK_EH_RESET_TIMER;
-	else
-		ret = mmc_cqe_timed_out(req);
-
+	ignore_tout = mq->recovery_needed || !mq->use_cqe;
 	spin_unlock_irqrestore(&mq->lock, flags);
 
-	return ret;
+	return ignore_tout ? BLK_EH_RESET_TIMER : mmc_cqe_timed_out(req);
 }
 
 static void mmc_mq_recovery_handler(struct work_struct *work)
diff --git a/drivers/mmc/core/quirks.h b/drivers/mmc/core/quirks.h
index 2d2d9ea8be4f..3dba15bccce2 100644
--- a/drivers/mmc/core/quirks.h
+++ b/drivers/mmc/core/quirks.h
@@ -119,7 +119,14 @@ static const struct mmc_fixup mmc_ext_csd_fixups[] = {
 	END_FIXUP
 };
 
+
 static const struct mmc_fixup sdio_fixup_methods[] = {
+	SDIO_FIXUP(SDIO_VENDOR_ID_TI_WL1251, SDIO_DEVICE_ID_TI_WL1251,
+		   add_quirk, MMC_QUIRK_NONSTD_FUNC_IF),
+
+	SDIO_FIXUP(SDIO_VENDOR_ID_TI_WL1251, SDIO_DEVICE_ID_TI_WL1251,
+		   add_quirk, MMC_QUIRK_DISABLE_CD),
+
 	SDIO_FIXUP(SDIO_VENDOR_ID_TI, SDIO_DEVICE_ID_TI_WL1271,
 		   add_quirk, MMC_QUIRK_NONSTD_FUNC_IF),
 
diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c
index 712a7742765e..8d93b668e897 100644
--- a/drivers/mmc/core/sdio.c
+++ b/drivers/mmc/core/sdio.c
@@ -720,9 +720,8 @@ try_again:
 			/* Retry init sequence, but without R4_18V_PRESENT. */
 			retries = 0;
 			goto try_again;
-		} else {
-			goto remove;
 		}
+		return err;
 	}
 
 	/*
diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c
index da2596c5fa28..582ec3d720f6 100644
--- a/drivers/mmc/core/slot-gpio.c
+++ b/drivers/mmc/core/slot-gpio.c
@@ -241,6 +241,9 @@ int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id,
 			return ret;
 	}
 
+	if (host->caps2 & MMC_CAP2_RO_ACTIVE_HIGH)
+		gpiod_toggle_active_low(desc);
+
 	if (gpio_invert)
 		*gpio_invert = !gpiod_is_active_low(desc);
 
diff --git a/drivers/mmc/host/alcor.c b/drivers/mmc/host/alcor.c
index e481535cba2b..d76ecd9bd452 100644
--- a/drivers/mmc/host/alcor.c
+++ b/drivers/mmc/host/alcor.c
@@ -1104,7 +1104,7 @@ static int alcor_pci_sdmmc_drv_probe(struct platform_device *pdev)
 
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to get irq for data line\n");
-		return ret;
+		goto free_host;
 	}
 
 	mutex_init(&host->cmd_mutex);
@@ -1116,6 +1116,10 @@ static int alcor_pci_sdmmc_drv_probe(struct platform_device *pdev)
 	dev_set_drvdata(&pdev->dev, host);
 	mmc_add_host(mmc);
 	return 0;
+
+free_host:
+	mmc_free_host(mmc);
+	return ret;
 }
 
 static int alcor_pci_sdmmc_drv_remove(struct platform_device *pdev)
diff --git a/drivers/mmc/host/cqhci.c b/drivers/mmc/host/cqhci.c
index 5047f7343ffc..c19f4c3f115a 100644
--- a/drivers/mmc/host/cqhci.c
+++ b/drivers/mmc/host/cqhci.c
@@ -5,6 +5,7 @@
 #include <linux/delay.h>
 #include <linux/highmem.h>
 #include <linux/io.h>
+#include <linux/iopoll.h>
 #include <linux/module.h>
 #include <linux/dma-mapping.h>
 #include <linux/slab.h>
@@ -343,12 +344,16 @@ static int cqhci_enable(struct mmc_host *mmc, struct mmc_card *card)
 /* CQHCI is idle and should halt immediately, so set a small timeout */
 #define CQHCI_OFF_TIMEOUT 100
 
+static u32 cqhci_read_ctl(struct cqhci_host *cq_host)
+{
+	return cqhci_readl(cq_host, CQHCI_CTL);
+}
+
 static void cqhci_off(struct mmc_host *mmc)
 {
 	struct cqhci_host *cq_host = mmc->cqe_private;
-	ktime_t timeout;
-	bool timed_out;
 	u32 reg;
+	int err;
 
 	if (!cq_host->enabled || !mmc->cqe_on || cq_host->recovery_halt)
 		return;
@@ -358,15 +363,9 @@ static void cqhci_off(struct mmc_host *mmc)
 
 	cqhci_writel(cq_host, CQHCI_HALT, CQHCI_CTL);
 
-	timeout = ktime_add_us(ktime_get(), CQHCI_OFF_TIMEOUT);
-	while (1) {
-		timed_out = ktime_compare(ktime_get(), timeout) > 0;
-		reg = cqhci_readl(cq_host, CQHCI_CTL);
-		if ((reg & CQHCI_HALT) || timed_out)
-			break;
-	}
-
-	if (timed_out)
+	err = readx_poll_timeout(cqhci_read_ctl, cq_host, reg,
+				 reg & CQHCI_HALT, 0, CQHCI_OFF_TIMEOUT);
+	if (err < 0)
 		pr_err("%s: cqhci: CQE stuck on\n", mmc_hostname(mmc));
 	else
 		pr_debug("%s: cqhci: CQE off\n", mmc_hostname(mmc));
diff --git a/drivers/mmc/host/meson-mx-sdio.c b/drivers/mmc/host/meson-mx-sdio.c
index ba9a63db73da..360d523132bd 100644
--- a/drivers/mmc/host/meson-mx-sdio.c
+++ b/drivers/mmc/host/meson-mx-sdio.c
@@ -246,6 +246,9 @@ static void meson_mx_mmc_request_done(struct meson_mx_mmc_host *host)
 
 	mrq = host->mrq;
 
+	if (host->cmd->error)
+		meson_mx_mmc_soft_reset(host);
+
 	host->mrq = NULL;
 	host->cmd = NULL;
 
@@ -357,14 +360,6 @@ static void meson_mx_mmc_request(struct mmc_host *mmc, struct mmc_request *mrq)
 		meson_mx_mmc_start_cmd(mmc, mrq->cmd);
 }
 
-static int meson_mx_mmc_card_busy(struct mmc_host *mmc)
-{
-	struct meson_mx_mmc_host *host = mmc_priv(mmc);
-	u32 irqc = readl(host->base + MESON_MX_SDIO_IRQC);
-
-	return !!(irqc & MESON_MX_SDIO_IRQC_FORCE_DATA_DAT_MASK);
-}
-
 static void meson_mx_mmc_read_response(struct mmc_host *mmc,
 				       struct mmc_command *cmd)
 {
@@ -506,7 +501,6 @@ static void meson_mx_mmc_timeout(struct timer_list *t)
 static struct mmc_host_ops meson_mx_mmc_ops = {
 	.request		= meson_mx_mmc_request,
 	.set_ios		= meson_mx_mmc_set_ios,
-	.card_busy		= meson_mx_mmc_card_busy,
 	.get_cd			= mmc_gpio_get_cd,
 	.get_ro			= mmc_gpio_get_ro,
 };
@@ -570,7 +564,7 @@ static int meson_mx_mmc_add_host(struct meson_mx_mmc_host *host)
 	mmc->f_max = clk_round_rate(host->cfg_div_clk,
 				    clk_get_rate(host->parent_clk));
 
-	mmc->caps |= MMC_CAP_ERASE | MMC_CAP_CMD23;
+	mmc->caps |= MMC_CAP_ERASE | MMC_CAP_CMD23 | MMC_CAP_WAIT_WHILE_BUSY;
 	mmc->ops = &meson_mx_mmc_ops;
 
 	ret = mmc_of_parse(mmc);
diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c
index 19544b121276..2a9af943709d 100644
--- a/drivers/mmc/host/mmc_spi.c
+++ b/drivers/mmc/host/mmc_spi.c
@@ -1134,17 +1134,22 @@ static void mmc_spi_initsequence(struct mmc_spi_host *host)
 	 * SPI protocol.  Another is that when chipselect is released while
 	 * the card returns BUSY status, the clock must issue several cycles
 	 * with chipselect high before the card will stop driving its output.
+	 *
+	 * SPI_CS_HIGH means "asserted" here. In some cases like when using
+	 * GPIOs for chip select, SPI_CS_HIGH is set but this will be logically
+	 * inverted by gpiolib, so if we want to ascertain to drive it high
+	 * we should toggle the default with an XOR as we do here.
 	 */
-	host->spi->mode |= SPI_CS_HIGH;
+	host->spi->mode ^= SPI_CS_HIGH;
 	if (spi_setup(host->spi) != 0) {
 		/* Just warn; most cards work without it. */
 		dev_warn(&host->spi->dev,
 				"can't change chip-select polarity\n");
-		host->spi->mode &= ~SPI_CS_HIGH;
+		host->spi->mode ^= SPI_CS_HIGH;
 	} else {
 		mmc_spi_readbytes(host, 18);
 
-		host->spi->mode &= ~SPI_CS_HIGH;
+		host->spi->mode ^= SPI_CS_HIGH;
 		if (spi_setup(host->spi) != 0) {
 			/* Wot, we can't get the same setup we had before? */
 			dev_err(&host->spi->dev,
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index b8554bf38f72..da59512e9411 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -168,6 +168,8 @@ static struct variant_data variant_ux500 = {
 	.cmdreg_srsp		= MCI_CPSM_RESPONSE,
 	.datalength_bits	= 24,
 	.datactrl_blocksz	= 11,
+	.datactrl_any_blocksz	= true,
+	.dma_power_of_2		= true,
 	.datactrl_mask_sdio	= MCI_DPSM_ST_SDIOEN,
 	.st_sdio		= true,
 	.st_clkdiv		= true,
@@ -201,6 +203,8 @@ static struct variant_data variant_ux500v2 = {
 	.datactrl_mask_ddrmode	= MCI_DPSM_ST_DDRMODE,
 	.datalength_bits	= 24,
 	.datactrl_blocksz	= 11,
+	.datactrl_any_blocksz	= true,
+	.dma_power_of_2		= true,
 	.datactrl_mask_sdio	= MCI_DPSM_ST_SDIOEN,
 	.st_sdio		= true,
 	.st_clkdiv		= true,
@@ -260,6 +264,7 @@ static struct variant_data variant_stm32_sdmmc = {
 	.datacnt_useless	= true,
 	.datalength_bits	= 25,
 	.datactrl_blocksz	= 14,
+	.datactrl_any_blocksz	= true,
 	.stm32_idmabsize_mask	= GENMASK(12, 5),
 	.init			= sdmmc_variant_init,
 };
@@ -279,6 +284,7 @@ static struct variant_data variant_qcom = {
 	.data_cmd_enable	= MCI_CPSM_QCOM_DATCMD,
 	.datalength_bits	= 24,
 	.datactrl_blocksz	= 11,
+	.datactrl_any_blocksz	= true,
 	.pwrreg_powerup		= MCI_PWR_UP,
 	.f_max			= 208000000,
 	.explicit_mclk_control	= true,
@@ -447,10 +453,11 @@ void mmci_dma_setup(struct mmci_host *host)
 static int mmci_validate_data(struct mmci_host *host,
 			      struct mmc_data *data)
 {
+	struct variant_data *variant = host->variant;
+
 	if (!data)
 		return 0;
-
-	if (!is_power_of_2(data->blksz)) {
+	if (!is_power_of_2(data->blksz) && !variant->datactrl_any_blocksz) {
 		dev_err(mmc_dev(host->mmc),
 			"unsupported block size (%d bytes)\n", data->blksz);
 		return -EINVAL;
@@ -515,7 +522,9 @@ int mmci_dma_start(struct mmci_host *host, unsigned int datactrl)
 		 "Submit MMCI DMA job, sglen %d blksz %04x blks %04x flags %08x\n",
 		 data->sg_len, data->blksz, data->blocks, data->flags);
 
-	host->ops->dma_start(host, &datactrl);
+	ret = host->ops->dma_start(host, &datactrl);
+	if (ret)
+		return ret;
 
 	/* Trigger the DMA transfer */
 	mmci_write_datactrlreg(host, datactrl);
@@ -822,6 +831,18 @@ static int _mmci_dmae_prep_data(struct mmci_host *host, struct mmc_data *data,
 	if (data->blksz * data->blocks <= variant->fifosize)
 		return -EINVAL;
 
+	/*
+	 * This is necessary to get SDIO working on the Ux500. We do not yet
+	 * know if this is a bug in:
+	 * - The Ux500 DMA controller (DMA40)
+	 * - The MMCI DMA interface on the Ux500
+	 * some power of two blocks (such as 64 bytes) are sent regularly
+	 * during SDIO traffic and those work fine so for these we enable DMA
+	 * transfers.
+	 */
+	if (host->variant->dma_power_of_2 && !is_power_of_2(data->blksz))
+		return -EINVAL;
+
 	device = chan->device;
 	nr_sg = dma_map_sg(device->dev, data->sg, data->sg_len,
 			   mmc_get_dma_dir(data));
@@ -872,9 +893,14 @@ int mmci_dmae_prep_data(struct mmci_host *host,
 int mmci_dmae_start(struct mmci_host *host, unsigned int *datactrl)
 {
 	struct mmci_dmae_priv *dmae = host->dma_priv;
+	int ret;
 
 	host->dma_in_progress = true;
-	dmaengine_submit(dmae->desc_current);
+	ret = dma_submit_error(dmaengine_submit(dmae->desc_current));
+	if (ret < 0) {
+		host->dma_in_progress = false;
+		return ret;
+	}
 	dma_async_issue_pending(dmae->cur);
 
 	*datactrl |= MCI_DPSM_DMAENABLE;
diff --git a/drivers/mmc/host/mmci.h b/drivers/mmc/host/mmci.h
index 833236ecb31e..89ab73343cf3 100644
--- a/drivers/mmc/host/mmci.h
+++ b/drivers/mmc/host/mmci.h
@@ -278,7 +278,11 @@ struct mmci_host;
  * @stm32_clkdiv: true if using a STM32-specific clock divider algorithm
  * @datactrl_mask_ddrmode: ddr mode mask in datactrl register.
  * @datactrl_mask_sdio: SDIO enable mask in datactrl register
- * @datactrl_blksz: block size in power of two
+ * @datactrl_blocksz: block size in power of two
+ * @datactrl_any_blocksz: true if block any block sizes are accepted by
+ *		  hardware, such as with some SDIO traffic that send
+ *		  odd packets.
+ * @dma_power_of_2: DMA only works with blocks that are a power of 2.
  * @datactrl_first: true if data must be setup before send command
  * @datacnt_useless: true if you could not use datacnt register to read
  *		     remaining data
@@ -323,6 +327,8 @@ struct variant_data {
 	unsigned int		datactrl_mask_ddrmode;
 	unsigned int		datactrl_mask_sdio;
 	unsigned int		datactrl_blocksz;
+	u8			datactrl_any_blocksz:1;
+	u8			dma_power_of_2:1;
 	u8			datactrl_first:1;
 	u8			datacnt_useless:1;
 	u8			st_sdio:1;
diff --git a/drivers/mmc/host/mmci_stm32_sdmmc.c b/drivers/mmc/host/mmci_stm32_sdmmc.c
index 8e83ae6920ae..0953bd8a4f79 100644
--- a/drivers/mmc/host/mmci_stm32_sdmmc.c
+++ b/drivers/mmc/host/mmci_stm32_sdmmc.c
@@ -162,6 +162,9 @@ static int sdmmc_idma_start(struct mmci_host *host, unsigned int *datactrl)
 static void sdmmc_idma_finalize(struct mmci_host *host, struct mmc_data *data)
 {
 	writel_relaxed(0, host->base + MMCI_STM32_IDMACTRLR);
+
+	if (!data->host_cookie)
+		sdmmc_idma_unprep_data(host, data, 0);
 }
 
 static void mmci_sdmmc_set_clkreg(struct mmci_host *host, unsigned int desired)
diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c
index 024acc1b0a2e..b2bbcb09a49e 100644
--- a/drivers/mmc/host/pxamci.c
+++ b/drivers/mmc/host/pxamci.c
@@ -740,16 +740,16 @@ static int pxamci_probe(struct platform_device *pdev)
 			goto out;
 		}
 
+		if (!host->pdata->gpio_card_ro_invert)
+			mmc->caps2 |= MMC_CAP2_RO_ACTIVE_HIGH;
+
 		ret = mmc_gpiod_request_ro(mmc, "wp", 0, 0, NULL);
 		if (ret && ret != -ENOENT) {
 			dev_err(dev, "Failed requesting gpio_ro\n");
 			goto out;
 		}
-		if (!ret) {
+		if (!ret)
 			host->use_ro_gpio = true;
-			mmc->caps2 |= host->pdata->gpio_card_ro_invert ?
-				0 : MMC_CAP2_RO_ACTIVE_HIGH;
-		}
 
 		if (host->pdata->init)
 			host->pdata->init(dev, pxamci_detect_irq, mmc);
diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c
index 5f8d57ac084f..474df33de02b 100644
--- a/drivers/mmc/host/renesas_sdhi_core.c
+++ b/drivers/mmc/host/renesas_sdhi_core.c
@@ -644,8 +644,8 @@ int renesas_sdhi_probe(struct platform_device *pdev,
 	struct tmio_mmc_dma *dma_priv;
 	struct tmio_mmc_host *host;
 	struct renesas_sdhi *priv;
+	int num_irqs, irq, ret, i;
 	struct resource *res;
-	int irq, ret, i;
 	u16 ver;
 
 	of_data = of_device_get_match_data(&pdev->dev);
@@ -823,24 +823,31 @@ int renesas_sdhi_probe(struct platform_device *pdev,
 		host->hs400_complete = renesas_sdhi_hs400_complete;
 	}
 
-	i = 0;
-	while (1) {
+	num_irqs = platform_irq_count(pdev);
+	if (num_irqs < 0) {
+		ret = num_irqs;
+		goto eirq;
+	}
+
+	/* There must be at least one IRQ source */
+	if (!num_irqs) {
+		ret = -ENXIO;
+		goto eirq;
+	}
+
+	for (i = 0; i < num_irqs; i++) {
 		irq = platform_get_irq(pdev, i);
-		if (irq < 0)
-			break;
-		i++;
+		if (irq < 0) {
+			ret = irq;
+			goto eirq;
+		}
+
 		ret = devm_request_irq(&pdev->dev, irq, tmio_mmc_irq, 0,
 				       dev_name(&pdev->dev), host);
 		if (ret)
 			goto eirq;
 	}
 
-	/* There must be at least one IRQ source */
-	if (!i) {
-		ret = irq;
-		goto eirq;
-	}
-
 	dev_info(&pdev->dev, "%s base at 0x%08lx max clock rate %u MHz\n",
 		 mmc_hostname(host->mmc), (unsigned long)
 		 (platform_get_resource(pdev, IORESOURCE_MEM, 0)->start),
diff --git a/drivers/mmc/host/renesas_sdhi_internal_dmac.c b/drivers/mmc/host/renesas_sdhi_internal_dmac.c
index 751fe91c7571..63eb203bba61 100644
--- a/drivers/mmc/host/renesas_sdhi_internal_dmac.c
+++ b/drivers/mmc/host/renesas_sdhi_internal_dmac.c
@@ -229,15 +229,12 @@ static void renesas_sdhi_internal_dmac_issue_tasklet_fn(unsigned long arg)
 					    DTRAN_CTRL_DM_START);
 }
 
-static void renesas_sdhi_internal_dmac_complete_tasklet_fn(unsigned long arg)
+static bool renesas_sdhi_internal_dmac_complete(struct tmio_mmc_host *host)
 {
-	struct tmio_mmc_host *host = (struct tmio_mmc_host *)arg;
 	enum dma_data_direction dir;
 
-	spin_lock_irq(&host->lock);
-
 	if (!host->data)
-		goto out;
+		return false;
 
 	if (host->data->flags & MMC_DATA_READ)
 		dir = DMA_FROM_DEVICE;
@@ -250,6 +247,17 @@ static void renesas_sdhi_internal_dmac_complete_tasklet_fn(unsigned long arg)
 	if (dir == DMA_FROM_DEVICE)
 		clear_bit(SDHI_INTERNAL_DMAC_RX_IN_USE, &global_flags);
 
+	return true;
+}
+
+static void renesas_sdhi_internal_dmac_complete_tasklet_fn(unsigned long arg)
+{
+	struct tmio_mmc_host *host = (struct tmio_mmc_host *)arg;
+
+	spin_lock_irq(&host->lock);
+	if (!renesas_sdhi_internal_dmac_complete(host))
+		goto out;
+
 	tmio_mmc_do_data_irq(host);
 out:
 	spin_unlock_irq(&host->lock);
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index 1604f512c7bd..01fc437ed965 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -602,10 +602,12 @@ static int sdhci_acpi_emmc_amd_probe_slot(struct platform_device *pdev,
 }
 
 static const struct sdhci_acpi_slot sdhci_acpi_slot_amd_emmc = {
-	.chip   = &sdhci_acpi_chip_amd,
-	.caps   = MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE,
-	.quirks = SDHCI_QUIRK_32BIT_DMA_ADDR | SDHCI_QUIRK_32BIT_DMA_SIZE |
-			SDHCI_QUIRK_32BIT_ADMA_SIZE,
+	.chip		= &sdhci_acpi_chip_amd,
+	.caps		= MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE,
+	.quirks		= SDHCI_QUIRK_32BIT_DMA_ADDR |
+			  SDHCI_QUIRK_32BIT_DMA_SIZE |
+			  SDHCI_QUIRK_32BIT_ADMA_SIZE,
+	.quirks2	= SDHCI_QUIRK2_BROKEN_64_BIT_DMA,
 	.probe_slot     = sdhci_acpi_emmc_amd_probe_slot,
 };
 
diff --git a/drivers/mmc/host/sdhci-cadence.c b/drivers/mmc/host/sdhci-cadence.c
index 44139fceac24..58d2fdd6155f 100644
--- a/drivers/mmc/host/sdhci-cadence.c
+++ b/drivers/mmc/host/sdhci-cadence.c
@@ -11,6 +11,7 @@
 #include <linux/mmc/host.h>
 #include <linux/mmc/mmc.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
 
 #include "sdhci-pltfm.h"
 
@@ -193,52 +194,6 @@ static u32 sdhci_cdns_get_emmc_mode(struct sdhci_cdns_priv *priv)
 	return FIELD_GET(SDHCI_CDNS_HRS06_MODE, tmp);
 }
 
-static void sdhci_cdns_set_uhs_signaling(struct sdhci_host *host,
-					 unsigned int timing)
-{
-	struct sdhci_cdns_priv *priv = sdhci_cdns_priv(host);
-	u32 mode;
-
-	switch (timing) {
-	case MMC_TIMING_MMC_HS:
-		mode = SDHCI_CDNS_HRS06_MODE_MMC_SDR;
-		break;
-	case MMC_TIMING_MMC_DDR52:
-		mode = SDHCI_CDNS_HRS06_MODE_MMC_DDR;
-		break;
-	case MMC_TIMING_MMC_HS200:
-		mode = SDHCI_CDNS_HRS06_MODE_MMC_HS200;
-		break;
-	case MMC_TIMING_MMC_HS400:
-		if (priv->enhanced_strobe)
-			mode = SDHCI_CDNS_HRS06_MODE_MMC_HS400ES;
-		else
-			mode = SDHCI_CDNS_HRS06_MODE_MMC_HS400;
-		break;
-	default:
-		mode = SDHCI_CDNS_HRS06_MODE_SD;
-		break;
-	}
-
-	sdhci_cdns_set_emmc_mode(priv, mode);
-
-	/* For SD, fall back to the default handler */
-	if (mode == SDHCI_CDNS_HRS06_MODE_SD)
-		sdhci_set_uhs_signaling(host, timing);
-}
-
-static const struct sdhci_ops sdhci_cdns_ops = {
-	.set_clock = sdhci_set_clock,
-	.get_timeout_clock = sdhci_cdns_get_timeout_clock,
-	.set_bus_width = sdhci_set_bus_width,
-	.reset = sdhci_reset,
-	.set_uhs_signaling = sdhci_cdns_set_uhs_signaling,
-};
-
-static const struct sdhci_pltfm_data sdhci_cdns_pltfm_data = {
-	.ops = &sdhci_cdns_ops,
-};
-
 static int sdhci_cdns_set_tune_val(struct sdhci_host *host, unsigned int val)
 {
 	struct sdhci_cdns_priv *priv = sdhci_cdns_priv(host);
@@ -272,23 +227,24 @@ static int sdhci_cdns_set_tune_val(struct sdhci_host *host, unsigned int val)
 	return 0;
 }
 
-static int sdhci_cdns_execute_tuning(struct mmc_host *mmc, u32 opcode)
+/*
+ * In SD mode, software must not use the hardware tuning and instead perform
+ * an almost identical procedure to eMMC.
+ */
+static int sdhci_cdns_execute_tuning(struct sdhci_host *host, u32 opcode)
 {
-	struct sdhci_host *host = mmc_priv(mmc);
 	int cur_streak = 0;
 	int max_streak = 0;
 	int end_of_streak = 0;
 	int i;
 
 	/*
-	 * This handler only implements the eMMC tuning that is specific to
-	 * this controller.  Fall back to the standard method for SD timing.
+	 * Do not execute tuning for UHS_SDR50 or UHS_DDR50.
+	 * The delay is set by probe, based on the DT properties.
 	 */
-	if (host->timing != MMC_TIMING_MMC_HS200)
-		return sdhci_execute_tuning(mmc, opcode);
-
-	if (WARN_ON(opcode != MMC_SEND_TUNING_BLOCK_HS200))
-		return -EINVAL;
+	if (host->timing != MMC_TIMING_MMC_HS200 &&
+	    host->timing != MMC_TIMING_UHS_SDR104)
+		return 0;
 
 	for (i = 0; i < SDHCI_CDNS_MAX_TUNING_LOOP; i++) {
 		if (sdhci_cdns_set_tune_val(host, i) ||
@@ -311,6 +267,58 @@ static int sdhci_cdns_execute_tuning(struct mmc_host *mmc, u32 opcode)
 	return sdhci_cdns_set_tune_val(host, end_of_streak - max_streak / 2);
 }
 
+static void sdhci_cdns_set_uhs_signaling(struct sdhci_host *host,
+					 unsigned int timing)
+{
+	struct sdhci_cdns_priv *priv = sdhci_cdns_priv(host);
+	u32 mode;
+
+	switch (timing) {
+	case MMC_TIMING_MMC_HS:
+		mode = SDHCI_CDNS_HRS06_MODE_MMC_SDR;
+		break;
+	case MMC_TIMING_MMC_DDR52:
+		mode = SDHCI_CDNS_HRS06_MODE_MMC_DDR;
+		break;
+	case MMC_TIMING_MMC_HS200:
+		mode = SDHCI_CDNS_HRS06_MODE_MMC_HS200;
+		break;
+	case MMC_TIMING_MMC_HS400:
+		if (priv->enhanced_strobe)
+			mode = SDHCI_CDNS_HRS06_MODE_MMC_HS400ES;
+		else
+			mode = SDHCI_CDNS_HRS06_MODE_MMC_HS400;
+		break;
+	default:
+		mode = SDHCI_CDNS_HRS06_MODE_SD;
+		break;
+	}
+
+	sdhci_cdns_set_emmc_mode(priv, mode);
+
+	/* For SD, fall back to the default handler */
+	if (mode == SDHCI_CDNS_HRS06_MODE_SD)
+		sdhci_set_uhs_signaling(host, timing);
+}
+
+static const struct sdhci_ops sdhci_cdns_ops = {
+	.set_clock = sdhci_set_clock,
+	.get_timeout_clock = sdhci_cdns_get_timeout_clock,
+	.set_bus_width = sdhci_set_bus_width,
+	.reset = sdhci_reset,
+	.platform_execute_tuning = sdhci_cdns_execute_tuning,
+	.set_uhs_signaling = sdhci_cdns_set_uhs_signaling,
+};
+
+static const struct sdhci_pltfm_data sdhci_cdns_uniphier_pltfm_data = {
+	.ops = &sdhci_cdns_ops,
+	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
+};
+
+static const struct sdhci_pltfm_data sdhci_cdns_pltfm_data = {
+	.ops = &sdhci_cdns_ops,
+};
+
 static void sdhci_cdns_hs400_enhanced_strobe(struct mmc_host *mmc,
 					     struct mmc_ios *ios)
 {
@@ -334,6 +342,7 @@ static void sdhci_cdns_hs400_enhanced_strobe(struct mmc_host *mmc,
 static int sdhci_cdns_probe(struct platform_device *pdev)
 {
 	struct sdhci_host *host;
+	const struct sdhci_pltfm_data *data;
 	struct sdhci_pltfm_host *pltfm_host;
 	struct sdhci_cdns_priv *priv;
 	struct clk *clk;
@@ -350,9 +359,13 @@ static int sdhci_cdns_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	data = of_device_get_match_data(dev);
+	if (!data)
+		data = &sdhci_cdns_pltfm_data;
+
 	nr_phy_params = sdhci_cdns_phy_param_count(dev->of_node);
 	priv_size = sizeof(*priv) + sizeof(priv->phy_params[0]) * nr_phy_params;
-	host = sdhci_pltfm_init(pdev, &sdhci_cdns_pltfm_data, priv_size);
+	host = sdhci_pltfm_init(pdev, data, priv_size);
 	if (IS_ERR(host)) {
 		ret = PTR_ERR(host);
 		goto disable_clk;
@@ -366,7 +379,6 @@ static int sdhci_cdns_probe(struct platform_device *pdev)
 	priv->hrs_addr = host->ioaddr;
 	priv->enhanced_strobe = false;
 	host->ioaddr += SDHCI_CDNS_SRS_BASE;
-	host->mmc_host_ops.execute_tuning = sdhci_cdns_execute_tuning;
 	host->mmc_host_ops.hs400_enhanced_strobe =
 				sdhci_cdns_hs400_enhanced_strobe;
 	sdhci_enable_v4_mode(host);
@@ -430,7 +442,10 @@ static const struct dev_pm_ops sdhci_cdns_pm_ops = {
 };
 
 static const struct of_device_id sdhci_cdns_match[] = {
-	{ .compatible = "socionext,uniphier-sd4hc" },
+	{
+		.compatible = "socionext,uniphier-sd4hc",
+		.data = &sdhci_cdns_uniphier_pltfm_data,
+	},
 	{ .compatible = "cdns,sd4hc" },
 	{ /* sentinel */ }
 };
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index 776a94216248..3ba49f80db9b 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -87,7 +87,7 @@
 #define ESDHC_STD_TUNING_EN		(1 << 24)
 /* NOTE: the minimum valid tuning start tap for mx6sl is 1 */
 #define ESDHC_TUNING_START_TAP_DEFAULT	0x1
-#define ESDHC_TUNING_START_TAP_MASK	0xff
+#define ESDHC_TUNING_START_TAP_MASK	0x7f
 #define ESDHC_TUNING_STEP_MASK		0x00070000
 #define ESDHC_TUNING_STEP_SHIFT		16
 
@@ -1381,13 +1381,14 @@ static int sdhci_esdhc_imx_probe_nondt(struct platform_device *pdev,
 				host->mmc->parent->platform_data);
 	/* write_protect */
 	if (boarddata->wp_type == ESDHC_WP_GPIO) {
+		host->mmc->caps2 |= MMC_CAP2_RO_ACTIVE_HIGH;
+
 		err = mmc_gpiod_request_ro(host->mmc, "wp", 0, 0, NULL);
 		if (err) {
 			dev_err(mmc_dev(host->mmc),
 				"failed to request write-protect gpio!\n");
 			return err;
 		}
-		host->mmc->caps2 |= MMC_CAP2_RO_ACTIVE_HIGH;
 	}
 
 	/* card_detect */
diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c
index 08e96072c027..256d9173acd5 100644
--- a/drivers/mmc/host/sdhci-msm.c
+++ b/drivers/mmc/host/sdhci-msm.c
@@ -1113,6 +1113,12 @@ static int sdhci_msm_execute_tuning(struct mmc_host *mmc, u32 opcode)
 	msm_host->use_cdr = true;
 
 	/*
+	 * Clear tuning_done flag before tuning to ensure proper
+	 * HS400 settings.
+	 */
+	msm_host->tuning_done = 0;
+
+	/*
 	 * For HS400 tuning in HS200 timing requires:
 	 * - select MCLK/2 in VENDOR_SPEC
 	 * - program MCLK to 400MHz (or nearest supported) in GCC
@@ -1736,7 +1742,9 @@ static const struct sdhci_ops sdhci_msm_ops = {
 static const struct sdhci_pltfm_data sdhci_msm_pdata = {
 	.quirks = SDHCI_QUIRK_BROKEN_CARD_DETECTION |
 		  SDHCI_QUIRK_SINGLE_POWER_WRITE |
-		  SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN,
+		  SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN |
+		  SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12,
+
 	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
 	.ops = &sdhci_msm_ops,
 };
@@ -1946,6 +1954,8 @@ static int sdhci_msm_probe(struct platform_device *pdev)
 		goto clk_disable;
 	}
 
+	msm_host->mmc->caps |= MMC_CAP_WAIT_WHILE_BUSY | MMC_CAP_NEED_RSP_BUSY;
+
 	pm_runtime_get_noresume(&pdev->dev);
 	pm_runtime_set_active(&pdev->dev);
 	pm_runtime_enable(&pdev->dev);
diff --git a/drivers/mmc/host/sdhci-of-at91.c b/drivers/mmc/host/sdhci-of-at91.c
index 0ae986c42bc8..881f8138e7de 100644
--- a/drivers/mmc/host/sdhci-of-at91.c
+++ b/drivers/mmc/host/sdhci-of-at91.c
@@ -118,7 +118,8 @@ static void sdhci_at91_reset(struct sdhci_host *host, u8 mask)
 {
 	sdhci_reset(host, mask);
 
-	if (host->mmc->caps & MMC_CAP_NONREMOVABLE)
+	if ((host->mmc->caps & MMC_CAP_NONREMOVABLE)
+	    || mmc_gpio_get_cd(host->mmc) >= 0)
 		sdhci_at91_set_force_card_detect(host);
 }
 
@@ -324,19 +325,22 @@ static int sdhci_at91_probe(struct platform_device *pdev)
 	priv->mainck = devm_clk_get(&pdev->dev, "baseclk");
 	if (IS_ERR(priv->mainck)) {
 		dev_err(&pdev->dev, "failed to get baseclk\n");
-		return PTR_ERR(priv->mainck);
+		ret = PTR_ERR(priv->mainck);
+		goto sdhci_pltfm_free;
 	}
 
 	priv->hclock = devm_clk_get(&pdev->dev, "hclock");
 	if (IS_ERR(priv->hclock)) {
 		dev_err(&pdev->dev, "failed to get hclock\n");
-		return PTR_ERR(priv->hclock);
+		ret = PTR_ERR(priv->hclock);
+		goto sdhci_pltfm_free;
 	}
 
 	priv->gck = devm_clk_get(&pdev->dev, "multclk");
 	if (IS_ERR(priv->gck)) {
 		dev_err(&pdev->dev, "failed to get multclk\n");
-		return PTR_ERR(priv->gck);
+		ret = PTR_ERR(priv->gck);
+		goto sdhci_pltfm_free;
 	}
 
 	ret = sdhci_at91_set_clks_presets(&pdev->dev);
@@ -394,8 +398,11 @@ static int sdhci_at91_probe(struct platform_device *pdev)
 	 * detection procedure using the SDMCC_CD signal is bypassed.
 	 * This bit is reset when a software reset for all command is performed
 	 * so we need to implement our own reset function to set back this bit.
+	 *
+	 * WA: SAMA5D2 doesn't drive CMD if using CD GPIO line.
 	 */
-	if (host->mmc->caps & MMC_CAP_NONREMOVABLE)
+	if ((host->mmc->caps & MMC_CAP_NONREMOVABLE)
+	    || mmc_gpio_get_cd(host->mmc) >= 0)
 		sdhci_at91_set_force_card_detect(host);
 
 	pm_runtime_put_autosuspend(&pdev->dev);
diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c
index 276e4449edca..e7b5a98d2622 100644
--- a/drivers/mmc/host/sdhci-of-esdhc.c
+++ b/drivers/mmc/host/sdhci-of-esdhc.c
@@ -704,23 +704,58 @@ static void esdhc_reset(struct sdhci_host *host, u8 mask)
 {
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct sdhci_esdhc *esdhc = sdhci_pltfm_priv(pltfm_host);
-	u32 val;
+	u32 val, bus_width = 0;
 
+	/*
+	 * Add delay to make sure all the DMA transfers are finished
+	 * for quirk.
+	 */
 	if (esdhc->quirk_delay_before_data_reset &&
 	    (mask & SDHCI_RESET_DATA) &&
 	    (host->flags & SDHCI_REQ_USE_DMA))
 		mdelay(5);
 
+	/*
+	 * Save bus-width for eSDHC whose vendor version is 2.2
+	 * or lower for data reset.
+	 */
+	if ((mask & SDHCI_RESET_DATA) &&
+	    (esdhc->vendor_ver <= VENDOR_V_22)) {
+		val = sdhci_readl(host, ESDHC_PROCTL);
+		bus_width = val & ESDHC_CTRL_BUSWIDTH_MASK;
+	}
+
 	sdhci_reset(host, mask);
 
-	sdhci_writel(host, host->ier, SDHCI_INT_ENABLE);
-	sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
+	/*
+	 * Restore bus-width setting and interrupt registers for eSDHC
+	 * whose vendor version is 2.2 or lower for data reset.
+	 */
+	if ((mask & SDHCI_RESET_DATA) &&
+	    (esdhc->vendor_ver <= VENDOR_V_22)) {
+		val = sdhci_readl(host, ESDHC_PROCTL);
+		val &= ~ESDHC_CTRL_BUSWIDTH_MASK;
+		val |= bus_width;
+		sdhci_writel(host, val, ESDHC_PROCTL);
+
+		sdhci_writel(host, host->ier, SDHCI_INT_ENABLE);
+		sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
+	}
 
-	if (mask & SDHCI_RESET_ALL) {
+	/*
+	 * Some bits have to be cleaned manually for eSDHC whose spec
+	 * version is higher than 3.0 for all reset.
+	 */
+	if ((mask & SDHCI_RESET_ALL) &&
+	    (esdhc->spec_ver >= SDHCI_SPEC_300)) {
 		val = sdhci_readl(host, ESDHC_TBCTL);
 		val &= ~ESDHC_TB_EN;
 		sdhci_writel(host, val, ESDHC_TBCTL);
 
+		/*
+		 * Initialize eSDHC_DLLCFG1[DLL_PD_PULSE_STRETCH_SEL] to
+		 * 0 for quirk.
+		 */
 		if (esdhc->quirk_unreliable_pulse_detection) {
 			val = sdhci_readl(host, ESDHC_DLLCFG1);
 			val &= ~ESDHC_DLL_PD_PULSE_STRETCH_SEL;
diff --git a/drivers/mmc/host/sdhci-omap.c b/drivers/mmc/host/sdhci-omap.c
index 083e7e053c95..d3135249b2e4 100644
--- a/drivers/mmc/host/sdhci-omap.c
+++ b/drivers/mmc/host/sdhci-omap.c
@@ -1134,6 +1134,9 @@ static int sdhci_omap_probe(struct platform_device *pdev)
 	host->mmc_host_ops.execute_tuning = sdhci_omap_execute_tuning;
 	host->mmc_host_ops.enable_sdio_irq = sdhci_omap_enable_sdio_irq;
 
+	/* R1B responses is required to properly manage HW busy detection. */
+	mmc->caps |= MMC_CAP_NEED_RSP_BUSY;
+
 	ret = sdhci_setup_host(host);
 	if (ret)
 		goto err_put_sync;
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index 8542158f67d0..3ac3ccf9af5c 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -21,6 +21,7 @@
 #include <linux/mmc/mmc.h>
 #include <linux/scatterlist.h>
 #include <linux/io.h>
+#include <linux/iopoll.h>
 #include <linux/gpio.h>
 #include <linux/pm_runtime.h>
 #include <linux/mmc/slot-gpio.h>
@@ -600,6 +601,9 @@ static int intel_select_drive_strength(struct mmc_card *card,
 	struct sdhci_pci_slot *slot = sdhci_priv(host);
 	struct intel_host *intel_host = sdhci_pci_priv(slot);
 
+	if (!(mmc_driver_type_mask(intel_host->drv_strength) & card_drv))
+		return 0;
+
 	return intel_host->drv_strength;
 }
 
@@ -1598,11 +1602,59 @@ static int amd_probe(struct sdhci_pci_chip *chip)
 	return 0;
 }
 
+static u32 sdhci_read_present_state(struct sdhci_host *host)
+{
+	return sdhci_readl(host, SDHCI_PRESENT_STATE);
+}
+
+static void amd_sdhci_reset(struct sdhci_host *host, u8 mask)
+{
+	struct sdhci_pci_slot *slot = sdhci_priv(host);
+	struct pci_dev *pdev = slot->chip->pdev;
+	u32 present_state;
+
+	/*
+	 * SDHC 0x7906 requires a hard reset to clear all internal state.
+	 * Otherwise it can get into a bad state where the DATA lines are always
+	 * read as zeros.
+	 */
+	if (pdev->device == 0x7906 && (mask & SDHCI_RESET_ALL)) {
+		pci_clear_master(pdev);
+
+		pci_save_state(pdev);
+
+		pci_set_power_state(pdev, PCI_D3cold);
+		pr_debug("%s: power_state=%u\n", mmc_hostname(host->mmc),
+			pdev->current_state);
+		pci_set_power_state(pdev, PCI_D0);
+
+		pci_restore_state(pdev);
+
+		/*
+		 * SDHCI_RESET_ALL says the card detect logic should not be
+		 * reset, but since we need to reset the entire controller
+		 * we should wait until the card detect logic has stabilized.
+		 *
+		 * This normally takes about 40ms.
+		 */
+		readx_poll_timeout(
+			sdhci_read_present_state,
+			host,
+			present_state,
+			present_state & SDHCI_CD_STABLE,
+			10000,
+			100000
+		);
+	}
+
+	return sdhci_reset(host, mask);
+}
+
 static const struct sdhci_ops amd_sdhci_pci_ops = {
 	.set_clock			= sdhci_set_clock,
 	.enable_dma			= sdhci_pci_enable_dma,
 	.set_bus_width			= sdhci_set_bus_width,
-	.reset				= sdhci_reset,
+	.reset				= amd_sdhci_reset,
 	.set_uhs_signaling		= sdhci_set_uhs_signaling,
 };
 
@@ -1678,6 +1730,9 @@ static const struct pci_device_id pci_ids[] = {
 	SDHCI_PCI_DEVICE(INTEL, ICP_SD,    intel_byt_sd),
 	SDHCI_PCI_DEVICE(INTEL, CML_EMMC,  intel_glk_emmc),
 	SDHCI_PCI_DEVICE(INTEL, CML_SD,    intel_byt_sd),
+	SDHCI_PCI_DEVICE(INTEL, CMLH_SD,   intel_byt_sd),
+	SDHCI_PCI_DEVICE(INTEL, JSL_EMMC,  intel_glk_emmc),
+	SDHCI_PCI_DEVICE(INTEL, JSL_SD,    intel_byt_sd),
 	SDHCI_PCI_DEVICE(O2, 8120,     o2),
 	SDHCI_PCI_DEVICE(O2, 8220,     o2),
 	SDHCI_PCI_DEVICE(O2, 8221,     o2),
diff --git a/drivers/mmc/host/sdhci-pci-o2micro.c b/drivers/mmc/host/sdhci-pci-o2micro.c
index 19944b0049db..7b3c9e6dab65 100644
--- a/drivers/mmc/host/sdhci-pci-o2micro.c
+++ b/drivers/mmc/host/sdhci-pci-o2micro.c
@@ -441,6 +441,12 @@ int sdhci_pci_o2_probe_slot(struct sdhci_pci_slot *slot)
 			slot->host->mmc_host_ops.get_cd = sdhci_o2_get_cd;
 		}
 
+		if (chip->pdev->device == PCI_DEVICE_ID_O2_SEABIRD1) {
+			slot->host->mmc_host_ops.get_cd = sdhci_o2_get_cd;
+			host->mmc->caps2 |= MMC_CAP2_NO_SDIO;
+			host->quirks2 |= SDHCI_QUIRK2_PRESET_VALUE_BROKEN;
+		}
+
 		host->mmc_host_ops.execute_tuning = sdhci_o2_execute_tuning;
 
 		if (chip->pdev->device != PCI_DEVICE_ID_O2_FUJIN2)
diff --git a/drivers/mmc/host/sdhci-pci.h b/drivers/mmc/host/sdhci-pci.h
index e5dc6e44c7a4..dbf7bdaa3fa3 100644
--- a/drivers/mmc/host/sdhci-pci.h
+++ b/drivers/mmc/host/sdhci-pci.h
@@ -52,6 +52,9 @@
 #define PCI_DEVICE_ID_INTEL_ICP_SD	0x34f8
 #define PCI_DEVICE_ID_INTEL_CML_EMMC	0x02c4
 #define PCI_DEVICE_ID_INTEL_CML_SD	0x02f5
+#define PCI_DEVICE_ID_INTEL_CMLH_SD	0x06f5
+#define PCI_DEVICE_ID_INTEL_JSL_EMMC	0x4dc4
+#define PCI_DEVICE_ID_INTEL_JSL_SD	0x4df8
 
 #define PCI_DEVICE_ID_SYSKONNECT_8000	0x8000
 #define PCI_DEVICE_ID_VIA_95D0		0x95d0
diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c
index a8df5ac97977..6faa36eca170 100644
--- a/drivers/mmc/host/sdhci-tegra.c
+++ b/drivers/mmc/host/sdhci-tegra.c
@@ -386,7 +386,7 @@ static void tegra_sdhci_reset(struct sdhci_host *host, u8 mask)
 			misc_ctrl |= SDHCI_MISC_CTRL_ENABLE_DDR50;
 		if (soc_data->nvquirks & NVQUIRK_ENABLE_SDR104)
 			misc_ctrl |= SDHCI_MISC_CTRL_ENABLE_SDR104;
-		if (soc_data->nvquirks & SDHCI_MISC_CTRL_ENABLE_SDR50)
+		if (soc_data->nvquirks & NVQUIRK_ENABLE_SDR50)
 			clk_ctrl |= SDHCI_CLOCK_CTRL_SDR50_TUNING_OVERRIDE;
 	}
 
@@ -1552,6 +1552,9 @@ static int sdhci_tegra_probe(struct platform_device *pdev)
 	if (tegra_host->soc_data->nvquirks & NVQUIRK_ENABLE_DDR50)
 		host->mmc->caps |= MMC_CAP_1_8V_DDR;
 
+	/* R1B responses is required to properly manage HW busy detection. */
+	host->mmc->caps |= MMC_CAP_NEED_RSP_BUSY;
+
 	tegra_sdhci_parse_dt(host);
 
 	tegra_host->power_gpio = devm_gpiod_get_optional(&pdev->dev, "power",
diff --git a/drivers/mmc/host/sdhci-xenon.c b/drivers/mmc/host/sdhci-xenon.c
index 1dea1ba66f7b..4703cd540c7f 100644
--- a/drivers/mmc/host/sdhci-xenon.c
+++ b/drivers/mmc/host/sdhci-xenon.c
@@ -235,6 +235,16 @@ static void xenon_voltage_switch(struct sdhci_host *host)
 {
 	/* Wait for 5ms after set 1.8V signal enable bit */
 	usleep_range(5000, 5500);
+
+	/*
+	 * For some reason the controller's Host Control2 register reports
+	 * the bit representing 1.8V signaling as 0 when read after it was
+	 * written as 1. Subsequent read reports 1.
+	 *
+	 * Since this may cause some issues, do an empty read of the Host
+	 * Control2 register here to circumvent this.
+	 */
+	sdhci_readw(host, SDHCI_HOST_CONTROL2);
 }
 
 static const struct sdhci_ops sdhci_xenon_ops = {
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index ee7bbd475ccc..5a8d97a8f1e1 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -152,7 +152,7 @@ static void sdhci_set_card_detection(struct sdhci_host *host, bool enable)
 	u32 present;
 
 	if ((host->quirks & SDHCI_QUIRK_BROKEN_CARD_DETECTION) ||
-	    !mmc_card_is_removable(host->mmc))
+	    !mmc_card_is_removable(host->mmc) || mmc_can_gpio_cd(host->mmc))
 		return;
 
 	if (enable) {
@@ -977,7 +977,7 @@ static void sdhci_set_transfer_irqs(struct sdhci_host *host)
 	sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
 }
 
-static void sdhci_set_data_timeout_irq(struct sdhci_host *host, bool enable)
+void sdhci_set_data_timeout_irq(struct sdhci_host *host, bool enable)
 {
 	if (enable)
 		host->ier |= SDHCI_INT_DATA_TIMEOUT;
@@ -986,28 +986,31 @@ static void sdhci_set_data_timeout_irq(struct sdhci_host *host, bool enable)
 	sdhci_writel(host, host->ier, SDHCI_INT_ENABLE);
 	sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
 }
+EXPORT_SYMBOL_GPL(sdhci_set_data_timeout_irq);
 
-static void sdhci_set_timeout(struct sdhci_host *host, struct mmc_command *cmd)
+void __sdhci_set_timeout(struct sdhci_host *host, struct mmc_command *cmd)
 {
-	u8 count;
-
-	if (host->ops->set_timeout) {
-		host->ops->set_timeout(host, cmd);
-	} else {
-		bool too_big = false;
-
-		count = sdhci_calc_timeout(host, cmd, &too_big);
+	bool too_big = false;
+	u8 count = sdhci_calc_timeout(host, cmd, &too_big);
+
+	if (too_big &&
+	    host->quirks2 & SDHCI_QUIRK2_DISABLE_HW_TIMEOUT) {
+		sdhci_calc_sw_timeout(host, cmd);
+		sdhci_set_data_timeout_irq(host, false);
+	} else if (!(host->ier & SDHCI_INT_DATA_TIMEOUT)) {
+		sdhci_set_data_timeout_irq(host, true);
+	}
 
-		if (too_big &&
-		    host->quirks2 & SDHCI_QUIRK2_DISABLE_HW_TIMEOUT) {
-			sdhci_calc_sw_timeout(host, cmd);
-			sdhci_set_data_timeout_irq(host, false);
-		} else if (!(host->ier & SDHCI_INT_DATA_TIMEOUT)) {
-			sdhci_set_data_timeout_irq(host, true);
-		}
+	sdhci_writeb(host, count, SDHCI_TIMEOUT_CONTROL);
+}
+EXPORT_SYMBOL_GPL(__sdhci_set_timeout);
 
-		sdhci_writeb(host, count, SDHCI_TIMEOUT_CONTROL);
-	}
+static void sdhci_set_timeout(struct sdhci_host *host, struct mmc_command *cmd)
+{
+	if (host->ops->set_timeout)
+		host->ops->set_timeout(host, cmd);
+	else
+		__sdhci_set_timeout(host, cmd);
 }
 
 static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_command *cmd)
@@ -3884,11 +3887,13 @@ int sdhci_setup_host(struct sdhci_host *host)
 	if (host->ops->get_min_clock)
 		mmc->f_min = host->ops->get_min_clock(host);
 	else if (host->version >= SDHCI_SPEC_300) {
-		if (host->clk_mul) {
-			mmc->f_min = (host->max_clk * host->clk_mul) / 1024;
+		if (host->clk_mul)
 			max_clk = host->max_clk * host->clk_mul;
-		} else
-			mmc->f_min = host->max_clk / SDHCI_MAX_DIV_SPEC_300;
+		/*
+		 * Divided Clock Mode minimum clock rate is always less than
+		 * Programmable Clock Mode minimum clock rate.
+		 */
+		mmc->f_min = host->max_clk / SDHCI_MAX_DIV_SPEC_300;
 	} else
 		mmc->f_min = host->max_clk / SDHCI_MAX_DIV_SPEC_200;
 
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index 1a506672bea8..f69bebe51520 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -799,5 +799,7 @@ void sdhci_start_tuning(struct sdhci_host *host);
 void sdhci_end_tuning(struct sdhci_host *host);
 void sdhci_reset_tuning(struct sdhci_host *host);
 void sdhci_send_tuning(struct sdhci_host *host, u32 opcode);
+void sdhci_set_data_timeout_irq(struct sdhci_host *host, bool enable);
+void __sdhci_set_timeout(struct sdhci_host *host, struct mmc_command *cmd);
 
 #endif /* __SDHCI_HW_H */
diff --git a/drivers/mmc/host/sdhci_am654.c b/drivers/mmc/host/sdhci_am654.c
index 3222ea4d584d..9839821fa27b 100644
--- a/drivers/mmc/host/sdhci_am654.c
+++ b/drivers/mmc/host/sdhci_am654.c
@@ -179,6 +179,22 @@ static void sdhci_am654_write_b(struct sdhci_host *host, u8 val, int reg)
 	writeb(val, host->ioaddr + reg);
 }
 
+static int sdhci_am654_execute_tuning(struct mmc_host *mmc, u32 opcode)
+{
+	struct sdhci_host *host = mmc_priv(mmc);
+	int err = sdhci_execute_tuning(mmc, opcode);
+
+	if (err)
+		return err;
+	/*
+	 * Tuning data remains in the buffer after tuning.
+	 * Do a command and data reset to get rid of it
+	 */
+	sdhci_reset(host, SDHCI_RESET_CMD | SDHCI_RESET_DATA);
+
+	return 0;
+}
+
 static struct sdhci_ops sdhci_am654_ops = {
 	.get_max_clock = sdhci_pltfm_clk_get_max_clock,
 	.get_timeout_clock = sdhci_pltfm_clk_get_max_clock,
@@ -344,6 +360,8 @@ static int sdhci_am654_probe(struct platform_device *pdev)
 		goto pm_runtime_put;
 	}
 
+	host->mmc_host_ops.execute_tuning = sdhci_am654_execute_tuning;
+
 	ret = sdhci_am654_init(host);
 	if (ret)
 		goto pm_runtime_put;
diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c
index 81bd9afb0980..98c575de43c7 100644
--- a/drivers/mmc/host/sh_mmcif.c
+++ b/drivers/mmc/host/sh_mmcif.c
@@ -1393,11 +1393,9 @@ static int sh_mmcif_probe(struct platform_device *pdev)
 	const char *name;
 
 	irq[0] = platform_get_irq(pdev, 0);
-	irq[1] = platform_get_irq(pdev, 1);
-	if (irq[0] < 0) {
-		dev_err(dev, "Get irq error\n");
+	irq[1] = platform_get_irq_optional(pdev, 1);
+	if (irq[0] < 0)
 		return -ENXIO;
-	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	reg = devm_ioremap_resource(dev, res);
diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c
index 0c5d040d194c..5c7869f4fc3d 100644
--- a/drivers/mmc/host/tmio_mmc_core.c
+++ b/drivers/mmc/host/tmio_mmc_core.c
@@ -1295,12 +1295,14 @@ void tmio_mmc_host_remove(struct tmio_mmc_host *host)
 	cancel_work_sync(&host->done);
 	cancel_delayed_work_sync(&host->delayed_reset_work);
 	tmio_mmc_release_dma(host);
+	tmio_mmc_disable_mmc_irqs(host, TMIO_MASK_ALL);
 
-	pm_runtime_dont_use_autosuspend(&pdev->dev);
 	if (host->native_hotplug)
 		pm_runtime_put_noidle(&pdev->dev);
-	pm_runtime_put_sync(&pdev->dev);
+
 	pm_runtime_disable(&pdev->dev);
+	pm_runtime_dont_use_autosuspend(&pdev->dev);
+	pm_runtime_put_noidle(&pdev->dev);
 }
 EXPORT_SYMBOL_GPL(tmio_mmc_host_remove);
 
diff --git a/drivers/mmc/host/uniphier-sd.c b/drivers/mmc/host/uniphier-sd.c
index 91a2be41edf6..a16d16f97190 100644
--- a/drivers/mmc/host/uniphier-sd.c
+++ b/drivers/mmc/host/uniphier-sd.c
@@ -616,11 +616,6 @@ static int uniphier_sd_probe(struct platform_device *pdev)
 		}
 	}
 
-	ret = devm_request_irq(dev, irq, tmio_mmc_irq, IRQF_SHARED,
-			       dev_name(dev), host);
-	if (ret)
-		goto free_host;
-
 	if (priv->caps & UNIPHIER_SD_CAP_EXTENDED_IP)
 		host->dma_ops = &uniphier_sd_internal_dma_ops;
 	else
@@ -648,8 +643,15 @@ static int uniphier_sd_probe(struct platform_device *pdev)
 	if (ret)
 		goto free_host;
 
+	ret = devm_request_irq(dev, irq, tmio_mmc_irq, IRQF_SHARED,
+			       dev_name(dev), host);
+	if (ret)
+		goto remove_host;
+
 	return 0;
 
+remove_host:
+	tmio_mmc_host_remove(host);
 free_host:
 	tmio_mmc_host_free(host);
 
diff --git a/drivers/mmc/host/via-sdmmc.c b/drivers/mmc/host/via-sdmmc.c
index f4ac064ff471..8d96ecba1b55 100644
--- a/drivers/mmc/host/via-sdmmc.c
+++ b/drivers/mmc/host/via-sdmmc.c
@@ -319,6 +319,8 @@ struct via_crdr_mmc_host {
 /* some devices need a very long delay for power to stabilize */
 #define VIA_CRDR_QUIRK_300MS_PWRDELAY	0x0001
 
+#define VIA_CMD_TIMEOUT_MS		1000
+
 static const struct pci_device_id via_ids[] = {
 	{PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_9530,
 	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0,},
@@ -551,14 +553,17 @@ static void via_sdc_send_command(struct via_crdr_mmc_host *host,
 {
 	void __iomem *addrbase;
 	struct mmc_data *data;
+	unsigned int timeout_ms;
 	u32 cmdctrl = 0;
 
 	WARN_ON(host->cmd);
 
 	data = cmd->data;
-	mod_timer(&host->timer, jiffies + HZ);
 	host->cmd = cmd;
 
+	timeout_ms = cmd->busy_timeout ? cmd->busy_timeout : VIA_CMD_TIMEOUT_MS;
+	mod_timer(&host->timer, jiffies + msecs_to_jiffies(timeout_ms));
+
 	/*Command index*/
 	cmdctrl = cmd->opcode << 8;
 
diff --git a/drivers/mtd/devices/mchp23k256.c b/drivers/mtd/devices/mchp23k256.c
index b20d02b4f830..77c872fd3d83 100644
--- a/drivers/mtd/devices/mchp23k256.c
+++ b/drivers/mtd/devices/mchp23k256.c
@@ -64,15 +64,17 @@ static int mchp23k256_write(struct mtd_info *mtd, loff_t to, size_t len,
 	struct spi_transfer transfer[2] = {};
 	struct spi_message message;
 	unsigned char command[MAX_CMD_SIZE];
-	int ret;
+	int ret, cmd_len;
 
 	spi_message_init(&message);
 
+	cmd_len = mchp23k256_cmdsz(flash);
+
 	command[0] = MCHP23K256_CMD_WRITE;
 	mchp23k256_addr2cmd(flash, to, command);
 
 	transfer[0].tx_buf = command;
-	transfer[0].len = mchp23k256_cmdsz(flash);
+	transfer[0].len = cmd_len;
 	spi_message_add_tail(&transfer[0], &message);
 
 	transfer[1].tx_buf = buf;
@@ -88,8 +90,8 @@ static int mchp23k256_write(struct mtd_info *mtd, loff_t to, size_t len,
 	if (ret)
 		return ret;
 
-	if (retlen && message.actual_length > sizeof(command))
-		*retlen += message.actual_length - sizeof(command);
+	if (retlen && message.actual_length > cmd_len)
+		*retlen += message.actual_length - cmd_len;
 
 	return 0;
 }
@@ -101,16 +103,18 @@ static int mchp23k256_read(struct mtd_info *mtd, loff_t from, size_t len,
 	struct spi_transfer transfer[2] = {};
 	struct spi_message message;
 	unsigned char command[MAX_CMD_SIZE];
-	int ret;
+	int ret, cmd_len;
 
 	spi_message_init(&message);
 
+	cmd_len = mchp23k256_cmdsz(flash);
+
 	memset(&transfer, 0, sizeof(transfer));
 	command[0] = MCHP23K256_CMD_READ;
 	mchp23k256_addr2cmd(flash, from, command);
 
 	transfer[0].tx_buf = command;
-	transfer[0].len = mchp23k256_cmdsz(flash);
+	transfer[0].len = cmd_len;
 	spi_message_add_tail(&transfer[0], &message);
 
 	transfer[1].rx_buf = buf;
@@ -126,8 +130,8 @@ static int mchp23k256_read(struct mtd_info *mtd, loff_t from, size_t len,
 	if (ret)
 		return ret;
 
-	if (retlen && message.actual_length > sizeof(command))
-		*retlen += message.actual_length - sizeof(command);
+	if (retlen && message.actual_length > cmd_len)
+		*retlen += message.actual_length - cmd_len;
 
 	return 0;
 }
diff --git a/drivers/mtd/devices/phram.c b/drivers/mtd/devices/phram.c
index c467286ca007..52a1c86874e6 100644
--- a/drivers/mtd/devices/phram.c
+++ b/drivers/mtd/devices/phram.c
@@ -243,22 +243,25 @@ static int phram_setup(const char *val)
 
 	ret = parse_num64(&start, token[1]);
 	if (ret) {
-		kfree(name);
 		parse_err("illegal start address\n");
+		goto error;
 	}
 
 	ret = parse_num64(&len, token[2]);
 	if (ret) {
-		kfree(name);
 		parse_err("illegal device length\n");
+		goto error;
 	}
 
 	ret = register_device(name, start, len);
-	if (!ret)
-		pr_info("%s device: %#llx at %#llx\n", name, len, start);
-	else
-		kfree(name);
+	if (ret)
+		goto error;
+
+	pr_info("%s device: %#llx at %#llx\n", name, len, start);
+	return 0;
 
+error:
+	kfree(name);
 	return ret;
 }
 
diff --git a/drivers/mtd/lpddr/lpddr_cmds.c b/drivers/mtd/lpddr/lpddr_cmds.c
index 1efc643c9871..9341a8a592e8 100644
--- a/drivers/mtd/lpddr/lpddr_cmds.c
+++ b/drivers/mtd/lpddr/lpddr_cmds.c
@@ -68,7 +68,6 @@ struct mtd_info *lpddr_cmdset(struct map_info *map)
 	shared = kmalloc_array(lpddr->numchips, sizeof(struct flchip_shared),
 						GFP_KERNEL);
 	if (!shared) {
-		kfree(lpddr);
 		kfree(mtd);
 		return NULL;
 	}
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index 975aed94f06c..48832f9b215c 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -354,9 +354,6 @@ static int mtdchar_writeoob(struct file *file, struct mtd_info *mtd,
 	uint32_t retlen;
 	int ret = 0;
 
-	if (!(file->f_mode & FMODE_WRITE))
-		return -EPERM;
-
 	if (length > 4096)
 		return -EINVAL;
 
@@ -641,6 +638,48 @@ static int mtdchar_ioctl(struct file *file, u_int cmd, u_long arg)
 
 	pr_debug("MTD_ioctl\n");
 
+	/*
+	 * Check the file mode to require "dangerous" commands to have write
+	 * permissions.
+	 */
+	switch (cmd) {
+	/* "safe" commands */
+	case MEMGETREGIONCOUNT:
+	case MEMGETREGIONINFO:
+	case MEMGETINFO:
+	case MEMREADOOB:
+	case MEMREADOOB64:
+	case MEMLOCK:
+	case MEMUNLOCK:
+	case MEMISLOCKED:
+	case MEMGETOOBSEL:
+	case MEMGETBADBLOCK:
+	case MEMSETBADBLOCK:
+	case OTPSELECT:
+	case OTPGETREGIONCOUNT:
+	case OTPGETREGIONINFO:
+	case OTPLOCK:
+	case ECCGETLAYOUT:
+	case ECCGETSTATS:
+	case MTDFILEMODE:
+	case BLKPG:
+	case BLKRRPART:
+		break;
+
+	/* "dangerous" commands */
+	case MEMERASE:
+	case MEMERASE64:
+	case MEMWRITEOOB:
+	case MEMWRITEOOB64:
+	case MEMWRITE:
+		if (!(file->f_mode & FMODE_WRITE))
+			return -EPERM;
+		break;
+
+	default:
+		return -ENOTTY;
+	}
+
 	switch (cmd) {
 	case MEMGETREGIONCOUNT:
 		if (copy_to_user(argp, &(mtd->numeraseregions), sizeof(int)))
@@ -688,9 +727,6 @@ static int mtdchar_ioctl(struct file *file, u_int cmd, u_long arg)
 	{
 		struct erase_info *erase;
 
-		if(!(file->f_mode & FMODE_WRITE))
-			return -EPERM;
-
 		erase=kzalloc(sizeof(struct erase_info),GFP_KERNEL);
 		if (!erase)
 			ret = -ENOMEM;
@@ -983,9 +1019,6 @@ static int mtdchar_ioctl(struct file *file, u_int cmd, u_long arg)
 		ret = 0;
 		break;
 	}
-
-	default:
-		ret = -ENOTTY;
 	}
 
 	return ret;
@@ -1029,6 +1062,11 @@ static long mtdchar_compat_ioctl(struct file *file, unsigned int cmd,
 		struct mtd_oob_buf32 buf;
 		struct mtd_oob_buf32 __user *buf_user = argp;
 
+		if (!(file->f_mode & FMODE_WRITE)) {
+			ret = -EPERM;
+			break;
+		}
+
 		if (copy_from_user(&buf, argp, sizeof(buf)))
 			ret = -EFAULT;
 		else
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 453242d6cf56..ef4ebbf0428c 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -487,7 +487,7 @@ static int mtd_nvmem_add(struct mtd_info *mtd)
 
 	config.id = -1;
 	config.dev = &mtd->dev;
-	config.name = mtd->name;
+	config.name = dev_name(&mtd->dev);
 	config.owner = THIS_MODULE;
 	config.reg_read = mtd_nvmem_reg_read;
 	config.size = mtd->size;
diff --git a/drivers/mtd/nand/onenand/omap2.c b/drivers/mtd/nand/onenand/omap2.c
index edf94ee54ec7..71a632b815aa 100644
--- a/drivers/mtd/nand/onenand/omap2.c
+++ b/drivers/mtd/nand/onenand/omap2.c
@@ -328,7 +328,8 @@ static inline int omap2_onenand_dma_transfer(struct omap2_onenand *c,
 	struct dma_async_tx_descriptor *tx;
 	dma_cookie_t cookie;
 
-	tx = dmaengine_prep_dma_memcpy(c->dma_chan, dst, src, count, 0);
+	tx = dmaengine_prep_dma_memcpy(c->dma_chan, dst, src, count,
+				       DMA_CTRL_ACK | DMA_PREP_INTERRUPT);
 	if (!tx) {
 		dev_err(&c->pdev->dev, "Failed to prepare DMA memcpy\n");
 		return -EIO;
diff --git a/drivers/mtd/nand/onenand/onenand_base.c b/drivers/mtd/nand/onenand/onenand_base.c
index d759c02d9cb2..23f388cac647 100644
--- a/drivers/mtd/nand/onenand/onenand_base.c
+++ b/drivers/mtd/nand/onenand/onenand_base.c
@@ -1248,44 +1248,44 @@ static int onenand_read_ops_nolock(struct mtd_info *mtd, loff_t from,
 
 	stats = mtd->ecc_stats;
 
- 	/* Read-while-load method */
+	/* Read-while-load method */
 
- 	/* Do first load to bufferRAM */
- 	if (read < len) {
- 		if (!onenand_check_bufferram(mtd, from)) {
+	/* Do first load to bufferRAM */
+	if (read < len) {
+		if (!onenand_check_bufferram(mtd, from)) {
 			this->command(mtd, ONENAND_CMD_READ, from, writesize);
- 			ret = this->wait(mtd, FL_READING);
- 			onenand_update_bufferram(mtd, from, !ret);
+			ret = this->wait(mtd, FL_READING);
+			onenand_update_bufferram(mtd, from, !ret);
 			if (mtd_is_eccerr(ret))
 				ret = 0;
- 		}
- 	}
+		}
+	}
 
 	thislen = min_t(int, writesize, len - read);
 	column = from & (writesize - 1);
 	if (column + thislen > writesize)
 		thislen = writesize - column;
 
- 	while (!ret) {
- 		/* If there is more to load then start next load */
- 		from += thislen;
- 		if (read + thislen < len) {
+	while (!ret) {
+		/* If there is more to load then start next load */
+		from += thislen;
+		if (read + thislen < len) {
 			this->command(mtd, ONENAND_CMD_READ, from, writesize);
- 			/*
- 			 * Chip boundary handling in DDP
- 			 * Now we issued chip 1 read and pointed chip 1
+			/*
+			 * Chip boundary handling in DDP
+			 * Now we issued chip 1 read and pointed chip 1
 			 * bufferram so we have to point chip 0 bufferram.
- 			 */
- 			if (ONENAND_IS_DDP(this) &&
- 			    unlikely(from == (this->chipsize >> 1))) {
- 				this->write_word(ONENAND_DDP_CHIP0, this->base + ONENAND_REG_START_ADDRESS2);
- 				boundary = 1;
- 			} else
- 				boundary = 0;
- 			ONENAND_SET_PREV_BUFFERRAM(this);
- 		}
- 		/* While load is going, read from last bufferRAM */
- 		this->read_bufferram(mtd, ONENAND_DATARAM, buf, column, thislen);
+			 */
+			if (ONENAND_IS_DDP(this) &&
+			    unlikely(from == (this->chipsize >> 1))) {
+				this->write_word(ONENAND_DDP_CHIP0, this->base + ONENAND_REG_START_ADDRESS2);
+				boundary = 1;
+			} else
+				boundary = 0;
+			ONENAND_SET_PREV_BUFFERRAM(this);
+		}
+		/* While load is going, read from last bufferRAM */
+		this->read_bufferram(mtd, ONENAND_DATARAM, buf, column, thislen);
 
 		/* Read oob area if needed */
 		if (oobbuf) {
@@ -1301,24 +1301,24 @@ static int onenand_read_ops_nolock(struct mtd_info *mtd, loff_t from,
 			oobcolumn = 0;
 		}
 
- 		/* See if we are done */
- 		read += thislen;
- 		if (read == len)
- 			break;
- 		/* Set up for next read from bufferRAM */
- 		if (unlikely(boundary))
- 			this->write_word(ONENAND_DDP_CHIP1, this->base + ONENAND_REG_START_ADDRESS2);
- 		ONENAND_SET_NEXT_BUFFERRAM(this);
- 		buf += thislen;
+		/* See if we are done */
+		read += thislen;
+		if (read == len)
+			break;
+		/* Set up for next read from bufferRAM */
+		if (unlikely(boundary))
+			this->write_word(ONENAND_DDP_CHIP1, this->base + ONENAND_REG_START_ADDRESS2);
+		ONENAND_SET_NEXT_BUFFERRAM(this);
+		buf += thislen;
 		thislen = min_t(int, writesize, len - read);
- 		column = 0;
- 		cond_resched();
- 		/* Now wait for load */
- 		ret = this->wait(mtd, FL_READING);
- 		onenand_update_bufferram(mtd, from, !ret);
+		column = 0;
+		cond_resched();
+		/* Now wait for load */
+		ret = this->wait(mtd, FL_READING);
+		onenand_update_bufferram(mtd, from, !ret);
 		if (mtd_is_eccerr(ret))
 			ret = 0;
- 	}
+	}
 
 	/*
 	 * Return success, if no ECC failures, else -EBADMSG
diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
index 873527753f52..9d0a532efcf2 100644
--- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c
+++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
@@ -483,8 +483,9 @@ static int brcmnand_revision_init(struct brcmnand_controller *ctrl)
 	} else {
 		ctrl->cs_offsets = brcmnand_cs_offsets;
 
-		/* v5.0 and earlier has a different CS0 offset layout */
-		if (ctrl->nand_version <= 0x0500)
+		/* v3.3-5.0 have a different CS0 offset layout */
+		if (ctrl->nand_version >= 0x0303 &&
+		    ctrl->nand_version <= 0x0500)
 			ctrl->cs0_offsets = brcmnand_cs_offsets_cs0;
 	}
 
@@ -903,11 +904,14 @@ static int brcmnand_hamming_ooblayout_free(struct mtd_info *mtd, int section,
 		if (!section) {
 			/*
 			 * Small-page NAND use byte 6 for BBI while large-page
-			 * NAND use byte 0.
+			 * NAND use bytes 0 and 1.
 			 */
-			if (cfg->page_size > 512)
-				oobregion->offset++;
-			oobregion->length--;
+			if (cfg->page_size > 512) {
+				oobregion->offset += 2;
+				oobregion->length -= 2;
+			} else {
+				oobregion->length--;
+			}
 		}
 	}
 
@@ -1662,25 +1666,31 @@ static int brcmnand_read_by_pio(struct mtd_info *mtd, struct nand_chip *chip,
 static int brcmstb_nand_verify_erased_page(struct mtd_info *mtd,
 		  struct nand_chip *chip, void *buf, u64 addr)
 {
-	int i, sas;
-	void *oob = chip->oob_poi;
+	struct mtd_oob_region ecc;
+	int i;
 	int bitflips = 0;
 	int page = addr >> chip->page_shift;
 	int ret;
+	void *ecc_bytes;
+	void *ecc_chunk;
 
 	if (!buf)
 		buf = nand_get_data_buf(chip);
 
-	sas = mtd->oobsize / chip->ecc.steps;
-
 	/* read without ecc for verification */
 	ret = chip->ecc.read_page_raw(chip, buf, true, page);
 	if (ret)
 		return ret;
 
-	for (i = 0; i < chip->ecc.steps; i++, oob += sas) {
-		ret = nand_check_erased_ecc_chunk(buf, chip->ecc.size,
-						  oob, sas, NULL, 0,
+	for (i = 0; i < chip->ecc.steps; i++) {
+		ecc_chunk = buf + chip->ecc.size * i;
+
+		mtd_ooblayout_ecc(mtd, i, &ecc);
+		ecc_bytes = chip->oob_poi + ecc.offset;
+
+		ret = nand_check_erased_ecc_chunk(ecc_chunk, chip->ecc.size,
+						  ecc_bytes, ecc.length,
+						  NULL, 0,
 						  chip->ecc.strength);
 		if (ret < 0)
 			return ret;
diff --git a/drivers/mtd/nand/raw/diskonchip.c b/drivers/mtd/nand/raw/diskonchip.c
index c0e1a8ebe820..522390b99d3c 100644
--- a/drivers/mtd/nand/raw/diskonchip.c
+++ b/drivers/mtd/nand/raw/diskonchip.c
@@ -1609,13 +1609,10 @@ static int __init doc_probe(unsigned long physadr)
 		numchips = doc2001_init(mtd);
 
 	if ((ret = nand_scan(nand, numchips)) || (ret = doc->late_init(mtd))) {
-		/* DBB note: i believe nand_release is necessary here, as
+		/* DBB note: i believe nand_cleanup is necessary here, as
 		   buffers may have been allocated in nand_base.  Check with
 		   Thomas. FIX ME! */
-		/* nand_release will call mtd_device_unregister, but we
-		   haven't yet added it.  This is handled without incident by
-		   mtd_device_unregister, as far as I can tell. */
-		nand_release(nand);
+		nand_cleanup(nand);
 		goto fail;
 	}
 
diff --git a/drivers/mtd/nand/raw/fsl_upm.c b/drivers/mtd/nand/raw/fsl_upm.c
index 1054cc070747..20b0ee174dc6 100644
--- a/drivers/mtd/nand/raw/fsl_upm.c
+++ b/drivers/mtd/nand/raw/fsl_upm.c
@@ -62,7 +62,6 @@ static int fun_chip_ready(struct nand_chip *chip)
 static void fun_wait_rnb(struct fsl_upm_nand *fun)
 {
 	if (fun->rnb_gpio[fun->mchip_number] >= 0) {
-		struct mtd_info *mtd = nand_to_mtd(&fun->chip);
 		int cnt = 1000000;
 
 		while (--cnt && !fun_chip_ready(&fun->chip))
diff --git a/drivers/mtd/nand/raw/ingenic/ingenic_nand_drv.c b/drivers/mtd/nand/raw/ingenic/ingenic_nand_drv.c
index d7b7c0f13909..31e152dd5099 100644
--- a/drivers/mtd/nand/raw/ingenic/ingenic_nand_drv.c
+++ b/drivers/mtd/nand/raw/ingenic/ingenic_nand_drv.c
@@ -310,7 +310,6 @@ static int ingenic_nand_init_chip(struct platform_device *pdev,
 	struct device *dev = &pdev->dev;
 	struct ingenic_nand *nand;
 	struct ingenic_nand_cs *cs;
-	struct resource *res;
 	struct nand_chip *chip;
 	struct mtd_info *mtd;
 	const __be32 *reg;
@@ -326,8 +325,7 @@ static int ingenic_nand_init_chip(struct platform_device *pdev,
 
 	jz4780_nemc_set_type(nfc->dev, cs->bank, JZ4780_NEMC_BANK_NAND);
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, chipnr);
-	cs->base = devm_ioremap_resource(dev, res);
+	cs->base = devm_platform_ioremap_resource(pdev, chipnr);
 	if (IS_ERR(cs->base))
 		return PTR_ERR(cs->base);
 
@@ -378,7 +376,7 @@ static int ingenic_nand_init_chip(struct platform_device *pdev,
 
 	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret) {
-		nand_release(chip);
+		nand_cleanup(chip);
 		return ret;
 	}
 
diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c
index fc49e13d81ec..ee4afa17d8a3 100644
--- a/drivers/mtd/nand/raw/marvell_nand.c
+++ b/drivers/mtd/nand/raw/marvell_nand.c
@@ -707,7 +707,7 @@ static int marvell_nfc_wait_op(struct nand_chip *chip, unsigned int timeout_ms)
 	 * In case the interrupt was not served in the required time frame,
 	 * check if the ISR was not served or if something went actually wrong.
 	 */
-	if (ret && !pending) {
+	if (!ret && !pending) {
 		dev_err(nfc->dev, "Timeout waiting for RB signal\n");
 		return -ETIMEDOUT;
 	}
@@ -2664,7 +2664,7 @@ static int marvell_nand_chip_init(struct device *dev, struct marvell_nfc *nfc,
 		ret = mtd_device_register(mtd, NULL, 0);
 	if (ret) {
 		dev_err(dev, "failed to register mtd device: %d\n", ret);
-		nand_release(chip);
+		nand_cleanup(chip);
 		return ret;
 	}
 
@@ -2673,6 +2673,16 @@ static int marvell_nand_chip_init(struct device *dev, struct marvell_nfc *nfc,
 	return 0;
 }
 
+static void marvell_nand_chips_cleanup(struct marvell_nfc *nfc)
+{
+	struct marvell_nand_chip *entry, *temp;
+
+	list_for_each_entry_safe(entry, temp, &nfc->chips, node) {
+		nand_release(&entry->chip);
+		list_del(&entry->node);
+	}
+}
+
 static int marvell_nand_chips_init(struct device *dev, struct marvell_nfc *nfc)
 {
 	struct device_node *np = dev->of_node;
@@ -2707,21 +2717,16 @@ static int marvell_nand_chips_init(struct device *dev, struct marvell_nfc *nfc)
 		ret = marvell_nand_chip_init(dev, nfc, nand_np);
 		if (ret) {
 			of_node_put(nand_np);
-			return ret;
+			goto cleanup_chips;
 		}
 	}
 
 	return 0;
-}
 
-static void marvell_nand_chips_cleanup(struct marvell_nfc *nfc)
-{
-	struct marvell_nand_chip *entry, *temp;
+cleanup_chips:
+	marvell_nand_chips_cleanup(nfc);
 
-	list_for_each_entry_safe(entry, temp, &nfc->chips, node) {
-		nand_release(&entry->chip);
-		list_del(&entry->node);
-	}
+	return ret;
 }
 
 static int marvell_nfc_init_dma(struct marvell_nfc *nfc)
diff --git a/drivers/mtd/nand/raw/mtk_nand.c b/drivers/mtd/nand/raw/mtk_nand.c
index d6a1354f4f62..080736f931ca 100644
--- a/drivers/mtd/nand/raw/mtk_nand.c
+++ b/drivers/mtd/nand/raw/mtk_nand.c
@@ -1380,7 +1380,7 @@ static int mtk_nfc_nand_chip_init(struct device *dev, struct mtk_nfc *nfc,
 	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret) {
 		dev_err(dev, "mtd parse partition error\n");
-		nand_release(nand);
+		nand_cleanup(nand);
 		return ret;
 	}
 
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 0a93001d2269..360b61411f07 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -731,8 +731,14 @@ EXPORT_SYMBOL_GPL(nand_soft_waitrdy);
 int nand_gpio_waitrdy(struct nand_chip *chip, struct gpio_desc *gpiod,
 		      unsigned long timeout_ms)
 {
-	/* Wait until R/B pin indicates chip is ready or timeout occurs */
-	timeout_ms = jiffies + msecs_to_jiffies(timeout_ms);
+
+	/*
+	 * Wait until R/B pin indicates chip is ready or timeout occurs.
+	 * +1 below is necessary because if we are now in the last fraction
+	 * of jiffy and msecs_to_jiffies is 1 then we will wait only that
+	 * small jiffy fraction - possibly leading to false timeout.
+	 */
+	timeout_ms = jiffies + msecs_to_jiffies(timeout_ms) + 1;
 	do {
 		if (gpiod_get_value_cansleep(gpiod))
 			return 0;
@@ -5911,6 +5917,8 @@ void nand_cleanup(struct nand_chip *chip)
 	    chip->ecc.algo == NAND_ECC_BCH)
 		nand_bch_free((struct nand_bch_control *)chip->ecc.priv);
 
+	nanddev_cleanup(&chip->base);
+
 	/* Free bad block table memory */
 	kfree(chip->bbt);
 	kfree(chip->data_buf);
diff --git a/drivers/mtd/nand/raw/nand_onfi.c b/drivers/mtd/nand/raw/nand_onfi.c
index 0b879bd0a68c..8fe8d7bdd203 100644
--- a/drivers/mtd/nand/raw/nand_onfi.c
+++ b/drivers/mtd/nand/raw/nand_onfi.c
@@ -173,7 +173,7 @@ int nand_onfi_detect(struct nand_chip *chip)
 		}
 
 		if (onfi_crc16(ONFI_CRC_BASE, (u8 *)&p[i], 254) ==
-				le16_to_cpu(p->crc)) {
+		    le16_to_cpu(p[i].crc)) {
 			if (i)
 				memcpy(p, &p[i], sizeof(*p));
 			break;
diff --git a/drivers/mtd/nand/raw/nand_timings.c b/drivers/mtd/nand/raw/nand_timings.c
index f64b06a71dfa..f12b7a7844c9 100644
--- a/drivers/mtd/nand/raw/nand_timings.c
+++ b/drivers/mtd/nand/raw/nand_timings.c
@@ -314,10 +314,9 @@ int onfi_fill_data_interface(struct nand_chip *chip,
 		/* microseconds -> picoseconds */
 		timings->tPROG_max = 1000000ULL * ONFI_DYN_TIMING_MAX;
 		timings->tBERS_max = 1000000ULL * ONFI_DYN_TIMING_MAX;
-		timings->tR_max = 1000000ULL * 200000000ULL;
 
-		/* nanoseconds -> picoseconds */
-		timings->tCCS_min = 1000UL * 500000;
+		timings->tR_max = 200000000;
+		timings->tCCS_min = 500000;
 	}
 
 	return 0;
diff --git a/drivers/mtd/nand/raw/orion_nand.c b/drivers/mtd/nand/raw/orion_nand.c
index d27b39a7223c..a3dcdf25f5f2 100644
--- a/drivers/mtd/nand/raw/orion_nand.c
+++ b/drivers/mtd/nand/raw/orion_nand.c
@@ -180,7 +180,7 @@ static int __init orion_nand_probe(struct platform_device *pdev)
 	mtd->name = "orion_nand";
 	ret = mtd_device_register(mtd, board->parts, board->nr_parts);
 	if (ret) {
-		nand_release(nc);
+		nand_cleanup(nc);
 		goto no_dev;
 	}
 
diff --git a/drivers/mtd/nand/raw/oxnas_nand.c b/drivers/mtd/nand/raw/oxnas_nand.c
index 30c51f772de6..504c4504300c 100644
--- a/drivers/mtd/nand/raw/oxnas_nand.c
+++ b/drivers/mtd/nand/raw/oxnas_nand.c
@@ -32,6 +32,7 @@ struct oxnas_nand_ctrl {
 	void __iomem *io_base;
 	struct clk *clk;
 	struct nand_chip *chips[OXNAS_NAND_MAX_CHIPS];
+	unsigned int nchips;
 };
 
 static uint8_t oxnas_nand_read_byte(struct nand_chip *chip)
@@ -79,9 +80,9 @@ static int oxnas_nand_probe(struct platform_device *pdev)
 	struct nand_chip *chip;
 	struct mtd_info *mtd;
 	struct resource *res;
-	int nchips = 0;
 	int count = 0;
 	int err = 0;
+	int i;
 
 	/* Allocate memory for the device structure (and zero it) */
 	oxnas = devm_kzalloc(&pdev->dev, sizeof(*oxnas),
@@ -116,7 +117,7 @@ static int oxnas_nand_probe(struct platform_device *pdev)
 				    GFP_KERNEL);
 		if (!chip) {
 			err = -ENOMEM;
-			goto err_clk_unprepare;
+			goto err_release_child;
 		}
 
 		chip->controller = &oxnas->base;
@@ -137,20 +138,20 @@ static int oxnas_nand_probe(struct platform_device *pdev)
 		/* Scan to find existence of the device */
 		err = nand_scan(chip, 1);
 		if (err)
-			goto err_clk_unprepare;
+			goto err_release_child;
 
 		err = mtd_device_register(mtd, NULL, 0);
 		if (err) {
 			nand_release(chip);
-			goto err_clk_unprepare;
+			goto err_release_child;
 		}
 
-		oxnas->chips[nchips] = chip;
-		++nchips;
+		oxnas->chips[oxnas->nchips] = chip;
+		++oxnas->nchips;
 	}
 
 	/* Exit if no chips found */
-	if (!nchips) {
+	if (!oxnas->nchips) {
 		err = -ENODEV;
 		goto err_clk_unprepare;
 	}
@@ -159,6 +160,15 @@ static int oxnas_nand_probe(struct platform_device *pdev)
 
 	return 0;
 
+err_release_child:
+	of_node_put(nand_np);
+
+	for (i = 0; i < oxnas->nchips; i++) {
+		chip = oxnas->chips[i];
+		WARN_ON(mtd_device_unregister(nand_to_mtd(chip)));
+		nand_cleanup(chip);
+	}
+
 err_clk_unprepare:
 	clk_disable_unprepare(oxnas->clk);
 	return err;
@@ -167,9 +177,13 @@ err_clk_unprepare:
 static int oxnas_nand_remove(struct platform_device *pdev)
 {
 	struct oxnas_nand_ctrl *oxnas = platform_get_drvdata(pdev);
+	struct nand_chip *chip;
+	int i;
 
-	if (oxnas->chips[0])
-		nand_release(oxnas->chips[0]);
+	for (i = 0; i < oxnas->nchips; i++) {
+		chip = oxnas->chips[i];
+		nand_release(chip);
+	}
 
 	clk_disable_unprepare(oxnas->clk);
 
diff --git a/drivers/mtd/nand/raw/pasemi_nand.c b/drivers/mtd/nand/raw/pasemi_nand.c
index 9cfe7395172a..066ff6dc9a23 100644
--- a/drivers/mtd/nand/raw/pasemi_nand.c
+++ b/drivers/mtd/nand/raw/pasemi_nand.c
@@ -146,7 +146,7 @@ static int pasemi_nand_probe(struct platform_device *ofdev)
 	if (mtd_device_register(pasemi_nand_mtd, NULL, 0)) {
 		dev_err(dev, "Unable to register MTD device\n");
 		err = -ENODEV;
-		goto out_lpc;
+		goto out_cleanup_nand;
 	}
 
 	dev_info(dev, "PA Semi NAND flash at %pR, control at I/O %x\n", &res,
@@ -154,6 +154,8 @@ static int pasemi_nand_probe(struct platform_device *ofdev)
 
 	return 0;
 
+ out_cleanup_nand:
+	nand_cleanup(chip);
  out_lpc:
 	release_region(lpcctl, 4);
  out_ior:
diff --git a/drivers/mtd/nand/raw/plat_nand.c b/drivers/mtd/nand/raw/plat_nand.c
index dc0f3074ddbf..3a495b233443 100644
--- a/drivers/mtd/nand/raw/plat_nand.c
+++ b/drivers/mtd/nand/raw/plat_nand.c
@@ -92,7 +92,7 @@ static int plat_nand_probe(struct platform_device *pdev)
 	if (!err)
 		return err;
 
-	nand_release(&data->chip);
+	nand_cleanup(&data->chip);
 out:
 	if (pdata->ctrl.remove)
 		pdata->ctrl.remove(pdev);
diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index 7bb9a7e8e1e7..c1c53b02b35f 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -459,11 +459,13 @@ struct qcom_nand_host {
  * among different NAND controllers.
  * @ecc_modes - ecc mode for NAND
  * @is_bam - whether NAND controller is using BAM
+ * @is_qpic - whether NAND CTRL is part of qpic IP
  * @dev_cmd_reg_start - NAND_DEV_CMD_* registers starting offset
  */
 struct qcom_nandc_props {
 	u32 ecc_modes;
 	bool is_bam;
+	bool is_qpic;
 	u32 dev_cmd_reg_start;
 };
 
@@ -2751,7 +2753,8 @@ static int qcom_nandc_setup(struct qcom_nand_controller *nandc)
 	u32 nand_ctrl;
 
 	/* kill onenand */
-	nandc_write(nandc, SFLASHC_BURST_CFG, 0);
+	if (!nandc->props->is_qpic)
+		nandc_write(nandc, SFLASHC_BURST_CFG, 0);
 	nandc_write(nandc, dev_cmd_reg_addr(nandc, NAND_DEV_CMD_VLD),
 		    NAND_DEV_CMD_VLD_VAL);
 
@@ -3007,12 +3010,14 @@ static const struct qcom_nandc_props ipq806x_nandc_props = {
 static const struct qcom_nandc_props ipq4019_nandc_props = {
 	.ecc_modes = (ECC_BCH_4BIT | ECC_BCH_8BIT),
 	.is_bam = true,
+	.is_qpic = true,
 	.dev_cmd_reg_start = 0x0,
 };
 
 static const struct qcom_nandc_props ipq8074_nandc_props = {
 	.ecc_modes = (ECC_BCH_4BIT | ECC_BCH_8BIT),
 	.is_bam = true,
+	.is_qpic = true,
 	.dev_cmd_reg_start = 0x7000,
 };
 
diff --git a/drivers/mtd/nand/raw/sharpsl.c b/drivers/mtd/nand/raw/sharpsl.c
index b47a9eaff89b..d8c52a016080 100644
--- a/drivers/mtd/nand/raw/sharpsl.c
+++ b/drivers/mtd/nand/raw/sharpsl.c
@@ -183,7 +183,7 @@ static int sharpsl_nand_probe(struct platform_device *pdev)
 	return 0;
 
 err_add:
-	nand_release(this);
+	nand_cleanup(this);
 
 err_scan:
 	iounmap(sharpsl->io);
diff --git a/drivers/mtd/nand/raw/socrates_nand.c b/drivers/mtd/nand/raw/socrates_nand.c
index 20f40c0e812c..7c94fc51a611 100644
--- a/drivers/mtd/nand/raw/socrates_nand.c
+++ b/drivers/mtd/nand/raw/socrates_nand.c
@@ -169,7 +169,7 @@ static int socrates_nand_probe(struct platform_device *ofdev)
 	if (!res)
 		return res;
 
-	nand_release(nand_chip);
+	nand_cleanup(nand_chip);
 
 out:
 	iounmap(host->io_base);
diff --git a/drivers/mtd/nand/raw/stm32_fmc2_nand.c b/drivers/mtd/nand/raw/stm32_fmc2_nand.c
index 76609b908b5e..e02985c2bf9f 100644
--- a/drivers/mtd/nand/raw/stm32_fmc2_nand.c
+++ b/drivers/mtd/nand/raw/stm32_fmc2_nand.c
@@ -37,6 +37,9 @@
 /* Max ECC buffer length */
 #define FMC2_MAX_ECC_BUF_LEN		(FMC2_BCHDSRS_LEN * FMC2_MAX_SG)
 
+#define FMC2_TIMEOUT_US			1000
+#define FMC2_TIMEOUT_MS			1000
+
 /* Timings */
 #define FMC2_THIZ			1
 #define FMC2_TIO			8000
@@ -51,6 +54,8 @@
 #define FMC2_PMEM			0x88
 #define FMC2_PATT			0x8c
 #define FMC2_HECCR			0x94
+#define FMC2_ISR			0x184
+#define FMC2_ICR			0x188
 #define FMC2_CSQCR			0x200
 #define FMC2_CSQCFGR1			0x204
 #define FMC2_CSQCFGR2			0x208
@@ -116,6 +121,12 @@
 #define FMC2_PATT_ATTHIZ(x)		(((x) & 0xff) << 24)
 #define FMC2_PATT_DEFAULT		0x0a0a0a0a
 
+/* Register: FMC2_ISR */
+#define FMC2_ISR_IHLF			BIT(1)
+
+/* Register: FMC2_ICR */
+#define FMC2_ICR_CIHLF			BIT(1)
+
 /* Register: FMC2_CSQCR */
 #define FMC2_CSQCR_CSQSTART		BIT(0)
 
@@ -530,7 +541,8 @@ static int stm32_fmc2_ham_calculate(struct nand_chip *chip, const u8 *data,
 	int ret;
 
 	ret = readl_relaxed_poll_timeout(fmc2->io_base + FMC2_SR,
-					 sr, sr & FMC2_SR_NWRF, 10, 1000);
+					 sr, sr & FMC2_SR_NWRF, 10,
+					 FMC2_TIMEOUT_MS);
 	if (ret) {
 		dev_err(fmc2->dev, "ham timeout\n");
 		return ret;
@@ -611,7 +623,7 @@ static int stm32_fmc2_bch_calculate(struct nand_chip *chip, const u8 *data,
 
 	/* Wait until the BCH code is ready */
 	if (!wait_for_completion_timeout(&fmc2->complete,
-					 msecs_to_jiffies(1000))) {
+					 msecs_to_jiffies(FMC2_TIMEOUT_MS))) {
 		dev_err(fmc2->dev, "bch timeout\n");
 		stm32_fmc2_disable_bch_irq(fmc2);
 		return -ETIMEDOUT;
@@ -696,7 +708,7 @@ static int stm32_fmc2_bch_correct(struct nand_chip *chip, u8 *dat,
 
 	/* Wait until the decoding error is ready */
 	if (!wait_for_completion_timeout(&fmc2->complete,
-					 msecs_to_jiffies(1000))) {
+					 msecs_to_jiffies(FMC2_TIMEOUT_MS))) {
 		dev_err(fmc2->dev, "bch timeout\n");
 		stm32_fmc2_disable_bch_irq(fmc2);
 		return -ETIMEDOUT;
@@ -969,7 +981,7 @@ static int stm32_fmc2_xfer(struct nand_chip *chip, const u8 *buf,
 
 	/* Wait end of sequencer transfer */
 	if (!wait_for_completion_timeout(&fmc2->complete,
-					 msecs_to_jiffies(1000))) {
+					 msecs_to_jiffies(FMC2_TIMEOUT_MS))) {
 		dev_err(fmc2->dev, "seq timeout\n");
 		stm32_fmc2_disable_seq_irq(fmc2);
 		dmaengine_terminate_all(dma_ch);
@@ -981,7 +993,7 @@ static int stm32_fmc2_xfer(struct nand_chip *chip, const u8 *buf,
 
 	/* Wait DMA data transfer completion */
 	if (!wait_for_completion_timeout(&fmc2->dma_data_complete,
-					 msecs_to_jiffies(100))) {
+					 msecs_to_jiffies(FMC2_TIMEOUT_MS))) {
 		dev_err(fmc2->dev, "data DMA timeout\n");
 		dmaengine_terminate_all(dma_ch);
 		ret = -ETIMEDOUT;
@@ -990,7 +1002,7 @@ static int stm32_fmc2_xfer(struct nand_chip *chip, const u8 *buf,
 	/* Wait DMA ECC transfer completion */
 	if (!write_data && !raw) {
 		if (!wait_for_completion_timeout(&fmc2->dma_ecc_complete,
-						 msecs_to_jiffies(100))) {
+					msecs_to_jiffies(FMC2_TIMEOUT_MS))) {
 			dev_err(fmc2->dev, "ECC DMA timeout\n");
 			dmaengine_terminate_all(fmc2->dma_ecc_ch);
 			ret = -ETIMEDOUT;
@@ -1319,6 +1331,31 @@ static void stm32_fmc2_write_data(struct nand_chip *chip, const void *buf,
 		stm32_fmc2_set_buswidth_16(fmc2, true);
 }
 
+static int stm32_fmc2_waitrdy(struct nand_chip *chip, unsigned long timeout_ms)
+{
+	struct stm32_fmc2_nfc *fmc2 = to_stm32_nfc(chip->controller);
+	const struct nand_sdr_timings *timings;
+	u32 isr, sr;
+
+	/* Check if there is no pending requests to the NAND flash */
+	if (readl_relaxed_poll_timeout_atomic(fmc2->io_base + FMC2_SR, sr,
+					      sr & FMC2_SR_NWRF, 1,
+					      FMC2_TIMEOUT_US))
+		dev_warn(fmc2->dev, "Waitrdy timeout\n");
+
+	/* Wait tWB before R/B# signal is low */
+	timings = nand_get_sdr_timings(&chip->data_interface);
+	ndelay(PSEC_TO_NSEC(timings->tWB_max));
+
+	/* R/B# signal is low, clear high level flag */
+	writel_relaxed(FMC2_ICR_CIHLF, fmc2->io_base + FMC2_ICR);
+
+	/* Wait R/B# signal is high */
+	return readl_relaxed_poll_timeout_atomic(fmc2->io_base + FMC2_ISR,
+						 isr, isr & FMC2_ISR_IHLF,
+						 5, 1000 * timeout_ms);
+}
+
 static int stm32_fmc2_exec_op(struct nand_chip *chip,
 			      const struct nand_operation *op,
 			      bool check_only)
@@ -1363,8 +1400,8 @@ static int stm32_fmc2_exec_op(struct nand_chip *chip,
 			break;
 
 		case NAND_OP_WAITRDY_INSTR:
-			ret = nand_soft_waitrdy(chip,
-						instr->ctx.waitrdy.timeout_ms);
+			ret = stm32_fmc2_waitrdy(chip,
+						 instr->ctx.waitrdy.timeout_ms);
 			break;
 		}
 	}
diff --git a/drivers/mtd/nand/raw/sunxi_nand.c b/drivers/mtd/nand/raw/sunxi_nand.c
index 89773293c64d..45c376fc571a 100644
--- a/drivers/mtd/nand/raw/sunxi_nand.c
+++ b/drivers/mtd/nand/raw/sunxi_nand.c
@@ -2003,7 +2003,7 @@ static int sunxi_nand_chip_init(struct device *dev, struct sunxi_nfc *nfc,
 	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret) {
 		dev_err(dev, "failed to register mtd device: %d\n", ret);
-		nand_release(nand);
+		nand_cleanup(nand);
 		return ret;
 	}
 
diff --git a/drivers/mtd/nand/raw/tmio_nand.c b/drivers/mtd/nand/raw/tmio_nand.c
index db030f1701ee..4e9a6d94f6e8 100644
--- a/drivers/mtd/nand/raw/tmio_nand.c
+++ b/drivers/mtd/nand/raw/tmio_nand.c
@@ -448,7 +448,7 @@ static int tmio_probe(struct platform_device *dev)
 	if (!retval)
 		return retval;
 
-	nand_release(nand_chip);
+	nand_cleanup(nand_chip);
 
 err_irq:
 	tmio_hw_stop(dev, tmio);
diff --git a/drivers/mtd/nand/raw/xway_nand.c b/drivers/mtd/nand/raw/xway_nand.c
index 834f794816a9..018311dc8fe1 100644
--- a/drivers/mtd/nand/raw/xway_nand.c
+++ b/drivers/mtd/nand/raw/xway_nand.c
@@ -210,7 +210,7 @@ static int xway_nand_probe(struct platform_device *pdev)
 
 	err = mtd_device_register(mtd, NULL, 0);
 	if (err)
-		nand_release(&data->chip);
+		nand_cleanup(&data->chip);
 
 	return err;
 }
diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c
index 20560c0b1f5d..40ee9ff6db7c 100644
--- a/drivers/mtd/nand/spi/core.c
+++ b/drivers/mtd/nand/spi/core.c
@@ -568,18 +568,18 @@ static int spinand_mtd_write(struct mtd_info *mtd, loff_t to,
 static bool spinand_isbad(struct nand_device *nand, const struct nand_pos *pos)
 {
 	struct spinand_device *spinand = nand_to_spinand(nand);
+	u8 marker[2] = { };
 	struct nand_page_io_req req = {
 		.pos = *pos,
-		.ooblen = 2,
+		.ooblen = sizeof(marker),
 		.ooboffs = 0,
-		.oobbuf.in = spinand->oobbuf,
+		.oobbuf.in = marker,
 		.mode = MTD_OPS_RAW,
 	};
 
-	memset(spinand->oobbuf, 0, 2);
 	spinand_select_target(spinand, pos->target);
 	spinand_read_page(spinand, &req, false);
-	if (spinand->oobbuf[0] != 0xff || spinand->oobbuf[1] != 0xff)
+	if (marker[0] != 0xff || marker[1] != 0xff)
 		return true;
 
 	return false;
@@ -603,15 +603,16 @@ static int spinand_mtd_block_isbad(struct mtd_info *mtd, loff_t offs)
 static int spinand_markbad(struct nand_device *nand, const struct nand_pos *pos)
 {
 	struct spinand_device *spinand = nand_to_spinand(nand);
+	u8 marker[2] = { };
 	struct nand_page_io_req req = {
 		.pos = *pos,
 		.ooboffs = 0,
-		.ooblen = 2,
-		.oobbuf.out = spinand->oobbuf,
+		.ooblen = sizeof(marker),
+		.oobbuf.out = marker,
+		.mode = MTD_OPS_RAW,
 	};
 	int ret;
 
-	/* Erase block before marking it bad. */
 	ret = spinand_select_target(spinand, pos->target);
 	if (ret)
 		return ret;
@@ -620,9 +621,6 @@ static int spinand_markbad(struct nand_device *nand, const struct nand_pos *pos)
 	if (ret)
 		return ret;
 
-	spinand_erase_op(spinand, pos);
-
-	memset(spinand->oobbuf, 0, 2);
 	return spinand_write_page(spinand, &req);
 }
 
@@ -1050,6 +1048,10 @@ static int spinand_init(struct spinand_device *spinand)
 
 	mtd->oobavail = ret;
 
+	/* Propagate ECC information to mtd_info */
+	mtd->ecc_strength = nand->eccreq.strength;
+	mtd->ecc_step_size = nand->eccreq.step_size;
+
 	return 0;
 
 err_cleanup_nanddev:
diff --git a/drivers/mtd/parsers/sharpslpart.c b/drivers/mtd/parsers/sharpslpart.c
index e5ea6127ab5a..671a61845bd5 100644
--- a/drivers/mtd/parsers/sharpslpart.c
+++ b/drivers/mtd/parsers/sharpslpart.c
@@ -165,10 +165,10 @@ static int sharpsl_nand_get_logical_num(u8 *oob)
 
 static int sharpsl_nand_init_ftl(struct mtd_info *mtd, struct sharpsl_ftl *ftl)
 {
-	unsigned int block_num, log_num, phymax;
+	unsigned int block_num, phymax;
+	int i, ret, log_num;
 	loff_t block_adr;
 	u8 *oob;
-	int i, ret;
 
 	oob = kzalloc(mtd->oobsize, GFP_KERNEL);
 	if (!oob)
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index 33ec2e7d2904..cce45379bc80 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -2172,7 +2172,7 @@ static int spi_nor_read(struct mtd_info *mtd, loff_t from, size_t len,
 			size_t *retlen, u_char *buf)
 {
 	struct spi_nor *nor = mtd_to_spi_nor(mtd);
-	int ret;
+	ssize_t ret;
 
 	dev_dbg(nor->dev, "from 0x%08x, len %zd\n", (u32)from, len);
 
@@ -2492,7 +2492,7 @@ static int spi_nor_hwcaps_pp2cmd(u32 hwcaps)
  */
 static int spi_nor_read_raw(struct spi_nor *nor, u32 addr, size_t len, u8 *buf)
 {
-	int ret;
+	ssize_t ret;
 
 	while (len) {
 		ret = nor->read(nor, addr, len, buf);
@@ -3750,8 +3750,6 @@ static int spi_nor_init_params(struct spi_nor *nor,
 		default:
 			/* Kept only for backward compatibility purpose. */
 			params->quad_enable = spansion_quad_enable;
-			if (nor->clear_sr_bp)
-				nor->clear_sr_bp = spi_nor_spansion_clear_sr_bp;
 			break;
 		}
 
@@ -4005,6 +4003,9 @@ static int spi_nor_init(struct spi_nor *nor)
 	int err;
 
 	if (nor->clear_sr_bp) {
+		if (nor->quad_enable == spansion_quad_enable)
+			nor->clear_sr_bp = spi_nor_spansion_clear_sr_bp;
+
 		err = nor->clear_sr_bp(nor);
 		if (err) {
 			dev_err(nor->dev,
diff --git a/drivers/mtd/ubi/debug.c b/drivers/mtd/ubi/debug.c
index a1dff92ceedf..8a83072401a7 100644
--- a/drivers/mtd/ubi/debug.c
+++ b/drivers/mtd/ubi/debug.c
@@ -392,9 +392,6 @@ static void *eraseblk_count_seq_start(struct seq_file *s, loff_t *pos)
 {
 	struct ubi_device *ubi = s->private;
 
-	if (*pos == 0)
-		return SEQ_START_TOKEN;
-
 	if (*pos < ubi->peb_count)
 		return pos;
 
@@ -408,8 +405,6 @@ static void *eraseblk_count_seq_next(struct seq_file *s, void *v, loff_t *pos)
 {
 	struct ubi_device *ubi = s->private;
 
-	if (v == SEQ_START_TOKEN)
-		return pos;
 	(*pos)++;
 
 	if (*pos < ubi->peb_count)
@@ -431,11 +426,8 @@ static int eraseblk_count_seq_show(struct seq_file *s, void *iter)
 	int err;
 
 	/* If this is the start, print a header */
-	if (iter == SEQ_START_TOKEN) {
-		seq_puts(s,
-			 "physical_block_number\terase_count\tblock_status\tread_status\n");
-		return 0;
-	}
+	if (*block_number == 0)
+		seq_puts(s, "physical_block_number\terase_count\n");
 
 	err = ubi_io_is_bad(ubi, *block_number);
 	if (err)
diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c
index 30621c67721a..604772fc4a96 100644
--- a/drivers/mtd/ubi/fastmap.c
+++ b/drivers/mtd/ubi/fastmap.c
@@ -64,7 +64,7 @@ static int self_check_seen(struct ubi_device *ubi, unsigned long *seen)
 		return 0;
 
 	for (pnum = 0; pnum < ubi->peb_count; pnum++) {
-		if (test_bit(pnum, seen) && ubi->lookuptbl[pnum]) {
+		if (!test_bit(pnum, seen) && ubi->lookuptbl[pnum]) {
 			ubi_err(ubi, "self-check failed for PEB %d, fastmap didn't see it", pnum);
 			ret = -EINVAL;
 		}
@@ -1137,7 +1137,7 @@ static int ubi_write_fastmap(struct ubi_device *ubi,
 	struct rb_node *tmp_rb;
 	int ret, i, j, free_peb_count, used_peb_count, vol_count;
 	int scrub_peb_count, erase_peb_count;
-	unsigned long *seen_pebs = NULL;
+	unsigned long *seen_pebs;
 
 	fm_raw = ubi->fm_buf;
 	memset(ubi->fm_buf, 0, ubi->fm_size);
@@ -1151,7 +1151,7 @@ static int ubi_write_fastmap(struct ubi_device *ubi,
 	dvbuf = new_fm_vbuf(ubi, UBI_FM_DATA_VOLUME_ID);
 	if (!dvbuf) {
 		ret = -ENOMEM;
-		goto out_kfree;
+		goto out_free_avbuf;
 	}
 
 	avhdr = ubi_get_vid_hdr(avbuf);
@@ -1160,7 +1160,7 @@ static int ubi_write_fastmap(struct ubi_device *ubi,
 	seen_pebs = init_seen(ubi);
 	if (IS_ERR(seen_pebs)) {
 		ret = PTR_ERR(seen_pebs);
-		goto out_kfree;
+		goto out_free_dvbuf;
 	}
 
 	spin_lock(&ubi->volumes_lock);
@@ -1328,7 +1328,7 @@ static int ubi_write_fastmap(struct ubi_device *ubi,
 	ret = ubi_io_write_vid_hdr(ubi, new_fm->e[0]->pnum, avbuf);
 	if (ret) {
 		ubi_err(ubi, "unable to write vid_hdr to fastmap SB!");
-		goto out_kfree;
+		goto out_free_seen;
 	}
 
 	for (i = 0; i < new_fm->used_blocks; i++) {
@@ -1350,7 +1350,7 @@ static int ubi_write_fastmap(struct ubi_device *ubi,
 		if (ret) {
 			ubi_err(ubi, "unable to write vid_hdr to PEB %i!",
 				new_fm->e[i]->pnum);
-			goto out_kfree;
+			goto out_free_seen;
 		}
 	}
 
@@ -1360,7 +1360,7 @@ static int ubi_write_fastmap(struct ubi_device *ubi,
 		if (ret) {
 			ubi_err(ubi, "unable to write fastmap to PEB %i!",
 				new_fm->e[i]->pnum);
-			goto out_kfree;
+			goto out_free_seen;
 		}
 	}
 
@@ -1370,10 +1370,13 @@ static int ubi_write_fastmap(struct ubi_device *ubi,
 	ret = self_check_seen(ubi, seen_pebs);
 	dbg_bld("fastmap written!");
 
-out_kfree:
-	ubi_free_vid_buf(avbuf);
-	ubi_free_vid_buf(dvbuf);
+out_free_seen:
 	free_seen(seen_pebs);
+out_free_dvbuf:
+	ubi_free_vid_buf(dvbuf);
+out_free_avbuf:
+	ubi_free_vid_buf(avbuf);
+
 out:
 	return ret;
 }
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 48e209e55843..01c7ff2d006b 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -106,6 +106,7 @@ config NET_FC
 config IFB
 	tristate "Intermediate Functional Block support"
 	depends on NET_CLS_ACT
+	select NET_REDIRECT
 	---help---
 	  This is an intermediate driver that allows sharing of
 	  resources.
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 790e41c6fdd0..2438d5c2746a 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -50,11 +50,6 @@ struct arp_pkt {
 };
 #pragma pack()
 
-static inline struct arp_pkt *arp_pkt(const struct sk_buff *skb)
-{
-	return (struct arp_pkt *)skb_network_header(skb);
-}
-
 /* Forward declaration */
 static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[],
 				      bool strict_match);
@@ -552,10 +547,11 @@ static void rlb_req_update_subnet_clients(struct bonding *bond, __be32 src_ip)
 	spin_unlock(&bond->mode_lock);
 }
 
-static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bond)
+static struct slave *rlb_choose_channel(struct sk_buff *skb,
+					struct bonding *bond,
+					const struct arp_pkt *arp)
 {
 	struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
-	struct arp_pkt *arp = arp_pkt(skb);
 	struct slave *assigned_slave, *curr_active_slave;
 	struct rlb_client_info *client_info;
 	u32 hash_index = 0;
@@ -652,8 +648,12 @@ static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bon
  */
 static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond)
 {
-	struct arp_pkt *arp = arp_pkt(skb);
 	struct slave *tx_slave = NULL;
+	struct arp_pkt *arp;
+
+	if (!pskb_network_may_pull(skb, sizeof(*arp)))
+		return NULL;
+	arp = (struct arp_pkt *)skb_network_header(skb);
 
 	/* Don't modify or load balance ARPs that do not originate locally
 	 * (e.g.,arrive via a bridge).
@@ -663,7 +663,7 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond)
 
 	if (arp->op_code == htons(ARPOP_REPLY)) {
 		/* the arp must be sent on the selected rx channel */
-		tx_slave = rlb_choose_channel(skb, bond);
+		tx_slave = rlb_choose_channel(skb, bond, arp);
 		if (tx_slave)
 			bond_hw_addr_copy(arp->mac_src, tx_slave->dev->dev_addr,
 					  tx_slave->dev->addr_len);
@@ -674,7 +674,7 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond)
 		 * When the arp reply is received the entry will be updated
 		 * with the correct unicast address of the client.
 		 */
-		rlb_choose_channel(skb, bond);
+		rlb_choose_channel(skb, bond, arp);
 
 		/* The ARP reply packets must be delayed so that
 		 * they can cancel out the influence of the ARP request.
@@ -1383,26 +1383,31 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 	bool do_tx_balance = true;
 	u32 hash_index = 0;
 	const u8 *hash_start = NULL;
-	struct ipv6hdr *ip6hdr;
 
 	skb_reset_mac_header(skb);
 	eth_data = eth_hdr(skb);
 
 	switch (ntohs(skb->protocol)) {
 	case ETH_P_IP: {
-		const struct iphdr *iph = ip_hdr(skb);
+		const struct iphdr *iph;
 
 		if (is_broadcast_ether_addr(eth_data->h_dest) ||
-		    iph->daddr == ip_bcast ||
-		    iph->protocol == IPPROTO_IGMP) {
+		    !pskb_network_may_pull(skb, sizeof(*iph))) {
+			do_tx_balance = false;
+			break;
+		}
+		iph = ip_hdr(skb);
+		if (iph->daddr == ip_bcast || iph->protocol == IPPROTO_IGMP) {
 			do_tx_balance = false;
 			break;
 		}
 		hash_start = (char *)&(iph->daddr);
 		hash_size = sizeof(iph->daddr);
-	}
 		break;
-	case ETH_P_IPV6:
+	}
+	case ETH_P_IPV6: {
+		const struct ipv6hdr *ip6hdr;
+
 		/* IPv6 doesn't really use broadcast mac address, but leave
 		 * that here just in case.
 		 */
@@ -1419,7 +1424,11 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 			break;
 		}
 
-		/* Additianally, DAD probes should not be tx-balanced as that
+		if (!pskb_network_may_pull(skb, sizeof(*ip6hdr))) {
+			do_tx_balance = false;
+			break;
+		}
+		/* Additionally, DAD probes should not be tx-balanced as that
 		 * will lead to false positives for duplicate addresses and
 		 * prevent address configuration from working.
 		 */
@@ -1429,17 +1438,26 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 			break;
 		}
 
-		hash_start = (char *)&(ipv6_hdr(skb)->daddr);
-		hash_size = sizeof(ipv6_hdr(skb)->daddr);
+		hash_start = (char *)&ip6hdr->daddr;
+		hash_size = sizeof(ip6hdr->daddr);
 		break;
-	case ETH_P_IPX:
-		if (ipx_hdr(skb)->ipx_checksum != IPX_NO_CHECKSUM) {
+	}
+	case ETH_P_IPX: {
+		const struct ipxhdr *ipxhdr;
+
+		if (pskb_network_may_pull(skb, sizeof(*ipxhdr))) {
+			do_tx_balance = false;
+			break;
+		}
+		ipxhdr = (struct ipxhdr *)skb_network_header(skb);
+
+		if (ipxhdr->ipx_checksum != IPX_NO_CHECKSUM) {
 			/* something is wrong with this packet */
 			do_tx_balance = false;
 			break;
 		}
 
-		if (ipx_hdr(skb)->ipx_type != IPX_TYPE_NCP) {
+		if (ipxhdr->ipx_type != IPX_TYPE_NCP) {
 			/* The only protocol worth balancing in
 			 * this family since it has an "ARP" like
 			 * mechanism
@@ -1448,9 +1466,11 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 			break;
 		}
 
+		eth_data = eth_hdr(skb);
 		hash_start = (char *)eth_data->h_dest;
 		hash_size = ETH_ALEN;
 		break;
+	}
 	case ETH_P_ARP:
 		do_tx_balance = false;
 		if (bond_info->rlb_enabled)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 965c46073860..350d960a3839 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3455,6 +3455,47 @@ static int bond_get_nest_level(struct net_device *bond_dev)
 	return bond->nest_level;
 }
 
+#ifdef CONFIG_LOCKDEP
+static int bond_get_lowest_level_rcu(struct net_device *dev)
+{
+	struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+	struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+	int cur = 0, max = 0;
+
+	now = dev;
+	iter = &dev->adj_list.lower;
+
+	while (1) {
+		next = NULL;
+		while (1) {
+			ldev = netdev_next_lower_dev_rcu(now, &iter);
+			if (!ldev)
+				break;
+
+			next = ldev;
+			niter = &ldev->adj_list.lower;
+			dev_stack[cur] = now;
+			iter_stack[cur++] = iter;
+			if (max <= cur)
+				max = cur;
+			break;
+		}
+
+		if (!next) {
+			if (!cur)
+				return max;
+			next = dev_stack[--cur];
+			niter = iter_stack[cur];
+		}
+
+		now = next;
+		iter = niter;
+	}
+
+	return max;
+}
+#endif
+
 static void bond_get_stats(struct net_device *bond_dev,
 			   struct rtnl_link_stats64 *stats)
 {
@@ -3462,11 +3503,17 @@ static void bond_get_stats(struct net_device *bond_dev,
 	struct rtnl_link_stats64 temp;
 	struct list_head *iter;
 	struct slave *slave;
+	int nest_level = 0;
 
-	spin_lock(&bond->stats_lock);
-	memcpy(stats, &bond->bond_stats, sizeof(*stats));
 
 	rcu_read_lock();
+#ifdef CONFIG_LOCKDEP
+	nest_level = bond_get_lowest_level_rcu(bond_dev);
+#endif
+
+	spin_lock_nested(&bond->stats_lock, nest_level);
+	memcpy(stats, &bond->bond_stats, sizeof(*stats));
+
 	bond_for_each_slave_rcu(bond, slave, iter) {
 		const struct rtnl_link_stats64 *new =
 			dev_get_stats(slave->dev, &temp);
@@ -3476,10 +3523,10 @@ static void bond_get_stats(struct net_device *bond_dev,
 		/* save off the slave stats for the next run */
 		memcpy(&slave->slave_stats, new, sizeof(*new));
 	}
-	rcu_read_unlock();
 
 	memcpy(&bond->bond_stats, stats, sizeof(*stats));
 	spin_unlock(&bond->stats_lock);
+	rcu_read_unlock();
 }
 
 static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd)
@@ -4838,15 +4885,19 @@ int bond_create(struct net *net, const char *name)
 	bond_dev->rtnl_link_ops = &bond_link_ops;
 
 	res = register_netdevice(bond_dev);
+	if (res < 0) {
+		free_netdev(bond_dev);
+		rtnl_unlock();
+
+		return res;
+	}
 
 	netif_carrier_off(bond_dev);
 
 	bond_work_init_all(bond);
 
 	rtnl_unlock();
-	if (res < 0)
-		free_netdev(bond_dev);
-	return res;
+	return 0;
 }
 
 static int __net_init bond_net_init(struct net *net)
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index b24cce48ae35..c3dfbd26b62b 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -447,11 +447,10 @@ static int bond_newlink(struct net *src_net, struct net_device *bond_dev,
 		return err;
 
 	err = register_netdevice(bond_dev);
-
-	netif_carrier_off(bond_dev);
 	if (!err) {
 		struct bonding *bond = netdev_priv(bond_dev);
 
+		netif_carrier_off(bond_dev);
 		bond_work_init_all(bond);
 	}
 
diff --git a/drivers/net/bonding/bond_sysfs_slave.c b/drivers/net/bonding/bond_sysfs_slave.c
index 007481557191..9b8346638f69 100644
--- a/drivers/net/bonding/bond_sysfs_slave.c
+++ b/drivers/net/bonding/bond_sysfs_slave.c
@@ -149,8 +149,10 @@ int bond_sysfs_slave_add(struct slave *slave)
 
 	err = kobject_init_and_add(&slave->kobj, &slave_ktype,
 				   &(slave->dev->dev.kobj), "bonding_slave");
-	if (err)
+	if (err) {
+		kobject_put(&slave->kobj);
 		return err;
+	}
 
 	for (a = slave_attrs; *a; ++a) {
 		err = sysfs_create_file(&slave->kobj, &((*a)->attr));
diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 99fa712b48b3..0bceae971a35 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -881,6 +881,7 @@ static const struct nla_policy can_policy[IFLA_CAN_MAX + 1] = {
 				= { .len = sizeof(struct can_bittiming) },
 	[IFLA_CAN_DATA_BITTIMING_CONST]
 				= { .len = sizeof(struct can_bittiming_const) },
+	[IFLA_CAN_TERMINATION]	= { .type = NLA_U16 },
 };
 
 static int can_validate(struct nlattr *tb[], struct nlattr *data[],
diff --git a/drivers/net/can/mscan/mscan.c b/drivers/net/can/mscan/mscan.c
index 8caf7af0dee2..99101d7027a8 100644
--- a/drivers/net/can/mscan/mscan.c
+++ b/drivers/net/can/mscan/mscan.c
@@ -381,13 +381,12 @@ static int mscan_rx_poll(struct napi_struct *napi, int quota)
 	struct net_device *dev = napi->dev;
 	struct mscan_regs __iomem *regs = priv->reg_base;
 	struct net_device_stats *stats = &dev->stats;
-	int npackets = 0;
-	int ret = 1;
+	int work_done = 0;
 	struct sk_buff *skb;
 	struct can_frame *frame;
 	u8 canrflg;
 
-	while (npackets < quota) {
+	while (work_done < quota) {
 		canrflg = in_8(&regs->canrflg);
 		if (!(canrflg & (MSCAN_RXF | MSCAN_ERR_IF)))
 			break;
@@ -408,18 +407,18 @@ static int mscan_rx_poll(struct napi_struct *napi, int quota)
 
 		stats->rx_packets++;
 		stats->rx_bytes += frame->can_dlc;
-		npackets++;
+		work_done++;
 		netif_receive_skb(skb);
 	}
 
-	if (!(in_8(&regs->canrflg) & (MSCAN_RXF | MSCAN_ERR_IF))) {
-		napi_complete(&priv->napi);
-		clear_bit(F_RX_PROGRESS, &priv->flags);
-		if (priv->can.state < CAN_STATE_BUS_OFF)
-			out_8(&regs->canrier, priv->shadow_canrier);
-		ret = 0;
+	if (work_done < quota) {
+		if (likely(napi_complete_done(&priv->napi, work_done))) {
+			clear_bit(F_RX_PROGRESS, &priv->flags);
+			if (priv->can.state < CAN_STATE_BUS_OFF)
+				out_8(&regs->canrier, priv->shadow_canrier);
+		}
 	}
-	return ret;
+	return work_done;
 }
 
 static irqreturn_t mscan_isr(int irq, void *dev_id)
diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c
index cf0769ad39cd..f99cd94509be 100644
--- a/drivers/net/can/slcan.c
+++ b/drivers/net/can/slcan.c
@@ -147,7 +147,7 @@ static void slc_bump(struct slcan *sl)
 	u32 tmpid;
 	char *cmd = sl->rbuff;
 
-	cf.can_id = 0;
+	memset(&cf, 0, sizeof(cf));
 
 	switch (*cmd) {
 	case 'r':
@@ -186,8 +186,6 @@ static void slc_bump(struct slcan *sl)
 	else
 		return;
 
-	*(u64 *) (&cf.data) = 0; /* clear payload */
-
 	/* RTR frames may have a dlc > 0 but they never have any data bytes */
 	if (!(cf.can_id & CAN_RTR_FLAG)) {
 		for (i = 0; i < cf.can_dlc; i++) {
@@ -343,9 +341,16 @@ static void slcan_transmit(struct work_struct *work)
  */
 static void slcan_write_wakeup(struct tty_struct *tty)
 {
-	struct slcan *sl = tty->disc_data;
+	struct slcan *sl;
+
+	rcu_read_lock();
+	sl = rcu_dereference(tty->disc_data);
+	if (!sl)
+		goto out;
 
 	schedule_work(&sl->tx_work);
+out:
+	rcu_read_unlock();
 }
 
 /* Send a can_frame to a TTY queue. */
@@ -614,7 +619,10 @@ err_free_chan:
 	tty->disc_data = NULL;
 	clear_bit(SLF_INUSE, &sl->flags);
 	slc_free_netdev(sl->dev);
+	/* do not call free_netdev before rtnl_unlock */
+	rtnl_unlock();
 	free_netdev(sl->dev);
+	return err;
 
 err_exit:
 	rtnl_unlock();
@@ -640,10 +648,11 @@ static void slcan_close(struct tty_struct *tty)
 		return;
 
 	spin_lock_bh(&sl->lock);
-	tty->disc_data = NULL;
+	rcu_assign_pointer(tty->disc_data, NULL);
 	sl->tty = NULL;
 	spin_unlock_bh(&sl->lock);
 
+	synchronize_rcu();
 	flush_work(&sl->tx_work);
 
 	/* Flush network side */
diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index 2f74f6704c12..a4b4b742c80c 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -918,7 +918,7 @@ static int gs_usb_probe(struct usb_interface *intf,
 			     GS_USB_BREQ_HOST_FORMAT,
 			     USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_INTERFACE,
 			     1,
-			     intf->altsetting[0].desc.bInterfaceNumber,
+			     intf->cur_altsetting->desc.bInterfaceNumber,
 			     hconf,
 			     sizeof(*hconf),
 			     1000);
@@ -941,7 +941,7 @@ static int gs_usb_probe(struct usb_interface *intf,
 			     GS_USB_BREQ_DEVICE_CONFIG,
 			     USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_INTERFACE,
 			     1,
-			     intf->altsetting[0].desc.bInterfaceNumber,
+			     intf->cur_altsetting->desc.bInterfaceNumber,
 			     dconf,
 			     sizeof(*dconf),
 			     1000);
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
index 5fc0be564274..7ab87a758754 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
@@ -1590,7 +1590,7 @@ static int kvaser_usb_hydra_setup_endpoints(struct kvaser_usb *dev)
 	struct usb_endpoint_descriptor *ep;
 	int i;
 
-	iface_desc = &dev->intf->altsetting[0];
+	iface_desc = dev->intf->cur_altsetting;
 
 	for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) {
 		ep = &iface_desc->endpoint[i].desc;
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
index ae4c37e1bb75..1b9957f12459 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
@@ -1310,7 +1310,7 @@ static int kvaser_usb_leaf_setup_endpoints(struct kvaser_usb *dev)
 	struct usb_endpoint_descriptor *endpoint;
 	int i;
 
-	iface_desc = &dev->intf->altsetting[0];
+	iface_desc = dev->intf->cur_altsetting;
 
 	for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) {
 		endpoint = &iface_desc->endpoint[i].desc;
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 3f728d609400..5ec898e4d6e1 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -664,7 +664,7 @@ int b53_configure_vlan(struct dsa_switch *ds)
 		b53_do_vlan_op(dev, VTA_CMD_CLEAR);
 	}
 
-	b53_enable_vlan(dev, false, ds->vlan_filtering);
+	b53_enable_vlan(dev, dev->vlan_enabled, ds->vlan_filtering);
 
 	b53_for_each_port(dev, i)
 		b53_write16(dev, B53_VLAN_PAGE,
@@ -1337,6 +1337,9 @@ void b53_vlan_add(struct dsa_switch *ds, int port,
 
 		b53_get_vlan_entry(dev, vid, vl);
 
+		if (vid == 0 && vid == b53_default_pvid(dev))
+			untagged = true;
+
 		vl->members |= BIT(port);
 		if (untagged && !dsa_is_cpu_port(ds, port))
 			vl->untag |= BIT(port);
@@ -1422,6 +1425,10 @@ static int b53_arl_rw_op(struct b53_device *dev, unsigned int op)
 		reg |= ARLTBL_RW;
 	else
 		reg &= ~ARLTBL_RW;
+	if (dev->vlan_enabled)
+		reg &= ~ARLTBL_IVL_SVL_SELECT;
+	else
+		reg |= ARLTBL_IVL_SVL_SELECT;
 	b53_write8(dev, B53_ARLIO_PAGE, B53_ARLTBL_RW_CTRL, reg);
 
 	return b53_arl_op_wait(dev);
@@ -1431,6 +1438,7 @@ static int b53_arl_read(struct b53_device *dev, u64 mac,
 			u16 vid, struct b53_arl_entry *ent, u8 *idx,
 			bool is_valid)
 {
+	DECLARE_BITMAP(free_bins, B53_ARLTBL_MAX_BIN_ENTRIES);
 	unsigned int i;
 	int ret;
 
@@ -1438,6 +1446,8 @@ static int b53_arl_read(struct b53_device *dev, u64 mac,
 	if (ret)
 		return ret;
 
+	bitmap_zero(free_bins, dev->num_arl_entries);
+
 	/* Read the bins */
 	for (i = 0; i < dev->num_arl_entries; i++) {
 		u64 mac_vid;
@@ -1449,13 +1459,24 @@ static int b53_arl_read(struct b53_device *dev, u64 mac,
 			   B53_ARLTBL_DATA_ENTRY(i), &fwd_entry);
 		b53_arl_to_entry(ent, mac_vid, fwd_entry);
 
-		if (!(fwd_entry & ARLTBL_VALID))
+		if (!(fwd_entry & ARLTBL_VALID)) {
+			set_bit(i, free_bins);
 			continue;
+		}
 		if ((mac_vid & ARLTBL_MAC_MASK) != mac)
 			continue;
+		if (dev->vlan_enabled &&
+		    ((mac_vid >> ARLTBL_VID_S) & ARLTBL_VID_MASK) != vid)
+			continue;
 		*idx = i;
+		return 0;
 	}
 
+	if (bitmap_weight(free_bins, dev->num_arl_entries) == 0)
+		return -ENOSPC;
+
+	*idx = find_first_bit(free_bins, dev->num_arl_entries);
+
 	return -ENOENT;
 }
 
@@ -1485,10 +1506,21 @@ static int b53_arl_op(struct b53_device *dev, int op, int port,
 	if (op)
 		return ret;
 
-	/* We could not find a matching MAC, so reset to a new entry */
-	if (ret) {
+	switch (ret) {
+	case -ENOSPC:
+		dev_dbg(dev->dev, "{%pM,%.4d} no space left in ARL\n",
+			addr, vid);
+		return is_valid ? ret : 0;
+	case -ENOENT:
+		/* We could not find a matching MAC, so reset to a new entry */
+		dev_dbg(dev->dev, "{%pM,%.4d} not found, using idx: %d\n",
+			addr, vid, idx);
 		fwd_entry = 0;
-		idx = 1;
+		break;
+	default:
+		dev_dbg(dev->dev, "{%pM,%.4d} found, using idx: %d\n",
+			addr, vid, idx);
+		break;
 	}
 
 	memset(&ent, 0, sizeof(ent));
diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h
index 2a9f421680aa..c90985c294a2 100644
--- a/drivers/net/dsa/b53/b53_regs.h
+++ b/drivers/net/dsa/b53/b53_regs.h
@@ -292,6 +292,7 @@
 /* ARL Table Read/Write Register (8 bit) */
 #define B53_ARLTBL_RW_CTRL		0x00
 #define    ARLTBL_RW			BIT(0)
+#define    ARLTBL_IVL_SVL_SELECT	BIT(6)
 #define    ARLTBL_START_DONE		BIT(7)
 
 /* MAC Address Index Register (48 bit) */
@@ -304,7 +305,7 @@
  *
  * BCM5325 and BCM5365 share most definitions below
  */
-#define B53_ARLTBL_MAC_VID_ENTRY(n)	(0x10 * (n))
+#define B53_ARLTBL_MAC_VID_ENTRY(n)	((0x10 * (n)) + 0x10)
 #define   ARLTBL_MAC_MASK		0xffffffffffffULL
 #define   ARLTBL_VID_S			48
 #define   ARLTBL_VID_MASK_25		0xff
@@ -316,13 +317,16 @@
 #define   ARLTBL_VALID_25		BIT(63)
 
 /* ARL Table Data Entry N Registers (32 bit) */
-#define B53_ARLTBL_DATA_ENTRY(n)	((0x10 * (n)) + 0x08)
+#define B53_ARLTBL_DATA_ENTRY(n)	((0x10 * (n)) + 0x18)
 #define   ARLTBL_DATA_PORT_ID_MASK	0x1ff
 #define   ARLTBL_TC(tc)			((3 & tc) << 11)
 #define   ARLTBL_AGE			BIT(14)
 #define   ARLTBL_STATIC			BIT(15)
 #define   ARLTBL_VALID			BIT(16)
 
+/* Maximum number of bin entries in the ARL for all switches */
+#define B53_ARLTBL_MAX_BIN_ENTRIES	4
+
 /* ARL Search Control Register (8 bit) */
 #define B53_ARL_SRCH_CTL		0x50
 #define B53_ARL_SRCH_CTL_25		0x20
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index ac9e88813cd5..2cf0a17f83bd 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -69,6 +69,7 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port)
 		/* Force link status for IMP port */
 		reg = core_readl(priv, offset);
 		reg |= (MII_SW_OR | LINK_STS);
+		reg &= ~GMII_SPEED_UP_2G;
 		core_writel(priv, reg, offset);
 
 		/* Enable Broadcast, Multicast, Unicast forwarding to IMP port */
@@ -455,7 +456,7 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds)
 	priv->slave_mii_bus->parent = ds->dev->parent;
 	priv->slave_mii_bus->phy_mask = ~priv->indir_phy_mask;
 
-	err = of_mdiobus_register(priv->slave_mii_bus, dn);
+	err = mdiobus_register(priv->slave_mii_bus);
 	if (err && dn)
 		of_node_put(dn);
 
@@ -1043,6 +1044,7 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev)
 	const struct bcm_sf2_of_data *data;
 	struct b53_platform_data *pdata;
 	struct dsa_switch_ops *ops;
+	struct device_node *ports;
 	struct bcm_sf2_priv *priv;
 	struct b53_device *dev;
 	struct dsa_switch *ds;
@@ -1106,7 +1108,13 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev)
 	set_bit(0, priv->cfp.used);
 	set_bit(0, priv->cfp.unique);
 
-	bcm_sf2_identify_ports(priv, dn->child);
+	/* Balance of_node_put() done by of_find_node_by_name() */
+	of_node_get(dn);
+	ports = of_find_node_by_name(dn, "ports");
+	if (ports) {
+		bcm_sf2_identify_ports(priv, ports);
+		of_node_put(ports);
+	}
 
 	priv->irq0 = irq_of_parse_and_map(dn, 0);
 	priv->irq1 = irq_of_parse_and_map(dn, 1);
diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index 471837cf0b21..e15d18bb981e 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -882,17 +882,14 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
 	     fs->m_ext.data[1]))
 		return -EINVAL;
 
-	if (fs->location != RX_CLS_LOC_ANY && fs->location >= CFP_NUM_RULES)
+	if (fs->location != RX_CLS_LOC_ANY &&
+	    fs->location > bcm_sf2_cfp_rule_size(priv))
 		return -EINVAL;
 
 	if (fs->location != RX_CLS_LOC_ANY &&
 	    test_bit(fs->location, priv->cfp.used))
 		return -EBUSY;
 
-	if (fs->location != RX_CLS_LOC_ANY &&
-	    fs->location > bcm_sf2_cfp_rule_size(priv))
-		return -EINVAL;
-
 	ret = bcm_sf2_cfp_rule_cmp(priv, port, fs);
 	if (ret == 0)
 		return -EEXIST;
@@ -973,7 +970,7 @@ static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port, u32 loc)
 	struct cfp_rule *rule;
 	int ret;
 
-	if (loc >= CFP_NUM_RULES)
+	if (loc > bcm_sf2_cfp_rule_size(priv))
 		return -EINVAL;
 
 	/* Refuse deleting unused rules, and those that are not unique since
diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c
index 925ed135a4d9..0df6c2b9484a 100644
--- a/drivers/net/dsa/dsa_loop.c
+++ b/drivers/net/dsa/dsa_loop.c
@@ -356,6 +356,7 @@ static void __exit dsa_loop_exit(void)
 }
 module_exit(dsa_loop_exit);
 
+MODULE_SOFTDEP("pre: dsa_loop_bdinfo");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Florian Fainelli");
 MODULE_DESCRIPTION("DSA loopback driver");
diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c
index 4e64835deac2..ecaa6690f159 100644
--- a/drivers/net/dsa/lantiq_gswip.c
+++ b/drivers/net/dsa/lantiq_gswip.c
@@ -1445,7 +1445,8 @@ static void gswip_phylink_validate(struct dsa_switch *ds, int port,
 
 unsupported:
 	bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS);
-	dev_err(ds->dev, "Unsupported interface: %d\n", state->interface);
+	dev_err(ds->dev, "Unsupported interface '%s' for port %d\n",
+		phy_modes(state->interface), port);
 	return;
 }
 
diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
index c026d15721f6..40dbe94bf9eb 100644
--- a/drivers/net/dsa/microchip/ksz9477.c
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -1009,23 +1009,6 @@ static void ksz9477_port_mirror_del(struct dsa_switch *ds, int port,
 			     PORT_MIRROR_SNIFFER, false);
 }
 
-static void ksz9477_phy_setup(struct ksz_device *dev, int port,
-			      struct phy_device *phy)
-{
-	/* Only apply to port with PHY. */
-	if (port >= dev->phy_port_cnt)
-		return;
-
-	/* The MAC actually cannot run in 1000 half-duplex mode. */
-	phy_remove_link_mode(phy,
-			     ETHTOOL_LINK_MODE_1000baseT_Half_BIT);
-
-	/* PHY does not support gigabit. */
-	if (!(dev->features & GBIT_SUPPORT))
-		phy_remove_link_mode(phy,
-				     ETHTOOL_LINK_MODE_1000baseT_Full_BIT);
-}
-
 static bool ksz9477_get_gbit(struct ksz_device *dev, u8 data)
 {
 	bool gbit;
@@ -1552,6 +1535,9 @@ static int ksz9477_switch_init(struct ksz_device *dev)
 			return -ENOMEM;
 	}
 
+	/* set the real number of ports */
+	dev->ds->num_ports = dev->port_cnt;
+
 	return 0;
 }
 
@@ -1564,7 +1550,6 @@ static const struct ksz_dev_ops ksz9477_dev_ops = {
 	.get_port_addr = ksz9477_get_port_addr,
 	.cfg_port_member = ksz9477_cfg_port_member,
 	.flush_dyn_mac_table = ksz9477_flush_dyn_mac_table,
-	.phy_setup = ksz9477_phy_setup,
 	.port_setup = ksz9477_port_setup,
 	.r_mib_cnt = ksz9477_r_mib_cnt,
 	.r_mib_pkt = ksz9477_r_mib_pkt,
@@ -1578,7 +1563,29 @@ static const struct ksz_dev_ops ksz9477_dev_ops = {
 
 int ksz9477_switch_register(struct ksz_device *dev)
 {
-	return ksz_switch_register(dev, &ksz9477_dev_ops);
+	int ret, i;
+	struct phy_device *phydev;
+
+	ret = ksz_switch_register(dev, &ksz9477_dev_ops);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < dev->phy_port_cnt; ++i) {
+		if (!dsa_is_user_port(dev->ds, i))
+			continue;
+
+		phydev = dsa_to_port(dev->ds, i)->slave->phydev;
+
+		/* The MAC actually cannot run in 1000 half-duplex mode. */
+		phy_remove_link_mode(phydev,
+				     ETHTOOL_LINK_MODE_1000baseT_Half_BIT);
+
+		/* PHY does not support gigabit. */
+		if (!(dev->features & GBIT_SUPPORT))
+			phy_remove_link_mode(phydev,
+					     ETHTOOL_LINK_MODE_1000baseT_Full_BIT);
+	}
+	return ret;
 }
 EXPORT_SYMBOL(ksz9477_switch_register);
 
diff --git a/drivers/net/dsa/microchip/ksz9477_spi.c b/drivers/net/dsa/microchip/ksz9477_spi.c
index fb15f255a1db..7419cf446783 100644
--- a/drivers/net/dsa/microchip/ksz9477_spi.c
+++ b/drivers/net/dsa/microchip/ksz9477_spi.c
@@ -175,6 +175,12 @@ static struct spi_driver ksz9477_spi_driver = {
 
 module_spi_driver(ksz9477_spi_driver);
 
+MODULE_ALIAS("spi:ksz9477");
+MODULE_ALIAS("spi:ksz9897");
+MODULE_ALIAS("spi:ksz9893");
+MODULE_ALIAS("spi:ksz9563");
+MODULE_ALIAS("spi:ksz8563");
+MODULE_ALIAS("spi:ksz9567");
 MODULE_AUTHOR("Woojung Huh <Woojung.Huh@microchip.com>");
 MODULE_DESCRIPTION("Microchip KSZ9477 Series Switch SPI access Driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index db91b213eae1..158644e592d2 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -373,7 +373,6 @@ int ksz_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy)
 
 	/* setup slave port */
 	dev->dev_ops->port_setup(dev, port, false);
-	dev->dev_ops->phy_setup(dev, port, phy);
 
 	/* port_stp_state_set() will be called after to enable the port so
 	 * there is no need to do anything.
diff --git a/drivers/net/dsa/microchip/ksz_priv.h b/drivers/net/dsa/microchip/ksz_priv.h
index b52e5ca17ab4..ef3156df7d58 100644
--- a/drivers/net/dsa/microchip/ksz_priv.h
+++ b/drivers/net/dsa/microchip/ksz_priv.h
@@ -136,8 +136,6 @@ struct ksz_dev_ops {
 	u32 (*get_port_addr)(int port, int offset);
 	void (*cfg_port_member)(struct ksz_device *dev, int port, u8 member);
 	void (*flush_dyn_mac_table)(struct ksz_device *dev, int port);
-	void (*phy_setup)(struct ksz_device *dev, int port,
-			  struct phy_device *phy);
 	void (*port_cleanup)(struct ksz_device *dev, int port);
 	void (*port_setup)(struct ksz_device *dev, int port, bool cpu_port);
 	void (*r_phy)(struct ksz_device *dev, u16 phy, u16 reg, u16 *val);
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index c7d352da5448..4a9d934d112d 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -675,11 +675,8 @@ mt7530_cpu_port_enable(struct mt7530_priv *priv,
 	/* Setup the MAC by default for the cpu port */
 	mt7530_write(priv, MT7530_PMCR_P(port), PMCR_CPUP_LINK);
 
-	/* Disable auto learning on the cpu port */
-	mt7530_set(priv, MT7530_PSC_P(port), SA_DIS);
-
-	/* Unknown unicast frame fordwarding to the cpu port */
-	mt7530_set(priv, MT7530_MFC, UNU_FFP(BIT(port)));
+	/* Unknown multicast frame forwarding to the cpu port */
+	mt7530_rmw(priv, MT7530_MFC, UNM_FFP_MASK, UNM_FFP(BIT(port)));
 
 	/* Set CPU port number */
 	if (priv->id == ID_MT7621)
@@ -817,8 +814,9 @@ mt7530_port_set_vlan_unaware(struct dsa_switch *ds, int port)
 	 */
 	mt7530_rmw(priv, MT7530_PCR_P(port), PCR_PORT_VLAN_MASK,
 		   MT7530_PORT_MATRIX_MODE);
-	mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK,
-		   VLAN_ATTR(MT7530_VLAN_TRANSPARENT));
+	mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK | PVC_EG_TAG_MASK,
+		   VLAN_ATTR(MT7530_VLAN_TRANSPARENT) |
+		   PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT));
 
 	for (i = 0; i < MT7530_NUM_PORTS; i++) {
 		if (dsa_is_user_port(ds, i) &&
@@ -834,8 +832,8 @@ mt7530_port_set_vlan_unaware(struct dsa_switch *ds, int port)
 	if (all_user_ports_removed) {
 		mt7530_write(priv, MT7530_PCR_P(MT7530_CPU_PORT),
 			     PCR_MATRIX(dsa_user_ports(priv->ds)));
-		mt7530_write(priv, MT7530_PVC_P(MT7530_CPU_PORT),
-			     PORT_SPEC_TAG);
+		mt7530_write(priv, MT7530_PVC_P(MT7530_CPU_PORT), PORT_SPEC_TAG
+			     | PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT));
 	}
 }
 
@@ -853,16 +851,22 @@ mt7530_port_set_vlan_aware(struct dsa_switch *ds, int port)
 		   PCR_MATRIX_MASK, PCR_MATRIX(MT7530_ALL_MEMBERS));
 
 	/* Trapped into security mode allows packet forwarding through VLAN
-	 * table lookup.
+	 * table lookup. CPU port is set to fallback mode to let untagged
+	 * frames pass through.
 	 */
-	mt7530_rmw(priv, MT7530_PCR_P(port), PCR_PORT_VLAN_MASK,
-		   MT7530_PORT_SECURITY_MODE);
+	if (dsa_is_cpu_port(ds, port))
+		mt7530_rmw(priv, MT7530_PCR_P(port), PCR_PORT_VLAN_MASK,
+			   MT7530_PORT_FALLBACK_MODE);
+	else
+		mt7530_rmw(priv, MT7530_PCR_P(port), PCR_PORT_VLAN_MASK,
+			   MT7530_PORT_SECURITY_MODE);
 
 	/* Set the port as a user port which is to be able to recognize VID
 	 * from incoming packets before fetching entry within the VLAN table.
 	 */
-	mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK,
-		   VLAN_ATTR(MT7530_VLAN_USER));
+	mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK | PVC_EG_TAG_MASK,
+		   VLAN_ATTR(MT7530_VLAN_USER) |
+		   PVC_EG_TAG(MT7530_VLAN_EG_DISABLED));
 }
 
 static void
@@ -1276,8 +1280,6 @@ mt7530_setup(struct dsa_switch *ds)
 	/* Enable and reset MIB counters */
 	mt7530_mib_reset(ds);
 
-	mt7530_clear(priv, MT7530_MFC, UNU_FFP_MASK);
-
 	for (i = 0; i < MT7530_NUM_PORTS; i++) {
 		/* Disable forwarding by default on all ports */
 		mt7530_rmw(priv, MT7530_PCR_P(i), PCR_MATRIX_MASK,
@@ -1287,6 +1289,10 @@ mt7530_setup(struct dsa_switch *ds)
 			mt7530_cpu_port_enable(priv, i);
 		else
 			mt7530_port_disable(ds, i);
+
+		/* Enable consistent egress tag */
+		mt7530_rmw(priv, MT7530_PVC_P(i), PVC_EG_TAG_MASK,
+			   PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT));
 	}
 
 	/* Flush the FDB table */
diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h
index 4331429969fa..7ef1f0f829c1 100644
--- a/drivers/net/dsa/mt7530.h
+++ b/drivers/net/dsa/mt7530.h
@@ -31,6 +31,7 @@ enum {
 #define MT7530_MFC			0x10
 #define  BC_FFP(x)			(((x) & 0xff) << 24)
 #define  UNM_FFP(x)			(((x) & 0xff) << 16)
+#define  UNM_FFP_MASK			UNM_FFP(~0)
 #define  UNU_FFP(x)			(((x) & 0xff) << 8)
 #define  UNU_FFP_MASK			UNU_FFP(~0)
 #define  CPU_EN				BIT(7)
@@ -147,6 +148,12 @@ enum mt7530_port_mode {
 	/* Port Matrix Mode: Frames are forwarded by the PCR_MATRIX members. */
 	MT7530_PORT_MATRIX_MODE = PORT_VLAN(0),
 
+	/* Fallback Mode: Forward received frames with ingress ports that do
+	 * not belong to the VLAN member. Frames whose VID is not listed on
+	 * the VLAN table are forwarded by the PCR_MATRIX members.
+	 */
+	MT7530_PORT_FALLBACK_MODE = PORT_VLAN(1),
+
 	/* Security Mode: Discard any frame due to ingress membership
 	 * violation or VID missed on the VLAN table.
 	 */
@@ -167,9 +174,16 @@ enum mt7530_port_mode {
 /* Register for port vlan control */
 #define MT7530_PVC_P(x)			(0x2010 + ((x) * 0x100))
 #define  PORT_SPEC_TAG			BIT(5)
+#define  PVC_EG_TAG(x)			(((x) & 0x7) << 8)
+#define  PVC_EG_TAG_MASK		PVC_EG_TAG(7)
 #define  VLAN_ATTR(x)			(((x) & 0x3) << 6)
 #define  VLAN_ATTR_MASK			VLAN_ATTR(3)
 
+enum mt7530_vlan_port_eg_tag {
+	MT7530_VLAN_EG_DISABLED = 0,
+	MT7530_VLAN_EG_CONSISTENT = 1,
+};
+
 enum mt7530_vlan_port_attr {
 	MT7530_VLAN_USER = 0,
 	MT7530_VLAN_TRANSPARENT = 3,
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 2e8b1ab2c6f7..d8b2d1310029 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -2844,7 +2844,6 @@ static const struct mv88e6xxx_ops mv88e6097_ops = {
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
 	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_set_ether_type = mv88e6351_port_set_ether_type,
-	.port_set_jumbo_size = mv88e6165_port_set_jumbo_size,
 	.port_egress_rate_limiting = mv88e6095_port_egress_rate_limiting,
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c
index 09b8a3d0dd37..92efcf724d7e 100644
--- a/drivers/net/dsa/mv88e6xxx/global1.c
+++ b/drivers/net/dsa/mv88e6xxx/global1.c
@@ -367,6 +367,11 @@ int mv88e6390_g1_set_cpu_port(struct mv88e6xxx_chip *chip, int port)
 {
 	u16 ptr = MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST;
 
+	/* Use the default high priority for management frames sent to
+	 * the CPU.
+	 */
+	port |= MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST_MGMTPRI;
+
 	return mv88e6390_g1_monitor_write(chip, ptr, port);
 }
 
diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h
index 7bd5ab733a3f..9b330c343aaa 100644
--- a/drivers/net/dsa/mv88e6xxx/global1.h
+++ b/drivers/net/dsa/mv88e6xxx/global1.h
@@ -193,6 +193,7 @@
 #define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_INGRESS_DEST		0x2000
 #define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_EGRESS_DEST		0x2100
 #define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST		0x3000
+#define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST_MGMTPRI	0x00e0
 #define MV88E6390_G1_MONITOR_MGMT_CTL_DATA_MASK			0x00ff
 
 /* Offset 0x1C: Global Control 2 */
diff --git a/drivers/net/dsa/mv88e6xxx/global2.c b/drivers/net/dsa/mv88e6xxx/global2.c
index 1546171210a1..d70f08cfcaf8 100644
--- a/drivers/net/dsa/mv88e6xxx/global2.c
+++ b/drivers/net/dsa/mv88e6xxx/global2.c
@@ -1043,6 +1043,13 @@ int mv88e6xxx_g2_irq_setup(struct mv88e6xxx_chip *chip)
 {
 	int err, irq, virq;
 
+	chip->g2_irq.masked = ~0;
+	mutex_lock(&chip->reg_lock);
+	err = mv88e6xxx_g2_int_mask(chip, ~chip->g2_irq.masked);
+	mutex_unlock(&chip->reg_lock);
+	if (err)
+		return err;
+
 	chip->g2_irq.domain = irq_domain_add_simple(
 		chip->dev->of_node, 16, 0, &mv88e6xxx_g2_irq_domain_ops, chip);
 	if (!chip->g2_irq.domain)
@@ -1052,7 +1059,6 @@ int mv88e6xxx_g2_irq_setup(struct mv88e6xxx_chip *chip)
 		irq_create_mapping(chip->g2_irq.domain, irq);
 
 	chip->g2_irq.chip = mv88e6xxx_g2_irq_chip;
-	chip->g2_irq.masked = ~0;
 
 	chip->device_irq = irq_find_mapping(chip->g1_irq.domain,
 					    MV88E6XXX_G1_STS_IRQ_DEVICE);
diff --git a/drivers/net/dsa/mv88e6xxx/smi.c b/drivers/net/dsa/mv88e6xxx/smi.c
index 92e9324f1fb9..919e0d6e0134 100644
--- a/drivers/net/dsa/mv88e6xxx/smi.c
+++ b/drivers/net/dsa/mv88e6xxx/smi.c
@@ -60,7 +60,7 @@ static int mv88e6xxx_smi_direct_wait(struct mv88e6xxx_chip *chip,
 		if (err)
 			return err;
 
-		if (!!(data >> bit) == !!val)
+		if (!!(data & BIT(bit)) == !!val)
 			return 0;
 	}
 
diff --git a/drivers/net/dsa/rtl8366.c b/drivers/net/dsa/rtl8366.c
index ac88caca5ad4..1368816abaed 100644
--- a/drivers/net/dsa/rtl8366.c
+++ b/drivers/net/dsa/rtl8366.c
@@ -43,18 +43,26 @@ int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member,
 	int ret;
 	int i;
 
+	dev_dbg(smi->dev,
+		"setting VLAN%d 4k members: 0x%02x, untagged: 0x%02x\n",
+		vid, member, untag);
+
 	/* Update the 4K table */
 	ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k);
 	if (ret)
 		return ret;
 
-	vlan4k.member = member;
-	vlan4k.untag = untag;
+	vlan4k.member |= member;
+	vlan4k.untag |= untag;
 	vlan4k.fid = fid;
 	ret = smi->ops->set_vlan_4k(smi, &vlan4k);
 	if (ret)
 		return ret;
 
+	dev_dbg(smi->dev,
+		"resulting VLAN%d 4k members: 0x%02x, untagged: 0x%02x\n",
+		vid, vlan4k.member, vlan4k.untag);
+
 	/* Try to find an existing MC entry for this VID */
 	for (i = 0; i < smi->num_vlan_mc; i++) {
 		struct rtl8366_vlan_mc vlanmc;
@@ -65,11 +73,16 @@ int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member,
 
 		if (vid == vlanmc.vid) {
 			/* update the MC entry */
-			vlanmc.member = member;
-			vlanmc.untag = untag;
+			vlanmc.member |= member;
+			vlanmc.untag |= untag;
 			vlanmc.fid = fid;
 
 			ret = smi->ops->set_vlan_mc(smi, i, &vlanmc);
+
+			dev_dbg(smi->dev,
+				"resulting VLAN%d MC members: 0x%02x, untagged: 0x%02x\n",
+				vid, vlanmc.member, vlanmc.untag);
+
 			break;
 		}
 	}
@@ -384,7 +397,7 @@ void rtl8366_vlan_add(struct dsa_switch *ds, int port,
 	if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port))
 		dev_err(smi->dev, "port is DSA or CPU port\n");
 
-	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
 		int pvid_val = 0;
 
 		dev_info(smi->dev, "add VLAN %04x\n", vid);
@@ -407,13 +420,13 @@ void rtl8366_vlan_add(struct dsa_switch *ds, int port,
 			if (ret < 0)
 				return;
 		}
-	}
 
-	ret = rtl8366_set_vlan(smi, port, member, untag, 0);
-	if (ret)
-		dev_err(smi->dev,
-			"failed to set up VLAN %04x",
-			vid);
+		ret = rtl8366_set_vlan(smi, vid, member, untag, 0);
+		if (ret)
+			dev_err(smi->dev,
+				"failed to set up VLAN %04x",
+				vid);
+	}
 }
 EXPORT_SYMBOL_GPL(rtl8366_vlan_add);
 
diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 8dd92868fe2d..c27071252184 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -575,7 +575,7 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv,
 	struct device *dev = &priv->spidev->dev;
 	struct device_node *child;
 
-	for_each_child_of_node(ports_node, child) {
+	for_each_available_child_of_node(ports_node, child) {
 		struct device_node *phy_node;
 		int phy_mode;
 		u32 index;
diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c
index 9e06dff619c3..2c07fc1eaecc 100644
--- a/drivers/net/ethernet/allwinner/sun4i-emac.c
+++ b/drivers/net/ethernet/allwinner/sun4i-emac.c
@@ -432,7 +432,7 @@ static void emac_timeout(struct net_device *dev)
 /* Hardware start transmission.
  * Send a packet to media from the upper layer.
  */
-static int emac_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t emac_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct emac_board_info *db = netdev_priv(dev);
 	unsigned long channel;
@@ -440,7 +440,7 @@ static int emac_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	channel = db->tx_fifo_stat & 3;
 	if (channel == 3)
-		return 1;
+		return NETDEV_TX_BUSY;
 
 	channel = (channel == 1 ? 1 : 0);
 
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index 7f8266b191ae..c68e14356186 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -200,6 +200,11 @@ static inline void comp_ctxt_release(struct ena_com_admin_queue *queue,
 static struct ena_comp_ctx *get_comp_ctxt(struct ena_com_admin_queue *queue,
 					  u16 command_id, bool capture)
 {
+	if (unlikely(!queue->comp_ctx)) {
+		pr_err("Completion context is NULL\n");
+		return NULL;
+	}
+
 	if (unlikely(command_id >= queue->q_depth)) {
 		pr_err("command id is larger than the queue size. cmd_id: %u queue size %d\n",
 		       command_id, queue->q_depth);
@@ -1021,9 +1026,41 @@ static int ena_com_get_feature(struct ena_com_dev *ena_dev,
 				      0);
 }
 
+int ena_com_get_current_hash_function(struct ena_com_dev *ena_dev)
+{
+	return ena_dev->rss.hash_func;
+}
+
+static void ena_com_hash_key_fill_default_key(struct ena_com_dev *ena_dev)
+{
+	struct ena_admin_feature_rss_flow_hash_control *hash_key =
+		(ena_dev->rss).hash_key;
+
+	netdev_rss_key_fill(&hash_key->key, sizeof(hash_key->key));
+	/* The key is stored in the device in u32 array
+	 * as well as the API requires the key to be passed in this
+	 * format. Thus the size of our array should be divided by 4
+	 */
+	hash_key->keys_num = sizeof(hash_key->key) / sizeof(u32);
+}
+
 static int ena_com_hash_key_allocate(struct ena_com_dev *ena_dev)
 {
 	struct ena_rss *rss = &ena_dev->rss;
+	struct ena_admin_feature_rss_flow_hash_control *hash_key;
+	struct ena_admin_get_feat_resp get_resp;
+	int rc;
+
+	hash_key = (ena_dev->rss).hash_key;
+
+	rc = ena_com_get_feature_ex(ena_dev, &get_resp,
+				    ENA_ADMIN_RSS_HASH_FUNCTION,
+				    ena_dev->rss.hash_key_dma_addr,
+				    sizeof(ena_dev->rss.hash_key));
+	if (unlikely(rc)) {
+		hash_key = NULL;
+		return -EOPNOTSUPP;
+	}
 
 	rss->hash_key =
 		dma_alloc_coherent(ena_dev->dmadev, sizeof(*rss->hash_key),
@@ -1234,30 +1271,6 @@ static int ena_com_ind_tbl_convert_to_device(struct ena_com_dev *ena_dev)
 	return 0;
 }
 
-static int ena_com_ind_tbl_convert_from_device(struct ena_com_dev *ena_dev)
-{
-	u16 dev_idx_to_host_tbl[ENA_TOTAL_NUM_QUEUES] = { (u16)-1 };
-	struct ena_rss *rss = &ena_dev->rss;
-	u8 idx;
-	u16 i;
-
-	for (i = 0; i < ENA_TOTAL_NUM_QUEUES; i++)
-		dev_idx_to_host_tbl[ena_dev->io_sq_queues[i].idx] = i;
-
-	for (i = 0; i < 1 << rss->tbl_log_size; i++) {
-		if (rss->rss_ind_tbl[i].cq_idx > ENA_TOTAL_NUM_QUEUES)
-			return -EINVAL;
-		idx = (u8)rss->rss_ind_tbl[i].cq_idx;
-
-		if (dev_idx_to_host_tbl[idx] > ENA_TOTAL_NUM_QUEUES)
-			return -EINVAL;
-
-		rss->host_rss_ind_tbl[i] = dev_idx_to_host_tbl[idx];
-	}
-
-	return 0;
-}
-
 static int ena_com_init_interrupt_moderation_table(struct ena_com_dev *ena_dev)
 {
 	size_t size;
@@ -2261,15 +2274,16 @@ int ena_com_fill_hash_function(struct ena_com_dev *ena_dev,
 
 	switch (func) {
 	case ENA_ADMIN_TOEPLITZ:
-		if (key_len > sizeof(hash_key->key)) {
-			pr_err("key len (%hu) is bigger than the max supported (%zu)\n",
-			       key_len, sizeof(hash_key->key));
-			return -EINVAL;
+		if (key) {
+			if (key_len != sizeof(hash_key->key)) {
+				pr_err("key len (%hu) doesn't equal the supported size (%zu)\n",
+				       key_len, sizeof(hash_key->key));
+				return -EINVAL;
+			}
+			memcpy(hash_key->key, key, key_len);
+			rss->hash_init_val = init_val;
+			hash_key->keys_num = key_len >> 2;
 		}
-
-		memcpy(hash_key->key, key, key_len);
-		rss->hash_init_val = init_val;
-		hash_key->keys_num = key_len >> 2;
 		break;
 	case ENA_ADMIN_CRC32:
 		rss->hash_init_val = init_val;
@@ -2299,6 +2313,9 @@ int ena_com_get_hash_function(struct ena_com_dev *ena_dev,
 		rss->hash_key;
 	int rc;
 
+	if (unlikely(!func))
+		return -EINVAL;
+
 	rc = ena_com_get_feature_ex(ena_dev, &get_resp,
 				    ENA_ADMIN_RSS_HASH_FUNCTION,
 				    rss->hash_key_dma_addr,
@@ -2306,9 +2323,12 @@ int ena_com_get_hash_function(struct ena_com_dev *ena_dev,
 	if (unlikely(rc))
 		return rc;
 
-	rss->hash_func = get_resp.u.flow_hash_func.selected_func;
-	if (func)
-		*func = rss->hash_func;
+	/* ffs() returns 1 in case the lsb is set */
+	rss->hash_func = ffs(get_resp.u.flow_hash_func.selected_func);
+	if (rss->hash_func)
+		rss->hash_func--;
+
+	*func = rss->hash_func;
 
 	if (key)
 		memcpy(key, hash_key->key, (size_t)(hash_key->keys_num) << 2);
@@ -2570,10 +2590,6 @@ int ena_com_indirect_table_get(struct ena_com_dev *ena_dev, u32 *ind_tbl)
 	if (!ind_tbl)
 		return 0;
 
-	rc = ena_com_ind_tbl_convert_from_device(ena_dev);
-	if (unlikely(rc))
-		return rc;
-
 	for (i = 0; i < (1 << rss->tbl_log_size); i++)
 		ind_tbl[i] = rss->host_rss_ind_tbl[i];
 
@@ -2590,9 +2606,15 @@ int ena_com_rss_init(struct ena_com_dev *ena_dev, u16 indr_tbl_log_size)
 	if (unlikely(rc))
 		goto err_indr_tbl;
 
+	/* The following function might return unsupported in case the
+	 * device doesn't support setting the key / hash function. We can safely
+	 * ignore this error and have indirection table support only.
+	 */
 	rc = ena_com_hash_key_allocate(ena_dev);
-	if (unlikely(rc))
+	if (unlikely(rc) && rc != -EOPNOTSUPP)
 		goto err_hash_key;
+	else if (rc != -EOPNOTSUPP)
+		ena_com_hash_key_fill_default_key(ena_dev);
 
 	rc = ena_com_hash_ctrl_init(ena_dev);
 	if (unlikely(rc))
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.h b/drivers/net/ethernet/amazon/ena/ena_com.h
index 25e160b3889d..fb383400f271 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.h
+++ b/drivers/net/ethernet/amazon/ena/ena_com.h
@@ -44,6 +44,7 @@
 #include <linux/spinlock.h>
 #include <linux/types.h>
 #include <linux/wait.h>
+#include <linux/netdevice.h>
 
 #include "ena_common_defs.h"
 #include "ena_admin_defs.h"
@@ -668,6 +669,14 @@ int ena_com_rss_init(struct ena_com_dev *ena_dev, u16 log_size);
  */
 void ena_com_rss_destroy(struct ena_com_dev *ena_dev);
 
+/* ena_com_get_current_hash_function - Get RSS hash function
+ * @ena_dev: ENA communication layer struct
+ *
+ * Return the current hash function.
+ * @return: 0 or one of the ena_admin_hash_functions values.
+ */
+int ena_com_get_current_hash_function(struct ena_com_dev *ena_dev);
+
 /* ena_com_fill_hash_function - Fill RSS hash function
  * @ena_dev: ENA communication layer struct
  * @func: The hash function (Toeplitz or crc)
diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
index fe596bc30a96..a44e8e0299c9 100644
--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c
+++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
@@ -651,6 +651,28 @@ static u32 ena_get_rxfh_key_size(struct net_device *netdev)
 	return ENA_HASH_KEY_SIZE;
 }
 
+static int ena_indirection_table_get(struct ena_adapter *adapter, u32 *indir)
+{
+	struct ena_com_dev *ena_dev = adapter->ena_dev;
+	int i, rc;
+
+	if (!indir)
+		return 0;
+
+	rc = ena_com_indirect_table_get(ena_dev, indir);
+	if (rc)
+		return rc;
+
+	/* Our internal representation of the indices is: even indices
+	 * for Tx and uneven indices for Rx. We need to convert the Rx
+	 * indices to be consecutive
+	 */
+	for (i = 0; i < ENA_RX_RSS_TABLE_SIZE; i++)
+		indir[i] = ENA_IO_RXQ_IDX_TO_COMBINED_IDX(indir[i]);
+
+	return rc;
+}
+
 static int ena_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 			u8 *hfunc)
 {
@@ -659,11 +681,25 @@ static int ena_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 	u8 func;
 	int rc;
 
-	rc = ena_com_indirect_table_get(adapter->ena_dev, indir);
+	rc = ena_indirection_table_get(adapter, indir);
 	if (rc)
 		return rc;
 
+	/* We call this function in order to check if the device
+	 * supports getting/setting the hash function.
+	 */
 	rc = ena_com_get_hash_function(adapter->ena_dev, &ena_func, key);
+
+	if (rc) {
+		if (rc == -EOPNOTSUPP) {
+			key = NULL;
+			hfunc = NULL;
+			rc = 0;
+		}
+
+		return rc;
+	}
+
 	if (rc)
 		return rc;
 
@@ -672,7 +708,7 @@ static int ena_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 		func = ETH_RSS_HASH_TOP;
 		break;
 	case ENA_ADMIN_CRC32:
-		func = ETH_RSS_HASH_XOR;
+		func = ETH_RSS_HASH_CRC32;
 		break;
 	default:
 		netif_err(adapter, drv, netdev,
@@ -715,10 +751,13 @@ static int ena_set_rxfh(struct net_device *netdev, const u32 *indir,
 	}
 
 	switch (hfunc) {
+	case ETH_RSS_HASH_NO_CHANGE:
+		func = ena_com_get_current_hash_function(ena_dev);
+		break;
 	case ETH_RSS_HASH_TOP:
 		func = ENA_ADMIN_TOEPLITZ;
 		break;
-	case ETH_RSS_HASH_XOR:
+	case ETH_RSS_HASH_CRC32:
 		func = ENA_ADMIN_CRC32;
 		break;
 	default:
@@ -819,6 +858,7 @@ static const struct ethtool_ops ena_ethtool_ops = {
 	.get_channels		= ena_get_channels,
 	.get_tunable		= ena_get_tunable,
 	.set_tunable		= ena_set_tunable,
+	.get_ts_info            = ethtool_op_get_ts_info,
 };
 
 void ena_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index ae0e145d8af1..14baeb7a2b64 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -2921,8 +2921,8 @@ static void check_for_missing_keep_alive(struct ena_adapter *adapter)
 	if (adapter->keep_alive_timeout == ENA_HW_HINTS_NO_TIMEOUT)
 		return;
 
-	keep_alive_expired = round_jiffies(adapter->last_keep_alive_jiffies +
-					   adapter->keep_alive_timeout);
+	keep_alive_expired = adapter->last_keep_alive_jiffies +
+			     adapter->keep_alive_timeout;
 	if (unlikely(time_is_before_jiffies(keep_alive_expired))) {
 		netif_err(adapter, drv, adapter->netdev,
 			  "Keep alive watchdog timeout.\n");
@@ -3024,7 +3024,7 @@ static void ena_timer_service(struct timer_list *t)
 	}
 
 	/* Reset the timer */
-	mod_timer(&adapter->timer_service, jiffies + HZ);
+	mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ));
 }
 
 static int ena_calc_io_queue_num(struct pci_dev *pdev,
@@ -3487,13 +3487,15 @@ err_disable_device:
 
 /*****************************************************************************/
 
-/* ena_remove - Device Removal Routine
+/* __ena_shutoff - Helper used in both PCI remove/shutdown routines
  * @pdev: PCI device information struct
+ * @shutdown: Is it a shutdown operation? If false, means it is a removal
  *
- * ena_remove is called by the PCI subsystem to alert the driver
- * that it should release a PCI device.
+ * __ena_shutoff is a helper routine that does the real work on shutdown and
+ * removal paths; the difference between those paths is with regards to whether
+ * dettach or unregister the netdevice.
  */
-static void ena_remove(struct pci_dev *pdev)
+static void __ena_shutoff(struct pci_dev *pdev, bool shutdown)
 {
 	struct ena_adapter *adapter = pci_get_drvdata(pdev);
 	struct ena_com_dev *ena_dev;
@@ -3512,13 +3514,17 @@ static void ena_remove(struct pci_dev *pdev)
 
 	cancel_work_sync(&adapter->reset_task);
 
-	rtnl_lock();
+	rtnl_lock(); /* lock released inside the below if-else block */
 	ena_destroy_device(adapter, true);
-	rtnl_unlock();
-
-	unregister_netdev(netdev);
-
-	free_netdev(netdev);
+	if (shutdown) {
+		netif_device_detach(netdev);
+		dev_close(netdev);
+		rtnl_unlock();
+	} else {
+		rtnl_unlock();
+		unregister_netdev(netdev);
+		free_netdev(netdev);
+	}
 
 	ena_com_rss_destroy(ena_dev);
 
@@ -3535,6 +3541,30 @@ static void ena_remove(struct pci_dev *pdev)
 	vfree(ena_dev);
 }
 
+/* ena_remove - Device Removal Routine
+ * @pdev: PCI device information struct
+ *
+ * ena_remove is called by the PCI subsystem to alert the driver
+ * that it should release a PCI device.
+ */
+
+static void ena_remove(struct pci_dev *pdev)
+{
+	__ena_shutoff(pdev, false);
+}
+
+/* ena_shutdown - Device Shutdown Routine
+ * @pdev: PCI device information struct
+ *
+ * ena_shutdown is called by the PCI subsystem to alert the driver that
+ * a shutdown/reboot (or kexec) is happening and device must be disabled.
+ */
+
+static void ena_shutdown(struct pci_dev *pdev)
+{
+	__ena_shutoff(pdev, true);
+}
+
 #ifdef CONFIG_PM
 /* ena_suspend - PM suspend callback
  * @pdev: PCI device information struct
@@ -3584,6 +3614,7 @@ static struct pci_driver ena_pci_driver = {
 	.id_table	= ena_pci_tbl,
 	.probe		= ena_probe,
 	.remove		= ena_remove,
+	.shutdown	= ena_shutdown,
 #ifdef CONFIG_PM
 	.suspend    = ena_suspend,
 	.resume     = ena_resume,
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index 63870072cbbd..1b3d163769e2 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -67,7 +67,7 @@
  * 16kB.
  */
 #if PAGE_SIZE > SZ_16K
-#define ENA_PAGE_SIZE SZ_16K
+#define ENA_PAGE_SIZE (_AC(SZ_16K, UL))
 #else
 #define ENA_PAGE_SIZE PAGE_SIZE
 #endif
@@ -125,6 +125,8 @@
 
 #define ENA_IO_TXQ_IDX(q)	(2 * (q))
 #define ENA_IO_RXQ_IDX(q)	(2 * (q) + 1)
+#define ENA_IO_TXQ_IDX_TO_COMBINED_IDX(q)	((q) / 2)
+#define ENA_IO_RXQ_IDX_TO_COMBINED_IDX(q)	(((q) - 1) / 2)
 
 #define ENA_MGMNT_IRQ_IDX		0
 #define ENA_IO_IRQ_FIRST_IDX		1
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 3dd0cecddba8..6d689ff3b74d 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -514,7 +514,7 @@ static void xgbe_isr_task(unsigned long data)
 				xgbe_disable_rx_tx_ints(pdata);
 
 				/* Turn on polling */
-				__napi_schedule_irqoff(&pdata->napi);
+				__napi_schedule(&pdata->napi);
 			}
 		} else {
 			/* Don't clear Rx/Tx status if doing per channel DMA
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
index 10b1c053e70a..a8ba616fa3ad 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
@@ -2022,7 +2022,7 @@ static int xgene_enet_probe(struct platform_device *pdev)
 	int ret;
 
 	ndev = alloc_etherdev_mqs(sizeof(struct xgene_enet_pdata),
-				  XGENE_NUM_RX_RING, XGENE_NUM_TX_RING);
+				  XGENE_NUM_TX_RING, XGENE_NUM_RX_RING);
 	if (!ndev)
 		return -ENOMEM;
 
diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c
index c40daad515d5..9fe027ea0f4d 100644
--- a/drivers/net/ethernet/apple/bmac.c
+++ b/drivers/net/ethernet/apple/bmac.c
@@ -1182,7 +1182,7 @@ bmac_get_station_address(struct net_device *dev, unsigned char *ea)
 	int i;
 	unsigned short data;
 
-	for (i = 0; i < 6; i++)
+	for (i = 0; i < 3; i++)
 		{
 			reset_and_select_srom(dev);
 			data = read_srom(dev, i + EnetAddressOffset/2, SROMAddressBits);
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
index 3dbf3ff1c450..11457ca0feb6 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
@@ -158,7 +158,7 @@ aq_check_approve_fvlan(struct aq_nic_s *aq_nic,
 	}
 
 	if ((aq_nic->ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) &&
-	    (!test_bit(be16_to_cpu(fsp->h_ext.vlan_tci),
+	    (!test_bit(be16_to_cpu(fsp->h_ext.vlan_tci) & VLAN_VID_MASK,
 		       aq_nic->active_vlans))) {
 		netdev_err(aq_nic->ndev,
 			   "ethtool: unknown vlan-id specified");
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 557e9a7bfd28..9574f091d5a0 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -453,8 +453,10 @@ static unsigned int aq_nic_map_skb(struct aq_nic_s *self,
 				     dx_buff->len,
 				     DMA_TO_DEVICE);
 
-	if (unlikely(dma_mapping_error(aq_nic_get_dev(self), dx_buff->pa)))
+	if (unlikely(dma_mapping_error(aq_nic_get_dev(self), dx_buff->pa))) {
+		ret = 0;
 		goto exit;
+	}
 
 	first = dx_buff;
 	dx_buff->len_pkt = skb->len;
@@ -584,10 +586,6 @@ int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb)
 	if (likely(frags)) {
 		err = self->aq_hw_ops->hw_ring_tx_xmit(self->aq_hw,
 						       ring, frags);
-		if (err >= 0) {
-			++ring->stats.tx.packets;
-			ring->stats.tx.bytes += skb->len;
-		}
 	} else {
 		err = NETDEV_TX_BUSY;
 	}
@@ -676,6 +674,9 @@ int aq_nic_get_regs(struct aq_nic_s *self, struct ethtool_regs *regs, void *p)
 	u32 *regs_buff = p;
 	int err = 0;
 
+	if (unlikely(!self->aq_hw_ops->hw_get_regs))
+		return -EOPNOTSUPP;
+
 	regs->version = 1;
 
 	err = self->aq_hw_ops->hw_get_regs(self->aq_hw,
@@ -690,6 +691,9 @@ err_exit:
 
 int aq_nic_get_regs_count(struct aq_nic_s *self)
 {
+	if (unlikely(!self->aq_hw_ops->hw_get_regs))
+		return 0;
+
 	return self->aq_nic_cfg.aq_hw_caps->mac_regs_count;
 }
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
index 74b9f3f1da81..0e8264c0b308 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
@@ -56,7 +56,7 @@ static const struct aq_board_revision_s hw_atl_boards[] = {
 	{ AQ_DEVICE_ID_D108,	AQ_HWREV_2,	&hw_atl_ops_b0, &hw_atl_b0_caps_aqc108, },
 	{ AQ_DEVICE_ID_D109,	AQ_HWREV_2,	&hw_atl_ops_b0, &hw_atl_b0_caps_aqc109, },
 
-	{ AQ_DEVICE_ID_AQC100,	AQ_HWREV_ANY,	&hw_atl_ops_b1, &hw_atl_b0_caps_aqc107, },
+	{ AQ_DEVICE_ID_AQC100,	AQ_HWREV_ANY,	&hw_atl_ops_b1, &hw_atl_b0_caps_aqc100, },
 	{ AQ_DEVICE_ID_AQC107,	AQ_HWREV_ANY,	&hw_atl_ops_b1, &hw_atl_b0_caps_aqc107, },
 	{ AQ_DEVICE_ID_AQC108,	AQ_HWREV_ANY,	&hw_atl_ops_b1, &hw_atl_b0_caps_aqc108, },
 	{ AQ_DEVICE_ID_AQC109,	AQ_HWREV_ANY,	&hw_atl_ops_b1, &hw_atl_b0_caps_aqc109, },
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index 5d650c58e6c5..6282f89868dc 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -243,9 +243,12 @@ bool aq_ring_tx_clean(struct aq_ring_s *self)
 			}
 		}
 
-		if (unlikely(buff->is_eop))
-			dev_kfree_skb_any(buff->skb);
+		if (unlikely(buff->is_eop)) {
+			++self->stats.rx.packets;
+			self->stats.tx.bytes += buff->skb->len;
 
+			dev_kfree_skb_any(buff->skb);
+		}
 		buff->pa = 0U;
 		buff->eop_index = 0xffffU;
 		self->sw_head = aq_ring_next_dx(self, self->sw_head);
@@ -321,7 +324,8 @@ int aq_ring_rx_clean(struct aq_ring_s *self,
 				err = 0;
 				goto err_exit;
 			}
-			if (buff->is_error || buff->is_cso_err) {
+			if (buff->is_error ||
+			    (buff->is_lro && buff->is_cso_err)) {
 				buff_ = buff;
 				do {
 					next_ = buff_->next,
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
index 6bd67210d0b7..e1c3a2e3b969 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
@@ -74,7 +74,8 @@ struct __packed aq_ring_buff_s {
 			u32 is_mapped:1;
 			u32 is_cleaned:1;
 			u32 is_error:1;
-			u32 rsvd3:6;
+			u32 is_lro:1;
+			u32 rsvd3:5;
 			u16 eop_index;
 			u16 rsvd4;
 		};
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
index 0f140a9fe404..9cf8add34e6c 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
@@ -776,7 +776,7 @@ static int hw_atl_a0_hw_multicast_list_set(struct aq_hw_s *self,
 	int err = 0;
 
 	if (count > (HW_ATL_A0_MAC_MAX - HW_ATL_A0_MAC_MIN)) {
-		err = EBADRQC;
+		err = -EBADRQC;
 		goto err_exit;
 	}
 	for (self->aq_nic_cfg->mc_list_count = 0U;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 84914297e326..40dfd5d23974 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -721,6 +721,8 @@ static int hw_atl_b0_hw_ring_rx_receive(struct aq_hw_s *self,
 			}
 		}
 
+		buff->is_lro = !!(HW_ATL_B0_RXD_WB_STAT2_RSCCNT &
+				  rxd_wb->status);
 		if (HW_ATL_B0_RXD_WB_STAT2_EOP & rxd_wb->status) {
 			buff->len = rxd_wb->pkt_len %
 				AQ_CFG_RX_FRAME_MAX;
@@ -733,8 +735,7 @@ static int hw_atl_b0_hw_ring_rx_receive(struct aq_hw_s *self,
 				rxd_wb->pkt_len > AQ_CFG_RX_FRAME_MAX ?
 				AQ_CFG_RX_FRAME_MAX : rxd_wb->pkt_len;
 
-			if (HW_ATL_B0_RXD_WB_STAT2_RSCCNT &
-				rxd_wb->status) {
+			if (buff->is_lro) {
 				/* LRO */
 				buff->next = rxd_wb->next_desc_ptr;
 				++ring->stats.rx.lro_packets;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
index bf6673aab7a4..06838a38a246 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
@@ -1581,7 +1581,7 @@ void hw_atl_rpfl3l4_ipv6_src_addr_set(struct aq_hw_s *aq_hw, u8 location,
 	for (i = 0; i < 4; ++i)
 		aq_hw_write_reg(aq_hw,
 				HW_ATL_RPF_L3_SRCA_ADR(location + i),
-				ipv6_src[i]);
+				ipv6_src[3 - i]);
 }
 
 void hw_atl_rpfl3l4_ipv6_dest_addr_set(struct aq_hw_s *aq_hw, u8 location,
@@ -1592,7 +1592,7 @@ void hw_atl_rpfl3l4_ipv6_dest_addr_set(struct aq_hw_s *aq_hw, u8 location,
 	for (i = 0; i < 4; ++i)
 		aq_hw_write_reg(aq_hw,
 				HW_ATL_RPF_L3_DSTA_ADR(location + i),
-				ipv6_dest[i]);
+				ipv6_dest[3 - i]);
 }
 
 u32 hw_atl_sem_ram_get(struct aq_hw_s *self)
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
index 436e98980012..6fec1da7c409 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
@@ -2546,7 +2546,7 @@
  */
 
  /* Register address for bitfield pif_rpf_l3_da0_i[31:0] */
-#define HW_ATL_RPF_L3_DSTA_ADR(location) (0x000053B0 + (location) * 0x4)
+#define HW_ATL_RPF_L3_DSTA_ADR(location) (0x000053D0 + (location) * 0x4)
 /* Bitmask for bitfield l3_da0[1F:0] */
 #define HW_ATL_RPF_L3_DSTA_MSK 0xFFFFFFFFu
 /* Inverted bitmask for bitfield l3_da0[1F:0] */
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
index 52646855495e..873f9865f0d1 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
@@ -22,6 +22,7 @@
 #define HW_ATL_MIF_ADDR         0x0208U
 #define HW_ATL_MIF_VAL          0x020CU
 
+#define HW_ATL_MPI_RPC_ADDR     0x0334U
 #define HW_ATL_RPC_CONTROL_ADR  0x0338U
 #define HW_ATL_RPC_STATE_ADR    0x033CU
 
@@ -48,15 +49,14 @@
 #define FORCE_FLASHLESS 0
 
 static int hw_atl_utils_ver_match(u32 ver_expected, u32 ver_actual);
-
 static int hw_atl_utils_mpi_set_state(struct aq_hw_s *self,
 				      enum hal_atl_utils_fw_state_e state);
-
 static u32 hw_atl_utils_get_mpi_mbox_tid(struct aq_hw_s *self);
 static u32 hw_atl_utils_mpi_get_state(struct aq_hw_s *self);
 static u32 hw_atl_utils_mif_cmd_get(struct aq_hw_s *self);
 static u32 hw_atl_utils_mif_addr_get(struct aq_hw_s *self);
 static u32 hw_atl_utils_rpc_state_get(struct aq_hw_s *self);
+static u32 aq_fw1x_rpc_get(struct aq_hw_s *self);
 
 int hw_atl_utils_initfw(struct aq_hw_s *self, const struct aq_fw_ops **fw_ops)
 {
@@ -413,6 +413,10 @@ static int hw_atl_utils_init_ucp(struct aq_hw_s *self,
 					self, self->mbox_addr,
 					self->mbox_addr != 0U,
 					1000U, 10000U);
+	err = readx_poll_timeout_atomic(aq_fw1x_rpc_get, self,
+					self->rpc_addr,
+					self->rpc_addr != 0U,
+					1000U, 100000U);
 
 	return err;
 }
@@ -469,6 +473,12 @@ int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self,
 						self, fw.val,
 						sw.tid == fw.tid,
 						1000U, 100000U);
+		if (err < 0)
+			goto err_exit;
+
+		err = aq_hw_err_from_flags(self);
+		if (err < 0)
+			goto err_exit;
 
 		if (fw.len == 0xFFFFU) {
 			err = hw_atl_utils_fw_rpc_call(self, sw.len);
@@ -950,6 +960,11 @@ static u32 hw_atl_utils_rpc_state_get(struct aq_hw_s *self)
 	return aq_hw_read_reg(self, HW_ATL_RPC_STATE_ADR);
 }
 
+static u32 aq_fw1x_rpc_get(struct aq_hw_s *self)
+{
+	return aq_hw_read_reg(self, HW_ATL_MPI_RPC_ADDR);
+}
+
 const struct aq_fw_ops aq_fw_1x_ops = {
 	.init = hw_atl_utils_mpi_create,
 	.deinit = hw_atl_fw1x_deinit,
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index e3538ba7d0e7..e73a677b463a 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -1249,8 +1249,12 @@ out_disable_adv_intr:
 
 static void __alx_stop(struct alx_priv *alx)
 {
-	alx_halt(alx);
 	alx_free_irq(alx);
+
+	cancel_work_sync(&alx->link_check_wk);
+	cancel_work_sync(&alx->reset_wk);
+
+	alx_halt(alx);
 	alx_free_rings(alx);
 	alx_free_napis(alx);
 }
@@ -1860,9 +1864,6 @@ static void alx_remove(struct pci_dev *pdev)
 	struct alx_priv *alx = pci_get_drvdata(pdev);
 	struct alx_hw *hw = &alx->hw;
 
-	cancel_work_sync(&alx->link_check_wk);
-	cancel_work_sync(&alx->reset_wk);
-
 	/* restore permanent mac address */
 	alx_set_macaddr(hw, hw->perm_addr);
 
diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c
index 97ab0dd25552..1a7710c399d7 100644
--- a/drivers/net/ethernet/broadcom/b44.c
+++ b/drivers/net/ethernet/broadcom/b44.c
@@ -1519,8 +1519,10 @@ static int b44_magic_pattern(u8 *macaddr, u8 *ppattern, u8 *pmask, int offset)
 	int ethaddr_bytes = ETH_ALEN;
 
 	memset(ppattern + offset, 0xff, magicsync);
-	for (j = 0; j < magicsync; j++)
-		set_bit(len++, (unsigned long *) pmask);
+	for (j = 0; j < magicsync; j++) {
+		pmask[len >> 3] |= BIT(len & 7);
+		len++;
+	}
 
 	for (j = 0; j < B44_MAX_PATTERNS; j++) {
 		if ((B44_PATTERN_SIZE - len) >= ETH_ALEN)
@@ -1532,7 +1534,8 @@ static int b44_magic_pattern(u8 *macaddr, u8 *ppattern, u8 *pmask, int offset)
 		for (k = 0; k< ethaddr_bytes; k++) {
 			ppattern[offset + magicsync +
 				(j * ETH_ALEN) + k] = macaddr[k];
-			set_bit(len++, (unsigned long *) pmask);
+			pmask[len >> 3] |= BIT(len & 7);
+			len++;
 		}
 	}
 	return len - 1;
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index cae9b77ff44b..20322c18f8b3 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -666,7 +666,8 @@ static struct sk_buff *bcm_sysport_rx_refill(struct bcm_sysport_priv *priv,
 	dma_addr_t mapping;
 
 	/* Allocate a new SKB for a new packet */
-	skb = netdev_alloc_skb(priv->netdev, RX_BUF_LENGTH);
+	skb = __netdev_alloc_skb(priv->netdev, RX_BUF_LENGTH,
+				 GFP_ATOMIC | __GFP_NOWARN);
 	if (!skb) {
 		priv->mib.alloc_rx_buff_failed++;
 		netif_err(priv, rx_err, ndev, "SKB alloc failed\n");
@@ -2136,7 +2137,7 @@ static int bcm_sysport_rule_set(struct bcm_sysport_priv *priv,
 		return -ENOSPC;
 
 	index = find_first_zero_bit(priv->filters, RXCHK_BRCM_TAG_MAX);
-	if (index > RXCHK_BRCM_TAG_MAX)
+	if (index >= RXCHK_BRCM_TAG_MAX)
 		return -ENOSPC;
 
 	/* Location is the classification ID, and index is the position
@@ -2324,7 +2325,7 @@ static int bcm_sysport_map_queues(struct notifier_block *nb,
 		ring->switch_queue = qp;
 		ring->switch_port = port;
 		ring->inspect = true;
-		priv->ring_map[q + port * num_tx_queues] = ring;
+		priv->ring_map[qp + port * num_tx_queues] = ring;
 		qp++;
 	}
 
@@ -2339,7 +2340,7 @@ static int bcm_sysport_unmap_queues(struct notifier_block *nb,
 	struct net_device *slave_dev;
 	unsigned int num_tx_queues;
 	struct net_device *dev;
-	unsigned int q, port;
+	unsigned int q, qp, port;
 
 	priv = container_of(nb, struct bcm_sysport_priv, dsa_notifier);
 	if (priv->netdev != info->master)
@@ -2365,7 +2366,8 @@ static int bcm_sysport_unmap_queues(struct notifier_block *nb,
 			continue;
 
 		ring->inspect = false;
-		priv->ring_map[q + port * num_tx_queues] = NULL;
+		qp = ring->switch_queue;
+		priv->ring_map[qp + port * num_tx_queues] = NULL;
 	}
 
 	return 0;
@@ -2730,6 +2732,9 @@ static int __maybe_unused bcm_sysport_resume(struct device *d)
 
 	umac_reset(priv);
 
+	/* Disable the UniMAC RX/TX */
+	umac_enable_set(priv, CMD_RX_EN | CMD_TX_EN, 0);
+
 	/* We may have been suspended and never received a WOL event that
 	 * would turn off MPD detection, take care of that now
 	 */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 9d582b3ebc88..8d86c9ded4fd 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -1934,7 +1934,8 @@ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
 	}
 
 	/* select a non-FCoE queue */
-	return netdev_pick_tx(dev, skb, NULL) % (BNX2X_NUM_ETH_QUEUES(bp));
+	return netdev_pick_tx(dev, skb, NULL) %
+			(BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos);
 }
 
 void bnx2x_set_num_queues(struct bnx2x *bp)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index 8b08cb18e363..3f63ffd7561b 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -1109,7 +1109,7 @@ static inline u8 bnx2x_get_path_func_num(struct bnx2x *bp)
 		for (i = 0; i < E1H_FUNC_MAX / 2; i++) {
 			u32 func_config =
 				MF_CFG_RD(bp,
-					  func_mf_config[BP_PORT(bp) + 2 * i].
+					  func_mf_config[BP_PATH(bp) + 2 * i].
 					  config);
 			func_num +=
 				((func_config & FUNC_MF_CFG_FUNC_HIDE) ? 0 : 1);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 192ff8d5da32..cff64e43bdd8 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -9976,10 +9976,18 @@ static void bnx2x_recovery_failed(struct bnx2x *bp)
  */
 static void bnx2x_parity_recover(struct bnx2x *bp)
 {
-	bool global = false;
 	u32 error_recovered, error_unrecovered;
-	bool is_parity;
+	bool is_parity, global = false;
+#ifdef CONFIG_BNX2X_SRIOV
+	int vf_idx;
+
+	for (vf_idx = 0; vf_idx < bp->requested_nr_virtfn; vf_idx++) {
+		struct bnx2x_virtf *vf = BP_VF(bp, vf_idx);
 
+		if (vf)
+			vf->state = VF_LOST;
+	}
+#endif
 	DP(NETIF_MSG_HW, "Handling parity\n");
 	while (1) {
 		switch (bp->recovery_state) {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
index b6ebd92ec565..3a716c015415 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
@@ -139,6 +139,7 @@ struct bnx2x_virtf {
 #define VF_ACQUIRED	1	/* VF acquired, but not initialized */
 #define VF_ENABLED	2	/* VF Enabled */
 #define VF_RESET	3	/* VF FLR'd, pending cleanup */
+#define VF_LOST		4	/* Recovery while VFs are loaded */
 
 	bool flr_clnup_stage;	/* true during flr cleanup */
 	bool malicious;		/* true if FW indicated so, until FLR */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index 0752b7fa4d9c..ea0e9394f898 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -2107,6 +2107,18 @@ static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf,
 {
 	int i;
 
+	if (vf->state == VF_LOST) {
+		/* Just ack the FW and return if VFs are lost
+		 * in case of parity error. VFs are supposed to be timedout
+		 * on waiting for PF response.
+		 */
+		DP(BNX2X_MSG_IOV,
+		   "VF 0x%x lost, not handling the request\n", vf->abs_vfid);
+
+		storm_memset_vf_mbx_ack(bp, vf->abs_vfid);
+		return;
+	}
+
 	/* check if tlv type is known */
 	if (bnx2x_tlv_supported(mbx->first_tlv.tl.type)) {
 		/* Lock the per vf op mutex and note the locker's identity.
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 9e911c399ef5..b6410921807e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6266,7 +6266,7 @@ static int bnxt_alloc_ctx_pg_tbls(struct bnxt *bp,
 	int rc;
 
 	if (!mem_size)
-		return 0;
+		return -EINVAL;
 
 	ctx_pg->nr_pages = DIV_ROUND_UP(mem_size, BNXT_PAGE_SIZE);
 	if (ctx_pg->nr_pages > MAX_CTX_TOTAL_PAGES) {
@@ -6480,12 +6480,12 @@ skip_rdma:
 	}
 	ena |= FUNC_BACKING_STORE_CFG_REQ_DFLT_ENABLES;
 	rc = bnxt_hwrm_func_backing_store_cfg(bp, ena);
-	if (rc)
+	if (rc) {
 		netdev_err(bp->dev, "Failed configuring context mem, rc = %d.\n",
 			   rc);
-	else
-		ctx->flags |= BNXT_CTX_FLAG_INITED;
-
+		return rc;
+	}
+	ctx->flags |= BNXT_CTX_FLAG_INITED;
 	return 0;
 }
 
@@ -6902,14 +6902,22 @@ static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp)
 		pri2cos = &resp2->pri0_cos_queue_id;
 		for (i = 0; i < 8; i++) {
 			u8 queue_id = pri2cos[i];
+			u8 queue_idx;
 
+			/* Per port queue IDs start from 0, 10, 20, etc */
+			queue_idx = queue_id % 10;
+			if (queue_idx > BNXT_MAX_QUEUE) {
+				bp->pri2cos_valid = false;
+				goto qstats_done;
+			}
 			for (j = 0; j < bp->max_q; j++) {
 				if (bp->q_ids[j] == queue_id)
-					bp->pri2cos[i] = j;
+					bp->pri2cos_idx[i] = queue_idx;
 			}
 		}
 		bp->pri2cos_valid = 1;
 	}
+qstats_done:
 	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
 }
@@ -7391,7 +7399,7 @@ static void bnxt_setup_msix(struct bnxt *bp)
 	int tcs, i;
 
 	tcs = netdev_get_num_tc(dev);
-	if (tcs > 1) {
+	if (tcs) {
 		int i, off, count;
 
 		for (i = 0; i < tcs; i++) {
@@ -8733,7 +8741,7 @@ static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init,
 	bnxt_free_skbs(bp);
 
 	/* Save ring stats before shutdown */
-	if (bp->bnapi)
+	if (bp->bnapi && irq_re_init)
 		bnxt_get_ring_stats(bp, &bp->net_stats_prev);
 	if (irq_re_init) {
 		bnxt_free_irq(bp);
@@ -9189,6 +9197,7 @@ static netdev_features_t bnxt_fix_features(struct net_device *dev,
 					   netdev_features_t features)
 {
 	struct bnxt *bp = netdev_priv(dev);
+	netdev_features_t vlan_features;
 
 	if ((features & NETIF_F_NTUPLE) && !bnxt_rfs_capable(bp))
 		features &= ~NETIF_F_NTUPLE;
@@ -9205,12 +9214,14 @@ static netdev_features_t bnxt_fix_features(struct net_device *dev,
 	/* Both CTAG and STAG VLAN accelaration on the RX side have to be
 	 * turned on or off together.
 	 */
-	if ((features & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX)) !=
-	    (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX)) {
+	vlan_features = features & (NETIF_F_HW_VLAN_CTAG_RX |
+				    NETIF_F_HW_VLAN_STAG_RX);
+	if (vlan_features != (NETIF_F_HW_VLAN_CTAG_RX |
+			      NETIF_F_HW_VLAN_STAG_RX)) {
 		if (dev->features & NETIF_F_HW_VLAN_CTAG_RX)
 			features &= ~(NETIF_F_HW_VLAN_CTAG_RX |
 				      NETIF_F_HW_VLAN_STAG_RX);
-		else
+		else if (vlan_features)
 			features |= NETIF_F_HW_VLAN_CTAG_RX |
 				    NETIF_F_HW_VLAN_STAG_RX;
 	}
@@ -9367,12 +9378,15 @@ static void bnxt_reset_task(struct bnxt *bp, bool silent)
 	if (netif_running(bp->dev)) {
 		int rc;
 
-		if (!silent)
+		if (silent) {
+			bnxt_close_nic(bp, false, false);
+			bnxt_open_nic(bp, false, false);
+		} else {
 			bnxt_ulp_stop(bp);
-		bnxt_close_nic(bp, false, false);
-		rc = bnxt_open_nic(bp, false, false);
-		if (!silent && !rc)
-			bnxt_ulp_start(bp);
+			bnxt_close_nic(bp, true, false);
+			rc = bnxt_open_nic(bp, true, false);
+			bnxt_ulp_start(bp, rc);
+		}
 	}
 }
 
@@ -9797,13 +9811,13 @@ static int bnxt_change_mtu(struct net_device *dev, int new_mtu)
 	struct bnxt *bp = netdev_priv(dev);
 
 	if (netif_running(dev))
-		bnxt_close_nic(bp, false, false);
+		bnxt_close_nic(bp, true, false);
 
 	dev->mtu = new_mtu;
 	bnxt_set_ring_params(bp);
 
 	if (netif_running(dev))
-		return bnxt_open_nic(bp, false, false);
+		return bnxt_open_nic(bp, true, false);
 
 	return 0;
 }
@@ -9914,11 +9928,23 @@ static bool bnxt_fltr_match(struct bnxt_ntuple_filter *f1,
 	struct flow_keys *keys1 = &f1->fkeys;
 	struct flow_keys *keys2 = &f2->fkeys;
 
-	if (keys1->addrs.v4addrs.src == keys2->addrs.v4addrs.src &&
-	    keys1->addrs.v4addrs.dst == keys2->addrs.v4addrs.dst &&
-	    keys1->ports.ports == keys2->ports.ports &&
-	    keys1->basic.ip_proto == keys2->basic.ip_proto &&
-	    keys1->basic.n_proto == keys2->basic.n_proto &&
+	if (keys1->basic.n_proto != keys2->basic.n_proto ||
+	    keys1->basic.ip_proto != keys2->basic.ip_proto)
+		return false;
+
+	if (keys1->basic.n_proto == htons(ETH_P_IP)) {
+		if (keys1->addrs.v4addrs.src != keys2->addrs.v4addrs.src ||
+		    keys1->addrs.v4addrs.dst != keys2->addrs.v4addrs.dst)
+			return false;
+	} else {
+		if (memcmp(&keys1->addrs.v6addrs.src, &keys2->addrs.v6addrs.src,
+			   sizeof(keys1->addrs.v6addrs.src)) ||
+		    memcmp(&keys1->addrs.v6addrs.dst, &keys2->addrs.v6addrs.dst,
+			   sizeof(keys1->addrs.v6addrs.dst)))
+			return false;
+	}
+
+	if (keys1->ports.ports == keys2->ports.ports &&
 	    keys1->control.flags == keys2->control.flags &&
 	    ether_addr_equal(f1->src_mac_addr, f2->src_mac_addr) &&
 	    ether_addr_equal(f1->dst_mac_addr, f2->dst_mac_addr))
@@ -10210,7 +10236,7 @@ int bnxt_get_port_parent_id(struct net_device *dev,
 		return -EOPNOTSUPP;
 
 	/* The PF and it's VF-reps only support the switchdev framework */
-	if (!BNXT_PF(bp))
+	if (!BNXT_PF(bp) || !(bp->flags & BNXT_FLAG_DSN_VALID))
 		return -EOPNOTSUPP;
 
 	ppid->id_len = sizeof(bp->switch_id);
@@ -10498,6 +10524,10 @@ static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
 		bp->rx_nr_rings++;
 		bp->cp_nr_rings++;
 	}
+	if (rc) {
+		bp->tx_nr_rings = 0;
+		bp->rx_nr_rings = 0;
+	}
 	return rc;
 }
 
@@ -10598,6 +10628,7 @@ static int bnxt_pcie_dsn_get(struct bnxt *bp, u8 dsn[])
 	put_unaligned_le32(dw, &dsn[0]);
 	pci_read_config_dword(pdev, pos + 4, &dw);
 	put_unaligned_le32(dw, &dsn[4]);
+	bp->flags |= BNXT_FLAG_DSN_VALID;
 	return 0;
 }
 
@@ -10614,6 +10645,14 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (version_printed++ == 0)
 		pr_info("%s", version);
 
+	/* Clear any pending DMA transactions from crash kernel
+	 * while loading driver in capture kernel.
+	 */
+	if (is_kdump_kernel()) {
+		pci_clear_master(pdev);
+		pcie_flr(pdev);
+	}
+
 	max_irqs = bnxt_get_max_irq(pdev);
 	dev = alloc_etherdev_mq(sizeof(*bp), max_irqs);
 	if (!dev)
@@ -10749,9 +10788,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	if (BNXT_PF(bp)) {
 		/* Read the adapter's DSN to use as the eswitch switch_id */
-		rc = bnxt_pcie_dsn_get(bp, bp->switch_id);
-		if (rc)
-			goto init_err_pci_clean;
+		bnxt_pcie_dsn_get(bp, bp->switch_id);
 	}
 	bnxt_hwrm_func_qcfg(bp);
 	bnxt_hwrm_vnic_qcaps(bp);
@@ -10851,10 +10888,10 @@ init_err_cleanup_tc:
 init_err_pci_clean:
 	bnxt_free_hwrm_short_cmd_req(bp);
 	bnxt_free_hwrm_resources(bp);
+	bnxt_cleanup_pci(bp);
 	bnxt_free_ctx_mem(bp);
 	kfree(bp->ctx);
 	bp->ctx = NULL;
-	bnxt_cleanup_pci(bp);
 
 init_err_free:
 	free_netdev(dev);
@@ -10878,10 +10915,10 @@ static void bnxt_shutdown(struct pci_dev *pdev)
 		dev_close(dev);
 
 	bnxt_ulp_shutdown(bp);
+	bnxt_clear_int_mode(bp);
+	pci_disable_device(pdev);
 
 	if (system_state == SYSTEM_POWER_OFF) {
-		bnxt_clear_int_mode(bp);
-		pci_disable_device(pdev);
 		pci_wake_from_d3(pdev, bp->wol);
 		pci_set_power_state(pdev, PCI_D3hot);
 	}
@@ -11012,18 +11049,20 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
 		if (!err && netif_running(netdev))
 			err = bnxt_open(netdev);
 
-		if (!err) {
+		if (!err)
 			result = PCI_ERS_RESULT_RECOVERED;
-			bnxt_ulp_start(bp);
-		}
+		bnxt_ulp_start(bp, err);
 	}
 
-	if (result != PCI_ERS_RESULT_RECOVERED && netif_running(netdev))
-		dev_close(netdev);
+	if (result != PCI_ERS_RESULT_RECOVERED) {
+		if (netif_running(netdev))
+			dev_close(netdev);
+		pci_disable_device(pdev);
+	}
 
 	rtnl_unlock();
 
-	return PCI_ERS_RESULT_RECOVERED;
+	return result;
 }
 
 /**
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index be438d82f939..f2c1b7d7a89b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1351,6 +1351,7 @@ struct bnxt {
 	#define BNXT_FLAG_NO_AGG_RINGS	0x20000
 	#define BNXT_FLAG_RX_PAGE_MODE	0x40000
 	#define BNXT_FLAG_MULTI_HOST	0x100000
+	#define BNXT_FLAG_DSN_VALID	0x200000
 	#define BNXT_FLAG_DOUBLE_DB	0x400000
 	#define BNXT_FLAG_CHIP_NITRO_A0	0x1000000
 	#define BNXT_FLAG_DIM		0x2000000
@@ -1516,7 +1517,7 @@ struct bnxt {
 	int			hw_port_stats_size;
 	u16			fw_rx_stats_ext_size;
 	u16			fw_tx_stats_ext_size;
-	u8			pri2cos[8];
+	u8			pri2cos_idx[8];
 	u8			pri2cos_valid;
 
 	u16			hwrm_max_req_len;
@@ -1715,9 +1716,6 @@ static inline bool bnxt_cfa_hwrm_message(u16 req_type)
 	case HWRM_CFA_ENCAP_RECORD_FREE:
 	case HWRM_CFA_DECAP_FILTER_ALLOC:
 	case HWRM_CFA_DECAP_FILTER_FREE:
-	case HWRM_CFA_NTUPLE_FILTER_ALLOC:
-	case HWRM_CFA_NTUPLE_FILTER_FREE:
-	case HWRM_CFA_NTUPLE_FILTER_CFG:
 	case HWRM_CFA_EM_FLOW_ALLOC:
 	case HWRM_CFA_EM_FLOW_FREE:
 	case HWRM_CFA_EM_FLOW_CFG:
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index 70775158c8c4..1c6198c53b5d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -482,24 +482,26 @@ static int bnxt_dcbnl_ieee_getets(struct net_device *dev, struct ieee_ets *ets)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	struct ieee_ets *my_ets = bp->ieee_ets;
+	int rc;
 
 	ets->ets_cap = bp->max_tc;
 
 	if (!my_ets) {
-		int rc;
-
 		if (bp->dcbx_cap & DCB_CAP_DCBX_HOST)
 			return 0;
 
 		my_ets = kzalloc(sizeof(*my_ets), GFP_KERNEL);
 		if (!my_ets)
-			return 0;
+			return -ENOMEM;
 		rc = bnxt_hwrm_queue_cos2bw_qcfg(bp, my_ets);
 		if (rc)
-			return 0;
+			goto error;
 		rc = bnxt_hwrm_queue_pri2cos_qcfg(bp, my_ets);
 		if (rc)
-			return 0;
+			goto error;
+
+		/* cache result */
+		bp->ieee_ets = my_ets;
 	}
 
 	ets->cbs = my_ets->cbs;
@@ -508,6 +510,9 @@ static int bnxt_dcbnl_ieee_getets(struct net_device *dev, struct ieee_ets *ets)
 	memcpy(ets->tc_tsa, my_ets->tc_tsa, sizeof(ets->tc_tsa));
 	memcpy(ets->prio_tc, my_ets->prio_tc, sizeof(ets->prio_tc));
 	return 0;
+error:
+	kfree(my_ets);
+	return rc;
 }
 
 static int bnxt_dcbnl_ieee_setets(struct net_device *dev, struct ieee_ets *ets)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
index 5b6b2c7d97cf..0af9e7259470 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
@@ -39,7 +39,7 @@ static inline void bnxt_link_bp_to_dl(struct bnxt *bp, struct devlink *dl)
 #define NVM_OFF_DIS_GRE_VER_CHECK	171
 #define NVM_OFF_ENABLE_SRIOV		401
 
-#define BNXT_MSIX_VEC_MAX	1280
+#define BNXT_MSIX_VEC_MAX	512
 #define BNXT_MSIX_VEC_MIN_MAX	128
 
 enum bnxt_nvm_dir_type {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index e6705f7cae40..3503699ef205 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -514,25 +514,25 @@ skip_ring_stats:
 		if (bp->pri2cos_valid) {
 			for (i = 0; i < 8; i++, j++) {
 				long n = bnxt_rx_bytes_pri_arr[i].base_off +
-					 bp->pri2cos[i];
+					 bp->pri2cos_idx[i];
 
 				buf[j] = le64_to_cpu(*(rx_port_stats_ext + n));
 			}
 			for (i = 0; i < 8; i++, j++) {
 				long n = bnxt_rx_pkts_pri_arr[i].base_off +
-					 bp->pri2cos[i];
+					 bp->pri2cos_idx[i];
 
 				buf[j] = le64_to_cpu(*(rx_port_stats_ext + n));
 			}
 			for (i = 0; i < 8; i++, j++) {
 				long n = bnxt_tx_bytes_pri_arr[i].base_off +
-					 bp->pri2cos[i];
+					 bp->pri2cos_idx[i];
 
 				buf[j] = le64_to_cpu(*(tx_port_stats_ext + n));
 			}
 			for (i = 0; i < 8; i++, j++) {
 				long n = bnxt_tx_pkts_pri_arr[i].base_off +
-					 bp->pri2cos[i];
+					 bp->pri2cos_idx[i];
 
 				buf[j] = le64_to_cpu(*(tx_port_stats_ext + n));
 			}
@@ -1630,8 +1630,11 @@ static int bnxt_set_pauseparam(struct net_device *dev,
 	if (epause->tx_pause)
 		link_info->req_flow_ctrl |= BNXT_LINK_PAUSE_TX;
 
-	if (netif_running(dev))
+	if (netif_running(dev)) {
+		mutex_lock(&bp->link_lock);
 		rc = bnxt_hwrm_set_pause(bp);
+		mutex_unlock(&bp->link_lock);
+	}
 	return rc;
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index 2b90a2bb1a1d..c1dcbfdedded 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -419,6 +419,7 @@ static void bnxt_free_vf_resources(struct bnxt *bp)
 		}
 	}
 
+	bp->pf.active_vfs = 0;
 	kfree(bp->pf.vf);
 	bp->pf.vf = NULL;
 }
@@ -812,7 +813,6 @@ void bnxt_sriov_disable(struct bnxt *bp)
 
 	bnxt_free_vf_resources(bp);
 
-	bp->pf.active_vfs = 0;
 	/* Reclaim all resources for the PF. */
 	rtnl_lock();
 	bnxt_restore_pf_fw_resources(bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index 0ee0d689d94e..5089f06209bd 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -186,7 +186,7 @@ static int bnxt_free_msix_vecs(struct bnxt_en_dev *edev, int ulp_id)
 
 	edev->ulp_tbl[ulp_id].msix_requested = 0;
 	edev->flags &= ~BNXT_EN_FLAG_MSIX_REQUESTED;
-	if (netif_running(dev)) {
+	if (netif_running(dev) && !(edev->flags & BNXT_EN_FLAG_ULP_STOPPED)) {
 		bnxt_close_nic(bp, true, false);
 		bnxt_open_nic(bp, true, false);
 	}
@@ -267,6 +267,7 @@ void bnxt_ulp_stop(struct bnxt *bp)
 	if (!edev)
 		return;
 
+	edev->flags |= BNXT_EN_FLAG_ULP_STOPPED;
 	for (i = 0; i < BNXT_MAX_ULP; i++) {
 		struct bnxt_ulp *ulp = &edev->ulp_tbl[i];
 
@@ -277,7 +278,7 @@ void bnxt_ulp_stop(struct bnxt *bp)
 	}
 }
 
-void bnxt_ulp_start(struct bnxt *bp)
+void bnxt_ulp_start(struct bnxt *bp, int err)
 {
 	struct bnxt_en_dev *edev = bp->edev;
 	struct bnxt_ulp_ops *ops;
@@ -286,6 +287,11 @@ void bnxt_ulp_start(struct bnxt *bp)
 	if (!edev)
 		return;
 
+	edev->flags &= ~BNXT_EN_FLAG_ULP_STOPPED;
+
+	if (err)
+		return;
+
 	for (i = 0; i < BNXT_MAX_ULP; i++) {
 		struct bnxt_ulp *ulp = &edev->ulp_tbl[i];
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
index cd78453d0bf0..9895406b9830 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
@@ -64,6 +64,7 @@ struct bnxt_en_dev {
 	#define BNXT_EN_FLAG_ROCE_CAP		(BNXT_EN_FLAG_ROCEV1_CAP | \
 						 BNXT_EN_FLAG_ROCEV2_CAP)
 	#define BNXT_EN_FLAG_MSIX_REQUESTED	0x4
+	#define BNXT_EN_FLAG_ULP_STOPPED	0x8
 	const struct bnxt_en_ops	*en_ops;
 	struct bnxt_ulp			ulp_tbl[BNXT_MAX_ULP];
 };
@@ -92,7 +93,7 @@ int bnxt_get_ulp_msix_num(struct bnxt *bp);
 int bnxt_get_ulp_msix_base(struct bnxt *bp);
 int bnxt_get_ulp_stat_ctxs(struct bnxt *bp);
 void bnxt_ulp_stop(struct bnxt *bp);
-void bnxt_ulp_start(struct bnxt *bp);
+void bnxt_ulp_start(struct bnxt *bp, int err);
 void bnxt_ulp_sriov_cfg(struct bnxt *bp, int num_vfs);
 void bnxt_ulp_shutdown(struct bnxt *bp);
 void bnxt_ulp_irq_stop(struct bnxt *bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
index f760921389a3..143c7a9cbbbf 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
@@ -413,6 +413,9 @@ static int bnxt_vf_reps_create(struct bnxt *bp)
 	struct net_device *dev;
 	int rc, i;
 
+	if (!(bp->flags & BNXT_FLAG_DSN_VALID))
+		return -ENODEV;
+
 	bp->vf_reps = kcalloc(num_vfs, sizeof(vf_rep), GFP_KERNEL);
 	if (!bp->vf_reps)
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index f64f3984e5cf..795ef2de5506 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -69,6 +69,9 @@
 #define GENET_RDMA_REG_OFF	(priv->hw_params->rdma_offset + \
 				TOTAL_DESC * DMA_DESC_SIZE)
 
+/* Forward declarations */
+static void bcmgenet_set_rx_mode(struct net_device *dev);
+
 static inline void bcmgenet_writel(u32 value, void __iomem *offset)
 {
 	/* MIPS chips strapped for BE will automagically configure the
@@ -995,6 +998,8 @@ static void bcmgenet_get_ethtool_stats(struct net_device *dev,
 	if (netif_running(dev))
 		bcmgenet_update_mib_counters(priv);
 
+	dev->netdev_ops->ndo_get_stats(dev);
+
 	for (i = 0; i < BCMGENET_STATS_LEN; i++) {
 		const struct bcmgenet_stats *s;
 		char *p;
@@ -1585,11 +1590,6 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto out;
 	}
 
-	if (skb_padto(skb, ETH_ZLEN)) {
-		ret = NETDEV_TX_OK;
-		goto out;
-	}
-
 	/* Retain how many bytes will be sent on the wire, without TSB inserted
 	 * by transmit checksum offload
 	 */
@@ -1638,6 +1638,9 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 		len_stat = (size << DMA_BUFLENGTH_SHIFT) |
 			   (priv->hw_params->qtag_mask << DMA_TX_QTAG_SHIFT);
 
+		/* Note: if we ever change from DMA_TX_APPEND_CRC below we
+		 * will need to restore software padding of "runt" packets
+		 */
 		if (!i) {
 			len_stat |= DMA_TX_APPEND_CRC | DMA_SOP;
 			if (skb->ip_summed == CHECKSUM_PARTIAL)
@@ -1694,7 +1697,8 @@ static struct sk_buff *bcmgenet_rx_refill(struct bcmgenet_priv *priv,
 	dma_addr_t mapping;
 
 	/* Allocate a new Rx skb */
-	skb = netdev_alloc_skb(priv->dev, priv->rx_buf_len + SKB_ALIGNMENT);
+	skb = __netdev_alloc_skb(priv->dev, priv->rx_buf_len + SKB_ALIGNMENT,
+				 GFP_ATOMIC | __GFP_NOWARN);
 	if (!skb) {
 		priv->mib.alloc_rx_buff_failed++;
 		netif_err(priv, rx_err, priv->dev,
@@ -2163,8 +2167,8 @@ static void bcmgenet_init_tx_ring(struct bcmgenet_priv *priv,
 				  DMA_END_ADDR);
 
 	/* Initialize Tx NAPI */
-	netif_napi_add(priv->dev, &ring->napi, bcmgenet_tx_poll,
-		       NAPI_POLL_WEIGHT);
+	netif_tx_napi_add(priv->dev, &ring->napi, bcmgenet_tx_poll,
+			  NAPI_POLL_WEIGHT);
 }
 
 /* Initialize a RDMA ring */
@@ -2853,6 +2857,7 @@ static void bcmgenet_netif_start(struct net_device *dev)
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 
 	/* Start the network engine */
+	bcmgenet_set_rx_mode(dev);
 	bcmgenet_enable_rx_napi(priv);
 
 	umac_enable_set(priv, CMD_TX_EN | CMD_RX_EN, true);
@@ -3208,6 +3213,7 @@ static struct net_device_stats *bcmgenet_get_stats(struct net_device *dev)
 	dev->stats.rx_packets = rx_packets;
 	dev->stats.rx_errors = rx_errors;
 	dev->stats.rx_missed_errors = rx_errors;
+	dev->stats.rx_dropped = rx_dropped;
 	return &dev->stats;
 }
 
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 51fc419f7410..b4df5e408f36 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -14,6 +14,7 @@
 #include <linux/if_vlan.h>
 #include <linux/phy.h>
 #include <linux/net_dim.h>
+#include <linux/ethtool.h>
 
 /* total number of Buffer Descriptors, same for Rx/Tx */
 #define TOTAL_DESC				256
@@ -674,6 +675,7 @@ struct bcmgenet_priv {
 	/* WOL */
 	struct clk *clk_wol;
 	u32 wolopts;
+	u8 sopass[SOPASS_MAX];
 
 	struct bcmgenet_mib_counters mib;
 
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
index ea20d94bd050..a41f82379369 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
@@ -41,18 +41,13 @@
 void bcmgenet_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	u32 reg;
 
 	wol->supported = WAKE_MAGIC | WAKE_MAGICSECURE;
 	wol->wolopts = priv->wolopts;
 	memset(wol->sopass, 0, sizeof(wol->sopass));
 
-	if (wol->wolopts & WAKE_MAGICSECURE) {
-		reg = bcmgenet_umac_readl(priv, UMAC_MPD_PW_MS);
-		put_unaligned_be16(reg, &wol->sopass[0]);
-		reg = bcmgenet_umac_readl(priv, UMAC_MPD_PW_LS);
-		put_unaligned_be32(reg, &wol->sopass[2]);
-	}
+	if (wol->wolopts & WAKE_MAGICSECURE)
+		memcpy(wol->sopass, priv->sopass, sizeof(priv->sopass));
 }
 
 /* ethtool function - set WOL (Wake on LAN) settings.
@@ -62,7 +57,6 @@ int bcmgenet_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	struct device *kdev = &priv->pdev->dev;
-	u32 reg;
 
 	if (!device_can_wakeup(kdev))
 		return -ENOTSUPP;
@@ -70,17 +64,8 @@ int bcmgenet_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 	if (wol->wolopts & ~(WAKE_MAGIC | WAKE_MAGICSECURE))
 		return -EINVAL;
 
-	reg = bcmgenet_umac_readl(priv, UMAC_MPD_CTRL);
-	if (wol->wolopts & WAKE_MAGICSECURE) {
-		bcmgenet_umac_writel(priv, get_unaligned_be16(&wol->sopass[0]),
-				     UMAC_MPD_PW_MS);
-		bcmgenet_umac_writel(priv, get_unaligned_be32(&wol->sopass[2]),
-				     UMAC_MPD_PW_LS);
-		reg |= MPD_PW_EN;
-	} else {
-		reg &= ~MPD_PW_EN;
-	}
-	bcmgenet_umac_writel(priv, reg, UMAC_MPD_CTRL);
+	if (wol->wolopts & WAKE_MAGICSECURE)
+		memcpy(priv->sopass, wol->sopass, sizeof(priv->sopass));
 
 	/* Flag the device and relevant IRQ as wakeup capable */
 	if (wol->wolopts) {
@@ -120,6 +105,14 @@ static int bcmgenet_poll_wol_status(struct bcmgenet_priv *priv)
 	return retries;
 }
 
+static void bcmgenet_set_mpd_password(struct bcmgenet_priv *priv)
+{
+	bcmgenet_umac_writel(priv, get_unaligned_be16(&priv->sopass[0]),
+			     UMAC_MPD_PW_MS);
+	bcmgenet_umac_writel(priv, get_unaligned_be32(&priv->sopass[2]),
+			     UMAC_MPD_PW_LS);
+}
+
 int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 				enum bcmgenet_power_mode mode)
 {
@@ -140,13 +133,17 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 
 	reg = bcmgenet_umac_readl(priv, UMAC_MPD_CTRL);
 	reg |= MPD_EN;
+	if (priv->wolopts & WAKE_MAGICSECURE) {
+		bcmgenet_set_mpd_password(priv);
+		reg |= MPD_PW_EN;
+	}
 	bcmgenet_umac_writel(priv, reg, UMAC_MPD_CTRL);
 
 	/* Do not leave UniMAC in MPD mode only */
 	retries = bcmgenet_poll_wol_status(priv);
 	if (retries < 0) {
 		reg = bcmgenet_umac_readl(priv, UMAC_MPD_CTRL);
-		reg &= ~MPD_EN;
+		reg &= ~(MPD_EN | MPD_PW_EN);
 		bcmgenet_umac_writel(priv, reg, UMAC_MPD_CTRL);
 		return retries;
 	}
@@ -185,7 +182,7 @@ void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
 	reg = bcmgenet_umac_readl(priv, UMAC_MPD_CTRL);
 	if (!(reg & MPD_EN))
 		return;	/* already powered up so skip the rest */
-	reg &= ~MPD_EN;
+	reg &= ~(MPD_EN | MPD_PW_EN);
 	bcmgenet_umac_writel(priv, reg, UMAC_MPD_CTRL);
 
 	/* Disable CRC Forward */
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 6d1f9c822548..4163e2cb1844 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -18174,8 +18174,8 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev,
 
 	rtnl_lock();
 
-	/* We probably don't have netdev yet */
-	if (!netdev || !netif_running(netdev))
+	/* Could be second call or maybe we don't have netdev yet */
+	if (!netdev || tp->pcierr_recovery || !netif_running(netdev))
 		goto done;
 
 	/* We needn't recover from permanent error */
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index a947050c4443..aef87ba68aec 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -65,7 +65,11 @@
 /* Max length of transmit frame must be a multiple of 8 bytes */
 #define MACB_TX_LEN_ALIGN	8
 #define MACB_MAX_TX_LEN		((unsigned int)((1 << MACB_TX_FRMLEN_SIZE) - 1) & ~((unsigned int)(MACB_TX_LEN_ALIGN - 1)))
-#define GEM_MAX_TX_LEN		((unsigned int)((1 << GEM_TX_FRMLEN_SIZE) - 1) & ~((unsigned int)(MACB_TX_LEN_ALIGN - 1)))
+/* Limit maximum TX length as per Cadence TSO errata. This is to avoid a
+ * false amba_error in TX path from the DMA assuming there is not enough
+ * space in the SRAM (16KB) even when there is.
+ */
+#define GEM_MAX_TX_LEN		(unsigned int)(0x3FC0)
 
 #define GEM_MTU_MIN_SIZE	ETH_MIN_MTU
 #define MACB_NETIF_LSO		NETIF_F_TSO
@@ -323,8 +327,10 @@ static int macb_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 	int status;
 
 	status = pm_runtime_get_sync(&bp->pdev->dev);
-	if (status < 0)
+	if (status < 0) {
+		pm_runtime_put_noidle(&bp->pdev->dev);
 		goto mdio_pm_exit;
+	}
 
 	status = macb_mdio_wait_for_idle(bp);
 	if (status < 0)
@@ -356,8 +362,10 @@ static int macb_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 	int status;
 
 	status = pm_runtime_get_sync(&bp->pdev->dev);
-	if (status < 0)
+	if (status < 0) {
+		pm_runtime_put_noidle(&bp->pdev->dev);
 		goto mdio_pm_exit;
+	}
 
 	status = macb_mdio_wait_for_idle(bp);
 	if (status < 0)
@@ -1655,16 +1663,14 @@ static netdev_features_t macb_features_check(struct sk_buff *skb,
 
 	/* Validate LSO compatibility */
 
-	/* there is only one buffer */
-	if (!skb_is_nonlinear(skb))
+	/* there is only one buffer or protocol is not UDP */
+	if (!skb_is_nonlinear(skb) || (ip_hdr(skb)->protocol != IPPROTO_UDP))
 		return features;
 
 	/* length of header */
 	hdrlen = skb_transport_offset(skb);
-	if (ip_hdr(skb)->protocol == IPPROTO_TCP)
-		hdrlen += tcp_hdrlen(skb);
 
-	/* For LSO:
+	/* For UFO only:
 	 * When software supplies two or more payload buffers all payload buffers
 	 * apart from the last must be a multiple of 8 bytes in size.
 	 */
@@ -3677,6 +3683,12 @@ static int at91ether_open(struct net_device *dev)
 	u32 ctl;
 	int ret;
 
+	ret = pm_runtime_get_sync(&lp->pdev->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(&lp->pdev->dev);
+		return ret;
+	}
+
 	/* Clear internal statistics */
 	ctl = macb_readl(lp, NCR);
 	macb_writel(lp, NCR, ctl | MACB_BIT(CLRSTAT));
@@ -3685,7 +3697,7 @@ static int at91ether_open(struct net_device *dev)
 
 	ret = at91ether_start(dev);
 	if (ret)
-		return ret;
+		goto pm_exit;
 
 	/* Enable MAC interrupts */
 	macb_writel(lp, IER, MACB_BIT(RCOMP)	|
@@ -3702,6 +3714,10 @@ static int at91ether_open(struct net_device *dev)
 	netif_start_queue(dev);
 
 	return 0;
+
+pm_exit:
+	pm_runtime_put_sync(&lp->pdev->dev);
+	return ret;
 }
 
 /* Close the interface */
@@ -3737,7 +3753,7 @@ static int at91ether_close(struct net_device *dev)
 			  q->rx_buffers, q->rx_buffers_dma);
 	q->rx_buffers = NULL;
 
-	return 0;
+	return pm_runtime_put(&lp->pdev->dev);
 }
 
 /* Transmit packet */
@@ -4132,7 +4148,7 @@ static int macb_probe(struct platform_device *pdev)
 	bp->wol = 0;
 	if (of_get_property(np, "magic-packet", NULL))
 		bp->wol |= MACB_WOL_HAS_MAGIC_PACKET;
-	device_init_wakeup(&pdev->dev, bp->wol & MACB_WOL_HAS_MAGIC_PACKET);
+	device_set_wakeup_capable(&pdev->dev, bp->wol & MACB_WOL_HAS_MAGIC_PACKET);
 
 	spin_lock_init(&bp->lock);
 
@@ -4325,7 +4341,8 @@ static int __maybe_unused macb_suspend(struct device *dev)
 	netif_carrier_off(netdev);
 	if (bp->ptp_info)
 		bp->ptp_info->ptp_remove(netdev);
-	pm_runtime_force_suspend(dev);
+	if (!device_may_wakeup(dev))
+		pm_runtime_force_suspend(dev);
 
 	return 0;
 }
@@ -4340,7 +4357,8 @@ static int __maybe_unused macb_resume(struct device *dev)
 	if (!netif_running(netdev))
 		return 0;
 
-	pm_runtime_force_resume(dev);
+	if (!device_may_wakeup(dev))
+		pm_runtime_force_resume(dev);
 
 	if (bp->wol & MACB_WOL_ENABLED) {
 		macb_writel(bp, IDR, MACB_BIT(WOL));
@@ -4379,7 +4397,7 @@ static int __maybe_unused macb_runtime_suspend(struct device *dev)
 	struct net_device *netdev = dev_get_drvdata(dev);
 	struct macb *bp = netdev_priv(netdev);
 
-	if (!(device_may_wakeup(&bp->dev->dev))) {
+	if (!(device_may_wakeup(dev))) {
 		clk_disable_unprepare(bp->tx_clk);
 		clk_disable_unprepare(bp->hclk);
 		clk_disable_unprepare(bp->pclk);
@@ -4395,7 +4413,7 @@ static int __maybe_unused macb_runtime_resume(struct device *dev)
 	struct net_device *netdev = dev_get_drvdata(dev);
 	struct macb *bp = netdev_priv(netdev);
 
-	if (!(device_may_wakeup(&bp->dev->dev))) {
+	if (!(device_may_wakeup(dev))) {
 		clk_prepare_enable(bp->pclk);
 		clk_prepare_enable(bp->hclk);
 		clk_prepare_enable(bp->tx_clk);
diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
index 43d11c38b38a..4cddd628d41b 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
@@ -1167,7 +1167,7 @@ static int cn23xx_get_pf_num(struct octeon_device *oct)
 		oct->pf_num = ((fdl_bit >> CN23XX_PCIE_SRIOV_FDL_BIT_POS) &
 			       CN23XX_PCIE_SRIOV_FDL_MASK);
 	} else {
-		ret = EINVAL;
+		ret = -EINVAL;
 
 		/* Under some virtual environments, extended PCI regs are
 		 * inaccessible, in which case the above read will have failed.
diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
index cdd7e5da4a74..d375e438d805 100644
--- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
+++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
@@ -235,6 +235,11 @@ static void octeon_mgmt_rx_fill_ring(struct net_device *netdev)
 
 		/* Put it in the ring.  */
 		p->rx_ring[p->rx_next_fill] = re.d64;
+		/* Make sure there is no reorder of filling the ring and ringing
+		 * the bell
+		 */
+		wmb();
+
 		dma_sync_single_for_device(p->dev, p->rx_ring_handle,
 					   ring_size_to_bytes(OCTEON_MGMT_RX_RING_SIZE),
 					   DMA_BIDIRECTIONAL);
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 48757afeb34e..e78e9e564e00 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -2046,11 +2046,11 @@ static void nicvf_set_rx_mode_task(struct work_struct *work_arg)
 	/* Save message data locally to prevent them from
 	 * being overwritten by next ndo_set_rx_mode call().
 	 */
-	spin_lock(&nic->rx_mode_wq_lock);
+	spin_lock_bh(&nic->rx_mode_wq_lock);
 	mode = vf_work->mode;
 	mc = vf_work->mc;
 	vf_work->mc = NULL;
-	spin_unlock(&nic->rx_mode_wq_lock);
+	spin_unlock_bh(&nic->rx_mode_wq_lock);
 
 	__nicvf_set_rx_mode_task(mode, mc, nic);
 }
@@ -2184,6 +2184,9 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		nic->max_queues *= 2;
 	nic->ptp_clock = ptp_clock;
 
+	/* Initialize mutex that serializes usage of VF's mailbox */
+	mutex_init(&nic->rx_mode_mtx);
+
 	/* MAP VF's configuration registers */
 	nic->reg_base = pcim_iomap(pdev, PCI_CFG_REG_BAR_NUM, 0);
 	if (!nic->reg_base) {
@@ -2260,7 +2263,6 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	INIT_WORK(&nic->rx_mode_work.work, nicvf_set_rx_mode_task);
 	spin_lock_init(&nic->rx_mode_wq_lock);
-	mutex_init(&nic->rx_mode_mtx);
 
 	err = register_netdev(netdev);
 	if (err) {
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 764d750825e9..7c691b052492 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -411,10 +411,19 @@ void bgx_lmac_rx_tx_enable(int node, int bgx_idx, int lmacid, bool enable)
 	lmac = &bgx->lmac[lmacid];
 
 	cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
-	if (enable)
+	if (enable) {
 		cfg |= CMR_PKT_RX_EN | CMR_PKT_TX_EN;
-	else
+
+		/* enable TX FIFO Underflow interrupt */
+		bgx_reg_modify(bgx, lmacid, BGX_GMP_GMI_TXX_INT_ENA_W1S,
+			       GMI_TXX_INT_UNDFLW);
+	} else {
 		cfg &= ~(CMR_PKT_RX_EN | CMR_PKT_TX_EN);
+
+		/* Disable TX FIFO Underflow interrupt */
+		bgx_reg_modify(bgx, lmacid, BGX_GMP_GMI_TXX_INT_ENA_W1C,
+			       GMI_TXX_INT_UNDFLW);
+	}
 	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg);
 
 	if (bgx->is_rgx)
@@ -1536,6 +1545,48 @@ static int bgx_init_phy(struct bgx *bgx)
 	return bgx_init_of_phy(bgx);
 }
 
+static irqreturn_t bgx_intr_handler(int irq, void *data)
+{
+	struct bgx *bgx = (struct bgx *)data;
+	u64 status, val;
+	int lmac;
+
+	for (lmac = 0; lmac < bgx->lmac_count; lmac++) {
+		status = bgx_reg_read(bgx, lmac, BGX_GMP_GMI_TXX_INT);
+		if (status & GMI_TXX_INT_UNDFLW) {
+			pci_err(bgx->pdev, "BGX%d lmac%d UNDFLW\n",
+				bgx->bgx_id, lmac);
+			val = bgx_reg_read(bgx, lmac, BGX_CMRX_CFG);
+			val &= ~CMR_EN;
+			bgx_reg_write(bgx, lmac, BGX_CMRX_CFG, val);
+			val |= CMR_EN;
+			bgx_reg_write(bgx, lmac, BGX_CMRX_CFG, val);
+		}
+		/* clear interrupts */
+		bgx_reg_write(bgx, lmac, BGX_GMP_GMI_TXX_INT, status);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void bgx_register_intr(struct pci_dev *pdev)
+{
+	struct bgx *bgx = pci_get_drvdata(pdev);
+	int ret;
+
+	ret = pci_alloc_irq_vectors(pdev, BGX_LMAC_VEC_OFFSET,
+				    BGX_LMAC_VEC_OFFSET, PCI_IRQ_ALL_TYPES);
+	if (ret < 0) {
+		pci_err(pdev, "Req for #%d msix vectors failed\n",
+			BGX_LMAC_VEC_OFFSET);
+		return;
+	}
+	ret = pci_request_irq(pdev, GMPX_GMI_TX_INT, bgx_intr_handler, NULL,
+			      bgx, "BGX%d", bgx->bgx_id);
+	if (ret)
+		pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx);
+}
+
 static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	int err;
@@ -1551,7 +1602,7 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	pci_set_drvdata(pdev, bgx);
 
-	err = pci_enable_device(pdev);
+	err = pcim_enable_device(pdev);
 	if (err) {
 		dev_err(dev, "Failed to enable PCI device\n");
 		pci_set_drvdata(pdev, NULL);
@@ -1605,6 +1656,8 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	bgx_init_hw(bgx);
 
+	bgx_register_intr(pdev);
+
 	/* Enable all LMACs */
 	for (lmac = 0; lmac < bgx->lmac_count; lmac++) {
 		err = bgx_lmac_enable(bgx, lmac);
@@ -1621,6 +1674,7 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 err_enable:
 	bgx_vnic[bgx->bgx_id] = NULL;
+	pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx);
 err_release_regions:
 	pci_release_regions(pdev);
 err_disable_device:
@@ -1638,6 +1692,8 @@ static void bgx_remove(struct pci_dev *pdev)
 	for (lmac = 0; lmac < bgx->lmac_count; lmac++)
 		bgx_lmac_disable(bgx, lmac);
 
+	pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx);
+
 	bgx_vnic[bgx->bgx_id] = NULL;
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
index 25888706bdcd..cdea49392185 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
@@ -180,6 +180,15 @@
 #define BGX_GMP_GMI_TXX_BURST		0x38228
 #define BGX_GMP_GMI_TXX_MIN_PKT		0x38240
 #define BGX_GMP_GMI_TXX_SGMII_CTL	0x38300
+#define BGX_GMP_GMI_TXX_INT		0x38500
+#define BGX_GMP_GMI_TXX_INT_W1S		0x38508
+#define BGX_GMP_GMI_TXX_INT_ENA_W1C	0x38510
+#define BGX_GMP_GMI_TXX_INT_ENA_W1S	0x38518
+#define  GMI_TXX_INT_PTP_LOST			BIT_ULL(4)
+#define  GMI_TXX_INT_LATE_COL			BIT_ULL(3)
+#define  GMI_TXX_INT_XSDEF			BIT_ULL(2)
+#define  GMI_TXX_INT_XSCOL			BIT_ULL(1)
+#define  GMI_TXX_INT_UNDFLW			BIT_ULL(0)
 
 #define BGX_MSIX_VEC_0_29_ADDR		0x400000 /* +(0..29) << 4 */
 #define BGX_MSIX_VEC_0_29_CTL		0x400008
diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
index 58f89f6a040f..97ff8608f0ab 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
@@ -2448,6 +2448,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr)
 
 		if (!is_offload(adapter))
 			return -EOPNOTSUPP;
+		if (!capable(CAP_NET_ADMIN))
+			return -EPERM;
 		if (!(adapter->flags & FULL_INIT_DONE))
 			return -EIO;	/* need the memory controllers */
 		if (copy_from_user(&t, useraddr, sizeof(t)))
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
index c2e92786608b..e26ae298a080 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
@@ -1054,9 +1054,9 @@ static void cudbg_t4_fwcache(struct cudbg_init *pdbg_init,
 	}
 }
 
-static unsigned long cudbg_mem_region_size(struct cudbg_init *pdbg_init,
-					   struct cudbg_error *cudbg_err,
-					   u8 mem_type)
+static int cudbg_mem_region_size(struct cudbg_init *pdbg_init,
+				 struct cudbg_error *cudbg_err,
+				 u8 mem_type, unsigned long *region_size)
 {
 	struct adapter *padap = pdbg_init->adap;
 	struct cudbg_meminfo mem_info;
@@ -1065,15 +1065,23 @@ static unsigned long cudbg_mem_region_size(struct cudbg_init *pdbg_init,
 
 	memset(&mem_info, 0, sizeof(struct cudbg_meminfo));
 	rc = cudbg_fill_meminfo(padap, &mem_info);
-	if (rc)
+	if (rc) {
+		cudbg_err->sys_err = rc;
 		return rc;
+	}
 
 	cudbg_t4_fwcache(pdbg_init, cudbg_err);
 	rc = cudbg_meminfo_get_mem_index(padap, &mem_info, mem_type, &mc_idx);
-	if (rc)
+	if (rc) {
+		cudbg_err->sys_err = rc;
 		return rc;
+	}
 
-	return mem_info.avail[mc_idx].limit - mem_info.avail[mc_idx].base;
+	if (region_size)
+		*region_size = mem_info.avail[mc_idx].limit -
+			       mem_info.avail[mc_idx].base;
+
+	return 0;
 }
 
 static int cudbg_collect_mem_region(struct cudbg_init *pdbg_init,
@@ -1081,7 +1089,12 @@ static int cudbg_collect_mem_region(struct cudbg_init *pdbg_init,
 				    struct cudbg_error *cudbg_err,
 				    u8 mem_type)
 {
-	unsigned long size = cudbg_mem_region_size(pdbg_init, cudbg_err, mem_type);
+	unsigned long size = 0;
+	int rc;
+
+	rc = cudbg_mem_region_size(pdbg_init, cudbg_err, mem_type, &size);
+	if (rc)
+		return rc;
 
 	return cudbg_read_fw_mem(pdbg_init, dbg_buff, mem_type, size,
 				 cudbg_err);
@@ -1967,7 +1980,6 @@ int cudbg_collect_dump_context(struct cudbg_init *pdbg_init,
 	u8 mem_type[CTXT_INGRESS + 1] = { 0 };
 	struct cudbg_buffer temp_buff = { 0 };
 	struct cudbg_ch_cntxt *buff;
-	u64 *dst_off, *src_off;
 	u8 *ctx_buf;
 	u8 i, k;
 	int rc;
@@ -2036,8 +2048,11 @@ int cudbg_collect_dump_context(struct cudbg_init *pdbg_init,
 		}
 
 		for (j = 0; j < max_ctx_qid; j++) {
+			__be64 *dst_off;
+			u64 *src_off;
+
 			src_off = (u64 *)(ctx_buf + j * SGE_CTXT_SIZE);
-			dst_off = (u64 *)buff->data;
+			dst_off = (__be64 *)buff->data;
 
 			/* The data is stored in 64-bit cpu order.  Convert it
 			 * to big endian before parsing.
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index d692251ee252..04b1ebd6d594 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -70,8 +70,7 @@ static void *seq_tab_start(struct seq_file *seq, loff_t *pos)
 static void *seq_tab_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	v = seq_tab_get_idx(seq->private, *pos + 1);
-	if (v)
-		++*pos;
+	++(*pos);
 	return v;
 }
 
@@ -2996,6 +2995,9 @@ static int sge_queue_entries(const struct adapter *adap)
 	int tot_uld_entries = 0;
 	int i;
 
+	if (!is_uld(adap))
+		goto lld_only;
+
 	mutex_lock(&uld_mutex);
 	for (i = 0; i < CXGB4_TX_MAX; i++)
 		tot_uld_entries += sge_qinfo_uld_txq_entries(adap, i);
@@ -3006,6 +3008,7 @@ static int sge_queue_entries(const struct adapter *adap)
 	}
 	mutex_unlock(&uld_mutex);
 
+lld_only:
 	return DIV_ROUND_UP(adap->sge.ethqsets, 4) +
 	       tot_uld_entries +
 	       DIV_ROUND_UP(MAX_CTRL_QUEUES, 4) + 1;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
index 4107007b6ec4..6e3c09890633 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
@@ -165,6 +165,9 @@ static void set_nat_params(struct adapter *adap, struct filter_entry *f,
 			   unsigned int tid, bool dip, bool sip, bool dp,
 			   bool sp)
 {
+	u8 *nat_lp = (u8 *)&f->fs.nat_lport;
+	u8 *nat_fp = (u8 *)&f->fs.nat_fport;
+
 	if (dip) {
 		if (f->fs.type) {
 			set_tcb_field(adap, f, tid, TCB_SND_UNA_RAW_W,
@@ -236,8 +239,9 @@ static void set_nat_params(struct adapter *adap, struct filter_entry *f,
 	}
 
 	set_tcb_field(adap, f, tid, TCB_PDU_HDR_LEN_W, WORD_MASK,
-		      (dp ? f->fs.nat_lport : 0) |
-		      (sp ? f->fs.nat_fport << 16 : 0), 1);
+		      (dp ? (nat_lp[1] | nat_lp[0] << 8) : 0) |
+		      (sp ? (nat_fp[1] << 16 | nat_fp[0] << 24) : 0),
+		      1);
 }
 
 /* Validate filter spec against configuration done on the card. */
@@ -655,6 +659,9 @@ int set_filter_wr(struct adapter *adapter, int fidx)
 	fwr->fpm = htons(f->fs.mask.fport);
 
 	if (adapter->params.filter2_wr_support) {
+		u8 *nat_lp = (u8 *)&f->fs.nat_lport;
+		u8 *nat_fp = (u8 *)&f->fs.nat_fport;
+
 		fwr->natmode_to_ulp_type =
 			FW_FILTER2_WR_ULP_TYPE_V(f->fs.nat_mode ?
 						 ULP_MODE_TCPDDP :
@@ -662,8 +669,8 @@ int set_filter_wr(struct adapter *adapter, int fidx)
 			FW_FILTER2_WR_NATMODE_V(f->fs.nat_mode);
 		memcpy(fwr->newlip, f->fs.nat_lip, sizeof(fwr->newlip));
 		memcpy(fwr->newfip, f->fs.nat_fip, sizeof(fwr->newfip));
-		fwr->newlport = htons(f->fs.nat_lport);
-		fwr->newfport = htons(f->fs.nat_fport);
+		fwr->newlport = htons(nat_lp[1] | nat_lp[0] << 8);
+		fwr->newfport = htons(nat_fp[1] | nat_fp[0] << 8);
 	}
 
 	/* Mark the filter as "pending" and ship off the Filter Work Request.
@@ -833,16 +840,16 @@ static bool is_addr_all_mask(u8 *ipmask, int family)
 		struct in_addr *addr;
 
 		addr = (struct in_addr *)ipmask;
-		if (addr->s_addr == 0xffffffff)
+		if (addr->s_addr == htonl(0xffffffff))
 			return true;
 	} else if (family == AF_INET6) {
 		struct in6_addr *addr6;
 
 		addr6 = (struct in6_addr *)ipmask;
-		if (addr6->s6_addr32[0] == 0xffffffff &&
-		    addr6->s6_addr32[1] == 0xffffffff &&
-		    addr6->s6_addr32[2] == 0xffffffff &&
-		    addr6->s6_addr32[3] == 0xffffffff)
+		if (addr6->s6_addr32[0] == htonl(0xffffffff) &&
+		    addr6->s6_addr32[1] == htonl(0xffffffff) &&
+		    addr6->s6_addr32[2] == htonl(0xffffffff) &&
+		    addr6->s6_addr32[3] == htonl(0xffffffff))
 			return true;
 	}
 	return false;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 715e4edcf4a2..bd34474a9ecf 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -2412,7 +2412,7 @@ int cxgb4_create_server_filter(const struct net_device *dev, unsigned int stid,
 
 	/* Clear out filter specifications */
 	memset(&f->fs, 0, sizeof(struct ch_filter_specification));
-	f->fs.val.lport = cpu_to_be16(sport);
+	f->fs.val.lport = be16_to_cpu(sport);
 	f->fs.mask.lport  = ~0;
 	val = (u8 *)&sip;
 	if ((val[0] | val[1] | val[2] | val[3]) != 0) {
@@ -2940,7 +2940,6 @@ static int cxgb_set_mac_addr(struct net_device *dev, void *p)
 		return ret;
 
 	memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
-	pi->xact_addr_filt = ret;
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c
index 58a039c3224a..f5bc996ac77d 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c
@@ -246,6 +246,9 @@ static int  cxgb4_ptp_fineadjtime(struct adapter *adapter, s64 delta)
 			     FW_PTP_CMD_PORTID_V(0));
 	c.retval_len16 = cpu_to_be32(FW_CMD_LEN16_V(sizeof(c) / 16));
 	c.u.ts.sc = FW_PTP_SC_ADJ_FTIME;
+	c.u.ts.sign = (delta < 0) ? 1 : 0;
+	if (delta < 0)
+		delta = -delta;
 	c.u.ts.tm = cpu_to_be64(delta);
 
 	err = t4_wr_mbox(adapter, adapter->mbox, &c, sizeof(c), NULL);
@@ -308,32 +311,17 @@ static int cxgb4_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
  */
 static int cxgb4_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
 {
-	struct adapter *adapter = (struct adapter *)container_of(ptp,
-				   struct adapter, ptp_clock_info);
-	struct fw_ptp_cmd c;
+	struct adapter *adapter = container_of(ptp, struct adapter,
+					       ptp_clock_info);
 	u64 ns;
-	int err;
 
-	memset(&c, 0, sizeof(c));
-	c.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PTP_CMD) |
-				     FW_CMD_REQUEST_F |
-				     FW_CMD_READ_F |
-				     FW_PTP_CMD_PORTID_V(0));
-	c.retval_len16 = cpu_to_be32(FW_CMD_LEN16_V(sizeof(c) / 16));
-	c.u.ts.sc = FW_PTP_SC_GET_TIME;
-
-	err = t4_wr_mbox(adapter, adapter->mbox, &c, sizeof(c), &c);
-	if (err < 0) {
-		dev_err(adapter->pdev_dev,
-			"PTP: %s error %d\n", __func__, -err);
-		return err;
-	}
+	ns = t4_read_reg(adapter, T5_PORT_REG(0, MAC_PORT_PTP_SUM_LO_A));
+	ns |= (u64)t4_read_reg(adapter,
+			       T5_PORT_REG(0, MAC_PORT_PTP_SUM_HI_A)) << 32;
 
 	/* convert to timespec*/
-	ns = be64_to_cpu(c.u.ts.tm);
 	*ts = ns_to_timespec64(ns);
-
-	return err;
+	return 0;
 }
 
 /**
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
index 56742fa0c1af..bde9dd4c9737 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
@@ -58,10 +58,6 @@ static struct ch_tc_pedit_fields pedits[] = {
 	PEDIT_FIELDS(IP6_, DST_63_32, 4, nat_lip, 4),
 	PEDIT_FIELDS(IP6_, DST_95_64, 4, nat_lip, 8),
 	PEDIT_FIELDS(IP6_, DST_127_96, 4, nat_lip, 12),
-	PEDIT_FIELDS(TCP_, SPORT, 2, nat_fport, 0),
-	PEDIT_FIELDS(TCP_, DPORT, 2, nat_lport, 0),
-	PEDIT_FIELDS(UDP_, SPORT, 2, nat_fport, 0),
-	PEDIT_FIELDS(UDP_, DPORT, 2, nat_lport, 0),
 };
 
 static struct ch_tc_flower_entry *allocate_flower_entry(void)
@@ -156,14 +152,14 @@ static void cxgb4_process_flow_match(struct net_device *dev,
 		struct flow_match_ports match;
 
 		flow_rule_match_ports(rule, &match);
-		fs->val.lport = cpu_to_be16(match.key->dst);
-		fs->mask.lport = cpu_to_be16(match.mask->dst);
-		fs->val.fport = cpu_to_be16(match.key->src);
-		fs->mask.fport = cpu_to_be16(match.mask->src);
+		fs->val.lport = be16_to_cpu(match.key->dst);
+		fs->mask.lport = be16_to_cpu(match.mask->dst);
+		fs->val.fport = be16_to_cpu(match.key->src);
+		fs->mask.fport = be16_to_cpu(match.mask->src);
 
 		/* also initialize nat_lport/fport to same values */
-		fs->nat_lport = cpu_to_be16(match.key->dst);
-		fs->nat_fport = cpu_to_be16(match.key->src);
+		fs->nat_lport = fs->val.lport;
+		fs->nat_fport = fs->val.fport;
 	}
 
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) {
@@ -354,12 +350,9 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val,
 		switch (offset) {
 		case PEDIT_TCP_SPORT_DPORT:
 			if (~mask & PEDIT_TCP_UDP_SPORT_MASK)
-				offload_pedit(fs, cpu_to_be32(val) >> 16,
-					      cpu_to_be32(mask) >> 16,
-					      TCP_SPORT);
+				fs->nat_fport = val;
 			else
-				offload_pedit(fs, cpu_to_be32(val),
-					      cpu_to_be32(mask), TCP_DPORT);
+				fs->nat_lport = val >> 16;
 		}
 		fs->nat_mode = NAT_MODE_ALL;
 		break;
@@ -367,12 +360,9 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val,
 		switch (offset) {
 		case PEDIT_UDP_SPORT_DPORT:
 			if (~mask & PEDIT_TCP_UDP_SPORT_MASK)
-				offload_pedit(fs, cpu_to_be32(val) >> 16,
-					      cpu_to_be32(mask) >> 16,
-					      UDP_SPORT);
+				fs->nat_fport = val;
 			else
-				offload_pedit(fs, cpu_to_be32(val),
-					      cpu_to_be32(mask), UDP_DPORT);
+				fs->nat_lport = val >> 16;
 		}
 		fs->nat_mode = NAT_MODE_ALL;
 	}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c
index 02fc63fa7f25..b3a342561a96 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c
@@ -47,7 +47,7 @@ static int fill_match_fields(struct adapter *adap,
 			     bool next_header)
 {
 	unsigned int i, j;
-	u32 val, mask;
+	__be32 val, mask;
 	int off, err;
 	bool found;
 
@@ -216,7 +216,7 @@ int cxgb4_config_knode(struct net_device *dev, struct tc_cls_u32_offload *cls)
 		const struct cxgb4_next_header *next;
 		bool found = false;
 		unsigned int i, j;
-		u32 val, mask;
+		__be32 val, mask;
 		int off;
 
 		if (t->table[link_uhtid - 1].link_handle) {
@@ -230,10 +230,10 @@ int cxgb4_config_knode(struct net_device *dev, struct tc_cls_u32_offload *cls)
 
 		/* Try to find matches that allow jumps to next header. */
 		for (i = 0; next[i].jump; i++) {
-			if (next[i].offoff != cls->knode.sel->offoff ||
-			    next[i].shift != cls->knode.sel->offshift ||
-			    next[i].mask != cls->knode.sel->offmask ||
-			    next[i].offset != cls->knode.sel->off)
+			if (next[i].sel.offoff != cls->knode.sel->offoff ||
+			    next[i].sel.offshift != cls->knode.sel->offshift ||
+			    next[i].sel.offmask != cls->knode.sel->offmask ||
+			    next[i].sel.off != cls->knode.sel->off)
 				continue;
 
 			/* Found a possible candidate.  Find a key that
@@ -245,9 +245,9 @@ int cxgb4_config_knode(struct net_device *dev, struct tc_cls_u32_offload *cls)
 				val = cls->knode.sel->keys[j].val;
 				mask = cls->knode.sel->keys[j].mask;
 
-				if (next[i].match_off == off &&
-				    next[i].match_val == val &&
-				    next[i].match_mask == mask) {
+				if (next[i].key.off == off &&
+				    next[i].key.val == val &&
+				    next[i].key.mask == mask) {
 					found = true;
 					break;
 				}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h
index a4b99edcc339..141085e159e5 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h
@@ -38,12 +38,12 @@
 struct cxgb4_match_field {
 	int off; /* Offset from the beginning of the header to match */
 	/* Fill the value/mask pair in the spec if matched */
-	int (*val)(struct ch_filter_specification *f, u32 val, u32 mask);
+	int (*val)(struct ch_filter_specification *f, __be32 val, __be32 mask);
 };
 
 /* IPv4 match fields */
 static inline int cxgb4_fill_ipv4_tos(struct ch_filter_specification *f,
-				      u32 val, u32 mask)
+				      __be32 val, __be32 mask)
 {
 	f->val.tos  = (ntohl(val)  >> 16) & 0x000000FF;
 	f->mask.tos = (ntohl(mask) >> 16) & 0x000000FF;
@@ -52,7 +52,7 @@ static inline int cxgb4_fill_ipv4_tos(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv4_frag(struct ch_filter_specification *f,
-				       u32 val, u32 mask)
+				       __be32 val, __be32 mask)
 {
 	u32 mask_val;
 	u8 frag_val;
@@ -74,7 +74,7 @@ static inline int cxgb4_fill_ipv4_frag(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv4_proto(struct ch_filter_specification *f,
-					u32 val, u32 mask)
+					__be32 val, __be32 mask)
 {
 	f->val.proto  = (ntohl(val)  >> 16) & 0x000000FF;
 	f->mask.proto = (ntohl(mask) >> 16) & 0x000000FF;
@@ -83,7 +83,7 @@ static inline int cxgb4_fill_ipv4_proto(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv4_src_ip(struct ch_filter_specification *f,
-					 u32 val, u32 mask)
+					 __be32 val, __be32 mask)
 {
 	memcpy(&f->val.fip[0],  &val,  sizeof(u32));
 	memcpy(&f->mask.fip[0], &mask, sizeof(u32));
@@ -92,7 +92,7 @@ static inline int cxgb4_fill_ipv4_src_ip(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv4_dst_ip(struct ch_filter_specification *f,
-					 u32 val, u32 mask)
+					 __be32 val, __be32 mask)
 {
 	memcpy(&f->val.lip[0],  &val,  sizeof(u32));
 	memcpy(&f->mask.lip[0], &mask, sizeof(u32));
@@ -111,7 +111,7 @@ static const struct cxgb4_match_field cxgb4_ipv4_fields[] = {
 
 /* IPv6 match fields */
 static inline int cxgb4_fill_ipv6_tos(struct ch_filter_specification *f,
-				      u32 val, u32 mask)
+				      __be32 val, __be32 mask)
 {
 	f->val.tos  = (ntohl(val)  >> 20) & 0x000000FF;
 	f->mask.tos = (ntohl(mask) >> 20) & 0x000000FF;
@@ -120,7 +120,7 @@ static inline int cxgb4_fill_ipv6_tos(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_proto(struct ch_filter_specification *f,
-					u32 val, u32 mask)
+					__be32 val, __be32 mask)
 {
 	f->val.proto  = (ntohl(val)  >> 8) & 0x000000FF;
 	f->mask.proto = (ntohl(mask) >> 8) & 0x000000FF;
@@ -129,7 +129,7 @@ static inline int cxgb4_fill_ipv6_proto(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_src_ip0(struct ch_filter_specification *f,
-					  u32 val, u32 mask)
+					  __be32 val, __be32 mask)
 {
 	memcpy(&f->val.fip[0],  &val,  sizeof(u32));
 	memcpy(&f->mask.fip[0], &mask, sizeof(u32));
@@ -138,7 +138,7 @@ static inline int cxgb4_fill_ipv6_src_ip0(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_src_ip1(struct ch_filter_specification *f,
-					  u32 val, u32 mask)
+					  __be32 val, __be32 mask)
 {
 	memcpy(&f->val.fip[4],  &val,  sizeof(u32));
 	memcpy(&f->mask.fip[4], &mask, sizeof(u32));
@@ -147,7 +147,7 @@ static inline int cxgb4_fill_ipv6_src_ip1(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_src_ip2(struct ch_filter_specification *f,
-					  u32 val, u32 mask)
+					  __be32 val, __be32 mask)
 {
 	memcpy(&f->val.fip[8],  &val,  sizeof(u32));
 	memcpy(&f->mask.fip[8], &mask, sizeof(u32));
@@ -156,7 +156,7 @@ static inline int cxgb4_fill_ipv6_src_ip2(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_src_ip3(struct ch_filter_specification *f,
-					  u32 val, u32 mask)
+					  __be32 val, __be32 mask)
 {
 	memcpy(&f->val.fip[12],  &val,  sizeof(u32));
 	memcpy(&f->mask.fip[12], &mask, sizeof(u32));
@@ -165,7 +165,7 @@ static inline int cxgb4_fill_ipv6_src_ip3(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_dst_ip0(struct ch_filter_specification *f,
-					  u32 val, u32 mask)
+					  __be32 val, __be32 mask)
 {
 	memcpy(&f->val.lip[0],  &val,  sizeof(u32));
 	memcpy(&f->mask.lip[0], &mask, sizeof(u32));
@@ -174,7 +174,7 @@ static inline int cxgb4_fill_ipv6_dst_ip0(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_dst_ip1(struct ch_filter_specification *f,
-					  u32 val, u32 mask)
+					  __be32 val, __be32 mask)
 {
 	memcpy(&f->val.lip[4],  &val,  sizeof(u32));
 	memcpy(&f->mask.lip[4], &mask, sizeof(u32));
@@ -183,7 +183,7 @@ static inline int cxgb4_fill_ipv6_dst_ip1(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_dst_ip2(struct ch_filter_specification *f,
-					  u32 val, u32 mask)
+					  __be32 val, __be32 mask)
 {
 	memcpy(&f->val.lip[8],  &val,  sizeof(u32));
 	memcpy(&f->mask.lip[8], &mask, sizeof(u32));
@@ -192,7 +192,7 @@ static inline int cxgb4_fill_ipv6_dst_ip2(struct ch_filter_specification *f,
 }
 
 static inline int cxgb4_fill_ipv6_dst_ip3(struct ch_filter_specification *f,
-					  u32 val, u32 mask)
+					  __be32 val, __be32 mask)
 {
 	memcpy(&f->val.lip[12],  &val,  sizeof(u32));
 	memcpy(&f->mask.lip[12], &mask, sizeof(u32));
@@ -216,7 +216,7 @@ static const struct cxgb4_match_field cxgb4_ipv6_fields[] = {
 
 /* TCP/UDP match */
 static inline int cxgb4_fill_l4_ports(struct ch_filter_specification *f,
-				      u32 val, u32 mask)
+				      __be32 val, __be32 mask)
 {
 	f->val.fport  = ntohl(val)  >> 16;
 	f->mask.fport = ntohl(mask) >> 16;
@@ -237,19 +237,13 @@ static const struct cxgb4_match_field cxgb4_udp_fields[] = {
 };
 
 struct cxgb4_next_header {
-	unsigned int offset; /* Offset to next header */
-	/* offset, shift, and mask added to offset above
+	/* Offset, shift, and mask added to beginning of the header
 	 * to get to next header.  Useful when using a header
 	 * field's value to jump to next header such as IHL field
 	 * in IPv4 header.
 	 */
-	unsigned int offoff;
-	u32 shift;
-	u32 mask;
-	/* match criteria to make this jump */
-	unsigned int match_off;
-	u32 match_val;
-	u32 match_mask;
+	struct tc_u32_sel sel;
+	struct tc_u32_key key;
 	/* location of jump to make */
 	const struct cxgb4_match_field *jump;
 };
@@ -258,26 +252,74 @@ struct cxgb4_next_header {
  * IPv4 header.
  */
 static const struct cxgb4_next_header cxgb4_ipv4_jumps[] = {
-	{ .offset = 0, .offoff = 0, .shift = 6, .mask = 0xF,
-	  .match_off = 8, .match_val = 0x600, .match_mask = 0xFF00,
-	  .jump = cxgb4_tcp_fields },
-	{ .offset = 0, .offoff = 0, .shift = 6, .mask = 0xF,
-	  .match_off = 8, .match_val = 0x1100, .match_mask = 0xFF00,
-	  .jump = cxgb4_udp_fields },
-	{ .jump = NULL }
+	{
+		/* TCP Jump */
+		.sel = {
+			.off = 0,
+			.offoff = 0,
+			.offshift = 6,
+			.offmask = cpu_to_be16(0x0f00),
+		},
+		.key = {
+			.off = 8,
+			.val = cpu_to_be32(0x00060000),
+			.mask = cpu_to_be32(0x00ff0000),
+		},
+		.jump = cxgb4_tcp_fields,
+	},
+	{
+		/* UDP Jump */
+		.sel = {
+			.off = 0,
+			.offoff = 0,
+			.offshift = 6,
+			.offmask = cpu_to_be16(0x0f00),
+		},
+		.key = {
+			.off = 8,
+			.val = cpu_to_be32(0x00110000),
+			.mask = cpu_to_be32(0x00ff0000),
+		},
+		.jump = cxgb4_udp_fields,
+	},
+	{ .jump = NULL },
 };
 
 /* Accept a rule with a jump directly past the 40 Bytes of IPv6 fixed header
  * to get to transport layer header.
  */
 static const struct cxgb4_next_header cxgb4_ipv6_jumps[] = {
-	{ .offset = 0x28, .offoff = 0, .shift = 0, .mask = 0,
-	  .match_off = 4, .match_val = 0x60000, .match_mask = 0xFF0000,
-	  .jump = cxgb4_tcp_fields },
-	{ .offset = 0x28, .offoff = 0, .shift = 0, .mask = 0,
-	  .match_off = 4, .match_val = 0x110000, .match_mask = 0xFF0000,
-	  .jump = cxgb4_udp_fields },
-	{ .jump = NULL }
+	{
+		/* TCP Jump */
+		.sel = {
+			.off = 40,
+			.offoff = 0,
+			.offshift = 0,
+			.offmask = 0,
+		},
+		.key = {
+			.off = 4,
+			.val = cpu_to_be32(0x00000600),
+			.mask = cpu_to_be32(0x0000ff00),
+		},
+		.jump = cxgb4_tcp_fields,
+	},
+	{
+		/* UDP Jump */
+		.sel = {
+			.off = 40,
+			.offoff = 0,
+			.offshift = 0,
+			.offmask = 0,
+		},
+		.key = {
+			.off = 4,
+			.val = cpu_to_be32(0x00001100),
+			.mask = cpu_to_be32(0x0000ff00),
+		},
+		.jump = cxgb4_udp_fields,
+	},
+	{ .jump = NULL },
 };
 
 struct cxgb4_link {
diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
index 1a407d3c1d67..a440c1cf0b61 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
@@ -507,40 +507,19 @@ u64 cxgb4_select_ntuple(struct net_device *dev,
 EXPORT_SYMBOL(cxgb4_select_ntuple);
 
 /*
- * Called when address resolution fails for an L2T entry to handle packets
- * on the arpq head.  If a packet specifies a failure handler it is invoked,
- * otherwise the packet is sent to the device.
- */
-static void handle_failed_resolution(struct adapter *adap, struct l2t_entry *e)
-{
-	struct sk_buff *skb;
-
-	while ((skb = __skb_dequeue(&e->arpq)) != NULL) {
-		const struct l2t_skb_cb *cb = L2T_SKB_CB(skb);
-
-		spin_unlock(&e->lock);
-		if (cb->arp_err_handler)
-			cb->arp_err_handler(cb->handle, skb);
-		else
-			t4_ofld_send(adap, skb);
-		spin_lock(&e->lock);
-	}
-}
-
-/*
  * Called when the host's neighbor layer makes a change to some entry that is
  * loaded into the HW L2 table.
  */
 void t4_l2t_update(struct adapter *adap, struct neighbour *neigh)
 {
-	struct l2t_entry *e;
-	struct sk_buff_head *arpq = NULL;
-	struct l2t_data *d = adap->l2t;
 	unsigned int addr_len = neigh->tbl->key_len;
 	u32 *addr = (u32 *) neigh->primary_key;
-	int ifidx = neigh->dev->ifindex;
-	int hash = addr_hash(d, addr, addr_len, ifidx);
+	int hash, ifidx = neigh->dev->ifindex;
+	struct sk_buff_head *arpq = NULL;
+	struct l2t_data *d = adap->l2t;
+	struct l2t_entry *e;
 
+	hash = addr_hash(d, addr, addr_len, ifidx);
 	read_lock_bh(&d->lock);
 	for (e = d->l2tab[hash].first; e; e = e->next)
 		if (!addreq(e, addr) && e->ifindex == ifidx) {
@@ -573,8 +552,25 @@ void t4_l2t_update(struct adapter *adap, struct neighbour *neigh)
 			write_l2e(adap, e, 0);
 	}
 
-	if (arpq)
-		handle_failed_resolution(adap, e);
+	if (arpq) {
+		struct sk_buff *skb;
+
+		/* Called when address resolution fails for an L2T
+		 * entry to handle packets on the arpq head. If a
+		 * packet specifies a failure handler it is invoked,
+		 * otherwise the packet is sent to the device.
+		 */
+		while ((skb = __skb_dequeue(&e->arpq)) != NULL) {
+			const struct l2t_skb_cb *cb = L2T_SKB_CB(skb);
+
+			spin_unlock(&e->lock);
+			if (cb->arp_err_handler)
+				cb->arp_err_handler(cb->handle, skb);
+			else
+				t4_ofld_send(adap, skb);
+			spin_lock(&e->lock);
+		}
+	}
 	spin_unlock_bh(&e->lock);
 }
 
@@ -682,8 +678,7 @@ static void *l2t_seq_start(struct seq_file *seq, loff_t *pos)
 static void *l2t_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	v = l2t_get_idx(seq, *pos);
-	if (v)
-		++*pos;
+	++(*pos);
 	return v;
 }
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index 928bfea5457b..049f1bbe27ab 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -1324,8 +1324,9 @@ static inline void t6_fill_tnl_lso(struct sk_buff *skb,
 int t4_sge_eth_txq_egress_update(struct adapter *adap, struct sge_eth_txq *eq,
 				 int maxreclaim)
 {
+	unsigned int reclaimed, hw_cidx;
 	struct sge_txq *q = &eq->q;
-	unsigned int reclaimed;
+	int hw_in_use;
 
 	if (!q->in_use || !__netif_tx_trylock(eq->txq))
 		return 0;
@@ -1333,12 +1334,17 @@ int t4_sge_eth_txq_egress_update(struct adapter *adap, struct sge_eth_txq *eq,
 	/* Reclaim pending completed TX Descriptors. */
 	reclaimed = reclaim_completed_tx(adap, &eq->q, maxreclaim, true);
 
+	hw_cidx = ntohs(READ_ONCE(q->stat->cidx));
+	hw_in_use = q->pidx - hw_cidx;
+	if (hw_in_use < 0)
+		hw_in_use += q->size;
+
 	/* If the TX Queue is currently stopped and there's now more than half
 	 * the queue available, restart it.  Otherwise bail out since the rest
 	 * of what we want do here is with the possibility of shipping any
 	 * currently buffered Coalesced TX Work Request.
 	 */
-	if (netif_tx_queue_stopped(eq->txq) && txq_avail(q) > (q->size / 2)) {
+	if (netif_tx_queue_stopped(eq->txq) && hw_in_use < (q->size / 2)) {
 		netif_tx_wake_queue(eq->txq);
 		eq->q.restarts++;
 	}
@@ -1469,16 +1475,7 @@ out_free:	dev_kfree_skb_any(skb);
 		 * has opened up.
 		 */
 		eth_txq_stop(q);
-
-		/* If we're using the SGE Doorbell Queue Timer facility, we
-		 * don't need to ask the Firmware to send us Egress Queue CIDX
-		 * Updates: the Hardware will do this automatically.  And
-		 * since we send the Ingress Queue CIDX Updates to the
-		 * corresponding Ethernet Response Queue, we'll get them very
-		 * quickly.
-		 */
-		if (!q->dbqt)
-			wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
+		wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
 	}
 
 	wr = (void *)&q->q.desc[q->q.pidx];
@@ -1792,16 +1789,7 @@ static netdev_tx_t cxgb4_vf_eth_xmit(struct sk_buff *skb,
 		 * has opened up.
 		 */
 		eth_txq_stop(txq);
-
-		/* If we're using the SGE Doorbell Queue Timer facility, we
-		 * don't need to ask the Firmware to send us Egress Queue CIDX
-		 * Updates: the Hardware will do this automatically.  And
-		 * since we send the Ingress Queue CIDX Updates to the
-		 * corresponding Ethernet Response Queue, we'll get them very
-		 * quickly.
-		 */
-		if (!txq->dbqt)
-			wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
+		wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
 	}
 
 	/* Start filling in our Work Request.  Note that we do _not_ handle
@@ -2453,6 +2441,7 @@ static inline int uld_send(struct adapter *adap, struct sk_buff *skb,
 	txq_info = adap->sge.uld_txq_info[tx_uld_type];
 	if (unlikely(!txq_info)) {
 		WARN_ON(true);
+		kfree_skb(skb);
 		return NET_XMIT_DROP;
 	}
 
@@ -2828,7 +2817,7 @@ static noinline int t4_systim_to_hwstamp(struct adapter *adapter,
 
 	hwtstamps = skb_hwtstamps(skb);
 	memset(hwtstamps, 0, sizeof(*hwtstamps));
-	hwtstamps->hwtstamp = ns_to_ktime(be64_to_cpu(*((u64 *)data)));
+	hwtstamps->hwtstamp = ns_to_ktime(get_unaligned_be64(data));
 
 	return RX_PTP_PKT_SUC;
 }
@@ -2924,26 +2913,6 @@ static void t4_tx_completion_handler(struct sge_rspq *rspq,
 	}
 
 	txq = &s->ethtxq[pi->first_qset + rspq->idx];
-
-	/* We've got the Hardware Consumer Index Update in the Egress Update
-	 * message.  If we're using the SGE Doorbell Queue Timer mechanism,
-	 * these Egress Update messages will be our sole CIDX Updates we get
-	 * since we don't want to chew up PCIe bandwidth for both Ingress
-	 * Messages and Status Page writes.  However, The code which manages
-	 * reclaiming successfully DMA'ed TX Work Requests uses the CIDX value
-	 * stored in the Status Page at the end of the TX Queue.  It's easiest
-	 * to simply copy the CIDX Update value from the Egress Update message
-	 * to the Status Page.  Also note that no Endian issues need to be
-	 * considered here since both are Big Endian and we're just copying
-	 * bytes consistently ...
-	 */
-	if (txq->dbqt) {
-		struct cpl_sge_egr_update *egr;
-
-		egr = (struct cpl_sge_egr_update *)rsp;
-		WRITE_ONCE(txq->q.stat->cidx, egr->cidx);
-	}
-
 	t4_sge_eth_txq_egress_update(adapter, txq, -1);
 }
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 33d046f0ac28..ab42cecb4285 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -3499,7 +3499,7 @@ int t4_prep_fw(struct adapter *adap, struct fw_info *fw_info,
 	drv_fw = &fw_info->fw_hdr;
 
 	/* Read the header of the firmware on the card */
-	ret = -t4_read_flash(adap, FLASH_FW_START,
+	ret = t4_read_flash(adap, FLASH_FW_START,
 			    sizeof(*card_fw) / sizeof(uint32_t),
 			    (uint32_t *)card_fw, 1);
 	if (ret == 0) {
@@ -3528,8 +3528,8 @@ int t4_prep_fw(struct adapter *adap, struct fw_info *fw_info,
 		   should_install_fs_fw(adap, card_fw_usable,
 					be32_to_cpu(fs_fw->fw_ver),
 					be32_to_cpu(card_fw->fw_ver))) {
-		ret = -t4_fw_upgrade(adap, adap->mbox, fw_data,
-				     fw_size, 0);
+		ret = t4_fw_upgrade(adap, adap->mbox, fw_data,
+				    fw_size, 0);
 		if (ret != 0) {
 			dev_err(adap->pdev_dev,
 				"failed to install firmware: %d\n", ret);
@@ -3560,7 +3560,7 @@ int t4_prep_fw(struct adapter *adap, struct fw_info *fw_info,
 			FW_HDR_FW_VER_MICRO_G(c), FW_HDR_FW_VER_BUILD_G(c),
 			FW_HDR_FW_VER_MAJOR_G(k), FW_HDR_FW_VER_MINOR_G(k),
 			FW_HDR_FW_VER_MICRO_G(k), FW_HDR_FW_VER_BUILD_G(k));
-		ret = EINVAL;
+		ret = -EINVAL;
 		goto bye;
 	}
 
@@ -3748,7 +3748,7 @@ int t4_phy_fw_ver(struct adapter *adap, int *phy_fw_ver)
 		 FW_PARAMS_PARAM_Z_V(FW_PARAMS_PARAM_DEV_PHYFW_VERSION));
 	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1,
 			      &param, &val);
-	if (ret < 0)
+	if (ret)
 		return ret;
 	*phy_fw_ver = val;
 	return 0;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
index eb222d40ddbf..a64eb6ac5c76 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
@@ -1896,6 +1896,9 @@
 
 #define MAC_PORT_CFG2_A 0x818
 
+#define MAC_PORT_PTP_SUM_LO_A 0x990
+#define MAC_PORT_PTP_SUM_HI_A 0x994
+
 #define MPS_CMN_CTL_A	0x9000
 
 #define COUNTPAUSEMCRX_S    5
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index acb2856936d2..6e2ab10ad2e6 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -2013,10 +2013,10 @@ static int enic_stop(struct net_device *netdev)
 		napi_disable(&enic->napi[i]);
 
 	netif_carrier_off(netdev);
-	netif_tx_disable(netdev);
 	if (vnic_dev_get_intr_mode(enic->vdev) == VNIC_DEV_INTR_MODE_MSIX)
 		for (i = 0; i < enic->wq_count; i++)
 			napi_disable(&enic->napi[enic_cq_wq(enic, i)]);
+	netif_tx_disable(netdev);
 
 	if (!enic_is_dynamic(enic) && !enic_is_sriov_vf(enic))
 		enic_dev_del_station_addr(enic);
diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index bd385c1927f2..d39f6ed0c235 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -2448,6 +2448,7 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev)
 	port->reset = devm_reset_control_get_exclusive(dev, NULL);
 	if (IS_ERR(port->reset)) {
 		dev_err(dev, "no reset\n");
+		clk_disable_unprepare(port->pclk);
 		return PTR_ERR(port->reset);
 	}
 	reset_control_reset(port->reset);
@@ -2503,8 +2504,10 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev)
 					IRQF_SHARED,
 					port_names[port->id],
 					port);
-	if (ret)
+	if (ret) {
+		clk_disable_unprepare(port->pclk);
 		return ret;
+	}
 
 	ret = register_netdev(netdev);
 	if (!ret) {
diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c
index 386bdc1378d1..39d52bbea150 100644
--- a/drivers/net/ethernet/davicom/dm9000.c
+++ b/drivers/net/ethernet/davicom/dm9000.c
@@ -1405,6 +1405,8 @@ static struct dm9000_plat_data *dm9000_parse_dt(struct device *dev)
 	mac_addr = of_get_mac_address(np);
 	if (!IS_ERR(mac_addr))
 		ether_addr_copy(pdata->dev_addr, mac_addr);
+	else if (PTR_ERR(mac_addr) == -EPROBE_DEFER)
+		return ERR_CAST(mac_addr);
 
 	return pdata;
 }
diff --git a/drivers/net/ethernet/dec/tulip/dmfe.c b/drivers/net/ethernet/dec/tulip/dmfe.c
index 0efdbd1a4a6f..32d470d4122a 100644
--- a/drivers/net/ethernet/dec/tulip/dmfe.c
+++ b/drivers/net/ethernet/dec/tulip/dmfe.c
@@ -2214,15 +2214,16 @@ static int __init dmfe_init_module(void)
 	if (cr6set)
 		dmfe_cr6_user_set = cr6set;
 
- 	switch(mode) {
-   	case DMFE_10MHF:
+	switch (mode) {
+	case DMFE_10MHF:
 	case DMFE_100MHF:
 	case DMFE_10MFD:
 	case DMFE_100MFD:
 	case DMFE_1M_HPNA:
 		dmfe_media_mode = mode;
 		break;
-	default:dmfe_media_mode = DMFE_AUTO;
+	default:
+		dmfe_media_mode = DMFE_AUTO;
 		break;
 	}
 
diff --git a/drivers/net/ethernet/dec/tulip/uli526x.c b/drivers/net/ethernet/dec/tulip/uli526x.c
index b1f30b194300..117ffe08800d 100644
--- a/drivers/net/ethernet/dec/tulip/uli526x.c
+++ b/drivers/net/ethernet/dec/tulip/uli526x.c
@@ -1809,8 +1809,8 @@ static int __init uli526x_init_module(void)
 	if (cr6set)
 		uli526x_cr6_user_set = cr6set;
 
- 	switch (mode) {
-   	case ULI526X_10MHF:
+	switch (mode) {
+	case ULI526X_10MHF:
 	case ULI526X_100MHF:
 	case ULI526X_10MFD:
 	case ULI526X_100MFD:
diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig
index 6a7e8993119f..941c7e667afc 100644
--- a/drivers/net/ethernet/freescale/Kconfig
+++ b/drivers/net/ethernet/freescale/Kconfig
@@ -77,6 +77,7 @@ config UCC_GETH
 	depends on QUICC_ENGINE
 	select FSL_PQ_MDIO
 	select PHYLIB
+	select FIXED_PHY
 	---help---
 	  This driver supports the Gigabit Ethernet mode of the QUICC Engine,
 	  which is available on some Freescale SOCs.
@@ -90,6 +91,7 @@ config GIANFAR
 	depends on HAS_DMA
 	select FSL_PQ_MDIO
 	select PHYLIB
+	select FIXED_PHY
 	select CRC32
 	---help---
 	  This driver supports the Gigabit TSEC on the MPC83xx, MPC85xx,
diff --git a/drivers/net/ethernet/freescale/dpaa/Kconfig b/drivers/net/ethernet/freescale/dpaa/Kconfig
index 3b325733a4f8..0a54c7e0e4ae 100644
--- a/drivers/net/ethernet/freescale/dpaa/Kconfig
+++ b/drivers/net/ethernet/freescale/dpaa/Kconfig
@@ -3,6 +3,7 @@ menuconfig FSL_DPAA_ETH
 	tristate "DPAA Ethernet"
 	depends on FSL_DPAA && FSL_FMAN
 	select PHYLIB
+	select FIXED_PHY
 	select FSL_FMAN_MAC
 	---help---
 	  Data Path Acceleration Architecture Ethernet driver,
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index f38c3fa7d705..1315cc42c88f 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -1600,13 +1600,15 @@ static int dpaa_eth_refill_bpools(struct dpaa_priv *priv)
  * Skb freeing is not handled here.
  *
  * This function may be called on error paths in the Tx function, so guard
- * against cases when not all fd relevant fields were filled in.
+ * against cases when not all fd relevant fields were filled in. To avoid
+ * reading the invalid transmission timestamp for the error paths set ts to
+ * false.
  *
  * Return the skb backpointer, since for S/G frames the buffer containing it
  * gets freed here.
  */
 static struct sk_buff *dpaa_cleanup_tx_fd(const struct dpaa_priv *priv,
-					  const struct qm_fd *fd)
+					  const struct qm_fd *fd, bool ts)
 {
 	const enum dma_data_direction dma_dir = DMA_TO_DEVICE;
 	struct device *dev = priv->net_dev->dev.parent;
@@ -1620,18 +1622,6 @@ static struct sk_buff *dpaa_cleanup_tx_fd(const struct dpaa_priv *priv,
 	skbh = (struct sk_buff **)phys_to_virt(addr);
 	skb = *skbh;
 
-	if (priv->tx_tstamp && skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) {
-		memset(&shhwtstamps, 0, sizeof(shhwtstamps));
-
-		if (!fman_port_get_tstamp(priv->mac_dev->port[TX], (void *)skbh,
-					  &ns)) {
-			shhwtstamps.hwtstamp = ns_to_ktime(ns);
-			skb_tstamp_tx(skb, &shhwtstamps);
-		} else {
-			dev_warn(dev, "fman_port_get_tstamp failed!\n");
-		}
-	}
-
 	if (unlikely(qm_fd_get_format(fd) == qm_fd_sg)) {
 		nr_frags = skb_shinfo(skb)->nr_frags;
 		dma_unmap_single(dev, addr,
@@ -1654,14 +1644,29 @@ static struct sk_buff *dpaa_cleanup_tx_fd(const struct dpaa_priv *priv,
 			dma_unmap_page(dev, qm_sg_addr(&sgt[i]),
 				       qm_sg_entry_get_len(&sgt[i]), dma_dir);
 		}
-
-		/* Free the page frag that we allocated on Tx */
-		skb_free_frag(phys_to_virt(addr));
 	} else {
 		dma_unmap_single(dev, addr,
 				 skb_tail_pointer(skb) - (u8 *)skbh, dma_dir);
 	}
 
+	/* DMA unmapping is required before accessing the HW provided info */
+	if (ts && priv->tx_tstamp &&
+	    skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) {
+		memset(&shhwtstamps, 0, sizeof(shhwtstamps));
+
+		if (!fman_port_get_tstamp(priv->mac_dev->port[TX], (void *)skbh,
+					  &ns)) {
+			shhwtstamps.hwtstamp = ns_to_ktime(ns);
+			skb_tstamp_tx(skb, &shhwtstamps);
+		} else {
+			dev_warn(dev, "fman_port_get_tstamp failed!\n");
+		}
+	}
+
+	if (qm_fd_get_format(fd) == qm_fd_sg)
+		/* Free the page frag that we allocated on Tx */
+		skb_free_frag(phys_to_virt(addr));
+
 	return skb;
 }
 
@@ -2114,7 +2119,7 @@ dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev)
 	if (likely(dpaa_xmit(priv, percpu_stats, queue_mapping, &fd) == 0))
 		return NETDEV_TX_OK;
 
-	dpaa_cleanup_tx_fd(priv, &fd);
+	dpaa_cleanup_tx_fd(priv, &fd, false);
 skb_to_fd_failed:
 enomem:
 	percpu_stats->tx_errors++;
@@ -2160,7 +2165,7 @@ static void dpaa_tx_error(struct net_device *net_dev,
 
 	percpu_priv->stats.tx_errors++;
 
-	skb = dpaa_cleanup_tx_fd(priv, fd);
+	skb = dpaa_cleanup_tx_fd(priv, fd, false);
 	dev_kfree_skb(skb);
 }
 
@@ -2200,7 +2205,7 @@ static void dpaa_tx_conf(struct net_device *net_dev,
 
 	percpu_priv->tx_confirm++;
 
-	skb = dpaa_cleanup_tx_fd(priv, fd);
+	skb = dpaa_cleanup_tx_fd(priv, fd, true);
 
 	consume_skb(skb);
 }
@@ -2430,7 +2435,7 @@ static void egress_ern(struct qman_portal *portal,
 	percpu_priv->stats.tx_fifo_errors++;
 	count_ern(percpu_priv, msg);
 
-	skb = dpaa_cleanup_tx_fd(priv, fd);
+	skb = dpaa_cleanup_tx_fd(priv, fd, false);
 	dev_kfree_skb_any(skb);
 }
 
@@ -2478,6 +2483,9 @@ static void dpaa_adjust_link(struct net_device *net_dev)
 	mac_dev->adjust_link(mac_dev);
 }
 
+/* The Aquantia PHYs are capable of performing rate adaptation */
+#define PHY_VEND_AQUANTIA	0x03a1b400
+
 static int dpaa_phy_init(struct net_device *net_dev)
 {
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
@@ -2496,9 +2504,14 @@ static int dpaa_phy_init(struct net_device *net_dev)
 		return -ENODEV;
 	}
 
-	/* Remove any features not supported by the controller */
-	ethtool_convert_legacy_u32_to_link_mode(mask, mac_dev->if_support);
-	linkmode_and(phy_dev->supported, phy_dev->supported, mask);
+	/* Unless the PHY is capable of rate adaptation */
+	if (mac_dev->phy_if != PHY_INTERFACE_MODE_XGMII ||
+	    ((phy_dev->drv->phy_id & GENMASK(31, 10)) != PHY_VEND_AQUANTIA)) {
+		/* remove any features not supported by the controller */
+		ethtool_convert_legacy_u32_to_link_mode(mask,
+							mac_dev->if_support);
+		linkmode_and(phy_dev->supported, phy_dev->supported, mask);
+	}
 
 	phy_support_asym_pause(phy_dev);
 
@@ -2757,9 +2770,7 @@ static inline u16 dpaa_get_headroom(struct dpaa_buffer_layout *bl)
 	headroom = (u16)(bl->priv_data_size + DPAA_PARSE_RESULTS_SIZE +
 		DPAA_TIME_STAMP_SIZE + DPAA_HASH_RESULTS_SIZE);
 
-	return DPAA_FD_DATA_ALIGNMENT ? ALIGN(headroom,
-					      DPAA_FD_DATA_ALIGNMENT) :
-					headroom;
+	return ALIGN(headroom, DPAA_FD_DATA_ALIGNMENT);
 }
 
 static int dpaa_eth_probe(struct platform_device *pdev)
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 60ac993ada36..c977c58dd3df 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -86,7 +86,7 @@ static void free_rx_fd(struct dpaa2_eth_priv *priv,
 	for (i = 1; i < DPAA2_ETH_MAX_SG_ENTRIES; i++) {
 		addr = dpaa2_sg_get_addr(&sgt[i]);
 		sg_vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr);
-		dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+		dma_unmap_page(dev, addr, priv->rx_buf_size,
 			       DMA_BIDIRECTIONAL);
 
 		free_pages((unsigned long)sg_vaddr, 0);
@@ -144,7 +144,7 @@ static struct sk_buff *build_frag_skb(struct dpaa2_eth_priv *priv,
 		/* Get the address and length from the S/G entry */
 		sg_addr = dpaa2_sg_get_addr(sge);
 		sg_vaddr = dpaa2_iova_to_virt(priv->iommu_domain, sg_addr);
-		dma_unmap_page(dev, sg_addr, DPAA2_ETH_RX_BUF_SIZE,
+		dma_unmap_page(dev, sg_addr, priv->rx_buf_size,
 			       DMA_BIDIRECTIONAL);
 
 		sg_length = dpaa2_sg_get_len(sge);
@@ -185,7 +185,7 @@ static struct sk_buff *build_frag_skb(struct dpaa2_eth_priv *priv,
 				(page_address(page) - page_address(head_page));
 
 			skb_add_rx_frag(skb, i - 1, head_page, page_offset,
-					sg_length, DPAA2_ETH_RX_BUF_SIZE);
+					sg_length, priv->rx_buf_size);
 		}
 
 		if (dpaa2_sg_is_final(sge))
@@ -211,7 +211,7 @@ static void free_bufs(struct dpaa2_eth_priv *priv, u64 *buf_array, int count)
 
 	for (i = 0; i < count; i++) {
 		vaddr = dpaa2_iova_to_virt(priv->iommu_domain, buf_array[i]);
-		dma_unmap_page(dev, buf_array[i], DPAA2_ETH_RX_BUF_SIZE,
+		dma_unmap_page(dev, buf_array[i], priv->rx_buf_size,
 			       DMA_BIDIRECTIONAL);
 		free_pages((unsigned long)vaddr, 0);
 	}
@@ -331,7 +331,7 @@ static u32 run_xdp(struct dpaa2_eth_priv *priv,
 		break;
 	case XDP_REDIRECT:
 		dma_unmap_page(priv->net_dev->dev.parent, addr,
-			       DPAA2_ETH_RX_BUF_SIZE, DMA_BIDIRECTIONAL);
+			       priv->rx_buf_size, DMA_BIDIRECTIONAL);
 		ch->buf_count--;
 		xdp.data_hard_start = vaddr;
 		err = xdp_do_redirect(priv->net_dev, &xdp, xdp_prog);
@@ -370,7 +370,7 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 	trace_dpaa2_rx_fd(priv->net_dev, fd);
 
 	vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr);
-	dma_sync_single_for_cpu(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+	dma_sync_single_for_cpu(dev, addr, priv->rx_buf_size,
 				DMA_BIDIRECTIONAL);
 
 	fas = dpaa2_get_fas(vaddr, false);
@@ -389,13 +389,13 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 			return;
 		}
 
-		dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+		dma_unmap_page(dev, addr, priv->rx_buf_size,
 			       DMA_BIDIRECTIONAL);
 		skb = build_linear_skb(ch, fd, vaddr);
 	} else if (fd_format == dpaa2_fd_sg) {
 		WARN_ON(priv->xdp_prog);
 
-		dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+		dma_unmap_page(dev, addr, priv->rx_buf_size,
 			       DMA_BIDIRECTIONAL);
 		skb = build_frag_skb(priv, ch, buf_data);
 		free_pages((unsigned long)vaddr, 0);
@@ -950,7 +950,7 @@ static int add_bufs(struct dpaa2_eth_priv *priv,
 		if (!page)
 			goto err_alloc;
 
-		addr = dma_map_page(dev, page, 0, DPAA2_ETH_RX_BUF_SIZE,
+		addr = dma_map_page(dev, page, 0, priv->rx_buf_size,
 				    DMA_BIDIRECTIONAL);
 		if (unlikely(dma_mapping_error(dev, addr)))
 			goto err_map;
@@ -960,7 +960,7 @@ static int add_bufs(struct dpaa2_eth_priv *priv,
 		/* tracing point */
 		trace_dpaa2_eth_buf_seed(priv->net_dev,
 					 page, DPAA2_ETH_RX_BUF_RAW_SIZE,
-					 addr, DPAA2_ETH_RX_BUF_SIZE,
+					 addr, priv->rx_buf_size,
 					 bpid);
 	}
 
@@ -1610,7 +1610,7 @@ static bool xdp_mtu_valid(struct dpaa2_eth_priv *priv, int mtu)
 	int mfl, linear_mfl;
 
 	mfl = DPAA2_ETH_L2_MAX_FRM(mtu);
-	linear_mfl = DPAA2_ETH_RX_BUF_SIZE - DPAA2_ETH_RX_HWA_SIZE -
+	linear_mfl = priv->rx_buf_size - DPAA2_ETH_RX_HWA_SIZE -
 		     dpaa2_eth_rx_head_room(priv) - XDP_PACKET_HEADROOM;
 
 	if (mfl > linear_mfl) {
@@ -1947,7 +1947,7 @@ close:
 free:
 	fsl_mc_object_free(dpcon);
 
-	return NULL;
+	return ERR_PTR(err);
 }
 
 static void free_dpcon(struct dpaa2_eth_priv *priv,
@@ -1971,8 +1971,8 @@ alloc_channel(struct dpaa2_eth_priv *priv)
 		return NULL;
 
 	channel->dpcon = setup_dpcon(priv);
-	if (IS_ERR_OR_NULL(channel->dpcon)) {
-		err = PTR_ERR_OR_ZERO(channel->dpcon);
+	if (IS_ERR(channel->dpcon)) {
+		err = PTR_ERR(channel->dpcon);
 		goto err_setup;
 	}
 
@@ -2299,6 +2299,11 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv)
 	else
 		rx_buf_align = DPAA2_ETH_RX_BUF_ALIGN;
 
+	/* We need to ensure that the buffer size seen by WRIOP is a multiple
+	 * of 64 or 256 bytes depending on the WRIOP version.
+	 */
+	priv->rx_buf_size = ALIGN_DOWN(DPAA2_ETH_RX_BUF_SIZE, rx_buf_align);
+
 	/* tx buffer */
 	buf_layout.private_data_size = DPAA2_ETH_SWA_SIZE;
 	buf_layout.pass_timestamp = true;
@@ -2900,7 +2905,7 @@ static int bind_dpni(struct dpaa2_eth_priv *priv)
 	pools_params.num_dpbp = 1;
 	pools_params.pools[0].dpbp_id = priv->dpbp_dev->obj_desc.id;
 	pools_params.pools[0].backup_pool = 0;
-	pools_params.pools[0].buffer_size = DPAA2_ETH_RX_BUF_SIZE;
+	pools_params.pools[0].buffer_size = priv->rx_buf_size;
 	err = dpni_set_pools(priv->mc_io, 0, priv->mc_token, &pools_params);
 	if (err) {
 		dev_err(dev, "dpni_set_pools() failed\n");
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index e180d5a68c98..2d470bbcf38f 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -369,6 +369,7 @@ struct dpaa2_eth_priv {
 	u16 tx_data_offset;
 
 	struct fsl_mc_device *dpbp_dev;
+	u16 rx_buf_size;
 	u16 bpid;
 	struct iommu_domain *iommu_domain;
 
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
index 7b182f4b263c..dd4c580fc9ae 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
@@ -583,7 +583,7 @@ static int num_rules(struct dpaa2_eth_priv *priv)
 
 static int update_cls_rule(struct net_device *net_dev,
 			   struct ethtool_rx_flow_spec *new_fs,
-			   int location)
+			   unsigned int location)
 {
 	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
 	struct dpaa2_eth_cls_rule *rule;
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 491475d87736..b758183be320 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -249,7 +249,7 @@ static irqreturn_t enetc_msix(int irq, void *data)
 	/* disable interrupts */
 	enetc_wr_reg(v->rbier, 0);
 
-	for_each_set_bit(i, &v->tx_rings_map, v->count_tx_rings)
+	for_each_set_bit(i, &v->tx_rings_map, ENETC_MAX_NUM_TXQS)
 		enetc_wr_reg(v->tbier_base + ENETC_BDR_OFF(i), 0);
 
 	napi_schedule_irqoff(&v->napi);
@@ -285,7 +285,7 @@ static int enetc_poll(struct napi_struct *napi, int budget)
 	/* enable interrupts */
 	enetc_wr_reg(v->rbier, ENETC_RBIER_RXTIE);
 
-	for_each_set_bit(i, &v->tx_rings_map, v->count_tx_rings)
+	for_each_set_bit(i, &v->tx_rings_map, ENETC_MAX_NUM_TXQS)
 		enetc_wr_reg(v->tbier_base + ENETC_BDR_OFF(i),
 			     ENETC_TBIER_TXTIE);
 
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index 78287c517095..32c1e9533b14 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -880,6 +880,7 @@ static int enetc_pf_probe(struct pci_dev *pdev,
 	return 0;
 
 err_reg_netdev:
+	enetc_mdio_remove(pf);
 	enetc_of_put_phy(priv);
 	enetc_free_msix(priv);
 err_alloc_msix:
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index f79e57f735b3..d89568f810bc 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -488,6 +488,12 @@ struct fec_enet_priv_rx_q {
 	struct  sk_buff *rx_skbuff[RX_RING_SIZE];
 };
 
+struct fec_stop_mode_gpr {
+	struct regmap *gpr;
+	u8 reg;
+	u8 bit;
+};
+
 /* The FEC buffer descriptors track the ring buffers.  The rx_bd_base and
  * tx_bd_base always point to the base of the buffer descriptors.  The
  * cur_rx and cur_tx point to the currently available buffer.
@@ -562,6 +568,7 @@ struct fec_enet_private {
 	int hwts_tx_en;
 	struct delayed_work time_keep;
 	struct regulator *reg_phy;
+	struct fec_stop_mode_gpr stop_gpr;
 
 	unsigned int tx_align;
 	unsigned int rx_align;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 95731bcd066d..6c3caec5f4e3 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -62,6 +62,8 @@
 #include <linux/if_vlan.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/prefetch.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
 #include <soc/imx/cpuidle.h>
 
 #include <asm/cacheflush.h>
@@ -84,6 +86,56 @@ static void fec_enet_itr_coal_init(struct net_device *ndev);
 #define FEC_ENET_OPD_V	0xFFF0
 #define FEC_MDIO_PM_TIMEOUT  100 /* ms */
 
+struct fec_devinfo {
+	u32 quirks;
+	u8 stop_gpr_reg;
+	u8 stop_gpr_bit;
+};
+
+static const struct fec_devinfo fec_imx25_info = {
+	.quirks = FEC_QUIRK_USE_GASKET | FEC_QUIRK_MIB_CLEAR |
+		  FEC_QUIRK_HAS_FRREG,
+};
+
+static const struct fec_devinfo fec_imx27_info = {
+	.quirks = FEC_QUIRK_MIB_CLEAR | FEC_QUIRK_HAS_FRREG,
+};
+
+static const struct fec_devinfo fec_imx28_info = {
+	.quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_SWAP_FRAME |
+		  FEC_QUIRK_SINGLE_MDIO | FEC_QUIRK_HAS_RACC |
+		  FEC_QUIRK_HAS_FRREG,
+};
+
+static const struct fec_devinfo fec_imx6q_info = {
+	.quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
+		  FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
+		  FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR006358 |
+		  FEC_QUIRK_HAS_RACC,
+	.stop_gpr_reg = 0x34,
+	.stop_gpr_bit = 27,
+};
+
+static const struct fec_devinfo fec_mvf600_info = {
+	.quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_RACC,
+};
+
+static const struct fec_devinfo fec_imx6x_info = {
+	.quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
+		  FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
+		  FEC_QUIRK_HAS_VLAN | FEC_QUIRK_HAS_AVB |
+		  FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE |
+		  FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE,
+};
+
+static const struct fec_devinfo fec_imx6ul_info = {
+	.quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
+		  FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
+		  FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR007885 |
+		  FEC_QUIRK_BUG_CAPTURE | FEC_QUIRK_HAS_RACC |
+		  FEC_QUIRK_HAS_COALESCE,
+};
+
 static struct platform_device_id fec_devtype[] = {
 	{
 		/* keep it for coldfire */
@@ -91,39 +143,25 @@ static struct platform_device_id fec_devtype[] = {
 		.driver_data = 0,
 	}, {
 		.name = "imx25-fec",
-		.driver_data = FEC_QUIRK_USE_GASKET | FEC_QUIRK_MIB_CLEAR |
-			       FEC_QUIRK_HAS_FRREG,
+		.driver_data = (kernel_ulong_t)&fec_imx25_info,
 	}, {
 		.name = "imx27-fec",
-		.driver_data = FEC_QUIRK_MIB_CLEAR | FEC_QUIRK_HAS_FRREG,
+		.driver_data = (kernel_ulong_t)&fec_imx27_info,
 	}, {
 		.name = "imx28-fec",
-		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_SWAP_FRAME |
-				FEC_QUIRK_SINGLE_MDIO | FEC_QUIRK_HAS_RACC |
-				FEC_QUIRK_HAS_FRREG,
+		.driver_data = (kernel_ulong_t)&fec_imx28_info,
 	}, {
 		.name = "imx6q-fec",
-		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
-				FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
-				FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR006358 |
-				FEC_QUIRK_HAS_RACC,
+		.driver_data = (kernel_ulong_t)&fec_imx6q_info,
 	}, {
 		.name = "mvf600-fec",
-		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_RACC,
+		.driver_data = (kernel_ulong_t)&fec_mvf600_info,
 	}, {
 		.name = "imx6sx-fec",
-		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
-				FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
-				FEC_QUIRK_HAS_VLAN | FEC_QUIRK_HAS_AVB |
-				FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE |
-				FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE,
+		.driver_data = (kernel_ulong_t)&fec_imx6x_info,
 	}, {
 		.name = "imx6ul-fec",
-		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
-				FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
-				FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR007885 |
-				FEC_QUIRK_BUG_CAPTURE | FEC_QUIRK_HAS_RACC |
-				FEC_QUIRK_HAS_COALESCE,
+		.driver_data = (kernel_ulong_t)&fec_imx6ul_info,
 	}, {
 		/* sentinel */
 	}
@@ -1089,11 +1127,28 @@ fec_restart(struct net_device *ndev)
 
 }
 
+static void fec_enet_stop_mode(struct fec_enet_private *fep, bool enabled)
+{
+	struct fec_platform_data *pdata = fep->pdev->dev.platform_data;
+	struct fec_stop_mode_gpr *stop_gpr = &fep->stop_gpr;
+
+	if (stop_gpr->gpr) {
+		if (enabled)
+			regmap_update_bits(stop_gpr->gpr, stop_gpr->reg,
+					   BIT(stop_gpr->bit),
+					   BIT(stop_gpr->bit));
+		else
+			regmap_update_bits(stop_gpr->gpr, stop_gpr->reg,
+					   BIT(stop_gpr->bit), 0);
+	} else if (pdata && pdata->sleep_mode_enable) {
+		pdata->sleep_mode_enable(enabled);
+	}
+}
+
 static void
 fec_stop(struct net_device *ndev)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
-	struct fec_platform_data *pdata = fep->pdev->dev.platform_data;
 	u32 rmii_mode = readl(fep->hwp + FEC_R_CNTRL) & (1 << 8);
 	u32 val;
 
@@ -1122,9 +1177,7 @@ fec_stop(struct net_device *ndev)
 		val = readl(fep->hwp + FEC_ECNTRL);
 		val |= (FEC_ECR_MAGICEN | FEC_ECR_SLEEP);
 		writel(val, fep->hwp + FEC_ECNTRL);
-
-		if (pdata && pdata->sleep_mode_enable)
-			pdata->sleep_mode_enable(true);
+		fec_enet_stop_mode(fep, true);
 	}
 	writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
 
@@ -2141,8 +2194,14 @@ static void fec_enet_get_regs(struct net_device *ndev,
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	u32 __iomem *theregs = (u32 __iomem *)fep->hwp;
+	struct device *dev = &fep->pdev->dev;
 	u32 *buf = (u32 *)regbuf;
 	u32 i, off;
+	int ret;
+
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0)
+		return;
 
 	regs->version = fec_enet_register_version;
 
@@ -2158,6 +2217,9 @@ static void fec_enet_get_regs(struct net_device *ndev,
 		off >>= 2;
 		buf[off] = readl(&theregs[off]);
 	}
+
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
 }
 
 static int fec_enet_get_ts_info(struct net_device *ndev,
@@ -2461,15 +2523,15 @@ fec_enet_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *ec)
 		return -EINVAL;
 	}
 
-	cycle = fec_enet_us_to_itr_clock(ndev, fep->rx_time_itr);
+	cycle = fec_enet_us_to_itr_clock(ndev, ec->rx_coalesce_usecs);
 	if (cycle > 0xFFFF) {
 		pr_err("Rx coalesced usec exceed hardware limitation\n");
 		return -EINVAL;
 	}
 
-	cycle = fec_enet_us_to_itr_clock(ndev, fep->tx_time_itr);
+	cycle = fec_enet_us_to_itr_clock(ndev, ec->tx_coalesce_usecs);
 	if (cycle > 0xFFFF) {
-		pr_err("Rx coalesced usec exceed hardware limitation\n");
+		pr_err("Tx coalesced usec exceed hardware limitation\n");
 		return -EINVAL;
 	}
 
@@ -3332,6 +3394,37 @@ static int fec_enet_get_irq_cnt(struct platform_device *pdev)
 	return irq_cnt;
 }
 
+static int fec_enet_init_stop_mode(struct fec_enet_private *fep,
+				   struct fec_devinfo *dev_info,
+				   struct device_node *np)
+{
+	struct device_node *gpr_np;
+	int ret = 0;
+
+	if (!dev_info)
+		return 0;
+
+	gpr_np = of_parse_phandle(np, "gpr", 0);
+	if (!gpr_np)
+		return 0;
+
+	fep->stop_gpr.gpr = syscon_node_to_regmap(gpr_np);
+	if (IS_ERR(fep->stop_gpr.gpr)) {
+		dev_err(&fep->pdev->dev, "could not find gpr regmap\n");
+		ret = PTR_ERR(fep->stop_gpr.gpr);
+		fep->stop_gpr.gpr = NULL;
+		goto out;
+	}
+
+	fep->stop_gpr.reg = dev_info->stop_gpr_reg;
+	fep->stop_gpr.bit = dev_info->stop_gpr_bit;
+
+out:
+	of_node_put(gpr_np);
+
+	return ret;
+}
+
 static int
 fec_probe(struct platform_device *pdev)
 {
@@ -3347,6 +3440,7 @@ fec_probe(struct platform_device *pdev)
 	int num_rx_qs;
 	char irq_name[8];
 	int irq_cnt;
+	struct fec_devinfo *dev_info;
 
 	fec_enet_get_queue_num(pdev, &num_tx_qs, &num_rx_qs);
 
@@ -3364,7 +3458,9 @@ fec_probe(struct platform_device *pdev)
 	of_id = of_match_device(fec_dt_ids, &pdev->dev);
 	if (of_id)
 		pdev->id_entry = of_id->data;
-	fep->quirks = pdev->id_entry->driver_data;
+	dev_info = (struct fec_devinfo *)pdev->id_entry->driver_data;
+	if (dev_info)
+		fep->quirks = dev_info->quirks;
 
 	fep->netdev = ndev;
 	fep->num_rx_queues = num_rx_qs;
@@ -3399,6 +3495,10 @@ fec_probe(struct platform_device *pdev)
 	if (of_get_property(np, "fsl,magic-packet", NULL))
 		fep->wol_flag |= FEC_WOL_HAS_MAGIC_PACKET;
 
+	ret = fec_enet_init_stop_mode(fep, dev_info, np);
+	if (ret)
+		goto failed_stop_mode;
+
 	phy_node = of_parse_phandle(np, "phy-handle", 0);
 	if (!phy_node && of_phy_is_fixed_link(np)) {
 		ret = of_phy_register_fixed_link(np);
@@ -3568,6 +3668,7 @@ failed_clk:
 	if (of_phy_is_fixed_link(np))
 		of_phy_deregister_fixed_link(np);
 	of_node_put(phy_node);
+failed_stop_mode:
 failed_phy:
 	dev_id--;
 failed_ioremap:
@@ -3645,7 +3746,6 @@ static int __maybe_unused fec_resume(struct device *dev)
 {
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct fec_enet_private *fep = netdev_priv(ndev);
-	struct fec_platform_data *pdata = fep->pdev->dev.platform_data;
 	int ret;
 	int val;
 
@@ -3663,8 +3763,8 @@ static int __maybe_unused fec_resume(struct device *dev)
 			goto failed_clk;
 		}
 		if (fep->wol_flag & FEC_WOL_FLAG_ENABLE) {
-			if (pdata && pdata->sleep_mode_enable)
-				pdata->sleep_mode_enable(false);
+			fec_enet_stop_mode(fep, false);
+
 			val = readl(fep->hwp + FEC_ECNTRL);
 			val &= ~(FEC_ECR_MAGICEN | FEC_ECR_SLEEP);
 			writel(val, fep->hwp + FEC_ECNTRL);
diff --git a/drivers/net/ethernet/freescale/fman/Kconfig b/drivers/net/ethernet/freescale/fman/Kconfig
index 0139cb9042ec..34150182cc35 100644
--- a/drivers/net/ethernet/freescale/fman/Kconfig
+++ b/drivers/net/ethernet/freescale/fman/Kconfig
@@ -8,3 +8,31 @@ config FSL_FMAN
 	help
 		Freescale Data-Path Acceleration Architecture Frame Manager
 		(FMan) support
+
+config DPAA_ERRATUM_A050385
+	bool
+	depends on ARM64 && FSL_DPAA
+	default y
+	help
+		DPAA FMan erratum A050385 software workaround implementation:
+		align buffers, data start, SG fragment length to avoid FMan DMA
+		splits.
+		FMAN DMA read or writes under heavy traffic load may cause FMAN
+		internal resource leak thus stopping further packet processing.
+		The FMAN internal queue can overflow when FMAN splits single
+		read or write transactions into multiple smaller transactions
+		such that more than 17 AXI transactions are in flight from FMAN
+		to interconnect. When the FMAN internal queue overflows, it can
+		stall further packet processing. The issue can occur with any
+		one of the following three conditions:
+		1. FMAN AXI transaction crosses 4K address boundary (Errata
+		A010022)
+		2. FMAN DMA address for an AXI transaction is not 16 byte
+		aligned, i.e. the last 4 bits of an address are non-zero
+		3. Scatter Gather (SG) frames have more than one SG buffer in
+		the SG list and any one of the buffers, except the last
+		buffer in the SG list has data size that is not a multiple
+		of 16 bytes, i.e., other than 16, 32, 48, 64, etc.
+		With any one of the above three conditions present, there is
+		likelihood of stalled FMAN packet processing, especially under
+		stress with multiple ports injecting line-rate traffic.
diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c
index e80fedb27cee..eba7e54ecf85 100644
--- a/drivers/net/ethernet/freescale/fman/fman.c
+++ b/drivers/net/ethernet/freescale/fman/fman.c
@@ -1,5 +1,6 @@
 /*
  * Copyright 2008-2015 Freescale Semiconductor Inc.
+ * Copyright 2020 NXP
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are met:
@@ -566,6 +567,10 @@ struct fman_cfg {
 	u32 qmi_def_tnums_thresh;
 };
 
+#ifdef CONFIG_DPAA_ERRATUM_A050385
+static bool fman_has_err_a050385;
+#endif
+
 static irqreturn_t fman_exceptions(struct fman *fman,
 				   enum fman_exceptions exception)
 {
@@ -1391,8 +1396,7 @@ static void enable_time_stamp(struct fman *fman)
 {
 	struct fman_fpm_regs __iomem *fpm_rg = fman->fpm_regs;
 	u16 fm_clk_freq = fman->state->fm_clk_freq;
-	u32 tmp, intgr, ts_freq;
-	u64 frac;
+	u32 tmp, intgr, ts_freq, frac;
 
 	ts_freq = (u32)(1 << fman->state->count1_micro_bit);
 	/* configure timestamp so that bit 8 will count 1 microsecond
@@ -2517,6 +2521,14 @@ struct fman *fman_bind(struct device *fm_dev)
 }
 EXPORT_SYMBOL(fman_bind);
 
+#ifdef CONFIG_DPAA_ERRATUM_A050385
+bool fman_has_errata_a050385(void)
+{
+	return fman_has_err_a050385;
+}
+EXPORT_SYMBOL(fman_has_errata_a050385);
+#endif
+
 static irqreturn_t fman_err_irq(int irq, void *handle)
 {
 	struct fman *fman = (struct fman *)handle;
@@ -2844,6 +2856,11 @@ static struct fman *read_dts_node(struct platform_device *of_dev)
 		goto fman_free;
 	}
 
+#ifdef CONFIG_DPAA_ERRATUM_A050385
+	fman_has_err_a050385 =
+		of_property_read_bool(fm_node, "fsl,erratum-a050385");
+#endif
+
 	return fman;
 
 fman_node_put:
diff --git a/drivers/net/ethernet/freescale/fman/fman.h b/drivers/net/ethernet/freescale/fman/fman.h
index 935c317fa696..f2ede1360f03 100644
--- a/drivers/net/ethernet/freescale/fman/fman.h
+++ b/drivers/net/ethernet/freescale/fman/fman.h
@@ -1,5 +1,6 @@
 /*
  * Copyright 2008-2015 Freescale Semiconductor Inc.
+ * Copyright 2020 NXP
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are met:
@@ -398,6 +399,10 @@ u16 fman_get_max_frm(void);
 
 int fman_get_rx_extra_headroom(void);
 
+#ifdef CONFIG_DPAA_ERRATUM_A050385
+bool fman_has_errata_a050385(void);
+#endif
+
 struct fman *fman_bind(struct device *dev);
 
 #endif /* __FM_H */
diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c
index 1ca543ac8f2c..d2de9ea80c43 100644
--- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c
+++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c
@@ -1205,7 +1205,7 @@ int dtsec_del_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr)
 		list_for_each(pos,
 			      &dtsec->multicast_addr_hash->lsts[bucket]) {
 			hash_entry = ETH_HASH_ENTRY_OBJ(pos);
-			if (hash_entry->addr == addr) {
+			if (hash_entry && hash_entry->addr == addr) {
 				list_del_init(&hash_entry->node);
 				kfree(hash_entry);
 				break;
@@ -1218,7 +1218,7 @@ int dtsec_del_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr)
 		list_for_each(pos,
 			      &dtsec->unicast_addr_hash->lsts[bucket]) {
 			hash_entry = ETH_HASH_ENTRY_OBJ(pos);
-			if (hash_entry->addr == addr) {
+			if (hash_entry && hash_entry->addr == addr) {
 				list_del_init(&hash_entry->node);
 				kfree(hash_entry);
 				break;
diff --git a/drivers/net/ethernet/freescale/fman/fman_mac.h b/drivers/net/ethernet/freescale/fman/fman_mac.h
index dd6d0526f6c1..19f327efdaff 100644
--- a/drivers/net/ethernet/freescale/fman/fman_mac.h
+++ b/drivers/net/ethernet/freescale/fman/fman_mac.h
@@ -252,7 +252,7 @@ static inline struct eth_hash_t *alloc_hash_table(u16 size)
 	struct eth_hash_t *hash;
 
 	/* Allocate address hash table */
-	hash = kmalloc_array(size, sizeof(struct eth_hash_t *), GFP_KERNEL);
+	hash = kmalloc(sizeof(*hash), GFP_KERNEL);
 	if (!hash)
 		return NULL;
 
diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c
index 41c6fa200e74..9088b4f4b4b8 100644
--- a/drivers/net/ethernet/freescale/fman/fman_memac.c
+++ b/drivers/net/ethernet/freescale/fman/fman_memac.c
@@ -110,7 +110,7 @@ do {									\
 /* Interface Mode Register (IF_MODE) */
 
 #define IF_MODE_MASK		0x00000003 /* 30-31 Mask on i/f mode bits */
-#define IF_MODE_XGMII		0x00000000 /* 30-31 XGMII (10G) interface */
+#define IF_MODE_10G		0x00000000 /* 30-31 10G interface */
 #define IF_MODE_GMII		0x00000002 /* 30-31 GMII (1G) interface */
 #define IF_MODE_RGMII		0x00000004
 #define IF_MODE_RGMII_AUTO	0x00008000
@@ -440,7 +440,7 @@ static int init(struct memac_regs __iomem *regs, struct memac_cfg *cfg,
 	tmp = 0;
 	switch (phy_if) {
 	case PHY_INTERFACE_MODE_XGMII:
-		tmp |= IF_MODE_XGMII;
+		tmp |= IF_MODE_10G;
 		break;
 	default:
 		tmp |= IF_MODE_GMII;
@@ -856,7 +856,6 @@ int memac_set_tx_pause_frames(struct fman_mac *memac, u8 priority,
 
 	tmp = ioread32be(&regs->command_config);
 	tmp &= ~CMD_CFG_PFC_MODE;
-	priority = 0;
 
 	iowrite32be(tmp, &regs->command_config);
 
@@ -986,7 +985,7 @@ int memac_del_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr)
 
 	list_for_each(pos, &memac->multicast_addr_hash->lsts[hash]) {
 		hash_entry = ETH_HASH_ENTRY_OBJ(pos);
-		if (hash_entry->addr == addr) {
+		if (hash_entry && hash_entry->addr == addr) {
 			list_del_init(&hash_entry->node);
 			kfree(hash_entry);
 			break;
diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c
index ee82ee1384eb..47f6fee1f396 100644
--- a/drivers/net/ethernet/freescale/fman/fman_port.c
+++ b/drivers/net/ethernet/freescale/fman/fman_port.c
@@ -1756,6 +1756,7 @@ static int fman_port_probe(struct platform_device *of_dev)
 	struct fman_port *port;
 	struct fman *fman;
 	struct device_node *fm_node, *port_node;
+	struct platform_device *fm_pdev;
 	struct resource res;
 	struct resource *dev_res;
 	u32 val;
@@ -1780,8 +1781,14 @@ static int fman_port_probe(struct platform_device *of_dev)
 		goto return_err;
 	}
 
-	fman = dev_get_drvdata(&of_find_device_by_node(fm_node)->dev);
+	fm_pdev = of_find_device_by_node(fm_node);
 	of_node_put(fm_node);
+	if (!fm_pdev) {
+		err = -EINVAL;
+		goto return_err;
+	}
+
+	fman = dev_get_drvdata(&fm_pdev->dev);
 	if (!fman) {
 		err = -EINVAL;
 		goto return_err;
diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.c b/drivers/net/ethernet/freescale/fman/fman_tgec.c
index f75b9c11b2d2..ac5a281e0ec3 100644
--- a/drivers/net/ethernet/freescale/fman/fman_tgec.c
+++ b/drivers/net/ethernet/freescale/fman/fman_tgec.c
@@ -630,7 +630,7 @@ int tgec_del_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr)
 
 	list_for_each(pos, &tgec->multicast_addr_hash->lsts[hash]) {
 		hash_entry = ETH_HASH_ENTRY_OBJ(pos);
-		if (hash_entry->addr == addr) {
+		if (hash_entry && hash_entry->addr == addr) {
 			list_del_init(&hash_entry->node);
 			kfree(hash_entry);
 			break;
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 7ea19e173339..17963f95ae58 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -2686,13 +2686,17 @@ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue)
 	skb_dirtytx = tx_queue->skb_dirtytx;
 
 	while ((skb = tx_queue->tx_skbuff[skb_dirtytx])) {
+		bool do_tstamp;
+
+		do_tstamp = (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
+			    priv->hwts_tx_en;
 
 		frags = skb_shinfo(skb)->nr_frags;
 
 		/* When time stamping, one additional TxBD must be freed.
 		 * Also, we need to dma_unmap_single() the TxPAL.
 		 */
-		if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS))
+		if (unlikely(do_tstamp))
 			nr_txbds = frags + 2;
 		else
 			nr_txbds = frags + 1;
@@ -2706,7 +2710,7 @@ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue)
 		    (lstatus & BD_LENGTH_MASK))
 			break;
 
-		if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) {
+		if (unlikely(do_tstamp)) {
 			next = next_txbd(bdp, base, tx_ring_size);
 			buflen = be16_to_cpu(next->length) +
 				 GMAC_FCB_LEN + GMAC_TXPAL_LEN;
@@ -2716,7 +2720,7 @@ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue)
 		dma_unmap_single(priv->dev, be32_to_cpu(bdp->bufPtr),
 				 buflen, DMA_TO_DEVICE);
 
-		if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) {
+		if (unlikely(do_tstamp)) {
 			struct skb_shared_hwtstamps shhwtstamps;
 			u64 *ns = (u64 *)(((uintptr_t)skb->data + 0x10) &
 					  ~0x7UL);
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index f839fa94ebdd..d3b8ce734c1b 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -42,6 +42,7 @@
 #include <soc/fsl/qe/ucc.h>
 #include <soc/fsl/qe/ucc_fast.h>
 #include <asm/machdep.h>
+#include <net/sch_generic.h>
 
 #include "ucc_geth.h"
 
@@ -1548,11 +1549,8 @@ static int ugeth_disable(struct ucc_geth_private *ugeth, enum comm_dir mode)
 
 static void ugeth_quiesce(struct ucc_geth_private *ugeth)
 {
-	/* Prevent any further xmits, plus detach the device. */
-	netif_device_detach(ugeth->ndev);
-
-	/* Wait for any current xmits to finish. */
-	netif_tx_disable(ugeth->ndev);
+	/* Prevent any further xmits */
+	netif_tx_stop_all_queues(ugeth->ndev);
 
 	/* Disable the interrupt to avoid NAPI rescheduling. */
 	disable_irq(ugeth->ug_info->uf_info.irq);
@@ -1565,7 +1563,10 @@ static void ugeth_activate(struct ucc_geth_private *ugeth)
 {
 	napi_enable(&ugeth->napi);
 	enable_irq(ugeth->ug_info->uf_info.irq);
-	netif_device_attach(ugeth->ndev);
+
+	/* allow to xmit again  */
+	netif_tx_wake_all_queues(ugeth->ndev);
+	__netdev_watchdog_up(ugeth->ndev);
 }
 
 /* Called every time the controller might need to be made
diff --git a/drivers/net/ethernet/freescale/xgmac_mdio.c b/drivers/net/ethernet/freescale/xgmac_mdio.c
index e03b30c60dcf..c82c85ef5fb3 100644
--- a/drivers/net/ethernet/freescale/xgmac_mdio.c
+++ b/drivers/net/ethernet/freescale/xgmac_mdio.c
@@ -49,6 +49,7 @@ struct tgec_mdio_controller {
 struct mdio_fsl_priv {
 	struct	tgec_mdio_controller __iomem *mdio_base;
 	bool	is_little_endian;
+	bool	has_a011043;
 };
 
 static u32 xgmac_read32(void __iomem *regs,
@@ -226,7 +227,8 @@ static int xgmac_mdio_read(struct mii_bus *bus, int phy_id, int regnum)
 		return ret;
 
 	/* Return all Fs if nothing was there */
-	if (xgmac_read32(&regs->mdio_stat, endian) & MDIO_STAT_RD_ER) {
+	if ((xgmac_read32(&regs->mdio_stat, endian) & MDIO_STAT_RD_ER) &&
+	    !priv->has_a011043) {
 		dev_err(&bus->dev,
 			"Error while reading PHY%d reg at %d.%hhu\n",
 			phy_id, dev_addr, regnum);
@@ -274,6 +276,9 @@ static int xgmac_mdio_probe(struct platform_device *pdev)
 	priv->is_little_endian = of_property_read_bool(pdev->dev.of_node,
 						       "little-endian");
 
+	priv->has_a011043 = of_property_read_bool(pdev->dev.of_node,
+						  "fsl,erratum-a011043");
+
 	ret = of_mdiobus_register(bus, np);
 	if (ret) {
 		dev_err(&pdev->dev, "cannot register MDIO bus\n");
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index dd0969a6cb20..7699fecc9de4 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -565,7 +565,6 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data,
 	skb = *out_skb = napi_alloc_skb(&ring_data->napi,
 					HNS_RX_HEAD_SIZE);
 	if (unlikely(!skb)) {
-		netdev_err(ndev, "alloc rx skb fail\n");
 		ring->stats.sw_err_cnt++;
 		return -ENOMEM;
 	}
@@ -1056,7 +1055,6 @@ static int hns_nic_common_poll(struct napi_struct *napi, int budget)
 		container_of(napi, struct hns_nic_ring_data, napi);
 	struct hnae_ring *ring = ring_data->ring;
 
-try_again:
 	clean_complete += ring_data->poll_one(
 				ring_data, budget - clean_complete,
 				ring_data->ex_process);
@@ -1066,7 +1064,7 @@ try_again:
 			napi_complete(napi);
 			ring->q->handle->dev->ops->toggle_ring_irq(ring, 0);
 		} else {
-			goto try_again;
+			return budget;
 		}
 	}
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index b43ef9f0857d..537caba74107 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -77,6 +77,7 @@
 	((ring)->p = ((ring)->p - 1 + (ring)->desc_num) % (ring)->desc_num)
 
 enum hns_desc_type {
+	DESC_TYPE_UNKNOWN,
 	DESC_TYPE_SKB,
 	DESC_TYPE_PAGE,
 };
@@ -273,6 +274,8 @@ struct hnae3_ae_dev {
  *   get auto autonegotiation of pause frame use
  * restart_autoneg()
  *   restart autonegotiation
+ * halt_autoneg()
+ *   halt/resume autonegotiation when autonegotiation on
  * get_coalesce_usecs()
  *   get usecs to delay a TX interrupt after a packet is sent
  * get_rx_max_coalesced_frames()
@@ -388,6 +391,7 @@ struct hnae3_ae_ops {
 	int (*set_autoneg)(struct hnae3_handle *handle, bool enable);
 	int (*get_autoneg)(struct hnae3_handle *handle);
 	int (*restart_autoneg)(struct hnae3_handle *handle);
+	int (*halt_autoneg)(struct hnae3_handle *handle, bool halt);
 
 	void (*get_coalesce_usecs)(struct hnae3_handle *handle,
 				   u32 *tx_usecs, u32 *rx_usecs);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 7f8a2d66f821..5132431fe372 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -44,6 +44,8 @@ MODULE_PARM_DESC(debug, " Network interface message level setting");
 #define DEFAULT_MSG_LEVEL (NETIF_MSG_PROBE | NETIF_MSG_LINK | \
 			   NETIF_MSG_IFDOWN | NETIF_MSG_IFUP)
 
+#define HNS3_MIN_TX_LEN		33U
+
 /* hns3_pci_tbl - PCI Device ID Table
  *
  * Last entry must be all 0s
@@ -1261,6 +1263,10 @@ static void hns3_clear_desc(struct hns3_enet_ring *ring, int next_to_use_orig)
 	unsigned int i;
 
 	for (i = 0; i < ring->desc_num; i++) {
+		struct hns3_desc *desc = &ring->desc[ring->next_to_use];
+
+		memset(desc, 0, sizeof(*desc));
+
 		/* check if this is where we started */
 		if (ring->next_to_use == next_to_use_orig)
 			break;
@@ -1268,6 +1274,9 @@ static void hns3_clear_desc(struct hns3_enet_ring *ring, int next_to_use_orig)
 		/* rollback one */
 		ring_ptr_move_bw(ring, next_to_use);
 
+		if (!ring->desc_cb[ring->next_to_use].dma)
+			continue;
+
 		/* unmap the descriptor dma address */
 		if (ring->desc_cb[ring->next_to_use].type == DESC_TYPE_SKB)
 			dma_unmap_single(dev,
@@ -1282,6 +1291,7 @@ static void hns3_clear_desc(struct hns3_enet_ring *ring, int next_to_use_orig)
 
 		ring->desc_cb[ring->next_to_use].length = 0;
 		ring->desc_cb[ring->next_to_use].dma = 0;
+		ring->desc_cb[ring->next_to_use].type = DESC_TYPE_UNKNOWN;
 	}
 }
 
@@ -1300,6 +1310,10 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 	int ret;
 	int i;
 
+	/* Hardware can only handle short frames above 32 bytes */
+	if (skb_put_padto(skb, HNS3_MIN_TX_LEN))
+		return NETDEV_TX_OK;
+
 	/* Prefetch the data used later */
 	prefetch(skb->data);
 
@@ -1555,7 +1569,7 @@ static int hns3_setup_tc(struct net_device *netdev, void *type_data)
 	kinfo = &h->kinfo;
 
 	return (kinfo->dcb_ops && kinfo->dcb_ops->setup_tc) ?
-		kinfo->dcb_ops->setup_tc(h, tc, prio_tc) : -EOPNOTSUPP;
+		kinfo->dcb_ops->setup_tc(h, tc ? tc : 1, prio_tc) : -EOPNOTSUPP;
 }
 
 static int hns3_nic_setup_tc(struct net_device *dev, enum tc_setup_type type,
@@ -3922,9 +3936,8 @@ static void hns3_client_uninit(struct hnae3_handle *handle, bool reset)
 
 	hns3_put_ring_config(priv);
 
-	hns3_dbg_uninit(handle);
-
 out_netdev_free:
+	hns3_dbg_uninit(handle);
 	free_netdev(netdev);
 }
 
@@ -3936,8 +3949,8 @@ static void hns3_link_status_change(struct hnae3_handle *handle, bool linkup)
 		return;
 
 	if (linkup) {
-		netif_carrier_on(netdev);
 		netif_tx_wake_all_queues(netdev);
+		netif_carrier_on(netdev);
 		if (netif_msg_link(handle))
 			netdev_info(netdev, "link up\n");
 	} else {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 24fce343e7fc..7735cf42347b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -163,18 +163,21 @@ static void hns3_lb_check_skb_data(struct hns3_enet_ring *ring,
 {
 	struct hns3_enet_tqp_vector *tqp_vector = ring->tqp_vector;
 	unsigned char *packet = skb->data;
+	u32 len = skb_headlen(skb);
 	u32 i;
 
-	for (i = 0; i < skb->len; i++)
+	len = min_t(u32, len, HNS3_NIC_LB_TEST_PACKET_SIZE);
+
+	for (i = 0; i < len; i++)
 		if (packet[i] != (unsigned char)(i & 0xff))
 			break;
 
 	/* The packet is correctly received */
-	if (i == skb->len)
+	if (i == HNS3_NIC_LB_TEST_PACKET_SIZE)
 		tqp_vector->rx_group.total_packets++;
 	else
 		print_hex_dump(KERN_ERR, "selftest:", DUMP_PREFIX_OFFSET, 16, 1,
-			       skb->data, skb->len, true);
+			       skb->data, len, true);
 
 	dev_kfree_skb_any(skb);
 }
@@ -329,6 +332,13 @@ static void hns3_self_test(struct net_device *ndev,
 		h->ae_algo->ops->enable_vlan_filter(h, false);
 #endif
 
+	/* Tell firmware to stop mac autoneg before loopback test start,
+	 * otherwise loopback test may be failed when the port is still
+	 * negotiating.
+	 */
+	if (h->ae_algo->ops->halt_autoneg)
+		h->ae_algo->ops->halt_autoneg(h, true);
+
 	set_bit(HNS3_NIC_STATE_TESTING, &priv->state);
 
 	for (i = 0; i < HNS3_SELF_TEST_TYPE_NUM; i++) {
@@ -351,6 +361,9 @@ static void hns3_self_test(struct net_device *ndev,
 
 	clear_bit(HNS3_NIC_STATE_TESTING, &priv->state);
 
+	if (h->ae_algo->ops->halt_autoneg)
+		h->ae_algo->ops->halt_autoneg(h, false);
+
 #if IS_ENABLED(CONFIG_VLAN_8021Q)
 	if (dis_vlan_filter)
 		h->ae_algo->ops->enable_vlan_filter(h, true);
@@ -675,6 +688,12 @@ static int hns3_check_ksettings_param(struct net_device *netdev,
 	u8 duplex;
 	int ret;
 
+	/* hw doesn't support use specified speed and duplex to negotiate,
+	 * unnecessary to check them when autoneg on.
+	 */
+	if (cmd->base.autoneg)
+		return 0;
+
 	if (ops->get_ksettings_an_result) {
 		ops->get_ksettings_an_result(handle, &autoneg, &speed, &duplex);
 		if (cmd->base.autoneg == autoneg && cmd->base.speed == speed &&
@@ -731,6 +750,15 @@ static int hns3_set_link_ksettings(struct net_device *netdev,
 			return ret;
 	}
 
+	/* hw doesn't support use specified speed and duplex to negotiate,
+	 * ignore them when autoneg on.
+	 */
+	if (cmd->base.autoneg) {
+		netdev_info(netdev,
+			    "autoneg is on, ignore the speed and duplex\n");
+		return 0;
+	}
+
 	if (ops->cfg_mac_speed_dup_h)
 		ret = ops->cfg_mac_speed_dup_h(handle, cmd->base.speed,
 					       cmd->base.duplex);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 8d0123f79ffe..49dbfcc649dd 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -31,6 +31,7 @@
 
 static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mps);
 static int hclge_init_vlan_config(struct hclge_dev *hdev);
+static void hclge_sync_vlan_filter(struct hclge_dev *hdev);
 static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev);
 static bool hclge_get_hw_reset_stat(struct hnae3_handle *handle);
 static int hclge_set_umv_space(struct hclge_dev *hdev, u16 space_size,
@@ -2244,10 +2245,12 @@ static int hclge_cfg_mac_speed_dup_hw(struct hclge_dev *hdev, int speed,
 
 int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex)
 {
+	struct hclge_mac *mac = &hdev->hw.mac;
 	int ret;
 
 	duplex = hclge_check_speed_dup(duplex, speed);
-	if (hdev->hw.mac.speed == speed && hdev->hw.mac.duplex == duplex)
+	if (!mac->support_autoneg && mac->speed == speed &&
+	    mac->duplex == duplex)
 		return 0;
 
 	ret = hclge_cfg_mac_speed_dup_hw(hdev, speed, duplex);
@@ -2334,6 +2337,17 @@ static int hclge_restart_autoneg(struct hnae3_handle *handle)
 	return hclge_notify_client(hdev, HNAE3_UP_CLIENT);
 }
 
+static int hclge_halt_autoneg(struct hnae3_handle *handle, bool halt)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+
+	if (hdev->hw.mac.support_autoneg && hdev->hw.mac.autoneg)
+		return hclge_set_autoneg_en(hdev, !halt);
+
+	return 0;
+}
+
 static int hclge_set_fec_hw(struct hclge_dev *hdev, u32 fec_mode)
 {
 	struct hclge_config_fec_cmd *req;
@@ -3556,6 +3570,7 @@ static void hclge_service_task(struct work_struct *work)
 	hclge_update_port_info(hdev);
 	hclge_update_link_status(hdev);
 	hclge_update_vport_alive(hdev);
+	hclge_sync_vlan_filter(hdev);
 	hclge_service_complete(hdev);
 }
 
@@ -5886,6 +5901,8 @@ static void hclge_ae_stop(struct hnae3_handle *handle)
 	for (i = 0; i < handle->kinfo.num_tqps; i++)
 		hclge_reset_tqp(handle, i);
 
+	hclge_config_mac_tnl_int(hdev, false);
+
 	/* Mac disable */
 	hclge_cfg_mac_mode(hdev, false);
 
@@ -7451,11 +7468,20 @@ int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto,
 	bool writen_to_tbl = false;
 	int ret = 0;
 
-	/* when port based VLAN enabled, we use port based VLAN as the VLAN
-	 * filter entry. In this case, we don't update VLAN filter table
-	 * when user add new VLAN or remove exist VLAN, just update the vport
-	 * VLAN list. The VLAN id in VLAN list won't be writen in VLAN filter
-	 * table until port based VLAN disabled
+	/* When device is resetting, firmware is unable to handle
+	 * mailbox. Just record the vlan id, and remove it after
+	 * reset finished.
+	 */
+	if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) && is_kill) {
+		set_bit(vlan_id, vport->vlan_del_fail_bmap);
+		return -EBUSY;
+	}
+
+	/* When port base vlan enabled, we use port base vlan as the vlan
+	 * filter entry. In this case, we don't update vlan filter table
+	 * when user add new vlan or remove exist vlan, just update the vport
+	 * vlan list. The vlan id in vlan list will be writen in vlan filter
+	 * table until port base vlan disabled
 	 */
 	if (handle->port_base_vlan_state == HNAE3_PORT_BASE_VLAN_DISABLE) {
 		ret = hclge_set_vlan_filter_hw(hdev, proto, vport->vport_id,
@@ -7463,16 +7489,53 @@ int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto,
 		writen_to_tbl = true;
 	}
 
-	if (ret)
-		return ret;
+	if (!ret) {
+		if (is_kill)
+			hclge_rm_vport_vlan_table(vport, vlan_id, false);
+		else
+			hclge_add_vport_vlan_table(vport, vlan_id,
+						   writen_to_tbl);
+	} else if (is_kill) {
+		/* When remove hw vlan filter failed, record the vlan id,
+		 * and try to remove it from hw later, to be consistence
+		 * with stack
+		 */
+		set_bit(vlan_id, vport->vlan_del_fail_bmap);
+	}
+	return ret;
+}
 
-	if (is_kill)
-		hclge_rm_vport_vlan_table(vport, vlan_id, false);
-	else
-		hclge_add_vport_vlan_table(vport, vlan_id,
-					   writen_to_tbl);
+static void hclge_sync_vlan_filter(struct hclge_dev *hdev)
+{
+#define HCLGE_MAX_SYNC_COUNT	60
 
-	return 0;
+	int i, ret, sync_cnt = 0;
+	u16 vlan_id;
+
+	/* start from vport 1 for PF is always alive */
+	for (i = 0; i < hdev->num_alloc_vport; i++) {
+		struct hclge_vport *vport = &hdev->vport[i];
+
+		vlan_id = find_first_bit(vport->vlan_del_fail_bmap,
+					 VLAN_N_VID);
+		while (vlan_id != VLAN_N_VID) {
+			ret = hclge_set_vlan_filter_hw(hdev, htons(ETH_P_8021Q),
+						       vport->vport_id, vlan_id,
+						       0, true);
+			if (ret && ret != -EINVAL)
+				return;
+
+			clear_bit(vlan_id, vport->vlan_del_fail_bmap);
+			hclge_rm_vport_vlan_table(vport, vlan_id, false);
+
+			sync_cnt++;
+			if (sync_cnt >= HCLGE_MAX_SYNC_COUNT)
+				return;
+
+			vlan_id = find_first_bit(vport->vlan_del_fail_bmap,
+						 VLAN_N_VID);
+		}
+	}
 }
 
 static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mps)
@@ -8427,6 +8490,13 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev)
 		return ret;
 	}
 
+	ret = init_mgr_tbl(hdev);
+	if (ret) {
+		dev_err(&pdev->dev,
+			"failed to reinit manager table, ret = %d\n", ret);
+		return ret;
+	}
+
 	ret = hclge_init_fd_config(hdev);
 	if (ret) {
 		dev_err(&pdev->dev,
@@ -8912,6 +8982,7 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.set_autoneg = hclge_set_autoneg,
 	.get_autoneg = hclge_get_autoneg,
 	.restart_autoneg = hclge_restart_autoneg,
+	.halt_autoneg = hclge_halt_autoneg,
 	.get_pauseparam = hclge_get_pauseparam,
 	.set_pauseparam = hclge_set_pauseparam,
 	.set_mtu = hclge_set_mtu,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 390cbb77e778..74fb80eac746 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -892,6 +892,7 @@ struct hclge_vport {
 	u32 bw_limit;		/* VSI BW Limit (0 = disabled) */
 	u8  dwrr;
 
+	unsigned long vlan_del_fail_bmap[BITS_TO_LONGS(VLAN_N_VID)];
 	struct hclge_port_base_vlan_config port_base_vlan_cfg;
 	struct hclge_tx_vtag_cfg  txvlan_cfg;
 	struct hclge_rx_vtag_cfg  rxvlan_cfg;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 48d943ae18be..ce92667dfde3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1256,6 +1256,7 @@ static int hclgevf_set_vlan_filter(struct hnae3_handle *handle,
 #define HCLGEVF_VLAN_MBX_MSG_LEN 5
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
 	u8 msg_data[HCLGEVF_VLAN_MBX_MSG_LEN];
+	int ret;
 
 	if (vlan_id > 4095)
 		return -EINVAL;
@@ -1263,12 +1264,53 @@ static int hclgevf_set_vlan_filter(struct hnae3_handle *handle,
 	if (proto != htons(ETH_P_8021Q))
 		return -EPROTONOSUPPORT;
 
+	/* When device is resetting, firmware is unable to handle
+	 * mailbox. Just record the vlan id, and remove it after
+	 * reset finished.
+	 */
+	if (test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state) && is_kill) {
+		set_bit(vlan_id, hdev->vlan_del_fail_bmap);
+		return -EBUSY;
+	}
+
 	msg_data[0] = is_kill;
 	memcpy(&msg_data[1], &vlan_id, sizeof(vlan_id));
 	memcpy(&msg_data[3], &proto, sizeof(proto));
-	return hclgevf_send_mbx_msg(hdev, HCLGE_MBX_SET_VLAN,
-				    HCLGE_MBX_VLAN_FILTER, msg_data,
-				    HCLGEVF_VLAN_MBX_MSG_LEN, false, NULL, 0);
+	ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_SET_VLAN,
+				   HCLGE_MBX_VLAN_FILTER, msg_data,
+				   HCLGEVF_VLAN_MBX_MSG_LEN, false, NULL, 0);
+
+	/* When remove hw vlan filter failed, record the vlan id,
+	 * and try to remove it from hw later, to be consistence
+	 * with stack.
+	 */
+	if (is_kill && ret)
+		set_bit(vlan_id, hdev->vlan_del_fail_bmap);
+
+	return ret;
+}
+
+static void hclgevf_sync_vlan_filter(struct hclgevf_dev *hdev)
+{
+#define HCLGEVF_MAX_SYNC_COUNT	60
+	struct hnae3_handle *handle = &hdev->nic;
+	int ret, sync_cnt = 0;
+	u16 vlan_id;
+
+	vlan_id = find_first_bit(hdev->vlan_del_fail_bmap, VLAN_N_VID);
+	while (vlan_id != VLAN_N_VID) {
+		ret = hclgevf_set_vlan_filter(handle, htons(ETH_P_8021Q),
+					      vlan_id, true);
+		if (ret)
+			return;
+
+		clear_bit(vlan_id, hdev->vlan_del_fail_bmap);
+		sync_cnt++;
+		if (sync_cnt >= HCLGEVF_MAX_SYNC_COUNT)
+			return;
+
+		vlan_id = find_first_bit(hdev->vlan_del_fail_bmap, VLAN_N_VID);
+	}
 }
 
 static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
@@ -1797,6 +1839,8 @@ static void hclgevf_service_task(struct work_struct *work)
 
 	hclgevf_update_link_mode(hdev);
 
+	hclgevf_sync_vlan_filter(hdev);
+
 	hclgevf_deferred_task_schedule(hdev);
 
 	clear_bit(HCLGEVF_STATE_SERVICE_SCHED, &hdev->state);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index d6798e07a8b4..b60d55ceefdc 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -4,6 +4,7 @@
 #ifndef __HCLGEVF_MAIN_H
 #define __HCLGEVF_MAIN_H
 #include <linux/fs.h>
+#include <linux/if_vlan.h>
 #include <linux/types.h>
 #include "hclge_mbx.h"
 #include "hclgevf_cmd.h"
@@ -266,6 +267,8 @@ struct hclgevf_dev {
 	u16 *vector_status;
 	int *vector_irq;
 
+	unsigned long vlan_del_fail_bmap[BITS_TO_LONGS(VLAN_N_VID)];
+
 	bool mbx_event_pending;
 	struct hclgevf_mbx_resp_status mbx_resp; /* mailbox response */
 	struct hclgevf_mbx_arq_ring arq; /* mailbox async rx queue */
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c
index eb53c15b13f3..5f2d57d1b2d3 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c
@@ -389,7 +389,8 @@ static int cmdq_sync_cmd_direct_resp(struct hinic_cmdq *cmdq,
 
 	spin_unlock_bh(&cmdq->cmdq_lock);
 
-	if (!wait_for_completion_timeout(&done, CMDQ_TIMEOUT)) {
+	if (!wait_for_completion_timeout(&done,
+					 msecs_to_jiffies(CMDQ_TIMEOUT))) {
 		spin_lock_bh(&cmdq->cmdq_lock);
 
 		if (cmdq->errcode[curr_prod_idx] == &errcode)
@@ -623,6 +624,8 @@ static int cmdq_cmd_ceq_handler(struct hinic_cmdq *cmdq, u16 ci,
 	if (!CMDQ_WQE_COMPLETED(be32_to_cpu(ctrl->ctrl_info)))
 		return -EBUSY;
 
+	dma_rmb();
+
 	errcode = CMDQ_WQE_ERRCODE_GET(be32_to_cpu(status->status_info), VAL);
 
 	cmdq_sync_cmd_handler(cmdq, ci, errcode);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
index 408705687de6..e69178694f28 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
@@ -300,6 +300,7 @@ static int set_hw_ioctxt(struct hinic_hwdev *hwdev, unsigned int rq_depth,
 	}
 
 	hw_ioctxt.func_idx = HINIC_HWIF_FUNC_IDX(hwif);
+	hw_ioctxt.ppf_idx = HINIC_HWIF_PPF_IDX(hwif);
 
 	hw_ioctxt.set_cmdq_depth = HW_IOCTXT_SET_CMDQ_DEPTH_DEFAULT;
 	hw_ioctxt.cmdq_depth = 0;
@@ -360,50 +361,6 @@ static int wait_for_db_state(struct hinic_hwdev *hwdev)
 	return -EFAULT;
 }
 
-static int wait_for_io_stopped(struct hinic_hwdev *hwdev)
-{
-	struct hinic_cmd_io_status cmd_io_status;
-	struct hinic_hwif *hwif = hwdev->hwif;
-	struct pci_dev *pdev = hwif->pdev;
-	struct hinic_pfhwdev *pfhwdev;
-	unsigned long end;
-	u16 out_size;
-	int err;
-
-	if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) {
-		dev_err(&pdev->dev, "Unsupported PCI Function type\n");
-		return -EINVAL;
-	}
-
-	pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev);
-
-	cmd_io_status.func_idx = HINIC_HWIF_FUNC_IDX(hwif);
-
-	end = jiffies + msecs_to_jiffies(IO_STATUS_TIMEOUT);
-	do {
-		err = hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, HINIC_MOD_COMM,
-					HINIC_COMM_CMD_IO_STATUS_GET,
-					&cmd_io_status, sizeof(cmd_io_status),
-					&cmd_io_status, &out_size,
-					HINIC_MGMT_MSG_SYNC);
-		if ((err) || (out_size != sizeof(cmd_io_status))) {
-			dev_err(&pdev->dev, "Failed to get IO status, ret = %d\n",
-				err);
-			return err;
-		}
-
-		if (cmd_io_status.status == IO_STOPPED) {
-			dev_info(&pdev->dev, "IO stopped\n");
-			return 0;
-		}
-
-		msleep(20);
-	} while (time_before(jiffies, end));
-
-	dev_err(&pdev->dev, "Wait for IO stopped - Timeout\n");
-	return -ETIMEDOUT;
-}
-
 /**
  * clear_io_resource - set the IO resources as not active in the NIC
  * @hwdev: the NIC HW device
@@ -423,11 +380,8 @@ static int clear_io_resources(struct hinic_hwdev *hwdev)
 		return -EINVAL;
 	}
 
-	err = wait_for_io_stopped(hwdev);
-	if (err) {
-		dev_err(&pdev->dev, "IO has not stopped yet\n");
-		return err;
-	}
+	/* sleep 100ms to wait for firmware stopping I/O */
+	msleep(100);
 
 	cmd_clear_io_res.func_idx = HINIC_HWIF_FUNC_IDX(hwif);
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
index a0a5b7434ad7..e052a2636991 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
@@ -99,8 +99,8 @@ struct hinic_cmd_hw_ioctxt {
 
 	u8      rsvd2;
 	u8      rsvd3;
+	u8      ppf_idx;
 	u8      rsvd4;
-	u8      rsvd5;
 
 	u16     rq_depth;
 	u16     rx_buf_sz_idx;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
index 79243b626ddb..c0b6bcb067cd 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
@@ -188,7 +188,7 @@ static u8 eq_cons_idx_checksum_set(u32 val)
  * eq_update_ci - update the HW cons idx of event queue
  * @eq: the event queue to update the cons idx for
  **/
-static void eq_update_ci(struct hinic_eq *eq)
+static void eq_update_ci(struct hinic_eq *eq, u32 arm_state)
 {
 	u32 val, addr = EQ_CONS_IDX_REG_ADDR(eq);
 
@@ -202,7 +202,7 @@ static void eq_update_ci(struct hinic_eq *eq)
 
 	val |= HINIC_EQ_CI_SET(eq->cons_idx, IDX)    |
 	       HINIC_EQ_CI_SET(eq->wrapped, WRAPPED) |
-	       HINIC_EQ_CI_SET(EQ_ARMED, INT_ARMED);
+	       HINIC_EQ_CI_SET(arm_state, INT_ARMED);
 
 	val |= HINIC_EQ_CI_SET(eq_cons_idx_checksum_set(val), XOR_CHKSUM);
 
@@ -235,6 +235,8 @@ static void aeq_irq_handler(struct hinic_eq *eq)
 		if (HINIC_EQ_ELEM_DESC_GET(aeqe_desc, WRAPPED) == eq->wrapped)
 			break;
 
+		dma_rmb();
+
 		event = HINIC_EQ_ELEM_DESC_GET(aeqe_desc, TYPE);
 		if (event >= HINIC_MAX_AEQ_EVENTS) {
 			dev_err(&pdev->dev, "Unknown AEQ Event %d\n", event);
@@ -347,7 +349,7 @@ static void eq_irq_handler(void *data)
 	else if (eq->type == HINIC_CEQ)
 		ceq_irq_handler(eq);
 
-	eq_update_ci(eq);
+	eq_update_ci(eq, EQ_ARMED);
 }
 
 /**
@@ -702,7 +704,7 @@ static int init_eq(struct hinic_eq *eq, struct hinic_hwif *hwif,
 	}
 
 	set_eq_ctrls(eq);
-	eq_update_ci(eq);
+	eq_update_ci(eq, EQ_ARMED);
 
 	err = alloc_eq_pages(eq);
 	if (err) {
@@ -752,18 +754,28 @@ err_req_irq:
  **/
 static void remove_eq(struct hinic_eq *eq)
 {
-	struct msix_entry *entry = &eq->msix_entry;
-
-	free_irq(entry->vector, eq);
+	hinic_set_msix_state(eq->hwif, eq->msix_entry.entry,
+			     HINIC_MSIX_DISABLE);
+	free_irq(eq->msix_entry.vector, eq);
 
 	if (eq->type == HINIC_AEQ) {
 		struct hinic_eq_work *aeq_work = &eq->aeq_work;
 
 		cancel_work_sync(&aeq_work->work);
+		/* clear aeq_len to avoid hw access host memory */
+		hinic_hwif_write_reg(eq->hwif,
+				     HINIC_CSR_AEQ_CTRL_1_ADDR(eq->q_id), 0);
 	} else if (eq->type == HINIC_CEQ) {
 		tasklet_kill(&eq->ceq_tasklet);
+		/* clear ceq_len to avoid hw access host memory */
+		hinic_hwif_write_reg(eq->hwif,
+				     HINIC_CSR_CEQ_CTRL_1_ADDR(eq->q_id), 0);
 	}
 
+	/* update cons_idx to avoid invalid interrupt */
+	eq->cons_idx = hinic_hwif_read_reg(eq->hwif, EQ_PROD_IDX_REG_ADDR(eq));
+	eq_update_ci(eq, EQ_NOT_ARMED);
+
 	free_eq_pages(eq);
 }
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
index 517794509eb2..c7bb9ceca72c 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
@@ -137,6 +137,7 @@
 #define HINIC_HWIF_FUNC_IDX(hwif)       ((hwif)->attr.func_idx)
 #define HINIC_HWIF_PCI_INTF(hwif)       ((hwif)->attr.pci_intf_idx)
 #define HINIC_HWIF_PF_IDX(hwif)         ((hwif)->attr.pf_idx)
+#define HINIC_HWIF_PPF_IDX(hwif)        ((hwif)->attr.ppf_idx)
 
 #define HINIC_FUNC_TYPE(hwif)           ((hwif)->attr.func_type)
 #define HINIC_IS_PF(hwif)               (HINIC_FUNC_TYPE(hwif) == HINIC_PF)
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
index c1a6be6bf6a8..992908e6eebf 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
@@ -43,7 +43,9 @@
 
 #define MSG_NOT_RESP                    0xFFFF
 
-#define MGMT_MSG_TIMEOUT                1000
+#define MGMT_MSG_TIMEOUT                5000
+
+#define SET_FUNC_PORT_MGMT_TIMEOUT	25000
 
 #define mgmt_to_pfhwdev(pf_mgmt)        \
 		container_of(pf_mgmt, struct hinic_pfhwdev, pf_to_mgmt)
@@ -238,12 +240,13 @@ static int msg_to_mgmt_sync(struct hinic_pf_to_mgmt *pf_to_mgmt,
 			    u8 *buf_in, u16 in_size,
 			    u8 *buf_out, u16 *out_size,
 			    enum mgmt_direction_type direction,
-			    u16 resp_msg_id)
+			    u16 resp_msg_id, u32 timeout)
 {
 	struct hinic_hwif *hwif = pf_to_mgmt->hwif;
 	struct pci_dev *pdev = hwif->pdev;
 	struct hinic_recv_msg *recv_msg;
 	struct completion *recv_done;
+	unsigned long timeo;
 	u16 msg_id;
 	int err;
 
@@ -267,7 +270,9 @@ static int msg_to_mgmt_sync(struct hinic_pf_to_mgmt *pf_to_mgmt,
 		goto unlock_sync_msg;
 	}
 
-	if (!wait_for_completion_timeout(recv_done, MGMT_MSG_TIMEOUT)) {
+	timeo = msecs_to_jiffies(timeout ? timeout : MGMT_MSG_TIMEOUT);
+
+	if (!wait_for_completion_timeout(recv_done, timeo)) {
 		dev_err(&pdev->dev, "MGMT timeout, MSG id = %d\n", msg_id);
 		err = -ETIMEDOUT;
 		goto unlock_sync_msg;
@@ -341,6 +346,7 @@ int hinic_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt,
 {
 	struct hinic_hwif *hwif = pf_to_mgmt->hwif;
 	struct pci_dev *pdev = hwif->pdev;
+	u32 timeout = 0;
 
 	if (sync != HINIC_MGMT_MSG_SYNC) {
 		dev_err(&pdev->dev, "Invalid MGMT msg type\n");
@@ -352,9 +358,12 @@ int hinic_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt,
 		return -EINVAL;
 	}
 
+	if (cmd == HINIC_PORT_CMD_SET_FUNC_STATE)
+		timeout = SET_FUNC_PORT_MGMT_TIMEOUT;
+
 	return msg_to_mgmt_sync(pf_to_mgmt, mod, cmd, buf_in, in_size,
 				buf_out, out_size, MGMT_DIRECT_SEND,
-				MSG_NOT_RESP);
+				MSG_NOT_RESP, timeout);
 }
 
 /**
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
index f4a339b10b10..79091e131418 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
@@ -94,6 +94,7 @@ struct hinic_rq {
 
 	struct hinic_wq         *wq;
 
+	struct cpumask		affinity_mask;
 	u32                     irq;
 	u16                     msix_entry;
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index b695d29d364c..5c1a7925d890 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -467,7 +467,6 @@ static int hinic_close(struct net_device *netdev)
 {
 	struct hinic_dev *nic_dev = netdev_priv(netdev);
 	unsigned int flags;
-	int err;
 
 	down(&nic_dev->mgmt_lock);
 
@@ -481,20 +480,9 @@ static int hinic_close(struct net_device *netdev)
 
 	up(&nic_dev->mgmt_lock);
 
-	err = hinic_port_set_func_state(nic_dev, HINIC_FUNC_PORT_DISABLE);
-	if (err) {
-		netif_err(nic_dev, drv, netdev,
-			  "Failed to set func port state\n");
-		nic_dev->flags |= (flags & HINIC_INTF_UP);
-		return err;
-	}
+	hinic_port_set_state(nic_dev, HINIC_PORT_DISABLE);
 
-	err = hinic_port_set_state(nic_dev, HINIC_PORT_DISABLE);
-	if (err) {
-		netif_err(nic_dev, drv, netdev, "Failed to set port state\n");
-		nic_dev->flags |= (flags & HINIC_INTF_UP);
-		return err;
-	}
+	hinic_port_set_func_state(nic_dev, HINIC_FUNC_PORT_DISABLE);
 
 	free_rxqs(nic_dev);
 	free_txqs(nic_dev);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
index 0850ea83d6c1..9fa64a1c5742 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
@@ -327,6 +327,9 @@ static int rxq_recv(struct hinic_rxq *rxq, int budget)
 		if (!rq_wqe)
 			break;
 
+		/* make sure we read rx_done before packet length */
+		dma_rmb();
+
 		hinic_rq_get_sge(rxq->rq, rq_wqe, ci, &sge);
 
 		rx_unmap_skb(rxq, hinic_sge_to_dma(&sge));
@@ -427,7 +430,6 @@ static int rx_request_irq(struct hinic_rxq *rxq)
 	struct hinic_hwdev *hwdev = nic_dev->hwdev;
 	struct hinic_rq *rq = rxq->rq;
 	struct hinic_qp *qp;
-	struct cpumask mask;
 	int err;
 
 	rx_add_napi(rxq);
@@ -444,8 +446,8 @@ static int rx_request_irq(struct hinic_rxq *rxq)
 	}
 
 	qp = container_of(rq, struct hinic_qp, rq);
-	cpumask_set_cpu(qp->q_id % num_online_cpus(), &mask);
-	return irq_set_affinity_hint(rq->irq, &mask);
+	cpumask_set_cpu(qp->q_id % num_online_cpus(), &rq->affinity_mask);
+	return irq_set_affinity_hint(rq->irq, &rq->affinity_mask);
 }
 
 static void rx_free_irq(struct hinic_rxq *rxq)
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
index b9fd8d720349..befe8fc50e4e 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
@@ -45,7 +45,7 @@
 
 #define HW_CONS_IDX(sq)                 be16_to_cpu(*(u16 *)((sq)->hw_ci_addr))
 
-#define MIN_SKB_LEN                     17
+#define MIN_SKB_LEN			32
 
 #define	MAX_PAYLOAD_OFFSET	        221
 #define TRANSPORT_OFFSET(l4_hdr, skb)	((u32)((l4_hdr) - (skb)->data))
@@ -597,6 +597,8 @@ static int free_tx_poll(struct napi_struct *napi, int budget)
 	do {
 		hw_ci = HW_CONS_IDX(sq) & wq->mask;
 
+		dma_rmb();
+
 		/* Reading a WQEBB to get real WQE size and consumer index. */
 		sq_wqe = hinic_sq_read_wqebb(sq, &skb, &wqe_size, &sw_ci);
 		if ((!sq_wqe) ||
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index c5be4ebd8437..aa32a5b04112 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1682,7 +1682,7 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	}
 
 	netdev->min_mtu = IBMVETH_MIN_MTU;
-	netdev->max_mtu = ETH_MAX_MTU;
+	netdev->max_mtu = ETH_MAX_MTU - IBMVETH_BUFF_OH;
 
 	memcpy(netdev->dev_addr, mac_addr_p, ETH_ALEN);
 
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 60dc39035336..44fb5d25efd0 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -779,12 +779,13 @@ static int ibmvnic_login(struct net_device *netdev)
 	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
 	unsigned long timeout = msecs_to_jiffies(30000);
 	int retry_count = 0;
+	int retries = 10;
 	bool retry;
 	int rc;
 
 	do {
 		retry = false;
-		if (retry_count > IBMVNIC_MAX_QUEUES) {
+		if (retry_count > retries) {
 			netdev_warn(netdev, "Login attempts exceeded\n");
 			return -1;
 		}
@@ -799,11 +800,23 @@ static int ibmvnic_login(struct net_device *netdev)
 
 		if (!wait_for_completion_timeout(&adapter->init_done,
 						 timeout)) {
-			netdev_warn(netdev, "Login timed out\n");
-			return -1;
+			netdev_warn(netdev, "Login timed out, retrying...\n");
+			retry = true;
+			adapter->init_done_rc = 0;
+			retry_count++;
+			continue;
 		}
 
-		if (adapter->init_done_rc == PARTIALSUCCESS) {
+		if (adapter->init_done_rc == ABORTED) {
+			netdev_warn(netdev, "Login aborted, retrying...\n");
+			retry = true;
+			adapter->init_done_rc = 0;
+			retry_count++;
+			/* FW or device may be busy, so
+			 * wait a bit before retrying login
+			 */
+			msleep(500);
+		} else if (adapter->init_done_rc == PARTIALSUCCESS) {
 			retry_count++;
 			release_sub_crqs(adapter, 1);
 
@@ -1865,13 +1878,18 @@ static int do_reset(struct ibmvnic_adapter *adapter,
 			release_sub_crqs(adapter, 1);
 		} else {
 			rc = ibmvnic_reset_crq(adapter);
-			if (!rc)
+			if (rc == H_CLOSED || rc == H_SUCCESS) {
 				rc = vio_enable_interrupts(adapter->vdev);
+				if (rc)
+					netdev_err(adapter->netdev,
+						   "Reset failed to enable interrupts. rc=%d\n",
+						   rc);
+			}
 		}
 
 		if (rc) {
 			netdev_err(adapter->netdev,
-				   "Couldn't initialize crq. rc=%d\n", rc);
+				   "Reset couldn't initialize crq. rc=%d\n", rc);
 			goto out;
 		}
 
@@ -2080,7 +2098,8 @@ static void __ibmvnic_reset(struct work_struct *work)
 				rc = do_hard_reset(adapter, rwi, reset_state);
 				rtnl_unlock();
 			}
-		} else {
+		} else if (!(rwi->reset_reason == VNIC_RESET_FATAL &&
+				adapter->from_passive_init)) {
 			rc = do_reset(adapter, rwi, reset_state);
 		}
 		kfree(rwi);
@@ -3044,7 +3063,7 @@ req_rx_irq_failed:
 req_tx_irq_failed:
 	for (j = 0; j < i; j++) {
 		free_irq(adapter->tx_scrq[j]->irq, adapter->tx_scrq[j]);
-		irq_dispose_mapping(adapter->rx_scrq[j]->irq);
+		irq_dispose_mapping(adapter->tx_scrq[j]->irq);
 	}
 	release_sub_crqs(adapter, 1);
 	return rc;
@@ -4511,12 +4530,10 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 			dev_err(dev, "Error %ld in VERSION_EXCHG_RSP\n", rc);
 			break;
 		}
-		dev_info(dev, "Partner protocol version is %d\n",
-			 crq->version_exchange_rsp.version);
-		if (be16_to_cpu(crq->version_exchange_rsp.version) <
-		    ibmvnic_version)
-			ibmvnic_version =
+		ibmvnic_version =
 			    be16_to_cpu(crq->version_exchange_rsp.version);
+		dev_info(dev, "Partner protocol version is %d\n",
+			 ibmvnic_version);
 		send_cap_queries(adapter);
 		break;
 	case QUERY_CAPABILITY_RSP:
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 551de8c2fef2..5e6722f286aa 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -3141,8 +3141,9 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
 		hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
 		if (skb->data_len && hdr_len == len) {
 			switch (hw->mac_type) {
+			case e1000_82544: {
 				unsigned int pull_size;
-			case e1000_82544:
+
 				/* Make sure we have room to chop off 4 bytes,
 				 * and that the end alignment will work out to
 				 * this hardware's requirements
@@ -3163,6 +3164,7 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
 				}
 				len = skb_headlen(skb);
 				break;
+			}
 			default:
 				/* do nothing */
 				break;
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index be13227f1697..b91d315b123f 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -577,7 +577,6 @@ static inline u32 __er32(struct e1000_hw *hw, unsigned long reg)
 
 #define er32(reg)	__er32(hw, E1000_##reg)
 
-s32 __ew32_prepare(struct e1000_hw *hw);
 void __ew32(struct e1000_hw *hw, unsigned long reg, u32 val);
 
 #define ew32(reg, val)	__ew32(hw, E1000_##reg, (val))
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index b081a1ef6859..4ac19ce5e251 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -119,14 +119,12 @@ static const struct e1000_reg_info e1000_reg_info_tbl[] = {
  * has bit 24 set while ME is accessing MAC CSR registers, wait if it is set
  * and try again a number of times.
  **/
-s32 __ew32_prepare(struct e1000_hw *hw)
+static void __ew32_prepare(struct e1000_hw *hw)
 {
 	s32 i = E1000_ICH_FWSM_PCIM2PCI_COUNT;
 
 	while ((er32(FWSM) & E1000_ICH_FWSM_PCIM2PCI) && --i)
 		udelay(50);
-
-	return i;
 }
 
 void __ew32(struct e1000_hw *hw, unsigned long reg, u32 val)
@@ -607,11 +605,11 @@ static void e1000e_update_rdt_wa(struct e1000_ring *rx_ring, unsigned int i)
 {
 	struct e1000_adapter *adapter = rx_ring->adapter;
 	struct e1000_hw *hw = &adapter->hw;
-	s32 ret_val = __ew32_prepare(hw);
 
+	__ew32_prepare(hw);
 	writel(i, rx_ring->tail);
 
-	if (unlikely(!ret_val && (i != readl(rx_ring->tail)))) {
+	if (unlikely(i != readl(rx_ring->tail))) {
 		u32 rctl = er32(RCTL);
 
 		ew32(RCTL, rctl & ~E1000_RCTL_EN);
@@ -624,11 +622,11 @@ static void e1000e_update_tdt_wa(struct e1000_ring *tx_ring, unsigned int i)
 {
 	struct e1000_adapter *adapter = tx_ring->adapter;
 	struct e1000_hw *hw = &adapter->hw;
-	s32 ret_val = __ew32_prepare(hw);
 
+	__ew32_prepare(hw);
 	writel(i, tx_ring->tail);
 
-	if (unlikely(!ret_val && (i != readl(tx_ring->tail)))) {
+	if (unlikely(i != readl(tx_ring->tail))) {
 		u32 tctl = er32(TCTL);
 
 		ew32(TCTL, tctl & ~E1000_TCTL_EN);
@@ -4713,12 +4711,12 @@ int e1000e_close(struct net_device *netdev)
 
 	pm_runtime_get_sync(&pdev->dev);
 
-	if (!test_bit(__E1000_DOWN, &adapter->state)) {
+	if (netif_device_present(netdev)) {
 		e1000e_down(adapter, true);
 		e1000_free_irq(adapter);
 
 		/* Link status message must follow this format */
-		pr_info("%s NIC Link is Down\n", adapter->netdev->name);
+		pr_info("%s NIC Link is Down\n", netdev->name);
 	}
 
 	napi_disable(&adapter->napi);
@@ -5273,6 +5271,10 @@ static void e1000_watchdog_task(struct work_struct *work)
 					/* oops */
 					break;
 				}
+				if (hw->mac.type == e1000_pch_spt) {
+					netdev->features &= ~NETIF_F_TSO;
+					netdev->features &= ~NETIF_F_TSO6;
+				}
 			}
 
 			/* enable transmits in the hardware, need to do this
@@ -6292,12 +6294,16 @@ fl_out:
 
 static int e1000e_pm_freeze(struct device *dev)
 {
-	struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev));
+	struct net_device *netdev = dev_get_drvdata(dev);
 	struct e1000_adapter *adapter = netdev_priv(netdev);
+	bool present;
 
+	rtnl_lock();
+
+	present = netif_device_present(netdev);
 	netif_device_detach(netdev);
 
-	if (netif_running(netdev)) {
+	if (present && netif_running(netdev)) {
 		int count = E1000_CHECK_RESET_COUNT;
 
 		while (test_bit(__E1000_RESETTING, &adapter->state) && count--)
@@ -6309,6 +6315,8 @@ static int e1000e_pm_freeze(struct device *dev)
 		e1000e_down(adapter, false);
 		e1000_free_irq(adapter);
 	}
+	rtnl_unlock();
+
 	e1000e_reset_interrupt_capability(adapter);
 
 	/* Allow time for pending master requests to run */
@@ -6322,11 +6330,17 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime)
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
-	u32 ctrl, ctrl_ext, rctl, status;
-	/* Runtime suspend should only enable wakeup for link changes */
-	u32 wufc = runtime ? E1000_WUFC_LNKC : adapter->wol;
+	u32 ctrl, ctrl_ext, rctl, status, wufc;
 	int retval = 0;
 
+	/* Runtime suspend should only enable wakeup for link changes */
+	if (runtime)
+		wufc = E1000_WUFC_LNKC;
+	else if (device_may_wakeup(&pdev->dev))
+		wufc = adapter->wol;
+	else
+		wufc = 0;
+
 	status = er32(STATUS);
 	if (status & E1000_STATUS_LU)
 		wufc &= ~E1000_WUFC_LNKC;
@@ -6383,7 +6397,7 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime)
 	if (adapter->hw.phy.type == e1000_phy_igp_3) {
 		e1000e_igp3_phy_powerdown_workaround_ich8lan(&adapter->hw);
 	} else if (hw->mac.type >= e1000_pch_lpt) {
-		if (!(wufc & (E1000_WUFC_EX | E1000_WUFC_MC | E1000_WUFC_BC)))
+		if (wufc && !(wufc & (E1000_WUFC_EX | E1000_WUFC_MC | E1000_WUFC_BC)))
 			/* ULP does not support wake from unicast, multicast
 			 * or broadcast.
 			 */
@@ -6556,6 +6570,30 @@ static void e1000e_disable_aspm_locked(struct pci_dev *pdev, u16 state)
 	__e1000e_disable_aspm(pdev, state, 1);
 }
 
+static int e1000e_pm_thaw(struct device *dev)
+{
+	struct net_device *netdev = dev_get_drvdata(dev);
+	struct e1000_adapter *adapter = netdev_priv(netdev);
+	int rc = 0;
+
+	e1000e_set_interrupt_capability(adapter);
+
+	rtnl_lock();
+	if (netif_running(netdev)) {
+		rc = e1000_request_irq(adapter);
+		if (rc)
+			goto err_irq;
+
+		e1000e_up(adapter);
+	}
+
+	netif_device_attach(netdev);
+err_irq:
+	rtnl_unlock();
+
+	return rc;
+}
+
 #ifdef CONFIG_PM
 static int __e1000_resume(struct pci_dev *pdev)
 {
@@ -6623,26 +6661,6 @@ static int __e1000_resume(struct pci_dev *pdev)
 }
 
 #ifdef CONFIG_PM_SLEEP
-static int e1000e_pm_thaw(struct device *dev)
-{
-	struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev));
-	struct e1000_adapter *adapter = netdev_priv(netdev);
-
-	e1000e_set_interrupt_capability(adapter);
-	if (netif_running(netdev)) {
-		u32 err = e1000_request_irq(adapter);
-
-		if (err)
-			return err;
-
-		e1000e_up(adapter);
-	}
-
-	netif_device_attach(netdev);
-
-	return 0;
-}
-
 static int e1000e_pm_suspend(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
@@ -6674,8 +6692,7 @@ static int e1000e_pm_resume(struct device *dev)
 
 static int e1000e_pm_runtime_idle(struct device *dev)
 {
-	struct pci_dev *pdev = to_pci_dev(dev);
-	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct net_device *netdev = dev_get_drvdata(dev);
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	u16 eee_lp;
 
@@ -6815,16 +6832,11 @@ static void e1000_netpoll(struct net_device *netdev)
 static pci_ers_result_t e1000_io_error_detected(struct pci_dev *pdev,
 						pci_channel_state_t state)
 {
-	struct net_device *netdev = pci_get_drvdata(pdev);
-	struct e1000_adapter *adapter = netdev_priv(netdev);
-
-	netif_device_detach(netdev);
+	e1000e_pm_freeze(&pdev->dev);
 
 	if (state == pci_channel_io_perm_failure)
 		return PCI_ERS_RESULT_DISCONNECT;
 
-	if (netif_running(netdev))
-		e1000e_down(adapter, true);
 	pci_disable_device(pdev);
 
 	/* Request a slot slot reset. */
@@ -6890,10 +6902,7 @@ static void e1000_io_resume(struct pci_dev *pdev)
 
 	e1000_init_manageability_pt(adapter);
 
-	if (netif_running(netdev))
-		e1000e_up(adapter);
-
-	netif_device_attach(netdev);
+	e1000e_pm_thaw(&pdev->dev);
 
 	/* If the controller has AMT, do not set DRV_LOAD until the interface
 	 * is up.  For all other cases, let the f/w know that the h/w is now
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 7ce42040b851..9ef2d3f86aff 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -1125,7 +1125,7 @@ void i40e_set_fec_in_flags(u8 fec_cfg, u32 *flags);
 
 static inline bool i40e_enabled_xdp_vsi(struct i40e_vsi *vsi)
 {
-	return !!vsi->xdp_prog;
+	return !!READ_ONCE(vsi->xdp_prog);
 }
 
 int i40e_create_queue_channel(struct i40e_vsi *vsi, struct i40e_channel *ch);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index f86d66139ecc..10173a7987c5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -457,11 +457,15 @@ static void i40e_get_netdev_stats_struct(struct net_device *netdev,
 		i40e_get_netdev_stats_struct_tx(ring, stats);
 
 		if (i40e_enabled_xdp_vsi(vsi)) {
-			ring++;
+			ring = READ_ONCE(vsi->xdp_rings[i]);
+			if (!ring)
+				continue;
 			i40e_get_netdev_stats_struct_tx(ring, stats);
 		}
 
-		ring++;
+		ring = READ_ONCE(vsi->rx_rings[i]);
+		if (!ring)
+			continue;
 		do {
 			start   = u64_stats_fetch_begin_irq(&ring->syncp);
 			packets = ring->stats.packets;
@@ -804,6 +808,8 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi)
 	for (q = 0; q < vsi->num_queue_pairs; q++) {
 		/* locate Tx ring */
 		p = READ_ONCE(vsi->tx_rings[q]);
+		if (!p)
+			continue;
 
 		do {
 			start = u64_stats_fetch_begin_irq(&p->syncp);
@@ -817,8 +823,11 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi)
 		tx_linearize += p->tx_stats.tx_linearize;
 		tx_force_wb += p->tx_stats.tx_force_wb;
 
-		/* Rx queue is part of the same block as Tx queue */
-		p = &p[1];
+		/* locate Rx ring */
+		p = READ_ONCE(vsi->rx_rings[q]);
+		if (!p)
+			continue;
+
 		do {
 			start = u64_stats_fetch_begin_irq(&p->syncp);
 			packets = p->stats.packets;
@@ -6272,6 +6281,7 @@ static int i40e_configure_queue_channels(struct i40e_vsi *vsi)
 				dev_err(&vsi->back->pdev->dev,
 					"Failed creating queue channel with TC%d: queues %d\n",
 					i, ch->num_queue_pairs);
+				kfree(ch);
 				goto err_free;
 			}
 			vsi->tc_seid_map[i] = ch->seid;
@@ -6789,8 +6799,8 @@ void i40e_down(struct i40e_vsi *vsi)
 	for (i = 0; i < vsi->num_queue_pairs; i++) {
 		i40e_clean_tx_ring(vsi->tx_rings[i]);
 		if (i40e_enabled_xdp_vsi(vsi)) {
-			/* Make sure that in-progress ndo_xdp_xmit
-			 * calls are completed.
+			/* Make sure that in-progress ndo_xdp_xmit and
+			 * ndo_xsk_wakeup calls are completed.
 			 */
 			synchronize_rcu();
 			i40e_clean_tx_ring(vsi->xdp_rings[i]);
@@ -10307,10 +10317,10 @@ static void i40e_vsi_clear_rings(struct i40e_vsi *vsi)
 	if (vsi->tx_rings && vsi->tx_rings[0]) {
 		for (i = 0; i < vsi->alloc_queue_pairs; i++) {
 			kfree_rcu(vsi->tx_rings[i], rcu);
-			vsi->tx_rings[i] = NULL;
-			vsi->rx_rings[i] = NULL;
+			WRITE_ONCE(vsi->tx_rings[i], NULL);
+			WRITE_ONCE(vsi->rx_rings[i], NULL);
 			if (vsi->xdp_rings)
-				vsi->xdp_rings[i] = NULL;
+				WRITE_ONCE(vsi->xdp_rings[i], NULL);
 		}
 	}
 }
@@ -10344,7 +10354,7 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi)
 		if (vsi->back->hw_features & I40E_HW_WB_ON_ITR_CAPABLE)
 			ring->flags = I40E_TXR_FLAGS_WB_ON_ITR;
 		ring->itr_setting = pf->tx_itr_default;
-		vsi->tx_rings[i] = ring++;
+		WRITE_ONCE(vsi->tx_rings[i], ring++);
 
 		if (!i40e_enabled_xdp_vsi(vsi))
 			goto setup_rx;
@@ -10362,7 +10372,7 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi)
 			ring->flags = I40E_TXR_FLAGS_WB_ON_ITR;
 		set_ring_xdp(ring);
 		ring->itr_setting = pf->tx_itr_default;
-		vsi->xdp_rings[i] = ring++;
+		WRITE_ONCE(vsi->xdp_rings[i], ring++);
 
 setup_rx:
 		ring->queue_index = i;
@@ -10375,7 +10385,7 @@ setup_rx:
 		ring->size = 0;
 		ring->dcb_tc = 0;
 		ring->itr_setting = pf->rx_itr_default;
-		vsi->rx_rings[i] = ring;
+		WRITE_ONCE(vsi->rx_rings[i], ring);
 	}
 
 	return 0;
@@ -12015,8 +12025,12 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi,
 
 	old_prog = xchg(&vsi->xdp_prog, prog);
 
-	if (need_reset)
+	if (need_reset) {
+		if (!prog)
+			/* Wait until ndo_xsk_wakeup completes. */
+			synchronize_rcu();
 		i40e_reset_and_rebuild(pf, true, true);
+	}
 
 	for (i = 0; i < vsi->num_queue_pairs; i++)
 		WRITE_ONCE(vsi->rx_rings[i]->xdp_prog, vsi->xdp_prog);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 479bc60c8f71..1b1e60b86f31 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -2307,6 +2307,22 @@ static int i40e_ctrl_vf_rx_rings(struct i40e_vsi *vsi, unsigned long q_map,
 }
 
 /**
+ * i40e_vc_validate_vqs_bitmaps - validate Rx/Tx queue bitmaps from VIRTHCHNL
+ * @vqs: virtchnl_queue_select structure containing bitmaps to validate
+ *
+ * Returns true if validation was successful, else false.
+ */
+static bool i40e_vc_validate_vqs_bitmaps(struct virtchnl_queue_select *vqs)
+{
+	if ((!vqs->rx_queues && !vqs->tx_queues) ||
+	    vqs->rx_queues >= BIT(I40E_MAX_VF_QUEUES) ||
+	    vqs->tx_queues >= BIT(I40E_MAX_VF_QUEUES))
+		return false;
+
+	return true;
+}
+
+/**
  * i40e_vc_enable_queues_msg
  * @vf: pointer to the VF info
  * @msg: pointer to the msg buffer
@@ -2332,7 +2348,7 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg)
 		goto error_param;
 	}
 
-	if ((0 == vqs->rx_queues) && (0 == vqs->tx_queues)) {
+	if (!i40e_vc_validate_vqs_bitmaps(vqs)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto error_param;
 	}
@@ -2389,9 +2405,7 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg)
 		goto error_param;
 	}
 
-	if ((vqs->rx_queues == 0 && vqs->tx_queues == 0) ||
-	    vqs->rx_queues > I40E_MAX_VF_QUEUES ||
-	    vqs->tx_queues > I40E_MAX_VF_QUEUES) {
+	if (!i40e_vc_validate_vqs_bitmaps(vqs)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto error_param;
 	}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 1b17486543ac..71ad5c93048d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -772,8 +772,12 @@ int i40e_xsk_async_xmit(struct net_device *dev, u32 queue_id)
 {
 	struct i40e_netdev_priv *np = netdev_priv(dev);
 	struct i40e_vsi *vsi = np->vsi;
+	struct i40e_pf *pf = vsi->back;
 	struct i40e_ring *ring;
 
+	if (test_bit(__I40E_CONFIG_BUSY, pf->state))
+		return -EAGAIN;
+
 	if (test_bit(__I40E_VSI_DOWN, vsi->state))
 		return -ENETDOWN;
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index 272d76b733aa..4df14be14ce3 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -415,4 +415,6 @@ void iavf_enable_channels(struct iavf_adapter *adapter);
 void iavf_disable_channels(struct iavf_adapter *adapter);
 void iavf_add_cloud_filter(struct iavf_adapter *adapter);
 void iavf_del_cloud_filter(struct iavf_adapter *adapter);
+struct iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter,
+					const u8 *macaddr);
 #endif /* _IAVF_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index eeaa9125f25e..cd89cf39f984 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -761,9 +761,8 @@ iavf_mac_filter *iavf_find_filter(struct iavf_adapter *adapter,
  *
  * Returns ptr to the filter object or NULL when no memory available.
  **/
-static struct
-iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter,
-				 const u8 *macaddr)
+struct iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter,
+					const u8 *macaddr)
 {
 	struct iavf_mac_filter *f;
 
@@ -1825,9 +1824,9 @@ static void iavf_reset_task(struct work_struct *work)
 	struct virtchnl_vf_resource *vfres = adapter->vf_res;
 	struct net_device *netdev = adapter->netdev;
 	struct iavf_hw *hw = &adapter->hw;
+	struct iavf_mac_filter *f, *ftmp;
 	struct iavf_vlan_filter *vlf;
 	struct iavf_cloud_filter *cf;
-	struct iavf_mac_filter *f;
 	u32 reg_val;
 	int i = 0, err;
 	bool running;
@@ -1941,6 +1940,16 @@ continue_reset:
 
 	spin_lock_bh(&adapter->mac_vlan_list_lock);
 
+	/* Delete filter for the current MAC address, it could have
+	 * been changed by the PF via administratively set MAC.
+	 * Will be re-added via VIRTCHNL_OP_GET_VF_RESOURCES.
+	 */
+	list_for_each_entry_safe(f, ftmp, &adapter->mac_filter_list, list) {
+		if (ether_addr_equal(f->macaddr, adapter->hw.mac.addr)) {
+			list_del(&f->list);
+			kfree(f);
+		}
+	}
 	/* re-add all MAC filters */
 	list_for_each_entry(f, &adapter->mac_filter_list, list) {
 		f->add = true;
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index e64751da0921..418890a9b551 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -1357,6 +1357,9 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 			ether_addr_copy(netdev->perm_addr,
 					adapter->hw.mac.addr);
 		}
+		spin_lock_bh(&adapter->mac_vlan_list_lock);
+		iavf_add_filter(adapter, adapter->hw.mac.addr);
+		spin_unlock_bh(&adapter->mac_vlan_list_lock);
 		iavf_process_config(adapter);
 		}
 		break;
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index da7878529929..28def013dab5 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -423,6 +423,7 @@ static void ice_init_flex_flds(struct ice_hw *hw, enum ice_rxdid prof_id)
 static enum ice_status ice_init_fltr_mgmt_struct(struct ice_hw *hw)
 {
 	struct ice_switch_info *sw;
+	enum ice_status status;
 
 	hw->switch_info = devm_kzalloc(ice_hw_to_dev(hw),
 				       sizeof(*hw->switch_info), GFP_KERNEL);
@@ -433,7 +434,12 @@ static enum ice_status ice_init_fltr_mgmt_struct(struct ice_hw *hw)
 
 	INIT_LIST_HEAD(&sw->vsi_list_map_head);
 
-	return ice_init_def_sw_recp(hw);
+	status = ice_init_def_sw_recp(hw);
+	if (status) {
+		devm_kfree(ice_hw_to_dev(hw), hw->switch_info);
+		return status;
+	}
+	return 0;
 }
 
 /**
@@ -842,7 +848,7 @@ void ice_deinit_hw(struct ice_hw *hw)
  */
 enum ice_status ice_check_reset(struct ice_hw *hw)
 {
-	u32 cnt, reg = 0, grst_delay;
+	u32 cnt, reg = 0, grst_delay, uld_mask;
 
 	/* Poll for Device Active state in case a recent CORER, GLOBR,
 	 * or EMPR has occurred. The grst delay value is in 100ms units.
@@ -864,13 +870,20 @@ enum ice_status ice_check_reset(struct ice_hw *hw)
 		return ICE_ERR_RESET_FAILED;
 	}
 
-#define ICE_RESET_DONE_MASK	(GLNVM_ULD_CORER_DONE_M | \
-				 GLNVM_ULD_GLOBR_DONE_M)
+#define ICE_RESET_DONE_MASK	(GLNVM_ULD_PCIER_DONE_M |\
+				 GLNVM_ULD_PCIER_DONE_1_M |\
+				 GLNVM_ULD_CORER_DONE_M |\
+				 GLNVM_ULD_GLOBR_DONE_M |\
+				 GLNVM_ULD_POR_DONE_M |\
+				 GLNVM_ULD_POR_DONE_1_M |\
+				 GLNVM_ULD_PCIER_DONE_2_M)
+
+	uld_mask = ICE_RESET_DONE_MASK;
 
 	/* Device is Active; check Global Reset processes are done */
 	for (cnt = 0; cnt < ICE_PF_RESET_WAIT_COUNT; cnt++) {
-		reg = rd32(hw, GLNVM_ULD) & ICE_RESET_DONE_MASK;
-		if (reg == ICE_RESET_DONE_MASK) {
+		reg = rd32(hw, GLNVM_ULD) & uld_mask;
+		if (reg == uld_mask) {
 			ice_debug(hw, ICE_DBG_INIT,
 				  "Global reset processes done. %d\n", cnt);
 			break;
diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c
index 7ad740632329..b33e24e02aab 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.c
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.c
@@ -199,7 +199,9 @@ unwind_alloc_rq_bufs:
 		cq->rq.r.rq_bi[i].pa = 0;
 		cq->rq.r.rq_bi[i].size = 0;
 	}
+	cq->rq.r.rq_bi = NULL;
 	devm_kfree(ice_hw_to_dev(hw), cq->rq.dma_head);
+	cq->rq.dma_head = NULL;
 
 	return ICE_ERR_NO_MEMORY;
 }
@@ -245,7 +247,9 @@ unwind_alloc_sq_bufs:
 		cq->sq.r.sq_bi[i].pa = 0;
 		cq->sq.r.sq_bi[i].size = 0;
 	}
+	cq->sq.r.sq_bi = NULL;
 	devm_kfree(ice_hw_to_dev(hw), cq->sq.dma_head);
+	cq->sq.dma_head = NULL;
 
 	return ICE_ERR_NO_MEMORY;
 }
@@ -304,6 +308,28 @@ ice_cfg_rq_regs(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 	return 0;
 }
 
+#define ICE_FREE_CQ_BUFS(hw, qi, ring)					\
+do {									\
+	int i;								\
+	/* free descriptors */						\
+	if ((qi)->ring.r.ring##_bi)					\
+		for (i = 0; i < (qi)->num_##ring##_entries; i++)	\
+			if ((qi)->ring.r.ring##_bi[i].pa) {		\
+				dmam_free_coherent(ice_hw_to_dev(hw),	\
+					(qi)->ring.r.ring##_bi[i].size,	\
+					(qi)->ring.r.ring##_bi[i].va,	\
+					(qi)->ring.r.ring##_bi[i].pa);	\
+					(qi)->ring.r.ring##_bi[i].va = NULL;\
+					(qi)->ring.r.ring##_bi[i].pa = 0;\
+					(qi)->ring.r.ring##_bi[i].size = 0;\
+		}							\
+	/* free the buffer info list */					\
+	if ((qi)->ring.cmd_buf)						\
+		devm_kfree(ice_hw_to_dev(hw), (qi)->ring.cmd_buf);	\
+	/* free DMA head */						\
+	devm_kfree(ice_hw_to_dev(hw), (qi)->ring.dma_head);		\
+} while (0)
+
 /**
  * ice_init_sq - main initialization routine for Control ATQ
  * @hw: pointer to the hardware structure
@@ -357,6 +383,7 @@ static enum ice_status ice_init_sq(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 	goto init_ctrlq_exit;
 
 init_ctrlq_free_rings:
+	ICE_FREE_CQ_BUFS(hw, cq, sq);
 	ice_free_cq_ring(hw, &cq->sq);
 
 init_ctrlq_exit:
@@ -416,33 +443,13 @@ static enum ice_status ice_init_rq(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 	goto init_ctrlq_exit;
 
 init_ctrlq_free_rings:
+	ICE_FREE_CQ_BUFS(hw, cq, rq);
 	ice_free_cq_ring(hw, &cq->rq);
 
 init_ctrlq_exit:
 	return ret_code;
 }
 
-#define ICE_FREE_CQ_BUFS(hw, qi, ring)					\
-do {									\
-	int i;								\
-	/* free descriptors */						\
-	for (i = 0; i < (qi)->num_##ring##_entries; i++)		\
-		if ((qi)->ring.r.ring##_bi[i].pa) {			\
-			dmam_free_coherent(ice_hw_to_dev(hw),		\
-					   (qi)->ring.r.ring##_bi[i].size,\
-					   (qi)->ring.r.ring##_bi[i].va,\
-					   (qi)->ring.r.ring##_bi[i].pa);\
-			(qi)->ring.r.ring##_bi[i].va = NULL;		\
-			(qi)->ring.r.ring##_bi[i].pa = 0;		\
-			(qi)->ring.r.ring##_bi[i].size = 0;		\
-		}							\
-	/* free the buffer info list */					\
-	if ((qi)->ring.cmd_buf)						\
-		devm_kfree(ice_hw_to_dev(hw), (qi)->ring.cmd_buf);	\
-	/* free dma head */						\
-	devm_kfree(ice_hw_to_dev(hw), (qi)->ring.dma_head);		\
-} while (0)
-
 /**
  * ice_shutdown_sq - shutdown the Control ATQ
  * @hw: pointer to the hardware structure
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 1341fde8d53f..4c81d77cf5cc 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -2032,13 +2032,6 @@ ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)
 	else
 		return -EINVAL;
 
-	/* Tell the OS link is going down, the link will go back up when fw
-	 * says it is ready asynchronously
-	 */
-	ice_print_link_msg(vsi, false);
-	netif_carrier_off(netdev);
-	netif_tx_stop_all_queues(netdev);
-
 	/* Set the FC mode and only restart AN if link is up */
 	status = ice_set_fc(pi, &aq_failures, link_up);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index ec25f26069b0..63b74424e402 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -264,8 +264,14 @@
 #define GLNVM_GENS_SR_SIZE_S			5
 #define GLNVM_GENS_SR_SIZE_M			ICE_M(0x7, 5)
 #define GLNVM_ULD				0x000B6008
+#define GLNVM_ULD_PCIER_DONE_M			BIT(0)
+#define GLNVM_ULD_PCIER_DONE_1_M		BIT(1)
 #define GLNVM_ULD_CORER_DONE_M			BIT(3)
 #define GLNVM_ULD_GLOBR_DONE_M			BIT(4)
+#define GLNVM_ULD_POR_DONE_M			BIT(5)
+#define GLNVM_ULD_POR_DONE_1_M			BIT(8)
+#define GLNVM_ULD_PCIER_DONE_2_M		BIT(9)
+#define GLNVM_ULD_PE_DONE_M			BIT(10)
 #define GLPCI_CNF2				0x000BE004
 #define GLPCI_CNF2_CACHELINE_SIZE_M		BIT(1)
 #define PF_FUNC_RID				0x0009E880
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index f312b2f92cd5..07fcda55f6df 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2329,7 +2329,7 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 	if (err) {
 		dev_err(dev, "ice_init_interrupt_scheme failed: %d\n", err);
 		err = -EIO;
-		goto err_init_interrupt_unroll;
+		goto err_init_vsi_unroll;
 	}
 
 	/* Driver is mostly up */
@@ -2394,6 +2394,7 @@ err_msix_misc_unroll:
 	ice_free_irq_msix_misc(pf);
 err_init_interrupt_unroll:
 	ice_clear_interrupt_scheme(pf);
+err_init_vsi_unroll:
 	devm_kfree(dev, pf->vsi);
 err_init_pf_unroll:
 	ice_deinit_pf(pf);
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index 1826e5562ce5..f4e9c6ba568f 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -1662,8 +1662,8 @@ static int ice_vc_get_stats_msg(struct ice_vf *vf, u8 *msg)
 	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
 	struct virtchnl_queue_select *vqs =
 		(struct virtchnl_queue_select *)msg;
+	struct ice_eth_stats stats = { 0 };
 	struct ice_pf *pf = vf->pf;
-	struct ice_eth_stats stats;
 	struct ice_vsi *vsi;
 
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
@@ -1682,7 +1682,6 @@ static int ice_vc_get_stats_msg(struct ice_vf *vf, u8 *msg)
 		goto error_param;
 	}
 
-	memset(&stats, 0, sizeof(struct ice_eth_stats));
 	ice_update_eth_stats(vsi);
 
 	stats = vsi->eth_stats;
diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c
index bafdcf70a353..fdab974b245b 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.c
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.c
@@ -530,7 +530,7 @@ static s32 igb_set_sfp_media_type_82575(struct e1000_hw *hw)
 		dev_spec->module_plugged = true;
 		if (eth_flags->e1000_base_lx || eth_flags->e1000_base_sx) {
 			hw->phy.media_type = e1000_media_type_internal_serdes;
-		} else if (eth_flags->e100_base_fx) {
+		} else if (eth_flags->e100_base_fx || eth_flags->e100_base_lx) {
 			dev_spec->sgmii_active = true;
 			hw->phy.media_type = e1000_media_type_internal_serdes;
 		} else if (eth_flags->e1000_base_t) {
@@ -657,14 +657,10 @@ static s32 igb_get_invariants_82575(struct e1000_hw *hw)
 			break;
 		}
 
-		/* do not change link mode for 100BaseFX */
-		if (dev_spec->eth_flags.e100_base_fx)
-			break;
-
 		/* change current link mode setting */
 		ctrl_ext &= ~E1000_CTRL_EXT_LINK_MODE_MASK;
 
-		if (hw->phy.media_type == e1000_media_type_copper)
+		if (dev_spec->sgmii_active)
 			ctrl_ext |= E1000_CTRL_EXT_LINK_MODE_SGMII;
 		else
 			ctrl_ext |= E1000_CTRL_EXT_LINK_MODE_PCIE_SERDES;
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index c645d9e648e0..fcfbc0407dd9 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -143,7 +143,8 @@ static int igb_get_link_ksettings(struct net_device *netdev,
 	u32 speed;
 	u32 supported, advertising;
 
-	status = rd32(E1000_STATUS);
+	status = pm_runtime_suspended(&adapter->pdev->dev) ?
+		 0 : rd32(E1000_STATUS);
 	if (hw->phy.media_type == e1000_media_type_copper) {
 
 		supported = (SUPPORTED_10baseT_Half |
@@ -181,7 +182,7 @@ static int igb_get_link_ksettings(struct net_device *netdev,
 				advertising &= ~ADVERTISED_1000baseKX_Full;
 			}
 		}
-		if (eth_flags->e100_base_fx) {
+		if (eth_flags->e100_base_fx || eth_flags->e100_base_lx) {
 			supported |= SUPPORTED_100baseT_Full;
 			advertising |= ADVERTISED_100baseT_Full;
 		}
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index a7e52e33c90a..879ade3adefc 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -6205,9 +6205,18 @@ static void igb_reset_task(struct work_struct *work)
 	struct igb_adapter *adapter;
 	adapter = container_of(work, struct igb_adapter, reset_task);
 
+	rtnl_lock();
+	/* If we're already down or resetting, just bail */
+	if (test_bit(__IGB_DOWN, &adapter->state) ||
+	    test_bit(__IGB_RESETTING, &adapter->state)) {
+		rtnl_unlock();
+		return;
+	}
+
 	igb_dump(adapter);
 	netdev_err(adapter->netdev, "Reset adapter\n");
 	igb_reinit_locked(adapter);
+	rtnl_unlock();
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
index 0bd1294ba517..39c5e6fdb72c 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
@@ -2243,7 +2243,7 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw)
 	}
 
 	/* Configure pause time (2 TCs per register) */
-	reg = hw->fc.pause_time * 0x00010001;
+	reg = hw->fc.pause_time * 0x00010001U;
 	for (i = 0; i < (MAX_TRAFFIC_CLASS / 2); i++)
 		IXGBE_WRITE_REG(hw, IXGBE_FCTTV(i), reg);
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
index cc3196ae5aea..636e6e840afa 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
@@ -923,7 +923,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
 		ring->queue_index = txr_idx;
 
 		/* assign ring to adapter */
-		adapter->tx_ring[txr_idx] = ring;
+		WRITE_ONCE(adapter->tx_ring[txr_idx], ring);
 
 		/* update count and index */
 		txr_count--;
@@ -950,7 +950,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
 		set_ring_xdp(ring);
 
 		/* assign ring to adapter */
-		adapter->xdp_ring[xdp_idx] = ring;
+		WRITE_ONCE(adapter->xdp_ring[xdp_idx], ring);
 
 		/* update count and index */
 		xdp_count--;
@@ -993,7 +993,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
 		ring->queue_index = rxr_idx;
 
 		/* assign ring to adapter */
-		adapter->rx_ring[rxr_idx] = ring;
+		WRITE_ONCE(adapter->rx_ring[rxr_idx], ring);
 
 		/* update count and index */
 		rxr_count--;
@@ -1022,13 +1022,13 @@ static void ixgbe_free_q_vector(struct ixgbe_adapter *adapter, int v_idx)
 
 	ixgbe_for_each_ring(ring, q_vector->tx) {
 		if (ring_is_xdp(ring))
-			adapter->xdp_ring[ring->queue_index] = NULL;
+			WRITE_ONCE(adapter->xdp_ring[ring->queue_index], NULL);
 		else
-			adapter->tx_ring[ring->queue_index] = NULL;
+			WRITE_ONCE(adapter->tx_ring[ring->queue_index], NULL);
 	}
 
 	ixgbe_for_each_ring(ring, q_vector->rx)
-		adapter->rx_ring[ring->queue_index] = NULL;
+		WRITE_ONCE(adapter->rx_ring[ring->queue_index], NULL);
 
 	adapter->q_vector[v_idx] = NULL;
 	napi_hash_del(&q_vector->napi);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 7fce21bf9fbb..93857de8261d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2252,7 +2252,8 @@ static void ixgbe_rx_buffer_flip(struct ixgbe_ring *rx_ring,
 	rx_buffer->page_offset ^= truesize;
 #else
 	unsigned int truesize = ring_uses_build_skb(rx_ring) ?
-				SKB_DATA_ALIGN(IXGBE_SKB_PAD + size) :
+				SKB_DATA_ALIGN(IXGBE_SKB_PAD + size) +
+				SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) :
 				SKB_DATA_ALIGN(size);
 
 	rx_buffer->page_offset += truesize;
@@ -5238,7 +5239,7 @@ static void ixgbe_fdir_filter_restore(struct ixgbe_adapter *adapter)
 	struct ixgbe_hw *hw = &adapter->hw;
 	struct hlist_node *node2;
 	struct ixgbe_fdir_filter *filter;
-	u64 action;
+	u8 queue;
 
 	spin_lock(&adapter->fdir_perfect_lock);
 
@@ -5247,17 +5248,34 @@ static void ixgbe_fdir_filter_restore(struct ixgbe_adapter *adapter)
 
 	hlist_for_each_entry_safe(filter, node2,
 				  &adapter->fdir_filter_list, fdir_node) {
-		action = filter->action;
-		if (action != IXGBE_FDIR_DROP_QUEUE && action != 0)
-			action =
-			(action >> ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF) - 1;
+		if (filter->action == IXGBE_FDIR_DROP_QUEUE) {
+			queue = IXGBE_FDIR_DROP_QUEUE;
+		} else {
+			u32 ring = ethtool_get_flow_spec_ring(filter->action);
+			u8 vf = ethtool_get_flow_spec_ring_vf(filter->action);
+
+			if (!vf && (ring >= adapter->num_rx_queues)) {
+				e_err(drv, "FDIR restore failed without VF, ring: %u\n",
+				      ring);
+				continue;
+			} else if (vf &&
+				   ((vf > adapter->num_vfs) ||
+				     ring >= adapter->num_rx_queues_per_pool)) {
+				e_err(drv, "FDIR restore failed with VF, vf: %hhu, ring: %u\n",
+				      vf, ring);
+				continue;
+			}
+
+			/* Map the ring onto the absolute queue index */
+			if (!vf)
+				queue = adapter->rx_ring[ring]->reg_idx;
+			else
+				queue = ((vf - 1) *
+					adapter->num_rx_queues_per_pool) + ring;
+		}
 
 		ixgbe_fdir_write_perfect_filter_82599(hw,
-				&filter->filter,
-				filter->sw_idx,
-				(action == IXGBE_FDIR_DROP_QUEUE) ?
-				IXGBE_FDIR_DROP_QUEUE :
-				adapter->rx_ring[action]->reg_idx);
+				&filter->filter, filter->sw_idx, queue);
 	}
 
 	spin_unlock(&adapter->fdir_perfect_lock);
@@ -7041,7 +7059,10 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
 	}
 
 	for (i = 0; i < adapter->num_rx_queues; i++) {
-		struct ixgbe_ring *rx_ring = adapter->rx_ring[i];
+		struct ixgbe_ring *rx_ring = READ_ONCE(adapter->rx_ring[i]);
+
+		if (!rx_ring)
+			continue;
 		non_eop_descs += rx_ring->rx_stats.non_eop_descs;
 		alloc_rx_page += rx_ring->rx_stats.alloc_rx_page;
 		alloc_rx_page_failed += rx_ring->rx_stats.alloc_rx_page_failed;
@@ -7062,15 +7083,20 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
 	packets = 0;
 	/* gather some stats to the adapter struct that are per queue */
 	for (i = 0; i < adapter->num_tx_queues; i++) {
-		struct ixgbe_ring *tx_ring = adapter->tx_ring[i];
+		struct ixgbe_ring *tx_ring = READ_ONCE(adapter->tx_ring[i]);
+
+		if (!tx_ring)
+			continue;
 		restart_queue += tx_ring->tx_stats.restart_queue;
 		tx_busy += tx_ring->tx_stats.tx_busy;
 		bytes += tx_ring->stats.bytes;
 		packets += tx_ring->stats.packets;
 	}
 	for (i = 0; i < adapter->num_xdp_queues; i++) {
-		struct ixgbe_ring *xdp_ring = adapter->xdp_ring[i];
+		struct ixgbe_ring *xdp_ring = READ_ONCE(adapter->xdp_ring[i]);
 
+		if (!xdp_ring)
+			continue;
 		restart_queue += xdp_ring->tx_stats.restart_queue;
 		tx_busy += xdp_ring->tx_stats.tx_busy;
 		bytes += xdp_ring->stats.bytes;
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index ac6c18821958..e35195a38122 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -2078,11 +2078,6 @@ static int ixgbevf_write_uc_addr_list(struct net_device *netdev)
 	struct ixgbe_hw *hw = &adapter->hw;
 	int count = 0;
 
-	if ((netdev_uc_count(netdev)) > 10) {
-		pr_err("Too many unicast filters - No Space\n");
-		return -ENOSPC;
-	}
-
 	if (!netdev_uc_empty(netdev)) {
 		struct netdev_hw_addr *ha;
 
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 269bd73be1a0..0f4ae3a6e043 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -104,9 +104,11 @@
 #define      MVNETA_TX_IN_PRGRS                  BIT(1)
 #define      MVNETA_TX_FIFO_EMPTY                BIT(8)
 #define MVNETA_RX_MIN_FRAME_SIZE                 0x247c
+/* Only exists on Armada XP and Armada 370 */
 #define MVNETA_SERDES_CFG			 0x24A0
 #define      MVNETA_SGMII_SERDES_PROTO		 0x0cc7
 #define      MVNETA_QSGMII_SERDES_PROTO		 0x0667
+#define      MVNETA_HSGMII_SERDES_PROTO		 0x1107
 #define MVNETA_TYPE_PRIO                         0x24bc
 #define      MVNETA_FORCE_UNI                    BIT(21)
 #define MVNETA_TXQ_CMD_1                         0x24e4
@@ -388,6 +390,8 @@ struct mvneta_pcpu_stats {
 	struct	u64_stats_sync syncp;
 	u64	rx_packets;
 	u64	rx_bytes;
+	u64	rx_dropped;
+	u64	rx_errors;
 	u64	tx_packets;
 	u64	tx_bytes;
 };
@@ -705,6 +709,8 @@ mvneta_get_stats64(struct net_device *dev,
 		struct mvneta_pcpu_stats *cpu_stats;
 		u64 rx_packets;
 		u64 rx_bytes;
+		u64 rx_dropped;
+		u64 rx_errors;
 		u64 tx_packets;
 		u64 tx_bytes;
 
@@ -713,19 +719,20 @@ mvneta_get_stats64(struct net_device *dev,
 			start = u64_stats_fetch_begin_irq(&cpu_stats->syncp);
 			rx_packets = cpu_stats->rx_packets;
 			rx_bytes   = cpu_stats->rx_bytes;
+			rx_dropped = cpu_stats->rx_dropped;
+			rx_errors  = cpu_stats->rx_errors;
 			tx_packets = cpu_stats->tx_packets;
 			tx_bytes   = cpu_stats->tx_bytes;
 		} while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start));
 
 		stats->rx_packets += rx_packets;
 		stats->rx_bytes   += rx_bytes;
+		stats->rx_dropped += rx_dropped;
+		stats->rx_errors  += rx_errors;
 		stats->tx_packets += tx_packets;
 		stats->tx_bytes   += tx_bytes;
 	}
 
-	stats->rx_errors	= dev->stats.rx_errors;
-	stats->rx_dropped	= dev->stats.rx_dropped;
-
 	stats->tx_dropped	= dev->stats.tx_dropped;
 }
 
@@ -1702,8 +1709,14 @@ static u32 mvneta_txq_desc_csum(int l3_offs, int l3_proto,
 static void mvneta_rx_error(struct mvneta_port *pp,
 			    struct mvneta_rx_desc *rx_desc)
 {
+	struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
 	u32 status = rx_desc->status;
 
+	/* update per-cpu counter */
+	u64_stats_update_begin(&stats->syncp);
+	stats->rx_errors++;
+	u64_stats_update_end(&stats->syncp);
+
 	switch (status & MVNETA_RXD_ERR_CODE_MASK) {
 	case MVNETA_RXD_ERR_CRC:
 		netdev_err(pp->dev, "bad rx status %08x (crc error), size=%d\n",
@@ -1964,7 +1977,6 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
 			/* Check errors only for FIRST descriptor */
 			if (rx_status & MVNETA_RXD_ERR_SUMMARY) {
 				mvneta_rx_error(pp, rx_desc);
-				dev->stats.rx_errors++;
 				/* leave the descriptor untouched */
 				continue;
 			}
@@ -1975,11 +1987,17 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
 			skb_size = max(rx_copybreak, rx_header_size);
 			rxq->skb = netdev_alloc_skb_ip_align(dev, skb_size);
 			if (unlikely(!rxq->skb)) {
+				struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
+
 				netdev_err(dev,
 					   "Can't allocate skb on queue %d\n",
 					   rxq->id);
-				dev->stats.rx_dropped++;
 				rxq->skb_alloc_err++;
+
+				u64_stats_update_begin(&stats->syncp);
+				stats->rx_dropped++;
+				u64_stats_update_end(&stats->syncp);
+
 				continue;
 			}
 			copy_size = min(skb_size, rx_bytes);
@@ -2136,7 +2154,6 @@ err_drop_frame_ret_pool:
 			mvneta_bm_pool_put_bp(pp->bm_priv, bm_pool,
 					      rx_desc->buf_phys_addr);
 err_drop_frame:
-			dev->stats.rx_errors++;
 			mvneta_rx_error(pp, rx_desc);
 			/* leave the descriptor untouched */
 			continue;
@@ -2788,11 +2805,10 @@ static int mvneta_poll(struct napi_struct *napi, int budget)
 	/* For the case where the last mvneta_poll did not process all
 	 * RX packets
 	 */
-	rx_queue = fls(((cause_rx_tx >> 8) & 0xff));
-
 	cause_rx_tx |= pp->neta_armada3700 ? pp->cause_rx_tx :
 		port->cause_rx_tx;
 
+	rx_queue = fls(((cause_rx_tx >> 8) & 0xff));
 	if (rx_queue) {
 		rx_queue = rx_queue - 1;
 		if (pp->bm_priv)
@@ -3149,26 +3165,60 @@ static int mvneta_setup_txqs(struct mvneta_port *pp)
 	return 0;
 }
 
-static int mvneta_comphy_init(struct mvneta_port *pp)
+static int mvneta_comphy_init(struct mvneta_port *pp, phy_interface_t interface)
 {
 	int ret;
 
-	if (!pp->comphy)
-		return 0;
-
-	ret = phy_set_mode_ext(pp->comphy, PHY_MODE_ETHERNET,
-			       pp->phy_interface);
+	ret = phy_set_mode_ext(pp->comphy, PHY_MODE_ETHERNET, interface);
 	if (ret)
 		return ret;
 
 	return phy_power_on(pp->comphy);
 }
 
+static int mvneta_config_interface(struct mvneta_port *pp,
+				   phy_interface_t interface)
+{
+	int ret = 0;
+
+	if (pp->comphy) {
+		if (interface == PHY_INTERFACE_MODE_SGMII ||
+		    interface == PHY_INTERFACE_MODE_1000BASEX ||
+		    interface == PHY_INTERFACE_MODE_2500BASEX) {
+			ret = mvneta_comphy_init(pp, interface);
+		}
+	} else {
+		switch (interface) {
+		case PHY_INTERFACE_MODE_QSGMII:
+			mvreg_write(pp, MVNETA_SERDES_CFG,
+				    MVNETA_QSGMII_SERDES_PROTO);
+			break;
+
+		case PHY_INTERFACE_MODE_SGMII:
+		case PHY_INTERFACE_MODE_1000BASEX:
+			mvreg_write(pp, MVNETA_SERDES_CFG,
+				    MVNETA_SGMII_SERDES_PROTO);
+			break;
+
+		case PHY_INTERFACE_MODE_2500BASEX:
+			mvreg_write(pp, MVNETA_SERDES_CFG,
+				    MVNETA_HSGMII_SERDES_PROTO);
+			break;
+		default:
+			break;
+		}
+	}
+
+	pp->phy_interface = interface;
+
+	return ret;
+}
+
 static void mvneta_start_dev(struct mvneta_port *pp)
 {
 	int cpu;
 
-	WARN_ON(mvneta_comphy_init(pp));
+	WARN_ON(mvneta_config_interface(pp, pp->phy_interface));
 
 	mvneta_max_rx_size_set(pp, pp->pkt_size);
 	mvneta_txq_max_tx_size_set(pp, pp->pkt_size);
@@ -3538,17 +3588,13 @@ static void mvneta_mac_config(struct net_device *ndev, unsigned int mode,
 	/* When at 2.5G, the link partner can send frames with shortened
 	 * preambles.
 	 */
-	if (state->speed == SPEED_2500)
+	if (state->interface == PHY_INTERFACE_MODE_2500BASEX)
 		new_ctrl4 |= MVNETA_GMAC4_SHORT_PREAMBLE_ENABLE;
 
-	if (pp->comphy && pp->phy_interface != state->interface &&
-	    (state->interface == PHY_INTERFACE_MODE_SGMII ||
-	     state->interface == PHY_INTERFACE_MODE_1000BASEX ||
-	     state->interface == PHY_INTERFACE_MODE_2500BASEX)) {
-		pp->phy_interface = state->interface;
-
-		WARN_ON(phy_power_off(pp->comphy));
-		WARN_ON(mvneta_comphy_init(pp));
+	if (pp->phy_interface != state->interface) {
+		if (pp->comphy)
+			WARN_ON(phy_power_off(pp->comphy));
+		WARN_ON(mvneta_config_interface(pp, state->interface));
 	}
 
 	if (new_ctrl0 != gmac_ctrl0)
@@ -4447,12 +4493,10 @@ static int mvneta_port_power_up(struct mvneta_port *pp, int phy_mode)
 	/* MAC Cause register should be cleared */
 	mvreg_write(pp, MVNETA_UNIT_INTR_CAUSE, 0);
 
-	if (phy_mode == PHY_INTERFACE_MODE_QSGMII)
-		mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_QSGMII_SERDES_PROTO);
-	else if (phy_mode == PHY_INTERFACE_MODE_SGMII ||
-		 phy_interface_mode_is_8023z(phy_mode))
-		mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_SGMII_SERDES_PROTO);
-	else if (!phy_interface_mode_is_rgmii(phy_mode))
+	if (phy_mode != PHY_INTERFACE_MODE_QSGMII &&
+	    phy_mode != PHY_INTERFACE_MODE_SGMII &&
+	    !phy_interface_mode_is_8023z(phy_mode) &&
+	    !phy_interface_mode_is_rgmii(phy_mode))
 		return -EINVAL;
 
 	return 0;
@@ -4637,10 +4681,10 @@ static int mvneta_probe(struct platform_device *pdev)
 	if (err < 0)
 		goto err_netdev;
 
-	err = mvneta_port_power_up(pp, phy_mode);
+	err = mvneta_port_power_up(pp, pp->phy_interface);
 	if (err < 0) {
 		dev_err(&pdev->dev, "can't power up port\n");
-		goto err_netdev;
+		return err;
 	}
 
 	/* Armada3700 network controller does not support per-cpu
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index fb06c0aa620a..e4d26092745a 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -1299,6 +1299,9 @@ int mvpp2_ethtool_cls_rule_del(struct mvpp2_port *port,
 	struct mvpp2_ethtool_fs *efs;
 	int ret;
 
+	if (info->fs.location >= MVPP2_N_RFS_ENTRIES_PER_FLOW)
+		return -EINVAL;
+
 	efs = port->rfs_rules[info->fs.location];
 	if (!efs)
 		return -EINVAL;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/common.h b/drivers/net/ethernet/marvell/octeontx2/af/common.h
index d414e0304523..9980598fe79e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/common.h
@@ -43,7 +43,7 @@ struct qmem {
 	void            *base;
 	dma_addr_t	iova;
 	int		alloc_sz;
-	u8		entry_sz;
+	u16		entry_sz;
 	u8		align;
 	u32		qsize;
 };
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 7e88446ac97a..0b88fb96503f 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -203,7 +203,7 @@ io_error:
 
 static inline u16 gm_phy_read(struct sky2_hw *hw, unsigned port, u16 reg)
 {
-	u16 v;
+	u16 v = 0;
 	__gm_phy_read(hw, port, reg, &v);
 	return v;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 36a92b19e613..82ecebdbeedb 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -43,6 +43,7 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/moduleparam.h>
+#include <linux/indirect_call_wrapper.h>
 
 #include "mlx4_en.h"
 
@@ -261,6 +262,10 @@ static void mlx4_en_stamp_wqe(struct mlx4_en_priv *priv,
 	}
 }
 
+INDIRECT_CALLABLE_DECLARE(u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
+						   struct mlx4_en_tx_ring *ring,
+						   int index, u64 timestamp,
+						   int napi_mode));
 
 u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
 			 struct mlx4_en_tx_ring *ring,
@@ -329,6 +334,11 @@ u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
 	return tx_info->nr_txbb;
 }
 
+INDIRECT_CALLABLE_DECLARE(u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv,
+						      struct mlx4_en_tx_ring *ring,
+						      int index, u64 timestamp,
+						      int napi_mode));
+
 u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv,
 			    struct mlx4_en_tx_ring *ring,
 			    int index, u64 timestamp,
@@ -449,7 +459,9 @@ bool mlx4_en_process_tx_cq(struct net_device *dev,
 				timestamp = mlx4_en_get_cqe_ts(cqe);
 
 			/* free next descriptor */
-			last_nr_txbb = ring->free_tx_desc(
+			last_nr_txbb = INDIRECT_CALL_2(ring->free_tx_desc,
+						       mlx4_en_free_tx_desc,
+						       mlx4_en_recycle_tx_desc,
 					priv, ring, ring_index,
 					timestamp, napi_budget);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 6e501af0e532..f6ff9620a137 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -2734,7 +2734,7 @@ void mlx4_opreq_action(struct work_struct *work)
 		if (err) {
 			mlx4_err(dev, "Failed to retrieve required operation: %d\n",
 				 err);
-			return;
+			goto out;
 		}
 		MLX4_GET(modifier, outbox, GET_OP_REQ_MODIFIER_OFFSET);
 		MLX4_GET(token, outbox, GET_OP_REQ_TOKEN_OFFSET);
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 1f6e16d5ea6b..260229138208 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2539,6 +2539,7 @@ static int mlx4_allocate_default_counters(struct mlx4_dev *dev)
 
 		if (!err || err == -ENOSPC) {
 			priv->def_counter[port] = idx;
+			err = 0;
 		} else if (err == -ENOENT) {
 			err = 0;
 			continue;
@@ -2589,7 +2590,8 @@ int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx, u8 usage)
 				   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
 		if (!err)
 			*idx = get_param_l(&out_param);
-
+		if (WARN_ON(err == -ENOSPC))
+			err = -EINVAL;
 		return err;
 	}
 	return __mlx4_counter_alloc(dev, idx);
@@ -4310,12 +4312,14 @@ end:
 static void mlx4_shutdown(struct pci_dev *pdev)
 {
 	struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev);
+	struct mlx4_dev *dev = persist->dev;
 
 	mlx4_info(persist->dev, "mlx4_shutdown was called\n");
 	mutex_lock(&persist->interface_state_mutex);
 	if (persist->interface_state & MLX4_INTERFACE_STATE_UP)
 		mlx4_unload_one(pdev);
 	mutex_unlock(&persist->interface_state_mutex);
+	mlx4_pci_disable_device(dev);
 }
 
 static const struct pci_error_handlers mlx4_err_handler = {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index e94686c42000..6c2b67efcd3d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -857,6 +857,7 @@ static void cmd_work_handler(struct work_struct *work)
 	int alloc_ret;
 	int cmd_mode;
 
+	complete(&ent->handling);
 	sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem;
 	down(sem);
 	if (!ent->page_queue) {
@@ -884,7 +885,6 @@ static void cmd_work_handler(struct work_struct *work)
 	}
 
 	cmd->ent_arr[ent->idx] = ent;
-	set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state);
 	lay = get_inst(cmd, ent->idx);
 	ent->lay = lay;
 	memset(lay, 0, sizeof(*lay));
@@ -906,6 +906,7 @@ static void cmd_work_handler(struct work_struct *work)
 
 	if (ent->callback)
 		schedule_delayed_work(&ent->cb_timeout_work, cb_timeout);
+	set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state);
 
 	/* Skip sending command to fw if internal error */
 	if (pci_channel_offline(dev->pdev) ||
@@ -918,6 +919,10 @@ static void cmd_work_handler(struct work_struct *work)
 		MLX5_SET(mbox_out, ent->out, syndrome, drv_synd);
 
 		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
+		/* no doorbell, no need to keep the entry */
+		free_ent(cmd, ent->idx);
+		if (ent->callback)
+			free_cmd(ent);
 		return;
 	}
 
@@ -970,6 +975,11 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 	struct mlx5_cmd *cmd = &dev->cmd;
 	int err;
 
+	if (!wait_for_completion_timeout(&ent->handling, timeout) &&
+	    cancel_work_sync(&ent->work)) {
+		ent->ret = -ECANCELED;
+		goto out_err;
+	}
 	if (cmd->mode == CMD_MODE_POLLING || ent->polling) {
 		wait_for_completion(&ent->done);
 	} else if (!wait_for_completion_timeout(&ent->done, timeout)) {
@@ -977,12 +987,17 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
 	}
 
+out_err:
 	err = ent->ret;
 
 	if (err == -ETIMEDOUT) {
 		mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n",
 			       mlx5_command_str(msg_to_opcode(ent->in)),
 			       msg_to_opcode(ent->in));
+	} else if (err == -ECANCELED) {
+		mlx5_core_warn(dev, "%s(0x%x) canceled on out of queue timeout.\n",
+			       mlx5_command_str(msg_to_opcode(ent->in)),
+			       msg_to_opcode(ent->in));
 	}
 	mlx5_core_dbg(dev, "err %d, delivery status %s(%d)\n",
 		      err, deliv_status_to_str(ent->status), ent->status);
@@ -1018,6 +1033,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 	ent->token = token;
 	ent->polling = force_polling;
 
+	init_completion(&ent->handling);
 	if (!callback)
 		init_completion(&ent->done);
 
@@ -1037,6 +1053,8 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 	err = wait_func(dev, ent);
 	if (err == -ETIMEDOUT)
 		goto out;
+	if (err == -ECANCELED)
+		goto out_free;
 
 	ds = ent->ts2 - ent->ts1;
 	op = MLX5_GET(mbox_in, in->first.data, opcode);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
index 6999f4486e9e..7b43d88284ae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -797,7 +797,7 @@ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev)
 		return NULL;
 	}
 
-	tracer = kzalloc(sizeof(*tracer), GFP_KERNEL);
+	tracer = kvzalloc(sizeof(*tracer), GFP_KERNEL);
 	if (!tracer)
 		return ERR_PTR(-ENOMEM);
 
@@ -843,7 +843,7 @@ destroy_workqueue:
 	tracer->dev = NULL;
 	destroy_workqueue(tracer->work_queue);
 free_tracer:
-	kfree(tracer);
+	kvfree(tracer);
 	return ERR_PTR(err);
 }
 
@@ -921,7 +921,7 @@ void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer)
 	mlx5_fw_tracer_destroy_log_buf(tracer);
 	flush_workqueue(tracer->work_queue);
 	destroy_workqueue(tracer->work_queue);
-	kfree(tracer);
+	kvfree(tracer);
 }
 
 static int fw_tracer_event(struct notifier_block *nb, unsigned long action, void *data)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index cc227a7aa79f..f38ce8422238 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1022,7 +1022,7 @@ void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq);
 int mlx5e_create_indirect_rqt(struct mlx5e_priv *priv);
 
 int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc);
-void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc);
+void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv);
 
 int mlx5e_create_direct_rqts(struct mlx5e_priv *priv);
 void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
index be5961ff24cc..ef78be441d35 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -113,6 +113,22 @@ enum {
 #endif
 };
 
+#define MLX5E_TTC_NUM_GROUPS	3
+#define MLX5E_TTC_GROUP1_SIZE	(BIT(3) + MLX5E_NUM_TUNNEL_TT)
+#define MLX5E_TTC_GROUP2_SIZE	 BIT(1)
+#define MLX5E_TTC_GROUP3_SIZE	 BIT(0)
+#define MLX5E_TTC_TABLE_SIZE	(MLX5E_TTC_GROUP1_SIZE +\
+				 MLX5E_TTC_GROUP2_SIZE +\
+				 MLX5E_TTC_GROUP3_SIZE)
+
+#define MLX5E_INNER_TTC_NUM_GROUPS	3
+#define MLX5E_INNER_TTC_GROUP1_SIZE	BIT(3)
+#define MLX5E_INNER_TTC_GROUP2_SIZE	BIT(1)
+#define MLX5E_INNER_TTC_GROUP3_SIZE	BIT(0)
+#define MLX5E_INNER_TTC_TABLE_SIZE	(MLX5E_INNER_TTC_GROUP1_SIZE +\
+					 MLX5E_INNER_TTC_GROUP2_SIZE +\
+					 MLX5E_INNER_TTC_GROUP3_SIZE)
+
 #ifdef CONFIG_MLX5_EN_RXNFC
 
 struct mlx5e_ethtool_table {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
index f777994f3005..21ce285b0572 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
@@ -77,11 +77,26 @@ static const u32 mlx5e_ext_link_speed[MLX5E_EXT_LINK_MODES_NUMBER] = {
 	[MLX5E_400GAUI_8]			= 400000,
 };
 
+bool mlx5e_ptys_ext_supported(struct mlx5_core_dev *mdev)
+{
+	struct mlx5e_port_eth_proto eproto;
+	int err;
+
+	if (MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet))
+		return true;
+
+	err = mlx5_port_query_eth_proto(mdev, 1, true, &eproto);
+	if (err)
+		return false;
+
+	return !!eproto.cap;
+}
+
 static void mlx5e_port_get_speed_arr(struct mlx5_core_dev *mdev,
 				     const u32 **arr, u32 *size,
 				     bool force_legacy)
 {
-	bool ext = force_legacy ? false : MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	bool ext = force_legacy ? false : mlx5e_ptys_ext_supported(mdev);
 
 	*size = ext ? ARRAY_SIZE(mlx5e_ext_link_speed) :
 		      ARRAY_SIZE(mlx5e_link_speed);
@@ -176,7 +191,7 @@ int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 	bool ext;
 	int err;
 
-	ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	ext = mlx5e_ptys_ext_supported(mdev);
 	err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto);
 	if (err)
 		goto out;
@@ -204,7 +219,7 @@ int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 	int err;
 	int i;
 
-	ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	ext = mlx5e_ptys_ext_supported(mdev);
 	err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto);
 	if (err)
 		return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
index 4a7f4497692b..e196888f7056 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
@@ -54,7 +54,7 @@ int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
 int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
 u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed,
 			       bool force_legacy);
-
+bool mlx5e_ptys_ext_supported(struct mlx5_core_dev *mdev);
 int mlx5e_port_query_pbmc(struct mlx5_core_dev *mdev, void *out);
 int mlx5e_port_set_pbmc(struct mlx5_core_dev *mdev, void *in);
 int mlx5e_port_query_priority2buffer(struct mlx5_core_dev *mdev, u8 *buffer);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 6f1216dc31da..267fd4ad8727 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -199,7 +199,7 @@ static void mlx5e_ethtool_get_speed_arr(struct mlx5_core_dev *mdev,
 					struct ptys2ethtool_config **arr,
 					u32 *size)
 {
-	bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	bool ext = mlx5e_ptys_ext_supported(mdev);
 
 	*arr = ext ? ptys2ext_ethtool_table : ptys2legacy_ethtool_table;
 	*size = ext ? ARRAY_SIZE(ptys2ext_ethtool_table) :
@@ -856,7 +856,7 @@ static void get_lp_advertising(struct mlx5_core_dev *mdev, u32 eth_proto_lp,
 			       struct ethtool_link_ksettings *link_ksettings)
 {
 	unsigned long *lp_advertising = link_ksettings->link_modes.lp_advertising;
-	bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	bool ext = mlx5e_ptys_ext_supported(mdev);
 
 	ptys2ethtool_adver_link(lp_advertising, eth_proto_lp, ext);
 }
@@ -885,7 +885,7 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
 			   __func__, err);
 		goto err_query_regs;
 	}
-	ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	ext = !!MLX5_GET_ETH_PROTO(ptys_reg, out, true, eth_proto_capability);
 	eth_proto_cap    = MLX5_GET_ETH_PROTO(ptys_reg, out, ext,
 					      eth_proto_capability);
 	eth_proto_admin  = MLX5_GET_ETH_PROTO(ptys_reg, out, ext,
@@ -1000,24 +1000,17 @@ static bool ext_link_mode_requested(const unsigned long *adver)
 {
 #define MLX5E_MIN_PTYS_EXT_LINK_MODE_BIT ETHTOOL_LINK_MODE_50000baseKR_Full_BIT
 	int size = __ETHTOOL_LINK_MODE_MASK_NBITS - MLX5E_MIN_PTYS_EXT_LINK_MODE_BIT;
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(modes);
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(modes) = {0,};
 
 	bitmap_set(modes, MLX5E_MIN_PTYS_EXT_LINK_MODE_BIT, size);
 	return bitmap_intersects(modes, adver, __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
 
-static bool ext_speed_requested(u32 speed)
-{
-#define MLX5E_MAX_PTYS_LEGACY_SPEED 100000
-	return !!(speed > MLX5E_MAX_PTYS_LEGACY_SPEED);
-}
-
-static bool ext_requested(u8 autoneg, const unsigned long *adver, u32 speed)
+static bool ext_requested(u8 autoneg, const unsigned long *adver, bool ext_supported)
 {
 	bool ext_link_mode = ext_link_mode_requested(adver);
-	bool ext_speed = ext_speed_requested(speed);
 
-	return  autoneg == AUTONEG_ENABLE ? ext_link_mode : ext_speed;
+	return  autoneg == AUTONEG_ENABLE ? ext_link_mode : ext_supported;
 }
 
 int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
@@ -1044,8 +1037,8 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 	autoneg = link_ksettings->base.autoneg;
 	speed = link_ksettings->base.speed;
 
-	ext = ext_requested(autoneg, adver, speed),
-	ext_supported = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	ext_supported = mlx5e_ptys_ext_supported(mdev);
+	ext = ext_requested(autoneg, adver, ext_supported);
 	if (!ext_supported && ext)
 		return -EOPNOTSUPP;
 
@@ -1540,6 +1533,10 @@ static int mlx5e_set_fecparam(struct net_device *netdev,
 	int mode;
 	int err;
 
+	if (bitmap_weight((unsigned long *)&fecparam->fec,
+			  ETHTOOL_FEC_BASER_BIT + 1) > 1)
+		return -EOPNOTSUPP;
+
 	for (mode = 0; mode < ARRAY_SIZE(pplm_fec_2_ethtool); mode++) {
 		if (!(pplm_fec_2_ethtool[mode] & fecparam->fec))
 			continue;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index 76cc10e44080..8a37efb26d68 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -854,22 +854,6 @@ del_rules:
 	return err;
 }
 
-#define MLX5E_TTC_NUM_GROUPS	3
-#define MLX5E_TTC_GROUP1_SIZE	(BIT(3) + MLX5E_NUM_TUNNEL_TT)
-#define MLX5E_TTC_GROUP2_SIZE	 BIT(1)
-#define MLX5E_TTC_GROUP3_SIZE	 BIT(0)
-#define MLX5E_TTC_TABLE_SIZE	(MLX5E_TTC_GROUP1_SIZE +\
-				 MLX5E_TTC_GROUP2_SIZE +\
-				 MLX5E_TTC_GROUP3_SIZE)
-
-#define MLX5E_INNER_TTC_NUM_GROUPS	3
-#define MLX5E_INNER_TTC_GROUP1_SIZE	BIT(3)
-#define MLX5E_INNER_TTC_GROUP2_SIZE	BIT(1)
-#define MLX5E_INNER_TTC_GROUP3_SIZE	BIT(0)
-#define MLX5E_INNER_TTC_TABLE_SIZE	(MLX5E_INNER_TTC_GROUP1_SIZE +\
-					 MLX5E_INNER_TTC_GROUP2_SIZE +\
-					 MLX5E_INNER_TTC_GROUP3_SIZE)
-
 static int mlx5e_create_ttc_table_groups(struct mlx5e_ttc_table *ttc,
 					 bool use_ipv)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 813baf5e6aa2..392d14031362 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -438,7 +438,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 		err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->mpwqe.wq,
 					&rq->wq_ctrl);
 		if (err)
-			return err;
+			goto err_rq_wq_destroy;
 
 		rq->mpwqe.wq.db = &rq->mpwqe.wq.db[MLX5_RCV_DBR];
 
@@ -483,7 +483,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 		err = mlx5_wq_cyc_create(mdev, &rqp->wq, rqc_wq, &rq->wqe.wq,
 					 &rq->wq_ctrl);
 		if (err)
-			return err;
+			goto err_rq_wq_destroy;
 
 		rq->wqe.wq.db = &rq->wqe.wq.db[MLX5_RCV_DBR];
 
@@ -2626,7 +2626,8 @@ void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
 		mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in, inlen);
 	}
 
-	if (!mlx5e_tunnel_inner_ft_supported(priv->mdev))
+	/* Verify inner tirs resources allocated */
+	if (!priv->inner_indir_tir[0].tirn)
 		return;
 
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
@@ -2888,6 +2889,25 @@ void mlx5e_timestamp_init(struct mlx5e_priv *priv)
 	priv->tstamp.rx_filter = HWTSTAMP_FILTER_NONE;
 }
 
+static void mlx5e_modify_admin_state(struct mlx5_core_dev *mdev,
+				     enum mlx5_port_status state)
+{
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
+	int vport_admin_state;
+
+	mlx5_set_port_admin_status(mdev, state);
+
+	if (!MLX5_ESWITCH_MANAGER(mdev) ||  mlx5_eswitch_mode(esw) == SRIOV_OFFLOADS)
+		return;
+
+	if (state == MLX5_PORT_UP)
+		vport_admin_state = MLX5_VPORT_ADMIN_STATE_AUTO;
+	else
+		vport_admin_state = MLX5_VPORT_ADMIN_STATE_DOWN;
+
+	mlx5_eswitch_set_vport_state(esw, MLX5_VPORT_UPLINK, vport_admin_state);
+}
+
 int mlx5e_open_locked(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -2920,7 +2940,7 @@ int mlx5e_open(struct net_device *netdev)
 	mutex_lock(&priv->state_lock);
 	err = mlx5e_open_locked(netdev);
 	if (!err)
-		mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_UP);
+		mlx5e_modify_admin_state(priv->mdev, MLX5_PORT_UP);
 	mutex_unlock(&priv->state_lock);
 
 	if (mlx5_vxlan_allowed(priv->mdev->vxlan))
@@ -2957,7 +2977,7 @@ int mlx5e_close(struct net_device *netdev)
 		return -ENODEV;
 
 	mutex_lock(&priv->state_lock);
-	mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_DOWN);
+	mlx5e_modify_admin_state(priv->mdev, MLX5_PORT_DOWN);
 	err = mlx5e_close_locked(netdev);
 	mutex_unlock(&priv->state_lock);
 
@@ -3234,14 +3254,15 @@ err_destroy_ch_tirs:
 	return err;
 }
 
-void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc)
+void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv)
 {
 	int i;
 
 	for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++)
 		mlx5e_destroy_tir(priv->mdev, &priv->indir_tir[i]);
 
-	if (!inner_ttc || !mlx5e_tunnel_inner_ft_supported(priv->mdev))
+	/* Verify inner tirs resources allocated */
+	if (!priv->inner_indir_tir[0].tirn)
 		return;
 
 	for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++)
@@ -3419,7 +3440,12 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	struct mlx5e_vport_stats *vstats = &priv->stats.vport;
 	struct mlx5e_pport_stats *pstats = &priv->stats.pport;
 
-	if (!mlx5e_monitor_counter_supported(priv)) {
+	/* In switchdev mode, monitor counters doesn't monitor
+	 * rx/tx stats of 802_3. The update stats mechanism
+	 * should keep the 802_3 layout counters updated
+	 */
+	if (!mlx5e_monitor_counter_supported(priv) ||
+	    mlx5e_is_uplink_rep(priv)) {
 		/* update HW stats in background for next time */
 		mlx5e_queue_update_stats(priv);
 	}
@@ -4841,7 +4867,7 @@ err_destroy_flow_steering:
 err_destroy_direct_tirs:
 	mlx5e_destroy_direct_tirs(priv);
 err_destroy_indirect_tirs:
-	mlx5e_destroy_indirect_tirs(priv, true);
+	mlx5e_destroy_indirect_tirs(priv);
 err_destroy_direct_rqts:
 	mlx5e_destroy_direct_rqts(priv);
 err_destroy_indirect_rqts:
@@ -4858,7 +4884,7 @@ static void mlx5e_cleanup_nic_rx(struct mlx5e_priv *priv)
 	mlx5e_tc_nic_cleanup(priv);
 	mlx5e_destroy_flow_steering(priv);
 	mlx5e_destroy_direct_tirs(priv);
-	mlx5e_destroy_indirect_tirs(priv, true);
+	mlx5e_destroy_indirect_tirs(priv);
 	mlx5e_destroy_direct_rqts(priv);
 	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
 	mlx5e_close_drop_rq(&priv->drop_rq);
@@ -4891,7 +4917,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 
 	/* Marking the link as currently not needed by the Driver */
 	if (!netif_running(netdev))
-		mlx5_set_port_admin_status(mdev, MLX5_PORT_DOWN);
+		mlx5e_modify_admin_state(mdev, MLX5_PORT_DOWN);
 
 	mlx5e_set_netdev_mtu_boundaries(priv);
 	mlx5e_set_dev_port_mtu(priv);
@@ -5064,6 +5090,8 @@ err_cleanup_tx:
 	profile->cleanup_tx(priv);
 
 out:
+	set_bit(MLX5E_STATE_DESTROYING, &priv->state);
+	cancel_work_sync(&priv->update_stats_work);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 2f406b161bcf..e6515fcb548b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1557,7 +1557,7 @@ err_destroy_ttc_table:
 err_destroy_direct_tirs:
 	mlx5e_destroy_direct_tirs(priv);
 err_destroy_indirect_tirs:
-	mlx5e_destroy_indirect_tirs(priv, false);
+	mlx5e_destroy_indirect_tirs(priv);
 err_destroy_direct_rqts:
 	mlx5e_destroy_direct_rqts(priv);
 err_destroy_indirect_rqts:
@@ -1574,7 +1574,7 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
 	mlx5_del_flow_rules(rpriv->vport_rx_rule);
 	mlx5e_destroy_ttc_table(priv, &priv->fs.ttc);
 	mlx5e_destroy_direct_tirs(priv);
-	mlx5e_destroy_indirect_tirs(priv, false);
+	mlx5e_destroy_indirect_tirs(priv);
 	mlx5e_destroy_direct_rqts(priv);
 	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
 	mlx5e_close_drop_rq(&priv->drop_rq);
@@ -1692,6 +1692,8 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
 	INIT_WORK(&rpriv->uplink_priv.reoffload_flows_work,
 		  mlx5e_tc_reoffload_flows_work);
 
+	mlx5_modify_vport_admin_state(mdev, MLX5_VPORT_STATE_OP_MOD_UPLINK,
+				      0, 0, MLX5_VPORT_ADMIN_STATE_AUTO);
 	mlx5_lag_add(mdev, netdev);
 	priv->events_nb.notifier_call = uplink_rep_async_event;
 	mlx5_notifier_register(mdev, &priv->events_nb);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 6c0491abf6e2..090ab8f51962 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1352,6 +1352,7 @@ out:
 
 #ifdef CONFIG_MLX5_CORE_IPOIB
 
+#define MLX5_IB_GRH_SGID_OFFSET 8
 #define MLX5_IB_GRH_DGID_OFFSET 24
 #define MLX5_GID_SIZE           16
 
@@ -1365,6 +1366,7 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
 	struct net_device *netdev;
 	struct mlx5e_priv *priv;
 	char *pseudo_header;
+	u32 flags_rqpn;
 	u32 qpn;
 	u8 *dgid;
 	u8 g;
@@ -1386,7 +1388,8 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
 	tstamp = &priv->tstamp;
 	stats = &priv->channel_stats[rq->ix].rq;
 
-	g = (be32_to_cpu(cqe->flags_rqpn) >> 28) & 3;
+	flags_rqpn = be32_to_cpu(cqe->flags_rqpn);
+	g = (flags_rqpn >> 28) & 3;
 	dgid = skb->data + MLX5_IB_GRH_DGID_OFFSET;
 	if ((!g) || dgid[0] != 0xff)
 		skb->pkt_type = PACKET_HOST;
@@ -1395,9 +1398,15 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
 	else
 		skb->pkt_type = PACKET_MULTICAST;
 
-	/* TODO: IB/ipoib: Allow mcast packets from other VFs
-	 * 68996a6e760e5c74654723eeb57bf65628ae87f4
+	/* Drop packets that this interface sent, ie multicast packets
+	 * that the HCA has replicated.
 	 */
+	if (g && (qpn == (flags_rqpn & 0xffffff)) &&
+	    (memcmp(netdev->dev_addr + 4, skb->data + MLX5_IB_GRH_SGID_OFFSET,
+		    MLX5_GID_SIZE) == 0)) {
+		skb->dev = NULL;
+		return;
+	}
 
 	skb_pull(skb, MLX5_IB_GRH_BYTES);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 483d321d2151..d12eb51e9d37 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -220,6 +220,9 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 			s->tx_tls_resync_bytes	+= sq_stats->tls_resync_bytes;
 #endif
 			s->tx_cqes		+= sq_stats->cqes;
+
+			/* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=92657 */
+			barrier();
 		}
 	}
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 57f738a0124a..235d981bd90f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -439,7 +439,7 @@ static void mlx5e_hairpin_set_ttc_params(struct mlx5e_hairpin *hp,
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++)
 		ttc_params->indir_tirn[tt] = hp->indir_tirn[tt];
 
-	ft_attr->max_fte = MLX5E_NUM_TT;
+	ft_attr->max_fte = MLX5E_TTC_TABLE_SIZE;
 	ft_attr->level = MLX5E_TC_TTC_FT_LEVEL;
 	ft_attr->prio = MLX5E_TC_PRIO;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 47826a35b8b6..cbcd7eb86bc2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -591,7 +591,8 @@ void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq)
 {
 	struct mlx5e_tx_wqe_info *wi;
 	struct sk_buff *skb;
-	u16 ci;
+	u32 nbytes = 0;
+	u16 ci, npkts = 0;
 	int i;
 
 	while (sq->cc != sq->pc) {
@@ -612,8 +613,12 @@ void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq)
 		}
 
 		dev_kfree_skb_any(skb);
+		npkts++;
+		nbytes += wi->num_bytes;
 		sq->cc += wi->num_wqebbs;
 	}
+
+	netdev_tx_completed_queue(sq->txq, npkts, nbytes);
 }
 
 #ifdef CONFIG_MLX5_CORE_IPOIB
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 580292749ad6..3fcc53a6b2dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1957,6 +1957,8 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw,
 				 u16 vport, int link_state)
 {
 	struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
+	int opmod = MLX5_VPORT_STATE_OP_MOD_ESW_VPORT;
+	int other_vport = 1;
 	int err = 0;
 
 	if (!ESW_ALLOWED(esw))
@@ -1964,15 +1966,17 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw,
 	if (IS_ERR(evport))
 		return PTR_ERR(evport);
 
+	if (vport == MLX5_VPORT_UPLINK) {
+		opmod = MLX5_VPORT_STATE_OP_MOD_UPLINK;
+		other_vport = 0;
+		vport = 0;
+	}
 	mutex_lock(&esw->state_lock);
 
-	err = mlx5_modify_vport_admin_state(esw->dev,
-					    MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
-					    vport, 1, link_state);
+	err = mlx5_modify_vport_admin_state(esw->dev, opmod, vport, other_vport, link_state);
 	if (err) {
-		mlx5_core_warn(esw->dev,
-			       "Failed to set vport %d link state, err = %d",
-			       vport, err);
+		mlx5_core_warn(esw->dev, "Failed to set vport %d link state, opmod = %d, err = %d",
+			       vport, opmod, err);
 		goto unlock;
 	}
 
@@ -2181,25 +2185,17 @@ out:
 
 int mlx5_eswitch_get_vepa(struct mlx5_eswitch *esw, u8 *setting)
 {
-	int err = 0;
-
 	if (!esw)
 		return -EOPNOTSUPP;
 
 	if (!ESW_ALLOWED(esw))
 		return -EPERM;
 
-	mutex_lock(&esw->state_lock);
-	if (esw->mode != SRIOV_LEGACY) {
-		err = -EOPNOTSUPP;
-		goto out;
-	}
+	if (esw->mode != SRIOV_LEGACY)
+		return -EOPNOTSUPP;
 
 	*setting = esw->fdb_table.legacy.vepa_uplink_rule ? 1 : 0;
-
-out:
-	mutex_unlock(&esw->state_lock);
-	return err;
+	return 0;
 }
 
 int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index d043d6f9797d..5df1759b2b9e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -498,6 +498,8 @@ static inline void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) {}
 static inline int  mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) { return 0; }
 static inline void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw) {}
 static inline bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0, struct mlx5_core_dev *dev1) { return true; }
+static inline
+int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, u16 vport, int link_state) { return 0; }
 
 #define FDB_MAX_CHAIN 1
 #define FDB_SLOW_PATH_CHAIN (FDB_MAX_CHAIN + 1)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index aa093c8a498b..777658070d13 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -759,7 +759,7 @@ out:
  */
 #define ESW_SIZE (16 * 1024 * 1024)
 const unsigned int ESW_POOLS[4] = { 4 * 1024 * 1024, 1 * 1024 * 1024,
-				    64 * 1024, 4 * 1024 };
+				    64 * 1024, 128 };
 
 static int
 get_sz_from_pool(struct mlx5_eswitch *esw)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index a81e8d2168d8..c7cab9e79cbd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -346,8 +346,10 @@ int mlx5_events_init(struct mlx5_core_dev *dev)
 	events->dev = dev;
 	dev->priv.events = events;
 	events->wq = create_singlethread_workqueue("mlx5_events");
-	if (!events->wq)
+	if (!events->wq) {
+		kfree(events);
 		return -ENOMEM;
+	}
 	INIT_WORK(&events->pcie_core_work, mlx5_pcie_event);
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
index 52c47d3dd5a5..f7d46393c1a2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
@@ -848,6 +848,7 @@ void mlx5_fpga_ipsec_delete_sa_ctx(void *context)
 	mutex_lock(&fpga_xfrm->lock);
 	if (!--fpga_xfrm->num_rules) {
 		mlx5_fpga_ipsec_release_sa_ctx(fpga_xfrm->sa_ctx);
+		kfree(fpga_xfrm->sa_ctx);
 		fpga_xfrm->sa_ctx = NULL;
 	}
 	mutex_unlock(&fpga_xfrm->lock);
@@ -1476,7 +1477,7 @@ int mlx5_fpga_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
 	if (!memcmp(&xfrm->attrs, attrs, sizeof(xfrm->attrs)))
 		return 0;
 
-	if (!mlx5_fpga_esp_validate_xfrm_attrs(mdev, attrs)) {
+	if (mlx5_fpga_esp_validate_xfrm_attrs(mdev, attrs)) {
 		mlx5_core_warn(mdev, "Tried to create an esp with unsupported attrs\n");
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index dc2301eaab38..53f43c576d56 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -778,18 +778,15 @@ static int connect_fts_in_prio(struct mlx5_core_dev *dev,
 {
 	struct mlx5_flow_root_namespace *root = find_root(&prio->node);
 	struct mlx5_flow_table *iter;
-	int i = 0;
 	int err;
 
 	fs_for_each_ft(iter, prio) {
-		i++;
 		err = root->cmds->modify_flow_table(root, iter, ft);
 		if (err) {
-			mlx5_core_warn(dev, "Failed to modify flow table %d\n",
-				       iter->id);
+			mlx5_core_err(dev,
+				      "Failed to modify flow table id %d, type %d, err %d\n",
+				      iter->id, iter->type, err);
 			/* The driver is out of sync with the FW */
-			if (i > 1)
-				WARN_ON(true);
 			return err;
 		}
 	}
@@ -1520,16 +1517,16 @@ struct match_list_head {
 	struct match_list first;
 };
 
-static void free_match_list(struct match_list_head *head)
+static void free_match_list(struct match_list_head *head, bool ft_locked)
 {
 	if (!list_empty(&head->list)) {
 		struct match_list *iter, *match_tmp;
 
 		list_del(&head->first.list);
-		tree_put_node(&head->first.g->node, false);
+		tree_put_node(&head->first.g->node, ft_locked);
 		list_for_each_entry_safe(iter, match_tmp, &head->list,
 					 list) {
-			tree_put_node(&iter->g->node, false);
+			tree_put_node(&iter->g->node, ft_locked);
 			list_del(&iter->list);
 			kfree(iter);
 		}
@@ -1538,7 +1535,8 @@ static void free_match_list(struct match_list_head *head)
 
 static int build_match_list(struct match_list_head *match_head,
 			    struct mlx5_flow_table *ft,
-			    struct mlx5_flow_spec *spec)
+			    struct mlx5_flow_spec *spec,
+			    bool ft_locked)
 {
 	struct rhlist_head *tmp, *list;
 	struct mlx5_flow_group *g;
@@ -1563,7 +1561,7 @@ static int build_match_list(struct match_list_head *match_head,
 
 		curr_match = kmalloc(sizeof(*curr_match), GFP_ATOMIC);
 		if (!curr_match) {
-			free_match_list(match_head);
+			free_match_list(match_head, ft_locked);
 			err = -ENOMEM;
 			goto out;
 		}
@@ -1745,7 +1743,7 @@ search_again_locked:
 	version = atomic_read(&ft->node.version);
 
 	/* Collect all fgs which has a matching match_criteria */
-	err = build_match_list(&match_head, ft, spec);
+	err = build_match_list(&match_head, ft, spec, take_write);
 	if (err) {
 		if (take_write)
 			up_write_ref_node(&ft->node, false);
@@ -1759,7 +1757,7 @@ search_again_locked:
 
 	rule = try_add_to_existing_fg(ft, &match_head.list, spec, flow_act, dest,
 				      dest_num, version);
-	free_match_list(&match_head);
+	free_match_list(&match_head, take_write);
 	if (!IS_ERR(rule) ||
 	    (PTR_ERR(rule) != -ENOENT && PTR_ERR(rule) != -EAGAIN)) {
 		if (take_write)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 603d294757b4..1ce0d8ea855e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -386,7 +386,7 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv)
 err_destroy_direct_tirs:
 	mlx5e_destroy_direct_tirs(priv);
 err_destroy_indirect_tirs:
-	mlx5e_destroy_indirect_tirs(priv, true);
+	mlx5e_destroy_indirect_tirs(priv);
 err_destroy_direct_rqts:
 	mlx5e_destroy_direct_rqts(priv);
 err_destroy_indirect_rqts:
@@ -402,7 +402,7 @@ static void mlx5i_cleanup_rx(struct mlx5e_priv *priv)
 {
 	mlx5i_destroy_flow_steering(priv);
 	mlx5e_destroy_direct_tirs(priv);
-	mlx5e_destroy_indirect_tirs(priv, true);
+	mlx5e_destroy_indirect_tirs(priv);
 	mlx5e_destroy_direct_rqts(priv);
 	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
 	mlx5e_close_drop_rq(&priv->drop_rq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index 0059b290e095..d08155d67bcc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -371,10 +371,31 @@ static int mlx5_ptp_enable(struct ptp_clock_info *ptp,
 	return 0;
 }
 
+enum {
+	MLX5_MTPPS_REG_CAP_PIN_X_MODE_SUPPORT_PPS_IN = BIT(0),
+	MLX5_MTPPS_REG_CAP_PIN_X_MODE_SUPPORT_PPS_OUT = BIT(1),
+};
+
 static int mlx5_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin,
 			   enum ptp_pin_function func, unsigned int chan)
 {
-	return (func == PTP_PF_PHYSYNC) ? -EOPNOTSUPP : 0;
+	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock,
+						ptp_info);
+
+	switch (func) {
+	case PTP_PF_NONE:
+		return 0;
+	case PTP_PF_EXTTS:
+		return !(clock->pps_info.pin_caps[pin] &
+			 MLX5_MTPPS_REG_CAP_PIN_X_MODE_SUPPORT_PPS_IN);
+	case PTP_PF_PEROUT:
+		return !(clock->pps_info.pin_caps[pin] &
+			 MLX5_MTPPS_REG_CAP_PIN_X_MODE_SUPPORT_PPS_OUT);
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return -EOPNOTSUPP;
 }
 
 static const struct ptp_clock_info mlx5_ptp_clock_info = {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index f553c701035f..480669878856 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -773,6 +773,11 @@ err_disable:
 
 static void mlx5_pci_close(struct mlx5_core_dev *dev)
 {
+	/* health work might still be active, and it needs pci bar in
+	 * order to know the NIC state. Therefore, drain the health WQ
+	 * before removing the pci bars
+	 */
+	mlx5_drain_health_wq(dev);
 	iounmap(dev->iseg);
 	pci_clear_master(dev->pdev);
 	release_bar(dev->pdev);
@@ -1135,7 +1140,7 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, bool boot)
 
 	err = mlx5_function_setup(dev, boot);
 	if (err)
-		goto out;
+		goto err_function;
 
 	if (boot) {
 		err = mlx5_init_once(dev);
@@ -1172,6 +1177,7 @@ err_load:
 		mlx5_cleanup_once(dev);
 function_teardown:
 	mlx5_function_teardown(dev, boot);
+err_function:
 	dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
 	mutex_unlock(&dev->intf_state_mutex);
 
@@ -1508,6 +1514,22 @@ static void shutdown(struct pci_dev *pdev)
 	mlx5_pci_disable_device(dev);
 }
 
+static int mlx5_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
+
+	mlx5_unload_one(dev, false);
+
+	return 0;
+}
+
+static int mlx5_resume(struct pci_dev *pdev)
+{
+	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
+
+	return mlx5_load_one(dev, false);
+}
+
 static const struct pci_device_id mlx5_core_pci_table[] = {
 	{ PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_CONNECTIB) },
 	{ PCI_VDEVICE(MELLANOX, 0x1012), MLX5_PCI_DEV_IS_VF},	/* Connect-IB VF */
@@ -1524,6 +1546,7 @@ static const struct pci_device_id mlx5_core_pci_table[] = {
 	{ PCI_VDEVICE(MELLANOX, 0x101d) },			/* ConnectX-6 Dx */
 	{ PCI_VDEVICE(MELLANOX, 0x101e), MLX5_PCI_DEV_IS_VF},	/* ConnectX Family mlx5Gen Virtual Function */
 	{ PCI_VDEVICE(MELLANOX, 0x101f) },			/* ConnectX-6 LX */
+	{ PCI_VDEVICE(MELLANOX, 0x1021) },			/* ConnectX-7 */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d2) },			/* BlueField integrated ConnectX-5 network controller */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF},	/* BlueField integrated ConnectX-5 network controller VF */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d6) },			/* BlueField-2 integrated ConnectX-6 Dx network controller */
@@ -1549,6 +1572,8 @@ static struct pci_driver mlx5_core_driver = {
 	.id_table       = mlx5_core_pci_table,
 	.probe          = init_one,
 	.remove         = remove_one,
+	.suspend        = mlx5_suspend,
+	.resume         = mlx5_resume,
 	.shutdown	= shutdown,
 	.err_handler	= &mlx5_err_handler,
 	.sriov_configure   = mlx5_core_sriov_configure,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index cc262b30aed5..dc589322940c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -293,7 +293,40 @@ static int mlx5_query_module_num(struct mlx5_core_dev *dev, int *module_num)
 	return 0;
 }
 
-static int mlx5_eeprom_page(int offset)
+static int mlx5_query_module_id(struct mlx5_core_dev *dev, int module_num,
+				u8 *module_id)
+{
+	u32 in[MLX5_ST_SZ_DW(mcia_reg)] = {};
+	u32 out[MLX5_ST_SZ_DW(mcia_reg)];
+	int err, status;
+	u8 *ptr;
+
+	MLX5_SET(mcia_reg, in, i2c_device_address, MLX5_I2C_ADDR_LOW);
+	MLX5_SET(mcia_reg, in, module, module_num);
+	MLX5_SET(mcia_reg, in, device_address, 0);
+	MLX5_SET(mcia_reg, in, page_number, 0);
+	MLX5_SET(mcia_reg, in, size, 1);
+	MLX5_SET(mcia_reg, in, l, 0);
+
+	err = mlx5_core_access_reg(dev, in, sizeof(in), out,
+				   sizeof(out), MLX5_REG_MCIA, 0, 0);
+	if (err)
+		return err;
+
+	status = MLX5_GET(mcia_reg, out, status);
+	if (status) {
+		mlx5_core_err(dev, "query_mcia_reg failed: status: 0x%x\n",
+			      status);
+		return -EIO;
+	}
+	ptr = MLX5_ADDR_OF(mcia_reg, out, dword_0);
+
+	*module_id = ptr[0];
+
+	return 0;
+}
+
+static int mlx5_qsfp_eeprom_page(u16 offset)
 {
 	if (offset < MLX5_EEPROM_PAGE_LENGTH)
 		/* Addresses between 0-255 - page 00 */
@@ -307,7 +340,7 @@ static int mlx5_eeprom_page(int offset)
 		    MLX5_EEPROM_HIGH_PAGE_LENGTH);
 }
 
-static int mlx5_eeprom_high_page_offset(int page_num)
+static int mlx5_qsfp_eeprom_high_page_offset(int page_num)
 {
 	if (!page_num) /* Page 0 always start from low page */
 		return 0;
@@ -316,35 +349,62 @@ static int mlx5_eeprom_high_page_offset(int page_num)
 	return page_num * MLX5_EEPROM_HIGH_PAGE_LENGTH;
 }
 
+static void mlx5_qsfp_eeprom_params_set(u16 *i2c_addr, int *page_num, u16 *offset)
+{
+	*i2c_addr = MLX5_I2C_ADDR_LOW;
+	*page_num = mlx5_qsfp_eeprom_page(*offset);
+	*offset -=  mlx5_qsfp_eeprom_high_page_offset(*page_num);
+}
+
+static void mlx5_sfp_eeprom_params_set(u16 *i2c_addr, int *page_num, u16 *offset)
+{
+	*i2c_addr = MLX5_I2C_ADDR_LOW;
+	*page_num = 0;
+
+	if (*offset < MLX5_EEPROM_PAGE_LENGTH)
+		return;
+
+	*i2c_addr = MLX5_I2C_ADDR_HIGH;
+	*offset -= MLX5_EEPROM_PAGE_LENGTH;
+}
+
 int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
 			     u16 offset, u16 size, u8 *data)
 {
-	int module_num, page_num, status, err;
+	int module_num, status, err, page_num = 0;
+	u32 in[MLX5_ST_SZ_DW(mcia_reg)] = {};
 	u32 out[MLX5_ST_SZ_DW(mcia_reg)];
-	u32 in[MLX5_ST_SZ_DW(mcia_reg)];
-	u16 i2c_addr;
-	void *ptr = MLX5_ADDR_OF(mcia_reg, out, dword_0);
+	u16 i2c_addr = 0;
+	u8 module_id;
+	void *ptr;
 
 	err = mlx5_query_module_num(dev, &module_num);
 	if (err)
 		return err;
 
-	memset(in, 0, sizeof(in));
-	size = min_t(int, size, MLX5_EEPROM_MAX_BYTES);
-
-	/* Get the page number related to the given offset */
-	page_num = mlx5_eeprom_page(offset);
+	err = mlx5_query_module_id(dev, module_num, &module_id);
+	if (err)
+		return err;
 
-	/* Set the right offset according to the page number,
-	 * For page_num > 0, relative offset is always >= 128 (high page).
-	 */
-	offset -= mlx5_eeprom_high_page_offset(page_num);
+	switch (module_id) {
+	case MLX5_MODULE_ID_SFP:
+		mlx5_sfp_eeprom_params_set(&i2c_addr, &page_num, &offset);
+		break;
+	case MLX5_MODULE_ID_QSFP:
+	case MLX5_MODULE_ID_QSFP_PLUS:
+	case MLX5_MODULE_ID_QSFP28:
+		mlx5_qsfp_eeprom_params_set(&i2c_addr, &page_num, &offset);
+		break;
+	default:
+		mlx5_core_err(dev, "Module ID not recognized: 0x%x\n", module_id);
+		return -EINVAL;
+	}
 
 	if (offset + size > MLX5_EEPROM_PAGE_LENGTH)
 		/* Cross pages read, read until offset 256 in low page */
 		size -= offset + size - MLX5_EEPROM_PAGE_LENGTH;
 
-	i2c_addr = MLX5_I2C_ADDR_LOW;
+	size = min_t(int, size, MLX5_EEPROM_MAX_BYTES);
 
 	MLX5_SET(mcia_reg, in, l, 0);
 	MLX5_SET(mcia_reg, in, module, module_num);
@@ -365,6 +425,7 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
 		return -EIO;
 	}
 
+	ptr = MLX5_ADDR_OF(mcia_reg, out, dword_0);
 	memcpy(data, ptr, size);
 
 	return size;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
index 86f77456f873..c70a75470358 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
@@ -14,9 +14,6 @@ static void mlx5_rdma_disable_roce_steering(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_roce *roce = &dev->priv.roce;
 
-	if (!roce->ft)
-		return;
-
 	mlx5_del_flow_rules(roce->allow_rule);
 	mlx5_destroy_flow_group(roce->fg);
 	mlx5_destroy_flow_table(roce->ft);
@@ -106,10 +103,10 @@ static int mlx5_rdma_enable_roce_steering(struct mlx5_core_dev *dev)
 
 	return 0;
 
-destroy_flow_table:
-	mlx5_destroy_flow_table(ft);
 destroy_flow_group:
 	mlx5_destroy_flow_group(fg);
+destroy_flow_table:
+	mlx5_destroy_flow_table(ft);
 free:
 	kvfree(spec);
 	kvfree(flow_group_in);
@@ -145,6 +142,11 @@ static int mlx5_rdma_add_roce_addr(struct mlx5_core_dev *dev)
 
 void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev)
 {
+	struct mlx5_core_roce *roce = &dev->priv.roce;
+
+	if (!roce->ft)
+		return;
+
 	mlx5_rdma_disable_roce_steering(dev);
 	mlx5_rdma_del_roce_addr(dev);
 	mlx5_nic_vport_disable_roce(dev);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 09eb0b56a50f..758bcd299aff 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -593,7 +593,7 @@ static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core)
 	err = mlxsw_core_trap_register(mlxsw_core, &mlxsw_emad_rx_listener,
 				       mlxsw_core);
 	if (err)
-		return err;
+		goto err_trap_register;
 
 	err = mlxsw_core->driver->basic_trap_groups_set(mlxsw_core);
 	if (err)
@@ -605,6 +605,7 @@ static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core)
 err_emad_trap_set:
 	mlxsw_core_trap_unregister(mlxsw_core, &mlxsw_emad_rx_listener,
 				   mlxsw_core);
+err_trap_register:
 	destroy_workqueue(mlxsw_core->emad_wq);
 	return err;
 }
@@ -1476,7 +1477,7 @@ static int mlxsw_core_reg_access_emad(struct mlxsw_core *mlxsw_core,
 	err = mlxsw_emad_reg_access(mlxsw_core, reg, payload, type, trans,
 				    bulk_list, cb, cb_priv, tid);
 	if (err) {
-		kfree(trans);
+		kfree_rcu(trans, rcu);
 		return err;
 	}
 	return 0;
@@ -1701,11 +1702,13 @@ void mlxsw_core_skb_receive(struct mlxsw_core *mlxsw_core, struct sk_buff *skb,
 			break;
 		}
 	}
-	rcu_read_unlock();
-	if (!found)
+	if (!found) {
+		rcu_read_unlock();
 		goto drop;
+	}
 
 	rxl->func(skb, local_port, rxl_item->priv);
+	rcu_read_unlock();
 	return;
 
 drop:
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
index e3832cb5bdda..685ed82b123f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.h
@@ -409,4 +409,13 @@ enum mlxsw_devlink_param_id {
 	MLXSW_DEVLINK_PARAM_ID_ACL_REGION_REHASH_INTERVAL,
 };
 
+struct mlxsw_skb_cb {
+};
+
+static inline struct mlxsw_skb_cb *mlxsw_skb_cb(struct sk_buff *skb)
+{
+	BUILD_BUG_ON(sizeof(mlxsw_skb_cb) > sizeof(skb->cb));
+	return (struct mlxsw_skb_cb *) skb->cb;
+}
+
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
index c51b2adfc1e1..2cbfa5cfefab 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
@@ -316,7 +316,7 @@ struct mlxsw_afa_block *mlxsw_afa_block_create(struct mlxsw_afa *mlxsw_afa)
 
 	block = kzalloc(sizeof(*block), GFP_KERNEL);
 	if (!block)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	INIT_LIST_HEAD(&block->resource_list);
 	block->afa = mlxsw_afa;
 
@@ -344,7 +344,7 @@ err_second_set_create:
 	mlxsw_afa_set_destroy(block->first_set);
 err_first_set_create:
 	kfree(block);
-	return NULL;
+	return ERR_PTR(-ENOMEM);
 }
 EXPORT_SYMBOL(mlxsw_afa_block_create);
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c
index cf2114273b72..089de6548f9c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c
@@ -186,8 +186,8 @@ mlxsw_m_port_create(struct mlxsw_m *mlxsw_m, u8 local_port, u8 module)
 
 err_register_netdev:
 	mlxsw_m->ports[local_port] = NULL;
-	free_netdev(dev);
 err_dev_addr_get:
+	free_netdev(dev);
 err_alloc_etherdev:
 	mlxsw_core_port_fini(mlxsw_m->core, local_port);
 	return err;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index b40455f8293d..8711a52fe05e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -1362,23 +1362,12 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core,
 	u16 num_pages;
 	int err;
 
-	mutex_init(&mlxsw_pci->cmd.lock);
-	init_waitqueue_head(&mlxsw_pci->cmd.wait);
-
 	mlxsw_pci->core = mlxsw_core;
 
 	mbox = mlxsw_cmd_mbox_alloc();
 	if (!mbox)
 		return -ENOMEM;
 
-	err = mlxsw_pci_mbox_alloc(mlxsw_pci, &mlxsw_pci->cmd.in_mbox);
-	if (err)
-		goto mbox_put;
-
-	err = mlxsw_pci_mbox_alloc(mlxsw_pci, &mlxsw_pci->cmd.out_mbox);
-	if (err)
-		goto err_out_mbox_alloc;
-
 	err = mlxsw_pci_sw_reset(mlxsw_pci, mlxsw_pci->id);
 	if (err)
 		goto err_sw_reset;
@@ -1475,9 +1464,6 @@ err_query_fw:
 	mlxsw_pci_free_irq_vectors(mlxsw_pci);
 err_alloc_irq:
 err_sw_reset:
-	mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.out_mbox);
-err_out_mbox_alloc:
-	mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.in_mbox);
 mbox_put:
 	mlxsw_cmd_mbox_free(mbox);
 	return err;
@@ -1491,8 +1477,6 @@ static void mlxsw_pci_fini(void *bus_priv)
 	mlxsw_pci_aqs_fini(mlxsw_pci);
 	mlxsw_pci_fw_area_fini(mlxsw_pci);
 	mlxsw_pci_free_irq_vectors(mlxsw_pci);
-	mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.out_mbox);
-	mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.in_mbox);
 }
 
 static struct mlxsw_pci_queue *
@@ -1682,6 +1666,37 @@ static const struct mlxsw_bus mlxsw_pci_bus = {
 	.features		= MLXSW_BUS_F_TXRX | MLXSW_BUS_F_RESET,
 };
 
+static int mlxsw_pci_cmd_init(struct mlxsw_pci *mlxsw_pci)
+{
+	int err;
+
+	mutex_init(&mlxsw_pci->cmd.lock);
+	init_waitqueue_head(&mlxsw_pci->cmd.wait);
+
+	err = mlxsw_pci_mbox_alloc(mlxsw_pci, &mlxsw_pci->cmd.in_mbox);
+	if (err)
+		goto err_in_mbox_alloc;
+
+	err = mlxsw_pci_mbox_alloc(mlxsw_pci, &mlxsw_pci->cmd.out_mbox);
+	if (err)
+		goto err_out_mbox_alloc;
+
+	return 0;
+
+err_out_mbox_alloc:
+	mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.in_mbox);
+err_in_mbox_alloc:
+	mutex_destroy(&mlxsw_pci->cmd.lock);
+	return err;
+}
+
+static void mlxsw_pci_cmd_fini(struct mlxsw_pci *mlxsw_pci)
+{
+	mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.out_mbox);
+	mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.in_mbox);
+	mutex_destroy(&mlxsw_pci->cmd.lock);
+}
+
 static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	const char *driver_name = pdev->driver->name;
@@ -1737,6 +1752,10 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	mlxsw_pci->pdev = pdev;
 	pci_set_drvdata(pdev, mlxsw_pci);
 
+	err = mlxsw_pci_cmd_init(mlxsw_pci);
+	if (err)
+		goto err_pci_cmd_init;
+
 	mlxsw_pci->bus_info.device_kind = driver_name;
 	mlxsw_pci->bus_info.device_name = pci_name(mlxsw_pci->pdev);
 	mlxsw_pci->bus_info.dev = &pdev->dev;
@@ -1753,6 +1772,8 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	return 0;
 
 err_bus_device_register:
+	mlxsw_pci_cmd_fini(mlxsw_pci);
+err_pci_cmd_init:
 	iounmap(mlxsw_pci->hw_addr);
 err_ioremap:
 err_pci_resource_len_check:
@@ -1770,6 +1791,7 @@ static void mlxsw_pci_remove(struct pci_dev *pdev)
 	struct mlxsw_pci *mlxsw_pci = pci_get_drvdata(pdev);
 
 	mlxsw_core_bus_device_unregister(mlxsw_pci->core, false);
+	mlxsw_pci_cmd_fini(mlxsw_pci);
 	iounmap(mlxsw_pci->hw_addr);
 	pci_release_regions(mlxsw_pci->pdev);
 	pci_disable_device(mlxsw_pci->pdev);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index d51442e63aba..78a22b8bbfe6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -738,20 +738,16 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb,
 	u64 len;
 	int err;
 
-	if (mlxsw_core_skb_transmit_busy(mlxsw_sp->core, &tx_info))
-		return NETDEV_TX_BUSY;
+	if (skb_cow_head(skb, MLXSW_TXHDR_LEN)) {
+		this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped);
+		dev_kfree_skb_any(skb);
+		return NETDEV_TX_OK;
+	}
 
-	if (unlikely(skb_headroom(skb) < MLXSW_TXHDR_LEN)) {
-		struct sk_buff *skb_orig = skb;
+	memset(skb->cb, 0, sizeof(struct mlxsw_skb_cb));
 
-		skb = skb_realloc_headroom(skb, MLXSW_TXHDR_LEN);
-		if (!skb) {
-			this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped);
-			dev_kfree_skb_any(skb_orig);
-			return NETDEV_TX_OK;
-		}
-		dev_consume_skb_any(skb_orig);
-	}
+	if (mlxsw_core_skb_transmit_busy(mlxsw_sp->core, &tx_info))
+		return NETDEV_TX_BUSY;
 
 	if (eth_skb_pad(skb)) {
 		this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped);
@@ -1091,6 +1087,9 @@ static void update_stats_cache(struct work_struct *work)
 			     periodic_hw_stats.update_dw.work);
 
 	if (!netif_carrier_ok(mlxsw_sp_port->dev))
+		/* Note: mlxsw_sp_port_down_wipe_counters() clears the cache as
+		 * necessary when port goes down.
+		 */
 		goto out;
 
 	mlxsw_sp_port_get_hw_stats(mlxsw_sp_port->dev,
@@ -3675,6 +3674,7 @@ static void mlxsw_sp_ports_remove(struct mlxsw_sp *mlxsw_sp)
 			mlxsw_sp_port_remove(mlxsw_sp, i);
 	kfree(mlxsw_sp->port_to_module);
 	kfree(mlxsw_sp->ports);
+	mlxsw_sp->ports = NULL;
 }
 
 static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp)
@@ -3723,6 +3723,7 @@ err_port_module_info_get:
 	kfree(mlxsw_sp->port_to_module);
 err_port_to_module_alloc:
 	kfree(mlxsw_sp->ports);
+	mlxsw_sp->ports = NULL;
 	return err;
 }
 
@@ -3777,6 +3778,14 @@ static void mlxsw_sp_port_unsplit_create(struct mlxsw_sp *mlxsw_sp,
 	}
 }
 
+static struct mlxsw_sp_port *
+mlxsw_sp_port_get_by_local_port(struct mlxsw_sp *mlxsw_sp, u8 local_port)
+{
+	if (mlxsw_sp->ports && mlxsw_sp->ports[local_port])
+		return mlxsw_sp->ports[local_port];
+	return NULL;
+}
+
 static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port,
 			       unsigned int count,
 			       struct netlink_ext_ack *extack)
@@ -3795,7 +3804,7 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port,
 	local_ports_in_1x = MLXSW_CORE_RES_GET(mlxsw_core, LOCAL_PORTS_IN_1X);
 	local_ports_in_2x = MLXSW_CORE_RES_GET(mlxsw_core, LOCAL_PORTS_IN_2X);
 
-	mlxsw_sp_port = mlxsw_sp->ports[local_port];
+	mlxsw_sp_port = mlxsw_sp_port_get_by_local_port(mlxsw_sp, local_port);
 	if (!mlxsw_sp_port) {
 		dev_err(mlxsw_sp->bus_info->dev, "Port number \"%d\" does not exist\n",
 			local_port);
@@ -3873,7 +3882,7 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port,
 	local_ports_in_1x = MLXSW_CORE_RES_GET(mlxsw_core, LOCAL_PORTS_IN_1X);
 	local_ports_in_2x = MLXSW_CORE_RES_GET(mlxsw_core, LOCAL_PORTS_IN_2X);
 
-	mlxsw_sp_port = mlxsw_sp->ports[local_port];
+	mlxsw_sp_port = mlxsw_sp_port_get_by_local_port(mlxsw_sp, local_port);
 	if (!mlxsw_sp_port) {
 		dev_err(mlxsw_sp->bus_info->dev, "Port number \"%d\" does not exist\n",
 			local_port);
@@ -3910,6 +3919,15 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port,
 	return 0;
 }
 
+static void
+mlxsw_sp_port_down_wipe_counters(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	int i;
+
+	for (i = 0; i < TC_MAX_QUEUE; i++)
+		mlxsw_sp_port->periodic_hw_stats.xstats.backlog[i] = 0;
+}
+
 static void mlxsw_sp_pude_event_func(const struct mlxsw_reg_info *reg,
 				     char *pude_pl, void *priv)
 {
@@ -3930,6 +3948,7 @@ static void mlxsw_sp_pude_event_func(const struct mlxsw_reg_info *reg,
 	} else {
 		netdev_info(mlxsw_sp_port->dev, "link down\n");
 		netif_carrier_off(mlxsw_sp_port->dev);
+		mlxsw_sp_port_down_wipe_counters(mlxsw_sp_port);
 	}
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
index 6c66a0f1b79e..ad69913f19c1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
@@ -88,8 +88,8 @@ static int mlxsw_sp2_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv,
 	 * to be written using PEFA register to all indexes for all regions.
 	 */
 	afa_block = mlxsw_afa_block_create(mlxsw_sp->afa);
-	if (!afa_block) {
-		err = -ENOMEM;
+	if (IS_ERR(afa_block)) {
+		err = PTR_ERR(afa_block);
 		goto err_afa_block;
 	}
 	err = mlxsw_afa_block_continue(afa_block);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index a146a44634e9..93a12b53de73 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -8,6 +8,7 @@
 #include <linux/string.h>
 #include <linux/rhashtable.h>
 #include <linux/netdevice.h>
+#include <linux/mutex.h>
 #include <net/net_namespace.h>
 #include <net/tc_act/tc_vlan.h>
 
@@ -25,6 +26,7 @@ struct mlxsw_sp_acl {
 	struct mlxsw_sp_fid *dummy_fid;
 	struct rhashtable ruleset_ht;
 	struct list_head rules;
+	struct mutex rules_lock; /* Protects rules list */
 	struct {
 		struct delayed_work dw;
 		unsigned long interval;	/* ms */
@@ -443,7 +445,7 @@ mlxsw_sp_acl_rulei_create(struct mlxsw_sp_acl *acl,
 
 	rulei = kzalloc(sizeof(*rulei), GFP_KERNEL);
 	if (!rulei)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	if (afa_block) {
 		rulei->act_block = afa_block;
@@ -702,7 +704,9 @@ int mlxsw_sp_acl_rule_add(struct mlxsw_sp *mlxsw_sp,
 			goto err_ruleset_block_bind;
 	}
 
+	mutex_lock(&mlxsw_sp->acl->rules_lock);
 	list_add_tail(&rule->list, &mlxsw_sp->acl->rules);
+	mutex_unlock(&mlxsw_sp->acl->rules_lock);
 	ruleset->ht_key.block->rule_count++;
 	return 0;
 
@@ -721,7 +725,9 @@ void mlxsw_sp_acl_rule_del(struct mlxsw_sp *mlxsw_sp,
 	const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops;
 
 	ruleset->ht_key.block->rule_count--;
+	mutex_lock(&mlxsw_sp->acl->rules_lock);
 	list_del(&rule->list);
+	mutex_unlock(&mlxsw_sp->acl->rules_lock);
 	if (!ruleset->ht_key.chain_index &&
 	    mlxsw_sp_acl_ruleset_is_singular(ruleset))
 		mlxsw_sp_acl_ruleset_block_unbind(mlxsw_sp, ruleset,
@@ -781,19 +787,18 @@ static int mlxsw_sp_acl_rules_activity_update(struct mlxsw_sp_acl *acl)
 	struct mlxsw_sp_acl_rule *rule;
 	int err;
 
-	/* Protect internal structures from changes */
-	rtnl_lock();
+	mutex_lock(&acl->rules_lock);
 	list_for_each_entry(rule, &acl->rules, list) {
 		err = mlxsw_sp_acl_rule_activity_update(acl->mlxsw_sp,
 							rule);
 		if (err)
 			goto err_rule_update;
 	}
-	rtnl_unlock();
+	mutex_unlock(&acl->rules_lock);
 	return 0;
 
 err_rule_update:
-	rtnl_unlock();
+	mutex_unlock(&acl->rules_lock);
 	return err;
 }
 
@@ -878,6 +883,7 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
 	acl->dummy_fid = fid;
 
 	INIT_LIST_HEAD(&acl->rules);
+	mutex_init(&acl->rules_lock);
 	err = mlxsw_sp_acl_tcam_init(mlxsw_sp, &acl->tcam);
 	if (err)
 		goto err_acl_ops_init;
@@ -890,6 +896,7 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
 	return 0;
 
 err_acl_ops_init:
+	mutex_destroy(&acl->rules_lock);
 	mlxsw_sp_fid_put(fid);
 err_fid_get:
 	rhashtable_destroy(&acl->ruleset_ht);
@@ -906,6 +913,7 @@ void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp)
 
 	cancel_delayed_work_sync(&mlxsw_sp->acl->rule_activity_update.dw);
 	mlxsw_sp_acl_tcam_fini(mlxsw_sp, &acl->tcam);
+	mutex_destroy(&acl->rules_lock);
 	WARN_ON(!list_empty(&acl->rules));
 	mlxsw_sp_fid_put(acl->dummy_fid);
 	rhashtable_destroy(&acl->ruleset_ht);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index e993159e8e4c..295b27112d36 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -986,8 +986,9 @@ mlxsw_sp_acl_tcam_vchunk_create(struct mlxsw_sp *mlxsw_sp,
 				unsigned int priority,
 				struct mlxsw_afk_element_usage *elusage)
 {
+	struct mlxsw_sp_acl_tcam_vchunk *vchunk, *vchunk2;
 	struct mlxsw_sp_acl_tcam_vregion *vregion;
-	struct mlxsw_sp_acl_tcam_vchunk *vchunk;
+	struct list_head *pos;
 	int err;
 
 	if (priority == MLXSW_SP_ACL_TCAM_CATCHALL_PRIO)
@@ -1025,7 +1026,14 @@ mlxsw_sp_acl_tcam_vchunk_create(struct mlxsw_sp *mlxsw_sp,
 	}
 
 	mlxsw_sp_acl_tcam_rehash_ctx_vregion_changed(vregion);
-	list_add_tail(&vchunk->list, &vregion->vchunk_list);
+
+	/* Position the vchunk inside the list according to priority */
+	list_for_each(pos, &vregion->vchunk_list) {
+		vchunk2 = list_entry(pos, typeof(*vchunk2), list);
+		if (vchunk2->priority > priority)
+			break;
+	}
+	list_add_tail(&vchunk->list, pos);
 	mutex_unlock(&vregion->lock);
 
 	return vchunk;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
index 49933818c6f5..2dc0978428e6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
@@ -215,7 +215,7 @@ mlxsw_sp_dpipe_table_erif_entries_dump(void *priv, bool counters_enabled,
 start_again:
 	err = devlink_dpipe_entry_ctx_prepare(dump_ctx);
 	if (err)
-		return err;
+		goto err_ctx_prepare;
 	j = 0;
 	for (; i < rif_count; i++) {
 		struct mlxsw_sp_rif *rif = mlxsw_sp_rif_by_index(mlxsw_sp, i);
@@ -247,6 +247,7 @@ start_again:
 	return 0;
 err_entry_append:
 err_entry_get:
+err_ctx_prepare:
 	rtnl_unlock();
 	devlink_dpipe_entry_clear(&entry);
 	return err;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index ca31c26e98c1..9eae5d593de1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -113,9 +113,12 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 			u8 prio = act->vlan.prio;
 			u16 vid = act->vlan.vid;
 
-			return mlxsw_sp_acl_rulei_act_vlan(mlxsw_sp, rulei,
-							   act->id, vid,
-							   proto, prio, extack);
+			err = mlxsw_sp_acl_rulei_act_vlan(mlxsw_sp, rulei,
+							  act->id, vid,
+							  proto, prio, extack);
+			if (err)
+				return err;
+			break;
 			}
 		default:
 			NL_SET_ERR_MSG_MOD(extack, "Unsupported action");
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
index 54275624718b..336e5ecc68f8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
@@ -637,12 +637,12 @@ static int mlxsw_sp_mr_vif_resolve(struct mlxsw_sp_mr_table *mr_table,
 	return 0;
 
 err_erif_unresolve:
-	list_for_each_entry_from_reverse(erve, &mr_vif->route_evif_list,
-					 vif_node)
+	list_for_each_entry_continue_reverse(erve, &mr_vif->route_evif_list,
+					     vif_node)
 		mlxsw_sp_mr_route_evif_unresolve(mr_table, erve);
 err_irif_unresolve:
-	list_for_each_entry_from_reverse(irve, &mr_vif->route_ivif_list,
-					 vif_node)
+	list_for_each_entry_continue_reverse(irve, &mr_vif->route_ivif_list,
+					     vif_node)
 		mlxsw_sp_mr_route_ivif_unresolve(mr_table, irve);
 	mr_vif->rif = NULL;
 	return err;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
index 346f4a5fe053..221aa6a474eb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
@@ -199,8 +199,8 @@ mlxsw_sp_mr_tcam_afa_block_create(struct mlxsw_sp *mlxsw_sp,
 	int err;
 
 	afa_block = mlxsw_afa_block_create(mlxsw_sp->afa);
-	if (!afa_block)
-		return ERR_PTR(-ENOMEM);
+	if (IS_ERR(afa_block))
+		return afa_block;
 
 	err = mlxsw_afa_block_append_allocated_counter(afa_block,
 						       counter_index);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
index bdf53cf350f6..dc63583c4948 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
@@ -195,6 +195,20 @@ mlxsw_sp_qdisc_get_xstats(struct mlxsw_sp_port *mlxsw_sp_port,
 	return -EOPNOTSUPP;
 }
 
+static u64
+mlxsw_sp_xstats_backlog(struct mlxsw_sp_port_xstats *xstats, int tclass_num)
+{
+	return xstats->backlog[tclass_num] +
+	       xstats->backlog[tclass_num + 8];
+}
+
+static u64
+mlxsw_sp_xstats_tail_drop(struct mlxsw_sp_port_xstats *xstats, int tclass_num)
+{
+	return xstats->tail_drop[tclass_num] +
+	       xstats->tail_drop[tclass_num + 8];
+}
+
 static void
 mlxsw_sp_qdisc_bstats_per_priority_get(struct mlxsw_sp_port_xstats *xstats,
 				       u8 prio_bitmap, u64 *tx_packets,
@@ -269,7 +283,7 @@ mlxsw_sp_setup_tc_qdisc_red_clean_stats(struct mlxsw_sp_port *mlxsw_sp_port,
 					       &stats_base->tx_bytes);
 	red_base->prob_mark = xstats->ecn;
 	red_base->prob_drop = xstats->wred_drop[tclass_num];
-	red_base->pdrop = xstats->tail_drop[tclass_num];
+	red_base->pdrop = mlxsw_sp_xstats_tail_drop(xstats, tclass_num);
 
 	stats_base->overlimits = red_base->prob_drop + red_base->prob_mark;
 	stats_base->drops = red_base->prob_drop + red_base->pdrop;
@@ -369,7 +383,8 @@ mlxsw_sp_qdisc_get_red_xstats(struct mlxsw_sp_port *mlxsw_sp_port,
 
 	early_drops = xstats->wred_drop[tclass_num] - xstats_base->prob_drop;
 	marks = xstats->ecn - xstats_base->prob_mark;
-	pdrops = xstats->tail_drop[tclass_num] - xstats_base->pdrop;
+	pdrops = mlxsw_sp_xstats_tail_drop(xstats, tclass_num) -
+		 xstats_base->pdrop;
 
 	res->pdrop += pdrops;
 	res->prob_drop += early_drops;
@@ -402,9 +417,10 @@ mlxsw_sp_qdisc_get_red_stats(struct mlxsw_sp_port *mlxsw_sp_port,
 
 	overlimits = xstats->wred_drop[tclass_num] + xstats->ecn -
 		     stats_base->overlimits;
-	drops = xstats->wred_drop[tclass_num] + xstats->tail_drop[tclass_num] -
+	drops = xstats->wred_drop[tclass_num] +
+		mlxsw_sp_xstats_tail_drop(xstats, tclass_num) -
 		stats_base->drops;
-	backlog = xstats->backlog[tclass_num];
+	backlog = mlxsw_sp_xstats_backlog(xstats, tclass_num);
 
 	_bstats_update(stats_ptr->bstats, tx_bytes, tx_packets);
 	stats_ptr->qstats->overlimits += overlimits;
@@ -575,9 +591,9 @@ mlxsw_sp_qdisc_get_prio_stats(struct mlxsw_sp_port *mlxsw_sp_port,
 	tx_packets = stats->tx_packets - stats_base->tx_packets;
 
 	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
-		drops += xstats->tail_drop[i];
+		drops += mlxsw_sp_xstats_tail_drop(xstats, i);
 		drops += xstats->wred_drop[i];
-		backlog += xstats->backlog[i];
+		backlog += mlxsw_sp_xstats_backlog(xstats, i);
 	}
 	drops = drops - stats_base->drops;
 
@@ -613,7 +629,7 @@ mlxsw_sp_setup_tc_qdisc_prio_clean_stats(struct mlxsw_sp_port *mlxsw_sp_port,
 
 	stats_base->drops = 0;
 	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
-		stats_base->drops += xstats->tail_drop[i];
+		stats_base->drops += mlxsw_sp_xstats_tail_drop(xstats, i);
 		stats_base->drops += xstats->wred_drop[i];
 	}
 
@@ -650,6 +666,13 @@ mlxsw_sp_qdisc_prio_graft(struct mlxsw_sp_port *mlxsw_sp_port,
 	    mlxsw_sp_port->tclass_qdiscs[tclass_num].handle == p->child_handle)
 		return 0;
 
+	if (!p->child_handle) {
+		/* This is an invisible FIFO replacing the original Qdisc.
+		 * Ignore it--the original Qdisc's destroy will follow.
+		 */
+		return 0;
+	}
+
 	/* See if the grafted qdisc is already offloaded on any tclass. If so,
 	 * unoffload it.
 	 */
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 58c232647b36..05ed0a6971b6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -6173,7 +6173,7 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
 	}
 
 	fib_work = kzalloc(sizeof(*fib_work), GFP_ATOMIC);
-	if (WARN_ON(!fib_work))
+	if (!fib_work)
 		return NOTIFY_BAD;
 
 	fib_work->mlxsw_sp = router->mlxsw_sp;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index fc4f19167262..2ea797b6c3fe 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -299,20 +299,17 @@ static netdev_tx_t mlxsw_sx_port_xmit(struct sk_buff *skb,
 	u64 len;
 	int err;
 
+	if (skb_cow_head(skb, MLXSW_TXHDR_LEN)) {
+		this_cpu_inc(mlxsw_sx_port->pcpu_stats->tx_dropped);
+		dev_kfree_skb_any(skb);
+		return NETDEV_TX_OK;
+	}
+
+	memset(skb->cb, 0, sizeof(struct mlxsw_skb_cb));
+
 	if (mlxsw_core_skb_transmit_busy(mlxsw_sx->core, &tx_info))
 		return NETDEV_TX_BUSY;
 
-	if (unlikely(skb_headroom(skb) < MLXSW_TXHDR_LEN)) {
-		struct sk_buff *skb_orig = skb;
-
-		skb = skb_realloc_headroom(skb, MLXSW_TXHDR_LEN);
-		if (!skb) {
-			this_cpu_inc(mlxsw_sx_port->pcpu_stats->tx_dropped);
-			dev_kfree_skb_any(skb_orig);
-			return NETDEV_TX_OK;
-		}
-		dev_consume_skb_any(skb_orig);
-	}
 	mlxsw_sx_txhdr_construct(skb, &tx_info);
 	/* TX header is consumed by HW on the way so we shouldn't count its
 	 * bytes as being sent.
@@ -1267,6 +1264,7 @@ static void mlxsw_sx_ports_remove(struct mlxsw_sx *mlxsw_sx)
 		if (mlxsw_sx_port_created(mlxsw_sx, i))
 			mlxsw_sx_port_remove(mlxsw_sx, i);
 	kfree(mlxsw_sx->ports);
+	mlxsw_sx->ports = NULL;
 }
 
 static int mlxsw_sx_ports_create(struct mlxsw_sx *mlxsw_sx)
@@ -1301,6 +1299,7 @@ err_port_module_info_get:
 		if (mlxsw_sx_port_created(mlxsw_sx, i))
 			mlxsw_sx_port_remove(mlxsw_sx, i);
 	kfree(mlxsw_sx->ports);
+	mlxsw_sx->ports = NULL;
 	return err;
 }
 
@@ -1384,6 +1383,12 @@ static int mlxsw_sx_port_type_set(struct mlxsw_core *mlxsw_core, u8 local_port,
 	u8 module, width;
 	int err;
 
+	if (!mlxsw_sx->ports || !mlxsw_sx->ports[local_port]) {
+		dev_err(mlxsw_sx->bus_info->dev, "Port number \"%d\" does not exist\n",
+			local_port);
+		return -EINVAL;
+	}
+
 	if (new_type == DEVLINK_PORT_TYPE_AUTO)
 		return -EOPNOTSUPP;
 
diff --git a/drivers/net/ethernet/micrel/ks8851_mll.c b/drivers/net/ethernet/micrel/ks8851_mll.c
index e52b015e31a9..de690d420689 100644
--- a/drivers/net/ethernet/micrel/ks8851_mll.c
+++ b/drivers/net/ethernet/micrel/ks8851_mll.c
@@ -157,21 +157,47 @@ static int msg_enable;
  */
 
 /**
- * ks_rdreg8 - read 8 bit register from device
+ * ks_check_endian - Check whether endianness of the bus is correct
  * @ks	  : The chip information
- * @offset: The register address
  *
- * Read a 8bit register from the chip, returning the result
+ * The KS8851-16MLL EESK pin allows selecting the endianness of the 16bit
+ * bus. To maintain optimum performance, the bus endianness should be set
+ * such that it matches the endianness of the CPU.
  */
-static u8 ks_rdreg8(struct ks_net *ks, int offset)
+
+static int ks_check_endian(struct ks_net *ks)
 {
-	u16 data;
-	u8 shift_bit = offset & 0x03;
-	u8 shift_data = (offset & 1) << 3;
-	ks->cmd_reg_cache = (u16) offset | (u16)(BE0 << shift_bit);
-	iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd);
-	data  = ioread16(ks->hw_addr);
-	return (u8)(data >> shift_data);
+	u16 cider;
+
+	/*
+	 * Read CIDER register first, however read it the "wrong" way around.
+	 * If the endian strap on the KS8851-16MLL in incorrect and the chip
+	 * is operating in different endianness than the CPU, then the meaning
+	 * of BE[3:0] byte-enable bits is also swapped such that:
+	 *    BE[3,2,1,0] becomes BE[1,0,3,2]
+	 *
+	 * Luckily for us, the byte-enable bits are the top four MSbits of
+	 * the address register and the CIDER register is at offset 0xc0.
+	 * Hence, by reading address 0xc0c0, which is not impacted by endian
+	 * swapping, we assert either BE[3:2] or BE[1:0] while reading the
+	 * CIDER register.
+	 *
+	 * If the bus configuration is correct, reading 0xc0c0 asserts
+	 * BE[3:2] and this read returns 0x0000, because to read register
+	 * with bottom two LSbits of address set to 0, BE[1:0] must be
+	 * asserted.
+	 *
+	 * If the bus configuration is NOT correct, reading 0xc0c0 asserts
+	 * BE[1:0] and this read returns non-zero 0x8872 value.
+	 */
+	iowrite16(BE3 | BE2 | KS_CIDER, ks->hw_addr_cmd);
+	cider = ioread16(ks->hw_addr);
+	if (!cider)
+		return 0;
+
+	netdev_err(ks->netdev, "incorrect EESK endian strap setting\n");
+
+	return -EINVAL;
 }
 
 /**
@@ -190,22 +216,6 @@ static u16 ks_rdreg16(struct ks_net *ks, int offset)
 }
 
 /**
- * ks_wrreg8 - write 8bit register value to chip
- * @ks: The chip information
- * @offset: The register address
- * @value: The value to write
- *
- */
-static void ks_wrreg8(struct ks_net *ks, int offset, u8 value)
-{
-	u8  shift_bit = (offset & 0x03);
-	u16 value_write = (u16)(value << ((offset & 1) << 3));
-	ks->cmd_reg_cache = (u16)offset | (BE0 << shift_bit);
-	iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd);
-	iowrite16(value_write, ks->hw_addr);
-}
-
-/**
  * ks_wrreg16 - write 16bit register value to chip
  * @ks: The chip information
  * @offset: The register address
@@ -324,8 +334,7 @@ static void ks_read_config(struct ks_net *ks)
 	u16 reg_data = 0;
 
 	/* Regardless of bus width, 8 bit read should always work.*/
-	reg_data = ks_rdreg8(ks, KS_CCR) & 0x00FF;
-	reg_data |= ks_rdreg8(ks, KS_CCR+1) << 8;
+	reg_data = ks_rdreg16(ks, KS_CCR);
 
 	/* addr/data bus are multiplexed */
 	ks->sharedbus = (reg_data & CCR_SHARED) == CCR_SHARED;
@@ -429,7 +438,7 @@ static inline void ks_read_qmu(struct ks_net *ks, u16 *buf, u32 len)
 
 	/* 1. set sudo DMA mode */
 	ks_wrreg16(ks, KS_RXFDPR, RXFDPR_RXFPAI);
-	ks_wrreg8(ks, KS_RXQCR, (ks->rc_rxqcr | RXQCR_SDA) & 0xff);
+	ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA);
 
 	/* 2. read prepend data */
 	/**
@@ -446,7 +455,7 @@ static inline void ks_read_qmu(struct ks_net *ks, u16 *buf, u32 len)
 	ks_inblk(ks, buf, ALIGN(len, 4));
 
 	/* 4. reset sudo DMA Mode */
-	ks_wrreg8(ks, KS_RXQCR, ks->rc_rxqcr);
+	ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr);
 }
 
 /**
@@ -548,14 +557,17 @@ static irqreturn_t ks_irq(int irq, void *pw)
 {
 	struct net_device *netdev = pw;
 	struct ks_net *ks = netdev_priv(netdev);
+	unsigned long flags;
 	u16 status;
 
+	spin_lock_irqsave(&ks->statelock, flags);
 	/*this should be the first in IRQ handler */
 	ks_save_cmd_reg(ks);
 
 	status = ks_rdreg16(ks, KS_ISR);
 	if (unlikely(!status)) {
 		ks_restore_cmd_reg(ks);
+		spin_unlock_irqrestore(&ks->statelock, flags);
 		return IRQ_NONE;
 	}
 
@@ -581,6 +593,7 @@ static irqreturn_t ks_irq(int irq, void *pw)
 		ks->netdev->stats.rx_over_errors++;
 	/* this should be the last in IRQ handler*/
 	ks_restore_cmd_reg(ks);
+	spin_unlock_irqrestore(&ks->statelock, flags);
 	return IRQ_HANDLED;
 }
 
@@ -650,6 +663,7 @@ static int ks_net_stop(struct net_device *netdev)
 
 	/* shutdown RX/TX QMU */
 	ks_disable_qmu(ks);
+	ks_disable_int(ks);
 
 	/* set powermode to soft power down to save power */
 	ks_set_powermode(ks, PMECR_PM_SOFTDOWN);
@@ -679,13 +693,13 @@ static void ks_write_qmu(struct ks_net *ks, u8 *pdata, u16 len)
 	ks->txh.txw[1] = cpu_to_le16(len);
 
 	/* 1. set sudo-DMA mode */
-	ks_wrreg8(ks, KS_RXQCR, (ks->rc_rxqcr | RXQCR_SDA) & 0xff);
+	ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA);
 	/* 2. write status/lenth info */
 	ks_outblk(ks, ks->txh.txw, 4);
 	/* 3. write pkt data */
 	ks_outblk(ks, (u16 *)pdata, ALIGN(len, 4));
 	/* 4. reset sudo-DMA mode */
-	ks_wrreg8(ks, KS_RXQCR, ks->rc_rxqcr);
+	ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr);
 	/* 5. Enqueue Tx(move the pkt from TX buffer into TXQ) */
 	ks_wrreg16(ks, KS_TXQCR, TXQCR_METFE);
 	/* 6. wait until TXQCR_METFE is auto-cleared */
@@ -706,10 +720,9 @@ static netdev_tx_t ks_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 {
 	netdev_tx_t retv = NETDEV_TX_OK;
 	struct ks_net *ks = netdev_priv(netdev);
+	unsigned long flags;
 
-	disable_irq(netdev->irq);
-	ks_disable_int(ks);
-	spin_lock(&ks->statelock);
+	spin_lock_irqsave(&ks->statelock, flags);
 
 	/* Extra space are required:
 	*  4 byte for alignment, 4 for status/length, 4 for CRC
@@ -723,9 +736,7 @@ static netdev_tx_t ks_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 		dev_kfree_skb(skb);
 	} else
 		retv = NETDEV_TX_BUSY;
-	spin_unlock(&ks->statelock);
-	ks_enable_int(ks);
-	enable_irq(netdev->irq);
+	spin_unlock_irqrestore(&ks->statelock, flags);
 	return retv;
 }
 
@@ -1254,6 +1265,10 @@ static int ks8851_probe(struct platform_device *pdev)
 		goto err_free;
 	}
 
+	err = ks_check_endian(ks);
+	if (err)
+		goto err_free;
+
 	netdev->irq = platform_get_irq(pdev, 0);
 
 	if ((int)netdev->irq < 0) {
diff --git a/drivers/net/ethernet/microchip/encx24j600.c b/drivers/net/ethernet/microchip/encx24j600.c
index 52c41d11f565..c3a6edc0ddf6 100644
--- a/drivers/net/ethernet/microchip/encx24j600.c
+++ b/drivers/net/ethernet/microchip/encx24j600.c
@@ -1070,7 +1070,7 @@ static int encx24j600_spi_probe(struct spi_device *spi)
 	if (unlikely(ret)) {
 		netif_err(priv, probe, ndev, "Error %d initializing card encx24j600 card\n",
 			  ret);
-		goto out_free;
+		goto out_stop;
 	}
 
 	eidled = encx24j600_read_reg(priv, EIDLED);
@@ -1088,6 +1088,8 @@ static int encx24j600_spi_probe(struct spi_device *spi)
 
 out_unregister:
 	unregister_netdev(priv->ndev);
+out_stop:
+	kthread_stop(priv->kworker_task);
 out_free:
 	free_netdev(ndev);
 
@@ -1100,6 +1102,7 @@ static int encx24j600_spi_remove(struct spi_device *spi)
 	struct encx24j600_priv *priv = dev_get_drvdata(&spi->dev);
 
 	unregister_netdev(priv->ndev);
+	kthread_stop(priv->kworker_task);
 
 	free_netdev(priv->ndev);
 
diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c
index e1651756bf9d..f70bb81e1ed6 100644
--- a/drivers/net/ethernet/moxa/moxart_ether.c
+++ b/drivers/net/ethernet/moxa/moxart_ether.c
@@ -564,7 +564,7 @@ static int moxart_remove(struct platform_device *pdev)
 	struct net_device *ndev = platform_get_drvdata(pdev);
 
 	unregister_netdev(ndev);
-	free_irq(ndev->irq, ndev);
+	devm_free_irq(&pdev->dev, ndev->irq, ndev);
 	moxart_mac_free_memory(ndev);
 	free_netdev(ndev);
 
diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c
index e7f90101d2e0..7eb7c2619d7c 100644
--- a/drivers/net/ethernet/mscc/ocelot_board.c
+++ b/drivers/net/ethernet/mscc/ocelot_board.c
@@ -108,6 +108,14 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg)
 		if (err != 4)
 			break;
 
+		/* At this point the IFH was read correctly, so it is safe to
+		 * presume that there is no error. The err needs to be reset
+		 * otherwise a frame could come in CPU queue between the while
+		 * condition and the check for error later on. And in that case
+		 * the new frame is just removed and not processed.
+		 */
+		err = 0;
+
 		ocelot_parse_ifh(ifh, &info);
 
 		dev = ocelot->ports[info.port]->dev;
diff --git a/drivers/net/ethernet/natsemi/jazzsonic.c b/drivers/net/ethernet/natsemi/jazzsonic.c
index 51fa82b429a3..40970352d208 100644
--- a/drivers/net/ethernet/natsemi/jazzsonic.c
+++ b/drivers/net/ethernet/natsemi/jazzsonic.c
@@ -235,11 +235,13 @@ static int jazz_sonic_probe(struct platform_device *pdev)
 
 	err = register_netdev(dev);
 	if (err)
-		goto out1;
+		goto undo_probe1;
 
 	return 0;
 
-out1:
+undo_probe1:
+	dma_free_coherent(lp->device, SIZEOF_SONIC_DESC * SONIC_BUS_SCALE(lp->dma_bitmode),
+			  lp->descriptors, lp->descriptors_laddr);
 	release_mem_region(dev->base_addr, SONIC_MEM_SIZE);
 out:
 	free_netdev(dev);
diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c
index d0a01e8f000a..05e760444a92 100644
--- a/drivers/net/ethernet/natsemi/sonic.c
+++ b/drivers/net/ethernet/natsemi/sonic.c
@@ -64,6 +64,8 @@ static int sonic_open(struct net_device *dev)
 
 	netif_dbg(lp, ifup, dev, "%s: initializing sonic driver\n", __func__);
 
+	spin_lock_init(&lp->lock);
+
 	for (i = 0; i < SONIC_NUM_RRS; i++) {
 		struct sk_buff *skb = netdev_alloc_skb(dev, SONIC_RBSIZE + 2);
 		if (skb == NULL) {
@@ -114,6 +116,24 @@ static int sonic_open(struct net_device *dev)
 	return 0;
 }
 
+/* Wait for the SONIC to become idle. */
+static void sonic_quiesce(struct net_device *dev, u16 mask)
+{
+	struct sonic_local * __maybe_unused lp = netdev_priv(dev);
+	int i;
+	u16 bits;
+
+	for (i = 0; i < 1000; ++i) {
+		bits = SONIC_READ(SONIC_CMD) & mask;
+		if (!bits)
+			return;
+		if (irqs_disabled() || in_interrupt())
+			udelay(20);
+		else
+			usleep_range(100, 200);
+	}
+	WARN_ONCE(1, "command deadline expired! 0x%04x\n", bits);
+}
 
 /*
  * Close the SONIC device
@@ -130,6 +150,9 @@ static int sonic_close(struct net_device *dev)
 	/*
 	 * stop the SONIC, disable interrupts
 	 */
+	SONIC_WRITE(SONIC_CMD, SONIC_CR_RXDIS);
+	sonic_quiesce(dev, SONIC_CR_ALL);
+
 	SONIC_WRITE(SONIC_IMR, 0);
 	SONIC_WRITE(SONIC_ISR, 0x7fff);
 	SONIC_WRITE(SONIC_CMD, SONIC_CR_RST);
@@ -169,6 +192,9 @@ static void sonic_tx_timeout(struct net_device *dev)
 	 * put the Sonic into software-reset mode and
 	 * disable all interrupts before releasing DMA buffers
 	 */
+	SONIC_WRITE(SONIC_CMD, SONIC_CR_RXDIS);
+	sonic_quiesce(dev, SONIC_CR_ALL);
+
 	SONIC_WRITE(SONIC_IMR, 0);
 	SONIC_WRITE(SONIC_ISR, 0x7fff);
 	SONIC_WRITE(SONIC_CMD, SONIC_CR_RST);
@@ -206,8 +232,6 @@ static void sonic_tx_timeout(struct net_device *dev)
  *   wake the tx queue
  * Concurrently with all of this, the SONIC is potentially writing to
  * the status flags of the TDs.
- * Until some mutual exclusion is added, this code will not work with SMP. However,
- * MIPS Jazz machines and m68k Macs were all uni-processor machines.
  */
 
 static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev)
@@ -215,7 +239,8 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev)
 	struct sonic_local *lp = netdev_priv(dev);
 	dma_addr_t laddr;
 	int length;
-	int entry = lp->next_tx;
+	int entry;
+	unsigned long flags;
 
 	netif_dbg(lp, tx_queued, dev, "%s: skb=%p\n", __func__, skb);
 
@@ -232,11 +257,15 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev)
 
 	laddr = dma_map_single(lp->device, skb->data, length, DMA_TO_DEVICE);
 	if (!laddr) {
-		printk(KERN_ERR "%s: failed to map tx DMA buffer.\n", dev->name);
-		dev_kfree_skb(skb);
-		return NETDEV_TX_BUSY;
+		pr_err_ratelimited("%s: failed to map tx DMA buffer.\n", dev->name);
+		dev_kfree_skb_any(skb);
+		return NETDEV_TX_OK;
 	}
 
+	spin_lock_irqsave(&lp->lock, flags);
+
+	entry = lp->next_tx;
+
 	sonic_tda_put(dev, entry, SONIC_TD_STATUS, 0);       /* clear status */
 	sonic_tda_put(dev, entry, SONIC_TD_FRAG_COUNT, 1);   /* single fragment */
 	sonic_tda_put(dev, entry, SONIC_TD_PKTSIZE, length); /* length of packet */
@@ -246,10 +275,6 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev)
 	sonic_tda_put(dev, entry, SONIC_TD_LINK,
 		sonic_tda_get(dev, entry, SONIC_TD_LINK) | SONIC_EOL);
 
-	/*
-	 * Must set tx_skb[entry] only after clearing status, and
-	 * before clearing EOL and before stopping queue
-	 */
 	wmb();
 	lp->tx_len[entry] = length;
 	lp->tx_laddr[entry] = laddr;
@@ -272,6 +297,8 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev)
 
 	SONIC_WRITE(SONIC_CMD, SONIC_CR_TXP);
 
+	spin_unlock_irqrestore(&lp->lock, flags);
+
 	return NETDEV_TX_OK;
 }
 
@@ -284,15 +311,28 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
 	struct net_device *dev = dev_id;
 	struct sonic_local *lp = netdev_priv(dev);
 	int status;
+	unsigned long flags;
+
+	/* The lock has two purposes. Firstly, it synchronizes sonic_interrupt()
+	 * with sonic_send_packet() so that the two functions can share state.
+	 * Secondly, it makes sonic_interrupt() re-entrant, as that is required
+	 * by macsonic which must use two IRQs with different priority levels.
+	 */
+	spin_lock_irqsave(&lp->lock, flags);
+
+	status = SONIC_READ(SONIC_ISR) & SONIC_IMR_DEFAULT;
+	if (!status) {
+		spin_unlock_irqrestore(&lp->lock, flags);
 
-	if (!(status = SONIC_READ(SONIC_ISR) & SONIC_IMR_DEFAULT))
 		return IRQ_NONE;
+	}
 
 	do {
+		SONIC_WRITE(SONIC_ISR, status); /* clear the interrupt(s) */
+
 		if (status & SONIC_INT_PKTRX) {
 			netif_dbg(lp, intr, dev, "%s: packet rx\n", __func__);
 			sonic_rx(dev);	/* got packet(s) */
-			SONIC_WRITE(SONIC_ISR, SONIC_INT_PKTRX); /* clear the interrupt */
 		}
 
 		if (status & SONIC_INT_TXDN) {
@@ -300,11 +340,12 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
 			int td_status;
 			int freed_some = 0;
 
-			/* At this point, cur_tx is the index of a TD that is one of:
-			 *   unallocated/freed                          (status set   & tx_skb[entry] clear)
-			 *   allocated and sent                         (status set   & tx_skb[entry] set  )
-			 *   allocated and not yet sent                 (status clear & tx_skb[entry] set  )
-			 *   still being allocated by sonic_send_packet (status clear & tx_skb[entry] clear)
+			/* The state of a Transmit Descriptor may be inferred
+			 * from { tx_skb[entry], td_status } as follows.
+			 * { clear, clear } => the TD has never been used
+			 * { set,   clear } => the TD was handed to SONIC
+			 * { set,   set   } => the TD was handed back
+			 * { clear, set   } => the TD is available for re-use
 			 */
 
 			netif_dbg(lp, intr, dev, "%s: tx done\n", __func__);
@@ -313,18 +354,19 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
 				if ((td_status = sonic_tda_get(dev, entry, SONIC_TD_STATUS)) == 0)
 					break;
 
-				if (td_status & 0x0001) {
+				if (td_status & SONIC_TCR_PTX) {
 					lp->stats.tx_packets++;
 					lp->stats.tx_bytes += sonic_tda_get(dev, entry, SONIC_TD_PKTSIZE);
 				} else {
-					lp->stats.tx_errors++;
-					if (td_status & 0x0642)
+					if (td_status & (SONIC_TCR_EXD |
+					    SONIC_TCR_EXC | SONIC_TCR_BCM))
 						lp->stats.tx_aborted_errors++;
-					if (td_status & 0x0180)
+					if (td_status &
+					    (SONIC_TCR_NCRS | SONIC_TCR_CRLS))
 						lp->stats.tx_carrier_errors++;
-					if (td_status & 0x0020)
+					if (td_status & SONIC_TCR_OWC)
 						lp->stats.tx_window_errors++;
-					if (td_status & 0x0004)
+					if (td_status & SONIC_TCR_FU)
 						lp->stats.tx_fifo_errors++;
 				}
 
@@ -346,7 +388,6 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
 			if (freed_some || lp->tx_skb[entry] == NULL)
 				netif_wake_queue(dev);  /* The ring is no longer full */
 			lp->cur_tx = entry;
-			SONIC_WRITE(SONIC_ISR, SONIC_INT_TXDN); /* clear the interrupt */
 		}
 
 		/*
@@ -355,42 +396,37 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
 		if (status & SONIC_INT_RFO) {
 			netif_dbg(lp, rx_err, dev, "%s: rx fifo overrun\n",
 				  __func__);
-			lp->stats.rx_fifo_errors++;
-			SONIC_WRITE(SONIC_ISR, SONIC_INT_RFO); /* clear the interrupt */
 		}
 		if (status & SONIC_INT_RDE) {
 			netif_dbg(lp, rx_err, dev, "%s: rx descriptors exhausted\n",
 				  __func__);
-			lp->stats.rx_dropped++;
-			SONIC_WRITE(SONIC_ISR, SONIC_INT_RDE); /* clear the interrupt */
 		}
 		if (status & SONIC_INT_RBAE) {
 			netif_dbg(lp, rx_err, dev, "%s: rx buffer area exceeded\n",
 				  __func__);
-			lp->stats.rx_dropped++;
-			SONIC_WRITE(SONIC_ISR, SONIC_INT_RBAE); /* clear the interrupt */
 		}
 
 		/* counter overruns; all counters are 16bit wide */
-		if (status & SONIC_INT_FAE) {
+		if (status & SONIC_INT_FAE)
 			lp->stats.rx_frame_errors += 65536;
-			SONIC_WRITE(SONIC_ISR, SONIC_INT_FAE); /* clear the interrupt */
-		}
-		if (status & SONIC_INT_CRC) {
+		if (status & SONIC_INT_CRC)
 			lp->stats.rx_crc_errors += 65536;
-			SONIC_WRITE(SONIC_ISR, SONIC_INT_CRC); /* clear the interrupt */
-		}
-		if (status & SONIC_INT_MP) {
+		if (status & SONIC_INT_MP)
 			lp->stats.rx_missed_errors += 65536;
-			SONIC_WRITE(SONIC_ISR, SONIC_INT_MP); /* clear the interrupt */
-		}
 
 		/* transmit error */
 		if (status & SONIC_INT_TXER) {
-			if (SONIC_READ(SONIC_TCR) & SONIC_TCR_FU)
-				netif_dbg(lp, tx_err, dev, "%s: tx fifo underrun\n",
-					  __func__);
-			SONIC_WRITE(SONIC_ISR, SONIC_INT_TXER); /* clear the interrupt */
+			u16 tcr = SONIC_READ(SONIC_TCR);
+
+			netif_dbg(lp, tx_err, dev, "%s: TXER intr, TCR %04x\n",
+				  __func__, tcr);
+
+			if (tcr & (SONIC_TCR_EXD | SONIC_TCR_EXC |
+				   SONIC_TCR_FU | SONIC_TCR_BCM)) {
+				/* Aborted transmission. Try again. */
+				netif_stop_queue(dev);
+				SONIC_WRITE(SONIC_CMD, SONIC_CR_TXP);
+			}
 		}
 
 		/* bus retry */
@@ -400,107 +436,164 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
 			/* ... to help debug DMA problems causing endless interrupts. */
 			/* Bounce the eth interface to turn on the interrupt again. */
 			SONIC_WRITE(SONIC_IMR, 0);
-			SONIC_WRITE(SONIC_ISR, SONIC_INT_BR); /* clear the interrupt */
 		}
 
-		/* load CAM done */
-		if (status & SONIC_INT_LCD)
-			SONIC_WRITE(SONIC_ISR, SONIC_INT_LCD); /* clear the interrupt */
-	} while((status = SONIC_READ(SONIC_ISR) & SONIC_IMR_DEFAULT));
+		status = SONIC_READ(SONIC_ISR) & SONIC_IMR_DEFAULT;
+	} while (status);
+
+	spin_unlock_irqrestore(&lp->lock, flags);
+
 	return IRQ_HANDLED;
 }
 
+/* Return the array index corresponding to a given Receive Buffer pointer. */
+static int index_from_addr(struct sonic_local *lp, dma_addr_t addr,
+			   unsigned int last)
+{
+	unsigned int i = last;
+
+	do {
+		i = (i + 1) & SONIC_RRS_MASK;
+		if (addr == lp->rx_laddr[i])
+			return i;
+	} while (i != last);
+
+	return -ENOENT;
+}
+
+/* Allocate and map a new skb to be used as a receive buffer. */
+static bool sonic_alloc_rb(struct net_device *dev, struct sonic_local *lp,
+			   struct sk_buff **new_skb, dma_addr_t *new_addr)
+{
+	*new_skb = netdev_alloc_skb(dev, SONIC_RBSIZE + 2);
+	if (!*new_skb)
+		return false;
+
+	if (SONIC_BUS_SCALE(lp->dma_bitmode) == 2)
+		skb_reserve(*new_skb, 2);
+
+	*new_addr = dma_map_single(lp->device, skb_put(*new_skb, SONIC_RBSIZE),
+				   SONIC_RBSIZE, DMA_FROM_DEVICE);
+	if (!*new_addr) {
+		dev_kfree_skb(*new_skb);
+		*new_skb = NULL;
+		return false;
+	}
+
+	return true;
+}
+
+/* Place a new receive resource in the Receive Resource Area and update RWP. */
+static void sonic_update_rra(struct net_device *dev, struct sonic_local *lp,
+			     dma_addr_t old_addr, dma_addr_t new_addr)
+{
+	unsigned int entry = sonic_rr_entry(dev, SONIC_READ(SONIC_RWP));
+	unsigned int end = sonic_rr_entry(dev, SONIC_READ(SONIC_RRP));
+	u32 buf;
+
+	/* The resources in the range [RRP, RWP) belong to the SONIC. This loop
+	 * scans the other resources in the RRA, those in the range [RWP, RRP).
+	 */
+	do {
+		buf = (sonic_rra_get(dev, entry, SONIC_RR_BUFADR_H) << 16) |
+		      sonic_rra_get(dev, entry, SONIC_RR_BUFADR_L);
+
+		if (buf == old_addr)
+			break;
+
+		entry = (entry + 1) & SONIC_RRS_MASK;
+	} while (entry != end);
+
+	WARN_ONCE(buf != old_addr, "failed to find resource!\n");
+
+	sonic_rra_put(dev, entry, SONIC_RR_BUFADR_H, new_addr >> 16);
+	sonic_rra_put(dev, entry, SONIC_RR_BUFADR_L, new_addr & 0xffff);
+
+	entry = (entry + 1) & SONIC_RRS_MASK;
+
+	SONIC_WRITE(SONIC_RWP, sonic_rr_addr(dev, entry));
+}
+
 /*
  * We have a good packet(s), pass it/them up the network stack.
  */
 static void sonic_rx(struct net_device *dev)
 {
 	struct sonic_local *lp = netdev_priv(dev);
-	int status;
 	int entry = lp->cur_rx;
+	int prev_entry = lp->eol_rx;
+	bool rbe = false;
 
 	while (sonic_rda_get(dev, entry, SONIC_RD_IN_USE) == 0) {
-		struct sk_buff *used_skb;
-		struct sk_buff *new_skb;
-		dma_addr_t new_laddr;
-		u16 bufadr_l;
-		u16 bufadr_h;
-		int pkt_len;
-
-		status = sonic_rda_get(dev, entry, SONIC_RD_STATUS);
-		if (status & SONIC_RCR_PRX) {
-			/* Malloc up new buffer. */
-			new_skb = netdev_alloc_skb(dev, SONIC_RBSIZE + 2);
-			if (new_skb == NULL) {
-				lp->stats.rx_dropped++;
+		u16 status = sonic_rda_get(dev, entry, SONIC_RD_STATUS);
+
+		/* If the RD has LPKT set, the chip has finished with the RB */
+		if ((status & SONIC_RCR_PRX) && (status & SONIC_RCR_LPKT)) {
+			struct sk_buff *new_skb;
+			dma_addr_t new_laddr;
+			u32 addr = (sonic_rda_get(dev, entry,
+						  SONIC_RD_PKTPTR_H) << 16) |
+				   sonic_rda_get(dev, entry, SONIC_RD_PKTPTR_L);
+			int i = index_from_addr(lp, addr, entry);
+
+			if (i < 0) {
+				WARN_ONCE(1, "failed to find buffer!\n");
 				break;
 			}
-			/* provide 16 byte IP header alignment unless DMA requires otherwise */
-			if(SONIC_BUS_SCALE(lp->dma_bitmode) == 2)
-				skb_reserve(new_skb, 2);
-
-			new_laddr = dma_map_single(lp->device, skb_put(new_skb, SONIC_RBSIZE),
-		                               SONIC_RBSIZE, DMA_FROM_DEVICE);
-			if (!new_laddr) {
-				dev_kfree_skb(new_skb);
-				printk(KERN_ERR "%s: Failed to map rx buffer, dropping packet.\n", dev->name);
+
+			if (sonic_alloc_rb(dev, lp, &new_skb, &new_laddr)) {
+				struct sk_buff *used_skb = lp->rx_skb[i];
+				int pkt_len;
+
+				/* Pass the used buffer up the stack */
+				dma_unmap_single(lp->device, addr, SONIC_RBSIZE,
+						 DMA_FROM_DEVICE);
+
+				pkt_len = sonic_rda_get(dev, entry,
+							SONIC_RD_PKTLEN);
+				skb_trim(used_skb, pkt_len);
+				used_skb->protocol = eth_type_trans(used_skb,
+								    dev);
+				netif_rx(used_skb);
+				lp->stats.rx_packets++;
+				lp->stats.rx_bytes += pkt_len;
+
+				lp->rx_skb[i] = new_skb;
+				lp->rx_laddr[i] = new_laddr;
+			} else {
+				/* Failed to obtain a new buffer so re-use it */
+				new_laddr = addr;
 				lp->stats.rx_dropped++;
-				break;
 			}
-
-			/* now we have a new skb to replace it, pass the used one up the stack */
-			dma_unmap_single(lp->device, lp->rx_laddr[entry], SONIC_RBSIZE, DMA_FROM_DEVICE);
-			used_skb = lp->rx_skb[entry];
-			pkt_len = sonic_rda_get(dev, entry, SONIC_RD_PKTLEN);
-			skb_trim(used_skb, pkt_len);
-			used_skb->protocol = eth_type_trans(used_skb, dev);
-			netif_rx(used_skb);
-			lp->stats.rx_packets++;
-			lp->stats.rx_bytes += pkt_len;
-
-			/* and insert the new skb */
-			lp->rx_laddr[entry] = new_laddr;
-			lp->rx_skb[entry] = new_skb;
-
-			bufadr_l = (unsigned long)new_laddr & 0xffff;
-			bufadr_h = (unsigned long)new_laddr >> 16;
-			sonic_rra_put(dev, entry, SONIC_RR_BUFADR_L, bufadr_l);
-			sonic_rra_put(dev, entry, SONIC_RR_BUFADR_H, bufadr_h);
-		} else {
-			/* This should only happen, if we enable accepting broken packets. */
-			lp->stats.rx_errors++;
-			if (status & SONIC_RCR_FAER)
-				lp->stats.rx_frame_errors++;
-			if (status & SONIC_RCR_CRCR)
-				lp->stats.rx_crc_errors++;
-		}
-		if (status & SONIC_RCR_LPKT) {
-			/*
-			 * this was the last packet out of the current receive buffer
-			 * give the buffer back to the SONIC
+			/* If RBE is already asserted when RWP advances then
+			 * it's safe to clear RBE after processing this packet.
 			 */
-			lp->cur_rwp += SIZEOF_SONIC_RR * SONIC_BUS_SCALE(lp->dma_bitmode);
-			if (lp->cur_rwp >= lp->rra_end) lp->cur_rwp = lp->rra_laddr & 0xffff;
-			SONIC_WRITE(SONIC_RWP, lp->cur_rwp);
-			if (SONIC_READ(SONIC_ISR) & SONIC_INT_RBE) {
-				netif_dbg(lp, rx_err, dev, "%s: rx buffer exhausted\n",
-					  __func__);
-				SONIC_WRITE(SONIC_ISR, SONIC_INT_RBE); /* clear the flag */
-			}
-		} else
-			printk(KERN_ERR "%s: rx desc without RCR_LPKT. Shouldn't happen !?\n",
-			     dev->name);
+			rbe = rbe || SONIC_READ(SONIC_ISR) & SONIC_INT_RBE;
+			sonic_update_rra(dev, lp, addr, new_laddr);
+		}
 		/*
 		 * give back the descriptor
 		 */
-		sonic_rda_put(dev, entry, SONIC_RD_LINK,
-			sonic_rda_get(dev, entry, SONIC_RD_LINK) | SONIC_EOL);
+		sonic_rda_put(dev, entry, SONIC_RD_STATUS, 0);
 		sonic_rda_put(dev, entry, SONIC_RD_IN_USE, 1);
-		sonic_rda_put(dev, lp->eol_rx, SONIC_RD_LINK,
-			sonic_rda_get(dev, lp->eol_rx, SONIC_RD_LINK) & ~SONIC_EOL);
-		lp->eol_rx = entry;
-		lp->cur_rx = entry = (entry + 1) & SONIC_RDS_MASK;
+
+		prev_entry = entry;
+		entry = (entry + 1) & SONIC_RDS_MASK;
+	}
+
+	lp->cur_rx = entry;
+
+	if (prev_entry != lp->eol_rx) {
+		/* Advance the EOL flag to put descriptors back into service */
+		sonic_rda_put(dev, prev_entry, SONIC_RD_LINK, SONIC_EOL |
+			      sonic_rda_get(dev, prev_entry, SONIC_RD_LINK));
+		sonic_rda_put(dev, lp->eol_rx, SONIC_RD_LINK, ~SONIC_EOL &
+			      sonic_rda_get(dev, lp->eol_rx, SONIC_RD_LINK));
+		lp->eol_rx = prev_entry;
 	}
+
+	if (rbe)
+		SONIC_WRITE(SONIC_ISR, SONIC_INT_RBE);
 	/*
 	 * If any worth-while packets have been received, netif_rx()
 	 * has done a mark_bh(NET_BH) for us and will work on them
@@ -550,6 +643,8 @@ static void sonic_multicast_list(struct net_device *dev)
 		    (netdev_mc_count(dev) > 15)) {
 			rcr |= SONIC_RCR_AMC;
 		} else {
+			unsigned long flags;
+
 			netif_dbg(lp, ifup, dev, "%s: mc_count %d\n", __func__,
 				  netdev_mc_count(dev));
 			sonic_set_cam_enable(dev, 1);  /* always enable our own address */
@@ -563,9 +658,14 @@ static void sonic_multicast_list(struct net_device *dev)
 				i++;
 			}
 			SONIC_WRITE(SONIC_CDC, 16);
-			/* issue Load CAM command */
 			SONIC_WRITE(SONIC_CDP, lp->cda_laddr & 0xffff);
+
+			/* LCAM and TXP commands can't be used simultaneously */
+			spin_lock_irqsave(&lp->lock, flags);
+			sonic_quiesce(dev, SONIC_CR_TXP);
 			SONIC_WRITE(SONIC_CMD, SONIC_CR_LCAM);
+			sonic_quiesce(dev, SONIC_CR_LCAM);
+			spin_unlock_irqrestore(&lp->lock, flags);
 		}
 	}
 
@@ -580,7 +680,6 @@ static void sonic_multicast_list(struct net_device *dev)
  */
 static int sonic_init(struct net_device *dev)
 {
-	unsigned int cmd;
 	struct sonic_local *lp = netdev_priv(dev);
 	int i;
 
@@ -592,12 +691,16 @@ static int sonic_init(struct net_device *dev)
 	SONIC_WRITE(SONIC_ISR, 0x7fff);
 	SONIC_WRITE(SONIC_CMD, SONIC_CR_RST);
 
+	/* While in reset mode, clear CAM Enable register */
+	SONIC_WRITE(SONIC_CE, 0);
+
 	/*
 	 * clear software reset flag, disable receiver, clear and
 	 * enable interrupts, then completely initialize the SONIC
 	 */
 	SONIC_WRITE(SONIC_CMD, 0);
-	SONIC_WRITE(SONIC_CMD, SONIC_CR_RXDIS);
+	SONIC_WRITE(SONIC_CMD, SONIC_CR_RXDIS | SONIC_CR_STP);
+	sonic_quiesce(dev, SONIC_CR_ALL);
 
 	/*
 	 * initialize the receive resource area
@@ -615,15 +718,10 @@ static int sonic_init(struct net_device *dev)
 	}
 
 	/* initialize all RRA registers */
-	lp->rra_end = (lp->rra_laddr + SONIC_NUM_RRS * SIZEOF_SONIC_RR *
-					SONIC_BUS_SCALE(lp->dma_bitmode)) & 0xffff;
-	lp->cur_rwp = (lp->rra_laddr + (SONIC_NUM_RRS - 1) * SIZEOF_SONIC_RR *
-					SONIC_BUS_SCALE(lp->dma_bitmode)) & 0xffff;
-
-	SONIC_WRITE(SONIC_RSA, lp->rra_laddr & 0xffff);
-	SONIC_WRITE(SONIC_REA, lp->rra_end);
-	SONIC_WRITE(SONIC_RRP, lp->rra_laddr & 0xffff);
-	SONIC_WRITE(SONIC_RWP, lp->cur_rwp);
+	SONIC_WRITE(SONIC_RSA, sonic_rr_addr(dev, 0));
+	SONIC_WRITE(SONIC_REA, sonic_rr_addr(dev, SONIC_NUM_RRS));
+	SONIC_WRITE(SONIC_RRP, sonic_rr_addr(dev, 0));
+	SONIC_WRITE(SONIC_RWP, sonic_rr_addr(dev, SONIC_NUM_RRS - 1));
 	SONIC_WRITE(SONIC_URRA, lp->rra_laddr >> 16);
 	SONIC_WRITE(SONIC_EOBC, (SONIC_RBSIZE >> 1) - (lp->dma_bitmode ? 2 : 1));
 
@@ -631,14 +729,7 @@ static int sonic_init(struct net_device *dev)
 	netif_dbg(lp, ifup, dev, "%s: issuing RRRA command\n", __func__);
 
 	SONIC_WRITE(SONIC_CMD, SONIC_CR_RRRA);
-	i = 0;
-	while (i++ < 100) {
-		if (SONIC_READ(SONIC_CMD) & SONIC_CR_RRRA)
-			break;
-	}
-
-	netif_dbg(lp, ifup, dev, "%s: status=%x, i=%d\n", __func__,
-		  SONIC_READ(SONIC_CMD), i);
+	sonic_quiesce(dev, SONIC_CR_RRRA);
 
 	/*
 	 * Initialize the receive descriptors so that they
@@ -713,28 +804,17 @@ static int sonic_init(struct net_device *dev)
 	 * load the CAM
 	 */
 	SONIC_WRITE(SONIC_CMD, SONIC_CR_LCAM);
-
-	i = 0;
-	while (i++ < 100) {
-		if (SONIC_READ(SONIC_ISR) & SONIC_INT_LCD)
-			break;
-	}
-	netif_dbg(lp, ifup, dev, "%s: CMD=%x, ISR=%x, i=%d\n", __func__,
-		  SONIC_READ(SONIC_CMD), SONIC_READ(SONIC_ISR), i);
+	sonic_quiesce(dev, SONIC_CR_LCAM);
 
 	/*
 	 * enable receiver, disable loopback
 	 * and enable all interrupts
 	 */
-	SONIC_WRITE(SONIC_CMD, SONIC_CR_RXEN | SONIC_CR_STP);
 	SONIC_WRITE(SONIC_RCR, SONIC_RCR_DEFAULT);
 	SONIC_WRITE(SONIC_TCR, SONIC_TCR_DEFAULT);
 	SONIC_WRITE(SONIC_ISR, 0x7fff);
 	SONIC_WRITE(SONIC_IMR, SONIC_IMR_DEFAULT);
-
-	cmd = SONIC_READ(SONIC_CMD);
-	if ((cmd & SONIC_CR_RXEN) == 0 || (cmd & SONIC_CR_STP) == 0)
-		printk(KERN_ERR "sonic_init: failed, status=%x\n", cmd);
+	SONIC_WRITE(SONIC_CMD, SONIC_CR_RXEN);
 
 	netif_dbg(lp, ifup, dev, "%s: new status=%x\n", __func__,
 		  SONIC_READ(SONIC_CMD));
diff --git a/drivers/net/ethernet/natsemi/sonic.h b/drivers/net/ethernet/natsemi/sonic.h
index 2b27f7049acb..1df6d2f06cc4 100644
--- a/drivers/net/ethernet/natsemi/sonic.h
+++ b/drivers/net/ethernet/natsemi/sonic.h
@@ -110,6 +110,9 @@
 #define SONIC_CR_TXP            0x0002
 #define SONIC_CR_HTX            0x0001
 
+#define SONIC_CR_ALL (SONIC_CR_LCAM | SONIC_CR_RRRA | \
+		      SONIC_CR_RXEN | SONIC_CR_TXP)
+
 /*
  * SONIC data configuration bits
  */
@@ -175,6 +178,7 @@
 #define SONIC_TCR_NCRS          0x0100
 #define SONIC_TCR_CRLS          0x0080
 #define SONIC_TCR_EXC           0x0040
+#define SONIC_TCR_OWC           0x0020
 #define SONIC_TCR_PMB           0x0008
 #define SONIC_TCR_FU            0x0004
 #define SONIC_TCR_BCM           0x0002
@@ -274,8 +278,9 @@
 #define SONIC_NUM_RDS   SONIC_NUM_RRS /* number of receive descriptors */
 #define SONIC_NUM_TDS   16            /* number of transmit descriptors */
 
-#define SONIC_RDS_MASK  (SONIC_NUM_RDS-1)
-#define SONIC_TDS_MASK  (SONIC_NUM_TDS-1)
+#define SONIC_RRS_MASK  (SONIC_NUM_RRS - 1)
+#define SONIC_RDS_MASK  (SONIC_NUM_RDS - 1)
+#define SONIC_TDS_MASK  (SONIC_NUM_TDS - 1)
 
 #define SONIC_RBSIZE	1520          /* size of one resource buffer */
 
@@ -312,8 +317,6 @@ struct sonic_local {
 	u32 rda_laddr;              /* logical DMA address of RDA */
 	dma_addr_t rx_laddr[SONIC_NUM_RRS]; /* logical DMA addresses of rx skbuffs */
 	dma_addr_t tx_laddr[SONIC_NUM_TDS]; /* logical DMA addresses of tx skbuffs */
-	unsigned int rra_end;
-	unsigned int cur_rwp;
 	unsigned int cur_rx;
 	unsigned int cur_tx;           /* first unacked transmit packet */
 	unsigned int eol_rx;
@@ -322,6 +325,7 @@ struct sonic_local {
 	int msg_enable;
 	struct device *device;         /* generic device */
 	struct net_device_stats stats;
+	spinlock_t lock;
 };
 
 #define TX_TIMEOUT (3 * HZ)
@@ -344,30 +348,30 @@ static void sonic_msg_init(struct net_device *dev);
    as far as we can tell. */
 /* OpenBSD calls this "SWO".  I'd like to think that sonic_buf_put()
    is a much better name. */
-static inline void sonic_buf_put(void* base, int bitmode,
+static inline void sonic_buf_put(u16 *base, int bitmode,
 				 int offset, __u16 val)
 {
 	if (bitmode)
 #ifdef __BIG_ENDIAN
-		((__u16 *) base + (offset*2))[1] = val;
+		__raw_writew(val, base + (offset * 2) + 1);
 #else
-		((__u16 *) base + (offset*2))[0] = val;
+		__raw_writew(val, base + (offset * 2) + 0);
 #endif
 	else
-	 	((__u16 *) base)[offset] = val;
+		__raw_writew(val, base + (offset * 1) + 0);
 }
 
-static inline __u16 sonic_buf_get(void* base, int bitmode,
+static inline __u16 sonic_buf_get(u16 *base, int bitmode,
 				  int offset)
 {
 	if (bitmode)
 #ifdef __BIG_ENDIAN
-		return ((volatile __u16 *) base + (offset*2))[1];
+		return __raw_readw(base + (offset * 2) + 1);
 #else
-		return ((volatile __u16 *) base + (offset*2))[0];
+		return __raw_readw(base + (offset * 2) + 0);
 #endif
 	else
-		return ((volatile __u16 *) base)[offset];
+		return __raw_readw(base + (offset * 1) + 0);
 }
 
 /* Inlines that you should actually use for reading/writing DMA buffers */
@@ -447,6 +451,22 @@ static inline __u16 sonic_rra_get(struct net_device* dev, int entry,
 			     (entry * SIZEOF_SONIC_RR) + offset);
 }
 
+static inline u16 sonic_rr_addr(struct net_device *dev, int entry)
+{
+	struct sonic_local *lp = netdev_priv(dev);
+
+	return lp->rra_laddr +
+	       entry * SIZEOF_SONIC_RR * SONIC_BUS_SCALE(lp->dma_bitmode);
+}
+
+static inline u16 sonic_rr_entry(struct net_device *dev, u16 addr)
+{
+	struct sonic_local *lp = netdev_priv(dev);
+
+	return (addr - (u16)lp->rra_laddr) / (SIZEOF_SONIC_RR *
+					      SONIC_BUS_SCALE(lp->dma_bitmode));
+}
+
 static const char version[] =
     "sonic.c:v0.92 20.9.98 tsbogend@alpha.franken.de\n";
 
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.h b/drivers/net/ethernet/neterion/vxge/vxge-config.h
index e678ba379598..628fa9b2f741 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-config.h
+++ b/drivers/net/ethernet/neterion/vxge/vxge-config.h
@@ -2045,7 +2045,7 @@ vxge_hw_vpath_strip_fcs_check(struct __vxge_hw_device *hldev, u64 vpath_mask);
 	if ((level >= VXGE_ERR && VXGE_COMPONENT_LL & VXGE_DEBUG_ERR_MASK) ||  \
 	    (level >= VXGE_TRACE && VXGE_COMPONENT_LL & VXGE_DEBUG_TRACE_MASK))\
 		if ((mask & VXGE_DEBUG_MASK) == mask)			       \
-			printk(fmt "\n", __VA_ARGS__);			       \
+			printk(fmt "\n", ##__VA_ARGS__);		       \
 } while (0)
 #else
 #define vxge_debug_ll(level, mask, fmt, ...)
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.h b/drivers/net/ethernet/neterion/vxge/vxge-main.h
index 59a57ff5e96a..9c86f4f9cd42 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-main.h
+++ b/drivers/net/ethernet/neterion/vxge/vxge-main.h
@@ -452,49 +452,49 @@ int vxge_fw_upgrade(struct vxgedev *vdev, char *fw_name, int override);
 
 #if (VXGE_DEBUG_LL_CONFIG & VXGE_DEBUG_MASK)
 #define vxge_debug_ll_config(level, fmt, ...) \
-	vxge_debug_ll(level, VXGE_DEBUG_LL_CONFIG, fmt, __VA_ARGS__)
+	vxge_debug_ll(level, VXGE_DEBUG_LL_CONFIG, fmt, ##__VA_ARGS__)
 #else
 #define vxge_debug_ll_config(level, fmt, ...)
 #endif
 
 #if (VXGE_DEBUG_INIT & VXGE_DEBUG_MASK)
 #define vxge_debug_init(level, fmt, ...) \
-	vxge_debug_ll(level, VXGE_DEBUG_INIT, fmt, __VA_ARGS__)
+	vxge_debug_ll(level, VXGE_DEBUG_INIT, fmt, ##__VA_ARGS__)
 #else
 #define vxge_debug_init(level, fmt, ...)
 #endif
 
 #if (VXGE_DEBUG_TX & VXGE_DEBUG_MASK)
 #define vxge_debug_tx(level, fmt, ...) \
-	vxge_debug_ll(level, VXGE_DEBUG_TX, fmt, __VA_ARGS__)
+	vxge_debug_ll(level, VXGE_DEBUG_TX, fmt, ##__VA_ARGS__)
 #else
 #define vxge_debug_tx(level, fmt, ...)
 #endif
 
 #if (VXGE_DEBUG_RX & VXGE_DEBUG_MASK)
 #define vxge_debug_rx(level, fmt, ...) \
-	vxge_debug_ll(level, VXGE_DEBUG_RX, fmt, __VA_ARGS__)
+	vxge_debug_ll(level, VXGE_DEBUG_RX, fmt, ##__VA_ARGS__)
 #else
 #define vxge_debug_rx(level, fmt, ...)
 #endif
 
 #if (VXGE_DEBUG_MEM & VXGE_DEBUG_MASK)
 #define vxge_debug_mem(level, fmt, ...) \
-	vxge_debug_ll(level, VXGE_DEBUG_MEM, fmt, __VA_ARGS__)
+	vxge_debug_ll(level, VXGE_DEBUG_MEM, fmt, ##__VA_ARGS__)
 #else
 #define vxge_debug_mem(level, fmt, ...)
 #endif
 
 #if (VXGE_DEBUG_ENTRYEXIT & VXGE_DEBUG_MASK)
 #define vxge_debug_entryexit(level, fmt, ...) \
-	vxge_debug_ll(level, VXGE_DEBUG_ENTRYEXIT, fmt, __VA_ARGS__)
+	vxge_debug_ll(level, VXGE_DEBUG_ENTRYEXIT, fmt, ##__VA_ARGS__)
 #else
 #define vxge_debug_entryexit(level, fmt, ...)
 #endif
 
 #if (VXGE_DEBUG_INTR & VXGE_DEBUG_MASK)
 #define vxge_debug_intr(level, fmt, ...) \
-	vxge_debug_ll(level, VXGE_DEBUG_INTR, fmt, __VA_ARGS__)
+	vxge_debug_ll(level, VXGE_DEBUG_INTR, fmt, ##__VA_ARGS__)
 #else
 #define vxge_debug_intr(level, fmt, ...)
 #endif
diff --git a/drivers/net/ethernet/netronome/nfp/abm/cls.c b/drivers/net/ethernet/netronome/nfp/abm/cls.c
index 39be107fbccc..ff3913085665 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/cls.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/cls.c
@@ -176,10 +176,8 @@ nfp_abm_u32_knode_replace(struct nfp_abm_link *alink,
 	u8 mask, val;
 	int err;
 
-	if (!nfp_abm_u32_check_knode(alink->abm, knode, proto, extack)) {
-		err = -EOPNOTSUPP;
+	if (!nfp_abm_u32_check_knode(alink->abm, knode, proto, extack))
 		goto err_delete;
-	}
 
 	tos_off = proto == htons(ETH_P_IP) ? 16 : 20;
 
@@ -200,18 +198,14 @@ nfp_abm_u32_knode_replace(struct nfp_abm_link *alink,
 		if ((iter->val & cmask) == (val & cmask) &&
 		    iter->band != knode->res->classid) {
 			NL_SET_ERR_MSG_MOD(extack, "conflict with already offloaded filter");
-			err = -EOPNOTSUPP;
 			goto err_delete;
 		}
 	}
 
 	if (!match) {
 		match = kzalloc(sizeof(*match), GFP_KERNEL);
-		if (!match) {
-			err = -ENOMEM;
-			goto err_delete;
-		}
-
+		if (!match)
+			return -ENOMEM;
 		list_add(&match->list, &alink->dscp_map);
 	}
 	match->handle = knode->handle;
@@ -227,7 +221,7 @@ nfp_abm_u32_knode_replace(struct nfp_abm_link *alink,
 
 err_delete:
 	nfp_abm_u32_knode_delete(alink, knode);
-	return err;
+	return -EOPNOTSUPP;
 }
 
 static int nfp_abm_setup_tc_block_cb(enum tc_setup_type type,
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c
index 9183b3e85d21..bdbf0726145e 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.c
@@ -283,6 +283,7 @@ nfp_abm_vnic_set_mac(struct nfp_pf *pf, struct nfp_abm *abm, struct nfp_net *nn,
 	if (!nfp_nsp_has_hwinfo_lookup(nsp)) {
 		nfp_warn(pf->cpp, "NSP doesn't support PF MAC generation\n");
 		eth_hw_addr_random(nn->dp.netdev);
+		nfp_nsp_close(nsp);
 		return;
 	}
 
@@ -332,8 +333,10 @@ nfp_abm_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id)
 		goto err_free_alink;
 
 	alink->prio_map = kzalloc(abm->prio_map_len, GFP_KERNEL);
-	if (!alink->prio_map)
+	if (!alink->prio_map) {
+		err = -ENOMEM;
 		goto err_free_alink;
+	}
 
 	/* This is a multi-host app, make sure MAC/PHY is up, but don't
 	 * make the MAC/PHY state follow the state of any of the ports.
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index f5ebd9403d72..71ee45bd2fee 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -1099,7 +1099,8 @@ __nfp_flower_update_merge_stats(struct nfp_app *app,
 		ctx_id = be32_to_cpu(sub_flow->meta.host_ctx_id);
 		priv->stats[ctx_id].pkts += pkts;
 		priv->stats[ctx_id].bytes += bytes;
-		max_t(u64, priv->stats[ctx_id].used, used);
+		priv->stats[ctx_id].used = max_t(u64, used,
+						 priv->stats[ctx_id].used);
 	}
 }
 
diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c
index 96f7a9818294..5245ffb0a806 100644
--- a/drivers/net/ethernet/ni/nixge.c
+++ b/drivers/net/ethernet/ni/nixge.c
@@ -1318,19 +1318,21 @@ static int nixge_probe(struct platform_device *pdev)
 	netif_napi_add(ndev, &priv->napi, nixge_poll, NAPI_POLL_WEIGHT);
 	err = nixge_of_get_resources(pdev);
 	if (err)
-		return err;
+		goto free_netdev;
 	__nixge_hw_set_mac_address(ndev);
 
 	priv->tx_irq = platform_get_irq_byname(pdev, "tx");
 	if (priv->tx_irq < 0) {
 		netdev_err(ndev, "could not find 'tx' irq");
-		return priv->tx_irq;
+		err = priv->tx_irq;
+		goto free_netdev;
 	}
 
 	priv->rx_irq = platform_get_irq_byname(pdev, "rx");
 	if (priv->rx_irq < 0) {
 		netdev_err(ndev, "could not find 'rx' irq");
-		return priv->rx_irq;
+		err = priv->rx_irq;
+		goto free_netdev;
 	}
 
 	priv->coalesce_count_rx = XAXIDMA_DFT_RX_THRESHOLD;
diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c
index b0c8be127bee..2f71e697f382 100644
--- a/drivers/net/ethernet/nxp/lpc_eth.c
+++ b/drivers/net/ethernet/nxp/lpc_eth.c
@@ -817,7 +817,8 @@ static int lpc_mii_init(struct netdata_local *pldat)
 	if (mdiobus_register(pldat->mii_bus))
 		goto err_out_unregister_bus;
 
-	if (lpc_mii_probe(pldat->ndev) != 0)
+	err = lpc_mii_probe(pldat->ndev);
+	if (err)
 		goto err_out_unregister_bus;
 
 	return 0;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index e61d1d905415..ea27220d6b14 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -396,7 +396,7 @@ static void qed_cxt_qm_iids(struct qed_hwfn *p_hwfn,
 		vf_tids += segs[NUM_TASK_PF_SEGMENTS].count;
 	}
 
-	iids->vf_cids += vf_cids * p_mngr->vf_count;
+	iids->vf_cids = vf_cids;
 	iids->tids += vf_tids * p_mngr->vf_count;
 
 	DP_VERBOSE(p_hwfn, QED_MSG_ILT,
@@ -2073,8 +2073,8 @@ static void qed_rdma_set_pf_params(struct qed_hwfn *p_hwfn,
 	num_srqs = min_t(u32, QED_RDMA_MAX_SRQS, p_params->num_srqs);
 
 	if (p_hwfn->mcp_info->func_info.protocol == QED_PCI_ETH_RDMA) {
-		DP_NOTICE(p_hwfn,
-			  "Current day drivers don't support RoCE & iWARP simultaneously on the same PF. Default to RoCE-only\n");
+		DP_VERBOSE(p_hwfn, QED_MSG_SP,
+			   "Current day drivers don't support RoCE & iWARP simultaneously on the same PF. Default to RoCE-only\n");
 		p_hwfn->hw_info.personality = QED_PCI_ETH_ROCE;
 	}
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c
index ab8cacbdee3e..01b6740af581 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c
@@ -7997,6 +7997,8 @@ static u32 qed_calc_regdump_header(enum debug_print_features feature,
 int qed_dbg_all_data(struct qed_dev *cdev, void *buffer)
 {
 	u8 cur_engine, omit_engine = 0, org_engine;
+	struct qed_hwfn *p_hwfn =
+		&cdev->hwfns[cdev->dbg_params.engine_for_debug];
 	u32 offset = 0, feature_size;
 	int rc;
 
@@ -8115,6 +8117,10 @@ int qed_dbg_all_data(struct qed_dev *cdev, void *buffer)
 		DP_ERR(cdev, "qed_dbg_mcp_trace failed. rc = %d\n", rc);
 	}
 
+	/* Re-populate nvm attribute info */
+	qed_mcp_nvm_info_free(p_hwfn);
+	qed_mcp_nvm_info_populate(p_hwfn);
+
 	/* nvm cfg1 */
 	rc = qed_dbg_nvm_image(cdev,
 			       (u8 *)buffer + offset + REGDUMP_HEADER_SIZE,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 8c40739e0d1b..ede2d1cc4c8a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -447,6 +447,8 @@ static void qed_dbg_user_data_free(struct qed_hwfn *p_hwfn)
 
 void qed_resc_free(struct qed_dev *cdev)
 {
+	struct qed_rdma_info *rdma_info;
+	struct qed_hwfn *p_hwfn;
 	int i;
 
 	if (IS_VF(cdev)) {
@@ -462,7 +464,8 @@ void qed_resc_free(struct qed_dev *cdev)
 	cdev->reset_stats = NULL;
 
 	for_each_hwfn(cdev, i) {
-		struct qed_hwfn *p_hwfn = &cdev->hwfns[i];
+		p_hwfn = cdev->hwfns + i;
+		rdma_info = p_hwfn->p_rdma_info;
 
 		qed_cxt_mngr_free(p_hwfn);
 		qed_qm_info_free(p_hwfn);
@@ -481,8 +484,10 @@ void qed_resc_free(struct qed_dev *cdev)
 			qed_ooo_free(p_hwfn);
 		}
 
-		if (QED_IS_RDMA_PERSONALITY(p_hwfn))
+		if (QED_IS_RDMA_PERSONALITY(p_hwfn) && rdma_info) {
+			qed_spq_unregister_async_cb(p_hwfn, rdma_info->proto);
 			qed_rdma_info_free(p_hwfn);
+		}
 
 		qed_iov_free(p_hwfn);
 		qed_l2_free(p_hwfn);
@@ -2146,7 +2151,7 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 		}
 
 		/* Log and clear previous pglue_b errors if such exist */
-		qed_pglueb_rbc_attn_handler(p_hwfn, p_hwfn->p_main_ptt);
+		qed_pglueb_rbc_attn_handler(p_hwfn, p_hwfn->p_main_ptt, true);
 
 		/* Enable the PF's internal FID_enable in the PXP */
 		rc = qed_pglueb_set_pfid_enable(p_hwfn, p_hwfn->p_main_ptt,
@@ -3434,12 +3439,6 @@ static int qed_get_dev_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	return 0;
 }
 
-static void qed_nvm_info_free(struct qed_hwfn *p_hwfn)
-{
-	kfree(p_hwfn->nvm_info.image_att);
-	p_hwfn->nvm_info.image_att = NULL;
-}
-
 static int qed_hw_prepare_single(struct qed_hwfn *p_hwfn,
 				 void __iomem *p_regview,
 				 void __iomem *p_doorbells,
@@ -3524,7 +3523,7 @@ static int qed_hw_prepare_single(struct qed_hwfn *p_hwfn,
 	return rc;
 err3:
 	if (IS_LEAD_HWFN(p_hwfn))
-		qed_nvm_info_free(p_hwfn);
+		qed_mcp_nvm_info_free(p_hwfn);
 err2:
 	if (IS_LEAD_HWFN(p_hwfn))
 		qed_iov_free_hw_info(p_hwfn->cdev);
@@ -3585,7 +3584,7 @@ int qed_hw_prepare(struct qed_dev *cdev,
 		if (rc) {
 			if (IS_PF(cdev)) {
 				qed_init_free(p_hwfn);
-				qed_nvm_info_free(p_hwfn);
+				qed_mcp_nvm_info_free(p_hwfn);
 				qed_mcp_free(p_hwfn);
 				qed_hw_hwfn_free(p_hwfn);
 			}
@@ -3619,7 +3618,7 @@ void qed_hw_remove(struct qed_dev *cdev)
 
 	qed_iov_free_hw_info(cdev);
 
-	qed_nvm_info_free(p_hwfn);
+	qed_mcp_nvm_info_free(p_hwfn);
 }
 
 static void qed_chain_free_next_ptr(struct qed_dev *cdev,
@@ -3664,26 +3663,20 @@ static void qed_chain_free_single(struct qed_dev *cdev,
 
 static void qed_chain_free_pbl(struct qed_dev *cdev, struct qed_chain *p_chain)
 {
-	void **pp_virt_addr_tbl = p_chain->pbl.pp_virt_addr_tbl;
+	struct addr_tbl_entry *pp_addr_tbl = p_chain->pbl.pp_addr_tbl;
 	u32 page_cnt = p_chain->page_cnt, i, pbl_size;
-	u8 *p_pbl_virt = p_chain->pbl_sp.p_virt_table;
 
-	if (!pp_virt_addr_tbl)
+	if (!pp_addr_tbl)
 		return;
 
-	if (!p_pbl_virt)
-		goto out;
-
 	for (i = 0; i < page_cnt; i++) {
-		if (!pp_virt_addr_tbl[i])
+		if (!pp_addr_tbl[i].virt_addr || !pp_addr_tbl[i].dma_map)
 			break;
 
 		dma_free_coherent(&cdev->pdev->dev,
 				  QED_CHAIN_PAGE_SIZE,
-				  pp_virt_addr_tbl[i],
-				  *(dma_addr_t *)p_pbl_virt);
-
-		p_pbl_virt += QED_CHAIN_PBL_ENTRY_SIZE;
+				  pp_addr_tbl[i].virt_addr,
+				  pp_addr_tbl[i].dma_map);
 	}
 
 	pbl_size = page_cnt * QED_CHAIN_PBL_ENTRY_SIZE;
@@ -3693,9 +3686,9 @@ static void qed_chain_free_pbl(struct qed_dev *cdev, struct qed_chain *p_chain)
 				  pbl_size,
 				  p_chain->pbl_sp.p_virt_table,
 				  p_chain->pbl_sp.p_phys_table);
-out:
-	vfree(p_chain->pbl.pp_virt_addr_tbl);
-	p_chain->pbl.pp_virt_addr_tbl = NULL;
+
+	vfree(p_chain->pbl.pp_addr_tbl);
+	p_chain->pbl.pp_addr_tbl = NULL;
 }
 
 void qed_chain_free(struct qed_dev *cdev, struct qed_chain *p_chain)
@@ -3796,19 +3789,19 @@ qed_chain_alloc_pbl(struct qed_dev *cdev,
 {
 	u32 page_cnt = p_chain->page_cnt, size, i;
 	dma_addr_t p_phys = 0, p_pbl_phys = 0;
-	void **pp_virt_addr_tbl = NULL;
+	struct addr_tbl_entry *pp_addr_tbl;
 	u8 *p_pbl_virt = NULL;
 	void *p_virt = NULL;
 
-	size = page_cnt * sizeof(*pp_virt_addr_tbl);
-	pp_virt_addr_tbl = vzalloc(size);
-	if (!pp_virt_addr_tbl)
+	size = page_cnt * sizeof(*pp_addr_tbl);
+	pp_addr_tbl =  vzalloc(size);
+	if (!pp_addr_tbl)
 		return -ENOMEM;
 
 	/* The allocation of the PBL table is done with its full size, since it
 	 * is expected to be successive.
 	 * qed_chain_init_pbl_mem() is called even in a case of an allocation
-	 * failure, since pp_virt_addr_tbl was previously allocated, and it
+	 * failure, since tbl was previously allocated, and it
 	 * should be saved to allow its freeing during the error flow.
 	 */
 	size = page_cnt * QED_CHAIN_PBL_ENTRY_SIZE;
@@ -3822,8 +3815,7 @@ qed_chain_alloc_pbl(struct qed_dev *cdev,
 		p_chain->b_external_pbl = true;
 	}
 
-	qed_chain_init_pbl_mem(p_chain, p_pbl_virt, p_pbl_phys,
-			       pp_virt_addr_tbl);
+	qed_chain_init_pbl_mem(p_chain, p_pbl_virt, p_pbl_phys, pp_addr_tbl);
 	if (!p_pbl_virt)
 		return -ENOMEM;
 
@@ -3842,7 +3834,8 @@ qed_chain_alloc_pbl(struct qed_dev *cdev,
 		/* Fill the PBL table with the physical address of the page */
 		*(dma_addr_t *)p_pbl_virt = p_phys;
 		/* Keep the virtual address of the page */
-		p_chain->pbl.pp_virt_addr_tbl[i] = p_virt;
+		p_chain->pbl.pp_addr_tbl[i].virt_addr = p_virt;
+		p_chain->pbl.pp_addr_tbl[i].dma_map = p_phys;
 
 		p_pbl_virt += QED_CHAIN_PBL_ENTRY_SIZE;
 	}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c
index 70a771cd8788..7f871d2b1217 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.c
@@ -256,9 +256,10 @@ out:
 #define PGLUE_ATTENTION_ZLR_VALID		(1 << 25)
 #define PGLUE_ATTENTION_ILT_VALID		(1 << 23)
 
-int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn,
-				struct qed_ptt *p_ptt)
+int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
+				bool hw_init)
 {
+	char msg[256];
 	u32 tmp;
 
 	tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_TX_ERR_WR_DETAILS2);
@@ -272,22 +273,23 @@ int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn,
 		details = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_TX_ERR_WR_DETAILS);
 
-		DP_NOTICE(p_hwfn,
-			  "Illegal write by chip to [%08x:%08x] blocked.\n"
-			  "Details: %08x [PFID %02x, VFID %02x, VF_VALID %02x]\n"
-			  "Details2 %08x [Was_error %02x BME deassert %02x FID_enable deassert %02x]\n",
-			  addr_hi, addr_lo, details,
-			  (u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_PFID),
-			  (u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_VFID),
-			  GET_FIELD(details,
-				    PGLUE_ATTENTION_DETAILS_VF_VALID) ? 1 : 0,
-			  tmp,
-			  GET_FIELD(tmp,
-				    PGLUE_ATTENTION_DETAILS2_WAS_ERR) ? 1 : 0,
-			  GET_FIELD(tmp,
-				    PGLUE_ATTENTION_DETAILS2_BME) ? 1 : 0,
-			  GET_FIELD(tmp,
-				    PGLUE_ATTENTION_DETAILS2_FID_EN) ? 1 : 0);
+		snprintf(msg, sizeof(msg),
+			 "Illegal write by chip to [%08x:%08x] blocked.\n"
+			 "Details: %08x [PFID %02x, VFID %02x, VF_VALID %02x]\n"
+			 "Details2 %08x [Was_error %02x BME deassert %02x FID_enable deassert %02x]",
+			 addr_hi, addr_lo, details,
+			 (u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_PFID),
+			 (u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_VFID),
+			 !!GET_FIELD(details, PGLUE_ATTENTION_DETAILS_VF_VALID),
+			 tmp,
+			 !!GET_FIELD(tmp, PGLUE_ATTENTION_DETAILS2_WAS_ERR),
+			 !!GET_FIELD(tmp, PGLUE_ATTENTION_DETAILS2_BME),
+			 !!GET_FIELD(tmp, PGLUE_ATTENTION_DETAILS2_FID_EN));
+
+		if (hw_init)
+			DP_VERBOSE(p_hwfn, NETIF_MSG_INTR, "%s\n", msg);
+		else
+			DP_NOTICE(p_hwfn, "%s\n", msg);
 	}
 
 	tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_TX_ERR_RD_DETAILS2);
@@ -320,8 +322,14 @@ int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn,
 	}
 
 	tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_TX_ERR_WR_DETAILS_ICPL);
-	if (tmp & PGLUE_ATTENTION_ICPL_VALID)
-		DP_NOTICE(p_hwfn, "ICPL error - %08x\n", tmp);
+	if (tmp & PGLUE_ATTENTION_ICPL_VALID) {
+		snprintf(msg, sizeof(msg), "ICPL error - %08x", tmp);
+
+		if (hw_init)
+			DP_VERBOSE(p_hwfn, NETIF_MSG_INTR, "%s\n", msg);
+		else
+			DP_NOTICE(p_hwfn, "%s\n", msg);
+	}
 
 	tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_MASTER_ZLR_ERR_DETAILS);
 	if (tmp & PGLUE_ATTENTION_ZLR_VALID) {
@@ -360,7 +368,7 @@ int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn,
 
 static int qed_pglueb_rbc_attn_cb(struct qed_hwfn *p_hwfn)
 {
-	return qed_pglueb_rbc_attn_handler(p_hwfn, p_hwfn->p_dpc_ptt);
+	return qed_pglueb_rbc_attn_handler(p_hwfn, p_hwfn->p_dpc_ptt, false);
 }
 
 #define QED_DORQ_ATTENTION_REASON_MASK  (0xfffff)
@@ -1172,7 +1180,8 @@ static int qed_int_attentions(struct qed_hwfn *p_hwfn)
 			index, attn_bits, attn_acks, asserted_bits,
 			deasserted_bits, p_sb_attn_sw->known_attn);
 	} else if (asserted_bits == 0x100) {
-		DP_INFO(p_hwfn, "MFW indication via attention\n");
+		DP_VERBOSE(p_hwfn, NETIF_MSG_INTR,
+			   "MFW indication via attention\n");
 	} else {
 		DP_VERBOSE(p_hwfn, NETIF_MSG_INTR,
 			   "MFW indication [deassertion]\n");
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.h b/drivers/net/ethernet/qlogic/qed/qed_int.h
index d473b522afc5..ba5cfebf2d0d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.h
@@ -431,7 +431,7 @@ int qed_int_set_timer_res(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
 
 #define QED_MAPPING_MEMORY_SIZE(dev)	(NUM_OF_SBS(dev))
 
-int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn,
-				struct qed_ptt *p_ptt);
+int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
+				bool hw_init);
 
 #endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
index eeea8683d99b..d9ea2eed0ee9 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
@@ -2808,8 +2808,6 @@ int qed_iwarp_stop(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	if (rc)
 		return rc;
 
-	qed_spq_unregister_async_cb(p_hwfn, PROTOCOLID_IWARP);
-
 	return qed_iwarp_ll2_stop(p_hwfn, p_ptt);
 }
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index c875a2fa7596..d26f6b1ebc2b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -974,9 +974,6 @@ static void qed_update_pf_params(struct qed_dev *cdev,
 #define QED_PERIODIC_DB_REC_INTERVAL_MS		100
 #define QED_PERIODIC_DB_REC_INTERVAL \
 	msecs_to_jiffies(QED_PERIODIC_DB_REC_INTERVAL_MS)
-#define QED_PERIODIC_DB_REC_WAIT_COUNT		10
-#define QED_PERIODIC_DB_REC_WAIT_INTERVAL \
-	(QED_PERIODIC_DB_REC_INTERVAL_MS / QED_PERIODIC_DB_REC_WAIT_COUNT)
 
 static int qed_slowpath_delayed_work(struct qed_hwfn *hwfn,
 				     enum qed_slowpath_wq_flag wq_flag,
@@ -1010,7 +1007,7 @@ void qed_periodic_db_rec_start(struct qed_hwfn *p_hwfn)
 
 static void qed_slowpath_wq_stop(struct qed_dev *cdev)
 {
-	int i, sleep_count = QED_PERIODIC_DB_REC_WAIT_COUNT;
+	int i;
 
 	if (IS_VF(cdev))
 		return;
@@ -1022,13 +1019,7 @@ static void qed_slowpath_wq_stop(struct qed_dev *cdev)
 		/* Stop queuing new delayed works */
 		cdev->hwfns[i].slowpath_wq_active = false;
 
-		/* Wait until the last periodic doorbell recovery is executed */
-		while (test_bit(QED_SLOWPATH_PERIODIC_DB_REC,
-				&cdev->hwfns[i].slowpath_task_flags) &&
-		       sleep_count--)
-			msleep(QED_PERIODIC_DB_REC_WAIT_INTERVAL);
-
-		flush_workqueue(cdev->hwfns[i].slowpath_wq);
+		cancel_delayed_work(&cdev->hwfns[i].slowpath_task);
 		destroy_workqueue(cdev->hwfns[i].slowpath_wq);
 	}
 }
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index cc27fd60d689..d54a1a8d0853 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -3149,6 +3149,13 @@ err0:
 	return rc;
 }
 
+void qed_mcp_nvm_info_free(struct qed_hwfn *p_hwfn)
+{
+	kfree(p_hwfn->nvm_info.image_att);
+	p_hwfn->nvm_info.image_att = NULL;
+	p_hwfn->nvm_info.valid = false;
+}
+
 int
 qed_mcp_get_nvm_image_att(struct qed_hwfn *p_hwfn,
 			  enum qed_nvm_images image_id,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
index 261c1a392e2c..5673a3521835 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
@@ -1180,6 +1180,13 @@ int qed_mcp_set_capabilities(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
 void qed_mcp_read_ufp_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
 
 /**
+ * @brief Delete nvm info shadow in the given hardware function
+ *
+ * @param p_hwfn
+ */
+void qed_mcp_nvm_info_free(struct qed_hwfn *p_hwfn);
+
+/**
  * @brief Populate the nvm info shadow in the given hardware function
  *
  * @param p_hwfn
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c
index e49fada85410..83817bb50e9f 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c
@@ -113,7 +113,6 @@ void qed_roce_stop(struct qed_hwfn *p_hwfn)
 			break;
 		}
 	}
-	qed_spq_unregister_async_cb(p_hwfn, PROTOCOLID_ROCE);
 }
 
 static void qed_rdma_copy_gids(struct qed_rdma_qp *qp, __le32 *src_gid,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c
index 5dda547772c1..93a0fbf6a132 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c
@@ -81,12 +81,17 @@ static void qed_vf_pf_req_end(struct qed_hwfn *p_hwfn, int req_status)
 	mutex_unlock(&(p_hwfn->vf_iov_info->mutex));
 }
 
+#define QED_VF_CHANNEL_USLEEP_ITERATIONS	90
+#define QED_VF_CHANNEL_USLEEP_DELAY		100
+#define QED_VF_CHANNEL_MSLEEP_ITERATIONS	10
+#define QED_VF_CHANNEL_MSLEEP_DELAY		25
+
 static int qed_send_msg2pf(struct qed_hwfn *p_hwfn, u8 *done, u32 resp_size)
 {
 	union vfpf_tlvs *p_req = p_hwfn->vf_iov_info->vf2pf_request;
 	struct ustorm_trigger_vf_zone trigger;
 	struct ustorm_vf_zone *zone_data;
-	int rc = 0, time = 100;
+	int iter, rc = 0;
 
 	zone_data = (struct ustorm_vf_zone *)PXP_VF_BAR0_START_USDM_ZONE_B;
 
@@ -126,11 +131,19 @@ static int qed_send_msg2pf(struct qed_hwfn *p_hwfn, u8 *done, u32 resp_size)
 	REG_WR(p_hwfn, (uintptr_t)&zone_data->trigger, *((u32 *)&trigger));
 
 	/* When PF would be done with the response, it would write back to the
-	 * `done' address. Poll until then.
+	 * `done' address from a coherent DMA zone. Poll until then.
 	 */
-	while ((!*done) && time) {
-		msleep(25);
-		time--;
+
+	iter = QED_VF_CHANNEL_USLEEP_ITERATIONS;
+	while (!*done && iter--) {
+		udelay(QED_VF_CHANNEL_USLEEP_DELAY);
+		dma_rmb();
+	}
+
+	iter = QED_VF_CHANNEL_MSLEEP_ITERATIONS;
+	while (!*done && iter--) {
+		msleep(QED_VF_CHANNEL_MSLEEP_DELAY);
+		dma_rmb();
 	}
 
 	if (!*done) {
diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index 92fe226980fd..f993d19ac0ee 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -162,6 +162,8 @@ struct qede_rdma_dev {
 	struct list_head entry;
 	struct list_head rdma_event_list;
 	struct workqueue_struct *rdma_wq;
+	struct kref refcnt;
+	struct completion event_comp;
 	bool exp_recovery;
 };
 
@@ -555,12 +557,14 @@ int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto,
 #define RX_RING_SIZE		((u16)BIT(RX_RING_SIZE_POW))
 #define NUM_RX_BDS_MAX		(RX_RING_SIZE - 1)
 #define NUM_RX_BDS_MIN		128
+#define NUM_RX_BDS_KDUMP_MIN	63
 #define NUM_RX_BDS_DEF		((u16)BIT(10) - 1)
 
 #define TX_RING_SIZE_POW	13
 #define TX_RING_SIZE		((u16)BIT(TX_RING_SIZE_POW))
 #define NUM_TX_BDS_MAX		(TX_RING_SIZE - 1)
 #define NUM_TX_BDS_MIN		128
+#define NUM_TX_BDS_KDUMP_MIN	63
 #define NUM_TX_BDS_DEF		NUM_TX_BDS_MAX
 
 #define QEDE_MIN_PKT_LEN		64
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index ff522260ca3b..174437df3631 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -29,6 +29,7 @@
  * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
+#include <linux/crash_dump.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/version.h>
@@ -720,8 +721,14 @@ static struct qede_dev *qede_alloc_etherdev(struct qed_dev *cdev,
 	edev->dp_module = dp_module;
 	edev->dp_level = dp_level;
 	edev->ops = qed_ops;
-	edev->q_num_rx_buffers = NUM_RX_BDS_DEF;
-	edev->q_num_tx_buffers = NUM_TX_BDS_DEF;
+
+	if (is_kdump_kernel()) {
+		edev->q_num_rx_buffers = NUM_RX_BDS_KDUMP_MIN;
+		edev->q_num_tx_buffers = NUM_TX_BDS_KDUMP_MIN;
+	} else {
+		edev->q_num_rx_buffers = NUM_RX_BDS_DEF;
+		edev->q_num_tx_buffers = NUM_TX_BDS_DEF;
+	}
 
 	DP_INFO(edev, "Allocated netdev with %d tx queues and %d rx queues\n",
 		info->num_queues, info->num_queues);
@@ -1164,7 +1171,7 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level,
 
 	/* PTP not supported on VFs */
 	if (!is_vf)
-		qede_ptp_enable(edev, (mode == QEDE_PROBE_NORMAL));
+		qede_ptp_enable(edev);
 
 	edev->ops->register_ops(cdev, &qede_ll_ops, edev);
 
@@ -1253,6 +1260,7 @@ static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode)
 	if (system_state == SYSTEM_POWER_OFF)
 		return;
 	qed_ops->common->remove(cdev);
+	edev->cdev = NULL;
 
 	/* Since this can happen out-of-sync with other flows,
 	 * don't release the netdevice until after slowpath stop
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c
index bddb2b5982dc..fb019a7cbdaa 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c
@@ -397,6 +397,7 @@ void qede_ptp_disable(struct qede_dev *edev)
 	if (ptp->tx_skb) {
 		dev_kfree_skb_any(ptp->tx_skb);
 		ptp->tx_skb = NULL;
+		clear_bit_unlock(QEDE_FLAGS_PTP_TX_IN_PRORGESS, &edev->flags);
 	}
 
 	/* Disable PTP in HW */
@@ -408,7 +409,7 @@ void qede_ptp_disable(struct qede_dev *edev)
 	edev->ptp = NULL;
 }
 
-static int qede_ptp_init(struct qede_dev *edev, bool init_tc)
+static int qede_ptp_init(struct qede_dev *edev)
 {
 	struct qede_ptp *ptp;
 	int rc;
@@ -429,25 +430,19 @@ static int qede_ptp_init(struct qede_dev *edev, bool init_tc)
 	/* Init work queue for Tx timestamping */
 	INIT_WORK(&ptp->work, qede_ptp_task);
 
-	/* Init cyclecounter and timecounter. This is done only in the first
-	 * load. If done in every load, PTP application will fail when doing
-	 * unload / load (e.g. MTU change) while it is running.
-	 */
-	if (init_tc) {
-		memset(&ptp->cc, 0, sizeof(ptp->cc));
-		ptp->cc.read = qede_ptp_read_cc;
-		ptp->cc.mask = CYCLECOUNTER_MASK(64);
-		ptp->cc.shift = 0;
-		ptp->cc.mult = 1;
-
-		timecounter_init(&ptp->tc, &ptp->cc,
-				 ktime_to_ns(ktime_get_real()));
-	}
+	/* Init cyclecounter and timecounter */
+	memset(&ptp->cc, 0, sizeof(ptp->cc));
+	ptp->cc.read = qede_ptp_read_cc;
+	ptp->cc.mask = CYCLECOUNTER_MASK(64);
+	ptp->cc.shift = 0;
+	ptp->cc.mult = 1;
 
-	return rc;
+	timecounter_init(&ptp->tc, &ptp->cc, ktime_to_ns(ktime_get_real()));
+
+	return 0;
 }
 
-int qede_ptp_enable(struct qede_dev *edev, bool init_tc)
+int qede_ptp_enable(struct qede_dev *edev)
 {
 	struct qede_ptp *ptp;
 	int rc;
@@ -468,7 +463,7 @@ int qede_ptp_enable(struct qede_dev *edev, bool init_tc)
 
 	edev->ptp = ptp;
 
-	rc = qede_ptp_init(edev, init_tc);
+	rc = qede_ptp_init(edev);
 	if (rc)
 		goto err1;
 
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.h b/drivers/net/ethernet/qlogic/qede/qede_ptp.h
index 691a14c4b2c5..89c7f3cf3ee2 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ptp.h
+++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.h
@@ -41,7 +41,7 @@ void qede_ptp_rx_ts(struct qede_dev *edev, struct sk_buff *skb);
 void qede_ptp_tx_ts(struct qede_dev *edev, struct sk_buff *skb);
 int qede_ptp_hw_ts(struct qede_dev *edev, struct ifreq *req);
 void qede_ptp_disable(struct qede_dev *edev);
-int qede_ptp_enable(struct qede_dev *edev, bool init_tc);
+int qede_ptp_enable(struct qede_dev *edev);
 int qede_ptp_get_ts_info(struct qede_dev *edev, struct ethtool_ts_info *ts);
 
 static inline void qede_ptp_record_rx_ts(struct qede_dev *edev,
diff --git a/drivers/net/ethernet/qlogic/qede/qede_rdma.c b/drivers/net/ethernet/qlogic/qede/qede_rdma.c
index ffabc2d2f082..668ccc9d49f8 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_rdma.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_rdma.c
@@ -59,6 +59,9 @@ static void _qede_rdma_dev_add(struct qede_dev *edev)
 static int qede_rdma_create_wq(struct qede_dev *edev)
 {
 	INIT_LIST_HEAD(&edev->rdma_info.rdma_event_list);
+	kref_init(&edev->rdma_info.refcnt);
+	init_completion(&edev->rdma_info.event_comp);
+
 	edev->rdma_info.rdma_wq = create_singlethread_workqueue("rdma_wq");
 	if (!edev->rdma_info.rdma_wq) {
 		DP_NOTICE(edev, "qedr: Could not create workqueue\n");
@@ -83,10 +86,26 @@ static void qede_rdma_cleanup_event(struct qede_dev *edev)
 	}
 }
 
+static void qede_rdma_complete_event(struct kref *ref)
+{
+	struct qede_rdma_dev *rdma_dev =
+		container_of(ref, struct qede_rdma_dev, refcnt);
+
+	/* no more events will be added after this */
+	complete(&rdma_dev->event_comp);
+}
+
 static void qede_rdma_destroy_wq(struct qede_dev *edev)
 {
+	/* Avoid race with add_event flow, make sure it finishes before
+	 * we start accessing the list and cleaning up the work
+	 */
+	kref_put(&edev->rdma_info.refcnt, qede_rdma_complete_event);
+	wait_for_completion(&edev->rdma_info.event_comp);
+
 	qede_rdma_cleanup_event(edev);
 	destroy_workqueue(edev->rdma_info.rdma_wq);
+	edev->rdma_info.rdma_wq = NULL;
 }
 
 int qede_rdma_dev_add(struct qede_dev *edev, bool recovery)
@@ -307,18 +326,27 @@ static void qede_rdma_add_event(struct qede_dev *edev,
 	if (edev->rdma_info.exp_recovery)
 		return;
 
-	if (!edev->rdma_info.qedr_dev)
+	if (!edev->rdma_info.qedr_dev || !edev->rdma_info.rdma_wq)
 		return;
 
+	/* We don't want the cleanup flow to start while we're allocating and
+	 * scheduling the work
+	 */
+	if (!kref_get_unless_zero(&edev->rdma_info.refcnt))
+		return; /* already being destroyed */
+
 	event_node = qede_rdma_get_free_event_node(edev);
 	if (!event_node)
-		return;
+		goto out;
 
 	event_node->event = event;
 	event_node->ptr = edev;
 
 	INIT_WORK(&event_node->work, qede_rdma_handle_event);
 	queue_work(edev->rdma_info.rdma_wq, &event_node->work);
+
+out:
+	kref_put(&edev->rdma_info.refcnt, qede_rdma_complete_event);
 }
 
 void qede_rdma_dev_event_open(struct qede_dev *edev)
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index 2a533280b124..29b9c728a65e 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -3651,7 +3651,7 @@ int qlcnic_83xx_interrupt_test(struct net_device *netdev)
 	ahw->diag_cnt = 0;
 	ret = qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_INTRPT_TEST);
 	if (ret)
-		goto fail_diag_irq;
+		goto fail_mbx_args;
 
 	if (adapter->flags & QLCNIC_MSIX_ENABLED)
 		intrpt_id = ahw->intr_tbl[0].id;
@@ -3681,6 +3681,8 @@ int qlcnic_83xx_interrupt_test(struct net_device *netdev)
 
 done:
 	qlcnic_free_mbx_args(&cmd);
+
+fail_mbx_args:
 	qlcnic_83xx_diag_free_res(netdev, drv_sds_rings);
 
 fail_diag_irq:
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
index a496390b8632..cda5b0a9e948 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
@@ -1720,7 +1720,7 @@ static int qlcnic_83xx_get_reset_instruction_template(struct qlcnic_adapter *p_d
 
 	ahw->reset.seq_error = 0;
 	ahw->reset.buff = kzalloc(QLC_83XX_RESTART_TEMPLATE_SIZE, GFP_KERNEL);
-	if (p_dev->ahw->reset.buff == NULL)
+	if (ahw->reset.buff == NULL)
 		return -ENOMEM;
 
 	p_buff = p_dev->ahw->reset.buff;
@@ -2043,6 +2043,7 @@ static void qlcnic_83xx_exec_template_cmd(struct qlcnic_adapter *p_dev,
 			break;
 		}
 		entry += p_hdr->size;
+		cond_resched();
 	}
 	p_dev->ahw->reset.seq_index = index;
 }
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c
index afa10a163da1..f34ae8c75bc5 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c
@@ -703,6 +703,7 @@ static u32 qlcnic_read_memory_test_agent(struct qlcnic_adapter *adapter,
 		addr += 16;
 		reg_read -= 16;
 		ret += 16;
+		cond_resched();
 	}
 out:
 	mutex_unlock(&adapter->ahw->mem_lock);
@@ -1383,6 +1384,7 @@ int qlcnic_dump_fw(struct qlcnic_adapter *adapter)
 		buf_offset += entry->hdr.cap_size;
 		entry_offset += entry->hdr.offset;
 		buffer = fw_dump->data + buf_offset;
+		cond_resched();
 	}
 
 	fw_dump->clr = 1;
diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c
index 59c2349b59df..b02536fb21fb 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac.c
@@ -485,13 +485,24 @@ static int emac_clks_phase1_init(struct platform_device *pdev,
 
 	ret = clk_prepare_enable(adpt->clk[EMAC_CLK_CFG_AHB]);
 	if (ret)
-		return ret;
+		goto disable_clk_axi;
 
 	ret = clk_set_rate(adpt->clk[EMAC_CLK_HIGH_SPEED], 19200000);
 	if (ret)
-		return ret;
+		goto disable_clk_cfg_ahb;
+
+	ret = clk_prepare_enable(adpt->clk[EMAC_CLK_HIGH_SPEED]);
+	if (ret)
+		goto disable_clk_cfg_ahb;
 
-	return clk_prepare_enable(adpt->clk[EMAC_CLK_HIGH_SPEED]);
+	return 0;
+
+disable_clk_cfg_ahb:
+	clk_disable_unprepare(adpt->clk[EMAC_CLK_CFG_AHB]);
+disable_clk_axi:
+	clk_disable_unprepare(adpt->clk[EMAC_CLK_AXI]);
+
+	return ret;
 }
 
 /* Enable clocks; needs emac_clks_phase1_init to be called before */
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
index 06de59521fc4..decfd82fdef3 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
@@ -13,25 +13,6 @@
 #include "rmnet_vnd.h"
 #include "rmnet_private.h"
 
-/* Locking scheme -
- * The shared resource which needs to be protected is realdev->rx_handler_data.
- * For the writer path, this is using rtnl_lock(). The writer paths are
- * rmnet_newlink(), rmnet_dellink() and rmnet_force_unassociate_device(). These
- * paths are already called with rtnl_lock() acquired in. There is also an
- * ASSERT_RTNL() to ensure that we are calling with rtnl acquired. For
- * dereference here, we will need to use rtnl_dereference(). Dev list writing
- * needs to happen with rtnl_lock() acquired for netdev_master_upper_dev_link().
- * For the reader path, the real_dev->rx_handler_data is called in the TX / RX
- * path. We only need rcu_read_lock() for these scenarios. In these cases,
- * the rcu_read_lock() is held in __dev_queue_xmit() and
- * netif_receive_skb_internal(), so readers need to use rcu_dereference_rtnl()
- * to get the relevant information. For dev list reading, we again acquire
- * rcu_read_lock() in rmnet_dellink() for netdev_master_upper_dev_get_rcu().
- * We also use unregister_netdevice_many() to free all rmnet devices in
- * rmnet_force_unassociate_device() so we dont lose the rtnl_lock() and free in
- * same context.
- */
-
 /* Local Definitions and Declarations */
 
 static const struct nla_policy rmnet_policy[IFLA_RMNET_MAX + 1] = {
@@ -51,9 +32,10 @@ rmnet_get_port_rtnl(const struct net_device *real_dev)
 	return rtnl_dereference(real_dev->rx_handler_data);
 }
 
-static int rmnet_unregister_real_device(struct net_device *real_dev,
-					struct rmnet_port *port)
+static int rmnet_unregister_real_device(struct net_device *real_dev)
 {
+	struct rmnet_port *port = rmnet_get_port_rtnl(real_dev);
+
 	if (port->nr_rmnet_devs)
 		return -EINVAL;
 
@@ -61,24 +43,29 @@ static int rmnet_unregister_real_device(struct net_device *real_dev,
 
 	kfree(port);
 
-	/* release reference on real_dev */
-	dev_put(real_dev);
-
 	netdev_dbg(real_dev, "Removed from rmnet\n");
 	return 0;
 }
 
-static int rmnet_register_real_device(struct net_device *real_dev)
+static int rmnet_register_real_device(struct net_device *real_dev,
+				      struct netlink_ext_ack *extack)
 {
 	struct rmnet_port *port;
 	int rc, entry;
 
 	ASSERT_RTNL();
 
-	if (rmnet_is_real_dev_registered(real_dev))
+	if (rmnet_is_real_dev_registered(real_dev)) {
+		port = rmnet_get_port_rtnl(real_dev);
+		if (port->rmnet_mode != RMNET_EPMODE_VND) {
+			NL_SET_ERR_MSG_MOD(extack, "bridge device already exists");
+			return -EINVAL;
+		}
+
 		return 0;
+	}
 
-	port = kzalloc(sizeof(*port), GFP_ATOMIC);
+	port = kzalloc(sizeof(*port), GFP_KERNEL);
 	if (!port)
 		return -ENOMEM;
 
@@ -89,9 +76,6 @@ static int rmnet_register_real_device(struct net_device *real_dev)
 		return -EBUSY;
 	}
 
-	/* hold on to real dev for MAP data */
-	dev_hold(real_dev);
-
 	for (entry = 0; entry < RMNET_MAX_LOGICAL_EP; entry++)
 		INIT_HLIST_HEAD(&port->muxed_ep[entry]);
 
@@ -99,28 +83,33 @@ static int rmnet_register_real_device(struct net_device *real_dev)
 	return 0;
 }
 
-static void rmnet_unregister_bridge(struct net_device *dev,
-				    struct rmnet_port *port)
+static void rmnet_unregister_bridge(struct rmnet_port *port)
 {
-	struct rmnet_port *bridge_port;
-	struct net_device *bridge_dev;
+	struct net_device *bridge_dev, *real_dev, *rmnet_dev;
+	struct rmnet_port *real_port;
 
 	if (port->rmnet_mode != RMNET_EPMODE_BRIDGE)
 		return;
 
-	/* bridge slave handling */
+	rmnet_dev = port->rmnet_dev;
 	if (!port->nr_rmnet_devs) {
-		bridge_dev = port->bridge_ep;
+		/* bridge device */
+		real_dev = port->bridge_ep;
+		bridge_dev = port->dev;
 
-		bridge_port = rmnet_get_port_rtnl(bridge_dev);
-		bridge_port->bridge_ep = NULL;
-		bridge_port->rmnet_mode = RMNET_EPMODE_VND;
+		real_port = rmnet_get_port_rtnl(real_dev);
+		real_port->bridge_ep = NULL;
+		real_port->rmnet_mode = RMNET_EPMODE_VND;
 	} else {
+		/* real device */
 		bridge_dev = port->bridge_ep;
 
-		bridge_port = rmnet_get_port_rtnl(bridge_dev);
-		rmnet_unregister_real_device(bridge_dev, bridge_port);
+		port->bridge_ep = NULL;
+		port->rmnet_mode = RMNET_EPMODE_VND;
 	}
+
+	netdev_upper_dev_unlink(bridge_dev, rmnet_dev);
+	rmnet_unregister_real_device(bridge_dev);
 }
 
 static int rmnet_newlink(struct net *src_net, struct net_device *dev,
@@ -135,29 +124,38 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev,
 	int err = 0;
 	u16 mux_id;
 
+	if (!tb[IFLA_LINK]) {
+		NL_SET_ERR_MSG_MOD(extack, "link not specified");
+		return -EINVAL;
+	}
+
 	real_dev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK]));
-	if (!real_dev || !dev)
+	if (!real_dev) {
+		NL_SET_ERR_MSG_MOD(extack, "link does not exist");
 		return -ENODEV;
+	}
 
-	if (!data[IFLA_RMNET_MUX_ID])
-		return -EINVAL;
-
-	ep = kzalloc(sizeof(*ep), GFP_ATOMIC);
+	ep = kzalloc(sizeof(*ep), GFP_KERNEL);
 	if (!ep)
 		return -ENOMEM;
 
 	mux_id = nla_get_u16(data[IFLA_RMNET_MUX_ID]);
 
-	err = rmnet_register_real_device(real_dev);
+	err = rmnet_register_real_device(real_dev, extack);
 	if (err)
 		goto err0;
 
 	port = rmnet_get_port_rtnl(real_dev);
-	err = rmnet_vnd_newlink(mux_id, dev, port, real_dev, ep);
+	err = rmnet_vnd_newlink(mux_id, dev, port, real_dev, ep, extack);
 	if (err)
 		goto err1;
 
+	err = netdev_upper_dev_link(real_dev, dev, extack);
+	if (err < 0)
+		goto err2;
+
 	port->rmnet_mode = mode;
+	port->rmnet_dev = dev;
 
 	hlist_add_head_rcu(&ep->hlnode, &port->muxed_ep[mux_id]);
 
@@ -173,8 +171,11 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev,
 
 	return 0;
 
+err2:
+	unregister_netdevice(dev);
+	rmnet_vnd_dellink(mux_id, port, ep);
 err1:
-	rmnet_unregister_real_device(real_dev, port);
+	rmnet_unregister_real_device(real_dev);
 err0:
 	kfree(ep);
 	return err;
@@ -183,77 +184,74 @@ err0:
 static void rmnet_dellink(struct net_device *dev, struct list_head *head)
 {
 	struct rmnet_priv *priv = netdev_priv(dev);
-	struct net_device *real_dev;
+	struct net_device *real_dev, *bridge_dev;
+	struct rmnet_port *real_port, *bridge_port;
 	struct rmnet_endpoint *ep;
-	struct rmnet_port *port;
-	u8 mux_id;
+	u8 mux_id = priv->mux_id;
 
 	real_dev = priv->real_dev;
 
-	if (!real_dev || !rmnet_is_real_dev_registered(real_dev))
+	if (!rmnet_is_real_dev_registered(real_dev))
 		return;
 
-	port = rmnet_get_port_rtnl(real_dev);
-
-	mux_id = rmnet_vnd_get_mux(dev);
+	real_port = rmnet_get_port_rtnl(real_dev);
+	bridge_dev = real_port->bridge_ep;
+	if (bridge_dev) {
+		bridge_port = rmnet_get_port_rtnl(bridge_dev);
+		rmnet_unregister_bridge(bridge_port);
+	}
 
-	ep = rmnet_get_endpoint(port, mux_id);
+	ep = rmnet_get_endpoint(real_port, mux_id);
 	if (ep) {
 		hlist_del_init_rcu(&ep->hlnode);
-		rmnet_unregister_bridge(dev, port);
-		rmnet_vnd_dellink(mux_id, port, ep);
+		rmnet_vnd_dellink(mux_id, real_port, ep);
 		kfree(ep);
 	}
-	rmnet_unregister_real_device(real_dev, port);
 
+	netdev_upper_dev_unlink(real_dev, dev);
+	rmnet_unregister_real_device(real_dev);
 	unregister_netdevice_queue(dev, head);
 }
 
-static void rmnet_force_unassociate_device(struct net_device *dev)
+static void rmnet_force_unassociate_device(struct net_device *real_dev)
 {
-	struct net_device *real_dev = dev;
 	struct hlist_node *tmp_ep;
 	struct rmnet_endpoint *ep;
 	struct rmnet_port *port;
 	unsigned long bkt_ep;
 	LIST_HEAD(list);
 
-	if (!rmnet_is_real_dev_registered(real_dev))
-		return;
-
-	ASSERT_RTNL();
-
-	port = rmnet_get_port_rtnl(dev);
-
-	rcu_read_lock();
-	rmnet_unregister_bridge(dev, port);
-
-	hash_for_each_safe(port->muxed_ep, bkt_ep, tmp_ep, ep, hlnode) {
-		unregister_netdevice_queue(ep->egress_dev, &list);
-		rmnet_vnd_dellink(ep->mux_id, port, ep);
+	port = rmnet_get_port_rtnl(real_dev);
 
-		hlist_del_init_rcu(&ep->hlnode);
-		kfree(ep);
+	if (port->nr_rmnet_devs) {
+		/* real device */
+		rmnet_unregister_bridge(port);
+		hash_for_each_safe(port->muxed_ep, bkt_ep, tmp_ep, ep, hlnode) {
+			unregister_netdevice_queue(ep->egress_dev, &list);
+			netdev_upper_dev_unlink(real_dev, ep->egress_dev);
+			rmnet_vnd_dellink(ep->mux_id, port, ep);
+			hlist_del_init_rcu(&ep->hlnode);
+			kfree(ep);
+		}
+		rmnet_unregister_real_device(real_dev);
+		unregister_netdevice_many(&list);
+	} else {
+		rmnet_unregister_bridge(port);
 	}
-
-	rcu_read_unlock();
-	unregister_netdevice_many(&list);
-
-	rmnet_unregister_real_device(real_dev, port);
 }
 
 static int rmnet_config_notify_cb(struct notifier_block *nb,
 				  unsigned long event, void *data)
 {
-	struct net_device *dev = netdev_notifier_info_to_dev(data);
+	struct net_device *real_dev = netdev_notifier_info_to_dev(data);
 
-	if (!dev)
+	if (!rmnet_is_real_dev_registered(real_dev))
 		return NOTIFY_DONE;
 
 	switch (event) {
 	case NETDEV_UNREGISTER:
-		netdev_dbg(dev, "Kernel unregister\n");
-		rmnet_force_unassociate_device(dev);
+		netdev_dbg(real_dev, "Kernel unregister\n");
+		rmnet_force_unassociate_device(real_dev);
 		break;
 
 	default:
@@ -272,12 +270,16 @@ static int rmnet_rtnl_validate(struct nlattr *tb[], struct nlattr *data[],
 {
 	u16 mux_id;
 
-	if (!data || !data[IFLA_RMNET_MUX_ID])
+	if (!data || !data[IFLA_RMNET_MUX_ID]) {
+		NL_SET_ERR_MSG_MOD(extack, "MUX ID not specified");
 		return -EINVAL;
+	}
 
 	mux_id = nla_get_u16(data[IFLA_RMNET_MUX_ID]);
-	if (mux_id > (RMNET_MAX_LOGICAL_EP - 1))
+	if (mux_id > (RMNET_MAX_LOGICAL_EP - 1)) {
+		NL_SET_ERR_MSG_MOD(extack, "invalid MUX ID");
 		return -ERANGE;
+	}
 
 	return 0;
 }
@@ -288,32 +290,41 @@ static int rmnet_changelink(struct net_device *dev, struct nlattr *tb[],
 {
 	struct rmnet_priv *priv = netdev_priv(dev);
 	struct net_device *real_dev;
-	struct rmnet_endpoint *ep;
 	struct rmnet_port *port;
 	u16 mux_id;
 
 	if (!dev)
 		return -ENODEV;
 
-	real_dev = __dev_get_by_index(dev_net(dev),
-				      nla_get_u32(tb[IFLA_LINK]));
-
-	if (!real_dev || !rmnet_is_real_dev_registered(real_dev))
+	real_dev = priv->real_dev;
+	if (!rmnet_is_real_dev_registered(real_dev))
 		return -ENODEV;
 
 	port = rmnet_get_port_rtnl(real_dev);
 
 	if (data[IFLA_RMNET_MUX_ID]) {
 		mux_id = nla_get_u16(data[IFLA_RMNET_MUX_ID]);
-		ep = rmnet_get_endpoint(port, priv->mux_id);
-		if (!ep)
-			return -ENODEV;
 
-		hlist_del_init_rcu(&ep->hlnode);
-		hlist_add_head_rcu(&ep->hlnode, &port->muxed_ep[mux_id]);
+		if (mux_id != priv->mux_id) {
+			struct rmnet_endpoint *ep;
+
+			ep = rmnet_get_endpoint(port, priv->mux_id);
+			if (!ep)
+				return -ENODEV;
 
-		ep->mux_id = mux_id;
-		priv->mux_id = mux_id;
+			if (rmnet_get_endpoint(port, mux_id)) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "MUX ID already exists");
+				return -EINVAL;
+			}
+
+			hlist_del_init_rcu(&ep->hlnode);
+			hlist_add_head_rcu(&ep->hlnode,
+					   &port->muxed_ep[mux_id]);
+
+			ep->mux_id = mux_id;
+			priv->mux_id = mux_id;
+		}
 	}
 
 	if (data[IFLA_RMNET_FLAGS]) {
@@ -379,11 +390,10 @@ struct rtnl_link_ops rmnet_link_ops __read_mostly = {
 	.fill_info	= rmnet_fill_info,
 };
 
-/* Needs either rcu_read_lock() or rtnl lock */
-struct rmnet_port *rmnet_get_port(struct net_device *real_dev)
+struct rmnet_port *rmnet_get_port_rcu(struct net_device *real_dev)
 {
 	if (rmnet_is_real_dev_registered(real_dev))
-		return rcu_dereference_rtnl(real_dev->rx_handler_data);
+		return rcu_dereference_bh(real_dev->rx_handler_data);
 	else
 		return NULL;
 }
@@ -409,24 +419,43 @@ int rmnet_add_bridge(struct net_device *rmnet_dev,
 	struct rmnet_port *port, *slave_port;
 	int err;
 
-	port = rmnet_get_port(real_dev);
+	port = rmnet_get_port_rtnl(real_dev);
 
 	/* If there is more than one rmnet dev attached, its probably being
 	 * used for muxing. Skip the briding in that case
 	 */
-	if (port->nr_rmnet_devs > 1)
+	if (port->nr_rmnet_devs > 1) {
+		NL_SET_ERR_MSG_MOD(extack, "more than one rmnet dev attached");
 		return -EINVAL;
+	}
+
+	if (port->rmnet_mode != RMNET_EPMODE_VND) {
+		NL_SET_ERR_MSG_MOD(extack, "more than one bridge dev attached");
+		return -EINVAL;
+	}
+
+	if (rmnet_is_real_dev_registered(slave_dev)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "slave cannot be another rmnet dev");
 
-	if (rmnet_is_real_dev_registered(slave_dev))
 		return -EBUSY;
+	}
 
-	err = rmnet_register_real_device(slave_dev);
+	err = rmnet_register_real_device(slave_dev, extack);
 	if (err)
 		return -EBUSY;
 
-	slave_port = rmnet_get_port(slave_dev);
+	err = netdev_master_upper_dev_link(slave_dev, rmnet_dev, NULL, NULL,
+					   extack);
+	if (err) {
+		rmnet_unregister_real_device(slave_dev);
+		return err;
+	}
+
+	slave_port = rmnet_get_port_rtnl(slave_dev);
 	slave_port->rmnet_mode = RMNET_EPMODE_BRIDGE;
 	slave_port->bridge_ep = real_dev;
+	slave_port->rmnet_dev = rmnet_dev;
 
 	port->rmnet_mode = RMNET_EPMODE_BRIDGE;
 	port->bridge_ep = slave_dev;
@@ -438,16 +467,9 @@ int rmnet_add_bridge(struct net_device *rmnet_dev,
 int rmnet_del_bridge(struct net_device *rmnet_dev,
 		     struct net_device *slave_dev)
 {
-	struct rmnet_priv *priv = netdev_priv(rmnet_dev);
-	struct net_device *real_dev = priv->real_dev;
-	struct rmnet_port *port, *slave_port;
-
-	port = rmnet_get_port(real_dev);
-	port->rmnet_mode = RMNET_EPMODE_VND;
-	port->bridge_ep = NULL;
+	struct rmnet_port *port = rmnet_get_port_rtnl(slave_dev);
 
-	slave_port = rmnet_get_port(slave_dev);
-	rmnet_unregister_real_device(slave_dev, slave_port);
+	rmnet_unregister_bridge(port);
 
 	netdev_dbg(slave_dev, "removed from rmnet as slave\n");
 	return 0;
@@ -473,8 +495,8 @@ static int __init rmnet_init(void)
 
 static void __exit rmnet_exit(void)
 {
-	unregister_netdevice_notifier(&rmnet_dev_notifier);
 	rtnl_link_unregister(&rmnet_link_ops);
+	unregister_netdevice_notifier(&rmnet_dev_notifier);
 }
 
 module_init(rmnet_init)
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h
index cd0a6bcbe74a..be515982d628 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h
@@ -28,6 +28,7 @@ struct rmnet_port {
 	u8 rmnet_mode;
 	struct hlist_head muxed_ep[RMNET_MAX_LOGICAL_EP];
 	struct net_device *bridge_ep;
+	struct net_device *rmnet_dev;
 };
 
 extern struct rtnl_link_ops rmnet_link_ops;
@@ -65,7 +66,7 @@ struct rmnet_priv {
 	struct rmnet_priv_stats stats;
 };
 
-struct rmnet_port *rmnet_get_port(struct net_device *real_dev);
+struct rmnet_port *rmnet_get_port_rcu(struct net_device *real_dev);
 struct rmnet_endpoint *rmnet_get_endpoint(struct rmnet_port *port, u8 mux_id);
 int rmnet_add_bridge(struct net_device *rmnet_dev,
 		     struct net_device *slave_dev,
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c
index 1b74bc160402..29a7bfa2584d 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c
@@ -159,6 +159,9 @@ static int rmnet_map_egress_handler(struct sk_buff *skb,
 static void
 rmnet_bridge_handler(struct sk_buff *skb, struct net_device *bridge_dev)
 {
+	if (skb_mac_header_was_set(skb))
+		skb_push(skb, skb->mac_len);
+
 	if (bridge_dev) {
 		skb->dev = bridge_dev;
 		dev_queue_xmit(skb);
@@ -184,7 +187,7 @@ rx_handler_result_t rmnet_rx_handler(struct sk_buff **pskb)
 		return RX_HANDLER_PASS;
 
 	dev = skb->dev;
-	port = rmnet_get_port(dev);
+	port = rmnet_get_port_rcu(dev);
 
 	switch (port->rmnet_mode) {
 	case RMNET_EPMODE_VND:
@@ -217,7 +220,7 @@ void rmnet_egress_handler(struct sk_buff *skb)
 	skb->dev = priv->real_dev;
 	mux_id = priv->mux_id;
 
-	port = rmnet_get_port(skb->dev);
+	port = rmnet_get_port_rcu(skb->dev);
 	if (!port)
 		goto drop;
 
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
index 509dfc895a33..d7c52e398e4a 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
@@ -222,16 +222,17 @@ void rmnet_vnd_setup(struct net_device *rmnet_dev)
 int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev,
 		      struct rmnet_port *port,
 		      struct net_device *real_dev,
-		      struct rmnet_endpoint *ep)
+		      struct rmnet_endpoint *ep,
+		      struct netlink_ext_ack *extack)
+
 {
 	struct rmnet_priv *priv = netdev_priv(rmnet_dev);
 	int rc;
 
-	if (ep->egress_dev)
-		return -EINVAL;
-
-	if (rmnet_get_endpoint(port, id))
+	if (rmnet_get_endpoint(port, id)) {
+		NL_SET_ERR_MSG_MOD(extack, "MUX ID already exists");
 		return -EBUSY;
+	}
 
 	rmnet_dev->hw_features = NETIF_F_RXCSUM;
 	rmnet_dev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
@@ -266,14 +267,6 @@ int rmnet_vnd_dellink(u8 id, struct rmnet_port *port,
 	return 0;
 }
 
-u8 rmnet_vnd_get_mux(struct net_device *rmnet_dev)
-{
-	struct rmnet_priv *priv;
-
-	priv = netdev_priv(rmnet_dev);
-	return priv->mux_id;
-}
-
 int rmnet_vnd_do_flow_control(struct net_device *rmnet_dev, int enable)
 {
 	netdev_dbg(rmnet_dev, "Setting VND TX queue state to %d\n", enable);
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h
index 54cbaf3c3bc4..4967f3461ed1 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h
@@ -11,11 +11,11 @@ int rmnet_vnd_do_flow_control(struct net_device *dev, int enable);
 int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev,
 		      struct rmnet_port *port,
 		      struct net_device *real_dev,
-		      struct rmnet_endpoint *ep);
+		      struct rmnet_endpoint *ep,
+		      struct netlink_ext_ack *extack);
 int rmnet_vnd_dellink(u8 id, struct rmnet_port *port,
 		      struct rmnet_endpoint *ep);
 void rmnet_vnd_rx_fixup(struct sk_buff *skb, struct net_device *dev);
 void rmnet_vnd_tx_fixup(struct sk_buff *skb, struct net_device *dev);
-u8 rmnet_vnd_get_mux(struct net_device *rmnet_dev);
 void rmnet_vnd_setup(struct net_device *dev);
 #endif /* _RMNET_VND_H_ */
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index a2ff23f0288f..76ba85822966 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -2241,6 +2241,8 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp)
 		{ 0x7cf, 0x348,	RTL_GIGA_MAC_VER_07 },
 		{ 0x7cf, 0x248,	RTL_GIGA_MAC_VER_07 },
 		{ 0x7cf, 0x340,	RTL_GIGA_MAC_VER_13 },
+		/* RTL8401, reportedly works if treated as RTL8101e */
+		{ 0x7cf, 0x240,	RTL_GIGA_MAC_VER_13 },
 		{ 0x7cf, 0x343,	RTL_GIGA_MAC_VER_10 },
 		{ 0x7cf, 0x342,	RTL_GIGA_MAC_VER_16 },
 		{ 0x7c8, 0x348,	RTL_GIGA_MAC_VER_09 },
@@ -7060,7 +7062,7 @@ static int rtl_alloc_irq(struct rtl8169_private *tp)
 		RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~MSIEnable);
 		rtl_lock_config_regs(tp);
 		/* fall through */
-	case RTL_GIGA_MAC_VER_07 ... RTL_GIGA_MAC_VER_24:
+	case RTL_GIGA_MAC_VER_07 ... RTL_GIGA_MAC_VER_17:
 		flags = PCI_IRQ_LEGACY;
 		break;
 	default:
@@ -7155,6 +7157,13 @@ static int r8169_mdio_register(struct rtl8169_private *tp)
 	if (!tp->phydev) {
 		mdiobus_unregister(new_bus);
 		return -ENODEV;
+	} else if (!tp->phydev->drv) {
+		/* Most chip versions fail with the genphy driver.
+		 * Therefore ensure that the dedicated PHY driver is loaded.
+		 */
+		dev_err(&pdev->dev, "realtek.ko not loaded, maybe it needs to be added to initramfs?\n");
+		mdiobus_unregister(new_bus);
+		return -EUNATCH;
 	}
 
 	/* PHY will be woken up in rtl_open() */
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 393644833cd5..972074776651 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1450,6 +1450,7 @@ static void ravb_tx_timeout_work(struct work_struct *work)
 	struct ravb_private *priv = container_of(work, struct ravb_private,
 						 work);
 	struct net_device *ndev = priv->ndev;
+	int error;
 
 	netif_tx_stop_all_queues(ndev);
 
@@ -1458,15 +1459,36 @@ static void ravb_tx_timeout_work(struct work_struct *work)
 		ravb_ptp_stop(ndev);
 
 	/* Wait for DMA stopping */
-	ravb_stop_dma(ndev);
+	if (ravb_stop_dma(ndev)) {
+		/* If ravb_stop_dma() fails, the hardware is still operating
+		 * for TX and/or RX. So, this should not call the following
+		 * functions because ravb_dmac_init() is possible to fail too.
+		 * Also, this should not retry ravb_stop_dma() again and again
+		 * here because it's possible to wait forever. So, this just
+		 * re-enables the TX and RX and skip the following
+		 * re-initialization procedure.
+		 */
+		ravb_rcv_snd_enable(ndev);
+		goto out;
+	}
 
 	ravb_ring_free(ndev, RAVB_BE);
 	ravb_ring_free(ndev, RAVB_NC);
 
 	/* Device init */
-	ravb_dmac_init(ndev);
+	error = ravb_dmac_init(ndev);
+	if (error) {
+		/* If ravb_dmac_init() fails, descriptors are freed. So, this
+		 * should return here to avoid re-enabling the TX and RX in
+		 * ravb_emac_init().
+		 */
+		netdev_err(ndev, "%s: ravb_dmac_init() failed, error %d\n",
+			   __func__, error);
+		return;
+	}
 	ravb_emac_init(ndev);
 
+out:
 	/* Initialise PTP Clock driver */
 	if (priv->chip_id == RCAR_GEN2)
 		ravb_ptp_init(ndev, priv->pdev);
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 7ba35a0bdb29..8aa1b1bda96d 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -2204,24 +2204,28 @@ static size_t __sh_eth_get_regs(struct net_device *ndev, u32 *buf)
 	if (cd->tsu) {
 		add_tsu_reg(ARSTR);
 		add_tsu_reg(TSU_CTRST);
-		add_tsu_reg(TSU_FWEN0);
-		add_tsu_reg(TSU_FWEN1);
-		add_tsu_reg(TSU_FCM);
-		add_tsu_reg(TSU_BSYSL0);
-		add_tsu_reg(TSU_BSYSL1);
-		add_tsu_reg(TSU_PRISL0);
-		add_tsu_reg(TSU_PRISL1);
-		add_tsu_reg(TSU_FWSL0);
-		add_tsu_reg(TSU_FWSL1);
+		if (cd->dual_port) {
+			add_tsu_reg(TSU_FWEN0);
+			add_tsu_reg(TSU_FWEN1);
+			add_tsu_reg(TSU_FCM);
+			add_tsu_reg(TSU_BSYSL0);
+			add_tsu_reg(TSU_BSYSL1);
+			add_tsu_reg(TSU_PRISL0);
+			add_tsu_reg(TSU_PRISL1);
+			add_tsu_reg(TSU_FWSL0);
+			add_tsu_reg(TSU_FWSL1);
+		}
 		add_tsu_reg(TSU_FWSLC);
-		add_tsu_reg(TSU_QTAGM0);
-		add_tsu_reg(TSU_QTAGM1);
-		add_tsu_reg(TSU_FWSR);
-		add_tsu_reg(TSU_FWINMK);
-		add_tsu_reg(TSU_ADQT0);
-		add_tsu_reg(TSU_ADQT1);
-		add_tsu_reg(TSU_VTAG0);
-		add_tsu_reg(TSU_VTAG1);
+		if (cd->dual_port) {
+			add_tsu_reg(TSU_QTAGM0);
+			add_tsu_reg(TSU_QTAGM1);
+			add_tsu_reg(TSU_FWSR);
+			add_tsu_reg(TSU_FWINMK);
+			add_tsu_reg(TSU_ADQT0);
+			add_tsu_reg(TSU_ADQT1);
+			add_tsu_reg(TSU_VTAG0);
+			add_tsu_reg(TSU_VTAG1);
+		}
 		add_tsu_reg(TSU_ADSBSY);
 		add_tsu_reg(TSU_TEN);
 		add_tsu_reg(TSU_POST1);
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index c245a0f15066..586fe03c96e3 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -647,10 +647,10 @@ static int rocker_dma_rings_init(struct rocker *rocker)
 err_dma_event_ring_bufs_alloc:
 	rocker_dma_ring_destroy(rocker, &rocker->event_ring);
 err_dma_event_ring_create:
+	rocker_dma_cmd_ring_waits_free(rocker);
+err_dma_cmd_ring_waits_alloc:
 	rocker_dma_ring_bufs_free(rocker, &rocker->cmd_ring,
 				  PCI_DMA_BIDIRECTIONAL);
-err_dma_cmd_ring_waits_alloc:
-	rocker_dma_cmd_ring_waits_free(rocker);
 err_dma_cmd_ring_bufs_alloc:
 	rocker_dma_ring_destroy(rocker, &rocker->cmd_ring);
 	return err;
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
index c56fcbb37066..38767d797914 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
@@ -2279,7 +2279,7 @@ static int __init sxgbe_cmdline_opt(char *str)
 	if (!str || !*str)
 		return -EINVAL;
 	while ((opt = strsep(&str, ",")) != NULL) {
-		if (!strncmp(opt, "eee_timer:", 6)) {
+		if (!strncmp(opt, "eee_timer:", 10)) {
 			if (kstrtoint(opt + 10, 0, &eee_timer))
 				goto err;
 		}
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 53b726bfe945..413ad2d029f8 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -519,6 +519,7 @@ efx_copy_channel(const struct efx_channel *old_channel)
 		if (tx_queue->channel)
 			tx_queue->channel = channel;
 		tx_queue->buffer = NULL;
+		tx_queue->cb_page = NULL;
 		memset(&tx_queue->txd, 0, sizeof(tx_queue->txd));
 	}
 
diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c
index af15a737c675..59b4f16896a8 100644
--- a/drivers/net/ethernet/sfc/ptp.c
+++ b/drivers/net/ethernet/sfc/ptp.c
@@ -560,13 +560,45 @@ efx_ptp_mac_nic_to_ktime_correction(struct efx_nic *efx,
 				    u32 nic_major, u32 nic_minor,
 				    s32 correction)
 {
+	u32 sync_timestamp;
 	ktime_t kt = { 0 };
+	s16 delta;
 
 	if (!(nic_major & 0x80000000)) {
 		WARN_ON_ONCE(nic_major >> 16);
-		/* Use the top bits from the latest sync event. */
-		nic_major &= 0xffff;
-		nic_major |= (last_sync_timestamp_major(efx) & 0xffff0000);
+
+		/* Medford provides 48 bits of timestamp, so we must get the top
+		 * 16 bits from the timesync event state.
+		 *
+		 * We only have the lower 16 bits of the time now, but we do
+		 * have a full resolution timestamp at some point in past. As
+		 * long as the difference between the (real) now and the sync
+		 * is less than 2^15, then we can reconstruct the difference
+		 * between those two numbers using only the lower 16 bits of
+		 * each.
+		 *
+		 * Put another way
+		 *
+		 * a - b = ((a mod k) - b) mod k
+		 *
+		 * when -k/2 < (a-b) < k/2. In our case k is 2^16. We know
+		 * (a mod k) and b, so can calculate the delta, a - b.
+		 *
+		 */
+		sync_timestamp = last_sync_timestamp_major(efx);
+
+		/* Because delta is s16 this does an implicit mask down to
+		 * 16 bits which is what we need, assuming
+		 * MEDFORD_TX_SECS_EVENT_BITS is 16. delta is signed so that
+		 * we can deal with the (unlikely) case of sync timestamps
+		 * arriving from the future.
+		 */
+		delta = nic_major - sync_timestamp;
+
+		/* Recover the fully specified time now, by applying the offset
+		 * to the (fully specified) sync time.
+		 */
+		nic_major = sync_timestamp + delta;
 
 		kt = ptp->nic_to_kernel_time(nic_major, nic_minor,
 					     correction);
diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c
index bd14803545de..6a67485828d6 100644
--- a/drivers/net/ethernet/smsc/smc911x.c
+++ b/drivers/net/ethernet/smsc/smc911x.c
@@ -935,7 +935,7 @@ static void smc911x_phy_configure(struct work_struct *work)
 	if (lp->ctl_rspeed != 100)
 		my_ad_caps &= ~(ADVERTISE_100BASE4|ADVERTISE_100FULL|ADVERTISE_100HALF);
 
-	 if (!lp->ctl_rfduplx)
+	if (!lp->ctl_rfduplx)
 		my_ad_caps &= ~(ADVERTISE_100FULL|ADVERTISE_10FULL);
 
 	/* Update our Auto-Neg Advertisement Register */
diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c
index 601e76ad99a0..24182dd3d38c 100644
--- a/drivers/net/ethernet/smsc/smc91x.c
+++ b/drivers/net/ethernet/smsc/smc91x.c
@@ -2275,7 +2275,7 @@ static int smc_drv_probe(struct platform_device *pdev)
 		ret = try_toggle_control_gpio(&pdev->dev, &lp->power_gpio,
 					      "power", 0, 0, 100);
 		if (ret)
-			return ret;
+			goto out_free_netdev;
 
 		/*
 		 * Optional reset GPIO configured? Minimum 100 ns reset needed
@@ -2284,7 +2284,7 @@ static int smc_drv_probe(struct platform_device *pdev)
 		ret = try_toggle_control_gpio(&pdev->dev, &lp->reset_gpio,
 					      "reset", 0, 0, 100);
 		if (ret)
-			return ret;
+			goto out_free_netdev;
 
 		/*
 		 * Need to wait for optional EEPROM to load, max 750 us according
diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
index 38068fc34141..c7bdada4d1b9 100644
--- a/drivers/net/ethernet/smsc/smsc911x.c
+++ b/drivers/net/ethernet/smsc/smsc911x.c
@@ -2502,20 +2502,20 @@ static int smsc911x_drv_probe(struct platform_device *pdev)
 
 	retval = smsc911x_init(dev);
 	if (retval < 0)
-		goto out_disable_resources;
+		goto out_init_fail;
 
 	netif_carrier_off(dev);
 
 	retval = smsc911x_mii_init(pdev, dev);
 	if (retval) {
 		SMSC_WARN(pdata, probe, "Error %i initialising mii", retval);
-		goto out_disable_resources;
+		goto out_init_fail;
 	}
 
 	retval = register_netdev(dev);
 	if (retval) {
 		SMSC_WARN(pdata, probe, "Error %i registering device", retval);
-		goto out_disable_resources;
+		goto out_init_fail;
 	} else {
 		SMSC_TRACE(pdata, probe,
 			   "Network interface: \"%s\"", dev->name);
@@ -2556,9 +2556,10 @@ static int smsc911x_drv_probe(struct platform_device *pdev)
 
 	return 0;
 
-out_disable_resources:
+out_init_fail:
 	pm_runtime_put(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
+out_disable_resources:
 	(void)smsc911x_disable_resources(pdev);
 out_enable_resources_fail:
 	smsc911x_free_resources(pdev);
diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c
index 51a7b48db4bc..6a102885fcfd 100644
--- a/drivers/net/ethernet/socionext/sni_ave.c
+++ b/drivers/net/ethernet/socionext/sni_ave.c
@@ -424,16 +424,22 @@ static void ave_ethtool_get_wol(struct net_device *ndev,
 		phy_ethtool_get_wol(ndev->phydev, wol);
 }
 
-static int ave_ethtool_set_wol(struct net_device *ndev,
-			       struct ethtool_wolinfo *wol)
+static int __ave_ethtool_set_wol(struct net_device *ndev,
+				 struct ethtool_wolinfo *wol)
 {
-	int ret;
-
 	if (!ndev->phydev ||
 	    (wol->wolopts & (WAKE_ARP | WAKE_MAGICSECURE)))
 		return -EOPNOTSUPP;
 
-	ret = phy_ethtool_set_wol(ndev->phydev, wol);
+	return phy_ethtool_set_wol(ndev->phydev, wol);
+}
+
+static int ave_ethtool_set_wol(struct net_device *ndev,
+			       struct ethtool_wolinfo *wol)
+{
+	int ret;
+
+	ret = __ave_ethtool_set_wol(ndev, wol);
 	if (!ret)
 		device_set_wakeup_enable(&ndev->dev, !!wol->wolopts);
 
@@ -1185,7 +1191,7 @@ static int ave_init(struct net_device *ndev)
 	ret = regmap_update_bits(priv->regmap, SG_ETPINMODE,
 				 priv->pinmode_mask, priv->pinmode_val);
 	if (ret)
-		return ret;
+		goto out_reset_assert;
 
 	ave_global_reset(ndev);
 
@@ -1216,7 +1222,7 @@ static int ave_init(struct net_device *ndev)
 
 	/* set wol initial state disabled */
 	wol.wolopts = 0;
-	ave_ethtool_set_wol(ndev, &wol);
+	__ave_ethtool_set_wol(ndev, &wol);
 
 	if (!phy_interface_is_rgmii(phydev))
 		phy_set_max_speed(phydev, SPEED_100);
@@ -1772,7 +1778,7 @@ static int ave_resume(struct device *dev)
 
 	ave_ethtool_get_wol(ndev, &wol);
 	wol.wolopts = priv->wolopts;
-	ave_ethtool_set_wol(ndev, &wol);
+	__ave_ethtool_set_wol(ndev, &wol);
 
 	if (ndev->phydev) {
 		ret = phy_resume(ndev->phydev);
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index c265cc5770e8..e32fcaf2b712 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -353,9 +353,8 @@ struct dma_features {
 	unsigned int frpes;
 };
 
-/* GMAC TX FIFO is 8K, Rx FIFO is 16K */
-#define BUF_SIZE_16KiB 16384
-/* RX Buffer size must be < 8191 and multiple of 4/8/16 bytes */
+/* RX Buffer size must be multiple of 4/8/16 bytes */
+#define BUF_SIZE_16KiB 16368
 #define BUF_SIZE_8KiB 8188
 #define BUF_SIZE_4KiB 4096
 #define BUF_SIZE_2KiB 2048
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
index 2c6d7c69c8f7..db3264d374f9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
@@ -318,6 +318,19 @@ static int ipq806x_gmac_probe(struct platform_device *pdev)
 	/* Enable PTP clock */
 	regmap_read(gmac->nss_common, NSS_COMMON_CLK_GATE, &val);
 	val |= NSS_COMMON_CLK_GATE_PTP_EN(gmac->id);
+	switch (gmac->phy_mode) {
+	case PHY_INTERFACE_MODE_RGMII:
+		val |= NSS_COMMON_CLK_GATE_RGMII_RX_EN(gmac->id) |
+			NSS_COMMON_CLK_GATE_RGMII_TX_EN(gmac->id);
+		break;
+	case PHY_INTERFACE_MODE_SGMII:
+		val |= NSS_COMMON_CLK_GATE_GMII_RX_EN(gmac->id) |
+				NSS_COMMON_CLK_GATE_GMII_TX_EN(gmac->id);
+		break;
+	default:
+		/* We don't get here; the switch above will have errored out */
+		unreachable();
+	}
 	regmap_write(gmac->nss_common, NSS_COMMON_CLK_GATE, val);
 
 	if (gmac->phy_mode == PHY_INTERFACE_MODE_SGMII) {
@@ -337,6 +350,7 @@ static int ipq806x_gmac_probe(struct platform_device *pdev)
 	plat_dat->has_gmac = true;
 	plat_dat->bsp_priv = gmac;
 	plat_dat->fix_mac_speed = ipq806x_gmac_fix_mac_speed;
+	plat_dat->multicast_filter_bins = 0;
 
 	err = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
 	if (err)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
index 4b5178097a01..ec2a7a318a47 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
@@ -119,6 +119,7 @@ static int meson8b_init_rgmii_tx_clk(struct meson8b_dwmac *dwmac)
 		{ .div = 5, .val = 5, },
 		{ .div = 6, .val = 6, },
 		{ .div = 7, .val = 7, },
+		{ /* end of array */ }
 	};
 
 	clk_configs = devm_kzalloc(dev, sizeof(*clk_configs), GFP_KERNEL);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index 7ec895407d23..bfc4a92f1d92 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -75,6 +75,11 @@ struct ethqos_emac_por {
 	unsigned int value;
 };
 
+struct ethqos_emac_driver_data {
+	const struct ethqos_emac_por *por;
+	unsigned int num_por;
+};
+
 struct qcom_ethqos {
 	struct platform_device *pdev;
 	void __iomem *rgmii_base;
@@ -171,6 +176,11 @@ static const struct ethqos_emac_por emac_v2_3_0_por[] = {
 	{ .offset = RGMII_IO_MACRO_CONFIG2,	.value = 0x00002060 },
 };
 
+static const struct ethqos_emac_driver_data emac_v2_3_0_data = {
+	.por = emac_v2_3_0_por,
+	.num_por = ARRAY_SIZE(emac_v2_3_0_por),
+};
+
 static int ethqos_dll_configure(struct qcom_ethqos *ethqos)
 {
 	unsigned int val;
@@ -413,6 +423,7 @@ static int ethqos_configure(struct qcom_ethqos *ethqos)
 			dll_lock = rgmii_readl(ethqos, SDC4_STATUS);
 			if (dll_lock & SDC4_STATUS_DLL_LOCK)
 				break;
+			retry--;
 		} while (retry > 0);
 		if (!retry)
 			dev_err(&ethqos->pdev->dev,
@@ -441,6 +452,7 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 	struct device_node *np = pdev->dev.of_node;
 	struct plat_stmmacenet_data *plat_dat;
 	struct stmmac_resources stmmac_res;
+	const struct ethqos_emac_driver_data *data;
 	struct qcom_ethqos *ethqos;
 	struct resource *res;
 	int ret;
@@ -470,7 +482,9 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 		goto err_mem;
 	}
 
-	ethqos->por = of_device_get_match_data(&pdev->dev);
+	data = of_device_get_match_data(&pdev->dev);
+	ethqos->por = data->por;
+	ethqos->num_por = data->num_por;
 
 	ethqos->rgmii_clk = devm_clk_get(&pdev->dev, "rgmii");
 	if (IS_ERR(ethqos->rgmii_clk)) {
@@ -525,7 +539,7 @@ static int qcom_ethqos_remove(struct platform_device *pdev)
 }
 
 static const struct of_device_id qcom_ethqos_match[] = {
-	{ .compatible = "qcom,qcs404-ethqos", .data = &emac_v2_3_0_por},
+	{ .compatible = "qcom,qcs404-ethqos", .data = &emac_v2_3_0_data},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, qcom_ethqos_match);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index e2e469c37a4d..9f9aaa47a8dc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -1411,7 +1411,7 @@ static int rk_gmac_probe(struct platform_device *pdev)
 
 	ret = rk_gmac_clk_init(plat_dat);
 	if (ret)
-		return ret;
+		goto err_remove_config_dt;
 
 	ret = rk_gmac_powerup(plat_dat->bsp_priv);
 	if (ret)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
index 8bdbddeec117..132e6317a3ba 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
@@ -233,6 +233,8 @@ static int socfpga_dwmac_set_phy_mode(struct socfpga_dwmac *dwmac)
 	switch (phymode) {
 	case PHY_INTERFACE_MODE_RGMII:
 	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
 		val = SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_RGMII;
 		break;
 	case PHY_INTERFACE_MODE_MII:
@@ -264,16 +266,19 @@ static int socfpga_dwmac_set_phy_mode(struct socfpga_dwmac *dwmac)
 	    phymode == PHY_INTERFACE_MODE_MII ||
 	    phymode == PHY_INTERFACE_MODE_GMII ||
 	    phymode == PHY_INTERFACE_MODE_SGMII) {
-		ctrl |= SYSMGR_EMACGRP_CTRL_PTP_REF_CLK_MASK << (reg_shift / 2);
 		regmap_read(sys_mgr_base_addr, SYSMGR_FPGAGRP_MODULE_REG,
 			    &module);
 		module |= (SYSMGR_FPGAGRP_MODULE_EMAC << (reg_shift / 2));
 		regmap_write(sys_mgr_base_addr, SYSMGR_FPGAGRP_MODULE_REG,
 			     module);
-	} else {
-		ctrl &= ~(SYSMGR_EMACGRP_CTRL_PTP_REF_CLK_MASK << (reg_shift / 2));
 	}
 
+	if (dwmac->f2h_ptp_ref_clk)
+		ctrl |= SYSMGR_EMACGRP_CTRL_PTP_REF_CLK_MASK << (reg_shift / 2);
+	else
+		ctrl &= ~(SYSMGR_EMACGRP_CTRL_PTP_REF_CLK_MASK <<
+			  (reg_shift / 2));
+
 	regmap_write(sys_mgr_base_addr, reg_offset, ctrl);
 
 	/* Deassert reset for the phy configuration to be sampled by
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index ec5e6ee92aec..5ca9e3dbdfa0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -937,6 +937,9 @@ static int sun8i_dwmac_set_syscon(struct stmmac_priv *priv)
 		/* default */
 		break;
 	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
 		reg |= SYSCON_EPIT | SYSCON_ETCS_INT_GMII;
 		break;
 	case PHY_INTERFACE_MODE_RMII:
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
index a299da3971b4..65a3e3b5face 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
@@ -44,7 +44,7 @@ static int sun7i_gmac_init(struct platform_device *pdev, void *priv)
 	 * rate, which then uses the auto-reparenting feature of the
 	 * clock driver, and enabling/disabling the clock.
 	 */
-	if (gmac->interface == PHY_INTERFACE_MODE_RGMII) {
+	if (phy_interface_mode_is_rgmii(gmac->interface)) {
 		clk_set_rate(gmac->tx_clk, SUN7I_GMAC_GMII_RGMII_RATE);
 		clk_prepare_enable(gmac->tx_clk);
 		gmac->clk_enabled = 1;
@@ -146,6 +146,8 @@ static int sun7i_gmac_probe(struct platform_device *pdev)
 	plat_dat->init = sun7i_gmac_init;
 	plat_dat->exit = sun7i_gmac_exit;
 	plat_dat->fix_mac_speed = sun7i_fix_speed;
+	plat_dat->tx_fifo_size = 4096;
+	plat_dat->rx_fifo_size = 16384;
 
 	ret = sun7i_gmac_init(pdev, plat_dat->bsp_priv);
 	if (ret)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index 54f4ffb36d60..054e79a36b5a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -24,6 +24,7 @@
 static void dwmac1000_core_init(struct mac_device_info *hw,
 				struct net_device *dev)
 {
+	struct stmmac_priv *priv = netdev_priv(dev);
 	void __iomem *ioaddr = hw->pcsr;
 	u32 value = readl(ioaddr + GMAC_CONTROL);
 	int mtu = dev->mtu;
@@ -35,7 +36,7 @@ static void dwmac1000_core_init(struct mac_device_info *hw,
 	 * Broadcom tags can look like invalid LLC/SNAP packets and cause the
 	 * hardware to truncate packets on reception.
 	 */
-	if (netdev_uses_dsa(dev))
+	if (netdev_uses_dsa(dev) || !priv->plat->enh_desc)
 		value &= ~GMAC_CONTROL_ACS;
 
 	if (mtu > 1500)
@@ -165,6 +166,9 @@ static void dwmac1000_set_filter(struct mac_device_info *hw,
 		value = GMAC_FRAME_FILTER_PR;
 	} else if (dev->flags & IFF_ALLMULTI) {
 		value = GMAC_FRAME_FILTER_PM;	/* pass all multi */
+	} else if (!netdev_mc_empty(dev) && (mcbitslog2 == 0)) {
+		/* Fall back to all multicast if we've no filter */
+		value = GMAC_FRAME_FILTER_PM;
 	} else if (!netdev_mc_empty(dev)) {
 		struct netdev_hw_addr *ha;
 
@@ -207,7 +211,7 @@ static void dwmac1000_set_filter(struct mac_device_info *hw,
 			reg++;
 		}
 
-		while (reg <= perfect_addr_number) {
+		while (reg < perfect_addr_number) {
 			writel(0, ioaddr + GMAC_ADDR_HIGH(reg));
 			writel(0, ioaddr + GMAC_ADDR_LOW(reg));
 			reg++;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
index 085b700a4994..13be6f2cad90 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -186,6 +186,8 @@
 #define XGMAC_DMA_CH_RX_CONTROL(x)	(0x00003108 + (0x80 * (x)))
 #define XGMAC_RxPBL			GENMASK(21, 16)
 #define XGMAC_RxPBL_SHIFT		16
+#define XGMAC_RBSZ			GENMASK(14, 1)
+#define XGMAC_RBSZ_SHIFT		1
 #define XGMAC_RXST			BIT(0)
 #define XGMAC_DMA_CH_TxDESC_LADDR(x)	(0x00003114 + (0x80 * (x)))
 #define XGMAC_DMA_CH_RxDESC_LADDR(x)	(0x0000311c + (0x80 * (x)))
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index 8788c8511a8c..19fdd29b54ac 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -443,7 +443,8 @@ static void dwxgmac2_set_bfsize(void __iomem *ioaddr, int bfsize, u32 chan)
 	u32 value;
 
 	value = readl(ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan));
-	value |= bfsize << 1;
+	value &= ~XGMAC_RBSZ;
+	value |= bfsize << XGMAC_RBSZ_SHIFT;
 	writel(value, ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan));
 }
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
index 020159622559..e5d9007c8090 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
@@ -26,12 +26,16 @@ static void config_sub_second_increment(void __iomem *ioaddr,
 	unsigned long data;
 	u32 reg_value;
 
-	/* For GMAC3.x, 4.x versions, convert the ptp_clock to nano second
-	 *	formula = (1/ptp_clock) * 1000000000
-	 * where ptp_clock is 50MHz if fine method is used to update system
+	/* For GMAC3.x, 4.x versions, in "fine adjustement mode" set sub-second
+	 * increment to twice the number of nanoseconds of a clock cycle.
+	 * The calculation of the default_addend value by the caller will set it
+	 * to mid-range = 2^31 when the remainder of this division is zero,
+	 * which will make the accumulator overflow once every 2 ptp_clock
+	 * cycles, adding twice the number of nanoseconds of a clock cycle :
+	 * 2000000000ULL / ptp_clock.
 	 */
 	if (value & PTP_TCR_TSCFUPDT)
-		data = (1000000000ULL / 50000000);
+		data = (2000000000ULL / ptp_clock);
 	else
 		data = (1000000000ULL / ptp_clock);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 6223de409be4..7ecd0ec39dcb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -44,7 +44,7 @@
 #include "dwxgmac2.h"
 #include "hwif.h"
 
-#define	STMMAC_ALIGN(x)		__ALIGN_KERNEL(x, SMP_CACHE_BYTES)
+#define	STMMAC_ALIGN(x)		ALIGN(ALIGN(x, SMP_CACHE_BYTES), 16)
 #define	TSO_MAX_BUFF_SIZE	(SZ_16K - 1)
 
 /* Module parameters */
@@ -104,6 +104,7 @@ MODULE_PARM_DESC(chain_mode, "To use chain instead of ring mode");
 static irqreturn_t stmmac_interrupt(int irq, void *dev_id);
 
 #ifdef CONFIG_DEBUG_FS
+static const struct net_device_ops stmmac_netdev_ops;
 static int stmmac_init_fs(struct net_device *dev);
 static void stmmac_exit_fs(struct net_device *dev);
 #endif
@@ -664,7 +665,8 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 			config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 			ptp_v2 = PTP_TCR_TSVER2ENA;
 			snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
-			ts_event_en = PTP_TCR_TSEVNTENA;
+			if (priv->synopsys_id != DWMAC_CORE_5_10)
+				ts_event_en = PTP_TCR_TSEVNTENA;
 			ptp_over_ipv4_udp = PTP_TCR_TSIPV4ENA;
 			ptp_over_ipv6_udp = PTP_TCR_TSIPV6ENA;
 			ptp_over_ethernet = PTP_TCR_TSIPENA;
@@ -1098,7 +1100,9 @@ static int stmmac_set_bfsize(int mtu, int bufsize)
 {
 	int ret = bufsize;
 
-	if (mtu >= BUF_SIZE_4KiB)
+	if (mtu >= BUF_SIZE_8KiB)
+		ret = BUF_SIZE_16KiB;
+	else if (mtu >= BUF_SIZE_4KiB)
 		ret = BUF_SIZE_8KiB;
 	else if (mtu >= BUF_SIZE_2KiB)
 		ret = BUF_SIZE_4KiB;
@@ -1281,19 +1285,9 @@ static int init_dma_rx_desc_rings(struct net_device *dev, gfp_t flags)
 	struct stmmac_priv *priv = netdev_priv(dev);
 	u32 rx_count = priv->plat->rx_queues_to_use;
 	int ret = -ENOMEM;
-	int bfsize = 0;
 	int queue;
 	int i;
 
-	bfsize = stmmac_set_16kib_bfsize(priv, dev->mtu);
-	if (bfsize < 0)
-		bfsize = 0;
-
-	if (bfsize < BUF_SIZE_16KiB)
-		bfsize = stmmac_set_bfsize(dev->mtu, priv->dma_buf_sz);
-
-	priv->dma_buf_sz = bfsize;
-
 	/* RX INITIALIZATION */
 	netif_dbg(priv, probe, priv->dev,
 		  "SKB addresses:\nskb\t\tskb data\tdma data\n");
@@ -1339,8 +1333,6 @@ static int init_dma_rx_desc_rings(struct net_device *dev, gfp_t flags)
 		}
 	}
 
-	buf_sz = bfsize;
-
 	return 0;
 
 err_init_rx_buffers:
@@ -2607,6 +2599,7 @@ static void stmmac_hw_teardown(struct net_device *dev)
 static int stmmac_open(struct net_device *dev)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
+	int bfsize = 0;
 	u32 chan;
 	int ret;
 
@@ -2626,7 +2619,16 @@ static int stmmac_open(struct net_device *dev)
 	memset(&priv->xstats, 0, sizeof(struct stmmac_extra_stats));
 	priv->xstats.threshold = tc;
 
-	priv->dma_buf_sz = STMMAC_ALIGN(buf_sz);
+	bfsize = stmmac_set_16kib_bfsize(priv, dev->mtu);
+	if (bfsize < 0)
+		bfsize = 0;
+
+	if (bfsize < BUF_SIZE_16KiB)
+		bfsize = stmmac_set_bfsize(dev->mtu, priv->dma_buf_sz);
+
+	priv->dma_buf_sz = bfsize;
+	buf_sz = bfsize;
+
 	priv->rx_copybreak = STMMAC_RX_COPYBREAK;
 
 	ret = alloc_dma_desc_resources(priv);
@@ -3010,6 +3012,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	tx_q->tx_tail_addr = tx_q->dma_tx_phy + (tx_q->cur_tx * sizeof(*desc));
 	stmmac_set_tx_tail_ptr(priv, priv->ioaddr, tx_q->tx_tail_addr, queue);
+	stmmac_tx_timer_arm(priv, queue);
 
 	return NETDEV_TX_OK;
 
@@ -3223,6 +3226,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	tx_q->tx_tail_addr = tx_q->dma_tx_phy + (tx_q->cur_tx * sizeof(*desc));
 	stmmac_set_tx_tail_ptr(priv, priv->ioaddr, tx_q->tx_tail_addr, queue);
+	stmmac_tx_timer_arm(priv, queue);
 
 	return NETDEV_TX_OK;
 
@@ -3622,12 +3626,24 @@ static void stmmac_set_rx_mode(struct net_device *dev)
 static int stmmac_change_mtu(struct net_device *dev, int new_mtu)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
+	int txfifosz = priv->plat->tx_fifo_size;
+
+	if (txfifosz == 0)
+		txfifosz = priv->dma_cap.tx_fifo_size;
+
+	txfifosz /= priv->plat->tx_queues_to_use;
 
 	if (netif_running(dev)) {
 		netdev_err(priv->dev, "must be stopped to change its MTU\n");
 		return -EBUSY;
 	}
 
+	new_mtu = STMMAC_ALIGN(new_mtu);
+
+	/* If condition true, FIFO is too small or MTU too large */
+	if ((txfifosz < new_mtu) || (new_mtu > BUF_SIZE_16KiB))
+		return -EINVAL;
+
 	dev->mtu = new_mtu;
 
 	netdev_update_features(dev);
@@ -3686,7 +3702,7 @@ static int stmmac_set_features(struct net_device *netdev,
 /**
  *  stmmac_interrupt - main ISR
  *  @irq: interrupt number.
- *  @dev_id: to pass the net device pointer.
+ *  @dev_id: to pass the net device pointer (must be valid).
  *  Description: this is the main driver interrupt service routine.
  *  It can call:
  *  o DMA service routine (to manage incoming frame reception and transmission
@@ -3710,11 +3726,6 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
 	if (priv->irq_wake)
 		pm_wakeup_event(priv->device, 0);
 
-	if (unlikely(!dev)) {
-		netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__);
-		return IRQ_NONE;
-	}
-
 	/* Check if adapter is up */
 	if (test_bit(STMMAC_DOWN, &priv->state))
 		return IRQ_HANDLED;
@@ -4039,10 +4050,40 @@ static int stmmac_dma_cap_show(struct seq_file *seq, void *v)
 }
 DEFINE_SHOW_ATTRIBUTE(stmmac_dma_cap);
 
+/* Use network device events to rename debugfs file entries.
+ */
+static int stmmac_device_event(struct notifier_block *unused,
+			       unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct stmmac_priv *priv = netdev_priv(dev);
+
+	if (dev->netdev_ops != &stmmac_netdev_ops)
+		goto done;
+
+	switch (event) {
+	case NETDEV_CHANGENAME:
+		if (priv->dbgfs_dir)
+			priv->dbgfs_dir = debugfs_rename(stmmac_fs_dir,
+							 priv->dbgfs_dir,
+							 stmmac_fs_dir,
+							 dev->name);
+		break;
+	}
+done:
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block stmmac_notifier = {
+	.notifier_call = stmmac_device_event,
+};
+
 static int stmmac_init_fs(struct net_device *dev)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 
+	rtnl_lock();
+
 	/* Create per netdev entries */
 	priv->dbgfs_dir = debugfs_create_dir(dev->name, stmmac_fs_dir);
 
@@ -4077,6 +4118,8 @@ static int stmmac_init_fs(struct net_device *dev)
 		return -ENOMEM;
 	}
 
+	rtnl_unlock();
+
 	return 0;
 }
 
@@ -4461,14 +4504,14 @@ int stmmac_dvr_remove(struct device *dev)
 
 	netdev_info(priv->dev, "%s: removing driver", __func__);
 
-#ifdef CONFIG_DEBUG_FS
-	stmmac_exit_fs(ndev);
-#endif
 	stmmac_stop_all_dma(priv);
 
 	stmmac_mac_set(priv, priv->ioaddr, false);
 	netif_carrier_off(ndev);
 	unregister_netdev(ndev);
+#ifdef CONFIG_DEBUG_FS
+	stmmac_exit_fs(ndev);
+#endif
 	if (priv->plat->stmmac_rst)
 		reset_control_assert(priv->plat->stmmac_rst);
 	clk_disable_unprepare(priv->plat->pclk);
@@ -4496,6 +4539,7 @@ int stmmac_suspend(struct device *dev)
 {
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct stmmac_priv *priv = netdev_priv(ndev);
+	u32 chan;
 
 	if (!ndev || !netif_running(ndev))
 		return 0;
@@ -4510,6 +4554,9 @@ int stmmac_suspend(struct device *dev)
 
 	stmmac_disable_all_queues(priv);
 
+	for (chan = 0; chan < priv->plat->tx_queues_to_use; chan++)
+		del_timer_sync(&priv->tx_queue[chan].txtimer);
+
 	/* Stop TX/RX DMA */
 	stmmac_stop_all_dma(priv);
 
@@ -4684,6 +4731,7 @@ static int __init stmmac_init(void)
 			return -ENOMEM;
 		}
 	}
+	register_netdevice_notifier(&stmmac_notifier);
 #endif
 
 	return 0;
@@ -4692,6 +4740,7 @@ static int __init stmmac_init(void)
 static void __exit stmmac_exit(void)
 {
 #ifdef CONFIG_DEBUG_FS
+	unregister_netdevice_notifier(&stmmac_notifier);
 	debugfs_remove_recursive(stmmac_fs_dir);
 #endif
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index fb8f6e2fe989..a4473143f582 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -636,16 +636,22 @@ int stmmac_get_platform_resources(struct platform_device *pdev,
 	 * In case the wake up interrupt is not passed from the platform
 	 * so the driver will continue to use the mac irq (ndev->irq)
 	 */
-	stmmac_res->wol_irq = platform_get_irq_byname(pdev, "eth_wake_irq");
+	stmmac_res->wol_irq =
+		platform_get_irq_byname_optional(pdev, "eth_wake_irq");
 	if (stmmac_res->wol_irq < 0) {
 		if (stmmac_res->wol_irq == -EPROBE_DEFER)
 			return -EPROBE_DEFER;
+		dev_info(&pdev->dev, "IRQ eth_wake_irq not found\n");
 		stmmac_res->wol_irq = stmmac_res->irq;
 	}
 
-	stmmac_res->lpi_irq = platform_get_irq_byname(pdev, "eth_lpi");
-	if (stmmac_res->lpi_irq == -EPROBE_DEFER)
-		return -EPROBE_DEFER;
+	stmmac_res->lpi_irq =
+		platform_get_irq_byname_optional(pdev, "eth_lpi");
+	if (stmmac_res->lpi_irq < 0) {
+		if (stmmac_res->lpi_irq == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+		dev_info(&pdev->dev, "IRQ eth_lpi not found\n");
+	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	stmmac_res->addr = devm_ioremap_resource(&pdev->dev, res);
diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index 6fc05c106afc..432d6cbf6028 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -4971,7 +4971,7 @@ static int cas_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 					  cas_cacheline_size)) {
 			dev_err(&pdev->dev, "Could not set PCI cache "
 			       "line size\n");
-			goto err_write_cacheline;
+			goto err_out_free_res;
 		}
 	}
 #endif
@@ -5144,7 +5144,6 @@ err_out_iounmap:
 err_out_free_res:
 	pci_release_regions(pdev);
 
-err_write_cacheline:
 	/* Try to restore it in case the error occurred after we
 	 * set it.
 	 */
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index d64fcd6976d4..beea202ec1ec 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1423,8 +1423,11 @@ static int cpsw_ndo_open(struct net_device *ndev)
 	return 0;
 
 err_cleanup:
-	cpdma_ctlr_stop(cpsw->dma);
-	for_each_slave(priv, cpsw_slave_stop, cpsw);
+	if (!cpsw->usage_count) {
+		cpdma_ctlr_stop(cpsw->dma);
+		for_each_slave(priv, cpsw_slave_stop, cpsw);
+	}
+
 	pm_runtime_put_sync(cpsw->dev);
 	netif_carrier_off(priv->ndev);
 	return ret;
@@ -2263,8 +2266,7 @@ no_phy_slave:
 
 static void cpsw_remove_dt(struct platform_device *pdev)
 {
-	struct net_device *ndev = platform_get_drvdata(pdev);
-	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+	struct cpsw_common *cpsw = platform_get_drvdata(pdev);
 	struct cpsw_platform_data *data = &cpsw->data;
 	struct device_node *node = pdev->dev.of_node;
 	struct device_node *slave_node;
@@ -2570,9 +2572,8 @@ clean_runtime_disable_ret:
 
 static int cpsw_remove(struct platform_device *pdev)
 {
-	struct net_device *ndev = platform_get_drvdata(pdev);
-	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
-	int ret;
+	struct cpsw_common *cpsw = platform_get_drvdata(pdev);
+	int i, ret;
 
 	ret = pm_runtime_get_sync(&pdev->dev);
 	if (ret < 0) {
@@ -2580,9 +2581,9 @@ static int cpsw_remove(struct platform_device *pdev)
 		return ret;
 	}
 
-	if (cpsw->data.dual_emac)
-		unregister_netdev(cpsw->slaves[1].ndev);
-	unregister_netdev(ndev);
+	for (i = 0; i < cpsw->data.slaves; i++)
+		if (cpsw->slaves[i].ndev)
+			unregister_netdev(cpsw->slaves[i].ndev);
 
 	cpts_release(cpsw->cpts);
 	cpdma_ctlr_destroy(cpsw->dma);
@@ -2595,20 +2596,17 @@ static int cpsw_remove(struct platform_device *pdev)
 #ifdef CONFIG_PM_SLEEP
 static int cpsw_suspend(struct device *dev)
 {
-	struct net_device	*ndev = dev_get_drvdata(dev);
-	struct cpsw_common	*cpsw = ndev_to_cpsw(ndev);
+	struct cpsw_common *cpsw = dev_get_drvdata(dev);
+	int i;
 
-	if (cpsw->data.dual_emac) {
-		int i;
+	rtnl_lock();
 
-		for (i = 0; i < cpsw->data.slaves; i++) {
+	for (i = 0; i < cpsw->data.slaves; i++)
+		if (cpsw->slaves[i].ndev)
 			if (netif_running(cpsw->slaves[i].ndev))
 				cpsw_ndo_stop(cpsw->slaves[i].ndev);
-		}
-	} else {
-		if (netif_running(ndev))
-			cpsw_ndo_stop(ndev);
-	}
+
+	rtnl_unlock();
 
 	/* Select sleep pin state */
 	pinctrl_pm_select_sleep_state(dev);
@@ -2618,25 +2616,20 @@ static int cpsw_suspend(struct device *dev)
 
 static int cpsw_resume(struct device *dev)
 {
-	struct net_device	*ndev = dev_get_drvdata(dev);
-	struct cpsw_common	*cpsw = ndev_to_cpsw(ndev);
+	struct cpsw_common *cpsw = dev_get_drvdata(dev);
+	int i;
 
 	/* Select default pin state */
 	pinctrl_pm_select_default_state(dev);
 
 	/* shut up ASSERT_RTNL() warning in netif_set_real_num_tx/rx_queues */
 	rtnl_lock();
-	if (cpsw->data.dual_emac) {
-		int i;
 
-		for (i = 0; i < cpsw->data.slaves; i++) {
+	for (i = 0; i < cpsw->data.slaves; i++)
+		if (cpsw->slaves[i].ndev)
 			if (netif_running(cpsw->slaves[i].ndev))
 				cpsw_ndo_open(cpsw->slaves[i].ndev);
-		}
-	} else {
-		if (netif_running(ndev))
-			cpsw_ndo_open(ndev);
-	}
+
 	rtnl_unlock();
 
 	return 0;
diff --git a/drivers/net/ethernet/ti/davinci_mdio.c b/drivers/net/ethernet/ti/davinci_mdio.c
index 38b7f6d35759..702fdc393da0 100644
--- a/drivers/net/ethernet/ti/davinci_mdio.c
+++ b/drivers/net/ethernet/ti/davinci_mdio.c
@@ -397,6 +397,8 @@ static int davinci_mdio_probe(struct platform_device *pdev)
 	data->dev = dev;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -EINVAL;
 	data->regs = devm_ioremap(dev, res->start, resource_size(res));
 	if (!data->regs)
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/toshiba/spider_net.c b/drivers/net/ethernet/toshiba/spider_net.c
index 5b196ebfed49..d75892169737 100644
--- a/drivers/net/ethernet/toshiba/spider_net.c
+++ b/drivers/net/ethernet/toshiba/spider_net.c
@@ -283,8 +283,8 @@ spider_net_free_chain(struct spider_net_card *card,
 		descr = descr->next;
 	} while (descr != chain->ring);
 
-	dma_free_coherent(&card->pdev->dev, chain->num_desc,
-	    chain->hwring, chain->dma_addr);
+	dma_free_coherent(&card->pdev->dev, chain->num_desc * sizeof(struct spider_net_hw_descr),
+			  chain->hwring, chain->dma_addr);
 }
 
 /**
diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c
index 3b5a26b05295..9f7f7eabafe9 100644
--- a/drivers/net/ethernet/toshiba/tc35815.c
+++ b/drivers/net/ethernet/toshiba/tc35815.c
@@ -644,7 +644,7 @@ static int tc_mii_probe(struct net_device *dev)
 		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, mask);
 		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, mask);
 	}
-	linkmode_and(phydev->supported, phydev->supported, mask);
+	linkmode_andnot(phydev->supported, phydev->supported, mask);
 	linkmode_copy(phydev->advertising, phydev->supported);
 
 	lp->link = 0;
diff --git a/drivers/net/ethernet/xilinx/ll_temac.h b/drivers/net/ethernet/xilinx/ll_temac.h
index 1aeda084b8f1..b274ac234c39 100644
--- a/drivers/net/ethernet/xilinx/ll_temac.h
+++ b/drivers/net/ethernet/xilinx/ll_temac.h
@@ -375,10 +375,14 @@ struct temac_local {
 	int tx_bd_next;
 	int tx_bd_tail;
 	int rx_bd_ci;
+	int rx_bd_tail;
 
 	/* DMA channel control setup */
 	u32 tx_chnl_ctrl;
 	u32 rx_chnl_ctrl;
+	u8 coalesce_count_rx;
+
+	struct delayed_work restart_work;
 };
 
 /* Wrappers for temac_ior()/temac_iow() function pointers above */
diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c
index 14870d659f7d..3a6ae1f3c45d 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_main.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_main.c
@@ -52,6 +52,7 @@
 #include <linux/ip.h>
 #include <linux/slab.h>
 #include <linux/interrupt.h>
+#include <linux/workqueue.h>
 #include <linux/dma-mapping.h>
 #include <linux/platform_data/xilinx-ll-temac.h>
 
@@ -300,6 +301,8 @@ static int temac_dma_bd_init(struct net_device *ndev)
 		skb_dma_addr = dma_map_single(ndev->dev.parent, skb->data,
 					      XTE_MAX_JUMBO_FRAME_SIZE,
 					      DMA_FROM_DEVICE);
+		if (dma_mapping_error(ndev->dev.parent, skb_dma_addr))
+			goto out;
 		lp->rx_bd_v[i].phys = cpu_to_be32(skb_dma_addr);
 		lp->rx_bd_v[i].len = cpu_to_be32(XTE_MAX_JUMBO_FRAME_SIZE);
 		lp->rx_bd_v[i].app0 = cpu_to_be32(STS_CTRL_APP0_IRQONEND);
@@ -320,12 +323,13 @@ static int temac_dma_bd_init(struct net_device *ndev)
 	lp->tx_bd_next = 0;
 	lp->tx_bd_tail = 0;
 	lp->rx_bd_ci = 0;
+	lp->rx_bd_tail = RX_BD_NUM - 1;
 
 	/* Enable RX DMA transfers */
 	wmb();
 	lp->dma_out(lp, RX_CURDESC_PTR,  lp->rx_bd_p);
 	lp->dma_out(lp, RX_TAILDESC_PTR,
-		       lp->rx_bd_p + (sizeof(*lp->rx_bd_v) * (RX_BD_NUM - 1)));
+		       lp->rx_bd_p + (sizeof(*lp->rx_bd_v) * lp->rx_bd_tail));
 
 	/* Prepare for TX DMA transfer */
 	lp->dma_out(lp, TX_CURDESC_PTR, lp->tx_bd_p);
@@ -704,6 +708,9 @@ static void temac_start_xmit_done(struct net_device *ndev)
 		stat = be32_to_cpu(cur_p->app0);
 	}
 
+	/* Matches barrier in temac_start_xmit */
+	smp_mb();
+
 	netif_wake_queue(ndev);
 }
 
@@ -746,9 +753,19 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	cur_p = &lp->tx_bd_v[lp->tx_bd_tail];
 
 	if (temac_check_tx_bd_space(lp, num_frag + 1)) {
-		if (!netif_queue_stopped(ndev))
-			netif_stop_queue(ndev);
-		return NETDEV_TX_BUSY;
+		if (netif_queue_stopped(ndev))
+			return NETDEV_TX_BUSY;
+
+		netif_stop_queue(ndev);
+
+		/* Matches barrier in temac_start_xmit_done */
+		smp_mb();
+
+		/* Space might have just been freed - check again */
+		if (temac_check_tx_bd_space(lp, num_frag))
+			return NETDEV_TX_BUSY;
+
+		netif_wake_queue(ndev);
 	}
 
 	cur_p->app0 = 0;
@@ -766,12 +783,16 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	skb_dma_addr = dma_map_single(ndev->dev.parent, skb->data,
 				      skb_headlen(skb), DMA_TO_DEVICE);
 	cur_p->len = cpu_to_be32(skb_headlen(skb));
+	if (WARN_ON_ONCE(dma_mapping_error(ndev->dev.parent, skb_dma_addr))) {
+		dev_kfree_skb_any(skb);
+		ndev->stats.tx_dropped++;
+		return NETDEV_TX_OK;
+	}
 	cur_p->phys = cpu_to_be32(skb_dma_addr);
 	ptr_to_txbd((void *)skb, cur_p);
 
 	for (ii = 0; ii < num_frag; ii++) {
-		lp->tx_bd_tail++;
-		if (lp->tx_bd_tail >= TX_BD_NUM)
+		if (++lp->tx_bd_tail >= TX_BD_NUM)
 			lp->tx_bd_tail = 0;
 
 		cur_p = &lp->tx_bd_v[lp->tx_bd_tail];
@@ -779,6 +800,27 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 					      skb_frag_address(frag),
 					      skb_frag_size(frag),
 					      DMA_TO_DEVICE);
+		if (dma_mapping_error(ndev->dev.parent, skb_dma_addr)) {
+			if (--lp->tx_bd_tail < 0)
+				lp->tx_bd_tail = TX_BD_NUM - 1;
+			cur_p = &lp->tx_bd_v[lp->tx_bd_tail];
+			while (--ii >= 0) {
+				--frag;
+				dma_unmap_single(ndev->dev.parent,
+						 be32_to_cpu(cur_p->phys),
+						 skb_frag_size(frag),
+						 DMA_TO_DEVICE);
+				if (--lp->tx_bd_tail < 0)
+					lp->tx_bd_tail = TX_BD_NUM - 1;
+				cur_p = &lp->tx_bd_v[lp->tx_bd_tail];
+			}
+			dma_unmap_single(ndev->dev.parent,
+					 be32_to_cpu(cur_p->phys),
+					 skb_headlen(skb), DMA_TO_DEVICE);
+			dev_kfree_skb_any(skb);
+			ndev->stats.tx_dropped++;
+			return NETDEV_TX_OK;
+		}
 		cur_p->phys = cpu_to_be32(skb_dma_addr);
 		cur_p->len = cpu_to_be32(skb_frag_size(frag));
 		cur_p->app0 = 0;
@@ -800,31 +842,56 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	return NETDEV_TX_OK;
 }
 
+static int ll_temac_recv_buffers_available(struct temac_local *lp)
+{
+	int available;
+
+	if (!lp->rx_skb[lp->rx_bd_ci])
+		return 0;
+	available = 1 + lp->rx_bd_tail - lp->rx_bd_ci;
+	if (available <= 0)
+		available += RX_BD_NUM;
+	return available;
+}
 
 static void ll_temac_recv(struct net_device *ndev)
 {
 	struct temac_local *lp = netdev_priv(ndev);
-	struct sk_buff *skb, *new_skb;
-	unsigned int bdstat;
-	struct cdmac_bd *cur_p;
-	dma_addr_t tail_p, skb_dma_addr;
-	int length;
 	unsigned long flags;
+	int rx_bd;
+	bool update_tail = false;
 
 	spin_lock_irqsave(&lp->rx_lock, flags);
 
-	tail_p = lp->rx_bd_p + sizeof(*lp->rx_bd_v) * lp->rx_bd_ci;
-	cur_p = &lp->rx_bd_v[lp->rx_bd_ci];
-
-	bdstat = be32_to_cpu(cur_p->app0);
-	while ((bdstat & STS_CTRL_APP0_CMPLT)) {
+	/* Process all received buffers, passing them on network
+	 * stack.  After this, the buffer descriptors will be in an
+	 * un-allocated stage, where no skb is allocated for it, and
+	 * they are therefore not available for TEMAC/DMA.
+	 */
+	do {
+		struct cdmac_bd *bd = &lp->rx_bd_v[lp->rx_bd_ci];
+		struct sk_buff *skb = lp->rx_skb[lp->rx_bd_ci];
+		unsigned int bdstat = be32_to_cpu(bd->app0);
+		int length;
+
+		/* While this should not normally happen, we can end
+		 * here when GFP_ATOMIC allocations fail, and we
+		 * therefore have un-allocated buffers.
+		 */
+		if (!skb)
+			break;
 
-		skb = lp->rx_skb[lp->rx_bd_ci];
-		length = be32_to_cpu(cur_p->app4) & 0x3FFF;
+		/* Loop over all completed buffer descriptors */
+		if (!(bdstat & STS_CTRL_APP0_CMPLT))
+			break;
 
-		dma_unmap_single(ndev->dev.parent, be32_to_cpu(cur_p->phys),
+		dma_unmap_single(ndev->dev.parent, be32_to_cpu(bd->phys),
 				 XTE_MAX_JUMBO_FRAME_SIZE, DMA_FROM_DEVICE);
+		/* The buffer is not valid for DMA anymore */
+		bd->phys = 0;
+		bd->len = 0;
 
+		length = be32_to_cpu(bd->app4) & 0x3FFF;
 		skb_put(skb, length);
 		skb->protocol = eth_type_trans(skb, ndev);
 		skb_checksum_none_assert(skb);
@@ -839,43 +906,102 @@ static void ll_temac_recv(struct net_device *ndev)
 			 * (back) for proper IP checksum byte order
 			 * (be16).
 			 */
-			skb->csum = htons(be32_to_cpu(cur_p->app3) & 0xFFFF);
+			skb->csum = htons(be32_to_cpu(bd->app3) & 0xFFFF);
 			skb->ip_summed = CHECKSUM_COMPLETE;
 		}
 
 		if (!skb_defer_rx_timestamp(skb))
 			netif_rx(skb);
+		/* The skb buffer is now owned by network stack above */
+		lp->rx_skb[lp->rx_bd_ci] = NULL;
 
 		ndev->stats.rx_packets++;
 		ndev->stats.rx_bytes += length;
 
-		new_skb = netdev_alloc_skb_ip_align(ndev,
-						XTE_MAX_JUMBO_FRAME_SIZE);
-		if (!new_skb) {
-			spin_unlock_irqrestore(&lp->rx_lock, flags);
-			return;
+		rx_bd = lp->rx_bd_ci;
+		if (++lp->rx_bd_ci >= RX_BD_NUM)
+			lp->rx_bd_ci = 0;
+	} while (rx_bd != lp->rx_bd_tail);
+
+	/* DMA operations will halt when the last buffer descriptor is
+	 * processed (ie. the one pointed to by RX_TAILDESC_PTR).
+	 * When that happens, no more interrupt events will be
+	 * generated.  No IRQ_COAL or IRQ_DLY, and not even an
+	 * IRQ_ERR.  To avoid stalling, we schedule a delayed work
+	 * when there is a potential risk of that happening.  The work
+	 * will call this function, and thus re-schedule itself until
+	 * enough buffers are available again.
+	 */
+	if (ll_temac_recv_buffers_available(lp) < lp->coalesce_count_rx)
+		schedule_delayed_work(&lp->restart_work, HZ / 1000);
+
+	/* Allocate new buffers for those buffer descriptors that were
+	 * passed to network stack.  Note that GFP_ATOMIC allocations
+	 * can fail (e.g. when a larger burst of GFP_ATOMIC
+	 * allocations occurs), so while we try to allocate all
+	 * buffers in the same interrupt where they were processed, we
+	 * continue with what we could get in case of allocation
+	 * failure.  Allocation of remaining buffers will be retried
+	 * in following calls.
+	 */
+	while (1) {
+		struct sk_buff *skb;
+		struct cdmac_bd *bd;
+		dma_addr_t skb_dma_addr;
+
+		rx_bd = lp->rx_bd_tail + 1;
+		if (rx_bd >= RX_BD_NUM)
+			rx_bd = 0;
+		bd = &lp->rx_bd_v[rx_bd];
+
+		if (bd->phys)
+			break;	/* All skb's allocated */
+
+		skb = netdev_alloc_skb_ip_align(ndev, XTE_MAX_JUMBO_FRAME_SIZE);
+		if (!skb) {
+			dev_warn(&ndev->dev, "skb alloc failed\n");
+			break;
 		}
 
-		cur_p->app0 = cpu_to_be32(STS_CTRL_APP0_IRQONEND);
-		skb_dma_addr = dma_map_single(ndev->dev.parent, new_skb->data,
+		skb_dma_addr = dma_map_single(ndev->dev.parent, skb->data,
 					      XTE_MAX_JUMBO_FRAME_SIZE,
 					      DMA_FROM_DEVICE);
-		cur_p->phys = cpu_to_be32(skb_dma_addr);
-		cur_p->len = cpu_to_be32(XTE_MAX_JUMBO_FRAME_SIZE);
-		lp->rx_skb[lp->rx_bd_ci] = new_skb;
+		if (WARN_ON_ONCE(dma_mapping_error(ndev->dev.parent,
+						   skb_dma_addr))) {
+			dev_kfree_skb_any(skb);
+			break;
+		}
 
-		lp->rx_bd_ci++;
-		if (lp->rx_bd_ci >= RX_BD_NUM)
-			lp->rx_bd_ci = 0;
+		bd->phys = cpu_to_be32(skb_dma_addr);
+		bd->len = cpu_to_be32(XTE_MAX_JUMBO_FRAME_SIZE);
+		bd->app0 = cpu_to_be32(STS_CTRL_APP0_IRQONEND);
+		lp->rx_skb[rx_bd] = skb;
 
-		cur_p = &lp->rx_bd_v[lp->rx_bd_ci];
-		bdstat = be32_to_cpu(cur_p->app0);
+		lp->rx_bd_tail = rx_bd;
+		update_tail = true;
+	}
+
+	/* Move tail pointer when buffers have been allocated */
+	if (update_tail) {
+		lp->dma_out(lp, RX_TAILDESC_PTR,
+			lp->rx_bd_p + sizeof(*lp->rx_bd_v) * lp->rx_bd_tail);
 	}
-	lp->dma_out(lp, RX_TAILDESC_PTR, tail_p);
 
 	spin_unlock_irqrestore(&lp->rx_lock, flags);
 }
 
+/* Function scheduled to ensure a restart in case of DMA halt
+ * condition caused by running out of buffer descriptors.
+ */
+static void ll_temac_restart_work_func(struct work_struct *work)
+{
+	struct temac_local *lp = container_of(work, struct temac_local,
+					      restart_work.work);
+	struct net_device *ndev = lp->ndev;
+
+	ll_temac_recv(ndev);
+}
+
 static irqreturn_t ll_temac_tx_irq(int irq, void *_ndev)
 {
 	struct net_device *ndev = _ndev;
@@ -968,6 +1094,8 @@ static int temac_stop(struct net_device *ndev)
 
 	dev_dbg(&ndev->dev, "temac_close()\n");
 
+	cancel_delayed_work_sync(&lp->restart_work);
+
 	free_irq(lp->tx_irq, ndev);
 	free_irq(lp->rx_irq, ndev);
 
@@ -1100,6 +1228,7 @@ static int temac_probe(struct platform_device *pdev)
 	lp->dev = &pdev->dev;
 	lp->options = XTE_OPTION_DEFAULTS;
 	spin_lock_init(&lp->rx_lock);
+	INIT_DELAYED_WORK(&lp->restart_work, ll_temac_restart_work_func);
 
 	/* Setup mutex for synchronization of indirect register access */
 	if (pdata) {
@@ -1206,6 +1335,7 @@ static int temac_probe(struct platform_device *pdev)
 		 */
 		lp->tx_chnl_ctrl = 0x10220000;
 		lp->rx_chnl_ctrl = 0xff070000;
+		lp->coalesce_count_rx = 0x07;
 
 		/* Finished with the DMA node; drop the reference */
 		of_node_put(dma_np);
@@ -1237,11 +1367,14 @@ static int temac_probe(struct platform_device *pdev)
 				(pdata->tx_irq_count << 16);
 		else
 			lp->tx_chnl_ctrl = 0x10220000;
-		if (pdata->rx_irq_timeout || pdata->rx_irq_count)
+		if (pdata->rx_irq_timeout || pdata->rx_irq_count) {
 			lp->rx_chnl_ctrl = (pdata->rx_irq_timeout << 24) |
 				(pdata->rx_irq_count << 16);
-		else
+			lp->coalesce_count_rx = pdata->rx_irq_count;
+		} else {
 			lp->rx_chnl_ctrl = 0xff070000;
+			lp->coalesce_count_rx = 0x07;
+		}
 	}
 
 	/* Error handle returned DMA RX and TX interrupts */
diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c
index 6fc04ffb22c2..d4e095d0e8f1 100644
--- a/drivers/net/ethernet/xscale/ixp4xx_eth.c
+++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c
@@ -517,25 +517,14 @@ static int ixp4xx_mdio_write(struct mii_bus *bus, int phy_id, int location,
 	return ret;
 }
 
-static int ixp4xx_mdio_register(void)
+static int ixp4xx_mdio_register(struct eth_regs __iomem *regs)
 {
 	int err;
 
 	if (!(mdio_bus = mdiobus_alloc()))
 		return -ENOMEM;
 
-	if (cpu_is_ixp43x()) {
-		/* IXP43x lacks NPE-B and uses NPE-C for MII PHY access */
-		if (!(ixp4xx_read_feature_bits() & IXP4XX_FEATURE_NPEC_ETH))
-			return -ENODEV;
-		mdio_regs = (struct eth_regs __iomem *)IXP4XX_EthC_BASE_VIRT;
-	} else {
-		/* All MII PHY accesses use NPE-B Ethernet registers */
-		if (!(ixp4xx_read_feature_bits() & IXP4XX_FEATURE_NPEB_ETH0))
-			return -ENODEV;
-		mdio_regs = (struct eth_regs __iomem *)IXP4XX_EthB_BASE_VIRT;
-	}
-
+	mdio_regs = regs;
 	__raw_writel(DEFAULT_CORE_CNTRL, &mdio_regs->core_control);
 	spin_lock_init(&mdio_lock);
 	mdio_bus->name = "IXP4xx MII Bus";
@@ -1374,7 +1363,7 @@ static const struct net_device_ops ixp4xx_netdev_ops = {
 	.ndo_validate_addr = eth_validate_addr,
 };
 
-static int eth_init_one(struct platform_device *pdev)
+static int ixp4xx_eth_probe(struct platform_device *pdev)
 {
 	struct port *port;
 	struct net_device *dev;
@@ -1384,7 +1373,7 @@ static int eth_init_one(struct platform_device *pdev)
 	char phy_id[MII_BUS_ID_SIZE + 3];
 	int err;
 
-	if (!(dev = alloc_etherdev(sizeof(struct port))))
+	if (!(dev = devm_alloc_etherdev(&pdev->dev, sizeof(struct port))))
 		return -ENOMEM;
 
 	SET_NETDEV_DEV(dev, &pdev->dev);
@@ -1394,20 +1383,51 @@ static int eth_init_one(struct platform_device *pdev)
 
 	switch (port->id) {
 	case IXP4XX_ETH_NPEA:
+		/* If the MDIO bus is not up yet, defer probe */
+		if (!mdio_bus)
+			return -EPROBE_DEFER;
 		port->regs = (struct eth_regs __iomem *)IXP4XX_EthA_BASE_VIRT;
 		regs_phys  = IXP4XX_EthA_BASE_PHYS;
 		break;
 	case IXP4XX_ETH_NPEB:
+		/*
+		 * On all except IXP43x, NPE-B is used for the MDIO bus.
+		 * If there is no NPE-B in the feature set, bail out, else
+		 * register the MDIO bus.
+		 */
+		if (!cpu_is_ixp43x()) {
+			if (!(ixp4xx_read_feature_bits() &
+			      IXP4XX_FEATURE_NPEB_ETH0))
+				return -ENODEV;
+			/* Else register the MDIO bus on NPE-B */
+			if ((err = ixp4xx_mdio_register(IXP4XX_EthC_BASE_VIRT)))
+				return err;
+		}
+		if (!mdio_bus)
+			return -EPROBE_DEFER;
 		port->regs = (struct eth_regs __iomem *)IXP4XX_EthB_BASE_VIRT;
 		regs_phys  = IXP4XX_EthB_BASE_PHYS;
 		break;
 	case IXP4XX_ETH_NPEC:
+		/*
+		 * IXP43x lacks NPE-B and uses NPE-C for the MDIO bus access,
+		 * of there is no NPE-C, no bus, nothing works, so bail out.
+		 */
+		if (cpu_is_ixp43x()) {
+			if (!(ixp4xx_read_feature_bits() &
+			      IXP4XX_FEATURE_NPEC_ETH))
+				return -ENODEV;
+			/* Else register the MDIO bus on NPE-C */
+			if ((err = ixp4xx_mdio_register(IXP4XX_EthC_BASE_VIRT)))
+				return err;
+		}
+		if (!mdio_bus)
+			return -EPROBE_DEFER;
 		port->regs = (struct eth_regs __iomem *)IXP4XX_EthC_BASE_VIRT;
 		regs_phys  = IXP4XX_EthC_BASE_PHYS;
 		break;
 	default:
-		err = -ENODEV;
-		goto err_free;
+		return -ENODEV;
 	}
 
 	dev->netdev_ops = &ixp4xx_netdev_ops;
@@ -1416,10 +1436,8 @@ static int eth_init_one(struct platform_device *pdev)
 
 	netif_napi_add(dev, &port->napi, eth_poll, NAPI_WEIGHT);
 
-	if (!(port->npe = npe_request(NPE_ID(port->id)))) {
-		err = -EIO;
-		goto err_free;
-	}
+	if (!(port->npe = npe_request(NPE_ID(port->id))))
+		return -EIO;
 
 	port->mem_res = request_mem_region(regs_phys, REGS_SIZE, dev->name);
 	if (!port->mem_res) {
@@ -1465,12 +1483,10 @@ err_free_mem:
 	release_resource(port->mem_res);
 err_npe_rel:
 	npe_release(port->npe);
-err_free:
-	free_netdev(dev);
 	return err;
 }
 
-static int eth_remove_one(struct platform_device *pdev)
+static int ixp4xx_eth_remove(struct platform_device *pdev)
 {
 	struct net_device *dev = platform_get_drvdata(pdev);
 	struct phy_device *phydev = dev->phydev;
@@ -1478,45 +1494,21 @@ static int eth_remove_one(struct platform_device *pdev)
 
 	unregister_netdev(dev);
 	phy_disconnect(phydev);
+	ixp4xx_mdio_remove();
 	npe_port_tab[NPE_ID(port->id)] = NULL;
 	npe_release(port->npe);
 	release_resource(port->mem_res);
-	free_netdev(dev);
 	return 0;
 }
 
 static struct platform_driver ixp4xx_eth_driver = {
 	.driver.name	= DRV_NAME,
-	.probe		= eth_init_one,
-	.remove		= eth_remove_one,
+	.probe		= ixp4xx_eth_probe,
+	.remove		= ixp4xx_eth_remove,
 };
-
-static int __init eth_init_module(void)
-{
-	int err;
-
-	/*
-	 * FIXME: we bail out on device tree boot but this really needs
-	 * to be fixed in a nicer way: this registers the MDIO bus before
-	 * even matching the driver infrastructure, we should only probe
-	 * detected hardware.
-	 */
-	if (of_have_populated_dt())
-		return -ENODEV;
-	if ((err = ixp4xx_mdio_register()))
-		return err;
-	return platform_driver_register(&ixp4xx_eth_driver);
-}
-
-static void __exit eth_cleanup_module(void)
-{
-	platform_driver_unregister(&ixp4xx_eth_driver);
-	ixp4xx_mdio_remove();
-}
+module_platform_driver(ixp4xx_eth_driver);
 
 MODULE_AUTHOR("Krzysztof Halasa");
 MODULE_DESCRIPTION("Intel IXP4xx Ethernet driver");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS("platform:ixp4xx_eth");
-module_init(eth_init_module);
-module_exit(eth_cleanup_module);
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index ac1470a6c64f..42bc72f7685a 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -987,9 +987,10 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (geneve->collect_md) {
 		info = skb_tunnel_info(skb);
 		if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) {
-			err = -EINVAL;
 			netdev_dbg(dev, "no tunnel metadata\n");
-			goto tx_error;
+			dev_kfree_skb(skb);
+			dev->stats.tx_dropped++;
+			return NETDEV_TX_OK;
 		}
 	} else {
 		info = &geneve->info;
@@ -1006,7 +1007,7 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	if (likely(!err))
 		return NETDEV_TX_OK;
-tx_error:
+
 	dev_kfree_skb(skb);
 
 	if (err == -ELOOP)
@@ -1207,7 +1208,7 @@ static int geneve_validate(struct nlattr *tb[], struct nlattr *data[],
 		enum ifla_geneve_df df = nla_get_u8(data[IFLA_GENEVE_DF]);
 
 		if (df < 0 || df > GENEVE_DF_MAX) {
-			NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_GENEVE_DF],
+			NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_DF],
 					    "Invalid DF attribute");
 			return -EINVAL;
 		}
@@ -1614,11 +1615,11 @@ static int geneve_changelink(struct net_device *dev, struct nlattr *tb[],
 			     struct netlink_ext_ack *extack)
 {
 	struct geneve_dev *geneve = netdev_priv(dev);
+	enum ifla_geneve_df df = geneve->df;
 	struct geneve_sock *gs4, *gs6;
 	struct ip_tunnel_info info;
 	bool metadata;
 	bool use_udp6_rx_checksums;
-	enum ifla_geneve_df df;
 	bool ttl_inherit;
 	int err;
 
@@ -1648,6 +1649,7 @@ static int geneve_changelink(struct net_device *dev, struct nlattr *tb[],
 	geneve->collect_md = metadata;
 	geneve->use_udp6_rx_checksums = use_udp6_rx_checksums;
 	geneve->ttl_inherit = ttl_inherit;
+	geneve->df = df;
 	geneve_unquiesce(geneve, gs4, gs6);
 
 	return 0;
@@ -1845,8 +1847,6 @@ static void geneve_destroy_tunnels(struct net *net, struct list_head *head)
 		if (!net_eq(dev_net(geneve->dev), net))
 			unregister_netdevice_queue(geneve->dev, head);
 	}
-
-	WARN_ON_ONCE(!list_empty(&gn->sock_list));
 }
 
 static void __net_exit geneve_exit_batch_net(struct list_head *net_list)
@@ -1861,6 +1861,12 @@ static void __net_exit geneve_exit_batch_net(struct list_head *net_list)
 	/* unregister the devices gathered above */
 	unregister_netdevice_many(&list);
 	rtnl_unlock();
+
+	list_for_each_entry(net, net_list, exit_list) {
+		const struct geneve_net *gn = net_generic(net, geneve_net_id);
+
+		WARN_ON_ONCE(!list_empty(&gn->sock_list));
+	}
 }
 
 static struct pernet_operations geneve_net_ops = {
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index fca471e27f39..d89ec99abcd6 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -767,12 +767,12 @@ static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize)
 	int i;
 
 	gtp->addr_hash = kmalloc_array(hsize, sizeof(struct hlist_head),
-				       GFP_KERNEL);
+				       GFP_KERNEL | __GFP_NOWARN);
 	if (gtp->addr_hash == NULL)
 		return -ENOMEM;
 
 	gtp->tid_hash = kmalloc_array(hsize, sizeof(struct hlist_head),
-				      GFP_KERNEL);
+				      GFP_KERNEL | __GFP_NOWARN);
 	if (gtp->tid_hash == NULL)
 		goto err1;
 
@@ -804,19 +804,21 @@ static struct sock *gtp_encap_enable_socket(int fd, int type,
 		return NULL;
 	}
 
-	if (sock->sk->sk_protocol != IPPROTO_UDP) {
+	sk = sock->sk;
+	if (sk->sk_protocol != IPPROTO_UDP ||
+	    sk->sk_type != SOCK_DGRAM ||
+	    (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)) {
 		pr_debug("socket fd=%d not UDP\n", fd);
 		sk = ERR_PTR(-EINVAL);
 		goto out_sock;
 	}
 
-	lock_sock(sock->sk);
-	if (sock->sk->sk_user_data) {
+	lock_sock(sk);
+	if (sk->sk_user_data) {
 		sk = ERR_PTR(-EBUSY);
-		goto out_sock;
+		goto out_rel_sock;
 	}
 
-	sk = sock->sk;
 	sock_hold(sk);
 
 	tuncfg.sk_user_data = gtp;
@@ -826,8 +828,9 @@ static struct sock *gtp_encap_enable_socket(int fd, int type,
 
 	setup_udp_tunnel_sock(sock_net(sock->sk), sock, &tuncfg);
 
-out_sock:
+out_rel_sock:
 	release_sock(sock->sk);
+out_sock:
 	sockfd_put(sock);
 	return sk;
 }
@@ -1169,11 +1172,11 @@ out_unlock:
 static struct genl_family gtp_genl_family;
 
 static int gtp_genl_fill_info(struct sk_buff *skb, u32 snd_portid, u32 snd_seq,
-			      u32 type, struct pdp_ctx *pctx)
+			      int flags, u32 type, struct pdp_ctx *pctx)
 {
 	void *genlh;
 
-	genlh = genlmsg_put(skb, snd_portid, snd_seq, &gtp_genl_family, 0,
+	genlh = genlmsg_put(skb, snd_portid, snd_seq, &gtp_genl_family, flags,
 			    type);
 	if (genlh == NULL)
 		goto nlmsg_failure;
@@ -1227,8 +1230,8 @@ static int gtp_genl_get_pdp(struct sk_buff *skb, struct genl_info *info)
 		goto err_unlock;
 	}
 
-	err = gtp_genl_fill_info(skb2, NETLINK_CB(skb).portid,
-				 info->snd_seq, info->nlhdr->nlmsg_type, pctx);
+	err = gtp_genl_fill_info(skb2, NETLINK_CB(skb).portid, info->snd_seq,
+				 0, info->nlhdr->nlmsg_type, pctx);
 	if (err < 0)
 		goto err_unlock_free;
 
@@ -1271,6 +1274,7 @@ static int gtp_genl_dump_pdp(struct sk_buff *skb,
 				    gtp_genl_fill_info(skb,
 					    NETLINK_CB(cb->skb).portid,
 					    cb->nlh->nlmsg_seq,
+					    NLM_F_MULTI,
 					    cb->nlh->nlmsg_type, pctx)) {
 					cb->args[0] = i;
 					cb->args[1] = j;
diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c
index fbec711ff514..1ad6085994b1 100644
--- a/drivers/net/hamradio/bpqether.c
+++ b/drivers/net/hamradio/bpqether.c
@@ -148,7 +148,8 @@ static inline struct net_device *bpq_get_ax25_dev(struct net_device *dev)
 {
 	struct bpqdev *bpq;
 
-	list_for_each_entry_rcu(bpq, &bpq_devices, bpq_list) {
+	list_for_each_entry_rcu(bpq, &bpq_devices, bpq_list,
+				lockdep_rtnl_is_held()) {
 		if (bpq->ethdev == dev)
 			return bpq->axdev;
 	}
diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c
index 71cdef9fb56b..5ab53e9942f3 100644
--- a/drivers/net/hamradio/yam.c
+++ b/drivers/net/hamradio/yam.c
@@ -1133,6 +1133,7 @@ static int __init yam_init_driver(void)
 		err = register_netdev(dev);
 		if (err) {
 			printk(KERN_WARNING "yam: cannot register net device %s\n", dev->name);
+			free_netdev(dev);
 			goto error;
 		}
 		yam_devs[i] = dev;
diff --git a/drivers/net/hippi/rrunner.c b/drivers/net/hippi/rrunner.c
index 7b9350dbebdd..dd6393394bab 100644
--- a/drivers/net/hippi/rrunner.c
+++ b/drivers/net/hippi/rrunner.c
@@ -1244,7 +1244,7 @@ static int rr_open(struct net_device *dev)
 		rrpriv->info = NULL;
 	}
 	if (rrpriv->rx_ctrl) {
-		pci_free_consistent(pdev, sizeof(struct ring_ctrl),
+		pci_free_consistent(pdev, 256 * sizeof(struct ring_ctrl),
 				    rrpriv->rx_ctrl, rrpriv->rx_ctrl_dma);
 		rrpriv->rx_ctrl = NULL;
 	}
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index ecc9af050387..bb38a59bf468 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -169,7 +169,6 @@ struct rndis_device {
 
 	u8 hw_mac_adr[ETH_ALEN];
 	u8 rss_key[NETVSC_HASH_KEYLEN];
-	u16 rx_table[ITAB_NUM];
 };
 
 
@@ -937,6 +936,8 @@ struct net_device_context {
 
 	u32 tx_table[VRSS_SEND_TAB_SIZE];
 
+	u16 rx_table[ITAB_NUM];
+
 	/* Ethtool settings */
 	u8 duplex;
 	u32 speed;
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index d22a36fc7a7c..7745febdac73 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -99,7 +99,7 @@ static struct netvsc_device *alloc_net_device(void)
 
 	init_waitqueue_head(&net_device->wait_drain);
 	net_device->destroy = false;
-	net_device->tx_disable = false;
+	net_device->tx_disable = true;
 
 	net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT;
 	net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT;
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 8ed79b418d88..b61d895b6a63 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -285,9 +285,9 @@ static inline u32 netvsc_get_hash(
 		else if (flow.basic.n_proto == htons(ETH_P_IPV6))
 			hash = jhash2((u32 *)&flow.addrs.v6addrs, 8, hashrnd);
 		else
-			hash = 0;
+			return 0;
 
-		skb_set_hash(skb, hash, PKT_HASH_TYPE_L3);
+		__skb_set_sw_hash(skb, hash, false);
 	}
 
 	return hash;
@@ -531,12 +531,13 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 	u32 hash;
 	struct hv_page_buffer pb[MAX_PAGE_BUFFER_COUNT];
 
-	/* if VF is present and up then redirect packets
-	 * already called with rcu_read_lock_bh
+	/* If VF is present and up then redirect packets to it.
+	 * Skip the VF if it is marked down or has no carrier.
+	 * If netpoll is in uses, then VF can not be used either.
 	 */
 	vf_netdev = rcu_dereference_bh(net_device_ctx->vf_netdev);
 	if (vf_netdev && netif_running(vf_netdev) &&
-	    !netpoll_tx_running(net))
+	    netif_carrier_ok(vf_netdev) && !netpoll_tx_running(net))
 		return netvsc_vf_xmit(net, vf_netdev, skb);
 
 	/* We will atmost need two pages to describe the rndis
@@ -795,8 +796,7 @@ static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net,
 	    skb->protocol == htons(ETH_P_IP))
 		netvsc_comp_ipcsum(skb);
 
-	/* Do L4 checksum offload if enabled and present.
-	 */
+	/* Do L4 checksum offload if enabled and present. */
 	if (csum_info && (net->features & NETIF_F_RXCSUM)) {
 		if (csum_info->receive.tcp_checksum_succeeded ||
 		    csum_info->receive.udp_checksum_succeeded)
@@ -974,6 +974,7 @@ static int netvsc_attach(struct net_device *ndev,
 	}
 
 	/* In any case device is now ready */
+	nvdev->tx_disable = false;
 	netif_device_attach(ndev);
 
 	/* Note: enable and attach happen when sub-channels setup */
@@ -1659,7 +1660,7 @@ static int netvsc_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
 	rndis_dev = ndev->extension;
 	if (indir) {
 		for (i = 0; i < ITAB_NUM; i++)
-			indir[i] = rndis_dev->rx_table[i];
+			indir[i] = ndc->rx_table[i];
 	}
 
 	if (key)
@@ -1689,7 +1690,7 @@ static int netvsc_set_rxfh(struct net_device *dev, const u32 *indir,
 				return -EINVAL;
 
 		for (i = 0; i < ITAB_NUM; i++)
-			rndis_dev->rx_table[i] = indir[i];
+			ndc->rx_table[i] = indir[i];
 	}
 
 	if (!key) {
@@ -2333,6 +2334,8 @@ static int netvsc_probe(struct hv_device *dev,
 	else
 		net->max_mtu = ETH_DATA_LEN;
 
+	nvdev->tx_disable = false;
+
 	ret = register_netdevice(net);
 	if (ret != 0) {
 		pr_err("Unable to register netdev.\n");
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index c0c2934552e4..539d58bd1558 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -767,6 +767,7 @@ static int rndis_set_rss_param_msg(struct rndis_device *rdev,
 				   const u8 *rss_key, u16 flag)
 {
 	struct net_device *ndev = rdev->ndev;
+	struct net_device_context *ndc = netdev_priv(ndev);
 	struct rndis_request *request;
 	struct rndis_set_request *set;
 	struct rndis_set_complete *set_complete;
@@ -806,7 +807,7 @@ static int rndis_set_rss_param_msg(struct rndis_device *rdev,
 	/* Set indirection table entries */
 	itab = (u32 *)(rssp + 1);
 	for (i = 0; i < ITAB_NUM; i++)
-		itab[i] = rdev->rx_table[i];
+		itab[i] = ndc->rx_table[i];
 
 	/* Set hask key values */
 	keyp = (u8 *)((unsigned long)rssp + rssp->hashkey_offset);
@@ -1304,6 +1305,7 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
 				      struct netvsc_device_info *device_info)
 {
 	struct net_device *net = hv_get_drvdata(dev);
+	struct net_device_context *ndc = netdev_priv(net);
 	struct netvsc_device *net_device;
 	struct rndis_device *rndis_device;
 	struct ndis_recv_scale_cap rsscap;
@@ -1390,9 +1392,11 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
 	/* We will use the given number of channels if available. */
 	net_device->num_chn = min(net_device->max_chn, device_info->num_chn);
 
-	for (i = 0; i < ITAB_NUM; i++)
-		rndis_device->rx_table[i] = ethtool_rxfh_indir_default(
+	if (!netif_is_rxfh_configured(net)) {
+		for (i = 0; i < ITAB_NUM; i++)
+			ndc->rx_table[i] = ethtool_rxfh_indir_default(
 						i, net_device->num_chn);
+	}
 
 	atomic_set(&net_device->open_chn, 1);
 	vmbus_set_sc_create_callback(dev->channel, netvsc_sc_open);
@@ -1431,8 +1435,6 @@ void rndis_filter_device_remove(struct hv_device *dev,
 	/* Halt and release the rndis device */
 	rndis_filter_halt_device(net_dev, rndis_dev);
 
-	net_dev->extension = NULL;
-
 	netvsc_device_remove(dev);
 }
 
diff --git a/drivers/net/ieee802154/adf7242.c b/drivers/net/ieee802154/adf7242.c
index c9392d70e639..3cbdda5e06e5 100644
--- a/drivers/net/ieee802154/adf7242.c
+++ b/drivers/net/ieee802154/adf7242.c
@@ -1269,7 +1269,7 @@ static int adf7242_probe(struct spi_device *spi)
 					     WQ_MEM_RECLAIM);
 	if (unlikely(!lp->wqueue)) {
 		ret = -ENOMEM;
-		goto err_hw_init;
+		goto err_alloc_wq;
 	}
 
 	ret = adf7242_hw_init(lp);
@@ -1301,6 +1301,8 @@ static int adf7242_probe(struct spi_device *spi)
 	return ret;
 
 err_hw_init:
+	destroy_workqueue(lp->wqueue);
+err_alloc_wq:
 	mutex_destroy(&lp->bmux);
 	ieee802154_free_hw(lp->hw);
 
diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c
index 242b9b0943f8..7fe306e76281 100644
--- a/drivers/net/ifb.c
+++ b/drivers/net/ifb.c
@@ -75,7 +75,7 @@ static void ifb_ri_tasklet(unsigned long _txp)
 	}
 
 	while ((skb = __skb_dequeue(&txp->tq)) != NULL) {
-		skb->tc_redirected = 0;
+		skb->redirected = 0;
 		skb->tc_skip_classify = 1;
 
 		u64_stats_update_begin(&txp->tsync);
@@ -96,7 +96,7 @@ static void ifb_ri_tasklet(unsigned long _txp)
 		rcu_read_unlock();
 		skb->skb_iif = txp->dev->ifindex;
 
-		if (!skb->tc_from_ingress) {
+		if (!skb->from_ingress) {
 			dev_queue_xmit(skb);
 		} else {
 			skb_pull_rcsum(skb, skb->mac_len);
@@ -243,7 +243,7 @@ static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev)
 	txp->rx_bytes += skb->len;
 	u64_stats_update_end(&txp->rsync);
 
-	if (!skb->tc_redirected || !skb->skb_iif) {
+	if (!skb->redirected || !skb->skb_iif) {
 		dev_kfree_skb(skb);
 		dev->stats.rx_dropped++;
 		return NETDEV_TX_OK;
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index 30cd0c4f0be0..8801d093135c 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -293,6 +293,7 @@ void ipvlan_process_multicast(struct work_struct *work)
 		}
 		if (dev)
 			dev_put(dev);
+		cond_resched();
 	}
 }
 
@@ -498,19 +499,21 @@ static int ipvlan_process_outbound(struct sk_buff *skb)
 	struct ethhdr *ethh = eth_hdr(skb);
 	int ret = NET_XMIT_DROP;
 
-	/* In this mode we dont care about multicast and broadcast traffic */
-	if (is_multicast_ether_addr(ethh->h_dest)) {
-		pr_debug_ratelimited("Dropped {multi|broad}cast of type=[%x]\n",
-				     ntohs(skb->protocol));
-		kfree_skb(skb);
-		goto out;
-	}
-
 	/* The ipvlan is a pseudo-L2 device, so the packets that we receive
 	 * will have L2; which need to discarded and processed further
 	 * in the net-ns of the main-device.
 	 */
 	if (skb_mac_header_was_set(skb)) {
+		/* In this mode we dont care about
+		 * multicast and broadcast traffic */
+		if (is_multicast_ether_addr(ethh->h_dest)) {
+			pr_debug_ratelimited(
+				"Dropped {multi|broad}cast of type=[%x]\n",
+				ntohs(skb->protocol));
+			kfree_skb(skb);
+			goto out;
+		}
+
 		skb_pull(skb, sizeof(*ethh));
 		skb->mac_header = (typeof(skb->mac_header))~0U;
 		skb_reset_network_header(skb);
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 1c96bed5a7c4..f55d8853248e 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -165,7 +165,6 @@ static void ipvlan_uninit(struct net_device *dev)
 static int ipvlan_open(struct net_device *dev)
 {
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
-	struct net_device *phy_dev = ipvlan->phy_dev;
 	struct ipvl_addr *addr;
 
 	if (ipvlan->port->mode == IPVLAN_MODE_L3 ||
@@ -179,7 +178,7 @@ static int ipvlan_open(struct net_device *dev)
 		ipvlan_ht_addr_add(ipvlan, addr);
 	rcu_read_unlock();
 
-	return dev_uc_add(phy_dev, phy_dev->dev_addr);
+	return 0;
 }
 
 static int ipvlan_stop(struct net_device *dev)
@@ -191,8 +190,6 @@ static int ipvlan_stop(struct net_device *dev)
 	dev_uc_unsync(phy_dev, dev);
 	dev_mc_unsync(phy_dev, dev);
 
-	dev_uc_del(phy_dev, phy_dev->dev_addr);
-
 	rcu_read_lock();
 	list_for_each_entry_rcu(addr, &ipvlan->addrs, anode)
 		ipvlan_ht_addr_del(addr);
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 1bd113b142ea..aa2d99712af1 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -16,6 +16,7 @@
 #include <net/genetlink.h>
 #include <net/sock.h>
 #include <net/gro_cells.h>
+#include <linux/if_arp.h>
 
 #include <uapi/linux/if_macsec.h>
 
@@ -533,6 +534,11 @@ static struct macsec_eth_header *macsec_ethhdr(struct sk_buff *skb)
 	return (struct macsec_eth_header *)skb_mac_header(skb);
 }
 
+static sci_t dev_to_sci(struct net_device *dev, __be16 port)
+{
+	return make_sci(dev->dev_addr, port);
+}
+
 static u32 tx_sa_update_pn(struct macsec_tx_sa *tx_sa, struct macsec_secy *secy)
 {
 	u32 pn;
@@ -1309,7 +1315,8 @@ static struct crypto_aead *macsec_alloc_tfm(char *key, int key_len, int icv_len)
 	struct crypto_aead *tfm;
 	int ret;
 
-	tfm = crypto_alloc_aead("gcm(aes)", 0, 0);
+	/* Pick a sync gcm(aes) cipher to ensure order is preserved. */
+	tfm = crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC);
 
 	if (IS_ERR(tfm))
 		return tfm;
@@ -2905,6 +2912,7 @@ static int macsec_set_mac_address(struct net_device *dev, void *p)
 
 out:
 	ether_addr_copy(dev->dev_addr, addr->sa_data);
+	macsec->secy.sci = dev_to_sci(dev, MACSEC_PORT_ES);
 	return 0;
 }
 
@@ -2985,6 +2993,7 @@ static const struct device_type macsec_type = {
 
 static const struct nla_policy macsec_rtnl_policy[IFLA_MACSEC_MAX + 1] = {
 	[IFLA_MACSEC_SCI] = { .type = NLA_U64 },
+	[IFLA_MACSEC_PORT] = { .type = NLA_U16 },
 	[IFLA_MACSEC_ICV_LEN] = { .type = NLA_U8 },
 	[IFLA_MACSEC_CIPHER_SUITE] = { .type = NLA_U64 },
 	[IFLA_MACSEC_WINDOW] = { .type = NLA_U32 },
@@ -3184,11 +3193,6 @@ static bool sci_exists(struct net_device *dev, sci_t sci)
 	return false;
 }
 
-static sci_t dev_to_sci(struct net_device *dev, __be16 port)
-{
-	return make_sci(dev->dev_addr, port);
-}
-
 static int macsec_add_dev(struct net_device *dev, sci_t sci, u8 icv_len)
 {
 	struct macsec_dev *macsec = macsec_priv(dev);
@@ -3231,17 +3235,19 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
 			  struct netlink_ext_ack *extack)
 {
 	struct macsec_dev *macsec = macsec_priv(dev);
+	rx_handler_func_t *rx_handler;
+	u8 icv_len = DEFAULT_ICV_LEN;
 	struct net_device *real_dev;
-	int err;
+	int err, mtu;
 	sci_t sci;
-	u8 icv_len = DEFAULT_ICV_LEN;
-	rx_handler_func_t *rx_handler;
 
 	if (!tb[IFLA_LINK])
 		return -EINVAL;
 	real_dev = __dev_get_by_index(net, nla_get_u32(tb[IFLA_LINK]));
 	if (!real_dev)
 		return -ENODEV;
+	if (real_dev->type != ARPHRD_ETHER)
+		return -EINVAL;
 
 	dev->priv_flags |= IFF_MACSEC;
 
@@ -3249,7 +3255,11 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
 
 	if (data && data[IFLA_MACSEC_ICV_LEN])
 		icv_len = nla_get_u8(data[IFLA_MACSEC_ICV_LEN]);
-	dev->mtu = real_dev->mtu - icv_len - macsec_extra_len(true);
+	mtu = real_dev->mtu - icv_len - macsec_extra_len(true);
+	if (mtu < 0)
+		dev->mtu = 0;
+	else
+		dev->mtu = mtu;
 
 	rx_handler = rtnl_dereference(real_dev->rx_handler);
 	if (rx_handler && rx_handler != macsec_handle_frame)
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 6d21c747a2b0..1f9a85901066 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -334,6 +334,8 @@ static void macvlan_process_broadcast(struct work_struct *w)
 		if (src)
 			dev_put(src->dev);
 		consume_skb(skb);
+
+		cond_resched();
 	}
 }
 
@@ -445,6 +447,10 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb)
 	int ret;
 	rx_handler_result_t handle_res;
 
+	/* Packets from dev_loopback_xmit() do not have L2 header, bail out */
+	if (unlikely(skb->pkt_type == PACKET_LOOPBACK))
+		return RX_HANDLER_PASS;
+
 	port = macvlan_port_get_rcu(skb->dev);
 	if (is_multicast_ether_addr(eth->h_dest)) {
 		unsigned int hash;
@@ -513,10 +519,11 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
 	const struct macvlan_dev *dest;
 
 	if (vlan->mode == MACVLAN_MODE_BRIDGE) {
-		const struct ethhdr *eth = (void *)skb->data;
+		const struct ethhdr *eth = skb_eth_hdr(skb);
 
 		/* send to other bridge ports directly */
 		if (is_multicast_ether_addr(eth->h_dest)) {
+			skb_reset_mac_header(skb);
 			macvlan_broadcast(skb, port, dev, MACVLAN_MODE_BRIDGE);
 			goto xmit_world;
 		}
@@ -1720,7 +1727,7 @@ static int macvlan_device_event(struct notifier_block *unused,
 						struct macvlan_dev,
 						list);
 
-		if (macvlan_sync_address(vlan->dev, dev->dev_addr))
+		if (vlan && macvlan_sync_address(vlan->dev, dev->dev_addr))
 			return NOTIFY_BAD;
 
 		break;
diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c
index b16a1221d19b..fb182bec8f06 100644
--- a/drivers/net/net_failover.c
+++ b/drivers/net/net_failover.c
@@ -61,7 +61,8 @@ static int net_failover_open(struct net_device *dev)
 	return 0;
 
 err_standby_open:
-	dev_close(primary_dev);
+	if (primary_dev)
+		dev_close(primary_dev);
 err_primary_open:
 	netif_tx_disable(dev);
 	return err;
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index 6825254eb882..3d770bf3d693 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -29,7 +29,7 @@ static struct dentry *nsim_dev_ddir;
 
 static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev)
 {
-	char dev_ddir_name[16];
+	char dev_ddir_name[sizeof(DRV_NAME) + 10];
 
 	sprintf(dev_ddir_name, DRV_NAME "%u", nsim_dev->nsim_bus_dev->dev.id);
 	nsim_dev->ddir = debugfs_create_dir(dev_ddir_name, nsim_dev_ddir);
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 533a182eefca..2a197cd22628 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -314,7 +314,7 @@ nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port)
 	rtnl_lock();
 	err = nsim_bpf_init(ns);
 	if (err)
-		goto err_free_netdev;
+		goto err_rtnl_unlock;
 
 	nsim_ipsec_init(ns);
 
@@ -328,8 +328,8 @@ nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port)
 err_ipsec_teardown:
 	nsim_ipsec_teardown(ns);
 	nsim_bpf_uninit(ns);
+err_rtnl_unlock:
 	rtnl_unlock();
-err_free_netdev:
 	free_netdev(dev);
 	return ERR_PTR(err);
 }
diff --git a/drivers/net/phy/bcm63xx.c b/drivers/net/phy/bcm63xx.c
index 23f1958ba6ad..459fb2069c7e 100644
--- a/drivers/net/phy/bcm63xx.c
+++ b/drivers/net/phy/bcm63xx.c
@@ -73,6 +73,7 @@ static struct phy_driver bcm63xx_driver[] = {
 	/* same phy as above, with just a different OUI */
 	.phy_id		= 0x002bdc00,
 	.phy_id_mask	= 0xfffffc00,
+	.name		= "Broadcom BCM63XX (2)",
 	/* PHY_BASIC_FEATURES */
 	.flags		= PHY_IS_INTERNAL,
 	.config_init	= bcm63xx_config_init,
diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index 67fa05d67523..8b2818ef52b7 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -26,18 +26,13 @@ MODULE_DESCRIPTION("Broadcom PHY driver");
 MODULE_AUTHOR("Maciej W. Rozycki");
 MODULE_LICENSE("GPL");
 
+static int bcm54xx_config_clock_delay(struct phy_device *phydev);
+
 static int bcm54210e_config_init(struct phy_device *phydev)
 {
 	int val;
 
-	val = bcm54xx_auxctl_read(phydev, MII_BCM54XX_AUXCTL_SHDWSEL_MISC);
-	val &= ~MII_BCM54XX_AUXCTL_SHDWSEL_MISC_RGMII_SKEW_EN;
-	val |= MII_BCM54XX_AUXCTL_MISC_WREN;
-	bcm54xx_auxctl_write(phydev, MII_BCM54XX_AUXCTL_SHDWSEL_MISC, val);
-
-	val = bcm_phy_read_shadow(phydev, BCM54810_SHD_CLK_CTL);
-	val &= ~BCM54810_SHD_CLK_CTL_GTXCLK_EN;
-	bcm_phy_write_shadow(phydev, BCM54810_SHD_CLK_CTL, val);
+	bcm54xx_config_clock_delay(phydev);
 
 	if (phydev->dev_flags & PHY_BRCM_EN_MASTER_MODE) {
 		val = phy_read(phydev, MII_CTRL1000);
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 6580094161a9..1205affd5caa 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -1103,7 +1103,7 @@ static struct dp83640_clock *dp83640_clock_get_bus(struct mii_bus *bus)
 		goto out;
 	}
 	dp83640_clock_init(clock, bus);
-	list_add_tail(&phyter_clocks, &clock->list);
+	list_add_tail(&clock->list, &phyter_clocks);
 out:
 	mutex_unlock(&phyter_clocks_lock);
 
@@ -1332,6 +1332,7 @@ static int dp83640_hwtstamp(struct phy_device *phydev, struct ifreq *ifr)
 		dp83640->hwts_rx_en = 1;
 		dp83640->layer = PTP_CLASS_L4;
 		dp83640->version = PTP_CLASS_V1;
+		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
@@ -1339,6 +1340,7 @@ static int dp83640_hwtstamp(struct phy_device *phydev, struct ifreq *ifr)
 		dp83640->hwts_rx_en = 1;
 		dp83640->layer = PTP_CLASS_L4;
 		dp83640->version = PTP_CLASS_V2;
+		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
@@ -1346,6 +1348,7 @@ static int dp83640_hwtstamp(struct phy_device *phydev, struct ifreq *ifr)
 		dp83640->hwts_rx_en = 1;
 		dp83640->layer = PTP_CLASS_L2;
 		dp83640->version = PTP_CLASS_V2;
+		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
@@ -1353,6 +1356,7 @@ static int dp83640_hwtstamp(struct phy_device *phydev, struct ifreq *ifr)
 		dp83640->hwts_rx_en = 1;
 		dp83640->layer = PTP_CLASS_L4 | PTP_CLASS_L2;
 		dp83640->version = PTP_CLASS_V2;
+		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		break;
 	default:
 		return -ERANGE;
diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c
index 97a1c4cf089c..6eaec42fec05 100644
--- a/drivers/net/phy/dp83867.c
+++ b/drivers/net/phy/dp83867.c
@@ -67,6 +67,7 @@
 #define DP83867_PHYCR_FIFO_DEPTH_SHIFT		14
 #define DP83867_PHYCR_FIFO_DEPTH_MASK		(3 << 14)
 #define DP83867_PHYCR_RESERVED_MASK		BIT(11)
+#define DP83867_PHYCR_FORCE_LINK_GOOD		BIT(10)
 
 /* RGMIIDCTL bits */
 #define DP83867_RGMII_TX_CLK_DELAY_SHIFT	4
@@ -345,7 +346,12 @@ static int dp83867_phy_reset(struct phy_device *phydev)
 
 	usleep_range(10, 20);
 
-	return 0;
+	/* After reset FORCE_LINK_GOOD bit is set. Although the
+	 * default value should be unset. Disable FORCE_LINK_GOOD
+	 * for the phy to work properly.
+	 */
+	return phy_modify(phydev, MII_DP83867_PHYCTRL,
+			 DP83867_PHYCR_FORCE_LINK_GOOD, 0);
 }
 
 static struct phy_driver dp83867_driver[] = {
diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c
index 7c5265fd2b94..4190f9ed5313 100644
--- a/drivers/net/phy/fixed_phy.c
+++ b/drivers/net/phy/fixed_phy.c
@@ -212,16 +212,13 @@ static struct gpio_desc *fixed_phy_get_gpiod(struct device_node *np)
 	 */
 	gpiod = gpiod_get_from_of_node(fixed_link_node, "link-gpios", 0,
 				       GPIOD_IN, "mdio");
-	of_node_put(fixed_link_node);
-	if (IS_ERR(gpiod)) {
-		if (PTR_ERR(gpiod) == -EPROBE_DEFER)
-			return gpiod;
-
+	if (IS_ERR(gpiod) && PTR_ERR(gpiod) != -EPROBE_DEFER) {
 		if (PTR_ERR(gpiod) != -ENOENT)
 			pr_err("error getting GPIO for fixed link %pOF, proceed without\n",
 			       fixed_link_node);
 		gpiod = NULL;
 	}
+	of_node_put(fixed_link_node);
 
 	return gpiod;
 }
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index a7796134e3be..91cf1d167263 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -358,7 +358,7 @@ static int m88e1101_config_aneg(struct phy_device *phydev)
 	return marvell_config_aneg(phydev);
 }
 
-#ifdef CONFIG_OF_MDIO
+#if IS_ENABLED(CONFIG_OF_MDIO)
 /* Set and/or override some configuration registers based on the
  * marvell,reg-init property stored in the of_node for the phydev.
  *
diff --git a/drivers/net/phy/mdio-bcm-iproc.c b/drivers/net/phy/mdio-bcm-iproc.c
index 7d0f388d8db8..fd0daf63be97 100644
--- a/drivers/net/phy/mdio-bcm-iproc.c
+++ b/drivers/net/phy/mdio-bcm-iproc.c
@@ -180,6 +180,23 @@ static int iproc_mdio_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+int iproc_mdio_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct iproc_mdio_priv *priv = platform_get_drvdata(pdev);
+
+	/* restore the mii clock configuration */
+	iproc_mdio_config_clk(priv->base);
+
+	return 0;
+}
+
+static const struct dev_pm_ops iproc_mdio_pm_ops = {
+	.resume = iproc_mdio_resume
+};
+#endif /* CONFIG_PM_SLEEP */
+
 static const struct of_device_id iproc_mdio_of_match[] = {
 	{ .compatible = "brcm,iproc-mdio", },
 	{ /* sentinel */ },
@@ -190,6 +207,9 @@ static struct platform_driver iproc_mdio_driver = {
 	.driver = {
 		.name = "iproc-mdio",
 		.of_match_table = iproc_mdio_of_match,
+#ifdef CONFIG_PM_SLEEP
+		.pm = &iproc_mdio_pm_ops,
+#endif
 	},
 	.probe = iproc_mdio_probe,
 	.remove = iproc_mdio_remove,
diff --git a/drivers/net/phy/mdio-bcm-unimac.c b/drivers/net/phy/mdio-bcm-unimac.c
index 4a28fb29adaa..fbd36891ee64 100644
--- a/drivers/net/phy/mdio-bcm-unimac.c
+++ b/drivers/net/phy/mdio-bcm-unimac.c
@@ -242,11 +242,9 @@ static int unimac_mdio_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
-	priv->clk = devm_clk_get(&pdev->dev, NULL);
-	if (PTR_ERR(priv->clk) == -EPROBE_DEFER)
+	priv->clk = devm_clk_get_optional(&pdev->dev, NULL);
+	if (IS_ERR(priv->clk))
 		return PTR_ERR(priv->clk);
-	else
-		priv->clk = NULL;
 
 	ret = clk_prepare_enable(priv->clk);
 	if (ret)
diff --git a/drivers/net/phy/mdio-mux-bcm-iproc.c b/drivers/net/phy/mdio-mux-bcm-iproc.c
index 88d409e48c1f..aad6809ebe39 100644
--- a/drivers/net/phy/mdio-mux-bcm-iproc.c
+++ b/drivers/net/phy/mdio-mux-bcm-iproc.c
@@ -288,8 +288,13 @@ static int mdio_mux_iproc_suspend(struct device *dev)
 static int mdio_mux_iproc_resume(struct device *dev)
 {
 	struct iproc_mdiomux_desc *md = dev_get_drvdata(dev);
+	int rc;
 
-	clk_prepare_enable(md->core_clk);
+	rc = clk_prepare_enable(md->core_clk);
+	if (rc) {
+		dev_err(md->dev, "failed to enable core clk\n");
+		return rc;
+	}
 	mdio_mux_iproc_config(md);
 
 	return 0;
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 909b6add61a4..9fa1c93ece7a 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -68,11 +68,12 @@ static int mdiobus_register_reset(struct mdio_device *mdiodev)
 	if (mdiodev->dev.of_node)
 		reset = of_reset_control_get_exclusive(mdiodev->dev.of_node,
 						       "phy");
-	if (PTR_ERR(reset) == -ENOENT ||
-	    PTR_ERR(reset) == -ENOTSUPP)
-		reset = NULL;
-	else if (IS_ERR(reset))
-		return PTR_ERR(reset);
+	if (IS_ERR(reset)) {
+		if (PTR_ERR(reset) == -ENOENT || PTR_ERR(reset) == -ENOTSUPP)
+			reset = NULL;
+		else
+			return PTR_ERR(reset);
+	}
 
 	mdiodev->reset_ctrl = reset;
 
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 63dedec0433d..663c68ed6ef9 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -25,6 +25,7 @@
 #include <linux/micrel_phy.h>
 #include <linux/of.h>
 #include <linux/clk.h>
+#include <linux/delay.h>
 
 /* Operation Mode Strap Override */
 #define MII_KSZPHY_OMSO				0x16
@@ -902,6 +903,12 @@ static int kszphy_resume(struct phy_device *phydev)
 
 	genphy_resume(phydev);
 
+	/* After switching from power-down to normal mode, an internal global
+	 * reset is automatically generated. Wait a minimum of 1 ms before
+	 * read/write access to the PHY registers.
+	 */
+	usleep_range(1000, 2000);
+
 	ret = kszphy_config_reset(phydev);
 	if (ret)
 		return ret;
@@ -1147,7 +1154,7 @@ static struct phy_driver ksphy_driver[] = {
 	.driver_data	= &ksz9021_type,
 	.probe		= kszphy_probe,
 	.config_init	= ksz9131_config_init,
-	.read_status	= ksz9031_read_status,
+	.read_status	= genphy_read_status,
 	.ack_interrupt	= kszphy_ack_interrupt,
 	.config_intr	= kszphy_config_intr,
 	.get_sset_count = kszphy_get_sset_count,
diff --git a/drivers/net/phy/microchip_t1.c b/drivers/net/phy/microchip_t1.c
index 3d09b471632c..fed3e395f18e 100644
--- a/drivers/net/phy/microchip_t1.c
+++ b/drivers/net/phy/microchip_t1.c
@@ -3,9 +3,21 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/delay.h>
 #include <linux/mii.h>
 #include <linux/phy.h>
 
+/* External Register Control Register */
+#define LAN87XX_EXT_REG_CTL                     (0x14)
+#define LAN87XX_EXT_REG_CTL_RD_CTL              (0x1000)
+#define LAN87XX_EXT_REG_CTL_WR_CTL              (0x0800)
+
+/* External Register Read Data Register */
+#define LAN87XX_EXT_REG_RD_DATA                 (0x15)
+
+/* External Register Write Data Register */
+#define LAN87XX_EXT_REG_WR_DATA                 (0x16)
+
 /* Interrupt Source Register */
 #define LAN87XX_INTERRUPT_SOURCE                (0x18)
 
@@ -14,9 +26,160 @@
 #define LAN87XX_MASK_LINK_UP                    (0x0004)
 #define LAN87XX_MASK_LINK_DOWN                  (0x0002)
 
+/* phyaccess nested types */
+#define	PHYACC_ATTR_MODE_READ		0
+#define	PHYACC_ATTR_MODE_WRITE		1
+#define	PHYACC_ATTR_MODE_MODIFY		2
+
+#define	PHYACC_ATTR_BANK_SMI		0
+#define	PHYACC_ATTR_BANK_MISC		1
+#define	PHYACC_ATTR_BANK_PCS		2
+#define	PHYACC_ATTR_BANK_AFE		3
+#define	PHYACC_ATTR_BANK_MAX		7
+
 #define DRIVER_AUTHOR	"Nisar Sayed <nisar.sayed@microchip.com>"
 #define DRIVER_DESC	"Microchip LAN87XX T1 PHY driver"
 
+struct access_ereg_val {
+	u8  mode;
+	u8  bank;
+	u8  offset;
+	u16 val;
+	u16 mask;
+};
+
+static int access_ereg(struct phy_device *phydev, u8 mode, u8 bank,
+		       u8 offset, u16 val)
+{
+	u16 ereg = 0;
+	int rc = 0;
+
+	if (mode > PHYACC_ATTR_MODE_WRITE || bank > PHYACC_ATTR_BANK_MAX)
+		return -EINVAL;
+
+	if (bank == PHYACC_ATTR_BANK_SMI) {
+		if (mode == PHYACC_ATTR_MODE_WRITE)
+			rc = phy_write(phydev, offset, val);
+		else
+			rc = phy_read(phydev, offset);
+		return rc;
+	}
+
+	if (mode == PHYACC_ATTR_MODE_WRITE) {
+		ereg = LAN87XX_EXT_REG_CTL_WR_CTL;
+		rc = phy_write(phydev, LAN87XX_EXT_REG_WR_DATA, val);
+		if (rc < 0)
+			return rc;
+	} else {
+		ereg = LAN87XX_EXT_REG_CTL_RD_CTL;
+	}
+
+	ereg |= (bank << 8) | offset;
+
+	rc = phy_write(phydev, LAN87XX_EXT_REG_CTL, ereg);
+	if (rc < 0)
+		return rc;
+
+	if (mode == PHYACC_ATTR_MODE_READ)
+		rc = phy_read(phydev, LAN87XX_EXT_REG_RD_DATA);
+
+	return rc;
+}
+
+static int access_ereg_modify_changed(struct phy_device *phydev,
+				      u8 bank, u8 offset, u16 val, u16 mask)
+{
+	int new = 0, rc = 0;
+
+	if (bank > PHYACC_ATTR_BANK_MAX)
+		return -EINVAL;
+
+	rc = access_ereg(phydev, PHYACC_ATTR_MODE_READ, bank, offset, val);
+	if (rc < 0)
+		return rc;
+
+	new = val | (rc & (mask ^ 0xFFFF));
+	rc = access_ereg(phydev, PHYACC_ATTR_MODE_WRITE, bank, offset, new);
+
+	return rc;
+}
+
+static int lan87xx_phy_init(struct phy_device *phydev)
+{
+	static const struct access_ereg_val init[] = {
+		/* TX Amplitude = 5 */
+		{PHYACC_ATTR_MODE_MODIFY, PHYACC_ATTR_BANK_AFE, 0x0B,
+		 0x000A, 0x001E},
+		/* Clear SMI interrupts */
+		{PHYACC_ATTR_MODE_READ, PHYACC_ATTR_BANK_SMI, 0x18,
+		 0, 0},
+		/* Clear MISC interrupts */
+		{PHYACC_ATTR_MODE_READ, PHYACC_ATTR_BANK_MISC, 0x08,
+		 0, 0},
+		/* Turn on TC10 Ring Oscillator (ROSC) */
+		{PHYACC_ATTR_MODE_MODIFY, PHYACC_ATTR_BANK_MISC, 0x20,
+		 0x0020, 0x0020},
+		/* WUR Detect Length to 1.2uS, LPC Detect Length to 1.09uS */
+		{PHYACC_ATTR_MODE_WRITE, PHYACC_ATTR_BANK_PCS, 0x20,
+		 0x283C, 0},
+		/* Wake_In Debounce Length to 39uS, Wake_Out Length to 79uS */
+		{PHYACC_ATTR_MODE_WRITE, PHYACC_ATTR_BANK_MISC, 0x21,
+		 0x274F, 0},
+		/* Enable Auto Wake Forward to Wake_Out, ROSC on, Sleep,
+		 * and Wake_In to wake PHY
+		 */
+		{PHYACC_ATTR_MODE_WRITE, PHYACC_ATTR_BANK_MISC, 0x20,
+		 0x80A7, 0},
+		/* Enable WUP Auto Fwd, Enable Wake on MDI, Wakeup Debouncer
+		 * to 128 uS
+		 */
+		{PHYACC_ATTR_MODE_WRITE, PHYACC_ATTR_BANK_MISC, 0x24,
+		 0xF110, 0},
+		/* Enable HW Init */
+		{PHYACC_ATTR_MODE_MODIFY, PHYACC_ATTR_BANK_SMI, 0x1A,
+		 0x0100, 0x0100},
+	};
+	int rc, i;
+
+	/* Start manual initialization procedures in Managed Mode */
+	rc = access_ereg_modify_changed(phydev, PHYACC_ATTR_BANK_SMI,
+					0x1a, 0x0000, 0x0100);
+	if (rc < 0)
+		return rc;
+
+	/* Soft Reset the SMI block */
+	rc = access_ereg_modify_changed(phydev, PHYACC_ATTR_BANK_SMI,
+					0x00, 0x8000, 0x8000);
+	if (rc < 0)
+		return rc;
+
+	/* Check to see if the self-clearing bit is cleared */
+	usleep_range(1000, 2000);
+	rc = access_ereg(phydev, PHYACC_ATTR_MODE_READ,
+			 PHYACC_ATTR_BANK_SMI, 0x00, 0);
+	if (rc < 0)
+		return rc;
+	if ((rc & 0x8000) != 0)
+		return -ETIMEDOUT;
+
+	/* PHY Initialization */
+	for (i = 0; i < ARRAY_SIZE(init); i++) {
+		if (init[i].mode == PHYACC_ATTR_MODE_MODIFY) {
+			rc = access_ereg_modify_changed(phydev, init[i].bank,
+							init[i].offset,
+							init[i].val,
+							init[i].mask);
+		} else {
+			rc = access_ereg(phydev, init[i].mode, init[i].bank,
+					 init[i].offset, init[i].val);
+		}
+		if (rc < 0)
+			return rc;
+	}
+
+	return 0;
+}
+
 static int lan87xx_phy_config_intr(struct phy_device *phydev)
 {
 	int rc, val = 0;
@@ -40,6 +203,13 @@ static int lan87xx_phy_ack_interrupt(struct phy_device *phydev)
 	return rc < 0 ? rc : 0;
 }
 
+static int lan87xx_config_init(struct phy_device *phydev)
+{
+	int rc = lan87xx_phy_init(phydev);
+
+	return rc < 0 ? rc : 0;
+}
+
 static struct phy_driver microchip_t1_phy_driver[] = {
 	{
 		.phy_id         = 0x0007c150,
@@ -48,7 +218,7 @@ static struct phy_driver microchip_t1_phy_driver[] = {
 
 		.features       = PHY_BASIC_T1_FEATURES,
 
-		.config_init    = genphy_config_init,
+		.config_init	= lan87xx_config_init,
 		.config_aneg    = genphy_config_aneg,
 
 		.ack_interrupt  = lan87xx_phy_ack_interrupt,
diff --git a/drivers/net/phy/mscc.c b/drivers/net/phy/mscc.c
index 645d354ffb48..8b89ac069011 100644
--- a/drivers/net/phy/mscc.c
+++ b/drivers/net/phy/mscc.c
@@ -302,11 +302,11 @@ enum rgmii_rx_clock_delay {
 				BIT(VSC8531_FORCE_LED_OFF) | \
 				BIT(VSC8531_FORCE_LED_ON))
 
-#define MSCC_VSC8584_REVB_INT8051_FW		"mscc_vsc8584_revb_int8051_fb48.bin"
+#define MSCC_VSC8584_REVB_INT8051_FW		"microchip/mscc_vsc8584_revb_int8051_fb48.bin"
 #define MSCC_VSC8584_REVB_INT8051_FW_START_ADDR	0xe800
 #define MSCC_VSC8584_REVB_INT8051_FW_CRC	0xfb48
 
-#define MSCC_VSC8574_REVB_INT8051_FW		"mscc_vsc8574_revb_int8051_29e8.bin"
+#define MSCC_VSC8574_REVB_INT8051_FW		"microchip/mscc_vsc8574_revb_int8051_29e8.bin"
 #define MSCC_VSC8574_REVB_INT8051_FW_START_ADDR	0x4000
 #define MSCC_VSC8574_REVB_INT8051_FW_CRC	0x29e8
 
diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index 7935593debb1..a1caeee12236 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -323,6 +323,8 @@ int genphy_c45_read_pma(struct phy_device *phydev)
 {
 	int val;
 
+	linkmode_zero(phydev->lp_advertising);
+
 	val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_CTRL1);
 	if (val < 0)
 		return val;
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 27ae10e317c2..8487b5f47695 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -558,9 +558,6 @@ int phy_start_aneg(struct phy_device *phydev)
 	if (AUTONEG_DISABLE == phydev->autoneg)
 		phy_sanitize_settings(phydev);
 
-	/* Invalidate LP advertising flags */
-	linkmode_zero(phydev->lp_advertising);
-
 	err = phy_config_aneg(phydev);
 	if (err < 0)
 		goto out_unlock;
@@ -1184,9 +1181,11 @@ int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data)
 		/* Restart autonegotiation so the new modes get sent to the
 		 * link partner.
 		 */
-		ret = phy_restart_aneg(phydev);
-		if (ret < 0)
-			return ret;
+		if (phydev->autoneg == AUTONEG_ENABLE) {
+			ret = phy_restart_aneg(phydev);
+			if (ret < 0)
+				return ret;
+		}
 	}
 
 	return 0;
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 9cf8284baf7e..2ea37519c56b 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -246,7 +246,7 @@ static bool mdio_bus_phy_may_suspend(struct phy_device *phydev)
 	 * MDIO bus driver and clock gated at this point.
 	 */
 	if (!netdev)
-		return !phydev->suspended;
+		goto out;
 
 	if (netdev->wol_enabled)
 		return false;
@@ -266,7 +266,8 @@ static bool mdio_bus_phy_may_suspend(struct phy_device *phydev)
 	if (device_may_wakeup(&netdev->dev))
 		return false;
 
-	return true;
+out:
+	return !phydev->suspended;
 }
 
 static int mdio_bus_phy_suspend(struct device *dev)
@@ -284,6 +285,8 @@ static int mdio_bus_phy_suspend(struct device *dev)
 	if (!mdio_bus_phy_may_suspend(phydev))
 		return 0;
 
+	phydev->suspended_by_mdio_bus = 1;
+
 	return phy_suspend(phydev);
 }
 
@@ -292,9 +295,11 @@ static int mdio_bus_phy_resume(struct device *dev)
 	struct phy_device *phydev = to_phy_device(dev);
 	int ret;
 
-	if (!mdio_bus_phy_may_suspend(phydev))
+	if (!phydev->suspended_by_mdio_bus)
 		goto no_resume;
 
+	phydev->suspended_by_mdio_bus = 0;
+
 	ret = phy_resume(phydev);
 	if (ret < 0)
 		return ret;
@@ -610,7 +615,9 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id,
 	if (c45_ids)
 		dev->c45_ids = *c45_ids;
 	dev->irq = bus->irq[addr];
+
 	dev_set_name(&mdiodev->dev, PHY_ID_FMT, bus->id, addr);
+	device_initialize(&mdiodev->dev);
 
 	dev->state = PHY_DOWN;
 
@@ -644,10 +651,8 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id,
 		ret = phy_request_driver_module(dev, phy_id);
 	}
 
-	if (!ret) {
-		device_initialize(&mdiodev->dev);
-	} else {
-		kfree(dev);
+	if (ret) {
+		put_device(&mdiodev->dev);
 		dev = ERR_PTR(ret);
 	}
 
@@ -792,8 +797,10 @@ static int get_phy_id(struct mii_bus *bus, int addr, u32 *phy_id,
 
 	/* Grab the bits from PHYIR2, and put them in the lower half */
 	phy_reg = mdiobus_read(bus, addr, MII_PHYSID2);
-	if (phy_reg < 0)
-		return -EIO;
+	if (phy_reg < 0) {
+		/* returning -ENODEV doesn't stop bus scanning */
+		return (phy_reg == -EIO || phy_reg == -ENODEV) ? -ENODEV : -EIO;
+	}
 
 	*phy_id |= phy_reg;
 
@@ -1782,7 +1789,14 @@ int genphy_read_status(struct phy_device *phydev)
 
 	linkmode_zero(phydev->lp_advertising);
 
-	if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete) {
+	if (phydev->autoneg == AUTONEG_ENABLE) {
+		if (!phydev->autoneg_complete) {
+			mii_stat1000_mod_linkmode_lpa_t(phydev->lp_advertising,
+							0);
+			mii_lpa_mod_linkmode_lpa_t(phydev->lp_advertising, 0);
+			return 0;
+		}
+
 		if (phydev->is_gigabit_capable) {
 			lpagb = phy_read(phydev, MII_STAT1000);
 			if (lpagb < 0)
diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index a669945eb829..1f11d21391bd 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -270,6 +270,15 @@ static struct phy_driver realtek_drvs[] = {
 		.read_page	= rtl821x_read_page,
 		.write_page	= rtl821x_write_page,
 	}, {
+		PHY_ID_MATCH_MODEL(0x001cc880),
+		.name		= "RTL8208 Fast Ethernet",
+		.read_mmd	= genphy_read_mmd_unsupported,
+		.write_mmd	= genphy_write_mmd_unsupported,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+		.read_page	= rtl821x_read_page,
+		.write_page	= rtl821x_write_page,
+	}, {
 		PHY_ID_MATCH_EXACT(0x001cc910),
 		.name		= "RTL8211 Gigabit Ethernet",
 		.config_aneg	= rtl8211_config_aneg,
diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c
index e9c187946cca..f64e9fcd5c4b 100644
--- a/drivers/net/phy/sfp-bus.c
+++ b/drivers/net/phy/sfp-bus.c
@@ -9,6 +9,12 @@
 
 #include "sfp.h"
 
+struct sfp_quirk {
+	const char *vendor;
+	const char *part;
+	void (*modes)(const struct sfp_eeprom_id *id, unsigned long *modes);
+};
+
 /**
  * struct sfp_bus - internal representation of a sfp bus
  */
@@ -21,6 +27,7 @@ struct sfp_bus {
 	const struct sfp_socket_ops *socket_ops;
 	struct device *sfp_dev;
 	struct sfp *sfp;
+	const struct sfp_quirk *sfp_quirk;
 
 	const struct sfp_upstream_ops *upstream_ops;
 	void *upstream;
@@ -31,6 +38,71 @@ struct sfp_bus {
 	bool started;
 };
 
+static void sfp_quirk_2500basex(const struct sfp_eeprom_id *id,
+				unsigned long *modes)
+{
+	phylink_set(modes, 2500baseX_Full);
+}
+
+static const struct sfp_quirk sfp_quirks[] = {
+	{
+		// Alcatel Lucent G-010S-P can operate at 2500base-X, but
+		// incorrectly report 2500MBd NRZ in their EEPROM
+		.vendor = "ALCATELLUCENT",
+		.part = "G010SP",
+		.modes = sfp_quirk_2500basex,
+	}, {
+		// Alcatel Lucent G-010S-A can operate at 2500base-X, but
+		// report 3.2GBd NRZ in their EEPROM
+		.vendor = "ALCATELLUCENT",
+		.part = "3FE46541AA",
+		.modes = sfp_quirk_2500basex,
+	}, {
+		// Huawei MA5671A can operate at 2500base-X, but report 1.2GBd
+		// NRZ in their EEPROM
+		.vendor = "HUAWEI",
+		.part = "MA5671A",
+		.modes = sfp_quirk_2500basex,
+	},
+};
+
+static size_t sfp_strlen(const char *str, size_t maxlen)
+{
+	size_t size, i;
+
+	/* Trailing characters should be filled with space chars */
+	for (i = 0, size = 0; i < maxlen; i++)
+		if (str[i] != ' ')
+			size = i + 1;
+
+	return size;
+}
+
+static bool sfp_match(const char *qs, const char *str, size_t len)
+{
+	if (!qs)
+		return true;
+	if (strlen(qs) != len)
+		return false;
+	return !strncmp(qs, str, len);
+}
+
+static const struct sfp_quirk *sfp_lookup_quirk(const struct sfp_eeprom_id *id)
+{
+	const struct sfp_quirk *q;
+	unsigned int i;
+	size_t vs, ps;
+
+	vs = sfp_strlen(id->base.vendor_name, ARRAY_SIZE(id->base.vendor_name));
+	ps = sfp_strlen(id->base.vendor_pn, ARRAY_SIZE(id->base.vendor_pn));
+
+	for (i = 0, q = sfp_quirks; i < ARRAY_SIZE(sfp_quirks); i++, q++)
+		if (sfp_match(q->vendor, id->base.vendor_name, vs) &&
+		    sfp_match(q->part, id->base.vendor_pn, ps))
+			return q;
+
+	return NULL;
+}
 /**
  * sfp_parse_port() - Parse the EEPROM base ID, setting the port type
  * @bus: a pointer to the &struct sfp_bus structure for the sfp module
@@ -234,6 +306,9 @@ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id,
 			phylink_set(modes, 1000baseX_Full);
 	}
 
+	if (bus->sfp_quirk)
+		bus->sfp_quirk->modes(id, modes);
+
 	bitmap_or(support, support, modes, __ETHTOOL_LINK_MODE_MASK_NBITS);
 
 	phylink_set(support, Autoneg);
@@ -557,6 +632,8 @@ int sfp_module_insert(struct sfp_bus *bus, const struct sfp_eeprom_id *id)
 	const struct sfp_upstream_ops *ops = sfp_get_upstream_ops(bus);
 	int ret = 0;
 
+	bus->sfp_quirk = sfp_lookup_quirk(id);
+
 	if (ops && ops->module_insert)
 		ret = ops->module_insert(bus->upstream, id);
 
@@ -570,6 +647,8 @@ void sfp_module_remove(struct sfp_bus *bus)
 
 	if (ops && ops->module_remove)
 		ops->module_remove(bus->upstream);
+
+	bus->sfp_quirk = NULL;
 }
 EXPORT_SYMBOL_GPL(sfp_module_remove);
 
diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c
index a7b9cf3269bf..29a0917a81e6 100644
--- a/drivers/net/ppp/ppp_async.c
+++ b/drivers/net/ppp/ppp_async.c
@@ -874,15 +874,15 @@ ppp_async_input(struct asyncppp *ap, const unsigned char *buf,
 				skb = dev_alloc_skb(ap->mru + PPP_HDRLEN + 2);
 				if (!skb)
 					goto nomem;
- 				ap->rpkt = skb;
- 			}
- 			if (skb->len == 0) {
- 				/* Try to get the payload 4-byte aligned.
- 				 * This should match the
- 				 * PPP_ALLSTATIONS/PPP_UI/compressed tests in
- 				 * process_input_packet, but we do not have
- 				 * enough chars here to test buf[1] and buf[2].
- 				 */
+				ap->rpkt = skb;
+			}
+			if (skb->len == 0) {
+				/* Try to get the payload 4-byte aligned.
+				 * This should match the
+				 * PPP_ALLSTATIONS/PPP_UI/compressed tests in
+				 * process_input_packet, but we do not have
+				 * enough chars here to test buf[1] and buf[2].
+				 */
 				if (buf[0] != PPP_ALLSTATIONS)
 					skb_reserve(skb, 2 + (buf[0] & 1));
 			}
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index a44dd3c8af63..087b01684135 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -492,6 +492,9 @@ static int pppoe_disc_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (!skb)
 		goto out;
 
+	if (skb->pkt_type != PACKET_HOST)
+		goto abort;
+
 	if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr)))
 		goto abort;
 
diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c
index ea90db3c7705..01334aeac577 100644
--- a/drivers/net/slip/slhc.c
+++ b/drivers/net/slip/slhc.c
@@ -232,7 +232,7 @@ slhc_compress(struct slcompress *comp, unsigned char *icp, int isize,
 	register struct cstate *cs = lcs->next;
 	register unsigned long deltaS, deltaA;
 	register short changes = 0;
-	int hlen;
+	int nlen, hlen;
 	unsigned char new_seq[16];
 	register unsigned char *cp = new_seq;
 	struct iphdr *ip;
@@ -248,6 +248,8 @@ slhc_compress(struct slcompress *comp, unsigned char *icp, int isize,
 		return isize;
 
 	ip = (struct iphdr *) icp;
+	if (ip->version != 4 || ip->ihl < 5)
+		return isize;
 
 	/* Bail if this packet isn't TCP, or is an IP fragment */
 	if (ip->protocol != IPPROTO_TCP || (ntohs(ip->frag_off) & 0x3fff)) {
@@ -258,10 +260,14 @@ slhc_compress(struct slcompress *comp, unsigned char *icp, int isize,
 			comp->sls_o_tcp++;
 		return isize;
 	}
-	/* Extract TCP header */
+	nlen = ip->ihl * 4;
+	if (isize < nlen + sizeof(*th))
+		return isize;
 
-	th = (struct tcphdr *)(((unsigned char *)ip) + ip->ihl*4);
-	hlen = ip->ihl*4 + th->doff*4;
+	th = (struct tcphdr *)(icp + nlen);
+	if (th->doff < sizeof(struct tcphdr) / 4)
+		return isize;
+	hlen = nlen + th->doff * 4;
 
 	/*  Bail if the TCP packet isn't `compressible' (i.e., ACK isn't set or
 	 *  some other control bit is set). Also uncompressible if
diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c
index 2a91c192659f..8e56a41dd758 100644
--- a/drivers/net/slip/slip.c
+++ b/drivers/net/slip/slip.c
@@ -452,9 +452,16 @@ static void slip_transmit(struct work_struct *work)
  */
 static void slip_write_wakeup(struct tty_struct *tty)
 {
-	struct slip *sl = tty->disc_data;
+	struct slip *sl;
+
+	rcu_read_lock();
+	sl = rcu_dereference(tty->disc_data);
+	if (!sl)
+		goto out;
 
 	schedule_work(&sl->tx_work);
+out:
+	rcu_read_unlock();
 }
 
 static void sl_tx_timeout(struct net_device *dev)
@@ -856,7 +863,10 @@ err_free_chan:
 	tty->disc_data = NULL;
 	clear_bit(SLF_INUSE, &sl->flags);
 	sl_free_netdev(sl->dev);
+	/* do not call free_netdev before rtnl_unlock */
+	rtnl_unlock();
 	free_netdev(sl->dev);
+	return err;
 
 err_exit:
 	rtnl_unlock();
@@ -882,10 +892,11 @@ static void slip_close(struct tty_struct *tty)
 		return;
 
 	spin_lock_bh(&sl->lock);
-	tty->disc_data = NULL;
+	rcu_assign_pointer(tty->disc_data, NULL);
 	sl->tty = NULL;
 	spin_unlock_bh(&sl->lock);
 
+	synchronize_rcu();
 	flush_work(&sl->tx_work);
 
 	/* VSV = very important to remove timers */
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index d1b4c7d8e2bc..491ab83a1872 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -468,6 +468,9 @@ static const struct team_mode *team_mode_get(const char *kind)
 	struct team_mode_item *mitem;
 	const struct team_mode *mode = NULL;
 
+	if (!try_module_get(THIS_MODULE))
+		return NULL;
+
 	spin_lock(&mode_list_lock);
 	mitem = __find_mode(kind);
 	if (!mitem) {
@@ -483,6 +486,7 @@ static const struct team_mode *team_mode_get(const char *kind)
 	}
 
 	spin_unlock(&mode_list_lock);
+	module_put(THIS_MODULE);
 	return mode;
 }
 
@@ -2204,6 +2208,8 @@ team_nl_option_policy[TEAM_ATTR_OPTION_MAX + 1] = {
 	[TEAM_ATTR_OPTION_CHANGED]		= { .type = NLA_FLAG },
 	[TEAM_ATTR_OPTION_TYPE]			= { .type = NLA_U8 },
 	[TEAM_ATTR_OPTION_DATA]			= { .type = NLA_BINARY },
+	[TEAM_ATTR_OPTION_PORT_IFINDEX]		= { .type = NLA_U32 },
+	[TEAM_ATTR_OPTION_ARRAY_INDEX]		= { .type = NLA_U32 },
 };
 
 static int team_nl_cmd_noop(struct sk_buff *skb, struct genl_info *info)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 34b0e1416525..ed20985cb7dd 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1716,8 +1716,12 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 			alloc_frag->offset += buflen;
 		}
 		err = tun_xdp_act(tun, xdp_prog, &xdp, act);
-		if (err < 0)
-			goto err_xdp;
+		if (err < 0) {
+			if (act == XDP_REDIRECT || act == XDP_TX)
+				put_page(alloc_frag->page);
+			goto out;
+		}
+
 		if (err == XDP_REDIRECT)
 			xdp_do_flush_map();
 		if (err != XDP_PASS)
@@ -1731,8 +1735,6 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 
 	return __tun_build_skb(tfile, alloc_frag, buf, buflen, len, pad);
 
-err_xdp:
-	put_page(alloc_frag->page);
 out:
 	rcu_read_unlock();
 	local_bh_enable();
@@ -1907,8 +1909,11 @@ drop:
 		skb->dev = tun->dev;
 		break;
 	case IFF_TAP:
-		if (!frags)
-			skb->protocol = eth_type_trans(skb, tun->dev);
+		if (frags && !pskb_may_pull(skb, ETH_HLEN)) {
+			err = -ENOMEM;
+			goto drop;
+		}
+		skb->protocol = eth_type_trans(skb, tun->dev);
 		break;
 	}
 
@@ -1924,6 +1929,7 @@ drop:
 
 	skb_reset_network_header(skb);
 	skb_probe_transport_header(skb);
+	skb_record_rx_queue(skb, tfile->queue_index);
 
 	if (skb_xdp) {
 		struct bpf_prog *xdp_prog;
@@ -1937,6 +1943,10 @@ drop:
 			if (ret != XDP_PASS) {
 				rcu_read_unlock();
 				local_bh_enable();
+				if (frags) {
+					tfile->napi.skb = NULL;
+					mutex_unlock(&tfile->napi_mutex);
+				}
 				return total_len;
 			}
 		}
@@ -1960,9 +1970,12 @@ drop:
 	}
 
 	if (frags) {
+		u32 headlen;
+
 		/* Exercise flow dissector code path. */
-		u32 headlen = eth_get_headlen(tun->dev, skb->data,
-					      skb_headlen(skb));
+		skb_push(skb, ETH_HLEN);
+		headlen = eth_get_headlen(tun->dev, skb->data,
+					  skb_headlen(skb));
 
 		if (unlikely(headlen > skb_headlen(skb))) {
 			this_cpu_inc(tun->pcpu_stats->rx_dropped);
@@ -2487,6 +2500,7 @@ build:
 	skb->protocol = eth_type_trans(skb, tun->dev);
 	skb_reset_network_header(skb);
 	skb_probe_transport_header(skb);
+	skb_record_rx_queue(skb, tfile->queue_index);
 
 	if (skb_xdp) {
 		err = do_xdp_generic(xdp_prog, skb);
@@ -2498,7 +2512,6 @@ build:
 	    !tfile->detached)
 		rxhash = __skb_get_hash_symmetric(skb);
 
-	skb_record_rx_queue(skb, tfile->queue_index);
 	netif_receive_skb(skb);
 
 	/* No need for get_cpu_ptr() here since this function is
diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c
index af3994e0853b..6101d82102e7 100644
--- a/drivers/net/usb/ax88172a.c
+++ b/drivers/net/usb/ax88172a.c
@@ -198,6 +198,7 @@ static int ax88172a_bind(struct usbnet *dev, struct usb_interface *intf)
 	ret = asix_read_cmd(dev, AX_CMD_READ_NODE_ID, 0, 0, ETH_ALEN, buf, 0);
 	if (ret < ETH_ALEN) {
 		netdev_err(dev->net, "Failed to read MAC address: %d\n", ret);
+		ret = -EIO;
 		goto free;
 	}
 	memcpy(dev->net->dev_addr, buf, ETH_ALEN);
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index 0bc457ba8574..23c461cd506d 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -1388,10 +1388,10 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 		}
 
 		if (pkt_cnt == 0) {
-			/* Skip IP alignment psudo header */
-			skb_pull(skb, 2);
 			skb->len = pkt_len;
-			skb_set_tail_pointer(skb, pkt_len);
+			/* Skip IP alignment pseudo header */
+			skb_pull(skb, 2);
+			skb_set_tail_pointer(skb, skb->len);
 			skb->truesize = pkt_len + sizeof(struct sk_buff);
 			ax88179_rx_checksum(skb, pkt_hdr);
 			return 1;
@@ -1400,8 +1400,9 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 		ax_skb = skb_clone(skb, GFP_ATOMIC);
 		if (ax_skb) {
 			ax_skb->len = pkt_len;
-			ax_skb->data = skb->data + 2;
-			skb_set_tail_pointer(ax_skb, pkt_len);
+			/* Skip IP alignment pseudo header */
+			skb_pull(ax_skb, 2);
+			skb_set_tail_pointer(ax_skb, ax_skb->len);
 			ax_skb->truesize = pkt_len + sizeof(struct sk_buff);
 			ax88179_rx_checksum(ax_skb, pkt_hdr);
 			usbnet_skb_return(dev, ax_skb);
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index fe630438f67b..9bb37ac99a10 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -808,14 +808,21 @@ static const struct usb_device_id	products[] = {
 	.driver_info = 0,
 },
 
-/* Microsoft Surface 3 dock (based on Realtek RTL8153) */
+/* Microsoft Surface Ethernet Adapter (based on Realtek RTL8153) */
 {
 	USB_DEVICE_AND_INTERFACE_INFO(MICROSOFT_VENDOR_ID, 0x07c6, USB_CLASS_COMM,
 			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
 	.driver_info = 0,
 },
 
-	/* TP-LINK UE300 USB 3.0 Ethernet Adapters (based on Realtek RTL8153) */
+/* Microsoft Surface Ethernet Adapter (based on Realtek RTL8153B) */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(MICROSOFT_VENDOR_ID, 0x0927, USB_CLASS_COMM,
+			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+
+/* TP-LINK UE300 USB 3.0 Ethernet Adapters (based on Realtek RTL8153) */
 {
 	USB_DEVICE_AND_INTERFACE_INFO(TPLINK_VENDOR_ID, 0x0601, USB_CLASS_COMM,
 			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index a505b2ab88b8..cab6ae76156b 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -1389,8 +1389,9 @@ static void hso_serial_set_termios(struct tty_struct *tty, struct ktermios *old)
 	unsigned long flags;
 
 	if (old)
-		hso_dbg(0x16, "Termios called with: cflags new[%d] - old[%d]\n",
-			tty->termios.c_cflag, old->c_cflag);
+		hso_dbg(0x16, "Termios called with: cflags new[%u] - old[%u]\n",
+			(unsigned int)tty->termios.c_cflag,
+			(unsigned int)old->c_cflag);
 
 	/* the actual setup */
 	spin_lock_irqsave(&serial->serial_lock, flags);
@@ -2259,12 +2260,14 @@ static int hso_serial_common_create(struct hso_serial *serial, int num_urbs,
 
 	minor = get_free_serial_index();
 	if (minor < 0)
-		goto exit;
+		goto exit2;
 
 	/* register our minor number */
 	serial->parent->dev = tty_port_register_device_attr(&serial->port,
 			tty_drv, minor, &serial->parent->interface->dev,
 			serial->parent, hso_serial_dev_groups);
+	if (IS_ERR(serial->parent->dev))
+		goto exit2;
 
 	/* fill in specific data for later use */
 	serial->minor = minor;
@@ -2309,6 +2312,7 @@ static int hso_serial_common_create(struct hso_serial *serial, int num_urbs,
 	return 0;
 exit:
 	hso_serial_tty_unregister(serial);
+exit2:
 	hso_serial_common_free(serial);
 	return -1;
 }
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 5195747d7135..c78cd0f5b922 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -20,6 +20,7 @@
 #include <linux/mdio.h>
 #include <linux/phy.h>
 #include <net/ip6_checksum.h>
+#include <net/vxlan.h>
 #include <linux/interrupt.h>
 #include <linux/irqdomain.h>
 #include <linux/irq.h>
@@ -376,10 +377,6 @@ struct lan78xx_net {
 	struct tasklet_struct	bh;
 	struct delayed_work	wq;
 
-	struct usb_host_endpoint *ep_blkin;
-	struct usb_host_endpoint *ep_blkout;
-	struct usb_host_endpoint *ep_intr;
-
 	int			msg_enable;
 
 	struct urb		*urb_intr;
@@ -511,7 +508,7 @@ static int lan78xx_read_stats(struct lan78xx_net *dev,
 		}
 	} else {
 		netdev_warn(dev->net,
-			    "Failed to read stat ret = 0x%x", ret);
+			    "Failed to read stat ret = %d", ret);
 	}
 
 	kfree(stats);
@@ -2725,11 +2722,6 @@ static int lan78xx_stop(struct net_device *net)
 	return 0;
 }
 
-static int lan78xx_linearize(struct sk_buff *skb)
-{
-	return skb_linearize(skb);
-}
-
 static struct sk_buff *lan78xx_tx_prep(struct lan78xx_net *dev,
 				       struct sk_buff *skb, gfp_t flags)
 {
@@ -2740,8 +2732,10 @@ static struct sk_buff *lan78xx_tx_prep(struct lan78xx_net *dev,
 		return NULL;
 	}
 
-	if (lan78xx_linearize(skb) < 0)
+	if (skb_linearize(skb)) {
+		dev_kfree_skb_any(skb);
 		return NULL;
+	}
 
 	tx_cmd_a = (u32)(skb->len & TX_CMD_A_LEN_MASK_) | TX_CMD_A_FCS_;
 
@@ -2874,78 +2868,12 @@ lan78xx_start_xmit(struct sk_buff *skb, struct net_device *net)
 	return NETDEV_TX_OK;
 }
 
-static int
-lan78xx_get_endpoints(struct lan78xx_net *dev, struct usb_interface *intf)
-{
-	int tmp;
-	struct usb_host_interface *alt = NULL;
-	struct usb_host_endpoint *in = NULL, *out = NULL;
-	struct usb_host_endpoint *status = NULL;
-
-	for (tmp = 0; tmp < intf->num_altsetting; tmp++) {
-		unsigned ep;
-
-		in = NULL;
-		out = NULL;
-		status = NULL;
-		alt = intf->altsetting + tmp;
-
-		for (ep = 0; ep < alt->desc.bNumEndpoints; ep++) {
-			struct usb_host_endpoint *e;
-			int intr = 0;
-
-			e = alt->endpoint + ep;
-			switch (e->desc.bmAttributes) {
-			case USB_ENDPOINT_XFER_INT:
-				if (!usb_endpoint_dir_in(&e->desc))
-					continue;
-				intr = 1;
-				/* FALLTHROUGH */
-			case USB_ENDPOINT_XFER_BULK:
-				break;
-			default:
-				continue;
-			}
-			if (usb_endpoint_dir_in(&e->desc)) {
-				if (!intr && !in)
-					in = e;
-				else if (intr && !status)
-					status = e;
-			} else {
-				if (!out)
-					out = e;
-			}
-		}
-		if (in && out)
-			break;
-	}
-	if (!alt || !in || !out)
-		return -EINVAL;
-
-	dev->pipe_in = usb_rcvbulkpipe(dev->udev,
-				       in->desc.bEndpointAddress &
-				       USB_ENDPOINT_NUMBER_MASK);
-	dev->pipe_out = usb_sndbulkpipe(dev->udev,
-					out->desc.bEndpointAddress &
-					USB_ENDPOINT_NUMBER_MASK);
-	dev->ep_intr = status;
-
-	return 0;
-}
-
 static int lan78xx_bind(struct lan78xx_net *dev, struct usb_interface *intf)
 {
 	struct lan78xx_priv *pdata = NULL;
 	int ret;
 	int i;
 
-	ret = lan78xx_get_endpoints(dev, intf);
-	if (ret) {
-		netdev_warn(dev->net, "lan78xx_get_endpoints failed: %d\n",
-			    ret);
-		return ret;
-	}
-
 	dev->data[0] = (unsigned long)kzalloc(sizeof(*pdata), GFP_KERNEL);
 
 	pdata = (struct lan78xx_priv *)(dev->data[0]);
@@ -3678,6 +3606,19 @@ static void lan78xx_tx_timeout(struct net_device *net)
 	tasklet_schedule(&dev->bh);
 }
 
+static netdev_features_t lan78xx_features_check(struct sk_buff *skb,
+						struct net_device *netdev,
+						netdev_features_t features)
+{
+	if (skb->len + TX_OVERHEAD > MAX_SINGLE_PACKET_SIZE)
+		features &= ~NETIF_F_GSO_MASK;
+
+	features = vlan_features_check(skb, features);
+	features = vxlan_features_check(skb, features);
+
+	return features;
+}
+
 static const struct net_device_ops lan78xx_netdev_ops = {
 	.ndo_open		= lan78xx_open,
 	.ndo_stop		= lan78xx_stop,
@@ -3691,6 +3632,7 @@ static const struct net_device_ops lan78xx_netdev_ops = {
 	.ndo_set_features	= lan78xx_set_features,
 	.ndo_vlan_rx_add_vid	= lan78xx_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= lan78xx_vlan_rx_kill_vid,
+	.ndo_features_check	= lan78xx_features_check,
 };
 
 static void lan78xx_stat_monitor(struct timer_list *t)
@@ -3703,6 +3645,7 @@ static void lan78xx_stat_monitor(struct timer_list *t)
 static int lan78xx_probe(struct usb_interface *intf,
 			 const struct usb_device_id *id)
 {
+	struct usb_host_endpoint *ep_blkin, *ep_blkout, *ep_intr;
 	struct lan78xx_net *dev;
 	struct net_device *netdev;
 	struct usb_device *udev;
@@ -3751,6 +3694,34 @@ static int lan78xx_probe(struct usb_interface *intf,
 
 	mutex_init(&dev->stats.access_lock);
 
+	if (intf->cur_altsetting->desc.bNumEndpoints < 3) {
+		ret = -ENODEV;
+		goto out2;
+	}
+
+	dev->pipe_in = usb_rcvbulkpipe(udev, BULK_IN_PIPE);
+	ep_blkin = usb_pipe_endpoint(udev, dev->pipe_in);
+	if (!ep_blkin || !usb_endpoint_is_bulk_in(&ep_blkin->desc)) {
+		ret = -ENODEV;
+		goto out2;
+	}
+
+	dev->pipe_out = usb_sndbulkpipe(udev, BULK_OUT_PIPE);
+	ep_blkout = usb_pipe_endpoint(udev, dev->pipe_out);
+	if (!ep_blkout || !usb_endpoint_is_bulk_out(&ep_blkout->desc)) {
+		ret = -ENODEV;
+		goto out2;
+	}
+
+	ep_intr = &intf->cur_altsetting->endpoint[2];
+	if (!usb_endpoint_is_int_in(&ep_intr->desc)) {
+		ret = -ENODEV;
+		goto out2;
+	}
+
+	dev->pipe_intr = usb_rcvintpipe(dev->udev,
+					usb_endpoint_num(&ep_intr->desc));
+
 	ret = lan78xx_bind(dev, intf);
 	if (ret < 0)
 		goto out2;
@@ -3760,19 +3731,9 @@ static int lan78xx_probe(struct usb_interface *intf,
 
 	/* MTU range: 68 - 9000 */
 	netdev->max_mtu = MAX_SINGLE_PACKET_SIZE;
+	netif_set_gso_max_size(netdev, MAX_SINGLE_PACKET_SIZE - MAX_HEADER);
 
-	dev->ep_blkin = (intf->cur_altsetting)->endpoint + 0;
-	dev->ep_blkout = (intf->cur_altsetting)->endpoint + 1;
-	dev->ep_intr = (intf->cur_altsetting)->endpoint + 2;
-
-	dev->pipe_in = usb_rcvbulkpipe(udev, BULK_IN_PIPE);
-	dev->pipe_out = usb_sndbulkpipe(udev, BULK_OUT_PIPE);
-
-	dev->pipe_intr = usb_rcvintpipe(dev->udev,
-					dev->ep_intr->desc.bEndpointAddress &
-					USB_ENDPOINT_NUMBER_MASK);
-	period = dev->ep_intr->desc.bInterval;
-
+	period = ep_intr->desc.bInterval;
 	maxp = usb_maxpacket(dev->udev, dev->pipe_intr, 0);
 	buf = kmalloc(maxp, GFP_KERNEL);
 	if (buf) {
@@ -3785,6 +3746,7 @@ static int lan78xx_probe(struct usb_interface *intf,
 			usb_fill_int_urb(dev->urb_intr, dev->udev,
 					 dev->pipe_intr, buf, maxp,
 					 intr_complete, dev, period);
+			dev->urb_intr->transfer_flags |= URB_FREE_BUFFER;
 		}
 	}
 
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 8ae07284113d..9348a2fa60e4 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -61,7 +61,6 @@ enum qmi_wwan_flags {
 
 enum qmi_wwan_quirks {
 	QMI_WWAN_QUIRK_DTR = 1 << 0,	/* needs "set DTR" request */
-	QMI_WWAN_QUIRK_QUECTEL_DYNCFG = 1 << 1,	/* check num. endpoints */
 };
 
 struct qmimux_hdr {
@@ -338,6 +337,9 @@ static void qmi_wwan_netdev_setup(struct net_device *net)
 		netdev_dbg(net, "mode: raw IP\n");
 	} else if (!net->header_ops) { /* don't bother if already set */
 		ether_setup(net);
+		/* Restoring min/max mtu values set originally by usbnet */
+		net->min_mtu = 0;
+		net->max_mtu = ETH_MAX_MTU;
 		clear_bit(EVENT_NO_IP_ALIGN, &dev->flags);
 		netdev_dbg(net, "mode: Ethernet\n");
 	}
@@ -916,16 +918,6 @@ static const struct driver_info	qmi_wwan_info_quirk_dtr = {
 	.data           = QMI_WWAN_QUIRK_DTR,
 };
 
-static const struct driver_info	qmi_wwan_info_quirk_quectel_dyncfg = {
-	.description	= "WWAN/QMI device",
-	.flags		= FLAG_WWAN | FLAG_SEND_ZLP,
-	.bind		= qmi_wwan_bind,
-	.unbind		= qmi_wwan_unbind,
-	.manage_power	= qmi_wwan_manage_power,
-	.rx_fixup       = qmi_wwan_rx_fixup,
-	.data           = QMI_WWAN_QUIRK_DTR | QMI_WWAN_QUIRK_QUECTEL_DYNCFG,
-};
-
 #define HUAWEI_VENDOR_ID	0x12D1
 
 /* map QMI/wwan function by a fixed interface number */
@@ -946,14 +938,18 @@ static const struct driver_info	qmi_wwan_info_quirk_quectel_dyncfg = {
 #define QMI_GOBI_DEVICE(vend, prod) \
 	QMI_FIXED_INTF(vend, prod, 0)
 
-/* Quectel does not use fixed interface numbers on at least some of their
- * devices. We need to check the number of endpoints to ensure that we bind to
- * the correct interface.
+/* Many devices have QMI and DIAG functions which are distinguishable
+ * from other vendor specific functions by class, subclass and
+ * protocol all being 0xff. The DIAG function has exactly 2 endpoints
+ * and is silently rejected when probed.
+ *
+ * This makes it possible to match dynamically numbered QMI functions
+ * as seen on e.g. many Quectel modems.
  */
-#define QMI_QUIRK_QUECTEL_DYNCFG(vend, prod) \
+#define QMI_MATCH_FF_FF_FF(vend, prod) \
 	USB_DEVICE_AND_INTERFACE_INFO(vend, prod, USB_CLASS_VENDOR_SPEC, \
 				      USB_SUBCLASS_VENDOR_SPEC, 0xff), \
-	.driver_info = (unsigned long)&qmi_wwan_info_quirk_quectel_dyncfg
+	.driver_info = (unsigned long)&qmi_wwan_info_quirk_dtr
 
 static const struct usb_device_id products[] = {
 	/* 1. CDC ECM like devices match on the control interface */
@@ -1059,9 +1055,10 @@ static const struct usb_device_id products[] = {
 		USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x581d, USB_CLASS_VENDOR_SPEC, 1, 7),
 		.driver_info = (unsigned long)&qmi_wwan_info,
 	},
-	{QMI_QUIRK_QUECTEL_DYNCFG(0x2c7c, 0x0125)},	/* Quectel EC25, EC20 R2.0  Mini PCIe */
-	{QMI_QUIRK_QUECTEL_DYNCFG(0x2c7c, 0x0306)},	/* Quectel EP06/EG06/EM06 */
-	{QMI_QUIRK_QUECTEL_DYNCFG(0x2c7c, 0x0512)},	/* Quectel EG12/EM12 */
+	{QMI_MATCH_FF_FF_FF(0x2c7c, 0x0125)},	/* Quectel EC25, EC20 R2.0  Mini PCIe */
+	{QMI_MATCH_FF_FF_FF(0x2c7c, 0x0306)},	/* Quectel EP06/EG06/EM06 */
+	{QMI_MATCH_FF_FF_FF(0x2c7c, 0x0512)},	/* Quectel EG12/EM12 */
+	{QMI_MATCH_FF_FF_FF(0x2c7c, 0x0800)},	/* Quectel RM500Q-GL */
 
 	/* 3. Combined interface devices matching on interface number */
 	{QMI_FIXED_INTF(0x0408, 0xea42, 4)},	/* Yota / Megafon M100-1 */
@@ -1213,6 +1210,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1435, 0xd182, 5)},	/* Wistron NeWeb D18 */
 	{QMI_FIXED_INTF(0x1435, 0xd191, 4)},	/* Wistron NeWeb D19Q1 */
 	{QMI_QUIRK_SET_DTR(0x1508, 0x1001, 4)},	/* Fibocom NL668 series */
+	{QMI_FIXED_INTF(0x1690, 0x7588, 4)},    /* ASKEY WWHC050 */
 	{QMI_FIXED_INTF(0x16d8, 0x6003, 0)},	/* CMOTech 6003 */
 	{QMI_FIXED_INTF(0x16d8, 0x6007, 0)},	/* CMOTech CHE-628S */
 	{QMI_FIXED_INTF(0x16d8, 0x6008, 0)},	/* CMOTech CMU-301 */
@@ -1325,7 +1323,9 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)},	/* Alcatel L800MA */
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
 	{QMI_FIXED_INTF(0x2357, 0x9000, 4)},	/* TP-LINK MA260 */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1031, 3)}, /* Telit LE910C1-EUX */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)},	/* Telit LE922A */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1050, 2)},	/* Telit FN980 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1100, 3)},	/* Telit ME910 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1101, 3)},	/* Telit ME910 dual modem */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */
@@ -1359,7 +1359,9 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x413c, 0x81b3, 8)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 8)},	/* Dell Wireless 5811e */
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 10)},	/* Dell Wireless 5811e */
+	{QMI_FIXED_INTF(0x413c, 0x81cc, 8)},	/* Dell Wireless 5816e */
 	{QMI_FIXED_INTF(0x413c, 0x81d7, 0)},	/* Dell Wireless 5821e */
+	{QMI_FIXED_INTF(0x413c, 0x81d7, 1)},	/* Dell Wireless 5821e preproduction config */
 	{QMI_FIXED_INTF(0x413c, 0x81e0, 0)},	/* Dell Wireless 5821e with eSIM support*/
 	{QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)},	/* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */
 	{QMI_FIXED_INTF(0x03f0, 0x9d1d, 1)},	/* HP lt4120 Snapdragon X5 LTE */
@@ -1367,6 +1369,7 @@ static const struct usb_device_id products[] = {
 	{QMI_QUIRK_SET_DTR(0x1e0e, 0x9001, 5)},	/* SIMCom 7100E, 7230E, 7600E ++ */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)},	/* Quectel EC21 Mini PCIe */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)},	/* Quectel EG91 */
+	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0195, 4)},	/* Quectel EG95 */
 	{QMI_FIXED_INTF(0x2c7c, 0x0296, 4)},	/* Quectel BG96 */
 	{QMI_QUIRK_SET_DTR(0x2cb7, 0x0104, 4)},	/* Fibocom NL678 series */
 	{QMI_FIXED_INTF(0x0489, 0xe0b4, 0)},	/* Foxconn T77W968 LTE */
@@ -1451,7 +1454,6 @@ static int qmi_wwan_probe(struct usb_interface *intf,
 {
 	struct usb_device_id *id = (struct usb_device_id *)prod;
 	struct usb_interface_descriptor *desc = &intf->cur_altsetting->desc;
-	const struct driver_info *info;
 
 	/* Workaround to enable dynamic IDs.  This disables usbnet
 	 * blacklisting functionality.  Which, if required, can be
@@ -1487,12 +1489,8 @@ static int qmi_wwan_probe(struct usb_interface *intf,
 	 * different. Ignore the current interface if the number of endpoints
 	 * equals the number for the diag interface (two).
 	 */
-	info = (void *)id->driver_info;
-
-	if (info->data & QMI_WWAN_QUIRK_QUECTEL_DYNCFG) {
-		if (desc->bNumEndpoints == 2)
-			return -ENODEV;
-	}
+	if (desc->bNumEndpoints == 2)
+		return -ENODEV;
 
 	return usbnet_probe(intf, id);
 }
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 19bf63f73688..dfa187ec355d 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -28,7 +28,7 @@
 #define NETNEXT_VERSION		"09"
 
 /* Information for net */
-#define NET_VERSION		"9"
+#define NET_VERSION		"11"
 
 #define DRIVER_VERSION		"v1." NETNEXT_VERSION "." NET_VERSION
 #define DRIVER_AUTHOR "Realtek linux nic maintainers <nic_swsd@realtek.com>"
@@ -59,6 +59,7 @@
 #define PLA_LED_FEATURE		0xdd92
 #define PLA_PHYAR		0xde00
 #define PLA_BOOT_CTRL		0xe004
+#define PLA_LWAKE_CTRL_REG	0xe007
 #define PLA_GPHY_INTR_IMR	0xe022
 #define PLA_EEE_CR		0xe040
 #define PLA_EEEP_CR		0xe080
@@ -86,6 +87,7 @@
 #define PLA_TALLYCNT		0xe890
 #define PLA_SFF_STS_7		0xe8de
 #define PLA_PHYSTATUS		0xe908
+#define PLA_CONFIG6		0xe90a /* CONFIG6 */
 #define PLA_BP_BA		0xfc26
 #define PLA_BP_0		0xfc28
 #define PLA_BP_1		0xfc2a
@@ -98,6 +100,7 @@
 #define PLA_BP_EN		0xfc38
 
 #define USB_USB2PHY		0xb41e
+#define USB_SSPHYLINK1		0xb426
 #define USB_SSPHYLINK2		0xb428
 #define USB_U2P3_CTRL		0xb460
 #define USB_CSR_DUMMY1		0xb464
@@ -282,6 +285,9 @@
 #define LINK_ON_WAKE_EN		0x0010
 #define LINK_OFF_WAKE_EN	0x0008
 
+/* PLA_CONFIG6 */
+#define LANWAKE_CLR_EN		BIT(0)
+
 /* PLA_CONFIG5 */
 #define BWF_EN			0x0040
 #define MWF_EN			0x0020
@@ -294,6 +300,7 @@
 /* PLA_PHY_PWR */
 #define TX_10M_IDLE_EN		0x0080
 #define PFM_PWM_SWITCH		0x0040
+#define TEST_IO_OFF		BIT(4)
 
 /* PLA_MAC_PWR_CTRL */
 #define D3_CLK_GATED_EN		0x00004000
@@ -306,6 +313,7 @@
 #define MAC_CLK_SPDWN_EN	BIT(15)
 
 /* PLA_MAC_PWR_CTRL3 */
+#define PLA_MCU_SPDWN_EN	BIT(14)
 #define PKT_AVAIL_SPDWN_EN	0x0100
 #define SUSPEND_SPDWN_EN	0x0004
 #define U1U2_SPDWN_EN		0x0002
@@ -336,10 +344,16 @@
 /* PLA_BOOT_CTRL */
 #define AUTOLOAD_DONE		0x0002
 
+/* PLA_LWAKE_CTRL_REG */
+#define LANWAKE_PIN		BIT(7)
+
 /* USB_USB2PHY */
 #define USB2PHY_SUSPEND		0x0001
 #define USB2PHY_L1		0x0002
 
+/* USB_SSPHYLINK1 */
+#define DELAY_PHY_PWR_CHG	BIT(1)
+
 /* USB_SSPHYLINK2 */
 #define pwd_dn_scale_mask	0x3ffe
 #define pwd_dn_scale(x)		((x) << 1)
@@ -2722,6 +2736,8 @@ static u16 r8153_phy_status(struct r8152 *tp, u16 desired)
 		}
 
 		msleep(20);
+		if (test_bit(RTL8152_UNPLUG, &tp->flags))
+			break;
 	}
 
 	return data;
@@ -2899,7 +2915,6 @@ static void rtl8153b_runtime_enable(struct r8152 *tp, bool enable)
 		r8153b_ups_en(tp, false);
 		r8153b_queue_wake(tp, false);
 		rtl_runtime_suspend_enable(tp, false);
-		r8153_u2p3en(tp, true);
 		r8153b_u1u2en(tp, true);
 	}
 }
@@ -3422,7 +3437,6 @@ static void r8153b_hw_phy_cfg(struct r8152 *tp)
 
 	r8153b_aldps_en(tp, true);
 	r8153b_enable_fc(tp);
-	r8153_u2p3en(tp, true);
 
 	set_bit(PHY_RESET, &tp->flags);
 }
@@ -3716,6 +3730,8 @@ static void rtl8152_down(struct r8152 *tp)
 
 static void rtl8153_up(struct r8152 *tp)
 {
+	u32 ocp_data;
+
 	if (test_bit(RTL8152_UNPLUG, &tp->flags))
 		return;
 
@@ -3723,6 +3739,19 @@ static void rtl8153_up(struct r8152 *tp)
 	r8153_u2p3en(tp, false);
 	r8153_aldps_en(tp, false);
 	r8153_first_init(tp);
+
+	ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6);
+	ocp_data |= LANWAKE_CLR_EN;
+	ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6, ocp_data);
+
+	ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_LWAKE_CTRL_REG);
+	ocp_data &= ~LANWAKE_PIN;
+	ocp_write_byte(tp, MCU_TYPE_PLA, PLA_LWAKE_CTRL_REG, ocp_data);
+
+	ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_SSPHYLINK1);
+	ocp_data &= ~DELAY_PHY_PWR_CHG;
+	ocp_write_word(tp, MCU_TYPE_USB, USB_SSPHYLINK1, ocp_data);
+
 	r8153_aldps_en(tp, true);
 
 	switch (tp->version) {
@@ -3741,11 +3770,17 @@ static void rtl8153_up(struct r8152 *tp)
 
 static void rtl8153_down(struct r8152 *tp)
 {
+	u32 ocp_data;
+
 	if (test_bit(RTL8152_UNPLUG, &tp->flags)) {
 		rtl_drop_queued_tx(tp);
 		return;
 	}
 
+	ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6);
+	ocp_data &= ~LANWAKE_CLR_EN;
+	ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6, ocp_data);
+
 	r8153_u1u2en(tp, false);
 	r8153_u2p3en(tp, false);
 	r8153_power_cut_en(tp, false);
@@ -3756,6 +3791,8 @@ static void rtl8153_down(struct r8152 *tp)
 
 static void rtl8153b_up(struct r8152 *tp)
 {
+	u32 ocp_data;
+
 	if (test_bit(RTL8152_UNPLUG, &tp->flags))
 		return;
 
@@ -3766,18 +3803,27 @@ static void rtl8153b_up(struct r8152 *tp)
 	r8153_first_init(tp);
 	ocp_write_dword(tp, MCU_TYPE_USB, USB_RX_BUF_TH, RX_THR_B);
 
+	ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3);
+	ocp_data &= ~PLA_MCU_SPDWN_EN;
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, ocp_data);
+
 	r8153b_aldps_en(tp, true);
-	r8153_u2p3en(tp, true);
 	r8153b_u1u2en(tp, true);
 }
 
 static void rtl8153b_down(struct r8152 *tp)
 {
+	u32 ocp_data;
+
 	if (test_bit(RTL8152_UNPLUG, &tp->flags)) {
 		rtl_drop_queued_tx(tp);
 		return;
 	}
 
+	ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3);
+	ocp_data |= PLA_MCU_SPDWN_EN;
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, ocp_data);
+
 	r8153b_u1u2en(tp, false);
 	r8153_u2p3en(tp, false);
 	r8153b_power_cut_en(tp, false);
@@ -4082,7 +4128,10 @@ static void r8153_init(struct r8152 *tp)
 		if (ocp_read_word(tp, MCU_TYPE_PLA, PLA_BOOT_CTRL) &
 		    AUTOLOAD_DONE)
 			break;
+
 		msleep(20);
+		if (test_bit(RTL8152_UNPLUG, &tp->flags))
+			break;
 	}
 
 	data = r8153_phy_status(tp, 0);
@@ -4161,6 +4210,14 @@ static void r8153_init(struct r8152 *tp)
 	r8153_mac_clk_spd(tp, false);
 	usb_enable_lpm(tp->udev);
 
+	ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6);
+	ocp_data |= LANWAKE_CLR_EN;
+	ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6, ocp_data);
+
+	ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_LWAKE_CTRL_REG);
+	ocp_data &= ~LANWAKE_PIN;
+	ocp_write_byte(tp, MCU_TYPE_PLA, PLA_LWAKE_CTRL_REG, ocp_data);
+
 	/* rx aggregation */
 	ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_USB_CTRL);
 	ocp_data &= ~(RX_AGG_DISABLE | RX_ZERO_EN);
@@ -4200,7 +4257,10 @@ static void r8153b_init(struct r8152 *tp)
 		if (ocp_read_word(tp, MCU_TYPE_PLA, PLA_BOOT_CTRL) &
 		    AUTOLOAD_DONE)
 			break;
+
 		msleep(20);
+		if (test_bit(RTL8152_UNPLUG, &tp->flags))
+			break;
 	}
 
 	data = r8153_phy_status(tp, 0);
@@ -4233,6 +4293,19 @@ static void r8153b_init(struct r8152 *tp)
 	ocp_data |= MAC_CLK_SPDWN_EN;
 	ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL2, ocp_data);
 
+	ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3);
+	ocp_data &= ~PLA_MCU_SPDWN_EN;
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, ocp_data);
+
+	if (tp->version == RTL_VER_09) {
+		/* Disable Test IO for 32QFN */
+		if (ocp_read_byte(tp, MCU_TYPE_PLA, 0xdc00) & BIT(5)) {
+			ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_PHY_PWR);
+			ocp_data |= TEST_IO_OFF;
+			ocp_write_word(tp, MCU_TYPE_PLA, PLA_PHY_PWR, ocp_data);
+		}
+	}
+
 	set_bit(GREEN_ETHERNET, &tp->flags);
 
 	/* rx aggregation */
@@ -5195,6 +5268,9 @@ static int rtl8152_probe(struct usb_interface *intf,
 		return -ENODEV;
 	}
 
+	if (intf->cur_altsetting->desc.bNumEndpoints < 3)
+		return -ENODEV;
+
 	usb_reset_device(udev);
 	netdev = alloc_etherdev(sizeof(struct r8152));
 	if (!netdev) {
@@ -5284,6 +5360,11 @@ static int rtl8152_probe(struct usb_interface *intf,
 
 	intf->needs_remote_wakeup = 1;
 
+	if (!rtl_can_wakeup(tp))
+		__rtl_set_wol(tp, 0);
+	else
+		tp->saved_wolopts = __rtl_get_wol(tp);
+
 	tp->rtl_ops.init(tp);
 	queue_delayed_work(system_long_wq, &tp->hw_phy_work, 0);
 	set_ethernet_addr(tp);
@@ -5297,10 +5378,6 @@ static int rtl8152_probe(struct usb_interface *intf,
 		goto out1;
 	}
 
-	if (!rtl_can_wakeup(tp))
-		__rtl_set_wol(tp, 0);
-
-	tp->saved_wolopts = __rtl_get_wol(tp);
 	if (tp->saved_wolopts)
 		device_set_wakeup_enable(&udev->dev, true);
 	else
@@ -5358,6 +5435,7 @@ static const struct usb_device_id rtl8152_table[] = {
 	{REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, 0x8153)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07ab)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07c6)},
+	{REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x0927)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x304f)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x3062)},
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index 355be77f4241..bb4ccbda031a 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -1287,11 +1287,14 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf)
 
 	/* Init all registers */
 	ret = smsc95xx_reset(dev);
+	if (ret)
+		goto free_pdata;
 
 	/* detect device revision as different features may be available */
 	ret = smsc95xx_read_reg(dev, ID_REV, &val);
 	if (ret < 0)
-		return ret;
+		goto free_pdata;
+
 	val >>= 16;
 	pdata->chip_id = val;
 	pdata->mdix_ctrl = get_mdix_status(dev->net);
@@ -1317,6 +1320,10 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf)
 	schedule_delayed_work(&pdata->carrier_check, CARRIER_CHECK_DELAY);
 
 	return 0;
+
+free_pdata:
+	kfree(pdata);
+	return ret;
 }
 
 static void smsc95xx_unbind(struct usbnet *dev, struct usb_interface *intf)
@@ -1324,7 +1331,7 @@ static void smsc95xx_unbind(struct usbnet *dev, struct usb_interface *intf)
 	struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]);
 
 	if (pdata) {
-		cancel_delayed_work(&pdata->carrier_check);
+		cancel_delayed_work_sync(&pdata->carrier_check);
 		netif_dbg(dev, ifdown, dev->net, "free pdata\n");
 		kfree(pdata);
 		pdata = NULL;
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 52110e54e621..adbd895d9acb 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -479,13 +479,15 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq,
 					unsigned int *xdp_xmit)
 {
 	void *hard_start = frame->data - frame->headroom;
-	void *head = hard_start - sizeof(struct xdp_frame);
 	int len = frame->len, delta = 0;
 	struct xdp_frame orig_frame;
 	struct bpf_prog *xdp_prog;
 	unsigned int headroom;
 	struct sk_buff *skb;
 
+	/* bpf_xdp_adjust_head() assures BPF cannot access xdp_frame area */
+	hard_start -= sizeof(struct xdp_frame);
+
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
 	if (likely(xdp_prog)) {
@@ -507,7 +509,6 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq,
 			break;
 		case XDP_TX:
 			orig_frame = *frame;
-			xdp.data_hard_start = head;
 			xdp.rxq->mem = frame->mem;
 			if (unlikely(veth_xdp_tx(rq->dev, &xdp) < 0)) {
 				trace_xdp_exception(rq->dev, xdp_prog, act);
@@ -519,7 +520,6 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq,
 			goto xdp_xmit;
 		case XDP_REDIRECT:
 			orig_frame = *frame;
-			xdp.data_hard_start = head;
 			xdp.rxq->mem = frame->mem;
 			if (xdp_do_redirect(rq->dev, &xdp, xdp_prog)) {
 				frame = &orig_frame;
@@ -541,7 +541,7 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq,
 	rcu_read_unlock();
 
 	headroom = sizeof(struct xdp_frame) + frame->headroom - delta;
-	skb = veth_build_skb(head, headroom, len, 0);
+	skb = veth_build_skb(hard_start, headroom, len, 0);
 	if (!skb) {
 		xdp_return_frame(frame);
 		goto err;
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 0d4115c9e20b..384883cdbd25 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1231,9 +1231,11 @@ static bool try_fill_recv(struct virtnet_info *vi, struct receive_queue *rq,
 			break;
 	} while (rq->vq->num_free);
 	if (virtqueue_kick_prepare(rq->vq) && virtqueue_notify(rq->vq)) {
-		u64_stats_update_begin(&rq->stats.syncp);
+		unsigned long flags;
+
+		flags = u64_stats_update_begin_irqsave(&rq->stats.syncp);
 		rq->stats.kicks++;
-		u64_stats_update_end(&rq->stats.syncp);
+		u64_stats_update_end_irqrestore(&rq->stats.syncp, flags);
 	}
 
 	return !oom;
diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c
index 559db051a500..88d18ab83e54 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethtool.c
+++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c
@@ -692,6 +692,8 @@ vmxnet3_get_rss(struct net_device *netdev, u32 *p, u8 *key, u8 *hfunc)
 		*hfunc = ETH_RSS_HASH_TOP;
 	if (!p)
 		return 0;
+	if (n > UPT1_RSS_MAX_IND_TABLE_SIZE)
+		return 0;
 	while (n--)
 		p[n] = rssConf->indTable[n];
 	return 0;
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 1a22165afb39..c46775517185 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -188,8 +188,8 @@ static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
 	fl6.flowi6_proto = iph->nexthdr;
 	fl6.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF;
 
-	dst = ip6_route_output(net, NULL, &fl6);
-	if (dst == dst_null)
+	dst = ip6_dst_lookup_flow(net, NULL, &fl6, NULL);
+	if (IS_ERR(dst) || dst == dst_null)
 		goto err;
 
 	skb_dst_drop(skb);
@@ -474,7 +474,8 @@ static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev,
 	if (rt6_need_strict(&ipv6_hdr(skb)->daddr))
 		return skb;
 
-	if (qdisc_tx_is_default(vrf_dev))
+	if (qdisc_tx_is_default(vrf_dev) ||
+	    IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED)
 		return vrf_ip6_out_direct(vrf_dev, sk, skb);
 
 	return vrf_ip6_out_redirect(vrf_dev, skb);
@@ -686,7 +687,8 @@ static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev,
 	    ipv4_is_lbcast(ip_hdr(skb)->daddr))
 		return skb;
 
-	if (qdisc_tx_is_default(vrf_dev))
+	if (qdisc_tx_is_default(vrf_dev) ||
+	    IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED)
 		return vrf_ip_out_direct(vrf_dev, sk, skb);
 
 	return vrf_ip_out_redirect(vrf_dev, skb);
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index ef55df321129..54e7d7a8ea01 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1213,6 +1213,7 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
 	for (h = 0; h < FDB_HASH_SIZE; ++h) {
 		struct vxlan_fdb *f;
 
+		rcu_read_lock();
 		hlist_for_each_entry_rcu(f, &vxlan->fdb_head[h], hlist) {
 			struct vxlan_rdst *rd;
 
@@ -1225,12 +1226,15 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
 						     cb->nlh->nlmsg_seq,
 						     RTM_NEWNEIGH,
 						     NLM_F_MULTI, rd);
-				if (err < 0)
+				if (err < 0) {
+					rcu_read_unlock();
 					goto out;
+				}
 skip:
 				*idx += 1;
 			}
 		}
+		rcu_read_unlock();
 	}
 out:
 	return err;
@@ -1910,6 +1914,10 @@ static struct sk_buff *vxlan_na_create(struct sk_buff *request,
 	ns_olen = request->len - skb_network_offset(request) -
 		sizeof(struct ipv6hdr) - sizeof(*ns);
 	for (i = 0; i < ns_olen-1; i += (ns->opt[i+1]<<3)) {
+		if (!ns->opt[i + 1]) {
+			kfree_skb(reply);
+			return NULL;
+		}
 		if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) {
 			daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
 			break;
@@ -2765,10 +2773,19 @@ static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan,
 /* Setup stats when device is created */
 static int vxlan_init(struct net_device *dev)
 {
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	int err;
+
 	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
 
+	err = gro_cells_init(&vxlan->gro_cells, dev);
+	if (err) {
+		free_percpu(dev->tstats);
+		return err;
+	}
+
 	return 0;
 }
 
@@ -2834,8 +2851,10 @@ static void vxlan_flush(struct vxlan_dev *vxlan, bool do_all)
 			if (!do_all && (f->state & (NUD_PERMANENT | NUD_NOARP)))
 				continue;
 			/* the all_zeros_mac entry is deleted at vxlan_uninit */
-			if (!is_zero_ether_addr(f->eth_addr))
-				vxlan_fdb_destroy(vxlan, f, true, true);
+			if (is_zero_ether_addr(f->eth_addr) &&
+			    f->vni == vxlan->cfg.vni)
+				continue;
+			vxlan_fdb_destroy(vxlan, f, true, true);
 		}
 	}
 	spin_unlock_bh(&vxlan->hash_lock);
@@ -3028,8 +3047,6 @@ static void vxlan_setup(struct net_device *dev)
 
 	vxlan->dev = dev;
 
-	gro_cells_init(&vxlan->gro_cells, dev);
-
 	for (h = 0; h < FDB_HASH_SIZE; ++h)
 		INIT_HLIST_HEAD(&vxlan->fdb_head[h]);
 }
@@ -3120,7 +3137,7 @@ static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[],
 		u32 id = nla_get_u32(data[IFLA_VXLAN_ID]);
 
 		if (id >= VXLAN_N_VID) {
-			NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_ID],
+			NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_ID],
 					    "VXLAN ID must be lower than 16777216");
 			return -ERANGE;
 		}
@@ -3131,7 +3148,7 @@ static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[],
 			= nla_data(data[IFLA_VXLAN_PORT_RANGE]);
 
 		if (ntohs(p->high) < ntohs(p->low)) {
-			NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_PORT_RANGE],
+			NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_PORT_RANGE],
 					    "Invalid source port range");
 			return -EINVAL;
 		}
@@ -3141,7 +3158,7 @@ static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[],
 		enum ifla_vxlan_df df = nla_get_u8(data[IFLA_VXLAN_DF]);
 
 		if (df < 0 || df > VXLAN_DF_MAX) {
-			NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_DF],
+			NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_DF],
 					    "Invalid DF attribute");
 			return -EINVAL;
 		}
diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c
index ca0f3be2b6bf..4ad0a0c33d85 100644
--- a/drivers/net/wan/fsl_ucc_hdlc.c
+++ b/drivers/net/wan/fsl_ucc_hdlc.c
@@ -73,7 +73,7 @@ static struct ucc_tdm_info utdm_primary_info = {
 	},
 };
 
-static struct ucc_tdm_info utdm_info[MAX_HDLC_NUM];
+static struct ucc_tdm_info utdm_info[UCC_MAX_NUM];
 
 static int uhdlc_init(struct ucc_hdlc_private *priv)
 {
@@ -245,6 +245,11 @@ static int uhdlc_init(struct ucc_hdlc_private *priv)
 		ret = -ENOMEM;
 		goto free_riptr;
 	}
+	if (riptr != (u16)riptr || tiptr != (u16)tiptr) {
+		dev_err(priv->dev, "MURAM allocation out of addressable range\n");
+		ret = -ENOMEM;
+		goto free_tiptr;
+	}
 
 	/* Set RIPTR, TIPTR */
 	iowrite16be(riptr, &priv->ucc_pram->riptr);
diff --git a/drivers/net/wan/hdlc_x25.c b/drivers/net/wan/hdlc_x25.c
index 5643675ff724..e2a83f4cd3bb 100644
--- a/drivers/net/wan/hdlc_x25.c
+++ b/drivers/net/wan/hdlc_x25.c
@@ -62,10 +62,13 @@ static int x25_data_indication(struct net_device *dev, struct sk_buff *skb)
 {
 	unsigned char *ptr;
 
-	skb_push(skb, 1);
-
-	if (skb_cow(skb, 1))
+	if (skb_cow(skb, 1)) {
+		kfree_skb(skb);
 		return NET_RX_DROP;
+	}
+
+	skb_push(skb, 1);
+	skb_reset_network_header(skb);
 
 	ptr  = skb->data;
 	*ptr = X25_IFACE_DATA;
@@ -79,6 +82,13 @@ static int x25_data_indication(struct net_device *dev, struct sk_buff *skb)
 static void x25_data_transmit(struct net_device *dev, struct sk_buff *skb)
 {
 	hdlc_device *hdlc = dev_to_hdlc(dev);
+
+	skb_reset_network_header(skb);
+	skb->protocol = hdlc_type_trans(skb, dev);
+
+	if (dev_nit_active(dev))
+		dev_queue_xmit_nit(skb, dev);
+
 	hdlc->xmit(skb, dev); /* Ignore return value :-( */
 }
 
@@ -93,6 +103,7 @@ static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev)
 	switch (skb->data[0]) {
 	case X25_IFACE_DATA:	/* Data to be transmitted */
 		skb_pull(skb, 1);
+		skb_reset_network_header(skb);
 		if ((result = lapb_data_request(dev, skb)) != LAPB_OK)
 			dev_kfree_skb(skb);
 		return NETDEV_TX_OK;
diff --git a/drivers/net/wan/ixp4xx_hss.c b/drivers/net/wan/ixp4xx_hss.c
index ea6ee6a608ce..e7619cec978a 100644
--- a/drivers/net/wan/ixp4xx_hss.c
+++ b/drivers/net/wan/ixp4xx_hss.c
@@ -258,7 +258,7 @@ struct port {
 	struct hss_plat_info *plat;
 	buffer_t *rx_buff_tab[RX_DESCS], *tx_buff_tab[TX_DESCS];
 	struct desc *desc_tab;	/* coherent */
-	u32 desc_tab_phys;
+	dma_addr_t desc_tab_phys;
 	unsigned int id;
 	unsigned int clock_type, clock_rate, loopback;
 	unsigned int initialized, carrier;
@@ -858,7 +858,7 @@ static int hss_hdlc_xmit(struct sk_buff *skb, struct net_device *dev)
 		dev->stats.tx_dropped++;
 		return NETDEV_TX_OK;
 	}
-	memcpy_swab32(mem, (u32 *)((int)skb->data & ~3), bytes / 4);
+	memcpy_swab32(mem, (u32 *)((uintptr_t)skb->data & ~3), bytes / 4);
 	dev_kfree_skb(skb);
 #endif
 
diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c
index 0f1217b506ad..996eb9c55b39 100644
--- a/drivers/net/wan/lapbether.c
+++ b/drivers/net/wan/lapbether.c
@@ -128,10 +128,12 @@ static int lapbeth_data_indication(struct net_device *dev, struct sk_buff *skb)
 {
 	unsigned char *ptr;
 
-	skb_push(skb, 1);
-
-	if (skb_cow(skb, 1))
+	if (skb_cow(skb, 1)) {
+		kfree_skb(skb);
 		return NET_RX_DROP;
+	}
+
+	skb_push(skb, 1);
 
 	ptr  = skb->data;
 	*ptr = X25_IFACE_DATA;
@@ -155,6 +157,12 @@ static netdev_tx_t lapbeth_xmit(struct sk_buff *skb,
 	if (!netif_running(dev))
 		goto drop;
 
+	/* There should be a pseudo header of 1 byte added by upper layers.
+	 * Check to make sure it is there before reading it.
+	 */
+	if (skb->len < 1)
+		goto drop;
+
 	switch (skb->data[0]) {
 	case X25_IFACE_DATA:
 		break;
@@ -303,7 +311,7 @@ static void lapbeth_setup(struct net_device *dev)
 	dev->netdev_ops	     = &lapbeth_netdev_ops;
 	dev->needs_free_netdev = true;
 	dev->type            = ARPHRD_X25;
-	dev->hard_header_len = 3;
+	dev->hard_header_len = 0;
 	dev->mtu             = 1000;
 	dev->addr_len        = 0;
 }
@@ -324,6 +332,15 @@ static int lapbeth_new_device(struct net_device *dev)
 	if (!ndev)
 		goto out;
 
+	/* When transmitting data:
+	 * first this driver removes a pseudo header of 1 byte,
+	 * then the lapb module prepends an LAPB header of at most 3 bytes,
+	 * then this driver prepends a length field of 2 bytes,
+	 * then the underlying Ethernet device prepends its own header.
+	 */
+	ndev->needed_headroom = -1 + 3 + 2 + dev->hard_header_len
+					   + dev->needed_headroom;
+
 	lapbeth = netdev_priv(ndev);
 	lapbeth->axdev = ndev;
 
diff --git a/drivers/net/wan/sdla.c b/drivers/net/wan/sdla.c
index a9ac3f37b904..af1798934f3b 100644
--- a/drivers/net/wan/sdla.c
+++ b/drivers/net/wan/sdla.c
@@ -707,7 +707,7 @@ static netdev_tx_t sdla_transmit(struct sk_buff *skb,
 
 					spin_lock_irqsave(&sdla_lock, flags);
 					SDLA_WINDOW(dev, addr);
-					pbuf = (void *)(((int) dev->mem_start) + (addr & SDLA_ADDR_MASK));
+					pbuf = (void *)(dev->mem_start + (addr & SDLA_ADDR_MASK));
 					__sdla_write(dev, pbuf->buf_addr, skb->data, skb->len);
 					SDLA_WINDOW(dev, addr);
 					pbuf->opp_flag = 1;
diff --git a/drivers/net/wan/x25_asy.c b/drivers/net/wan/x25_asy.c
index d78bc838d631..24923471360e 100644
--- a/drivers/net/wan/x25_asy.c
+++ b/drivers/net/wan/x25_asy.c
@@ -183,7 +183,7 @@ static inline void x25_asy_unlock(struct x25_asy *sl)
 	netif_wake_queue(sl->dev);
 }
 
-/* Send one completely decapsulated IP datagram to the IP layer. */
+/* Send an LAPB frame to the LAPB module to process. */
 
 static void x25_asy_bump(struct x25_asy *sl)
 {
@@ -195,13 +195,12 @@ static void x25_asy_bump(struct x25_asy *sl)
 	count = sl->rcount;
 	dev->stats.rx_bytes += count;
 
-	skb = dev_alloc_skb(count+1);
+	skb = dev_alloc_skb(count);
 	if (skb == NULL) {
 		netdev_warn(sl->dev, "memory squeeze, dropping packet\n");
 		dev->stats.rx_dropped++;
 		return;
 	}
-	skb_push(skb, 1);	/* LAPB internal control */
 	skb_put_data(skb, sl->rbuff, count);
 	skb->protocol = x25_type_trans(skb, sl->dev);
 	err = lapb_data_received(skb->dev, skb);
@@ -209,7 +208,6 @@ static void x25_asy_bump(struct x25_asy *sl)
 		kfree_skb(skb);
 		printk(KERN_DEBUG "x25_asy: data received err - %d\n", err);
 	} else {
-		netif_rx(skb);
 		dev->stats.rx_packets++;
 	}
 }
@@ -356,12 +354,21 @@ static netdev_tx_t x25_asy_xmit(struct sk_buff *skb,
  */
 
 /*
- *	Called when I frame data arrives. We did the work above - throw it
- *	at the net layer.
+ *	Called when I frame data arrive. We add a pseudo header for upper
+ *	layers and pass it to upper layers.
  */
 
 static int x25_asy_data_indication(struct net_device *dev, struct sk_buff *skb)
 {
+	if (skb_cow(skb, 1)) {
+		kfree_skb(skb);
+		return NET_RX_DROP;
+	}
+	skb_push(skb, 1);
+	skb->data[0] = X25_IFACE_DATA;
+
+	skb->protocol = x25_type_trans(skb, dev);
+
 	return netif_rx(skb);
 }
 
@@ -657,7 +664,7 @@ static void x25_asy_unesc(struct x25_asy *sl, unsigned char s)
 	switch (s) {
 	case X25_END:
 		if (!test_and_clear_bit(SLF_ERROR, &sl->flags) &&
-		    sl->rcount > 2)
+		    sl->rcount >= 2)
 			x25_asy_bump(sl);
 		clear_bit(SLF_ESCAPE, &sl->flags);
 		sl->rcount = 0;
diff --git a/drivers/net/wimax/i2400m/usb-fw.c b/drivers/net/wimax/i2400m/usb-fw.c
index 529ebca1e9e1..1f7709d24f35 100644
--- a/drivers/net/wimax/i2400m/usb-fw.c
+++ b/drivers/net/wimax/i2400m/usb-fw.c
@@ -354,6 +354,7 @@ out:
 		usb_autopm_put_interface(i2400mu->usb_iface);
 	d_fnend(8, dev, "(i2400m %p ack %p size %zu) = %ld\n",
 		i2400m, ack, ack_size, (long) result);
+	usb_put_urb(&notif_urb);
 	return result;
 
 error_exceeded:
diff --git a/drivers/net/wireless/ath/ath10k/htt.h b/drivers/net/wireless/ath/ath10k/htt.h
index 4cee5492abc8..4ad62c1cc6ea 100644
--- a/drivers/net/wireless/ath/ath10k/htt.h
+++ b/drivers/net/wireless/ath/ath10k/htt.h
@@ -1995,6 +1995,7 @@ struct ath10k_htt_tx_ops {
 	int (*htt_h2t_aggr_cfg_msg)(struct ath10k_htt *htt,
 				    u8 max_subfrms_ampdu,
 				    u8 max_subfrms_amsdu);
+	void (*htt_flush_tx)(struct ath10k_htt *htt);
 };
 
 static inline int ath10k_htt_send_rx_ring_cfg(struct ath10k_htt *htt)
@@ -2034,6 +2035,12 @@ static inline int ath10k_htt_tx(struct ath10k_htt *htt,
 	return htt->tx_ops->htt_tx(htt, txmode, msdu);
 }
 
+static inline void ath10k_htt_flush_tx(struct ath10k_htt *htt)
+{
+	if (htt->tx_ops->htt_flush_tx)
+		htt->tx_ops->htt_flush_tx(htt);
+}
+
 static inline int ath10k_htt_alloc_txbuff(struct ath10k_htt *htt)
 {
 	if (!htt->tx_ops->htt_alloc_txbuff)
diff --git a/drivers/net/wireless/ath/ath10k/htt_tx.c b/drivers/net/wireless/ath/ath10k/htt_tx.c
index d8e9cc0bb772..50ab8a300cf4 100644
--- a/drivers/net/wireless/ath/ath10k/htt_tx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_tx.c
@@ -529,9 +529,14 @@ void ath10k_htt_tx_destroy(struct ath10k_htt *htt)
 	htt->tx_mem_allocated = false;
 }
 
-void ath10k_htt_tx_stop(struct ath10k_htt *htt)
+static void ath10k_htt_flush_tx_queue(struct ath10k_htt *htt)
 {
 	idr_for_each(&htt->pending_tx, ath10k_htt_tx_clean_up_pending, htt->ar);
+}
+
+void ath10k_htt_tx_stop(struct ath10k_htt *htt)
+{
+	ath10k_htt_flush_tx_queue(htt);
 	idr_destroy(&htt->pending_tx);
 }
 
@@ -1508,7 +1513,9 @@ static int ath10k_htt_tx_32(struct ath10k_htt *htt,
 err_unmap_msdu:
 	dma_unmap_single(dev, skb_cb->paddr, msdu->len, DMA_TO_DEVICE);
 err_free_msdu_id:
+	spin_lock_bh(&htt->tx_lock);
 	ath10k_htt_tx_free_msdu_id(htt, msdu_id);
+	spin_unlock_bh(&htt->tx_lock);
 err:
 	return res;
 }
@@ -1715,7 +1722,9 @@ static int ath10k_htt_tx_64(struct ath10k_htt *htt,
 err_unmap_msdu:
 	dma_unmap_single(dev, skb_cb->paddr, msdu->len, DMA_TO_DEVICE);
 err_free_msdu_id:
+	spin_lock_bh(&htt->tx_lock);
 	ath10k_htt_tx_free_msdu_id(htt, msdu_id);
+	spin_unlock_bh(&htt->tx_lock);
 err:
 	return res;
 }
@@ -1746,6 +1755,7 @@ static const struct ath10k_htt_tx_ops htt_tx_ops_hl = {
 	.htt_send_rx_ring_cfg = ath10k_htt_send_rx_ring_cfg_hl,
 	.htt_send_frag_desc_bank_cfg = ath10k_htt_send_frag_desc_bank_cfg_32,
 	.htt_tx = ath10k_htt_tx_hl,
+	.htt_flush_tx = ath10k_htt_flush_tx_queue,
 };
 
 void ath10k_htt_set_tx_ops(struct ath10k_htt *htt)
diff --git a/drivers/net/wireless/ath/ath10k/hw.c b/drivers/net/wireless/ath/ath10k/hw.c
index b242085c3c16..ea0c22fa2378 100644
--- a/drivers/net/wireless/ath/ath10k/hw.c
+++ b/drivers/net/wireless/ath/ath10k/hw.c
@@ -1145,6 +1145,7 @@ static bool ath10k_qca99x0_rx_desc_msdu_limit_error(struct htt_rx_desc *rxd)
 const struct ath10k_hw_ops qca99x0_ops = {
 	.rx_desc_get_l3_pad_bytes = ath10k_qca99x0_rx_desc_get_l3_pad_bytes,
 	.rx_desc_get_msdu_limit_error = ath10k_qca99x0_rx_desc_msdu_limit_error,
+	.is_rssi_enable = ath10k_htt_tx_rssi_enable,
 };
 
 const struct ath10k_hw_ops qca6174_ops = {
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 702ebc9c71d8..41101dec285e 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -3875,6 +3875,9 @@ void ath10k_mgmt_over_wmi_tx_work(struct work_struct *work)
 			if (ret) {
 				ath10k_warn(ar, "failed to transmit management frame by ref via WMI: %d\n",
 					    ret);
+				/* remove this msdu from idr tracking */
+				ath10k_wmi_cleanup_mgmt_tx_send(ar, skb);
+
 				dma_unmap_single(ar->dev, paddr, skb->len,
 						 DMA_TO_DEVICE);
 				ieee80211_free_txskb(ar->hw, skb);
@@ -6993,6 +6996,7 @@ static void ath10k_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 					ath10k_wmi_peer_flush(ar, arvif->vdev_id,
 							      arvif->bssid, bitmap);
 			}
+			ath10k_htt_flush_tx(&ar->htt);
 		}
 		return;
 	}
@@ -8631,7 +8635,6 @@ int ath10k_mac_register(struct ath10k *ar)
 	ar->hw->wiphy->max_scan_ie_len = WLAN_SCAN_PARAMS_MAX_IE_LEN;
 
 	if (test_bit(WMI_SERVICE_NLO, ar->wmi.svc_map)) {
-		ar->hw->wiphy->max_sched_scan_reqs = 1;
 		ar->hw->wiphy->max_sched_scan_ssids = WMI_PNO_MAX_SUPP_NETWORKS;
 		ar->hw->wiphy->max_match_sets = WMI_PNO_MAX_SUPP_NETWORKS;
 		ar->hw->wiphy->max_sched_scan_ie_len = WMI_PNO_MAX_IE_LENGTH;
diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c
index 7f7cb96dc1b5..05644d2b95b9 100644
--- a/drivers/net/wireless/ath/ath10k/pci.c
+++ b/drivers/net/wireless/ath/ath10k/pci.c
@@ -1608,11 +1608,22 @@ static int ath10k_pci_dump_memory_reg(struct ath10k *ar,
 {
 	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
 	u32 i;
+	int ret;
+
+	mutex_lock(&ar->conf_mutex);
+	if (ar->state != ATH10K_STATE_ON) {
+		ath10k_warn(ar, "Skipping pci_dump_memory_reg invalid state\n");
+		ret = -EIO;
+		goto done;
+	}
 
 	for (i = 0; i < region->len; i += 4)
 		*(u32 *)(buf + i) = ioread32(ar_pci->mem + region->start + i);
 
-	return region->len;
+	ret = region->len;
+done:
+	mutex_unlock(&ar->conf_mutex);
+	return ret;
 }
 
 /* if an error happened returns < 0, otherwise the length */
@@ -1708,7 +1719,11 @@ static void ath10k_pci_dump_memory(struct ath10k *ar,
 			count = ath10k_pci_dump_memory_sram(ar, current_region, buf);
 			break;
 		case ATH10K_MEM_REGION_TYPE_IOREG:
-			count = ath10k_pci_dump_memory_reg(ar, current_region, buf);
+			ret = ath10k_pci_dump_memory_reg(ar, current_region, buf);
+			if (ret < 0)
+				break;
+
+			count = ret;
 			break;
 		default:
 			ret = ath10k_pci_dump_memory_generic(ar, current_region, buf);
@@ -2063,6 +2078,7 @@ static void ath10k_pci_hif_stop(struct ath10k *ar)
 	ath10k_pci_irq_sync(ar);
 	napi_synchronize(&ar->napi);
 	napi_disable(&ar->napi);
+	cancel_work_sync(&ar_pci->dump_work);
 
 	/* Most likely the device has HTT Rx ring configured. The only way to
 	 * prevent the device from accessing (and possible corrupting) host
diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c
index c0fc96c29bf1..00f442c86fb4 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.c
+++ b/drivers/net/wireless/ath/ath10k/snoc.c
@@ -1714,13 +1714,16 @@ static int ath10k_snoc_probe(struct platform_device *pdev)
 	ret = ath10k_qmi_init(ar, msa_size);
 	if (ret) {
 		ath10k_warn(ar, "failed to register wlfw qmi client: %d\n", ret);
-		goto err_core_destroy;
+		goto err_power_off;
 	}
 
 	ath10k_dbg(ar, ATH10K_DBG_SNOC, "snoc probe\n");
 
 	return 0;
 
+err_power_off:
+	ath10k_hw_power_off(ar);
+
 err_free_irq:
 	ath10k_snoc_free_irq(ar);
 
diff --git a/drivers/net/wireless/ath/ath10k/txrx.c b/drivers/net/wireless/ath/ath10k/txrx.c
index 39abf8b12903..f46b9083bbf1 100644
--- a/drivers/net/wireless/ath/ath10k/txrx.c
+++ b/drivers/net/wireless/ath/ath10k/txrx.c
@@ -84,9 +84,11 @@ int ath10k_txrx_tx_unref(struct ath10k_htt *htt,
 		wake_up(&htt->empty_tx_wq);
 	spin_unlock_bh(&htt->tx_lock);
 
+	rcu_read_lock();
 	if (txq && txq->sta && skb_cb->airtime_est)
 		ieee80211_sta_register_airtime(txq->sta, txq->tid,
 					       skb_cb->airtime_est, 0);
+	rcu_read_unlock();
 
 	if (ar->bus_param.dev_type != ATH10K_DEV_TYPE_HL)
 		dma_unmap_single(dev, skb_cb->paddr, msdu->len, DMA_TO_DEVICE);
diff --git a/drivers/net/wireless/ath/ath10k/wmi-ops.h b/drivers/net/wireless/ath/ath10k/wmi-ops.h
index 1491c25518bb..edccabc667e8 100644
--- a/drivers/net/wireless/ath/ath10k/wmi-ops.h
+++ b/drivers/net/wireless/ath/ath10k/wmi-ops.h
@@ -133,6 +133,7 @@ struct wmi_ops {
 	struct sk_buff *(*gen_mgmt_tx_send)(struct ath10k *ar,
 					    struct sk_buff *skb,
 					    dma_addr_t paddr);
+	int (*cleanup_mgmt_tx_send)(struct ath10k *ar, struct sk_buff *msdu);
 	struct sk_buff *(*gen_dbglog_cfg)(struct ath10k *ar, u64 module_enable,
 					  u32 log_level);
 	struct sk_buff *(*gen_pktlog_enable)(struct ath10k *ar, u32 filter);
@@ -442,6 +443,15 @@ ath10k_wmi_get_txbf_conf_scheme(struct ath10k *ar)
 }
 
 static inline int
+ath10k_wmi_cleanup_mgmt_tx_send(struct ath10k *ar, struct sk_buff *msdu)
+{
+	if (!ar->wmi.ops->cleanup_mgmt_tx_send)
+		return -EOPNOTSUPP;
+
+	return ar->wmi.ops->cleanup_mgmt_tx_send(ar, msdu);
+}
+
+static inline int
 ath10k_wmi_mgmt_tx_send(struct ath10k *ar, struct sk_buff *msdu,
 			dma_addr_t paddr)
 {
diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.c b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
index 9deca6d33ecd..54869c0493d8 100644
--- a/drivers/net/wireless/ath/ath10k/wmi-tlv.c
+++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
@@ -2785,6 +2785,18 @@ ath10k_wmi_tlv_op_gen_request_stats(struct ath10k *ar, u32 stats_mask)
 }
 
 static int
+ath10k_wmi_tlv_op_cleanup_mgmt_tx_send(struct ath10k *ar,
+				       struct sk_buff *msdu)
+{
+	struct ath10k_skb_cb *cb = ATH10K_SKB_CB(msdu);
+	struct ath10k_wmi *wmi = &ar->wmi;
+
+	idr_remove(&wmi->mgmt_pending_tx, cb->msdu_id);
+
+	return 0;
+}
+
+static int
 ath10k_wmi_mgmt_tx_alloc_msdu_id(struct ath10k *ar, struct sk_buff *skb,
 				 dma_addr_t paddr)
 {
@@ -2858,6 +2870,8 @@ ath10k_wmi_tlv_op_gen_mgmt_tx_send(struct ath10k *ar, struct sk_buff *msdu,
 	if (desc_id < 0)
 		goto err_free_skb;
 
+	cb->msdu_id = desc_id;
+
 	ptr = (void *)skb->data;
 	tlv = ptr;
 	tlv->tag = __cpu_to_le16(WMI_TLV_TAG_STRUCT_MGMT_TX_CMD);
@@ -3597,6 +3611,7 @@ ath10k_wmi_tlv_op_gen_config_pno_start(struct ath10k *ar,
 	struct wmi_tlv *tlv;
 	struct sk_buff *skb;
 	__le32 *channel_list;
+	u16 tlv_len;
 	size_t len;
 	void *ptr;
 	u32 i;
@@ -3654,10 +3669,12 @@ ath10k_wmi_tlv_op_gen_config_pno_start(struct ath10k *ar,
 	/* nlo_configured_parameters(nlo_list) */
 	cmd->no_of_ssids = __cpu_to_le32(min_t(u8, pno->uc_networks_count,
 					       WMI_NLO_MAX_SSIDS));
+	tlv_len = __le32_to_cpu(cmd->no_of_ssids) *
+		sizeof(struct nlo_configured_parameters);
 
 	tlv = ptr;
 	tlv->tag = __cpu_to_le16(WMI_TLV_TAG_ARRAY_STRUCT);
-	tlv->len = __cpu_to_le16(len);
+	tlv->len = __cpu_to_le16(tlv_len);
 
 	ptr += sizeof(*tlv);
 	nlo_list = ptr;
@@ -4283,6 +4300,7 @@ static const struct wmi_ops wmi_tlv_ops = {
 	.gen_force_fw_hang = ath10k_wmi_tlv_op_gen_force_fw_hang,
 	/* .gen_mgmt_tx = not implemented; HTT is used */
 	.gen_mgmt_tx_send = ath10k_wmi_tlv_op_gen_mgmt_tx_send,
+	.cleanup_mgmt_tx_send = ath10k_wmi_tlv_op_cleanup_mgmt_tx_send,
 	.gen_dbglog_cfg = ath10k_wmi_tlv_op_gen_dbglog_cfg,
 	.gen_pktlog_enable = ath10k_wmi_tlv_op_gen_pktlog_enable,
 	.gen_pktlog_disable = ath10k_wmi_tlv_op_gen_pktlog_disable,
diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c
index 98a90e49d666..7e1bef34ba19 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -9397,7 +9397,7 @@ static int ath10k_wmi_mgmt_tx_clean_up_pending(int msdu_id, void *ptr,
 
 	msdu = pkt_addr->vaddr;
 	dma_unmap_single(ar->dev, pkt_addr->paddr,
-			 msdu->len, DMA_FROM_DEVICE);
+			 msdu->len, DMA_TO_DEVICE);
 	ieee80211_free_txskb(ar->hw, msdu);
 
 	return 0;
diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c
index fb649d85b8fc..3f563e02d17d 100644
--- a/drivers/net/wireless/ath/ath9k/hif_usb.c
+++ b/drivers/net/wireless/ath/ath9k/hif_usb.c
@@ -612,6 +612,11 @@ static void ath9k_hif_usb_rx_stream(struct hif_device_usb *hif_dev,
 			hif_dev->remain_skb = nskb;
 			spin_unlock(&hif_dev->rx_lock);
 		} else {
+			if (pool_index == MAX_PKT_NUM_IN_TRANSFER) {
+				dev_err(&hif_dev->udev->dev,
+					"ath9k_htc: over RX MAX_PKT_NUM\n");
+				goto err;
+			}
 			nskb = __dev_alloc_skb(pkt_len + 32, GFP_ATOMIC);
 			if (!nskb) {
 				dev_err(&hif_dev->udev->dev,
@@ -638,9 +643,9 @@ err:
 
 static void ath9k_hif_usb_rx_cb(struct urb *urb)
 {
-	struct sk_buff *skb = (struct sk_buff *) urb->context;
-	struct hif_device_usb *hif_dev =
-		usb_get_intfdata(usb_ifnum_to_if(urb->dev, 0));
+	struct rx_buf *rx_buf = (struct rx_buf *)urb->context;
+	struct hif_device_usb *hif_dev = rx_buf->hif_dev;
+	struct sk_buff *skb = rx_buf->skb;
 	int ret;
 
 	if (!skb)
@@ -680,14 +685,15 @@ resubmit:
 	return;
 free:
 	kfree_skb(skb);
+	kfree(rx_buf);
 }
 
 static void ath9k_hif_usb_reg_in_cb(struct urb *urb)
 {
-	struct sk_buff *skb = (struct sk_buff *) urb->context;
+	struct rx_buf *rx_buf = (struct rx_buf *)urb->context;
+	struct hif_device_usb *hif_dev = rx_buf->hif_dev;
+	struct sk_buff *skb = rx_buf->skb;
 	struct sk_buff *nskb;
-	struct hif_device_usb *hif_dev =
-		usb_get_intfdata(usb_ifnum_to_if(urb->dev, 0));
 	int ret;
 
 	if (!skb)
@@ -727,11 +733,13 @@ static void ath9k_hif_usb_reg_in_cb(struct urb *urb)
 			return;
 		}
 
+		rx_buf->skb = nskb;
+
 		usb_fill_int_urb(urb, hif_dev->udev,
 				 usb_rcvintpipe(hif_dev->udev,
 						 USB_REG_IN_PIPE),
 				 nskb->data, MAX_REG_IN_BUF_SIZE,
-				 ath9k_hif_usb_reg_in_cb, nskb, 1);
+				 ath9k_hif_usb_reg_in_cb, rx_buf, 1);
 	}
 
 resubmit:
@@ -745,6 +753,7 @@ resubmit:
 	return;
 free:
 	kfree_skb(skb);
+	kfree(rx_buf);
 	urb->context = NULL;
 }
 
@@ -790,7 +799,7 @@ static int ath9k_hif_usb_alloc_tx_urbs(struct hif_device_usb *hif_dev)
 	init_usb_anchor(&hif_dev->mgmt_submitted);
 
 	for (i = 0; i < MAX_TX_URB_NUM; i++) {
-		tx_buf = kzalloc(sizeof(struct tx_buf), GFP_KERNEL);
+		tx_buf = kzalloc(sizeof(*tx_buf), GFP_KERNEL);
 		if (!tx_buf)
 			goto err;
 
@@ -827,8 +836,9 @@ static void ath9k_hif_usb_dealloc_rx_urbs(struct hif_device_usb *hif_dev)
 
 static int ath9k_hif_usb_alloc_rx_urbs(struct hif_device_usb *hif_dev)
 {
-	struct urb *urb = NULL;
+	struct rx_buf *rx_buf = NULL;
 	struct sk_buff *skb = NULL;
+	struct urb *urb = NULL;
 	int i, ret;
 
 	init_usb_anchor(&hif_dev->rx_submitted);
@@ -836,6 +846,12 @@ static int ath9k_hif_usb_alloc_rx_urbs(struct hif_device_usb *hif_dev)
 
 	for (i = 0; i < MAX_RX_URB_NUM; i++) {
 
+		rx_buf = kzalloc(sizeof(*rx_buf), GFP_KERNEL);
+		if (!rx_buf) {
+			ret = -ENOMEM;
+			goto err_rxb;
+		}
+
 		/* Allocate URB */
 		urb = usb_alloc_urb(0, GFP_KERNEL);
 		if (urb == NULL) {
@@ -850,11 +866,14 @@ static int ath9k_hif_usb_alloc_rx_urbs(struct hif_device_usb *hif_dev)
 			goto err_skb;
 		}
 
+		rx_buf->hif_dev = hif_dev;
+		rx_buf->skb = skb;
+
 		usb_fill_bulk_urb(urb, hif_dev->udev,
 				  usb_rcvbulkpipe(hif_dev->udev,
 						  USB_WLAN_RX_PIPE),
 				  skb->data, MAX_RX_BUF_SIZE,
-				  ath9k_hif_usb_rx_cb, skb);
+				  ath9k_hif_usb_rx_cb, rx_buf);
 
 		/* Anchor URB */
 		usb_anchor_urb(urb, &hif_dev->rx_submitted);
@@ -880,6 +899,8 @@ err_submit:
 err_skb:
 	usb_free_urb(urb);
 err_urb:
+	kfree(rx_buf);
+err_rxb:
 	ath9k_hif_usb_dealloc_rx_urbs(hif_dev);
 	return ret;
 }
@@ -891,14 +912,21 @@ static void ath9k_hif_usb_dealloc_reg_in_urbs(struct hif_device_usb *hif_dev)
 
 static int ath9k_hif_usb_alloc_reg_in_urbs(struct hif_device_usb *hif_dev)
 {
-	struct urb *urb = NULL;
+	struct rx_buf *rx_buf = NULL;
 	struct sk_buff *skb = NULL;
+	struct urb *urb = NULL;
 	int i, ret;
 
 	init_usb_anchor(&hif_dev->reg_in_submitted);
 
 	for (i = 0; i < MAX_REG_IN_URB_NUM; i++) {
 
+		rx_buf = kzalloc(sizeof(*rx_buf), GFP_KERNEL);
+		if (!rx_buf) {
+			ret = -ENOMEM;
+			goto err_rxb;
+		}
+
 		/* Allocate URB */
 		urb = usb_alloc_urb(0, GFP_KERNEL);
 		if (urb == NULL) {
@@ -913,11 +941,14 @@ static int ath9k_hif_usb_alloc_reg_in_urbs(struct hif_device_usb *hif_dev)
 			goto err_skb;
 		}
 
+		rx_buf->hif_dev = hif_dev;
+		rx_buf->skb = skb;
+
 		usb_fill_int_urb(urb, hif_dev->udev,
 				  usb_rcvintpipe(hif_dev->udev,
 						  USB_REG_IN_PIPE),
 				  skb->data, MAX_REG_IN_BUF_SIZE,
-				  ath9k_hif_usb_reg_in_cb, skb, 1);
+				  ath9k_hif_usb_reg_in_cb, rx_buf, 1);
 
 		/* Anchor URB */
 		usb_anchor_urb(urb, &hif_dev->reg_in_submitted);
@@ -943,6 +974,8 @@ err_submit:
 err_skb:
 	usb_free_urb(urb);
 err_urb:
+	kfree(rx_buf);
+err_rxb:
 	ath9k_hif_usb_dealloc_reg_in_urbs(hif_dev);
 	return ret;
 }
@@ -973,7 +1006,7 @@ err:
 	return -ENOMEM;
 }
 
-static void ath9k_hif_usb_dealloc_urbs(struct hif_device_usb *hif_dev)
+void ath9k_hif_usb_dealloc_urbs(struct hif_device_usb *hif_dev)
 {
 	usb_kill_anchored_urbs(&hif_dev->regout_submitted);
 	ath9k_hif_usb_dealloc_reg_in_urbs(hif_dev);
@@ -1216,7 +1249,7 @@ err_fw:
 static int send_eject_command(struct usb_interface *interface)
 {
 	struct usb_device *udev = interface_to_usbdev(interface);
-	struct usb_host_interface *iface_desc = &interface->altsetting[0];
+	struct usb_host_interface *iface_desc = interface->cur_altsetting;
 	struct usb_endpoint_descriptor *endpoint;
 	unsigned char *cmd;
 	u8 bulk_out_ep;
@@ -1341,8 +1374,9 @@ static void ath9k_hif_usb_disconnect(struct usb_interface *interface)
 
 	if (hif_dev->flags & HIF_USB_READY) {
 		ath9k_htc_hw_deinit(hif_dev->htc_handle, unplugged);
-		ath9k_htc_hw_free(hif_dev->htc_handle);
 		ath9k_hif_usb_dev_deinit(hif_dev);
+		ath9k_destoy_wmi(hif_dev->htc_handle->drv_priv);
+		ath9k_htc_hw_free(hif_dev->htc_handle);
 	}
 
 	usb_set_intfdata(interface, NULL);
diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.h b/drivers/net/wireless/ath/ath9k/hif_usb.h
index 7846916aa01d..5985aa15ca93 100644
--- a/drivers/net/wireless/ath/ath9k/hif_usb.h
+++ b/drivers/net/wireless/ath/ath9k/hif_usb.h
@@ -86,6 +86,11 @@ struct tx_buf {
 	struct list_head list;
 };
 
+struct rx_buf {
+	struct sk_buff *skb;
+	struct hif_device_usb *hif_dev;
+};
+
 #define HIF_USB_TX_STOP  BIT(0)
 #define HIF_USB_TX_FLUSH BIT(1)
 
@@ -133,5 +138,6 @@ struct hif_device_usb {
 
 int ath9k_hif_usb_init(void);
 void ath9k_hif_usb_exit(void);
+void ath9k_hif_usb_dealloc_urbs(struct hif_device_usb *hif_dev);
 
 #endif /* HTC_USB_H */
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_init.c b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
index 214c68269a69..27d9fe6799f5 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_init.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
@@ -933,8 +933,9 @@ err_init:
 int ath9k_htc_probe_device(struct htc_target *htc_handle, struct device *dev,
 			   u16 devid, char *product, u32 drv_info)
 {
-	struct ieee80211_hw *hw;
+	struct hif_device_usb *hif_dev;
 	struct ath9k_htc_priv *priv;
+	struct ieee80211_hw *hw;
 	int ret;
 
 	hw = ieee80211_alloc_hw(sizeof(struct ath9k_htc_priv), &ath9k_htc_ops);
@@ -969,7 +970,10 @@ int ath9k_htc_probe_device(struct htc_target *htc_handle, struct device *dev,
 	return 0;
 
 err_init:
-	ath9k_deinit_wmi(priv);
+	ath9k_stop_wmi(priv);
+	hif_dev = (struct hif_device_usb *)htc_handle->hif_dev;
+	ath9k_hif_usb_dealloc_urbs(hif_dev);
+	ath9k_destoy_wmi(priv);
 err_free:
 	ieee80211_free_hw(hw);
 	return ret;
@@ -984,7 +988,7 @@ void ath9k_htc_disconnect_device(struct htc_target *htc_handle, bool hotunplug)
 			htc_handle->drv_priv->ah->ah_flags |= AH_UNPLUGGED;
 
 		ath9k_deinit_device(htc_handle->drv_priv);
-		ath9k_deinit_wmi(htc_handle->drv_priv);
+		ath9k_stop_wmi(htc_handle->drv_priv);
 		ieee80211_free_hw(htc_handle->drv_priv->hw);
 	}
 }
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
index 4e8e80ac8341..118e5550b10c 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
@@ -973,6 +973,8 @@ static bool ath9k_rx_prepare(struct ath9k_htc_priv *priv,
 	struct ath_htc_rx_status *rxstatus;
 	struct ath_rx_status rx_stats;
 	bool decrypt_error = false;
+	__be16 rs_datalen;
+	bool is_phyerr;
 
 	if (skb->len < HTC_RX_FRAME_HEADER_SIZE) {
 		ath_err(common, "Corrupted RX frame, dropping (len: %d)\n",
@@ -982,11 +984,24 @@ static bool ath9k_rx_prepare(struct ath9k_htc_priv *priv,
 
 	rxstatus = (struct ath_htc_rx_status *)skb->data;
 
-	if (be16_to_cpu(rxstatus->rs_datalen) -
-	    (skb->len - HTC_RX_FRAME_HEADER_SIZE) != 0) {
+	rs_datalen = be16_to_cpu(rxstatus->rs_datalen);
+	if (unlikely(rs_datalen -
+	    (skb->len - HTC_RX_FRAME_HEADER_SIZE) != 0)) {
 		ath_err(common,
 			"Corrupted RX data len, dropping (dlen: %d, skblen: %d)\n",
-			rxstatus->rs_datalen, skb->len);
+			rs_datalen, skb->len);
+		goto rx_next;
+	}
+
+	is_phyerr = rxstatus->rs_status & ATH9K_RXERR_PHY;
+	/*
+	 * Discard zero-length packets and packets smaller than an ACK
+	 * which are not PHY_ERROR (short radar pulses have a length of 3)
+	 */
+	if (unlikely(!rs_datalen || (rs_datalen < 10 && !is_phyerr))) {
+		ath_dbg(common, ANY,
+			"Short RX data len, dropping (dlen: %d)\n",
+			rs_datalen);
 		goto rx_next;
 	}
 
@@ -1011,7 +1026,7 @@ static bool ath9k_rx_prepare(struct ath9k_htc_priv *priv,
 	 * Process PHY errors and return so that the packet
 	 * can be dropped.
 	 */
-	if (rx_stats.rs_status & ATH9K_RXERR_PHY) {
+	if (unlikely(is_phyerr)) {
 		/* TODO: Not using DFS processing now. */
 		if (ath_cmn_process_fft(&priv->spec_priv, hdr,
 				    &rx_stats, rx_status->mactime)) {
diff --git a/drivers/net/wireless/ath/ath9k/htc_hst.c b/drivers/net/wireless/ath/ath9k/htc_hst.c
index d091c8ebdcf0..d2e062eaf561 100644
--- a/drivers/net/wireless/ath/ath9k/htc_hst.c
+++ b/drivers/net/wireless/ath/ath9k/htc_hst.c
@@ -113,6 +113,9 @@ static void htc_process_conn_rsp(struct htc_target *target,
 
 	if (svc_rspmsg->status == HTC_SERVICE_SUCCESS) {
 		epid = svc_rspmsg->endpoint_id;
+		if (epid < 0 || epid >= ENDPOINT_MAX)
+			return;
+
 		service_id = be16_to_cpu(svc_rspmsg->service_id);
 		max_msglen = be16_to_cpu(svc_rspmsg->max_msg_len);
 		endpoint = &target->endpoint[epid];
@@ -170,7 +173,6 @@ static int htc_config_pipe_credits(struct htc_target *target)
 	time_left = wait_for_completion_timeout(&target->cmd_wait, HZ);
 	if (!time_left) {
 		dev_err(target->dev, "HTC credit config timeout\n");
-		kfree_skb(skb);
 		return -ETIMEDOUT;
 	}
 
@@ -206,7 +208,6 @@ static int htc_setup_complete(struct htc_target *target)
 	time_left = wait_for_completion_timeout(&target->cmd_wait, HZ);
 	if (!time_left) {
 		dev_err(target->dev, "HTC start timeout\n");
-		kfree_skb(skb);
 		return -ETIMEDOUT;
 	}
 
@@ -279,7 +280,6 @@ int htc_connect_service(struct htc_target *target,
 	if (!time_left) {
 		dev_err(target->dev, "Service connection timeout for: %d\n",
 			service_connreq->service_id);
-		kfree_skb(skb);
 		return -ETIMEDOUT;
 	}
 
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index f23cb2f3d296..ca49cc56efcc 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -1457,6 +1457,9 @@ static int ath9k_config(struct ieee80211_hw *hw, u32 changed)
 		ath_chanctx_set_channel(sc, ctx, &hw->conf.chandef);
 	}
 
+	if (changed & IEEE80211_CONF_CHANGE_POWER)
+		ath9k_set_txpower(sc, NULL);
+
 	mutex_unlock(&sc->mutex);
 	ath9k_ps_restore(sc);
 
diff --git a/drivers/net/wireless/ath/ath9k/wmi.c b/drivers/net/wireless/ath/ath9k/wmi.c
index cdc146091194..e7a3127395be 100644
--- a/drivers/net/wireless/ath/ath9k/wmi.c
+++ b/drivers/net/wireless/ath/ath9k/wmi.c
@@ -112,14 +112,17 @@ struct wmi *ath9k_init_wmi(struct ath9k_htc_priv *priv)
 	return wmi;
 }
 
-void ath9k_deinit_wmi(struct ath9k_htc_priv *priv)
+void ath9k_stop_wmi(struct ath9k_htc_priv *priv)
 {
 	struct wmi *wmi = priv->wmi;
 
 	mutex_lock(&wmi->op_mutex);
 	wmi->stopped = true;
 	mutex_unlock(&wmi->op_mutex);
+}
 
+void ath9k_destoy_wmi(struct ath9k_htc_priv *priv)
+{
 	kfree(priv->wmi);
 }
 
@@ -336,7 +339,6 @@ int ath9k_wmi_cmd(struct wmi *wmi, enum wmi_cmd_id cmd_id,
 		ath_dbg(common, WMI, "Timeout waiting for WMI command: %s\n",
 			wmi_cmd_to_name(cmd_id));
 		mutex_unlock(&wmi->op_mutex);
-		kfree_skb(skb);
 		return -ETIMEDOUT;
 	}
 
diff --git a/drivers/net/wireless/ath/ath9k/wmi.h b/drivers/net/wireless/ath/ath9k/wmi.h
index 380175d5ecd7..d8b912206232 100644
--- a/drivers/net/wireless/ath/ath9k/wmi.h
+++ b/drivers/net/wireless/ath/ath9k/wmi.h
@@ -179,7 +179,6 @@ struct wmi {
 };
 
 struct wmi *ath9k_init_wmi(struct ath9k_htc_priv *priv);
-void ath9k_deinit_wmi(struct ath9k_htc_priv *priv);
 int ath9k_wmi_connect(struct htc_target *htc, struct wmi *wmi,
 		      enum htc_endpoint_id *wmi_ctrl_epid);
 int ath9k_wmi_cmd(struct wmi *wmi, enum wmi_cmd_id cmd_id,
@@ -189,6 +188,8 @@ int ath9k_wmi_cmd(struct wmi *wmi, enum wmi_cmd_id cmd_id,
 void ath9k_wmi_event_tasklet(unsigned long data);
 void ath9k_fatal_work(struct work_struct *work);
 void ath9k_wmi_event_drain(struct ath9k_htc_priv *priv);
+void ath9k_stop_wmi(struct ath9k_htc_priv *priv);
+void ath9k_destoy_wmi(struct ath9k_htc_priv *priv);
 
 #define WMI_CMD(_wmi_cmd)						\
 	do {								\
diff --git a/drivers/net/wireless/ath/carl9170/fw.c b/drivers/net/wireless/ath/carl9170/fw.c
index 51934d191f33..1ab09e1c9ec5 100644
--- a/drivers/net/wireless/ath/carl9170/fw.c
+++ b/drivers/net/wireless/ath/carl9170/fw.c
@@ -338,9 +338,7 @@ static int carl9170_fw(struct ar9170 *ar, const __u8 *data, size_t len)
 		ar->hw->wiphy->interface_modes |= BIT(NL80211_IFTYPE_ADHOC);
 
 		if (SUPP(CARL9170FW_WLANTX_CAB)) {
-			if_comb_types |=
-				BIT(NL80211_IFTYPE_AP) |
-				BIT(NL80211_IFTYPE_P2P_GO);
+			if_comb_types |= BIT(NL80211_IFTYPE_AP);
 
 #ifdef CONFIG_MAC80211_MESH
 			if_comb_types |=
diff --git a/drivers/net/wireless/ath/carl9170/main.c b/drivers/net/wireless/ath/carl9170/main.c
index 7f1bdea742b8..7064e6fc5dbb 100644
--- a/drivers/net/wireless/ath/carl9170/main.c
+++ b/drivers/net/wireless/ath/carl9170/main.c
@@ -582,11 +582,10 @@ static int carl9170_init_interface(struct ar9170 *ar,
 	ar->disable_offload |= ((vif->type != NL80211_IFTYPE_STATION) &&
 	    (vif->type != NL80211_IFTYPE_AP));
 
-	/* While the driver supports HW offload in a single
-	 * P2P client configuration, it doesn't support HW
-	 * offload in the favourit, concurrent P2P GO+CLIENT
-	 * configuration. Hence, HW offload will always be
-	 * disabled for P2P.
+	/* The driver used to have P2P GO+CLIENT support,
+	 * but since this was dropped and we don't know if
+	 * there are any gremlins lurking in the shadows,
+	 * so best we keep HW offload disabled for P2P.
 	 */
 	ar->disable_offload |= vif->p2p;
 
@@ -639,18 +638,6 @@ static int carl9170_op_add_interface(struct ieee80211_hw *hw,
 			if (vif->type == NL80211_IFTYPE_STATION)
 				break;
 
-			/* P2P GO [master] use-case
-			 * Because the P2P GO station is selected dynamically
-			 * by all participating peers of a WIFI Direct network,
-			 * the driver has be able to change the main interface
-			 * operating mode on the fly.
-			 */
-			if (main_vif->p2p && vif->p2p &&
-			    vif->type == NL80211_IFTYPE_AP) {
-				old_main = main_vif;
-				break;
-			}
-
 			err = -EBUSY;
 			rcu_read_unlock();
 
diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c
index 79998a3ddb7a..ad051f34e65b 100644
--- a/drivers/net/wireless/ath/wcn36xx/main.c
+++ b/drivers/net/wireless/ath/wcn36xx/main.c
@@ -1341,7 +1341,7 @@ static int wcn36xx_probe(struct platform_device *pdev)
 	if (addr && ret != ETH_ALEN) {
 		wcn36xx_err("invalid local-mac-address\n");
 		ret = -EINVAL;
-		goto out_wq;
+		goto out_destroy_ept;
 	} else if (addr) {
 		wcn36xx_info("mac address: %pM\n", addr);
 		SET_IEEE80211_PERM_ADDR(wcn->hw, addr);
@@ -1349,7 +1349,7 @@ static int wcn36xx_probe(struct platform_device *pdev)
 
 	ret = wcn36xx_platform_get_resources(wcn, pdev);
 	if (ret)
-		goto out_wq;
+		goto out_destroy_ept;
 
 	wcn36xx_init_ieee80211(wcn);
 	ret = ieee80211_register_hw(wcn->hw);
@@ -1361,6 +1361,8 @@ static int wcn36xx_probe(struct platform_device *pdev)
 out_unmap:
 	iounmap(wcn->ccu_base);
 	iounmap(wcn->dxe_base);
+out_destroy_ept:
+	rpmsg_destroy_ept(wcn->smd_channel);
 out_wq:
 	ieee80211_free_hw(hw);
 out_err:
diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.c b/drivers/net/wireless/ath/wil6210/txrx_edma.c
index f6fce6ff73d9..59e7ec0f6728 100644
--- a/drivers/net/wireless/ath/wil6210/txrx_edma.c
+++ b/drivers/net/wireless/ath/wil6210/txrx_edma.c
@@ -867,6 +867,7 @@ static struct sk_buff *wil_sring_reap_rx_edma(struct wil6210_priv *wil,
 	u8 data_offset;
 	struct wil_rx_status_extended *s;
 	u16 sring_idx = sring - wil->srings;
+	int invalid_buff_id_retry;
 
 	BUILD_BUG_ON(sizeof(struct wil_rx_status_extended) > sizeof(skb->cb));
 
@@ -881,9 +882,9 @@ again:
 	/* Extract the buffer ID from the status message */
 	buff_id = le16_to_cpu(wil_rx_status_get_buff_id(msg));
 
+	invalid_buff_id_retry = 0;
 	while (!buff_id) {
 		struct wil_rx_status_extended *s;
-		int invalid_buff_id_retry = 0;
 
 		wil_dbg_txrx(wil,
 			     "buff_id is not updated yet by HW, (swhead 0x%x)\n",
diff --git a/drivers/net/wireless/broadcom/b43/main.c b/drivers/net/wireless/broadcom/b43/main.c
index 20815a71680b..e483bb7e8486 100644
--- a/drivers/net/wireless/broadcom/b43/main.c
+++ b/drivers/net/wireless/broadcom/b43/main.c
@@ -5574,7 +5574,7 @@ static struct b43_wl *b43_wireless_init(struct b43_bus_dev *dev)
 	/* fill hw info */
 	ieee80211_hw_set(hw, RX_INCLUDES_FCS);
 	ieee80211_hw_set(hw, SIGNAL_DBM);
-
+	ieee80211_hw_set(hw, MFP_CAPABLE);
 	hw->wiphy->interface_modes =
 		BIT(NL80211_IFTYPE_AP) |
 		BIT(NL80211_IFTYPE_MESH_POINT) |
diff --git a/drivers/net/wireless/broadcom/b43legacy/main.c b/drivers/net/wireless/broadcom/b43legacy/main.c
index 4325e91736eb..5208a39fd6f7 100644
--- a/drivers/net/wireless/broadcom/b43legacy/main.c
+++ b/drivers/net/wireless/broadcom/b43legacy/main.c
@@ -1275,8 +1275,9 @@ static void handle_irq_ucode_debug(struct b43legacy_wldev *dev)
 }
 
 /* Interrupt handler bottom-half */
-static void b43legacy_interrupt_tasklet(struct b43legacy_wldev *dev)
+static void b43legacy_interrupt_tasklet(unsigned long data)
 {
+	struct b43legacy_wldev *dev = (struct b43legacy_wldev *)data;
 	u32 reason;
 	u32 dma_reason[ARRAY_SIZE(dev->dma_reason)];
 	u32 merged_dma_reason = 0;
@@ -3741,7 +3742,7 @@ static int b43legacy_one_core_attach(struct ssb_device *dev,
 	b43legacy_set_status(wldev, B43legacy_STAT_UNINIT);
 	wldev->bad_frames_preempt = modparam_bad_frames_preempt;
 	tasklet_init(&wldev->isr_tasklet,
-		     (void (*)(unsigned long))b43legacy_interrupt_tasklet,
+		     b43legacy_interrupt_tasklet,
 		     (unsigned long)wldev);
 	if (modparam_pio)
 		wldev->__using_pio = true;
@@ -3800,6 +3801,7 @@ static int b43legacy_wireless_init(struct ssb_device *dev)
 	/* fill hw info */
 	ieee80211_hw_set(hw, RX_INCLUDES_FCS);
 	ieee80211_hw_set(hw, SIGNAL_DBM);
+	ieee80211_hw_set(hw, MFP_CAPABLE); /* Allow WPA3 in software */
 
 	hw->wiphy->interface_modes =
 		BIT(NL80211_IFTYPE_AP) |
diff --git a/drivers/net/wireless/broadcom/b43legacy/xmit.c b/drivers/net/wireless/broadcom/b43legacy/xmit.c
index e9b23c2e5bd4..efd63f4ce74f 100644
--- a/drivers/net/wireless/broadcom/b43legacy/xmit.c
+++ b/drivers/net/wireless/broadcom/b43legacy/xmit.c
@@ -558,6 +558,7 @@ void b43legacy_rx(struct b43legacy_wldev *dev,
 	default:
 		b43legacywarn(dev->wl, "Unexpected value for chanstat (0x%X)\n",
 		       chanstat);
+		goto drop;
 	}
 
 	memcpy(IEEE80211_SKB_RXCB(skb), &status, sizeof(status));
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c
index 22534bf2a90c..fcaf19165891 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c
@@ -707,8 +707,10 @@ static u32 brcmf_chip_tcm_rambase(struct brcmf_chip_priv *ci)
 	return 0;
 }
 
-static int brcmf_chip_get_raminfo(struct brcmf_chip_priv *ci)
+int brcmf_chip_get_raminfo(struct brcmf_chip *pub)
 {
+	struct brcmf_chip_priv *ci = container_of(pub, struct brcmf_chip_priv,
+						  pub);
 	struct brcmf_core_priv *mem_core;
 	struct brcmf_core *mem;
 
@@ -990,7 +992,7 @@ static int brcmf_chip_recognition(struct brcmf_chip_priv *ci)
 		brcmf_chip_set_passive(&ci->pub);
 	}
 
-	return brcmf_chip_get_raminfo(ci);
+	return brcmf_chip_get_raminfo(&ci->pub);
 }
 
 static void brcmf_chip_disable_arm(struct brcmf_chip_priv *chip, u16 id)
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.h
index 0ae3b33bab62..4794cf38b4d3 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.h
@@ -80,6 +80,7 @@ struct brcmf_buscore_ops {
 	void (*activate)(void *ctx, struct brcmf_chip *chip, u32 rstvec);
 };
 
+int brcmf_chip_get_raminfo(struct brcmf_chip *pub);
 struct brcmf_chip *brcmf_chip_attach(void *ctx,
 				     const struct brcmf_buscore_ops *ops);
 void brcmf_chip_detach(struct brcmf_chip *chip);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
index acca719b3907..15fc1eb3ac63 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
@@ -293,13 +293,14 @@ void brcmf_feat_attach(struct brcmf_pub *drvr)
 	if (!err)
 		ifp->drvr->feat_flags |= BIT(BRCMF_FEAT_SCAN_RANDOM_MAC);
 
+	brcmf_feat_iovar_int_get(ifp, BRCMF_FEAT_FWSUP, "sup_wpa");
+
 	if (drvr->settings->feature_disable) {
 		brcmf_dbg(INFO, "Features: 0x%02x, disable: 0x%02x\n",
 			  ifp->drvr->feat_flags,
 			  drvr->settings->feature_disable);
 		ifp->drvr->feat_flags &= ~drvr->settings->feature_disable;
 	}
-	brcmf_feat_iovar_int_get(ifp, BRCMF_FEAT_FWSUP, "sup_wpa");
 
 	brcmf_feat_firmware_overrides(drvr);
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h
index 39ac1bbb6cc0..7ca7afdd598e 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h
@@ -30,7 +30,7 @@
 #define BRCMF_ARP_OL_PEER_AUTO_REPLY	0x00000008
 
 #define	BRCMF_BSS_INFO_VERSION	109 /* curr ver of brcmf_bss_info_le struct */
-#define BRCMF_BSS_RSSI_ON_CHANNEL	0x0002
+#define BRCMF_BSS_RSSI_ON_CHANNEL	0x0004
 
 #define BRCMF_STA_BRCM			0x00000001	/* Running a Broadcom driver */
 #define BRCMF_STA_WME			0x00000002	/* WMM association */
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
index c22c49ae552e..834ddb34502d 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
@@ -654,6 +654,7 @@ static inline int brcmf_fws_hanger_poppkt(struct brcmf_fws_hanger *h,
 static void brcmf_fws_psq_flush(struct brcmf_fws_info *fws, struct pktq *q,
 				int ifidx)
 {
+	struct brcmf_fws_hanger_item *hi;
 	bool (*matchfn)(struct sk_buff *, void *) = NULL;
 	struct sk_buff *skb;
 	int prec;
@@ -665,6 +666,9 @@ static void brcmf_fws_psq_flush(struct brcmf_fws_info *fws, struct pktq *q,
 		skb = brcmu_pktq_pdeq_match(q, prec, matchfn, &ifidx);
 		while (skb) {
 			hslot = brcmf_skb_htod_tag_get_field(skb, HSLOT);
+			hi = &fws->hanger.items[hslot];
+			WARN_ON(skb != hi->pkt);
+			hi->state = BRCMF_FWS_HANGER_ITEM_STATE_FREE;
 			brcmf_fws_hanger_poppkt(&fws->hanger, hslot, &skb,
 						true);
 			brcmu_pkt_buf_free_skb(skb);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
index 73a0e550f2b2..6e524de3d58c 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c
@@ -2103,7 +2103,8 @@ static struct wireless_dev *brcmf_p2p_create_p2pdev(struct brcmf_p2p_info *p2p,
 	/* firmware requires unique mac address for p2pdev interface */
 	if (addr && ether_addr_equal(addr, pri_ifp->mac_addr)) {
 		bphy_err(drvr, "discovery vif must be different from primary interface\n");
-		return ERR_PTR(-EINVAL);
+		err = -EINVAL;
+		goto fail;
 	}
 
 	brcmf_p2p_generate_bss_mac(p2p, addr);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
index 921349a0a6ab..1ec2e91e1b2b 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
@@ -1781,6 +1781,12 @@ static void brcmf_pcie_setup(struct device *dev, int ret,
 	nvram_len = fwreq->items[BRCMF_PCIE_FW_NVRAM].nv_data.len;
 	kfree(fwreq);
 
+	ret = brcmf_chip_get_raminfo(devinfo->ci);
+	if (ret) {
+		brcmf_err(bus, "Failed to get RAM info\n");
+		goto fail;
+	}
+
 	/* Some of the firmwares have the size of the memory of the device
 	 * defined inside the firmware. This is because part of the memory in
 	 * the device is shared and the devision is determined by FW. Parse
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
index 9a51f1ba87c3..868560c10544 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
@@ -1945,7 +1945,10 @@ static uint brcmf_sdio_readframes(struct brcmf_sdio *bus, uint maxframes)
 			if (brcmf_sdio_hdparse(bus, bus->rxhdr, &rd_new,
 					       BRCMF_SDIO_FT_NORMAL)) {
 				rd->len = 0;
+				brcmf_sdio_rxfail(bus, true, true);
+				sdio_release_host(bus->sdiodev->func1);
 				brcmu_pkt_buf_free_skb(pkt);
+				continue;
 			}
 			bus->sdcnt.rx_readahead_cnt++;
 			if (rd->len != roundup(rd_new.len, 16)) {
@@ -3693,7 +3696,11 @@ static void brcmf_sdio_bus_watchdog(struct brcmf_sdio *bus)
 			if (bus->idlecount > bus->idletime) {
 				brcmf_dbg(SDIO, "idle\n");
 				sdio_claim_host(bus->sdiodev->func1);
-				brcmf_sdio_wd_timer(bus, false);
+#ifdef DEBUG
+				if (!BRCMF_FWCON_ON() ||
+				    bus->console_interval == 0)
+#endif
+					brcmf_sdio_wd_timer(bus, false);
 				bus->idlecount = 0;
 				brcmf_sdio_bus_sleep(bus, true, false);
 				sdio_release_host(bus->sdiodev->func1);
@@ -4236,6 +4243,12 @@ static void brcmf_sdio_firmware_callback(struct device *dev, int err,
 	}
 
 	if (err == 0) {
+		/* Assign bus interface call back */
+		sdiod->bus_if->dev = sdiod->dev;
+		sdiod->bus_if->ops = &brcmf_sdio_bus_ops;
+		sdiod->bus_if->chip = bus->ci->chip;
+		sdiod->bus_if->chiprev = bus->ci->chiprev;
+
 		/* Allow full data communication using DPC from now on. */
 		brcmf_sdiod_change_state(bus->sdiodev, BRCMF_SDIOD_DATA);
 
@@ -4252,12 +4265,6 @@ static void brcmf_sdio_firmware_callback(struct device *dev, int err,
 
 	sdio_release_host(sdiod->func1);
 
-	/* Assign bus interface call back */
-	sdiod->bus_if->dev = sdiod->dev;
-	sdiod->bus_if->ops = &brcmf_sdio_bus_ops;
-	sdiod->bus_if->chip = bus->ci->chip;
-	sdiod->bus_if->chiprev = bus->ci->chiprev;
-
 	/* Attach to the common layer, reserve hdr space */
 	err = brcmf_attach(sdiod->dev, sdiod->settings);
 	if (err != 0) {
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
index 75fcd6752edc..205d46e2117a 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
@@ -441,6 +441,7 @@ fail:
 			usb_free_urb(req->urb);
 		list_del(q->next);
 	}
+	kfree(reqs);
 	return NULL;
 
 }
@@ -1350,7 +1351,7 @@ brcmf_usb_probe(struct usb_interface *intf, const struct usb_device_id *id)
 		goto fail;
 	}
 
-	desc = &intf->altsetting[0].desc;
+	desc = &intf->cur_altsetting->desc;
 	if ((desc->bInterfaceClass != USB_CLASS_VENDOR_SPEC) ||
 	    (desc->bInterfaceSubClass != 2) ||
 	    (desc->bInterfaceProtocol != 0xff)) {
@@ -1363,7 +1364,7 @@ brcmf_usb_probe(struct usb_interface *intf, const struct usb_device_id *id)
 
 	num_of_eps = desc->bNumEndpoints;
 	for (ep = 0; ep < num_of_eps; ep++) {
-		endpoint = &intf->altsetting[0].endpoint[ep].desc;
+		endpoint = &intf->cur_altsetting->endpoint[ep].desc;
 		endpoint_num = usb_endpoint_num(endpoint);
 		if (!usb_endpoint_xfer_bulk(endpoint))
 			continue;
diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c
index 3f5a14112c6b..bd6ec4f5bcd8 100644
--- a/drivers/net/wireless/cisco/airo.c
+++ b/drivers/net/wireless/cisco/airo.c
@@ -1928,6 +1928,10 @@ static netdev_tx_t mpi_start_xmit(struct sk_buff *skb,
 		airo_print_err(dev->name, "%s: skb == NULL!",__func__);
 		return NETDEV_TX_OK;
 	}
+	if (skb_padto(skb, ETH_ZLEN)) {
+		dev->stats.tx_dropped++;
+		return NETDEV_TX_OK;
+	}
 	npacks = skb_queue_len (&ai->txq);
 
 	if (npacks >= MAXTXQ - 1) {
@@ -2130,6 +2134,10 @@ static netdev_tx_t airo_start_xmit(struct sk_buff *skb,
 		airo_print_err(dev->name, "%s: skb == NULL!", __func__);
 		return NETDEV_TX_OK;
 	}
+	if (skb_padto(skb, ETH_ZLEN)) {
+		dev->stats.tx_dropped++;
+		return NETDEV_TX_OK;
+	}
 
 	/* Find a vacant FID */
 	for( i = 0; i < MAX_FIDS / 2 && (fids[i] & 0xffff0000); i++ );
@@ -2204,6 +2212,10 @@ static netdev_tx_t airo_start_xmit11(struct sk_buff *skb,
 		airo_print_err(dev->name, "%s: skb == NULL!", __func__);
 		return NETDEV_TX_OK;
 	}
+	if (skb_padto(skb, ETH_ZLEN)) {
+		dev->stats.tx_dropped++;
+		return NETDEV_TX_OK;
+	}
 
 	/* Find a vacant FID */
 	for( i = MAX_FIDS / 2; i < MAX_FIDS && (fids[i] & 0xffff0000); i++ );
@@ -7786,16 +7798,8 @@ static int readrids(struct net_device *dev, aironet_ioctl *comp) {
 	case AIROGVLIST:    ridcode = RID_APLIST;       break;
 	case AIROGDRVNAM:   ridcode = RID_DRVNAME;      break;
 	case AIROGEHTENC:   ridcode = RID_ETHERENCAP;   break;
-	case AIROGWEPKTMP:  ridcode = RID_WEP_TEMP;
-		/* Only super-user can read WEP keys */
-		if (!capable(CAP_NET_ADMIN))
-			return -EPERM;
-		break;
-	case AIROGWEPKNV:   ridcode = RID_WEP_PERM;
-		/* Only super-user can read WEP keys */
-		if (!capable(CAP_NET_ADMIN))
-			return -EPERM;
-		break;
+	case AIROGWEPKTMP:  ridcode = RID_WEP_TEMP;	break;
+	case AIROGWEPKNV:   ridcode = RID_WEP_PERM;	break;
 	case AIROGSTAT:     ridcode = RID_STATUS;       break;
 	case AIROGSTATSD32: ridcode = RID_STATSDELTA;   break;
 	case AIROGSTATSC32: ridcode = RID_STATS;        break;
@@ -7809,7 +7813,13 @@ static int readrids(struct net_device *dev, aironet_ioctl *comp) {
 		return -EINVAL;
 	}
 
-	if ((iobuf = kmalloc(RIDSIZE, GFP_KERNEL)) == NULL)
+	if (ridcode == RID_WEP_TEMP || ridcode == RID_WEP_PERM) {
+		/* Only super-user can read WEP keys */
+		if (!capable(CAP_NET_ADMIN))
+			return -EPERM;
+	}
+
+	if ((iobuf = kzalloc(RIDSIZE, GFP_KERNEL)) == NULL)
 		return -ENOMEM;
 
 	PC4500_readrid(ai,ridcode,iobuf,RIDSIZE, 1);
diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2100.c b/drivers/net/wireless/intel/ipw2x00/ipw2100.c
index 75c0c29d81f0..4f62febc4713 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2100.c
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2100.c
@@ -3206,8 +3206,9 @@ static void ipw2100_tx_send_data(struct ipw2100_priv *priv)
 	}
 }
 
-static void ipw2100_irq_tasklet(struct ipw2100_priv *priv)
+static void ipw2100_irq_tasklet(unsigned long data)
 {
+	struct ipw2100_priv *priv = (struct ipw2100_priv *)data;
 	struct net_device *dev = priv->net_dev;
 	unsigned long flags;
 	u32 inta, tmp;
@@ -6007,7 +6008,7 @@ static void ipw2100_rf_kill(struct work_struct *work)
 	spin_unlock_irqrestore(&priv->low_lock, flags);
 }
 
-static void ipw2100_irq_tasklet(struct ipw2100_priv *priv);
+static void ipw2100_irq_tasklet(unsigned long data);
 
 static const struct net_device_ops ipw2100_netdev_ops = {
 	.ndo_open		= ipw2100_open,
@@ -6137,7 +6138,7 @@ static struct net_device *ipw2100_alloc_device(struct pci_dev *pci_dev,
 	INIT_DELAYED_WORK(&priv->rf_kill, ipw2100_rf_kill);
 	INIT_DELAYED_WORK(&priv->scan_event, ipw2100_scan_event);
 
-	tasklet_init(&priv->irq_tasklet, (void (*)(unsigned long))
+	tasklet_init(&priv->irq_tasklet,
 		     ipw2100_irq_tasklet, (unsigned long)priv);
 
 	/* NOTE:  We do not start the deferred work for status checks yet */
diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2200.c b/drivers/net/wireless/intel/ipw2x00/ipw2200.c
index fa55d2ccbfab..21a6b600d7eb 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2200.c
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2200.c
@@ -1945,8 +1945,9 @@ static void notify_wx_assoc_event(struct ipw_priv *priv)
 	wireless_send_event(priv->net_dev, SIOCGIWAP, &wrqu, NULL);
 }
 
-static void ipw_irq_tasklet(struct ipw_priv *priv)
+static void ipw_irq_tasklet(unsigned long data)
 {
+	struct ipw_priv *priv = (struct ipw_priv *)data;
 	u32 inta, inta_mask, handled = 0;
 	unsigned long flags;
 	int rc = 0;
@@ -10680,7 +10681,7 @@ static int ipw_setup_deferred_work(struct ipw_priv *priv)
 	INIT_WORK(&priv->qos_activate, ipw_bg_qos_activate);
 #endif				/* CONFIG_IPW2200_QOS */
 
-	tasklet_init(&priv->irq_tasklet, (void (*)(unsigned long))
+	tasklet_init(&priv->irq_tasklet,
 		     ipw_irq_tasklet, (unsigned long)priv);
 
 	return ret;
diff --git a/drivers/net/wireless/intel/iwlegacy/3945-mac.c b/drivers/net/wireless/intel/iwlegacy/3945-mac.c
index b82da75a9ae3..ceb7f8376b75 100644
--- a/drivers/net/wireless/intel/iwlegacy/3945-mac.c
+++ b/drivers/net/wireless/intel/iwlegacy/3945-mac.c
@@ -1377,8 +1377,9 @@ il3945_dump_nic_error_log(struct il_priv *il)
 }
 
 static void
-il3945_irq_tasklet(struct il_priv *il)
+il3945_irq_tasklet(unsigned long data)
 {
+	struct il_priv *il = (struct il_priv *)data;
 	u32 inta, handled = 0;
 	u32 inta_fh;
 	unsigned long flags;
@@ -3404,7 +3405,7 @@ il3945_setup_deferred_work(struct il_priv *il)
 	timer_setup(&il->watchdog, il_bg_watchdog, 0);
 
 	tasklet_init(&il->irq_tasklet,
-		     (void (*)(unsigned long))il3945_irq_tasklet,
+		     il3945_irq_tasklet,
 		     (unsigned long)il);
 }
 
diff --git a/drivers/net/wireless/intel/iwlegacy/3945-rs.c b/drivers/net/wireless/intel/iwlegacy/3945-rs.c
index 5bd8a9ee8b1e..602f3b3e6c47 100644
--- a/drivers/net/wireless/intel/iwlegacy/3945-rs.c
+++ b/drivers/net/wireless/intel/iwlegacy/3945-rs.c
@@ -374,7 +374,7 @@ out:
 }
 
 static void *
-il3945_rs_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir)
+il3945_rs_alloc(struct ieee80211_hw *hw)
 {
 	return hw->priv;
 }
diff --git a/drivers/net/wireless/intel/iwlegacy/4965-mac.c b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
index fa2c02881939..8a988c1d347b 100644
--- a/drivers/net/wireless/intel/iwlegacy/4965-mac.c
+++ b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
@@ -4345,8 +4345,9 @@ il4965_synchronize_irq(struct il_priv *il)
 }
 
 static void
-il4965_irq_tasklet(struct il_priv *il)
+il4965_irq_tasklet(unsigned long data)
 {
+	struct il_priv *il = (struct il_priv *)data;
 	u32 inta, handled = 0;
 	u32 inta_fh;
 	unsigned long flags;
@@ -6239,7 +6240,7 @@ il4965_setup_deferred_work(struct il_priv *il)
 	timer_setup(&il->watchdog, il_bg_watchdog, 0);
 
 	tasklet_init(&il->irq_tasklet,
-		     (void (*)(unsigned long))il4965_irq_tasklet,
+		     il4965_irq_tasklet,
 		     (unsigned long)il);
 }
 
diff --git a/drivers/net/wireless/intel/iwlegacy/4965-rs.c b/drivers/net/wireless/intel/iwlegacy/4965-rs.c
index a824a10a43b6..ba3069bce935 100644
--- a/drivers/net/wireless/intel/iwlegacy/4965-rs.c
+++ b/drivers/net/wireless/intel/iwlegacy/4965-rs.c
@@ -2478,7 +2478,7 @@ il4965_rs_fill_link_cmd(struct il_priv *il, struct il_lq_sta *lq_sta,
 }
 
 static void *
-il4965_rs_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir)
+il4965_rs_alloc(struct ieee80211_hw *hw)
 {
 	return hw->priv;
 }
diff --git a/drivers/net/wireless/intel/iwlegacy/common.c b/drivers/net/wireless/intel/iwlegacy/common.c
index 4a88e35d58d7..ba005a13b923 100644
--- a/drivers/net/wireless/intel/iwlegacy/common.c
+++ b/drivers/net/wireless/intel/iwlegacy/common.c
@@ -699,7 +699,7 @@ il_eeprom_init(struct il_priv *il)
 	u32 gp = _il_rd(il, CSR_EEPROM_GP);
 	int sz;
 	int ret;
-	u16 addr;
+	int addr;
 
 	/* allocate eeprom */
 	sz = il->cfg->eeprom_size;
@@ -4286,8 +4286,8 @@ il_apm_init(struct il_priv *il)
 	 *    power savings, even without L1.
 	 */
 	if (il->cfg->set_l0s) {
-		pcie_capability_read_word(il->pci_dev, PCI_EXP_LNKCTL, &lctl);
-		if (lctl & PCI_EXP_LNKCTL_ASPM_L1) {
+		ret = pcie_capability_read_word(il->pci_dev, PCI_EXP_LNKCTL, &lctl);
+		if (!ret && (lctl & PCI_EXP_LNKCTL_ASPM_L1)) {
 			/* L1-ASPM enabled; disable(!) L0S  */
 			il_set_bit(il, CSR_GIO_REG,
 				   CSR_GIO_REG_VAL_L0S_ENABLED);
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/rs.c b/drivers/net/wireless/intel/iwlwifi/dvm/rs.c
index b500c9279a32..2ac498d2852c 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/rs.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/rs.c
@@ -3023,7 +3023,7 @@ static void rs_fill_link_cmd(struct iwl_priv *priv,
 			cpu_to_le16(priv->lib->bt_params->agg_time_limit);
 }
 
-static void *rs_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir)
+static void *rs_alloc(struct ieee80211_hw *hw)
 {
 	return hw->priv;
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/txq.h b/drivers/net/wireless/intel/iwlwifi/fw/api/txq.h
index 73196cbc7fbe..75d958bab0e3 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/txq.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/txq.h
@@ -8,7 +8,7 @@
  * Copyright(c) 2007 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2019 Intel Corporation
+ * Copyright(c) 2019 - 2020 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -31,7 +31,7 @@
  * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2019 Intel Corporation
+ * Copyright(c) 2019 - 2020 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -99,7 +99,7 @@ enum iwl_mvm_dqa_txq {
 	IWL_MVM_DQA_MAX_MGMT_QUEUE = 8,
 	IWL_MVM_DQA_AP_PROBE_RESP_QUEUE = 9,
 	IWL_MVM_DQA_MIN_DATA_QUEUE = 10,
-	IWL_MVM_DQA_MAX_DATA_QUEUE = 31,
+	IWL_MVM_DQA_MAX_DATA_QUEUE = 30,
 };
 
 enum iwl_mvm_tx_fifo {
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index be9778757755..f7c636d0b343 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -8,7 +8,7 @@
  * Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2018 - 2020 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -31,7 +31,7 @@
  * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2018 - 2020 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -1377,11 +1377,7 @@ static int iwl_dump_ini_rxf_iter(struct iwl_fw_runtime *fwrt,
 		goto out;
 	}
 
-	/*
-	 * region register have absolute value so apply rxf offset after
-	 * reading the registers
-	 */
-	offs += rxf_data.offset;
+	offs = rxf_data.offset;
 
 	/* Lock fence */
 	iwl_write_prph_no_grab(fwrt->trans, RXF_SET_FENCE_MODE + offs, 0x1);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index d87a6bb3e456..6fceae1fa14e 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -225,6 +225,34 @@ enum iwl_nvm_channel_flags {
 	NVM_CHANNEL_DC_HIGH		= BIT(12),
 };
 
+/**
+ * enum iwl_reg_capa_flags - global flags applied for the whole regulatory
+ * domain.
+ * @REG_CAPA_BF_CCD_LOW_BAND: Beam-forming or Cyclic Delay Diversity in the
+ *	2.4Ghz band is allowed.
+ * @REG_CAPA_BF_CCD_HIGH_BAND: Beam-forming or Cyclic Delay Diversity in the
+ *	5Ghz band is allowed.
+ * @REG_CAPA_160MHZ_ALLOWED: 11ac channel with a width of 160Mhz is allowed
+ *	for this regulatory domain (valid only in 5Ghz).
+ * @REG_CAPA_80MHZ_ALLOWED: 11ac channel with a width of 80Mhz is allowed
+ *	for this regulatory domain (valid only in 5Ghz).
+ * @REG_CAPA_MCS_8_ALLOWED: 11ac with MCS 8 is allowed.
+ * @REG_CAPA_MCS_9_ALLOWED: 11ac with MCS 9 is allowed.
+ * @REG_CAPA_40MHZ_FORBIDDEN: 11n channel with a width of 40Mhz is forbidden
+ *	for this regulatory domain (valid only in 5Ghz).
+ * @REG_CAPA_DC_HIGH_ENABLED: DC HIGH allowed.
+ */
+enum iwl_reg_capa_flags {
+	REG_CAPA_BF_CCD_LOW_BAND	= BIT(0),
+	REG_CAPA_BF_CCD_HIGH_BAND	= BIT(1),
+	REG_CAPA_160MHZ_ALLOWED		= BIT(2),
+	REG_CAPA_80MHZ_ALLOWED		= BIT(3),
+	REG_CAPA_MCS_8_ALLOWED		= BIT(4),
+	REG_CAPA_MCS_9_ALLOWED		= BIT(5),
+	REG_CAPA_40MHZ_FORBIDDEN	= BIT(7),
+	REG_CAPA_DC_HIGH_ENABLED	= BIT(9),
+};
+
 static inline void iwl_nvm_print_channel_flags(struct device *dev, u32 level,
 					       int chan, u32 flags)
 {
@@ -496,8 +524,7 @@ static struct ieee80211_sband_iftype_data iwl_he_capa[] = {
 					IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US |
 					IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8,
 				.mac_cap_info[2] =
-					IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP |
-					IEEE80211_HE_MAC_CAP2_ACK_EN,
+					IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP,
 				.mac_cap_info[3] =
 					IEEE80211_HE_MAC_CAP3_OMI_CONTROL |
 					IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_2,
@@ -581,8 +608,7 @@ static struct ieee80211_sband_iftype_data iwl_he_capa[] = {
 					IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US |
 					IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8,
 				.mac_cap_info[2] =
-					IEEE80211_HE_MAC_CAP2_BSR |
-					IEEE80211_HE_MAC_CAP2_ACK_EN,
+					IEEE80211_HE_MAC_CAP2_BSR,
 				.mac_cap_info[3] =
 					IEEE80211_HE_MAC_CAP3_OMI_CONTROL |
 					IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_2,
@@ -1025,6 +1051,7 @@ IWL_EXPORT_SYMBOL(iwl_parse_nvm_data);
 
 static u32 iwl_nvm_get_regdom_bw_flags(const u16 *nvm_chan,
 				       int ch_idx, u16 nvm_flags,
+				       u16 cap_flags,
 				       const struct iwl_cfg *cfg)
 {
 	u32 flags = NL80211_RRF_NO_HT40;
@@ -1063,6 +1090,20 @@ static u32 iwl_nvm_get_regdom_bw_flags(const u16 *nvm_chan,
 	    (flags & NL80211_RRF_NO_IR))
 		flags |= NL80211_RRF_GO_CONCURRENT;
 
+	/*
+	 * cap_flags is per regulatory domain so apply it for every channel
+	 */
+	if (ch_idx >= NUM_2GHZ_CHANNELS) {
+		if (cap_flags & REG_CAPA_40MHZ_FORBIDDEN)
+			flags |= NL80211_RRF_NO_HT40;
+
+		if (!(cap_flags & REG_CAPA_80MHZ_ALLOWED))
+			flags |= NL80211_RRF_NO_80MHZ;
+
+		if (!(cap_flags & REG_CAPA_160MHZ_ALLOWED))
+			flags |= NL80211_RRF_NO_160MHZ;
+	}
+
 	return flags;
 }
 
@@ -1074,7 +1115,7 @@ struct regdb_ptrs {
 struct ieee80211_regdomain *
 iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
 		       int num_of_ch, __le32 *channels, u16 fw_mcc,
-		       u16 geo_info)
+		       u16 geo_info, u16 cap)
 {
 	int ch_idx;
 	u16 ch_flags;
@@ -1139,7 +1180,8 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
 		}
 
 		reg_rule_flags = iwl_nvm_get_regdom_bw_flags(nvm_chan, ch_idx,
-							     ch_flags, cfg);
+							     ch_flags, cap,
+							     cfg);
 
 		/* we can't continue the same rule */
 		if (ch_idx == 0 || prev_reg_rule_flags != reg_rule_flags ||
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
index b7e1ddf8f177..4eeedb41e9ac 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
@@ -7,7 +7,7 @@
  *
  * Copyright(c) 2008 - 2015 Intel Corporation. All rights reserved.
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018        Intel Corporation
+ * Copyright(c) 2018 - 2019 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -29,7 +29,7 @@
  *
  * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018        Intel Corporation
+ * Copyright(c) 2018 - 2019 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -103,7 +103,7 @@ iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 struct ieee80211_regdomain *
 iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
 		       int num_of_ch, __le32 *channels, u16 fw_mcc,
-		       u16 geo_info);
+		       u16 geo_info, u16 cap);
 
 /**
  * struct iwl_nvm_section - describes an NVM section in memory.
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h b/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h
index cbd1a8eed620..f37d6fee0225 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h
@@ -8,7 +8,7 @@
  * Copyright(c) 2007 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
  * Copyright(c) 2015        Intel Deutschland GmbH
- * Copyright(c) 2018 Intel Corporation
+ * Copyright(c) 2018 - 2019 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -31,7 +31,7 @@
  * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
  * Copyright(c) 2015        Intel Deutschland GmbH
- * Copyright(c) 2018 Intel Corporation
+ * Copyright(c) 2018 - 2019 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
index e7e68fb2bd29..a6feb6ecc191 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
@@ -736,40 +736,16 @@ iwl_mvm_get_wowlan_config(struct iwl_mvm *mvm,
 	return 0;
 }
 
-static void
-iwl_mvm_iter_d0i3_ap_keys(struct iwl_mvm *mvm,
-			  struct ieee80211_vif *vif,
-			  void (*iter)(struct ieee80211_hw *hw,
-				       struct ieee80211_vif *vif,
-				       struct ieee80211_sta *sta,
-				       struct ieee80211_key_conf *key,
-				       void *data),
-			  void *data)
-{
-	struct ieee80211_sta *ap_sta;
-
-	rcu_read_lock();
-
-	ap_sta = rcu_dereference(mvm->fw_id_to_mac_id[mvm->d0i3_ap_sta_id]);
-	if (IS_ERR_OR_NULL(ap_sta))
-		goto out;
-
-	ieee80211_iter_keys_rcu(mvm->hw, vif, iter, data);
-out:
-	rcu_read_unlock();
-}
-
-int iwl_mvm_wowlan_config_key_params(struct iwl_mvm *mvm,
-				     struct ieee80211_vif *vif,
-				     bool d0i3,
-				     u32 cmd_flags)
+static int iwl_mvm_wowlan_config_key_params(struct iwl_mvm *mvm,
+					    struct ieee80211_vif *vif,
+					    u32 cmd_flags)
 {
 	struct iwl_wowlan_kek_kck_material_cmd kek_kck_cmd = {};
 	struct iwl_wowlan_tkip_params_cmd tkip_cmd = {};
 	bool unified = fw_has_capa(&mvm->fw->ucode_capa,
 				   IWL_UCODE_TLV_CAPA_CNSLDTD_D3_D0_IMG);
 	struct wowlan_key_data key_data = {
-		.configure_keys = !d0i3 && !unified,
+		.configure_keys = !unified,
 		.use_rsc_tsc = false,
 		.tkip = &tkip_cmd,
 		.use_tkip = false,
@@ -785,25 +761,16 @@ int iwl_mvm_wowlan_config_key_params(struct iwl_mvm *mvm,
 	 * if we have to configure keys, call ieee80211_iter_keys(),
 	 * as we need non-atomic context in order to take the
 	 * required locks.
-	 * for the d0i3 we can't use ieee80211_iter_keys(), as
-	 * taking (almost) any mutex might result in deadlock.
 	 */
-	if (!d0i3) {
-		/*
-		 * Note that currently we don't propagate cmd_flags
-		 * to the iterator. In case of key_data.configure_keys,
-		 * all the configured commands are SYNC, and
-		 * iwl_mvm_wowlan_program_keys() will take care of
-		 * locking/unlocking mvm->mutex.
-		 */
-		ieee80211_iter_keys(mvm->hw, vif,
-				    iwl_mvm_wowlan_program_keys,
-				    &key_data);
-	} else {
-		iwl_mvm_iter_d0i3_ap_keys(mvm, vif,
-					  iwl_mvm_wowlan_program_keys,
-					  &key_data);
-	}
+	/*
+	 * Note that currently we don't propagate cmd_flags
+	 * to the iterator. In case of key_data.configure_keys,
+	 * all the configured commands are SYNC, and
+	 * iwl_mvm_wowlan_program_keys() will take care of
+	 * locking/unlocking mvm->mutex.
+	 */
+	ieee80211_iter_keys(mvm->hw, vif, iwl_mvm_wowlan_program_keys,
+			    &key_data);
 
 	if (key_data.error) {
 		ret = -EIO;
@@ -831,7 +798,7 @@ int iwl_mvm_wowlan_config_key_params(struct iwl_mvm *mvm,
 	}
 
 	/* configure rekey data only if offloaded rekey is supported (d3) */
-	if (mvmvif->rekey_data.valid && !d0i3) {
+	if (mvmvif->rekey_data.valid) {
 		memset(&kek_kck_cmd, 0, sizeof(kek_kck_cmd));
 		memcpy(kek_kck_cmd.kck, mvmvif->rekey_data.kck,
 		       NL80211_KCK_LEN);
@@ -882,8 +849,7 @@ iwl_mvm_wowlan_config(struct iwl_mvm *mvm,
 		 * that isn't really a problem though.
 		 */
 		mutex_unlock(&mvm->mutex);
-		ret = iwl_mvm_wowlan_config_key_params(mvm, vif, false,
-						       CMD_ASYNC);
+		ret = iwl_mvm_wowlan_config_key_params(mvm, vif, CMD_ASYNC);
 		mutex_lock(&mvm->mutex);
 		if (ret)
 			return ret;
@@ -1106,7 +1072,6 @@ static int __iwl_mvm_suspend(struct ieee80211_hw *hw,
 		iwl_mvm_free_nd(mvm);
 
 		if (!unified_image) {
-			iwl_mvm_ref(mvm, IWL_MVM_REF_UCODE_DOWN);
 			if (mvm->fw_restart > 0) {
 				mvm->fw_restart--;
 				ieee80211_restart_hw(mvm->hw);
@@ -1119,37 +1084,12 @@ static int __iwl_mvm_suspend(struct ieee80211_hw *hw,
 	return ret;
 }
 
-static int iwl_mvm_enter_d0i3_sync(struct iwl_mvm *mvm)
-{
-	struct iwl_notification_wait wait_d3;
-	static const u16 d3_notif[] = { D3_CONFIG_CMD };
-	int ret;
-
-	iwl_init_notification_wait(&mvm->notif_wait, &wait_d3,
-				   d3_notif, ARRAY_SIZE(d3_notif),
-				   NULL, NULL);
-
-	ret = iwl_mvm_enter_d0i3(mvm->hw->priv);
-	if (ret)
-		goto remove_notif;
-
-	ret = iwl_wait_notification(&mvm->notif_wait, &wait_d3, HZ);
-	WARN_ON_ONCE(ret);
-	return ret;
-
-remove_notif:
-	iwl_remove_notification(&mvm->notif_wait, &wait_d3);
-	return ret;
-}
-
 int iwl_mvm_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 	struct iwl_trans *trans = mvm->trans;
 	int ret;
 
-	/* make sure the d0i3 exit work is not pending */
-	flush_work(&mvm->d0i3_exit_work);
 	iwl_mvm_pause_tcm(mvm, true);
 
 	iwl_fw_runtime_suspend(&mvm->fwrt);
@@ -1158,25 +1098,6 @@ int iwl_mvm_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
 	if (ret)
 		return ret;
 
-	if (wowlan->any) {
-		trans->system_pm_mode = IWL_PLAT_PM_MODE_D0I3;
-
-		if (iwl_mvm_enter_d0i3_on_suspend(mvm)) {
-			ret = iwl_mvm_enter_d0i3_sync(mvm);
-
-			if (ret)
-				return ret;
-		}
-
-		mutex_lock(&mvm->d0i3_suspend_mutex);
-		__set_bit(D0I3_DEFER_WAKEUP, &mvm->d0i3_suspend_flags);
-		mutex_unlock(&mvm->d0i3_suspend_mutex);
-
-		iwl_trans_d3_suspend(trans, false, false);
-
-		return 0;
-	}
-
 	trans->system_pm_mode = IWL_PLAT_PM_MODE_D3;
 
 	return __iwl_mvm_suspend(hw, wowlan, false);
@@ -1752,30 +1673,6 @@ out_unlock:
 	return false;
 }
 
-void iwl_mvm_d0i3_update_keys(struct iwl_mvm *mvm,
-			      struct ieee80211_vif *vif,
-			      struct iwl_wowlan_status *status)
-{
-	struct iwl_mvm_d3_gtk_iter_data gtkdata = {
-		.mvm = mvm,
-		.status = status,
-	};
-
-	/*
-	 * rekey handling requires taking locks that can't be taken now.
-	 * however, d0i3 doesn't offload rekey, so we're fine.
-	 */
-	if (WARN_ON_ONCE(status->num_of_gtk_rekeys))
-		return;
-
-	/* find last GTK that we used initially, if any */
-	gtkdata.find_phase = true;
-	iwl_mvm_iter_d0i3_ap_keys(mvm, vif, iwl_mvm_d3_update_keys, &gtkdata);
-
-	gtkdata.find_phase = false;
-	iwl_mvm_iter_d0i3_ap_keys(mvm, vif, iwl_mvm_d3_update_keys, &gtkdata);
-}
-
 #define ND_QUERY_BUF_LEN (sizeof(struct iwl_scan_offload_profile_match) * \
 			  IWL_SCAN_MAX_PROFILES)
 
@@ -2115,14 +2012,6 @@ out:
 	 * 2. We are using a unified image but had an error while exiting D3
 	 */
 	set_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, &mvm->status);
-	/*
-	 * When switching images we return 1, which causes mac80211
-	 * to do a reconfig with IEEE80211_RECONFIG_TYPE_RESTART.
-	 * This type of reconfig calls iwl_mvm_restart_complete(),
-	 * where we unref the IWL_MVM_REF_UCODE_DOWN, so we need
-	 * to take the reference here.
-	 */
-	iwl_mvm_ref(mvm, IWL_MVM_REF_UCODE_DOWN);
 
 	return 1;
 }
@@ -2134,53 +2023,12 @@ static int iwl_mvm_resume_d3(struct iwl_mvm *mvm)
 	return __iwl_mvm_resume(mvm, false);
 }
 
-static int iwl_mvm_resume_d0i3(struct iwl_mvm *mvm)
-{
-	bool exit_now;
-	enum iwl_d3_status d3_status;
-	struct iwl_trans *trans = mvm->trans;
-
-	iwl_trans_d3_resume(trans, &d3_status, false, false);
-
-	/*
-	 * make sure to clear D0I3_DEFER_WAKEUP before
-	 * calling iwl_trans_resume(), which might wait
-	 * for d0i3 exit completion.
-	 */
-	mutex_lock(&mvm->d0i3_suspend_mutex);
-	__clear_bit(D0I3_DEFER_WAKEUP, &mvm->d0i3_suspend_flags);
-	exit_now = __test_and_clear_bit(D0I3_PENDING_WAKEUP,
-					&mvm->d0i3_suspend_flags);
-	mutex_unlock(&mvm->d0i3_suspend_mutex);
-	if (exit_now) {
-		IWL_DEBUG_RPM(mvm, "Run deferred d0i3 exit\n");
-		_iwl_mvm_exit_d0i3(mvm);
-	}
-
-	iwl_trans_resume(trans);
-
-	if (iwl_mvm_enter_d0i3_on_suspend(mvm)) {
-		int ret = iwl_mvm_exit_d0i3(mvm->hw->priv);
-
-		if (ret)
-			return ret;
-		/*
-		 * d0i3 exit will be deferred until reconfig_complete.
-		 * make sure there we are out of d0i3.
-		 */
-	}
-	return 0;
-}
-
 int iwl_mvm_resume(struct ieee80211_hw *hw)
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 	int ret;
 
-	if (mvm->trans->system_pm_mode == IWL_PLAT_PM_MODE_D0I3)
-		ret = iwl_mvm_resume_d0i3(mvm);
-	else
-		ret = iwl_mvm_resume_d3(mvm);
+	ret = iwl_mvm_resume_d3(mvm);
 
 	mvm->trans->system_pm_mode = IWL_PLAT_PM_MODE_DISABLED;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
index 5b1bb76c5d28..2dd5af0285ac 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
@@ -1016,19 +1016,11 @@ static ssize_t iwl_dbgfs_fw_restart_write(struct iwl_mvm *mvm, char *buf,
 static ssize_t iwl_dbgfs_fw_nmi_write(struct iwl_mvm *mvm, char *buf,
 				      size_t count, loff_t *ppos)
 {
-	int ret;
-
 	if (!iwl_mvm_firmware_running(mvm))
 		return -EIO;
 
-	ret = iwl_mvm_ref_sync(mvm, IWL_MVM_REF_NMI);
-	if (ret)
-		return ret;
-
 	iwl_force_nmi(mvm->trans);
 
-	iwl_mvm_unref(mvm, IWL_MVM_REF_NMI);
-
 	return count;
 }
 
@@ -1340,19 +1332,12 @@ static ssize_t iwl_dbgfs_fw_dbg_collect_write(struct iwl_mvm *mvm,
 					      char *buf, size_t count,
 					      loff_t *ppos)
 {
-	int ret;
-
-	ret = iwl_mvm_ref_sync(mvm, IWL_MVM_REF_PRPH_WRITE);
-	if (ret)
-		return ret;
 	if (count == 0)
 		return 0;
 
 	iwl_fw_dbg_collect(&mvm->fwrt, FW_DBG_TRIGGER_USER, buf,
 			   (count - 1), NULL);
 
-	iwl_mvm_unref(mvm, IWL_MVM_REF_PRPH_WRITE);
-
 	return count;
 }
 
@@ -1557,87 +1542,6 @@ static ssize_t iwl_dbgfs_bcast_filters_macs_write(struct iwl_mvm *mvm,
 }
 #endif
 
-#define PRINT_MVM_REF(ref) do {						\
-	if (mvm->refs[ref])						\
-		pos += scnprintf(buf + pos, bufsz - pos,		\
-				 "\t(0x%lx): %d %s\n",			\
-				 BIT(ref), mvm->refs[ref], #ref);	\
-} while (0)
-
-static ssize_t iwl_dbgfs_d0i3_refs_read(struct file *file,
-					char __user *user_buf,
-					size_t count, loff_t *ppos)
-{
-	struct iwl_mvm *mvm = file->private_data;
-	int i, pos = 0;
-	char buf[256];
-	const size_t bufsz = sizeof(buf);
-	u32 refs = 0;
-
-	for (i = 0; i < IWL_MVM_REF_COUNT; i++)
-		if (mvm->refs[i])
-			refs |= BIT(i);
-
-	pos += scnprintf(buf + pos, bufsz - pos, "taken mvm refs: 0x%x\n",
-			 refs);
-
-	PRINT_MVM_REF(IWL_MVM_REF_UCODE_DOWN);
-	PRINT_MVM_REF(IWL_MVM_REF_SCAN);
-	PRINT_MVM_REF(IWL_MVM_REF_ROC);
-	PRINT_MVM_REF(IWL_MVM_REF_ROC_AUX);
-	PRINT_MVM_REF(IWL_MVM_REF_P2P_CLIENT);
-	PRINT_MVM_REF(IWL_MVM_REF_AP_IBSS);
-	PRINT_MVM_REF(IWL_MVM_REF_USER);
-	PRINT_MVM_REF(IWL_MVM_REF_TX);
-	PRINT_MVM_REF(IWL_MVM_REF_TX_AGG);
-	PRINT_MVM_REF(IWL_MVM_REF_ADD_IF);
-	PRINT_MVM_REF(IWL_MVM_REF_START_AP);
-	PRINT_MVM_REF(IWL_MVM_REF_BSS_CHANGED);
-	PRINT_MVM_REF(IWL_MVM_REF_PREPARE_TX);
-	PRINT_MVM_REF(IWL_MVM_REF_PROTECT_TDLS);
-	PRINT_MVM_REF(IWL_MVM_REF_CHECK_CTKILL);
-	PRINT_MVM_REF(IWL_MVM_REF_PRPH_READ);
-	PRINT_MVM_REF(IWL_MVM_REF_PRPH_WRITE);
-	PRINT_MVM_REF(IWL_MVM_REF_NMI);
-	PRINT_MVM_REF(IWL_MVM_REF_TM_CMD);
-	PRINT_MVM_REF(IWL_MVM_REF_EXIT_WORK);
-	PRINT_MVM_REF(IWL_MVM_REF_PROTECT_CSA);
-	PRINT_MVM_REF(IWL_MVM_REF_FW_DBG_COLLECT);
-	PRINT_MVM_REF(IWL_MVM_REF_INIT_UCODE);
-	PRINT_MVM_REF(IWL_MVM_REF_SENDING_CMD);
-	PRINT_MVM_REF(IWL_MVM_REF_RX);
-
-	return simple_read_from_buffer(user_buf, count, ppos, buf, pos);
-}
-
-static ssize_t iwl_dbgfs_d0i3_refs_write(struct iwl_mvm *mvm, char *buf,
-					 size_t count, loff_t *ppos)
-{
-	unsigned long value;
-	int ret;
-	bool taken;
-
-	ret = kstrtoul(buf, 10, &value);
-	if (ret < 0)
-		return ret;
-
-	mutex_lock(&mvm->mutex);
-
-	taken = mvm->refs[IWL_MVM_REF_USER];
-	if (value == 1 && !taken)
-		iwl_mvm_ref(mvm, IWL_MVM_REF_USER);
-	else if (value == 0 && taken)
-		iwl_mvm_unref(mvm, IWL_MVM_REF_USER);
-	else
-		ret = -EINVAL;
-
-	mutex_unlock(&mvm->mutex);
-
-	if (ret < 0)
-		return ret;
-	return count;
-}
-
 #define MVM_DEBUGFS_WRITE_FILE_OPS(name, bufsz) \
 	_MVM_DEBUGFS_WRITE_FILE_OPS(name, bufsz, struct iwl_mvm)
 #define MVM_DEBUGFS_READ_WRITE_FILE_OPS(name, bufsz) \
@@ -1670,21 +1574,14 @@ iwl_dbgfs_prph_reg_read(struct file *file,
 	int pos = 0;
 	char buf[32];
 	const size_t bufsz = sizeof(buf);
-	int ret;
 
 	if (!mvm->dbgfs_prph_reg_addr)
 		return -EINVAL;
 
-	ret = iwl_mvm_ref_sync(mvm, IWL_MVM_REF_PRPH_READ);
-	if (ret)
-		return ret;
-
 	pos += scnprintf(buf + pos, bufsz - pos, "Reg 0x%x: (0x%x)\n",
 		mvm->dbgfs_prph_reg_addr,
 		iwl_read_prph(mvm->trans, mvm->dbgfs_prph_reg_addr));
 
-	iwl_mvm_unref(mvm, IWL_MVM_REF_PRPH_READ);
-
 	return simple_read_from_buffer(user_buf, count, ppos, buf, pos);
 }
 
@@ -1694,7 +1591,6 @@ iwl_dbgfs_prph_reg_write(struct iwl_mvm *mvm, char *buf,
 {
 	u8 args;
 	u32 value;
-	int ret;
 
 	args = sscanf(buf, "%i %i", &mvm->dbgfs_prph_reg_addr, &value);
 	/* if we only want to set the reg address - nothing more to do */
@@ -1705,13 +1601,8 @@ iwl_dbgfs_prph_reg_write(struct iwl_mvm *mvm, char *buf,
 	if (args != 2)
 		return -EINVAL;
 
-	ret = iwl_mvm_ref_sync(mvm, IWL_MVM_REF_PRPH_WRITE);
-	if (ret)
-		return ret;
-
 	iwl_write_prph(mvm->trans, mvm->dbgfs_prph_reg_addr, value);
 
-	iwl_mvm_unref(mvm, IWL_MVM_REF_PRPH_WRITE);
 out:
 	return count;
 }
@@ -1870,7 +1761,6 @@ MVM_DEBUGFS_WRITE_FILE_OPS(fw_nmi, 10);
 MVM_DEBUGFS_WRITE_FILE_OPS(bt_tx_prio, 10);
 MVM_DEBUGFS_WRITE_FILE_OPS(bt_force_ant, 10);
 MVM_DEBUGFS_READ_WRITE_FILE_OPS(scan_ant_rxchain, 8);
-MVM_DEBUGFS_READ_WRITE_FILE_OPS(d0i3_refs, 8);
 MVM_DEBUGFS_READ_WRITE_FILE_OPS(fw_dbg_conf, 8);
 MVM_DEBUGFS_WRITE_FILE_OPS(fw_dbg_collect, 64);
 MVM_DEBUGFS_WRITE_FILE_OPS(max_amsdu_len, 8);
@@ -2066,7 +1956,6 @@ void iwl_mvm_dbgfs_register(struct iwl_mvm *mvm, struct dentry *dbgfs_dir)
 	MVM_DEBUGFS_ADD_FILE(bt_force_ant, mvm->debugfs_dir, 0200);
 	MVM_DEBUGFS_ADD_FILE(scan_ant_rxchain, mvm->debugfs_dir, 0600);
 	MVM_DEBUGFS_ADD_FILE(prph_reg, mvm->debugfs_dir, 0600);
-	MVM_DEBUGFS_ADD_FILE(d0i3_refs, mvm->debugfs_dir, 0600);
 	MVM_DEBUGFS_ADD_FILE(fw_dbg_conf, mvm->debugfs_dir, 0600);
 	MVM_DEBUGFS_ADD_FILE(fw_dbg_collect, mvm->debugfs_dir, 0200);
 	MVM_DEBUGFS_ADD_FILE(max_amsdu_len, mvm->debugfs_dir, 0200);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
index fec38a47696e..ff2eb27e9491 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
@@ -8,6 +8,7 @@
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
  * Copyright (C) 2018 Intel Corporation
  * Copyright (C) 2019 Intel Corporation
+ * Copyright (C) 2020 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -30,6 +31,7 @@
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
  * Copyright (C) 2018 Intel Corporation
  * Copyright (C) 2019 Intel Corporation
+ * Copyright (C) 2020 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -389,6 +391,8 @@ void iwl_mvm_ftm_abort(struct iwl_mvm *mvm, struct cfg80211_pmsr_request *req)
 	if (req != mvm->ftm_initiator.req)
 		return;
 
+	iwl_mvm_ftm_reset(mvm);
+
 	if (iwl_mvm_send_cmd_pdu(mvm, iwl_cmd_id(TOF_RANGE_ABORT_CMD,
 						 LOCATION_GROUP, 0),
 				 0, sizeof(cmd), &cmd))
@@ -502,7 +506,6 @@ void iwl_mvm_ftm_range_resp(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb)
 	lockdep_assert_held(&mvm->mutex);
 
 	if (!mvm->ftm_initiator.req) {
-		IWL_ERR(mvm, "Got FTM response but have no request?\n");
 		return;
 	}
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index 884f64f46d2d..fd91d41e7c67 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -1322,10 +1322,6 @@ int iwl_mvm_up(struct iwl_mvm *mvm)
 			goto error;
 	}
 
-	/* allow FW/transport low power modes if not during restart */
-	if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status))
-		iwl_mvm_unref(mvm, IWL_MVM_REF_UCODE_DOWN);
-
 	if (test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status))
 		iwl_mvm_send_recovery_cmd(mvm, ERROR_RECOVERY_UPDATE_DB);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index a6183281ee1e..1fc74c8d7dd2 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -5,10 +5,9 @@
  *
  * GPL LICENSE SUMMARY
  *
- * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2012 - 2014, 2018 - 2020 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -28,10 +27,9 @@
  *
  * BSD LICENSE
  *
- * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2012 - 2014, 2018 - 2020 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -213,91 +211,6 @@ static int __iwl_mvm_mac_set_key(struct ieee80211_hw *hw,
 				 struct ieee80211_sta *sta,
 				 struct ieee80211_key_conf *key);
 
-void iwl_mvm_ref(struct iwl_mvm *mvm, enum iwl_mvm_ref_type ref_type)
-{
-	if (!iwl_mvm_is_d0i3_supported(mvm))
-		return;
-
-	IWL_DEBUG_RPM(mvm, "Take mvm reference - type %d\n", ref_type);
-	spin_lock_bh(&mvm->refs_lock);
-	mvm->refs[ref_type]++;
-	spin_unlock_bh(&mvm->refs_lock);
-	iwl_trans_ref(mvm->trans);
-}
-
-void iwl_mvm_unref(struct iwl_mvm *mvm, enum iwl_mvm_ref_type ref_type)
-{
-	if (!iwl_mvm_is_d0i3_supported(mvm))
-		return;
-
-	IWL_DEBUG_RPM(mvm, "Leave mvm reference - type %d\n", ref_type);
-	spin_lock_bh(&mvm->refs_lock);
-	if (WARN_ON(!mvm->refs[ref_type])) {
-		spin_unlock_bh(&mvm->refs_lock);
-		return;
-	}
-	mvm->refs[ref_type]--;
-	spin_unlock_bh(&mvm->refs_lock);
-	iwl_trans_unref(mvm->trans);
-}
-
-static void iwl_mvm_unref_all_except(struct iwl_mvm *mvm,
-				     enum iwl_mvm_ref_type except_ref)
-{
-	int i, j;
-
-	if (!iwl_mvm_is_d0i3_supported(mvm))
-		return;
-
-	spin_lock_bh(&mvm->refs_lock);
-	for (i = 0; i < IWL_MVM_REF_COUNT; i++) {
-		if (except_ref == i || !mvm->refs[i])
-			continue;
-
-		IWL_DEBUG_RPM(mvm, "Cleanup: remove mvm ref type %d (%d)\n",
-			      i, mvm->refs[i]);
-		for (j = 0; j < mvm->refs[i]; j++)
-			iwl_trans_unref(mvm->trans);
-		mvm->refs[i] = 0;
-	}
-	spin_unlock_bh(&mvm->refs_lock);
-}
-
-bool iwl_mvm_ref_taken(struct iwl_mvm *mvm)
-{
-	int i;
-	bool taken = false;
-
-	if (!iwl_mvm_is_d0i3_supported(mvm))
-		return true;
-
-	spin_lock_bh(&mvm->refs_lock);
-	for (i = 0; i < IWL_MVM_REF_COUNT; i++) {
-		if (mvm->refs[i]) {
-			taken = true;
-			break;
-		}
-	}
-	spin_unlock_bh(&mvm->refs_lock);
-
-	return taken;
-}
-
-int iwl_mvm_ref_sync(struct iwl_mvm *mvm, enum iwl_mvm_ref_type ref_type)
-{
-	iwl_mvm_ref(mvm, ref_type);
-
-	if (!wait_event_timeout(mvm->d0i3_exit_waitq,
-				!test_bit(IWL_MVM_STATUS_IN_D0I3, &mvm->status),
-				HZ)) {
-		WARN_ON_ONCE(1);
-		iwl_mvm_unref(mvm, ref_type);
-		return -EIO;
-	}
-
-	return 0;
-}
-
 static void iwl_mvm_reset_phy_ctxts(struct iwl_mvm *mvm)
 {
 	int i;
@@ -341,7 +254,8 @@ struct ieee80211_regdomain *iwl_mvm_get_regdomain(struct wiphy *wiphy,
 				      __le32_to_cpu(resp->n_channels),
 				      resp->channels,
 				      __le16_to_cpu(resp->mcc),
-				      __le16_to_cpu(resp->geo_info));
+				      __le16_to_cpu(resp->geo_info),
+				      __le16_to_cpu(resp->cap));
 	/* Store the return source id */
 	src_id = resp->source_id;
 	kfree(resp);
@@ -762,12 +676,6 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 	mvm->rts_threshold = IEEE80211_MAX_RTS_THRESHOLD;
 
 #ifdef CONFIG_PM_SLEEP
-	if (iwl_mvm_is_d0i3_supported(mvm) &&
-	    device_can_wakeup(mvm->trans->dev)) {
-		mvm->wowlan.flags = WIPHY_WOWLAN_ANY;
-		hw->wiphy->wowlan = &mvm->wowlan;
-	}
-
 	if ((unified || mvm->fw->img[IWL_UCODE_WOWLAN].num_sec) &&
 	    mvm->trans->ops->d3_suspend &&
 	    mvm->trans->ops->d3_resume &&
@@ -833,44 +741,18 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 	return ret;
 }
 
-static bool iwl_mvm_defer_tx(struct iwl_mvm *mvm,
-			     struct ieee80211_sta *sta,
-			     struct sk_buff *skb)
+static void iwl_mvm_tx_skb(struct iwl_mvm *mvm, struct sk_buff *skb,
+			   struct ieee80211_sta *sta)
 {
-	struct iwl_mvm_sta *mvmsta;
-	bool defer = false;
-
-	/*
-	 * double check the IN_D0I3 flag both before and after
-	 * taking the spinlock, in order to prevent taking
-	 * the spinlock when not needed.
-	 */
-	if (likely(!test_bit(IWL_MVM_STATUS_IN_D0I3, &mvm->status)))
-		return false;
-
-	spin_lock(&mvm->d0i3_tx_lock);
-	/*
-	 * testing the flag again ensures the skb dequeue
-	 * loop (on d0i3 exit) hasn't run yet.
-	 */
-	if (!test_bit(IWL_MVM_STATUS_IN_D0I3, &mvm->status))
-		goto out;
-
-	mvmsta = iwl_mvm_sta_from_mac80211(sta);
-	if (mvmsta->sta_id == IWL_MVM_INVALID_STA ||
-	    mvmsta->sta_id != mvm->d0i3_ap_sta_id)
-		goto out;
-
-	__skb_queue_tail(&mvm->d0i3_tx, skb);
-
-	/* trigger wakeup */
-	iwl_mvm_ref(mvm, IWL_MVM_REF_TX);
-	iwl_mvm_unref(mvm, IWL_MVM_REF_TX);
+	if (likely(sta)) {
+		if (likely(iwl_mvm_tx_skb_sta(mvm, skb, sta) == 0))
+			return;
+	} else {
+		if (likely(iwl_mvm_tx_skb_non_sta(mvm, skb) == 0))
+			return;
+	}
 
-	defer = true;
-out:
-	spin_unlock(&mvm->d0i3_tx_lock);
-	return defer;
+	ieee80211_free_txskb(mvm->hw, skb);
 }
 
 static void iwl_mvm_mac_tx(struct ieee80211_hw *hw,
@@ -916,16 +798,7 @@ static void iwl_mvm_mac_tx(struct ieee80211_hw *hw,
 		}
 	}
 
-	if (sta) {
-		if (iwl_mvm_defer_tx(mvm, sta, skb))
-			return;
-		if (iwl_mvm_tx_skb(mvm, skb, sta))
-			goto drop;
-		return;
-	}
-
-	if (iwl_mvm_tx_skb_non_sta(mvm, skb))
-		goto drop;
+	iwl_mvm_tx_skb(mvm, skb, sta);
 	return;
  drop:
 	ieee80211_free_txskb(hw, skb);
@@ -975,10 +848,7 @@ void iwl_mvm_mac_itxq_xmit(struct ieee80211_hw *hw, struct ieee80211_txq *txq)
 				break;
 			}
 
-			if (!txq->sta)
-				iwl_mvm_tx_skb_non_sta(mvm, skb);
-			else
-				iwl_mvm_tx_skb(mvm, skb, txq->sta);
+			iwl_mvm_tx_skb(mvm, skb, txq->sta);
 		}
 	} while (atomic_dec_return(&mvmtxq->tx_request));
 	rcu_read_unlock();
@@ -1086,7 +956,6 @@ static int iwl_mvm_mac_ampdu_action(struct ieee80211_hw *hw,
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 	int ret;
-	bool tx_agg_ref = false;
 	struct ieee80211_sta *sta = params->sta;
 	enum ieee80211_ampdu_mlme_action action = params->action;
 	u16 tid = params->tid;
@@ -1101,31 +970,6 @@ static int iwl_mvm_mac_ampdu_action(struct ieee80211_hw *hw,
 	if (!(mvm->nvm_data->sku_cap_11n_enable))
 		return -EACCES;
 
-	/* return from D0i3 before starting a new Tx aggregation */
-	switch (action) {
-	case IEEE80211_AMPDU_TX_START:
-	case IEEE80211_AMPDU_TX_STOP_CONT:
-	case IEEE80211_AMPDU_TX_STOP_FLUSH:
-	case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT:
-	case IEEE80211_AMPDU_TX_OPERATIONAL:
-		/*
-		 * for tx start, wait synchronously until D0i3 exit to
-		 * get the correct sequence number for the tid.
-		 * additionally, some other ampdu actions use direct
-		 * target access, which is not handled automatically
-		 * by the trans layer (unlike commands), so wait for
-		 * d0i3 exit in these cases as well.
-		 */
-		ret = iwl_mvm_ref_sync(mvm, IWL_MVM_REF_TX_AGG);
-		if (ret)
-			return ret;
-
-		tx_agg_ref = true;
-		break;
-	default:
-		break;
-	}
-
 	mutex_lock(&mvm->mutex);
 
 	switch (action) {
@@ -1186,13 +1030,6 @@ static int iwl_mvm_mac_ampdu_action(struct ieee80211_hw *hw,
 	}
 	mutex_unlock(&mvm->mutex);
 
-	/*
-	 * If the tid is marked as started, we won't use it for offloaded
-	 * traffic on the next D0i3 entry. It's safe to unref.
-	 */
-	if (tx_agg_ref)
-		iwl_mvm_unref(mvm, IWL_MVM_REF_TX_AGG);
-
 	return ret;
 }
 
@@ -1216,11 +1053,6 @@ static void iwl_mvm_cleanup_iterator(void *data, u8 *mac,
 
 static void iwl_mvm_restart_cleanup(struct iwl_mvm *mvm)
 {
-	/* cleanup all stale references (scan, roc), but keep the
-	 * ucode_down ref until reconfig is complete
-	 */
-	iwl_mvm_unref_all_except(mvm, IWL_MVM_REF_UCODE_DOWN);
-
 	iwl_mvm_stop_device(mvm);
 
 	mvm->cur_aid = 0;
@@ -1242,7 +1074,6 @@ static void iwl_mvm_restart_cleanup(struct iwl_mvm *mvm)
 	ieee80211_iterate_interfaces(mvm->hw, 0, iwl_mvm_cleanup_iterator, mvm);
 
 	mvm->p2p_device_vif = NULL;
-	mvm->d0i3_ap_sta_id = IWL_MVM_INVALID_STA;
 
 	iwl_mvm_reset_phy_ctxts(mvm);
 	memset(mvm->fw_key_table, 0, sizeof(mvm->fw_key_table));
@@ -1251,9 +1082,6 @@ static void iwl_mvm_restart_cleanup(struct iwl_mvm *mvm)
 
 	ieee80211_wake_queues(mvm->hw);
 
-	/* clear any stale d0i3 state */
-	clear_bit(IWL_MVM_STATUS_IN_D0I3, &mvm->status);
-
 	mvm->vif_count = 0;
 	mvm->rx_ba_sessions = 0;
 	mvm->fwrt.dump.conf = FW_DBG_INVALID;
@@ -1278,14 +1106,6 @@ int __iwl_mvm_mac_start(struct iwl_mvm *mvm)
 		clear_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, &mvm->status);
 		/* Clean up some internal and mac80211 state on restart */
 		iwl_mvm_restart_cleanup(mvm);
-	} else {
-		/* Hold the reference to prevent runtime suspend while
-		 * the start procedure runs.  It's a bit confusing
-		 * that the UCODE_DOWN reference is taken, but it just
-		 * means "UCODE is not UP yet". ( TODO: rename this
-		 * reference).
-		 */
-		iwl_mvm_ref(mvm, IWL_MVM_REF_UCODE_DOWN);
 	}
 	ret = iwl_mvm_up(mvm);
 
@@ -1297,9 +1117,6 @@ int __iwl_mvm_mac_start(struct iwl_mvm *mvm)
 		 * would do.
 		 */
 		clear_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status);
-#ifdef CONFIG_PM
-		iwl_mvm_d0i3_enable_tx(mvm, NULL);
-#endif
 	}
 
 	return ret;
@@ -1310,19 +1127,6 @@ static int iwl_mvm_mac_start(struct ieee80211_hw *hw)
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 	int ret;
 
-	/* Some hw restart cleanups must not hold the mutex */
-	if (test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status)) {
-		/*
-		 * Make sure we are out of d0i3. This is needed
-		 * to make sure the reference accounting is correct
-		 * (and there is no stale d0i3_exit_work).
-		 */
-		wait_event_timeout(mvm->d0i3_exit_waitq,
-				   !test_bit(IWL_MVM_STATUS_IN_D0I3,
-					     &mvm->status),
-				   HZ);
-	}
-
 	mutex_lock(&mvm->mutex);
 	ret = __iwl_mvm_mac_start(mvm);
 	mutex_unlock(&mvm->mutex);
@@ -1337,17 +1141,12 @@ static void iwl_mvm_restart_complete(struct iwl_mvm *mvm)
 	mutex_lock(&mvm->mutex);
 
 	clear_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status);
-#ifdef CONFIG_PM
-	iwl_mvm_d0i3_enable_tx(mvm, NULL);
-#endif
+
 	ret = iwl_mvm_update_quotas(mvm, true, NULL);
 	if (ret)
 		IWL_ERR(mvm, "Failed to update quotas after restart (%d)\n",
 			ret);
 
-	/* allow transport/FW low power modes */
-	iwl_mvm_unref(mvm, IWL_MVM_REF_UCODE_DOWN);
-
 	iwl_mvm_send_recovery_cmd(mvm, ERROR_RECOVERY_END_OF_RECOVERY);
 
 	/*
@@ -1359,17 +1158,6 @@ static void iwl_mvm_restart_complete(struct iwl_mvm *mvm)
 	mutex_unlock(&mvm->mutex);
 }
 
-static void iwl_mvm_resume_complete(struct iwl_mvm *mvm)
-{
-	if (iwl_mvm_is_d0i3_supported(mvm) &&
-	    iwl_mvm_enter_d0i3_on_suspend(mvm))
-		WARN_ONCE(!wait_event_timeout(mvm->d0i3_exit_waitq,
-					      !test_bit(IWL_MVM_STATUS_IN_D0I3,
-							&mvm->status),
-					      HZ),
-			  "D0i3 exit on resume timed out\n");
-}
-
 static void
 iwl_mvm_mac_reconfig_complete(struct ieee80211_hw *hw,
 			      enum ieee80211_reconfig_type reconfig_type)
@@ -1381,7 +1169,6 @@ iwl_mvm_mac_reconfig_complete(struct ieee80211_hw *hw,
 		iwl_mvm_restart_complete(mvm);
 		break;
 	case IEEE80211_RECONFIG_TYPE_SUSPEND:
-		iwl_mvm_resume_complete(mvm);
 		break;
 	}
 }
@@ -1403,14 +1190,13 @@ void __iwl_mvm_mac_stop(struct iwl_mvm *mvm)
 	 */
 	flush_work(&mvm->roc_done_wk);
 
+	iwl_mvm_rm_aux_sta(mvm);
+
 	iwl_mvm_stop_device(mvm);
 
 	iwl_mvm_async_handlers_purge(mvm);
 	/* async_handlers_list is empty and will stay empty: HW is stopped */
 
-	/* the fw is stopped, the aux sta is dead: clean up driver state */
-	iwl_mvm_del_aux_sta(mvm);
-
 	/*
 	 * Clear IN_HW_RESTART and HW_RESTART_REQUESTED flag when stopping the
 	 * hw (as restart_complete() won't be called in this case) and mac80211
@@ -1443,7 +1229,6 @@ static void iwl_mvm_mac_stop(struct ieee80211_hw *hw)
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 
-	flush_work(&mvm->d0i3_exit_work);
 	flush_work(&mvm->async_handlers_wk);
 	flush_work(&mvm->add_stream_wk);
 
@@ -1612,15 +1397,6 @@ static int iwl_mvm_mac_add_interface(struct ieee80211_hw *hw,
 	RCU_INIT_POINTER(mvmvif->probe_resp_data, NULL);
 
 	/*
-	 * make sure D0i3 exit is completed, otherwise a target access
-	 * during tx queue configuration could be done when still in
-	 * D0i3 state.
-	 */
-	ret = iwl_mvm_ref_sync(mvm, IWL_MVM_REF_ADD_IF);
-	if (ret)
-		return ret;
-
-	/*
 	 * Not much to do here. The stack will not allow interface
 	 * types or combinations that we didn't advertise, so we
 	 * don't really have to check the types.
@@ -1755,8 +1531,6 @@ static int iwl_mvm_mac_add_interface(struct ieee80211_hw *hw,
  out_unlock:
 	mutex_unlock(&mvm->mutex);
 
-	iwl_mvm_unref(mvm, IWL_MVM_REF_ADD_IF);
-
 	return ret;
 }
 
@@ -2241,7 +2015,7 @@ static void iwl_mvm_cfg_he_sta(struct iwl_mvm *mvm,
 	rcu_read_lock();
 
 	sta = rcu_dereference(mvm->fw_id_to_mac_id[sta_ctxt_cmd.sta_id]);
-	if (IS_ERR(sta)) {
+	if (IS_ERR_OR_NULL(sta)) {
 		rcu_read_unlock();
 		WARN(1, "Can't find STA to configure HE\n");
 		return;
@@ -2519,7 +2293,6 @@ static void iwl_mvm_bss_info_changed_station(struct iwl_mvm *mvm,
 			iwl_mvm_sf_update(mvm, vif, false);
 			iwl_mvm_power_vif_assoc(mvm, vif);
 			if (vif->p2p) {
-				iwl_mvm_ref(mvm, IWL_MVM_REF_P2P_CLIENT);
 				iwl_mvm_update_smps(mvm, vif,
 						    IWL_MVM_SMPS_REQ_PROT,
 						    IEEE80211_SMPS_DYNAMIC);
@@ -2555,9 +2328,6 @@ static void iwl_mvm_bss_info_changed_station(struct iwl_mvm *mvm,
 					IWL_ERR(mvm,
 						"failed to remove AP station\n");
 
-				if (mvm->d0i3_ap_sta_id == mvmvif->ap_sta_id)
-					mvm->d0i3_ap_sta_id =
-						IWL_MVM_INVALID_STA;
 				mvmvif->ap_sta_id = IWL_MVM_INVALID_STA;
 			}
 
@@ -2566,9 +2336,6 @@ static void iwl_mvm_bss_info_changed_station(struct iwl_mvm *mvm,
 			if (ret)
 				IWL_ERR(mvm, "failed to update quotas\n");
 
-			if (vif->p2p)
-				iwl_mvm_unref(mvm, IWL_MVM_REF_P2P_CLIENT);
-
 			/* this will take the cleared BSSID from bss_conf */
 			ret = iwl_mvm_mac_ctxt_changed(mvm, vif, false, NULL);
 			if (ret)
@@ -2656,14 +2423,6 @@ static int iwl_mvm_start_ap_ibss(struct ieee80211_hw *hw,
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
 	int ret, i;
 
-	/*
-	 * iwl_mvm_mac_ctxt_add() might read directly from the device
-	 * (the system time), so make sure it is available.
-	 */
-	ret = iwl_mvm_ref_sync(mvm, IWL_MVM_REF_START_AP);
-	if (ret)
-		return ret;
-
 	mutex_lock(&mvm->mutex);
 
 	/* Send the beacon template */
@@ -2759,8 +2518,6 @@ static int iwl_mvm_start_ap_ibss(struct ieee80211_hw *hw,
 	if (vif->p2p && mvm->p2p_device_vif)
 		iwl_mvm_mac_ctxt_changed(mvm, mvm->p2p_device_vif, false, NULL);
 
-	iwl_mvm_ref(mvm, IWL_MVM_REF_AP_IBSS);
-
 	iwl_mvm_bt_coex_vif_change(mvm);
 
 	/* we don't support TDLS during DCM */
@@ -2782,7 +2539,6 @@ out_remove:
 	iwl_mvm_mac_ctxt_remove(mvm, vif);
 out_unlock:
 	mutex_unlock(&mvm->mutex);
-	iwl_mvm_unref(mvm, IWL_MVM_REF_START_AP);
 	return ret;
 }
 
@@ -2820,8 +2576,6 @@ static void iwl_mvm_stop_ap_ibss(struct ieee80211_hw *hw,
 
 	iwl_mvm_bt_coex_vif_change(mvm);
 
-	iwl_mvm_unref(mvm, IWL_MVM_REF_AP_IBSS);
-
 	/* Need to update the P2P Device MAC (only GO, IBSS is single vif) */
 	if (vif->p2p && mvm->p2p_device_vif)
 		iwl_mvm_mac_ctxt_changed(mvm, mvm->p2p_device_vif, false, NULL);
@@ -2895,14 +2649,6 @@ static void iwl_mvm_bss_info_changed(struct ieee80211_hw *hw,
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 
-	/*
-	 * iwl_mvm_bss_info_changed_station() might call
-	 * iwl_mvm_protect_session(), which reads directly from
-	 * the device (the system time), so make sure it is available.
-	 */
-	if (iwl_mvm_ref_sync(mvm, IWL_MVM_REF_BSS_CHANGED))
-		return;
-
 	mutex_lock(&mvm->mutex);
 
 	if (changes & BSS_CHANGED_IDLE && !bss_conf->idle)
@@ -2926,7 +2672,6 @@ static void iwl_mvm_bss_info_changed(struct ieee80211_hw *hw,
 	}
 
 	mutex_unlock(&mvm->mutex);
-	iwl_mvm_unref(mvm, IWL_MVM_REF_BSS_CHANGED);
 }
 
 static int iwl_mvm_mac_hw_scan(struct ieee80211_hw *hw,
@@ -3436,13 +3181,6 @@ static void iwl_mvm_mac_mgd_prepare_tx(struct ieee80211_hw *hw,
 	u32 duration = IWL_MVM_TE_SESSION_PROTECTION_MAX_TIME_MS;
 	u32 min_duration = IWL_MVM_TE_SESSION_PROTECTION_MIN_TIME_MS;
 
-	/*
-	 * iwl_mvm_protect_session() reads directly from the device
-	 * (the system time), so make sure it is available.
-	 */
-	if (iwl_mvm_ref_sync(mvm, IWL_MVM_REF_PREPARE_TX))
-		return;
-
 	if (req_duration > duration)
 		duration = req_duration;
 
@@ -3450,8 +3188,6 @@ static void iwl_mvm_mac_mgd_prepare_tx(struct ieee80211_hw *hw,
 	/* Try really hard to protect the session and hear a beacon */
 	iwl_mvm_protect_session(mvm, vif, duration, min_duration, 500, false);
 	mutex_unlock(&mvm->mutex);
-
-	iwl_mvm_unref(mvm, IWL_MVM_REF_PREPARE_TX);
 }
 
 static int iwl_mvm_mac_sched_scan_start(struct ieee80211_hw *hw,
@@ -4266,23 +4002,12 @@ static int __iwl_mvm_assign_vif_chanctx(struct iwl_mvm *mvm,
 				 IWL_UCODE_TLV_CAPA_CHANNEL_SWITCH_CMD)) {
 			u32 duration = 3 * vif->bss_conf.beacon_int;
 
-
-			/* iwl_mvm_protect_session() reads directly from the
-			 * device (the system time), so make sure it is
-			 * available.
-			 */
-			ret = iwl_mvm_ref_sync(mvm, IWL_MVM_REF_PROTECT_CSA);
-			if (ret)
-				goto out_remove_binding;
-
 			/* Protect the session to make sure we hear the first
 			 * beacon on the new channel.
 			 */
 			iwl_mvm_protect_session(mvm, vif, duration, duration,
 						vif->bss_conf.beacon_int / 2,
 						true);
-
-			iwl_mvm_unref(mvm, IWL_MVM_REF_PROTECT_CSA);
 		}
 
 		iwl_mvm_update_quotas(mvm, false, NULL);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 0c11a219e347..7c6462b56874 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -258,38 +258,6 @@ enum iwl_mvm_smps_type_request {
 	NUM_IWL_MVM_SMPS_REQ,
 };
 
-enum iwl_mvm_ref_type {
-	IWL_MVM_REF_UCODE_DOWN,
-	IWL_MVM_REF_SCAN,
-	IWL_MVM_REF_ROC,
-	IWL_MVM_REF_ROC_AUX,
-	IWL_MVM_REF_P2P_CLIENT,
-	IWL_MVM_REF_AP_IBSS,
-	IWL_MVM_REF_USER,
-	IWL_MVM_REF_TX,
-	IWL_MVM_REF_TX_AGG,
-	IWL_MVM_REF_ADD_IF,
-	IWL_MVM_REF_START_AP,
-	IWL_MVM_REF_BSS_CHANGED,
-	IWL_MVM_REF_PREPARE_TX,
-	IWL_MVM_REF_PROTECT_TDLS,
-	IWL_MVM_REF_CHECK_CTKILL,
-	IWL_MVM_REF_PRPH_READ,
-	IWL_MVM_REF_PRPH_WRITE,
-	IWL_MVM_REF_NMI,
-	IWL_MVM_REF_TM_CMD,
-	IWL_MVM_REF_EXIT_WORK,
-	IWL_MVM_REF_PROTECT_CSA,
-	IWL_MVM_REF_FW_DBG_COLLECT,
-	IWL_MVM_REF_INIT_UCODE,
-	IWL_MVM_REF_SENDING_CMD,
-	IWL_MVM_REF_RX,
-
-	/* update debugfs.c when changing this */
-
-	IWL_MVM_REF_COUNT,
-};
-
 enum iwl_bt_force_ant_mode {
 	BT_FORCE_ANT_DIS = 0,
 	BT_FORCE_ANT_AUTO,
@@ -617,11 +585,6 @@ struct iwl_mvm_frame_stats {
 	int last_frame_idx;
 };
 
-enum {
-	D0I3_DEFER_WAKEUP,
-	D0I3_PENDING_WAKEUP,
-};
-
 #define IWL_MVM_DEBUG_SET_TEMPERATURE_DISABLE 0xff
 #define IWL_MVM_DEBUG_SET_TEMPERATURE_MIN -100
 #define IWL_MVM_DEBUG_SET_TEMPERATURE_MAX 200
@@ -1011,10 +974,6 @@ struct iwl_mvm {
 	unsigned long fw_key_table[BITS_TO_LONGS(STA_KEY_MAX_NUM)];
 	u8 fw_key_deleted[STA_KEY_MAX_NUM];
 
-	/* references taken by the driver and spinlock protecting them */
-	spinlock_t refs_lock;
-	u8 refs[IWL_MVM_REF_COUNT];
-
 	u8 vif_count;
 	struct ieee80211_vif __rcu *vif_id_to_mac[NUM_MAC_INDEX_DRIVER];
 
@@ -1048,17 +1007,6 @@ struct iwl_mvm {
 #endif
 #endif
 
-	/* d0i3 */
-	u8 d0i3_ap_sta_id;
-	bool d0i3_offloading;
-	struct work_struct d0i3_exit_work;
-	struct sk_buff_head d0i3_tx;
-	/* protect d0i3_suspend_flags */
-	struct mutex d0i3_suspend_mutex;
-	unsigned long d0i3_suspend_flags;
-	/* sync d0i3_tx queue and IWL_MVM_STATUS_IN_D0I3 status flag */
-	spinlock_t d0i3_tx_lock;
-	wait_queue_head_t d0i3_exit_waitq;
 	wait_queue_head_t rx_sync_waitq;
 
 	/* BT-Coex */
@@ -1202,7 +1150,6 @@ struct iwl_mvm {
  * @IWL_MVM_STATUS_ROC_RUNNING: remain-on-channel is running
  * @IWL_MVM_STATUS_HW_RESTART_REQUESTED: HW restart was requested
  * @IWL_MVM_STATUS_IN_HW_RESTART: HW restart is active
- * @IWL_MVM_STATUS_IN_D0I3: NIC is in D0i3
  * @IWL_MVM_STATUS_ROC_AUX_RUNNING: AUX remain-on-channel is running
  * @IWL_MVM_STATUS_FIRMWARE_RUNNING: firmware is running
  * @IWL_MVM_STATUS_NEED_FLUSH_P2P: need to flush P2P bcast STA
@@ -1213,7 +1160,6 @@ enum iwl_mvm_status {
 	IWL_MVM_STATUS_ROC_RUNNING,
 	IWL_MVM_STATUS_HW_RESTART_REQUESTED,
 	IWL_MVM_STATUS_IN_HW_RESTART,
-	IWL_MVM_STATUS_IN_D0I3,
 	IWL_MVM_STATUS_ROC_AUX_RUNNING,
 	IWL_MVM_STATUS_FIRMWARE_RUNNING,
 	IWL_MVM_STATUS_NEED_FLUSH_P2P,
@@ -1292,13 +1238,6 @@ iwl_mvm_rcu_dereference_vif_id(struct iwl_mvm *mvm, u8 vif_id, bool rcu)
 					 lockdep_is_held(&mvm->mutex));
 }
 
-static inline bool iwl_mvm_is_d0i3_supported(struct iwl_mvm *mvm)
-{
-	return !iwlwifi_mod_params.d0i3_disable &&
-		fw_has_capa(&mvm->fw->ucode_capa,
-			    IWL_UCODE_TLV_CAPA_D0I3_SUPPORT);
-}
-
 static inline bool iwl_mvm_is_adaptive_dwell_supported(struct iwl_mvm *mvm)
 {
 	return fw_has_api(&mvm->fw->ucode_capa,
@@ -1328,19 +1267,6 @@ static inline bool iwl_mvm_is_short_beacon_notif_supported(struct iwl_mvm *mvm)
 			  IWL_UCODE_TLV_API_SHORT_BEACON_NOTIF);
 }
 
-static inline bool iwl_mvm_enter_d0i3_on_suspend(struct iwl_mvm *mvm)
-{
-	/* For now we only use this mode to differentiate between
-	 * slave transports, which handle D0i3 entry in suspend by
-	 * themselves in conjunction with runtime PM D0i3.  So, this
-	 * function is used to check whether we need to do anything
-	 * when entering suspend or if the transport layer has already
-	 * done it.
-	 */
-	return (mvm->trans->system_pm_mode == IWL_PLAT_PM_MODE_D0I3) &&
-		(mvm->trans->runtime_pm_mode != IWL_PLAT_PM_MODE_D0I3);
-}
-
 static inline bool iwl_mvm_is_dqa_data_queue(struct iwl_mvm *mvm, u8 queue)
 {
 	return (queue >= IWL_MVM_DQA_MIN_DATA_QUEUE) &&
@@ -1553,8 +1479,8 @@ int __must_check iwl_mvm_send_cmd_status(struct iwl_mvm *mvm,
 int __must_check iwl_mvm_send_cmd_pdu_status(struct iwl_mvm *mvm, u32 id,
 					     u16 len, const void *data,
 					     u32 *status);
-int iwl_mvm_tx_skb(struct iwl_mvm *mvm, struct sk_buff *skb,
-		   struct ieee80211_sta *sta);
+int iwl_mvm_tx_skb_sta(struct iwl_mvm *mvm, struct sk_buff *skb,
+		       struct ieee80211_sta *sta);
 int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb);
 void iwl_mvm_set_tx_cmd(struct iwl_mvm *mvm, struct sk_buff *skb,
 			struct iwl_tx_cmd *tx_cmd,
@@ -1857,30 +1783,9 @@ void iwl_mvm_set_default_unicast_key(struct ieee80211_hw *hw,
 extern const struct file_operations iwl_dbgfs_d3_test_ops;
 struct iwl_wowlan_status *iwl_mvm_send_wowlan_get_status(struct iwl_mvm *mvm);
 #ifdef CONFIG_PM
-int iwl_mvm_wowlan_config_key_params(struct iwl_mvm *mvm,
-				     struct ieee80211_vif *vif,
-				     bool host_awake,
-				     u32 cmd_flags);
-void iwl_mvm_d0i3_update_keys(struct iwl_mvm *mvm,
-			      struct ieee80211_vif *vif,
-			      struct iwl_wowlan_status *status);
 void iwl_mvm_set_last_nonqos_seq(struct iwl_mvm *mvm,
 				 struct ieee80211_vif *vif);
 #else
-static inline int iwl_mvm_wowlan_config_key_params(struct iwl_mvm *mvm,
-						   struct ieee80211_vif *vif,
-						   bool host_awake,
-						   u32 cmd_flags)
-{
-	return 0;
-}
-
-static inline void iwl_mvm_d0i3_update_keys(struct iwl_mvm *mvm,
-					    struct ieee80211_vif *vif,
-					    struct iwl_wowlan_status *status)
-{
-}
-
 static inline void
 iwl_mvm_set_last_nonqos_seq(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 {
@@ -1894,19 +1799,6 @@ int iwl_mvm_send_proto_offload(struct iwl_mvm *mvm,
 			       bool offload_ns,
 			       u32 cmd_flags);
 
-/* D0i3 */
-void iwl_mvm_ref(struct iwl_mvm *mvm, enum iwl_mvm_ref_type ref_type);
-void iwl_mvm_unref(struct iwl_mvm *mvm, enum iwl_mvm_ref_type ref_type);
-int iwl_mvm_ref_sync(struct iwl_mvm *mvm, enum iwl_mvm_ref_type ref_type);
-bool iwl_mvm_ref_taken(struct iwl_mvm *mvm);
-
-#ifdef CONFIG_PM
-void iwl_mvm_d0i3_enable_tx(struct iwl_mvm *mvm, __le16 *qos_seq);
-int iwl_mvm_enter_d0i3(struct iwl_op_mode *op_mode);
-int iwl_mvm_exit_d0i3(struct iwl_op_mode *op_mode);
-int _iwl_mvm_exit_d0i3(struct iwl_mvm *mvm);
-#endif
-
 /* BT Coex */
 int iwl_mvm_send_bt_init_conf(struct iwl_mvm *mvm);
 void iwl_mvm_rx_bt_coex_notif(struct iwl_mvm *mvm,
@@ -1937,9 +1829,6 @@ iwl_mvm_beacon_filter_debugfs_parameters(struct ieee80211_vif *vif,
 					 struct iwl_beacon_filter_cmd *cmd)
 {}
 #endif
-int iwl_mvm_update_d0i3_power_mode(struct iwl_mvm *mvm,
-				   struct ieee80211_vif *vif,
-				   bool enable, u32 flags);
 int iwl_mvm_enable_beacon_filter(struct iwl_mvm *mvm,
 				 struct ieee80211_vif *vif,
 				 u32 flags);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
index 7bdbd010ae6b..14dabf418b4f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
@@ -281,7 +281,7 @@ iwl_parse_nvm_sections(struct iwl_mvm *mvm)
 	int regulatory_type;
 
 	/* Checking for required sections */
-	if (mvm->trans->cfg->nvm_type != IWL_NVM_EXT) {
+	if (mvm->trans->cfg->nvm_type == IWL_NVM) {
 		if (!mvm->nvm_sections[NVM_SECTION_TYPE_SW].data ||
 		    !mvm->nvm_sections[mvm->cfg->nvm_hw_section_num].data) {
 			IWL_ERR(mvm, "Can't parse empty OTP/NVM sections\n");
@@ -309,7 +309,8 @@ iwl_parse_nvm_sections(struct iwl_mvm *mvm)
 		}
 
 		/* PHY_SKU section is mandatory in B0 */
-		if (!mvm->nvm_sections[NVM_SECTION_TYPE_PHY_SKU].data) {
+		if (mvm->trans->cfg->nvm_type == IWL_NVM_EXT &&
+		    !mvm->nvm_sections[NVM_SECTION_TYPE_PHY_SKU].data) {
 			IWL_ERR(mvm,
 				"Can't parse phy_sku in B0, empty sections\n");
 			return NULL;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index fad3bf563712..f82a60ec4540 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -514,9 +514,6 @@ static const struct iwl_hcmd_arr iwl_mvm_groups[] = {
 
 /* this forward declaration can avoid to export the function */
 static void iwl_mvm_async_handlers_wk(struct work_struct *wk);
-#ifdef CONFIG_PM
-static void iwl_mvm_d0i3_exit_work(struct work_struct *wk);
-#endif
 
 static u32 iwl_mvm_min_backoff(struct iwl_mvm *mvm)
 {
@@ -564,14 +561,8 @@ unlock:
 static int iwl_mvm_fwrt_dump_start(void *ctx)
 {
 	struct iwl_mvm *mvm = ctx;
-	int ret;
-
-	ret = iwl_mvm_ref_sync(mvm, IWL_MVM_REF_FW_DBG_COLLECT);
-	if (ret)
-		return ret;
 
 	mutex_lock(&mvm->mutex);
-
 	return 0;
 }
 
@@ -580,8 +571,6 @@ static void iwl_mvm_fwrt_dump_end(void *ctx)
 	struct iwl_mvm *mvm = ctx;
 
 	mutex_unlock(&mvm->mutex);
-
-	iwl_mvm_unref(mvm, IWL_MVM_REF_FW_DBG_COLLECT);
 }
 
 static bool iwl_mvm_fwrt_fw_running(void *ctx)
@@ -700,7 +689,6 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	mvm->drop_bcn_ap_mode = true;
 
 	mutex_init(&mvm->mutex);
-	mutex_init(&mvm->d0i3_suspend_mutex);
 	spin_lock_init(&mvm->async_handlers_lock);
 	INIT_LIST_HEAD(&mvm->time_event_list);
 	INIT_LIST_HEAD(&mvm->aux_roc_te_list);
@@ -710,18 +698,11 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 
 	INIT_WORK(&mvm->async_handlers_wk, iwl_mvm_async_handlers_wk);
 	INIT_WORK(&mvm->roc_done_wk, iwl_mvm_roc_done_wk);
-#ifdef CONFIG_PM
-	INIT_WORK(&mvm->d0i3_exit_work, iwl_mvm_d0i3_exit_work);
-#endif
 	INIT_DELAYED_WORK(&mvm->tdls_cs.dwork, iwl_mvm_tdls_ch_switch_work);
 	INIT_DELAYED_WORK(&mvm->scan_timeout_dwork, iwl_mvm_scan_timeout_wk);
 	INIT_WORK(&mvm->add_stream_wk, iwl_mvm_add_new_dqa_stream_wk);
 	INIT_LIST_HEAD(&mvm->add_stream_txqs);
 
-	spin_lock_init(&mvm->d0i3_tx_lock);
-	spin_lock_init(&mvm->refs_lock);
-	skb_queue_head_init(&mvm->d0i3_tx);
-	init_waitqueue_head(&mvm->d0i3_exit_waitq);
 	init_waitqueue_head(&mvm->rx_sync_waitq);
 
 	atomic_set(&mvm->queue_sync_counter, 0);
@@ -832,13 +813,11 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 		goto out_free;
 
 	mutex_lock(&mvm->mutex);
-	iwl_mvm_ref(mvm, IWL_MVM_REF_INIT_UCODE);
 	err = iwl_run_init_mvm_ucode(mvm, true);
 	if (err && err != -ERFKILL)
 		iwl_fw_dbg_error_collect(&mvm->fwrt, FW_DBG_TRIGGER_DRIVER);
 	if (!iwlmvm_mod_params.init_dbg || !err)
 		iwl_mvm_stop_device(mvm);
-	iwl_mvm_unref(mvm, IWL_MVM_REF_INIT_UCODE);
 	mutex_unlock(&mvm->mutex);
 	if (err < 0) {
 		IWL_ERR(mvm, "Failed to run INIT ucode: %d\n", err);
@@ -870,11 +849,6 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	else
 		memset(&mvm->rx_stats, 0, sizeof(struct mvm_statistics_rx));
 
-	/* The transport always starts with a taken reference, we can
-	 * release it now if d0i3 is supported */
-	if (iwl_mvm_is_d0i3_supported(mvm))
-		iwl_trans_unref(mvm->trans);
-
 	iwl_mvm_toggle_tx_ant(mvm, &mvm->mgmt_last_antenna_idx);
 
 	return op_mode;
@@ -898,13 +872,6 @@ static void iwl_op_mode_mvm_stop(struct iwl_op_mode *op_mode)
 	struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode);
 	int i;
 
-	/* If d0i3 is supported, we have released the reference that
-	 * the transport started with, so we should take it back now
-	 * that we are leaving.
-	 */
-	if (iwl_mvm_is_d0i3_supported(mvm))
-		iwl_trans_ref(mvm->trans);
-
 	iwl_mvm_leds_exit(mvm);
 
 	iwl_mvm_thermal_exit(mvm);
@@ -931,7 +898,6 @@ static void iwl_op_mode_mvm_stop(struct iwl_op_mode *op_mode)
 
 	iwl_fw_runtime_free(&mvm->fwrt);
 	mutex_destroy(&mvm->mutex);
-	mutex_destroy(&mvm->d0i3_suspend_mutex);
 
 	ieee80211_free_hw(mvm->hw);
 }
@@ -1319,9 +1285,6 @@ void iwl_mvm_nic_restart(struct iwl_mvm *mvm, bool fw_error)
 	} else if (mvm->fwrt.cur_fw_img == IWL_UCODE_REGULAR &&
 		   mvm->hw_registered &&
 		   !test_bit(STATUS_TRANS_DEAD, &mvm->trans->status)) {
-		/* don't let the transport/FW power down */
-		iwl_mvm_ref(mvm, IWL_MVM_REF_UCODE_DOWN);
-
 		if (mvm->fw->ucode_capa.error_log_size) {
 			u32 src_size = mvm->fw->ucode_capa.error_log_size;
 			u32 src_addr = mvm->fw->ucode_capa.error_log_addr;
@@ -1363,422 +1326,6 @@ static void iwl_mvm_cmd_queue_full(struct iwl_op_mode *op_mode)
 	iwl_mvm_nic_restart(mvm, true);
 }
 
-#ifdef CONFIG_PM
-struct iwl_d0i3_iter_data {
-	struct iwl_mvm *mvm;
-	struct ieee80211_vif *connected_vif;
-	u8 ap_sta_id;
-	u8 vif_count;
-	u8 offloading_tid;
-	bool disable_offloading;
-};
-
-static bool iwl_mvm_disallow_offloading(struct iwl_mvm *mvm,
-					struct ieee80211_vif *vif,
-					struct iwl_d0i3_iter_data *iter_data)
-{
-	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
-	struct iwl_mvm_sta *mvmsta;
-	u32 available_tids = 0;
-	u8 tid;
-
-	if (WARN_ON(vif->type != NL80211_IFTYPE_STATION ||
-		    mvmvif->ap_sta_id == IWL_MVM_INVALID_STA))
-		return false;
-
-	mvmsta = iwl_mvm_sta_from_staid_rcu(mvm, mvmvif->ap_sta_id);
-	if (!mvmsta)
-		return false;
-
-	spin_lock_bh(&mvmsta->lock);
-	for (tid = 0; tid < IWL_MAX_TID_COUNT; tid++) {
-		struct iwl_mvm_tid_data *tid_data = &mvmsta->tid_data[tid];
-
-		/*
-		 * in case of pending tx packets, don't use this tid
-		 * for offloading in order to prevent reuse of the same
-		 * qos seq counters.
-		 */
-		if (iwl_mvm_tid_queued(mvm, tid_data))
-			continue;
-
-		if (tid_data->state != IWL_AGG_OFF)
-			continue;
-
-		available_tids |= BIT(tid);
-	}
-	spin_unlock_bh(&mvmsta->lock);
-
-	/*
-	 * disallow protocol offloading if we have no available tid
-	 * (with no pending frames and no active aggregation,
-	 * as we don't handle "holes" properly - the scheduler needs the
-	 * frame's seq number and TFD index to match)
-	 */
-	if (!available_tids)
-		return true;
-
-	/* for simplicity, just use the first available tid */
-	iter_data->offloading_tid = ffs(available_tids) - 1;
-	return false;
-}
-
-static void iwl_mvm_enter_d0i3_iterator(void *_data, u8 *mac,
-					struct ieee80211_vif *vif)
-{
-	struct iwl_d0i3_iter_data *data = _data;
-	struct iwl_mvm *mvm = data->mvm;
-	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
-	u32 flags = CMD_ASYNC | CMD_HIGH_PRIO | CMD_SEND_IN_IDLE;
-
-	IWL_DEBUG_RPM(mvm, "entering D0i3 - vif %pM\n", vif->addr);
-	if (vif->type != NL80211_IFTYPE_STATION ||
-	    !vif->bss_conf.assoc)
-		return;
-
-	/*
-	 * in case of pending tx packets or active aggregations,
-	 * avoid offloading features in order to prevent reuse of
-	 * the same qos seq counters.
-	 */
-	if (iwl_mvm_disallow_offloading(mvm, vif, data))
-		data->disable_offloading = true;
-
-	iwl_mvm_update_d0i3_power_mode(mvm, vif, true, flags);
-	iwl_mvm_send_proto_offload(mvm, vif, data->disable_offloading,
-				   false, flags);
-
-	/*
-	 * on init/association, mvm already configures POWER_TABLE_CMD
-	 * and REPLY_MCAST_FILTER_CMD, so currently don't
-	 * reconfigure them (we might want to use different
-	 * params later on, though).
-	 */
-	data->ap_sta_id = mvmvif->ap_sta_id;
-	data->vif_count++;
-
-	/*
-	 * no new commands can be sent at this stage, so it's safe
-	 * to save the vif pointer during d0i3 entrance.
-	 */
-	data->connected_vif = vif;
-}
-
-static void iwl_mvm_set_wowlan_data(struct iwl_mvm *mvm,
-				    struct iwl_wowlan_config_cmd *cmd,
-				    struct iwl_d0i3_iter_data *iter_data)
-{
-	struct ieee80211_sta *ap_sta;
-	struct iwl_mvm_sta *mvm_ap_sta;
-
-	if (iter_data->ap_sta_id == IWL_MVM_INVALID_STA)
-		return;
-
-	rcu_read_lock();
-
-	ap_sta = rcu_dereference(mvm->fw_id_to_mac_id[iter_data->ap_sta_id]);
-	if (IS_ERR_OR_NULL(ap_sta))
-		goto out;
-
-	mvm_ap_sta = iwl_mvm_sta_from_mac80211(ap_sta);
-	cmd->is_11n_connection = ap_sta->ht_cap.ht_supported;
-	cmd->offloading_tid = iter_data->offloading_tid;
-	cmd->flags = ENABLE_L3_FILTERING | ENABLE_NBNS_FILTERING |
-		ENABLE_DHCP_FILTERING | ENABLE_STORE_BEACON;
-	/*
-	 * The d0i3 uCode takes care of the nonqos counters,
-	 * so configure only the qos seq ones.
-	 */
-	iwl_mvm_set_wowlan_qos_seq(mvm_ap_sta, cmd);
-out:
-	rcu_read_unlock();
-}
-
-int iwl_mvm_enter_d0i3(struct iwl_op_mode *op_mode)
-{
-	struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode);
-	u32 flags = CMD_ASYNC | CMD_HIGH_PRIO | CMD_SEND_IN_IDLE;
-	int ret;
-	struct iwl_d0i3_iter_data d0i3_iter_data = {
-		.mvm = mvm,
-	};
-	struct iwl_wowlan_config_cmd wowlan_config_cmd = {
-		.wakeup_filter = cpu_to_le32(IWL_WOWLAN_WAKEUP_RX_FRAME |
-					     IWL_WOWLAN_WAKEUP_BEACON_MISS |
-					     IWL_WOWLAN_WAKEUP_LINK_CHANGE),
-	};
-	struct iwl_d3_manager_config d3_cfg_cmd = {
-		.min_sleep_time = cpu_to_le32(1000),
-		.wakeup_flags = cpu_to_le32(IWL_WAKEUP_D3_CONFIG_FW_ERROR),
-	};
-
-	IWL_DEBUG_RPM(mvm, "MVM entering D0i3\n");
-
-	if (WARN_ON_ONCE(mvm->fwrt.cur_fw_img != IWL_UCODE_REGULAR))
-		return -EINVAL;
-
-	set_bit(IWL_MVM_STATUS_IN_D0I3, &mvm->status);
-
-	/*
-	 * iwl_mvm_ref_sync takes a reference before checking the flag.
-	 * so by checking there is no held reference we prevent a state
-	 * in which iwl_mvm_ref_sync continues successfully while we
-	 * configure the firmware to enter d0i3
-	 */
-	if (iwl_mvm_ref_taken(mvm)) {
-		IWL_DEBUG_RPM(mvm->trans, "abort d0i3 due to taken ref\n");
-		clear_bit(IWL_MVM_STATUS_IN_D0I3, &mvm->status);
-		wake_up(&mvm->d0i3_exit_waitq);
-		return 1;
-	}
-
-	ieee80211_iterate_active_interfaces_atomic(mvm->hw,
-						   IEEE80211_IFACE_ITER_NORMAL,
-						   iwl_mvm_enter_d0i3_iterator,
-						   &d0i3_iter_data);
-	if (d0i3_iter_data.vif_count == 1) {
-		mvm->d0i3_ap_sta_id = d0i3_iter_data.ap_sta_id;
-		mvm->d0i3_offloading = !d0i3_iter_data.disable_offloading;
-	} else {
-		WARN_ON_ONCE(d0i3_iter_data.vif_count > 1);
-		mvm->d0i3_ap_sta_id = IWL_MVM_INVALID_STA;
-		mvm->d0i3_offloading = false;
-	}
-
-	iwl_mvm_pause_tcm(mvm, true);
-	/* make sure we have no running tx while configuring the seqno */
-	synchronize_net();
-
-	/* Flush the hw queues, in case something got queued during entry */
-	/* TODO new tx api */
-	if (iwl_mvm_has_new_tx_api(mvm)) {
-		WARN_ONCE(1, "d0i3: Need to implement flush TX queue\n");
-	} else {
-		ret = iwl_mvm_flush_tx_path(mvm, iwl_mvm_flushable_queues(mvm),
-					    flags);
-		if (ret)
-			return ret;
-	}
-
-	/* configure wowlan configuration only if needed */
-	if (mvm->d0i3_ap_sta_id != IWL_MVM_INVALID_STA) {
-		/* wake on beacons only if beacon storing isn't supported */
-		if (!fw_has_capa(&mvm->fw->ucode_capa,
-				 IWL_UCODE_TLV_CAPA_BEACON_STORING))
-			wowlan_config_cmd.wakeup_filter |=
-				cpu_to_le32(IWL_WOWLAN_WAKEUP_BCN_FILTERING);
-
-		iwl_mvm_wowlan_config_key_params(mvm,
-						 d0i3_iter_data.connected_vif,
-						 true, flags);
-
-		iwl_mvm_set_wowlan_data(mvm, &wowlan_config_cmd,
-					&d0i3_iter_data);
-
-		ret = iwl_mvm_send_cmd_pdu(mvm, WOWLAN_CONFIGURATION, flags,
-					   sizeof(wowlan_config_cmd),
-					   &wowlan_config_cmd);
-		if (ret)
-			return ret;
-	}
-
-	return iwl_mvm_send_cmd_pdu(mvm, D3_CONFIG_CMD,
-				    flags | CMD_MAKE_TRANS_IDLE,
-				    sizeof(d3_cfg_cmd), &d3_cfg_cmd);
-}
-
-static void iwl_mvm_exit_d0i3_iterator(void *_data, u8 *mac,
-				       struct ieee80211_vif *vif)
-{
-	struct iwl_mvm *mvm = _data;
-	u32 flags = CMD_ASYNC | CMD_HIGH_PRIO;
-
-	IWL_DEBUG_RPM(mvm, "exiting D0i3 - vif %pM\n", vif->addr);
-	if (vif->type != NL80211_IFTYPE_STATION ||
-	    !vif->bss_conf.assoc)
-		return;
-
-	iwl_mvm_update_d0i3_power_mode(mvm, vif, false, flags);
-}
-
-struct iwl_mvm_d0i3_exit_work_iter_data {
-	struct iwl_mvm *mvm;
-	struct iwl_wowlan_status *status;
-	u32 wakeup_reasons;
-};
-
-static void iwl_mvm_d0i3_exit_work_iter(void *_data, u8 *mac,
-					struct ieee80211_vif *vif)
-{
-	struct iwl_mvm_d0i3_exit_work_iter_data *data = _data;
-	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
-	u32 reasons = data->wakeup_reasons;
-
-	/* consider only the relevant station interface */
-	if (vif->type != NL80211_IFTYPE_STATION || !vif->bss_conf.assoc ||
-	    data->mvm->d0i3_ap_sta_id != mvmvif->ap_sta_id)
-		return;
-
-	if (reasons & IWL_WOWLAN_WAKEUP_BY_DISCONNECTION_ON_DEAUTH)
-		iwl_mvm_connection_loss(data->mvm, vif, "D0i3");
-	else if (reasons & IWL_WOWLAN_WAKEUP_BY_DISCONNECTION_ON_MISSED_BEACON)
-		ieee80211_beacon_loss(vif);
-	else
-		iwl_mvm_d0i3_update_keys(data->mvm, vif, data->status);
-}
-
-void iwl_mvm_d0i3_enable_tx(struct iwl_mvm *mvm, __le16 *qos_seq)
-{
-	struct ieee80211_sta *sta = NULL;
-	struct iwl_mvm_sta *mvm_ap_sta;
-	int i;
-	bool wake_queues = false;
-
-	lockdep_assert_held(&mvm->mutex);
-
-	spin_lock_bh(&mvm->d0i3_tx_lock);
-
-	if (mvm->d0i3_ap_sta_id == IWL_MVM_INVALID_STA)
-		goto out;
-
-	IWL_DEBUG_RPM(mvm, "re-enqueue packets\n");
-
-	/* get the sta in order to update seq numbers and re-enqueue skbs */
-	sta = rcu_dereference_protected(
-			mvm->fw_id_to_mac_id[mvm->d0i3_ap_sta_id],
-			lockdep_is_held(&mvm->mutex));
-
-	if (IS_ERR_OR_NULL(sta)) {
-		sta = NULL;
-		goto out;
-	}
-
-	if (mvm->d0i3_offloading && qos_seq) {
-		/* update qos seq numbers if offloading was enabled */
-		mvm_ap_sta = iwl_mvm_sta_from_mac80211(sta);
-		for (i = 0; i < IWL_MAX_TID_COUNT; i++) {
-			u16 seq = le16_to_cpu(qos_seq[i]);
-			/* firmware stores last-used one, we store next one */
-			seq += 0x10;
-			mvm_ap_sta->tid_data[i].seq_number = seq;
-		}
-	}
-out:
-	/* re-enqueue (or drop) all packets */
-	while (!skb_queue_empty(&mvm->d0i3_tx)) {
-		struct sk_buff *skb = __skb_dequeue(&mvm->d0i3_tx);
-
-		if (!sta || iwl_mvm_tx_skb(mvm, skb, sta))
-			ieee80211_free_txskb(mvm->hw, skb);
-
-		/* if the skb_queue is not empty, we need to wake queues */
-		wake_queues = true;
-	}
-	clear_bit(IWL_MVM_STATUS_IN_D0I3, &mvm->status);
-	wake_up(&mvm->d0i3_exit_waitq);
-	mvm->d0i3_ap_sta_id = IWL_MVM_INVALID_STA;
-	if (wake_queues)
-		ieee80211_wake_queues(mvm->hw);
-
-	spin_unlock_bh(&mvm->d0i3_tx_lock);
-}
-
-static void iwl_mvm_d0i3_exit_work(struct work_struct *wk)
-{
-	struct iwl_mvm *mvm = container_of(wk, struct iwl_mvm, d0i3_exit_work);
-	struct iwl_mvm_d0i3_exit_work_iter_data iter_data = {
-		.mvm = mvm,
-	};
-
-	struct iwl_wowlan_status *status;
-	u32 wakeup_reasons = 0;
-	__le16 *qos_seq = NULL;
-
-	mutex_lock(&mvm->mutex);
-
-	status = iwl_mvm_send_wowlan_get_status(mvm);
-	if (IS_ERR_OR_NULL(status)) {
-		/* set to NULL so we don't need to check before kfree'ing */
-		status = NULL;
-		goto out;
-	}
-
-	wakeup_reasons = le32_to_cpu(status->wakeup_reasons);
-	qos_seq = status->qos_seq_ctr;
-
-	IWL_DEBUG_RPM(mvm, "wakeup reasons: 0x%x\n", wakeup_reasons);
-
-	iter_data.wakeup_reasons = wakeup_reasons;
-	iter_data.status = status;
-	ieee80211_iterate_active_interfaces(mvm->hw,
-					    IEEE80211_IFACE_ITER_NORMAL,
-					    iwl_mvm_d0i3_exit_work_iter,
-					    &iter_data);
-out:
-	iwl_mvm_d0i3_enable_tx(mvm, qos_seq);
-
-	IWL_DEBUG_INFO(mvm, "d0i3 exit completed (wakeup reasons: 0x%x)\n",
-		       wakeup_reasons);
-
-	/* qos_seq might point inside resp_pkt, so free it only now */
-	kfree(status);
-
-	/* the FW might have updated the regdomain */
-	iwl_mvm_update_changed_regdom(mvm);
-
-	iwl_mvm_resume_tcm(mvm);
-	iwl_mvm_unref(mvm, IWL_MVM_REF_EXIT_WORK);
-	mutex_unlock(&mvm->mutex);
-}
-
-int _iwl_mvm_exit_d0i3(struct iwl_mvm *mvm)
-{
-	u32 flags = CMD_ASYNC | CMD_HIGH_PRIO | CMD_SEND_IN_IDLE |
-		    CMD_WAKE_UP_TRANS;
-	int ret;
-
-	IWL_DEBUG_RPM(mvm, "MVM exiting D0i3\n");
-
-	if (WARN_ON_ONCE(mvm->fwrt.cur_fw_img != IWL_UCODE_REGULAR))
-		return -EINVAL;
-
-	mutex_lock(&mvm->d0i3_suspend_mutex);
-	if (test_bit(D0I3_DEFER_WAKEUP, &mvm->d0i3_suspend_flags)) {
-		IWL_DEBUG_RPM(mvm, "Deferring d0i3 exit until resume\n");
-		__set_bit(D0I3_PENDING_WAKEUP, &mvm->d0i3_suspend_flags);
-		mutex_unlock(&mvm->d0i3_suspend_mutex);
-		return 0;
-	}
-	mutex_unlock(&mvm->d0i3_suspend_mutex);
-
-	ret = iwl_mvm_send_cmd_pdu(mvm, D0I3_END_CMD, flags, 0, NULL);
-	if (ret)
-		goto out;
-
-	ieee80211_iterate_active_interfaces_atomic(mvm->hw,
-						   IEEE80211_IFACE_ITER_NORMAL,
-						   iwl_mvm_exit_d0i3_iterator,
-						   mvm);
-out:
-	schedule_work(&mvm->d0i3_exit_work);
-	return ret;
-}
-
-int iwl_mvm_exit_d0i3(struct iwl_op_mode *op_mode)
-{
-	struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode);
-
-	iwl_mvm_ref(mvm, IWL_MVM_REF_EXIT_WORK);
-	return _iwl_mvm_exit_d0i3(mvm);
-}
-
-#define IWL_MVM_D0I3_OPS					\
-	.enter_d0i3 = iwl_mvm_enter_d0i3,			\
-	.exit_d0i3 = iwl_mvm_exit_d0i3,
-#else /* CONFIG_PM */
-#define IWL_MVM_D0I3_OPS
-#endif /* CONFIG_PM */
-
 #define IWL_MVM_COMMON_OPS					\
 	/* these could be differentiated */			\
 	.async_cb = iwl_mvm_async_cb,				\
@@ -1789,7 +1336,6 @@ int iwl_mvm_exit_d0i3(struct iwl_op_mode *op_mode)
 	.nic_error = iwl_mvm_nic_error,				\
 	.cmd_queue_full = iwl_mvm_cmd_queue_full,		\
 	.nic_config = iwl_mvm_nic_config,			\
-	IWL_MVM_D0I3_OPS					\
 	/* as we only register one, these MUST be common! */	\
 	.start = iwl_op_mode_mvm_start,				\
 	.stop = iwl_op_mode_mvm_stop
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/power.c b/drivers/net/wireless/intel/iwlwifi/mvm/power.c
index 36f5fa1ee793..22136e4832ea 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/power.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/power.c
@@ -127,12 +127,11 @@ int iwl_mvm_beacon_filter_send_cmd(struct iwl_mvm *mvm,
 static
 void iwl_mvm_beacon_filter_set_cqm_params(struct iwl_mvm *mvm,
 					  struct ieee80211_vif *vif,
-					  struct iwl_beacon_filter_cmd *cmd,
-					  bool d0i3)
+					  struct iwl_beacon_filter_cmd *cmd)
 {
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
 
-	if (vif->bss_conf.cqm_rssi_thold && !d0i3) {
+	if (vif->bss_conf.cqm_rssi_thold) {
 		cmd->bf_energy_delta =
 			cpu_to_le32(vif->bss_conf.cqm_rssi_hyst);
 		/* fw uses an absolute value for this */
@@ -849,8 +848,7 @@ iwl_mvm_beacon_filter_debugfs_parameters(struct ieee80211_vif *vif,
 static int _iwl_mvm_enable_beacon_filter(struct iwl_mvm *mvm,
 					 struct ieee80211_vif *vif,
 					 struct iwl_beacon_filter_cmd *cmd,
-					 u32 cmd_flags,
-					 bool d0i3)
+					 u32 cmd_flags)
 {
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
 	int ret;
@@ -859,13 +857,11 @@ static int _iwl_mvm_enable_beacon_filter(struct iwl_mvm *mvm,
 	    vif->type != NL80211_IFTYPE_STATION || vif->p2p)
 		return 0;
 
-	iwl_mvm_beacon_filter_set_cqm_params(mvm, vif, cmd, d0i3);
-	if (!d0i3)
-		iwl_mvm_beacon_filter_debugfs_parameters(vif, cmd);
+	iwl_mvm_beacon_filter_set_cqm_params(mvm, vif, cmd);
+	iwl_mvm_beacon_filter_debugfs_parameters(vif, cmd);
 	ret = iwl_mvm_beacon_filter_send_cmd(mvm, cmd, cmd_flags);
 
-	/* don't change bf_enabled in case of temporary d0i3 configuration */
-	if (!ret && !d0i3)
+	if (!ret)
 		mvmvif->bf_data.bf_enabled = true;
 
 	return ret;
@@ -880,12 +876,12 @@ int iwl_mvm_enable_beacon_filter(struct iwl_mvm *mvm,
 		.bf_enable_beacon_filter = cpu_to_le32(1),
 	};
 
-	return _iwl_mvm_enable_beacon_filter(mvm, vif, &cmd, flags, false);
+	return _iwl_mvm_enable_beacon_filter(mvm, vif, &cmd, flags);
 }
 
 static int _iwl_mvm_disable_beacon_filter(struct iwl_mvm *mvm,
 					  struct ieee80211_vif *vif,
-					  u32 flags, bool d0i3)
+					  u32 flags)
 {
 	struct iwl_beacon_filter_cmd cmd = {};
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
@@ -896,8 +892,7 @@ static int _iwl_mvm_disable_beacon_filter(struct iwl_mvm *mvm,
 
 	ret = iwl_mvm_beacon_filter_send_cmd(mvm, &cmd, flags);
 
-	/* don't change bf_enabled in case of temporary d0i3 configuration */
-	if (!ret && !d0i3)
+	if (!ret)
 		mvmvif->bf_data.bf_enabled = false;
 
 	return ret;
@@ -907,7 +902,7 @@ int iwl_mvm_disable_beacon_filter(struct iwl_mvm *mvm,
 				  struct ieee80211_vif *vif,
 				  u32 flags)
 {
-	return _iwl_mvm_disable_beacon_filter(mvm, vif, flags, false);
+	return _iwl_mvm_disable_beacon_filter(mvm, vif, flags);
 }
 
 static int iwl_mvm_power_set_ps(struct iwl_mvm *mvm)
@@ -958,7 +953,7 @@ static int iwl_mvm_power_set_ba(struct iwl_mvm *mvm,
 				       !vif->bss_conf.ps ||
 				       iwl_mvm_vif_low_latency(mvmvif));
 
-	return _iwl_mvm_enable_beacon_filter(mvm, vif, &cmd, 0, false);
+	return _iwl_mvm_enable_beacon_filter(mvm, vif, &cmd, 0);
 }
 
 int iwl_mvm_power_update_ps(struct iwl_mvm *mvm)
@@ -1022,58 +1017,3 @@ int iwl_mvm_power_update_mac(struct iwl_mvm *mvm)
 
 	return 0;
 }
-
-int iwl_mvm_update_d0i3_power_mode(struct iwl_mvm *mvm,
-				   struct ieee80211_vif *vif,
-				   bool enable, u32 flags)
-{
-	int ret;
-	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
-	struct iwl_mac_power_cmd cmd = {};
-
-	if (vif->type != NL80211_IFTYPE_STATION || vif->p2p)
-		return 0;
-
-	if (!vif->bss_conf.assoc)
-		return 0;
-
-	iwl_mvm_power_build_cmd(mvm, vif, &cmd, !enable);
-
-	iwl_mvm_power_log(mvm, &cmd);
-#ifdef CONFIG_IWLWIFI_DEBUGFS
-	memcpy(&mvmvif->mac_pwr_cmd, &cmd, sizeof(cmd));
-#endif
-	ret = iwl_mvm_send_cmd_pdu(mvm, MAC_PM_POWER_TABLE, flags,
-				   sizeof(cmd), &cmd);
-	if (ret)
-		return ret;
-
-	/* configure beacon filtering */
-	if (mvmvif != mvm->bf_allowed_vif)
-		return 0;
-
-	if (enable) {
-		struct iwl_beacon_filter_cmd cmd_bf = {
-			IWL_BF_CMD_CONFIG_D0I3,
-			.bf_enable_beacon_filter = cpu_to_le32(1),
-		};
-		/*
-		 * When beacon storing is supported - disable beacon filtering
-		 * altogether - the latest beacon will be sent when exiting d0i3
-		 */
-		if (fw_has_capa(&mvm->fw->ucode_capa,
-				IWL_UCODE_TLV_CAPA_BEACON_STORING))
-			ret = _iwl_mvm_disable_beacon_filter(mvm, vif, flags,
-							     true);
-		else
-			ret = _iwl_mvm_enable_beacon_filter(mvm, vif, &cmd_bf,
-							    flags, true);
-	} else {
-		if (mvmvif->bf_data.bf_enabled)
-			ret = iwl_mvm_enable_beacon_filter(mvm, vif, flags);
-		else
-			ret = iwl_mvm_disable_beacon_filter(mvm, vif, flags);
-	}
-
-	return ret;
-}
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
index be62f499c595..f973e9f4862f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
@@ -148,7 +148,11 @@ static u16 rs_fw_get_config_flags(struct iwl_mvm *mvm,
 	     (vht_ena && (vht_cap->cap & IEEE80211_VHT_CAP_RXLDPC))))
 		flags |= IWL_TLC_MNG_CFG_FLAGS_LDPC_MSK;
 
-	/* consider our LDPC support in case of HE */
+	/* consider LDPC support in case of HE */
+	if (he_cap->has_he && (he_cap->he_cap_elem.phy_cap_info[1] &
+	    IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD))
+		flags |= IWL_TLC_MNG_CFG_FLAGS_LDPC_MSK;
+
 	if (sband->iftype_data && sband->iftype_data->he_cap.has_he &&
 	    !(sband->iftype_data->he_cap.he_cap_elem.phy_cap_info[1] &
 	     IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD))
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
index dd34d07aeaf8..e5b7f7e4cad4 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
@@ -3671,7 +3671,7 @@ static void rs_fill_lq_cmd(struct iwl_mvm *mvm,
 			cpu_to_le16(iwl_mvm_coex_agg_time_limit(mvm, sta));
 }
 
-static void *rs_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir)
+static void *rs_alloc(struct ieee80211_hw *hw)
 {
 	return hw->priv;
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
index a231c5a82b60..8ce50833deeb 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
@@ -8,6 +8,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 - 2020 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -29,6 +30,8 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
+ * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 - 2020 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -350,7 +353,6 @@ void iwl_mvm_rx_rx_mpdu(struct iwl_mvm *mvm, struct napi_struct *napi,
 	u32 rate_n_flags;
 	u32 rx_pkt_status;
 	u8 crypt_len = 0;
-	bool take_ref;
 
 	phy_info = &mvm->last_phy_info;
 	rx_res = (struct iwl_rx_mpdu_res_start *)pkt->data;
@@ -558,26 +560,13 @@ void iwl_mvm_rx_rx_mpdu(struct iwl_mvm *mvm, struct napi_struct *napi,
 		     ieee80211_is_probe_resp(hdr->frame_control)))
 		rx_status->boottime_ns = ktime_get_boot_ns();
 
-	/* Take a reference briefly to kick off a d0i3 entry delay so
-	 * we can handle bursts of RX packets without toggling the
-	 * state too often.  But don't do this for beacons if we are
-	 * going to idle because the beacon filtering changes we make
-	 * cause the firmware to send us collateral beacons. */
-	take_ref = !(test_bit(STATUS_TRANS_GOING_IDLE, &mvm->trans->status) &&
-		     ieee80211_is_beacon(hdr->frame_control));
-
-	if (take_ref)
-		iwl_mvm_ref(mvm, IWL_MVM_REF_RX);
-
 	iwl_mvm_pass_packet_to_mac80211(mvm, sta, napi, skb, hdr, len,
 					crypt_len, rxb);
-
-	if (take_ref)
-		iwl_mvm_unref(mvm, IWL_MVM_REF_RX);
 }
 
 struct iwl_mvm_stat_data {
 	struct iwl_mvm *mvm;
+	__le32 flags;
 	__le32 mac_id;
 	u8 beacon_filter_average_energy;
 	void *general;
@@ -618,6 +607,13 @@ static void iwl_mvm_stat_iterator(void *_data, u8 *mac,
 			-general->beacon_average_energy[vif_id];
 	}
 
+	/* make sure that beacon statistics don't go backwards with TCM
+	 * request to clear statistics
+	 */
+	if (le32_to_cpu(data->flags) & IWL_STATISTICS_REPLY_FLG_CLEAR)
+		mvmvif->beacon_stats.accu_num_beacons +=
+			mvmvif->beacon_stats.num_beacons;
+
 	if (mvmvif->id != id)
 		return;
 
@@ -775,6 +771,7 @@ void iwl_mvm_handle_rx_statistics(struct iwl_mvm *mvm,
 
 		flags = stats->flag;
 	}
+	data.flags = flags;
 
 	iwl_mvm_rx_stats_check_trigger(mvm, pkt);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index d9ddf9ff6428..b0d877250602 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -510,7 +510,6 @@ void iwl_mvm_rx_lmac_scan_complete_notif(struct iwl_mvm *mvm,
 
 		mvm->scan_status &= ~IWL_MVM_SCAN_REGULAR;
 		ieee80211_scan_completed(mvm->hw, &info);
-		iwl_mvm_unref(mvm, IWL_MVM_REF_SCAN);
 		cancel_delayed_work(&mvm->scan_timeout_dwork);
 		iwl_mvm_resume_tcm(mvm);
 	} else {
@@ -1752,7 +1751,6 @@ int iwl_mvm_reg_scan_start(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	IWL_DEBUG_SCAN(mvm, "Scan request was sent successfully\n");
 	mvm->scan_status |= IWL_MVM_SCAN_REGULAR;
 	mvm->scan_vif = iwl_mvm_vif_from_mac80211(vif);
-	iwl_mvm_ref(mvm, IWL_MVM_REF_SCAN);
 
 	schedule_delayed_work(&mvm->scan_timeout_dwork,
 			      msecs_to_jiffies(SCAN_TIMEOUT));
@@ -1878,7 +1876,6 @@ void iwl_mvm_rx_umac_scan_complete_notif(struct iwl_mvm *mvm,
 		memcpy(info.tsf_bssid, mvm->scan_vif->bssid, ETH_ALEN);
 		ieee80211_scan_completed(mvm->hw, &info);
 		mvm->scan_vif = NULL;
-		iwl_mvm_unref(mvm, IWL_MVM_REF_SCAN);
 		cancel_delayed_work(&mvm->scan_timeout_dwork);
 		iwl_mvm_resume_tcm(mvm);
 	} else if (mvm->scan_uid_status[uid] == IWL_MVM_SCAN_SCHED) {
@@ -2093,10 +2090,6 @@ out:
 	mvm->scan_status &= ~type;
 
 	if (type == IWL_MVM_SCAN_REGULAR) {
-		/* Since the rx handler won't do anything now, we have
-		 * to release the scan reference here.
-		 */
-		iwl_mvm_unref(mvm, IWL_MVM_REF_SCAN);
 		cancel_delayed_work(&mvm->scan_timeout_dwork);
 		if (notify) {
 			struct cfg80211_scan_info info = {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index 946d4cd30694..a2e03190e7e2 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -730,6 +730,11 @@ static int iwl_mvm_find_free_queue(struct iwl_mvm *mvm, u8 sta_id,
 
 	lockdep_assert_held(&mvm->mutex);
 
+	if (WARN(maxq >= mvm->trans->cfg->base_params->num_of_queues,
+		 "max queue %d >= num_of_queues (%d)", maxq,
+		 mvm->trans->cfg->base_params->num_of_queues))
+		maxq = mvm->trans->cfg->base_params->num_of_queues - 1;
+
 	/* This should not be hit with new TX path */
 	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
 		return -ENOSPC;
@@ -1895,10 +1900,6 @@ int iwl_mvm_rm_sta(struct iwl_mvm *mvm,
 
 		/* unassoc - go ahead - remove the AP STA now */
 		mvmvif->ap_sta_id = IWL_MVM_INVALID_STA;
-
-		/* clear d0i3_ap_sta_id if no longer relevant */
-		if (mvm->d0i3_ap_sta_id == sta_id)
-			mvm->d0i3_ap_sta_id = IWL_MVM_INVALID_STA;
 	}
 
 	/*
@@ -2070,16 +2071,24 @@ int iwl_mvm_rm_snif_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 	return ret;
 }
 
-void iwl_mvm_dealloc_snif_sta(struct iwl_mvm *mvm)
+int iwl_mvm_rm_aux_sta(struct iwl_mvm *mvm)
 {
-	iwl_mvm_dealloc_int_sta(mvm, &mvm->snif_sta);
-}
+	int ret;
 
-void iwl_mvm_del_aux_sta(struct iwl_mvm *mvm)
-{
 	lockdep_assert_held(&mvm->mutex);
 
+	iwl_mvm_disable_txq(mvm, NULL, mvm->aux_queue, IWL_MAX_TID_COUNT, 0);
+	ret = iwl_mvm_rm_sta_common(mvm, mvm->aux_sta.sta_id);
+	if (ret)
+		IWL_WARN(mvm, "Failed sending remove station\n");
 	iwl_mvm_dealloc_int_sta(mvm, &mvm->aux_sta);
+
+	return ret;
+}
+
+void iwl_mvm_dealloc_snif_sta(struct iwl_mvm *mvm)
+{
+	iwl_mvm_dealloc_int_sta(mvm, &mvm->snif_sta);
 }
 
 /*
@@ -2771,13 +2780,6 @@ int iwl_mvm_sta_tx_agg_start(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 
 	spin_lock_bh(&mvmsta->lock);
 
-	/* possible race condition - we entered D0i3 while starting agg */
-	if (test_bit(IWL_MVM_STATUS_IN_D0I3, &mvm->status)) {
-		spin_unlock_bh(&mvmsta->lock);
-		IWL_ERR(mvm, "Entered D0i3 while starting Tx agg\n");
-		return -EIO;
-	}
-
 	/*
 	 * Note the possible cases:
 	 *  1. An enabled TXQ - TXQ needs to become agg'ed
@@ -3314,6 +3316,10 @@ static int iwl_mvm_send_sta_igtk(struct iwl_mvm *mvm,
 	igtk_cmd.sta_id = cpu_to_le32(sta_id);
 
 	if (remove_key) {
+		/* This is a valid situation for IGTK */
+		if (sta_id == IWL_MVM_INVALID_STA)
+			return 0;
+
 		igtk_cmd.ctrl_flags |= cpu_to_le32(STA_KEY_NOT_VALID);
 	} else {
 		struct ieee80211_key_seq seq;
@@ -3568,9 +3574,9 @@ int iwl_mvm_remove_sta_key(struct iwl_mvm *mvm,
 	IWL_DEBUG_WEP(mvm, "mvm remove dynamic key: idx=%d sta=%d\n",
 		      keyconf->keyidx, sta_id);
 
-	if (mvm_sta && (keyconf->cipher == WLAN_CIPHER_SUITE_AES_CMAC ||
-			keyconf->cipher == WLAN_CIPHER_SUITE_BIP_GMAC_128 ||
-			keyconf->cipher == WLAN_CIPHER_SUITE_BIP_GMAC_256))
+	if (keyconf->cipher == WLAN_CIPHER_SUITE_AES_CMAC ||
+	    keyconf->cipher == WLAN_CIPHER_SUITE_BIP_GMAC_128 ||
+	    keyconf->cipher == WLAN_CIPHER_SUITE_BIP_GMAC_256)
 		return iwl_mvm_send_sta_igtk(mvm, keyconf, sta_id, true);
 
 	if (!__test_and_clear_bit(keyconf->hw_key_idx, mvm->fw_key_table)) {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
index b4d4071b865d..d744ca656f2f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
@@ -8,7 +8,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
  * Copyright(c) 2015 - 2016 Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2018 - 2020 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -31,7 +31,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
  * Copyright(c) 2015 - 2016 Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2018 - 2020 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -529,7 +529,7 @@ int iwl_mvm_sta_tx_agg(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
 		       int tid, u8 queue, bool start);
 
 int iwl_mvm_add_aux_sta(struct iwl_mvm *mvm);
-void iwl_mvm_del_aux_sta(struct iwl_mvm *mvm);
+int iwl_mvm_rm_aux_sta(struct iwl_mvm *mvm);
 
 int iwl_mvm_alloc_bcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif);
 int iwl_mvm_send_add_bcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c b/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c
index 9df21a8d1fc1..1851719e9f4b 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c
@@ -205,19 +205,10 @@ void iwl_mvm_mac_mgd_protect_tdls_discover(struct ieee80211_hw *hw,
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 	u32 duration = 2 * vif->bss_conf.dtim_period * vif->bss_conf.beacon_int;
 
-	/*
-	 * iwl_mvm_protect_session() reads directly from the device
-	 * (the system time), so make sure it is available.
-	 */
-	if (iwl_mvm_ref_sync(mvm, IWL_MVM_REF_PROTECT_TDLS))
-		return;
-
 	mutex_lock(&mvm->mutex);
 	/* Protect the session to hear the TDLS setup response on the channel */
 	iwl_mvm_protect_session(mvm, vif, duration, duration, 100, true);
 	mutex_unlock(&mvm->mutex);
-
-	iwl_mvm_unref(mvm, IWL_MVM_REF_PROTECT_TDLS);
 }
 
 static const char *
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
index 4d34e5ab1bff..a06bc63fb516 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
@@ -106,10 +106,8 @@ void iwl_mvm_roc_done_wk(struct work_struct *wk)
 	 * in the case that the time event actually completed in the firmware
 	 * (which is handled in iwl_mvm_te_handle_notif).
 	 */
-	if (test_and_clear_bit(IWL_MVM_STATUS_ROC_RUNNING, &mvm->status))
-		iwl_mvm_unref(mvm, IWL_MVM_REF_ROC);
-	if (test_and_clear_bit(IWL_MVM_STATUS_ROC_AUX_RUNNING, &mvm->status))
-		iwl_mvm_unref(mvm, IWL_MVM_REF_ROC_AUX);
+	clear_bit(IWL_MVM_STATUS_ROC_RUNNING, &mvm->status);
+	clear_bit(IWL_MVM_STATUS_ROC_AUX_RUNNING, &mvm->status);
 
 	synchronize_net();
 
@@ -357,7 +355,6 @@ static void iwl_mvm_te_handle_notif(struct iwl_mvm *mvm,
 
 		if (te_data->vif->type == NL80211_IFTYPE_P2P_DEVICE) {
 			set_bit(IWL_MVM_STATUS_ROC_RUNNING, &mvm->status);
-			iwl_mvm_ref(mvm, IWL_MVM_REF_ROC);
 			ieee80211_ready_on_channel(mvm->hw);
 		} else if (te_data->id == TE_CHANNEL_SWITCH_PERIOD) {
 			iwl_mvm_te_handle_notify_csa(mvm, te_data, notif);
@@ -405,7 +402,6 @@ static int iwl_mvm_aux_roc_te_handle_notif(struct iwl_mvm *mvm,
 	} else if (le32_to_cpu(notif->action) == TE_V2_NOTIF_HOST_EVENT_START) {
 		set_bit(IWL_MVM_STATUS_ROC_AUX_RUNNING, &mvm->status);
 		te_data->running = true;
-		iwl_mvm_ref(mvm, IWL_MVM_REF_ROC_AUX);
 		ieee80211_ready_on_channel(mvm->hw); /* Start TE */
 	} else {
 		IWL_DEBUG_TE(mvm,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
index 0b3e5c99d316..89cecb4489f4 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
@@ -5,7 +5,7 @@
  *
  * GPL LICENSE SUMMARY
  *
- * Copyright(c) 2013 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2013 - 2014, 2019 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
  * Copyright(c) 2015 - 2016 Intel Deutschland GmbH
  *
@@ -27,7 +27,7 @@
  *
  * BSD LICENSE
  *
- * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2012 - 2014, 2019 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
  * Copyright(c) 2015 - 2016 Intel Deutschland GmbH
  * All rights reserved.
@@ -298,16 +298,8 @@ static void check_exit_ctkill(struct work_struct *work)
 	if (__iwl_mvm_mac_start(mvm))
 		goto reschedule;
 
-	/* make sure the device is available for direct read/writes */
-	if (iwl_mvm_ref_sync(mvm, IWL_MVM_REF_CHECK_CTKILL)) {
-		__iwl_mvm_mac_stop(mvm);
-		goto reschedule;
-	}
-
 	ret = iwl_mvm_get_temp(mvm, &temp);
 
-	iwl_mvm_unref(mvm, IWL_MVM_REF_CHECK_CTKILL);
-
 	__iwl_mvm_mac_stop(mvm);
 
 	if (ret)
@@ -734,7 +726,8 @@ static  struct thermal_zone_device_ops tzone_ops = {
 static void iwl_mvm_thermal_zone_register(struct iwl_mvm *mvm)
 {
 	int i;
-	char name[] = "iwlwifi";
+	char name[16];
+	static atomic_t counter = ATOMIC_INIT(0);
 
 	if (!iwl_mvm_is_tt_in_fw(mvm)) {
 		mvm->tz_device.tzone = NULL;
@@ -744,6 +737,7 @@ static void iwl_mvm_thermal_zone_register(struct iwl_mvm *mvm)
 
 	BUILD_BUG_ON(ARRAY_SIZE(name) >= THERMAL_NAME_LENGTH);
 
+	sprintf(name, "iwlwifi_%u", atomic_inc_return(&counter) & 0xFF);
 	mvm->tz_device.tzone = thermal_zone_device_register(name,
 							IWL_MAX_DTS_TRIPS,
 							IWL_WRITABLE_TRIPS_MSK,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index a12ee20fb9ab..f562b7ac864e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -1151,7 +1151,7 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb,
 	if (WARN_ONCE(txq_id == IWL_MVM_INVALID_QUEUE, "Invalid TXQ id")) {
 		iwl_trans_free_tx_cmd(mvm->trans, dev_cmd);
 		spin_unlock(&mvmsta->lock);
-		return 0;
+		return -1;
 	}
 
 	if (!iwl_mvm_has_new_tx_api(mvm)) {
@@ -1202,8 +1202,8 @@ drop:
 	return -1;
 }
 
-int iwl_mvm_tx_skb(struct iwl_mvm *mvm, struct sk_buff *skb,
-		   struct ieee80211_sta *sta)
+int iwl_mvm_tx_skb_sta(struct iwl_mvm *mvm, struct sk_buff *skb,
+		       struct ieee80211_sta *sta)
 {
 	struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
 	struct ieee80211_tx_info info;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
index a71277de2e0e..b0795dea64ad 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
@@ -88,17 +88,11 @@ int iwl_mvm_send_cmd(struct iwl_mvm *mvm, struct iwl_host_cmd *cmd)
 	 * the mutex, this ensures we don't try to send two
 	 * (or more) synchronous commands at a time.
 	 */
-	if (!(cmd->flags & CMD_ASYNC)) {
+	if (!(cmd->flags & CMD_ASYNC))
 		lockdep_assert_held(&mvm->mutex);
-		if (!(cmd->flags & CMD_SEND_IN_IDLE))
-			iwl_mvm_ref(mvm, IWL_MVM_REF_SENDING_CMD);
-	}
 
 	ret = iwl_trans_send_cmd(mvm->trans, cmd);
 
-	if (!(cmd->flags & (CMD_ASYNC | CMD_SEND_IN_IDLE)))
-		iwl_mvm_unref(mvm, IWL_MVM_REF_SENDING_CMD);
-
 	/*
 	 * If the caller wants the SKB, then don't hide any problems, the
 	 * caller might access the response buffer which will be NULL if
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index 07255a289579..319b398c715c 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -1306,6 +1306,9 @@ void iwl_trans_pcie_dyn_txq_free(struct iwl_trans *trans, int queue)
 
 	iwl_pcie_gen2_txq_unmap(trans, queue);
 
+	iwl_pcie_gen2_txq_free_memory(trans, trans_pcie->txq[queue]);
+	trans_pcie->txq[queue] = NULL;
+
 	IWL_DEBUG_TX_QUEUES(trans, "Deactivate queue %d\n", queue);
 }
 
diff --git a/drivers/net/wireless/intersil/hostap/hostap_ap.c b/drivers/net/wireless/intersil/hostap/hostap_ap.c
index 0094b1d2b577..3ec46f48cfde 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_ap.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_ap.c
@@ -2508,7 +2508,7 @@ static int prism2_hostapd_add_sta(struct ap_data *ap,
 		sta->supported_rates[0] = 2;
 	if (sta->tx_supp_rates & WLAN_RATE_2M)
 		sta->supported_rates[1] = 4;
- 	if (sta->tx_supp_rates & WLAN_RATE_5M5)
+	if (sta->tx_supp_rates & WLAN_RATE_5M5)
 		sta->supported_rates[2] = 11;
 	if (sta->tx_supp_rates & WLAN_RATE_11M)
 		sta->supported_rates[3] = 22;
diff --git a/drivers/net/wireless/intersil/orinoco/orinoco_usb.c b/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
index 40a8b941ad5c..e753f43e0162 100644
--- a/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
+++ b/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
@@ -1361,7 +1361,8 @@ static int ezusb_init(struct hermes *hw)
 	int retval;
 
 	BUG_ON(in_interrupt());
-	BUG_ON(!upriv);
+	if (!upriv)
+		return -EINVAL;
 
 	upriv->reply_count = 0;
 	/* Write the MAGIC number on the simulated registers to keep
@@ -1608,9 +1609,9 @@ static int ezusb_probe(struct usb_interface *interface,
 	/* set up the endpoint information */
 	/* check out the endpoints */
 
-	iface_desc = &interface->altsetting[0].desc;
+	iface_desc = &interface->cur_altsetting->desc;
 	for (i = 0; i < iface_desc->bNumEndpoints; ++i) {
-		ep = &interface->altsetting[0].endpoint[i].desc;
+		ep = &interface->cur_altsetting->endpoint[i].desc;
 
 		if (usb_endpoint_is_bulk_in(ep)) {
 			/* we found a bulk in endpoint */
diff --git a/drivers/net/wireless/intersil/p54/p54usb.c b/drivers/net/wireless/intersil/p54/p54usb.c
index b94764c88750..ff0e30c0c14c 100644
--- a/drivers/net/wireless/intersil/p54/p54usb.c
+++ b/drivers/net/wireless/intersil/p54/p54usb.c
@@ -61,6 +61,7 @@ static const struct usb_device_id p54u_table[] = {
 	{USB_DEVICE(0x0db0, 0x6826)},	/* MSI UB54G (MS-6826) */
 	{USB_DEVICE(0x107b, 0x55f2)},	/* Gateway WGU-210 (Gemtek) */
 	{USB_DEVICE(0x124a, 0x4023)},	/* Shuttle PN15, Airvast WM168g, IOGear GWU513 */
+	{USB_DEVICE(0x124a, 0x4026)},	/* AirVasT USB wireless device */
 	{USB_DEVICE(0x1435, 0x0210)},	/* Inventel UR054G */
 	{USB_DEVICE(0x15a9, 0x0002)},	/* Gemtek WUBI-100GW 802.11g */
 	{USB_DEVICE(0x1630, 0x0005)},	/* 2Wire 802.11g USB (v1) / Z-Com */
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index faec05ab4275..a87ab1f2153a 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -3476,9 +3476,9 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info)
 	}
 
 	if (info->attrs[HWSIM_ATTR_RADIO_NAME]) {
-		hwname = kasprintf(GFP_KERNEL, "%.*s",
-				   nla_len(info->attrs[HWSIM_ATTR_RADIO_NAME]),
-				   (char *)nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME]));
+		hwname = kstrndup((char *)nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME]),
+				  nla_len(info->attrs[HWSIM_ATTR_RADIO_NAME]),
+				  GFP_KERNEL);
 		if (!hwname)
 			return -ENOMEM;
 		param.hwname = hwname;
@@ -3498,9 +3498,9 @@ static int hwsim_del_radio_nl(struct sk_buff *msg, struct genl_info *info)
 	if (info->attrs[HWSIM_ATTR_RADIO_ID]) {
 		idx = nla_get_u32(info->attrs[HWSIM_ATTR_RADIO_ID]);
 	} else if (info->attrs[HWSIM_ATTR_RADIO_NAME]) {
-		hwname = kasprintf(GFP_KERNEL, "%.*s",
-				   nla_len(info->attrs[HWSIM_ATTR_RADIO_NAME]),
-				   (char *)nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME]));
+		hwname = kstrndup((char *)nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME]),
+				  nla_len(info->attrs[HWSIM_ATTR_RADIO_NAME]),
+				  GFP_KERNEL);
 		if (!hwname)
 			return -ENOMEM;
 	} else
diff --git a/drivers/net/wireless/marvell/libertas_tf/if_usb.c b/drivers/net/wireless/marvell/libertas_tf/if_usb.c
index 28a8bd3cf10c..636bfdef28ee 100644
--- a/drivers/net/wireless/marvell/libertas_tf/if_usb.c
+++ b/drivers/net/wireless/marvell/libertas_tf/if_usb.c
@@ -247,10 +247,10 @@ static void if_usb_disconnect(struct usb_interface *intf)
 
 	lbtf_deb_enter(LBTF_DEB_MAIN);
 
-	if_usb_reset_device(priv);
-
-	if (priv)
+	if (priv) {
+		if_usb_reset_device(priv);
 		lbtf_remove_card(priv);
+	}
 
 	/* Unlink and free urb */
 	if_usb_free(cardp);
diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index e11a4bb67172..1f0c8cea48ae 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -1496,7 +1496,8 @@ mwifiex_cfg80211_dump_station(struct wiphy *wiphy, struct net_device *dev,
 			      int idx, u8 *mac, struct station_info *sinfo)
 {
 	struct mwifiex_private *priv = mwifiex_netdev_get_priv(dev);
-	static struct mwifiex_sta_node *node;
+	struct mwifiex_sta_node *node;
+	int i;
 
 	if ((GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_STA) &&
 	    priv->media_connected && idx == 0) {
@@ -1506,13 +1507,10 @@ mwifiex_cfg80211_dump_station(struct wiphy *wiphy, struct net_device *dev,
 		mwifiex_send_cmd(priv, HOST_CMD_APCMD_STA_LIST,
 				 HostCmd_ACT_GEN_GET, 0, NULL, true);
 
-		if (node && (&node->list == &priv->sta_list)) {
-			node = NULL;
-			return -ENOENT;
-		}
-
-		node = list_prepare_entry(node, &priv->sta_list, list);
-		list_for_each_entry_continue(node, &priv->sta_list, list) {
+		i = 0;
+		list_for_each_entry(node, &priv->sta_list, list) {
+			if (i++ != idx)
+				continue;
 			ether_addr_copy(mac, node->mac_addr);
 			return mwifiex_dump_station_info(priv, node, sinfo);
 		}
diff --git a/drivers/net/wireless/marvell/mwifiex/scan.c b/drivers/net/wireless/marvell/mwifiex/scan.c
index dd02bbd9544e..85d6d5f3dce5 100644
--- a/drivers/net/wireless/marvell/mwifiex/scan.c
+++ b/drivers/net/wireless/marvell/mwifiex/scan.c
@@ -2894,6 +2894,13 @@ mwifiex_cmd_append_vsie_tlv(struct mwifiex_private *priv,
 			vs_param_set->header.len =
 				cpu_to_le16((((u16) priv->vs_ie[id].ie[1])
 				& 0x00FF) + 2);
+			if (le16_to_cpu(vs_param_set->header.len) >
+				MWIFIEX_MAX_VSIE_LEN) {
+				mwifiex_dbg(priv->adapter, ERROR,
+					    "Invalid param length!\n");
+				break;
+			}
+
 			memcpy(vs_param_set->ie, priv->vs_ie[id].ie,
 			       le16_to_cpu(vs_param_set->header.len));
 			*buffer += le16_to_cpu(vs_param_set->header.len) +
diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.h b/drivers/net/wireless/marvell/mwifiex/sdio.h
index f672bdf52cc1..2d9ec225aead 100644
--- a/drivers/net/wireless/marvell/mwifiex/sdio.h
+++ b/drivers/net/wireless/marvell/mwifiex/sdio.h
@@ -36,9 +36,9 @@
 #define SD8897_DEFAULT_FW_NAME "mrvl/sd8897_uapsta.bin"
 #define SD8887_DEFAULT_FW_NAME "mrvl/sd8887_uapsta.bin"
 #define SD8801_DEFAULT_FW_NAME "mrvl/sd8801_uapsta.bin"
-#define SD8977_DEFAULT_FW_NAME "mrvl/sd8977_uapsta.bin"
+#define SD8977_DEFAULT_FW_NAME "mrvl/sdsd8977_combo_v2.bin"
 #define SD8987_DEFAULT_FW_NAME "mrvl/sd8987_uapsta.bin"
-#define SD8997_DEFAULT_FW_NAME "mrvl/sd8997_uapsta.bin"
+#define SD8997_DEFAULT_FW_NAME "mrvl/sdsd8997_combo_v4.bin"
 
 #define BLOCK_MODE	1
 #define BYTE_MODE	0
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c b/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c
index 24b33e20e7a9..ec34a429a97f 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c
@@ -581,6 +581,11 @@ static int mwifiex_ret_802_11_key_material_v1(struct mwifiex_private *priv,
 {
 	struct host_cmd_ds_802_11_key_material *key =
 						&resp->params.key_material;
+	int len;
+
+	len = le16_to_cpu(key->key_param_set.key_len);
+	if (len > sizeof(key->key_param_set.key))
+		return -EINVAL;
 
 	if (le16_to_cpu(key->action) == HostCmd_ACT_GEN_SET) {
 		if ((le16_to_cpu(key->key_param_set.key_info) & KEY_MCAST)) {
@@ -594,9 +599,8 @@ static int mwifiex_ret_802_11_key_material_v1(struct mwifiex_private *priv,
 
 	memset(priv->aes_key.key_param_set.key, 0,
 	       sizeof(key->key_param_set.key));
-	priv->aes_key.key_param_set.key_len = key->key_param_set.key_len;
-	memcpy(priv->aes_key.key_param_set.key, key->key_param_set.key,
-	       le16_to_cpu(priv->aes_key.key_param_set.key_len));
+	priv->aes_key.key_param_set.key_len = cpu_to_le16(len);
+	memcpy(priv->aes_key.key_param_set.key, key->key_param_set.key, len);
 
 	return 0;
 }
@@ -611,9 +615,14 @@ static int mwifiex_ret_802_11_key_material_v2(struct mwifiex_private *priv,
 					      struct host_cmd_ds_command *resp)
 {
 	struct host_cmd_ds_802_11_key_material_v2 *key_v2;
-	__le16 len;
+	int len;
 
 	key_v2 = &resp->params.key_material_v2;
+
+	len = le16_to_cpu(key_v2->key_param_set.key_params.aes.key_len);
+	if (len > WLAN_KEY_LEN_CCMP)
+		return -EINVAL;
+
 	if (le16_to_cpu(key_v2->action) == HostCmd_ACT_GEN_SET) {
 		if ((le16_to_cpu(key_v2->key_param_set.key_info) & KEY_MCAST)) {
 			mwifiex_dbg(priv->adapter, INFO, "info: key: GTK is set\n");
@@ -629,10 +638,9 @@ static int mwifiex_ret_802_11_key_material_v2(struct mwifiex_private *priv,
 	memset(priv->aes_key_v2.key_param_set.key_params.aes.key, 0,
 	       WLAN_KEY_LEN_CCMP);
 	priv->aes_key_v2.key_param_set.key_params.aes.key_len =
-				key_v2->key_param_set.key_params.aes.key_len;
-	len = priv->aes_key_v2.key_param_set.key_params.aes.key_len;
+				cpu_to_le16(len);
 	memcpy(priv->aes_key_v2.key_param_set.key_params.aes.key,
-	       key_v2->key_param_set.key_params.aes.key, le16_to_cpu(len));
+	       key_v2->key_param_set.key_params.aes.key, len);
 
 	return 0;
 }
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
index 6dd835f1efc2..fbfa0b15d0c8 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
@@ -232,6 +232,7 @@ static int mwifiex_process_country_ie(struct mwifiex_private *priv,
 
 	if (country_ie_len >
 	    (IEEE80211_COUNTRY_STRING_LEN + MWIFIEX_MAX_TRIPLET_802_11D)) {
+		rcu_read_unlock();
 		mwifiex_dbg(priv->adapter, ERROR,
 			    "11D: country_ie_len overflow!, deauth AP\n");
 		return -EINVAL;
diff --git a/drivers/net/wireless/marvell/mwifiex/tdls.c b/drivers/net/wireless/marvell/mwifiex/tdls.c
index 6058c48d56dc..b6b7bbe168eb 100644
--- a/drivers/net/wireless/marvell/mwifiex/tdls.c
+++ b/drivers/net/wireless/marvell/mwifiex/tdls.c
@@ -897,7 +897,7 @@ void mwifiex_process_tdls_action_frame(struct mwifiex_private *priv,
 	u8 *peer, *pos, *end;
 	u8 i, action, basic;
 	u16 cap = 0;
-	int ie_len = 0;
+	int ies_len = 0;
 
 	if (len < (sizeof(struct ethhdr) + 3))
 		return;
@@ -919,7 +919,7 @@ void mwifiex_process_tdls_action_frame(struct mwifiex_private *priv,
 		pos = buf + sizeof(struct ethhdr) + 4;
 		/* payload 1+ category 1 + action 1 + dialog 1 */
 		cap = get_unaligned_le16(pos);
-		ie_len = len - sizeof(struct ethhdr) - TDLS_REQ_FIX_LEN;
+		ies_len = len - sizeof(struct ethhdr) - TDLS_REQ_FIX_LEN;
 		pos += 2;
 		break;
 
@@ -929,7 +929,7 @@ void mwifiex_process_tdls_action_frame(struct mwifiex_private *priv,
 		/* payload 1+ category 1 + action 1 + dialog 1 + status code 2*/
 		pos = buf + sizeof(struct ethhdr) + 6;
 		cap = get_unaligned_le16(pos);
-		ie_len = len - sizeof(struct ethhdr) - TDLS_RESP_FIX_LEN;
+		ies_len = len - sizeof(struct ethhdr) - TDLS_RESP_FIX_LEN;
 		pos += 2;
 		break;
 
@@ -937,7 +937,7 @@ void mwifiex_process_tdls_action_frame(struct mwifiex_private *priv,
 		if (len < (sizeof(struct ethhdr) + TDLS_CONFIRM_FIX_LEN))
 			return;
 		pos = buf + sizeof(struct ethhdr) + TDLS_CONFIRM_FIX_LEN;
-		ie_len = len - sizeof(struct ethhdr) - TDLS_CONFIRM_FIX_LEN;
+		ies_len = len - sizeof(struct ethhdr) - TDLS_CONFIRM_FIX_LEN;
 		break;
 	default:
 		mwifiex_dbg(priv->adapter, ERROR, "Unknown TDLS frame type.\n");
@@ -950,33 +950,33 @@ void mwifiex_process_tdls_action_frame(struct mwifiex_private *priv,
 
 	sta_ptr->tdls_cap.capab = cpu_to_le16(cap);
 
-	for (end = pos + ie_len; pos + 1 < end; pos += 2 + pos[1]) {
-		if (pos + 2 + pos[1] > end)
+	for (end = pos + ies_len; pos + 1 < end; pos += 2 + pos[1]) {
+		u8 ie_len = pos[1];
+
+		if (pos + 2 + ie_len > end)
 			break;
 
 		switch (*pos) {
 		case WLAN_EID_SUPP_RATES:
-			if (pos[1] > 32)
+			if (ie_len > sizeof(sta_ptr->tdls_cap.rates))
 				return;
-			sta_ptr->tdls_cap.rates_len = pos[1];
-			for (i = 0; i < pos[1]; i++)
+			sta_ptr->tdls_cap.rates_len = ie_len;
+			for (i = 0; i < ie_len; i++)
 				sta_ptr->tdls_cap.rates[i] = pos[i + 2];
 			break;
 
 		case WLAN_EID_EXT_SUPP_RATES:
-			if (pos[1] > 32)
+			if (ie_len > sizeof(sta_ptr->tdls_cap.rates))
 				return;
 			basic = sta_ptr->tdls_cap.rates_len;
-			if (pos[1] > 32 - basic)
+			if (ie_len > sizeof(sta_ptr->tdls_cap.rates) - basic)
 				return;
-			for (i = 0; i < pos[1]; i++)
+			for (i = 0; i < ie_len; i++)
 				sta_ptr->tdls_cap.rates[basic + i] = pos[i + 2];
-			sta_ptr->tdls_cap.rates_len += pos[1];
+			sta_ptr->tdls_cap.rates_len += ie_len;
 			break;
 		case WLAN_EID_HT_CAPABILITY:
-			if (pos > end - sizeof(struct ieee80211_ht_cap) - 2)
-				return;
-			if (pos[1] != sizeof(struct ieee80211_ht_cap))
+			if (ie_len != sizeof(struct ieee80211_ht_cap))
 				return;
 			/* copy the ie's value into ht_capb*/
 			memcpy((u8 *)&sta_ptr->tdls_cap.ht_capb, pos + 2,
@@ -984,59 +984,45 @@ void mwifiex_process_tdls_action_frame(struct mwifiex_private *priv,
 			sta_ptr->is_11n_enabled = 1;
 			break;
 		case WLAN_EID_HT_OPERATION:
-			if (pos > end -
-			    sizeof(struct ieee80211_ht_operation) - 2)
-				return;
-			if (pos[1] != sizeof(struct ieee80211_ht_operation))
+			if (ie_len != sizeof(struct ieee80211_ht_operation))
 				return;
 			/* copy the ie's value into ht_oper*/
 			memcpy(&sta_ptr->tdls_cap.ht_oper, pos + 2,
 			       sizeof(struct ieee80211_ht_operation));
 			break;
 		case WLAN_EID_BSS_COEX_2040:
-			if (pos > end - 3)
-				return;
-			if (pos[1] != 1)
+			if (ie_len != sizeof(pos[2]))
 				return;
 			sta_ptr->tdls_cap.coex_2040 = pos[2];
 			break;
 		case WLAN_EID_EXT_CAPABILITY:
-			if (pos > end - sizeof(struct ieee_types_header))
-				return;
-			if (pos[1] < sizeof(struct ieee_types_header))
+			if (ie_len < sizeof(struct ieee_types_header))
 				return;
-			if (pos[1] > 8)
+			if (ie_len > 8)
 				return;
 			memcpy((u8 *)&sta_ptr->tdls_cap.extcap, pos,
 			       sizeof(struct ieee_types_header) +
-			       min_t(u8, pos[1], 8));
+			       min_t(u8, ie_len, 8));
 			break;
 		case WLAN_EID_RSN:
-			if (pos > end - sizeof(struct ieee_types_header))
+			if (ie_len < sizeof(struct ieee_types_header))
 				return;
-			if (pos[1] < sizeof(struct ieee_types_header))
-				return;
-			if (pos[1] > IEEE_MAX_IE_SIZE -
+			if (ie_len > IEEE_MAX_IE_SIZE -
 			    sizeof(struct ieee_types_header))
 				return;
 			memcpy((u8 *)&sta_ptr->tdls_cap.rsn_ie, pos,
 			       sizeof(struct ieee_types_header) +
-			       min_t(u8, pos[1], IEEE_MAX_IE_SIZE -
+			       min_t(u8, ie_len, IEEE_MAX_IE_SIZE -
 				     sizeof(struct ieee_types_header)));
 			break;
 		case WLAN_EID_QOS_CAPA:
-			if (pos > end - 3)
-				return;
-			if (pos[1] != 1)
+			if (ie_len != sizeof(pos[2]))
 				return;
 			sta_ptr->tdls_cap.qos_info = pos[2];
 			break;
 		case WLAN_EID_VHT_OPERATION:
 			if (priv->adapter->is_hw_11ac_capable) {
-				if (pos > end -
-				    sizeof(struct ieee80211_vht_operation) - 2)
-					return;
-				if (pos[1] !=
+				if (ie_len !=
 				    sizeof(struct ieee80211_vht_operation))
 					return;
 				/* copy the ie's value into vhtoper*/
@@ -1046,10 +1032,7 @@ void mwifiex_process_tdls_action_frame(struct mwifiex_private *priv,
 			break;
 		case WLAN_EID_VHT_CAPABILITY:
 			if (priv->adapter->is_hw_11ac_capable) {
-				if (pos > end -
-				    sizeof(struct ieee80211_vht_cap) - 2)
-					return;
-				if (pos[1] != sizeof(struct ieee80211_vht_cap))
+				if (ie_len != sizeof(struct ieee80211_vht_cap))
 					return;
 				/* copy the ie's value into vhtcap*/
 				memcpy((u8 *)&sta_ptr->tdls_cap.vhtcap, pos + 2,
@@ -1059,9 +1042,7 @@ void mwifiex_process_tdls_action_frame(struct mwifiex_private *priv,
 			break;
 		case WLAN_EID_AID:
 			if (priv->adapter->is_hw_11ac_capable) {
-				if (pos > end - 4)
-					return;
-				if (pos[1] != 2)
+				if (ie_len != sizeof(u16))
 					return;
 				sta_ptr->tdls_cap.aid =
 					get_unaligned_le16((pos + 2));
diff --git a/drivers/net/wireless/marvell/mwifiex/wmm.c b/drivers/net/wireless/marvell/mwifiex/wmm.c
index 64916ba15df5..429ea2752e6a 100644
--- a/drivers/net/wireless/marvell/mwifiex/wmm.c
+++ b/drivers/net/wireless/marvell/mwifiex/wmm.c
@@ -977,6 +977,10 @@ int mwifiex_ret_wmm_get_status(struct mwifiex_private *priv,
 				    "WMM Parameter Set Count: %d\n",
 				    wmm_param_ie->qos_info_bitmap & mask);
 
+			if (wmm_param_ie->vend_hdr.len + 2 >
+				sizeof(struct ieee_types_wmm_parameter))
+				break;
+
 			memcpy((u8 *) &priv->curr_bss_params.bss_descriptor.
 			       wmm_ie, wmm_param_ie,
 			       wmm_param_ie->vend_hdr.len + 2);
diff --git a/drivers/net/wireless/mediatek/mt76/agg-rx.c b/drivers/net/wireless/mediatek/mt76/agg-rx.c
index 27e3ff039c48..caeb5086737c 100644
--- a/drivers/net/wireless/mediatek/mt76/agg-rx.c
+++ b/drivers/net/wireless/mediatek/mt76/agg-rx.c
@@ -154,8 +154,8 @@ void mt76_rx_aggr_reorder(struct sk_buff *skb, struct sk_buff_head *frames)
 	struct ieee80211_sta *sta;
 	struct mt76_rx_tid *tid;
 	bool sn_less;
-	u16 seqno, head, size;
-	u8 ackp, idx;
+	u16 seqno, head, size, idx;
+	u8 ackp;
 
 	__skb_queue_tail(frames, skb);
 
@@ -240,7 +240,7 @@ out:
 }
 
 int mt76_rx_aggr_start(struct mt76_dev *dev, struct mt76_wcid *wcid, u8 tidno,
-		       u16 ssn, u8 size)
+		       u16 ssn, u16 size)
 {
 	struct mt76_rx_tid *tid;
 
@@ -264,7 +264,7 @@ EXPORT_SYMBOL_GPL(mt76_rx_aggr_start);
 
 static void mt76_rx_aggr_shutdown(struct mt76_dev *dev, struct mt76_rx_tid *tid)
 {
-	u8 size = tid->size;
+	u16 size = tid->size;
 	int i;
 
 	cancel_delayed_work(&tid->reorder_work);
diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c
index 5fb158f40a95..4dd92db52f46 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/dma.c
@@ -453,10 +453,13 @@ mt76_add_fragment(struct mt76_dev *dev, struct mt76_queue *q, void *data,
 	struct page *page = virt_to_head_page(data);
 	int offset = data - page_address(page);
 	struct sk_buff *skb = q->rx_head;
+	struct skb_shared_info *shinfo = skb_shinfo(skb);
 
-	offset += q->buf_offset;
-	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, offset, len,
-			q->buf_size);
+	if (shinfo->nr_frags < ARRAY_SIZE(shinfo->frags)) {
+		offset += q->buf_offset;
+		skb_add_rx_frag(skb, shinfo->nr_frags, page, offset, len,
+				q->buf_size);
+	}
 
 	if (more)
 		return;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index c736bd0b8eab..6e556fbace22 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -248,8 +248,8 @@ struct mt76_rx_tid {
 	struct delayed_work reorder_work;
 
 	u16 head;
-	u8 size;
-	u8 nframes;
+	u16 size;
+	u16 nframes;
 
 	u8 started:1, stopped:1, timer_pending:1;
 
@@ -375,8 +375,8 @@ enum mt76u_in_ep {
 
 enum mt76u_out_ep {
 	MT_EP_OUT_INBAND_CMD,
-	MT_EP_OUT_AC_BK,
 	MT_EP_OUT_AC_BE,
+	MT_EP_OUT_AC_BK,
 	MT_EP_OUT_AC_VI,
 	MT_EP_OUT_AC_VO,
 	MT_EP_OUT_HCCA,
@@ -712,7 +712,7 @@ int mt76_get_survey(struct ieee80211_hw *hw, int idx,
 void mt76_set_stream_caps(struct mt76_dev *dev, bool vht);
 
 int mt76_rx_aggr_start(struct mt76_dev *dev, struct mt76_wcid *wcid, u8 tid,
-		       u16 ssn, u8 size);
+		       u16 ssn, u16 size);
 void mt76_rx_aggr_stop(struct mt76_dev *dev, struct mt76_wcid *wcid, u8 tid);
 
 void mt76_wcid_key_setup(struct mt76_dev *dev, struct mt76_wcid *wcid,
@@ -782,7 +782,8 @@ static inline int
 mt76u_bulk_msg(struct mt76_dev *dev, void *data, int len, int *actual_len,
 	       int timeout)
 {
-	struct usb_device *udev = to_usb_device(dev->dev);
+	struct usb_interface *uintf = to_usb_interface(dev->dev);
+	struct usb_device *udev = interface_to_usbdev(uintf);
 	struct mt76_usb *usb = &dev->usb;
 	unsigned int pipe;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
index f877e3862f8d..a43d6939bb2a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
@@ -78,7 +78,7 @@ static int __mt7615_mcu_msg_send(struct mt7615_dev *dev, struct sk_buff *skb,
 
 	txd = mcu_txd->txd;
 
-	val = FIELD_PREP(MT_TXD0_TX_BYTES, cpu_to_le16(skb->len)) |
+	val = FIELD_PREP(MT_TXD0_TX_BYTES, skb->len) |
 	      FIELD_PREP(MT_TXD0_P_IDX, MT_TX_PORT_IDX_MCU) |
 	      FIELD_PREP(MT_TXD0_Q_IDX, q_idx);
 	txd[0] = cpu_to_le32(val);
@@ -771,7 +771,7 @@ static void bss_info_ext_bss_handler (struct mt7615_dev *dev,
 /* SIFS 20us + 512 byte beacon tranmitted by 1Mbps (3906us) */
 #define BCN_TX_ESTIMATE_TIME (4096 + 20)
 	struct bss_info_ext_bss tlv = {0};
-	int ext_bss_idx;
+	int ext_bss_idx, tsf_offset;
 
 	ext_bss_idx = bss_info->omac_idx - EXT_BSSID_START;
 
@@ -780,7 +780,8 @@ static void bss_info_ext_bss_handler (struct mt7615_dev *dev,
 
 	tlv.tag = cpu_to_le16(BSS_INFO_EXT_BSS);
 	tlv.len = cpu_to_le16(sizeof(tlv));
-	tlv.mbss_tsf_offset = ext_bss_idx * BCN_TX_ESTIMATE_TIME;
+	tsf_offset = ext_bss_idx * BCN_TX_ESTIMATE_TIME;
+	tlv.mbss_tsf_offset = cpu_to_le32(tsf_offset);
 
 	memcpy(skb_put(skb, sizeof(tlv)), &tlv, sizeof(tlv));
 }
@@ -1451,10 +1452,8 @@ int mt7615_mcu_set_ht_cap(struct mt7615_dev *dev, struct ieee80211_vif *vif,
 		sta_rec_vht->tag = cpu_to_le16(STA_REC_VHT);
 		sta_rec_vht->len = cpu_to_le16(sizeof(*sta_rec_vht));
 		sta_rec_vht->vht_cap = cpu_to_le32(sta->vht_cap.cap);
-		sta_rec_vht->vht_rx_mcs_map =
-			cpu_to_le16(sta->vht_cap.vht_mcs.rx_mcs_map);
-		sta_rec_vht->vht_tx_mcs_map =
-			cpu_to_le16(sta->vht_cap.vht_mcs.tx_mcs_map);
+		sta_rec_vht->vht_rx_mcs_map = sta->vht_cap.vht_mcs.rx_mcs_map;
+		sta_rec_vht->vht_tx_mcs_map = sta->vht_cap.vht_mcs.tx_mcs_map;
 	}
 
 	ret = __mt7615_mcu_set_sta_rec(dev, mvif->idx, msta->wcid.idx,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h
index 929b39fa57c3..2841cbd48c48 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h
@@ -15,7 +15,7 @@
 #define MT7615_WTBL_STA			(MT7615_WTBL_RESERVED - \
 					 MT7615_MAX_INTERFACES)
 
-#define MT7615_WATCHDOG_TIME		100 /* ms */
+#define MT7615_WATCHDOG_TIME		(HZ / 10)
 #define MT7615_RATE_RETRY		2
 
 #define MT7615_TX_RING_SIZE		1024
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
index 4585e1b756c2..6117e6ca08cb 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
@@ -62,6 +62,19 @@ static void mt76x0e_stop(struct ieee80211_hw *hw)
 	mt76x0e_stop_hw(dev);
 }
 
+static int
+mt76x0e_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
+		struct ieee80211_vif *vif, struct ieee80211_sta *sta,
+		struct ieee80211_key_conf *key)
+{
+	struct mt76x02_dev *dev = hw->priv;
+
+	if (is_mt7630(dev))
+		return -EOPNOTSUPP;
+
+	return mt76x02_set_key(hw, cmd, vif, sta, key);
+}
+
 static void
 mt76x0e_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	      u32 queues, bool drop)
@@ -78,7 +91,7 @@ static const struct ieee80211_ops mt76x0e_ops = {
 	.configure_filter = mt76x02_configure_filter,
 	.bss_info_changed = mt76x02_bss_info_changed,
 	.sta_state = mt76_sta_state,
-	.set_key = mt76x02_set_key,
+	.set_key = mt76x0e_set_key,
 	.conf_tx = mt76x02_conf_tx,
 	.sw_scan_start = mt76x02_sw_scan,
 	.sw_scan_complete = mt76x02_sw_scan_complete,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
index 109309b5d24a..71cef827c65e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
@@ -214,7 +214,7 @@ static int mt76x0u_probe(struct usb_interface *usb_intf,
 	u32 mac_rev;
 	int ret;
 
-	mdev = mt76_alloc_device(&usb_dev->dev, sizeof(*dev), &mt76x0u_ops,
+	mdev = mt76_alloc_device(&usb_intf->dev, sizeof(*dev), &mt76x0u_ops,
 				 &drv_ops);
 	if (!mdev)
 		return -ENOMEM;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02.h b/drivers/net/wireless/mediatek/mt76/mt76x02.h
index 687bd14b2d77..ab309e697645 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02.h
@@ -220,6 +220,7 @@ static inline bool is_mt76x0(struct mt76x02_dev *dev)
 static inline bool is_mt76x2(struct mt76x02_dev *dev)
 {
 	return mt76_chip(&dev->mt76) == 0x7612 ||
+	       mt76_chip(&dev->mt76) == 0x7632 ||
 	       mt76_chip(&dev->mt76) == 0x7662 ||
 	       mt76_chip(&dev->mt76) == 0x7602;
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
index 7a994a783510..211801f444a2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
@@ -29,6 +29,7 @@ static const struct usb_device_id mt76x2u_device_table[] = {
 	{ USB_DEVICE(0x7392, 0xb711) },	/* Edimax EW 7722 UAC */
 	{ USB_DEVICE(0x0846, 0x9053) },	/* Netgear A6210 */
 	{ USB_DEVICE(0x045e, 0x02e6) },	/* XBox One Wireless Adapter */
+	{ USB_DEVICE(0x045e, 0x02fe) },	/* XBox One Wireless Adapter */
 	{ },
 };
 
@@ -49,7 +50,7 @@ static int mt76x2u_probe(struct usb_interface *intf,
 	struct mt76_dev *mdev;
 	int err;
 
-	mdev = mt76_alloc_device(&udev->dev, sizeof(*dev), &mt76x2u_ops,
+	mdev = mt76_alloc_device(&intf->dev, sizeof(*dev), &mt76x2u_ops,
 				 &drv_ops);
 	if (!mdev)
 		return -ENOMEM;
diff --git a/drivers/net/wireless/mediatek/mt76/usb.c b/drivers/net/wireless/mediatek/mt76/usb.c
index 28e3af7332bf..0a01520e693a 100644
--- a/drivers/net/wireless/mediatek/mt76/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/usb.c
@@ -31,7 +31,8 @@ static int __mt76u_vendor_request(struct mt76_dev *dev, u8 req,
 				  u8 req_type, u16 val, u16 offset,
 				  void *buf, size_t len)
 {
-	struct usb_device *udev = to_usb_device(dev->dev);
+	struct usb_interface *uintf = to_usb_interface(dev->dev);
+	struct usb_device *udev = interface_to_usbdev(uintf);
 	unsigned int pipe;
 	int i, ret;
 
@@ -246,7 +247,8 @@ mt76u_rd_rp(struct mt76_dev *dev, u32 base,
 
 static bool mt76u_check_sg(struct mt76_dev *dev)
 {
-	struct usb_device *udev = to_usb_device(dev->dev);
+	struct usb_interface *uintf = to_usb_interface(dev->dev);
+	struct usb_device *udev = interface_to_usbdev(uintf);
 
 	return (!disable_usb_sg && udev->bus->sg_tablesize > 0 &&
 		(udev->bus->no_sg_constraint ||
@@ -311,7 +313,7 @@ mt76u_fill_rx_sg(struct mt76_dev *dev, struct mt76_queue *q, struct urb *urb,
 	}
 
 	urb->num_sgs = max_t(int, i, urb->num_sgs);
-	urb->transfer_buffer_length = urb->num_sgs * q->buf_size,
+	urb->transfer_buffer_length = urb->num_sgs * q->buf_size;
 	sg_init_marker(urb->sg, urb->num_sgs);
 
 	return i ? : -ENOMEM;
@@ -382,7 +384,8 @@ mt76u_fill_bulk_urb(struct mt76_dev *dev, int dir, int index,
 		    struct urb *urb, usb_complete_t complete_fn,
 		    void *context)
 {
-	struct usb_device *udev = to_usb_device(dev->dev);
+	struct usb_interface *uintf = to_usb_interface(dev->dev);
+	struct usb_device *udev = interface_to_usbdev(uintf);
 	unsigned int pipe;
 
 	if (dir == USB_DIR_IN)
@@ -960,6 +963,7 @@ int mt76u_init(struct mt76_dev *dev,
 		.rd_rp = mt76u_rd_rp,
 		.type = MT76_BUS_USB,
 	};
+	struct usb_device *udev = interface_to_usbdev(intf);
 	struct mt76_usb *usb = &dev->usb;
 
 	tasklet_init(&usb->rx_tasklet, mt76u_rx_tasklet, (unsigned long)dev);
@@ -973,6 +977,8 @@ int mt76u_init(struct mt76_dev *dev,
 	dev->bus = &mt76u_ops;
 	dev->queue_ops = &usb_queue_ops;
 
+	dev_set_drvdata(&udev->dev, dev);
+
 	usb->sg_en = mt76u_check_sg(dev);
 
 	return mt76u_set_endpoints(intf, usb);
diff --git a/drivers/net/wireless/mediatek/mt7601u/phy.c b/drivers/net/wireless/mediatek/mt7601u/phy.c
index 06f5702ab4bd..d863ab4a66c9 100644
--- a/drivers/net/wireless/mediatek/mt7601u/phy.c
+++ b/drivers/net/wireless/mediatek/mt7601u/phy.c
@@ -213,7 +213,7 @@ int mt7601u_wait_bbp_ready(struct mt7601u_dev *dev)
 
 	do {
 		val = mt7601u_bbp_rr(dev, MT_BBP_REG_VERSION);
-		if (val && ~val)
+		if (val && val != 0xff)
 			break;
 	} while (--i);
 
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
index 5673dd858811..73cda9301578 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c
@@ -5753,8 +5753,7 @@ static int rt2800_init_registers(struct rt2x00_dev *rt2x00dev)
 		rt2800_register_write(rt2x00dev, TX_TXBF_CFG_0, 0x8000fc21);
 		rt2800_register_write(rt2x00dev, TX_TXBF_CFG_3, 0x00009c40);
 	} else if (rt2x00_rt(rt2x00dev, RT5390) ||
-		   rt2x00_rt(rt2x00dev, RT5392) ||
-		   rt2x00_rt(rt2x00dev, RT6352)) {
+		   rt2x00_rt(rt2x00dev, RT5392)) {
 		rt2800_register_write(rt2x00dev, TX_SW_CFG0, 0x00000404);
 		rt2800_register_write(rt2x00dev, TX_SW_CFG1, 0x00080606);
 		rt2800_register_write(rt2x00dev, TX_SW_CFG2, 0x00000000);
@@ -5768,8 +5767,6 @@ static int rt2800_init_registers(struct rt2x00_dev *rt2x00dev)
 		rt2800_register_write(rt2x00dev, TX_SW_CFG0, 0x00000401);
 		rt2800_register_write(rt2x00dev, TX_SW_CFG1, 0x000C0000);
 		rt2800_register_write(rt2x00dev, TX_SW_CFG2, 0x00000000);
-		rt2800_register_write(rt2x00dev, MIMO_PS_CFG, 0x00000002);
-		rt2800_register_write(rt2x00dev, TX_PIN_CFG, 0x00150F0F);
 		rt2800_register_write(rt2x00dev, TX_ALC_VGA3, 0x00000000);
 		rt2800_register_write(rt2x00dev, TX0_BB_GAIN_ATTEN, 0x0);
 		rt2800_register_write(rt2x00dev, TX1_BB_GAIN_ATTEN, 0x0);
diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
index 0791192579cb..5fcb1a27f29c 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
@@ -5914,7 +5914,7 @@ static int rtl8xxxu_parse_usb(struct rtl8xxxu_priv *priv,
 	u8 dir, xtype, num;
 	int ret = 0;
 
-	host_interface = &interface->altsetting[0];
+	host_interface = interface->cur_altsetting;
 	interface_desc = &host_interface->desc;
 	endpoints = interface_desc->bNumEndpoints;
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.c b/drivers/net/wireless/realtek/rtlwifi/pci.c
index 05050f6c36db..d651b8bfde47 100644
--- a/drivers/net/wireless/realtek/rtlwifi/pci.c
+++ b/drivers/net/wireless/realtek/rtlwifi/pci.c
@@ -1061,13 +1061,15 @@ done:
 	return ret;
 }
 
-static void _rtl_pci_irq_tasklet(struct ieee80211_hw *hw)
+static void _rtl_pci_irq_tasklet(unsigned long data)
 {
+	struct ieee80211_hw *hw = (struct ieee80211_hw *)data;
 	_rtl_pci_tx_chk_waitq(hw);
 }
 
-static void _rtl_pci_prepare_bcn_tasklet(struct ieee80211_hw *hw)
+static void _rtl_pci_prepare_bcn_tasklet(unsigned long data)
 {
+	struct ieee80211_hw *hw = (struct ieee80211_hw *)data;
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	struct rtl_mac *mac = rtl_mac(rtl_priv(hw));
@@ -1193,10 +1195,10 @@ static void _rtl_pci_init_struct(struct ieee80211_hw *hw,
 
 	/*task */
 	tasklet_init(&rtlpriv->works.irq_tasklet,
-		     (void (*)(unsigned long))_rtl_pci_irq_tasklet,
+		     _rtl_pci_irq_tasklet,
 		     (unsigned long)hw);
 	tasklet_init(&rtlpriv->works.irq_prepare_bcn_tasklet,
-		     (void (*)(unsigned long))_rtl_pci_prepare_bcn_tasklet,
+		     _rtl_pci_prepare_bcn_tasklet,
 		     (unsigned long)hw);
 	INIT_WORK(&rtlpriv->works.lps_change_work,
 		  rtl_lps_change_work_callback);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rc.c b/drivers/net/wireless/realtek/rtlwifi/rc.c
index cf8e42a01015..ceb2283ee036 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rc.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rc.c
@@ -264,7 +264,7 @@ static void rtl_rate_update(void *ppriv,
 {
 }
 
-static void *rtl_rate_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir)
+static void *rtl_rate_alloc(struct ieee80211_hw *hw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	return rtlpriv;
diff --git a/drivers/net/wireless/realtek/rtlwifi/regd.c b/drivers/net/wireless/realtek/rtlwifi/regd.c
index 6ccb5b93a595..9ee5fb01e9eb 100644
--- a/drivers/net/wireless/realtek/rtlwifi/regd.c
+++ b/drivers/net/wireless/realtek/rtlwifi/regd.c
@@ -404,7 +404,7 @@ int rtl_regd_init(struct ieee80211_hw *hw,
 	struct wiphy *wiphy = hw->wiphy;
 	struct country_code_to_enum_rd *country = NULL;
 
-	if (wiphy == NULL || &rtlpriv->regd == NULL)
+	if (!wiphy)
 		return -EINVAL;
 
 	/* init country_code from efuse channel plan */
diff --git a/drivers/net/wireless/realtek/rtlwifi/usb.c b/drivers/net/wireless/realtek/rtlwifi/usb.c
index de770bbc3aa2..8eede87f9d39 100644
--- a/drivers/net/wireless/realtek/rtlwifi/usb.c
+++ b/drivers/net/wireless/realtek/rtlwifi/usb.c
@@ -893,10 +893,8 @@ static struct urb *_rtl_usb_tx_urb_setup(struct ieee80211_hw *hw,
 
 	WARN_ON(NULL == skb);
 	_urb = usb_alloc_urb(0, GFP_ATOMIC);
-	if (!_urb) {
-		kfree_skb(skb);
+	if (!_urb)
 		return NULL;
-	}
 	_rtl_install_trx_info(rtlusb, skb, ep_num);
 	usb_fill_bulk_urb(_urb, rtlusb->udev, usb_sndbulkpipe(rtlusb->udev,
 			  ep_num), skb->data, skb->len, _rtl_tx_complete, skb);
@@ -910,7 +908,6 @@ static void _rtl_usb_transmit(struct ieee80211_hw *hw, struct sk_buff *skb,
 	struct rtl_usb *rtlusb = rtl_usbdev(rtl_usbpriv(hw));
 	u32 ep_num;
 	struct urb *_urb = NULL;
-	struct sk_buff *_skb = NULL;
 
 	WARN_ON(NULL == rtlusb->usb_tx_aggregate_hdl);
 	if (unlikely(IS_USB_STOP(rtlusb))) {
@@ -919,8 +916,7 @@ static void _rtl_usb_transmit(struct ieee80211_hw *hw, struct sk_buff *skb,
 		return;
 	}
 	ep_num = rtlusb->ep_map.ep_mapping[qnum];
-	_skb = skb;
-	_urb = _rtl_usb_tx_urb_setup(hw, _skb, ep_num);
+	_urb = _rtl_usb_tx_urb_setup(hw, skb, ep_num);
 	if (unlikely(!_urb)) {
 		pr_err("Can't allocate urb. Drop skb!\n");
 		kfree_skb(skb);
diff --git a/drivers/net/wireless/realtek/rtw88/debug.c b/drivers/net/wireless/realtek/rtw88/debug.c
index f0ae26018f97..a7d45f4d34c4 100644
--- a/drivers/net/wireless/realtek/rtw88/debug.c
+++ b/drivers/net/wireless/realtek/rtw88/debug.c
@@ -76,7 +76,7 @@ static const struct file_operations file_ops_single_r = {
 	.open = rtw_debugfs_single_open_rw,
 	.read = seq_read,
 	.llseek = seq_lseek,
-	.release = seq_release,
+	.release = single_release,
 };
 
 static const struct file_operations file_ops_single_rw = {
diff --git a/drivers/net/wireless/realtek/rtw88/fw.c b/drivers/net/wireless/realtek/rtw88/fw.c
index 628477971213..04f6f0bed7fe 100644
--- a/drivers/net/wireless/realtek/rtw88/fw.c
+++ b/drivers/net/wireless/realtek/rtw88/fw.c
@@ -209,7 +209,7 @@ void rtw_fw_send_ra_info(struct rtw_dev *rtwdev, struct rtw_sta_info *si)
 	SET_RA_INFO_INIT_RA_LVL(h2c_pkt, si->init_ra_lv);
 	SET_RA_INFO_SGI_EN(h2c_pkt, si->sgi_enable);
 	SET_RA_INFO_BW_MODE(h2c_pkt, si->bw_mode);
-	SET_RA_INFO_LDPC(h2c_pkt, si->ldpc_en);
+	SET_RA_INFO_LDPC(h2c_pkt, !!si->ldpc_en);
 	SET_RA_INFO_NO_UPDATE(h2c_pkt, no_update);
 	SET_RA_INFO_VHT_EN(h2c_pkt, si->vht_enable);
 	SET_RA_INFO_DIS_PT(h2c_pkt, disable_pt);
@@ -367,9 +367,6 @@ static void rtw_rsvd_page_list_to_buf(struct rtw_dev *rtwdev, u8 page_size,
 {
 	struct sk_buff *skb = rsvd_pkt->skb;
 
-	if (rsvd_pkt->add_txdesc)
-		rtw_fill_rsvd_page_desc(rtwdev, skb);
-
 	if (page >= 1)
 		memcpy(buf + page_margin + page_size * (page - 1),
 		       skb->data, skb->len);
@@ -494,16 +491,37 @@ static u8 *rtw_build_rsvd_page(struct rtw_dev *rtwdev,
 	list_for_each_entry(rsvd_pkt, &rtwdev->rsvd_page_list, list) {
 		iter = rtw_get_rsvd_page_skb(hw, vif, rsvd_pkt->type);
 		if (!iter) {
-			rtw_err(rtwdev, "fail to build rsvd packet\n");
+			rtw_err(rtwdev, "failed to build rsvd packet\n");
 			goto release_skb;
 		}
+
+		/* Fill the tx_desc for the rsvd pkt that requires one.
+		 * And iter->len will be added with size of tx_desc_sz.
+		 */
+		if (rsvd_pkt->add_txdesc)
+			rtw_fill_rsvd_page_desc(rtwdev, iter);
+
 		rsvd_pkt->skb = iter;
 		rsvd_pkt->page = total_page;
-		if (rsvd_pkt->add_txdesc)
+
+		/* Reserved page is downloaded via TX path, and TX path will
+		 * generate a tx_desc at the header to describe length of
+		 * the buffer. If we are not counting page numbers with the
+		 * size of tx_desc added at the first rsvd_pkt (usually a
+		 * beacon, firmware default refer to the first page as the
+		 * content of beacon), we could generate a buffer which size
+		 * is smaller than the actual size of the whole rsvd_page
+		 */
+		if (total_page == 0) {
+			if (rsvd_pkt->type != RSVD_BEACON) {
+				rtw_err(rtwdev, "first page should be a beacon\n");
+				goto release_skb;
+			}
 			total_page += rtw_len_to_page(iter->len + tx_desc_sz,
 						      page_size);
-		else
+		} else {
 			total_page += rtw_len_to_page(iter->len, page_size);
+		}
 	}
 
 	if (total_page > rtwdev->fifo.rsvd_drv_pg_num) {
@@ -516,13 +534,24 @@ static u8 *rtw_build_rsvd_page(struct rtw_dev *rtwdev,
 	if (!buf)
 		goto release_skb;
 
+	/* Copy the content of each rsvd_pkt to the buf, and they should
+	 * be aligned to the pages.
+	 *
+	 * Note that the first rsvd_pkt is a beacon no matter what vif->type.
+	 * And that rsvd_pkt does not require tx_desc because when it goes
+	 * through TX path, the TX path will generate one for it.
+	 */
 	list_for_each_entry(rsvd_pkt, &rtwdev->rsvd_page_list, list) {
 		rtw_rsvd_page_list_to_buf(rtwdev, page_size, page_margin,
 					  page, buf, rsvd_pkt);
-		page += rtw_len_to_page(rsvd_pkt->skb->len, page_size);
-	}
-	list_for_each_entry(rsvd_pkt, &rtwdev->rsvd_page_list, list)
+		if (page == 0)
+			page += rtw_len_to_page(rsvd_pkt->skb->len +
+						tx_desc_sz, page_size);
+		else
+			page += rtw_len_to_page(rsvd_pkt->skb->len, page_size);
+
 		kfree_skb(rsvd_pkt->skb);
+	}
 
 	return buf;
 
@@ -575,6 +604,11 @@ int rtw_fw_download_rsvd_page(struct rtw_dev *rtwdev, struct ieee80211_vif *vif)
 		goto free;
 	}
 
+	/* The last thing is to download the *ONLY* beacon again, because
+	 * the previous tx_desc is to describe the total rsvd page. Download
+	 * the beacon again to replace the TX desc header, and we will get
+	 * a correct tx_desc for the beacon in the rsvd page.
+	 */
 	ret = rtw_download_beacon(rtwdev, vif);
 	if (ret) {
 		rtw_err(rtwdev, "failed to download beacon\n");
diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c
index 7f29d05afce6..d72b346d7307 100644
--- a/drivers/net/wireless/realtek/rtw88/main.c
+++ b/drivers/net/wireless/realtek/rtw88/main.c
@@ -505,20 +505,18 @@ void rtw_update_sta_info(struct rtw_dev *rtwdev, struct rtw_sta_info *si)
 			stbc_en = VHT_STBC_EN;
 		if (sta->vht_cap.cap & IEEE80211_VHT_CAP_RXLDPC)
 			ldpc_en = VHT_LDPC_EN;
-		if (sta->vht_cap.cap & IEEE80211_VHT_CAP_SHORT_GI_80)
-			is_support_sgi = true;
 	} else if (sta->ht_cap.ht_supported) {
-		ra_mask |= (sta->ht_cap.mcs.rx_mask[NL80211_BAND_5GHZ] << 20) |
-			   (sta->ht_cap.mcs.rx_mask[NL80211_BAND_2GHZ] << 12);
+		ra_mask |= (sta->ht_cap.mcs.rx_mask[1] << 20) |
+			   (sta->ht_cap.mcs.rx_mask[0] << 12);
 		if (sta->ht_cap.cap & IEEE80211_HT_CAP_RX_STBC)
 			stbc_en = HT_STBC_EN;
 		if (sta->ht_cap.cap & IEEE80211_HT_CAP_LDPC_CODING)
 			ldpc_en = HT_LDPC_EN;
-		if (sta->ht_cap.cap & IEEE80211_HT_CAP_SGI_20 ||
-		    sta->ht_cap.cap & IEEE80211_HT_CAP_SGI_40)
-			is_support_sgi = true;
 	}
 
+	if (efuse->hw_cap.nss == 1)
+		ra_mask &= RA_MASK_VHT_RATES_1SS | RA_MASK_HT_RATES_1SS;
+
 	if (hal->current_band_type == RTW_BAND_5G) {
 		ra_mask |= (u64)sta->supp_rates[NL80211_BAND_5GHZ] << 4;
 		if (sta->vht_cap.vht_supported) {
@@ -552,20 +550,21 @@ void rtw_update_sta_info(struct rtw_dev *rtwdev, struct rtw_sta_info *si)
 		wireless_set = 0;
 	}
 
-	if (efuse->hw_cap.nss == 1) {
-		ra_mask &= RA_MASK_VHT_RATES_1SS;
-		ra_mask &= RA_MASK_HT_RATES_1SS;
-	}
-
 	switch (sta->bandwidth) {
 	case IEEE80211_STA_RX_BW_80:
 		bw_mode = RTW_CHANNEL_WIDTH_80;
+		is_support_sgi = sta->vht_cap.vht_supported &&
+				 (sta->vht_cap.cap & IEEE80211_VHT_CAP_SHORT_GI_80);
 		break;
 	case IEEE80211_STA_RX_BW_40:
 		bw_mode = RTW_CHANNEL_WIDTH_40;
+		is_support_sgi = sta->ht_cap.ht_supported &&
+				 (sta->ht_cap.cap & IEEE80211_HT_CAP_SGI_40);
 		break;
 	default:
 		bw_mode = RTW_CHANNEL_WIDTH_20;
+		is_support_sgi = sta->ht_cap.ht_supported &&
+				 (sta->ht_cap.cap & IEEE80211_HT_CAP_SGI_20);
 		break;
 	}
 
@@ -990,19 +989,19 @@ static int rtw_chip_efuse_info_setup(struct rtw_dev *rtwdev)
 	/* power on mac to read efuse */
 	ret = rtw_chip_efuse_enable(rtwdev);
 	if (ret)
-		goto out;
+		goto out_unlock;
 
 	ret = rtw_parse_efuse_map(rtwdev);
 	if (ret)
-		goto out;
+		goto out_disable;
 
 	ret = rtw_dump_hw_feature(rtwdev);
 	if (ret)
-		goto out;
+		goto out_disable;
 
 	ret = rtw_check_supported_rfe(rtwdev);
 	if (ret)
-		goto out;
+		goto out_disable;
 
 	if (efuse->crystal_cap == 0xff)
 		efuse->crystal_cap = 0;
@@ -1026,9 +1025,10 @@ static int rtw_chip_efuse_info_setup(struct rtw_dev *rtwdev)
 	efuse->ext_pa_5g = efuse->pa_type_5g & BIT(0) ? 1 : 0;
 	efuse->ext_lna_2g = efuse->lna_type_5g & BIT(3) ? 1 : 0;
 
+out_disable:
 	rtw_chip_efuse_disable(rtwdev);
 
-out:
+out_unlock:
 	mutex_unlock(&rtwdev->mutex);
 	return ret;
 }
diff --git a/drivers/net/wireless/realtek/rtw88/pci.c b/drivers/net/wireless/realtek/rtw88/pci.c
index 68fae52151dd..24e410a22a0f 100644
--- a/drivers/net/wireless/realtek/rtw88/pci.c
+++ b/drivers/net/wireless/realtek/rtw88/pci.c
@@ -727,6 +727,11 @@ static void rtw_pci_tx_isr(struct rtw_dev *rtwdev, struct rtw_pci *rtwpci,
 
 	while (count--) {
 		skb = skb_dequeue(&ring->queue);
+		if (!skb) {
+			rtw_err(rtwdev, "failed to dequeue %d skb TX queue %d, BD=0x%08x, rp %d -> %d\n",
+				count, hw_queue, bd_idx, ring->r.rp, cur_rp);
+			break;
+		}
 		tx_data = rtw_pci_get_tx_data(skb);
 		pci_unmap_single(rtwpci->pdev, tx_data->dma, skb->len,
 				 PCI_DMA_TODEVICE);
@@ -914,6 +919,7 @@ static int rtw_pci_io_mapping(struct rtw_dev *rtwdev,
 	len = pci_resource_len(pdev, bar_id);
 	rtwpci->mmap = pci_iomap(pdev, bar_id, len);
 	if (!rtwpci->mmap) {
+		pci_release_regions(pdev);
 		rtw_err(rtwdev, "failed to map pci memory\n");
 		return -ENOMEM;
 	}
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822c.c b/drivers/net/wireless/realtek/rtw88/rtw8822c.c
index b4f7242e5aa3..53c243ba04a7 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822c.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822c.c
@@ -1257,9 +1257,9 @@ static void query_phy_status_page0(struct rtw_dev *rtwdev, u8 *phy_status,
 	else if (gain_a > u_bnd)
 		rx_power[RF_PATH_A] -= (gain_a - u_bnd) << 1;
 	if (gain_b < l_bnd)
-		rx_power[RF_PATH_A] += (l_bnd - gain_b) << 1;
+		rx_power[RF_PATH_B] += (l_bnd - gain_b) << 1;
 	else if (gain_b > u_bnd)
-		rx_power[RF_PATH_A] -= (gain_b - u_bnd) << 1;
+		rx_power[RF_PATH_B] -= (gain_b - u_bnd) << 1;
 
 	rx_power[RF_PATH_A] -= 110;
 	rx_power[RF_PATH_B] -= 110;
diff --git a/drivers/net/wireless/rsi/rsi_91x_hal.c b/drivers/net/wireless/rsi/rsi_91x_hal.c
index f84250bdb8cf..6f8d5f9a9f7e 100644
--- a/drivers/net/wireless/rsi/rsi_91x_hal.c
+++ b/drivers/net/wireless/rsi/rsi_91x_hal.c
@@ -622,6 +622,7 @@ static int bl_cmd(struct rsi_hw *adapter, u8 cmd, u8 exp_resp, char *str)
 	bl_start_cmd_timer(adapter, timeout);
 	status = bl_write_cmd(adapter, cmd, exp_resp, &regout_val);
 	if (status < 0) {
+		bl_stop_cmd_timer(adapter);
 		rsi_dbg(ERR_ZONE,
 			"%s: Command %s (%0x) writing failed..\n",
 			__func__, str, cmd);
@@ -737,10 +738,9 @@ static int ping_pong_write(struct rsi_hw *adapter, u8 cmd, u8 *addr, u32 size)
 	}
 
 	status = bl_cmd(adapter, cmd_req, cmd_resp, str);
-	if (status) {
-		bl_stop_cmd_timer(adapter);
+	if (status)
 		return status;
-	}
+
 	return 0;
 }
 
@@ -828,10 +828,9 @@ static int auto_fw_upgrade(struct rsi_hw *adapter, u8 *flash_content,
 
 	status = bl_cmd(adapter, EOF_REACHED, FW_LOADING_SUCCESSFUL,
 			"EOF_REACHED");
-	if (status) {
-		bl_stop_cmd_timer(adapter);
+	if (status)
 		return status;
-	}
+
 	rsi_dbg(INFO_ZONE, "FW loading is done and FW is running..\n");
 	return 0;
 }
@@ -849,6 +848,7 @@ static int rsi_hal_prepare_fwload(struct rsi_hw *adapter)
 						  &regout_val,
 						  RSI_COMMON_REG_SIZE);
 		if (status < 0) {
+			bl_stop_cmd_timer(adapter);
 			rsi_dbg(ERR_ZONE,
 				"%s: REGOUT read failed\n", __func__);
 			return status;
diff --git a/drivers/net/wireless/rsi/rsi_91x_usb.c b/drivers/net/wireless/rsi/rsi_91x_usb.c
index 760eaffeebd6..4b9e406b8461 100644
--- a/drivers/net/wireless/rsi/rsi_91x_usb.c
+++ b/drivers/net/wireless/rsi/rsi_91x_usb.c
@@ -16,6 +16,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/types.h>
 #include <net/rsi_91x.h>
 #include "rsi_usb.h"
 #include "rsi_hal.h"
@@ -29,7 +30,7 @@ MODULE_PARM_DESC(dev_oper_mode,
 		 "9[Wi-Fi STA + BT LE], 13[Wi-Fi STA + BT classic + BT LE]\n"
 		 "6[AP + BT classic], 14[AP + BT classic + BT LE]");
 
-static int rsi_rx_urb_submit(struct rsi_hw *adapter, u8 ep_num);
+static int rsi_rx_urb_submit(struct rsi_hw *adapter, u8 ep_num, gfp_t flags);
 
 /**
  * rsi_usb_card_write() - This function writes to the USB Card.
@@ -117,7 +118,7 @@ static int rsi_find_bulk_in_and_out_endpoints(struct usb_interface *interface,
 	__le16 buffer_size;
 	int ii, bin_found = 0, bout_found = 0;
 
-	iface_desc = &(interface->altsetting[0]);
+	iface_desc = interface->cur_altsetting;
 
 	for (ii = 0; ii < iface_desc->desc.bNumEndpoints; ++ii) {
 		endpoint = &(iface_desc->endpoint[ii].desc);
@@ -285,20 +286,29 @@ static void rsi_rx_done_handler(struct urb *urb)
 	status = 0;
 
 out:
-	if (rsi_rx_urb_submit(dev->priv, rx_cb->ep_num))
+	if (rsi_rx_urb_submit(dev->priv, rx_cb->ep_num, GFP_ATOMIC))
 		rsi_dbg(ERR_ZONE, "%s: Failed in urb submission", __func__);
 
 	if (status)
 		dev_kfree_skb(rx_cb->rx_skb);
 }
 
+static void rsi_rx_urb_kill(struct rsi_hw *adapter, u8 ep_num)
+{
+	struct rsi_91x_usbdev *dev = (struct rsi_91x_usbdev *)adapter->rsi_dev;
+	struct rx_usb_ctrl_block *rx_cb = &dev->rx_cb[ep_num - 1];
+	struct urb *urb = rx_cb->rx_urb;
+
+	usb_kill_urb(urb);
+}
+
 /**
  * rsi_rx_urb_submit() - This function submits the given URB to the USB stack.
  * @adapter: Pointer to the adapter structure.
  *
  * Return: 0 on success, a negative error code on failure.
  */
-static int rsi_rx_urb_submit(struct rsi_hw *adapter, u8 ep_num)
+static int rsi_rx_urb_submit(struct rsi_hw *adapter, u8 ep_num, gfp_t mem_flags)
 {
 	struct rsi_91x_usbdev *dev = (struct rsi_91x_usbdev *)adapter->rsi_dev;
 	struct rx_usb_ctrl_block *rx_cb = &dev->rx_cb[ep_num - 1];
@@ -328,9 +338,11 @@ static int rsi_rx_urb_submit(struct rsi_hw *adapter, u8 ep_num)
 			  rsi_rx_done_handler,
 			  rx_cb);
 
-	status = usb_submit_urb(urb, GFP_KERNEL);
-	if (status)
+	status = usb_submit_urb(urb, mem_flags);
+	if (status) {
 		rsi_dbg(ERR_ZONE, "%s: Failed in urb submission\n", __func__);
+		dev_kfree_skb(skb);
+	}
 
 	return status;
 }
@@ -816,17 +828,20 @@ static int rsi_probe(struct usb_interface *pfunction,
 		rsi_dbg(INIT_ZONE, "%s: Device Init Done\n", __func__);
 	}
 
-	status = rsi_rx_urb_submit(adapter, WLAN_EP);
+	status = rsi_rx_urb_submit(adapter, WLAN_EP, GFP_KERNEL);
 	if (status)
 		goto err1;
 
 	if (adapter->priv->coex_mode > 1) {
-		status = rsi_rx_urb_submit(adapter, BT_EP);
+		status = rsi_rx_urb_submit(adapter, BT_EP, GFP_KERNEL);
 		if (status)
-			goto err1;
+			goto err_kill_wlan_urb;
 	}
 
 	return 0;
+
+err_kill_wlan_urb:
+	rsi_rx_urb_kill(adapter, WLAN_EP);
 err1:
 	rsi_deinit_usb_interface(adapter);
 err:
@@ -857,6 +872,10 @@ static void rsi_disconnect(struct usb_interface *pfunction)
 		adapter->priv->bt_adapter = NULL;
 	}
 
+	if (adapter->priv->coex_mode > 1)
+		rsi_rx_urb_kill(adapter, BT_EP);
+	rsi_rx_urb_kill(adapter, WLAN_EP);
+
 	rsi_reset_card(adapter);
 	rsi_deinit_usb_interface(adapter);
 	rsi_91x_deinit(adapter);
diff --git a/drivers/net/wireless/st/cw1200/fwio.c b/drivers/net/wireless/st/cw1200/fwio.c
index 6574e78e05ea..2a03dc533b6a 100644
--- a/drivers/net/wireless/st/cw1200/fwio.c
+++ b/drivers/net/wireless/st/cw1200/fwio.c
@@ -320,12 +320,12 @@ int cw1200_load_firmware(struct cw1200_common *priv)
 		goto out;
 	}
 
-	priv->hw_type = cw1200_get_hw_type(val32, &major_revision);
-	if (priv->hw_type < 0) {
+	ret = cw1200_get_hw_type(val32, &major_revision);
+	if (ret < 0) {
 		pr_err("Can't deduce hardware type.\n");
-		ret = -ENOTSUPP;
 		goto out;
 	}
+	priv->hw_type = ret;
 
 	/* Set DPLL Reg value, and read back to confirm writes work */
 	ret = cw1200_reg_write_32(priv, ST90TDS_TSET_GEN_R_W_REG_ID,
diff --git a/drivers/net/wireless/ti/wl1251/event.c b/drivers/net/wireless/ti/wl1251/event.c
index 850864dbafa1..e6d426edab56 100644
--- a/drivers/net/wireless/ti/wl1251/event.c
+++ b/drivers/net/wireless/ti/wl1251/event.c
@@ -70,7 +70,7 @@ static int wl1251_event_ps_report(struct wl1251 *wl,
 		break;
 	}
 
-	return 0;
+	return ret;
 }
 
 static void wl1251_event_mbox_dump(struct event_mailbox *mbox)
diff --git a/drivers/net/wireless/zydas/zd1211rw/zd_usb.c b/drivers/net/wireless/zydas/zd1211rw/zd_usb.c
index 1965cd0fafc4..c403ad31473f 100644
--- a/drivers/net/wireless/zydas/zd1211rw/zd_usb.c
+++ b/drivers/net/wireless/zydas/zd1211rw/zd_usb.c
@@ -1263,7 +1263,7 @@ static void print_id(struct usb_device *udev)
 static int eject_installer(struct usb_interface *intf)
 {
 	struct usb_device *udev = interface_to_usbdev(intf);
-	struct usb_host_interface *iface_desc = &intf->altsetting[0];
+	struct usb_host_interface *iface_desc = intf->cur_altsetting;
 	struct usb_endpoint_descriptor *endpoint;
 	unsigned char *cmd;
 	u8 bulk_out_ep;
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 7370e06a0e4b..a2c59b2ba6cc 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -63,6 +63,8 @@ module_param_named(max_queues, xennet_max_queues, uint, 0644);
 MODULE_PARM_DESC(max_queues,
 		 "Maximum number of queues per virtual interface");
 
+#define XENNET_TIMEOUT  (5 * HZ)
+
 static const struct ethtool_ops xennet_ethtool_ops;
 
 struct netfront_cb {
@@ -1334,12 +1336,15 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev)
 
 	netif_carrier_off(netdev);
 
-	xenbus_switch_state(dev, XenbusStateInitialising);
-	wait_event(module_wq,
-		   xenbus_read_driver_state(dev->otherend) !=
-		   XenbusStateClosed &&
-		   xenbus_read_driver_state(dev->otherend) !=
-		   XenbusStateUnknown);
+	do {
+		xenbus_switch_state(dev, XenbusStateInitialising);
+		err = wait_event_timeout(module_wq,
+				 xenbus_read_driver_state(dev->otherend) !=
+				 XenbusStateClosed &&
+				 xenbus_read_driver_state(dev->otherend) !=
+				 XenbusStateUnknown, XENNET_TIMEOUT);
+	} while (!err);
+
 	return netdev;
 
  exit:
@@ -2139,28 +2144,43 @@ static const struct attribute_group xennet_dev_group = {
 };
 #endif /* CONFIG_SYSFS */
 
-static int xennet_remove(struct xenbus_device *dev)
+static void xennet_bus_close(struct xenbus_device *dev)
 {
-	struct netfront_info *info = dev_get_drvdata(&dev->dev);
-
-	dev_dbg(&dev->dev, "%s\n", dev->nodename);
+	int ret;
 
-	if (xenbus_read_driver_state(dev->otherend) != XenbusStateClosed) {
+	if (xenbus_read_driver_state(dev->otherend) == XenbusStateClosed)
+		return;
+	do {
 		xenbus_switch_state(dev, XenbusStateClosing);
-		wait_event(module_wq,
-			   xenbus_read_driver_state(dev->otherend) ==
-			   XenbusStateClosing ||
-			   xenbus_read_driver_state(dev->otherend) ==
-			   XenbusStateUnknown);
+		ret = wait_event_timeout(module_wq,
+				   xenbus_read_driver_state(dev->otherend) ==
+				   XenbusStateClosing ||
+				   xenbus_read_driver_state(dev->otherend) ==
+				   XenbusStateClosed ||
+				   xenbus_read_driver_state(dev->otherend) ==
+				   XenbusStateUnknown,
+				   XENNET_TIMEOUT);
+	} while (!ret);
+
+	if (xenbus_read_driver_state(dev->otherend) == XenbusStateClosed)
+		return;
 
+	do {
 		xenbus_switch_state(dev, XenbusStateClosed);
-		wait_event(module_wq,
-			   xenbus_read_driver_state(dev->otherend) ==
-			   XenbusStateClosed ||
-			   xenbus_read_driver_state(dev->otherend) ==
-			   XenbusStateUnknown);
-	}
+		ret = wait_event_timeout(module_wq,
+				   xenbus_read_driver_state(dev->otherend) ==
+				   XenbusStateClosed ||
+				   xenbus_read_driver_state(dev->otherend) ==
+				   XenbusStateUnknown,
+				   XENNET_TIMEOUT);
+	} while (!ret);
+}
+
+static int xennet_remove(struct xenbus_device *dev)
+{
+	struct netfront_info *info = dev_get_drvdata(&dev->dev);
 
+	xennet_bus_close(dev);
 	xennet_disconnect_backend(info);
 
 	if (info->netdev->reg_state == NETREG_REGISTERED)
diff --git a/drivers/nfc/fdp/fdp.c b/drivers/nfc/fdp/fdp.c
index 0cc9ac856fe2..ed2123129e0e 100644
--- a/drivers/nfc/fdp/fdp.c
+++ b/drivers/nfc/fdp/fdp.c
@@ -184,7 +184,7 @@ static int fdp_nci_send_patch(struct nci_dev *ndev, u8 conn_id, u8 type)
 	const struct firmware *fw;
 	struct sk_buff *skb;
 	unsigned long len;
-	u8 max_size, payload_size;
+	int max_size, payload_size;
 	int rc = 0;
 
 	if ((type == NCI_PATCH_TYPE_OTP && !info->otp_patch) ||
@@ -207,8 +207,7 @@ static int fdp_nci_send_patch(struct nci_dev *ndev, u8 conn_id, u8 type)
 
 	while (len) {
 
-		payload_size = min_t(unsigned long, (unsigned long) max_size,
-				     len);
+		payload_size = min_t(unsigned long, max_size, len);
 
 		skb = nci_skb_alloc(ndev, (NCI_CTRL_HDR_SIZE + payload_size),
 				    GFP_KERNEL);
diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c
index e897e4d768ef..d7a355d05368 100644
--- a/drivers/nfc/pn533/usb.c
+++ b/drivers/nfc/pn533/usb.c
@@ -391,7 +391,7 @@ static int pn533_acr122_poweron_rdr(struct pn533_usb_phy *phy)
 		       cmd, sizeof(cmd), false);
 
 	rc = usb_bulk_msg(phy->udev, phy->out_urb->pipe, buffer, sizeof(cmd),
-			  &transferred, 0);
+			  &transferred, 5000);
 	kfree(buffer);
 	if (rc || (transferred != sizeof(cmd))) {
 		nfc_err(&phy->udev->dev,
diff --git a/drivers/nfc/pn544/i2c.c b/drivers/nfc/pn544/i2c.c
index 720c89d6066e..4ac8cb262559 100644
--- a/drivers/nfc/pn544/i2c.c
+++ b/drivers/nfc/pn544/i2c.c
@@ -225,6 +225,7 @@ static void pn544_hci_i2c_platform_init(struct pn544_i2c_phy *phy)
 
 out:
 	gpiod_set_value_cansleep(phy->gpiod_en, !phy->en_polarity);
+	usleep_range(10000, 15000);
 }
 
 static void pn544_hci_i2c_enable_mode(struct pn544_i2c_phy *phy, int run_mode)
diff --git a/drivers/nfc/pn544/pn544.c b/drivers/nfc/pn544/pn544.c
index cda996f6954e..2b83156efe3f 100644
--- a/drivers/nfc/pn544/pn544.c
+++ b/drivers/nfc/pn544/pn544.c
@@ -693,7 +693,7 @@ static int pn544_hci_check_presence(struct nfc_hci_dev *hdev,
 		    target->nfcid1_len != 10)
 			return -EOPNOTSUPP;
 
-		 return nfc_hci_send_cmd(hdev, NFC_HCI_RF_READER_A_GATE,
+		return nfc_hci_send_cmd(hdev, NFC_HCI_RF_READER_A_GATE,
 				     PN544_RF_READER_CMD_ACTIVATE_NEXT,
 				     target->nfcid1, target->nfcid1_len, NULL);
 	} else if (target->supported_protocols & (NFC_PROTO_JEWEL_MASK |
diff --git a/drivers/nfc/port100.c b/drivers/nfc/port100.c
index 604dba4f18af..8e4d355dc3ae 100644
--- a/drivers/nfc/port100.c
+++ b/drivers/nfc/port100.c
@@ -565,7 +565,7 @@ static void port100_tx_update_payload_len(void *_frame, int len)
 {
 	struct port100_frame *frame = _frame;
 
-	frame->datalen = cpu_to_le16(le16_to_cpu(frame->datalen) + len);
+	le16_add_cpu(&frame->datalen, len);
 }
 
 static bool port100_rx_frame_is_valid(void *_frame)
diff --git a/drivers/nfc/s3fwrn5/core.c b/drivers/nfc/s3fwrn5/core.c
index 91d4d5b28a7d..ba6c486d6465 100644
--- a/drivers/nfc/s3fwrn5/core.c
+++ b/drivers/nfc/s3fwrn5/core.c
@@ -198,6 +198,7 @@ int s3fwrn5_recv_frame(struct nci_dev *ndev, struct sk_buff *skb,
 	case S3FWRN5_MODE_FW:
 		return s3fwrn5_fw_recv_frame(ndev, skb);
 	default:
+		kfree_skb(skb);
 		return -ENODEV;
 	}
 }
diff --git a/drivers/nfc/st21nfca/dep.c b/drivers/nfc/st21nfca/dep.c
index 60acdfd1cb8c..856a10c293f8 100644
--- a/drivers/nfc/st21nfca/dep.c
+++ b/drivers/nfc/st21nfca/dep.c
@@ -173,8 +173,10 @@ static int st21nfca_tm_send_atr_res(struct nfc_hci_dev *hdev,
 		memcpy(atr_res->gbi, atr_req->gbi, gb_len);
 		r = nfc_set_remote_general_bytes(hdev->ndev, atr_res->gbi,
 						  gb_len);
-		if (r < 0)
+		if (r < 0) {
+			kfree_skb(skb);
 			return r;
+		}
 	}
 
 	info->dep_info.curr_nfc_dep_pni = 0;
diff --git a/drivers/ntb/ntb.c b/drivers/ntb/ntb.c
index 2581ab724c34..f8f75a504a58 100644
--- a/drivers/ntb/ntb.c
+++ b/drivers/ntb/ntb.c
@@ -214,10 +214,8 @@ int ntb_default_port_number(struct ntb_dev *ntb)
 	case NTB_TOPO_B2B_DSD:
 		return NTB_PORT_SEC_DSD;
 	default:
-		break;
+		return 0;
 	}
-
-	return -EINVAL;
 }
 EXPORT_SYMBOL(ntb_default_port_number);
 
@@ -240,10 +238,8 @@ int ntb_default_peer_port_number(struct ntb_dev *ntb, int pidx)
 	case NTB_TOPO_B2B_DSD:
 		return NTB_PORT_PRI_USD;
 	default:
-		break;
+		return 0;
 	}
-
-	return -EINVAL;
 }
 EXPORT_SYMBOL(ntb_default_peer_port_number);
 
@@ -315,4 +311,3 @@ static void __exit ntb_driver_exit(void)
 	bus_unregister(&ntb_bus);
 }
 module_exit(ntb_driver_exit);
-
diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c
index c6a1dee3c429..104cb181efc4 100644
--- a/drivers/ntb/test/ntb_perf.c
+++ b/drivers/ntb/test/ntb_perf.c
@@ -158,6 +158,8 @@ struct perf_peer {
 	/* NTB connection setup service */
 	struct work_struct	service;
 	unsigned long		sts;
+
+	struct completion init_comp;
 };
 #define to_peer_service(__work) \
 	container_of(__work, struct perf_peer, service)
@@ -546,6 +548,7 @@ static int perf_setup_outbuf(struct perf_peer *peer)
 
 	/* Initialization is finally done */
 	set_bit(PERF_STS_DONE, &peer->sts);
+	complete_all(&peer->init_comp);
 
 	return 0;
 }
@@ -556,7 +559,7 @@ static void perf_free_inbuf(struct perf_peer *peer)
 		return;
 
 	(void)ntb_mw_clear_trans(peer->perf->ntb, peer->pidx, peer->gidx);
-	dma_free_coherent(&peer->perf->ntb->dev, peer->inbuf_size,
+	dma_free_coherent(&peer->perf->ntb->pdev->dev, peer->inbuf_size,
 			  peer->inbuf, peer->inbuf_xlat);
 	peer->inbuf = NULL;
 }
@@ -585,8 +588,9 @@ static int perf_setup_inbuf(struct perf_peer *peer)
 
 	perf_free_inbuf(peer);
 
-	peer->inbuf = dma_alloc_coherent(&perf->ntb->dev, peer->inbuf_size,
-					 &peer->inbuf_xlat, GFP_KERNEL);
+	peer->inbuf = dma_alloc_coherent(&perf->ntb->pdev->dev,
+					 peer->inbuf_size, &peer->inbuf_xlat,
+					 GFP_KERNEL);
 	if (!peer->inbuf) {
 		dev_err(&perf->ntb->dev, "Failed to alloc inbuf of %pa\n",
 			&peer->inbuf_size);
@@ -636,6 +640,7 @@ static void perf_service_work(struct work_struct *work)
 		perf_setup_outbuf(peer);
 
 	if (test_and_clear_bit(PERF_CMD_CLEAR, &peer->sts)) {
+		init_completion(&peer->init_comp);
 		clear_bit(PERF_STS_DONE, &peer->sts);
 		if (test_bit(0, &peer->perf->busy_flag) &&
 		    peer == peer->perf->test_peer) {
@@ -652,7 +657,7 @@ static int perf_init_service(struct perf_ctx *perf)
 {
 	u64 mask;
 
-	if (ntb_peer_mw_count(perf->ntb) < perf->pcnt + 1) {
+	if (ntb_peer_mw_count(perf->ntb) < perf->pcnt) {
 		dev_err(&perf->ntb->dev, "Not enough memory windows\n");
 		return -EINVAL;
 	}
@@ -1043,8 +1048,9 @@ static int perf_submit_test(struct perf_peer *peer)
 	struct perf_thread *pthr;
 	int tidx, ret;
 
-	if (!test_bit(PERF_STS_DONE, &peer->sts))
-		return -ENOLINK;
+	ret = wait_for_completion_interruptible(&peer->init_comp);
+	if (ret < 0)
+		return ret;
 
 	if (test_and_set_bit_lock(0, &perf->busy_flag))
 		return -EBUSY;
@@ -1410,10 +1416,21 @@ static int perf_init_peers(struct perf_ctx *perf)
 			peer->gidx = pidx;
 		}
 		INIT_WORK(&peer->service, perf_service_work);
+		init_completion(&peer->init_comp);
 	}
 	if (perf->gidx == -1)
 		perf->gidx = pidx;
 
+	/*
+	 * Hardware with only two ports may not have unique port
+	 * numbers. In this case, the gidxs should all be zero.
+	 */
+	if (perf->pcnt == 1 &&  ntb_port_number(perf->ntb) == 0 &&
+	    ntb_peer_port_number(perf->ntb, 0) == 0) {
+		perf->gidx = 0;
+		perf->peers[0].gidx = 0;
+	}
+
 	for (pidx = 0; pidx < perf->pcnt; pidx++) {
 		ret = perf_setup_peer_mw(&perf->peers[pidx]);
 		if (ret)
@@ -1509,4 +1526,3 @@ static void __exit perf_exit(void)
 	destroy_workqueue(perf_wq);
 }
 module_exit(perf_exit);
-
diff --git a/drivers/ntb/test/ntb_pingpong.c b/drivers/ntb/test/ntb_pingpong.c
index 65865e460ab8..18d00eec7b02 100644
--- a/drivers/ntb/test/ntb_pingpong.c
+++ b/drivers/ntb/test/ntb_pingpong.c
@@ -121,15 +121,14 @@ static int pp_find_next_peer(struct pp_ctx *pp)
 	link = ntb_link_is_up(pp->ntb, NULL, NULL);
 
 	/* Find next available peer */
-	if (link & pp->nmask) {
+	if (link & pp->nmask)
 		pidx = __ffs64(link & pp->nmask);
-		out_db = BIT_ULL(pidx + 1);
-	} else if (link & pp->pmask) {
+	else if (link & pp->pmask)
 		pidx = __ffs64(link & pp->pmask);
-		out_db = BIT_ULL(pidx);
-	} else {
+	else
 		return -ENODEV;
-	}
+
+	out_db = BIT_ULL(ntb_peer_port_number(pp->ntb, pidx));
 
 	spin_lock(&pp->lock);
 	pp->out_pidx = pidx;
@@ -303,7 +302,7 @@ static void pp_init_flds(struct pp_ctx *pp)
 			break;
 	}
 
-	pp->in_db = BIT_ULL(pidx);
+	pp->in_db = BIT_ULL(lport);
 	pp->pmask = GENMASK_ULL(pidx, 0) >> 1;
 	pp->nmask = GENMASK_ULL(pcnt - 1, pidx);
 
@@ -435,4 +434,3 @@ static void __exit pp_exit(void)
 	debugfs_remove_recursive(pp_dbgfs_topdir);
 }
 module_exit(pp_exit);
-
diff --git a/drivers/ntb/test/ntb_tool.c b/drivers/ntb/test/ntb_tool.c
index d592c0ffbd19..311d6ab8d016 100644
--- a/drivers/ntb/test/ntb_tool.c
+++ b/drivers/ntb/test/ntb_tool.c
@@ -504,7 +504,7 @@ static ssize_t tool_peer_link_read(struct file *filep, char __user *ubuf,
 	buf[1] = '\n';
 	buf[2] = '\0';
 
-	return simple_read_from_buffer(ubuf, size, offp, buf, 3);
+	return simple_read_from_buffer(ubuf, size, offp, buf, 2);
 }
 
 static TOOL_FOPS_RDWR(tool_peer_link_fops,
@@ -590,7 +590,7 @@ static int tool_setup_mw(struct tool_ctx *tc, int pidx, int widx,
 	inmw->size = min_t(resource_size_t, req_size, size);
 	inmw->size = round_up(inmw->size, addr_align);
 	inmw->size = round_up(inmw->size, size_align);
-	inmw->mm_base = dma_alloc_coherent(&tc->ntb->dev, inmw->size,
+	inmw->mm_base = dma_alloc_coherent(&tc->ntb->pdev->dev, inmw->size,
 					   &inmw->dma_base, GFP_KERNEL);
 	if (!inmw->mm_base)
 		return -ENOMEM;
@@ -612,7 +612,7 @@ static int tool_setup_mw(struct tool_ctx *tc, int pidx, int widx,
 	return 0;
 
 err_free_dma:
-	dma_free_coherent(&tc->ntb->dev, inmw->size, inmw->mm_base,
+	dma_free_coherent(&tc->ntb->pdev->dev, inmw->size, inmw->mm_base,
 			  inmw->dma_base);
 	inmw->mm_base = NULL;
 	inmw->dma_base = 0;
@@ -629,7 +629,7 @@ static void tool_free_mw(struct tool_ctx *tc, int pidx, int widx)
 
 	if (inmw->mm_base != NULL) {
 		ntb_mw_clear_trans(tc->ntb, pidx, widx);
-		dma_free_coherent(&tc->ntb->dev, inmw->size,
+		dma_free_coherent(&tc->ntb->pdev->dev, inmw->size,
 				  inmw->mm_base, inmw->dma_base);
 	}
 
@@ -1690,4 +1690,3 @@ static void __exit tool_exit(void)
 	debugfs_remove_recursive(tool_dbgfs_topdir);
 }
 module_exit(tool_exit);
-
diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index 0d97158e7ac3..f6ad9d27be6b 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -1006,8 +1006,10 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
 			return -EFAULT;
 	}
 
-	if (!desc || (desc->out_num + desc->in_num == 0) ||
-			!test_bit(cmd, &cmd_mask))
+	if (!desc ||
+	    (desc->out_num + desc->in_num == 0) ||
+	    cmd > ND_CMD_CALL ||
+	    !test_bit(cmd, &cmd_mask))
 		return -ENOTTY;
 
 	/* fail write commands (when read-only) */
diff --git a/drivers/nvdimm/security.c b/drivers/nvdimm/security.c
index a570f2263a42..bb1851133f28 100644
--- a/drivers/nvdimm/security.c
+++ b/drivers/nvdimm/security.c
@@ -461,14 +461,19 @@ void __nvdimm_security_overwrite_query(struct nvdimm *nvdimm)
 	else
 		dev_dbg(&nvdimm->dev, "overwrite completed\n");
 
-	if (nvdimm->sec.overwrite_state)
-		sysfs_notify_dirent(nvdimm->sec.overwrite_state);
+	/*
+	 * Mark the overwrite work done and update dimm security flags,
+	 * then send a sysfs event notification to wake up userspace
+	 * poll threads to picked up the changed state.
+	 */
 	nvdimm->sec.overwrite_tmo = 0;
 	clear_bit(NDD_SECURITY_OVERWRITE, &nvdimm->flags);
 	clear_bit(NDD_WORK_PENDING, &nvdimm->flags);
-	put_device(&nvdimm->dev);
 	nvdimm->sec.state = nvdimm_security_state(nvdimm, NVDIMM_USER);
 	nvdimm->sec.ext_state = nvdimm_security_state(nvdimm, NVDIMM_MASTER);
+	if (nvdimm->sec.overwrite_state)
+		sysfs_notify_dirent(nvdimm->sec.overwrite_state);
+	put_device(&nvdimm->dev);
 }
 
 void nvdimm_security_overwrite_query(struct work_struct *work)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 9c114b58d722..eee1711d9639 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -6,6 +6,7 @@
 
 #include <linux/blkdev.h>
 #include <linux/blk-mq.h>
+#include <linux/compat.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/hdreg.h>
@@ -66,8 +67,8 @@ MODULE_PARM_DESC(streams, "turn on support for Streams write directives");
  * nvme_reset_wq - hosts nvme reset works
  * nvme_delete_wq - hosts nvme delete works
  *
- * nvme_wq will host works such are scan, aen handling, fw activation,
- * keep-alive error recovery, periodic reconnects etc. nvme_reset_wq
+ * nvme_wq will host works such as scan, aen handling, fw activation,
+ * keep-alive, periodic reconnects etc. nvme_reset_wq
  * runs reset works which also flush works hosted on nvme_wq for
  * serialization purposes. nvme_delete_wq host controller deletion
  * works which flush reset works for serialization.
@@ -935,7 +936,7 @@ static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status)
 		startka = true;
 	spin_unlock_irqrestore(&ctrl->lock, flags);
 	if (startka)
-		schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
+		queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ);
 }
 
 static int nvme_keep_alive(struct nvme_ctrl *ctrl)
@@ -965,7 +966,7 @@ static void nvme_keep_alive_work(struct work_struct *work)
 		dev_dbg(ctrl->device,
 			"reschedule traffic based keep-alive timer\n");
 		ctrl->comp_seen = false;
-		schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
+		queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ);
 		return;
 	}
 
@@ -982,7 +983,7 @@ static void nvme_start_keep_alive(struct nvme_ctrl *ctrl)
 	if (unlikely(ctrl->kato == 0))
 		return;
 
-	schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
+	queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ);
 }
 
 void nvme_stop_keep_alive(struct nvme_ctrl *ctrl)
@@ -994,6 +995,19 @@ void nvme_stop_keep_alive(struct nvme_ctrl *ctrl)
 }
 EXPORT_SYMBOL_GPL(nvme_stop_keep_alive);
 
+/*
+ * In NVMe 1.0 the CNS field was just a binary controller or namespace
+ * flag, thus sending any new CNS opcodes has a big chance of not working.
+ * Qemu unfortunately had that bug after reporting a 1.1 version compliance
+ * (but not for any later version).
+ */
+static bool nvme_ctrl_limited_cns(struct nvme_ctrl *ctrl)
+{
+	if (ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)
+		return ctrl->vs < NVME_VS(1, 2, 0);
+	return ctrl->vs < NVME_VS(1, 1, 0);
+}
+
 static int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
 {
 	struct nvme_command c = { };
@@ -1126,8 +1140,8 @@ static struct nvme_id_ns *nvme_identify_ns(struct nvme_ctrl *ctrl,
 static int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11,
 		      void *buffer, size_t buflen, u32 *result)
 {
+	union nvme_result res = { 0 };
 	struct nvme_command c;
-	union nvme_result res;
 	int ret;
 
 	memset(&c, 0, sizeof(c));
@@ -1188,6 +1202,18 @@ static void nvme_enable_aen(struct nvme_ctrl *ctrl)
 			 supported_aens);
 }
 
+/*
+ * Convert integer values from ioctl structures to user pointers, silently
+ * ignoring the upper bits in the compat case to match behaviour of 32-bit
+ * kernels.
+ */
+static void __user *nvme_to_user_ptr(uintptr_t ptrval)
+{
+	if (in_compat_syscall())
+		ptrval = (compat_uptr_t)ptrval;
+	return (void __user *)ptrval;
+}
+
 static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 {
 	struct nvme_user_io io;
@@ -1211,7 +1237,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 
 	length = (io.nblocks + 1) << ns->lba_shift;
 	meta_len = (io.nblocks + 1) * ns->ms;
-	metadata = (void __user *)(uintptr_t)io.metadata;
+	metadata = nvme_to_user_ptr(io.metadata);
 
 	if (ns->ext) {
 		length += meta_len;
@@ -1234,7 +1260,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 	c.rw.appmask = cpu_to_le16(io.appmask);
 
 	return nvme_submit_user_cmd(ns->queue, &c,
-			(void __user *)(uintptr_t)io.addr, length,
+			nvme_to_user_ptr(io.addr), length,
 			metadata, meta_len, lower_32_bits(io.slba), NULL, 0);
 }
 
@@ -1355,9 +1381,9 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 
 	effects = nvme_passthru_start(ctrl, ns, cmd.opcode);
 	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
-			(void __user *)(uintptr_t)cmd.addr, cmd.data_len,
-			(void __user *)(uintptr_t)cmd.metadata,
-			cmd.metadata_len, 0, &result, timeout);
+			nvme_to_user_ptr(cmd.addr), cmd.data_len,
+			nvme_to_user_ptr(cmd.metadata), cmd.metadata_len,
+			0, &result, timeout);
 	nvme_passthru_end(ctrl, effects);
 
 	if (status >= 0) {
@@ -1402,8 +1428,8 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 
 	effects = nvme_passthru_start(ctrl, ns, cmd.opcode);
 	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
-			(void __user *)(uintptr_t)cmd.addr, cmd.data_len,
-			(void __user *)(uintptr_t)cmd.metadata, cmd.metadata_len,
+			nvme_to_user_ptr(cmd.addr), cmd.data_len,
+			nvme_to_user_ptr(cmd.metadata), cmd.metadata_len,
 			0, &cmd.result, timeout);
 	nvme_passthru_end(ctrl, effects);
 
@@ -1756,7 +1782,7 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 	if (ns->head->disk) {
 		nvme_update_disk_info(ns->head->disk, ns, id);
 		blk_queue_stack_limits(ns->head->disk->queue, ns->queue);
-		revalidate_disk(ns->head->disk);
+		nvme_mpath_update_disk_size(ns->head->disk);
 	}
 #endif
 }
@@ -2456,8 +2482,8 @@ static bool nvme_validate_cntlid(struct nvme_subsystem *subsys,
 	lockdep_assert_held(&nvme_subsystems_lock);
 
 	list_for_each_entry(tmp, &subsys->ctrls, subsys_entry) {
-		if (ctrl->state == NVME_CTRL_DELETING ||
-		    ctrl->state == NVME_CTRL_DEAD)
+		if (tmp->state == NVME_CTRL_DELETING ||
+		    tmp->state == NVME_CTRL_DEAD)
 			continue;
 
 		if (tmp->cntlid == ctrl->cntlid) {
@@ -3420,6 +3446,8 @@ static int nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 
 	return 0;
  out_put_disk:
+	/* prevent double queue cleanup */
+	ns->disk->queue = NULL;
 	put_disk(ns->disk);
  out_unlink_ns:
 	mutex_lock(&ctrl->subsys->lock);
@@ -3593,8 +3621,7 @@ static void nvme_scan_work(struct work_struct *work)
 
 	mutex_lock(&ctrl->scan_lock);
 	nn = le32_to_cpu(id->nn);
-	if (ctrl->vs >= NVME_VS(1, 1, 0) &&
-	    !(ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)) {
+	if (!nvme_ctrl_limited_cns(ctrl)) {
 		if (!nvme_scan_ns_list(ctrl, nn))
 			goto out_free_id;
 	}
@@ -3692,7 +3719,7 @@ static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl)
 	if (!log)
 		return;
 
-	if (nvme_get_log(ctrl, NVME_NSID_ALL, 0, NVME_LOG_FW_SLOT, log,
+	if (nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_FW_SLOT, 0, log,
 			sizeof(*log), 0))
 		dev_warn(ctrl->device, "Get FW SLOT INFO log error\n");
 	kfree(log);
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index dd8169bbf0d2..551d5f16e83c 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -2882,10 +2882,22 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status)
 static void
 __nvme_fc_terminate_io(struct nvme_fc_ctrl *ctrl)
 {
-	nvme_stop_keep_alive(&ctrl->ctrl);
+	/*
+	 * if state is connecting - the error occurred as part of a
+	 * reconnect attempt. The create_association error paths will
+	 * clean up any outstanding io.
+	 *
+	 * if it's a different state - ensure all pending io is
+	 * terminated. Given this can delay while waiting for the
+	 * aborted io to return, we recheck adapter state below
+	 * before changing state.
+	 */
+	if (ctrl->ctrl.state != NVME_CTRL_CONNECTING) {
+		nvme_stop_keep_alive(&ctrl->ctrl);
 
-	/* will block will waiting for io to terminate */
-	nvme_fc_delete_association(ctrl);
+		/* will block will waiting for io to terminate */
+		nvme_fc_delete_association(ctrl);
+	}
 
 	if (ctrl->ctrl.state != NVME_CTRL_CONNECTING &&
 	    !nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING))
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 526fe68692ca..ec3c0f2ba405 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -3,6 +3,7 @@
  * Copyright (c) 2017-2018 Christoph Hellwig.
  */
 
+#include <linux/backing-dev.h>
 #include <linux/moduleparam.h>
 #include <trace/events/block.h>
 #include "nvme.h"
@@ -166,14 +167,19 @@ void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
 	mutex_unlock(&ctrl->scan_lock);
 }
 
+static bool nvme_path_is_disabled(struct nvme_ns *ns)
+{
+	return ns->ctrl->state != NVME_CTRL_LIVE ||
+		test_bit(NVME_NS_ANA_PENDING, &ns->flags);
+}
+
 static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head, int node)
 {
 	int found_distance = INT_MAX, fallback_distance = INT_MAX, distance;
 	struct nvme_ns *found = NULL, *fallback = NULL, *ns;
 
 	list_for_each_entry_rcu(ns, &head->list, siblings) {
-		if (ns->ctrl->state != NVME_CTRL_LIVE ||
-		    test_bit(NVME_NS_ANA_PENDING, &ns->flags))
+		if (nvme_path_is_disabled(ns))
 			continue;
 
 		if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_NUMA)
@@ -227,8 +233,7 @@ static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head,
 	for (ns = nvme_next_ns(head, old);
 	     ns != old;
 	     ns = nvme_next_ns(head, ns)) {
-		if (ns->ctrl->state != NVME_CTRL_LIVE ||
-		    test_bit(NVME_NS_ANA_PENDING, &ns->flags))
+		if (nvme_path_is_disabled(ns))
 			continue;
 
 		if (ns->ana_state == NVME_ANA_OPTIMIZED) {
@@ -239,6 +244,17 @@ static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head,
 			fallback = ns;
 	}
 
+	/*
+	 * The loop above skips the current path for round-robin semantics.
+	 * Fall back to the current path if either:
+	 *  - no other optimized path found and current is optimized,
+	 *  - no other usable path found and current is usable.
+	 */
+	if (!nvme_path_is_disabled(old) &&
+	    (old->ana_state == NVME_ANA_OPTIMIZED ||
+	     (!fallback && old->ana_state == NVME_ANA_NONOPTIMIZED)))
+		return old;
+
 	if (!fallback)
 		return NULL;
 	found = fallback;
@@ -259,10 +275,13 @@ inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head)
 	struct nvme_ns *ns;
 
 	ns = srcu_dereference(head->current_path[node], &head->srcu);
-	if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_RR && ns)
-		ns = nvme_round_robin_path(head, node, ns);
-	if (unlikely(!ns || !nvme_path_is_optimized(ns)))
-		ns = __nvme_find_path(head, node);
+	if (unlikely(!ns))
+		return __nvme_find_path(head, node);
+
+	if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_RR)
+		return nvme_round_robin_path(head, node, ns);
+	if (unlikely(!nvme_path_is_optimized(ns)))
+		return __nvme_find_path(head, node);
 	return ns;
 }
 
@@ -404,15 +423,14 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
 {
 	struct nvme_ns_head *head = ns->head;
 
-	lockdep_assert_held(&ns->head->lock);
-
 	if (!head->disk)
 		return;
 
-	if (!(head->disk->flags & GENHD_FL_UP))
+	if (!test_and_set_bit(NVME_NSHEAD_DISK_LIVE, &head->flags))
 		device_add_disk(&head->subsys->dev, head->disk,
 				nvme_ns_id_attr_groups);
 
+	mutex_lock(&head->lock);
 	if (nvme_path_is_optimized(ns)) {
 		int node, srcu_idx;
 
@@ -421,9 +439,10 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
 			__nvme_find_path(head, node);
 		srcu_read_unlock(&head->srcu, srcu_idx);
 	}
+	mutex_unlock(&head->lock);
 
-	synchronize_srcu(&ns->head->srcu);
-	kblockd_schedule_work(&ns->head->requeue_work);
+	synchronize_srcu(&head->srcu);
+	kblockd_schedule_work(&head->requeue_work);
 }
 
 static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data,
@@ -474,14 +493,12 @@ static inline bool nvme_state_is_live(enum nvme_ana_state state)
 static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc,
 		struct nvme_ns *ns)
 {
-	mutex_lock(&ns->head->lock);
 	ns->ana_grpid = le32_to_cpu(desc->grpid);
 	ns->ana_state = desc->state;
 	clear_bit(NVME_NS_ANA_PENDING, &ns->flags);
 
 	if (nvme_state_is_live(ns->ana_state))
 		nvme_mpath_set_live(ns);
-	mutex_unlock(&ns->head->lock);
 }
 
 static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
@@ -501,7 +518,7 @@ static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
 	if (!nr_nsids)
 		return 0;
 
-	down_write(&ctrl->namespaces_rwsem);
+	down_read(&ctrl->namespaces_rwsem);
 	list_for_each_entry(ns, &ctrl->namespaces, list) {
 		unsigned nsid = le32_to_cpu(desc->nsids[n]);
 
@@ -512,7 +529,7 @@ static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
 		if (++n == nr_nsids)
 			break;
 	}
-	up_write(&ctrl->namespaces_rwsem);
+	up_read(&ctrl->namespaces_rwsem);
 	return 0;
 }
 
@@ -632,31 +649,45 @@ static ssize_t ana_state_show(struct device *dev, struct device_attribute *attr,
 }
 DEVICE_ATTR_RO(ana_state);
 
-static int nvme_set_ns_ana_state(struct nvme_ctrl *ctrl,
+static int nvme_lookup_ana_group_desc(struct nvme_ctrl *ctrl,
 		struct nvme_ana_group_desc *desc, void *data)
 {
-	struct nvme_ns *ns = data;
+	struct nvme_ana_group_desc *dst = data;
 
-	if (ns->ana_grpid == le32_to_cpu(desc->grpid)) {
-		nvme_update_ns_ana_state(desc, ns);
-		return -ENXIO; /* just break out of the loop */
-	}
+	if (desc->grpid != dst->grpid)
+		return 0;
 
-	return 0;
+	*dst = *desc;
+	return -ENXIO; /* just break out of the loop */
 }
 
 void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id)
 {
 	if (nvme_ctrl_use_ana(ns->ctrl)) {
+		struct nvme_ana_group_desc desc = {
+			.grpid = id->anagrpid,
+			.state = 0,
+		};
+
 		mutex_lock(&ns->ctrl->ana_lock);
 		ns->ana_grpid = le32_to_cpu(id->anagrpid);
-		nvme_parse_ana_log(ns->ctrl, ns, nvme_set_ns_ana_state);
+		nvme_parse_ana_log(ns->ctrl, &desc, nvme_lookup_ana_group_desc);
 		mutex_unlock(&ns->ctrl->ana_lock);
+		if (desc.state) {
+			/* found the group desc: update */
+			nvme_update_ns_ana_state(&desc, ns);
+		}
 	} else {
-		mutex_lock(&ns->head->lock);
 		ns->ana_state = NVME_ANA_OPTIMIZED; 
 		nvme_mpath_set_live(ns);
-		mutex_unlock(&ns->head->lock);
+	}
+
+	if (bdi_cap_stable_pages_required(ns->queue->backing_dev_info)) {
+		struct gendisk *disk = ns->head->disk;
+
+		if (disk)
+			disk->queue->backing_dev_info->capabilities |=
+					BDI_CAP_STABLE_WRITES;
 	}
 }
 
@@ -671,6 +702,14 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 	kblockd_schedule_work(&head->requeue_work);
 	flush_work(&head->requeue_work);
 	blk_cleanup_queue(head->disk->queue);
+	if (!test_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) {
+		/*
+		 * if device_add_disk wasn't called, prevent
+		 * disk release to put a bogus reference on the
+		 * request queue
+		 */
+		head->disk->queue = NULL;
+	}
 	put_disk(head->disk);
 }
 
@@ -703,6 +742,7 @@ int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	}
 
 	INIT_WORK(&ctrl->ana_work, nvme_ana_work);
+	kfree(ctrl->ana_log_buf);
 	ctrl->ana_log_buf = kmalloc(ctrl->ana_log_size, GFP_KERNEL);
 	if (!ctrl->ana_log_buf) {
 		error = -ENOMEM;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 81215ca32671..9036cf3c44b4 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -309,6 +309,8 @@ struct nvme_ns_head {
 	spinlock_t		requeue_lock;
 	struct work_struct	requeue_work;
 	struct mutex		lock;
+	unsigned long		flags;
+#define NVME_NSHEAD_DISK_LIVE	0
 	struct nvme_ns __rcu	*current_path[];
 #endif
 };
@@ -502,6 +504,16 @@ static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
 		kblockd_schedule_work(&head->requeue_work);
 }
 
+static inline void nvme_mpath_update_disk_size(struct gendisk *disk)
+{
+	struct block_device *bdev = bdget_disk(disk, 0);
+
+	if (bdev) {
+		bd_set_size(bdev, get_capacity(disk) << SECTOR_SHIFT);
+		bdput(bdev);
+	}
+}
+
 extern struct device_attribute dev_attr_ana_grpid;
 extern struct device_attribute dev_attr_ana_state;
 extern struct device_attribute subsys_attr_iopolicy;
@@ -572,6 +584,9 @@ static inline void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys)
 static inline void nvme_mpath_start_freeze(struct nvme_subsystem *subsys)
 {
 }
+static inline void nvme_mpath_update_disk_size(struct gendisk *disk)
+{
+}
 #endif /* CONFIG_NVME_MULTIPATH */
 
 #ifdef CONFIG_NVM
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index c9f5983a9f82..727fec79b6cf 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -73,13 +73,13 @@ static const struct kernel_param_ops queue_count_ops = {
 	.get = param_get_int,
 };
 
-static int write_queues;
+static unsigned int write_queues;
 module_param_cb(write_queues, &queue_count_ops, &write_queues, 0644);
 MODULE_PARM_DESC(write_queues,
 	"Number of queues to use for writes. If not set, reads and writes "
 	"will share a queue set.");
 
-static int poll_queues = 0;
+static unsigned int poll_queues = 0;
 module_param_cb(poll_queues, &queue_count_ops, &poll_queues, 0644);
 MODULE_PARM_DESC(poll_queues, "Number of queues to use for polled IO.");
 
@@ -183,7 +183,6 @@ struct nvme_queue {
 	 /* only used for poll queues: */
 	spinlock_t cq_poll_lock ____cacheline_aligned_in_smp;
 	volatile struct nvme_completion *cqes;
-	struct blk_mq_tags **tags;
 	dma_addr_t sq_dma_addr;
 	dma_addr_t cq_dma_addr;
 	u32 __iomem *q_db;
@@ -392,29 +391,17 @@ static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 
 	WARN_ON(hctx_idx != 0);
 	WARN_ON(dev->admin_tagset.tags[0] != hctx->tags);
-	WARN_ON(nvmeq->tags);
 
 	hctx->driver_data = nvmeq;
-	nvmeq->tags = &dev->admin_tagset.tags[0];
 	return 0;
 }
 
-static void nvme_admin_exit_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
-{
-	struct nvme_queue *nvmeq = hctx->driver_data;
-
-	nvmeq->tags = NULL;
-}
-
 static int nvme_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 			  unsigned int hctx_idx)
 {
 	struct nvme_dev *dev = data;
 	struct nvme_queue *nvmeq = &dev->queues[hctx_idx + 1];
 
-	if (!nvmeq->tags)
-		nvmeq->tags = &dev->tagset.tags[hctx_idx];
-
 	WARN_ON(dev->tagset.tags[hctx_idx] != hctx->tags);
 	hctx->driver_data = nvmeq;
 	return 0;
@@ -963,6 +950,13 @@ static inline void nvme_ring_cq_doorbell(struct nvme_queue *nvmeq)
 		writel(head, nvmeq->q_db + nvmeq->dev->db_stride);
 }
 
+static inline struct blk_mq_tags *nvme_queue_tagset(struct nvme_queue *nvmeq)
+{
+	if (!nvmeq->qid)
+		return nvmeq->dev->admin_tagset.tags[0];
+	return nvmeq->dev->tagset.tags[nvmeq->qid - 1];
+}
+
 static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
 {
 	volatile struct nvme_completion *cqe = &nvmeq->cqes[idx];
@@ -988,7 +982,7 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
 		return;
 	}
 
-	req = blk_mq_tag_to_rq(*nvmeq->tags, cqe->command_id);
+	req = blk_mq_tag_to_rq(nvme_queue_tagset(nvmeq), cqe->command_id);
 	trace_nvme_sq(req, cqe->sq_head, nvmeq->sq_tail);
 	nvme_end_request(req, cqe->status, cqe->result);
 }
@@ -1103,9 +1097,9 @@ static int nvme_poll(struct blk_mq_hw_ctx *hctx)
 
 	spin_lock(&nvmeq->cq_poll_lock);
 	found = nvme_process_cq(nvmeq, &start, &end, -1);
+	nvme_complete_cqes(nvmeq, start, end);
 	spin_unlock(&nvmeq->cq_poll_lock);
 
-	nvme_complete_cqes(nvmeq, start, end);
 	return found;
 }
 
@@ -1426,6 +1420,25 @@ static void nvme_disable_admin_queue(struct nvme_dev *dev, bool shutdown)
 	nvme_poll_irqdisable(nvmeq, -1);
 }
 
+/*
+ * Called only on a device that has been disabled and after all other threads
+ * that can check this device's completion queues have synced, except
+ * nvme_poll(). This is the last chance for the driver to see a natural
+ * completion before nvme_cancel_request() terminates all incomplete requests.
+ */
+static void nvme_reap_pending_cqes(struct nvme_dev *dev)
+{
+	u16 start, end;
+	int i;
+
+	for (i = dev->ctrl.queue_count - 1; i > 0; i--) {
+		spin_lock(&dev->queues[i].cq_poll_lock);
+		nvme_process_cq(&dev->queues[i], &start, &end, -1);
+		spin_unlock(&dev->queues[i].cq_poll_lock);
+		nvme_complete_cqes(&dev->queues[i], start, end);
+	}
+}
+
 static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues,
 				int entry_size)
 {
@@ -1591,7 +1604,6 @@ static const struct blk_mq_ops nvme_mq_admin_ops = {
 	.queue_rq	= nvme_queue_rq,
 	.complete	= nvme_pci_complete_rq,
 	.init_hctx	= nvme_admin_init_hctx,
-	.exit_hctx      = nvme_admin_exit_hctx,
 	.init_request	= nvme_init_request,
 	.timeout	= nvme_timeout,
 };
@@ -2073,7 +2085,6 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
 		.priv		= dev,
 	};
 	unsigned int irq_queues, this_p_queues;
-	unsigned int nr_cpus = num_possible_cpus();
 
 	/*
 	 * Poll queues don't need interrupts, but we need at least one IO
@@ -2084,10 +2095,7 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
 		this_p_queues = nr_io_queues - 1;
 		irq_queues = 1;
 	} else {
-		if (nr_cpus < nr_io_queues - this_p_queues)
-			irq_queues = nr_cpus + 1;
-		else
-			irq_queues = nr_io_queues - this_p_queues + 1;
+		irq_queues = nr_io_queues - this_p_queues + 1;
 	}
 	dev->io_queues[HCTX_TYPE_POLL] = this_p_queues;
 
@@ -2250,11 +2258,6 @@ static bool __nvme_disable_io_queues(struct nvme_dev *dev, u8 opcode)
 		if (timeout == 0)
 			return false;
 
-		/* handle any remaining CQEs */
-		if (opcode == nvme_admin_delete_cq &&
-		    !test_bit(NVMEQ_DELETE_ERROR, &nvmeq->flags))
-			nvme_poll_irqdisable(nvmeq, -1);
-
 		sent--;
 		if (nr_queues)
 			goto retry;
@@ -2417,6 +2420,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 	nvme_suspend_io_queues(dev);
 	nvme_suspend_queue(&dev->queues[0]);
 	nvme_pci_disable(dev);
+	nvme_reap_pending_cqes(dev);
 
 	blk_mq_tagset_busy_iter(&dev->tagset, nvme_cancel_request, &dev->ctrl);
 	blk_mq_tagset_busy_iter(&dev->admin_tagset, nvme_cancel_request, &dev->ctrl);
@@ -2966,6 +2970,8 @@ static const struct pci_device_id nvme_id_table[] = {
 	{ PCI_DEVICE(0x1cc1, 0x8201),   /* ADATA SX8200PNP 512GB */
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
 				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
+	{ PCI_DEVICE(0x1c5c, 0x1504),   /* SK Hynix PC400 */
+		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index c51e55ce2545..ad17c79fd1e2 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -142,14 +142,6 @@ static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc);
 static const struct blk_mq_ops nvme_rdma_mq_ops;
 static const struct blk_mq_ops nvme_rdma_admin_mq_ops;
 
-/* XXX: really should move to a generic header sooner or later.. */
-static inline void put_unaligned_le24(u32 val, u8 *p)
-{
-	*p++ = val;
-	*p++ = val >> 8;
-	*p++ = val >> 16;
-}
-
 static inline int nvme_rdma_queue_idx(struct nvme_rdma_queue *queue)
 {
 	return queue - queue->ctrl->queues;
@@ -451,7 +443,7 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue)
 	 * Spread I/O queues completion vectors according their queue index.
 	 * Admin queues can always go on completion vector 0.
 	 */
-	comp_vector = idx == 0 ? idx : idx - 1;
+	comp_vector = (idx == 0 ? idx : idx - 1) % ibdev->num_comp_vectors;
 
 	/* Polling queues need direct cq polling context */
 	if (nvme_rdma_poll_queue(queue))
@@ -843,9 +835,11 @@ out_free_tagset:
 	if (new)
 		blk_mq_free_tag_set(ctrl->ctrl.admin_tagset);
 out_free_async_qe:
-	nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe,
-		sizeof(struct nvme_command), DMA_TO_DEVICE);
-	ctrl->async_event_sqe.data = NULL;
+	if (ctrl->async_event_sqe.data) {
+		nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe,
+			sizeof(struct nvme_command), DMA_TO_DEVICE);
+		ctrl->async_event_sqe.data = NULL;
+	}
 out_free_queue:
 	nvme_rdma_free_queue(&ctrl->queues[0]);
 	return error;
@@ -881,15 +875,20 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
 			ret = PTR_ERR(ctrl->ctrl.connect_q);
 			goto out_free_tag_set;
 		}
-	} else {
-		blk_mq_update_nr_hw_queues(&ctrl->tag_set,
-			ctrl->ctrl.queue_count - 1);
 	}
 
 	ret = nvme_rdma_start_io_queues(ctrl);
 	if (ret)
 		goto out_cleanup_connect_q;
 
+	if (!new) {
+		nvme_start_queues(&ctrl->ctrl);
+		nvme_wait_freeze(&ctrl->ctrl);
+		blk_mq_update_nr_hw_queues(ctrl->ctrl.tagset,
+			ctrl->ctrl.queue_count - 1);
+		nvme_unfreeze(&ctrl->ctrl);
+	}
+
 	return 0;
 
 out_cleanup_connect_q:
@@ -919,6 +918,7 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
 		bool remove)
 {
 	if (ctrl->ctrl.queue_count > 1) {
+		nvme_start_freeze(&ctrl->ctrl);
 		nvme_stop_queues(&ctrl->ctrl);
 		nvme_rdma_stop_io_queues(ctrl);
 		if (ctrl->ctrl.tagset)
@@ -1075,7 +1075,7 @@ static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl)
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING))
 		return;
 
-	queue_work(nvme_wq, &ctrl->err_work);
+	queue_work(nvme_reset_wq, &ctrl->err_work);
 }
 
 static void nvme_rdma_wr_error(struct ib_cq *cq, struct ib_wc *wc,
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index bdadb27b28bb..8651b6cfd3ee 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -162,16 +162,14 @@ static inline bool nvme_tcp_async_req(struct nvme_tcp_request *req)
 static inline bool nvme_tcp_has_inline_data(struct nvme_tcp_request *req)
 {
 	struct request *rq;
-	unsigned int bytes;
 
 	if (unlikely(nvme_tcp_async_req(req)))
 		return false; /* async events don't have a request */
 
 	rq = blk_mq_rq_from_pdu(req);
-	bytes = blk_rq_payload_bytes(rq);
 
-	return rq_data_dir(rq) == WRITE && bytes &&
-		bytes <= nvme_tcp_inline_data_size(req->queue);
+	return rq_data_dir(rq) == WRITE && req->data_len &&
+		req->data_len <= nvme_tcp_inline_data_size(req->queue);
 }
 
 static inline struct page *nvme_tcp_req_cur_page(struct nvme_tcp_request *req)
@@ -420,7 +418,7 @@ static void nvme_tcp_error_recovery(struct nvme_ctrl *ctrl)
 	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
 		return;
 
-	queue_work(nvme_wq, &to_tcp_ctrl(ctrl)->err_work);
+	queue_work(nvme_reset_wq, &to_tcp_ctrl(ctrl)->err_work);
 }
 
 static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue,
@@ -785,11 +783,11 @@ static void nvme_tcp_data_ready(struct sock *sk)
 {
 	struct nvme_tcp_queue *queue;
 
-	read_lock(&sk->sk_callback_lock);
+	read_lock_bh(&sk->sk_callback_lock);
 	queue = sk->sk_user_data;
 	if (likely(queue && queue->rd_enabled))
 		queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work);
-	read_unlock(&sk->sk_callback_lock);
+	read_unlock_bh(&sk->sk_callback_lock);
 }
 
 static void nvme_tcp_write_space(struct sock *sk)
@@ -1051,7 +1049,12 @@ static void nvme_tcp_io_work(struct work_struct *w)
 		} else if (unlikely(result < 0)) {
 			dev_err(queue->ctrl->ctrl.device,
 				"failed to send request %d\n", result);
-			if (result != -EPIPE)
+
+			/*
+			 * Fail the request unless peer closed the connection,
+			 * in which case error recovery flow will complete all.
+			 */
+			if ((result != -EPIPE) && (result != -ECONNRESET))
 				nvme_tcp_fail_request(queue->request);
 			nvme_tcp_done_send_req(queue);
 			return;
@@ -1301,6 +1304,9 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
 		goto err_sock;
 	}
 
+	/* Set 10 seconds timeout for icresp recvmsg */
+	queue->sock->sk->sk_rcvtimeo = 10 * HZ;
+
 	queue->sock->sk->sk_allocation = GFP_ATOMIC;
 	if (!qid)
 		n = 0;
@@ -1653,15 +1659,20 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
 			ret = PTR_ERR(ctrl->connect_q);
 			goto out_free_tag_set;
 		}
-	} else {
-		blk_mq_update_nr_hw_queues(ctrl->tagset,
-			ctrl->queue_count - 1);
 	}
 
 	ret = nvme_tcp_start_io_queues(ctrl);
 	if (ret)
 		goto out_cleanup_connect_q;
 
+	if (!new) {
+		nvme_start_queues(ctrl);
+		nvme_wait_freeze(ctrl);
+		blk_mq_update_nr_hw_queues(ctrl->tagset,
+			ctrl->queue_count - 1);
+		nvme_unfreeze(ctrl);
+	}
+
 	return 0;
 
 out_cleanup_connect_q:
@@ -1760,6 +1771,7 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
 {
 	if (ctrl->queue_count <= 1)
 		return;
+	nvme_start_freeze(ctrl);
 	nvme_stop_queues(ctrl);
 	nvme_tcp_stop_io_queues(ctrl);
 	if (ctrl->tagset)
@@ -2042,7 +2054,9 @@ static blk_status_t nvme_tcp_map_data(struct nvme_tcp_queue *queue,
 
 	c->common.flags |= NVME_CMD_SGL_METABUF;
 
-	if (rq_data_dir(rq) == WRITE && req->data_len &&
+	if (!blk_rq_nr_phys_segments(rq))
+		nvme_tcp_set_sg_null(c);
+	else if (rq_data_dir(rq) == WRITE &&
 	    req->data_len <= nvme_tcp_inline_data_size(queue))
 		nvme_tcp_set_sg_inline(queue, c, req->data_len);
 	else
@@ -2069,7 +2083,8 @@ static blk_status_t nvme_tcp_setup_cmd_pdu(struct nvme_ns *ns,
 	req->data_sent = 0;
 	req->pdu_len = 0;
 	req->pdu_sent = 0;
-	req->data_len = blk_rq_payload_bytes(rq);
+	req->data_len = blk_rq_nr_phys_segments(rq) ?
+				blk_rq_payload_bytes(rq) : 0;
 	req->curr_bio = rq->bio;
 
 	if (rq_data_dir(rq) == WRITE &&
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 396cbc7ea353..cabe50eaa745 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -550,7 +550,8 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
 	} else {
 		struct nvmet_ns *old;
 
-		list_for_each_entry_rcu(old, &subsys->namespaces, dev_link) {
+		list_for_each_entry_rcu(old, &subsys->namespaces, dev_link,
+					lockdep_is_held(&subsys->lock)) {
 			BUG_ON(ns->nsid == old->nsid);
 			if (ns->nsid < old->nsid)
 				break;
@@ -1164,7 +1165,8 @@ static void nvmet_setup_p2p_ns_map(struct nvmet_ctrl *ctrl,
 
 	ctrl->p2p_client = get_device(req->p2p_client);
 
-	list_for_each_entry_rcu(ns, &ctrl->subsys->namespaces, dev_link)
+	list_for_each_entry_rcu(ns, &ctrl->subsys->namespaces, dev_link,
+				lockdep_is_held(&ctrl->subsys->lock))
 		nvmet_p2pmem_ns_add_p2p(ctrl, ns);
 }
 
diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c
index 3b9f79aba98f..129f11a8a522 100644
--- a/drivers/nvme/target/fabrics-cmd.c
+++ b/drivers/nvme/target/fabrics-cmd.c
@@ -105,6 +105,7 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req)
 	u16 qid = le16_to_cpu(c->qid);
 	u16 sqsize = le16_to_cpu(c->sqsize);
 	struct nvmet_ctrl *old;
+	u16 ret;
 
 	old = cmpxchg(&req->sq->ctrl, NULL, ctrl);
 	if (old) {
@@ -115,7 +116,8 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req)
 	if (!sqsize) {
 		pr_warn("queue size zero!\n");
 		req->error_loc = offsetof(struct nvmf_connect_command, sqsize);
-		return NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
+		ret = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
+		goto err;
 	}
 
 	/* note: convert queue size from 0's-based value to 1's-based value */
@@ -128,16 +130,19 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req)
 	}
 
 	if (ctrl->ops->install_queue) {
-		u16 ret = ctrl->ops->install_queue(req->sq);
-
+		ret = ctrl->ops->install_queue(req->sq);
 		if (ret) {
 			pr_err("failed to install queue %d cntlid %d ret %x\n",
-				qid, ret, ctrl->cntlid);
-			return ret;
+				qid, ctrl->cntlid, ret);
+			goto err;
 		}
 	}
 
 	return 0;
+
+err:
+	req->sq->ctrl = NULL;
+	return ret;
 }
 
 static void nvmet_execute_admin_connect(struct nvmet_req *req)
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 36d906a7f70d..dc193526d4da 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -143,12 +143,6 @@ static int num_pages(int len)
 	return 1 + (((len - 1) & PAGE_MASK) >> PAGE_SHIFT);
 }
 
-/* XXX: really should move to a generic header sooner or later.. */
-static inline u32 get_unaligned_le24(const u8 *p)
-{
-	return (u32)p[0] | (u32)p[1] << 8 | (u32)p[2] << 16;
-}
-
 static inline bool nvmet_rdma_need_data_in(struct nvmet_rdma_rsp *rsp)
 {
 	return nvme_is_write(rsp->req.cmd) &&
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 69b83fa0c76c..23a42a06b543 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -515,7 +515,7 @@ static int nvmet_try_send_data_pdu(struct nvmet_tcp_cmd *cmd)
 	return 1;
 }
 
-static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd)
+static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
 {
 	struct nvmet_tcp_queue *queue = cmd->queue;
 	int ret;
@@ -523,9 +523,15 @@ static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd)
 	while (cmd->cur_sg) {
 		struct page *page = sg_page(cmd->cur_sg);
 		u32 left = cmd->cur_sg->length - cmd->offset;
+		int flags = MSG_DONTWAIT;
+
+		if ((!last_in_batch && cmd->queue->send_list_len) ||
+		    cmd->wbytes_done + left < cmd->req.transfer_len ||
+		    queue->data_digest || !queue->nvme_sq.sqhd_disabled)
+			flags |= MSG_MORE;
 
 		ret = kernel_sendpage(cmd->queue->sock, page, cmd->offset,
-					left, MSG_DONTWAIT | MSG_MORE);
+					left, flags);
 		if (ret <= 0)
 			return ret;
 
@@ -660,7 +666,7 @@ static int nvmet_tcp_try_send_one(struct nvmet_tcp_queue *queue,
 	}
 
 	if (cmd->state == NVMET_TCP_SEND_DATA) {
-		ret = nvmet_try_send_data(cmd);
+		ret = nvmet_try_send_data(cmd, last_in_batch);
 		if (ret <= 0)
 			goto done_send;
 	}
@@ -788,7 +794,7 @@ static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue)
 	icresp->hdr.pdo = 0;
 	icresp->hdr.plen = cpu_to_le32(icresp->hdr.hlen);
 	icresp->pfv = cpu_to_le16(NVME_TCP_PFV_1_0);
-	icresp->maxdata = cpu_to_le32(0xffff); /* FIXME: support r2t */
+	icresp->maxdata = cpu_to_le32(0x400000); /* 16M arbitrary limit */
 	icresp->cpda = 0;
 	if (queue->hdr_digest)
 		icresp->digest |= NVME_TCP_HDR_DIGEST_ENABLE;
diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index c7892c3da91f..a93e17f10e9b 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -115,7 +115,7 @@ static void nvmem_cell_drop(struct nvmem_cell *cell)
 	list_del(&cell->node);
 	mutex_unlock(&nvmem_mutex);
 	of_node_put(cell->np);
-	kfree(cell->name);
+	kfree_const(cell->name);
 	kfree(cell);
 }
 
@@ -142,7 +142,9 @@ static int nvmem_cell_info_to_nvmem_cell(struct nvmem_device *nvmem,
 	cell->nvmem = nvmem;
 	cell->offset = info->offset;
 	cell->bytes = info->bytes;
-	cell->name = info->name;
+	cell->name = kstrdup_const(info->name, GFP_KERNEL);
+	if (!cell->name)
+		return -ENOMEM;
 
 	cell->bit_offset = info->bit_offset;
 	cell->nbits = info->nbits;
@@ -332,7 +334,7 @@ static int nvmem_add_cells_from_of(struct nvmem_device *nvmem)
 			dev_err(dev, "cell %s unaligned to nvmem stride %d\n",
 				cell->name, nvmem->stride);
 			/* Cells already added will be freed later. */
-			kfree(cell->name);
+			kfree_const(cell->name);
 			kfree(cell);
 			return -EINVAL;
 		}
diff --git a/drivers/nvmem/nvmem-sysfs.c b/drivers/nvmem/nvmem-sysfs.c
index 9e0c429cd08a..8759c4470012 100644
--- a/drivers/nvmem/nvmem-sysfs.c
+++ b/drivers/nvmem/nvmem-sysfs.c
@@ -56,6 +56,9 @@ static ssize_t bin_attr_nvmem_read(struct file *filp, struct kobject *kobj,
 
 	count = round_down(count, nvmem->word_size);
 
+	if (!nvmem->reg_read)
+		return -EPERM;
+
 	rc = nvmem->reg_read(nvmem->priv, pos, buf, count);
 
 	if (rc)
@@ -90,6 +93,9 @@ static ssize_t bin_attr_nvmem_write(struct file *filp, struct kobject *kobj,
 
 	count = round_down(count, nvmem->word_size);
 
+	if (!nvmem->reg_write)
+		return -EPERM;
+
 	rc = nvmem->reg_write(nvmem->priv, pos, buf, count);
 
 	if (rc)
diff --git a/drivers/nvmem/qfprom.c b/drivers/nvmem/qfprom.c
index d057f1bfb2e9..8a91717600be 100644
--- a/drivers/nvmem/qfprom.c
+++ b/drivers/nvmem/qfprom.c
@@ -27,25 +27,11 @@ static int qfprom_reg_read(void *context,
 	return 0;
 }
 
-static int qfprom_reg_write(void *context,
-			 unsigned int reg, void *_val, size_t bytes)
-{
-	struct qfprom_priv *priv = context;
-	u8 *val = _val;
-	int i = 0, words = bytes;
-
-	while (words--)
-		writeb(*val++, priv->base + reg + i++);
-
-	return 0;
-}
-
 static struct nvmem_config econfig = {
 	.name = "qfprom",
 	.stride = 1,
 	.word_size = 1,
 	.reg_read = qfprom_reg_read,
-	.reg_write = qfprom_reg_write,
 };
 
 static int qfprom_probe(struct platform_device *pdev)
diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig
index 37c2ccbefecd..d91618641be6 100644
--- a/drivers/of/Kconfig
+++ b/drivers/of/Kconfig
@@ -103,4 +103,8 @@ config OF_OVERLAY
 config OF_NUMA
 	bool
 
+config OF_DMA_DEFAULT_COHERENT
+	# arches should select this if DMA is coherent by default for OF devices
+	bool
+
 endif # OF
diff --git a/drivers/of/address.c b/drivers/of/address.c
index 978427a9d5e6..8f74c4626e0e 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -998,12 +998,16 @@ EXPORT_SYMBOL_GPL(of_dma_get_range);
  * @np:	device node
  *
  * It returns true if "dma-coherent" property was found
- * for this device in DT.
+ * for this device in the DT, or if DMA is coherent by
+ * default for OF devices on the current platform.
  */
 bool of_dma_is_coherent(struct device_node *np)
 {
 	struct device_node *node = of_node_get(np);
 
+	if (IS_ENABLED(CONFIG_OF_DMA_DEFAULT_COHERENT))
+		return true;
+
 	while (node) {
 		if (of_property_read_bool(node, "dma-coherent")) {
 			of_node_put(node);
diff --git a/drivers/of/kobj.c b/drivers/of/kobj.c
index c72eef988041..a32e60b024b8 100644
--- a/drivers/of/kobj.c
+++ b/drivers/of/kobj.c
@@ -134,8 +134,6 @@ int __of_attach_node_sysfs(struct device_node *np)
 	if (!name)
 		return -ENOMEM;
 
-	of_node_get(np);
-
 	rc = kobject_add(&np->kobj, parent, "%s", name);
 	kfree(name);
 	if (rc)
@@ -144,6 +142,7 @@ int __of_attach_node_sysfs(struct device_node *np)
 	for_each_property_of_node(np, pp)
 		__of_add_property_sysfs(np, pp);
 
+	of_node_get(np);
 	return 0;
 }
 
diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index 3b67896d9d74..882d6d5b9560 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -265,8 +265,14 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np)
 				 child, addr);
 
 			if (of_mdiobus_child_is_phy(child)) {
+				/* -ENODEV is the return code that PHYLIB has
+				 * standardized on to indicate that bus
+				 * scanning should continue.
+				 */
 				rc = of_mdiobus_register_phy(mdio, child, addr);
-				if (rc && rc != -ENODEV)
+				if (!rc)
+					break;
+				if (rc != -ENODEV)
 					goto unregister;
 			}
 		}
diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c
index c423e94baf0f..1688f576ee8a 100644
--- a/drivers/of/overlay.c
+++ b/drivers/of/overlay.c
@@ -261,6 +261,8 @@ static struct property *dup_and_fixup_symbol_prop(
 
 	of_property_set_flag(new_prop, OF_DYNAMIC);
 
+	kfree(target_path);
+
 	return new_prop;
 
 err_free_new_prop:
@@ -305,7 +307,6 @@ static int add_changeset_property(struct overlay_changeset *ovcs,
 {
 	struct property *new_prop = NULL, *prop;
 	int ret = 0;
-	bool check_for_non_overlay_node = false;
 
 	if (target->in_livetree)
 		if (!of_prop_cmp(overlay_prop->name, "name") ||
@@ -318,6 +319,25 @@ static int add_changeset_property(struct overlay_changeset *ovcs,
 	else
 		prop = NULL;
 
+	if (prop) {
+		if (!of_prop_cmp(prop->name, "#address-cells")) {
+			if (!of_prop_val_eq(prop, overlay_prop)) {
+				pr_err("ERROR: changing value of #address-cells is not allowed in %pOF\n",
+				       target->np);
+				ret = -EINVAL;
+			}
+			return ret;
+
+		} else if (!of_prop_cmp(prop->name, "#size-cells")) {
+			if (!of_prop_val_eq(prop, overlay_prop)) {
+				pr_err("ERROR: changing value of #size-cells is not allowed in %pOF\n",
+				       target->np);
+				ret = -EINVAL;
+			}
+			return ret;
+		}
+	}
+
 	if (is_symbols_prop) {
 		if (prop)
 			return -EINVAL;
@@ -330,33 +350,18 @@ static int add_changeset_property(struct overlay_changeset *ovcs,
 		return -ENOMEM;
 
 	if (!prop) {
-		check_for_non_overlay_node = true;
 		if (!target->in_livetree) {
 			new_prop->next = target->np->deadprops;
 			target->np->deadprops = new_prop;
 		}
 		ret = of_changeset_add_property(&ovcs->cset, target->np,
 						new_prop);
-	} else if (!of_prop_cmp(prop->name, "#address-cells")) {
-		if (!of_prop_val_eq(prop, new_prop)) {
-			pr_err("ERROR: changing value of #address-cells is not allowed in %pOF\n",
-			       target->np);
-			ret = -EINVAL;
-		}
-	} else if (!of_prop_cmp(prop->name, "#size-cells")) {
-		if (!of_prop_val_eq(prop, new_prop)) {
-			pr_err("ERROR: changing value of #size-cells is not allowed in %pOF\n",
-			       target->np);
-			ret = -EINVAL;
-		}
 	} else {
-		check_for_non_overlay_node = true;
 		ret = of_changeset_update_property(&ovcs->cset, target->np,
 						   new_prop);
 	}
 
-	if (check_for_non_overlay_node &&
-	    !of_node_check_flag(target->np, OF_OVERLAY))
+	if (!of_node_check_flag(target->np, OF_OVERLAY))
 		pr_err("WARNING: memory leak will occur if overlay removed, property: %pOF/%s\n",
 		       target->np, new_prop->name);
 
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index 4c019e264e21..cd58d1432640 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -776,6 +776,10 @@ static void __init of_unittest_changeset(void)
 	unittest(!of_changeset_revert(&chgset), "revert failed\n");
 
 	of_changeset_destroy(&chgset);
+
+	of_node_put(n1);
+	of_node_put(n2);
+	of_node_put(n21);
 #endif
 }
 
@@ -1059,10 +1063,13 @@ static void __init of_unittest_platform_populate(void)
 
 	of_platform_populate(np, match, NULL, &test_bus->dev);
 	for_each_child_of_node(np, child) {
-		for_each_child_of_node(child, grandchild)
-			unittest(of_find_device_by_node(grandchild),
+		for_each_child_of_node(child, grandchild) {
+			pdev = of_find_device_by_node(grandchild);
+			unittest(pdev,
 				 "Could not create device for node '%pOFn'\n",
 				 grandchild);
+			of_dev_put(pdev);
+		}
 	}
 
 	of_platform_depopulate(&test_bus->dev);
@@ -2472,8 +2479,11 @@ static __init void of_unittest_overlay_high_level(void)
 				goto err_unlock;
 			}
 			if (__of_add_property(of_symbols, new_prop)) {
+				kfree(new_prop->name);
+				kfree(new_prop->value);
+				kfree(new_prop);
 				/* "name" auto-generated by unflatten */
-				if (!strcmp(new_prop->name, "name"))
+				if (!strcmp(prop->name, "name"))
 					continue;
 				unittest(0, "duplicate property '%s' in overlay_base node __symbols__",
 					 prop->name);
diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c
index 296668caf7e5..c18541db7c20 100644
--- a/drivers/parisc/sba_iommu.c
+++ b/drivers/parisc/sba_iommu.c
@@ -1277,7 +1277,7 @@ sba_ioc_init_pluto(struct parisc_device *sba, struct ioc *ioc, int ioc_num)
 	** (one that doesn't overlap memory or LMMIO space) in the
 	** IBASE and IMASK registers.
 	*/
-	ioc->ibase = READ_REG(ioc->ioc_hpa + IOC_IBASE);
+	ioc->ibase = READ_REG(ioc->ioc_hpa + IOC_IBASE) & ~0x1fffffULL;
 	iova_space_size = ~(READ_REG(ioc->ioc_hpa + IOC_IMASK) & 0xFFFFFFFFUL) + 1;
 
 	if ((ioc->ibase < 0xfed00000UL) && ((ioc->ibase + iova_space_size) > 0xfee00000UL)) {
diff --git a/drivers/pci/access.c b/drivers/pci/access.c
index 544922f097c0..0914ddeae17f 100644
--- a/drivers/pci/access.c
+++ b/drivers/pci/access.c
@@ -204,17 +204,13 @@ EXPORT_SYMBOL(pci_bus_set_ops);
 static DECLARE_WAIT_QUEUE_HEAD(pci_cfg_wait);
 
 static noinline void pci_wait_cfg(struct pci_dev *dev)
+	__must_hold(&pci_lock)
 {
-	DECLARE_WAITQUEUE(wait, current);
-
-	__add_wait_queue(&pci_cfg_wait, &wait);
 	do {
-		set_current_state(TASK_UNINTERRUPTIBLE);
 		raw_spin_unlock_irq(&pci_lock);
-		schedule();
+		wait_event(pci_cfg_wait, !dev->block_cfg_access);
 		raw_spin_lock_irq(&pci_lock);
 	} while (dev->block_cfg_access);
-	__remove_wait_queue(&pci_cfg_wait, &wait);
 }
 
 /* Returns 0 on success, negative values indicate error. */
@@ -336,15 +332,6 @@ static inline int pcie_cap_version(const struct pci_dev *dev)
 	return pcie_caps_reg(dev) & PCI_EXP_FLAGS_VERS;
 }
 
-static bool pcie_downstream_port(const struct pci_dev *dev)
-{
-	int type = pci_pcie_type(dev);
-
-	return type == PCI_EXP_TYPE_ROOT_PORT ||
-	       type == PCI_EXP_TYPE_DOWNSTREAM ||
-	       type == PCI_EXP_TYPE_PCIE_BRIDGE;
-}
-
 bool pcie_cap_has_lnkctl(const struct pci_dev *dev)
 {
 	int type = pci_pcie_type(dev);
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 495059d923f7..ff1170dd172d 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -322,12 +322,8 @@ void pci_bus_add_device(struct pci_dev *dev)
 
 	dev->match_driver = true;
 	retval = device_attach(&dev->dev);
-	if (retval < 0 && retval != -EPROBE_DEFER) {
+	if (retval < 0 && retval != -EPROBE_DEFER)
 		pci_warn(dev, "device attach failed (%d)\n", retval);
-		pci_proc_detach_device(dev);
-		pci_remove_sysfs_dev_files(dev);
-		return;
-	}
 
 	pci_dev_assign_added(dev, true);
 }
diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
index af677254a072..c8c702c494a2 100644
--- a/drivers/pci/controller/dwc/pci-keystone.c
+++ b/drivers/pci/controller/dwc/pci-keystone.c
@@ -422,7 +422,7 @@ static void ks_pcie_setup_rc_app_regs(struct keystone_pcie *ks_pcie)
 				   lower_32_bits(start) | OB_ENABLEN);
 		ks_pcie_app_writel(ks_pcie, OB_OFFSET_HI(i),
 				   upper_32_bits(start));
-		start += OB_WIN_SIZE;
+		start += OB_WIN_SIZE * SZ_1M;
 	}
 
 	val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
@@ -510,7 +510,7 @@ static void ks_pcie_stop_link(struct dw_pcie *pci)
 	/* Disable Link training */
 	val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
 	val &= ~LTSSM_EN_VAL;
-	ks_pcie_app_writel(ks_pcie, CMD_STATUS, LTSSM_EN_VAL | val);
+	ks_pcie_app_writel(ks_pcie, CMD_STATUS, val);
 }
 
 static int ks_pcie_start_link(struct dw_pcie *pci)
@@ -1354,7 +1354,7 @@ static int __init ks_pcie_probe(struct platform_device *pdev)
 		ret = of_property_read_u32(np, "num-viewport", &num_viewport);
 		if (ret < 0) {
 			dev_err(dev, "unable to read *num-viewport* property\n");
-			return ret;
+			goto err_get_sync;
 		}
 
 		/*
diff --git a/drivers/pci/controller/dwc/pci-meson.c b/drivers/pci/controller/dwc/pci-meson.c
index e35e9eaa50ee..8c9f88704874 100644
--- a/drivers/pci/controller/dwc/pci-meson.c
+++ b/drivers/pci/controller/dwc/pci-meson.c
@@ -250,15 +250,15 @@ static int meson_pcie_probe_clocks(struct meson_pcie *mp)
 	if (IS_ERR(res->port_clk))
 		return PTR_ERR(res->port_clk);
 
-	res->mipi_gate = meson_pcie_probe_clock(dev, "pcie_mipi_en", 0);
+	res->mipi_gate = meson_pcie_probe_clock(dev, "mipi", 0);
 	if (IS_ERR(res->mipi_gate))
 		return PTR_ERR(res->mipi_gate);
 
-	res->general_clk = meson_pcie_probe_clock(dev, "pcie_general", 0);
+	res->general_clk = meson_pcie_probe_clock(dev, "general", 0);
 	if (IS_ERR(res->general_clk))
 		return PTR_ERR(res->general_clk);
 
-	res->clk = meson_pcie_probe_clock(dev, "pcie", 0);
+	res->clk = meson_pcie_probe_clock(dev, "pclk", 0);
 	if (IS_ERR(res->clk))
 		return PTR_ERR(res->clk);
 
@@ -301,11 +301,11 @@ static void meson_pcie_init_dw(struct meson_pcie *mp)
 	meson_cfg_writel(mp, val, PCIE_CFG0);
 
 	val = meson_elb_readl(mp, PCIE_PORT_LINK_CTRL_OFF);
-	val &= ~LINK_CAPABLE_MASK;
+	val &= ~(LINK_CAPABLE_MASK | FAST_LINK_MODE);
 	meson_elb_writel(mp, val, PCIE_PORT_LINK_CTRL_OFF);
 
 	val = meson_elb_readl(mp, PCIE_PORT_LINK_CTRL_OFF);
-	val |= LINK_CAPABLE_X1 | FAST_LINK_MODE;
+	val |= LINK_CAPABLE_X1;
 	meson_elb_writel(mp, val, PCIE_PORT_LINK_CTRL_OFF);
 
 	val = meson_elb_readl(mp, PCIE_GEN2_CTRL_OFF);
diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c
index 77db32529319..c8b93aae77ed 100644
--- a/drivers/pci/controller/dwc/pcie-designware-host.c
+++ b/drivers/pci/controller/dwc/pcie-designware-host.c
@@ -78,7 +78,8 @@ static struct msi_domain_info dw_pcie_msi_domain_info = {
 irqreturn_t dw_handle_msi_irq(struct pcie_port *pp)
 {
 	int i, pos, irq;
-	u32 val, num_ctrls;
+	unsigned long val;
+	u32 status, num_ctrls;
 	irqreturn_t ret = IRQ_NONE;
 
 	num_ctrls = pp->num_vectors / MAX_MSI_IRQS_PER_CTRL;
@@ -86,14 +87,14 @@ irqreturn_t dw_handle_msi_irq(struct pcie_port *pp)
 	for (i = 0; i < num_ctrls; i++) {
 		dw_pcie_rd_own_conf(pp, PCIE_MSI_INTR0_STATUS +
 					(i * MSI_REG_CTRL_BLOCK_SIZE),
-				    4, &val);
-		if (!val)
+				    4, &status);
+		if (!status)
 			continue;
 
 		ret = IRQ_HANDLED;
+		val = status;
 		pos = 0;
-		while ((pos = find_next_bit((unsigned long *) &val,
-					    MAX_MSI_IRQS_PER_CTRL,
+		while ((pos = find_next_bit(&val, MAX_MSI_IRQS_PER_CTRL,
 					    pos)) != MAX_MSI_IRQS_PER_CTRL) {
 			irq = irq_find_mapping(pp->irq_domain,
 					       (i * MAX_MSI_IRQS_PER_CTRL) +
@@ -262,6 +263,8 @@ int dw_pcie_allocate_domains(struct pcie_port *pp)
 		return -ENOMEM;
 	}
 
+	irq_domain_update_bus_token(pp->irq_domain, DOMAIN_BUS_NEXUS);
+
 	pp->msi_domain = pci_msi_create_irq_domain(fwnode,
 						   &dw_pcie_msi_domain_info,
 						   pp->irq_domain);
diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
index 5d1713069d14..a16994e59776 100644
--- a/drivers/pci/controller/dwc/pcie-qcom.c
+++ b/drivers/pci/controller/dwc/pcie-qcom.c
@@ -45,7 +45,13 @@
 #define PCIE_CAP_CPL_TIMEOUT_DISABLE		0x10
 
 #define PCIE20_PARF_PHY_CTRL			0x40
+#define PHY_CTRL_PHY_TX0_TERM_OFFSET_MASK	GENMASK(20, 16)
+#define PHY_CTRL_PHY_TX0_TERM_OFFSET(x)		((x) << 16)
+
 #define PCIE20_PARF_PHY_REFCLK			0x4C
+#define PHY_REFCLK_SSP_EN			BIT(16)
+#define PHY_REFCLK_USE_PAD			BIT(12)
+
 #define PCIE20_PARF_DBI_BASE_ADDR		0x168
 #define PCIE20_PARF_SLV_ADDR_SPACE_SIZE		0x16C
 #define PCIE20_PARF_MHI_CLOCK_RESET_CTRL	0x174
@@ -76,6 +82,18 @@
 #define DBI_RO_WR_EN				1
 
 #define PERST_DELAY_US				1000
+/* PARF registers */
+#define PCIE20_PARF_PCS_DEEMPH			0x34
+#define PCS_DEEMPH_TX_DEEMPH_GEN1(x)		((x) << 16)
+#define PCS_DEEMPH_TX_DEEMPH_GEN2_3_5DB(x)	((x) << 8)
+#define PCS_DEEMPH_TX_DEEMPH_GEN2_6DB(x)	((x) << 0)
+
+#define PCIE20_PARF_PCS_SWING			0x38
+#define PCS_SWING_TX_SWING_FULL(x)		((x) << 8)
+#define PCS_SWING_TX_SWING_LOW(x)		((x) << 0)
+
+#define PCIE20_PARF_CONFIG_BITS		0x50
+#define PHY_RX0_EQ(x)				((x) << 24)
 
 #define PCIE20_v3_PARF_SLV_ADDR_SPACE_SIZE	0x358
 #define SLV_ADDR_SPACE_SZ			0x10000000
@@ -275,6 +293,7 @@ static int qcom_pcie_init_2_1_0(struct qcom_pcie *pcie)
 	struct qcom_pcie_resources_2_1_0 *res = &pcie->res.v2_1_0;
 	struct dw_pcie *pci = pcie->pci;
 	struct device *dev = pci->dev;
+	struct device_node *node = dev->of_node;
 	u32 val;
 	int ret;
 
@@ -319,9 +338,29 @@ static int qcom_pcie_init_2_1_0(struct qcom_pcie *pcie)
 	val &= ~BIT(0);
 	writel(val, pcie->parf + PCIE20_PARF_PHY_CTRL);
 
+	if (of_device_is_compatible(node, "qcom,pcie-ipq8064")) {
+		writel(PCS_DEEMPH_TX_DEEMPH_GEN1(24) |
+			       PCS_DEEMPH_TX_DEEMPH_GEN2_3_5DB(24) |
+			       PCS_DEEMPH_TX_DEEMPH_GEN2_6DB(34),
+		       pcie->parf + PCIE20_PARF_PCS_DEEMPH);
+		writel(PCS_SWING_TX_SWING_FULL(120) |
+			       PCS_SWING_TX_SWING_LOW(120),
+		       pcie->parf + PCIE20_PARF_PCS_SWING);
+		writel(PHY_RX0_EQ(4), pcie->parf + PCIE20_PARF_CONFIG_BITS);
+	}
+
+	if (of_device_is_compatible(node, "qcom,pcie-ipq8064")) {
+		/* set TX termination offset */
+		val = readl(pcie->parf + PCIE20_PARF_PHY_CTRL);
+		val &= ~PHY_CTRL_PHY_TX0_TERM_OFFSET_MASK;
+		val |= PHY_CTRL_PHY_TX0_TERM_OFFSET(7);
+		writel(val, pcie->parf + PCIE20_PARF_PHY_CTRL);
+	}
+
 	/* enable external reference clock */
 	val = readl(pcie->parf + PCIE20_PARF_PHY_REFCLK);
-	val |= BIT(16);
+	val &= ~PHY_REFCLK_USE_PAD;
+	val |= PHY_REFCLK_SSP_EN;
 	writel(val, pcie->parf + PCIE20_PARF_PHY_REFCLK);
 
 	ret = reset_control_deassert(res->phy_reset);
@@ -1298,7 +1337,13 @@ static void qcom_fixup_class(struct pci_dev *dev)
 {
 	dev->class = PCI_CLASS_BRIDGE_PCI << 8;
 }
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, PCI_ANY_ID, qcom_fixup_class);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x0101, qcom_fixup_class);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x0104, qcom_fixup_class);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x0106, qcom_fixup_class);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x0107, qcom_fixup_class);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x0302, qcom_fixup_class);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x1000, qcom_fixup_class);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x1001, qcom_fixup_class);
 
 static struct platform_driver qcom_pcie_driver = {
 	.probe = qcom_pcie_probe,
diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c
index 134e0306ff00..a2006cc1de8c 100644
--- a/drivers/pci/controller/pci-aardvark.c
+++ b/drivers/pci/controller/pci-aardvark.c
@@ -180,6 +180,8 @@
 #define LINK_WAIT_MAX_RETRIES		10
 #define LINK_WAIT_USLEEP_MIN		90000
 #define LINK_WAIT_USLEEP_MAX		100000
+#define RETRAIN_WAIT_MAX_RETRIES	10
+#define RETRAIN_WAIT_USLEEP_US		2000
 
 #define MSI_IRQ_NUM			32
 
@@ -239,6 +241,17 @@ static int advk_pcie_wait_for_link(struct advk_pcie *pcie)
 	return -ETIMEDOUT;
 }
 
+static void advk_pcie_wait_for_retrain(struct advk_pcie *pcie)
+{
+	size_t retries;
+
+	for (retries = 0; retries < RETRAIN_WAIT_MAX_RETRIES; ++retries) {
+		if (!advk_pcie_link_up(pcie))
+			break;
+		udelay(RETRAIN_WAIT_USLEEP_US);
+	}
+}
+
 static void advk_pcie_setup_hw(struct advk_pcie *pcie)
 {
 	u32 reg;
@@ -331,10 +344,6 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie)
 
 	advk_pcie_wait_for_link(pcie);
 
-	reg = PCIE_CORE_LINK_L0S_ENTRY |
-		(1 << PCIE_CORE_LINK_WIDTH_SHIFT);
-	advk_writel(pcie, reg, PCIE_CORE_LINK_CTRL_STAT_REG);
-
 	reg = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG);
 	reg |= PCIE_CORE_CMD_MEM_ACCESS_EN |
 		PCIE_CORE_CMD_IO_ACCESS_EN |
@@ -415,7 +424,7 @@ advk_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge,
 
 	case PCI_EXP_RTCTL: {
 		u32 val = advk_readl(pcie, PCIE_ISR0_MASK_REG);
-		*value = (val & PCIE_MSG_PM_PME_MASK) ? PCI_EXP_RTCTL_PMEIE : 0;
+		*value = (val & PCIE_MSG_PM_PME_MASK) ? 0 : PCI_EXP_RTCTL_PMEIE;
 		return PCI_BRIDGE_EMUL_HANDLED;
 	}
 
@@ -426,11 +435,20 @@ advk_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge,
 		return PCI_BRIDGE_EMUL_HANDLED;
 	}
 
+	case PCI_EXP_LNKCTL: {
+		/* u32 contains both PCI_EXP_LNKCTL and PCI_EXP_LNKSTA */
+		u32 val = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + reg) &
+			~(PCI_EXP_LNKSTA_LT << 16);
+		if (!advk_pcie_link_up(pcie))
+			val |= (PCI_EXP_LNKSTA_LT << 16);
+		*value = val;
+		return PCI_BRIDGE_EMUL_HANDLED;
+	}
+
 	case PCI_CAP_LIST_ID:
 	case PCI_EXP_DEVCAP:
 	case PCI_EXP_DEVCTL:
 	case PCI_EXP_LNKCAP:
-	case PCI_EXP_LNKCTL:
 		*value = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + reg);
 		return PCI_BRIDGE_EMUL_HANDLED;
 	default:
@@ -447,14 +465,24 @@ advk_pci_bridge_emul_pcie_conf_write(struct pci_bridge_emul *bridge,
 
 	switch (reg) {
 	case PCI_EXP_DEVCTL:
+		advk_writel(pcie, new, PCIE_CORE_PCIEXP_CAP + reg);
+		break;
+
 	case PCI_EXP_LNKCTL:
 		advk_writel(pcie, new, PCIE_CORE_PCIEXP_CAP + reg);
+		if (new & PCI_EXP_LNKCTL_RL)
+			advk_pcie_wait_for_retrain(pcie);
 		break;
 
-	case PCI_EXP_RTCTL:
-		new = (new & PCI_EXP_RTCTL_PMEIE) << 3;
-		advk_writel(pcie, new, PCIE_ISR0_MASK_REG);
+	case PCI_EXP_RTCTL: {
+		/* Only mask/unmask PME interrupt */
+		u32 val = advk_readl(pcie, PCIE_ISR0_MASK_REG) &
+			~PCIE_MSG_PM_PME_MASK;
+		if ((new & PCI_EXP_RTCTL_PMEIE) == 0)
+			val |= PCIE_MSG_PM_PME_MASK;
+		advk_writel(pcie, val, PCIE_ISR0_MASK_REG);
 		break;
+	}
 
 	case PCI_EXP_RTSTA:
 		new = (new & PCI_EXP_RTSTA_PME) >> 9;
diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index 03c42e8684f6..952f7cfebdf8 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -2414,7 +2414,7 @@ static int tegra_pcie_probe(struct platform_device *pdev)
 
 	pm_runtime_enable(pcie->dev);
 	err = pm_runtime_get_sync(pcie->dev);
-	if (err) {
+	if (err < 0) {
 		dev_err(dev, "fail to enable pcie controller: %d\n", err);
 		goto teardown_msi;
 	}
diff --git a/drivers/pci/controller/pci-v3-semi.c b/drivers/pci/controller/pci-v3-semi.c
index d219404bad92..9a86bb7448ac 100644
--- a/drivers/pci/controller/pci-v3-semi.c
+++ b/drivers/pci/controller/pci-v3-semi.c
@@ -743,7 +743,7 @@ static int v3_pci_probe(struct platform_device *pdev)
 	int ret;
 	LIST_HEAD(res);
 
-	host = pci_alloc_host_bridge(sizeof(*v3));
+	host = devm_pci_alloc_host_bridge(dev, sizeof(*v3));
 	if (!host)
 		return -ENOMEM;
 
diff --git a/drivers/pci/controller/pcie-cadence-host.c b/drivers/pci/controller/pcie-cadence-host.c
index 97e251090b4f..0dfc778f40a7 100644
--- a/drivers/pci/controller/pcie-cadence-host.c
+++ b/drivers/pci/controller/pcie-cadence-host.c
@@ -102,6 +102,7 @@ static int cdns_pcie_host_init_root_port(struct cdns_pcie_rc *rc)
 {
 	struct cdns_pcie *pcie = &rc->pcie;
 	u32 value, ctrl;
+	u32 id;
 
 	/*
 	 * Set the root complex BAR configuration register:
@@ -121,8 +122,12 @@ static int cdns_pcie_host_init_root_port(struct cdns_pcie_rc *rc)
 	cdns_pcie_writel(pcie, CDNS_PCIE_LM_RC_BAR_CFG, value);
 
 	/* Set root port configuration space */
-	if (rc->vendor_id != 0xffff)
-		cdns_pcie_rp_writew(pcie, PCI_VENDOR_ID, rc->vendor_id);
+	if (rc->vendor_id != 0xffff) {
+		id = CDNS_PCIE_LM_ID_VENDOR(rc->vendor_id) |
+			CDNS_PCIE_LM_ID_SUBSYS(rc->vendor_id);
+		cdns_pcie_writel(pcie, CDNS_PCIE_LM_ID, id);
+	}
+
 	if (rc->device_id != 0xffff)
 		cdns_pcie_rp_writew(pcie, PCI_DEVICE_ID, rc->device_id);
 
diff --git a/drivers/pci/controller/pcie-iproc.c b/drivers/pci/controller/pcie-iproc.c
index e3ca46497470..0795c46b2bbb 100644
--- a/drivers/pci/controller/pcie-iproc.c
+++ b/drivers/pci/controller/pcie-iproc.c
@@ -1608,6 +1608,30 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd802,
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd804,
 			quirk_paxc_disable_msi_parsing);
 
+static void quirk_paxc_bridge(struct pci_dev *pdev)
+{
+	/*
+	 * The PCI config space is shared with the PAXC root port and the first
+	 * Ethernet device.  So, we need to workaround this by telling the PCI
+	 * code that the bridge is not an Ethernet device.
+	 */
+	if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
+		pdev->class = PCI_CLASS_BRIDGE_PCI << 8;
+
+	/*
+	 * MPSS is not being set properly (as it is currently 0).  This is
+	 * because that area of the PCI config space is hard coded to zero, and
+	 * is not modifiable by firmware.  Set this to 2 (e.g., 512 byte MPS)
+	 * so that the MPS can be set to the real max value.
+	 */
+	pdev->pcie_mpss = 2;
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x16cd, quirk_paxc_bridge);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x16f0, quirk_paxc_bridge);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd750, quirk_paxc_bridge);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd802, quirk_paxc_bridge);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd804, quirk_paxc_bridge);
+
 MODULE_AUTHOR("Ray Jui <rjui@broadcom.com>");
 MODULE_DESCRIPTION("Broadcom iPROC PCIe common driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/controller/pcie-rcar.c b/drivers/pci/controller/pcie-rcar.c
index 34d2f6424403..8be0e8d880e4 100644
--- a/drivers/pci/controller/pcie-rcar.c
+++ b/drivers/pci/controller/pcie-rcar.c
@@ -338,11 +338,12 @@ static struct pci_ops rcar_pcie_ops = {
 };
 
 static void rcar_pcie_setup_window(int win, struct rcar_pcie *pcie,
-				   struct resource *res)
+				   struct resource_entry *window)
 {
 	/* Setup PCIe address space mappings for each resource */
 	resource_size_t size;
 	resource_size_t res_start;
+	struct resource *res = window->res;
 	u32 mask;
 
 	rcar_pci_write_reg(pcie, 0x00000000, PCIEPTCTLR(win));
@@ -356,9 +357,9 @@ static void rcar_pcie_setup_window(int win, struct rcar_pcie *pcie,
 	rcar_pci_write_reg(pcie, mask << 7, PCIEPAMR(win));
 
 	if (res->flags & IORESOURCE_IO)
-		res_start = pci_pio_to_address(res->start);
+		res_start = pci_pio_to_address(res->start) - window->offset;
 	else
-		res_start = res->start;
+		res_start = res->start - window->offset;
 
 	rcar_pci_write_reg(pcie, upper_32_bits(res_start), PCIEPAUR(win));
 	rcar_pci_write_reg(pcie, lower_32_bits(res_start) & ~0x7F,
@@ -387,7 +388,7 @@ static int rcar_pcie_setup(struct list_head *resource, struct rcar_pcie *pci)
 		switch (resource_type(res)) {
 		case IORESOURCE_IO:
 		case IORESOURCE_MEM:
-			rcar_pcie_setup_window(i, pci, res);
+			rcar_pcie_setup_window(i, pci, win);
 			i++;
 			break;
 		case IORESOURCE_BUS:
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index 21ee1833a247..583abbb7a7a2 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -593,9 +593,11 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features)
 			if (!membar2)
 				return -ENOMEM;
 			offset[0] = vmd->dev->resource[VMD_MEMBAR1].start -
-					readq(membar2 + MB2_SHADOW_OFFSET);
+					(readq(membar2 + MB2_SHADOW_OFFSET) &
+					 PCI_BASE_ADDRESS_MEM_MASK);
 			offset[1] = vmd->dev->resource[VMD_MEMBAR2].start -
-					readq(membar2 + MB2_SHADOW_OFFSET + 8);
+					(readq(membar2 + MB2_SHADOW_OFFSET + 8) &
+					 PCI_BASE_ADDRESS_MEM_MASK);
 			pci_iounmap(vmd->dev, membar2);
 		}
 	}
@@ -854,6 +856,8 @@ static const struct pci_device_id vmd_ids[] = {
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VMD_28C0),
 		.driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW |
 				VMD_FEAT_HAS_BUS_RESTRICTIONS,},
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VMD_9A0B),
+		.driver_data = VMD_FEAT_HAS_BUS_RESTRICTIONS,},
 	{0,}
 };
 MODULE_DEVICE_TABLE(pci, vmd_ids);
diff --git a/drivers/pci/endpoint/pci-epc-mem.c b/drivers/pci/endpoint/pci-epc-mem.c
index 2bf8bd1f0563..abfac1109a13 100644
--- a/drivers/pci/endpoint/pci-epc-mem.c
+++ b/drivers/pci/endpoint/pci-epc-mem.c
@@ -79,6 +79,7 @@ int __pci_epc_mem_init(struct pci_epc *epc, phys_addr_t phys_base, size_t size,
 	mem->page_size = page_size;
 	mem->pages = pages;
 	mem->size = size;
+	mutex_init(&mem->lock);
 
 	epc->mem = mem;
 
@@ -122,7 +123,7 @@ void __iomem *pci_epc_mem_alloc_addr(struct pci_epc *epc,
 				     phys_addr_t *phys_addr, size_t size)
 {
 	int pageno;
-	void __iomem *virt_addr;
+	void __iomem *virt_addr = NULL;
 	struct pci_epc_mem *mem = epc->mem;
 	unsigned int page_shift = ilog2(mem->page_size);
 	int order;
@@ -130,15 +131,18 @@ void __iomem *pci_epc_mem_alloc_addr(struct pci_epc *epc,
 	size = ALIGN(size, mem->page_size);
 	order = pci_epc_mem_get_order(mem, size);
 
+	mutex_lock(&mem->lock);
 	pageno = bitmap_find_free_region(mem->bitmap, mem->pages, order);
 	if (pageno < 0)
-		return NULL;
+		goto ret;
 
-	*phys_addr = mem->phys_base + (pageno << page_shift);
+	*phys_addr = mem->phys_base + ((phys_addr_t)pageno << page_shift);
 	virt_addr = ioremap(*phys_addr, size);
 	if (!virt_addr)
 		bitmap_release_region(mem->bitmap, pageno, order);
 
+ret:
+	mutex_unlock(&mem->lock);
 	return virt_addr;
 }
 EXPORT_SYMBOL_GPL(pci_epc_mem_alloc_addr);
@@ -164,7 +168,9 @@ void pci_epc_mem_free_addr(struct pci_epc *epc, phys_addr_t phys_addr,
 	pageno = (phys_addr - mem->phys_base) >> page_shift;
 	size = ALIGN(size, mem->page_size);
 	order = pci_epc_mem_get_order(mem, size);
+	mutex_lock(&mem->lock);
 	bitmap_release_region(mem->bitmap, pageno, order);
+	mutex_unlock(&mem->lock);
 }
 EXPORT_SYMBOL_GPL(pci_epc_mem_free_addr);
 
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index b3869951c0eb..6e60b4b1bf53 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -122,13 +122,21 @@ static struct acpiphp_context *acpiphp_grab_context(struct acpi_device *adev)
 	struct acpiphp_context *context;
 
 	acpi_lock_hp_context();
+
 	context = acpiphp_get_context(adev);
-	if (!context || context->func.parent->is_going_away) {
-		acpi_unlock_hp_context();
-		return NULL;
+	if (!context)
+		goto unlock;
+
+	if (context->func.parent->is_going_away) {
+		acpiphp_put_context(context);
+		context = NULL;
+		goto unlock;
 	}
+
 	get_bridge(context->func.parent);
 	acpiphp_put_context(context);
+
+unlock:
 	acpi_unlock_hp_context();
 	return context;
 }
diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index e316bde45c7b..e28b4fffd84d 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -175,10 +175,10 @@ int pciehp_query_power_fault(struct controller *ctrl);
 void pciehp_green_led_on(struct controller *ctrl);
 void pciehp_green_led_off(struct controller *ctrl);
 void pciehp_green_led_blink(struct controller *ctrl);
-bool pciehp_card_present(struct controller *ctrl);
-bool pciehp_card_present_or_link_active(struct controller *ctrl);
+int pciehp_card_present(struct controller *ctrl);
+int pciehp_card_present_or_link_active(struct controller *ctrl);
 int pciehp_check_link_status(struct controller *ctrl);
-bool pciehp_check_link_active(struct controller *ctrl);
+int pciehp_check_link_active(struct controller *ctrl);
 void pciehp_release_ctrl(struct controller *ctrl);
 
 int pciehp_sysfs_enable_slot(struct hotplug_slot *hotplug_slot);
diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index 6ad0d86762cb..4c032d75c874 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -134,10 +134,15 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value)
 {
 	struct controller *ctrl = to_ctrl(hotplug_slot);
 	struct pci_dev *pdev = ctrl->pcie->port;
+	int ret;
 
 	pci_config_pm_runtime_get(pdev);
-	*value = pciehp_card_present_or_link_active(ctrl);
+	ret = pciehp_card_present_or_link_active(ctrl);
 	pci_config_pm_runtime_put(pdev);
+	if (ret < 0)
+		return ret;
+
+	*value = ret;
 	return 0;
 }
 
@@ -153,13 +158,13 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value)
  */
 static void pciehp_check_presence(struct controller *ctrl)
 {
-	bool occupied;
+	int occupied;
 
 	down_read(&ctrl->reset_lock);
 	mutex_lock(&ctrl->state_lock);
 
 	occupied = pciehp_card_present_or_link_active(ctrl);
-	if ((occupied && (ctrl->state == OFF_STATE ||
+	if ((occupied > 0 && (ctrl->state == OFF_STATE ||
 			  ctrl->state == BLINKINGON_STATE)) ||
 	    (!occupied && (ctrl->state == ON_STATE ||
 			   ctrl->state == BLINKINGOFF_STATE)))
@@ -248,7 +253,7 @@ static bool pme_is_native(struct pcie_device *dev)
 	return pcie_ports_native || host->native_pme;
 }
 
-static int pciehp_suspend(struct pcie_device *dev)
+static void pciehp_disable_interrupt(struct pcie_device *dev)
 {
 	/*
 	 * Disable hotplug interrupt so that it does not trigger
@@ -256,7 +261,19 @@ static int pciehp_suspend(struct pcie_device *dev)
 	 */
 	if (pme_is_native(dev))
 		pcie_disable_interrupt(get_service_data(dev));
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int pciehp_suspend(struct pcie_device *dev)
+{
+	/*
+	 * If the port is already runtime suspended we can keep it that
+	 * way.
+	 */
+	if (dev_pm_smart_suspend_and_suspended(&dev->port->dev))
+		return 0;
 
+	pciehp_disable_interrupt(dev);
 	return 0;
 }
 
@@ -274,6 +291,7 @@ static int pciehp_resume_noirq(struct pcie_device *dev)
 
 	return 0;
 }
+#endif
 
 static int pciehp_resume(struct pcie_device *dev)
 {
@@ -287,6 +305,12 @@ static int pciehp_resume(struct pcie_device *dev)
 	return 0;
 }
 
+static int pciehp_runtime_suspend(struct pcie_device *dev)
+{
+	pciehp_disable_interrupt(dev);
+	return 0;
+}
+
 static int pciehp_runtime_resume(struct pcie_device *dev)
 {
 	struct controller *ctrl = get_service_data(dev);
@@ -313,10 +337,12 @@ static struct pcie_port_service_driver hpdriver_portdrv = {
 	.remove		= pciehp_remove,
 
 #ifdef	CONFIG_PM
+#ifdef	CONFIG_PM_SLEEP
 	.suspend	= pciehp_suspend,
 	.resume_noirq	= pciehp_resume_noirq,
 	.resume		= pciehp_resume,
-	.runtime_suspend = pciehp_suspend,
+#endif
+	.runtime_suspend = pciehp_runtime_suspend,
 	.runtime_resume	= pciehp_runtime_resume,
 #endif	/* PM */
 };
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index 1ce9ce335291..abb460c93554 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -221,7 +221,7 @@ void pciehp_handle_disable_request(struct controller *ctrl)
 
 void pciehp_handle_presence_or_link_change(struct controller *ctrl, u32 events)
 {
-	bool present, link_active;
+	int present, link_active;
 
 	/*
 	 * If the slot is on and presence or link has changed, turn it off.
@@ -252,7 +252,7 @@ void pciehp_handle_presence_or_link_change(struct controller *ctrl, u32 events)
 	mutex_lock(&ctrl->state_lock);
 	present = pciehp_card_present(ctrl);
 	link_active = pciehp_check_link_active(ctrl);
-	if (!present && !link_active) {
+	if (present <= 0 && link_active <= 0) {
 		mutex_unlock(&ctrl->state_lock);
 		return;
 	}
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 9e2d7688e8cc..bbb1f23fb510 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -201,17 +201,29 @@ static void pcie_write_cmd_nowait(struct controller *ctrl, u16 cmd, u16 mask)
 	pcie_do_write_cmd(ctrl, cmd, mask, false);
 }
 
-bool pciehp_check_link_active(struct controller *ctrl)
+/**
+ * pciehp_check_link_active() - Is the link active
+ * @ctrl: PCIe hotplug controller
+ *
+ * Check whether the downstream link is currently active. Note it is
+ * possible that the card is removed immediately after this so the
+ * caller may need to take it into account.
+ *
+ * If the hotplug controller itself is not available anymore returns
+ * %-ENODEV.
+ */
+int pciehp_check_link_active(struct controller *ctrl)
 {
 	struct pci_dev *pdev = ctrl_dev(ctrl);
 	u16 lnk_status;
-	bool ret;
+	int ret;
 
-	pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnk_status);
-	ret = !!(lnk_status & PCI_EXP_LNKSTA_DLLLA);
+	ret = pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnk_status);
+	if (ret == PCIBIOS_DEVICE_NOT_FOUND || lnk_status == (u16)~0)
+		return -ENODEV;
 
-	if (ret)
-		ctrl_dbg(ctrl, "%s: lnk_status = %x\n", __func__, lnk_status);
+	ret = !!(lnk_status & PCI_EXP_LNKSTA_DLLLA);
+	ctrl_dbg(ctrl, "%s: lnk_status = %x\n", __func__, lnk_status);
 
 	return ret;
 }
@@ -373,13 +385,29 @@ void pciehp_get_latch_status(struct controller *ctrl, u8 *status)
 	*status = !!(slot_status & PCI_EXP_SLTSTA_MRLSS);
 }
 
-bool pciehp_card_present(struct controller *ctrl)
+/**
+ * pciehp_card_present() - Is the card present
+ * @ctrl: PCIe hotplug controller
+ *
+ * Function checks whether the card is currently present in the slot and
+ * in that case returns true. Note it is possible that the card is
+ * removed immediately after the check so the caller may need to take
+ * this into account.
+ *
+ * It the hotplug controller itself is not available anymore returns
+ * %-ENODEV.
+ */
+int pciehp_card_present(struct controller *ctrl)
 {
 	struct pci_dev *pdev = ctrl_dev(ctrl);
 	u16 slot_status;
+	int ret;
 
-	pcie_capability_read_word(pdev, PCI_EXP_SLTSTA, &slot_status);
-	return slot_status & PCI_EXP_SLTSTA_PDS;
+	ret = pcie_capability_read_word(pdev, PCI_EXP_SLTSTA, &slot_status);
+	if (ret == PCIBIOS_DEVICE_NOT_FOUND || slot_status == (u16)~0)
+		return -ENODEV;
+
+	return !!(slot_status & PCI_EXP_SLTSTA_PDS);
 }
 
 /**
@@ -390,10 +418,19 @@ bool pciehp_card_present(struct controller *ctrl)
  * Presence Detect State bit, this helper also returns true if the Link Active
  * bit is set.  This is a concession to broken hotplug ports which hardwire
  * Presence Detect State to zero, such as Wilocity's [1ae9:0200].
+ *
+ * Returns: %1 if the slot is occupied and %0 if it is not. If the hotplug
+ *	    port is not present anymore returns %-ENODEV.
  */
-bool pciehp_card_present_or_link_active(struct controller *ctrl)
+int pciehp_card_present_or_link_active(struct controller *ctrl)
 {
-	return pciehp_card_present(ctrl) || pciehp_check_link_active(ctrl);
+	int ret;
+
+	ret = pciehp_card_present(ctrl);
+	if (ret)
+		return ret;
+
+	return pciehp_check_link_active(ctrl);
 }
 
 int pciehp_query_power_fault(struct controller *ctrl)
@@ -615,17 +652,15 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id)
 	if (atomic_fetch_and(~RERUN_ISR, &ctrl->pending_events) & RERUN_ISR) {
 		ret = pciehp_isr(irq, dev_id);
 		enable_irq(irq);
-		if (ret != IRQ_WAKE_THREAD) {
-			pci_config_pm_runtime_put(pdev);
-			return ret;
-		}
+		if (ret != IRQ_WAKE_THREAD)
+			goto out;
 	}
 
 	synchronize_hardirq(irq);
 	events = atomic_xchg(&ctrl->pending_events, 0);
 	if (!events) {
-		pci_config_pm_runtime_put(pdev);
-		return IRQ_NONE;
+		ret = IRQ_NONE;
+		goto out;
 	}
 
 	/* Check Attention Button Pressed */
@@ -654,10 +689,12 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id)
 		pciehp_handle_presence_or_link_change(ctrl, events);
 	up_read(&ctrl->reset_lock);
 
+	ret = IRQ_HANDLED;
+out:
 	pci_config_pm_runtime_put(pdev);
 	ctrl->ist_running = false;
 	wake_up(&ctrl->requester);
-	return IRQ_HANDLED;
+	return ret;
 }
 
 static int pciehp_poll(void *data)
diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index 3aa115ed3a65..1f35a6b0e71a 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -189,10 +189,10 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id)
 	sprintf(buf, "virtfn%u", id);
 	rc = sysfs_create_link(&dev->dev.kobj, &virtfn->dev.kobj, buf);
 	if (rc)
-		goto failed2;
+		goto failed1;
 	rc = sysfs_create_link(&virtfn->dev.kobj, &dev->dev.kobj, "physfn");
 	if (rc)
-		goto failed3;
+		goto failed2;
 
 	kobject_uevent(&virtfn->dev.kobj, KOBJ_CHANGE);
 
@@ -200,11 +200,10 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id)
 
 	return 0;
 
-failed3:
-	sysfs_remove_link(&dev->dev.kobj, buf);
 failed2:
-	pci_stop_and_remove_bus_device(virtfn);
+	sysfs_remove_link(&dev->dev.kobj, buf);
 failed1:
+	pci_stop_and_remove_bus_device(virtfn);
 	pci_dev_put(dev);
 failed0:
 	virtfn_remove_bus(dev->bus, bus);
diff --git a/drivers/pci/pci-bridge-emul.c b/drivers/pci/pci-bridge-emul.c
index 702966e4fcaa..84f1865b1ab6 100644
--- a/drivers/pci/pci-bridge-emul.c
+++ b/drivers/pci/pci-bridge-emul.c
@@ -195,8 +195,8 @@ static const struct pci_bridge_reg_behavior pcie_cap_regs_behavior[] = {
 		 * RO, the rest is reserved
 		 */
 		.w1c = GENMASK(19, 16),
-		.ro = GENMASK(20, 19),
-		.rsvd = GENMASK(31, 21),
+		.ro = GENMASK(21, 20),
+		.rsvd = GENMASK(31, 22),
 	},
 
 	[PCI_EXP_LNKCAP / 4] = {
@@ -236,7 +236,7 @@ static const struct pci_bridge_reg_behavior pcie_cap_regs_behavior[] = {
 			PCI_EXP_SLTSTA_CC | PCI_EXP_SLTSTA_DLLSC) << 16,
 		.ro = (PCI_EXP_SLTSTA_MRLSS | PCI_EXP_SLTSTA_PDS |
 		       PCI_EXP_SLTSTA_EIS) << 16,
-		.rsvd = GENMASK(15, 12) | (GENMASK(15, 9) << 16),
+		.rsvd = GENMASK(15, 13) | (GENMASK(15, 9) << 16),
 	},
 
 	[PCI_EXP_RTCTL / 4] = {
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 8d912deb92f0..346f4ce5a318 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -900,6 +900,8 @@ static int pci_pm_resume_noirq(struct device *dev)
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
 	struct device_driver *drv = dev->driver;
+	pci_power_t prev_state = pci_dev->current_state;
+	bool skip_bus_pm = pci_dev->skip_bus_pm;
 	int error = 0;
 
 	if (dev_pm_may_skip_resume(dev))
@@ -919,16 +921,18 @@ static int pci_pm_resume_noirq(struct device *dev)
 	 * configuration here and attempting to put them into D0 again is
 	 * pointless, so avoid doing that.
 	 */
-	if (!(pci_dev->skip_bus_pm && pm_suspend_no_platform()))
+	if (!(skip_bus_pm && pm_suspend_no_platform()))
 		pci_pm_default_resume_early(pci_dev);
 
 	pci_fixup_device(pci_fixup_resume_early, pci_dev);
+	pcie_pme_root_status_cleanup(pci_dev);
+
+	if (!skip_bus_pm && prev_state == PCI_D3cold)
+		pci_bridge_wait_for_secondary_bus(pci_dev);
 
 	if (pci_has_legacy_pm_support(pci_dev))
 		return pci_legacy_resume_early(dev);
 
-	pcie_pme_root_status_cleanup(pci_dev);
-
 	if (drv && drv->pm && drv->pm->resume_noirq)
 		error = drv->pm->resume_noirq(dev);
 
@@ -1339,6 +1343,7 @@ static int pci_pm_runtime_resume(struct device *dev)
 	int rc = 0;
 	struct pci_dev *pci_dev = to_pci_dev(dev);
 	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+	pci_power_t prev_state = pci_dev->current_state;
 
 	/*
 	 * Restoring config space is necessary even if the device is not bound
@@ -1354,6 +1359,9 @@ static int pci_pm_runtime_resume(struct device *dev)
 	pci_enable_wake(pci_dev, PCI_D0, false);
 	pci_fixup_device(pci_fixup_resume, pci_dev);
 
+	if (prev_state == PCI_D3cold)
+		pci_bridge_wait_for_secondary_bus(pci_dev);
+
 	if (pm && pm->runtime_resume)
 		rc = pm->runtime_resume(dev);
 
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 42922dae29be..4edfa4f5f65e 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -796,7 +796,9 @@ static inline bool platform_pci_need_resume(struct pci_dev *dev)
 
 static inline bool platform_pci_bridge_d3(struct pci_dev *dev)
 {
-	return pci_platform_pm ? pci_platform_pm->bridge_d3(dev) : false;
+	if (pci_platform_pm && pci_platform_pm->bridge_d3)
+		return pci_platform_pm->bridge_d3(dev);
+	return false;
 }
 
 /**
@@ -991,15 +993,11 @@ static void __pci_start_power_transition(struct pci_dev *dev, pci_power_t state)
 	if (state == PCI_D0) {
 		pci_platform_power_transition(dev, PCI_D0);
 		/*
-		 * Mandatory power management transition delays, see
-		 * PCI Express Base Specification Revision 2.0 Section
-		 * 6.6.1: Conventional Reset.  Do not delay for
-		 * devices powered on/off by corresponding bridge,
-		 * because have already delayed for the bridge.
+		 * Mandatory power management transition delays are handled in
+		 * pci_pm_resume_noirq() and pci_pm_runtime_resume() of the
+		 * corresponding bridge.
 		 */
 		if (dev->runtime_d3cold) {
-			if (dev->d3cold_delay && !dev->imm_ready)
-				msleep(dev->d3cold_delay);
 			/*
 			 * When powering on a bridge from D3cold, the
 			 * whole hierarchy may be powered on into
@@ -4573,14 +4571,17 @@ static int pci_pm_reset(struct pci_dev *dev, int probe)
 
 	return pci_dev_wait(dev, "PM D3->D0", PCIE_RESET_READY_POLL_MS);
 }
+
 /**
- * pcie_wait_for_link - Wait until link is active or inactive
+ * pcie_wait_for_link_delay - Wait until link is active or inactive
  * @pdev: Bridge device
  * @active: waiting for active or inactive?
+ * @delay: Delay to wait after link has become active (in ms)
  *
  * Use this to wait till link becomes active or inactive.
  */
-bool pcie_wait_for_link(struct pci_dev *pdev, bool active)
+static bool pcie_wait_for_link_delay(struct pci_dev *pdev, bool active,
+				     int delay)
 {
 	int timeout = 1000;
 	bool ret;
@@ -4588,10 +4589,10 @@ bool pcie_wait_for_link(struct pci_dev *pdev, bool active)
 
 	/*
 	 * Some controllers might not implement link active reporting. In this
-	 * case, we wait for 1000 + 100 ms.
+	 * case, we wait for 1000 ms + any delay requested by the caller.
 	 */
 	if (!pdev->link_active_reporting) {
-		msleep(1100);
+		msleep(timeout + delay);
 		return true;
 	}
 
@@ -4617,13 +4618,144 @@ bool pcie_wait_for_link(struct pci_dev *pdev, bool active)
 		timeout -= 10;
 	}
 	if (active && ret)
-		msleep(100);
+		msleep(delay);
 	else if (ret != active)
 		pci_info(pdev, "Data Link Layer Link Active not %s in 1000 msec\n",
 			active ? "set" : "cleared");
 	return ret == active;
 }
 
+/**
+ * pcie_wait_for_link - Wait until link is active or inactive
+ * @pdev: Bridge device
+ * @active: waiting for active or inactive?
+ *
+ * Use this to wait till link becomes active or inactive.
+ */
+bool pcie_wait_for_link(struct pci_dev *pdev, bool active)
+{
+	return pcie_wait_for_link_delay(pdev, active, 100);
+}
+
+/*
+ * Find maximum D3cold delay required by all the devices on the bus.  The
+ * spec says 100 ms, but firmware can lower it and we allow drivers to
+ * increase it as well.
+ *
+ * Called with @pci_bus_sem locked for reading.
+ */
+static int pci_bus_max_d3cold_delay(const struct pci_bus *bus)
+{
+	const struct pci_dev *pdev;
+	int min_delay = 100;
+	int max_delay = 0;
+
+	list_for_each_entry(pdev, &bus->devices, bus_list) {
+		if (pdev->d3cold_delay < min_delay)
+			min_delay = pdev->d3cold_delay;
+		if (pdev->d3cold_delay > max_delay)
+			max_delay = pdev->d3cold_delay;
+	}
+
+	return max(min_delay, max_delay);
+}
+
+/**
+ * pci_bridge_wait_for_secondary_bus - Wait for secondary bus to be accessible
+ * @dev: PCI bridge
+ *
+ * Handle necessary delays before access to the devices on the secondary
+ * side of the bridge are permitted after D3cold to D0 transition.
+ *
+ * For PCIe this means the delays in PCIe 5.0 section 6.6.1. For
+ * conventional PCI it means Tpvrh + Trhfa specified in PCI 3.0 section
+ * 4.3.2.
+ */
+void pci_bridge_wait_for_secondary_bus(struct pci_dev *dev)
+{
+	struct pci_dev *child;
+	int delay;
+
+	if (pci_dev_is_disconnected(dev))
+		return;
+
+	if (!pci_is_bridge(dev) || !dev->bridge_d3)
+		return;
+
+	down_read(&pci_bus_sem);
+
+	/*
+	 * We only deal with devices that are present currently on the bus.
+	 * For any hot-added devices the access delay is handled in pciehp
+	 * board_added(). In case of ACPI hotplug the firmware is expected
+	 * to configure the devices before OS is notified.
+	 */
+	if (!dev->subordinate || list_empty(&dev->subordinate->devices)) {
+		up_read(&pci_bus_sem);
+		return;
+	}
+
+	/* Take d3cold_delay requirements into account */
+	delay = pci_bus_max_d3cold_delay(dev->subordinate);
+	if (!delay) {
+		up_read(&pci_bus_sem);
+		return;
+	}
+
+	child = list_first_entry(&dev->subordinate->devices, struct pci_dev,
+				 bus_list);
+	up_read(&pci_bus_sem);
+
+	/*
+	 * Conventional PCI and PCI-X we need to wait Tpvrh + Trhfa before
+	 * accessing the device after reset (that is 1000 ms + 100 ms). In
+	 * practice this should not be needed because we don't do power
+	 * management for them (see pci_bridge_d3_possible()).
+	 */
+	if (!pci_is_pcie(dev)) {
+		pci_dbg(dev, "waiting %d ms for secondary bus\n", 1000 + delay);
+		msleep(1000 + delay);
+		return;
+	}
+
+	/*
+	 * For PCIe downstream and root ports that do not support speeds
+	 * greater than 5 GT/s need to wait minimum 100 ms. For higher
+	 * speeds (gen3) we need to wait first for the data link layer to
+	 * become active.
+	 *
+	 * However, 100 ms is the minimum and the PCIe spec says the
+	 * software must allow at least 1s before it can determine that the
+	 * device that did not respond is a broken device. There is
+	 * evidence that 100 ms is not always enough, for example certain
+	 * Titan Ridge xHCI controller does not always respond to
+	 * configuration requests if we only wait for 100 ms (see
+	 * https://bugzilla.kernel.org/show_bug.cgi?id=203885).
+	 *
+	 * Therefore we wait for 100 ms and check for the device presence.
+	 * If it is still not present give it an additional 100 ms.
+	 */
+	if (!pcie_downstream_port(dev))
+		return;
+
+	if (pcie_get_speed_cap(dev) <= PCIE_SPEED_5_0GT) {
+		pci_dbg(dev, "waiting %d ms for downstream link\n", delay);
+		msleep(delay);
+	} else {
+		pci_dbg(dev, "waiting %d ms for downstream link, after activation\n",
+			delay);
+		if (!pcie_wait_for_link_delay(dev, true, delay)) {
+			/* Did not train, no need to wait any further */
+			return;
+		}
+	}
+
+	if (!pci_device_is_present(child)) {
+		pci_dbg(child, "waiting additional %d ms to become accessible\n", delay);
+		msleep(delay);
+	}
+}
+
 void pci_reset_secondary_bus(struct pci_dev *dev)
 {
 	u16 ctrl;
@@ -5820,10 +5952,29 @@ int pci_set_vga_state(struct pci_dev *dev, bool decode,
 	return 0;
 }
 
+#ifdef CONFIG_ACPI
+bool pci_pr3_present(struct pci_dev *pdev)
+{
+	struct acpi_device *adev;
+
+	if (acpi_disabled)
+		return false;
+
+	adev = ACPI_COMPANION(&pdev->dev);
+	if (!adev)
+		return false;
+
+	return adev->power.flags.power_resources &&
+		acpi_has_method(adev->handle, "_PR3");
+}
+EXPORT_SYMBOL_GPL(pci_pr3_present);
+#endif
+
 /**
  * pci_add_dma_alias - Add a DMA devfn alias for a device
  * @dev: the PCI device for which alias is added
- * @devfn: alias slot and function
+ * @devfn_from: alias slot and function
+ * @nr_devfns: number of subsequent devfns to alias
  *
  * This helper encodes an 8-bit devfn as a bit number in dma_alias_mask
  * which is used to program permissible bus-devfn source addresses for DMA
@@ -5839,18 +5990,29 @@ int pci_set_vga_state(struct pci_dev *dev, bool decode,
  * cannot be left as a userspace activity).  DMA aliases should therefore
  * be configured via quirks, such as the PCI fixup header quirk.
  */
-void pci_add_dma_alias(struct pci_dev *dev, u8 devfn)
+void pci_add_dma_alias(struct pci_dev *dev, u8 devfn_from, unsigned nr_devfns)
 {
+	int devfn_to;
+
+	nr_devfns = min(nr_devfns, (unsigned) MAX_NR_DEVFNS - devfn_from);
+	devfn_to = devfn_from + nr_devfns - 1;
+
 	if (!dev->dma_alias_mask)
-		dev->dma_alias_mask = bitmap_zalloc(U8_MAX, GFP_KERNEL);
+		dev->dma_alias_mask = bitmap_zalloc(MAX_NR_DEVFNS, GFP_KERNEL);
 	if (!dev->dma_alias_mask) {
 		pci_warn(dev, "Unable to allocate DMA alias mask\n");
 		return;
 	}
 
-	set_bit(devfn, dev->dma_alias_mask);
-	pci_info(dev, "Enabling fixed DMA alias to %02x.%d\n",
-		 PCI_SLOT(devfn), PCI_FUNC(devfn));
+	bitmap_set(dev->dma_alias_mask, devfn_from, nr_devfns);
+
+	if (nr_devfns == 1)
+		pci_info(dev, "Enabling fixed DMA alias to %02x.%d\n",
+				PCI_SLOT(devfn_from), PCI_FUNC(devfn_from));
+	else if (nr_devfns > 1)
+		pci_info(dev, "Enabling fixed DMA alias for devfn range from %02x.%d to %02x.%d\n",
+				PCI_SLOT(devfn_from), PCI_FUNC(devfn_from),
+				PCI_SLOT(devfn_to), PCI_FUNC(devfn_to));
 }
 
 bool pci_devs_are_dma_aliases(struct pci_dev *dev1, struct pci_dev *dev2)
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 9cb99380c61e..8e858d0a24ba 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -4,6 +4,9 @@
 
 #include <linux/pci.h>
 
+/* Number of possible devfns: 0.0 to 1f.7 inclusive */
+#define MAX_NR_DEVFNS 256
+
 #define PCI_FIND_CAP_TTL	48
 
 #define PCI_VSEC_ID_INTEL_TBT	0x1234	/* Thunderbolt */
@@ -92,6 +95,7 @@ void pci_allocate_cap_save_buffers(struct pci_dev *dev);
 void pci_free_cap_save_buffers(struct pci_dev *dev);
 bool pci_bridge_d3_possible(struct pci_dev *dev);
 void pci_bridge_d3_update(struct pci_dev *dev);
+void pci_bridge_wait_for_secondary_bus(struct pci_dev *dev);
 
 static inline void pci_wakeup_event(struct pci_dev *dev)
 {
@@ -113,6 +117,15 @@ static inline bool pci_power_manageable(struct pci_dev *pci_dev)
 	return !pci_has_subordinate(pci_dev) || pci_dev->bridge_d3;
 }
 
+static inline bool pcie_downstream_port(const struct pci_dev *dev)
+{
+	int type = pci_pcie_type(dev);
+
+	return type == PCI_EXP_TYPE_ROOT_PORT ||
+	       type == PCI_EXP_TYPE_DOWNSTREAM ||
+	       type == PCI_EXP_TYPE_PCIE_BRIDGE;
+}
+
 int pci_vpd_init(struct pci_dev *dev);
 void pci_vpd_release(struct pci_dev *dev);
 void pcie_vpd_create_sysfs_dev_files(struct pci_dev *dev);
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index b45bc47d04fe..271aecfbc3bf 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -1387,6 +1387,7 @@ static int aer_probe(struct pcie_device *dev)
 		return -ENOMEM;
 
 	rpc->rpd = port;
+	INIT_KFIFO(rpc->aer_fifo);
 	set_service_data(dev, rpc);
 
 	status = devm_request_threaded_irq(device, dev->irq, aer_irq, aer_isr,
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index fd4cb75088f9..676863722695 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -65,6 +65,7 @@ struct pcie_link_state {
 	u32 clkpm_capable:1;		/* Clock PM capable? */
 	u32 clkpm_enabled:1;		/* Current Clock PM state */
 	u32 clkpm_default:1;		/* Default Clock PM state by BIOS */
+	u32 clkpm_disable:1;		/* Clock PM disabled */
 
 	/* Exit latencies */
 	struct aspm_latency latency_up;	/* Upstream direction exit latency */
@@ -162,8 +163,11 @@ static void pcie_set_clkpm_nocheck(struct pcie_link_state *link, int enable)
 
 static void pcie_set_clkpm(struct pcie_link_state *link, int enable)
 {
-	/* Don't enable Clock PM if the link is not Clock PM capable */
-	if (!link->clkpm_capable)
+	/*
+	 * Don't enable Clock PM if the link is not Clock PM capable
+	 * or Clock PM is disabled
+	 */
+	if (!link->clkpm_capable || link->clkpm_disable)
 		enable = 0;
 	/* Need nothing if the specified equals to current state */
 	if (link->clkpm_enabled == enable)
@@ -193,7 +197,8 @@ static void pcie_clkpm_cap_init(struct pcie_link_state *link, int blacklist)
 	}
 	link->clkpm_enabled = enabled;
 	link->clkpm_default = enabled;
-	link->clkpm_capable = (blacklist) ? 0 : capable;
+	link->clkpm_capable = capable;
+	link->clkpm_disable = blacklist ? 1 : 0;
 }
 
 static bool pcie_retrain_link(struct pcie_link_state *link)
@@ -624,16 +629,6 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist)
 
 	/* Setup initial capable state. Will be updated later */
 	link->aspm_capable = link->aspm_support;
-	/*
-	 * If the downstream component has pci bridge function, don't
-	 * do ASPM for now.
-	 */
-	list_for_each_entry(child, &linkbus->devices, bus_list) {
-		if (pci_pcie_type(child) == PCI_EXP_TYPE_PCI_BRIDGE) {
-			link->aspm_disable = ASPM_STATE_ALL;
-			break;
-		}
-	}
 
 	/* Get and check endpoint acceptable latencies */
 	list_for_each_entry(child, &linkbus->devices, bus_list) {
@@ -743,9 +738,9 @@ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state)
 
 	/* Enable what we need to enable */
 	pci_clear_and_set_dword(parent, up_cap_ptr + PCI_L1SS_CTL1,
-				PCI_L1SS_CAP_L1_PM_SS, val);
+				PCI_L1SS_CTL1_L1SS_MASK, val);
 	pci_clear_and_set_dword(child, dw_cap_ptr + PCI_L1SS_CTL1,
-				PCI_L1SS_CAP_L1_PM_SS, val);
+				PCI_L1SS_CTL1_L1SS_MASK, val);
 }
 
 static void pcie_config_aspm_dev(struct pci_dev *pdev, u32 val)
@@ -1098,10 +1093,9 @@ static void __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem)
 		link->aspm_disable |= ASPM_STATE_L1;
 	pcie_config_aspm_link(link, policy_to_aspm_state(link));
 
-	if (state & PCIE_LINK_STATE_CLKPM) {
-		link->clkpm_capable = 0;
-		pcie_set_clkpm(link, 0);
-	}
+	if (state & PCIE_LINK_STATE_CLKPM)
+		link->clkpm_disable = 1;
+	pcie_set_clkpm(link, policy_to_clkpm_state(link));
 	mutex_unlock(&aspm_lock);
 	if (sem)
 		up_read(&pci_bus_sem);
@@ -1162,6 +1156,7 @@ static int pcie_aspm_get_policy(char *buffer, const struct kernel_param *kp)
 			cnt += sprintf(buffer + cnt, "[%s] ", policy_str[i]);
 		else
 			cnt += sprintf(buffer + cnt, "%s ", policy_str[i]);
+	cnt += sprintf(buffer + cnt, "\n");
 	return cnt;
 }
 
diff --git a/drivers/pci/pcie/ptm.c b/drivers/pci/pcie/ptm.c
index 98cfa30f3fae..357a454cafa0 100644
--- a/drivers/pci/pcie/ptm.c
+++ b/drivers/pci/pcie/ptm.c
@@ -21,7 +21,7 @@ static void pci_ptm_info(struct pci_dev *dev)
 		snprintf(clock_desc, sizeof(clock_desc), ">254ns");
 		break;
 	default:
-		snprintf(clock_desc, sizeof(clock_desc), "%udns",
+		snprintf(clock_desc, sizeof(clock_desc), "%uns",
 			 dev->ptm_granularity);
 		break;
 	}
@@ -39,10 +39,6 @@ void pci_ptm_init(struct pci_dev *dev)
 	if (!pci_is_pcie(dev))
 		return;
 
-	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_PTM);
-	if (!pos)
-		return;
-
 	/*
 	 * Enable PTM only on interior devices (root ports, switch ports,
 	 * etc.) on the assumption that it causes no link traffic until an
@@ -52,6 +48,23 @@ void pci_ptm_init(struct pci_dev *dev)
 	     pci_pcie_type(dev) == PCI_EXP_TYPE_RC_END))
 		return;
 
+	/*
+	 * Switch Downstream Ports are not permitted to have a PTM
+	 * capability; their PTM behavior is controlled by the Upstream
+	 * Port (PCIe r5.0, sec 7.9.16).
+	 */
+	ups = pci_upstream_bridge(dev);
+	if (pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM &&
+	    ups && ups->ptm_enabled) {
+		dev->ptm_granularity = ups->ptm_granularity;
+		dev->ptm_enabled = 1;
+		return;
+	}
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_PTM);
+	if (!pos)
+		return;
+
 	pci_read_config_dword(dev, pos + PCI_PTM_CAP, &cap);
 	local_clock = (cap & PCI_PTM_GRANULARITY_MASK) >> 8;
 
@@ -61,7 +74,6 @@ void pci_ptm_init(struct pci_dev *dev)
 	 * the spec recommendation (PCIe r3.1, sec 7.32.3), select the
 	 * furthest upstream Time Source as the PTM Root.
 	 */
-	ups = pci_upstream_bridge(dev);
 	if (ups && ups->ptm_enabled) {
 		ctrl = PCI_PTM_CTRL_ENABLE;
 		if (ups->ptm_granularity == 0)
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 1910b3394d2c..37770fe6948e 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -577,6 +577,7 @@ static void devm_pci_release_host_bridge_dev(struct device *dev)
 		bridge->release_fn(bridge);
 
 	pci_free_resource_list(&bridge->windows);
+	pci_free_resource_list(&bridge->dma_ranges);
 }
 
 static void pci_release_host_bridge_dev(struct device *dev)
@@ -871,9 +872,10 @@ static int pci_register_host_bridge(struct pci_host_bridge *bridge)
 		goto free;
 
 	err = device_register(&bridge->dev);
-	if (err)
+	if (err) {
 		put_device(&bridge->dev);
-
+		goto free;
+	}
 	bus->bridge = get_device(&bridge->dev);
 	device_enable_async_suspend(bus->bridge);
 	pci_set_bus_of_node(bus);
@@ -1771,7 +1773,7 @@ int pci_setup_device(struct pci_dev *dev)
 	/* Device class may be changed after fixup */
 	class = dev->class >> 8;
 
-	if (dev->non_compliant_bars) {
+	if (dev->non_compliant_bars && !dev->mmio_always_on) {
 		pci_read_config_word(dev, PCI_COMMAND, &cmd);
 		if (cmd & (PCI_COMMAND_IO | PCI_COMMAND_MEMORY)) {
 			pci_info(dev, "device has non-compliant BARs; disabling IO/MEM decoding\n");
@@ -1883,13 +1885,33 @@ static void pci_configure_mps(struct pci_dev *dev)
 	struct pci_dev *bridge = pci_upstream_bridge(dev);
 	int mps, mpss, p_mps, rc;
 
-	if (!pci_is_pcie(dev) || !bridge || !pci_is_pcie(bridge))
+	if (!pci_is_pcie(dev))
 		return;
 
 	/* MPS and MRRS fields are of type 'RsvdP' for VFs, short-circuit out */
 	if (dev->is_virtfn)
 		return;
 
+	/*
+	 * For Root Complex Integrated Endpoints, program the maximum
+	 * supported value unless limited by the PCIE_BUS_PEER2PEER case.
+	 */
+	if (pci_pcie_type(dev) == PCI_EXP_TYPE_RC_END) {
+		if (pcie_bus_config == PCIE_BUS_PEER2PEER)
+			mps = 128;
+		else
+			mps = 128 << dev->pcie_mpss;
+		rc = pcie_set_mps(dev, mps);
+		if (rc) {
+			pci_warn(dev, "can't set Max Payload Size to %d; if necessary, use \"pci=pcie_bus_safe\" and report a bug\n",
+				 mps);
+		}
+		return;
+	}
+
+	if (!bridge || !pci_is_pcie(bridge))
+		return;
+
 	mps = pcie_get_mps(dev);
 	p_mps = pcie_get_mps(bridge);
 
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 5676326d1f8c..0e23f47ef36d 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -1872,19 +1872,40 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x2609, quirk_intel_pcie_pm);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x260a, quirk_intel_pcie_pm);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x260b, quirk_intel_pcie_pm);
 
+static void quirk_d3hot_delay(struct pci_dev *dev, unsigned int delay)
+{
+	if (dev->d3_delay >= delay)
+		return;
+
+	dev->d3_delay = delay;
+	pci_info(dev, "extending delay after power-on from D3hot to %d msec\n",
+		 dev->d3_delay);
+}
+
 static void quirk_radeon_pm(struct pci_dev *dev)
 {
 	if (dev->subsystem_vendor == PCI_VENDOR_ID_APPLE &&
-	    dev->subsystem_device == 0x00e2) {
-		if (dev->d3_delay < 20) {
-			dev->d3_delay = 20;
-			pci_info(dev, "extending delay after power-on from D3 to %d msec\n",
-				 dev->d3_delay);
-		}
-	}
+	    dev->subsystem_device == 0x00e2)
+		quirk_d3hot_delay(dev, 20);
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x6741, quirk_radeon_pm);
 
+/*
+ * Ryzen5/7 XHCI controllers fail upon resume from runtime suspend or s2idle.
+ * https://bugzilla.kernel.org/show_bug.cgi?id=205587
+ *
+ * The kernel attempts to transition these devices to D3cold, but that seems
+ * to be ineffective on the platforms in question; the PCI device appears to
+ * remain on in D3hot state. The D3hot-to-D0 transition then requires an
+ * extended delay in order to succeed.
+ */
+static void quirk_ryzen_xhci_d3hot(struct pci_dev *dev)
+{
+	quirk_d3hot_delay(dev, 20);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x15e0, quirk_ryzen_xhci_d3hot);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x15e1, quirk_ryzen_xhci_d3hot);
+
 #ifdef CONFIG_X86_IO_APIC
 static int dmi_disable_ioapicreroute(const struct dmi_system_id *d)
 {
@@ -1950,26 +1971,92 @@ DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_80332_1,	quirk
 /*
  * IO-APIC1 on 6300ESB generates boot interrupts, see Intel order no
  * 300641-004US, section 5.7.3.
+ *
+ * Core IO on Xeon E5 1600/2600/4600, see Intel order no 326509-003.
+ * Core IO on Xeon E5 v2, see Intel order no 329188-003.
+ * Core IO on Xeon E7 v2, see Intel order no 329595-002.
+ * Core IO on Xeon E5 v3, see Intel order no 330784-003.
+ * Core IO on Xeon E7 v3, see Intel order no 332315-001US.
+ * Core IO on Xeon E5 v4, see Intel order no 333810-002US.
+ * Core IO on Xeon E7 v4, see Intel order no 332315-001US.
+ * Core IO on Xeon D-1500, see Intel order no 332051-001.
+ * Core IO on Xeon Scalable, see Intel order no 610950.
  */
-#define INTEL_6300_IOAPIC_ABAR		0x40
+#define INTEL_6300_IOAPIC_ABAR		0x40	/* Bus 0, Dev 29, Func 5 */
 #define INTEL_6300_DISABLE_BOOT_IRQ	(1<<14)
 
+#define INTEL_CIPINTRC_CFG_OFFSET	0x14C	/* Bus 0, Dev 5, Func 0 */
+#define INTEL_CIPINTRC_DIS_INTX_ICH	(1<<25)
+
 static void quirk_disable_intel_boot_interrupt(struct pci_dev *dev)
 {
 	u16 pci_config_word;
+	u32 pci_config_dword;
 
 	if (noioapicquirk)
 		return;
 
-	pci_read_config_word(dev, INTEL_6300_IOAPIC_ABAR, &pci_config_word);
-	pci_config_word |= INTEL_6300_DISABLE_BOOT_IRQ;
-	pci_write_config_word(dev, INTEL_6300_IOAPIC_ABAR, pci_config_word);
-
+	switch (dev->device) {
+	case PCI_DEVICE_ID_INTEL_ESB_10:
+		pci_read_config_word(dev, INTEL_6300_IOAPIC_ABAR,
+				     &pci_config_word);
+		pci_config_word |= INTEL_6300_DISABLE_BOOT_IRQ;
+		pci_write_config_word(dev, INTEL_6300_IOAPIC_ABAR,
+				      pci_config_word);
+		break;
+	case 0x3c28:	/* Xeon E5 1600/2600/4600	*/
+	case 0x0e28:	/* Xeon E5/E7 V2		*/
+	case 0x2f28:	/* Xeon E5/E7 V3,V4		*/
+	case 0x6f28:	/* Xeon D-1500			*/
+	case 0x2034:	/* Xeon Scalable Family		*/
+		pci_read_config_dword(dev, INTEL_CIPINTRC_CFG_OFFSET,
+				      &pci_config_dword);
+		pci_config_dword |= INTEL_CIPINTRC_DIS_INTX_ICH;
+		pci_write_config_dword(dev, INTEL_CIPINTRC_CFG_OFFSET,
+				       pci_config_dword);
+		break;
+	default:
+		return;
+	}
 	pci_info(dev, "disabled boot interrupts on device [%04x:%04x]\n",
 		 dev->vendor, dev->device);
 }
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,   PCI_DEVICE_ID_INTEL_ESB_10,	quirk_disable_intel_boot_interrupt);
-DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,   PCI_DEVICE_ID_INTEL_ESB_10,	quirk_disable_intel_boot_interrupt);
+/*
+ * Device 29 Func 5 Device IDs of IO-APIC
+ * containing ABAR—APIC1 Alternate Base Address Register
+ */
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ESB_10,
+		quirk_disable_intel_boot_interrupt);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ESB_10,
+		quirk_disable_intel_boot_interrupt);
+
+/*
+ * Device 5 Func 0 Device IDs of Core IO modules/hubs
+ * containing Coherent Interface Protocol Interrupt Control
+ *
+ * Device IDs obtained from volume 2 datasheets of commented
+ * families above.
+ */
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x3c28,
+		quirk_disable_intel_boot_interrupt);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x0e28,
+		quirk_disable_intel_boot_interrupt);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x2f28,
+		quirk_disable_intel_boot_interrupt);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x6f28,
+		quirk_disable_intel_boot_interrupt);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x2034,
+		quirk_disable_intel_boot_interrupt);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	0x3c28,
+		quirk_disable_intel_boot_interrupt);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	0x0e28,
+		quirk_disable_intel_boot_interrupt);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	0x2f28,
+		quirk_disable_intel_boot_interrupt);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	0x6f28,
+		quirk_disable_intel_boot_interrupt);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	0x2034,
+		quirk_disable_intel_boot_interrupt);
 
 /* Disable boot interrupts on HT-1000 */
 #define BC_HT1000_FEATURE_REG		0x64
@@ -2244,6 +2331,19 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10f1, quirk_disable_aspm_l0s);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10f4, quirk_disable_aspm_l0s);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1508, quirk_disable_aspm_l0s);
 
+static void quirk_disable_aspm_l0s_l1(struct pci_dev *dev)
+{
+	pci_info(dev, "Disabling ASPM L0s/L1\n");
+	pci_disable_link_state(dev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1);
+}
+
+/*
+ * ASM1083/1085 PCIe-PCI bridge devices cause AER timeout errors on the
+ * upstream PCIe root port when ASPM is enabled. At least L0s mode is affected;
+ * disable both L0s and L1 for now to be safe.
+ */
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ASMEDIA, 0x1080, quirk_disable_aspm_l0s_l1);
+
 /*
  * Some Pericom PCIe-to-PCI bridges in reverse mode need the PCIe Retrain
  * Link bit cleared after starting the link retrain process to allow this
@@ -2382,32 +2482,6 @@ DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_BROADCOM,
 			 PCI_DEVICE_ID_TIGON3_5719,
 			 quirk_brcm_5719_limit_mrrs);
 
-#ifdef CONFIG_PCIE_IPROC_PLATFORM
-static void quirk_paxc_bridge(struct pci_dev *pdev)
-{
-	/*
-	 * The PCI config space is shared with the PAXC root port and the first
-	 * Ethernet device.  So, we need to workaround this by telling the PCI
-	 * code that the bridge is not an Ethernet device.
-	 */
-	if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
-		pdev->class = PCI_CLASS_BRIDGE_PCI << 8;
-
-	/*
-	 * MPSS is not being set properly (as it is currently 0).  This is
-	 * because that area of the PCI config space is hard coded to zero, and
-	 * is not modifiable by firmware.  Set this to 2 (e.g., 512 byte MPS)
-	 * so that the MPS can be set to the real max value.
-	 */
-	pdev->pcie_mpss = 2;
-}
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x16cd, quirk_paxc_bridge);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x16f0, quirk_paxc_bridge);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd750, quirk_paxc_bridge);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd802, quirk_paxc_bridge);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd804, quirk_paxc_bridge);
-#endif
-
 /*
  * Originally in EDAC sources for i82875P: Intel tells BIOS developers to
  * hide device 6 which configures the overflow device access containing the
@@ -3862,7 +3936,7 @@ int pci_dev_specific_reset(struct pci_dev *dev, int probe)
 static void quirk_dma_func0_alias(struct pci_dev *dev)
 {
 	if (PCI_FUNC(dev->devfn) != 0)
-		pci_add_dma_alias(dev, PCI_DEVFN(PCI_SLOT(dev->devfn), 0));
+		pci_add_dma_alias(dev, PCI_DEVFN(PCI_SLOT(dev->devfn), 0), 1);
 }
 
 /*
@@ -3876,7 +3950,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_RICOH, 0xe476, quirk_dma_func0_alias);
 static void quirk_dma_func1_alias(struct pci_dev *dev)
 {
 	if (PCI_FUNC(dev->devfn) != 1)
-		pci_add_dma_alias(dev, PCI_DEVFN(PCI_SLOT(dev->devfn), 1));
+		pci_add_dma_alias(dev, PCI_DEVFN(PCI_SLOT(dev->devfn), 1), 1);
 }
 
 /*
@@ -3961,7 +4035,7 @@ static void quirk_fixed_dma_alias(struct pci_dev *dev)
 
 	id = pci_match_id(fixed_dma_alias_tbl, dev);
 	if (id)
-		pci_add_dma_alias(dev, id->driver_data);
+		pci_add_dma_alias(dev, id->driver_data, 1);
 }
 
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ADAPTEC2, 0x0285, quirk_fixed_dma_alias);
@@ -4003,14 +4077,43 @@ DECLARE_PCI_FIXUP_HEADER(0x8086, 0x244e, quirk_use_pcie_bridge_dma_alias);
  */
 static void quirk_mic_x200_dma_alias(struct pci_dev *pdev)
 {
-	pci_add_dma_alias(pdev, PCI_DEVFN(0x10, 0x0));
-	pci_add_dma_alias(pdev, PCI_DEVFN(0x11, 0x0));
-	pci_add_dma_alias(pdev, PCI_DEVFN(0x12, 0x3));
+	pci_add_dma_alias(pdev, PCI_DEVFN(0x10, 0x0), 1);
+	pci_add_dma_alias(pdev, PCI_DEVFN(0x11, 0x0), 1);
+	pci_add_dma_alias(pdev, PCI_DEVFN(0x12, 0x3), 1);
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2260, quirk_mic_x200_dma_alias);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2264, quirk_mic_x200_dma_alias);
 
 /*
+ * Intel Visual Compute Accelerator (VCA) is a family of PCIe add-in devices
+ * exposing computational units via Non Transparent Bridges (NTB, PEX 87xx).
+ *
+ * Similarly to MIC x200, we need to add DMA aliases to allow buffer access
+ * when IOMMU is enabled.  These aliases allow computational unit access to
+ * host memory.  These aliases mark the whole VCA device as one IOMMU
+ * group.
+ *
+ * All possible slot numbers (0x20) are used, since we are unable to tell
+ * what slot is used on other side.  This quirk is intended for both host
+ * and computational unit sides.  The VCA devices have up to five functions
+ * (four for DMA channels and one additional).
+ */
+static void quirk_pex_vca_alias(struct pci_dev *pdev)
+{
+	const unsigned int num_pci_slots = 0x20;
+	unsigned int slot;
+
+	for (slot = 0; slot < num_pci_slots; slot++)
+		pci_add_dma_alias(pdev, PCI_DEVFN(slot, 0x0), 5);
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2954, quirk_pex_vca_alias);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2955, quirk_pex_vca_alias);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2956, quirk_pex_vca_alias);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2958, quirk_pex_vca_alias);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2959, quirk_pex_vca_alias);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x295A, quirk_pex_vca_alias);
+
+/*
  * The IOMMU and interrupt controller on Broadcom Vulcan/Cavium ThunderX2 are
  * associated not at the root bus, but at a bridge below. This quirk avoids
  * generating invalid DMA aliases.
@@ -4193,6 +4296,24 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_CHELSIO, PCI_ANY_ID,
 			 quirk_chelsio_T5_disable_root_port_attributes);
 
 /*
+ * pci_acs_ctrl_enabled - compare desired ACS controls with those provided
+ *			  by a device
+ * @acs_ctrl_req: Bitmask of desired ACS controls
+ * @acs_ctrl_ena: Bitmask of ACS controls enabled or provided implicitly by
+ *		  the hardware design
+ *
+ * Return 1 if all ACS controls in the @acs_ctrl_req bitmask are included
+ * in @acs_ctrl_ena, i.e., the device provides all the access controls the
+ * caller desires.  Return 0 otherwise.
+ */
+static int pci_acs_ctrl_enabled(u16 acs_ctrl_req, u16 acs_ctrl_ena)
+{
+	if ((acs_ctrl_req & acs_ctrl_ena) == acs_ctrl_req)
+		return 1;
+	return 0;
+}
+
+/*
  * AMD has indicated that the devices below do not support peer-to-peer
  * in any system where they are found in the southbridge with an AMD
  * IOMMU in the system.  Multifunction devices that do not support
@@ -4232,10 +4353,12 @@ static int pci_quirk_amd_sb_acs(struct pci_dev *dev, u16 acs_flags)
 	if (ACPI_FAILURE(status))
 		return -ENODEV;
 
+	acpi_put_table(header);
+
 	/* Filter out flags not applicable to multifunction */
 	acs_flags &= (PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC | PCI_ACS_DT);
 
-	return acs_flags & ~(PCI_ACS_RR | PCI_ACS_CR) ? 0 : 1;
+	return pci_acs_ctrl_enabled(acs_flags, PCI_ACS_RR | PCI_ACS_CR);
 #else
 	return -ENODEV;
 #endif
@@ -4251,20 +4374,19 @@ static bool pci_quirk_cavium_acs_match(struct pci_dev *dev)
 
 static int pci_quirk_cavium_acs(struct pci_dev *dev, u16 acs_flags)
 {
+	if (!pci_quirk_cavium_acs_match(dev))
+		return -ENOTTY;
+
 	/*
-	 * Cavium root ports don't advertise an ACS capability.  However,
+	 * Cavium Root Ports don't advertise an ACS capability.  However,
 	 * the RTL internally implements similar protection as if ACS had
-	 * Request Redirection, Completion Redirection, Source Validation,
+	 * Source Validation, Request Redirection, Completion Redirection,
 	 * and Upstream Forwarding features enabled.  Assert that the
 	 * hardware implements and enables equivalent ACS functionality for
 	 * these flags.
 	 */
-	acs_flags &= ~(PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_SV | PCI_ACS_UF);
-
-	if (!pci_quirk_cavium_acs_match(dev))
-		return -ENOTTY;
-
-	return acs_flags ? 0 : 1;
+	return pci_acs_ctrl_enabled(acs_flags,
+		PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF);
 }
 
 static int pci_quirk_xgene_acs(struct pci_dev *dev, u16 acs_flags)
@@ -4274,13 +4396,35 @@ static int pci_quirk_xgene_acs(struct pci_dev *dev, u16 acs_flags)
 	 * transactions with others, allowing masking out these bits as if they
 	 * were unimplemented in the ACS capability.
 	 */
-	acs_flags &= ~(PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF);
+	return pci_acs_ctrl_enabled(acs_flags,
+		PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF);
+}
+
+/*
+ * Many Zhaoxin Root Ports and Switch Downstream Ports have no ACS capability.
+ * But the implementation could block peer-to-peer transactions between them
+ * and provide ACS-like functionality.
+ */
+static int  pci_quirk_zhaoxin_pcie_ports_acs(struct pci_dev *dev, u16 acs_flags)
+{
+	if (!pci_is_pcie(dev) ||
+	    ((pci_pcie_type(dev) != PCI_EXP_TYPE_ROOT_PORT) &&
+	     (pci_pcie_type(dev) != PCI_EXP_TYPE_DOWNSTREAM)))
+		return -ENOTTY;
+
+	switch (dev->device) {
+	case 0x0710 ... 0x071e:
+	case 0x0721:
+	case 0x0723 ... 0x0732:
+		return pci_acs_ctrl_enabled(acs_flags,
+			PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF);
+	}
 
-	return acs_flags ? 0 : 1;
+	return false;
 }
 
 /*
- * Many Intel PCH root ports do provide ACS-like features to disable peer
+ * Many Intel PCH Root Ports do provide ACS-like features to disable peer
  * transactions and validate bus numbers in requests, but do not provide an
  * actual PCIe ACS capability.  This is the list of device IDs known to fall
  * into that category as provided by Intel in Red Hat bugzilla 1037684.
@@ -4328,37 +4472,32 @@ static bool pci_quirk_intel_pch_acs_match(struct pci_dev *dev)
 	return false;
 }
 
-#define INTEL_PCH_ACS_FLAGS (PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF | PCI_ACS_SV)
-
 static int pci_quirk_intel_pch_acs(struct pci_dev *dev, u16 acs_flags)
 {
-	u16 flags = dev->dev_flags & PCI_DEV_FLAGS_ACS_ENABLED_QUIRK ?
-		    INTEL_PCH_ACS_FLAGS : 0;
-
 	if (!pci_quirk_intel_pch_acs_match(dev))
 		return -ENOTTY;
 
-	return acs_flags & ~flags ? 0 : 1;
+	if (dev->dev_flags & PCI_DEV_FLAGS_ACS_ENABLED_QUIRK)
+		return pci_acs_ctrl_enabled(acs_flags,
+			PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF);
+
+	return pci_acs_ctrl_enabled(acs_flags, 0);
 }
 
 /*
- * These QCOM root ports do provide ACS-like features to disable peer
+ * These QCOM Root Ports do provide ACS-like features to disable peer
  * transactions and validate bus numbers in requests, but do not provide an
  * actual PCIe ACS capability.  Hardware supports source validation but it
  * will report the issue as Completer Abort instead of ACS Violation.
- * Hardware doesn't support peer-to-peer and each root port is a root
- * complex with unique segment numbers.  It is not possible for one root
- * port to pass traffic to another root port.  All PCIe transactions are
- * terminated inside the root port.
+ * Hardware doesn't support peer-to-peer and each Root Port is a Root
+ * Complex with unique segment numbers.  It is not possible for one Root
+ * Port to pass traffic to another Root Port.  All PCIe transactions are
+ * terminated inside the Root Port.
  */
 static int pci_quirk_qcom_rp_acs(struct pci_dev *dev, u16 acs_flags)
 {
-	u16 flags = (PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF | PCI_ACS_SV);
-	int ret = acs_flags & ~flags ? 0 : 1;
-
-	pci_info(dev, "Using QCOM ACS Quirk (%d)\n", ret);
-
-	return ret;
+	return pci_acs_ctrl_enabled(acs_flags,
+		PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF);
 }
 
 /*
@@ -4441,7 +4580,7 @@ static int pci_quirk_intel_spt_pch_acs(struct pci_dev *dev, u16 acs_flags)
 
 	pci_read_config_dword(dev, pos + INTEL_SPT_ACS_CTRL, &ctrl);
 
-	return acs_flags & ~ctrl ? 0 : 1;
+	return pci_acs_ctrl_enabled(acs_flags, ctrl);
 }
 
 static int pci_quirk_mf_endpoint_acs(struct pci_dev *dev, u16 acs_flags)
@@ -4455,10 +4594,35 @@ static int pci_quirk_mf_endpoint_acs(struct pci_dev *dev, u16 acs_flags)
 	 * perform peer-to-peer with other functions, allowing us to mask out
 	 * these bits as if they were unimplemented in the ACS capability.
 	 */
-	acs_flags &= ~(PCI_ACS_SV | PCI_ACS_TB | PCI_ACS_RR |
-		       PCI_ACS_CR | PCI_ACS_UF | PCI_ACS_DT);
+	return pci_acs_ctrl_enabled(acs_flags,
+		PCI_ACS_SV | PCI_ACS_TB | PCI_ACS_RR |
+		PCI_ACS_CR | PCI_ACS_UF | PCI_ACS_DT);
+}
+
+static int pci_quirk_rciep_acs(struct pci_dev *dev, u16 acs_flags)
+{
+	/*
+	 * Intel RCiEP's are required to allow p2p only on translated
+	 * addresses.  Refer to Intel VT-d specification, r3.1, sec 3.16,
+	 * "Root-Complex Peer to Peer Considerations".
+	 */
+	if (pci_pcie_type(dev) != PCI_EXP_TYPE_RC_END)
+		return -ENOTTY;
+
+	return pci_acs_ctrl_enabled(acs_flags,
+		PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF);
+}
 
-	return acs_flags ? 0 : 1;
+static int pci_quirk_brcm_acs(struct pci_dev *dev, u16 acs_flags)
+{
+	/*
+	 * iProc PAXB Root Ports don't advertise an ACS capability, but
+	 * they do not allow peer-to-peer transactions between Root Ports.
+	 * Allow each Root Port to be in a separate IOMMU group by masking
+	 * SV/RR/CR/UF bits.
+	 */
+	return pci_acs_ctrl_enabled(acs_flags,
+		PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF);
 }
 
 static const struct pci_dev_acs_enabled {
@@ -4531,6 +4695,7 @@ static const struct pci_dev_acs_enabled {
 	/* I219 */
 	{ PCI_VENDOR_ID_INTEL, 0x15b7, pci_quirk_mf_endpoint_acs },
 	{ PCI_VENDOR_ID_INTEL, 0x15b8, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_quirk_rciep_acs },
 	/* QCOM QDF2xxx root ports */
 	{ PCI_VENDOR_ID_QCOM, 0x0400, pci_quirk_qcom_rp_acs },
 	{ PCI_VENDOR_ID_QCOM, 0x0401, pci_quirk_qcom_rp_acs },
@@ -4554,9 +4719,27 @@ static const struct pci_dev_acs_enabled {
 	{ PCI_VENDOR_ID_AMPERE, 0xE00A, pci_quirk_xgene_acs },
 	{ PCI_VENDOR_ID_AMPERE, 0xE00B, pci_quirk_xgene_acs },
 	{ PCI_VENDOR_ID_AMPERE, 0xE00C, pci_quirk_xgene_acs },
+	{ PCI_VENDOR_ID_BROADCOM, 0xD714, pci_quirk_brcm_acs },
+	/* Zhaoxin multi-function devices */
+	{ PCI_VENDOR_ID_ZHAOXIN, 0x3038, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_ZHAOXIN, 0x3104, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_ZHAOXIN, 0x9083, pci_quirk_mf_endpoint_acs },
+	/* Zhaoxin Root/Downstream Ports */
+	{ PCI_VENDOR_ID_ZHAOXIN, PCI_ANY_ID, pci_quirk_zhaoxin_pcie_ports_acs },
 	{ 0 }
 };
 
+/*
+ * pci_dev_specific_acs_enabled - check whether device provides ACS controls
+ * @dev:	PCI device
+ * @acs_flags:	Bitmask of desired ACS controls
+ *
+ * Returns:
+ *   -ENOTTY:	No quirk applies to this device; we can't tell whether the
+ *		device provides the desired controls
+ *   0:		Device does not provide all the desired controls
+ *   >0:	Device provides all the controls in @acs_flags
+ */
 int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags)
 {
 	const struct pci_dev_acs_enabled *i;
@@ -4876,13 +5059,25 @@ static void quirk_intel_qat_vf_cap(struct pci_dev *pdev)
 }
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x443, quirk_intel_qat_vf_cap);
 
-/* FLR may cause some 82579 devices to hang */
-static void quirk_intel_no_flr(struct pci_dev *dev)
+/*
+ * FLR may cause the following to devices to hang:
+ *
+ * AMD Starship/Matisse HD Audio Controller 0x1487
+ * AMD Starship USB 3.0 Host Controller 0x148c
+ * AMD Matisse USB 3.0 Host Controller 0x149c
+ * Intel 82579LM Gigabit Ethernet Controller 0x1502
+ * Intel 82579V Gigabit Ethernet Controller 0x1503
+ *
+ */
+static void quirk_no_flr(struct pci_dev *dev)
 {
 	dev->dev_flags |= PCI_DEV_FLAGS_NO_FLR_RESET;
 }
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1502, quirk_intel_no_flr);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1503, quirk_intel_no_flr);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x1487, quirk_no_flr);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x148c, quirk_no_flr);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x149c, quirk_no_flr);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1502, quirk_no_flr);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1503, quirk_no_flr);
 
 static void quirk_no_ext_tags(struct pci_dev *pdev)
 {
@@ -4906,18 +5101,28 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0422, quirk_no_ext_tags);
 
 #ifdef CONFIG_PCI_ATS
 /*
- * Some devices have a broken ATS implementation causing IOMMU stalls.
- * Don't use ATS for those devices.
+ * Some devices require additional driver setup to enable ATS.  Don't use
+ * ATS for those devices as ATS will be enabled before the driver has had a
+ * chance to load and configure the device.
  */
-static void quirk_no_ats(struct pci_dev *pdev)
+static void quirk_amd_harvest_no_ats(struct pci_dev *pdev)
 {
-	pci_info(pdev, "disabling ATS (broken on this device)\n");
+	if ((pdev->device == 0x7312 && pdev->revision != 0x00) ||
+	    (pdev->device == 0x7340 && pdev->revision != 0xc5))
+		return;
+
+	pci_info(pdev, "disabling ATS\n");
 	pdev->ats_cap = 0;
 }
 
 /* AMD Stoney platform GPU */
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x98e4, quirk_no_ats);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x6900, quirk_no_ats);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x98e4, quirk_amd_harvest_no_ats);
+/* AMD Iceland dGPU */
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x6900, quirk_amd_harvest_no_ats);
+/* AMD Navi10 dGPU */
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7312, quirk_amd_harvest_no_ats);
+/* AMD Navi14 dGPU */
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7340, quirk_amd_harvest_no_ats);
 #endif /* CONFIG_PCI_ATS */
 
 /* Freescale PCIe doesn't support MSI in RC mode */
@@ -5094,7 +5299,7 @@ static void quirk_switchtec_ntb_dma_alias(struct pci_dev *pdev)
 			pci_dbg(pdev,
 				"Aliasing Partition %d Proxy ID %02x.%d\n",
 				pp, PCI_SLOT(devfn), PCI_FUNC(devfn));
-			pci_add_dma_alias(pdev, devfn);
+			pci_add_dma_alias(pdev, devfn, 1);
 		}
 	}
 
@@ -5137,6 +5342,21 @@ SWITCHTEC_QUIRK(0x8575);  /* PFXI 80XG3 */
 SWITCHTEC_QUIRK(0x8576);  /* PFXI 96XG3 */
 
 /*
+ * The PLX NTB uses devfn proxy IDs to move TLPs between NT endpoints.
+ * These IDs are used to forward responses to the originator on the other
+ * side of the NTB.  Alias all possible IDs to the NTB to permit access when
+ * the IOMMU is turned on.
+ */
+static void quirk_plx_ntb_dma_alias(struct pci_dev *pdev)
+{
+	pci_info(pdev, "Setting PLX NTB proxy ID aliases\n");
+	/* PLX NTB may use all 256 devfns */
+	pci_add_dma_alias(pdev, 0, 256);
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_PLX, 0x87b0, quirk_plx_ntb_dma_alias);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_PLX, 0x87b1, quirk_plx_ntb_dma_alias);
+
+/*
  * On Lenovo Thinkpad P50 SKUs with a Nvidia Quadro M1000M, the BIOS does
  * not always reset the secondary Nvidia GPU between reboots if the system
  * is configured to use Hybrid Graphics mode.  This results in the GPU
@@ -5181,7 +5401,7 @@ static void quirk_reset_lenovo_thinkpad_p50_nvgpu(struct pci_dev *pdev)
 	 */
 	if (ioread32(map + 0x2240c) & 0x2) {
 		pci_info(pdev, FW_BUG "GPU left initialized by EFI, resetting\n");
-		ret = pci_reset_function(pdev);
+		ret = pci_reset_bus(pdev);
 		if (ret < 0)
 			pci_err(pdev, "Failed to reset GPU: %d\n", ret);
 	}
@@ -5193,3 +5413,34 @@ out_disable:
 DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_NVIDIA, 0x13b1,
 			      PCI_CLASS_DISPLAY_VGA, 8,
 			      quirk_reset_lenovo_thinkpad_p50_nvgpu);
+
+/*
+ * Device [1b21:2142]
+ * When in D0, PME# doesn't get asserted when plugging USB 3.0 device.
+ */
+static void pci_fixup_no_d0_pme(struct pci_dev *dev)
+{
+	pci_info(dev, "PME# does not work under D0, disabling it\n");
+	dev->pme_support &= ~(PCI_PM_CAP_PME_D0 >> PCI_PM_CAP_PME_SHIFT);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ASMEDIA, 0x2142, pci_fixup_no_d0_pme);
+
+static void apex_pci_fixup_class(struct pci_dev *pdev)
+{
+	pdev->class = (PCI_CLASS_SYSTEM_OTHER << 8) | pdev->class;
+}
+DECLARE_PCI_FIXUP_CLASS_HEADER(0x1ac1, 0x089a,
+			       PCI_CLASS_NOT_DEFINED, 8, apex_pci_fixup_class);
+
+/*
+ * Device [12d8:0x400e] and [12d8:0x400f]
+ * These devices advertise PME# support in all power states but don't
+ * reliably assert it.
+ */
+static void pci_fixup_no_pme(struct pci_dev *dev)
+{
+	pci_info(dev, "PME# is unreliable, disabling it\n");
+	dev->pme_support = 0;
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_PERICOM, 0x400e, pci_fixup_no_pme);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_PERICOM, 0x400f, pci_fixup_no_pme);
diff --git a/drivers/pci/search.c b/drivers/pci/search.c
index 5c7922612733..68326e5849da 100644
--- a/drivers/pci/search.c
+++ b/drivers/pci/search.c
@@ -42,9 +42,9 @@ int pci_for_each_dma_alias(struct pci_dev *pdev,
 	 * DMA, iterate over that too.
 	 */
 	if (unlikely(pdev->dma_alias_mask)) {
-		u8 devfn;
+		unsigned int devfn;
 
-		for_each_set_bit(devfn, pdev->dma_alias_mask, U8_MAX) {
+		for_each_set_bit(devfn, pdev->dma_alias_mask, MAX_NR_DEVFNS) {
 			ret = fn(pdev, PCI_DEVID(pdev->bus->number, devfn),
 				 data);
 			if (ret)
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 0cdd5ff389de..6bbfcc825199 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -1780,12 +1780,18 @@ again:
 	/* Restore size and flags */
 	list_for_each_entry(fail_res, &fail_head, list) {
 		struct resource *res = fail_res->res;
+		int idx;
 
 		res->start = fail_res->start;
 		res->end = fail_res->end;
 		res->flags = fail_res->flags;
-		if (fail_res->dev->subordinate)
-			res->flags = 0;
+
+		if (pci_is_bridge(fail_res->dev)) {
+			idx = res - &fail_res->dev->resource[0];
+			if (idx >= PCI_BRIDGE_RESOURCES &&
+			    idx <= PCI_BRIDGE_RESOURCE_END)
+				res->flags = 0;
+		}
 	}
 	free_list(&fail_head);
 
@@ -2031,12 +2037,18 @@ again:
 	/* Restore size and flags */
 	list_for_each_entry(fail_res, &fail_head, list) {
 		struct resource *res = fail_res->res;
+		int idx;
 
 		res->start = fail_res->start;
 		res->end = fail_res->end;
 		res->flags = fail_res->flags;
-		if (fail_res->dev->subordinate)
-			res->flags = 0;
+
+		if (pci_is_bridge(fail_res->dev)) {
+			idx = res - &fail_res->dev->resource[0];
+			if (idx >= PCI_BRIDGE_RESOURCES &&
+			    idx <= PCI_BRIDGE_RESOURCE_END)
+				res->flags = 0;
+		}
 	}
 	free_list(&fail_head);
 
diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c
index d8ca40a97693..d21fa04fa44d 100644
--- a/drivers/pci/setup-res.c
+++ b/drivers/pci/setup-res.c
@@ -439,10 +439,11 @@ int pci_resize_resource(struct pci_dev *dev, int resno, int size)
 	res->end = res->start + pci_rebar_size_to_bytes(size) - 1;
 
 	/* Check if the new config works by trying to assign everything. */
-	ret = pci_reassign_bridge_resources(dev->bus->self, res->flags);
-	if (ret)
-		goto error_resize;
-
+	if (dev->bus->self) {
+		ret = pci_reassign_bridge_resources(dev->bus->self, res->flags);
+		if (ret)
+			goto error_resize;
+	}
 	return 0;
 
 error_resize:
diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c
index 5ed9a92a9c9a..2ad1c30b9ef1 100644
--- a/drivers/pci/switch/switchtec.c
+++ b/drivers/pci/switch/switchtec.c
@@ -171,7 +171,7 @@ static int mrpc_queue_cmd(struct switchtec_user *stuser)
 	kref_get(&stuser->kref);
 	stuser->read_len = sizeof(stuser->data);
 	stuser_set_state(stuser, MRPC_QUEUED);
-	init_completion(&stuser->comp);
+	reinit_completion(&stuser->comp);
 	list_add_tail(&stuser->list, &stdev->mrpc_queue);
 
 	mrpc_cmd_submit(stdev);
@@ -1268,7 +1268,7 @@ static int switchtec_init_isr(struct switchtec_dev *stdev)
 	if (nvecs < 0)
 		return nvecs;
 
-	event_irq = ioread32(&stdev->mmio_part_cfg->vep_vector_number);
+	event_irq = ioread16(&stdev->mmio_part_cfg->vep_vector_number);
 	if (event_irq < 0 || event_irq >= nvecs)
 		return -EFAULT;
 
@@ -1341,7 +1341,7 @@ static int switchtec_init_pci(struct switchtec_dev *stdev,
 	if (rc)
 		return rc;
 
-	rc = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64));
+	rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
 	if (rc)
 		return rc;
 
diff --git a/drivers/perf/arm-cci.c b/drivers/perf/arm-cci.c
index 8f8606b9bc9e..aca4570f78a8 100644
--- a/drivers/perf/arm-cci.c
+++ b/drivers/perf/arm-cci.c
@@ -1720,6 +1720,7 @@ static struct platform_driver cci_pmu_driver = {
 	.driver = {
 		   .name = DRIVER_NAME,
 		   .of_match_table = arm_cci_pmu_matches,
+		   .suppress_bind_attrs = true,
 		  },
 	.probe = cci_pmu_probe,
 	.remove = cci_pmu_remove,
diff --git a/drivers/perf/arm-ccn.c b/drivers/perf/arm-ccn.c
index 6fc0273b6129..336948b41bd1 100644
--- a/drivers/perf/arm-ccn.c
+++ b/drivers/perf/arm-ccn.c
@@ -1545,6 +1545,7 @@ static struct platform_driver arm_ccn_driver = {
 	.driver = {
 		.name = "arm-ccn",
 		.of_match_table = arm_ccn_match,
+		.suppress_bind_attrs = true,
 	},
 	.probe = arm_ccn_probe,
 	.remove = arm_ccn_remove,
diff --git a/drivers/perf/arm_dsu_pmu.c b/drivers/perf/arm_dsu_pmu.c
index 70968c8c09d7..4594e2ed13d5 100644
--- a/drivers/perf/arm_dsu_pmu.c
+++ b/drivers/perf/arm_dsu_pmu.c
@@ -759,6 +759,7 @@ static struct platform_driver dsu_pmu_driver = {
 	.driver = {
 		.name	= DRVNAME,
 		.of_match_table = of_match_ptr(dsu_pmu_of_match),
+		.suppress_bind_attrs = true,
 	},
 	.probe = dsu_pmu_device_probe,
 	.remove = dsu_pmu_device_remove,
diff --git a/drivers/perf/arm_pmu_acpi.c b/drivers/perf/arm_pmu_acpi.c
index d2c2978409d2..a1185927009d 100644
--- a/drivers/perf/arm_pmu_acpi.c
+++ b/drivers/perf/arm_pmu_acpi.c
@@ -24,8 +24,6 @@ static int arm_pmu_acpi_register_irq(int cpu)
 	int gsi, trigger;
 
 	gicc = acpi_cpu_get_madt_gicc(cpu);
-	if (WARN_ON(!gicc))
-		return -EINVAL;
 
 	gsi = gicc->performance_interrupt;
 
@@ -64,11 +62,10 @@ static void arm_pmu_acpi_unregister_irq(int cpu)
 	int gsi;
 
 	gicc = acpi_cpu_get_madt_gicc(cpu);
-	if (!gicc)
-		return;
 
 	gsi = gicc->performance_interrupt;
-	acpi_unregister_gsi(gsi);
+	if (gsi)
+		acpi_unregister_gsi(gsi);
 }
 
 static int arm_pmu_acpi_parse_irqs(void)
diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c
index 94f1e83bec2e..f3028f0d5f52 100644
--- a/drivers/perf/arm_smmuv3_pmu.c
+++ b/drivers/perf/arm_smmuv3_pmu.c
@@ -721,6 +721,7 @@ static int smmu_pmu_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, smmu_pmu);
 
 	smmu_pmu->pmu = (struct pmu) {
+		.module		= THIS_MODULE,
 		.task_ctx_nr    = perf_invalid_context,
 		.pmu_enable	= smmu_pmu_enable,
 		.pmu_disable	= smmu_pmu_disable,
@@ -751,7 +752,7 @@ static int smmu_pmu_probe(struct platform_device *pdev)
 		smmu_pmu->reloc_base = smmu_pmu->reg_base;
 	}
 
-	irq = platform_get_irq(pdev, 0);
+	irq = platform_get_irq_optional(pdev, 0);
 	if (irq > 0)
 		smmu_pmu->irq = irq;
 
@@ -794,7 +795,7 @@ static int smmu_pmu_probe(struct platform_device *pdev)
 	if (err) {
 		dev_err(dev, "Error %d registering hotplug, PMU @%pa\n",
 			err, &res_0->start);
-		goto out_cpuhp_err;
+		goto out_clear_affinity;
 	}
 
 	err = perf_pmu_register(&smmu_pmu->pmu, name, -1);
@@ -813,8 +814,8 @@ static int smmu_pmu_probe(struct platform_device *pdev)
 
 out_unregister:
 	cpuhp_state_remove_instance_nocalls(cpuhp_state_num, &smmu_pmu->node);
-out_cpuhp_err:
-	put_cpu();
+out_clear_affinity:
+	irq_set_affinity_hint(smmu_pmu->irq, NULL);
 	return err;
 }
 
@@ -824,6 +825,7 @@ static int smmu_pmu_remove(struct platform_device *pdev)
 
 	perf_pmu_unregister(&smmu_pmu->pmu);
 	cpuhp_state_remove_instance_nocalls(cpuhp_state_num, &smmu_pmu->node);
+	irq_set_affinity_hint(smmu_pmu->irq, NULL);
 
 	return 0;
 }
@@ -845,6 +847,7 @@ static struct platform_driver smmu_pmu_driver = {
 	.driver = {
 		.name = "arm-smmu-v3-pmcg",
 		.of_match_table	= of_match_ptr(smmu_pmu_of_match),
+		.suppress_bind_attrs = true,
 	},
 	.probe = smmu_pmu_probe,
 	.remove = smmu_pmu_remove,
diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c
index 49b490925255..a6e0cccce3ba 100644
--- a/drivers/perf/arm_spe_pmu.c
+++ b/drivers/perf/arm_spe_pmu.c
@@ -1220,6 +1220,7 @@ static struct platform_driver arm_spe_pmu_driver = {
 	.driver	= {
 		.name		= DRVNAME,
 		.of_match_table	= of_match_ptr(arm_spe_pmu_of_match),
+		.suppress_bind_attrs = true,
 	},
 	.probe	= arm_spe_pmu_device_dt_probe,
 	.remove	= arm_spe_pmu_device_remove,
diff --git a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
index 6ad0823bcf23..9fc278620c28 100644
--- a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
@@ -383,6 +383,7 @@ static int hisi_ddrc_pmu_probe(struct platform_device *pdev)
 			      ddrc_pmu->sccl_id, ddrc_pmu->index_id);
 	ddrc_pmu->pmu = (struct pmu) {
 		.name		= name,
+		.module		= THIS_MODULE,
 		.task_ctx_nr	= perf_invalid_context,
 		.event_init	= hisi_uncore_pmu_event_init,
 		.pmu_enable	= hisi_uncore_pmu_enable,
@@ -421,6 +422,7 @@ static struct platform_driver hisi_ddrc_pmu_driver = {
 	.driver = {
 		.name = "hisi_ddrc_pmu",
 		.acpi_match_table = ACPI_PTR(hisi_ddrc_pmu_acpi_match),
+		.suppress_bind_attrs = true,
 	},
 	.probe = hisi_ddrc_pmu_probe,
 	.remove = hisi_ddrc_pmu_remove,
diff --git a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
index 4f2917f3e25e..2c2513de57d6 100644
--- a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
@@ -287,7 +287,7 @@ static struct attribute *hisi_hha_pmu_events_attr[] = {
 	HISI_PMU_EVENT_ATTR(rx_wbip,		0x05),
 	HISI_PMU_EVENT_ATTR(rx_wtistash,	0x11),
 	HISI_PMU_EVENT_ATTR(rd_ddr_64b,		0x1c),
-	HISI_PMU_EVENT_ATTR(wr_dr_64b,		0x1d),
+	HISI_PMU_EVENT_ATTR(wr_ddr_64b,		0x1d),
 	HISI_PMU_EVENT_ATTR(rd_ddr_128b,	0x1e),
 	HISI_PMU_EVENT_ATTR(wr_ddr_128b,	0x1f),
 	HISI_PMU_EVENT_ATTR(spill_num,		0x20),
@@ -394,6 +394,7 @@ static int hisi_hha_pmu_probe(struct platform_device *pdev)
 			      hha_pmu->sccl_id, hha_pmu->index_id);
 	hha_pmu->pmu = (struct pmu) {
 		.name		= name,
+		.module		= THIS_MODULE,
 		.task_ctx_nr	= perf_invalid_context,
 		.event_init	= hisi_uncore_pmu_event_init,
 		.pmu_enable	= hisi_uncore_pmu_enable,
@@ -432,6 +433,7 @@ static struct platform_driver hisi_hha_pmu_driver = {
 	.driver = {
 		.name = "hisi_hha_pmu",
 		.acpi_match_table = ACPI_PTR(hisi_hha_pmu_acpi_match),
+		.suppress_bind_attrs = true,
 	},
 	.probe = hisi_hha_pmu_probe,
 	.remove = hisi_hha_pmu_remove,
diff --git a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
index 9153e093f9df..0991fc96ecc1 100644
--- a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
@@ -35,7 +35,7 @@
 /* L3C has 8-counters */
 #define L3C_NR_COUNTERS		0x8
 
-#define L3C_PERF_CTRL_EN	0x20000
+#define L3C_PERF_CTRL_EN	0x10000
 #define L3C_EVTYPE_NONE		0xff
 
 /*
@@ -384,6 +384,7 @@ static int hisi_l3c_pmu_probe(struct platform_device *pdev)
 			      l3c_pmu->sccl_id, l3c_pmu->index_id);
 	l3c_pmu->pmu = (struct pmu) {
 		.name		= name,
+		.module		= THIS_MODULE,
 		.task_ctx_nr	= perf_invalid_context,
 		.event_init	= hisi_uncore_pmu_event_init,
 		.pmu_enable	= hisi_uncore_pmu_enable,
@@ -422,6 +423,7 @@ static struct platform_driver hisi_l3c_pmu_driver = {
 	.driver = {
 		.name = "hisi_l3c_pmu",
 		.acpi_match_table = ACPI_PTR(hisi_l3c_pmu_acpi_match),
+		.suppress_bind_attrs = true,
 	},
 	.probe = hisi_l3c_pmu_probe,
 	.remove = hisi_l3c_pmu_remove,
diff --git a/drivers/perf/qcom_l2_pmu.c b/drivers/perf/qcom_l2_pmu.c
index d06182fe14b8..3f7c02da5781 100644
--- a/drivers/perf/qcom_l2_pmu.c
+++ b/drivers/perf/qcom_l2_pmu.c
@@ -1032,6 +1032,7 @@ static struct platform_driver l2_cache_pmu_driver = {
 	.driver = {
 		.name = "qcom-l2cache-pmu",
 		.acpi_match_table = ACPI_PTR(l2_cache_pmu_acpi_match),
+		.suppress_bind_attrs = true,
 	},
 	.probe = l2_cache_pmu_probe,
 	.remove = l2_cache_pmu_remove,
diff --git a/drivers/perf/qcom_l3_pmu.c b/drivers/perf/qcom_l3_pmu.c
index 15b8c10c2b2b..fc4704cd7a27 100644
--- a/drivers/perf/qcom_l3_pmu.c
+++ b/drivers/perf/qcom_l3_pmu.c
@@ -814,6 +814,7 @@ static struct platform_driver qcom_l3_cache_pmu_driver = {
 	.driver = {
 		.name = "qcom-l3cache-pmu",
 		.acpi_match_table = ACPI_PTR(qcom_l3_cache_pmu_acpi_match),
+		.suppress_bind_attrs = true,
 	},
 	.probe = qcom_l3_cache_pmu_probe,
 };
diff --git a/drivers/perf/thunderx2_pmu.c b/drivers/perf/thunderx2_pmu.c
index 43d76c85da56..9e1c3c7eeba9 100644
--- a/drivers/perf/thunderx2_pmu.c
+++ b/drivers/perf/thunderx2_pmu.c
@@ -816,6 +816,7 @@ static struct platform_driver tx2_uncore_driver = {
 	.driver = {
 		.name		= "tx2-uncore-pmu",
 		.acpi_match_table = ACPI_PTR(tx2_uncore_acpi_match),
+		.suppress_bind_attrs = true,
 	},
 	.probe = tx2_uncore_probe,
 	.remove = tx2_uncore_remove,
diff --git a/drivers/perf/xgene_pmu.c b/drivers/perf/xgene_pmu.c
index 3259e2ebeb39..30cb581db6d4 100644
--- a/drivers/perf/xgene_pmu.c
+++ b/drivers/perf/xgene_pmu.c
@@ -1983,6 +1983,7 @@ static struct platform_driver xgene_pmu_driver = {
 		.name		= "xgene-pmu",
 		.of_match_table = xgene_pmu_of_match,
 		.acpi_match_table = ACPI_PTR(xgene_pmu_acpi_match),
+		.suppress_bind_attrs = true,
 	},
 };
 
diff --git a/drivers/phy/allwinner/phy-sun4i-usb.c b/drivers/phy/allwinner/phy-sun4i-usb.c
index 856927382248..e5842e48a5e0 100644
--- a/drivers/phy/allwinner/phy-sun4i-usb.c
+++ b/drivers/phy/allwinner/phy-sun4i-usb.c
@@ -545,13 +545,14 @@ static void sun4i_usb_phy0_id_vbus_det_scan(struct work_struct *work)
 	struct sun4i_usb_phy_data *data =
 		container_of(work, struct sun4i_usb_phy_data, detect.work);
 	struct phy *phy0 = data->phys[0].phy;
-	struct sun4i_usb_phy *phy = phy_get_drvdata(phy0);
+	struct sun4i_usb_phy *phy;
 	bool force_session_end, id_notify = false, vbus_notify = false;
 	int id_det, vbus_det;
 
-	if (phy0 == NULL)
+	if (!phy0)
 		return;
 
+	phy = phy_get_drvdata(phy0);
 	id_det = sun4i_usb_phy0_get_id_det(data);
 	vbus_det = sun4i_usb_phy0_get_vbus_det(data);
 
diff --git a/drivers/phy/broadcom/phy-bcm-sr-usb.c b/drivers/phy/broadcom/phy-bcm-sr-usb.c
index fe6c58910e4c..7c7862b4f41f 100644
--- a/drivers/phy/broadcom/phy-bcm-sr-usb.c
+++ b/drivers/phy/broadcom/phy-bcm-sr-usb.c
@@ -16,8 +16,6 @@ enum bcm_usb_phy_version {
 };
 
 enum bcm_usb_phy_reg {
-	PLL_NDIV_FRAC,
-	PLL_NDIV_INT,
 	PLL_CTRL,
 	PHY_CTRL,
 	PHY_PLL_CTRL,
@@ -31,18 +29,11 @@ static const u8 bcm_usb_combo_phy_ss[] = {
 };
 
 static const u8 bcm_usb_combo_phy_hs[] = {
-	[PLL_NDIV_FRAC]	= 0x04,
-	[PLL_NDIV_INT]	= 0x08,
 	[PLL_CTRL]	= 0x0c,
 	[PHY_CTRL]	= 0x10,
 };
 
-#define HSPLL_NDIV_INT_VAL	0x13
-#define HSPLL_NDIV_FRAC_VAL	0x1005
-
 static const u8 bcm_usb_hs_phy[] = {
-	[PLL_NDIV_FRAC]	= 0x0,
-	[PLL_NDIV_INT]	= 0x4,
 	[PLL_CTRL]	= 0x8,
 	[PHY_CTRL]	= 0xc,
 };
@@ -52,7 +43,6 @@ enum pll_ctrl_bits {
 	SSPLL_SUSPEND_EN,
 	PLL_SEQ_START,
 	PLL_LOCK,
-	PLL_PDIV,
 };
 
 static const u8 u3pll_ctrl[] = {
@@ -66,29 +56,17 @@ static const u8 u3pll_ctrl[] = {
 #define HSPLL_PDIV_VAL		0x1
 
 static const u8 u2pll_ctrl[] = {
-	[PLL_PDIV]	= 1,
 	[PLL_RESETB]	= 5,
 	[PLL_LOCK]	= 6,
 };
 
 enum bcm_usb_phy_ctrl_bits {
 	CORERDY,
-	AFE_LDO_PWRDWNB,
-	AFE_PLL_PWRDWNB,
-	AFE_BG_PWRDWNB,
-	PHY_ISO,
 	PHY_RESETB,
 	PHY_PCTL,
 };
 
 #define PHY_PCTL_MASK	0xffff
-/*
- * 0x0806 of PCTL_VAL has below bits set
- * BIT-8 : refclk divider 1
- * BIT-3:2: device mode; mode is not effect
- * BIT-1: soft reset active low
- */
-#define HSPHY_PCTL_VAL	0x0806
 #define SSPHY_PCTL_VAL	0x0006
 
 static const u8 u3phy_ctrl[] = {
@@ -98,10 +76,6 @@ static const u8 u3phy_ctrl[] = {
 
 static const u8 u2phy_ctrl[] = {
 	[CORERDY]		= 0,
-	[AFE_LDO_PWRDWNB]	= 1,
-	[AFE_PLL_PWRDWNB]	= 2,
-	[AFE_BG_PWRDWNB]	= 3,
-	[PHY_ISO]		= 4,
 	[PHY_RESETB]		= 5,
 	[PHY_PCTL]		= 6,
 };
@@ -186,38 +160,13 @@ static int bcm_usb_hs_phy_init(struct bcm_usb_phy_cfg *phy_cfg)
 	int ret = 0;
 	void __iomem *regs = phy_cfg->regs;
 	const u8 *offset;
-	u32 rd_data;
 
 	offset = phy_cfg->offset;
 
-	writel(HSPLL_NDIV_INT_VAL, regs + offset[PLL_NDIV_INT]);
-	writel(HSPLL_NDIV_FRAC_VAL, regs + offset[PLL_NDIV_FRAC]);
-
-	rd_data = readl(regs + offset[PLL_CTRL]);
-	rd_data &= ~(HSPLL_PDIV_MASK << u2pll_ctrl[PLL_PDIV]);
-	rd_data |= (HSPLL_PDIV_VAL << u2pll_ctrl[PLL_PDIV]);
-	writel(rd_data, regs + offset[PLL_CTRL]);
-
-	/* Set Core Ready high */
-	bcm_usb_reg32_setbits(regs + offset[PHY_CTRL],
-			      BIT(u2phy_ctrl[CORERDY]));
-
-	/* Maximum timeout for Core Ready done */
-	msleep(30);
-
+	bcm_usb_reg32_clrbits(regs + offset[PLL_CTRL],
+			      BIT(u2pll_ctrl[PLL_RESETB]));
 	bcm_usb_reg32_setbits(regs + offset[PLL_CTRL],
 			      BIT(u2pll_ctrl[PLL_RESETB]));
-	bcm_usb_reg32_setbits(regs + offset[PHY_CTRL],
-			      BIT(u2phy_ctrl[PHY_RESETB]));
-
-
-	rd_data = readl(regs + offset[PHY_CTRL]);
-	rd_data &= ~(PHY_PCTL_MASK << u2phy_ctrl[PHY_PCTL]);
-	rd_data |= (HSPHY_PCTL_VAL << u2phy_ctrl[PHY_PCTL]);
-	writel(rd_data, regs + offset[PHY_CTRL]);
-
-	/* Maximum timeout for PLL reset done */
-	msleep(30);
 
 	ret = bcm_usb_pll_lock_check(regs + offset[PLL_CTRL],
 				     BIT(u2pll_ctrl[PLL_LOCK]));
diff --git a/drivers/phy/marvell/phy-armada38x-comphy.c b/drivers/phy/marvell/phy-armada38x-comphy.c
index 3e00bc679d4e..10169b2a5968 100644
--- a/drivers/phy/marvell/phy-armada38x-comphy.c
+++ b/drivers/phy/marvell/phy-armada38x-comphy.c
@@ -41,6 +41,7 @@ struct a38x_comphy_lane {
 
 struct a38x_comphy {
 	void __iomem *base;
+	void __iomem *conf;
 	struct device *dev;
 	struct a38x_comphy_lane lane[MAX_A38X_COMPHY];
 };
@@ -54,6 +55,21 @@ static const u8 gbe_mux[MAX_A38X_COMPHY][MAX_A38X_PORTS] = {
 	{ 0, 0, 3 },
 };
 
+static void a38x_set_conf(struct a38x_comphy_lane *lane, bool enable)
+{
+	struct a38x_comphy *priv = lane->priv;
+	u32 conf;
+
+	if (priv->conf) {
+		conf = readl_relaxed(priv->conf);
+		if (enable)
+			conf |= BIT(lane->port);
+		else
+			conf &= ~BIT(lane->port);
+		writel(conf, priv->conf);
+	}
+}
+
 static void a38x_comphy_set_reg(struct a38x_comphy_lane *lane,
 				unsigned int offset, u32 mask, u32 value)
 {
@@ -97,6 +113,7 @@ static int a38x_comphy_set_mode(struct phy *phy, enum phy_mode mode, int sub)
 {
 	struct a38x_comphy_lane *lane = phy_get_drvdata(phy);
 	unsigned int gen;
+	int ret;
 
 	if (mode != PHY_MODE_ETHERNET)
 		return -EINVAL;
@@ -115,13 +132,20 @@ static int a38x_comphy_set_mode(struct phy *phy, enum phy_mode mode, int sub)
 		return -EINVAL;
 	}
 
+	a38x_set_conf(lane, false);
+
 	a38x_comphy_set_speed(lane, gen, gen);
 
-	return a38x_comphy_poll(lane, COMPHY_STAT1,
-				COMPHY_STAT1_PLL_RDY_TX |
-				COMPHY_STAT1_PLL_RDY_RX,
-				COMPHY_STAT1_PLL_RDY_TX |
-				COMPHY_STAT1_PLL_RDY_RX);
+	ret = a38x_comphy_poll(lane, COMPHY_STAT1,
+			       COMPHY_STAT1_PLL_RDY_TX |
+			       COMPHY_STAT1_PLL_RDY_RX,
+			       COMPHY_STAT1_PLL_RDY_TX |
+			       COMPHY_STAT1_PLL_RDY_RX);
+
+	if (ret == 0)
+		a38x_set_conf(lane, true);
+
+	return ret;
 }
 
 static const struct phy_ops a38x_comphy_ops = {
@@ -174,14 +198,21 @@ static int a38x_comphy_probe(struct platform_device *pdev)
 	if (!priv)
 		return -ENOMEM;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	base = devm_ioremap_resource(&pdev->dev, res);
+	base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(base))
 		return PTR_ERR(base);
 
 	priv->dev = &pdev->dev;
 	priv->base = base;
 
+	/* Optional */
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "conf");
+	if (res) {
+		priv->conf = devm_ioremap_resource(&pdev->dev, res);
+		if (IS_ERR(priv->conf))
+			return PTR_ERR(priv->conf);
+	}
+
 	for_each_available_child_of_node(pdev->dev.of_node, child) {
 		struct phy *phy;
 		int ret;
diff --git a/drivers/phy/motorola/phy-cpcap-usb.c b/drivers/phy/motorola/phy-cpcap-usb.c
index 6601ad0dfb3a..593c77dbde2e 100644
--- a/drivers/phy/motorola/phy-cpcap-usb.c
+++ b/drivers/phy/motorola/phy-cpcap-usb.c
@@ -115,7 +115,7 @@ struct cpcap_usb_ints_state {
 enum cpcap_gpio_mode {
 	CPCAP_DM_DP,
 	CPCAP_MDM_RX_TX,
-	CPCAP_UNKNOWN,
+	CPCAP_UNKNOWN_DISABLED,	/* Seems to disable USB lines */
 	CPCAP_OTG_DM_DP,
 };
 
@@ -207,6 +207,19 @@ static int cpcap_phy_get_ints_state(struct cpcap_phy_ddata *ddata,
 static int cpcap_usb_set_uart_mode(struct cpcap_phy_ddata *ddata);
 static int cpcap_usb_set_usb_mode(struct cpcap_phy_ddata *ddata);
 
+static void cpcap_usb_try_musb_mailbox(struct cpcap_phy_ddata *ddata,
+				       enum musb_vbus_id_status status)
+{
+	int error;
+
+	error = musb_mailbox(status);
+	if (!error)
+		return;
+
+	dev_dbg(ddata->dev, "%s: musb_mailbox failed: %i\n",
+		__func__, error);
+}
+
 static void cpcap_usb_detect(struct work_struct *work)
 {
 	struct cpcap_phy_ddata *ddata;
@@ -226,9 +239,7 @@ static void cpcap_usb_detect(struct work_struct *work)
 		if (error)
 			goto out_err;
 
-		error = musb_mailbox(MUSB_ID_GROUND);
-		if (error)
-			goto out_err;
+		cpcap_usb_try_musb_mailbox(ddata, MUSB_ID_GROUND);
 
 		error = regmap_update_bits(ddata->reg, CPCAP_REG_USBC3,
 					   CPCAP_BIT_VBUSSTBY_EN,
@@ -255,9 +266,7 @@ static void cpcap_usb_detect(struct work_struct *work)
 			error = cpcap_usb_set_usb_mode(ddata);
 			if (error)
 				goto out_err;
-			error = musb_mailbox(MUSB_ID_GROUND);
-			if (error)
-				goto out_err;
+			cpcap_usb_try_musb_mailbox(ddata, MUSB_ID_GROUND);
 
 			return;
 		}
@@ -267,22 +276,18 @@ static void cpcap_usb_detect(struct work_struct *work)
 		error = cpcap_usb_set_usb_mode(ddata);
 		if (error)
 			goto out_err;
-		error = musb_mailbox(MUSB_VBUS_VALID);
-		if (error)
-			goto out_err;
+		cpcap_usb_try_musb_mailbox(ddata, MUSB_VBUS_VALID);
 
 		return;
 	}
 
+	cpcap_usb_try_musb_mailbox(ddata, MUSB_VBUS_OFF);
+
 	/* Default to debug UART mode */
 	error = cpcap_usb_set_uart_mode(ddata);
 	if (error)
 		goto out_err;
 
-	error = musb_mailbox(MUSB_VBUS_OFF);
-	if (error)
-		goto out_err;
-
 	dev_dbg(ddata->dev, "set UART mode\n");
 
 	return;
@@ -374,7 +379,8 @@ static int cpcap_usb_set_uart_mode(struct cpcap_phy_ddata *ddata)
 {
 	int error;
 
-	error = cpcap_usb_gpio_set_mode(ddata, CPCAP_DM_DP);
+	/* Disable lines to prevent glitches from waking up mdm6600 */
+	error = cpcap_usb_gpio_set_mode(ddata, CPCAP_UNKNOWN_DISABLED);
 	if (error)
 		goto out_err;
 
@@ -401,6 +407,11 @@ static int cpcap_usb_set_uart_mode(struct cpcap_phy_ddata *ddata)
 	if (error)
 		goto out_err;
 
+	/* Enable UART mode */
+	error = cpcap_usb_gpio_set_mode(ddata, CPCAP_DM_DP);
+	if (error)
+		goto out_err;
+
 	return 0;
 
 out_err:
@@ -413,7 +424,8 @@ static int cpcap_usb_set_usb_mode(struct cpcap_phy_ddata *ddata)
 {
 	int error;
 
-	error = cpcap_usb_gpio_set_mode(ddata, CPCAP_OTG_DM_DP);
+	/* Disable lines to prevent glitches from waking up mdm6600 */
+	error = cpcap_usb_gpio_set_mode(ddata, CPCAP_UNKNOWN_DISABLED);
 	if (error)
 		return error;
 
@@ -453,6 +465,11 @@ static int cpcap_usb_set_usb_mode(struct cpcap_phy_ddata *ddata)
 	if (error)
 		goto out_err;
 
+	/* Enable USB mode */
+	error = cpcap_usb_gpio_set_mode(ddata, CPCAP_OTG_DM_DP);
+	if (error)
+		goto out_err;
+
 	return 0;
 
 out_err:
@@ -647,9 +664,7 @@ static int cpcap_usb_phy_remove(struct platform_device *pdev)
 	if (error)
 		dev_err(ddata->dev, "could not set UART mode\n");
 
-	error = musb_mailbox(MUSB_VBUS_OFF);
-	if (error)
-		dev_err(ddata->dev, "could not set mailbox\n");
+	cpcap_usb_try_musb_mailbox(ddata, MUSB_VBUS_OFF);
 
 	usb_remove_phy(&ddata->phy);
 	cancel_delayed_work_sync(&ddata->detect_work);
diff --git a/drivers/phy/motorola/phy-mapphone-mdm6600.c b/drivers/phy/motorola/phy-mapphone-mdm6600.c
index ee184d5607bd..94a34cf75eb3 100644
--- a/drivers/phy/motorola/phy-mapphone-mdm6600.c
+++ b/drivers/phy/motorola/phy-mapphone-mdm6600.c
@@ -20,6 +20,7 @@
 
 #define PHY_MDM6600_PHY_DELAY_MS	4000	/* PHY enable 2.2s to 3.5s */
 #define PHY_MDM6600_ENABLED_DELAY_MS	8000	/* 8s more total for MDM6600 */
+#define PHY_MDM6600_WAKE_KICK_MS	600	/* time on after GPIO toggle */
 #define MDM6600_MODEM_IDLE_DELAY_MS	1000	/* modem after USB suspend */
 #define MDM6600_MODEM_WAKE_DELAY_MS	200	/* modem response after idle */
 
@@ -200,7 +201,7 @@ static void phy_mdm6600_status(struct work_struct *work)
 	struct phy_mdm6600 *ddata;
 	struct device *dev;
 	DECLARE_BITMAP(values, PHY_MDM6600_NR_STATUS_LINES);
-	int error, i, val = 0;
+	int error;
 
 	ddata = container_of(work, struct phy_mdm6600, status_work.work);
 	dev = ddata->dev;
@@ -212,16 +213,11 @@ static void phy_mdm6600_status(struct work_struct *work)
 	if (error)
 		return;
 
-	for (i = 0; i < PHY_MDM6600_NR_STATUS_LINES; i++) {
-		val |= test_bit(i, values) << i;
-		dev_dbg(ddata->dev, "XXX %s: i: %i values[i]: %i val: %i\n",
-			__func__, i, test_bit(i, values), val);
-	}
-	ddata->status = values[0];
+	ddata->status = values[0] & ((1 << PHY_MDM6600_NR_STATUS_LINES) - 1);
 
 	dev_info(dev, "modem status: %i %s\n",
 		 ddata->status,
-		 phy_mdm6600_status_name[ddata->status & 7]);
+		 phy_mdm6600_status_name[ddata->status]);
 	complete(&ddata->ack);
 }
 
@@ -248,10 +244,24 @@ static irqreturn_t phy_mdm6600_wakeirq_thread(int irq, void *data)
 {
 	struct phy_mdm6600 *ddata = data;
 	struct gpio_desc *mode_gpio1;
+	int error, wakeup;
 
 	mode_gpio1 = ddata->mode_gpios->desc[PHY_MDM6600_MODE1];
-	dev_dbg(ddata->dev, "OOB wake on mode_gpio1: %i\n",
-		gpiod_get_value(mode_gpio1));
+	wakeup = gpiod_get_value(mode_gpio1);
+	if (!wakeup)
+		return IRQ_NONE;
+
+	dev_dbg(ddata->dev, "OOB wake on mode_gpio1: %i\n", wakeup);
+	error = pm_runtime_get_sync(ddata->dev);
+	if (error < 0) {
+		pm_runtime_put_noidle(ddata->dev);
+
+		return IRQ_NONE;
+	}
+
+	/* Just wake-up and kick the autosuspend timer */
+	pm_runtime_mark_last_busy(ddata->dev);
+	pm_runtime_put_autosuspend(ddata->dev);
 
 	return IRQ_HANDLED;
 }
@@ -501,8 +511,14 @@ static void phy_mdm6600_modem_wake(struct work_struct *work)
 
 	ddata = container_of(work, struct phy_mdm6600, modem_wake_work.work);
 	phy_mdm6600_wake_modem(ddata);
+
+	/*
+	 * The modem does not always stay awake 1.2 seconds after toggling
+	 * the wake GPIO, and sometimes it idles after about some 600 ms
+	 * making writes time out.
+	 */
 	schedule_delayed_work(&ddata->modem_wake_work,
-			      msecs_to_jiffies(MDM6600_MODEM_IDLE_DELAY_MS));
+			      msecs_to_jiffies(PHY_MDM6600_WAKE_KICK_MS));
 }
 
 static int __maybe_unused phy_mdm6600_runtime_suspend(struct device *dev)
diff --git a/drivers/phy/qualcomm/phy-qcom-apq8064-sata.c b/drivers/phy/qualcomm/phy-qcom-apq8064-sata.c
index 42bc5150dd92..febe0aef68d4 100644
--- a/drivers/phy/qualcomm/phy-qcom-apq8064-sata.c
+++ b/drivers/phy/qualcomm/phy-qcom-apq8064-sata.c
@@ -80,7 +80,7 @@ static int read_poll_timeout(void __iomem *addr, u32 mask)
 		if (readl_relaxed(addr) & mask)
 			return 0;
 
-		 usleep_range(DELAY_INTERVAL_US, DELAY_INTERVAL_US + 50);
+		usleep_range(DELAY_INTERVAL_US, DELAY_INTERVAL_US + 50);
 	} while (!time_after(jiffies, timeout));
 
 	return (readl_relaxed(addr) & mask) ? 0 : -ETIMEDOUT;
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp.c b/drivers/phy/qualcomm/phy-qcom-qmp.c
index 7e171d37bcd6..ac7dd9113784 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp.c
@@ -66,7 +66,7 @@
 /* QPHY_V3_PCS_MISC_CLAMP_ENABLE register bits */
 #define CLAMP_EN				BIT(0) /* enables i/o clamp_n */
 
-#define PHY_INIT_COMPLETE_TIMEOUT		1000
+#define PHY_INIT_COMPLETE_TIMEOUT		10000
 #define POWER_DOWN_DELAY_US_MIN			10
 #define POWER_DOWN_DELAY_US_MAX			11
 
diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
index 6fd1390fd06e..5087b7c44d55 100644
--- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c
+++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
@@ -111,6 +111,7 @@ struct rcar_gen3_chan {
 	struct work_struct work;
 	struct mutex lock;	/* protects rphys[...].powered */
 	enum usb_dr_mode dr_mode;
+	int irq;
 	bool extcon_host;
 	bool is_otg_channel;
 	bool uses_otg_pins;
@@ -389,12 +390,38 @@ static void rcar_gen3_init_otg(struct rcar_gen3_chan *ch)
 	rcar_gen3_device_recognition(ch);
 }
 
+static irqreturn_t rcar_gen3_phy_usb2_irq(int irq, void *_ch)
+{
+	struct rcar_gen3_chan *ch = _ch;
+	void __iomem *usb2_base = ch->base;
+	u32 status = readl(usb2_base + USB2_OBINTSTA);
+	irqreturn_t ret = IRQ_NONE;
+
+	if (status & USB2_OBINT_BITS) {
+		dev_vdbg(ch->dev, "%s: %08x\n", __func__, status);
+		writel(USB2_OBINT_BITS, usb2_base + USB2_OBINTSTA);
+		rcar_gen3_device_recognition(ch);
+		ret = IRQ_HANDLED;
+	}
+
+	return ret;
+}
+
 static int rcar_gen3_phy_usb2_init(struct phy *p)
 {
 	struct rcar_gen3_phy *rphy = phy_get_drvdata(p);
 	struct rcar_gen3_chan *channel = rphy->ch;
 	void __iomem *usb2_base = channel->base;
 	u32 val;
+	int ret;
+
+	if (!rcar_gen3_is_any_rphy_initialized(channel) && channel->irq >= 0) {
+		INIT_WORK(&channel->work, rcar_gen3_phy_usb2_work);
+		ret = request_irq(channel->irq, rcar_gen3_phy_usb2_irq,
+				  IRQF_SHARED, dev_name(channel->dev), channel);
+		if (ret < 0)
+			dev_err(channel->dev, "No irq handler (%d)\n", channel->irq);
+	}
 
 	/* Initialize USB2 part */
 	val = readl(usb2_base + USB2_INT_ENABLE);
@@ -433,6 +460,9 @@ static int rcar_gen3_phy_usb2_exit(struct phy *p)
 		val &= ~USB2_INT_ENABLE_UCOM_INTEN;
 	writel(val, usb2_base + USB2_INT_ENABLE);
 
+	if (channel->irq >= 0 && !rcar_gen3_is_any_rphy_initialized(channel))
+		free_irq(channel->irq, channel);
+
 	return 0;
 }
 
@@ -503,23 +533,6 @@ static const struct phy_ops rz_g1c_phy_usb2_ops = {
 	.owner		= THIS_MODULE,
 };
 
-static irqreturn_t rcar_gen3_phy_usb2_irq(int irq, void *_ch)
-{
-	struct rcar_gen3_chan *ch = _ch;
-	void __iomem *usb2_base = ch->base;
-	u32 status = readl(usb2_base + USB2_OBINTSTA);
-	irqreturn_t ret = IRQ_NONE;
-
-	if (status & USB2_OBINT_BITS) {
-		dev_vdbg(ch->dev, "%s: %08x\n", __func__, status);
-		writel(USB2_OBINT_BITS, usb2_base + USB2_OBINTSTA);
-		rcar_gen3_device_recognition(ch);
-		ret = IRQ_HANDLED;
-	}
-
-	return ret;
-}
-
 static const struct of_device_id rcar_gen3_phy_usb2_match_table[] = {
 	{
 		.compatible = "renesas,usb2-phy-r8a77470",
@@ -598,7 +611,7 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev)
 	struct phy_provider *provider;
 	struct resource *res;
 	const struct phy_ops *phy_usb2_ops;
-	int irq, ret = 0, i;
+	int ret = 0, i;
 
 	if (!dev->of_node) {
 		dev_err(dev, "This driver needs device tree\n");
@@ -614,16 +627,8 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev)
 	if (IS_ERR(channel->base))
 		return PTR_ERR(channel->base);
 
-	/* call request_irq for OTG */
-	irq = platform_get_irq(pdev, 0);
-	if (irq >= 0) {
-		INIT_WORK(&channel->work, rcar_gen3_phy_usb2_work);
-		irq = devm_request_irq(dev, irq, rcar_gen3_phy_usb2_irq,
-				       IRQF_SHARED, dev_name(dev), channel);
-		if (irq < 0)
-			dev_err(dev, "No irq handler (%d)\n", irq);
-	}
-
+	/* get irq number here and request_irq for OTG in phy_init */
+	channel->irq = platform_get_irq_optional(pdev, 0);
 	channel->dr_mode = rcar_gen3_get_dr_mode(dev->of_node);
 	if (channel->dr_mode != USB_DR_MODE_UNKNOWN) {
 		int ret;
diff --git a/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c b/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c
index b10a84cab4a7..93290d0f1e7e 100644
--- a/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c
+++ b/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c
@@ -603,6 +603,8 @@ static long inno_hdmi_phy_rk3228_clk_round_rate(struct clk_hw *hw,
 {
 	const struct pre_pll_config *cfg = pre_pll_cfg_table;
 
+	rate = (rate / 1000) * 1000;
+
 	for (; cfg->pixclock != 0; cfg++)
 		if (cfg->pixclock == rate && !cfg->fracdiv)
 			break;
@@ -755,6 +757,8 @@ static long inno_hdmi_phy_rk3328_clk_round_rate(struct clk_hw *hw,
 {
 	const struct pre_pll_config *cfg = pre_pll_cfg_table;
 
+	rate = (rate / 1000) * 1000;
+
 	for (; cfg->pixclock != 0; cfg++)
 		if (cfg->pixclock == rate)
 			break;
diff --git a/drivers/phy/samsung/phy-exynos5-usbdrd.c b/drivers/phy/samsung/phy-exynos5-usbdrd.c
index 646259bee909..f07edd80d2f3 100644
--- a/drivers/phy/samsung/phy-exynos5-usbdrd.c
+++ b/drivers/phy/samsung/phy-exynos5-usbdrd.c
@@ -714,7 +714,9 @@ static int exynos5_usbdrd_phy_calibrate(struct phy *phy)
 	struct phy_usb_instance *inst = phy_get_drvdata(phy);
 	struct exynos5_usbdrd_phy *phy_drd = to_usbdrd_phy(inst);
 
-	return exynos5420_usbdrd_phy_calibrate(phy_drd);
+	if (inst->phy_cfg->id == EXYNOS5_DRDPHY_UTMI)
+		return exynos5420_usbdrd_phy_calibrate(phy_drd);
+	return 0;
 }
 
 static const struct phy_ops exynos5_usbdrd_phy_ops = {
diff --git a/drivers/phy/socionext/phy-uniphier-usb3ss.c b/drivers/phy/socionext/phy-uniphier-usb3ss.c
index ec231e40ef2a..a7577e316baf 100644
--- a/drivers/phy/socionext/phy-uniphier-usb3ss.c
+++ b/drivers/phy/socionext/phy-uniphier-usb3ss.c
@@ -315,6 +315,10 @@ static const struct of_device_id uniphier_u3ssphy_match[] = {
 		.data = &uniphier_pro4_data,
 	},
 	{
+		.compatible = "socionext,uniphier-pro5-usb3-ssphy",
+		.data = &uniphier_pro4_data,
+	},
+	{
 		.compatible = "socionext,uniphier-pxs2-usb3-ssphy",
 		.data = &uniphier_pxs2_data,
 	},
diff --git a/drivers/phy/ti/phy-am654-serdes.c b/drivers/phy/ti/phy-am654-serdes.c
index d3769200cb9b..3b9eb639a740 100644
--- a/drivers/phy/ti/phy-am654-serdes.c
+++ b/drivers/phy/ti/phy-am654-serdes.c
@@ -405,6 +405,7 @@ static int serdes_am654_clk_register(struct serdes_am654 *am654_phy,
 	const __be32 *addr;
 	unsigned int reg;
 	struct clk *clk;
+	int ret = 0;
 
 	mux = devm_kzalloc(dev, sizeof(*mux), GFP_KERNEL);
 	if (!mux)
@@ -413,34 +414,40 @@ static int serdes_am654_clk_register(struct serdes_am654 *am654_phy,
 	init = &mux->clk_data;
 
 	regmap_node = of_parse_phandle(node, "ti,serdes-clk", 0);
-	of_node_put(regmap_node);
 	if (!regmap_node) {
 		dev_err(dev, "Fail to get serdes-clk node\n");
-		return -ENODEV;
+		ret = -ENODEV;
+		goto out_put_node;
 	}
 
 	regmap = syscon_node_to_regmap(regmap_node->parent);
 	if (IS_ERR(regmap)) {
 		dev_err(dev, "Fail to get Syscon regmap\n");
-		return PTR_ERR(regmap);
+		ret = PTR_ERR(regmap);
+		goto out_put_node;
 	}
 
 	num_parents = of_clk_get_parent_count(node);
 	if (num_parents < 2) {
 		dev_err(dev, "SERDES clock must have parents\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out_put_node;
 	}
 
 	parent_names = devm_kzalloc(dev, (sizeof(char *) * num_parents),
 				    GFP_KERNEL);
-	if (!parent_names)
-		return -ENOMEM;
+	if (!parent_names) {
+		ret = -ENOMEM;
+		goto out_put_node;
+	}
 
 	of_clk_parent_fill(node, parent_names, num_parents);
 
 	addr = of_get_address(regmap_node, 0, NULL, NULL);
-	if (!addr)
-		return -EINVAL;
+	if (!addr) {
+		ret = -EINVAL;
+		goto out_put_node;
+	}
 
 	reg = be32_to_cpu(*addr);
 
@@ -456,12 +463,16 @@ static int serdes_am654_clk_register(struct serdes_am654 *am654_phy,
 	mux->hw.init = init;
 
 	clk = devm_clk_register(dev, &mux->hw);
-	if (IS_ERR(clk))
-		return PTR_ERR(clk);
+	if (IS_ERR(clk)) {
+		ret = PTR_ERR(clk);
+		goto out_put_node;
+	}
 
 	am654_phy->clks[clock_num] = clk;
 
-	return 0;
+out_put_node:
+	of_node_put(regmap_node);
+	return ret;
 }
 
 static const struct of_device_id serdes_am654_id_table[] = {
diff --git a/drivers/phy/ti/phy-gmii-sel.c b/drivers/phy/ti/phy-gmii-sel.c
index a52c5bb35033..1c536fc03c83 100644
--- a/drivers/phy/ti/phy-gmii-sel.c
+++ b/drivers/phy/ti/phy-gmii-sel.c
@@ -69,31 +69,31 @@ static int phy_gmii_sel_mode(struct phy *phy, enum phy_mode mode, int submode)
 		break;
 
 	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
 		gmii_sel_mode = AM33XX_GMII_SEL_MODE_RGMII;
 		break;
 
 	case PHY_INTERFACE_MODE_RGMII_ID:
-	case PHY_INTERFACE_MODE_RGMII_RXID:
 	case PHY_INTERFACE_MODE_RGMII_TXID:
 		gmii_sel_mode = AM33XX_GMII_SEL_MODE_RGMII;
 		rgmii_id = 1;
 		break;
 
 	case PHY_INTERFACE_MODE_MII:
-		mode = AM33XX_GMII_SEL_MODE_MII;
+	case PHY_INTERFACE_MODE_GMII:
+		gmii_sel_mode = AM33XX_GMII_SEL_MODE_MII;
 		break;
 
 	default:
-		dev_warn(dev,
-			 "port%u: unsupported mode: \"%s\". Defaulting to MII.\n",
-			 if_phy->id, phy_modes(rgmii_id));
+		dev_warn(dev, "port%u: unsupported mode: \"%s\"\n",
+			 if_phy->id, phy_modes(submode));
 		return -EINVAL;
 	}
 
 	if_phy->phy_if_mode = submode;
 
 	dev_dbg(dev, "%s id:%u mode:%u rgmii_id:%d rmii_clk_ext:%d\n",
-		__func__, if_phy->id, mode, rgmii_id,
+		__func__, if_phy->id, submode, rgmii_id,
 		if_phy->rmii_clock_external);
 
 	regfield = if_phy->fields[PHY_GMII_SEL_PORT_MODE];
diff --git a/drivers/pinctrl/cirrus/Kconfig b/drivers/pinctrl/cirrus/Kconfig
index e546a6b75b4d..288838fd26dc 100644
--- a/drivers/pinctrl/cirrus/Kconfig
+++ b/drivers/pinctrl/cirrus/Kconfig
@@ -2,6 +2,7 @@
 config PINCTRL_LOCHNAGAR
 	tristate "Cirrus Logic Lochnagar pinctrl driver"
 	depends on MFD_LOCHNAGAR
+	select GPIOLIB
 	select PINMUX
 	select PINCONF
 	select GENERIC_PINCONF
diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index a64849a9d1b0..9807ff04c649 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -2007,7 +2007,6 @@ static int pinctrl_claim_hogs(struct pinctrl_dev *pctldev)
 		return PTR_ERR(pctldev->p);
 	}
 
-	kref_get(&pctldev->p->users);
 	pctldev->hog_default =
 		pinctrl_lookup_state(pctldev->p, PINCTRL_STATE_DEFAULT);
 	if (IS_ERR(pctldev->hog_default)) {
diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c
index 83ff9532bae6..c51773383bdc 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx.c
@@ -767,16 +767,6 @@ static int imx_pinctrl_probe_dt(struct platform_device *pdev,
 	return 0;
 }
 
-/*
- * imx_free_resources() - free memory used by this driver
- * @info: info driver instance
- */
-static void imx_free_resources(struct imx_pinctrl *ipctl)
-{
-	if (ipctl->pctl)
-		pinctrl_unregister(ipctl->pctl);
-}
-
 int imx_pinctrl_probe(struct platform_device *pdev,
 		      const struct imx_pinctrl_soc_info *info)
 {
@@ -867,23 +857,18 @@ int imx_pinctrl_probe(struct platform_device *pdev,
 					     &ipctl->pctl);
 	if (ret) {
 		dev_err(&pdev->dev, "could not register IMX pinctrl driver\n");
-		goto free;
+		return ret;
 	}
 
 	ret = imx_pinctrl_probe_dt(pdev, ipctl);
 	if (ret) {
 		dev_err(&pdev->dev, "fail to probe dt properties\n");
-		goto free;
+		return ret;
 	}
 
 	dev_info(&pdev->dev, "initialized IMX pinctrl driver\n");
 
 	return pinctrl_enable(ipctl->pctl);
-
-free:
-	imx_free_resources(ipctl);
-
-	return ret;
 }
 
 static int __maybe_unused imx_pinctrl_suspend(struct device *dev)
diff --git a/drivers/pinctrl/freescale/pinctrl-imx1-core.c b/drivers/pinctrl/freescale/pinctrl-imx1-core.c
index 7e29e3fecdb2..5bb183c0ce31 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx1-core.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx1-core.c
@@ -638,7 +638,6 @@ int imx1_pinctrl_core_probe(struct platform_device *pdev,
 
 	ret = of_platform_populate(pdev->dev.of_node, NULL, NULL, &pdev->dev);
 	if (ret) {
-		pinctrl_unregister(ipctl->pctl);
 		dev_err(&pdev->dev, "Failed to populate subdevices\n");
 		return ret;
 	}
diff --git a/drivers/pinctrl/freescale/pinctrl-scu.c b/drivers/pinctrl/freescale/pinctrl-scu.c
index 73bf1d9f9cc6..23cf04bdfc55 100644
--- a/drivers/pinctrl/freescale/pinctrl-scu.c
+++ b/drivers/pinctrl/freescale/pinctrl-scu.c
@@ -23,12 +23,12 @@ struct imx_sc_msg_req_pad_set {
 	struct imx_sc_rpc_msg hdr;
 	u32 val;
 	u16 pad;
-} __packed;
+} __packed __aligned(4);
 
 struct imx_sc_msg_req_pad_get {
 	struct imx_sc_rpc_msg hdr;
 	u16 pad;
-} __packed;
+} __packed __aligned(4);
 
 struct imx_sc_msg_resp_pad_get {
 	struct imx_sc_rpc_msg hdr;
diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index e1cd1d44fdde..9d277267db6e 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -951,7 +951,13 @@ static void byt_gpio_clear_triggering(struct byt_gpio *vg, unsigned int offset)
 
 	raw_spin_lock_irqsave(&byt_lock, flags);
 	value = readl(reg);
-	value &= ~(BYT_TRIG_POS | BYT_TRIG_NEG | BYT_TRIG_LVL);
+
+	/* Do not clear direct-irq enabled IRQs (from gpio_disable_free) */
+	if (value & BYT_DIRECT_IRQ_EN)
+		/* nothing to do */ ;
+	else
+		value &= ~(BYT_TRIG_POS | BYT_TRIG_NEG | BYT_TRIG_LVL);
+
 	writel(value, reg);
 	raw_spin_unlock_irqrestore(&byt_lock, flags);
 }
@@ -1490,6 +1496,7 @@ static const struct gpio_chip byt_gpio_chip = {
 	.direction_output	= byt_gpio_direction_output,
 	.get			= byt_gpio_get,
 	.set			= byt_gpio_set,
+	.set_config		= gpiochip_generic_config,
 	.dbg_show		= byt_gpio_dbg_show,
 };
 
diff --git a/drivers/pinctrl/intel/pinctrl-broxton.c b/drivers/pinctrl/intel/pinctrl-broxton.c
index e2d4505d6747..2be7e414f803 100644
--- a/drivers/pinctrl/intel/pinctrl-broxton.c
+++ b/drivers/pinctrl/intel/pinctrl-broxton.c
@@ -15,8 +15,9 @@
 #include "pinctrl-intel.h"
 
 #define BXT_PAD_OWN	0x020
-#define BXT_HOSTSW_OWN	0x080
 #define BXT_PADCFGLOCK	0x060
+#define BXT_HOSTSW_OWN	0x080
+#define BXT_GPI_IS	0x100
 #define BXT_GPI_IE	0x110
 
 #define BXT_COMMUNITY(s, e)				\
@@ -24,6 +25,7 @@
 		.padown_offset = BXT_PAD_OWN,		\
 		.padcfglock_offset = BXT_PADCFGLOCK,	\
 		.hostown_offset = BXT_HOSTSW_OWN,	\
+		.is_offset = BXT_GPI_IS,		\
 		.ie_offset = BXT_GPI_IE,		\
 		.gpp_size = 32,                         \
 		.pin_base = (s),			\
diff --git a/drivers/pinctrl/intel/pinctrl-cannonlake.c b/drivers/pinctrl/intel/pinctrl-cannonlake.c
index 08024b065033..f51b27bbf9f1 100644
--- a/drivers/pinctrl/intel/pinctrl-cannonlake.c
+++ b/drivers/pinctrl/intel/pinctrl-cannonlake.c
@@ -19,6 +19,7 @@
 #define CNL_PADCFGLOCK		0x080
 #define CNL_LP_HOSTSW_OWN	0x0b0
 #define CNL_H_HOSTSW_OWN	0x0c0
+#define CNL_GPI_IS		0x100
 #define CNL_GPI_IE		0x120
 
 #define CNL_GPP(r, s, e, g)				\
@@ -37,6 +38,7 @@
 		.padown_offset = CNL_PAD_OWN,		\
 		.padcfglock_offset = CNL_PADCFGLOCK,	\
 		.hostown_offset = (o),			\
+		.is_offset = CNL_GPI_IS,		\
 		.ie_offset = CNL_GPI_IE,		\
 		.pin_base = (s),			\
 		.npins = ((e) - (s) + 1),		\
diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c
index e26e356bbe8c..33fdcd3bcf72 100644
--- a/drivers/pinctrl/intel/pinctrl-cherryview.c
+++ b/drivers/pinctrl/intel/pinctrl-cherryview.c
@@ -1474,11 +1474,15 @@ static void chv_gpio_irq_handler(struct irq_desc *desc)
 	struct chv_pinctrl *pctrl = gpiochip_get_data(gc);
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	unsigned long pending;
+	unsigned long flags;
 	u32 intr_line;
 
 	chained_irq_enter(chip, desc);
 
+	raw_spin_lock_irqsave(&chv_lock, flags);
 	pending = readl(pctrl->regs + CHV_INTSTAT);
+	raw_spin_unlock_irqrestore(&chv_lock, flags);
+
 	for_each_set_bit(intr_line, &pending, pctrl->community->nirqs) {
 		unsigned irq, offset;
 
@@ -1663,7 +1667,6 @@ static int chv_pinctrl_probe(struct platform_device *pdev)
 {
 	struct chv_pinctrl *pctrl;
 	struct acpi_device *adev;
-	struct resource *res;
 	acpi_status status;
 	int ret, irq, i;
 
@@ -1693,8 +1696,7 @@ static int chv_pinctrl_probe(struct platform_device *pdev)
 		return -ENOMEM;
 #endif
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	pctrl->regs = devm_ioremap_resource(&pdev->dev, res);
+	pctrl->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(pctrl->regs))
 		return PTR_ERR(pctrl->regs);
 
diff --git a/drivers/pinctrl/intel/pinctrl-denverton.c b/drivers/pinctrl/intel/pinctrl-denverton.c
index 3a4932b557b4..fde83cd4aac5 100644
--- a/drivers/pinctrl/intel/pinctrl-denverton.c
+++ b/drivers/pinctrl/intel/pinctrl-denverton.c
@@ -15,8 +15,9 @@
 #include "pinctrl-intel.h"
 
 #define DNV_PAD_OWN	0x020
-#define DNV_HOSTSW_OWN	0x0C0
 #define DNV_PADCFGLOCK	0x090
+#define DNV_HOSTSW_OWN	0x0C0
+#define DNV_GPI_IS	0x100
 #define DNV_GPI_IE	0x120
 
 #define DNV_GPP(n, s, e)				\
@@ -32,6 +33,7 @@
 		.padown_offset = DNV_PAD_OWN,		\
 		.padcfglock_offset = DNV_PADCFGLOCK,	\
 		.hostown_offset = DNV_HOSTSW_OWN,	\
+		.is_offset = DNV_GPI_IS,		\
 		.ie_offset = DNV_GPI_IE,		\
 		.pin_base = (s),			\
 		.npins = ((e) - (s) + 1),		\
diff --git a/drivers/pinctrl/intel/pinctrl-geminilake.c b/drivers/pinctrl/intel/pinctrl-geminilake.c
index 331b8fd54d88..df02028b40f3 100644
--- a/drivers/pinctrl/intel/pinctrl-geminilake.c
+++ b/drivers/pinctrl/intel/pinctrl-geminilake.c
@@ -17,6 +17,7 @@
 #define GLK_PAD_OWN	0x020
 #define GLK_PADCFGLOCK	0x080
 #define GLK_HOSTSW_OWN	0x0b0
+#define GLK_GPI_IS	0x100
 #define GLK_GPI_IE	0x110
 
 #define GLK_COMMUNITY(s, e)				\
@@ -24,6 +25,7 @@
 		.padown_offset = GLK_PAD_OWN,		\
 		.padcfglock_offset = GLK_PADCFGLOCK,	\
 		.hostown_offset = GLK_HOSTSW_OWN,	\
+		.is_offset = GLK_GPI_IS,		\
 		.ie_offset = GLK_GPI_IE,		\
 		.gpp_size = 32,                         \
 		.pin_base = (s),			\
diff --git a/drivers/pinctrl/intel/pinctrl-icelake.c b/drivers/pinctrl/intel/pinctrl-icelake.c
index 5f2f5c61ad41..6489e9bbb61f 100644
--- a/drivers/pinctrl/intel/pinctrl-icelake.c
+++ b/drivers/pinctrl/intel/pinctrl-icelake.c
@@ -18,6 +18,7 @@
 #define ICL_PAD_OWN	0x020
 #define ICL_PADCFGLOCK	0x080
 #define ICL_HOSTSW_OWN	0x0b0
+#define ICL_GPI_IS	0x100
 #define ICL_GPI_IE	0x110
 
 #define ICL_GPP(r, s, e, g)				\
@@ -36,6 +37,7 @@
 		.padown_offset = ICL_PAD_OWN,		\
 		.padcfglock_offset = ICL_PADCFGLOCK,	\
 		.hostown_offset = ICL_HOSTSW_OWN,	\
+		.is_offset = ICL_GPI_IS,		\
 		.ie_offset = ICL_GPI_IE,		\
 		.pin_base = (s),			\
 		.npins = ((e) - (s) + 1),		\
diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index 8fb6c9668c37..1a743414e383 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -29,7 +29,6 @@
 #define REVID_MASK			GENMASK(31, 16)
 
 #define PADBAR				0x00c
-#define GPI_IS				0x100
 
 #define PADOWN_BITS			4
 #define PADOWN_SHIFT(p)			((p) % 8 * PADOWN_BITS)
@@ -1365,9 +1364,6 @@ static int intel_pinctrl_probe(struct platform_device *pdev,
 		community->regs = regs;
 		community->pad_regs = regs + padbar;
 
-		if (!community->is_offset)
-			community->is_offset = GPI_IS;
-
 		ret = intel_pinctrl_add_padgroups(pctrl, community);
 		if (ret)
 			return ret;
diff --git a/drivers/pinctrl/intel/pinctrl-intel.h b/drivers/pinctrl/intel/pinctrl-intel.h
index a8e958f1dcf5..f0234ca154a0 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.h
+++ b/drivers/pinctrl/intel/pinctrl-intel.h
@@ -75,8 +75,7 @@ struct intel_padgroup {
  * @hostown_offset: Register offset of HOSTSW_OWN from @regs. If %0 then it
  *                  is assumed that the host owns the pin (rather than
  *                  ACPI).
- * @is_offset: Register offset of GPI_IS from @regs. If %0 then uses the
- *             default (%0x100).
+ * @is_offset: Register offset of GPI_IS from @regs.
  * @ie_offset: Register offset of GPI_IE from @regs.
  * @pin_base: Starting pin of pins in this community
  * @gpp_size: Maximum number of pads in each group, such as PADCFGLOCK,
diff --git a/drivers/pinctrl/intel/pinctrl-lewisburg.c b/drivers/pinctrl/intel/pinctrl-lewisburg.c
index 03b04c7ae9e8..7fdf4257df1e 100644
--- a/drivers/pinctrl/intel/pinctrl-lewisburg.c
+++ b/drivers/pinctrl/intel/pinctrl-lewisburg.c
@@ -17,6 +17,7 @@
 #define LBG_PAD_OWN	0x020
 #define LBG_PADCFGLOCK	0x060
 #define LBG_HOSTSW_OWN	0x080
+#define LBG_GPI_IS	0x100
 #define LBG_GPI_IE	0x110
 
 #define LBG_COMMUNITY(b, s, e)				\
@@ -25,12 +26,14 @@
 		.padown_offset = LBG_PAD_OWN,		\
 		.padcfglock_offset = LBG_PADCFGLOCK,	\
 		.hostown_offset = LBG_HOSTSW_OWN,	\
+		.is_offset = LBG_GPI_IS,		\
 		.ie_offset = LBG_GPI_IE,		\
 		.gpp_size = 24,				\
 		.pin_base = (s),			\
 		.npins = ((e) - (s) + 1),		\
 	}
 
+/* Lewisburg */
 static const struct pinctrl_pin_desc lbg_pins[] = {
 	/* GPP_A */
 	PINCTRL_PIN(0, "RCINB"),
@@ -70,7 +73,7 @@ static const struct pinctrl_pin_desc lbg_pins[] = {
 	PINCTRL_PIN(33, "SRCCLKREQB_4"),
 	PINCTRL_PIN(34, "SRCCLKREQB_5"),
 	PINCTRL_PIN(35, "GPP_B_11"),
-	PINCTRL_PIN(36, "GLB_RST_WARN_N"),
+	PINCTRL_PIN(36, "SLP_S0B"),
 	PINCTRL_PIN(37, "PLTRSTB"),
 	PINCTRL_PIN(38, "SPKR"),
 	PINCTRL_PIN(39, "GPP_B_15"),
@@ -183,96 +186,96 @@ static const struct pinctrl_pin_desc lbg_pins[] = {
 	PINCTRL_PIN(141, "GBE_PCI_DIS"),
 	PINCTRL_PIN(142, "GBE_LAN_DIS"),
 	PINCTRL_PIN(143, "GPP_I_10"),
-	PINCTRL_PIN(144, "GPIO_RCOMP_3P3"),
 	/* GPP_J */
-	PINCTRL_PIN(145, "GBE_LED_0_0"),
-	PINCTRL_PIN(146, "GBE_LED_0_1"),
-	PINCTRL_PIN(147, "GBE_LED_1_0"),
-	PINCTRL_PIN(148, "GBE_LED_1_1"),
-	PINCTRL_PIN(149, "GBE_LED_2_0"),
-	PINCTRL_PIN(150, "GBE_LED_2_1"),
-	PINCTRL_PIN(151, "GBE_LED_3_0"),
-	PINCTRL_PIN(152, "GBE_LED_3_1"),
-	PINCTRL_PIN(153, "GBE_SCL_0"),
-	PINCTRL_PIN(154, "GBE_SDA_0"),
-	PINCTRL_PIN(155, "GBE_SCL_1"),
-	PINCTRL_PIN(156, "GBE_SDA_1"),
-	PINCTRL_PIN(157, "GBE_SCL_2"),
-	PINCTRL_PIN(158, "GBE_SDA_2"),
-	PINCTRL_PIN(159, "GBE_SCL_3"),
-	PINCTRL_PIN(160, "GBE_SDA_3"),
-	PINCTRL_PIN(161, "GBE_SDP_0_0"),
-	PINCTRL_PIN(162, "GBE_SDP_0_1"),
-	PINCTRL_PIN(163, "GBE_SDP_1_0"),
-	PINCTRL_PIN(164, "GBE_SDP_1_1"),
-	PINCTRL_PIN(165, "GBE_SDP_2_0"),
-	PINCTRL_PIN(166, "GBE_SDP_2_1"),
-	PINCTRL_PIN(167, "GBE_SDP_3_0"),
-	PINCTRL_PIN(168, "GBE_SDP_3_1"),
+	PINCTRL_PIN(144, "GBE_LED_0_0"),
+	PINCTRL_PIN(145, "GBE_LED_0_1"),
+	PINCTRL_PIN(146, "GBE_LED_1_0"),
+	PINCTRL_PIN(147, "GBE_LED_1_1"),
+	PINCTRL_PIN(148, "GBE_LED_2_0"),
+	PINCTRL_PIN(149, "GBE_LED_2_1"),
+	PINCTRL_PIN(150, "GBE_LED_3_0"),
+	PINCTRL_PIN(151, "GBE_LED_3_1"),
+	PINCTRL_PIN(152, "GBE_SCL_0"),
+	PINCTRL_PIN(153, "GBE_SDA_0"),
+	PINCTRL_PIN(154, "GBE_SCL_1"),
+	PINCTRL_PIN(155, "GBE_SDA_1"),
+	PINCTRL_PIN(156, "GBE_SCL_2"),
+	PINCTRL_PIN(157, "GBE_SDA_2"),
+	PINCTRL_PIN(158, "GBE_SCL_3"),
+	PINCTRL_PIN(159, "GBE_SDA_3"),
+	PINCTRL_PIN(160, "GBE_SDP_0_0"),
+	PINCTRL_PIN(161, "GBE_SDP_0_1"),
+	PINCTRL_PIN(162, "GBE_SDP_1_0"),
+	PINCTRL_PIN(163, "GBE_SDP_1_1"),
+	PINCTRL_PIN(164, "GBE_SDP_2_0"),
+	PINCTRL_PIN(165, "GBE_SDP_2_1"),
+	PINCTRL_PIN(166, "GBE_SDP_3_0"),
+	PINCTRL_PIN(167, "GBE_SDP_3_1"),
 	/* GPP_K */
-	PINCTRL_PIN(169, "GBE_RMIICLK"),
-	PINCTRL_PIN(170, "GBE_RMII_TXD_0"),
-	PINCTRL_PIN(171, "GBE_RMII_TXD_1"),
+	PINCTRL_PIN(168, "GBE_RMIICLK"),
+	PINCTRL_PIN(169, "GBE_RMII_RXD_0"),
+	PINCTRL_PIN(170, "GBE_RMII_RXD_1"),
+	PINCTRL_PIN(171, "GBE_RMII_CRS_DV"),
 	PINCTRL_PIN(172, "GBE_RMII_TX_EN"),
-	PINCTRL_PIN(173, "GBE_RMII_CRS_DV"),
-	PINCTRL_PIN(174, "GBE_RMII_RXD_0"),
-	PINCTRL_PIN(175, "GBE_RMII_RXD_1"),
-	PINCTRL_PIN(176, "GBE_RMII_RX_ER"),
-	PINCTRL_PIN(177, "GBE_RMII_ARBIN"),
-	PINCTRL_PIN(178, "GBE_RMII_ARB_OUT"),
-	PINCTRL_PIN(179, "PE_RST_N"),
-	PINCTRL_PIN(180, "GPIO_RCOMP_1P8_3P3"),
+	PINCTRL_PIN(173, "GBE_RMII_TXD_0"),
+	PINCTRL_PIN(174, "GBE_RMII_TXD_1"),
+	PINCTRL_PIN(175, "GBE_RMII_RX_ER"),
+	PINCTRL_PIN(176, "GBE_RMII_ARBIN"),
+	PINCTRL_PIN(177, "GBE_RMII_ARB_OUT"),
+	PINCTRL_PIN(178, "PE_RST_N"),
 	/* GPP_G */
-	PINCTRL_PIN(181, "FAN_TACH_0"),
-	PINCTRL_PIN(182, "FAN_TACH_1"),
-	PINCTRL_PIN(183, "FAN_TACH_2"),
-	PINCTRL_PIN(184, "FAN_TACH_3"),
-	PINCTRL_PIN(185, "FAN_TACH_4"),
-	PINCTRL_PIN(186, "FAN_TACH_5"),
-	PINCTRL_PIN(187, "FAN_TACH_6"),
-	PINCTRL_PIN(188, "FAN_TACH_7"),
-	PINCTRL_PIN(189, "FAN_PWM_0"),
-	PINCTRL_PIN(190, "FAN_PWM_1"),
-	PINCTRL_PIN(191, "FAN_PWM_2"),
-	PINCTRL_PIN(192, "FAN_PWM_3"),
-	PINCTRL_PIN(193, "GSXDOUT"),
-	PINCTRL_PIN(194, "GSXSLOAD"),
-	PINCTRL_PIN(195, "GSXDIN"),
-	PINCTRL_PIN(196, "GSXSRESETB"),
-	PINCTRL_PIN(197, "GSXCLK"),
-	PINCTRL_PIN(198, "ADR_COMPLETE"),
-	PINCTRL_PIN(199, "NMIB"),
-	PINCTRL_PIN(200, "SMIB"),
-	PINCTRL_PIN(201, "SSATA_DEVSLP_0"),
-	PINCTRL_PIN(202, "SSATA_DEVSLP_1"),
-	PINCTRL_PIN(203, "SSATA_DEVSLP_2"),
-	PINCTRL_PIN(204, "SSATAXPCIE0_SSATAGP0"),
+	PINCTRL_PIN(179, "FAN_TACH_0"),
+	PINCTRL_PIN(180, "FAN_TACH_1"),
+	PINCTRL_PIN(181, "FAN_TACH_2"),
+	PINCTRL_PIN(182, "FAN_TACH_3"),
+	PINCTRL_PIN(183, "FAN_TACH_4"),
+	PINCTRL_PIN(184, "FAN_TACH_5"),
+	PINCTRL_PIN(185, "FAN_TACH_6"),
+	PINCTRL_PIN(186, "FAN_TACH_7"),
+	PINCTRL_PIN(187, "FAN_PWM_0"),
+	PINCTRL_PIN(188, "FAN_PWM_1"),
+	PINCTRL_PIN(189, "FAN_PWM_2"),
+	PINCTRL_PIN(190, "FAN_PWM_3"),
+	PINCTRL_PIN(191, "GSXDOUT"),
+	PINCTRL_PIN(192, "GSXSLOAD"),
+	PINCTRL_PIN(193, "GSXDIN"),
+	PINCTRL_PIN(194, "GSXSRESETB"),
+	PINCTRL_PIN(195, "GSXCLK"),
+	PINCTRL_PIN(196, "ADR_COMPLETE"),
+	PINCTRL_PIN(197, "NMIB"),
+	PINCTRL_PIN(198, "SMIB"),
+	PINCTRL_PIN(199, "SSATA_DEVSLP_0"),
+	PINCTRL_PIN(200, "SSATA_DEVSLP_1"),
+	PINCTRL_PIN(201, "SSATA_DEVSLP_2"),
+	PINCTRL_PIN(202, "SSATAXPCIE0_SSATAGP0"),
 	/* GPP_H */
-	PINCTRL_PIN(205, "SRCCLKREQB_6"),
-	PINCTRL_PIN(206, "SRCCLKREQB_7"),
-	PINCTRL_PIN(207, "SRCCLKREQB_8"),
-	PINCTRL_PIN(208, "SRCCLKREQB_9"),
-	PINCTRL_PIN(209, "SRCCLKREQB_10"),
-	PINCTRL_PIN(210, "SRCCLKREQB_11"),
-	PINCTRL_PIN(211, "SRCCLKREQB_12"),
-	PINCTRL_PIN(212, "SRCCLKREQB_13"),
-	PINCTRL_PIN(213, "SRCCLKREQB_14"),
-	PINCTRL_PIN(214, "SRCCLKREQB_15"),
-	PINCTRL_PIN(215, "SML2CLK"),
-	PINCTRL_PIN(216, "SML2DATA"),
-	PINCTRL_PIN(217, "SML2ALERTB"),
-	PINCTRL_PIN(218, "SML3CLK"),
-	PINCTRL_PIN(219, "SML3DATA"),
-	PINCTRL_PIN(220, "SML3ALERTB"),
-	PINCTRL_PIN(221, "SML4CLK"),
-	PINCTRL_PIN(222, "SML4DATA"),
-	PINCTRL_PIN(223, "SML4ALERTB"),
-	PINCTRL_PIN(224, "SSATAXPCIE1_SSATAGP1"),
-	PINCTRL_PIN(225, "SSATAXPCIE2_SSATAGP2"),
-	PINCTRL_PIN(226, "SSATAXPCIE3_SSATAGP3"),
-	PINCTRL_PIN(227, "SSATAXPCIE4_SSATAGP4"),
-	PINCTRL_PIN(228, "SSATAXPCIE5_SSATAGP5"),
+	PINCTRL_PIN(203, "SRCCLKREQB_6"),
+	PINCTRL_PIN(204, "SRCCLKREQB_7"),
+	PINCTRL_PIN(205, "SRCCLKREQB_8"),
+	PINCTRL_PIN(206, "SRCCLKREQB_9"),
+	PINCTRL_PIN(207, "SRCCLKREQB_10"),
+	PINCTRL_PIN(208, "SRCCLKREQB_11"),
+	PINCTRL_PIN(209, "SRCCLKREQB_12"),
+	PINCTRL_PIN(210, "SRCCLKREQB_13"),
+	PINCTRL_PIN(211, "SRCCLKREQB_14"),
+	PINCTRL_PIN(212, "SRCCLKREQB_15"),
+	PINCTRL_PIN(213, "SML2CLK"),
+	PINCTRL_PIN(214, "SML2DATA"),
+	PINCTRL_PIN(215, "SML2ALERTB"),
+	PINCTRL_PIN(216, "SML3CLK"),
+	PINCTRL_PIN(217, "SML3DATA"),
+	PINCTRL_PIN(218, "SML3ALERTB"),
+	PINCTRL_PIN(219, "SML4CLK"),
+	PINCTRL_PIN(220, "SML4DATA"),
+	PINCTRL_PIN(221, "SML4ALERTB"),
+	PINCTRL_PIN(222, "SSATAXPCIE1_SSATAGP1"),
+	PINCTRL_PIN(223, "SSATAXPCIE2_SSATAGP2"),
+	PINCTRL_PIN(224, "SSATAXPCIE3_SSATAGP3"),
+	PINCTRL_PIN(225, "SSATAXPCIE4_SSATAGP4"),
+	PINCTRL_PIN(226, "SSATAXPCIE5_SSATAGP5"),
 	/* GPP_L */
+	PINCTRL_PIN(227, "GPP_L_0"),
+	PINCTRL_PIN(228, "EC_CSME_INTR_OUT"),
 	PINCTRL_PIN(229, "VISA2CH0_D0"),
 	PINCTRL_PIN(230, "VISA2CH0_D1"),
 	PINCTRL_PIN(231, "VISA2CH0_D2"),
diff --git a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
index ccafeea4939c..7b7736abe9d8 100644
--- a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
+++ b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
@@ -15,17 +15,20 @@
 
 #include "pinctrl-intel.h"
 
-#define SPT_PAD_OWN	0x020
-#define SPT_PADCFGLOCK	0x0a0
-#define SPT_HOSTSW_OWN	0x0d0
-#define SPT_GPI_IE	0x120
+#define SPT_PAD_OWN		0x020
+#define SPT_H_PADCFGLOCK	0x090
+#define SPT_LP_PADCFGLOCK	0x0a0
+#define SPT_HOSTSW_OWN		0x0d0
+#define SPT_GPI_IS		0x100
+#define SPT_GPI_IE		0x120
 
 #define SPT_COMMUNITY(b, s, e)				\
 	{						\
 		.barno = (b),				\
 		.padown_offset = SPT_PAD_OWN,		\
-		.padcfglock_offset = SPT_PADCFGLOCK,	\
+		.padcfglock_offset = SPT_LP_PADCFGLOCK,	\
 		.hostown_offset = SPT_HOSTSW_OWN,	\
+		.is_offset = SPT_GPI_IS,		\
 		.ie_offset = SPT_GPI_IE,		\
 		.gpp_size = 24,				\
 		.gpp_num_padown_regs = 4,		\
@@ -45,8 +48,9 @@
 	{						\
 		.barno = (b),				\
 		.padown_offset = SPT_PAD_OWN,		\
-		.padcfglock_offset = SPT_PADCFGLOCK,	\
+		.padcfglock_offset = SPT_H_PADCFGLOCK,	\
 		.hostown_offset = SPT_HOSTSW_OWN,	\
+		.is_offset = SPT_GPI_IS,		\
 		.ie_offset = SPT_GPI_IE,		\
 		.pin_base = (s),			\
 		.npins = ((e) - (s) + 1),		\
diff --git a/drivers/pinctrl/meson/pinctrl-meson-gxl.c b/drivers/pinctrl/meson/pinctrl-meson-gxl.c
index 72c5373c8dc1..e8d1f3050487 100644
--- a/drivers/pinctrl/meson/pinctrl-meson-gxl.c
+++ b/drivers/pinctrl/meson/pinctrl-meson-gxl.c
@@ -147,8 +147,8 @@ static const unsigned int sdio_d0_pins[]	= { GPIOX_0 };
 static const unsigned int sdio_d1_pins[]	= { GPIOX_1 };
 static const unsigned int sdio_d2_pins[]	= { GPIOX_2 };
 static const unsigned int sdio_d3_pins[]	= { GPIOX_3 };
-static const unsigned int sdio_cmd_pins[]	= { GPIOX_4 };
-static const unsigned int sdio_clk_pins[]	= { GPIOX_5 };
+static const unsigned int sdio_clk_pins[]	= { GPIOX_4 };
+static const unsigned int sdio_cmd_pins[]	= { GPIOX_5 };
 static const unsigned int sdio_irq_pins[]	= { GPIOX_7 };
 
 static const unsigned int nand_ce0_pins[]	= { BOOT_8 };
diff --git a/drivers/pinctrl/pinctrl-amd.h b/drivers/pinctrl/pinctrl-amd.h
index 3e5760f1a715..d4a192df5fab 100644
--- a/drivers/pinctrl/pinctrl-amd.h
+++ b/drivers/pinctrl/pinctrl-amd.h
@@ -252,7 +252,7 @@ static const struct amd_pingroup kerncz_groups[] = {
 	{
 		.name = "uart0",
 		.pins = uart0_pins,
-		.npins = 9,
+		.npins = 5,
 	},
 	{
 		.name = "uart1",
diff --git a/drivers/pinctrl/pinctrl-ingenic.c b/drivers/pinctrl/pinctrl-ingenic.c
index c8ef3b91a730..0e95c247def6 100644
--- a/drivers/pinctrl/pinctrl-ingenic.c
+++ b/drivers/pinctrl/pinctrl-ingenic.c
@@ -873,9 +873,9 @@ static void ingenic_gpio_irq_ack(struct irq_data *irqd)
 		 */
 		high = ingenic_gpio_get_value(jzgc, irq);
 		if (high)
-			irq_set_type(jzgc, irq, IRQ_TYPE_EDGE_FALLING);
+			irq_set_type(jzgc, irq, IRQ_TYPE_LEVEL_LOW);
 		else
-			irq_set_type(jzgc, irq, IRQ_TYPE_EDGE_RISING);
+			irq_set_type(jzgc, irq, IRQ_TYPE_LEVEL_HIGH);
 	}
 
 	if (jzgc->jzpc->version >= ID_JZ4770)
@@ -911,7 +911,7 @@ static int ingenic_gpio_irq_set_type(struct irq_data *irqd, unsigned int type)
 		 */
 		bool high = ingenic_gpio_get_value(jzgc, irqd->hwirq);
 
-		type = high ? IRQ_TYPE_EDGE_FALLING : IRQ_TYPE_EDGE_RISING;
+		type = high ? IRQ_TYPE_LEVEL_LOW : IRQ_TYPE_LEVEL_HIGH;
 	}
 
 	irq_set_type(jzgc, irqd->hwirq, type);
diff --git a/drivers/pinctrl/pinctrl-ocelot.c b/drivers/pinctrl/pinctrl-ocelot.c
index fb76fb2e9ea5..0a951a75c82b 100644
--- a/drivers/pinctrl/pinctrl-ocelot.c
+++ b/drivers/pinctrl/pinctrl-ocelot.c
@@ -711,11 +711,12 @@ static void ocelot_irq_handler(struct irq_desc *desc)
 	struct irq_chip *parent_chip = irq_desc_get_chip(desc);
 	struct gpio_chip *chip = irq_desc_get_handler_data(desc);
 	struct ocelot_pinctrl *info = gpiochip_get_data(chip);
+	unsigned int id_reg = OCELOT_GPIO_INTR_IDENT * info->stride;
 	unsigned int reg = 0, irq, i;
 	unsigned long irqs;
 
 	for (i = 0; i < info->stride; i++) {
-		regmap_read(info->map, OCELOT_GPIO_INTR_IDENT + 4 * i, &reg);
+		regmap_read(info->map, id_reg + 4 * i, &reg);
 		if (!reg)
 			continue;
 
diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c
index 62a622159006..814cf20899e1 100644
--- a/drivers/pinctrl/pinctrl-rockchip.c
+++ b/drivers/pinctrl/pinctrl-rockchip.c
@@ -506,8 +506,8 @@ static int rockchip_dt_node_to_map(struct pinctrl_dev *pctldev,
 	}
 
 	map_num += grp->npins;
-	new_map = devm_kcalloc(pctldev->dev, map_num, sizeof(*new_map),
-								GFP_KERNEL);
+
+	new_map = kcalloc(map_num, sizeof(*new_map), GFP_KERNEL);
 	if (!new_map)
 		return -ENOMEM;
 
@@ -517,7 +517,7 @@ static int rockchip_dt_node_to_map(struct pinctrl_dev *pctldev,
 	/* create mux map */
 	parent = of_get_parent(np);
 	if (!parent) {
-		devm_kfree(pctldev->dev, new_map);
+		kfree(new_map);
 		return -EINVAL;
 	}
 	new_map[0].type = PIN_MAP_TYPE_MUX_GROUP;
@@ -544,6 +544,7 @@ static int rockchip_dt_node_to_map(struct pinctrl_dev *pctldev,
 static void rockchip_dt_free_map(struct pinctrl_dev *pctldev,
 				    struct pinctrl_map *map, unsigned num_maps)
 {
+	kfree(map);
 }
 
 static const struct pinctrl_ops rockchip_pctrl_ops = {
diff --git a/drivers/pinctrl/pinctrl-rza1.c b/drivers/pinctrl/pinctrl-rza1.c
index 021e37b7689e..ad65f9d57518 100644
--- a/drivers/pinctrl/pinctrl-rza1.c
+++ b/drivers/pinctrl/pinctrl-rza1.c
@@ -418,7 +418,7 @@ static const struct rza1_bidir_entry rza1l_bidir_entries[RZA1_NPORTS] = {
 };
 
 static const struct rza1_swio_entry rza1l_swio_entries[] = {
-	[0] = { ARRAY_SIZE(rza1h_swio_pins), rza1h_swio_pins },
+	[0] = { ARRAY_SIZE(rza1l_swio_pins), rza1l_swio_pins },
 };
 
 /* RZ/A1L (r7s72102x) pinmux flags table */
diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index 1e0614daee9b..a9d511982780 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -916,7 +916,7 @@ static int pcs_parse_pinconf(struct pcs_device *pcs, struct device_node *np,
 
 	/* If pinconf isn't supported, don't parse properties in below. */
 	if (!PCS_HAS_PINCONF)
-		return 0;
+		return -ENOTSUPP;
 
 	/* cacluate how much properties are supported in current node */
 	for (i = 0; i < ARRAY_SIZE(prop2); i++) {
@@ -928,7 +928,7 @@ static int pcs_parse_pinconf(struct pcs_device *pcs, struct device_node *np,
 			nconfs++;
 	}
 	if (!nconfs)
-		return 0;
+		return -ENOTSUPP;
 
 	func->conf = devm_kcalloc(pcs->dev,
 				  nconfs, sizeof(struct pcs_conf_vals),
@@ -1056,9 +1056,12 @@ static int pcs_parse_one_pinctrl_entry(struct pcs_device *pcs,
 
 	if (PCS_HAS_PINCONF && function) {
 		res = pcs_parse_pinconf(pcs, np, function, map);
-		if (res)
+		if (res == 0)
+			*num_maps = 2;
+		else if (res == -ENOTSUPP)
+			*num_maps = 1;
+		else
 			goto free_pingroups;
-		*num_maps = 2;
 	} else {
 		*num_maps = 1;
 	}
diff --git a/drivers/pinctrl/pinctrl-stmfx.c b/drivers/pinctrl/pinctrl-stmfx.c
index fe734135b0f2..0ca62a96a829 100644
--- a/drivers/pinctrl/pinctrl-stmfx.c
+++ b/drivers/pinctrl/pinctrl-stmfx.c
@@ -277,7 +277,7 @@ static int stmfx_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin,
 	struct pinctrl_gpio_range *range;
 	enum pin_config_param param;
 	u32 arg;
-	int dir, i, ret;
+	int i, ret;
 
 	range = pinctrl_find_gpio_range_from_pin_nolock(pctldev, pin);
 	if (!range) {
@@ -285,10 +285,6 @@ static int stmfx_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin,
 		return -EINVAL;
 	}
 
-	dir = stmfx_gpio_get_direction(&pctl->gpio_chip, pin);
-	if (dir < 0)
-		return dir;
-
 	for (i = 0; i < num_configs; i++) {
 		param = pinconf_to_config_param(configs[i]);
 		arg = pinconf_to_config_argument(configs[i]);
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index 6e319bcc2326..d1986da935dc 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -674,7 +674,7 @@ static void msm_gpio_update_dual_edge_pos(struct msm_pinctrl *pctrl,
 
 		pol = msm_readl_intr_cfg(pctrl, g);
 		pol ^= BIT(g->intr_polarity_bit);
-		msm_writel_intr_cfg(val, pctrl, g);
+		msm_writel_intr_cfg(pol, pctrl, g);
 
 		val2 = msm_readl_io(pctrl, g) & BIT(g->in_bit);
 		intstat = msm_readl_intr_status(pctrl, g);
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c
index 0599f5127b01..84501c785473 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.c
@@ -40,6 +40,8 @@ struct exynos_irq_chip {
 	u32 eint_pend;
 	u32 eint_wake_mask_value;
 	u32 eint_wake_mask_reg;
+	void (*set_eint_wakeup_mask)(struct samsung_pinctrl_drv_data *drvdata,
+				     struct exynos_irq_chip *irq_chip);
 };
 
 static inline struct exynos_irq_chip *to_exynos_irq_chip(struct irq_chip *chip)
@@ -265,6 +267,7 @@ struct exynos_eint_gpio_save {
 	u32 eint_con;
 	u32 eint_fltcon0;
 	u32 eint_fltcon1;
+	u32 eint_mask;
 };
 
 /*
@@ -342,6 +345,47 @@ static int exynos_wkup_irq_set_wake(struct irq_data *irqd, unsigned int on)
 	return 0;
 }
 
+static void
+exynos_pinctrl_set_eint_wakeup_mask(struct samsung_pinctrl_drv_data *drvdata,
+				    struct exynos_irq_chip *irq_chip)
+{
+	struct regmap *pmu_regs;
+
+	if (!drvdata->retention_ctrl || !drvdata->retention_ctrl->priv) {
+		dev_warn(drvdata->dev,
+			 "No retention data configured bank with external wakeup interrupt. Wake-up mask will not be set.\n");
+		return;
+	}
+
+	pmu_regs = drvdata->retention_ctrl->priv;
+	dev_info(drvdata->dev,
+		 "Setting external wakeup interrupt mask: 0x%x\n",
+		 irq_chip->eint_wake_mask_value);
+
+	regmap_write(pmu_regs, irq_chip->eint_wake_mask_reg,
+		     irq_chip->eint_wake_mask_value);
+}
+
+static void
+s5pv210_pinctrl_set_eint_wakeup_mask(struct samsung_pinctrl_drv_data *drvdata,
+				    struct exynos_irq_chip *irq_chip)
+
+{
+	void __iomem *clk_base;
+
+	if (!drvdata->retention_ctrl || !drvdata->retention_ctrl->priv) {
+		dev_warn(drvdata->dev,
+			 "No retention data configured bank with external wakeup interrupt. Wake-up mask will not be set.\n");
+		return;
+	}
+
+
+	clk_base = (void __iomem *) drvdata->retention_ctrl->priv;
+
+	__raw_writel(irq_chip->eint_wake_mask_value,
+		     clk_base + irq_chip->eint_wake_mask_reg);
+}
+
 /*
  * irq_chip for wakeup interrupts
  */
@@ -360,8 +404,9 @@ static const struct exynos_irq_chip s5pv210_wkup_irq_chip __initconst = {
 	.eint_mask = EXYNOS_WKUP_EMASK_OFFSET,
 	.eint_pend = EXYNOS_WKUP_EPEND_OFFSET,
 	.eint_wake_mask_value = EXYNOS_EINT_WAKEUP_MASK_DISABLED,
-	/* Only difference with exynos4210_wkup_irq_chip: */
+	/* Only differences with exynos4210_wkup_irq_chip: */
 	.eint_wake_mask_reg = S5PV210_EINT_WAKEUP_MASK,
+	.set_eint_wakeup_mask = s5pv210_pinctrl_set_eint_wakeup_mask,
 };
 
 static const struct exynos_irq_chip exynos4210_wkup_irq_chip __initconst = {
@@ -380,6 +425,7 @@ static const struct exynos_irq_chip exynos4210_wkup_irq_chip __initconst = {
 	.eint_pend = EXYNOS_WKUP_EPEND_OFFSET,
 	.eint_wake_mask_value = EXYNOS_EINT_WAKEUP_MASK_DISABLED,
 	.eint_wake_mask_reg = EXYNOS_EINT_WAKEUP_MASK,
+	.set_eint_wakeup_mask = exynos_pinctrl_set_eint_wakeup_mask,
 };
 
 static const struct exynos_irq_chip exynos7_wkup_irq_chip __initconst = {
@@ -398,6 +444,7 @@ static const struct exynos_irq_chip exynos7_wkup_irq_chip __initconst = {
 	.eint_pend = EXYNOS7_WKUP_EPEND_OFFSET,
 	.eint_wake_mask_value = EXYNOS_EINT_WAKEUP_MASK_DISABLED,
 	.eint_wake_mask_reg = EXYNOS5433_EINT_WAKEUP_MASK,
+	.set_eint_wakeup_mask = exynos_pinctrl_set_eint_wakeup_mask,
 };
 
 /* list of external wakeup controllers supported */
@@ -574,27 +621,6 @@ int exynos_eint_wkup_init(struct samsung_pinctrl_drv_data *d)
 	return 0;
 }
 
-static void
-exynos_pinctrl_set_eint_wakeup_mask(struct samsung_pinctrl_drv_data *drvdata,
-				    struct exynos_irq_chip *irq_chip)
-{
-	struct regmap *pmu_regs;
-
-	if (!drvdata->retention_ctrl || !drvdata->retention_ctrl->priv) {
-		dev_warn(drvdata->dev,
-			 "No retention data configured bank with external wakeup interrupt. Wake-up mask will not be set.\n");
-		return;
-	}
-
-	pmu_regs = drvdata->retention_ctrl->priv;
-	dev_info(drvdata->dev,
-		 "Setting external wakeup interrupt mask: 0x%x\n",
-		 irq_chip->eint_wake_mask_value);
-
-	regmap_write(pmu_regs, irq_chip->eint_wake_mask_reg,
-		     irq_chip->eint_wake_mask_value);
-}
-
 static void exynos_pinctrl_suspend_bank(
 				struct samsung_pinctrl_drv_data *drvdata,
 				struct samsung_pin_bank *bank)
@@ -608,10 +634,13 @@ static void exynos_pinctrl_suspend_bank(
 						+ 2 * bank->eint_offset);
 	save->eint_fltcon1 = readl(regs + EXYNOS_GPIO_EFLTCON_OFFSET
 						+ 2 * bank->eint_offset + 4);
+	save->eint_mask = readl(regs + bank->irq_chip->eint_mask
+						+ bank->eint_offset);
 
 	pr_debug("%s: save     con %#010x\n", bank->name, save->eint_con);
 	pr_debug("%s: save fltcon0 %#010x\n", bank->name, save->eint_fltcon0);
 	pr_debug("%s: save fltcon1 %#010x\n", bank->name, save->eint_fltcon1);
+	pr_debug("%s: save    mask %#010x\n", bank->name, save->eint_mask);
 }
 
 void exynos_pinctrl_suspend(struct samsung_pinctrl_drv_data *drvdata)
@@ -626,8 +655,8 @@ void exynos_pinctrl_suspend(struct samsung_pinctrl_drv_data *drvdata)
 		else if (bank->eint_type == EINT_TYPE_WKUP) {
 			if (!irq_chip) {
 				irq_chip = bank->irq_chip;
-				exynos_pinctrl_set_eint_wakeup_mask(drvdata,
-								    irq_chip);
+				irq_chip->set_eint_wakeup_mask(drvdata,
+							       irq_chip);
 			} else if (bank->irq_chip != irq_chip) {
 				dev_warn(drvdata->dev,
 					 "More than one external wakeup interrupt chip configured (bank: %s). This is not supported by hardware nor by driver.\n",
@@ -653,6 +682,9 @@ static void exynos_pinctrl_resume_bank(
 	pr_debug("%s: fltcon1 %#010x => %#010x\n", bank->name,
 			readl(regs + EXYNOS_GPIO_EFLTCON_OFFSET
 			+ 2 * bank->eint_offset + 4), save->eint_fltcon1);
+	pr_debug("%s:    mask %#010x => %#010x\n", bank->name,
+			readl(regs + bank->irq_chip->eint_mask
+			+ bank->eint_offset), save->eint_mask);
 
 	writel(save->eint_con, regs + EXYNOS_GPIO_ECON_OFFSET
 						+ bank->eint_offset);
@@ -660,6 +692,8 @@ static void exynos_pinctrl_resume_bank(
 						+ 2 * bank->eint_offset);
 	writel(save->eint_fltcon1, regs + EXYNOS_GPIO_EFLTCON_OFFSET
 						+ 2 * bank->eint_offset + 4);
+	writel(save->eint_mask, regs + bank->irq_chip->eint_mask
+						+ bank->eint_offset);
 }
 
 void exynos_pinctrl_resume(struct samsung_pinctrl_drv_data *drvdata)
diff --git a/drivers/pinctrl/sh-pfc/core.c b/drivers/pinctrl/sh-pfc/core.c
index 3f989f5cb021..28232c8cb963 100644
--- a/drivers/pinctrl/sh-pfc/core.c
+++ b/drivers/pinctrl/sh-pfc/core.c
@@ -29,12 +29,12 @@
 static int sh_pfc_map_resources(struct sh_pfc *pfc,
 				struct platform_device *pdev)
 {
-	unsigned int num_windows, num_irqs;
 	struct sh_pfc_window *windows;
 	unsigned int *irqs = NULL;
+	unsigned int num_windows;
 	struct resource *res;
 	unsigned int i;
-	int irq;
+	int num_irqs;
 
 	/* Count the MEM and IRQ resources. */
 	for (num_windows = 0;; num_windows++) {
@@ -42,17 +42,13 @@ static int sh_pfc_map_resources(struct sh_pfc *pfc,
 		if (!res)
 			break;
 	}
-	for (num_irqs = 0;; num_irqs++) {
-		irq = platform_get_irq(pdev, num_irqs);
-		if (irq == -EPROBE_DEFER)
-			return irq;
-		if (irq < 0)
-			break;
-	}
-
 	if (num_windows == 0)
 		return -EINVAL;
 
+	num_irqs = platform_irq_count(pdev);
+	if (num_irqs < 0)
+		return num_irqs;
+
 	/* Allocate memory windows and IRQs arrays. */
 	windows = devm_kcalloc(pfc->dev, num_windows, sizeof(*windows),
 			       GFP_KERNEL);
@@ -717,7 +713,7 @@ static int sh_pfc_suspend_init(struct sh_pfc *pfc) { return 0; }
 #endif /* CONFIG_PM_SLEEP && CONFIG_ARM_PSCI_FW */
 
 #ifdef DEBUG
-static bool is0s(const u16 *enum_ids, unsigned int n)
+static bool __init is0s(const u16 *enum_ids, unsigned int n)
 {
 	unsigned int i;
 
@@ -728,11 +724,11 @@ static bool is0s(const u16 *enum_ids, unsigned int n)
 	return true;
 }
 
-static unsigned int sh_pfc_errors;
-static unsigned int sh_pfc_warnings;
+static unsigned int sh_pfc_errors __initdata = 0;
+static unsigned int sh_pfc_warnings __initdata = 0;
 
-static void sh_pfc_check_cfg_reg(const char *drvname,
-				 const struct pinmux_cfg_reg *cfg_reg)
+static void __init sh_pfc_check_cfg_reg(const char *drvname,
+					const struct pinmux_cfg_reg *cfg_reg)
 {
 	unsigned int i, n, rw, fw;
 
@@ -764,7 +760,7 @@ static void sh_pfc_check_cfg_reg(const char *drvname,
 	}
 }
 
-static void sh_pfc_check_info(const struct sh_pfc_soc_info *info)
+static void __init sh_pfc_check_info(const struct sh_pfc_soc_info *info)
 {
 	const struct sh_pfc_function *func;
 	const char *drvname = info->name;
@@ -803,8 +799,8 @@ static void sh_pfc_check_info(const struct sh_pfc_soc_info *info)
 			       info->groups[i].name);
 			sh_pfc_errors++;
 		} else if (refcnts[i] > 1) {
-			pr_err("%s: group %s referred by %u functions\n",
-			       drvname, info->groups[i].name, refcnts[i]);
+			pr_warn("%s: group %s referenced by %u functions\n",
+				drvname, info->groups[i].name, refcnts[i]);
 			sh_pfc_warnings++;
 		}
 	}
@@ -816,7 +812,7 @@ static void sh_pfc_check_info(const struct sh_pfc_soc_info *info)
 		sh_pfc_check_cfg_reg(drvname, &info->cfg_regs[i]);
 }
 
-static void sh_pfc_check_driver(const struct platform_driver *pdrv)
+static void __init sh_pfc_check_driver(const struct platform_driver *pdrv)
 {
 	unsigned int i;
 
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7778.c b/drivers/pinctrl/sh-pfc/pfc-r8a7778.c
index 49fe52d35f30..304604740e44 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a7778.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a7778.c
@@ -2318,7 +2318,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = {
 		FN_ATAG0_A,	0,		FN_REMOCON_B,	0,
 		/* IP0_11_8 [4] */
 		FN_SD1_DAT2_A,	FN_MMC_D2,	0,		FN_BS,
-		FN_ATADIR0_A,	0,		FN_SDSELF_B,	0,
+		FN_ATADIR0_A,	0,		FN_SDSELF_A,	0,
 		FN_PWM4_B,	0,		0,		0,
 		0,		0,		0,		0,
 		/* IP0_7_5 [3] */
@@ -2362,7 +2362,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = {
 		FN_TS_SDAT0_A,	0,		0,		0,
 		0,		0,		0,		0,
 		/* IP1_10_8 [3] */
-		FN_SD1_CLK_B,	FN_MMC_D6,	0,		FN_A24,
+		FN_SD1_CD_A,	FN_MMC_D6,	0,		FN_A24,
 		FN_DREQ1_A,	0,		FN_HRX0_B,	FN_TS_SPSYNC0_A,
 		/* IP1_7_5 [3] */
 		FN_A23,		FN_HTX0_B,	FN_TX2_B,	FN_DACK2_A,
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a77965.c b/drivers/pinctrl/sh-pfc/pfc-r8a77965.c
index 090024355eba..743dcd0bde2c 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a77965.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a77965.c
@@ -5950,7 +5950,7 @@ static const struct pinmux_drive_reg pinmux_drive_regs[] = {
 		{ PIN_A_NUMBER('P', 8),  0, 2 },	/* DU_DOTCLKIN1 */
 	} },
 	{ PINMUX_DRIVE_REG("DRVCTRL12", 0xe6060330) {
-		{ PIN_A_NUMBER('R', 8),  28, 2 },	/* DU_DOTCLKIN3 */
+		{ PIN_A_NUMBER('R', 8),  24, 2 },	/* DU_DOTCLKIN3 */
 		{ PIN_A_NUMBER('D', 38), 20, 2 },	/* FSCLKST */
 		{ PIN_A_NUMBER('R', 30),  4, 2 },	/* TMS */
 	} },
@@ -6206,8 +6206,8 @@ static const struct pinmux_bias_reg pinmux_bias_regs[] = {
 		[31] = PIN_A_NUMBER('P', 8),	/* DU_DOTCLKIN1 */
 	} },
 	{ PINMUX_BIAS_REG("PUEN3", 0xe606040c, "PUD3", 0xe606044c) {
-		[ 0] = PIN_A_NUMBER('R', 8),	/* DU_DOTCLKIN3 */
-		[ 1] = PIN_NONE,
+		[ 0] = PIN_NONE,
+		[ 1] = PIN_A_NUMBER('R', 8),	/* DU_DOTCLKIN3 */
 		[ 2] = PIN_A_NUMBER('D', 38),	/* FSCLKST */
 		[ 3] = PIN_A_NUMBER('D', 39),	/* EXTALR*/
 		[ 4] = PIN_A_NUMBER('R', 26),	/* TRST# */
diff --git a/drivers/pinctrl/sh-pfc/pfc-sh7264.c b/drivers/pinctrl/sh-pfc/pfc-sh7264.c
index 4a95867deb8a..5a026601d4f9 100644
--- a/drivers/pinctrl/sh-pfc/pfc-sh7264.c
+++ b/drivers/pinctrl/sh-pfc/pfc-sh7264.c
@@ -497,17 +497,15 @@ enum {
 	SD_WP_MARK, SD_CLK_MARK, SD_CMD_MARK,
 	CRX0_MARK, CRX1_MARK,
 	CTX0_MARK, CTX1_MARK,
+	CRX0_CRX1_MARK, CTX0_CTX1_MARK,
 
 	PWM1A_MARK, PWM1B_MARK, PWM1C_MARK, PWM1D_MARK,
 	PWM1E_MARK, PWM1F_MARK, PWM1G_MARK, PWM1H_MARK,
 	PWM2A_MARK, PWM2B_MARK, PWM2C_MARK, PWM2D_MARK,
 	PWM2E_MARK, PWM2F_MARK, PWM2G_MARK, PWM2H_MARK,
 	IERXD_MARK, IETXD_MARK,
-	CRX0_CRX1_MARK,
 	WDTOVF_MARK,
 
-	CRX0X1_MARK,
-
 	/* DMAC */
 	TEND0_MARK, DACK0_MARK, DREQ0_MARK,
 	TEND1_MARK, DACK1_MARK, DREQ1_MARK,
@@ -995,12 +993,12 @@ static const u16 pinmux_data[] = {
 
 	PINMUX_DATA(PJ3_DATA, PJ3MD_00),
 	PINMUX_DATA(CRX1_MARK, PJ3MD_01),
-	PINMUX_DATA(CRX0X1_MARK, PJ3MD_10),
+	PINMUX_DATA(CRX0_CRX1_MARK, PJ3MD_10),
 	PINMUX_DATA(IRQ1_PJ_MARK, PJ3MD_11),
 
 	PINMUX_DATA(PJ2_DATA, PJ2MD_000),
 	PINMUX_DATA(CTX1_MARK, PJ2MD_001),
-	PINMUX_DATA(CRX0_CRX1_MARK, PJ2MD_010),
+	PINMUX_DATA(CTX0_CTX1_MARK, PJ2MD_010),
 	PINMUX_DATA(CS2_MARK, PJ2MD_011),
 	PINMUX_DATA(SCK0_MARK, PJ2MD_100),
 	PINMUX_DATA(LCD_M_DISP_MARK, PJ2MD_101),
@@ -1245,6 +1243,7 @@ static const struct pinmux_func pinmux_func_gpios[] = {
 	GPIO_FN(CTX1),
 	GPIO_FN(CRX1),
 	GPIO_FN(CTX0),
+	GPIO_FN(CTX0_CTX1),
 	GPIO_FN(CRX0),
 	GPIO_FN(CRX0_CRX1),
 
diff --git a/drivers/pinctrl/sh-pfc/pfc-sh7269.c b/drivers/pinctrl/sh-pfc/pfc-sh7269.c
index 6cbb18ef77dc..d20974a55d93 100644
--- a/drivers/pinctrl/sh-pfc/pfc-sh7269.c
+++ b/drivers/pinctrl/sh-pfc/pfc-sh7269.c
@@ -737,13 +737,12 @@ enum {
 	CRX0_MARK, CTX0_MARK,
 	CRX1_MARK, CTX1_MARK,
 	CRX2_MARK, CTX2_MARK,
-	CRX0_CRX1_MARK,
-	CRX0_CRX1_CRX2_MARK,
-	CTX0CTX1CTX2_MARK,
+	CRX0_CRX1_MARK, CTX0_CTX1_MARK,
+	CRX0_CRX1_CRX2_MARK, CTX0_CTX1_CTX2_MARK,
 	CRX1_PJ22_MARK, CTX1_PJ23_MARK,
 	CRX2_PJ20_MARK, CTX2_PJ21_MARK,
-	CRX0CRX1_PJ22_MARK,
-	CRX0CRX1CRX2_PJ20_MARK,
+	CRX0_CRX1_PJ22_MARK, CTX0_CTX1_PJ23_MARK,
+	CRX0_CRX1_CRX2_PJ20_MARK, CTX0_CTX1_CTX2_PJ21_MARK,
 
 	/* VDC */
 	DV_CLK_MARK,
@@ -821,6 +820,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_DATA(CS3_MARK, PC8MD_001),
 	PINMUX_DATA(TXD7_MARK, PC8MD_010),
 	PINMUX_DATA(CTX1_MARK, PC8MD_011),
+	PINMUX_DATA(CTX0_CTX1_MARK, PC8MD_100),
 
 	PINMUX_DATA(PC7_DATA, PC7MD_000),
 	PINMUX_DATA(CKE_MARK, PC7MD_001),
@@ -833,11 +833,12 @@ static const u16 pinmux_data[] = {
 	PINMUX_DATA(CAS_MARK, PC6MD_001),
 	PINMUX_DATA(SCK7_MARK, PC6MD_010),
 	PINMUX_DATA(CTX0_MARK, PC6MD_011),
+	PINMUX_DATA(CTX0_CTX1_CTX2_MARK, PC6MD_100),
 
 	PINMUX_DATA(PC5_DATA, PC5MD_000),
 	PINMUX_DATA(RAS_MARK, PC5MD_001),
 	PINMUX_DATA(CRX0_MARK, PC5MD_011),
-	PINMUX_DATA(CTX0CTX1CTX2_MARK, PC5MD_100),
+	PINMUX_DATA(CTX0_CTX1_CTX2_MARK, PC5MD_100),
 	PINMUX_DATA(IRQ0_PC_MARK, PC5MD_101),
 
 	PINMUX_DATA(PC4_DATA, PC4MD_00),
@@ -1289,30 +1290,32 @@ static const u16 pinmux_data[] = {
 	PINMUX_DATA(LCD_DATA23_PJ23_MARK, PJ23MD_010),
 	PINMUX_DATA(LCD_TCON6_MARK, PJ23MD_011),
 	PINMUX_DATA(IRQ3_PJ_MARK, PJ23MD_100),
-	PINMUX_DATA(CTX1_MARK, PJ23MD_101),
+	PINMUX_DATA(CTX1_PJ23_MARK, PJ23MD_101),
+	PINMUX_DATA(CTX0_CTX1_PJ23_MARK, PJ23MD_110),
 
 	PINMUX_DATA(PJ22_DATA, PJ22MD_000),
 	PINMUX_DATA(DV_DATA22_MARK, PJ22MD_001),
 	PINMUX_DATA(LCD_DATA22_PJ22_MARK, PJ22MD_010),
 	PINMUX_DATA(LCD_TCON5_MARK, PJ22MD_011),
 	PINMUX_DATA(IRQ2_PJ_MARK, PJ22MD_100),
-	PINMUX_DATA(CRX1_MARK, PJ22MD_101),
-	PINMUX_DATA(CRX0_CRX1_MARK, PJ22MD_110),
+	PINMUX_DATA(CRX1_PJ22_MARK, PJ22MD_101),
+	PINMUX_DATA(CRX0_CRX1_PJ22_MARK, PJ22MD_110),
 
 	PINMUX_DATA(PJ21_DATA, PJ21MD_000),
 	PINMUX_DATA(DV_DATA21_MARK, PJ21MD_001),
 	PINMUX_DATA(LCD_DATA21_PJ21_MARK, PJ21MD_010),
 	PINMUX_DATA(LCD_TCON4_MARK, PJ21MD_011),
 	PINMUX_DATA(IRQ1_PJ_MARK, PJ21MD_100),
-	PINMUX_DATA(CTX2_MARK, PJ21MD_101),
+	PINMUX_DATA(CTX2_PJ21_MARK, PJ21MD_101),
+	PINMUX_DATA(CTX0_CTX1_CTX2_PJ21_MARK, PJ21MD_110),
 
 	PINMUX_DATA(PJ20_DATA, PJ20MD_000),
 	PINMUX_DATA(DV_DATA20_MARK, PJ20MD_001),
 	PINMUX_DATA(LCD_DATA20_PJ20_MARK, PJ20MD_010),
 	PINMUX_DATA(LCD_TCON3_MARK, PJ20MD_011),
 	PINMUX_DATA(IRQ0_PJ_MARK, PJ20MD_100),
-	PINMUX_DATA(CRX2_MARK, PJ20MD_101),
-	PINMUX_DATA(CRX0CRX1CRX2_PJ20_MARK, PJ20MD_110),
+	PINMUX_DATA(CRX2_PJ20_MARK, PJ20MD_101),
+	PINMUX_DATA(CRX0_CRX1_CRX2_PJ20_MARK, PJ20MD_110),
 
 	PINMUX_DATA(PJ19_DATA, PJ19MD_000),
 	PINMUX_DATA(DV_DATA19_MARK, PJ19MD_001),
@@ -1663,12 +1666,24 @@ static const struct pinmux_func pinmux_func_gpios[] = {
 	GPIO_FN(WDTOVF),
 
 	/* CAN */
+	GPIO_FN(CTX2),
+	GPIO_FN(CRX2),
 	GPIO_FN(CTX1),
 	GPIO_FN(CRX1),
 	GPIO_FN(CTX0),
 	GPIO_FN(CRX0),
+	GPIO_FN(CTX0_CTX1),
 	GPIO_FN(CRX0_CRX1),
+	GPIO_FN(CTX0_CTX1_CTX2),
 	GPIO_FN(CRX0_CRX1_CRX2),
+	GPIO_FN(CTX2_PJ21),
+	GPIO_FN(CRX2_PJ20),
+	GPIO_FN(CTX1_PJ23),
+	GPIO_FN(CRX1_PJ22),
+	GPIO_FN(CTX0_CTX1_PJ23),
+	GPIO_FN(CRX0_CRX1_PJ22),
+	GPIO_FN(CTX0_CTX1_CTX2_PJ21),
+	GPIO_FN(CRX0_CRX1_CRX2_PJ20),
 
 	/* DMAC */
 	GPIO_FN(TEND0),
diff --git a/drivers/pinctrl/sh-pfc/sh_pfc.h b/drivers/pinctrl/sh-pfc/sh_pfc.h
index 7db5819eea7e..24469f9a3b0c 100644
--- a/drivers/pinctrl/sh-pfc/sh_pfc.h
+++ b/drivers/pinctrl/sh-pfc/sh_pfc.h
@@ -418,12 +418,12 @@ extern const struct sh_pfc_soc_info shx3_pinmux_info;
 /*
  * Describe a pinmux configuration in which a pin is physically multiplexed
  * with other pins.
- *   - ipsr: IPSR field (unused, for documentation purposes only)
+ *   - ipsr: IPSR field
  *   - fn: Function name
  *   - psel: Physical multiplexing selector
  */
 #define PINMUX_IPSR_PHYS(ipsr, fn, psel) \
-	PINMUX_DATA(fn##_MARK, FN_##psel)
+	PINMUX_DATA(fn##_MARK, FN_##psel, FN_##ipsr)
 
 /*
  * Describe a pinmux configuration for a single-function pin with GPIO
diff --git a/drivers/pinctrl/ti/pinctrl-ti-iodelay.c b/drivers/pinctrl/ti/pinctrl-ti-iodelay.c
index e5e7f1f22813..b522ca010332 100644
--- a/drivers/pinctrl/ti/pinctrl-ti-iodelay.c
+++ b/drivers/pinctrl/ti/pinctrl-ti-iodelay.c
@@ -496,7 +496,7 @@ static int ti_iodelay_dt_node_to_map(struct pinctrl_dev *pctldev,
 		return -EINVAL;
 
 	rows = pinctrl_count_index_with_args(np, name);
-	if (rows == -EINVAL)
+	if (rows < 0)
 		return rows;
 
 	*map = devm_kzalloc(iod->dev, sizeof(**map), GFP_KERNEL);
diff --git a/drivers/platform/chrome/cros_ec_rpmsg.c b/drivers/platform/chrome/cros_ec_rpmsg.c
index bec19d4814ab..641e5274ccde 100644
--- a/drivers/platform/chrome/cros_ec_rpmsg.c
+++ b/drivers/platform/chrome/cros_ec_rpmsg.c
@@ -42,6 +42,8 @@ struct cros_ec_rpmsg {
 	struct completion xfer_ack;
 	struct work_struct host_event_work;
 	struct rpmsg_endpoint *ept;
+	bool has_pending_host_event;
+	bool probe_done;
 };
 
 /**
@@ -186,7 +188,14 @@ static int cros_ec_rpmsg_callback(struct rpmsg_device *rpdev, void *data,
 		memcpy(ec_dev->din, resp->data, len);
 		complete(&ec_rpmsg->xfer_ack);
 	} else if (resp->type == HOST_EVENT_MARK) {
-		schedule_work(&ec_rpmsg->host_event_work);
+		/*
+		 * If the host event is sent before cros_ec_register is
+		 * finished, queue the host event.
+		 */
+		if (ec_rpmsg->probe_done)
+			schedule_work(&ec_rpmsg->host_event_work);
+		else
+			ec_rpmsg->has_pending_host_event = true;
 	} else {
 		dev_warn(ec_dev->dev, "rpmsg received invalid type = %d",
 			 resp->type);
@@ -249,6 +258,11 @@ static int cros_ec_rpmsg_probe(struct rpmsg_device *rpdev)
 		return ret;
 	}
 
+	ec_rpmsg->probe_done = true;
+
+	if (ec_rpmsg->has_pending_host_event)
+		schedule_work(&ec_rpmsg->host_event_work);
+
 	return 0;
 }
 
diff --git a/drivers/platform/mellanox/mlxbf-tmfifo.c b/drivers/platform/mellanox/mlxbf-tmfifo.c
index 9a5c9fd2dbc6..5739a9669b29 100644
--- a/drivers/platform/mellanox/mlxbf-tmfifo.c
+++ b/drivers/platform/mellanox/mlxbf-tmfifo.c
@@ -149,7 +149,7 @@ struct mlxbf_tmfifo_irq_info {
  * @work: work struct for deferred process
  * @timer: background timer
  * @vring: Tx/Rx ring
- * @spin_lock: spin lock
+ * @spin_lock: Tx/Rx spin lock
  * @is_ready: ready flag
  */
 struct mlxbf_tmfifo {
@@ -164,7 +164,7 @@ struct mlxbf_tmfifo {
 	struct work_struct work;
 	struct timer_list timer;
 	struct mlxbf_tmfifo_vring *vring[2];
-	spinlock_t spin_lock;		/* spin lock */
+	spinlock_t spin_lock[2];	/* spin lock */
 	bool is_ready;
 };
 
@@ -525,7 +525,7 @@ static void mlxbf_tmfifo_console_tx(struct mlxbf_tmfifo *fifo, int avail)
 	writeq(*(u64 *)&hdr, fifo->tx_base + MLXBF_TMFIFO_TX_DATA);
 
 	/* Use spin-lock to protect the 'cons->tx_buf'. */
-	spin_lock_irqsave(&fifo->spin_lock, flags);
+	spin_lock_irqsave(&fifo->spin_lock[0], flags);
 
 	while (size > 0) {
 		addr = cons->tx_buf.buf + cons->tx_buf.tail;
@@ -552,7 +552,7 @@ static void mlxbf_tmfifo_console_tx(struct mlxbf_tmfifo *fifo, int avail)
 		}
 	}
 
-	spin_unlock_irqrestore(&fifo->spin_lock, flags);
+	spin_unlock_irqrestore(&fifo->spin_lock[0], flags);
 }
 
 /* Rx/Tx one word in the descriptor buffer. */
@@ -731,9 +731,9 @@ static bool mlxbf_tmfifo_rxtx_one_desc(struct mlxbf_tmfifo_vring *vring,
 		fifo->vring[is_rx] = NULL;
 
 		/* Notify upper layer that packet is done. */
-		spin_lock_irqsave(&fifo->spin_lock, flags);
+		spin_lock_irqsave(&fifo->spin_lock[is_rx], flags);
 		vring_interrupt(0, vring->vq);
-		spin_unlock_irqrestore(&fifo->spin_lock, flags);
+		spin_unlock_irqrestore(&fifo->spin_lock[is_rx], flags);
 	}
 
 mlxbf_tmfifo_desc_done:
@@ -852,10 +852,10 @@ static bool mlxbf_tmfifo_virtio_notify(struct virtqueue *vq)
 		 * worker handler.
 		 */
 		if (vring->vdev_id == VIRTIO_ID_CONSOLE) {
-			spin_lock_irqsave(&fifo->spin_lock, flags);
+			spin_lock_irqsave(&fifo->spin_lock[0], flags);
 			tm_vdev = fifo->vdev[VIRTIO_ID_CONSOLE];
 			mlxbf_tmfifo_console_output(tm_vdev, vring);
-			spin_unlock_irqrestore(&fifo->spin_lock, flags);
+			spin_unlock_irqrestore(&fifo->spin_lock[0], flags);
 		} else if (test_and_set_bit(MLXBF_TM_TX_LWM_IRQ,
 					    &fifo->pend_events)) {
 			return true;
@@ -1189,7 +1189,8 @@ static int mlxbf_tmfifo_probe(struct platform_device *pdev)
 	if (!fifo)
 		return -ENOMEM;
 
-	spin_lock_init(&fifo->spin_lock);
+	spin_lock_init(&fifo->spin_lock[0]);
+	spin_lock_init(&fifo->spin_lock[1]);
 	INIT_WORK(&fifo->work, mlxbf_tmfifo_work_handler);
 	mutex_init(&fifo->lock);
 
diff --git a/drivers/platform/mips/cpu_hwmon.c b/drivers/platform/mips/cpu_hwmon.c
index a7f184bb47e0..3d29a11c1d6b 100644
--- a/drivers/platform/mips/cpu_hwmon.c
+++ b/drivers/platform/mips/cpu_hwmon.c
@@ -161,7 +161,7 @@ static int __init loongson_hwmon_init(void)
 
 	cpu_hwmon_dev = hwmon_device_register(NULL);
 	if (IS_ERR(cpu_hwmon_dev)) {
-		ret = -ENOMEM;
+		ret = PTR_ERR(cpu_hwmon_dev);
 		pr_err("hwmon_device_register fail!\n");
 		goto fail_hwmon_device_register;
 	}
diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
index 8d9e30dbb5af..fec5a1e544e4 100644
--- a/drivers/platform/x86/asus-nb-wmi.c
+++ b/drivers/platform/x86/asus-nb-wmi.c
@@ -110,6 +110,16 @@ static struct quirk_entry quirk_asus_forceals = {
 	.wmi_force_als_set = true,
 };
 
+static struct quirk_entry quirk_asus_ga401i = {
+	.wmi_backlight_power = true,
+	.wmi_backlight_set_devstate = true,
+};
+
+static struct quirk_entry quirk_asus_ga502i = {
+	.wmi_backlight_power = true,
+	.wmi_backlight_set_devstate = true,
+};
+
 static int dmi_matched(const struct dmi_system_id *dmi)
 {
 	pr_info("Identified laptop model '%s'\n", dmi->ident);
@@ -402,6 +412,78 @@ static const struct dmi_system_id asus_quirks[] = {
 		},
 		.driver_data = &quirk_asus_forceals,
 	},
+	{
+		.callback = dmi_matched,
+		.ident = "ASUSTeK COMPUTER INC. GA401IH",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "GA401IH"),
+		},
+		.driver_data = &quirk_asus_ga401i,
+	},
+	{
+		.callback = dmi_matched,
+		.ident = "ASUSTeK COMPUTER INC. GA401II",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "GA401II"),
+		},
+		.driver_data = &quirk_asus_ga401i,
+	},
+	{
+		.callback = dmi_matched,
+		.ident = "ASUSTeK COMPUTER INC. GA401IU",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "GA401IU"),
+		},
+		.driver_data = &quirk_asus_ga401i,
+	},
+	{
+		.callback = dmi_matched,
+		.ident = "ASUSTeK COMPUTER INC. GA401IV",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "GA401IV"),
+		},
+		.driver_data = &quirk_asus_ga401i,
+	},
+	{
+		.callback = dmi_matched,
+		.ident = "ASUSTeK COMPUTER INC. GA401IVC",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "GA401IVC"),
+		},
+		.driver_data = &quirk_asus_ga401i,
+	},
+		{
+		.callback = dmi_matched,
+		.ident = "ASUSTeK COMPUTER INC. GA502II",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "GA502II"),
+		},
+		.driver_data = &quirk_asus_ga502i,
+	},
+	{
+		.callback = dmi_matched,
+		.ident = "ASUSTeK COMPUTER INC. GA502IU",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "GA502IU"),
+		},
+		.driver_data = &quirk_asus_ga502i,
+	},
+	{
+		.callback = dmi_matched,
+		.ident = "ASUSTeK COMPUTER INC. GA502IV",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "GA502IV"),
+		},
+		.driver_data = &quirk_asus_ga502i,
+	},
 	{},
 };
 
@@ -504,9 +586,33 @@ static struct asus_wmi_driver asus_nb_wmi_driver = {
 	.detect_quirks = asus_nb_wmi_quirks,
 };
 
+static const struct dmi_system_id asus_nb_wmi_blacklist[] __initconst = {
+	{
+		/*
+		 * asus-nb-wm adds no functionality. The T100TA has a detachable
+		 * USB kbd, so no hotkeys and it has no WMI rfkill; and loading
+		 * asus-nb-wm causes the camera LED to turn and _stay_ on.
+		 */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100TA"),
+		},
+	},
+	{
+		/* The Asus T200TA has the same issue as the T100TA */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T200TA"),
+		},
+	},
+	{} /* Terminating entry */
+};
 
 static int __init asus_nb_wmi_init(void)
 {
+	if (dmi_check_system(asus_nb_wmi_blacklist))
+		return -ENODEV;
+
 	return asus_wmi_register_driver(&asus_nb_wmi_driver);
 }
 
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index abfa99d18fea..7cc9064b40d6 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -86,6 +86,8 @@ struct bios_args {
 	u32 arg0;
 	u32 arg1;
 	u32 arg2; /* At least TUF Gaming series uses 3 dword input buffer. */
+	u32 arg4;
+	u32 arg5;
 } __packed;
 
 /*
@@ -377,13 +379,7 @@ static void kbd_led_update(struct asus_wmi *asus)
 {
 	int ctrl_param = 0;
 
-	/*
-	 * bits 0-2: level
-	 * bit 7: light on/off
-	 */
-	if (asus->kbd_led_wk > 0)
-		ctrl_param = 0x80 | (asus->kbd_led_wk & 0x7F);
-
+	ctrl_param = 0x80 | (asus->kbd_led_wk & 0x7F);
 	asus_wmi_set_devstate(ASUS_WMI_DEVID_KBD_BACKLIGHT, ctrl_param, NULL);
 }
 
diff --git a/drivers/platform/x86/dell-laptop.c b/drivers/platform/x86/dell-laptop.c
index 4e2f76aa98de..53d3f175b961 100644
--- a/drivers/platform/x86/dell-laptop.c
+++ b/drivers/platform/x86/dell-laptop.c
@@ -33,6 +33,7 @@
 
 struct quirk_entry {
 	bool touchpad_led;
+	bool kbd_led_not_present;
 	bool kbd_led_levels_off_1;
 	bool kbd_missing_ac_tag;
 
@@ -73,6 +74,10 @@ static struct quirk_entry quirk_dell_latitude_e6410 = {
 	.kbd_led_levels_off_1 = true,
 };
 
+static struct quirk_entry quirk_dell_inspiron_1012 = {
+	.kbd_led_not_present = true,
+};
+
 static struct platform_driver platform_driver = {
 	.driver = {
 		.name = "dell-laptop",
@@ -310,6 +315,24 @@ static const struct dmi_system_id dell_quirks[] __initconst = {
 		},
 		.driver_data = &quirk_dell_latitude_e6410,
 	},
+	{
+		.callback = dmi_matched,
+		.ident = "Dell Inspiron 1012",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 1012"),
+		},
+		.driver_data = &quirk_dell_inspiron_1012,
+	},
+	{
+		.callback = dmi_matched,
+		.ident = "Dell Inspiron 1018",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 1018"),
+		},
+		.driver_data = &quirk_dell_inspiron_1012,
+	},
 	{ }
 };
 
@@ -1493,6 +1516,9 @@ static void kbd_init(void)
 {
 	int ret;
 
+	if (quirks && quirks->kbd_led_not_present)
+		return;
+
 	ret = kbd_init_info();
 	kbd_init_tokens();
 
@@ -2179,10 +2205,13 @@ static int __init dell_init(void)
 
 	dell_laptop_register_notifier(&dell_laptop_notifier);
 
-	micmute_led_cdev.brightness = ledtrig_audio_get(LED_AUDIO_MICMUTE);
-	ret = led_classdev_register(&platform_device->dev, &micmute_led_cdev);
-	if (ret < 0)
-		goto fail_led;
+	if (dell_smbios_find_token(GLOBAL_MIC_MUTE_DISABLE) &&
+	    dell_smbios_find_token(GLOBAL_MIC_MUTE_ENABLE)) {
+		micmute_led_cdev.brightness = ledtrig_audio_get(LED_AUDIO_MICMUTE);
+		ret = led_classdev_register(&platform_device->dev, &micmute_led_cdev);
+		if (ret < 0)
+			goto fail_led;
+	}
 
 	if (acpi_video_get_backlight_type() != acpi_backlight_vendor)
 		return 0;
diff --git a/drivers/platform/x86/gpd-pocket-fan.c b/drivers/platform/x86/gpd-pocket-fan.c
index be85ed966bf3..5b516e4c2bfb 100644
--- a/drivers/platform/x86/gpd-pocket-fan.c
+++ b/drivers/platform/x86/gpd-pocket-fan.c
@@ -16,17 +16,27 @@
 
 #define MAX_SPEED 3
 
-static int temp_limits[3] = { 55000, 60000, 65000 };
+#define TEMP_LIMIT0_DEFAULT	55000
+#define TEMP_LIMIT1_DEFAULT	60000
+#define TEMP_LIMIT2_DEFAULT	65000
+
+#define HYSTERESIS_DEFAULT	3000
+
+#define SPEED_ON_AC_DEFAULT	2
+
+static int temp_limits[3] = {
+	TEMP_LIMIT0_DEFAULT, TEMP_LIMIT1_DEFAULT, TEMP_LIMIT2_DEFAULT,
+};
 module_param_array(temp_limits, int, NULL, 0444);
 MODULE_PARM_DESC(temp_limits,
 		 "Millicelsius values above which the fan speed increases");
 
-static int hysteresis = 3000;
+static int hysteresis = HYSTERESIS_DEFAULT;
 module_param(hysteresis, int, 0444);
 MODULE_PARM_DESC(hysteresis,
 		 "Hysteresis in millicelsius before lowering the fan speed");
 
-static int speed_on_ac = 2;
+static int speed_on_ac = SPEED_ON_AC_DEFAULT;
 module_param(speed_on_ac, int, 0444);
 MODULE_PARM_DESC(speed_on_ac,
 		 "minimum fan speed to allow when system is powered by AC");
@@ -117,21 +127,24 @@ static int gpd_pocket_fan_probe(struct platform_device *pdev)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(temp_limits); i++) {
-		if (temp_limits[i] < 40000 || temp_limits[i] > 70000) {
-			dev_err(&pdev->dev, "Invalid temp-limit %d (must be between 40000 and 70000)\n",
+		if (temp_limits[i] < 20000 || temp_limits[i] > 90000) {
+			dev_err(&pdev->dev, "Invalid temp-limit %d (must be between 20000 and 90000)\n",
 				temp_limits[i]);
-			return -EINVAL;
+			temp_limits[0] = TEMP_LIMIT0_DEFAULT;
+			temp_limits[1] = TEMP_LIMIT1_DEFAULT;
+			temp_limits[2] = TEMP_LIMIT2_DEFAULT;
+			break;
 		}
 	}
 	if (hysteresis < 1000 || hysteresis > 10000) {
 		dev_err(&pdev->dev, "Invalid hysteresis %d (must be between 1000 and 10000)\n",
 			hysteresis);
-		return -EINVAL;
+		hysteresis = HYSTERESIS_DEFAULT;
 	}
 	if (speed_on_ac < 0 || speed_on_ac > MAX_SPEED) {
 		dev_err(&pdev->dev, "Invalid speed_on_ac %d (must be between 0 and 3)\n",
 			speed_on_ac);
-		return -EINVAL;
+		speed_on_ac = SPEED_ON_AC_DEFAULT;
 	}
 
 	fan = devm_kzalloc(&pdev->dev, sizeof(*fan), GFP_KERNEL);
diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c
index 1b1733157d89..dac8f51f9f57 100644
--- a/drivers/platform/x86/hp-wmi.c
+++ b/drivers/platform/x86/hp-wmi.c
@@ -461,8 +461,14 @@ static ssize_t postcode_show(struct device *dev, struct device_attribute *attr,
 static ssize_t als_store(struct device *dev, struct device_attribute *attr,
 			 const char *buf, size_t count)
 {
-	u32 tmp = simple_strtoul(buf, NULL, 10);
-	int ret = hp_wmi_perform_query(HPWMI_ALS_QUERY, HPWMI_WRITE, &tmp,
+	u32 tmp;
+	int ret;
+
+	ret = kstrtou32(buf, 10, &tmp);
+	if (ret)
+		return ret;
+
+	ret = hp_wmi_perform_query(HPWMI_ALS_QUERY, HPWMI_WRITE, &tmp,
 				       sizeof(tmp), sizeof(tmp));
 	if (ret)
 		return ret < 0 ? ret : -EINVAL;
diff --git a/drivers/platform/x86/intel-hid.c b/drivers/platform/x86/intel-hid.c
index bc0d55a59015..820268cd0c8d 100644
--- a/drivers/platform/x86/intel-hid.c
+++ b/drivers/platform/x86/intel-hid.c
@@ -77,6 +77,13 @@ static const struct dmi_system_id button_array_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Wacom MobileStudio Pro 16"),
 		},
 	},
+	{
+		.ident = "HP Spectre x2 (2015)",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP Spectre x2 Detachable"),
+		},
+	},
 	{ }
 };
 
@@ -547,7 +554,7 @@ check_acpi_dev(acpi_handle handle, u32 lvl, void *context, void **rv)
 		return AE_OK;
 
 	if (acpi_match_device_ids(dev, ids) == 0)
-		if (acpi_create_platform_device(dev, NULL))
+		if (!IS_ERR_OR_NULL(acpi_create_platform_device(dev, NULL)))
 			dev_info(&dev->dev,
 				 "intel-hid: created platform device\n");
 
diff --git a/drivers/platform/x86/intel-vbtn.c b/drivers/platform/x86/intel-vbtn.c
index a0d0cecff55f..c7c8b432c163 100644
--- a/drivers/platform/x86/intel-vbtn.c
+++ b/drivers/platform/x86/intel-vbtn.c
@@ -39,28 +39,51 @@ static const struct key_entry intel_vbtn_keymap[] = {
 	{ KE_IGNORE, 0xC7, { KEY_VOLUMEDOWN } },	/* volume-down key release */
 	{ KE_KEY,    0xC8, { KEY_ROTATE_LOCK_TOGGLE } },	/* rotate-lock key press */
 	{ KE_KEY,    0xC9, { KEY_ROTATE_LOCK_TOGGLE } },	/* rotate-lock key release */
+};
+
+static const struct key_entry intel_vbtn_switchmap[] = {
 	{ KE_SW,     0xCA, { .sw = { SW_DOCK, 1 } } },		/* Docked */
 	{ KE_SW,     0xCB, { .sw = { SW_DOCK, 0 } } },		/* Undocked */
 	{ KE_SW,     0xCC, { .sw = { SW_TABLET_MODE, 1 } } },	/* Tablet */
 	{ KE_SW,     0xCD, { .sw = { SW_TABLET_MODE, 0 } } },	/* Laptop */
-	{ KE_END },
 };
 
+#define KEYMAP_LEN \
+	(ARRAY_SIZE(intel_vbtn_keymap) + ARRAY_SIZE(intel_vbtn_switchmap) + 1)
+
 struct intel_vbtn_priv {
+	struct key_entry keymap[KEYMAP_LEN];
 	struct input_dev *input_dev;
+	bool has_switches;
 	bool wakeup_mode;
 };
 
 static int intel_vbtn_input_setup(struct platform_device *device)
 {
 	struct intel_vbtn_priv *priv = dev_get_drvdata(&device->dev);
-	int ret;
+	int ret, keymap_len = 0;
+
+	if (true) {
+		memcpy(&priv->keymap[keymap_len], intel_vbtn_keymap,
+		       ARRAY_SIZE(intel_vbtn_keymap) *
+		       sizeof(struct key_entry));
+		keymap_len += ARRAY_SIZE(intel_vbtn_keymap);
+	}
+
+	if (priv->has_switches) {
+		memcpy(&priv->keymap[keymap_len], intel_vbtn_switchmap,
+		       ARRAY_SIZE(intel_vbtn_switchmap) *
+		       sizeof(struct key_entry));
+		keymap_len += ARRAY_SIZE(intel_vbtn_switchmap);
+	}
+
+	priv->keymap[keymap_len].type = KE_END;
 
 	priv->input_dev = devm_input_allocate_device(&device->dev);
 	if (!priv->input_dev)
 		return -ENOMEM;
 
-	ret = sparse_keymap_setup(priv->input_dev, intel_vbtn_keymap, NULL);
+	ret = sparse_keymap_setup(priv->input_dev, priv->keymap, NULL);
 	if (ret)
 		return ret;
 
@@ -115,31 +138,40 @@ out_unknown:
 
 static void detect_tablet_mode(struct platform_device *device)
 {
-	const char *chassis_type = dmi_get_system_info(DMI_CHASSIS_TYPE);
 	struct intel_vbtn_priv *priv = dev_get_drvdata(&device->dev);
 	acpi_handle handle = ACPI_HANDLE(&device->dev);
-	struct acpi_buffer vgbs_output = { ACPI_ALLOCATE_BUFFER, NULL };
-	union acpi_object *obj;
+	unsigned long long vgbs;
 	acpi_status status;
 	int m;
 
-	if (!(chassis_type && strcmp(chassis_type, "31") == 0))
-		goto out;
-
-	status = acpi_evaluate_object(handle, "VGBS", NULL, &vgbs_output);
+	status = acpi_evaluate_integer(handle, "VGBS", NULL, &vgbs);
 	if (ACPI_FAILURE(status))
-		goto out;
-
-	obj = vgbs_output.pointer;
-	if (!(obj && obj->type == ACPI_TYPE_INTEGER))
-		goto out;
+		return;
 
-	m = !(obj->integer.value & TABLET_MODE_FLAG);
+	m = !(vgbs & TABLET_MODE_FLAG);
 	input_report_switch(priv->input_dev, SW_TABLET_MODE, m);
-	m = (obj->integer.value & DOCK_MODE_FLAG) ? 1 : 0;
+	m = (vgbs & DOCK_MODE_FLAG) ? 1 : 0;
 	input_report_switch(priv->input_dev, SW_DOCK, m);
-out:
-	kfree(vgbs_output.pointer);
+}
+
+static bool intel_vbtn_has_switches(acpi_handle handle)
+{
+	const char *chassis_type = dmi_get_system_info(DMI_CHASSIS_TYPE);
+	unsigned long long vgbs;
+	acpi_status status;
+
+	/*
+	 * Some normal laptops have a VGBS method despite being non-convertible
+	 * and their VGBS method always returns 0, causing detect_tablet_mode()
+	 * to report SW_TABLET_MODE=1 to userspace, which causes issues.
+	 * These laptops have a DMI chassis_type of 9 ("Laptop"), do not report
+	 * switches on any devices with a DMI chassis_type of 9.
+	 */
+	if (chassis_type && strcmp(chassis_type, "9") == 0)
+		return false;
+
+	status = acpi_evaluate_integer(handle, "VGBS", NULL, &vgbs);
+	return ACPI_SUCCESS(status);
 }
 
 static int intel_vbtn_probe(struct platform_device *device)
@@ -160,13 +192,16 @@ static int intel_vbtn_probe(struct platform_device *device)
 		return -ENOMEM;
 	dev_set_drvdata(&device->dev, priv);
 
+	priv->has_switches = intel_vbtn_has_switches(handle);
+
 	err = intel_vbtn_input_setup(device);
 	if (err) {
 		pr_err("Failed to setup Intel Virtual Button\n");
 		return err;
 	}
 
-	detect_tablet_mode(device);
+	if (priv->has_switches)
+		detect_tablet_mode(device);
 
 	status = acpi_install_notify_handler(handle,
 					     ACPI_DEVICE_NOTIFY,
@@ -237,7 +272,7 @@ check_acpi_dev(acpi_handle handle, u32 lvl, void *context, void **rv)
 		return AE_OK;
 
 	if (acpi_match_device_ids(dev, ids) == 0)
-		if (acpi_create_platform_device(dev, NULL))
+		if (!IS_ERR_OR_NULL(acpi_create_platform_device(dev, NULL)))
 			dev_info(&dev->dev,
 				 "intel-vbtn: created platform device\n");
 
diff --git a/drivers/platform/x86/intel_mid_powerbtn.c b/drivers/platform/x86/intel_mid_powerbtn.c
index 292bace83f1e..6f436836fe50 100644
--- a/drivers/platform/x86/intel_mid_powerbtn.c
+++ b/drivers/platform/x86/intel_mid_powerbtn.c
@@ -146,9 +146,10 @@ static int mid_pb_probe(struct platform_device *pdev)
 
 	input_set_capability(input, EV_KEY, KEY_POWER);
 
-	ddata = (struct mid_pb_ddata *)id->driver_data;
+	ddata = devm_kmemdup(&pdev->dev, (void *)id->driver_data,
+			     sizeof(*ddata), GFP_KERNEL);
 	if (!ddata)
-		return -ENODATA;
+		return -ENOMEM;
 
 	ddata->dev = &pdev->dev;
 	ddata->irq = irq;
diff --git a/drivers/platform/x86/intel_punit_ipc.c b/drivers/platform/x86/intel_punit_ipc.c
index ab7ae1950867..fa97834fdb78 100644
--- a/drivers/platform/x86/intel_punit_ipc.c
+++ b/drivers/platform/x86/intel_punit_ipc.c
@@ -293,9 +293,8 @@ static int intel_punit_ipc_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, punit_ipcdev);
 
-	irq = platform_get_irq(pdev, 0);
+	irq = platform_get_irq_optional(pdev, 0);
 	if (irq < 0) {
-		punit_ipcdev->irq = 0;
 		dev_warn(&pdev->dev, "Invalid IRQ, using polling mode\n");
 	} else {
 		ret = devm_request_irq(&pdev->dev, irq, intel_punit_ioc,
diff --git a/drivers/platform/x86/intel_scu_ipc.c b/drivers/platform/x86/intel_scu_ipc.c
index cdab916fbf92..e330ec73c465 100644
--- a/drivers/platform/x86/intel_scu_ipc.c
+++ b/drivers/platform/x86/intel_scu_ipc.c
@@ -67,26 +67,22 @@
 struct intel_scu_ipc_pdata_t {
 	u32 i2c_base;
 	u32 i2c_len;
-	u8 irq_mode;
 };
 
 static const struct intel_scu_ipc_pdata_t intel_scu_ipc_lincroft_pdata = {
 	.i2c_base = 0xff12b000,
 	.i2c_len = 0x10,
-	.irq_mode = 0,
 };
 
 /* Penwell and Cloverview */
 static const struct intel_scu_ipc_pdata_t intel_scu_ipc_penwell_pdata = {
 	.i2c_base = 0xff12b000,
 	.i2c_len = 0x10,
-	.irq_mode = 1,
 };
 
 static const struct intel_scu_ipc_pdata_t intel_scu_ipc_tangier_pdata = {
 	.i2c_base  = 0xff00d000,
 	.i2c_len = 0x10,
-	.irq_mode = 0,
 };
 
 struct intel_scu_ipc_dev {
@@ -99,6 +95,9 @@ struct intel_scu_ipc_dev {
 
 static struct intel_scu_ipc_dev  ipcdev; /* Only one for now */
 
+#define IPC_STATUS		0x04
+#define IPC_STATUS_IRQ		BIT(2)
+
 /*
  * IPC Read Buffer (Read Only):
  * 16 byte buffer for receiving data from SCU, if IPC command
@@ -120,11 +119,8 @@ static DEFINE_MUTEX(ipclock); /* lock used to prevent multiple call to SCU */
  */
 static inline void ipc_command(struct intel_scu_ipc_dev *scu, u32 cmd)
 {
-	if (scu->irq_mode) {
-		reinit_completion(&scu->cmd_complete);
-		writel(cmd | IPC_IOC, scu->ipc_base);
-	}
-	writel(cmd, scu->ipc_base);
+	reinit_completion(&scu->cmd_complete);
+	writel(cmd | IPC_IOC, scu->ipc_base);
 }
 
 /*
@@ -610,9 +606,10 @@ EXPORT_SYMBOL(intel_scu_ipc_i2c_cntrl);
 static irqreturn_t ioc(int irq, void *dev_id)
 {
 	struct intel_scu_ipc_dev *scu = dev_id;
+	int status = ipc_read_status(scu);
 
-	if (scu->irq_mode)
-		complete(&scu->cmd_complete);
+	writel(status | IPC_STATUS_IRQ, scu->ipc_base + IPC_STATUS);
+	complete(&scu->cmd_complete);
 
 	return IRQ_HANDLED;
 }
@@ -638,8 +635,6 @@ static int ipc_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (!pdata)
 		return -ENODEV;
 
-	scu->irq_mode = pdata->irq_mode;
-
 	err = pcim_enable_device(pdev);
 	if (err)
 		return err;
diff --git a/drivers/platform/x86/pmc_atom.c b/drivers/platform/x86/pmc_atom.c
index 60e509753c77..1405ff0566fd 100644
--- a/drivers/platform/x86/pmc_atom.c
+++ b/drivers/platform/x86/pmc_atom.c
@@ -406,6 +406,14 @@ static const struct dmi_system_id critclk_systems[] = {
 	},
 	{
 		/* pmc_plt_clk* - are used for ethernet controllers */
+		.ident = "Lex 2I385SW",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Lex BayTrail"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "2I385SW"),
+		},
+	},
+	{
+		/* pmc_plt_clk* - are used for ethernet controllers */
 		.ident = "Beckhoff CB3163",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Beckhoff Automation"),
@@ -443,6 +451,14 @@ static const struct dmi_system_id critclk_systems[] = {
 			DMI_MATCH(DMI_PRODUCT_VERSION, "6ES7647-8B"),
 		},
 	},
+	{
+		.ident = "CONNECT X300",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "SIEMENS AG"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "A5E45074588"),
+		},
+	},
+
 	{ /*sentinel*/ }
 };
 
diff --git a/drivers/power/reset/vexpress-poweroff.c b/drivers/power/reset/vexpress-poweroff.c
index 90cbaa8341e3..0bf9ab8653ae 100644
--- a/drivers/power/reset/vexpress-poweroff.c
+++ b/drivers/power/reset/vexpress-poweroff.c
@@ -143,6 +143,7 @@ static struct platform_driver vexpress_reset_driver = {
 	.driver = {
 		.name = "vexpress-reset",
 		.of_match_table = vexpress_reset_of_match,
+		.suppress_bind_attrs = true,
 	},
 };
 
diff --git a/drivers/power/supply/88pm860x_battery.c b/drivers/power/supply/88pm860x_battery.c
index 5ca047b3f58f..23e7d6447ae9 100644
--- a/drivers/power/supply/88pm860x_battery.c
+++ b/drivers/power/supply/88pm860x_battery.c
@@ -433,7 +433,7 @@ static void pm860x_init_battery(struct pm860x_battery_info *info)
 	int ret;
 	int data;
 	int bat_remove;
-	int soc;
+	int soc = 0;
 
 	/* measure enable on GPADC1 */
 	data = MEAS1_GP1;
@@ -496,7 +496,9 @@ static void pm860x_init_battery(struct pm860x_battery_info *info)
 	}
 	mutex_unlock(&info->lock);
 
-	calc_soc(info, OCV_MODE_ACTIVE, &soc);
+	ret = calc_soc(info, OCV_MODE_ACTIVE, &soc);
+	if (ret < 0)
+		goto out;
 
 	data = pm860x_reg_read(info->i2c, PM8607_POWER_UP_LOG);
 	bat_remove = data & BAT_WU_LOG;
diff --git a/drivers/power/supply/Kconfig b/drivers/power/supply/Kconfig
index dd7da41f230c..e5314c83a49d 100644
--- a/drivers/power/supply/Kconfig
+++ b/drivers/power/supply/Kconfig
@@ -574,7 +574,7 @@ config CHARGER_BQ24257
 	tristate "TI BQ24250/24251/24257 battery charger driver"
 	depends on I2C
 	depends on GPIOLIB || COMPILE_TEST
-	depends on REGMAP_I2C
+	select REGMAP_I2C
 	help
 	  Say Y to enable support for the TI BQ24250, BQ24251, and BQ24257 battery
 	  chargers.
diff --git a/drivers/power/supply/axp20x_ac_power.c b/drivers/power/supply/axp20x_ac_power.c
index 0d34a932b6d5..f74b0556bb6b 100644
--- a/drivers/power/supply/axp20x_ac_power.c
+++ b/drivers/power/supply/axp20x_ac_power.c
@@ -23,6 +23,8 @@
 #define AXP20X_PWR_STATUS_ACIN_PRESENT	BIT(7)
 #define AXP20X_PWR_STATUS_ACIN_AVAIL	BIT(6)
 
+#define AXP813_ACIN_PATH_SEL		BIT(7)
+
 #define AXP813_VHOLD_MASK		GENMASK(5, 3)
 #define AXP813_VHOLD_UV_TO_BIT(x)	((((x) / 100000) - 40) << 3)
 #define AXP813_VHOLD_REG_TO_UV(x)	\
@@ -40,6 +42,7 @@ struct axp20x_ac_power {
 	struct power_supply *supply;
 	struct iio_channel *acin_v;
 	struct iio_channel *acin_i;
+	bool has_acin_path_sel;
 };
 
 static irqreturn_t axp20x_ac_power_irq(int irq, void *devid)
@@ -86,6 +89,17 @@ static int axp20x_ac_power_get_property(struct power_supply *psy,
 			return ret;
 
 		val->intval = !!(reg & AXP20X_PWR_STATUS_ACIN_AVAIL);
+
+		/* ACIN_PATH_SEL disables ACIN even if ACIN_AVAIL is set. */
+		if (val->intval && power->has_acin_path_sel) {
+			ret = regmap_read(power->regmap, AXP813_ACIN_PATH_CTRL,
+					  &reg);
+			if (ret)
+				return ret;
+
+			val->intval = !!(reg & AXP813_ACIN_PATH_SEL);
+		}
+
 		return 0;
 
 	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
@@ -224,21 +238,25 @@ static const struct power_supply_desc axp813_ac_power_desc = {
 struct axp_data {
 	const struct power_supply_desc	*power_desc;
 	bool				acin_adc;
+	bool				acin_path_sel;
 };
 
 static const struct axp_data axp20x_data = {
-	.power_desc = &axp20x_ac_power_desc,
-	.acin_adc = true,
+	.power_desc	= &axp20x_ac_power_desc,
+	.acin_adc	= true,
+	.acin_path_sel	= false,
 };
 
 static const struct axp_data axp22x_data = {
-	.power_desc = &axp22x_ac_power_desc,
-	.acin_adc = false,
+	.power_desc	= &axp22x_ac_power_desc,
+	.acin_adc	= false,
+	.acin_path_sel	= false,
 };
 
 static const struct axp_data axp813_data = {
-	.power_desc = &axp813_ac_power_desc,
-	.acin_adc = false,
+	.power_desc	= &axp813_ac_power_desc,
+	.acin_adc	= false,
+	.acin_path_sel	= true,
 };
 
 static int axp20x_ac_power_probe(struct platform_device *pdev)
@@ -282,6 +300,7 @@ static int axp20x_ac_power_probe(struct platform_device *pdev)
 	}
 
 	power->regmap = dev_get_regmap(pdev->dev.parent, NULL);
+	power->has_acin_path_sel = axp_data->acin_path_sel;
 
 	platform_set_drvdata(pdev, power);
 
diff --git a/drivers/power/supply/axp288_charger.c b/drivers/power/supply/axp288_charger.c
index 1bbba6bba673..cf4c67b2d235 100644
--- a/drivers/power/supply/axp288_charger.c
+++ b/drivers/power/supply/axp288_charger.c
@@ -21,6 +21,7 @@
 #include <linux/property.h>
 #include <linux/mfd/axp20x.h>
 #include <linux/extcon.h>
+#include <linux/dmi.h>
 
 #define PS_STAT_VBUS_TRIGGER		BIT(0)
 #define PS_STAT_BAT_CHRG_DIR		BIT(2)
@@ -545,6 +546,49 @@ out:
 	return IRQ_HANDLED;
 }
 
+/*
+ * The HP Pavilion x2 10 series comes in a number of variants:
+ * Bay Trail SoC    + AXP288 PMIC, DMI_BOARD_NAME: "815D"
+ * Cherry Trail SoC + AXP288 PMIC, DMI_BOARD_NAME: "813E"
+ * Cherry Trail SoC + TI PMIC,     DMI_BOARD_NAME: "827C" or "82F4"
+ *
+ * The variants with the AXP288 PMIC are all kinds of special:
+ *
+ * 1. All variants use a Type-C connector which the AXP288 does not support, so
+ * when using a Type-C charger it is not recognized. Unlike most AXP288 devices,
+ * this model actually has mostly working ACPI AC / Battery code, the ACPI code
+ * "solves" this by simply setting the input_current_limit to 3A.
+ * There are still some issues with the ACPI code, so we use this native driver,
+ * and to solve the charging not working (500mA is not enough) issue we hardcode
+ * the 3A input_current_limit like the ACPI code does.
+ *
+ * 2. If no charger is connected the machine boots with the vbus-path disabled.
+ * Normally this is done when a 5V boost converter is active to avoid the PMIC
+ * trying to charge from the 5V boost converter's output. This is done when
+ * an OTG host cable is inserted and the ID pin on the micro-B receptacle is
+ * pulled low and the ID pin has an ACPI event handler associated with it
+ * which re-enables the vbus-path when the ID pin is pulled high when the
+ * OTG host cable is removed. The Type-C connector has no ID pin, there is
+ * no ID pin handler and there appears to be no 5V boost converter, so we
+ * end up not charging because the vbus-path is disabled, until we unplug
+ * the charger which automatically clears the vbus-path disable bit and then
+ * on the second plug-in of the adapter we start charging. To solve the not
+ * charging on first charger plugin we unconditionally enable the vbus-path at
+ * probe on this model, which is safe since there is no 5V boost converter.
+ */
+static const struct dmi_system_id axp288_hp_x2_dmi_ids[] = {
+	{
+		/*
+		 * Bay Trail model has "Hewlett-Packard" as sys_vendor, Cherry
+		 * Trail model has "HP", so we only match on product_name.
+		 */
+		.matches = {
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion x2 Detachable"),
+		},
+	},
+	{} /* Terminating entry */
+};
+
 static void axp288_charger_extcon_evt_worker(struct work_struct *work)
 {
 	struct axp288_chrg_info *info =
@@ -568,7 +612,11 @@ static void axp288_charger_extcon_evt_worker(struct work_struct *work)
 	}
 
 	/* Determine cable/charger type */
-	if (extcon_get_state(edev, EXTCON_CHG_USB_SDP) > 0) {
+	if (dmi_check_system(axp288_hp_x2_dmi_ids)) {
+		/* See comment above axp288_hp_x2_dmi_ids declaration */
+		dev_dbg(&info->pdev->dev, "HP X2 with Type-C, setting inlmt to 3A\n");
+		current_limit = 3000000;
+	} else if (extcon_get_state(edev, EXTCON_CHG_USB_SDP) > 0) {
 		dev_dbg(&info->pdev->dev, "USB SDP charger is connected\n");
 		current_limit = 500000;
 	} else if (extcon_get_state(edev, EXTCON_CHG_USB_CDP) > 0) {
@@ -685,6 +733,13 @@ static int charger_init_hw_regs(struct axp288_chrg_info *info)
 		return ret;
 	}
 
+	if (dmi_check_system(axp288_hp_x2_dmi_ids)) {
+		/* See comment above axp288_hp_x2_dmi_ids declaration */
+		ret = axp288_charger_vbus_path_select(info, true);
+		if (ret < 0)
+			return ret;
+	}
+
 	/* Read current charge voltage and current limit */
 	ret = regmap_read(info->regmap, AXP20X_CHRG_CTRL1, &val);
 	if (ret < 0) {
diff --git a/drivers/power/supply/axp288_fuel_gauge.c b/drivers/power/supply/axp288_fuel_gauge.c
index 44169dabb705..7ff2b779cb5b 100644
--- a/drivers/power/supply/axp288_fuel_gauge.c
+++ b/drivers/power/supply/axp288_fuel_gauge.c
@@ -699,14 +699,14 @@ static const struct dmi_system_id axp288_fuel_gauge_blacklist[] = {
 	{
 		/* Intel Cherry Trail Compute Stick, Windows version */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Intel Corporation"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Intel"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "STK1AW32SC"),
 		},
 	},
 	{
 		/* Intel Cherry Trail Compute Stick, version without an OS */
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Intel Corporation"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Intel"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "STK1A32SC"),
 		},
 	},
diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c
index 195c18c2f426..664e50103eaa 100644
--- a/drivers/power/supply/bq27xxx_battery.c
+++ b/drivers/power/supply/bq27xxx_battery.c
@@ -1885,7 +1885,10 @@ int bq27xxx_battery_setup(struct bq27xxx_device_info *di)
 
 	di->bat = power_supply_register_no_ws(di->dev, psy_desc, &psy_cfg);
 	if (IS_ERR(di->bat)) {
-		dev_err(di->dev, "failed to register battery\n");
+		if (PTR_ERR(di->bat) == -EPROBE_DEFER)
+			dev_dbg(di->dev, "failed to register battery, deferring probe\n");
+		else
+			dev_err(di->dev, "failed to register battery\n");
 		return PTR_ERR(di->bat);
 	}
 
diff --git a/drivers/power/supply/ingenic-battery.c b/drivers/power/supply/ingenic-battery.c
index 35816d4b3012..2748715c4c75 100644
--- a/drivers/power/supply/ingenic-battery.c
+++ b/drivers/power/supply/ingenic-battery.c
@@ -100,10 +100,17 @@ static int ingenic_battery_set_scale(struct ingenic_battery *bat)
 		return -EINVAL;
 	}
 
-	return iio_write_channel_attribute(bat->channel,
-					   scale_raw[best_idx],
-					   scale_raw[best_idx + 1],
-					   IIO_CHAN_INFO_SCALE);
+	/* Only set scale if there is more than one (fractional) entry */
+	if (scale_len > 2) {
+		ret = iio_write_channel_attribute(bat->channel,
+						  scale_raw[best_idx],
+						  scale_raw[best_idx + 1],
+						  IIO_CHAN_INFO_SCALE);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
 }
 
 static enum power_supply_property ingenic_battery_properties[] = {
diff --git a/drivers/power/supply/lp8788-charger.c b/drivers/power/supply/lp8788-charger.c
index 84a206f42a8e..e7931ffb7151 100644
--- a/drivers/power/supply/lp8788-charger.c
+++ b/drivers/power/supply/lp8788-charger.c
@@ -572,27 +572,14 @@ static void lp8788_setup_adc_channel(struct device *dev,
 		return;
 
 	/* ADC channel for battery voltage */
-	chan = iio_channel_get(dev, pdata->adc_vbatt);
+	chan = devm_iio_channel_get(dev, pdata->adc_vbatt);
 	pchg->chan[LP8788_VBATT] = IS_ERR(chan) ? NULL : chan;
 
 	/* ADC channel for battery temperature */
-	chan = iio_channel_get(dev, pdata->adc_batt_temp);
+	chan = devm_iio_channel_get(dev, pdata->adc_batt_temp);
 	pchg->chan[LP8788_BATT_TEMP] = IS_ERR(chan) ? NULL : chan;
 }
 
-static void lp8788_release_adc_channel(struct lp8788_charger *pchg)
-{
-	int i;
-
-	for (i = 0; i < LP8788_NUM_CHG_ADC; i++) {
-		if (!pchg->chan[i])
-			continue;
-
-		iio_channel_release(pchg->chan[i]);
-		pchg->chan[i] = NULL;
-	}
-}
-
 static ssize_t lp8788_show_charger_status(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
@@ -735,7 +722,6 @@ static int lp8788_charger_remove(struct platform_device *pdev)
 	flush_work(&pchg->charger_work);
 	lp8788_irq_unregister(pdev, pchg);
 	lp8788_psy_unregister(pchg);
-	lp8788_release_adc_channel(pchg);
 
 	return 0;
 }
diff --git a/drivers/power/supply/ltc2941-battery-gauge.c b/drivers/power/supply/ltc2941-battery-gauge.c
index da49436176cd..30a9014b2f95 100644
--- a/drivers/power/supply/ltc2941-battery-gauge.c
+++ b/drivers/power/supply/ltc2941-battery-gauge.c
@@ -449,7 +449,7 @@ static int ltc294x_i2c_remove(struct i2c_client *client)
 {
 	struct ltc294x_info *info = i2c_get_clientdata(client);
 
-	cancel_delayed_work(&info->work);
+	cancel_delayed_work_sync(&info->work);
 	power_supply_unregister(info->supply);
 	return 0;
 }
diff --git a/drivers/power/supply/smb347-charger.c b/drivers/power/supply/smb347-charger.c
index c1d124b8be0c..d102921b3ab2 100644
--- a/drivers/power/supply/smb347-charger.c
+++ b/drivers/power/supply/smb347-charger.c
@@ -1138,6 +1138,7 @@ static bool smb347_volatile_reg(struct device *dev, unsigned int reg)
 	switch (reg) {
 	case IRQSTAT_A:
 	case IRQSTAT_C:
+	case IRQSTAT_D:
 	case IRQSTAT_E:
 	case IRQSTAT_F:
 	case STAT_A:
diff --git a/drivers/power/supply/ucs1002_power.c b/drivers/power/supply/ucs1002_power.c
index 1c89d030c045..1b80ae479e7d 100644
--- a/drivers/power/supply/ucs1002_power.c
+++ b/drivers/power/supply/ucs1002_power.c
@@ -336,7 +336,7 @@ static int ucs1002_get_usb_type(struct ucs1002_info *info,
 	case F_ACTIVE_MODE_BC12_CDP:
 		type = POWER_SUPPLY_USB_TYPE_CDP;
 		break;
-	};
+	}
 
 	val->intval = type;
 
diff --git a/drivers/pwm/pwm-bcm-iproc.c b/drivers/pwm/pwm-bcm-iproc.c
index 31b01035d0ab..8cfba3614e60 100644
--- a/drivers/pwm/pwm-bcm-iproc.c
+++ b/drivers/pwm/pwm-bcm-iproc.c
@@ -85,8 +85,6 @@ static void iproc_pwmc_get_state(struct pwm_chip *chip, struct pwm_device *pwm,
 	u64 tmp, multi, rate;
 	u32 value, prescale;
 
-	rate = clk_get_rate(ip->clk);
-
 	value = readl(ip->base + IPROC_PWM_CTRL_OFFSET);
 
 	if (value & BIT(IPROC_PWM_CTRL_EN_SHIFT(pwm->hwpwm)))
@@ -99,6 +97,13 @@ static void iproc_pwmc_get_state(struct pwm_chip *chip, struct pwm_device *pwm,
 	else
 		state->polarity = PWM_POLARITY_INVERSED;
 
+	rate = clk_get_rate(ip->clk);
+	if (rate == 0) {
+		state->period = 0;
+		state->duty_cycle = 0;
+		return;
+	}
+
 	value = readl(ip->base + IPROC_PWM_PRESCALE_OFFSET);
 	prescale = value >> IPROC_PWM_PRESCALE_SHIFT(pwm->hwpwm);
 	prescale &= IPROC_PWM_PRESCALE_MAX;
diff --git a/drivers/pwm/pwm-bcm2835.c b/drivers/pwm/pwm-bcm2835.c
index 5652f461d994..6a1cb67f0faf 100644
--- a/drivers/pwm/pwm-bcm2835.c
+++ b/drivers/pwm/pwm-bcm2835.c
@@ -163,6 +163,7 @@ static int bcm2835_pwm_probe(struct platform_device *pdev)
 
 	pc->chip.dev = &pdev->dev;
 	pc->chip.ops = &bcm2835_pwm_ops;
+	pc->chip.base = -1;
 	pc->chip.npwm = 2;
 	pc->chip.of_xlate = of_pwm_xlate_with_flags;
 	pc->chip.of_pwm_n_cells = 3;
diff --git a/drivers/pwm/pwm-img.c b/drivers/pwm/pwm-img.c
index c9e57bd109fb..599a0f66a384 100644
--- a/drivers/pwm/pwm-img.c
+++ b/drivers/pwm/pwm-img.c
@@ -129,8 +129,10 @@ static int img_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
 	duty = DIV_ROUND_UP(timebase * duty_ns, period_ns);
 
 	ret = pm_runtime_get_sync(chip->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_autosuspend(chip->dev);
 		return ret;
+	}
 
 	val = img_pwm_readl(pwm_chip, PWM_CTRL_CFG);
 	val &= ~(PWM_CTRL_CFG_DIV_MASK << PWM_CTRL_CFG_DIV_SHIFT(pwm->hwpwm));
@@ -331,8 +333,10 @@ static int img_pwm_remove(struct platform_device *pdev)
 	int ret;
 
 	ret = pm_runtime_get_sync(&pdev->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put(&pdev->dev);
 		return ret;
+	}
 
 	for (i = 0; i < pwm_chip->chip.npwm; i++) {
 		val = img_pwm_readl(pwm_chip, PWM_CTRL_CFG);
diff --git a/drivers/pwm/pwm-meson.c b/drivers/pwm/pwm-meson.c
index fb5a369b1a8d..dc5fc7bb6bfe 100644
--- a/drivers/pwm/pwm-meson.c
+++ b/drivers/pwm/pwm-meson.c
@@ -433,8 +433,17 @@ static const struct meson_pwm_data pwm_axg_ao_data = {
 	.num_parents = ARRAY_SIZE(pwm_axg_ao_parent_names),
 };
 
+static const char * const pwm_g12a_ao_ab_parent_names[] = {
+	"xtal", "aoclk81", "fclk_div4", "fclk_div5"
+};
+
+static const struct meson_pwm_data pwm_g12a_ao_ab_data = {
+	.parent_names = pwm_g12a_ao_ab_parent_names,
+	.num_parents = ARRAY_SIZE(pwm_g12a_ao_ab_parent_names),
+};
+
 static const char * const pwm_g12a_ao_cd_parent_names[] = {
-	"aoclk81", "xtal",
+	"xtal", "aoclk81",
 };
 
 static const struct meson_pwm_data pwm_g12a_ao_cd_data = {
@@ -478,7 +487,7 @@ static const struct of_device_id meson_pwm_matches[] = {
 	},
 	{
 		.compatible = "amlogic,meson-g12a-ao-pwm-ab",
-		.data = &pwm_axg_ao_data
+		.data = &pwm_g12a_ao_ab_data
 	},
 	{
 		.compatible = "amlogic,meson-g12a-ao-pwm-cd",
diff --git a/drivers/pwm/pwm-omap-dmtimer.c b/drivers/pwm/pwm-omap-dmtimer.c
index 00772fc53490..88a3c5690fea 100644
--- a/drivers/pwm/pwm-omap-dmtimer.c
+++ b/drivers/pwm/pwm-omap-dmtimer.c
@@ -256,7 +256,7 @@ static int pwm_omap_dmtimer_probe(struct platform_device *pdev)
 	if (!timer_pdev) {
 		dev_err(&pdev->dev, "Unable to find Timer pdev\n");
 		ret = -ENODEV;
-		goto put;
+		goto err_find_timer_pdev;
 	}
 
 	timer_pdata = dev_get_platdata(&timer_pdev->dev);
@@ -264,7 +264,7 @@ static int pwm_omap_dmtimer_probe(struct platform_device *pdev)
 		dev_dbg(&pdev->dev,
 			 "dmtimer pdata structure NULL, deferring probe\n");
 		ret = -EPROBE_DEFER;
-		goto put;
+		goto err_platdata;
 	}
 
 	pdata = timer_pdata->timer_ops;
@@ -283,30 +283,25 @@ static int pwm_omap_dmtimer_probe(struct platform_device *pdev)
 	    !pdata->write_counter) {
 		dev_err(&pdev->dev, "Incomplete dmtimer pdata structure\n");
 		ret = -EINVAL;
-		goto put;
+		goto err_platdata;
 	}
 
 	if (!of_get_property(timer, "ti,timer-pwm", NULL)) {
 		dev_err(&pdev->dev, "Missing ti,timer-pwm capability\n");
 		ret = -ENODEV;
-		goto put;
+		goto err_timer_property;
 	}
 
 	dm_timer = pdata->request_by_node(timer);
 	if (!dm_timer) {
 		ret = -EPROBE_DEFER;
-		goto put;
+		goto err_request_timer;
 	}
 
-put:
-	of_node_put(timer);
-	if (ret < 0)
-		return ret;
-
 	omap = devm_kzalloc(&pdev->dev, sizeof(*omap), GFP_KERNEL);
 	if (!omap) {
-		pdata->free(dm_timer);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err_alloc_omap;
 	}
 
 	omap->pdata = pdata;
@@ -339,27 +334,56 @@ put:
 	ret = pwmchip_add(&omap->chip);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to register PWM\n");
-		omap->pdata->free(omap->dm_timer);
-		return ret;
+		goto err_pwmchip_add;
 	}
 
+	of_node_put(timer);
+
 	platform_set_drvdata(pdev, omap);
 
 	return 0;
+
+err_pwmchip_add:
+
+	/*
+	 * *omap is allocated using devm_kzalloc,
+	 * so no free necessary here
+	 */
+err_alloc_omap:
+
+	pdata->free(dm_timer);
+err_request_timer:
+
+err_timer_property:
+err_platdata:
+
+	put_device(&timer_pdev->dev);
+err_find_timer_pdev:
+
+	of_node_put(timer);
+
+	return ret;
 }
 
 static int pwm_omap_dmtimer_remove(struct platform_device *pdev)
 {
 	struct pwm_omap_dmtimer_chip *omap = platform_get_drvdata(pdev);
+	int ret;
+
+	ret = pwmchip_remove(&omap->chip);
+	if (ret)
+		return ret;
 
 	if (pm_runtime_active(&omap->dm_timer_pdev->dev))
 		omap->pdata->stop(omap->dm_timer);
 
 	omap->pdata->free(omap->dm_timer);
 
+	put_device(&omap->dm_timer_pdev->dev);
+
 	mutex_destroy(&omap->mutex);
 
-	return pwmchip_remove(&omap->chip);
+	return 0;
 }
 
 static const struct of_device_id pwm_omap_dmtimer_of_match[] = {
diff --git a/drivers/pwm/pwm-pca9685.c b/drivers/pwm/pwm-pca9685.c
index 168684b02ebc..590375be5214 100644
--- a/drivers/pwm/pwm-pca9685.c
+++ b/drivers/pwm/pwm-pca9685.c
@@ -20,6 +20,7 @@
 #include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/pm_runtime.h>
+#include <linux/bitmap.h>
 
 /*
  * Because the PCA9685 has only one prescaler per chip, changing the period of
@@ -74,6 +75,7 @@ struct pca9685 {
 #if IS_ENABLED(CONFIG_GPIOLIB)
 	struct mutex lock;
 	struct gpio_chip gpio;
+	DECLARE_BITMAP(pwms_inuse, PCA9685_MAXCHAN + 1);
 #endif
 };
 
@@ -83,51 +85,51 @@ static inline struct pca9685 *to_pca(struct pwm_chip *chip)
 }
 
 #if IS_ENABLED(CONFIG_GPIOLIB)
-static int pca9685_pwm_gpio_request(struct gpio_chip *gpio, unsigned int offset)
+static bool pca9685_pwm_test_and_set_inuse(struct pca9685 *pca, int pwm_idx)
 {
-	struct pca9685 *pca = gpiochip_get_data(gpio);
-	struct pwm_device *pwm;
+	bool is_inuse;
 
 	mutex_lock(&pca->lock);
-
-	pwm = &pca->chip.pwms[offset];
-
-	if (pwm->flags & (PWMF_REQUESTED | PWMF_EXPORTED)) {
-		mutex_unlock(&pca->lock);
-		return -EBUSY;
+	if (pwm_idx >= PCA9685_MAXCHAN) {
+		/*
+		 * "all LEDs" channel:
+		 * pretend already in use if any of the PWMs are requested
+		 */
+		if (!bitmap_empty(pca->pwms_inuse, PCA9685_MAXCHAN)) {
+			is_inuse = true;
+			goto out;
+		}
+	} else {
+		/*
+		 * regular channel:
+		 * pretend already in use if the "all LEDs" channel is requested
+		 */
+		if (test_bit(PCA9685_MAXCHAN, pca->pwms_inuse)) {
+			is_inuse = true;
+			goto out;
+		}
 	}
-
-	pwm_set_chip_data(pwm, (void *)1);
-
+	is_inuse = test_and_set_bit(pwm_idx, pca->pwms_inuse);
+out:
 	mutex_unlock(&pca->lock);
-	pm_runtime_get_sync(pca->chip.dev);
-	return 0;
+	return is_inuse;
 }
 
-static bool pca9685_pwm_is_gpio(struct pca9685 *pca, struct pwm_device *pwm)
+static void pca9685_pwm_clear_inuse(struct pca9685 *pca, int pwm_idx)
 {
-	bool is_gpio = false;
-
 	mutex_lock(&pca->lock);
+	clear_bit(pwm_idx, pca->pwms_inuse);
+	mutex_unlock(&pca->lock);
+}
 
-	if (pwm->hwpwm >= PCA9685_MAXCHAN) {
-		unsigned int i;
-
-		/*
-		 * Check if any of the GPIOs are requested and in that case
-		 * prevent using the "all LEDs" channel.
-		 */
-		for (i = 0; i < pca->gpio.ngpio; i++)
-			if (gpiochip_is_requested(&pca->gpio, i)) {
-				is_gpio = true;
-				break;
-			}
-	} else if (pwm_get_chip_data(pwm)) {
-		is_gpio = true;
-	}
+static int pca9685_pwm_gpio_request(struct gpio_chip *gpio, unsigned int offset)
+{
+	struct pca9685 *pca = gpiochip_get_data(gpio);
 
-	mutex_unlock(&pca->lock);
-	return is_gpio;
+	if (pca9685_pwm_test_and_set_inuse(pca, offset))
+		return -EBUSY;
+	pm_runtime_get_sync(pca->chip.dev);
+	return 0;
 }
 
 static int pca9685_pwm_gpio_get(struct gpio_chip *gpio, unsigned int offset)
@@ -159,13 +161,10 @@ static void pca9685_pwm_gpio_set(struct gpio_chip *gpio, unsigned int offset,
 static void pca9685_pwm_gpio_free(struct gpio_chip *gpio, unsigned int offset)
 {
 	struct pca9685 *pca = gpiochip_get_data(gpio);
-	struct pwm_device *pwm;
 
 	pca9685_pwm_gpio_set(gpio, offset, 0);
 	pm_runtime_put(pca->chip.dev);
-	mutex_lock(&pca->lock);
-	pwm = &pca->chip.pwms[offset];
-	mutex_unlock(&pca->lock);
+	pca9685_pwm_clear_inuse(pca, offset);
 }
 
 static int pca9685_pwm_gpio_get_direction(struct gpio_chip *chip,
@@ -217,12 +216,17 @@ static int pca9685_pwm_gpio_probe(struct pca9685 *pca)
 	return devm_gpiochip_add_data(dev, &pca->gpio, pca);
 }
 #else
-static inline bool pca9685_pwm_is_gpio(struct pca9685 *pca,
-				       struct pwm_device *pwm)
+static inline bool pca9685_pwm_test_and_set_inuse(struct pca9685 *pca,
+						  int pwm_idx)
 {
 	return false;
 }
 
+static inline void
+pca9685_pwm_clear_inuse(struct pca9685 *pca, int pwm_idx)
+{
+}
+
 static inline int pca9685_pwm_gpio_probe(struct pca9685 *pca)
 {
 	return 0;
@@ -406,7 +410,7 @@ static int pca9685_pwm_request(struct pwm_chip *chip, struct pwm_device *pwm)
 {
 	struct pca9685 *pca = to_pca(chip);
 
-	if (pca9685_pwm_is_gpio(pca, pwm))
+	if (pca9685_pwm_test_and_set_inuse(pca, pwm->hwpwm))
 		return -EBUSY;
 	pm_runtime_get_sync(chip->dev);
 
@@ -415,8 +419,11 @@ static int pca9685_pwm_request(struct pwm_chip *chip, struct pwm_device *pwm)
 
 static void pca9685_pwm_free(struct pwm_chip *chip, struct pwm_device *pwm)
 {
+	struct pca9685 *pca = to_pca(chip);
+
 	pca9685_pwm_disable(chip, pwm);
 	pm_runtime_put(chip->dev);
+	pca9685_pwm_clear_inuse(pca, pwm->hwpwm);
 }
 
 static const struct pwm_ops pca9685_pwm_ops = {
diff --git a/drivers/pwm/pwm-rcar.c b/drivers/pwm/pwm-rcar.c
index cfe7dd1b448e..e4e0aa56fffb 100644
--- a/drivers/pwm/pwm-rcar.c
+++ b/drivers/pwm/pwm-rcar.c
@@ -228,24 +228,28 @@ static int rcar_pwm_probe(struct platform_device *pdev)
 	rcar_pwm->chip.base = -1;
 	rcar_pwm->chip.npwm = 1;
 
+	pm_runtime_enable(&pdev->dev);
+
 	ret = pwmchip_add(&rcar_pwm->chip);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to register PWM chip: %d\n", ret);
+		pm_runtime_disable(&pdev->dev);
 		return ret;
 	}
 
-	pm_runtime_enable(&pdev->dev);
-
 	return 0;
 }
 
 static int rcar_pwm_remove(struct platform_device *pdev)
 {
 	struct rcar_pwm_chip *rcar_pwm = platform_get_drvdata(pdev);
+	int ret;
+
+	ret = pwmchip_remove(&rcar_pwm->chip);
 
 	pm_runtime_disable(&pdev->dev);
 
-	return pwmchip_remove(&rcar_pwm->chip);
+	return ret;
 }
 
 static const struct of_device_id rcar_pwm_of_table[] = {
diff --git a/drivers/pwm/pwm-renesas-tpu.c b/drivers/pwm/pwm-renesas-tpu.c
index 4a855a21b782..8032acc84161 100644
--- a/drivers/pwm/pwm-renesas-tpu.c
+++ b/drivers/pwm/pwm-renesas-tpu.c
@@ -415,16 +415,17 @@ static int tpu_probe(struct platform_device *pdev)
 	tpu->chip.base = -1;
 	tpu->chip.npwm = TPU_CHANNEL_MAX;
 
+	pm_runtime_enable(&pdev->dev);
+
 	ret = pwmchip_add(&tpu->chip);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to register PWM chip\n");
+		pm_runtime_disable(&pdev->dev);
 		return ret;
 	}
 
 	dev_info(&pdev->dev, "TPU PWM %d registered\n", tpu->pdev->id);
 
-	pm_runtime_enable(&pdev->dev);
-
 	return 0;
 }
 
@@ -434,12 +435,10 @@ static int tpu_remove(struct platform_device *pdev)
 	int ret;
 
 	ret = pwmchip_remove(&tpu->chip);
-	if (ret)
-		return ret;
 
 	pm_runtime_disable(&pdev->dev);
 
-	return 0;
+	return ret;
 }
 
 #ifdef CONFIG_OF
diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c
index 8155f59ece38..10af330153b5 100644
--- a/drivers/rapidio/devices/rio_mport_cdev.c
+++ b/drivers/rapidio/devices/rio_mport_cdev.c
@@ -877,6 +877,11 @@ rio_dma_transfer(struct file *filp, u32 transfer_mode,
 				rmcd_error("pinned %ld out of %ld pages",
 					   pinned, nr_pages);
 			ret = -EFAULT;
+			/*
+			 * Set nr_pages up to mean "how many pages to unpin, in
+			 * the error handler:
+			 */
+			nr_pages = pinned;
 			goto err_pg;
 		}
 
diff --git a/drivers/regulator/ab8500.c b/drivers/regulator/ab8500.c
index efb2f01a9101..f60e1b26c2d2 100644
--- a/drivers/regulator/ab8500.c
+++ b/drivers/regulator/ab8500.c
@@ -953,23 +953,6 @@ static struct ab8500_regulator_info
 		.update_val_idle	= 0x82,
 		.update_val_normal	= 0x02,
 	},
-	[AB8505_LDO_USB] = {
-		.desc = {
-			.name           = "LDO-USB",
-			.ops            = &ab8500_regulator_mode_ops,
-			.type           = REGULATOR_VOLTAGE,
-			.id             = AB8505_LDO_USB,
-			.owner          = THIS_MODULE,
-			.n_voltages     = 1,
-			.volt_table	= fixed_3300000_voltage,
-		},
-		.update_bank            = 0x03,
-		.update_reg             = 0x82,
-		.update_mask            = 0x03,
-		.update_val		= 0x01,
-		.update_val_idle	= 0x03,
-		.update_val_normal	= 0x01,
-	},
 	[AB8505_LDO_AUDIO] = {
 		.desc = {
 			.name		= "LDO-AUDIO",
diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c
index 989506bd90b1..16f0c8570036 100644
--- a/drivers/regulator/axp20x-regulator.c
+++ b/drivers/regulator/axp20x-regulator.c
@@ -413,10 +413,13 @@ static int axp20x_set_ramp_delay(struct regulator_dev *rdev, int ramp)
 		int i;
 
 		for (i = 0; i < rate_count; i++) {
-			if (ramp <= slew_rates[i])
-				cfg = AXP20X_DCDC2_LDO3_V_RAMP_LDO3_RATE(i);
-			else
+			if (ramp > slew_rates[i])
 				break;
+
+			if (id == AXP20X_DCDC2)
+				cfg = AXP20X_DCDC2_LDO3_V_RAMP_DCDC2_RATE(i);
+			else
+				cfg = AXP20X_DCDC2_LDO3_V_RAMP_LDO3_RATE(i);
 		}
 
 		if (cfg == 0xff) {
@@ -605,7 +608,7 @@ static const struct regulator_desc axp22x_regulators[] = {
 		 AXP22X_PWR_OUT_CTRL2, AXP22X_PWR_OUT_ELDO1_MASK),
 	AXP_DESC(AXP22X, ELDO2, "eldo2", "eldoin", 700, 3300, 100,
 		 AXP22X_ELDO2_V_OUT, AXP22X_ELDO2_V_OUT_MASK,
-		 AXP22X_PWR_OUT_CTRL2, AXP22X_PWR_OUT_ELDO1_MASK),
+		 AXP22X_PWR_OUT_CTRL2, AXP22X_PWR_OUT_ELDO2_MASK),
 	AXP_DESC(AXP22X, ELDO3, "eldo3", "eldoin", 700, 3300, 100,
 		 AXP22X_ELDO3_V_OUT, AXP22X_ELDO3_V_OUT_MASK,
 		 AXP22X_PWR_OUT_CTRL2, AXP22X_PWR_OUT_ELDO3_MASK),
diff --git a/drivers/regulator/bd70528-regulator.c b/drivers/regulator/bd70528-regulator.c
index 30e3ed430a8a..457dde3191a0 100644
--- a/drivers/regulator/bd70528-regulator.c
+++ b/drivers/regulator/bd70528-regulator.c
@@ -102,7 +102,6 @@ static const struct regulator_ops bd70528_ldo_ops = {
 	.set_voltage_sel = regulator_set_voltage_sel_regmap,
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
 	.set_voltage_time_sel = regulator_set_voltage_time_sel,
-	.set_ramp_delay = bd70528_set_ramp_delay,
 };
 
 static const struct regulator_ops bd70528_led_ops = {
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 40abd7746f51..cb5f33b97082 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -23,6 +23,7 @@
 #include <linux/regmap.h>
 #include <linux/regulator/of_regulator.h>
 #include <linux/regulator/consumer.h>
+#include <linux/regulator/coupler.h>
 #include <linux/regulator/driver.h>
 #include <linux/regulator/machine.h>
 #include <linux/module.h>
@@ -50,6 +51,7 @@ static DEFINE_MUTEX(regulator_list_mutex);
 static LIST_HEAD(regulator_map_list);
 static LIST_HEAD(regulator_ena_gpio_list);
 static LIST_HEAD(regulator_supply_alias_list);
+static LIST_HEAD(regulator_coupler_list);
 static bool has_full_constraints;
 
 static struct dentry *debugfs_root;
@@ -93,7 +95,6 @@ struct regulator_supply_alias {
 
 static int _regulator_is_enabled(struct regulator_dev *rdev);
 static int _regulator_disable(struct regulator *regulator);
-static int _regulator_get_voltage(struct regulator_dev *rdev);
 static int _regulator_get_current_limit(struct regulator_dev *rdev);
 static unsigned int _regulator_get_mode(struct regulator_dev *rdev);
 static int _notifier_call_chain(struct regulator_dev *rdev,
@@ -102,15 +103,12 @@ static int _regulator_do_set_voltage(struct regulator_dev *rdev,
 				     int min_uV, int max_uV);
 static int regulator_balance_voltage(struct regulator_dev *rdev,
 				     suspend_state_t state);
-static int regulator_set_voltage_rdev(struct regulator_dev *rdev,
-				      int min_uV, int max_uV,
-				      suspend_state_t state);
 static struct regulator *create_regulator(struct regulator_dev *rdev,
 					  struct device *dev,
 					  const char *supply_name);
 static void _regulator_put(struct regulator *regulator);
 
-static const char *rdev_get_name(struct regulator_dev *rdev)
+const char *rdev_get_name(struct regulator_dev *rdev)
 {
 	if (rdev->constraints && rdev->constraints->name)
 		return rdev->constraints->name;
@@ -424,8 +422,8 @@ static struct device_node *of_get_regulator(struct device *dev, const char *supp
 }
 
 /* Platform voltage constraint check */
-static int regulator_check_voltage(struct regulator_dev *rdev,
-				   int *min_uV, int *max_uV)
+int regulator_check_voltage(struct regulator_dev *rdev,
+			    int *min_uV, int *max_uV)
 {
 	BUG_ON(*min_uV > *max_uV);
 
@@ -457,9 +455,9 @@ static int regulator_check_states(suspend_state_t state)
 /* Make sure we select a voltage that suits the needs of all
  * regulator consumers
  */
-static int regulator_check_consumers(struct regulator_dev *rdev,
-				     int *min_uV, int *max_uV,
-				     suspend_state_t state)
+int regulator_check_consumers(struct regulator_dev *rdev,
+			      int *min_uV, int *max_uV,
+			      suspend_state_t state)
 {
 	struct regulator *regulator;
 	struct regulator_voltage *voltage;
@@ -570,7 +568,7 @@ static ssize_t regulator_uV_show(struct device *dev,
 	ssize_t ret;
 
 	regulator_lock(rdev);
-	ret = sprintf(buf, "%d\n", _regulator_get_voltage(rdev));
+	ret = sprintf(buf, "%d\n", regulator_get_voltage_rdev(rdev));
 	regulator_unlock(rdev);
 
 	return ret;
@@ -941,7 +939,7 @@ static int drms_uA_update(struct regulator_dev *rdev)
 			rdev_err(rdev, "failed to set load %d\n", current_uA);
 	} else {
 		/* get output voltage */
-		output_uV = _regulator_get_voltage(rdev);
+		output_uV = regulator_get_voltage_rdev(rdev);
 		if (output_uV <= 0) {
 			rdev_err(rdev, "invalid output voltage found\n");
 			return -EINVAL;
@@ -1054,7 +1052,7 @@ static void print_constraints(struct regulator_dev *rdev)
 
 	if (!constraints->min_uV ||
 	    constraints->min_uV != constraints->max_uV) {
-		ret = _regulator_get_voltage(rdev);
+		ret = regulator_get_voltage_rdev(rdev);
 		if (ret > 0)
 			count += scnprintf(buf + count, len - count,
 					   "at %d mV ", ret / 1000);
@@ -1113,7 +1111,7 @@ static int machine_constraints_voltage(struct regulator_dev *rdev,
 	if (rdev->constraints->apply_uV &&
 	    rdev->constraints->min_uV && rdev->constraints->max_uV) {
 		int target_min, target_max;
-		int current_uV = _regulator_get_voltage(rdev);
+		int current_uV = regulator_get_voltage_rdev(rdev);
 
 		if (current_uV == -ENOTRECOVERABLE) {
 			/* This regulator can't be read and must be initialized */
@@ -1123,7 +1121,7 @@ static int machine_constraints_voltage(struct regulator_dev *rdev,
 			_regulator_do_set_voltage(rdev,
 						  rdev->constraints->min_uV,
 						  rdev->constraints->max_uV);
-			current_uV = _regulator_get_voltage(rdev);
+			current_uV = regulator_get_voltage_rdev(rdev);
 		}
 
 		if (current_uV < 0) {
@@ -1934,8 +1932,8 @@ struct regulator *_regulator_get(struct device *dev, const char *id,
 	regulator = create_regulator(rdev, dev, id);
 	if (regulator == NULL) {
 		regulator = ERR_PTR(-ENOMEM);
-		put_device(&rdev->dev);
 		module_put(rdev->owner);
+		put_device(&rdev->dev);
 		return regulator;
 	}
 
@@ -2056,13 +2054,13 @@ static void _regulator_put(struct regulator *regulator)
 
 	rdev->open_count--;
 	rdev->exclusive = 0;
-	put_device(&rdev->dev);
 	regulator_unlock(rdev);
 
 	kfree_const(regulator->supply_name);
 	kfree(regulator);
 
 	module_put(rdev->owner);
+	put_device(&rdev->dev);
 }
 
 /**
@@ -3067,7 +3065,7 @@ static int _regulator_call_set_voltage(struct regulator_dev *rdev,
 	struct pre_voltage_change_data data;
 	int ret;
 
-	data.old_uV = _regulator_get_voltage(rdev);
+	data.old_uV = regulator_get_voltage_rdev(rdev);
 	data.min_uV = min_uV;
 	data.max_uV = max_uV;
 	ret = _notifier_call_chain(rdev, REGULATOR_EVENT_PRE_VOLTAGE_CHANGE,
@@ -3091,7 +3089,7 @@ static int _regulator_call_set_voltage_sel(struct regulator_dev *rdev,
 	struct pre_voltage_change_data data;
 	int ret;
 
-	data.old_uV = _regulator_get_voltage(rdev);
+	data.old_uV = regulator_get_voltage_rdev(rdev);
 	data.min_uV = uV;
 	data.max_uV = uV;
 	ret = _notifier_call_chain(rdev, REGULATOR_EVENT_PRE_VOLTAGE_CHANGE,
@@ -3144,7 +3142,7 @@ static int _regulator_do_set_voltage(struct regulator_dev *rdev,
 	unsigned int selector;
 	int old_selector = -1;
 	const struct regulator_ops *ops = rdev->desc->ops;
-	int old_uV = _regulator_get_voltage(rdev);
+	int old_uV = regulator_get_voltage_rdev(rdev);
 
 	trace_regulator_set_voltage(rdev_get_name(rdev), min_uV, max_uV);
 
@@ -3171,7 +3169,7 @@ static int _regulator_do_set_voltage(struct regulator_dev *rdev,
 				best_val = ops->list_voltage(rdev,
 							     selector);
 			else
-				best_val = _regulator_get_voltage(rdev);
+				best_val = regulator_get_voltage_rdev(rdev);
 		}
 
 	} else if (ops->set_voltage_sel) {
@@ -3290,7 +3288,7 @@ static int regulator_set_voltage_unlocked(struct regulator *regulator,
 	 * changing the voltage.
 	 */
 	if (!regulator_ops_is_valid(rdev, REGULATOR_CHANGE_VOLTAGE)) {
-		current_uV = _regulator_get_voltage(rdev);
+		current_uV = regulator_get_voltage_rdev(rdev);
 		if (min_uV <= current_uV && current_uV <= max_uV) {
 			voltage->min_uV = min_uV;
 			voltage->max_uV = max_uV;
@@ -3327,8 +3325,8 @@ out:
 	return ret;
 }
 
-static int regulator_set_voltage_rdev(struct regulator_dev *rdev, int min_uV,
-				      int max_uV, suspend_state_t state)
+int regulator_set_voltage_rdev(struct regulator_dev *rdev, int min_uV,
+			       int max_uV, suspend_state_t state)
 {
 	int best_supply_uV = 0;
 	int supply_change_uV = 0;
@@ -3356,7 +3354,7 @@ static int regulator_set_voltage_rdev(struct regulator_dev *rdev, int min_uV,
 
 		best_supply_uV += rdev->desc->min_dropout_uV;
 
-		current_supply_uV = _regulator_get_voltage(rdev->supply->rdev);
+		current_supply_uV = regulator_get_voltage_rdev(rdev->supply->rdev);
 		if (current_supply_uV < 0) {
 			ret = current_supply_uV;
 			goto out;
@@ -3396,6 +3394,7 @@ static int regulator_set_voltage_rdev(struct regulator_dev *rdev, int min_uV,
 out:
 	return ret;
 }
+EXPORT_SYMBOL_GPL(regulator_set_voltage_rdev);
 
 static int regulator_limit_voltage_step(struct regulator_dev *rdev,
 					int *current_uV, int *min_uV)
@@ -3407,7 +3406,7 @@ static int regulator_limit_voltage_step(struct regulator_dev *rdev,
 		return 1;
 
 	if (*current_uV < 0) {
-		*current_uV = _regulator_get_voltage(rdev);
+		*current_uV = regulator_get_voltage_rdev(rdev);
 
 		if (*current_uV < 0)
 			return *current_uV;
@@ -3436,11 +3435,10 @@ static int regulator_get_optimal_voltage(struct regulator_dev *rdev,
 	struct coupling_desc *c_desc = &rdev->coupling_desc;
 	struct regulator_dev **c_rdevs = c_desc->coupled_rdevs;
 	struct regulation_constraints *constraints = rdev->constraints;
-	int max_spread = constraints->max_spread;
 	int desired_min_uV = 0, desired_max_uV = INT_MAX;
 	int max_current_uV = 0, min_current_uV = INT_MAX;
 	int highest_min_uV = 0, target_uV, possible_uV;
-	int i, ret;
+	int i, ret, max_spread;
 	bool done;
 
 	*current_uV = -1;
@@ -3494,6 +3492,8 @@ static int regulator_get_optimal_voltage(struct regulator_dev *rdev,
 		}
 	}
 
+	max_spread = constraints->max_spread[0];
+
 	/*
 	 * Let target_uV be equal to the desired one if possible.
 	 * If not, set it to minimum voltage, allowed by other coupled
@@ -3511,7 +3511,7 @@ static int regulator_get_optimal_voltage(struct regulator_dev *rdev,
 		if (!_regulator_is_enabled(c_rdevs[i]))
 			continue;
 
-		tmp_act = _regulator_get_voltage(c_rdevs[i]);
+		tmp_act = regulator_get_voltage_rdev(c_rdevs[i]);
 		if (tmp_act < 0)
 			return tmp_act;
 
@@ -3553,7 +3553,7 @@ finish:
 	if (n_coupled > 1 && *current_uV == -1) {
 
 		if (_regulator_is_enabled(rdev)) {
-			ret = _regulator_get_voltage(rdev);
+			ret = regulator_get_voltage_rdev(rdev);
 			if (ret < 0)
 				return ret;
 
@@ -3575,9 +3575,11 @@ static int regulator_balance_voltage(struct regulator_dev *rdev,
 	struct regulator_dev **c_rdevs;
 	struct regulator_dev *best_rdev;
 	struct coupling_desc *c_desc = &rdev->coupling_desc;
+	struct regulator_coupler *coupler = c_desc->coupler;
 	int i, ret, n_coupled, best_min_uV, best_max_uV, best_c_rdev;
-	bool best_c_rdev_done, c_rdev_done[MAX_COUPLED];
 	unsigned int delta, best_delta;
+	unsigned long c_rdev_done = 0;
+	bool best_c_rdev_done;
 
 	c_rdevs = c_desc->coupled_rdevs;
 	n_coupled = c_desc->n_coupled;
@@ -3594,8 +3596,9 @@ static int regulator_balance_voltage(struct regulator_dev *rdev,
 		return -EPERM;
 	}
 
-	for (i = 0; i < n_coupled; i++)
-		c_rdev_done[i] = false;
+	/* Invoke custom balancer for customized couplers */
+	if (coupler && coupler->balance_voltage)
+		return coupler->balance_voltage(coupler, rdev, state);
 
 	/*
 	 * Find the best possible voltage change on each loop. Leave the loop
@@ -3622,7 +3625,7 @@ static int regulator_balance_voltage(struct regulator_dev *rdev,
 			 */
 			int optimal_uV = 0, optimal_max_uV = 0, current_uV = 0;
 
-			if (c_rdev_done[i])
+			if (test_bit(i, &c_rdev_done))
 				continue;
 
 			ret = regulator_get_optimal_voltage(c_rdevs[i],
@@ -3657,7 +3660,8 @@ static int regulator_balance_voltage(struct regulator_dev *rdev,
 		if (ret < 0)
 			goto out;
 
-		c_rdev_done[best_c_rdev] = best_c_rdev_done;
+		if (best_c_rdev_done)
+			set_bit(best_c_rdev, &c_rdev_done);
 
 	} while (n_coupled > 1);
 
@@ -3913,7 +3917,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(regulator_sync_voltage);
 
-static int _regulator_get_voltage(struct regulator_dev *rdev)
+int regulator_get_voltage_rdev(struct regulator_dev *rdev)
 {
 	int sel, ret;
 	bool bypassed;
@@ -3930,7 +3934,7 @@ static int _regulator_get_voltage(struct regulator_dev *rdev)
 				return -EPROBE_DEFER;
 			}
 
-			return _regulator_get_voltage(rdev->supply->rdev);
+			return regulator_get_voltage_rdev(rdev->supply->rdev);
 		}
 	}
 
@@ -3946,7 +3950,7 @@ static int _regulator_get_voltage(struct regulator_dev *rdev)
 	} else if (rdev->desc->fixed_uV && (rdev->desc->n_voltages == 1)) {
 		ret = rdev->desc->fixed_uV;
 	} else if (rdev->supply) {
-		ret = _regulator_get_voltage(rdev->supply->rdev);
+		ret = regulator_get_voltage_rdev(rdev->supply->rdev);
 	} else {
 		return -EINVAL;
 	}
@@ -3955,6 +3959,7 @@ static int _regulator_get_voltage(struct regulator_dev *rdev)
 		return ret;
 	return ret - rdev->constraints->uV_offset;
 }
+EXPORT_SYMBOL_GPL(regulator_get_voltage_rdev);
 
 /**
  * regulator_get_voltage - get regulator output voltage
@@ -3971,7 +3976,7 @@ int regulator_get_voltage(struct regulator *regulator)
 	int ret;
 
 	regulator_lock_dependent(regulator->rdev, &ww_ctx);
-	ret = _regulator_get_voltage(regulator->rdev);
+	ret = regulator_get_voltage_rdev(regulator->rdev);
 	regulator_unlock_dependent(regulator->rdev, &ww_ctx);
 
 	return ret;
@@ -4709,8 +4714,60 @@ static int regulator_register_resolve_supply(struct device *dev, void *data)
 	return 0;
 }
 
+int regulator_coupler_register(struct regulator_coupler *coupler)
+{
+	mutex_lock(&regulator_list_mutex);
+	list_add_tail(&coupler->list, &regulator_coupler_list);
+	mutex_unlock(&regulator_list_mutex);
+
+	return 0;
+}
+
+static struct regulator_coupler *
+regulator_find_coupler(struct regulator_dev *rdev)
+{
+	struct regulator_coupler *coupler;
+	int err;
+
+	/*
+	 * Note that regulators are appended to the list and the generic
+	 * coupler is registered first, hence it will be attached at last
+	 * if nobody cared.
+	 */
+	list_for_each_entry_reverse(coupler, &regulator_coupler_list, list) {
+		err = coupler->attach_regulator(coupler, rdev);
+		if (!err) {
+			if (!coupler->balance_voltage &&
+			    rdev->coupling_desc.n_coupled > 2)
+				goto err_unsupported;
+
+			return coupler;
+		}
+
+		if (err < 0)
+			return ERR_PTR(err);
+
+		if (err == 1)
+			continue;
+
+		break;
+	}
+
+	return ERR_PTR(-EINVAL);
+
+err_unsupported:
+	if (coupler->detach_regulator)
+		coupler->detach_regulator(coupler, rdev);
+
+	rdev_err(rdev,
+		"Voltage balancing for multiple regulator couples is unimplemented\n");
+
+	return ERR_PTR(-EPERM);
+}
+
 static void regulator_resolve_coupling(struct regulator_dev *rdev)
 {
+	struct regulator_coupler *coupler = rdev->coupling_desc.coupler;
 	struct coupling_desc *c_desc = &rdev->coupling_desc;
 	int n_coupled = c_desc->n_coupled;
 	struct regulator_dev *c_rdev;
@@ -4726,6 +4783,12 @@ static void regulator_resolve_coupling(struct regulator_dev *rdev)
 		if (!c_rdev)
 			continue;
 
+		if (c_rdev->coupling_desc.coupler != coupler) {
+			rdev_err(rdev, "coupler mismatch with %s\n",
+				 rdev_get_name(c_rdev));
+			return;
+		}
+
 		regulator_lock(c_rdev);
 
 		c_desc->coupled_rdevs[i] = c_rdev;
@@ -4739,10 +4802,12 @@ static void regulator_resolve_coupling(struct regulator_dev *rdev)
 
 static void regulator_remove_coupling(struct regulator_dev *rdev)
 {
+	struct regulator_coupler *coupler = rdev->coupling_desc.coupler;
 	struct coupling_desc *__c_desc, *c_desc = &rdev->coupling_desc;
 	struct regulator_dev *__c_rdev, *c_rdev;
 	unsigned int __n_coupled, n_coupled;
 	int i, k;
+	int err;
 
 	n_coupled = c_desc->n_coupled;
 
@@ -4772,21 +4837,33 @@ static void regulator_remove_coupling(struct regulator_dev *rdev)
 		c_desc->coupled_rdevs[i] = NULL;
 		c_desc->n_resolved--;
 	}
+
+	if (coupler && coupler->detach_regulator) {
+		err = coupler->detach_regulator(coupler, rdev);
+		if (err)
+			rdev_err(rdev, "failed to detach from coupler: %d\n",
+				 err);
+	}
+
+	kfree(rdev->coupling_desc.coupled_rdevs);
+	rdev->coupling_desc.coupled_rdevs = NULL;
 }
 
 static int regulator_init_coupling(struct regulator_dev *rdev)
 {
-	int n_phandles;
+	int err, n_phandles;
+	size_t alloc_size;
 
 	if (!IS_ENABLED(CONFIG_OF))
 		n_phandles = 0;
 	else
 		n_phandles = of_get_n_coupled(rdev);
 
-	if (n_phandles + 1 > MAX_COUPLED) {
-		rdev_err(rdev, "too many regulators coupled\n");
-		return -EPERM;
-	}
+	alloc_size = sizeof(*rdev) * (n_phandles + 1);
+
+	rdev->coupling_desc.coupled_rdevs = kzalloc(alloc_size, GFP_KERNEL);
+	if (!rdev->coupling_desc.coupled_rdevs)
+		return -ENOMEM;
 
 	/*
 	 * Every regulator should always have coupling descriptor filled with
@@ -4800,23 +4877,38 @@ static int regulator_init_coupling(struct regulator_dev *rdev)
 	if (n_phandles == 0)
 		return 0;
 
-	/* regulator, which can't change its voltage, can't be coupled */
-	if (!regulator_ops_is_valid(rdev, REGULATOR_CHANGE_VOLTAGE)) {
-		rdev_err(rdev, "voltage operation not allowed\n");
+	if (!of_check_coupling_data(rdev))
 		return -EPERM;
-	}
 
-	if (rdev->constraints->max_spread <= 0) {
-		rdev_err(rdev, "wrong max_spread value\n");
-		return -EPERM;
+	mutex_lock(&regulator_list_mutex);
+	rdev->coupling_desc.coupler = regulator_find_coupler(rdev);
+	mutex_unlock(&regulator_list_mutex);
+
+	if (IS_ERR(rdev->coupling_desc.coupler)) {
+		err = PTR_ERR(rdev->coupling_desc.coupler);
+		rdev_err(rdev, "failed to get coupler: %d\n", err);
+		return err;
 	}
 
-	if (!of_check_coupling_data(rdev))
+	return 0;
+}
+
+static int generic_coupler_attach(struct regulator_coupler *coupler,
+				  struct regulator_dev *rdev)
+{
+	if (rdev->coupling_desc.n_coupled > 2) {
+		rdev_err(rdev,
+			 "Voltage balancing for multiple regulator couples is unimplemented\n");
 		return -EPERM;
+	}
 
 	return 0;
 }
 
+static struct regulator_coupler generic_regulator_coupler = {
+	.attach_regulator = generic_coupler_attach,
+};
+
 /**
  * regulator_register - register regulator
  * @regulator_desc: regulator to register
@@ -4886,6 +4978,7 @@ regulator_register(const struct regulator_desc *regulator_desc,
 		ret = -ENOMEM;
 		goto rinse;
 	}
+	device_initialize(&rdev->dev);
 
 	/*
 	 * Duplicate the config so the driver could override it after
@@ -4893,13 +4986,23 @@ regulator_register(const struct regulator_desc *regulator_desc,
 	 */
 	config = kmemdup(cfg, sizeof(*cfg), GFP_KERNEL);
 	if (config == NULL) {
-		kfree(rdev);
 		ret = -ENOMEM;
-		goto rinse;
+		goto clean;
 	}
 
 	init_data = regulator_of_get_init_data(dev, regulator_desc, config,
 					       &rdev->dev.of_node);
+
+	/*
+	 * Sometimes not all resources are probed already so we need to take
+	 * that into account. This happens most the time if the ena_gpiod comes
+	 * from a gpio extender or something else.
+	 */
+	if (PTR_ERR(init_data) == -EPROBE_DEFER) {
+		ret = -EPROBE_DEFER;
+		goto clean;
+	}
+
 	/*
 	 * We need to keep track of any GPIO descriptor coming from the
 	 * device tree until we have handled it over to the core. If the
@@ -4956,6 +5059,7 @@ regulator_register(const struct regulator_desc *regulator_desc,
 	rdev->dev.parent = dev;
 	dev_set_name(&rdev->dev, "regulator.%lu",
 		    (unsigned long) atomic_inc_return(&regulator_no));
+	dev_set_drvdata(&rdev->dev, rdev);
 
 	/* set regulator constraints */
 	if (init_data)
@@ -5004,12 +5108,9 @@ regulator_register(const struct regulator_desc *regulator_desc,
 	    !rdev->desc->fixed_uV)
 		rdev->is_switch = true;
 
-	dev_set_drvdata(&rdev->dev, rdev);
-	ret = device_register(&rdev->dev);
-	if (ret != 0) {
-		put_device(&rdev->dev);
+	ret = device_add(&rdev->dev);
+	if (ret != 0)
 		goto unset_supplies;
-	}
 
 	rdev_init_debugfs(rdev);
 
@@ -5027,18 +5128,18 @@ regulator_register(const struct regulator_desc *regulator_desc,
 unset_supplies:
 	mutex_lock(&regulator_list_mutex);
 	unset_regulator_supplies(rdev);
+	regulator_remove_coupling(rdev);
 	mutex_unlock(&regulator_list_mutex);
 wash:
 	kfree(rdev->coupling_desc.coupled_rdevs);
-	kfree(rdev->constraints);
 	mutex_lock(&regulator_list_mutex);
 	regulator_ena_gpio_free(rdev);
 	mutex_unlock(&regulator_list_mutex);
 clean:
 	if (dangling_of_gpiod)
 		gpiod_put(config->ena_gpiod);
-	kfree(rdev);
 	kfree(config);
+	put_device(&rdev->dev);
 rinse:
 	if (dangling_cfg_gpiod)
 		gpiod_put(cfg->ena_gpiod);
@@ -5281,7 +5382,7 @@ static void regulator_summary_show_subtree(struct seq_file *s,
 		   rdev->use_count, rdev->open_count, rdev->bypass_count,
 		   regulator_opmode_to_str(opmode));
 
-	seq_printf(s, "%5dmV ", _regulator_get_voltage(rdev) / 1000);
+	seq_printf(s, "%5dmV ", regulator_get_voltage_rdev(rdev) / 1000);
 	seq_printf(s, "%5dmA ",
 		   _regulator_get_current_limit_unlocked(rdev) / 1000);
 
@@ -5483,6 +5584,8 @@ static int __init regulator_init(void)
 #endif
 	regulator_dummy_init();
 
+	regulator_coupler_register(&generic_regulator_coupler);
+
 	return ret;
 }
 
diff --git a/drivers/regulator/helpers.c b/drivers/regulator/helpers.c
index b9ae45d2d199..599f0b755158 100644
--- a/drivers/regulator/helpers.c
+++ b/drivers/regulator/helpers.c
@@ -14,6 +14,8 @@
 #include <linux/regulator/driver.h>
 #include <linux/module.h>
 
+#include "internal.h"
+
 /**
  * regulator_is_enabled_regmap - standard is_enabled() for regmap users
  *
@@ -861,3 +863,15 @@ int regulator_get_current_limit_regmap(struct regulator_dev *rdev)
 	return -EINVAL;
 }
 EXPORT_SYMBOL_GPL(regulator_get_current_limit_regmap);
+
+/**
+ * regulator_is_equal - test whether two regulators are the same
+ *
+ * @reg1: first regulator to operate on
+ * @reg2: second regulator to operate on
+ */
+bool regulator_is_equal(struct regulator *reg1, struct regulator *reg2)
+{
+	return reg1->rdev == reg2->rdev;
+}
+EXPORT_SYMBOL_GPL(regulator_is_equal);
diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c
index 557ce6c9c024..d0c2aecd2734 100644
--- a/drivers/regulator/of_regulator.c
+++ b/drivers/regulator/of_regulator.c
@@ -21,7 +21,8 @@ static const char *const regulator_states[PM_SUSPEND_MAX + 1] = {
 	[PM_SUSPEND_MAX]	= "regulator-state-disk",
 };
 
-static void of_get_regulation_constraints(struct device_node *np,
+static int of_get_regulation_constraints(struct device *dev,
+					struct device_node *np,
 					struct regulator_init_data **init_data,
 					const struct regulator_desc *desc)
 {
@@ -30,8 +31,13 @@ static void of_get_regulation_constraints(struct device_node *np,
 	struct device_node *suspend_np;
 	unsigned int mode;
 	int ret, i, len;
+	int n_phandles;
 	u32 pval;
 
+	n_phandles = of_count_phandle_with_args(np, "regulator-coupled-with",
+						NULL);
+	n_phandles = max(n_phandles, 0);
+
 	constraints->name = of_get_property(np, "regulator-name", NULL);
 
 	if (!of_property_read_u32(np, "regulator-min-microvolt", &pval))
@@ -163,9 +169,17 @@ static void of_get_regulation_constraints(struct device_node *np,
 	if (!of_property_read_u32(np, "regulator-system-load", &pval))
 		constraints->system_load = pval;
 
-	if (!of_property_read_u32(np, "regulator-coupled-max-spread",
-				  &pval))
-		constraints->max_spread = pval;
+	if (n_phandles) {
+		constraints->max_spread = devm_kzalloc(dev,
+				sizeof(*constraints->max_spread) * n_phandles,
+				GFP_KERNEL);
+
+		if (!constraints->max_spread)
+			return -ENOMEM;
+
+		of_property_read_u32_array(np, "regulator-coupled-max-spread",
+					   constraints->max_spread, n_phandles);
+	}
 
 	if (!of_property_read_u32(np, "regulator-max-step-microvolt",
 				  &pval))
@@ -242,6 +256,8 @@ static void of_get_regulation_constraints(struct device_node *np,
 		suspend_state = NULL;
 		suspend_np = NULL;
 	}
+
+	return 0;
 }
 
 /**
@@ -267,7 +283,9 @@ struct regulator_init_data *of_get_regulator_init_data(struct device *dev,
 	if (!init_data)
 		return NULL; /* Out of memory? */
 
-	of_get_regulation_constraints(node, &init_data, desc);
+	if (of_get_regulation_constraints(dev, node, &init_data, desc))
+		return NULL;
+
 	return init_data;
 }
 EXPORT_SYMBOL_GPL(of_get_regulator_init_data);
@@ -425,11 +443,20 @@ struct regulator_init_data *regulator_of_get_init_data(struct device *dev,
 		goto error;
 	}
 
-	if (desc->of_parse_cb && desc->of_parse_cb(child, desc, config)) {
-		dev_err(dev,
-			"driver callback failed to parse DT for regulator %pOFn\n",
-			child);
-		goto error;
+	if (desc->of_parse_cb) {
+		int ret;
+
+		ret = desc->of_parse_cb(child, desc, config);
+		if (ret) {
+			if (ret == -EPROBE_DEFER) {
+				of_node_put(child);
+				return ERR_PTR(-EPROBE_DEFER);
+			}
+			dev_err(dev,
+				"driver callback failed to parse DT for regulator %pOFn\n",
+				child);
+			goto error;
+		}
 	}
 
 	*node = child;
@@ -473,7 +500,8 @@ int of_get_n_coupled(struct regulator_dev *rdev)
 
 /* Looks for "to_find" device_node in src's "regulator-coupled-with" property */
 static bool of_coupling_find_node(struct device_node *src,
-				  struct device_node *to_find)
+				  struct device_node *to_find,
+				  int *index)
 {
 	int n_phandles, i;
 	bool found = false;
@@ -495,8 +523,10 @@ static bool of_coupling_find_node(struct device_node *src,
 
 		of_node_put(tmp);
 
-		if (found)
+		if (found) {
+			*index = i;
 			break;
+		}
 	}
 
 	return found;
@@ -517,22 +547,23 @@ static bool of_coupling_find_node(struct device_node *src,
  */
 bool of_check_coupling_data(struct regulator_dev *rdev)
 {
-	int max_spread = rdev->constraints->max_spread;
 	struct device_node *node = rdev->dev.of_node;
 	int n_phandles = of_get_n_coupled(rdev);
 	struct device_node *c_node;
+	int index;
 	int i;
 	bool ret = true;
 
-	if (max_spread <= 0) {
-		dev_err(&rdev->dev, "max_spread value invalid\n");
-		return false;
-	}
-
 	/* iterate over rdev's phandles */
 	for (i = 0; i < n_phandles; i++) {
+		int max_spread = rdev->constraints->max_spread[i];
 		int c_max_spread, c_n_phandles;
 
+		if (max_spread <= 0) {
+			dev_err(&rdev->dev, "max_spread value invalid\n");
+			return false;
+		}
+
 		c_node = of_parse_phandle(node,
 					  "regulator-coupled-with", i);
 
@@ -549,22 +580,23 @@ bool of_check_coupling_data(struct regulator_dev *rdev)
 			goto clean;
 		}
 
-		if (of_property_read_u32(c_node, "regulator-coupled-max-spread",
-					 &c_max_spread)) {
+		if (!of_coupling_find_node(c_node, node, &index)) {
+			dev_err(&rdev->dev, "missing 2-way linking for coupled regulators\n");
 			ret = false;
 			goto clean;
 		}
 
-		if (c_max_spread != max_spread) {
-			dev_err(&rdev->dev,
-				"coupled regulators max_spread mismatch\n");
+		if (of_property_read_u32_index(c_node, "regulator-coupled-max-spread",
+					       index, &c_max_spread)) {
 			ret = false;
 			goto clean;
 		}
 
-		if (!of_coupling_find_node(c_node, node)) {
-			dev_err(&rdev->dev, "missing 2-way linking for coupled regulators\n");
+		if (c_max_spread != max_spread) {
+			dev_err(&rdev->dev,
+				"coupled regulators max_spread mismatch\n");
 			ret = false;
+			goto clean;
 		}
 
 clean:
diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c
index 689537927f6f..4c8e8b472287 100644
--- a/drivers/regulator/pfuze100-regulator.c
+++ b/drivers/regulator/pfuze100-regulator.c
@@ -209,6 +209,19 @@ static const struct regulator_ops pfuze100_swb_regulator_ops = {
 
 };
 
+static const struct regulator_ops pfuze3000_sw_regulator_ops = {
+	.enable = regulator_enable_regmap,
+	.disable = regulator_disable_regmap,
+	.is_enabled = regulator_is_enabled_regmap,
+	.list_voltage = regulator_list_voltage_table,
+	.map_voltage = regulator_map_voltage_ascend,
+	.set_voltage_sel = regulator_set_voltage_sel_regmap,
+	.get_voltage_sel = regulator_get_voltage_sel_regmap,
+	.set_voltage_time_sel = regulator_set_voltage_time_sel,
+	.set_ramp_delay = pfuze100_set_ramp_delay,
+
+};
+
 #define PFUZE100_FIXED_REG(_chip, _name, base, voltage)	\
 	[_chip ## _ ## _name] = {	\
 		.desc = {	\
@@ -318,23 +331,28 @@ static const struct regulator_ops pfuze100_swb_regulator_ops = {
 	.stby_mask = 0x20,	\
 }
 
-
-#define PFUZE3000_SW2_REG(_chip, _name, base, min, max, step)	{	\
-	.desc = {	\
-		.name = #_name,\
-		.n_voltages = ((max) - (min)) / (step) + 1,	\
-		.ops = &pfuze100_sw_regulator_ops,	\
-		.type = REGULATOR_VOLTAGE,	\
-		.id = _chip ## _ ## _name,	\
-		.owner = THIS_MODULE,	\
-		.min_uV = (min),	\
-		.uV_step = (step),	\
-		.vsel_reg = (base) + PFUZE100_VOL_OFFSET,	\
-		.vsel_mask = 0x7,	\
-	},	\
-	.stby_reg = (base) + PFUZE100_STANDBY_OFFSET,	\
-	.stby_mask = 0x7,	\
-}
+/* No linar case for the some switches of PFUZE3000 */
+#define PFUZE3000_SW_REG(_chip, _name, base, mask, voltages)	\
+	[_chip ## _ ##  _name] = {	\
+		.desc = {	\
+			.name = #_name,	\
+			.n_voltages = ARRAY_SIZE(voltages),	\
+			.ops = &pfuze3000_sw_regulator_ops,	\
+			.type = REGULATOR_VOLTAGE,	\
+			.id = _chip ## _ ## _name,	\
+			.owner = THIS_MODULE,	\
+			.volt_table = voltages,	\
+			.vsel_reg = (base) + PFUZE100_VOL_OFFSET,	\
+			.vsel_mask = (mask),	\
+			.enable_reg = (base) + PFUZE100_MODE_OFFSET,	\
+			.enable_mask = 0xf,	\
+			.enable_val = 0x8,	\
+			.enable_time = 500,	\
+		},	\
+		.stby_reg = (base) + PFUZE100_STANDBY_OFFSET,	\
+		.stby_mask = (mask),	\
+		.sw_reg = true,		\
+	}
 
 #define PFUZE3000_SW3_REG(_chip, _name, base, min, max, step)	{	\
 	.desc = {	\
@@ -391,9 +409,9 @@ static struct pfuze_regulator pfuze200_regulators[] = {
 };
 
 static struct pfuze_regulator pfuze3000_regulators[] = {
-	PFUZE100_SWB_REG(PFUZE3000, SW1A, PFUZE100_SW1ABVOL, 0x1f, pfuze3000_sw1a),
+	PFUZE3000_SW_REG(PFUZE3000, SW1A, PFUZE100_SW1ABVOL, 0x1f, pfuze3000_sw1a),
 	PFUZE100_SW_REG(PFUZE3000, SW1B, PFUZE100_SW1CVOL, 700000, 1475000, 25000),
-	PFUZE100_SWB_REG(PFUZE3000, SW2, PFUZE100_SW2VOL, 0x7, pfuze3000_sw2lo),
+	PFUZE3000_SW_REG(PFUZE3000, SW2, PFUZE100_SW2VOL, 0x7, pfuze3000_sw2lo),
 	PFUZE3000_SW3_REG(PFUZE3000, SW3, PFUZE100_SW3AVOL, 900000, 1650000, 50000),
 	PFUZE100_SWB_REG(PFUZE3000, SWBST, PFUZE100_SWBSTCON1, 0x3, pfuze100_swbst),
 	PFUZE100_SWB_REG(PFUZE3000, VSNVS, PFUZE100_VSNVSVOL, 0x7, pfuze100_vsnvs),
@@ -407,8 +425,8 @@ static struct pfuze_regulator pfuze3000_regulators[] = {
 };
 
 static struct pfuze_regulator pfuze3001_regulators[] = {
-	PFUZE100_SWB_REG(PFUZE3001, SW1, PFUZE100_SW1ABVOL, 0x1f, pfuze3000_sw1a),
-	PFUZE100_SWB_REG(PFUZE3001, SW2, PFUZE100_SW2VOL, 0x7, pfuze3000_sw2lo),
+	PFUZE3000_SW_REG(PFUZE3001, SW1, PFUZE100_SW1ABVOL, 0x1f, pfuze3000_sw1a),
+	PFUZE3000_SW_REG(PFUZE3001, SW2, PFUZE100_SW2VOL, 0x7, pfuze3000_sw2lo),
 	PFUZE3000_SW3_REG(PFUZE3001, SW3, PFUZE100_SW3AVOL, 900000, 1650000, 50000),
 	PFUZE100_SWB_REG(PFUZE3001, VSNVS, PFUZE100_VSNVSVOL, 0x7, pfuze100_vsnvs),
 	PFUZE100_VGEN_REG(PFUZE3001, VLDO1, PFUZE100_VGEN1VOL, 1800000, 3300000, 100000),
diff --git a/drivers/regulator/rk808-regulator.c b/drivers/regulator/rk808-regulator.c
index 061ebc4b3477..424b81427b71 100644
--- a/drivers/regulator/rk808-regulator.c
+++ b/drivers/regulator/rk808-regulator.c
@@ -712,7 +712,7 @@ static int rk808_regulator_dt_parse_pdata(struct device *dev,
 		}
 
 		if (!pdata->dvs_gpio[i]) {
-			dev_warn(dev, "there is no dvs%d gpio\n", i);
+			dev_info(dev, "there is no dvs%d gpio\n", i);
 			continue;
 		}
 
diff --git a/drivers/regulator/rn5t618-regulator.c b/drivers/regulator/rn5t618-regulator.c
index eb807a059479..aa6e7c5341ce 100644
--- a/drivers/regulator/rn5t618-regulator.c
+++ b/drivers/regulator/rn5t618-regulator.c
@@ -148,6 +148,7 @@ static struct platform_driver rn5t618_regulator_driver = {
 
 module_platform_driver(rn5t618_regulator_driver);
 
+MODULE_ALIAS("platform:rn5t618-regulator");
 MODULE_AUTHOR("Beniamino Galvani <b.galvani@gmail.com>");
 MODULE_DESCRIPTION("RN5T618 regulator driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/regulator/stm32-vrefbuf.c b/drivers/regulator/stm32-vrefbuf.c
index 8919a5130bec..25f24df9aa82 100644
--- a/drivers/regulator/stm32-vrefbuf.c
+++ b/drivers/regulator/stm32-vrefbuf.c
@@ -88,7 +88,7 @@ static int stm32_vrefbuf_disable(struct regulator_dev *rdev)
 	}
 
 	val = readl_relaxed(priv->base + STM32_VREFBUF_CSR);
-	val = (val & ~STM32_ENVR) | STM32_HIZ;
+	val &= ~STM32_ENVR;
 	writel_relaxed(val, priv->base + STM32_VREFBUF_CSR);
 
 	pm_runtime_mark_last_busy(priv->dev);
@@ -175,6 +175,7 @@ static const struct regulator_desc stm32_vrefbuf_regu = {
 	.volt_table = stm32_vrefbuf_voltages,
 	.n_voltages = ARRAY_SIZE(stm32_vrefbuf_voltages),
 	.ops = &stm32_vrefbuf_volt_ops,
+	.off_on_delay = 1000,
 	.type = REGULATOR_VOLTAGE,
 	.owner = THIS_MODULE,
 };
diff --git a/drivers/regulator/vctrl-regulator.c b/drivers/regulator/vctrl-regulator.c
index 9a9ee8188109..cbadb1c99679 100644
--- a/drivers/regulator/vctrl-regulator.c
+++ b/drivers/regulator/vctrl-regulator.c
@@ -11,10 +11,13 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/regulator/coupler.h>
 #include <linux/regulator/driver.h>
 #include <linux/regulator/of_regulator.h>
 #include <linux/sort.h>
 
+#include "internal.h"
+
 struct vctrl_voltage_range {
 	int min_uV;
 	int max_uV;
@@ -79,7 +82,7 @@ static int vctrl_calc_output_voltage(struct vctrl_data *vctrl, int ctrl_uV)
 static int vctrl_get_voltage(struct regulator_dev *rdev)
 {
 	struct vctrl_data *vctrl = rdev_get_drvdata(rdev);
-	int ctrl_uV = regulator_get_voltage(vctrl->ctrl_reg);
+	int ctrl_uV = regulator_get_voltage_rdev(vctrl->ctrl_reg->rdev);
 
 	return vctrl_calc_output_voltage(vctrl, ctrl_uV);
 }
@@ -90,16 +93,16 @@ static int vctrl_set_voltage(struct regulator_dev *rdev,
 {
 	struct vctrl_data *vctrl = rdev_get_drvdata(rdev);
 	struct regulator *ctrl_reg = vctrl->ctrl_reg;
-	int orig_ctrl_uV = regulator_get_voltage(ctrl_reg);
+	int orig_ctrl_uV = regulator_get_voltage_rdev(ctrl_reg->rdev);
 	int uV = vctrl_calc_output_voltage(vctrl, orig_ctrl_uV);
 	int ret;
 
 	if (req_min_uV >= uV || !vctrl->ovp_threshold)
 		/* voltage rising or no OVP */
-		return regulator_set_voltage(
-			ctrl_reg,
+		return regulator_set_voltage_rdev(ctrl_reg->rdev,
 			vctrl_calc_ctrl_voltage(vctrl, req_min_uV),
-			vctrl_calc_ctrl_voltage(vctrl, req_max_uV));
+			vctrl_calc_ctrl_voltage(vctrl, req_max_uV),
+			PM_SUSPEND_ON);
 
 	while (uV > req_min_uV) {
 		int max_drop_uV = (uV * vctrl->ovp_threshold) / 100;
@@ -114,9 +117,10 @@ static int vctrl_set_voltage(struct regulator_dev *rdev,
 		next_uV = max_t(int, req_min_uV, uV - max_drop_uV);
 		next_ctrl_uV = vctrl_calc_ctrl_voltage(vctrl, next_uV);
 
-		ret = regulator_set_voltage(ctrl_reg,
+		ret = regulator_set_voltage_rdev(ctrl_reg->rdev,
+					    next_ctrl_uV,
 					    next_ctrl_uV,
-					    next_ctrl_uV);
+					    PM_SUSPEND_ON);
 		if (ret)
 			goto err;
 
@@ -130,7 +134,8 @@ static int vctrl_set_voltage(struct regulator_dev *rdev,
 
 err:
 	/* Try to go back to original voltage */
-	regulator_set_voltage(ctrl_reg, orig_ctrl_uV, orig_ctrl_uV);
+	regulator_set_voltage_rdev(ctrl_reg->rdev, orig_ctrl_uV, orig_ctrl_uV,
+				   PM_SUSPEND_ON);
 
 	return ret;
 }
@@ -155,9 +160,10 @@ static int vctrl_set_voltage_sel(struct regulator_dev *rdev,
 
 	if (selector >= vctrl->sel || !vctrl->ovp_threshold) {
 		/* voltage rising or no OVP */
-		ret = regulator_set_voltage(ctrl_reg,
+		ret = regulator_set_voltage_rdev(ctrl_reg->rdev,
+					    vctrl->vtable[selector].ctrl,
 					    vctrl->vtable[selector].ctrl,
-					    vctrl->vtable[selector].ctrl);
+					    PM_SUSPEND_ON);
 		if (!ret)
 			vctrl->sel = selector;
 
@@ -173,9 +179,10 @@ static int vctrl_set_voltage_sel(struct regulator_dev *rdev,
 		else
 			next_sel = vctrl->vtable[vctrl->sel].ovp_min_sel;
 
-		ret = regulator_set_voltage(ctrl_reg,
+		ret = regulator_set_voltage_rdev(ctrl_reg->rdev,
 					    vctrl->vtable[next_sel].ctrl,
-					    vctrl->vtable[next_sel].ctrl);
+					    vctrl->vtable[next_sel].ctrl,
+					    PM_SUSPEND_ON);
 		if (ret) {
 			dev_err(&rdev->dev,
 				"failed to set control voltage to %duV\n",
@@ -195,9 +202,10 @@ static int vctrl_set_voltage_sel(struct regulator_dev *rdev,
 err:
 	if (vctrl->sel != orig_sel) {
 		/* Try to go back to original voltage */
-		if (!regulator_set_voltage(ctrl_reg,
+		if (!regulator_set_voltage_rdev(ctrl_reg->rdev,
+					   vctrl->vtable[orig_sel].ctrl,
 					   vctrl->vtable[orig_sel].ctrl,
-					   vctrl->vtable[orig_sel].ctrl))
+					   PM_SUSPEND_ON))
 			vctrl->sel = orig_sel;
 		else
 			dev_warn(&rdev->dev,
@@ -482,7 +490,7 @@ static int vctrl_probe(struct platform_device *pdev)
 		if (ret)
 			return ret;
 
-		ctrl_uV = regulator_get_voltage(vctrl->ctrl_reg);
+		ctrl_uV = regulator_get_voltage_rdev(vctrl->ctrl_reg->rdev);
 		if (ctrl_uV < 0) {
 			dev_err(&pdev->dev, "failed to get control voltage\n");
 			return ctrl_uV;
diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig
index 18be41b8aa7e..164e82b2b53c 100644
--- a/drivers/remoteproc/Kconfig
+++ b/drivers/remoteproc/Kconfig
@@ -116,6 +116,7 @@ config QCOM_Q6V5_MSS
 	depends on RPMSG_QCOM_GLINK_SMEM || RPMSG_QCOM_GLINK_SMEM=n
 	depends on QCOM_SYSMON || QCOM_SYSMON=n
 	select MFD_SYSCON
+	select QCOM_MDT_LOADER
 	select QCOM_Q6V5_COMMON
 	select QCOM_RPROC_COMMON
 	select QCOM_SCM
diff --git a/drivers/remoteproc/qcom_q6v5.c b/drivers/remoteproc/qcom_q6v5.c
index 0d33e3079f0d..ef61cb709acd 100644
--- a/drivers/remoteproc/qcom_q6v5.c
+++ b/drivers/remoteproc/qcom_q6v5.c
@@ -151,6 +151,8 @@ int qcom_q6v5_request_stop(struct qcom_q6v5 *q6v5)
 {
 	int ret;
 
+	q6v5->running = false;
+
 	qcom_smem_state_update_bits(q6v5->state,
 				    BIT(q6v5->stop_bit), BIT(q6v5->stop_bit));
 
diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c
index 981581bcdd56..abdef10eadec 100644
--- a/drivers/remoteproc/qcom_q6v5_mss.c
+++ b/drivers/remoteproc/qcom_q6v5_mss.c
@@ -381,6 +381,12 @@ static int q6v5_load(struct rproc *rproc, const struct firmware *fw)
 {
 	struct q6v5 *qproc = rproc->priv;
 
+	/* MBA is restricted to a maximum size of 1M */
+	if (fw->size > qproc->mba_size || fw->size > SZ_1M) {
+		dev_err(qproc->dev, "MBA firmware load failed\n");
+		return -EINVAL;
+	}
+
 	memcpy(qproc->mba_region, fw->data, fw->size);
 
 	return 0;
@@ -659,23 +665,29 @@ static int q6v5_mpss_init_image(struct q6v5 *qproc, const struct firmware *fw)
 {
 	unsigned long dma_attrs = DMA_ATTR_FORCE_CONTIGUOUS;
 	dma_addr_t phys;
+	void *metadata;
 	int mdata_perm;
 	int xferop_ret;
+	size_t size;
 	void *ptr;
 	int ret;
 
-	ptr = dma_alloc_attrs(qproc->dev, fw->size, &phys, GFP_KERNEL, dma_attrs);
+	metadata = qcom_mdt_read_metadata(fw, &size);
+	if (IS_ERR(metadata))
+		return PTR_ERR(metadata);
+
+	ptr = dma_alloc_attrs(qproc->dev, size, &phys, GFP_KERNEL, dma_attrs);
 	if (!ptr) {
+		kfree(metadata);
 		dev_err(qproc->dev, "failed to allocate mdt buffer\n");
 		return -ENOMEM;
 	}
 
-	memcpy(ptr, fw->data, fw->size);
+	memcpy(ptr, metadata, size);
 
 	/* Hypervisor mapping to access metadata by modem */
 	mdata_perm = BIT(QCOM_SCM_VMID_HLOS);
-	ret = q6v5_xfer_mem_ownership(qproc, &mdata_perm,
-				      true, phys, fw->size);
+	ret = q6v5_xfer_mem_ownership(qproc, &mdata_perm, true, phys, size);
 	if (ret) {
 		dev_err(qproc->dev,
 			"assigning Q6 access to metadata failed: %d\n", ret);
@@ -693,14 +705,14 @@ static int q6v5_mpss_init_image(struct q6v5 *qproc, const struct firmware *fw)
 		dev_err(qproc->dev, "MPSS header authentication failed: %d\n", ret);
 
 	/* Metadata authentication done, remove modem access */
-	xferop_ret = q6v5_xfer_mem_ownership(qproc, &mdata_perm,
-					     false, phys, fw->size);
+	xferop_ret = q6v5_xfer_mem_ownership(qproc, &mdata_perm, false, phys, size);
 	if (xferop_ret)
 		dev_warn(qproc->dev,
 			 "mdt buffer not reclaimed system may become unstable\n");
 
 free_dma_attrs:
-	dma_free_attrs(qproc->dev, fw->size, ptr, phys, dma_attrs);
+	dma_free_attrs(qproc->dev, size, ptr, phys, dma_attrs);
+	kfree(metadata);
 
 	return ret < 0 ? ret : 0;
 }
@@ -869,11 +881,6 @@ static void q6v5_mba_reclaim(struct q6v5 *qproc)
 		writel(val, qproc->reg_base + QDSP6SS_PWR_CTL_REG);
 	}
 
-	ret = q6v5_xfer_mem_ownership(qproc, &qproc->mpss_perm,
-				      false, qproc->mpss_phys,
-				      qproc->mpss_size);
-	WARN_ON(ret);
-
 	q6v5_reset_assert(qproc);
 
 	q6v5_clk_disable(qproc->dev, qproc->reset_clks,
@@ -903,6 +910,23 @@ static void q6v5_mba_reclaim(struct q6v5 *qproc)
 	}
 }
 
+static int q6v5_reload_mba(struct rproc *rproc)
+{
+	struct q6v5 *qproc = rproc->priv;
+	const struct firmware *fw;
+	int ret;
+
+	ret = request_firmware(&fw, rproc->firmware, qproc->dev);
+	if (ret < 0)
+		return ret;
+
+	q6v5_load(rproc, fw);
+	ret = q6v5_mba_load(qproc);
+	release_firmware(fw);
+
+	return ret;
+}
+
 static int q6v5_mpss_load(struct q6v5 *qproc)
 {
 	const struct elf32_phdr *phdrs;
@@ -963,6 +987,14 @@ static int q6v5_mpss_load(struct q6v5 *qproc)
 			max_addr = ALIGN(phdr->p_paddr + phdr->p_memsz, SZ_4K);
 	}
 
+	/**
+	 * In case of a modem subsystem restart on secure devices, the modem
+	 * memory can be reclaimed only after MBA is loaded. For modem cold
+	 * boot this will be a nop
+	 */
+	q6v5_xfer_mem_ownership(qproc, &qproc->mpss_perm, false,
+				qproc->mpss_phys, qproc->mpss_size);
+
 	mpss_reloc = relocate ? min_addr : qproc->mpss_phys;
 	qproc->mpss_reloc = mpss_reloc;
 	/* Load firmware segments */
@@ -979,19 +1011,37 @@ static int q6v5_mpss_load(struct q6v5 *qproc)
 			goto release_firmware;
 		}
 
-		ptr = qproc->mpss_region + offset;
+		ptr = ioremap_wc(qproc->mpss_phys + offset, phdr->p_memsz);
+		if (!ptr) {
+			dev_err(qproc->dev,
+				"unable to map memory region: %pa+%zx-%x\n",
+				&qproc->mpss_phys, offset, phdr->p_memsz);
+			goto release_firmware;
+		}
+
+		if (phdr->p_filesz && phdr->p_offset < fw->size) {
+			/* Firmware is large enough to be non-split */
+			if (phdr->p_offset + phdr->p_filesz > fw->size) {
+				dev_err(qproc->dev,
+					"failed to load segment %d from truncated file %s\n",
+					i, fw_name);
+				ret = -EINVAL;
+				iounmap(ptr);
+				goto release_firmware;
+			}
 
-		if (phdr->p_filesz) {
+			memcpy(ptr, fw->data + phdr->p_offset, phdr->p_filesz);
+		} else if (phdr->p_filesz) {
 			/* Replace "xxx.xxx" with "xxx.bxx" */
 			sprintf(fw_name + fw_name_len - 3, "b%02d", i);
-			ret = request_firmware(&seg_fw, fw_name, qproc->dev);
+			ret = request_firmware_into_buf(&seg_fw, fw_name, qproc->dev,
+							ptr, phdr->p_filesz);
 			if (ret) {
 				dev_err(qproc->dev, "failed to load %s\n", fw_name);
+				iounmap(ptr);
 				goto release_firmware;
 			}
 
-			memcpy(ptr, seg_fw->data, seg_fw->size);
-
 			release_firmware(seg_fw);
 		}
 
@@ -999,6 +1049,7 @@ static int q6v5_mpss_load(struct q6v5 *qproc)
 			memset(ptr + phdr->p_filesz, 0,
 			       phdr->p_memsz - phdr->p_filesz);
 		}
+		iounmap(ptr);
 		size += phdr->p_memsz;
 	}
 
@@ -1038,23 +1089,43 @@ static void qcom_q6v5_dump_segment(struct rproc *rproc,
 	int ret = 0;
 	struct q6v5 *qproc = rproc->priv;
 	unsigned long mask = BIT((unsigned long)segment->priv);
-	void *ptr = rproc_da_to_va(rproc, segment->da, segment->size);
+	int offset = segment->da - qproc->mpss_reloc;
+	void *ptr = NULL;
 
 	/* Unlock mba before copying segments */
-	if (!qproc->dump_mba_loaded)
-		ret = q6v5_mba_load(qproc);
+	if (!qproc->dump_mba_loaded) {
+		ret = q6v5_reload_mba(rproc);
+		if (!ret) {
+			/* Reset ownership back to Linux to copy segments */
+			ret = q6v5_xfer_mem_ownership(qproc, &qproc->mpss_perm,
+						      false,
+						      qproc->mpss_phys,
+						      qproc->mpss_size);
+		}
+	}
 
-	if (!ptr || ret)
-		memset(dest, 0xff, segment->size);
-	else
+	if (!ret)
+		ptr = ioremap_wc(qproc->mpss_phys + offset, segment->size);
+
+	if (ptr) {
 		memcpy(dest, ptr, segment->size);
+		iounmap(ptr);
+	} else {
+		memset(dest, 0xff, segment->size);
+	}
 
 	qproc->dump_segment_mask |= mask;
 
 	/* Reclaim mba after copying segments */
 	if (qproc->dump_segment_mask == qproc->dump_complete_mask) {
-		if (qproc->dump_mba_loaded)
+		if (qproc->dump_mba_loaded) {
+			/* Try to reset ownership back to Q6 */
+			q6v5_xfer_mem_ownership(qproc, &qproc->mpss_perm,
+						true,
+						qproc->mpss_phys,
+						qproc->mpss_size);
 			q6v5_mba_reclaim(qproc);
+		}
 	}
 }
 
@@ -1094,10 +1165,6 @@ static int q6v5_start(struct rproc *rproc)
 	return 0;
 
 reclaim_mpss:
-	xfermemop_ret = q6v5_xfer_mem_ownership(qproc, &qproc->mpss_perm,
-						false, qproc->mpss_phys,
-						qproc->mpss_size);
-	WARN_ON(xfermemop_ret);
 	q6v5_mba_reclaim(qproc);
 
 	return ret;
@@ -1346,12 +1413,6 @@ static int q6v5_alloc_memory_region(struct q6v5 *qproc)
 
 	qproc->mpss_phys = qproc->mpss_reloc = r.start;
 	qproc->mpss_size = resource_size(&r);
-	qproc->mpss_region = devm_ioremap_wc(qproc->dev, qproc->mpss_phys, qproc->mpss_size);
-	if (!qproc->mpss_region) {
-		dev_err(qproc->dev, "unable to map memory region: %pa+%zx\n",
-			&r.start, qproc->mpss_size);
-		return -EBUSY;
-	}
 
 	return 0;
 }
@@ -1393,7 +1454,7 @@ static int q6v5_probe(struct platform_device *pdev)
 	ret = of_property_read_string_index(pdev->dev.of_node, "firmware-name",
 					    1, &qproc->hexagon_mdt_image);
 	if (ret < 0 && ret != -EINVAL)
-		return ret;
+		goto free_rproc;
 
 	platform_set_drvdata(pdev, qproc);
 
diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index 5031c6806908..3bceb333cf04 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -400,7 +400,7 @@ rproc_parse_vring(struct rproc_vdev *rvdev, struct fw_rsc_vdev *rsc, int i)
 void rproc_free_vring(struct rproc_vring *rvring)
 {
 	struct rproc *rproc = rvring->rvdev->rproc;
-	int idx = rvring->rvdev->vring - rvring;
+	int idx = rvring - rvring->rvdev->vring;
 	struct fw_rsc_vdev *rsc;
 
 	idr_remove(&rproc->notifyids, rvring->notifyid);
@@ -511,7 +511,7 @@ static int rproc_handle_vdev(struct rproc *rproc, struct fw_rsc_vdev *rsc,
 
 	/* Initialise vdev subdevice */
 	snprintf(name, sizeof(name), "vdev%dbuffer", rvdev->index);
-	rvdev->dev.parent = rproc->dev.parent;
+	rvdev->dev.parent = &rproc->dev;
 	rvdev->dev.dma_pfn_offset = rproc->dev.parent->dma_pfn_offset;
 	rvdev->dev.release = rproc_rvdev_release;
 	dev_set_name(&rvdev->dev, "%s#%s", dev_name(rvdev->dev.parent), name);
@@ -2022,6 +2022,7 @@ struct rproc *rproc_alloc(struct device *dev, const char *name,
 	rproc->dev.type = &rproc_type;
 	rproc->dev.class = &rproc_class;
 	rproc->dev.driver_data = rproc;
+	idr_init(&rproc->notifyids);
 
 	/* Assign a unique device index and name */
 	rproc->index = ida_simple_get(&rproc_dev_index, 0, 0, GFP_KERNEL);
@@ -2046,8 +2047,6 @@ struct rproc *rproc_alloc(struct device *dev, const char *name,
 
 	mutex_init(&rproc->lock);
 
-	idr_init(&rproc->notifyids);
-
 	INIT_LIST_HEAD(&rproc->carveouts);
 	INIT_LIST_HEAD(&rproc->mappings);
 	INIT_LIST_HEAD(&rproc->traces);
@@ -2210,7 +2209,7 @@ static int __init remoteproc_init(void)
 
 	return 0;
 }
-module_init(remoteproc_init);
+subsys_initcall(remoteproc_init);
 
 static void __exit remoteproc_exit(void)
 {
diff --git a/drivers/remoteproc/remoteproc_virtio.c b/drivers/remoteproc/remoteproc_virtio.c
index 8c07cb2ca8ba..c45ba428791b 100644
--- a/drivers/remoteproc/remoteproc_virtio.c
+++ b/drivers/remoteproc/remoteproc_virtio.c
@@ -334,6 +334,12 @@ int rproc_add_virtio_dev(struct rproc_vdev *rvdev, int id)
 	struct rproc_mem_entry *mem;
 	int ret;
 
+	if (rproc->ops->kick == NULL) {
+		ret = -EINVAL;
+		dev_err(dev, ".kick method not defined for %s\n", rproc->name);
+		goto out;
+	}
+
 	/* Try to find dedicated vdev buffer carveout */
 	mem = rproc_find_carveout_by_name(rproc, "vdev%dbuffer", rvdev->index);
 	if (mem) {
@@ -368,6 +374,18 @@ int rproc_add_virtio_dev(struct rproc_vdev *rvdev, int id)
 				goto out;
 			}
 		}
+	} else {
+		struct device_node *np = rproc->dev.parent->of_node;
+
+		/*
+		 * If we don't have dedicated buffer, just attempt to re-assign
+		 * the reserved memory from our parent. A default memory-region
+		 * at index 0 from the parent's memory-regions is assigned for
+		 * the rvdev dev to allocate from. Failure is non-critical and
+		 * the allocations will fall back to global pools, so don't
+		 * check return value either.
+		 */
+		of_reserved_mem_device_init_by_idx(dev, np, 0);
 	}
 
 	/* Allocate virtio device */
diff --git a/drivers/reset/core.c b/drivers/reset/core.c
index 8b1e79d90e91..8210c9f7dd95 100644
--- a/drivers/reset/core.c
+++ b/drivers/reset/core.c
@@ -791,7 +791,7 @@ struct reset_control *__devm_reset_control_get(struct device *dev,
 		return ERR_PTR(-ENOMEM);
 
 	rstc = __reset_control_get(dev, id, index, shared, optional, acquired);
-	if (!IS_ERR(rstc)) {
+	if (!IS_ERR_OR_NULL(rstc)) {
 		*ptr = rstc;
 		devres_add(dev, ptr);
 	} else {
@@ -864,8 +864,7 @@ static int of_reset_control_get_count(struct device_node *node)
  * @acquired: only one reset control may be acquired for a given controller
  *            and ID
  *
- * Returns pointer to allocated reset_control_array on success or
- * error on failure
+ * Returns pointer to allocated reset_control on success or error on failure
  */
 struct reset_control *
 of_reset_control_array_get(struct device_node *np, bool shared, bool optional,
@@ -918,8 +917,7 @@ EXPORT_SYMBOL_GPL(of_reset_control_array_get);
  * that just have to be asserted or deasserted, without any
  * requirements on the order.
  *
- * Returns pointer to allocated reset_control_array on success or
- * error on failure
+ * Returns pointer to allocated reset_control on success or error on failure
  */
 struct reset_control *
 devm_reset_control_array_get(struct device *dev, bool shared, bool optional)
@@ -933,7 +931,7 @@ devm_reset_control_array_get(struct device *dev, bool shared, bool optional)
 		return ERR_PTR(-ENOMEM);
 
 	rstc = of_reset_control_array_get(dev->of_node, shared, optional, true);
-	if (IS_ERR(rstc)) {
+	if (IS_ERR_OR_NULL(rstc)) {
 		devres_free(devres);
 		return rstc;
 	}
diff --git a/drivers/reset/reset-brcmstb.c b/drivers/reset/reset-brcmstb.c
index a608f445dad6..f213264c8567 100644
--- a/drivers/reset/reset-brcmstb.c
+++ b/drivers/reset/reset-brcmstb.c
@@ -91,12 +91,6 @@ static int brcmstb_reset_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!IS_ALIGNED(res->start, SW_INIT_BANK_SIZE) ||
-	    !IS_ALIGNED(resource_size(res), SW_INIT_BANK_SIZE)) {
-		dev_err(kdev, "incorrect register range\n");
-		return -EINVAL;
-	}
-
 	priv->base = devm_ioremap_resource(kdev, res);
 	if (IS_ERR(priv->base))
 		return PTR_ERR(priv->base);
diff --git a/drivers/reset/reset-uniphier.c b/drivers/reset/reset-uniphier.c
index 74e589f5dd6a..279e535bf5d8 100644
--- a/drivers/reset/reset-uniphier.c
+++ b/drivers/reset/reset-uniphier.c
@@ -193,8 +193,8 @@ static const struct uniphier_reset_data uniphier_pro5_sd_reset_data[] = {
 #define UNIPHIER_PERI_RESET_FI2C(id, ch)		\
 	UNIPHIER_RESETX((id), 0x114, 24 + (ch))
 
-#define UNIPHIER_PERI_RESET_SCSSI(id)			\
-	UNIPHIER_RESETX((id), 0x110, 17)
+#define UNIPHIER_PERI_RESET_SCSSI(id, ch)		\
+	UNIPHIER_RESETX((id), 0x110, 17 + (ch))
 
 #define UNIPHIER_PERI_RESET_MCSSI(id)			\
 	UNIPHIER_RESETX((id), 0x114, 14)
@@ -209,7 +209,7 @@ static const struct uniphier_reset_data uniphier_ld4_peri_reset_data[] = {
 	UNIPHIER_PERI_RESET_I2C(6, 2),
 	UNIPHIER_PERI_RESET_I2C(7, 3),
 	UNIPHIER_PERI_RESET_I2C(8, 4),
-	UNIPHIER_PERI_RESET_SCSSI(11),
+	UNIPHIER_PERI_RESET_SCSSI(11, 0),
 	UNIPHIER_RESET_END,
 };
 
@@ -225,8 +225,11 @@ static const struct uniphier_reset_data uniphier_pro4_peri_reset_data[] = {
 	UNIPHIER_PERI_RESET_FI2C(8, 4),
 	UNIPHIER_PERI_RESET_FI2C(9, 5),
 	UNIPHIER_PERI_RESET_FI2C(10, 6),
-	UNIPHIER_PERI_RESET_SCSSI(11),
-	UNIPHIER_PERI_RESET_MCSSI(12),
+	UNIPHIER_PERI_RESET_SCSSI(11, 0),
+	UNIPHIER_PERI_RESET_SCSSI(12, 1),
+	UNIPHIER_PERI_RESET_SCSSI(13, 2),
+	UNIPHIER_PERI_RESET_SCSSI(14, 3),
+	UNIPHIER_PERI_RESET_MCSSI(15),
 	UNIPHIER_RESET_END,
 };
 
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 5c0790eed656..1753bacf3fe5 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -240,6 +240,7 @@ config RTC_DRV_AS3722
 
 config RTC_DRV_DS1307
 	tristate "Dallas/Maxim DS1307/37/38/39/40/41, ST M41T00, EPSON RX-8025, ISL12057"
+	select REGMAP_I2C
 	help
 	  If you say yes here you get support for various compatible RTC
 	  chips (often with battery backup) connected with I2C. This driver
@@ -326,6 +327,7 @@ config RTC_DRV_MAX6900
 config RTC_DRV_MAX8907
 	tristate "Maxim MAX8907"
 	depends on MFD_MAX8907 || COMPILE_TEST
+	select REGMAP_IRQ
 	help
 	  If you say yes here you will get support for the
 	  RTC of Maxim MAX8907 PMIC.
@@ -612,6 +614,7 @@ config RTC_DRV_RX8010
 
 config RTC_DRV_RX8581
 	tristate "Epson RX-8571/RX-8581"
+	select REGMAP_I2C
 	help
 	  If you say yes here you will get support for the Epson RX-8571/
 	  RX-8581.
@@ -639,6 +642,7 @@ config RTC_DRV_EM3027
 
 config RTC_DRV_RV3028
 	tristate "Micro Crystal RV3028"
+	select REGMAP_I2C
 	help
 	  If you say yes here you get support for the Micro Crystal
 	  RV3028.
@@ -668,6 +672,7 @@ config RTC_DRV_S5M
 
 config RTC_DRV_SD3078
     tristate "ZXW Shenzhen whwave SD3078"
+    select REGMAP_I2C
     help
       If you say yes here you get support for the ZXW Shenzhen whwave
       SD3078 RTC chips.
@@ -838,14 +843,14 @@ config RTC_I2C_AND_SPI
 	default m if I2C=m
 	default y if I2C=y
 	default y if SPI_MASTER=y
-	select REGMAP_I2C if I2C
-	select REGMAP_SPI if SPI_MASTER
 
 comment "SPI and I2C RTC drivers"
 
 config RTC_DRV_DS3232
 	tristate "Dallas/Maxim DS3232/DS3234"
 	depends on RTC_I2C_AND_SPI
+	select REGMAP_I2C if I2C
+	select REGMAP_SPI if SPI_MASTER
 	help
 	  If you say yes here you get support for Dallas Semiconductor
 	  DS3232 and DS3234 real-time clock chips. If an interrupt is associated
@@ -865,6 +870,8 @@ config RTC_DRV_DS3232_HWMON
 config RTC_DRV_PCF2127
 	tristate "NXP PCF2127"
 	depends on RTC_I2C_AND_SPI
+	select REGMAP_I2C if I2C
+	select REGMAP_SPI if SPI_MASTER
 	help
 	  If you say yes here you get support for the NXP PCF2127/29 RTC
 	  chips.
@@ -875,6 +882,8 @@ config RTC_DRV_PCF2127
 config RTC_DRV_RV3029C2
 	tristate "Micro Crystal RV3029/3049"
 	depends on RTC_I2C_AND_SPI
+	select REGMAP_I2C if I2C
+	select REGMAP_SPI if SPI_MASTER
 	help
 	  If you say yes here you get support for the Micro Crystal
 	  RV3029 and RV3049 RTC chips.
diff --git a/drivers/rtc/rtc-88pm860x.c b/drivers/rtc/rtc-88pm860x.c
index 434285f495e0..fb51f2b9b05e 100644
--- a/drivers/rtc/rtc-88pm860x.c
+++ b/drivers/rtc/rtc-88pm860x.c
@@ -338,6 +338,10 @@ static int pm860x_rtc_probe(struct platform_device *pdev)
 	info->dev = &pdev->dev;
 	dev_set_drvdata(&pdev->dev, info);
 
+	info->rtc_dev = devm_rtc_allocate_device(&pdev->dev);
+	if (IS_ERR(info->rtc_dev))
+		return PTR_ERR(info->rtc_dev);
+
 	ret = devm_request_threaded_irq(&pdev->dev, info->irq, NULL,
 					rtc_update_handler, IRQF_ONESHOT, "rtc",
 					info);
@@ -379,13 +383,11 @@ static int pm860x_rtc_probe(struct platform_device *pdev)
 		}
 	}
 
-	info->rtc_dev = devm_rtc_device_register(&pdev->dev, "88pm860x-rtc",
-					    &pm860x_rtc_ops, THIS_MODULE);
-	ret = PTR_ERR(info->rtc_dev);
-	if (IS_ERR(info->rtc_dev)) {
-		dev_err(&pdev->dev, "Failed to register RTC device: %d\n", ret);
+	info->rtc_dev->ops = &pm860x_rtc_ops;
+
+	ret = rtc_register_device(info->rtc_dev);
+	if (ret)
 		return ret;
-	}
 
 	/*
 	 * enable internal XO instead of internal 3.25MHz clock since it can
diff --git a/drivers/rtc/rtc-brcmstb-waketimer.c b/drivers/rtc/rtc-brcmstb-waketimer.c
index 2f65943867f5..11ac54027ded 100644
--- a/drivers/rtc/rtc-brcmstb-waketimer.c
+++ b/drivers/rtc/rtc-brcmstb-waketimer.c
@@ -279,6 +279,7 @@ static int brcmstb_waketmr_remove(struct platform_device *pdev)
 	struct brcmstb_waketmr *timer = dev_get_drvdata(&pdev->dev);
 
 	unregister_reboot_notifier(&timer->reboot_notifier);
+	clk_disable_unprepare(timer->clk);
 
 	return 0;
 }
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index 033303708c8b..cb28bbdc9e17 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -850,7 +850,7 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq)
 			rtc_cmos_int_handler = cmos_interrupt;
 
 		retval = request_irq(rtc_irq, rtc_cmos_int_handler,
-				IRQF_SHARED, dev_name(&cmos_rtc.rtc->dev),
+				0, dev_name(&cmos_rtc.rtc->dev),
 				cmos_rtc.rtc);
 		if (retval < 0) {
 			dev_dbg(dev, "IRQ %d is already in use\n", rtc_irq);
diff --git a/drivers/rtc/rtc-hym8563.c b/drivers/rtc/rtc-hym8563.c
index 443f6d05ce29..fb6d7967ec00 100644
--- a/drivers/rtc/rtc-hym8563.c
+++ b/drivers/rtc/rtc-hym8563.c
@@ -97,7 +97,7 @@ static int hym8563_rtc_read_time(struct device *dev, struct rtc_time *tm)
 
 	if (!hym8563->valid) {
 		dev_warn(&client->dev, "no valid clock/calendar values available\n");
-		return -EPERM;
+		return -EINVAL;
 	}
 
 	ret = i2c_smbus_read_i2c_block_data(client, HYM8563_SEC, 7, buf);
diff --git a/drivers/rtc/rtc-mc13xxx.c b/drivers/rtc/rtc-mc13xxx.c
index afce2c0b4bd6..d6802e6191cb 100644
--- a/drivers/rtc/rtc-mc13xxx.c
+++ b/drivers/rtc/rtc-mc13xxx.c
@@ -308,8 +308,10 @@ static int __init mc13xxx_rtc_probe(struct platform_device *pdev)
 	mc13xxx_unlock(mc13xxx);
 
 	ret = rtc_register_device(priv->rtc);
-	if (ret)
+	if (ret) {
+		mc13xxx_lock(mc13xxx);
 		goto err_irq_request;
+	}
 
 	return 0;
 
diff --git a/drivers/rtc/rtc-msm6242.c b/drivers/rtc/rtc-msm6242.c
index 1c2d3c4a4963..b1f2bedee77e 100644
--- a/drivers/rtc/rtc-msm6242.c
+++ b/drivers/rtc/rtc-msm6242.c
@@ -133,7 +133,8 @@ static int msm6242_read_time(struct device *dev, struct rtc_time *tm)
 		      msm6242_read(priv, MSM6242_SECOND1);
 	tm->tm_min  = msm6242_read(priv, MSM6242_MINUTE10) * 10 +
 		      msm6242_read(priv, MSM6242_MINUTE1);
-	tm->tm_hour = (msm6242_read(priv, MSM6242_HOUR10 & 3)) * 10 +
+	tm->tm_hour = (msm6242_read(priv, MSM6242_HOUR10) &
+		       MSM6242_HOUR10_HR_MASK) * 10 +
 		      msm6242_read(priv, MSM6242_HOUR1);
 	tm->tm_mday = msm6242_read(priv, MSM6242_DAY10) * 10 +
 		      msm6242_read(priv, MSM6242_DAY1);
diff --git a/drivers/rtc/rtc-mt6397.c b/drivers/rtc/rtc-mt6397.c
index b46ed4dc7015..4006676536fe 100644
--- a/drivers/rtc/rtc-mt6397.c
+++ b/drivers/rtc/rtc-mt6397.c
@@ -47,6 +47,14 @@
 
 #define RTC_AL_SEC		0x0018
 
+#define RTC_AL_SEC_MASK        0x003f
+#define RTC_AL_MIN_MASK        0x003f
+#define RTC_AL_HOU_MASK        0x001f
+#define RTC_AL_DOM_MASK        0x001f
+#define RTC_AL_DOW_MASK        0x0007
+#define RTC_AL_MTH_MASK        0x000f
+#define RTC_AL_YEA_MASK        0x007f
+
 #define RTC_PDN2		0x002e
 #define RTC_PDN2_PWRON_ALARM	BIT(4)
 
@@ -103,7 +111,7 @@ static irqreturn_t mtk_rtc_irq_handler_thread(int irq, void *data)
 		irqen = irqsta & ~RTC_IRQ_EN_AL;
 		mutex_lock(&rtc->lock);
 		if (regmap_write(rtc->regmap, rtc->addr_base + RTC_IRQ_EN,
-				 irqen) < 0)
+				 irqen) == 0)
 			mtk_rtc_write_trigger(rtc);
 		mutex_unlock(&rtc->lock);
 
@@ -225,12 +233,12 @@ static int mtk_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alm)
 	alm->pending = !!(pdn2 & RTC_PDN2_PWRON_ALARM);
 	mutex_unlock(&rtc->lock);
 
-	tm->tm_sec = data[RTC_OFFSET_SEC];
-	tm->tm_min = data[RTC_OFFSET_MIN];
-	tm->tm_hour = data[RTC_OFFSET_HOUR];
-	tm->tm_mday = data[RTC_OFFSET_DOM];
-	tm->tm_mon = data[RTC_OFFSET_MTH];
-	tm->tm_year = data[RTC_OFFSET_YEAR];
+	tm->tm_sec = data[RTC_OFFSET_SEC] & RTC_AL_SEC_MASK;
+	tm->tm_min = data[RTC_OFFSET_MIN] & RTC_AL_MIN_MASK;
+	tm->tm_hour = data[RTC_OFFSET_HOUR] & RTC_AL_HOU_MASK;
+	tm->tm_mday = data[RTC_OFFSET_DOM] & RTC_AL_DOM_MASK;
+	tm->tm_mon = data[RTC_OFFSET_MTH] & RTC_AL_MTH_MASK;
+	tm->tm_year = data[RTC_OFFSET_YEAR] & RTC_AL_YEA_MASK;
 
 	tm->tm_year += RTC_MIN_YEAR_OFFSET;
 	tm->tm_mon--;
@@ -251,14 +259,25 @@ static int mtk_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm)
 	tm->tm_year -= RTC_MIN_YEAR_OFFSET;
 	tm->tm_mon++;
 
-	data[RTC_OFFSET_SEC] = tm->tm_sec;
-	data[RTC_OFFSET_MIN] = tm->tm_min;
-	data[RTC_OFFSET_HOUR] = tm->tm_hour;
-	data[RTC_OFFSET_DOM] = tm->tm_mday;
-	data[RTC_OFFSET_MTH] = tm->tm_mon;
-	data[RTC_OFFSET_YEAR] = tm->tm_year;
-
 	mutex_lock(&rtc->lock);
+	ret = regmap_bulk_read(rtc->regmap, rtc->addr_base + RTC_AL_SEC,
+			       data, RTC_OFFSET_COUNT);
+	if (ret < 0)
+		goto exit;
+
+	data[RTC_OFFSET_SEC] = ((data[RTC_OFFSET_SEC] & ~(RTC_AL_SEC_MASK)) |
+				(tm->tm_sec & RTC_AL_SEC_MASK));
+	data[RTC_OFFSET_MIN] = ((data[RTC_OFFSET_MIN] & ~(RTC_AL_MIN_MASK)) |
+				(tm->tm_min & RTC_AL_MIN_MASK));
+	data[RTC_OFFSET_HOUR] = ((data[RTC_OFFSET_HOUR] & ~(RTC_AL_HOU_MASK)) |
+				(tm->tm_hour & RTC_AL_HOU_MASK));
+	data[RTC_OFFSET_DOM] = ((data[RTC_OFFSET_DOM] & ~(RTC_AL_DOM_MASK)) |
+				(tm->tm_mday & RTC_AL_DOM_MASK));
+	data[RTC_OFFSET_MTH] = ((data[RTC_OFFSET_MTH] & ~(RTC_AL_MTH_MASK)) |
+				(tm->tm_mon & RTC_AL_MTH_MASK));
+	data[RTC_OFFSET_YEAR] = ((data[RTC_OFFSET_YEAR] & ~(RTC_AL_YEA_MASK)) |
+				(tm->tm_year & RTC_AL_YEA_MASK));
+
 	if (alm->enabled) {
 		ret = regmap_bulk_write(rtc->regmap,
 					rtc->addr_base + RTC_AL_SEC,
diff --git a/drivers/rtc/rtc-rv3028.c b/drivers/rtc/rtc-rv3028.c
index 06884ebb7a61..f935021ab97d 100644
--- a/drivers/rtc/rtc-rv3028.c
+++ b/drivers/rtc/rtc-rv3028.c
@@ -625,6 +625,8 @@ static int rv3028_probe(struct i2c_client *client)
 		return -ENOMEM;
 
 	rv3028->regmap = devm_regmap_init_i2c(client, &regmap_config);
+	if (IS_ERR(rv3028->regmap))
+		return PTR_ERR(rv3028->regmap);
 
 	i2c_set_clientdata(client, rv3028);
 
diff --git a/drivers/s390/block/dasd_diag.c b/drivers/s390/block/dasd_diag.c
index e1fe02477ea8..b60f88907269 100644
--- a/drivers/s390/block/dasd_diag.c
+++ b/drivers/s390/block/dasd_diag.c
@@ -319,7 +319,7 @@ dasd_diag_check_device(struct dasd_device *device)
 	struct dasd_diag_characteristics *rdc_data;
 	struct vtoc_cms_label *label;
 	struct dasd_block *block;
-	struct dasd_diag_bio bio;
+	struct dasd_diag_bio *bio;
 	unsigned int sb, bsize;
 	blocknum_t end_block;
 	int rc;
@@ -395,29 +395,36 @@ dasd_diag_check_device(struct dasd_device *device)
 		rc = -ENOMEM;
 		goto out;
 	}
+	bio = kzalloc(sizeof(*bio), GFP_KERNEL);
+	if (bio == NULL)  {
+		DBF_DEV_EVENT(DBF_WARNING, device, "%s",
+			      "No memory to allocate initialization bio");
+		rc = -ENOMEM;
+		goto out_label;
+	}
 	rc = 0;
 	end_block = 0;
 	/* try all sizes - needed for ECKD devices */
 	for (bsize = 512; bsize <= PAGE_SIZE; bsize <<= 1) {
 		mdsk_init_io(device, bsize, 0, &end_block);
-		memset(&bio, 0, sizeof (struct dasd_diag_bio));
-		bio.type = MDSK_READ_REQ;
-		bio.block_number = private->pt_block + 1;
-		bio.buffer = label;
+		memset(bio, 0, sizeof(*bio));
+		bio->type = MDSK_READ_REQ;
+		bio->block_number = private->pt_block + 1;
+		bio->buffer = label;
 		memset(&private->iob, 0, sizeof (struct dasd_diag_rw_io));
 		private->iob.dev_nr = rdc_data->dev_nr;
 		private->iob.key = 0;
 		private->iob.flags = 0;	/* do synchronous io */
 		private->iob.block_count = 1;
 		private->iob.interrupt_params = 0;
-		private->iob.bio_list = &bio;
+		private->iob.bio_list = bio;
 		private->iob.flaga = DASD_DIAG_FLAGA_DEFAULT;
 		rc = dia250(&private->iob, RW_BIO);
 		if (rc == 3) {
 			pr_warn("%s: A 64-bit DIAG call failed\n",
 				dev_name(&device->cdev->dev));
 			rc = -EOPNOTSUPP;
-			goto out_label;
+			goto out_bio;
 		}
 		mdsk_term_io(device);
 		if (rc == 0)
@@ -427,7 +434,7 @@ dasd_diag_check_device(struct dasd_device *device)
 		pr_warn("%s: Accessing the DASD failed because of an incorrect format (rc=%d)\n",
 			dev_name(&device->cdev->dev), rc);
 		rc = -EIO;
-		goto out_label;
+		goto out_bio;
 	}
 	/* check for label block */
 	if (memcmp(label->label_id, DASD_DIAG_CMS1,
@@ -457,6 +464,8 @@ dasd_diag_check_device(struct dasd_device *device)
 			(rc == 4) ? ", read-only device" : "");
 		rc = 0;
 	}
+out_bio:
+	kfree(bio);
 out_label:
 	free_page((long) label);
 out:
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index c09039eea707..d9e9431747e4 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -1135,7 +1135,8 @@ static u32 get_fcx_max_data(struct dasd_device *device)
 {
 	struct dasd_eckd_private *private = device->private;
 	int fcx_in_css, fcx_in_gneq, fcx_in_features;
-	int tpm, mdc;
+	unsigned int mdc;
+	int tpm;
 
 	if (dasd_nofcx)
 		return 0;
@@ -1149,7 +1150,7 @@ static u32 get_fcx_max_data(struct dasd_device *device)
 		return 0;
 
 	mdc = ccw_device_get_mdc(device->cdev, 0);
-	if (mdc < 0) {
+	if (mdc == 0) {
 		dev_warn(&device->cdev->dev, "Detecting the maximum supported data size for zHPF requests failed\n");
 		return 0;
 	} else {
@@ -1160,12 +1161,12 @@ static u32 get_fcx_max_data(struct dasd_device *device)
 static int verify_fcx_max_data(struct dasd_device *device, __u8 lpm)
 {
 	struct dasd_eckd_private *private = device->private;
-	int mdc;
+	unsigned int mdc;
 	u32 fcx_max_data;
 
 	if (private->fcx_max_data) {
 		mdc = ccw_device_get_mdc(device->cdev, lpm);
-		if ((mdc < 0)) {
+		if (mdc == 0) {
 			dev_warn(&device->cdev->dev,
 				 "Detecting the maximum data size for zHPF "
 				 "requests failed (rc=%d) for a new path %x\n",
@@ -1769,7 +1770,7 @@ out_err2:
 	dasd_free_block(device->block);
 	device->block = NULL;
 out_err1:
-	kfree(private->conf_data);
+	dasd_eckd_clear_conf_data(device);
 	kfree(device->private);
 	device->private = NULL;
 	return rc;
@@ -1778,7 +1779,6 @@ out_err1:
 static void dasd_eckd_uncheck_device(struct dasd_device *device)
 {
 	struct dasd_eckd_private *private = device->private;
-	int i;
 
 	if (!private)
 		return;
@@ -1788,21 +1788,7 @@ static void dasd_eckd_uncheck_device(struct dasd_device *device)
 	private->sneq = NULL;
 	private->vdsneq = NULL;
 	private->gneq = NULL;
-	private->conf_len = 0;
-	for (i = 0; i < 8; i++) {
-		kfree(device->path[i].conf_data);
-		if ((__u8 *)device->path[i].conf_data ==
-		    private->conf_data) {
-			private->conf_data = NULL;
-			private->conf_len = 0;
-		}
-		device->path[i].conf_data = NULL;
-		device->path[i].cssid = 0;
-		device->path[i].ssid = 0;
-		device->path[i].chpid = 0;
-	}
-	kfree(private->conf_data);
-	private->conf_data = NULL;
+	dasd_eckd_clear_conf_data(device);
 }
 
 static struct dasd_ccw_req *
diff --git a/drivers/s390/cio/blacklist.c b/drivers/s390/cio/blacklist.c
index 2a3f874a21d5..9cebff8e8d74 100644
--- a/drivers/s390/cio/blacklist.c
+++ b/drivers/s390/cio/blacklist.c
@@ -303,8 +303,10 @@ static void *
 cio_ignore_proc_seq_next(struct seq_file *s, void *it, loff_t *offset)
 {
 	struct ccwdev_iter *iter;
+	loff_t p = *offset;
 
-	if (*offset >= (__MAX_SUBCHANNEL + 1) * (__MAX_SSID + 1))
+	(*offset)++;
+	if (p >= (__MAX_SUBCHANNEL + 1) * (__MAX_SSID + 1))
 		return NULL;
 	iter = it;
 	if (iter->devno == __MAX_SUBCHANNEL) {
@@ -314,7 +316,6 @@ cio_ignore_proc_seq_next(struct seq_file *s, void *it, loff_t *offset)
 			return NULL;
 	} else
 		iter->devno++;
-	(*offset)++;
 	return iter;
 }
 
diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index 1540229a37bb..c9bc9a6bd73b 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -827,8 +827,10 @@ static void io_subchannel_register(struct ccw_device *cdev)
 	 * Now we know this subchannel will stay, we can throw
 	 * our delayed uevent.
 	 */
-	dev_set_uevent_suppress(&sch->dev, 0);
-	kobject_uevent(&sch->dev.kobj, KOBJ_ADD);
+	if (dev_get_uevent_suppress(&sch->dev)) {
+		dev_set_uevent_suppress(&sch->dev, 0);
+		kobject_uevent(&sch->dev.kobj, KOBJ_ADD);
+	}
 	/* make it known to the system */
 	ret = ccw_device_add(cdev);
 	if (ret) {
@@ -1036,8 +1038,11 @@ static int io_subchannel_probe(struct subchannel *sch)
 		 * Throw the delayed uevent for the subchannel, register
 		 * the ccw_device and exit.
 		 */
-		dev_set_uevent_suppress(&sch->dev, 0);
-		kobject_uevent(&sch->dev.kobj, KOBJ_ADD);
+		if (dev_get_uevent_suppress(&sch->dev)) {
+			/* should always be the case for the console */
+			dev_set_uevent_suppress(&sch->dev, 0);
+			kobject_uevent(&sch->dev.kobj, KOBJ_ADD);
+		}
 		cdev = sch_get_cdev(sch);
 		rc = ccw_device_add(cdev);
 		if (rc) {
diff --git a/drivers/s390/cio/device_ops.c b/drivers/s390/cio/device_ops.c
index 4435ae0b3027..f0cae1973f78 100644
--- a/drivers/s390/cio/device_ops.c
+++ b/drivers/s390/cio/device_ops.c
@@ -624,7 +624,7 @@ EXPORT_SYMBOL(ccw_device_tm_start_timeout);
  * @mask: mask of paths to use
  *
  * Return the number of 64K-bytes blocks all paths at least support
- * for a transport command. Return values <= 0 indicate failures.
+ * for a transport command. Return value 0 indicates failure.
  */
 int ccw_device_get_mdc(struct ccw_device *cdev, u8 mask)
 {
diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h
index a06944399865..e4e035f69860 100644
--- a/drivers/s390/cio/qdio.h
+++ b/drivers/s390/cio/qdio.h
@@ -373,7 +373,6 @@ static inline int multicast_outbound(struct qdio_q *q)
 extern u64 last_ai_time;
 
 /* prototypes for thin interrupt */
-void qdio_setup_thinint(struct qdio_irq *irq_ptr);
 int qdio_establish_thinint(struct qdio_irq *irq_ptr);
 void qdio_shutdown_thinint(struct qdio_irq *irq_ptr);
 void tiqdio_add_input_queues(struct qdio_irq *irq_ptr);
diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c
index d4101cecdc8d..892edb9c1250 100644
--- a/drivers/s390/cio/qdio_setup.c
+++ b/drivers/s390/cio/qdio_setup.c
@@ -8,6 +8,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/io.h>
 #include <asm/qdio.h>
 
 #include "cio.h"
@@ -207,7 +208,7 @@ static void setup_storage_lists(struct qdio_q *q, struct qdio_irq *irq_ptr,
 
 	/* fill in sl */
 	for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; j++)
-		q->sl->element[j].sbal = (unsigned long)q->sbal[j];
+		q->sl->element[j].sbal = virt_to_phys(q->sbal[j]);
 }
 
 static void setup_queues(struct qdio_irq *irq_ptr,
@@ -478,7 +479,6 @@ int qdio_setup_irq(struct qdio_initialize *init_data)
 	setup_queues(irq_ptr, init_data);
 
 	setup_qib(irq_ptr, init_data);
-	qdio_setup_thinint(irq_ptr);
 	set_impl_params(irq_ptr, init_data->qib_param_field_format,
 			init_data->qib_param_field,
 			init_data->input_slib_elements,
diff --git a/drivers/s390/cio/qdio_thinint.c b/drivers/s390/cio/qdio_thinint.c
index d9763bbecbf9..82aa511fd374 100644
--- a/drivers/s390/cio/qdio_thinint.c
+++ b/drivers/s390/cio/qdio_thinint.c
@@ -267,17 +267,19 @@ int __init tiqdio_register_thinints(void)
 
 int qdio_establish_thinint(struct qdio_irq *irq_ptr)
 {
+	int rc;
+
 	if (!is_thinint_irq(irq_ptr))
 		return 0;
-	return set_subchannel_ind(irq_ptr, 0);
-}
 
-void qdio_setup_thinint(struct qdio_irq *irq_ptr)
-{
-	if (!is_thinint_irq(irq_ptr))
-		return;
 	irq_ptr->dsci = get_indicator();
 	DBF_HEX(&irq_ptr->dsci, sizeof(void *));
+
+	rc = set_subchannel_ind(irq_ptr, 0);
+	if (rc)
+		put_indicator(irq_ptr->dsci);
+
+	return rc;
 }
 
 void qdio_shutdown_thinint(struct qdio_irq *irq_ptr)
diff --git a/drivers/s390/cio/vfio_ccw_async.c b/drivers/s390/cio/vfio_ccw_async.c
index 8c1d2357ef5b..7a838e3d7c0f 100644
--- a/drivers/s390/cio/vfio_ccw_async.c
+++ b/drivers/s390/cio/vfio_ccw_async.c
@@ -70,7 +70,7 @@ static void vfio_ccw_async_region_release(struct vfio_ccw_private *private,
 
 }
 
-const struct vfio_ccw_regops vfio_ccw_async_region_ops = {
+static const struct vfio_ccw_regops vfio_ccw_async_region_ops = {
 	.read = vfio_ccw_async_region_read,
 	.write = vfio_ccw_async_region_write,
 	.release = vfio_ccw_async_region_release,
diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
index 8a8fbde7e186..013117113ede 100644
--- a/drivers/s390/cio/vfio_ccw_drv.c
+++ b/drivers/s390/cio/vfio_ccw_drv.c
@@ -159,6 +159,11 @@ static int vfio_ccw_sch_probe(struct subchannel *sch)
 	if (ret)
 		goto out_disable;
 
+	if (dev_get_uevent_suppress(&sch->dev)) {
+		dev_set_uevent_suppress(&sch->dev, 0);
+		kobject_uevent(&sch->dev.kobj, KOBJ_ADD);
+	}
+
 	return 0;
 
 out_disable:
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index b9fc502c58c2..eb0f8430e11d 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -794,8 +794,6 @@ static int ap_device_probe(struct device *dev)
 		drvres = ap_drv->flags & AP_DRIVER_FLAG_DEFAULT;
 		if (!!devres != !!drvres)
 			return -ENODEV;
-		/* (re-)init queue's state machine */
-		ap_queue_reinit_state(to_ap_queue(dev));
 	}
 
 	/* Add queue/card to list of active queues/cards */
diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h
index 6f3cf37776ca..36a3bfada3e4 100644
--- a/drivers/s390/crypto/ap_bus.h
+++ b/drivers/s390/crypto/ap_bus.h
@@ -161,7 +161,7 @@ struct ap_card {
 	unsigned int functions;		/* AP device function bitfield. */
 	int queue_depth;		/* AP queue depth.*/
 	int id;				/* AP card number. */
-	atomic_t total_request_count;	/* # requests ever for this AP device.*/
+	atomic64_t total_request_count;	/* # requests ever for this AP device.*/
 };
 
 #define to_ap_card(x) container_of((x), struct ap_card, ap_dev.device)
@@ -178,7 +178,7 @@ struct ap_queue {
 	enum ap_state state;		/* State of the AP device. */
 	int pendingq_count;		/* # requests on pendingq list. */
 	int requestq_count;		/* # requests on requestq list. */
-	int total_request_count;	/* # requests ever for this AP device.*/
+	u64 total_request_count;	/* # requests ever for this AP device.*/
 	int request_timeout;		/* Request timeout in jiffies. */
 	struct timer_list timeout;	/* Timer for request timeouts. */
 	struct list_head pendingq;	/* List of message sent to AP queue. */
@@ -260,7 +260,7 @@ void ap_queue_prepare_remove(struct ap_queue *aq);
 void ap_queue_remove(struct ap_queue *aq);
 void ap_queue_suspend(struct ap_device *ap_dev);
 void ap_queue_resume(struct ap_device *ap_dev);
-void ap_queue_reinit_state(struct ap_queue *aq);
+void ap_queue_init_state(struct ap_queue *aq);
 
 struct ap_card *ap_card_create(int id, int queue_depth, int raw_device_type,
 			       int comp_device_type, unsigned int functions);
diff --git a/drivers/s390/crypto/ap_card.c b/drivers/s390/crypto/ap_card.c
index 63b4cc6cd7e5..e85bfca1ed16 100644
--- a/drivers/s390/crypto/ap_card.c
+++ b/drivers/s390/crypto/ap_card.c
@@ -63,13 +63,13 @@ static ssize_t request_count_show(struct device *dev,
 				  char *buf)
 {
 	struct ap_card *ac = to_ap_card(dev);
-	unsigned int req_cnt;
+	u64 req_cnt;
 
 	req_cnt = 0;
 	spin_lock_bh(&ap_list_lock);
-	req_cnt = atomic_read(&ac->total_request_count);
+	req_cnt = atomic64_read(&ac->total_request_count);
 	spin_unlock_bh(&ap_list_lock);
-	return snprintf(buf, PAGE_SIZE, "%d\n", req_cnt);
+	return snprintf(buf, PAGE_SIZE, "%llu\n", req_cnt);
 }
 
 static ssize_t request_count_store(struct device *dev,
@@ -83,7 +83,7 @@ static ssize_t request_count_store(struct device *dev,
 	for_each_ap_queue(aq, ac)
 		aq->total_request_count = 0;
 	spin_unlock_bh(&ap_list_lock);
-	atomic_set(&ac->total_request_count, 0);
+	atomic64_set(&ac->total_request_count, 0);
 
 	return count;
 }
diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c
index 5ea83dc4f1d7..4d3a31b9e14d 100644
--- a/drivers/s390/crypto/ap_queue.c
+++ b/drivers/s390/crypto/ap_queue.c
@@ -478,12 +478,12 @@ static ssize_t request_count_show(struct device *dev,
 				  char *buf)
 {
 	struct ap_queue *aq = to_ap_queue(dev);
-	unsigned int req_cnt;
+	u64 req_cnt;
 
 	spin_lock_bh(&aq->lock);
 	req_cnt = aq->total_request_count;
 	spin_unlock_bh(&aq->lock);
-	return snprintf(buf, PAGE_SIZE, "%d\n", req_cnt);
+	return snprintf(buf, PAGE_SIZE, "%llu\n", req_cnt);
 }
 
 static ssize_t request_count_store(struct device *dev,
@@ -637,7 +637,7 @@ struct ap_queue *ap_queue_create(ap_qid_t qid, int device_type)
 	aq->ap_dev.device.type = &ap_queue_type;
 	aq->ap_dev.device_type = device_type;
 	aq->qid = qid;
-	aq->state = AP_STATE_RESET_START;
+	aq->state = AP_STATE_UNBOUND;
 	aq->interrupt = AP_INTR_DISABLED;
 	spin_lock_init(&aq->lock);
 	INIT_LIST_HEAD(&aq->list);
@@ -675,7 +675,7 @@ void ap_queue_message(struct ap_queue *aq, struct ap_message *ap_msg)
 	list_add_tail(&ap_msg->list, &aq->requestq);
 	aq->requestq_count++;
 	aq->total_request_count++;
-	atomic_inc(&aq->card->total_request_count);
+	atomic64_inc(&aq->card->total_request_count);
 	/* Send/receive as many request from the queue as possible. */
 	ap_wait(ap_sm_event_loop(aq, AP_EVENT_POLL));
 	spin_unlock_bh(&aq->lock);
@@ -770,10 +770,11 @@ void ap_queue_remove(struct ap_queue *aq)
 	spin_unlock_bh(&aq->lock);
 }
 
-void ap_queue_reinit_state(struct ap_queue *aq)
+void ap_queue_init_state(struct ap_queue *aq)
 {
 	spin_lock_bh(&aq->lock);
 	aq->state = AP_STATE_RESET_START;
 	ap_wait(ap_sm_event(aq, AP_EVENT_POLL));
 	spin_unlock_bh(&aq->lock);
 }
+EXPORT_SYMBOL(ap_queue_init_state);
diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c
index 35a0e9569239..71e20fb6a1af 100644
--- a/drivers/s390/crypto/zcrypt_api.c
+++ b/drivers/s390/crypto/zcrypt_api.c
@@ -622,8 +622,8 @@ static inline bool zcrypt_card_compare(struct zcrypt_card *zc,
 	weight += atomic_read(&zc->load);
 	pref_weight += atomic_read(&pref_zc->load);
 	if (weight == pref_weight)
-		return atomic_read(&zc->card->total_request_count) >
-			atomic_read(&pref_zc->card->total_request_count);
+		return atomic64_read(&zc->card->total_request_count) >
+			atomic64_read(&pref_zc->card->total_request_count);
 	return weight > pref_weight;
 }
 
@@ -1205,11 +1205,12 @@ static void zcrypt_qdepth_mask(char qdepth[], size_t max_adapters)
 	spin_unlock(&zcrypt_list_lock);
 }
 
-static void zcrypt_perdev_reqcnt(int reqcnt[], size_t max_adapters)
+static void zcrypt_perdev_reqcnt(u32 reqcnt[], size_t max_adapters)
 {
 	struct zcrypt_card *zc;
 	struct zcrypt_queue *zq;
 	int card;
+	u64 cnt;
 
 	memset(reqcnt, 0, sizeof(int) * max_adapters);
 	spin_lock(&zcrypt_list_lock);
@@ -1221,8 +1222,9 @@ static void zcrypt_perdev_reqcnt(int reqcnt[], size_t max_adapters)
 			    || card >= max_adapters)
 				continue;
 			spin_lock(&zq->queue->lock);
-			reqcnt[card] = zq->queue->total_request_count;
+			cnt = zq->queue->total_request_count;
 			spin_unlock(&zq->queue->lock);
+			reqcnt[card] = (cnt < UINT_MAX) ? (u32) cnt : UINT_MAX;
 		}
 	}
 	local_bh_enable();
@@ -1400,9 +1402,9 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd,
 		return 0;
 	}
 	case ZCRYPT_PERDEV_REQCNT: {
-		int *reqcnt;
+		u32 *reqcnt;
 
-		reqcnt = kcalloc(AP_DEVICES, sizeof(int), GFP_KERNEL);
+		reqcnt = kcalloc(AP_DEVICES, sizeof(u32), GFP_KERNEL);
 		if (!reqcnt)
 			return -ENOMEM;
 		zcrypt_perdev_reqcnt(reqcnt, AP_DEVICES);
@@ -1459,7 +1461,7 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd,
 	}
 	case Z90STAT_PERDEV_REQCNT: {
 		/* the old ioctl supports only 64 adapters */
-		int reqcnt[MAX_ZDEV_CARDIDS];
+		u32 reqcnt[MAX_ZDEV_CARDIDS];
 
 		zcrypt_perdev_reqcnt(reqcnt, MAX_ZDEV_CARDIDS);
 		if (copy_to_user((int __user *) arg, reqcnt, sizeof(reqcnt)))
diff --git a/drivers/s390/crypto/zcrypt_cex2a.c b/drivers/s390/crypto/zcrypt_cex2a.c
index c50f3e86cc74..7cbb384ec535 100644
--- a/drivers/s390/crypto/zcrypt_cex2a.c
+++ b/drivers/s390/crypto/zcrypt_cex2a.c
@@ -175,6 +175,7 @@ static int zcrypt_cex2a_queue_probe(struct ap_device *ap_dev)
 	zq->queue = aq;
 	zq->online = 1;
 	atomic_set(&zq->load, 0);
+	ap_queue_init_state(aq);
 	ap_queue_init_reply(aq, &zq->reply);
 	aq->request_timeout = CEX2A_CLEANUP_TIME,
 	aq->private = zq;
diff --git a/drivers/s390/crypto/zcrypt_cex2c.c b/drivers/s390/crypto/zcrypt_cex2c.c
index 35c7c6672713..c78c0d119806 100644
--- a/drivers/s390/crypto/zcrypt_cex2c.c
+++ b/drivers/s390/crypto/zcrypt_cex2c.c
@@ -220,6 +220,7 @@ static int zcrypt_cex2c_queue_probe(struct ap_device *ap_dev)
 	zq->queue = aq;
 	zq->online = 1;
 	atomic_set(&zq->load, 0);
+	ap_rapq(aq->qid);
 	rc = zcrypt_cex2c_rng_supported(aq);
 	if (rc < 0) {
 		zcrypt_queue_free(zq);
@@ -231,6 +232,7 @@ static int zcrypt_cex2c_queue_probe(struct ap_device *ap_dev)
 	else
 		zq->ops = zcrypt_msgtype(MSGTYPE06_NAME,
 					 MSGTYPE06_VARIANT_NORNG);
+	ap_queue_init_state(aq);
 	ap_queue_init_reply(aq, &zq->reply);
 	aq->request_timeout = CEX2C_CLEANUP_TIME;
 	aq->private = zq;
diff --git a/drivers/s390/crypto/zcrypt_cex4.c b/drivers/s390/crypto/zcrypt_cex4.c
index 582ffa7e0f18..9425026d2dfe 100644
--- a/drivers/s390/crypto/zcrypt_cex4.c
+++ b/drivers/s390/crypto/zcrypt_cex4.c
@@ -254,6 +254,7 @@ static int zcrypt_cex4_queue_probe(struct ap_device *ap_dev)
 	zq->queue = aq;
 	zq->online = 1;
 	atomic_set(&zq->load, 0);
+	ap_queue_init_state(aq);
 	ap_queue_init_reply(aq, &zq->reply);
 	aq->request_timeout = CEX4_CLEANUP_TIME,
 	aq->private = zq;
diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c
index 4fc2056bd227..e615dc240150 100644
--- a/drivers/s390/net/ism_drv.c
+++ b/drivers/s390/net/ism_drv.c
@@ -521,8 +521,10 @@ static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	ism->smcd = smcd_alloc_dev(&pdev->dev, dev_name(&pdev->dev), &ism_ops,
 				   ISM_NR_DMBS);
-	if (!ism->smcd)
+	if (!ism->smcd) {
+		ret = -ENOMEM;
 		goto err_resource;
+	}
 
 	ism->smcd->priv = ism;
 	ret = ism_dev_init(ism);
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 6b8f99e7d8a8..d32cef686074 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -676,17 +676,17 @@ static int qeth_check_idx_response(struct qeth_card *card,
 	unsigned char *buffer)
 {
 	QETH_DBF_HEX(CTRL, 2, buffer, QETH_DBF_CTRL_LEN);
-	if ((buffer[2] & 0xc0) == 0xc0) {
+	if ((buffer[2] & QETH_IDX_TERMINATE_MASK) == QETH_IDX_TERMINATE) {
 		QETH_DBF_MESSAGE(2, "received an IDX TERMINATE with cause code %#04x\n",
 				 buffer[4]);
 		QETH_CARD_TEXT(card, 2, "ckidxres");
 		QETH_CARD_TEXT(card, 2, " idxterm");
-		QETH_CARD_TEXT_(card, 2, "  rc%d", -EIO);
-		if (buffer[4] == 0xf6) {
+		QETH_CARD_TEXT_(card, 2, "rc%x", buffer[4]);
+		if (buffer[4] == QETH_IDX_TERM_BAD_TRANSPORT ||
+		    buffer[4] == QETH_IDX_TERM_BAD_TRANSPORT_VM) {
 			dev_err(&card->gdev->dev,
-			"The qeth device is not configured "
-			"for the OSI layer required by z/VM\n");
-			return -EPERM;
+				"The device does not support the configured transport mode\n");
+			return -EPROTONOSUPPORT;
 		}
 		return -EIO;
 	}
@@ -792,10 +792,10 @@ static void qeth_issue_next_read_cb(struct qeth_card *card,
 	case 0:
 		break;
 	case -EIO:
-		qeth_clear_ipacmd_list(card);
 		qeth_schedule_recovery(card);
 		/* fall through */
 	default:
+		qeth_clear_ipacmd_list(card);
 		goto out;
 	}
 
@@ -1305,7 +1305,6 @@ static int qeth_osa_set_output_queues(struct qeth_card *card, bool single)
 	if (count == 1)
 		dev_info(&card->gdev->dev, "Priority Queueing not supported\n");
 
-	card->qdio.default_out_queue = single ? 0 : QETH_DEFAULT_QUEUE;
 	card->qdio.no_out_queues = count;
 	return 0;
 }
@@ -2538,50 +2537,46 @@ static int qeth_mpc_initialize(struct qeth_card *card)
 	rc = qeth_cm_enable(card);
 	if (rc) {
 		QETH_DBF_TEXT_(SETUP, 2, "2err%d", rc);
-		goto out_qdio;
+		return rc;
 	}
 	rc = qeth_cm_setup(card);
 	if (rc) {
 		QETH_DBF_TEXT_(SETUP, 2, "3err%d", rc);
-		goto out_qdio;
+		return rc;
 	}
 	rc = qeth_ulp_enable(card);
 	if (rc) {
 		QETH_DBF_TEXT_(SETUP, 2, "4err%d", rc);
-		goto out_qdio;
+		return rc;
 	}
 	rc = qeth_ulp_setup(card);
 	if (rc) {
 		QETH_DBF_TEXT_(SETUP, 2, "5err%d", rc);
-		goto out_qdio;
+		return rc;
 	}
 	rc = qeth_alloc_qdio_queues(card);
 	if (rc) {
 		QETH_DBF_TEXT_(SETUP, 2, "5err%d", rc);
-		goto out_qdio;
+		return rc;
 	}
 	rc = qeth_qdio_establish(card);
 	if (rc) {
 		QETH_DBF_TEXT_(SETUP, 2, "6err%d", rc);
 		qeth_free_qdio_queues(card);
-		goto out_qdio;
+		return rc;
 	}
 	rc = qeth_qdio_activate(card);
 	if (rc) {
 		QETH_DBF_TEXT_(SETUP, 2, "7err%d", rc);
-		goto out_qdio;
+		return rc;
 	}
 	rc = qeth_dm_act(card);
 	if (rc) {
 		QETH_DBF_TEXT_(SETUP, 2, "8err%d", rc);
-		goto out_qdio;
+		return rc;
 	}
 
 	return 0;
-out_qdio:
-	qeth_qdio_clear_card(card, !IS_IQD(card));
-	qdio_free(CARD_DDEV(card));
-	return rc;
 }
 
 void qeth_print_status_message(struct qeth_card *card)
@@ -2694,12 +2689,12 @@ static int qeth_init_input_buffer(struct qeth_card *card,
 		buf->rx_skb = netdev_alloc_skb(card->dev,
 					       QETH_RX_PULL_LEN + ETH_HLEN);
 		if (!buf->rx_skb)
-			return 1;
+			return -ENOMEM;
 	}
 
 	pool_entry = qeth_find_free_buffer_pool_entry(card);
 	if (!pool_entry)
-		return 1;
+		return -ENOBUFS;
 
 	/*
 	 * since the buffer is accessed only from the input_tasklet
@@ -2731,10 +2726,15 @@ int qeth_init_qdio_queues(struct qeth_card *card)
 	/* inbound queue */
 	qdio_reset_buffers(card->qdio.in_q->qdio_bufs, QDIO_MAX_BUFFERS_PER_Q);
 	memset(&card->rx, 0, sizeof(struct qeth_rx));
+
 	qeth_initialize_working_pool_list(card);
 	/*give only as many buffers to hardware as we have buffer pool entries*/
-	for (i = 0; i < card->qdio.in_buf_pool.buf_count - 1; ++i)
-		qeth_init_input_buffer(card, &card->qdio.in_q->bufs[i]);
+	for (i = 0; i < card->qdio.in_buf_pool.buf_count - 1; i++) {
+		rc = qeth_init_input_buffer(card, &card->qdio.in_q->bufs[i]);
+		if (rc)
+			return rc;
+	}
+
 	card->qdio.in_q->next_buf_to_init =
 		card->qdio.in_buf_pool.buf_count - 1;
 	rc = do_QDIO(CARD_DDEV(card), QDIO_FLAG_SYNC_INPUT, 0, 0,
@@ -3464,11 +3464,6 @@ int qeth_configure_cq(struct qeth_card *card, enum qeth_cq cq)
 			goto out;
 		}
 
-		if (card->state != CARD_STATE_DOWN) {
-			rc = -1;
-			goto out;
-		}
-
 		qeth_free_qdio_queues(card);
 		card->options.cq = cq;
 		rc = 0;
@@ -4243,9 +4238,6 @@ static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card,
 	int fallback = *(int *)reply->param;
 
 	QETH_CARD_TEXT(card, 4, "setaccb");
-	if (cmd->hdr.return_code)
-		return -EIO;
-	qeth_setadpparms_inspect_rc(cmd);
 
 	access_ctrl_req = &cmd->data.setadapterparms.data.set_access_ctrl;
 	QETH_DBF_TEXT_(SETUP, 2, "setaccb");
@@ -4257,7 +4249,7 @@ static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card,
 		QETH_DBF_MESSAGE(3, "ERR:SET_ACCESS_CTRL(%#x) on device %x: %#x\n",
 				 access_ctrl_req->subcmd_code, CARD_DEVID(card),
 				 cmd->data.setadapterparms.hdr.return_code);
-	switch (cmd->data.setadapterparms.hdr.return_code) {
+	switch (qeth_setadpparms_inspect_rc(cmd)) {
 	case SET_ACCESS_CTRL_RC_SUCCESS:
 		if (card->options.isolation == ISOLATION_MODE_NONE) {
 			dev_info(&card->gdev->dev,
@@ -4832,10 +4824,10 @@ static void qeth_qdio_establish_cq(struct qeth_card *card,
 	if (card->options.cq == QETH_CQ_ENABLED) {
 		int offset = QDIO_MAX_BUFFERS_PER_Q *
 			     (card->qdio.no_in_queues - 1);
-		for (i = 0; i < QDIO_MAX_BUFFERS_PER_Q; ++i) {
-			in_sbal_ptrs[offset + i] = (struct qdio_buffer *)
-				virt_to_phys(card->qdio.c_q->bufs[i].buffer);
-		}
+
+		for (i = 0; i < QDIO_MAX_BUFFERS_PER_Q; i++)
+			in_sbal_ptrs[offset + i] =
+				card->qdio.c_q->bufs[i].buffer;
 
 		queue_start_poll[card->qdio.no_in_queues - 1] = NULL;
 	}
@@ -4870,10 +4862,9 @@ static int qeth_qdio_establish(struct qeth_card *card)
 		rc = -ENOMEM;
 		goto out_free_qib_param;
 	}
-	for (i = 0; i < QDIO_MAX_BUFFERS_PER_Q; ++i) {
-		in_sbal_ptrs[i] = (struct qdio_buffer *)
-			virt_to_phys(card->qdio.in_q->bufs[i].buffer);
-	}
+
+	for (i = 0; i < QDIO_MAX_BUFFERS_PER_Q; i++)
+		in_sbal_ptrs[i] = card->qdio.in_q->bufs[i].buffer;
 
 	queue_start_poll = kcalloc(card->qdio.no_in_queues, sizeof(void *),
 				   GFP_KERNEL);
@@ -4894,11 +4885,11 @@ static int qeth_qdio_establish(struct qeth_card *card)
 		rc = -ENOMEM;
 		goto out_free_queue_start_poll;
 	}
+
 	for (i = 0, k = 0; i < card->qdio.no_out_queues; ++i)
-		for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; ++j, ++k) {
-			out_sbal_ptrs[k] = (struct qdio_buffer *)virt_to_phys(
-				card->qdio.out_qs[i]->bufs[j]->buffer);
-		}
+		for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; j++, k++)
+			out_sbal_ptrs[k] =
+				card->qdio.out_qs[i]->bufs[j]->buffer;
 
 	memset(&init_data, 0, sizeof(struct qdio_initialize));
 	init_data.cdev                   = CARD_DDEV(card);
@@ -5111,10 +5102,8 @@ retriable:
 	}
 	if (qeth_adp_supported(card, IPA_SETADP_SET_DIAG_ASSIST)) {
 		rc = qeth_query_setdiagass(card);
-		if (rc < 0) {
+		if (rc)
 			QETH_DBF_TEXT_(SETUP, 2, "8err%d", rc);
-			goto out;
-		}
 	}
 	return 0;
 out:
diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h
index f5237b7c14c4..a1c62748f006 100644
--- a/drivers/s390/net/qeth_core_mpc.h
+++ b/drivers/s390/net/qeth_core_mpc.h
@@ -918,6 +918,11 @@ extern unsigned char IDX_ACTIVATE_WRITE[];
 #define QETH_IDX_ACT_ERR_AUTH		0x1E
 #define QETH_IDX_ACT_ERR_AUTH_USER	0x20
 
+#define QETH_IDX_TERMINATE		0xc0
+#define QETH_IDX_TERMINATE_MASK		0xc0
+#define QETH_IDX_TERM_BAD_TRANSPORT	0x41
+#define QETH_IDX_TERM_BAD_TRANSPORT_VM	0xf6
+
 #define PDU_ENCAPSULATION(buffer) \
 	(buffer + *(buffer + (*(buffer + 0x0b)) + \
 	 *(buffer + *(buffer + 0x0b) + 0x11) + 0x07))
diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c
index 9f392497d570..4c3e222e5572 100644
--- a/drivers/s390/net/qeth_core_sys.c
+++ b/drivers/s390/net/qeth_core_sys.c
@@ -227,7 +227,7 @@ static ssize_t qeth_dev_prioqing_store(struct device *dev,
 		card->qdio.default_out_queue = QETH_DEFAULT_QUEUE;
 	} else if (sysfs_streq(buf, "prio_queueing_vlan")) {
 		if (IS_LAYER3(card)) {
-			rc = -ENOTSUPP;
+			rc = -EOPNOTSUPP;
 			goto out;
 		}
 		card->qdio.do_prio_queueing = QETH_PRIO_Q_ING_VLAN;
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index ff8a6cd790b1..2e51675e8d45 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -287,7 +287,6 @@ static void qeth_l2_stop_card(struct qeth_card *card)
 		card->state = CARD_STATE_HARDSETUP;
 	}
 	if (card->state == CARD_STATE_HARDSETUP) {
-		qeth_qdio_clear_card(card, 0);
 		qeth_drain_output_queues(card);
 		qeth_clear_working_pool_list(card);
 		card->state = CARD_STATE_DOWN;
@@ -297,8 +296,10 @@ static void qeth_l2_stop_card(struct qeth_card *card)
 		qeth_clear_cmd_buffers(&card->write);
 	}
 
+	qeth_qdio_clear_card(card, 0);
 	flush_workqueue(card->event_wq);
 	card->info.mac_bits &= ~QETH_LAYER2_MAC_REGISTERED;
+	card->info.promisc_mode = 0;
 }
 
 static int qeth_l2_process_inbound_buffer(struct qeth_card *card,
@@ -1254,6 +1255,10 @@ static void qeth_bridge_state_change(struct qeth_card *card,
 	int extrasize;
 
 	QETH_CARD_TEXT(card, 2, "brstchng");
+	if (qports->num_entries == 0) {
+		QETH_CARD_TEXT(card, 2, "BPempty");
+		return;
+	}
 	if (qports->entry_length != sizeof(struct qeth_sbp_port_entry)) {
 		QETH_CARD_TEXT_(card, 2, "BPsz%04x", qports->entry_length);
 		return;
@@ -1920,15 +1925,14 @@ int qeth_l2_vnicc_set_state(struct qeth_card *card, u32 vnicc, bool state)
 
 	QETH_CARD_TEXT(card, 2, "vniccsch");
 
-	/* do not change anything if BridgePort is enabled */
-	if (qeth_bridgeport_is_in_use(card))
-		return -EBUSY;
-
 	/* check if characteristic and enable/disable are supported */
 	if (!(card->options.vnicc.sup_chars & vnicc) ||
 	    !(card->options.vnicc.set_char_sup & vnicc))
 		return -EOPNOTSUPP;
 
+	if (qeth_bridgeport_is_in_use(card))
+		return -EBUSY;
+
 	/* set enable/disable command and store wanted characteristic */
 	if (state) {
 		cmd = IPA_VNICC_ENABLE;
@@ -1974,14 +1978,13 @@ int qeth_l2_vnicc_get_state(struct qeth_card *card, u32 vnicc, bool *state)
 
 	QETH_CARD_TEXT(card, 2, "vniccgch");
 
-	/* do not get anything if BridgePort is enabled */
-	if (qeth_bridgeport_is_in_use(card))
-		return -EBUSY;
-
 	/* check if characteristic is supported */
 	if (!(card->options.vnicc.sup_chars & vnicc))
 		return -EOPNOTSUPP;
 
+	if (qeth_bridgeport_is_in_use(card))
+		return -EBUSY;
+
 	/* if card is ready, query current VNICC state */
 	if (qeth_card_hw_is_reachable(card))
 		rc = qeth_l2_vnicc_query_chars(card);
@@ -1999,15 +2002,14 @@ int qeth_l2_vnicc_set_timeout(struct qeth_card *card, u32 timeout)
 
 	QETH_CARD_TEXT(card, 2, "vniccsto");
 
-	/* do not change anything if BridgePort is enabled */
-	if (qeth_bridgeport_is_in_use(card))
-		return -EBUSY;
-
 	/* check if characteristic and set_timeout are supported */
 	if (!(card->options.vnicc.sup_chars & QETH_VNICC_LEARNING) ||
 	    !(card->options.vnicc.getset_timeout_sup & QETH_VNICC_LEARNING))
 		return -EOPNOTSUPP;
 
+	if (qeth_bridgeport_is_in_use(card))
+		return -EBUSY;
+
 	/* do we need to do anything? */
 	if (card->options.vnicc.learning_timeout == timeout)
 		return rc;
@@ -2036,14 +2038,14 @@ int qeth_l2_vnicc_get_timeout(struct qeth_card *card, u32 *timeout)
 
 	QETH_CARD_TEXT(card, 2, "vniccgto");
 
-	/* do not get anything if BridgePort is enabled */
-	if (qeth_bridgeport_is_in_use(card))
-		return -EBUSY;
-
 	/* check if characteristic and get_timeout are supported */
 	if (!(card->options.vnicc.sup_chars & QETH_VNICC_LEARNING) ||
 	    !(card->options.vnicc.getset_timeout_sup & QETH_VNICC_LEARNING))
 		return -EOPNOTSUPP;
+
+	if (qeth_bridgeport_is_in_use(card))
+		return -EBUSY;
+
 	/* if card is ready, get timeout. Otherwise, just return stored value */
 	*timeout = card->options.vnicc.learning_timeout;
 	if (qeth_card_hw_is_reachable(card))
@@ -2057,8 +2059,7 @@ int qeth_l2_vnicc_get_timeout(struct qeth_card *card, u32 *timeout)
 /* check if VNICC is currently enabled */
 bool qeth_l2_vnicc_is_in_use(struct qeth_card *card)
 {
-	/* if everything is turned off, VNICC is not active */
-	if (!card->options.vnicc.cur_chars)
+	if (!card->options.vnicc.sup_chars)
 		return false;
 	/* default values are only OK if rx_bcast was not enabled by user
 	 * or the card is offline.
@@ -2138,8 +2139,9 @@ static void qeth_l2_vnicc_init(struct qeth_card *card)
 	/* enforce assumed default values and recover settings, if changed  */
 	error = qeth_l2_vnicc_recover_timeout(card, QETH_VNICC_LEARNING,
 					      timeout);
-	chars_tmp = card->options.vnicc.wanted_chars ^ QETH_VNICC_DEFAULT;
-	chars_tmp |= QETH_VNICC_BRIDGE_INVISIBLE;
+	/* Change chars, if necessary  */
+	chars_tmp = card->options.vnicc.wanted_chars ^
+		    card->options.vnicc.cur_chars;
 	chars_len = sizeof(card->options.vnicc.wanted_chars) * BITS_PER_BYTE;
 	for_each_set_bit(i, &chars_tmp, chars_len) {
 		vnicc = BIT(i);
diff --git a/drivers/s390/net/qeth_l2_sys.c b/drivers/s390/net/qeth_l2_sys.c
index f2c3b127b1e4..10c2fd44170b 100644
--- a/drivers/s390/net/qeth_l2_sys.c
+++ b/drivers/s390/net/qeth_l2_sys.c
@@ -269,7 +269,8 @@ void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card)
 		return;
 	if (!card->options.sbp.supported_funcs)
 		return;
-	if (card->options.sbp.role != QETH_SBP_ROLE_NONE) {
+	if (!card->options.sbp.reflect_promisc &&
+	    card->options.sbp.role != QETH_SBP_ROLE_NONE) {
 		/* Conditional to avoid spurious error messages */
 		qeth_bridgeport_setrole(card, card->options.sbp.role);
 		/* Let the callback function refresh the stored role value. */
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 13bf3e2e9cea..7b898d4b2b02 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -1431,7 +1431,6 @@ static void qeth_l3_stop_card(struct qeth_card *card)
 		card->state = CARD_STATE_HARDSETUP;
 	}
 	if (card->state == CARD_STATE_HARDSETUP) {
-		qeth_qdio_clear_card(card, 0);
 		qeth_drain_output_queues(card);
 		qeth_clear_working_pool_list(card);
 		card->state = CARD_STATE_DOWN;
@@ -1441,7 +1440,9 @@ static void qeth_l3_stop_card(struct qeth_card *card)
 		qeth_clear_cmd_buffers(&card->write);
 	}
 
+	qeth_qdio_clear_card(card, 0);
 	flush_workqueue(card->event_wq);
+	card->info.promisc_mode = 0;
 }
 
 /*
diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c
index 2f73b33c9347..333fd4619dc6 100644
--- a/drivers/s390/net/qeth_l3_sys.c
+++ b/drivers/s390/net/qeth_l3_sys.c
@@ -270,24 +270,36 @@ static ssize_t qeth_l3_dev_hsuid_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
 	struct qeth_card *card = dev_get_drvdata(dev);
+	int rc = 0;
 	char *tmp;
-	int rc;
 
 	if (!card)
 		return -EINVAL;
 
 	if (!IS_IQD(card))
 		return -EPERM;
-	if (card->state != CARD_STATE_DOWN)
-		return -EPERM;
-	if (card->options.sniffer)
-		return -EPERM;
-	if (card->options.cq == QETH_CQ_NOTAVAILABLE)
-		return -EPERM;
+
+	mutex_lock(&card->conf_mutex);
+	if (card->state != CARD_STATE_DOWN) {
+		rc = -EPERM;
+		goto out;
+	}
+
+	if (card->options.sniffer) {
+		rc = -EPERM;
+		goto out;
+	}
+
+	if (card->options.cq == QETH_CQ_NOTAVAILABLE) {
+		rc = -EPERM;
+		goto out;
+	}
 
 	tmp = strsep((char **)&buf, "\n");
-	if (strlen(tmp) > 8)
-		return -EINVAL;
+	if (strlen(tmp) > 8) {
+		rc = -EINVAL;
+		goto out;
+	}
 
 	if (card->options.hsuid[0])
 		/* delete old ip address */
@@ -298,11 +310,13 @@ static ssize_t qeth_l3_dev_hsuid_store(struct device *dev,
 		card->options.hsuid[0] = '\0';
 		memcpy(card->dev->perm_addr, card->options.hsuid, 9);
 		qeth_configure_cq(card, QETH_CQ_DISABLED);
-		return count;
+		goto out;
 	}
 
-	if (qeth_configure_cq(card, QETH_CQ_ENABLED))
-		return -EPERM;
+	if (qeth_configure_cq(card, QETH_CQ_ENABLED)) {
+		rc = -EPERM;
+		goto out;
+	}
 
 	snprintf(card->options.hsuid, sizeof(card->options.hsuid),
 		 "%-8s", tmp);
@@ -311,6 +325,8 @@ static ssize_t qeth_l3_dev_hsuid_store(struct device *dev,
 
 	rc = qeth_l3_modify_hsuid(card, true);
 
+out:
+	mutex_unlock(&card->conf_mutex);
 	return rc ? rc : count;
 }
 
diff --git a/drivers/s390/scsi/zfcp_erp.c b/drivers/s390/scsi/zfcp_erp.c
index 96f0d34e9459..08dc2efb7d8a 100644
--- a/drivers/s390/scsi/zfcp_erp.c
+++ b/drivers/s390/scsi/zfcp_erp.c
@@ -576,7 +576,10 @@ static void zfcp_erp_strategy_check_fsfreq(struct zfcp_erp_action *act)
 				   ZFCP_STATUS_ERP_TIMEDOUT)) {
 			req->status |= ZFCP_STATUS_FSFREQ_DISMISSED;
 			zfcp_dbf_rec_run("erscf_1", act);
-			req->erp_action = NULL;
+			/* lock-free concurrent access with
+			 * zfcp_erp_timeout_handler()
+			 */
+			WRITE_ONCE(req->erp_action, NULL);
 		}
 		if (act->status & ZFCP_STATUS_ERP_TIMEDOUT)
 			zfcp_dbf_rec_run("erscf_2", act);
@@ -612,8 +615,14 @@ void zfcp_erp_notify(struct zfcp_erp_action *erp_action, unsigned long set_mask)
 void zfcp_erp_timeout_handler(struct timer_list *t)
 {
 	struct zfcp_fsf_req *fsf_req = from_timer(fsf_req, t, timer);
-	struct zfcp_erp_action *act = fsf_req->erp_action;
+	struct zfcp_erp_action *act;
 
+	if (fsf_req->status & ZFCP_STATUS_FSFREQ_DISMISSED)
+		return;
+	/* lock-free concurrent access with zfcp_erp_strategy_check_fsfreq() */
+	act = READ_ONCE(fsf_req->erp_action);
+	if (!act)
+		return;
 	zfcp_erp_notify(act, ZFCP_STATUS_ERP_TIMEDOUT);
 }
 
@@ -725,7 +734,7 @@ static void zfcp_erp_enqueue_ptp_port(struct zfcp_adapter *adapter)
 				 adapter->peer_d_id);
 	if (IS_ERR(port)) /* error or port already attached */
 		return;
-	_zfcp_erp_port_reopen(port, 0, "ereptp1");
+	zfcp_erp_port_reopen(port, 0, "ereptp1");
 }
 
 static enum zfcp_erp_act_result zfcp_erp_adapter_strat_fsf_xconf(
diff --git a/drivers/scsi/aic7xxx/aic7xxx_core.c b/drivers/scsi/aic7xxx/aic7xxx_core.c
index a9d40d3b90ef..4190a025381a 100644
--- a/drivers/scsi/aic7xxx/aic7xxx_core.c
+++ b/drivers/scsi/aic7xxx/aic7xxx_core.c
@@ -2314,7 +2314,7 @@ ahc_find_syncrate(struct ahc_softc *ahc, u_int *period,
 			 * At some speeds, we only support
 			 * ST transfers.
 			 */
-		 	if ((syncrate->sxfr_u2 & ST_SXFR) != 0)
+			if ((syncrate->sxfr_u2 & ST_SXFR) != 0)
 				*ppr_options &= ~MSG_EXT_PPR_DT_REQ;
 			break;
 		}
diff --git a/drivers/scsi/arm/acornscsi.c b/drivers/scsi/arm/acornscsi.c
index d12dd89538df..deab66598910 100644
--- a/drivers/scsi/arm/acornscsi.c
+++ b/drivers/scsi/arm/acornscsi.c
@@ -2911,8 +2911,10 @@ static int acornscsi_probe(struct expansion_card *ec, const struct ecard_id *id)
 
 	ashost->base = ecardm_iomap(ec, ECARD_RES_MEMC, 0, 0);
 	ashost->fast = ecardm_iomap(ec, ECARD_RES_IOCFAST, 0, 0);
-	if (!ashost->base || !ashost->fast)
+	if (!ashost->base || !ashost->fast) {
+		ret = -ENOMEM;
 		goto out_put;
+	}
 
 	host->irq = ec->irq;
 	ashost->host = host;
diff --git a/drivers/scsi/arm/cumana_2.c b/drivers/scsi/arm/cumana_2.c
index a1f3e9ee4e63..14e1d001253c 100644
--- a/drivers/scsi/arm/cumana_2.c
+++ b/drivers/scsi/arm/cumana_2.c
@@ -450,7 +450,7 @@ static int cumanascsi2_probe(struct expansion_card *ec,
 
 	if (info->info.scsi.dma != NO_DMA)
 		free_dma(info->info.scsi.dma);
-	free_irq(ec->irq, host);
+	free_irq(ec->irq, info);
 
  out_release:
 	fas216_release(host);
diff --git a/drivers/scsi/arm/eesox.c b/drivers/scsi/arm/eesox.c
index 134f040d58e2..f441ec8eb93d 100644
--- a/drivers/scsi/arm/eesox.c
+++ b/drivers/scsi/arm/eesox.c
@@ -571,7 +571,7 @@ static int eesoxscsi_probe(struct expansion_card *ec, const struct ecard_id *id)
 
 	if (info->info.scsi.dma != NO_DMA)
 		free_dma(info->info.scsi.dma);
-	free_irq(ec->irq, host);
+	free_irq(ec->irq, info);
 
  out_remove:
 	fas216_remove(host);
diff --git a/drivers/scsi/arm/powertec.c b/drivers/scsi/arm/powertec.c
index c795537a671c..2dc0df005cb3 100644
--- a/drivers/scsi/arm/powertec.c
+++ b/drivers/scsi/arm/powertec.c
@@ -378,7 +378,7 @@ static int powertecscsi_probe(struct expansion_card *ec,
 
 	if (info->info.scsi.dma != NO_DMA)
 		free_dma(info->info.scsi.dma);
-	free_irq(ec->irq, host);
+	free_irq(ec->irq, info);
 
  out_release:
 	fas216_release(host);
diff --git a/drivers/scsi/bnx2i/bnx2i_iscsi.c b/drivers/scsi/bnx2i/bnx2i_iscsi.c
index c5fa5f3b00e9..0b28d44d3573 100644
--- a/drivers/scsi/bnx2i/bnx2i_iscsi.c
+++ b/drivers/scsi/bnx2i/bnx2i_iscsi.c
@@ -915,12 +915,12 @@ void bnx2i_free_hba(struct bnx2i_hba *hba)
 	INIT_LIST_HEAD(&hba->ep_ofld_list);
 	INIT_LIST_HEAD(&hba->ep_active_list);
 	INIT_LIST_HEAD(&hba->ep_destroy_list);
-	pci_dev_put(hba->pcidev);
 
 	if (hba->regview) {
 		pci_iounmap(hba->pcidev, hba->regview);
 		hba->regview = NULL;
 	}
+	pci_dev_put(hba->pcidev);
 	bnx2i_free_mp_bdt(hba);
 	bnx2i_release_free_cid_que(hba);
 	iscsi_host_free(shost);
diff --git a/drivers/scsi/csiostor/csio_scsi.c b/drivers/scsi/csiostor/csio_scsi.c
index 469d0bc9f5fe..00cf33573136 100644
--- a/drivers/scsi/csiostor/csio_scsi.c
+++ b/drivers/scsi/csiostor/csio_scsi.c
@@ -1383,7 +1383,7 @@ csio_device_reset(struct device *dev,
 		return -EINVAL;
 
 	/* Delete NPIV lnodes */
-	 csio_lnodes_exit(hw, 1);
+	csio_lnodes_exit(hw, 1);
 
 	/* Block upper IOs */
 	csio_lnodes_block_request(hw);
diff --git a/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c
index b8dd9e648dd0..ce7f0364a62a 100644
--- a/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c
+++ b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c
@@ -959,6 +959,7 @@ static int init_act_open(struct cxgbi_sock *csk)
 	struct net_device *ndev = cdev->ports[csk->port_id];
 	struct cxgbi_hba *chba = cdev->hbas[csk->port_id];
 	struct sk_buff *skb = NULL;
+	int ret;
 
 	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
 		"csk 0x%p,%u,0x%lx.\n", csk, csk->state, csk->flags);
@@ -979,16 +980,16 @@ static int init_act_open(struct cxgbi_sock *csk)
 	csk->atid = cxgb3_alloc_atid(t3dev, &t3_client, csk);
 	if (csk->atid < 0) {
 		pr_err("NO atid available.\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto put_sock;
 	}
 	cxgbi_sock_set_flag(csk, CTPF_HAS_ATID);
 	cxgbi_sock_get(csk);
 
 	skb = alloc_wr(sizeof(struct cpl_act_open_req), 0, GFP_KERNEL);
 	if (!skb) {
-		cxgb3_free_atid(t3dev, csk->atid);
-		cxgbi_sock_put(csk);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto free_atid;
 	}
 	skb->sk = (struct sock *)csk;
 	set_arp_failure_handler(skb, act_open_arp_failure);
@@ -1010,6 +1011,15 @@ static int init_act_open(struct cxgbi_sock *csk)
 	cxgbi_sock_set_state(csk, CTP_ACTIVE_OPEN);
 	send_act_open_req(csk, skb, csk->l2t);
 	return 0;
+
+free_atid:
+	cxgb3_free_atid(t3dev, csk->atid);
+put_sock:
+	cxgbi_sock_put(csk);
+	l2t_release(t3dev, csk->l2t);
+	csk->l2t = NULL;
+
+	return ret;
 }
 
 cxgb3_cpl_handler_func cxgb3i_cpl_handlers[NUM_CPL_CMDS] = {
diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c
index 7d43e014bd21..1d3305416075 100644
--- a/drivers/scsi/cxgbi/libcxgbi.c
+++ b/drivers/scsi/cxgbi/libcxgbi.c
@@ -121,7 +121,8 @@ static inline void cxgbi_device_destroy(struct cxgbi_device *cdev)
 		"cdev 0x%p, p# %u.\n", cdev, cdev->nports);
 	cxgbi_hbas_remove(cdev);
 	cxgbi_device_portmap_cleanup(cdev);
-	cxgbi_ppm_release(cdev->cdev2ppm(cdev));
+	if (cdev->cdev2ppm)
+		cxgbi_ppm_release(cdev->cdev2ppm(cdev));
 	if (cdev->pmap.max_connect)
 		cxgbi_free_big_mem(cdev->pmap.port_csk);
 	kfree(cdev);
diff --git a/drivers/scsi/esas2r/esas2r_flash.c b/drivers/scsi/esas2r/esas2r_flash.c
index 7bd376d95ed5..b02ac389e6c6 100644
--- a/drivers/scsi/esas2r/esas2r_flash.c
+++ b/drivers/scsi/esas2r/esas2r_flash.c
@@ -1197,6 +1197,7 @@ bool esas2r_nvram_read_direct(struct esas2r_adapter *a)
 	if (!esas2r_read_flash_block(a, a->nvram, FLS_OFFSET_NVR,
 				     sizeof(struct esas2r_sas_nvram))) {
 		esas2r_hdebug("NVRAM read failed, using defaults");
+		up(&a->nvram_semaphore);
 		return false;
 	}
 
diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c
index 80608b53897b..e3f5c91d5e4f 100644
--- a/drivers/scsi/fnic/fnic_scsi.c
+++ b/drivers/scsi/fnic/fnic_scsi.c
@@ -439,6 +439,9 @@ static int fnic_queuecommand_lck(struct scsi_cmnd *sc, void (*done)(struct scsi_
 	if (unlikely(fnic_chk_state_flags_locked(fnic, FNIC_FLAGS_IO_BLOCKED)))
 		return SCSI_MLQUEUE_HOST_BUSY;
 
+	if (unlikely(fnic_chk_state_flags_locked(fnic, FNIC_FLAGS_FWRESET)))
+		return SCSI_MLQUEUE_HOST_BUSY;
+
 	rport = starget_to_rport(scsi_target(sc->device));
 	if (!rport) {
 		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
diff --git a/drivers/scsi/fnic/vnic_dev.c b/drivers/scsi/fnic/vnic_dev.c
index 78af9cc2009b..522636e94628 100644
--- a/drivers/scsi/fnic/vnic_dev.c
+++ b/drivers/scsi/fnic/vnic_dev.c
@@ -688,26 +688,26 @@ int vnic_dev_soft_reset_done(struct vnic_dev *vdev, int *done)
 
 int vnic_dev_hang_notify(struct vnic_dev *vdev)
 {
-	u64 a0, a1;
+	u64 a0 = 0, a1 = 0;
 	int wait = 1000;
 	return vnic_dev_cmd(vdev, CMD_HANG_NOTIFY, &a0, &a1, wait);
 }
 
 int vnic_dev_mac_addr(struct vnic_dev *vdev, u8 *mac_addr)
 {
-	u64 a0, a1;
+	u64 a[2] = {};
 	int wait = 1000;
 	int err, i;
 
 	for (i = 0; i < ETH_ALEN; i++)
 		mac_addr[i] = 0;
 
-	err = vnic_dev_cmd(vdev, CMD_MAC_ADDR, &a0, &a1, wait);
+	err = vnic_dev_cmd(vdev, CMD_MAC_ADDR, &a[0], &a[1], wait);
 	if (err)
 		return err;
 
 	for (i = 0; i < ETH_ALEN; i++)
-		mac_addr[i] = ((u8 *)&a0)[i];
+		mac_addr[i] = ((u8 *)&a)[i];
 
 	return 0;
 }
@@ -732,30 +732,30 @@ void vnic_dev_packet_filter(struct vnic_dev *vdev, int directed, int multicast,
 
 void vnic_dev_add_addr(struct vnic_dev *vdev, u8 *addr)
 {
-	u64 a0 = 0, a1 = 0;
+	u64 a[2] = {};
 	int wait = 1000;
 	int err;
 	int i;
 
 	for (i = 0; i < ETH_ALEN; i++)
-		((u8 *)&a0)[i] = addr[i];
+		((u8 *)&a)[i] = addr[i];
 
-	err = vnic_dev_cmd(vdev, CMD_ADDR_ADD, &a0, &a1, wait);
+	err = vnic_dev_cmd(vdev, CMD_ADDR_ADD, &a[0], &a[1], wait);
 	if (err)
 		pr_err("Can't add addr [%pM], %d\n", addr, err);
 }
 
 void vnic_dev_del_addr(struct vnic_dev *vdev, u8 *addr)
 {
-	u64 a0 = 0, a1 = 0;
+	u64 a[2] = {};
 	int wait = 1000;
 	int err;
 	int i;
 
 	for (i = 0; i < ETH_ALEN; i++)
-		((u8 *)&a0)[i] = addr[i];
+		((u8 *)&a)[i] = addr[i];
 
-	err = vnic_dev_cmd(vdev, CMD_ADDR_DEL, &a0, &a1, wait);
+	err = vnic_dev_cmd(vdev, CMD_ADDR_DEL, &a[0], &a[1], wait);
 	if (err)
 		pr_err("Can't del addr [%pM], %d\n", addr, err);
 }
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index a21bd4f7a4a5..d8553c855194 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -936,8 +936,11 @@ void hisi_sas_phy_oob_ready(struct hisi_hba *hisi_hba, int phy_no)
 	struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
 	struct device *dev = hisi_hba->dev;
 
+	dev_dbg(dev, "phy%d OOB ready\n", phy_no);
+	if (phy->phy_attached)
+		return;
+
 	if (!timer_pending(&phy->timer)) {
-		dev_dbg(dev, "phy%d OOB ready\n", phy_no);
 		phy->timer.expires = jiffies + HISI_SAS_WAIT_PHYUP_TIMEOUT * HZ;
 		add_timer(&phy->timer);
 	}
@@ -1006,12 +1009,13 @@ static void hisi_sas_port_notify_formed(struct asd_sas_phy *sas_phy)
 	struct hisi_hba *hisi_hba = sas_ha->lldd_ha;
 	struct hisi_sas_phy *phy = sas_phy->lldd_phy;
 	struct asd_sas_port *sas_port = sas_phy->port;
-	struct hisi_sas_port *port = to_hisi_sas_port(sas_port);
+	struct hisi_sas_port *port;
 	unsigned long flags;
 
 	if (!sas_port)
 		return;
 
+	port = to_hisi_sas_port(sas_port);
 	spin_lock_irqsave(&hisi_hba->lock, flags);
 	port->port_attached = 1;
 	port->id = phy->port_id;
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index 4aea97ee4b24..4744d0c6da1f 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -415,6 +415,8 @@ static int ibmvscsi_reenable_crq_queue(struct crq_queue *queue,
 	int rc = 0;
 	struct vio_dev *vdev = to_vio_dev(hostdata->dev);
 
+	set_adapter_info(hostdata);
+
 	/* Re-enable the CRQ */
 	do {
 		if (rc)
@@ -2281,16 +2283,12 @@ static int ibmvscsi_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 static int ibmvscsi_remove(struct vio_dev *vdev)
 {
 	struct ibmvscsi_host_data *hostdata = dev_get_drvdata(&vdev->dev);
-	unsigned long flags;
 
 	srp_remove_host(hostdata->host);
 	scsi_remove_host(hostdata->host);
 
 	purge_requests(hostdata, DID_ERROR);
-
-	spin_lock_irqsave(hostdata->host->host_lock, flags);
 	release_event_pool(&hostdata->pool, hostdata);
-	spin_unlock_irqrestore(hostdata->host->host_lock, flags);
 
 	ibmvscsi_release_crq_queue(&hostdata->queue, hostdata,
 					max_events);
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index d06bc1a817a1..a3e81f427609 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -9944,6 +9944,7 @@ static void ipr_init_ioa_cfg(struct ipr_ioa_cfg *ioa_cfg,
 	ioa_cfg->max_devs_supported = ipr_max_devs;
 
 	if (ioa_cfg->sis64) {
+		host->max_channel = IPR_MAX_SIS64_BUSES;
 		host->max_id = IPR_MAX_SIS64_TARGETS_PER_BUS;
 		host->max_lun = IPR_MAX_SIS64_LUNS_PER_TARGET;
 		if (ipr_max_devs > IPR_MAX_SIS64_DEVS)
@@ -9952,6 +9953,7 @@ static void ipr_init_ioa_cfg(struct ipr_ioa_cfg *ioa_cfg,
 					   + ((sizeof(struct ipr_config_table_entry64)
 					       * ioa_cfg->max_devs_supported)));
 	} else {
+		host->max_channel = IPR_VSET_BUS;
 		host->max_id = IPR_MAX_NUM_TARGETS_PER_BUS;
 		host->max_lun = IPR_MAX_NUM_LUNS_PER_TARGET;
 		if (ipr_max_devs > IPR_MAX_PHYSICAL_DEVS)
@@ -9961,7 +9963,6 @@ static void ipr_init_ioa_cfg(struct ipr_ioa_cfg *ioa_cfg,
 					       * ioa_cfg->max_devs_supported)));
 	}
 
-	host->max_channel = IPR_VSET_BUS;
 	host->unique_id = host->host_no;
 	host->max_cmd_len = IPR_MAX_CDB_LEN;
 	host->can_queue = ioa_cfg->max_cmds;
diff --git a/drivers/scsi/ipr.h b/drivers/scsi/ipr.h
index a67baeb36d1f..b97aa9ac2ffe 100644
--- a/drivers/scsi/ipr.h
+++ b/drivers/scsi/ipr.h
@@ -1300,6 +1300,7 @@ struct ipr_resource_entry {
 #define IPR_ARRAY_VIRTUAL_BUS			0x1
 #define IPR_VSET_VIRTUAL_BUS			0x2
 #define IPR_IOAFP_VIRTUAL_BUS			0x3
+#define IPR_MAX_SIS64_BUSES			0x4
 
 #define IPR_GET_RES_PHYS_LOC(res) \
 	(((res)->bus << 24) | ((res)->target << 8) | (res)->lun)
diff --git a/drivers/scsi/iscsi_boot_sysfs.c b/drivers/scsi/iscsi_boot_sysfs.c
index e4857b728033..a64abe38db2d 100644
--- a/drivers/scsi/iscsi_boot_sysfs.c
+++ b/drivers/scsi/iscsi_boot_sysfs.c
@@ -352,7 +352,7 @@ iscsi_boot_create_kobj(struct iscsi_boot_kset *boot_kset,
 	boot_kobj->kobj.kset = boot_kset->kset;
 	if (kobject_init_and_add(&boot_kobj->kobj, &iscsi_boot_ktype,
 				 NULL, name, index)) {
-		kfree(boot_kobj);
+		kobject_put(&boot_kobj->kobj);
 		return NULL;
 	}
 	boot_kobj->data = data;
diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index 0bc63a7ab41c..b5dd1caae5e9 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -887,6 +887,10 @@ free_host:
 static void iscsi_sw_tcp_session_destroy(struct iscsi_cls_session *cls_session)
 {
 	struct Scsi_Host *shost = iscsi_session_to_shost(cls_session);
+	struct iscsi_session *session = cls_session->dd_data;
+
+	if (WARN_ON_ONCE(session->leadconn))
+		return;
 
 	iscsi_tcp_r2tpool_free(cls_session->dd_data);
 	iscsi_session_teardown(cls_session);
diff --git a/drivers/scsi/libfc/fc_disc.c b/drivers/scsi/libfc/fc_disc.c
index 9c5f7c9178c6..2b865c6423e2 100644
--- a/drivers/scsi/libfc/fc_disc.c
+++ b/drivers/scsi/libfc/fc_disc.c
@@ -628,6 +628,8 @@ redisc:
 	}
 out:
 	kref_put(&rdata->kref, fc_rport_destroy);
+	if (!IS_ERR(fp))
+		fc_frame_free(fp);
 }
 
 /**
diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c
index da6e97d8dc3b..6bb8917b99a1 100644
--- a/drivers/scsi/libfc/fc_rport.c
+++ b/drivers/scsi/libfc/fc_rport.c
@@ -1208,9 +1208,15 @@ static void fc_rport_prli_resp(struct fc_seq *sp, struct fc_frame *fp,
 		rjt = fc_frame_payload_get(fp, sizeof(*rjt));
 		if (!rjt)
 			FC_RPORT_DBG(rdata, "PRLI bad response\n");
-		else
+		else {
 			FC_RPORT_DBG(rdata, "PRLI ELS rejected, reason %x expl %x\n",
 				     rjt->er_reason, rjt->er_explan);
+			if (rjt->er_reason == ELS_RJT_UNAB &&
+			    rjt->er_explan == ELS_EXPL_PLOGI_REQD) {
+				fc_rport_enter_plogi(rdata);
+				goto out;
+			}
+		}
 		fc_rport_error_retry(rdata, FC_EX_ELS_RJT);
 	}
 
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 4604e1bc334c..273426dfdd9a 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -740,6 +740,7 @@ struct lpfc_hba {
 					 */
 #define HBA_NVME_IOQ_FLUSH      0x80000 /* NVME IO queues flushed. */
 #define HBA_FLOGI_ISSUED	0x100000 /* FLOGI was issued */
+#define HBA_DEFER_FLOGI		0x800000 /* Defer FLOGI till read_sparm cmpl */
 
 	uint32_t fcp_ring_in_use; /* When polling test if intr-hndlr active*/
 	struct lpfc_dmabuf slim2p;
@@ -1204,6 +1205,15 @@ struct lpfc_hba {
 	uint64_t ktime_seg10_min;
 	uint64_t ktime_seg10_max;
 #endif
+
+	struct hlist_node cpuhp;	/* used for cpuhp per hba callback */
+	struct timer_list cpuhp_poll_timer;
+	struct list_head poll_list;	/* slowpath eq polling list */
+#define LPFC_POLL_HB	1		/* slowpath heartbeat */
+#define LPFC_POLL_FASTPATH	0	/* called from fastpath */
+#define LPFC_POLL_SLOWPATH	1	/* called from slowpath */
+
+	char os_host_name[MAXHOSTNAMELEN];
 };
 
 static inline struct Scsi_Host *
diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c
index b0202bc0aa62..ef7f62b68413 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.c
+++ b/drivers/scsi/lpfc/lpfc_bsg.c
@@ -4492,12 +4492,6 @@ lpfc_bsg_write_ebuf_set(struct lpfc_hba *phba, struct bsg_job *job,
 	phba->mbox_ext_buf_ctx.seqNum++;
 	nemb_tp = phba->mbox_ext_buf_ctx.nembType;
 
-	dd_data = kmalloc(sizeof(struct bsg_job_data), GFP_KERNEL);
-	if (!dd_data) {
-		rc = -ENOMEM;
-		goto job_error;
-	}
-
 	pbuf = (uint8_t *)dmabuf->virt;
 	size = job->request_payload.payload_len;
 	sg_copy_to_buffer(job->request_payload.sg_list,
@@ -4534,6 +4528,13 @@ lpfc_bsg_write_ebuf_set(struct lpfc_hba *phba, struct bsg_job *job,
 				"2968 SLI_CONFIG ext-buffer wr all %d "
 				"ebuffers received\n",
 				phba->mbox_ext_buf_ctx.numBuf);
+
+		dd_data = kmalloc(sizeof(struct bsg_job_data), GFP_KERNEL);
+		if (!dd_data) {
+			rc = -ENOMEM;
+			goto job_error;
+		}
+
 		/* mailbox command structure for base driver */
 		pmboxq = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 		if (!pmboxq) {
@@ -4582,6 +4583,8 @@ lpfc_bsg_write_ebuf_set(struct lpfc_hba *phba, struct bsg_job *job,
 	return SLI_CONFIG_HANDLED;
 
 job_error:
+	if (pmboxq)
+		mempool_free(pmboxq, phba->mbox_mem_pool);
 	lpfc_bsg_dma_page_free(phba, dmabuf);
 	kfree(dd_data);
 
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index e0b14d791b8c..4aa91d0b6291 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -179,7 +179,7 @@ int lpfc_issue_gidft(struct lpfc_vport *vport);
 int lpfc_get_gidft_type(struct lpfc_vport *vport, struct lpfc_iocbq *iocbq);
 int lpfc_ns_cmd(struct lpfc_vport *, int, uint8_t, uint32_t);
 int lpfc_fdmi_cmd(struct lpfc_vport *, struct lpfc_nodelist *, int, uint32_t);
-void lpfc_fdmi_num_disc_check(struct lpfc_vport *);
+void lpfc_fdmi_change_check(struct lpfc_vport *vport);
 void lpfc_delayed_disc_tmo(struct timer_list *);
 void lpfc_delayed_disc_timeout_handler(struct lpfc_vport *);
 
@@ -214,6 +214,12 @@ irqreturn_t lpfc_sli_fp_intr_handler(int, void *);
 irqreturn_t lpfc_sli4_intr_handler(int, void *);
 irqreturn_t lpfc_sli4_hba_intr_handler(int, void *);
 
+void lpfc_sli4_cleanup_poll_list(struct lpfc_hba *phba);
+int lpfc_sli4_poll_eq(struct lpfc_queue *q, uint8_t path);
+void lpfc_sli4_poll_hbtimer(struct timer_list *t);
+void lpfc_sli4_start_polling(struct lpfc_queue *q);
+void lpfc_sli4_stop_polling(struct lpfc_queue *q);
+
 void lpfc_read_rev(struct lpfc_hba *, LPFC_MBOXQ_t *);
 void lpfc_sli4_swap_str(struct lpfc_hba *, LPFC_MBOXQ_t *);
 void lpfc_config_ring(struct lpfc_hba *, int, LPFC_MBOXQ_t *);
diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index 4812bbbf43cc..6bc53d01d49e 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -1439,33 +1439,35 @@ int
 lpfc_vport_symbolic_node_name(struct lpfc_vport *vport, char *symbol,
 	size_t size)
 {
-	char fwrev[FW_REV_STR_SIZE];
-	int n;
+	char fwrev[FW_REV_STR_SIZE] = {0};
+	char tmp[MAXHOSTNAMELEN] = {0};
 
-	lpfc_decode_firmware_rev(vport->phba, fwrev, 0);
+	memset(symbol, 0, size);
 
-	n = scnprintf(symbol, size, "Emulex %s", vport->phba->ModelName);
-	if (size < n)
-		return n;
+	scnprintf(tmp, sizeof(tmp), "Emulex %s", vport->phba->ModelName);
+	if (strlcat(symbol, tmp, size) >= size)
+		goto buffer_done;
 
-	n += scnprintf(symbol + n, size - n, " FV%s", fwrev);
-	if (size < n)
-		return n;
+	lpfc_decode_firmware_rev(vport->phba, fwrev, 0);
+	scnprintf(tmp, sizeof(tmp), " FV%s", fwrev);
+	if (strlcat(symbol, tmp, size) >= size)
+		goto buffer_done;
 
-	n += scnprintf(symbol + n, size - n, " DV%s.",
-		      lpfc_release_version);
-	if (size < n)
-		return n;
+	scnprintf(tmp, sizeof(tmp), " DV%s", lpfc_release_version);
+	if (strlcat(symbol, tmp, size) >= size)
+		goto buffer_done;
 
-	n += scnprintf(symbol + n, size - n, " HN:%s.",
-		      init_utsname()->nodename);
-	if (size < n)
-		return n;
+	scnprintf(tmp, sizeof(tmp), " HN:%s", vport->phba->os_host_name);
+	if (strlcat(symbol, tmp, size) >= size)
+		goto buffer_done;
 
 	/* Note :- OS name is "Linux" */
-	n += scnprintf(symbol + n, size - n, " OS:%s",
-		      init_utsname()->sysname);
-	return n;
+	scnprintf(tmp, sizeof(tmp), " OS:%s", init_utsname()->sysname);
+	strlcat(symbol, tmp, size);
+
+buffer_done:
+	return strnlen(symbol, size);
+
 }
 
 static uint32_t
@@ -1938,14 +1940,16 @@ lpfc_cmpl_ct_disc_fdmi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 
 
 /**
- * lpfc_fdmi_num_disc_check - Check how many mapped NPorts we are connected to
+ * lpfc_fdmi_change_check - Check for changed FDMI parameters
  * @vport: pointer to a host virtual N_Port data structure.
  *
- * Called from hbeat timeout routine to check if the number of discovered
- * ports has changed. If so, re-register thar port Attribute.
+ * Check how many mapped NPorts we are connected to
+ * Check if our hostname changed
+ * Called from hbeat timeout routine to check if any FDMI parameters
+ * changed. If so, re-register those Attributes.
  */
 void
-lpfc_fdmi_num_disc_check(struct lpfc_vport *vport)
+lpfc_fdmi_change_check(struct lpfc_vport *vport)
 {
 	struct lpfc_hba *phba = vport->phba;
 	struct lpfc_nodelist *ndlp;
@@ -1958,17 +1962,41 @@ lpfc_fdmi_num_disc_check(struct lpfc_vport *vport)
 	if (!(vport->fc_flag & FC_FABRIC))
 		return;
 
+	ndlp = lpfc_findnode_did(vport, FDMI_DID);
+	if (!ndlp || !NLP_CHK_NODE_ACT(ndlp))
+		return;
+
+	/* Check if system hostname changed */
+	if (strcmp(phba->os_host_name, init_utsname()->nodename)) {
+		memset(phba->os_host_name, 0, sizeof(phba->os_host_name));
+		scnprintf(phba->os_host_name, sizeof(phba->os_host_name), "%s",
+			  init_utsname()->nodename);
+		lpfc_ns_cmd(vport, SLI_CTNS_RSNN_NN, 0, 0);
+
+		/* Since this effects multiple HBA and PORT attributes, we need
+		 * de-register and go thru the whole FDMI registration cycle.
+		 * DHBA -> DPRT -> RHBA -> RPA  (physical port)
+		 * DPRT -> RPRT (vports)
+		 */
+		if (vport->port_type == LPFC_PHYSICAL_PORT)
+			lpfc_fdmi_cmd(vport, ndlp, SLI_MGMT_DHBA, 0);
+		else
+			lpfc_fdmi_cmd(vport, ndlp, SLI_MGMT_DPRT, 0);
+
+		/* Since this code path registers all the port attributes
+		 * we can just return without further checking.
+		 */
+		return;
+	}
+
 	if (!(vport->fdmi_port_mask & LPFC_FDMI_PORT_ATTR_num_disc))
 		return;
 
+	/* Check if the number of mapped NPorts changed */
 	cnt = lpfc_find_map_node(vport);
 	if (cnt == vport->fdmi_num_disc)
 		return;
 
-	ndlp = lpfc_findnode_did(vport, FDMI_DID);
-	if (!ndlp || !NLP_CHK_NODE_ACT(ndlp))
-		return;
-
 	if (vport->port_type == LPFC_PHYSICAL_PORT) {
 		lpfc_fdmi_cmd(vport, ndlp, SLI_MGMT_RPA,
 			      LPFC_FDMI_PORT_ATTR_num_disc);
@@ -2551,8 +2579,8 @@ lpfc_fdmi_port_attr_host_name(struct lpfc_vport *vport,
 	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
 	memset(ae, 0, 256);
 
-	snprintf(ae->un.AttrString, sizeof(ae->un.AttrString), "%s",
-		 init_utsname()->nodename);
+	scnprintf(ae->un.AttrString, sizeof(ae->un.AttrString), "%s",
+		  vport->phba->os_host_name);
 
 	len = strnlen(ae->un.AttrString, sizeof(ae->un.AttrString));
 	len += (len & 3) ? (4 - (len & 3)) : 4;
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 46a65073ebc2..c958e550911f 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -8181,6 +8181,8 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	spin_lock_irq(shost->host_lock);
 	if (ndlp->nlp_flag & NLP_IN_DEV_LOSS) {
 		spin_unlock_irq(shost->host_lock);
+		if (newnode)
+			lpfc_nlp_put(ndlp);
 		goto dropit;
 	}
 	spin_unlock_irq(shost->host_lock);
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 3170f38e800c..120d2844f3cb 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -28,6 +28,7 @@
 #include <linux/kthread.h>
 #include <linux/interrupt.h>
 #include <linux/lockdep.h>
+#include <linux/utsname.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_device.h>
@@ -1131,7 +1132,6 @@ void
 lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 {
 	struct lpfc_vport *vport = pmb->vport;
-	uint8_t bbscn = 0;
 
 	if (pmb->u.mb.mbxStatus)
 		goto out;
@@ -1156,18 +1156,15 @@ lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	}
 
 	/* Start discovery by sending a FLOGI. port_state is identically
-	 * LPFC_FLOGI while waiting for FLOGI cmpl
+	 * LPFC_FLOGI while waiting for FLOGI cmpl. Check if sending
+	 * the FLOGI is being deferred till after MBX_READ_SPARAM completes.
 	 */
 	if (vport->port_state != LPFC_FLOGI) {
-		if (phba->bbcredit_support && phba->cfg_enable_bbcr) {
-			bbscn = bf_get(lpfc_bbscn_def,
-				       &phba->sli4_hba.bbscn_params);
-			vport->fc_sparam.cmn.bbRcvSizeMsb &= 0xf;
-			vport->fc_sparam.cmn.bbRcvSizeMsb |= (bbscn << 4);
-		}
-		lpfc_initial_flogi(vport);
-	} else if (vport->fc_flag & FC_PT2PT) {
-		lpfc_disc_start(vport);
+		if (!(phba->hba_flag & HBA_DEFER_FLOGI))
+			lpfc_initial_flogi(vport);
+	} else {
+		if (vport->fc_flag & FC_PT2PT)
+			lpfc_disc_start(vport);
 	}
 	return;
 
@@ -3093,6 +3090,14 @@ lpfc_mbx_cmpl_read_sparam(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	lpfc_mbuf_free(phba, mp->virt, mp->phys);
 	kfree(mp);
 	mempool_free(pmb, phba->mbox_mem_pool);
+
+	/* Check if sending the FLOGI is being deferred to after we get
+	 * up to date CSPs from MBX_READ_SPARAM.
+	 */
+	if (phba->hba_flag & HBA_DEFER_FLOGI) {
+		lpfc_initial_flogi(vport);
+		phba->hba_flag &= ~HBA_DEFER_FLOGI;
+	}
 	return;
 
 out:
@@ -3222,6 +3227,23 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la)
 	}
 
 	lpfc_linkup(phba);
+	sparam_mbox = NULL;
+
+	if (!(phba->hba_flag & HBA_FCOE_MODE)) {
+		cfglink_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+		if (!cfglink_mbox)
+			goto out;
+		vport->port_state = LPFC_LOCAL_CFG_LINK;
+		lpfc_config_link(phba, cfglink_mbox);
+		cfglink_mbox->vport = vport;
+		cfglink_mbox->mbox_cmpl = lpfc_mbx_cmpl_local_config_link;
+		rc = lpfc_sli_issue_mbox(phba, cfglink_mbox, MBX_NOWAIT);
+		if (rc == MBX_NOT_FINISHED) {
+			mempool_free(cfglink_mbox, phba->mbox_mem_pool);
+			goto out;
+		}
+	}
+
 	sparam_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 	if (!sparam_mbox)
 		goto out;
@@ -3242,20 +3264,7 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la)
 		goto out;
 	}
 
-	if (!(phba->hba_flag & HBA_FCOE_MODE)) {
-		cfglink_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
-		if (!cfglink_mbox)
-			goto out;
-		vport->port_state = LPFC_LOCAL_CFG_LINK;
-		lpfc_config_link(phba, cfglink_mbox);
-		cfglink_mbox->vport = vport;
-		cfglink_mbox->mbox_cmpl = lpfc_mbx_cmpl_local_config_link;
-		rc = lpfc_sli_issue_mbox(phba, cfglink_mbox, MBX_NOWAIT);
-		if (rc == MBX_NOT_FINISHED) {
-			mempool_free(cfglink_mbox, phba->mbox_mem_pool);
-			goto out;
-		}
-	} else {
+	if (phba->hba_flag & HBA_FCOE_MODE) {
 		vport->port_state = LPFC_VPORT_UNKNOWN;
 		/*
 		 * Add the driver's default FCF record at FCF index 0 now. This
@@ -3312,8 +3321,16 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la)
 		}
 		/* Reset FCF roundrobin bmask for new discovery */
 		lpfc_sli4_clear_fcf_rr_bmask(phba);
+	} else {
+		if (phba->bbcredit_support && phba->cfg_enable_bbcr &&
+		    !(phba->link_flag & LS_LOOPBACK_MODE))
+			phba->hba_flag |= HBA_DEFER_FLOGI;
 	}
 
+	/* Prepare for LINK up registrations */
+	memset(phba->os_host_name, 0, sizeof(phba->os_host_name));
+	scnprintf(phba->os_host_name, sizeof(phba->os_host_name), "%s",
+		  init_utsname()->nodename);
 	return;
 out:
 	lpfc_vport_set_state(vport, FC_VPORT_FAILED);
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 2fd8f15f9997..546cdc345e6d 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -39,6 +39,7 @@
 #include <linux/msi.h>
 #include <linux/irq.h>
 #include <linux/bitops.h>
+#include <linux/cpuhotplug.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_device.h>
@@ -71,9 +72,13 @@ char *_dump_buf_dif;
 unsigned long _dump_buf_dif_order;
 spinlock_t _dump_buf_lock;
 
+static enum cpuhp_state lpfc_cpuhp_state;
 /* Used when mapping IRQ vectors in a driver centric manner */
 uint32_t lpfc_present_cpu;
 
+static void __lpfc_cpuhp_remove(struct lpfc_hba *phba);
+static void lpfc_cpuhp_remove(struct lpfc_hba *phba);
+static void lpfc_cpuhp_add(struct lpfc_hba *phba);
 static void lpfc_get_hba_model_desc(struct lpfc_hba *, uint8_t *, uint8_t *);
 static int lpfc_post_rcv_buf(struct lpfc_hba *);
 static int lpfc_sli4_queue_verify(struct lpfc_hba *);
@@ -1376,7 +1381,7 @@ lpfc_hb_timeout_handler(struct lpfc_hba *phba)
 	if (vports != NULL)
 		for (i = 0; i <= phba->max_vports && vports[i] != NULL; i++) {
 			lpfc_rcv_seq_check_edtov(vports[i]);
-			lpfc_fdmi_num_disc_check(vports[i]);
+			lpfc_fdmi_change_check(vports[i]);
 		}
 	lpfc_destroy_vport_work_array(phba, vports);
 
@@ -3401,6 +3406,8 @@ lpfc_online(struct lpfc_hba *phba)
 	if (phba->cfg_xri_rebalancing)
 		lpfc_create_multixri_pools(phba);
 
+	lpfc_cpuhp_add(phba);
+
 	lpfc_unblock_mgmt_io(phba);
 	return 0;
 }
@@ -3559,6 +3566,7 @@ lpfc_offline(struct lpfc_hba *phba)
 			spin_unlock_irq(shost->host_lock);
 		}
 	lpfc_destroy_vport_work_array(phba, vports);
+	__lpfc_cpuhp_remove(phba);
 
 	if (phba->cfg_xri_rebalancing)
 		lpfc_destroy_multixri_pools(phba);
@@ -9172,6 +9180,8 @@ lpfc_sli4_queue_destroy(struct lpfc_hba *phba)
 	}
 	spin_unlock_irq(&phba->hbalock);
 
+	lpfc_sli4_cleanup_poll_list(phba);
+
 	/* Release HBA eqs */
 	if (phba->sli4_hba.hdwq)
 		lpfc_sli4_release_hdwq(phba);
@@ -10726,6 +10736,170 @@ lpfc_cpu_affinity_check(struct lpfc_hba *phba, int vectors)
 }
 
 /**
+ * lpfc_cpuhp_get_eq
+ *
+ * @phba:   pointer to lpfc hba data structure.
+ * @cpu:    cpu going offline
+ * @eqlist:
+ */
+static void
+lpfc_cpuhp_get_eq(struct lpfc_hba *phba, unsigned int cpu,
+		  struct list_head *eqlist)
+{
+	struct lpfc_vector_map_info *map;
+	const struct cpumask *maskp;
+	struct lpfc_queue *eq;
+	unsigned int i;
+	cpumask_t tmp;
+	u16 idx;
+
+	for (idx = 0; idx < phba->cfg_irq_chann; idx++) {
+		maskp = pci_irq_get_affinity(phba->pcidev, idx);
+		if (!maskp)
+			continue;
+		/*
+		 * if irq is not affinitized to the cpu going
+		 * then we don't need to poll the eq attached
+		 * to it.
+		 */
+		if (!cpumask_and(&tmp, maskp, cpumask_of(cpu)))
+			continue;
+		/* get the cpus that are online and are affini-
+		 * tized to this irq vector.  If the count is
+		 * more than 1 then cpuhp is not going to shut-
+		 * down this vector.  Since this cpu has not
+		 * gone offline yet, we need >1.
+		 */
+		cpumask_and(&tmp, maskp, cpu_online_mask);
+		if (cpumask_weight(&tmp) > 1)
+			continue;
+
+		/* Now that we have an irq to shutdown, get the eq
+		 * mapped to this irq.  Note: multiple hdwq's in
+		 * the software can share an eq, but eventually
+		 * only eq will be mapped to this vector
+		 */
+		for_each_possible_cpu(i) {
+			map = &phba->sli4_hba.cpu_map[i];
+			if (!(map->irq == pci_irq_vector(phba->pcidev, idx)))
+				continue;
+			eq = phba->sli4_hba.hdwq[map->hdwq].hba_eq;
+			list_add(&eq->_poll_list, eqlist);
+			/* 1 is good enough. others will be a copy of this */
+			break;
+		}
+	}
+}
+
+static void __lpfc_cpuhp_remove(struct lpfc_hba *phba)
+{
+	if (phba->sli_rev != LPFC_SLI_REV4)
+		return;
+
+	cpuhp_state_remove_instance_nocalls(lpfc_cpuhp_state,
+					    &phba->cpuhp);
+	/*
+	 * unregistering the instance doesn't stop the polling
+	 * timer. Wait for the poll timer to retire.
+	 */
+	synchronize_rcu();
+	del_timer_sync(&phba->cpuhp_poll_timer);
+}
+
+static void lpfc_cpuhp_remove(struct lpfc_hba *phba)
+{
+	if (phba->pport->fc_flag & FC_OFFLINE_MODE)
+		return;
+
+	__lpfc_cpuhp_remove(phba);
+}
+
+static void lpfc_cpuhp_add(struct lpfc_hba *phba)
+{
+	if (phba->sli_rev != LPFC_SLI_REV4)
+		return;
+
+	rcu_read_lock();
+
+	if (!list_empty(&phba->poll_list)) {
+		timer_setup(&phba->cpuhp_poll_timer, lpfc_sli4_poll_hbtimer, 0);
+		mod_timer(&phba->cpuhp_poll_timer,
+			  jiffies + msecs_to_jiffies(LPFC_POLL_HB));
+	}
+
+	rcu_read_unlock();
+
+	cpuhp_state_add_instance_nocalls(lpfc_cpuhp_state,
+					 &phba->cpuhp);
+}
+
+static int __lpfc_cpuhp_checks(struct lpfc_hba *phba, int *retval)
+{
+	if (phba->pport->load_flag & FC_UNLOADING) {
+		*retval = -EAGAIN;
+		return true;
+	}
+
+	if (phba->sli_rev != LPFC_SLI_REV4) {
+		*retval = 0;
+		return true;
+	}
+
+	/* proceed with the hotplug */
+	return false;
+}
+
+static int lpfc_cpu_offline(unsigned int cpu, struct hlist_node *node)
+{
+	struct lpfc_hba *phba = hlist_entry_safe(node, struct lpfc_hba, cpuhp);
+	struct lpfc_queue *eq, *next;
+	LIST_HEAD(eqlist);
+	int retval;
+
+	if (!phba) {
+		WARN_ONCE(!phba, "cpu: %u. phba:NULL", raw_smp_processor_id());
+		return 0;
+	}
+
+	if (__lpfc_cpuhp_checks(phba, &retval))
+		return retval;
+
+	lpfc_cpuhp_get_eq(phba, cpu, &eqlist);
+
+	/* start polling on these eq's */
+	list_for_each_entry_safe(eq, next, &eqlist, _poll_list) {
+		list_del_init(&eq->_poll_list);
+		lpfc_sli4_start_polling(eq);
+	}
+
+	return 0;
+}
+
+static int lpfc_cpu_online(unsigned int cpu, struct hlist_node *node)
+{
+	struct lpfc_hba *phba = hlist_entry_safe(node, struct lpfc_hba, cpuhp);
+	struct lpfc_queue *eq, *next;
+	unsigned int n;
+	int retval;
+
+	if (!phba) {
+		WARN_ONCE(!phba, "cpu: %u. phba:NULL", raw_smp_processor_id());
+		return 0;
+	}
+
+	if (__lpfc_cpuhp_checks(phba, &retval))
+		return retval;
+
+	list_for_each_entry_safe(eq, next, &phba->poll_list, _poll_list) {
+		n = lpfc_find_cpu_handle(phba, eq->hdwq, LPFC_FIND_BY_HDWQ);
+		if (n == cpu)
+			lpfc_sli4_stop_polling(eq);
+	}
+
+	return 0;
+}
+
+/**
  * lpfc_sli4_enable_msix - Enable MSI-X interrupt mode to SLI-4 device
  * @phba: pointer to lpfc hba data structure.
  *
@@ -11155,6 +11329,10 @@ lpfc_sli4_hba_unset(struct lpfc_hba *phba)
 	/* Wait for completion of device XRI exchange busy */
 	lpfc_sli4_xri_exchange_busy_wait(phba);
 
+	/* per-phba callback de-registration for hotplug event */
+	if (phba->pport)
+		lpfc_cpuhp_remove(phba);
+
 	/* Disable PCI subsystem interrupt */
 	lpfc_sli4_disable_intr(phba);
 
@@ -12380,6 +12558,9 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid)
 	/* Enable RAS FW log support */
 	lpfc_sli4_ras_setup(phba);
 
+	INIT_LIST_HEAD(&phba->poll_list);
+	cpuhp_state_add_instance_nocalls(lpfc_cpuhp_state, &phba->cpuhp);
+
 	return 0;
 
 out_free_sysfs_attr:
@@ -13206,11 +13387,24 @@ lpfc_init(void)
 	/* Initialize in case vector mapping is needed */
 	lpfc_present_cpu = num_present_cpus();
 
+	error = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
+					"lpfc/sli4:online",
+					lpfc_cpu_online, lpfc_cpu_offline);
+	if (error < 0)
+		goto cpuhp_failure;
+	lpfc_cpuhp_state = error;
+
 	error = pci_register_driver(&lpfc_driver);
-	if (error) {
-		fc_release_transport(lpfc_transport_template);
-		fc_release_transport(lpfc_vport_transport_template);
-	}
+	if (error)
+		goto unwind;
+
+	return error;
+
+unwind:
+	cpuhp_remove_multi_state(lpfc_cpuhp_state);
+cpuhp_failure:
+	fc_release_transport(lpfc_transport_template);
+	fc_release_transport(lpfc_vport_transport_template);
 
 	return error;
 }
@@ -13227,6 +13421,7 @@ lpfc_exit(void)
 {
 	misc_deregister(&lpfc_mgmt_dev);
 	pci_unregister_driver(&lpfc_driver);
+	cpuhp_remove_multi_state(lpfc_cpuhp_state);
 	fc_release_transport(lpfc_transport_template);
 	fc_release_transport(lpfc_vport_transport_template);
 	if (_dump_buf_data) {
diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index 9d99cb915390..532d44d3055e 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -342,13 +342,15 @@ lpfc_nvme_remoteport_delete(struct nvme_fc_remote_port *remoteport)
 	if (ndlp->upcall_flags & NLP_WAIT_FOR_UNREG) {
 		ndlp->nrport = NULL;
 		ndlp->upcall_flags &= ~NLP_WAIT_FOR_UNREG;
-	}
-	spin_unlock_irq(&vport->phba->hbalock);
+		spin_unlock_irq(&vport->phba->hbalock);
 
-	/* Remove original register reference. The host transport
-	 * won't reference this rport/remoteport any further.
-	 */
-	lpfc_nlp_put(ndlp);
+		/* Remove original register reference. The host transport
+		 * won't reference this rport/remoteport any further.
+		 */
+		lpfc_nlp_put(ndlp);
+	} else {
+		spin_unlock_irq(&vport->phba->hbalock);
+	}
 
  rport_err:
 	return;
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index d74bfd264495..8a93dfa79297 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -1723,7 +1723,7 @@ lpfc_nvmet_destroy_targetport(struct lpfc_hba *phba)
 		}
 		tgtp->tport_unreg_cmp = &tport_unreg_cmp;
 		nvmet_fc_unregister_targetport(phba->targetport);
-		if (!wait_for_completion_timeout(tgtp->tport_unreg_cmp,
+		if (!wait_for_completion_timeout(&tport_unreg_cmp,
 					msecs_to_jiffies(LPFC_NVMET_WAIT_TMO)))
 			lpfc_printf_log(phba, KERN_ERR, LOG_NVME,
 					"6179 Unreg targetport %p timeout "
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 265137270bb1..6e97d85c698d 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -485,7 +485,8 @@ lpfc_sli4_eq_flush(struct lpfc_hba *phba, struct lpfc_queue *eq)
 }
 
 static int
-lpfc_sli4_process_eq(struct lpfc_hba *phba, struct lpfc_queue *eq)
+lpfc_sli4_process_eq(struct lpfc_hba *phba, struct lpfc_queue *eq,
+		     uint8_t rearm)
 {
 	struct lpfc_eqe *eqe;
 	int count = 0, consumed = 0;
@@ -519,8 +520,8 @@ lpfc_sli4_process_eq(struct lpfc_hba *phba, struct lpfc_queue *eq)
 	eq->queue_claimed = 0;
 
 rearm_and_exit:
-	/* Always clear and re-arm the EQ */
-	phba->sli4_hba.sli4_write_eq_db(phba, eq, consumed, LPFC_QUEUE_REARM);
+	/* Always clear the EQ. */
+	phba->sli4_hba.sli4_write_eq_db(phba, eq, consumed, rearm);
 
 	return count;
 }
@@ -2463,6 +2464,8 @@ lpfc_sli_def_mbox_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	    !pmb->u.mb.mbxStatus) {
 		rpi = pmb->u.mb.un.varWords[0];
 		vpi = pmb->u.mb.un.varRegLogin.vpi;
+		if (phba->sli_rev == LPFC_SLI_REV4)
+			vpi -= phba->sli4_hba.max_cfg_param.vpi_base;
 		lpfc_unreg_login(phba, vpi, rpi, pmb);
 		pmb->vport = vport;
 		pmb->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
@@ -3991,6 +3994,11 @@ lpfc_sli_flush_fcp_rings(struct lpfc_hba *phba)
 	struct lpfc_iocbq *piocb, *next_iocb;
 
 	spin_lock_irq(&phba->hbalock);
+	if (phba->hba_flag & HBA_FCP_IOQ_FLUSH ||
+	    !phba->sli4_hba.hdwq) {
+		spin_unlock_irq(&phba->hbalock);
+		return;
+	}
 	/* Indicate the I/O queues are flushed */
 	phba->hba_flag |= HBA_FCP_IOQ_FLUSH;
 	spin_unlock_irq(&phba->hbalock);
@@ -7915,7 +7923,7 @@ lpfc_sli4_process_missed_mbox_completions(struct lpfc_hba *phba)
 
 	if (mbox_pending)
 		/* process and rearm the EQ */
-		lpfc_sli4_process_eq(phba, fpeq);
+		lpfc_sli4_process_eq(phba, fpeq, LPFC_QUEUE_REARM);
 	else
 		/* Always clear and re-arm the EQ */
 		sli4_hba->sli4_write_eq_db(phba, fpeq, 0, LPFC_QUEUE_REARM);
@@ -10068,10 +10076,13 @@ lpfc_sli_issue_iocb(struct lpfc_hba *phba, uint32_t ring_number,
 		    struct lpfc_iocbq *piocb, uint32_t flag)
 {
 	struct lpfc_sli_ring *pring;
+	struct lpfc_queue *eq;
 	unsigned long iflags;
 	int rc;
 
 	if (phba->sli_rev == LPFC_SLI_REV4) {
+		eq = phba->sli4_hba.hdwq[piocb->hba_wqidx].hba_eq;
+
 		pring = lpfc_sli4_calc_ring(phba, piocb);
 		if (unlikely(pring == NULL))
 			return IOCB_ERROR;
@@ -10079,6 +10090,8 @@ lpfc_sli_issue_iocb(struct lpfc_hba *phba, uint32_t ring_number,
 		spin_lock_irqsave(&pring->ring_lock, iflags);
 		rc = __lpfc_sli_issue_iocb(phba, ring_number, piocb, flag);
 		spin_unlock_irqrestore(&pring->ring_lock, iflags);
+
+		lpfc_sli4_poll_eq(eq, LPFC_POLL_FASTPATH);
 	} else {
 		/* For now, SLI2/3 will still use hbalock */
 		spin_lock_irqsave(&phba->hbalock, iflags);
@@ -14271,7 +14284,7 @@ lpfc_sli4_hba_intr_handler(int irq, void *dev_id)
 		lpfc_sli4_mod_hba_eq_delay(phba, fpeq, LPFC_MAX_AUTO_EQ_DELAY);
 
 	/* process and rearm the EQ */
-	ecount = lpfc_sli4_process_eq(phba, fpeq);
+	ecount = lpfc_sli4_process_eq(phba, fpeq, LPFC_QUEUE_REARM);
 
 	if (unlikely(ecount == 0)) {
 		fpeq->EQ_no_entry++;
@@ -14331,6 +14344,147 @@ lpfc_sli4_intr_handler(int irq, void *dev_id)
 	return (hba_handled == true) ? IRQ_HANDLED : IRQ_NONE;
 } /* lpfc_sli4_intr_handler */
 
+void lpfc_sli4_poll_hbtimer(struct timer_list *t)
+{
+	struct lpfc_hba *phba = from_timer(phba, t, cpuhp_poll_timer);
+	struct lpfc_queue *eq;
+	int i = 0;
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(eq, &phba->poll_list, _poll_list)
+		i += lpfc_sli4_poll_eq(eq, LPFC_POLL_SLOWPATH);
+	if (!list_empty(&phba->poll_list))
+		mod_timer(&phba->cpuhp_poll_timer,
+			  jiffies + msecs_to_jiffies(LPFC_POLL_HB));
+
+	rcu_read_unlock();
+}
+
+inline int lpfc_sli4_poll_eq(struct lpfc_queue *eq, uint8_t path)
+{
+	struct lpfc_hba *phba = eq->phba;
+	int i = 0;
+
+	/*
+	 * Unlocking an irq is one of the entry point to check
+	 * for re-schedule, but we are good for io submission
+	 * path as midlayer does a get_cpu to glue us in. Flush
+	 * out the invalidate queue so we can see the updated
+	 * value for flag.
+	 */
+	smp_rmb();
+
+	if (READ_ONCE(eq->mode) == LPFC_EQ_POLL)
+		/* We will not likely get the completion for the caller
+		 * during this iteration but i guess that's fine.
+		 * Future io's coming on this eq should be able to
+		 * pick it up.  As for the case of single io's, they
+		 * will be handled through a sched from polling timer
+		 * function which is currently triggered every 1msec.
+		 */
+		i = lpfc_sli4_process_eq(phba, eq, LPFC_QUEUE_NOARM);
+
+	return i;
+}
+
+static inline void lpfc_sli4_add_to_poll_list(struct lpfc_queue *eq)
+{
+	struct lpfc_hba *phba = eq->phba;
+
+	if (list_empty(&phba->poll_list)) {
+		timer_setup(&phba->cpuhp_poll_timer, lpfc_sli4_poll_hbtimer, 0);
+		/* kickstart slowpath processing for this eq */
+		mod_timer(&phba->cpuhp_poll_timer,
+			  jiffies + msecs_to_jiffies(LPFC_POLL_HB));
+	}
+
+	list_add_rcu(&eq->_poll_list, &phba->poll_list);
+	synchronize_rcu();
+}
+
+static inline void lpfc_sli4_remove_from_poll_list(struct lpfc_queue *eq)
+{
+	struct lpfc_hba *phba = eq->phba;
+
+	/* Disable slowpath processing for this eq.  Kick start the eq
+	 * by RE-ARMING the eq's ASAP
+	 */
+	list_del_rcu(&eq->_poll_list);
+	synchronize_rcu();
+
+	if (list_empty(&phba->poll_list))
+		del_timer_sync(&phba->cpuhp_poll_timer);
+}
+
+void lpfc_sli4_cleanup_poll_list(struct lpfc_hba *phba)
+{
+	struct lpfc_queue *eq, *next;
+
+	list_for_each_entry_safe(eq, next, &phba->poll_list, _poll_list)
+		list_del(&eq->_poll_list);
+
+	INIT_LIST_HEAD(&phba->poll_list);
+	synchronize_rcu();
+}
+
+static inline void
+__lpfc_sli4_switch_eqmode(struct lpfc_queue *eq, uint8_t mode)
+{
+	if (mode == eq->mode)
+		return;
+	/*
+	 * currently this function is only called during a hotplug
+	 * event and the cpu on which this function is executing
+	 * is going offline.  By now the hotplug has instructed
+	 * the scheduler to remove this cpu from cpu active mask.
+	 * So we don't need to work about being put aside by the
+	 * scheduler for a high priority process.  Yes, the inte-
+	 * rrupts could come but they are known to retire ASAP.
+	 */
+
+	/* Disable polling in the fastpath */
+	WRITE_ONCE(eq->mode, mode);
+	/* flush out the store buffer */
+	smp_wmb();
+
+	/*
+	 * Add this eq to the polling list and start polling. For
+	 * a grace period both interrupt handler and poller will
+	 * try to process the eq _but_ that's fine.  We have a
+	 * synchronization mechanism in place (queue_claimed) to
+	 * deal with it.  This is just a draining phase for int-
+	 * errupt handler (not eq's) as we have guranteed through
+	 * barrier that all the CPUs have seen the new CQ_POLLED
+	 * state. which will effectively disable the REARMING of
+	 * the EQ.  The whole idea is eq's die off eventually as
+	 * we are not rearming EQ's anymore.
+	 */
+	mode ? lpfc_sli4_add_to_poll_list(eq) :
+	       lpfc_sli4_remove_from_poll_list(eq);
+}
+
+void lpfc_sli4_start_polling(struct lpfc_queue *eq)
+{
+	__lpfc_sli4_switch_eqmode(eq, LPFC_EQ_POLL);
+}
+
+void lpfc_sli4_stop_polling(struct lpfc_queue *eq)
+{
+	struct lpfc_hba *phba = eq->phba;
+
+	__lpfc_sli4_switch_eqmode(eq, LPFC_EQ_INTERRUPT);
+
+	/* Kick start for the pending io's in h/w.
+	 * Once we switch back to interrupt processing on a eq
+	 * the io path completion will only arm eq's when it
+	 * receives a completion.  But since eq's are in disa-
+	 * rmed state it doesn't receive a completion.  This
+	 * creates a deadlock scenaro.
+	 */
+	phba->sli4_hba.sli4_write_eq_db(phba, eq, 0, LPFC_QUEUE_REARM);
+}
+
 /**
  * lpfc_sli4_queue_free - free a queue structure and associated memory
  * @queue: The queue structure to free.
@@ -14405,6 +14559,7 @@ lpfc_sli4_queue_alloc(struct lpfc_hba *phba, uint32_t page_size,
 		return NULL;
 
 	INIT_LIST_HEAD(&queue->list);
+	INIT_LIST_HEAD(&queue->_poll_list);
 	INIT_LIST_HEAD(&queue->wq_list);
 	INIT_LIST_HEAD(&queue->wqfull_list);
 	INIT_LIST_HEAD(&queue->page_list);
@@ -19707,6 +19862,8 @@ lpfc_sli4_issue_wqe(struct lpfc_hba *phba, struct lpfc_sli4_hdw_queue *qp,
 
 		lpfc_sli_ringtxcmpl_put(phba, pring, pwqe);
 		spin_unlock_irqrestore(&pring->ring_lock, iflags);
+
+		lpfc_sli4_poll_eq(qp->hba_eq, LPFC_POLL_FASTPATH);
 		return 0;
 	}
 
@@ -19727,6 +19884,8 @@ lpfc_sli4_issue_wqe(struct lpfc_hba *phba, struct lpfc_sli4_hdw_queue *qp,
 		}
 		lpfc_sli_ringtxcmpl_put(phba, pring, pwqe);
 		spin_unlock_irqrestore(&pring->ring_lock, iflags);
+
+		lpfc_sli4_poll_eq(qp->hba_eq, LPFC_POLL_FASTPATH);
 		return 0;
 	}
 
@@ -19755,6 +19914,8 @@ lpfc_sli4_issue_wqe(struct lpfc_hba *phba, struct lpfc_sli4_hdw_queue *qp,
 		}
 		lpfc_sli_ringtxcmpl_put(phba, pring, pwqe);
 		spin_unlock_irqrestore(&pring->ring_lock, iflags);
+
+		lpfc_sli4_poll_eq(qp->hba_eq, LPFC_POLL_FASTPATH);
 		return 0;
 	}
 	return WQE_ERROR;
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index 986594ec40e2..9c3100246375 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -137,6 +137,23 @@ struct lpfc_rqb {
 struct lpfc_queue {
 	struct list_head list;
 	struct list_head wq_list;
+
+	/*
+	 * If interrupts are in effect on _all_ the eq's the footprint
+	 * of polling code is zero (except mode). This memory is chec-
+	 * ked for every io to see if the io needs to be polled and
+	 * while completion to check if the eq's needs to be rearmed.
+	 * Keep in same cacheline as the queue ptr to avoid cpu fetch
+	 * stalls. Using 1B memory will leave us with 7B hole. Fill
+	 * it with other frequently used members.
+	 */
+	uint16_t last_cpu;	/* most recent cpu */
+	uint16_t hdwq;
+	uint8_t	 qe_valid;
+	uint8_t  mode;	/* interrupt or polling */
+#define LPFC_EQ_INTERRUPT	0
+#define LPFC_EQ_POLL		1
+
 	struct list_head wqfull_list;
 	enum lpfc_sli4_queue_type type;
 	enum lpfc_sli4_queue_subtype subtype;
@@ -241,10 +258,8 @@ struct lpfc_queue {
 	struct delayed_work	sched_spwork;
 
 	uint64_t isr_timestamp;
-	uint16_t hdwq;
-	uint16_t last_cpu;	/* most recent cpu */
-	uint8_t	qe_valid;
 	struct lpfc_queue *assoc_qp;
+	struct list_head _poll_list;
 	void **q_pgs;	/* array to index entries per page */
 };
 
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 5f30016e9b64..f63f9bb6e7d3 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -4197,7 +4197,8 @@ dcmd_timeout_ocr_possible(struct megasas_instance *instance) {
 	if (instance->adapter_type == MFI_SERIES)
 		return KILL_ADAPTER;
 	else if (instance->unload ||
-			test_bit(MEGASAS_FUSION_IN_RESET, &instance->reset_flags))
+			test_bit(MEGASAS_FUSION_OCR_NOT_POSSIBLE,
+				 &instance->reset_flags))
 		return IGNORE_TIMEOUT;
 	else
 		return INITIATE_OCR;
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index 4dfa0685a86c..74df9edc6cda 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -523,7 +523,8 @@ retry_alloc:
 
 	fusion->io_request_frames =
 			dma_pool_alloc(fusion->io_request_frames_pool,
-				GFP_KERNEL, &fusion->io_request_frames_phys);
+				GFP_KERNEL | __GFP_NOWARN,
+				&fusion->io_request_frames_phys);
 	if (!fusion->io_request_frames) {
 		if (instance->max_fw_cmds >= (MEGASAS_REDUCE_QD_COUNT * 2)) {
 			instance->max_fw_cmds -= MEGASAS_REDUCE_QD_COUNT;
@@ -561,7 +562,7 @@ retry_alloc:
 
 		fusion->io_request_frames =
 			dma_pool_alloc(fusion->io_request_frames_pool,
-				       GFP_KERNEL,
+				       GFP_KERNEL | __GFP_NOWARN,
 				       &fusion->io_request_frames_phys);
 
 		if (!fusion->io_request_frames) {
@@ -3996,6 +3997,7 @@ void megasas_refire_mgmt_cmd(struct megasas_instance *instance)
 	struct fusion_context *fusion;
 	struct megasas_cmd *cmd_mfi;
 	union MEGASAS_REQUEST_DESCRIPTOR_UNION *req_desc;
+	struct MPI2_RAID_SCSI_IO_REQUEST *scsi_io_req;
 	u16 smid;
 	bool refire_cmd = 0;
 	u8 result;
@@ -4046,6 +4048,11 @@ void megasas_refire_mgmt_cmd(struct megasas_instance *instance)
 			break;
 		}
 
+		scsi_io_req = (struct MPI2_RAID_SCSI_IO_REQUEST *)
+				cmd_fusion->io_request;
+		if (scsi_io_req->Function == MPI2_FUNCTION_SCSI_TASK_MGMT)
+			result = RETURN_CMD;
+
 		switch (result) {
 		case REFIRE_CMD:
 			megasas_fire_cmd_fusion(instance, req_desc);
@@ -4243,7 +4250,6 @@ megasas_issue_tm(struct megasas_instance *instance, u16 device_handle,
 	if (!timeleft) {
 		dev_err(&instance->pdev->dev,
 			"task mgmt type 0x%x timed out\n", type);
-		cmd_mfi->flags |= DRV_DCMD_SKIP_REFIRE;
 		mutex_unlock(&instance->reset_mutex);
 		rc = megasas_reset_fusion(instance->host, MFI_IO_TIMEOUT_OCR);
 		mutex_lock(&instance->reset_mutex);
@@ -4608,6 +4614,7 @@ int megasas_reset_fusion(struct Scsi_Host *shost, int reason)
 	if (instance->requestorId && !instance->skip_heartbeat_timer_del)
 		del_timer_sync(&instance->sriov_heartbeat_timer);
 	set_bit(MEGASAS_FUSION_IN_RESET, &instance->reset_flags);
+	set_bit(MEGASAS_FUSION_OCR_NOT_POSSIBLE, &instance->reset_flags);
 	atomic_set(&instance->adprecovery, MEGASAS_ADPRESET_SM_POLLING);
 	instance->instancet->disable_intr(instance);
 	megasas_sync_irqs((unsigned long)instance);
@@ -4803,7 +4810,7 @@ fail_kill_adapter:
 		atomic_set(&instance->adprecovery, MEGASAS_HBA_OPERATIONAL);
 	}
 out:
-	clear_bit(MEGASAS_FUSION_IN_RESET, &instance->reset_flags);
+	clear_bit(MEGASAS_FUSION_OCR_NOT_POSSIBLE, &instance->reset_flags);
 	mutex_unlock(&instance->reset_mutex);
 	return retval;
 }
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.h b/drivers/scsi/megaraid/megaraid_sas_fusion.h
index 7fa73eaca1a8..c2fb21fc099c 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.h
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.h
@@ -89,6 +89,7 @@ enum MR_RAID_FLAGS_IO_SUB_TYPE {
 #define MEGASAS_FP_CMD_LEN	16
 #define MEGASAS_FUSION_IN_RESET 0
 #define THRESHOLD_REPLY_COUNT 50
+#define MEGASAS_FUSION_OCR_NOT_POSSIBLE 1
 #define RAID_1_PEER_CMDS 2
 #define JBOD_MAPS_COUNT	2
 #define MEGASAS_REDUCE_QD_COUNT 64
diff --git a/drivers/scsi/mesh.c b/drivers/scsi/mesh.c
index 74fb50644678..4dd50db90677 100644
--- a/drivers/scsi/mesh.c
+++ b/drivers/scsi/mesh.c
@@ -1045,6 +1045,8 @@ static void handle_error(struct mesh_state *ms)
 		while ((in_8(&mr->bus_status1) & BS1_RST) != 0)
 			udelay(1);
 		printk("done\n");
+		if (ms->dma_started)
+			halt_dma(ms);
 		handle_reset(ms);
 		/* request_q is empty, no point in mesh_start() */
 		return;
@@ -1357,7 +1359,8 @@ static void halt_dma(struct mesh_state *ms)
 		       ms->conn_tgt, ms->data_ptr, scsi_bufflen(cmd),
 		       ms->tgts[ms->conn_tgt].data_goes_out);
 	}
-	scsi_dma_unmap(cmd);
+	if (cmd)
+		scsi_dma_unmap(cmd);
 	ms->dma_started = 0;
 }
 
@@ -1712,6 +1715,9 @@ static int mesh_host_reset(struct scsi_cmnd *cmd)
 
 	spin_lock_irqsave(ms->host->host_lock, flags);
 
+	if (ms->dma_started)
+		halt_dma(ms);
+
 	/* Reset the controller & dbdma channel */
 	out_le32(&md->control, (RUN|PAUSE|FLUSH|WAKE) << 16);	/* stop dma */
 	out_8(&mr->exception, 0xff);	/* clear all exception bits */
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index f2d61d023bcb..eeb6d58ae867 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -4380,7 +4380,9 @@ _base_release_memory_pools(struct MPT3SAS_ADAPTER *ioc)
 	}
 
 	kfree(ioc->hpr_lookup);
+	ioc->hpr_lookup = NULL;
 	kfree(ioc->internal_lookup);
+	ioc->internal_lookup = NULL;
 	if (ioc->chain_lookup) {
 		for (i = 0; i < ioc->scsiio_depth; i++) {
 			for (j = ioc->chains_per_prp_buffer;
@@ -4836,7 +4838,6 @@ _base_allocate_memory_pools(struct MPT3SAS_ADAPTER *ioc)
 					&ct->chain_buffer_dma);
 			if (!ct->chain_buffer) {
 				ioc_err(ioc, "chain_lookup: pci_pool_alloc failed\n");
-				_base_release_memory_pools(ioc);
 				goto out;
 			}
 		}
diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
index c20b4b70a3c8..10f8e1791a5a 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
@@ -2893,19 +2893,18 @@ _ctl_BRM_status_show(struct device *cdev, struct device_attribute *attr,
 	if (!ioc->is_warpdrive) {
 		ioc_err(ioc, "%s: BRM attribute is only for warpdrive\n",
 			__func__);
-		goto out;
+		return 0;
 	}
 	/* pci_access_mutex lock acquired by sysfs show path */
 	mutex_lock(&ioc->pci_access_mutex);
-	if (ioc->pci_error_recovery || ioc->remove_host) {
-		mutex_unlock(&ioc->pci_access_mutex);
-		return 0;
-	}
+	if (ioc->pci_error_recovery || ioc->remove_host)
+		goto out;
 
 	/* allocate upto GPIOVal 36 entries */
 	sz = offsetof(Mpi2IOUnitPage3_t, GPIOVal) + (sizeof(u16) * 36);
 	io_unit_pg3 = kzalloc(sz, GFP_KERNEL);
 	if (!io_unit_pg3) {
+		rc = -ENOMEM;
 		ioc_err(ioc, "%s: failed allocating memory for iounit_pg3: (%d) bytes\n",
 			__func__, sz);
 		goto out;
@@ -2915,6 +2914,7 @@ _ctl_BRM_status_show(struct device *cdev, struct device_attribute *attr,
 	    0) {
 		ioc_err(ioc, "%s: failed reading iounit_pg3\n",
 			__func__);
+		rc = -EINVAL;
 		goto out;
 	}
 
@@ -2922,12 +2922,14 @@ _ctl_BRM_status_show(struct device *cdev, struct device_attribute *attr,
 	if (ioc_status != MPI2_IOCSTATUS_SUCCESS) {
 		ioc_err(ioc, "%s: iounit_pg3 failed with ioc_status(0x%04x)\n",
 			__func__, ioc_status);
+		rc = -EINVAL;
 		goto out;
 	}
 
 	if (io_unit_pg3->GPIOCount < 25) {
 		ioc_err(ioc, "%s: iounit_pg3->GPIOCount less than 25 entries, detected (%d) entries\n",
 			__func__, io_unit_pg3->GPIOCount);
+		rc = -EINVAL;
 		goto out;
 	}
 
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 1ccfbc7eebe0..4c5a8e460b50 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -9673,8 +9673,8 @@ static void scsih_remove(struct pci_dev *pdev)
 
 	ioc->remove_host = 1;
 
-	mpt3sas_wait_for_commands_to_complete(ioc);
-	_scsih_flush_running_cmds(ioc);
+	if (!pci_device_is_present(pdev))
+		_scsih_flush_running_cmds(ioc);
 
 	_scsih_fw_event_cleanup_queue(ioc);
 
@@ -9750,8 +9750,8 @@ scsih_shutdown(struct pci_dev *pdev)
 
 	ioc->remove_host = 1;
 
-	mpt3sas_wait_for_commands_to_complete(ioc);
-	_scsih_flush_running_cmds(ioc);
+	if (!pci_device_is_present(pdev))
+		_scsih_flush_running_cmds(ioc);
 
 	_scsih_fw_event_cleanup_queue(ioc);
 
diff --git a/drivers/scsi/qedf/qedf.h b/drivers/scsi/qedf/qedf.h
index 5a021217bfc9..1fe4aa3befd5 100644
--- a/drivers/scsi/qedf/qedf.h
+++ b/drivers/scsi/qedf/qedf.h
@@ -354,6 +354,7 @@ struct qedf_ctx {
 #define QEDF_GRCDUMP_CAPTURE		4
 #define QEDF_IN_RECOVERY		5
 #define QEDF_DBG_STOP_IO		6
+#define QEDF_PROBING			8
 	unsigned long flags; /* Miscellaneous state flags */
 	int fipvlan_retries;
 	u8 num_queues;
diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c
index 6ef0f741bf89..7b24c21edc37 100644
--- a/drivers/scsi/qedf/qedf_main.c
+++ b/drivers/scsi/qedf/qedf_main.c
@@ -3101,7 +3101,7 @@ static int __qedf_probe(struct pci_dev *pdev, int mode)
 {
 	int rc = -EINVAL;
 	struct fc_lport *lport;
-	struct qedf_ctx *qedf;
+	struct qedf_ctx *qedf = NULL;
 	struct Scsi_Host *host;
 	bool is_vf = false;
 	struct qed_ll2_params params;
@@ -3131,6 +3131,7 @@ static int __qedf_probe(struct pci_dev *pdev, int mode)
 
 		/* Initialize qedf_ctx */
 		qedf = lport_priv(lport);
+		set_bit(QEDF_PROBING, &qedf->flags);
 		qedf->lport = lport;
 		qedf->ctlr.lp = lport;
 		qedf->pdev = pdev;
@@ -3154,9 +3155,12 @@ static int __qedf_probe(struct pci_dev *pdev, int mode)
 	} else {
 		/* Init pointers during recovery */
 		qedf = pci_get_drvdata(pdev);
+		set_bit(QEDF_PROBING, &qedf->flags);
 		lport = qedf->lport;
 	}
 
+	QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_DISC, "Probe started.\n");
+
 	host = lport->host;
 
 	/* Allocate mempool for qedf_io_work structs */
@@ -3453,6 +3457,10 @@ static int __qedf_probe(struct pci_dev *pdev, int mode)
 	else
 		fc_fabric_login(lport);
 
+	QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_DISC, "Probe done.\n");
+
+	clear_bit(QEDF_PROBING, &qedf->flags);
+
 	/* All good */
 	return 0;
 
@@ -3478,6 +3486,11 @@ err2:
 err1:
 	scsi_host_put(lport->host);
 err0:
+	if (qedf) {
+		QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_DISC, "Probe done.\n");
+
+		clear_bit(QEDF_PROBING, &qedf->flags);
+	}
 	return rc;
 }
 
@@ -3627,11 +3640,25 @@ void qedf_get_protocol_tlv_data(void *dev, void *data)
 {
 	struct qedf_ctx *qedf = dev;
 	struct qed_mfw_tlv_fcoe *fcoe = data;
-	struct fc_lport *lport = qedf->lport;
-	struct Scsi_Host *host = lport->host;
-	struct fc_host_attrs *fc_host = shost_to_fc_host(host);
+	struct fc_lport *lport;
+	struct Scsi_Host *host;
+	struct fc_host_attrs *fc_host;
 	struct fc_host_statistics *hst;
 
+	if (!qedf) {
+		QEDF_ERR(NULL, "qedf is null.\n");
+		return;
+	}
+
+	if (test_bit(QEDF_PROBING, &qedf->flags)) {
+		QEDF_ERR(&qedf->dbg_ctx, "Function is still probing.\n");
+		return;
+	}
+
+	lport = qedf->lport;
+	host = lport->host;
+	fc_host = shost_to_fc_host(host);
+
 	/* Force a refresh of the fc_host stats including offload stats */
 	hst = qedf_fc_get_host_stats(host);
 
diff --git a/drivers/scsi/qedi/qedi_iscsi.c b/drivers/scsi/qedi/qedi_iscsi.c
index 8829880a54c3..0f57c8073406 100644
--- a/drivers/scsi/qedi/qedi_iscsi.c
+++ b/drivers/scsi/qedi/qedi_iscsi.c
@@ -997,7 +997,8 @@ static void qedi_ep_disconnect(struct iscsi_endpoint *ep)
 	if (qedi_ep->state == EP_STATE_OFLDCONN_START)
 		goto ep_exit_recover;
 
-	flush_work(&qedi_ep->offload_work);
+	if (qedi_ep->state != EP_STATE_OFLDCONN_NONE)
+		flush_work(&qedi_ep->offload_work);
 
 	if (qedi_ep->conn) {
 		qedi_conn = qedi_ep->conn;
@@ -1214,6 +1215,10 @@ static int qedi_set_path(struct Scsi_Host *shost, struct iscsi_path *path_data)
 	}
 
 	iscsi_cid = (u32)path_data->handle;
+	if (iscsi_cid >= qedi->max_active_conns) {
+		ret = -EINVAL;
+		goto set_path_exit;
+	}
 	qedi_ep = qedi->ep_tbl[iscsi_cid];
 	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
 		  "iscsi_cid=0x%x, qedi_ep=%p\n", iscsi_cid, qedi_ep);
diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index 96aa024ef621..6954520f6ac6 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -1775,9 +1775,6 @@ qla2x00_port_speed_show(struct device *dev, struct device_attribute *attr,
 		return -EINVAL;
 	}
 
-	ql_log(ql_log_info, vha, 0x70d6,
-	    "port speed:%d\n", ha->link_data_rate);
-
 	return scnprintf(buf, PAGE_SIZE, "%s\n", spd[ha->link_data_rate]);
 }
 
@@ -2924,11 +2921,11 @@ qla24xx_vport_delete(struct fc_vport *fc_vport)
 	    test_bit(FCPORT_UPDATE_NEEDED, &vha->dpc_flags))
 		msleep(1000);
 
-	qla_nvme_delete(vha);
 
 	qla24xx_disable_vp(vha);
 	qla2x00_wait_for_sess_deletion(vha);
 
+	qla_nvme_delete(vha);
 	vha->flags.delete_progress = 1;
 
 	qlt_remove_target(ha, vha);
diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c
index 9e80646722e2..d31c8657c894 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.c
+++ b/drivers/scsi/qla2xxx/qla_dbg.c
@@ -2519,12 +2519,6 @@ qla83xx_fw_dump_failed:
 /*                         Driver Debug Functions.                          */
 /****************************************************************************/
 
-static inline int
-ql_mask_match(uint level)
-{
-	return (level & ql2xextended_error_logging) == level;
-}
-
 /*
  * This function is for formatting and logging debug information.
  * It is to be used when vha is available. It formats the message
diff --git a/drivers/scsi/qla2xxx/qla_dbg.h b/drivers/scsi/qla2xxx/qla_dbg.h
index bb01b680ce9f..433e95502808 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.h
+++ b/drivers/scsi/qla2xxx/qla_dbg.h
@@ -374,3 +374,9 @@ extern int qla24xx_dump_ram(struct qla_hw_data *, uint32_t, uint32_t *,
 extern void qla24xx_pause_risc(struct device_reg_24xx __iomem *,
 	struct qla_hw_data *);
 extern int qla24xx_soft_reset(struct qla_hw_data *);
+
+static inline int
+ql_mask_match(uint level)
+{
+	return (level & ql2xextended_error_logging) == level;
+}
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 1a4095c56eee..b3dd0e980156 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -2335,6 +2335,7 @@ typedef struct fc_port {
 	unsigned int query:1;
 	unsigned int id_changed:1;
 	unsigned int scan_needed:1;
+	unsigned int explicit_logout:1;
 
 	struct work_struct nvme_del_work;
 	struct completion nvme_del_done;
diff --git a/drivers/scsi/qla2xxx/qla_dsd.h b/drivers/scsi/qla2xxx/qla_dsd.h
index 7479924ba422..20788054b91b 100644
--- a/drivers/scsi/qla2xxx/qla_dsd.h
+++ b/drivers/scsi/qla2xxx/qla_dsd.h
@@ -1,6 +1,8 @@
 #ifndef _QLA_DSD_H_
 #define _QLA_DSD_H_
 
+#include <asm/unaligned.h>
+
 /* 32-bit data segment descriptor (8 bytes) */
 struct dsd32 {
 	__le32 address;
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 9091d37ffd95..670259fe08bb 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -3096,103 +3096,113 @@ qla24xx_chip_diag(scsi_qla_host_t *vha)
 }
 
 static void
-qla2x00_alloc_offload_mem(scsi_qla_host_t *vha)
+qla2x00_init_fce_trace(scsi_qla_host_t *vha)
 {
 	int rval;
 	dma_addr_t tc_dma;
 	void *tc;
 	struct qla_hw_data *ha = vha->hw;
 
-	if (ha->eft) {
+	if (!IS_FWI2_CAPABLE(ha))
+		return;
+
+	if (!IS_QLA25XX(ha) && !IS_QLA81XX(ha) && !IS_QLA83XX(ha) &&
+	    !IS_QLA27XX(ha) && !IS_QLA28XX(ha))
+		return;
+
+	if (ha->fce) {
 		ql_dbg(ql_dbg_init, vha, 0x00bd,
-		    "%s: Offload Mem is already allocated.\n",
-		    __func__);
+		       "%s: FCE Mem is already allocated.\n",
+		       __func__);
 		return;
 	}
 
-	if (IS_FWI2_CAPABLE(ha)) {
-		/* Allocate memory for Fibre Channel Event Buffer. */
-		if (!IS_QLA25XX(ha) && !IS_QLA81XX(ha) && !IS_QLA83XX(ha) &&
-		    !IS_QLA27XX(ha) && !IS_QLA28XX(ha))
-			goto try_eft;
+	/* Allocate memory for Fibre Channel Event Buffer. */
+	tc = dma_alloc_coherent(&ha->pdev->dev, FCE_SIZE, &tc_dma,
+				GFP_KERNEL);
+	if (!tc) {
+		ql_log(ql_log_warn, vha, 0x00be,
+		       "Unable to allocate (%d KB) for FCE.\n",
+		       FCE_SIZE / 1024);
+		return;
+	}
 
-		if (ha->fce)
-			dma_free_coherent(&ha->pdev->dev,
-			    FCE_SIZE, ha->fce, ha->fce_dma);
+	rval = qla2x00_enable_fce_trace(vha, tc_dma, FCE_NUM_BUFFERS,
+					ha->fce_mb, &ha->fce_bufs);
+	if (rval) {
+		ql_log(ql_log_warn, vha, 0x00bf,
+		       "Unable to initialize FCE (%d).\n", rval);
+		dma_free_coherent(&ha->pdev->dev, FCE_SIZE, tc, tc_dma);
+		return;
+	}
 
-		/* Allocate memory for Fibre Channel Event Buffer. */
-		tc = dma_alloc_coherent(&ha->pdev->dev, FCE_SIZE, &tc_dma,
-					GFP_KERNEL);
-		if (!tc) {
-			ql_log(ql_log_warn, vha, 0x00be,
-			    "Unable to allocate (%d KB) for FCE.\n",
-			    FCE_SIZE / 1024);
-			goto try_eft;
-		}
-
-		rval = qla2x00_enable_fce_trace(vha, tc_dma, FCE_NUM_BUFFERS,
-		    ha->fce_mb, &ha->fce_bufs);
-		if (rval) {
-			ql_log(ql_log_warn, vha, 0x00bf,
-			    "Unable to initialize FCE (%d).\n", rval);
-			dma_free_coherent(&ha->pdev->dev, FCE_SIZE, tc,
-			    tc_dma);
-			ha->flags.fce_enabled = 0;
-			goto try_eft;
-		}
-		ql_dbg(ql_dbg_init, vha, 0x00c0,
-		    "Allocate (%d KB) for FCE...\n", FCE_SIZE / 1024);
-
-		ha->flags.fce_enabled = 1;
-		ha->fce_dma = tc_dma;
-		ha->fce = tc;
-
-try_eft:
-		if (ha->eft)
-			dma_free_coherent(&ha->pdev->dev,
-			    EFT_SIZE, ha->eft, ha->eft_dma);
+	ql_dbg(ql_dbg_init, vha, 0x00c0,
+	       "Allocated (%d KB) for FCE...\n", FCE_SIZE / 1024);
 
-		/* Allocate memory for Extended Trace Buffer. */
-		tc = dma_alloc_coherent(&ha->pdev->dev, EFT_SIZE, &tc_dma,
-					GFP_KERNEL);
-		if (!tc) {
-			ql_log(ql_log_warn, vha, 0x00c1,
-			    "Unable to allocate (%d KB) for EFT.\n",
-			    EFT_SIZE / 1024);
-			goto eft_err;
-		}
+	ha->flags.fce_enabled = 1;
+	ha->fce_dma = tc_dma;
+	ha->fce = tc;
+}
 
-		rval = qla2x00_enable_eft_trace(vha, tc_dma, EFT_NUM_BUFFERS);
-		if (rval) {
-			ql_log(ql_log_warn, vha, 0x00c2,
-			    "Unable to initialize EFT (%d).\n", rval);
-			dma_free_coherent(&ha->pdev->dev, EFT_SIZE, tc,
-			    tc_dma);
-			goto eft_err;
-		}
-		ql_dbg(ql_dbg_init, vha, 0x00c3,
-		    "Allocated (%d KB) EFT ...\n", EFT_SIZE / 1024);
+static void
+qla2x00_init_eft_trace(scsi_qla_host_t *vha)
+{
+	int rval;
+	dma_addr_t tc_dma;
+	void *tc;
+	struct qla_hw_data *ha = vha->hw;
+
+	if (!IS_FWI2_CAPABLE(ha))
+		return;
 
-		ha->eft_dma = tc_dma;
-		ha->eft = tc;
+	if (ha->eft) {
+		ql_dbg(ql_dbg_init, vha, 0x00bd,
+		    "%s: EFT Mem is already allocated.\n",
+		    __func__);
+		return;
 	}
 
-eft_err:
-	return;
+	/* Allocate memory for Extended Trace Buffer. */
+	tc = dma_alloc_coherent(&ha->pdev->dev, EFT_SIZE, &tc_dma,
+				GFP_KERNEL);
+	if (!tc) {
+		ql_log(ql_log_warn, vha, 0x00c1,
+		       "Unable to allocate (%d KB) for EFT.\n",
+		       EFT_SIZE / 1024);
+		return;
+	}
+
+	rval = qla2x00_enable_eft_trace(vha, tc_dma, EFT_NUM_BUFFERS);
+	if (rval) {
+		ql_log(ql_log_warn, vha, 0x00c2,
+		       "Unable to initialize EFT (%d).\n", rval);
+		dma_free_coherent(&ha->pdev->dev, EFT_SIZE, tc, tc_dma);
+		return;
+	}
+
+	ql_dbg(ql_dbg_init, vha, 0x00c3,
+	       "Allocated (%d KB) EFT ...\n", EFT_SIZE / 1024);
+
+	ha->eft_dma = tc_dma;
+	ha->eft = tc;
+}
+
+static void
+qla2x00_alloc_offload_mem(scsi_qla_host_t *vha)
+{
+	qla2x00_init_fce_trace(vha);
+	qla2x00_init_eft_trace(vha);
 }
 
 void
 qla2x00_alloc_fw_dump(scsi_qla_host_t *vha)
 {
-	int rval;
 	uint32_t dump_size, fixed_size, mem_size, req_q_size, rsp_q_size,
 	    eft_size, fce_size, mq_size;
 	struct qla_hw_data *ha = vha->hw;
 	struct req_que *req = ha->req_q_map[0];
 	struct rsp_que *rsp = ha->rsp_q_map[0];
 	struct qla2xxx_fw_dump *fw_dump;
-	dma_addr_t tc_dma;
-	void *tc;
 
 	dump_size = fixed_size = mem_size = eft_size = fce_size = mq_size = 0;
 	req_q_size = rsp_q_size = 0;
@@ -3230,37 +3240,13 @@ qla2x00_alloc_fw_dump(scsi_qla_host_t *vha)
 		}
 		if (ha->tgt.atio_ring)
 			mq_size += ha->tgt.atio_q_length * sizeof(request_t);
-		/* Allocate memory for Fibre Channel Event Buffer. */
-		if (!IS_QLA25XX(ha) && !IS_QLA81XX(ha) && !IS_QLA83XX(ha) &&
-		    !IS_QLA27XX(ha) && !IS_QLA28XX(ha))
-			goto try_eft;
 
-		fce_size = sizeof(struct qla2xxx_fce_chain) + FCE_SIZE;
-try_eft:
+		qla2x00_init_fce_trace(vha);
+		if (ha->fce)
+			fce_size = sizeof(struct qla2xxx_fce_chain) + FCE_SIZE;
+		qla2x00_init_eft_trace(vha);
 		if (ha->eft)
-			dma_free_coherent(&ha->pdev->dev,
-			    EFT_SIZE, ha->eft, ha->eft_dma);
-
-		/* Allocate memory for Extended Trace Buffer. */
-		tc = dma_alloc_coherent(&ha->pdev->dev, EFT_SIZE, &tc_dma,
-					 GFP_KERNEL);
-		if (!tc) {
-			ql_log(ql_log_warn, vha, 0x00c1,
-			    "Unable to allocate (%d KB) for EFT.\n",
-			    EFT_SIZE / 1024);
-			goto allocate;
-		}
-
-		rval = qla2x00_enable_eft_trace(vha, tc_dma, EFT_NUM_BUFFERS);
-		if (rval) {
-			ql_log(ql_log_warn, vha, 0x00c2,
-			    "Unable to initialize EFT (%d).\n", rval);
-			dma_free_coherent(&ha->pdev->dev, EFT_SIZE, tc,
-			    tc_dma);
-		}
-		ql_dbg(ql_dbg_init, vha, 0x00c3,
-		    "Allocated (%d KB) EFT ...\n", EFT_SIZE / 1024);
-		eft_size = EFT_SIZE;
+			eft_size = EFT_SIZE;
 	}
 
 	if (IS_QLA27XX(ha) || IS_QLA28XX(ha)) {
@@ -3282,24 +3268,22 @@ try_eft:
 			    j, fwdt->dump_size);
 			dump_size += fwdt->dump_size;
 		}
-		goto allocate;
+	} else {
+		req_q_size = req->length * sizeof(request_t);
+		rsp_q_size = rsp->length * sizeof(response_t);
+		dump_size = offsetof(struct qla2xxx_fw_dump, isp);
+		dump_size += fixed_size + mem_size + req_q_size + rsp_q_size
+			+ eft_size;
+		ha->chain_offset = dump_size;
+		dump_size += mq_size + fce_size;
+		if (ha->exchoffld_buf)
+			dump_size += sizeof(struct qla2xxx_offld_chain) +
+				ha->exchoffld_size;
+		if (ha->exlogin_buf)
+			dump_size += sizeof(struct qla2xxx_offld_chain) +
+				ha->exlogin_size;
 	}
 
-	req_q_size = req->length * sizeof(request_t);
-	rsp_q_size = rsp->length * sizeof(response_t);
-	dump_size = offsetof(struct qla2xxx_fw_dump, isp);
-	dump_size += fixed_size + mem_size + req_q_size + rsp_q_size + eft_size;
-	ha->chain_offset = dump_size;
-	dump_size += mq_size + fce_size;
-
-	if (ha->exchoffld_buf)
-		dump_size += sizeof(struct qla2xxx_offld_chain) +
-			ha->exchoffld_size;
-	if (ha->exlogin_buf)
-		dump_size += sizeof(struct qla2xxx_offld_chain) +
-			ha->exlogin_size;
-
-allocate:
 	if (!ha->fw_dump_len || dump_size > ha->fw_dump_alloc_len) {
 
 		ql_dbg(ql_dbg_init, vha, 0x00c5,
@@ -4974,14 +4958,8 @@ qla2x00_configure_loop(scsi_qla_host_t *vha)
 		set_bit(RSCN_UPDATE, &flags);
 		clear_bit(LOCAL_LOOP_UPDATE, &flags);
 
-	} else if (ha->current_topology == ISP_CFG_N) {
-		clear_bit(RSCN_UPDATE, &flags);
-		if (qla_tgt_mode_enabled(vha)) {
-			/* allow the other side to start the login */
-			clear_bit(LOCAL_LOOP_UPDATE, &flags);
-			set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
-		}
-	} else if (ha->current_topology == ISP_CFG_NL) {
+	} else if (ha->current_topology == ISP_CFG_NL ||
+		   ha->current_topology == ISP_CFG_N) {
 		clear_bit(RSCN_UPDATE, &flags);
 		set_bit(LOCAL_LOOP_UPDATE, &flags);
 	} else if (!vha->flags.online ||
@@ -5096,7 +5074,6 @@ qla2x00_configure_local_loop(scsi_qla_host_t *vha)
 
 			memcpy(&ha->plogi_els_payld.data, (void *)ha->init_cb,
 			    sizeof(ha->plogi_els_payld.data));
-			set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
 		} else {
 			ql_dbg(ql_dbg_init, vha, 0x00d1,
 			    "PLOGI ELS param read fail.\n");
@@ -5929,8 +5906,7 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha)
 		if (test_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags))
 			break;
 
-		if ((fcport->flags & FCF_FABRIC_DEVICE) == 0 ||
-		    (fcport->flags & FCF_LOGIN_NEEDED) == 0)
+		if ((fcport->flags & FCF_FABRIC_DEVICE) == 0)
 			continue;
 
 		if (fcport->scan_state == QLA_FCPORT_SCAN) {
@@ -5953,7 +5929,8 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha)
 			}
 		}
 
-		if (fcport->scan_state == QLA_FCPORT_FOUND)
+		if (fcport->scan_state == QLA_FCPORT_FOUND &&
+		    (fcport->flags & FCF_LOGIN_NEEDED) != 0)
 			qla24xx_fcport_handle_login(vha, fcport);
 	}
 	return (rval);
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index 9312b19ed708..4ab44f8fb285 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -2441,11 +2441,19 @@ qla2x00_login_iocb(srb_t *sp, struct mbx_entry *mbx)
 static void
 qla24xx_logout_iocb(srb_t *sp, struct logio_entry_24xx *logio)
 {
+	u16 control_flags = LCF_COMMAND_LOGO;
 	logio->entry_type = LOGINOUT_PORT_IOCB_TYPE;
-	logio->control_flags =
-	    cpu_to_le16(LCF_COMMAND_LOGO|LCF_IMPL_LOGO);
-	if (!sp->fcport->keep_nport_handle)
-		logio->control_flags |= cpu_to_le16(LCF_FREE_NPORT);
+
+	if (sp->fcport->explicit_logout) {
+		control_flags |= LCF_EXPL_LOGO|LCF_FREE_NPORT;
+	} else {
+		control_flags |= LCF_IMPL_LOGO;
+
+		if (!sp->fcport->keep_nport_handle)
+			control_flags |= LCF_FREE_NPORT;
+	}
+
+	logio->control_flags = cpu_to_le16(control_flags);
 	logio->nport_handle = cpu_to_le16(sp->fcport->loop_id);
 	logio->port_id[0] = sp->fcport->d_id.b.al_pa;
 	logio->port_id[1] = sp->fcport->d_id.b.area;
@@ -2715,7 +2723,8 @@ qla24xx_els_logo_iocb(srb_t *sp, struct els_entry_24xx *els_iocb)
 		ql_dbg(ql_dbg_io + ql_dbg_buffer, vha, 0x3073,
 		    "PLOGI ELS IOCB:\n");
 		ql_dump_buffer(ql_log_info, vha, 0x0109,
-		    (uint8_t *)els_iocb, 0x70);
+		    (uint8_t *)els_iocb,
+		    sizeof(*els_iocb));
 	} else {
 		els_iocb->tx_byte_count = sizeof(struct els_logo_payload);
 		put_unaligned_le64(elsio->u.els_logo.els_logo_pyld_dma,
@@ -2876,7 +2885,8 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode,
 
 	ql_dbg(ql_dbg_disc + ql_dbg_buffer, vha, 0x3073, "PLOGI buffer:\n");
 	ql_dump_buffer(ql_dbg_disc + ql_dbg_buffer, vha, 0x0109,
-	    (uint8_t *)elsio->u.els_plogi.els_plogi_pyld, 0x70);
+	    (uint8_t *)elsio->u.els_plogi.els_plogi_pyld,
+	    sizeof(*elsio->u.els_plogi.els_plogi_pyld));
 
 	rval = qla2x00_start_sp(sp);
 	if (rval != QLA_SUCCESS) {
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 78aec50abe0f..18a70859a0b7 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -1062,8 +1062,6 @@ global_port_update:
 			ql_dbg(ql_dbg_async, vha, 0x5011,
 			    "Asynchronous PORT UPDATE ignored %04x/%04x/%04x.\n",
 			    mb[1], mb[2], mb[3]);
-
-			qlt_async_event(mb[0], vha, mb);
 			break;
 		}
 
@@ -1080,8 +1078,6 @@ global_port_update:
 		set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
 		set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags);
 		set_bit(VP_CONFIG_OK, &vha->vp_flags);
-
-		qlt_async_event(mb[0], vha, mb);
 		break;
 
 	case MBA_RSCN_UPDATE:		/* State Change Registration */
@@ -1903,6 +1899,18 @@ static void qla24xx_nvme_iocb_entry(scsi_qla_host_t *vha, struct req_que *req,
 		inbuf = (uint32_t *)&sts->nvme_ersp_data;
 		outbuf = (uint32_t *)fd->rspaddr;
 		iocb->u.nvme.rsp_pyld_len = le16_to_cpu(sts->nvme_rsp_pyld_len);
+		if (unlikely(iocb->u.nvme.rsp_pyld_len >
+		    sizeof(struct nvme_fc_ersp_iu))) {
+			if (ql_mask_match(ql_dbg_io)) {
+				WARN_ONCE(1, "Unexpected response payload length %u.\n",
+				    iocb->u.nvme.rsp_pyld_len);
+				ql_log(ql_log_warn, fcport->vha, 0x5100,
+				    "Unexpected response payload length %u.\n",
+				    iocb->u.nvme.rsp_pyld_len);
+			}
+			iocb->u.nvme.rsp_pyld_len =
+			    sizeof(struct nvme_fc_ersp_iu);
+		}
 		iter = iocb->u.nvme.rsp_pyld_len >> 2;
 		for (; iter; iter--)
 			*outbuf++ = swab32(*inbuf++);
@@ -3633,7 +3641,7 @@ qla2x00_request_irqs(struct qla_hw_data *ha, struct rsp_que *rsp)
 skip_msix:
 
 	ql_log(ql_log_info, vha, 0x0037,
-	    "Falling back-to MSI mode -%d.\n", ret);
+	    "Falling back-to MSI mode -- ret=%d.\n", ret);
 
 	if (!IS_QLA24XX(ha) && !IS_QLA2532(ha) && !IS_QLA8432(ha) &&
 	    !IS_QLA8001(ha) && !IS_P3P_TYPE(ha) && !IS_QLAFX00(ha) &&
@@ -3641,13 +3649,13 @@ skip_msix:
 		goto skip_msi;
 
 	ret = pci_alloc_irq_vectors(ha->pdev, 1, 1, PCI_IRQ_MSI);
-	if (!ret) {
+	if (ret > 0) {
 		ql_dbg(ql_dbg_init, vha, 0x0038,
 		    "MSI: Enabled.\n");
 		ha->flags.msi_enabled = 1;
 	} else
 		ql_log(ql_log_warn, vha, 0x0039,
-		    "Falling back-to INTa mode -- %d.\n", ret);
+		    "Falling back-to INTa mode -- ret=%d.\n", ret);
 skip_msi:
 
 	/* Skip INTx on ISP82xx. */
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 24ca1bcb6f7f..2774c81fefb7 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -3125,7 +3125,7 @@ qla24xx_abort_command(srb_t *sp)
 	ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x108c,
 	    "Entered %s.\n", __func__);
 
-	if (vha->flags.qpairs_available && sp->qpair)
+	if (sp->qpair)
 		req = sp->qpair->req;
 	else
 		return QLA_FUNCTION_FAILED;
@@ -3918,6 +3918,7 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
 					vha->d_id.b24 = 0;
 					vha->d_id.b.al_pa = 1;
 					ha->flags.n2n_bigger = 1;
+					ha->flags.n2n_ae = 0;
 
 					id.b.al_pa = 2;
 					ql_dbg(ql_dbg_async, vha, 0x5075,
@@ -3928,6 +3929,7 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
 					    "Format 1: Remote login - Waiting for WWPN %8phC.\n",
 					    rptid_entry->u.f1.port_name);
 					ha->flags.n2n_bigger = 0;
+					ha->flags.n2n_ae = 1;
 				}
 				qla24xx_post_newsess_work(vha, &id,
 				    rptid_entry->u.f1.port_name,
@@ -3939,7 +3941,6 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
 			/* if our portname is higher then initiate N2N login */
 
 			set_bit(N2N_LOGIN_NEEDED, &vha->dpc_flags);
-			ha->flags.n2n_ae = 1;
 			return;
 			break;
 		case TOPO_FL:
@@ -6139,9 +6140,8 @@ qla2x00_dump_mctp_data(scsi_qla_host_t *vha, dma_addr_t req_dma, uint32_t addr,
 	mcp->mb[7] = LSW(MSD(req_dma));
 	mcp->mb[8] = MSW(addr);
 	/* Setting RAM ID to valid */
-	mcp->mb[10] |= BIT_7;
 	/* For MCTP RAM ID is 0x40 */
-	mcp->mb[10] |= 0x40;
+	mcp->mb[10] = BIT_7 | 0x40;
 
 	mcp->out_mb |= MBX_10|MBX_8|MBX_7|MBX_6|MBX_5|MBX_4|MBX_3|MBX_2|MBX_1|
 	    MBX_0;
diff --git a/drivers/scsi/qla2xxx/qla_nx.c b/drivers/scsi/qla2xxx/qla_nx.c
index c760ae354174..55df42933c4b 100644
--- a/drivers/scsi/qla2xxx/qla_nx.c
+++ b/drivers/scsi/qla2xxx/qla_nx.c
@@ -1612,8 +1612,7 @@ qla82xx_get_bootld_offset(struct qla_hw_data *ha)
 	return (u8 *)&ha->hablob->fw->data[offset];
 }
 
-static __le32
-qla82xx_get_fw_size(struct qla_hw_data *ha)
+static u32 qla82xx_get_fw_size(struct qla_hw_data *ha)
 {
 	struct qla82xx_uri_data_desc *uri_desc = NULL;
 
@@ -1624,7 +1623,7 @@ qla82xx_get_fw_size(struct qla_hw_data *ha)
 			return cpu_to_le32(uri_desc->size);
 	}
 
-	return cpu_to_le32(*(u32 *)&ha->hablob->fw->data[FW_SIZE_OFFSET]);
+	return get_unaligned_le32(&ha->hablob->fw->data[FW_SIZE_OFFSET]);
 }
 
 static u8 *
@@ -1816,7 +1815,7 @@ qla82xx_fw_load_from_blob(struct qla_hw_data *ha)
 	}
 
 	flashaddr = FLASH_ADDR_START;
-	size = (__force u32)qla82xx_get_fw_size(ha) / 8;
+	size = qla82xx_get_fw_size(ha) / 8;
 	ptr64 = (u64 *)qla82xx_get_fw_offs(ha);
 
 	for (i = 0; i < size; i++) {
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index e1e966df1203..4af35179475f 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -1269,6 +1269,7 @@ static int
 qla2xxx_eh_abort(struct scsi_cmnd *cmd)
 {
 	scsi_qla_host_t *vha = shost_priv(cmd->device->host);
+	DECLARE_COMPLETION_ONSTACK(comp);
 	srb_t *sp;
 	int ret;
 	unsigned int id;
@@ -1304,6 +1305,7 @@ qla2xxx_eh_abort(struct scsi_cmnd *cmd)
 		return SUCCESS;
 	}
 
+	/* Get a reference to the sp and drop the lock. */
 	if (sp_get(sp)){
 		/* ref_count is already 0 */
 		spin_unlock_irqrestore(qpair->qp_lock_ptr, flags);
@@ -1331,6 +1333,23 @@ qla2xxx_eh_abort(struct scsi_cmnd *cmd)
 		sp->done(sp, DID_ABORT << 16);
 		ret = SUCCESS;
 		break;
+	case QLA_FUNCTION_PARAMETER_ERROR: {
+		/* Wait for the command completion. */
+		uint32_t ratov = ha->r_a_tov/10;
+		uint32_t ratov_j = msecs_to_jiffies(4 * ratov * 1000);
+
+		WARN_ON_ONCE(sp->comp);
+		sp->comp = &comp;
+		if (!wait_for_completion_timeout(&comp, ratov_j)) {
+			ql_dbg(ql_dbg_taskm, vha, 0xffff,
+			    "%s: Abort wait timer (4 * R_A_TOV[%d]) expired\n",
+			    __func__, ha->r_a_tov);
+			ret = FAILED;
+		} else {
+			ret = SUCCESS;
+		}
+		break;
+	}
 	default:
 		/*
 		 * Either abort failed or abort and completion raced. Let
@@ -1340,6 +1359,8 @@ qla2xxx_eh_abort(struct scsi_cmnd *cmd)
 		break;
 	}
 
+	sp->comp = NULL;
+	atomic_dec(&sp->ref_count);
 	ql_log(ql_log_info, vha, 0x801c,
 	    "Abort command issued nexus=%ld:%d:%llu -- %x.\n",
 	    vha->host_no, id, lun, ret);
@@ -1746,6 +1767,8 @@ static void qla2x00_abort_srb(struct qla_qpair *qp, srb_t *sp, const int res,
 		spin_lock_irqsave(qp->qp_lock_ptr, *flags);
 		sp->comp = NULL;
 	}
+
+	atomic_dec(&sp->ref_count);
 }
 
 static void
@@ -3695,6 +3718,13 @@ qla2x00_remove_one(struct pci_dev *pdev)
 	}
 	qla2x00_wait_for_hba_ready(base_vha);
 
+	/*
+	 * if UNLOADING flag is already set, then continue unload,
+	 * where it was set first.
+	 */
+	if (test_and_set_bit(UNLOADING, &base_vha->dpc_flags))
+		return;
+
 	if (IS_QLA25XX(ha) || IS_QLA2031(ha) || IS_QLA27XX(ha) ||
 	    IS_QLA28XX(ha)) {
 		if (ha->flags.fw_started)
@@ -3713,15 +3743,6 @@ qla2x00_remove_one(struct pci_dev *pdev)
 
 	qla2x00_wait_for_sess_deletion(base_vha);
 
-	/*
-	 * if UNLOAD flag is already set, then continue unload,
-	 * where it was set first.
-	 */
-	if (test_bit(UNLOADING, &base_vha->dpc_flags))
-		return;
-
-	set_bit(UNLOADING, &base_vha->dpc_flags);
-
 	qla_nvme_delete(base_vha);
 
 	dma_free_coherent(&ha->pdev->dev,
@@ -4606,6 +4627,7 @@ qla2x00_free_fw_dump(struct qla_hw_data *ha)
 
 	ha->fce = NULL;
 	ha->fce_dma = 0;
+	ha->flags.fce_enabled = 0;
 	ha->eft = NULL;
 	ha->eft_dma = 0;
 	ha->fw_dumped = 0;
@@ -4854,6 +4876,9 @@ qla2x00_alloc_work(struct scsi_qla_host *vha, enum qla_work_type type)
 	struct qla_work_evt *e;
 	uint8_t bail;
 
+	if (test_bit(UNLOADING, &vha->dpc_flags))
+		return NULL;
+
 	QLA_VHA_MARK_BUSY(vha, bail);
 	if (bail)
 		return NULL;
@@ -6060,13 +6085,6 @@ qla2x00_disable_board_on_pci_error(struct work_struct *work)
 	struct pci_dev *pdev = ha->pdev;
 	scsi_qla_host_t *base_vha = pci_get_drvdata(ha->pdev);
 
-	/*
-	 * if UNLOAD flag is already set, then continue unload,
-	 * where it was set first.
-	 */
-	if (test_bit(UNLOADING, &base_vha->dpc_flags))
-		return;
-
 	ql_log(ql_log_warn, base_vha, 0x015b,
 	    "Disabling adapter.\n");
 
@@ -6077,9 +6095,14 @@ qla2x00_disable_board_on_pci_error(struct work_struct *work)
 		return;
 	}
 
-	qla2x00_wait_for_sess_deletion(base_vha);
+	/*
+	 * if UNLOADING flag is already set, then continue unload,
+	 * where it was set first.
+	 */
+	if (test_and_set_bit(UNLOADING, &base_vha->dpc_flags))
+		return;
 
-	set_bit(UNLOADING, &base_vha->dpc_flags);
+	qla2x00_wait_for_sess_deletion(base_vha);
 
 	qla2x00_delete_all_vps(ha, base_vha);
 
@@ -6303,6 +6326,7 @@ qla2x00_do_dpc(void *data)
 
 			if (do_reset && !(test_and_set_bit(ABORT_ISP_ACTIVE,
 			    &base_vha->dpc_flags))) {
+				base_vha->flags.online = 1;
 				ql_dbg(ql_dbg_dpc, base_vha, 0x4007,
 				    "ISP abort scheduled.\n");
 				if (ha->isp_ops->abort_isp(base_vha)) {
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index bb4f3d51a305..51f16346e3e4 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -1099,6 +1099,7 @@ void qlt_free_session_done(struct work_struct *work)
 		}
 	}
 
+	sess->explicit_logout = 0;
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
 
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf001,
@@ -1269,7 +1270,6 @@ void qlt_schedule_sess_for_deletion(struct fc_port *sess)
 	    "Scheduling sess %p for deletion %8phC\n",
 	    sess, sess->port_name);
 
-	INIT_WORK(&sess->del_work, qla24xx_delete_sess_fn);
 	WARN_ON(!queue_work(sess->vha->hw->wq, &sess->del_work));
 }
 
@@ -4838,6 +4838,7 @@ static int qlt_handle_login(struct scsi_qla_host *vha,
 
 	switch (sess->disc_state) {
 	case DSC_DELETED:
+	case DSC_LOGIN_PEND:
 		qlt_plogi_ack_unref(vha, pla);
 		break;
 
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index 8c6354037686..8fb8fb8a48ad 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -350,6 +350,7 @@ static void tcm_qla2xxx_close_session(struct se_session *se_sess)
 	target_sess_cmd_list_set_waiting(se_sess);
 	spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
 
+	sess->explicit_logout = 1;
 	tcm_qla2xxx_put_sess(sess);
 }
 
@@ -921,6 +922,7 @@ static ssize_t tcm_qla2xxx_tpg_enable_store(struct config_item *item,
 
 		atomic_set(&tpg->lport_tpg_enabled, 0);
 		qlt_stop_phase1(vha->vha_tgt.qla_tgt);
+		qlt_stop_phase2(vha->vha_tgt.qla_tgt);
 	}
 
 	return count;
@@ -1083,6 +1085,7 @@ static ssize_t tcm_qla2xxx_npiv_tpg_enable_store(struct config_item *item,
 
 		atomic_set(&tpg->lport_tpg_enabled, 0);
 		qlt_stop_phase1(vha->vha_tgt.qla_tgt);
+		qlt_stop_phase2(vha->vha_tgt.qla_tgt);
 	}
 
 	return count;
diff --git a/drivers/scsi/qla4xxx/ql4_mbx.c b/drivers/scsi/qla4xxx/ql4_mbx.c
index dac9a7013208..02636b4785c5 100644
--- a/drivers/scsi/qla4xxx/ql4_mbx.c
+++ b/drivers/scsi/qla4xxx/ql4_mbx.c
@@ -640,9 +640,6 @@ int qla4xxx_initialize_fw_cb(struct scsi_qla_host * ha)
 
 	if (qla4xxx_get_ifcb(ha, &mbox_cmd[0], &mbox_sts[0], init_fw_cb_dma) !=
 	    QLA_SUCCESS) {
-		dma_free_coherent(&ha->pdev->dev,
-				  sizeof(struct addr_ctrl_blk),
-				  init_fw_cb, init_fw_cb_dma);
 		goto exit_init_fw_cb;
 	}
 
diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index 8c674eca09f1..5504ab11decc 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -4145,7 +4145,7 @@ static void qla4xxx_mem_free(struct scsi_qla_host *ha)
 		dma_free_coherent(&ha->pdev->dev, ha->queues_len, ha->queues,
 				  ha->queues_dma);
 
-	 if (ha->fw_dump)
+	if (ha->fw_dump)
 		vfree(ha->fw_dump);
 
 	ha->queues_len = 0;
@@ -4275,7 +4275,6 @@ static int qla4xxx_mem_alloc(struct scsi_qla_host *ha)
 	return QLA_SUCCESS;
 
 mem_alloc_error_exit:
-	qla4xxx_mem_free(ha);
 	return QLA_ERROR;
 }
 
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 32965ec76965..44181a2cbf18 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -5296,6 +5296,12 @@ static int __init scsi_debug_init(void)
 		pr_err("submit_queues must be 1 or more\n");
 		return -EINVAL;
 	}
+
+	if ((sdebug_max_queue > SDEBUG_CANQUEUE) || (sdebug_max_queue < 1)) {
+		pr_err("max_queue must be in range [1, %d]\n", SDEBUG_CANQUEUE);
+		return -EINVAL;
+	}
+
 	sdebug_q_arr = kcalloc(submit_queues, sizeof(struct sdebug_queue),
 			       GFP_KERNEL);
 	if (sdebug_q_arr == NULL)
diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c
index a08ff3bd6310..d16d8b6aaccc 100644
--- a/drivers/scsi/scsi_devinfo.c
+++ b/drivers/scsi/scsi_devinfo.c
@@ -239,6 +239,7 @@ static struct {
 	{"LSI", "Universal Xport", "*", BLIST_NO_ULD_ATTACH},
 	{"ENGENIO", "Universal Xport", "*", BLIST_NO_ULD_ATTACH},
 	{"LENOVO", "Universal Xport", "*", BLIST_NO_ULD_ATTACH},
+	{"FUJITSU", "Universal Xport", "*", BLIST_NO_ULD_ATTACH},
 	{"SMSC", "USB 2 HS-CF", NULL, BLIST_SPARSELUN | BLIST_INQUIRY_36},
 	{"SONY", "CD-ROM CDU-8001", NULL, BLIST_BORKEN},
 	{"SONY", "TSL", NULL, BLIST_FORCELUN},		/* DDS3 & DDS4 autoloaders */
diff --git a/drivers/scsi/scsi_dh.c b/drivers/scsi/scsi_dh.c
index 42f0550d6b11..6f41e4b5a2b8 100644
--- a/drivers/scsi/scsi_dh.c
+++ b/drivers/scsi/scsi_dh.c
@@ -63,6 +63,7 @@ static const struct scsi_dh_blist scsi_dh_blist[] = {
 	{"LSI", "INF-01-00",		"rdac", },
 	{"ENGENIO", "INF-01-00",	"rdac", },
 	{"LENOVO", "DE_Series",		"rdac", },
+	{"FUJITSU", "ETERNUS_AHB",	"rdac", },
 	{NULL, NULL,			NULL },
 };
 
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 3093e8f3af6e..65646497295f 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -539,7 +539,7 @@ static void scsi_uninit_cmd(struct scsi_cmnd *cmd)
 	}
 }
 
-static void scsi_mq_free_sgtables(struct scsi_cmnd *cmd)
+static void scsi_free_sgtables(struct scsi_cmnd *cmd)
 {
 	if (cmd->sdb.table.nents)
 		sg_free_table_chained(&cmd->sdb.table, true);
@@ -549,11 +549,20 @@ static void scsi_mq_free_sgtables(struct scsi_cmnd *cmd)
 
 static void scsi_mq_uninit_cmd(struct scsi_cmnd *cmd)
 {
-	scsi_mq_free_sgtables(cmd);
+	scsi_free_sgtables(cmd);
 	scsi_uninit_cmd(cmd);
 	scsi_del_cmd_from_list(cmd);
 }
 
+static void scsi_run_queue_async(struct scsi_device *sdev)
+{
+	if (scsi_target(sdev)->single_lun ||
+	    !list_empty(&sdev->host->starved_list))
+		kblockd_schedule_work(&sdev->requeue_work);
+	else
+		blk_mq_run_hw_queues(sdev->request_queue, true);
+}
+
 /* Returns false when no more bytes to process, true if there are more */
 static bool scsi_end_request(struct request *req, blk_status_t error,
 		unsigned int bytes)
@@ -598,11 +607,7 @@ static bool scsi_end_request(struct request *req, blk_status_t error,
 
 	__blk_mq_end_request(req, error);
 
-	if (scsi_target(sdev)->single_lun ||
-	    !list_empty(&sdev->host->starved_list))
-		kblockd_schedule_work(&sdev->requeue_work);
-	else
-		blk_mq_run_hw_queues(q, true);
+	scsi_run_queue_async(sdev);
 
 	percpu_ref_put(&q->q_usage_counter);
 	return false;
@@ -1047,7 +1052,7 @@ blk_status_t scsi_init_io(struct scsi_cmnd *cmd)
 
 	return BLK_STS_OK;
 out_free_sgtables:
-	scsi_mq_free_sgtables(cmd);
+	scsi_free_sgtables(cmd);
 	return ret;
 }
 EXPORT_SYMBOL(scsi_init_io);
@@ -1198,6 +1203,7 @@ static blk_status_t scsi_setup_cmnd(struct scsi_device *sdev,
 		struct request *req)
 {
 	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(req);
+	blk_status_t ret;
 
 	if (!blk_rq_bytes(req))
 		cmd->sc_data_direction = DMA_NONE;
@@ -1207,9 +1213,14 @@ static blk_status_t scsi_setup_cmnd(struct scsi_device *sdev,
 		cmd->sc_data_direction = DMA_FROM_DEVICE;
 
 	if (blk_rq_is_scsi(req))
-		return scsi_setup_scsi_cmnd(sdev, req);
+		ret = scsi_setup_scsi_cmnd(sdev, req);
 	else
-		return scsi_setup_fs_cmnd(sdev, req);
+		ret = scsi_setup_fs_cmnd(sdev, req);
+
+	if (ret != BLK_STS_OK)
+		scsi_free_sgtables(cmd);
+
+	return ret;
 }
 
 static blk_status_t
@@ -1706,6 +1717,7 @@ out_put_budget:
 		 */
 		if (req->rq_flags & RQF_DONTPREP)
 			scsi_mq_uninit_cmd(cmd);
+		scsi_run_queue_async(sdev);
 		break;
 	}
 	return ret;
diff --git a/drivers/scsi/scsi_pm.c b/drivers/scsi/scsi_pm.c
index 48ee68059fe6..453f320e85ec 100644
--- a/drivers/scsi/scsi_pm.c
+++ b/drivers/scsi/scsi_pm.c
@@ -80,6 +80,10 @@ static int scsi_dev_type_resume(struct device *dev,
 	dev_dbg(dev, "scsi resume: %d\n", err);
 
 	if (err == 0) {
+		bool was_runtime_suspended;
+
+		was_runtime_suspended = pm_runtime_suspended(dev);
+
 		pm_runtime_disable(dev);
 		err = pm_runtime_set_active(dev);
 		pm_runtime_enable(dev);
@@ -93,8 +97,9 @@ static int scsi_dev_type_resume(struct device *dev,
 		 */
 		if (!err && scsi_is_sdev_device(dev)) {
 			struct scsi_device *sdev = to_scsi_device(dev);
-
-			if (sdev->request_queue->dev)
+			if (was_runtime_suspended)
+				blk_post_runtime_resume(sdev->request_queue, 0);
+			else
 				blk_set_runtime_active(sdev->request_queue);
 		}
 	}
diff --git a/drivers/scsi/scsi_trace.c b/drivers/scsi/scsi_trace.c
index 07a2425ffa2c..ac35c301c792 100644
--- a/drivers/scsi/scsi_trace.c
+++ b/drivers/scsi/scsi_trace.c
@@ -9,7 +9,7 @@
 #include <trace/events/scsi.h>
 
 #define SERVICE_ACTION16(cdb) (cdb[1] & 0x1f)
-#define SERVICE_ACTION32(cdb) ((cdb[8] << 8) | cdb[9])
+#define SERVICE_ACTION32(cdb) (get_unaligned_be16(&cdb[8]))
 
 static const char *
 scsi_trace_misc(struct trace_seq *, unsigned char *, int);
@@ -39,17 +39,12 @@ static const char *
 scsi_trace_rw10(struct trace_seq *p, unsigned char *cdb, int len)
 {
 	const char *ret = trace_seq_buffer_ptr(p);
-	sector_t lba = 0, txlen = 0;
+	u32 lba, txlen;
 
-	lba |= (cdb[2] << 24);
-	lba |= (cdb[3] << 16);
-	lba |= (cdb[4] << 8);
-	lba |=  cdb[5];
-	txlen |= (cdb[7] << 8);
-	txlen |=  cdb[8];
+	lba = get_unaligned_be32(&cdb[2]);
+	txlen = get_unaligned_be16(&cdb[7]);
 
-	trace_seq_printf(p, "lba=%llu txlen=%llu protect=%u",
-			 (unsigned long long)lba, (unsigned long long)txlen,
+	trace_seq_printf(p, "lba=%u txlen=%u protect=%u", lba, txlen,
 			 cdb[1] >> 5);
 
 	if (cdb[0] == WRITE_SAME)
@@ -64,19 +59,12 @@ static const char *
 scsi_trace_rw12(struct trace_seq *p, unsigned char *cdb, int len)
 {
 	const char *ret = trace_seq_buffer_ptr(p);
-	sector_t lba = 0, txlen = 0;
-
-	lba |= (cdb[2] << 24);
-	lba |= (cdb[3] << 16);
-	lba |= (cdb[4] << 8);
-	lba |=  cdb[5];
-	txlen |= (cdb[6] << 24);
-	txlen |= (cdb[7] << 16);
-	txlen |= (cdb[8] << 8);
-	txlen |=  cdb[9];
-
-	trace_seq_printf(p, "lba=%llu txlen=%llu protect=%u",
-			 (unsigned long long)lba, (unsigned long long)txlen,
+	u32 lba, txlen;
+
+	lba = get_unaligned_be32(&cdb[2]);
+	txlen = get_unaligned_be32(&cdb[6]);
+
+	trace_seq_printf(p, "lba=%u txlen=%u protect=%u", lba, txlen,
 			 cdb[1] >> 5);
 	trace_seq_putc(p, 0);
 
@@ -87,23 +75,13 @@ static const char *
 scsi_trace_rw16(struct trace_seq *p, unsigned char *cdb, int len)
 {
 	const char *ret = trace_seq_buffer_ptr(p);
-	sector_t lba = 0, txlen = 0;
-
-	lba |= ((u64)cdb[2] << 56);
-	lba |= ((u64)cdb[3] << 48);
-	lba |= ((u64)cdb[4] << 40);
-	lba |= ((u64)cdb[5] << 32);
-	lba |= (cdb[6] << 24);
-	lba |= (cdb[7] << 16);
-	lba |= (cdb[8] << 8);
-	lba |=  cdb[9];
-	txlen |= (cdb[10] << 24);
-	txlen |= (cdb[11] << 16);
-	txlen |= (cdb[12] << 8);
-	txlen |=  cdb[13];
-
-	trace_seq_printf(p, "lba=%llu txlen=%llu protect=%u",
-			 (unsigned long long)lba, (unsigned long long)txlen,
+	u64 lba;
+	u32 txlen;
+
+	lba = get_unaligned_be64(&cdb[2]);
+	txlen = get_unaligned_be32(&cdb[10]);
+
+	trace_seq_printf(p, "lba=%llu txlen=%u protect=%u", lba, txlen,
 			 cdb[1] >> 5);
 
 	if (cdb[0] == WRITE_SAME_16)
@@ -118,8 +96,8 @@ static const char *
 scsi_trace_rw32(struct trace_seq *p, unsigned char *cdb, int len)
 {
 	const char *ret = trace_seq_buffer_ptr(p), *cmd;
-	sector_t lba = 0, txlen = 0;
-	u32 ei_lbrt = 0;
+	u64 lba;
+	u32 ei_lbrt, txlen;
 
 	switch (SERVICE_ACTION32(cdb)) {
 	case READ_32:
@@ -139,26 +117,12 @@ scsi_trace_rw32(struct trace_seq *p, unsigned char *cdb, int len)
 		goto out;
 	}
 
-	lba |= ((u64)cdb[12] << 56);
-	lba |= ((u64)cdb[13] << 48);
-	lba |= ((u64)cdb[14] << 40);
-	lba |= ((u64)cdb[15] << 32);
-	lba |= (cdb[16] << 24);
-	lba |= (cdb[17] << 16);
-	lba |= (cdb[18] << 8);
-	lba |=  cdb[19];
-	ei_lbrt |= (cdb[20] << 24);
-	ei_lbrt |= (cdb[21] << 16);
-	ei_lbrt |= (cdb[22] << 8);
-	ei_lbrt |=  cdb[23];
-	txlen |= (cdb[28] << 24);
-	txlen |= (cdb[29] << 16);
-	txlen |= (cdb[30] << 8);
-	txlen |=  cdb[31];
-
-	trace_seq_printf(p, "%s_32 lba=%llu txlen=%llu protect=%u ei_lbrt=%u",
-			 cmd, (unsigned long long)lba,
-			 (unsigned long long)txlen, cdb[10] >> 5, ei_lbrt);
+	lba = get_unaligned_be64(&cdb[12]);
+	ei_lbrt = get_unaligned_be32(&cdb[20]);
+	txlen = get_unaligned_be32(&cdb[28]);
+
+	trace_seq_printf(p, "%s_32 lba=%llu txlen=%u protect=%u ei_lbrt=%u",
+			 cmd, lba, txlen, cdb[10] >> 5, ei_lbrt);
 
 	if (SERVICE_ACTION32(cdb) == WRITE_SAME_32)
 		trace_seq_printf(p, " unmap=%u", cdb[10] >> 3 & 1);
@@ -173,7 +137,7 @@ static const char *
 scsi_trace_unmap(struct trace_seq *p, unsigned char *cdb, int len)
 {
 	const char *ret = trace_seq_buffer_ptr(p);
-	unsigned int regions = cdb[7] << 8 | cdb[8];
+	unsigned int regions = get_unaligned_be16(&cdb[7]);
 
 	trace_seq_printf(p, "regions=%u", (regions - 8) / 16);
 	trace_seq_putc(p, 0);
@@ -185,8 +149,8 @@ static const char *
 scsi_trace_service_action_in(struct trace_seq *p, unsigned char *cdb, int len)
 {
 	const char *ret = trace_seq_buffer_ptr(p), *cmd;
-	sector_t lba = 0;
-	u32 alloc_len = 0;
+	u64 lba;
+	u32 alloc_len;
 
 	switch (SERVICE_ACTION16(cdb)) {
 	case SAI_READ_CAPACITY_16:
@@ -200,21 +164,10 @@ scsi_trace_service_action_in(struct trace_seq *p, unsigned char *cdb, int len)
 		goto out;
 	}
 
-	lba |= ((u64)cdb[2] << 56);
-	lba |= ((u64)cdb[3] << 48);
-	lba |= ((u64)cdb[4] << 40);
-	lba |= ((u64)cdb[5] << 32);
-	lba |= (cdb[6] << 24);
-	lba |= (cdb[7] << 16);
-	lba |= (cdb[8] << 8);
-	lba |=  cdb[9];
-	alloc_len |= (cdb[10] << 24);
-	alloc_len |= (cdb[11] << 16);
-	alloc_len |= (cdb[12] << 8);
-	alloc_len |=  cdb[13];
-
-	trace_seq_printf(p, "%s lba=%llu alloc_len=%u", cmd,
-			 (unsigned long long)lba, alloc_len);
+	lba = get_unaligned_be64(&cdb[2]);
+	alloc_len = get_unaligned_be32(&cdb[10]);
+
+	trace_seq_printf(p, "%s lba=%llu alloc_len=%u", cmd, lba, alloc_len);
 
 out:
 	trace_seq_putc(p, 0);
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index 417b868d8735..a5c78b38d302 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -24,6 +24,8 @@
 
 #define ISCSI_TRANSPORT_VERSION "2.0-870"
 
+#define ISCSI_SEND_MAX_ALLOWED  10
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/iscsi.h>
 
@@ -2010,7 +2012,7 @@ static void __iscsi_unbind_session(struct work_struct *work)
 	if (session->target_id == ISCSI_MAX_TARGET) {
 		spin_unlock_irqrestore(&session->lock, flags);
 		mutex_unlock(&ihost->mutex);
-		return;
+		goto unbind_session_exit;
 	}
 
 	target_id = session->target_id;
@@ -2022,6 +2024,8 @@ static void __iscsi_unbind_session(struct work_struct *work)
 		ida_simple_remove(&iscsi_sess_ida, target_id);
 
 	scsi_remove_target(&session->dev);
+
+unbind_session_exit:
 	iscsi_session_event(session, ISCSI_KEVENT_UNBIND_SESSION);
 	ISCSI_DBG_TRANS_SESSION(session, "Completed target removal\n");
 }
@@ -2945,6 +2949,24 @@ iscsi_set_path(struct iscsi_transport *transport, struct iscsi_uevent *ev)
 	return err;
 }
 
+static int iscsi_session_has_conns(int sid)
+{
+	struct iscsi_cls_conn *conn;
+	unsigned long flags;
+	int found = 0;
+
+	spin_lock_irqsave(&connlock, flags);
+	list_for_each_entry(conn, &connlist, conn_list) {
+		if (iscsi_conn_get_sid(conn) == sid) {
+			found = 1;
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&connlock, flags);
+
+	return found;
+}
+
 static int
 iscsi_set_iface_params(struct iscsi_transport *transport,
 		       struct iscsi_uevent *ev, uint32_t len)
@@ -3522,10 +3544,12 @@ iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group)
 		break;
 	case ISCSI_UEVENT_DESTROY_SESSION:
 		session = iscsi_session_lookup(ev->u.d_session.sid);
-		if (session)
-			transport->destroy_session(session);
-		else
+		if (!session)
 			err = -EINVAL;
+		else if (iscsi_session_has_conns(ev->u.d_session.sid))
+			err = -EBUSY;
+		else
+			transport->destroy_session(session);
 		break;
 	case ISCSI_UEVENT_UNBIND_SESSION:
 		session = iscsi_session_lookup(ev->u.d_session.sid);
@@ -3682,6 +3706,7 @@ iscsi_if_rx(struct sk_buff *skb)
 		struct nlmsghdr	*nlh;
 		struct iscsi_uevent *ev;
 		uint32_t group;
+		int retries = ISCSI_SEND_MAX_ALLOWED;
 
 		nlh = nlmsg_hdr(skb);
 		if (nlh->nlmsg_len < sizeof(*nlh) + sizeof(*ev) ||
@@ -3712,6 +3737,10 @@ iscsi_if_rx(struct sk_buff *skb)
 				break;
 			err = iscsi_if_send_reply(portid, nlh->nlmsg_type,
 						  ev, sizeof(*ev));
+			if (err == -EAGAIN && --retries < 0) {
+				printk(KERN_WARNING "Send reply failed, error %d\n", err);
+				break;
+			}
 		} while (err < 0 && err != -ECONNREFUSED && err != -ESRCH);
 		skb_pull(skb, rlen);
 	}
diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c
index ef138c57e2a6..182fd25c7c43 100644
--- a/drivers/scsi/scsi_transport_sas.c
+++ b/drivers/scsi/scsi_transport_sas.c
@@ -1391,9 +1391,6 @@ static void sas_expander_release(struct device *dev)
 	struct sas_rphy *rphy = dev_to_rphy(dev);
 	struct sas_expander_device *edev = rphy_to_expander_device(rphy);
 
-	if (rphy->q)
-		blk_cleanup_queue(rphy->q);
-
 	put_device(dev->parent);
 	kfree(edev);
 }
@@ -1403,9 +1400,6 @@ static void sas_end_device_release(struct device *dev)
 	struct sas_rphy *rphy = dev_to_rphy(dev);
 	struct sas_end_device *edev = rphy_to_end_device(rphy);
 
-	if (rphy->q)
-		blk_cleanup_queue(rphy->q);
-
 	put_device(dev->parent);
 	kfree(edev);
 }
@@ -1634,8 +1628,7 @@ sas_rphy_remove(struct sas_rphy *rphy)
 	}
 
 	sas_rphy_unlink(rphy);
-	if (rphy->q)
-		bsg_unregister_queue(rphy->q);
+	bsg_remove_queue(rphy->q);
 	transport_remove_device(dev);
 	device_del(dev);
 }
diff --git a/drivers/scsi/scsi_transport_spi.c b/drivers/scsi/scsi_transport_spi.c
index f8661062ef95..f3d5b1bbd5aa 100644
--- a/drivers/scsi/scsi_transport_spi.c
+++ b/drivers/scsi/scsi_transport_spi.c
@@ -339,7 +339,7 @@ store_spi_transport_##field(struct device *dev, 			\
 	struct spi_transport_attrs *tp					\
 		= (struct spi_transport_attrs *)&starget->starget_data;	\
 									\
-	if (i->f->set_##field)						\
+	if (!i->f->set_##field)						\
 		return -EINVAL;						\
 	val = simple_strtoul(buf, NULL, 0);				\
 	if (val > tp->max_##field)					\
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 3f52e925dd1f..d84dfa286d0a 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1694,20 +1694,30 @@ static void sd_rescan(struct device *dev)
 static int sd_compat_ioctl(struct block_device *bdev, fmode_t mode,
 			   unsigned int cmd, unsigned long arg)
 {
-	struct scsi_device *sdev = scsi_disk(bdev->bd_disk)->device;
+	struct gendisk *disk = bdev->bd_disk;
+	struct scsi_disk *sdkp = scsi_disk(disk);
+	struct scsi_device *sdev = sdkp->device;
+	void __user *p = compat_ptr(arg);
 	int error;
 
+	error = scsi_verify_blk_ioctl(bdev, cmd);
+	if (error < 0)
+		return error;
+
 	error = scsi_ioctl_block_when_processing_errors(sdev, cmd,
 			(mode & FMODE_NDELAY) != 0);
 	if (error)
 		return error;
+
+	if (is_sed_ioctl(cmd))
+		return sed_ioctl(sdkp->opal_dev, cmd, p);
 	       
 	/* 
 	 * Let the static ioctl translation table take care of it.
 	 */
 	if (!sdev->host->hostt->compat_ioctl)
 		return -ENOIOCTLCMD; 
-	return sdev->host->hostt->compat_ioctl(sdev, cmd, (void __user *)arg);
+	return sdev->host->hostt->compat_ioctl(sdev, cmd, p);
 }
 #endif
 
@@ -2195,8 +2205,10 @@ static int sd_read_protection_type(struct scsi_disk *sdkp, unsigned char *buffer
 	u8 type;
 	int ret = 0;
 
-	if (scsi_device_protection(sdp) == 0 || (buffer[12] & 1) == 0)
+	if (scsi_device_protection(sdp) == 0 || (buffer[12] & 1) == 0) {
+		sdkp->protection_type = 0;
 		return ret;
+	}
 
 	type = ((buffer[12] >> 1) & 7) + 1; /* P_TYPE 0 = Type 1 */
 
@@ -3162,9 +3174,11 @@ static int sd_revalidate_disk(struct gendisk *disk)
 	if (sd_validate_opt_xfer_size(sdkp, dev_max)) {
 		q->limits.io_opt = logical_to_bytes(sdp, sdkp->opt_xfer_blocks);
 		rw_max = logical_to_sectors(sdp, sdkp->opt_xfer_blocks);
-	} else
+	} else {
+		q->limits.io_opt = 0;
 		rw_max = min_not_zero(logical_to_sectors(sdp, dev_max),
 				      (sector_t)BLK_DEF_MAX_SECTORS);
+	}
 
 	/* Do not exceed controller limit */
 	rw_max = min(rw_max, queue_max_hw_sectors(q));
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index cce757506383..9c6bf13daaee 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -689,8 +689,10 @@ sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos)
 	hp->flags = input_size;	/* structure abuse ... */
 	hp->pack_id = old_hdr.pack_id;
 	hp->usr_ptr = NULL;
-	if (__copy_from_user(cmnd, buf, cmd_size))
+	if (__copy_from_user(cmnd, buf, cmd_size)) {
+		sg_remove_request(sfp, srp);
 		return -EFAULT;
+	}
 	/*
 	 * SG_DXFER_TO_FROM_DEV is functionally equivalent to SG_DXFER_FROM_DEV,
 	 * but is is possible that the app intended SG_DXFER_TO_DEV, because there
@@ -803,8 +805,10 @@ sg_common_write(Sg_fd * sfp, Sg_request * srp,
 			"sg_common_write:  scsi opcode=0x%02x, cmd_size=%d\n",
 			(int) cmnd[0], (int) hp->cmd_len));
 
-	if (hp->dxfer_len >= SZ_256M)
+	if (hp->dxfer_len >= SZ_256M) {
+		sg_remove_request(sfp, srp);
 		return -EINVAL;
+	}
 
 	k = sg_start_req(srp, cmnd);
 	if (k) {
diff --git a/drivers/scsi/smartpqi/smartpqi.h b/drivers/scsi/smartpqi/smartpqi.h
index e8e768849c70..2cc9c858beee 100644
--- a/drivers/scsi/smartpqi/smartpqi.h
+++ b/drivers/scsi/smartpqi/smartpqi.h
@@ -906,7 +906,6 @@ struct pqi_scsi_dev {
 	u8	scsi3addr[8];
 	__be64	wwid;
 	u8	volume_id[16];
-	u8	unique_id[16];
 	u8	is_physical_device : 1;
 	u8	is_external_raid_device : 1;
 	u8	is_expander_smp_device : 1;
@@ -1123,8 +1122,9 @@ struct pqi_ctrl_info {
 	struct mutex	ofa_mutex; /* serialize ofa */
 	bool		controller_online;
 	bool		block_requests;
-	bool		in_shutdown;
+	bool		block_device_reset;
 	bool		in_ofa;
+	bool		in_shutdown;
 	u8		inbound_spanning_supported : 1;
 	u8		outbound_spanning_supported : 1;
 	u8		pqi_mode_enabled : 1;
@@ -1166,6 +1166,7 @@ struct pqi_ctrl_info {
 	struct          pqi_ofa_memory *pqi_ofa_mem_virt_addr;
 	dma_addr_t      pqi_ofa_mem_dma_handle;
 	void            **pqi_ofa_chunk_virt_addr;
+	atomic_t	sync_cmds_outstanding;
 };
 
 enum pqi_ctrl_mode {
@@ -1407,6 +1408,11 @@ static inline bool pqi_ctrl_blocked(struct pqi_ctrl_info *ctrl_info)
 	return ctrl_info->block_requests;
 }
 
+static inline bool pqi_device_reset_blocked(struct pqi_ctrl_info *ctrl_info)
+{
+	return ctrl_info->block_device_reset;
+}
+
 void pqi_sas_smp_handler(struct bsg_job *job, struct Scsi_Host *shost,
 	struct sas_rphy *rphy);
 
diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index 8fd5ffc55792..55cc7ede3f6e 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -237,6 +237,11 @@ static inline void pqi_ctrl_unblock_requests(struct pqi_ctrl_info *ctrl_info)
 	scsi_unblock_requests(ctrl_info->scsi_host);
 }
 
+static inline void pqi_ctrl_block_device_reset(struct pqi_ctrl_info *ctrl_info)
+{
+	ctrl_info->block_device_reset = true;
+}
+
 static unsigned long pqi_wait_if_ctrl_blocked(struct pqi_ctrl_info *ctrl_info,
 	unsigned long timeout_msecs)
 {
@@ -319,6 +324,16 @@ static inline bool pqi_device_in_remove(struct pqi_ctrl_info *ctrl_info,
 	return device->in_remove && !ctrl_info->in_shutdown;
 }
 
+static inline void pqi_ctrl_shutdown_start(struct pqi_ctrl_info *ctrl_info)
+{
+	ctrl_info->in_shutdown = true;
+}
+
+static inline bool pqi_ctrl_in_shutdown(struct pqi_ctrl_info *ctrl_info)
+{
+	return ctrl_info->in_shutdown;
+}
+
 static inline void pqi_schedule_rescan_worker_with_delay(
 	struct pqi_ctrl_info *ctrl_info, unsigned long delay)
 {
@@ -348,6 +363,11 @@ static inline void pqi_cancel_rescan_worker(struct pqi_ctrl_info *ctrl_info)
 	cancel_delayed_work_sync(&ctrl_info->rescan_work);
 }
 
+static inline void pqi_cancel_event_worker(struct pqi_ctrl_info *ctrl_info)
+{
+	cancel_work_sync(&ctrl_info->event_work);
+}
+
 static inline u32 pqi_read_heartbeat_counter(struct pqi_ctrl_info *ctrl_info)
 {
 	if (!ctrl_info->heartbeat_counter)
@@ -607,79 +627,6 @@ static inline int pqi_scsi_inquiry(struct pqi_ctrl_info *ctrl_info,
 		buffer, buffer_length, vpd_page, NULL, NO_TIMEOUT);
 }
 
-static bool pqi_vpd_page_supported(struct pqi_ctrl_info *ctrl_info,
-	u8 *scsi3addr, u16 vpd_page)
-{
-	int rc;
-	int i;
-	int pages;
-	unsigned char *buf, bufsize;
-
-	buf = kzalloc(256, GFP_KERNEL);
-	if (!buf)
-		return false;
-
-	/* Get the size of the page list first */
-	rc = pqi_scsi_inquiry(ctrl_info, scsi3addr,
-				VPD_PAGE | SCSI_VPD_SUPPORTED_PAGES,
-				buf, SCSI_VPD_HEADER_SZ);
-	if (rc != 0)
-		goto exit_unsupported;
-
-	pages = buf[3];
-	if ((pages + SCSI_VPD_HEADER_SZ) <= 255)
-		bufsize = pages + SCSI_VPD_HEADER_SZ;
-	else
-		bufsize = 255;
-
-	/* Get the whole VPD page list */
-	rc = pqi_scsi_inquiry(ctrl_info, scsi3addr,
-				VPD_PAGE | SCSI_VPD_SUPPORTED_PAGES,
-				buf, bufsize);
-	if (rc != 0)
-		goto exit_unsupported;
-
-	pages = buf[3];
-	for (i = 1; i <= pages; i++)
-		if (buf[3 + i] == vpd_page)
-			goto exit_supported;
-
-exit_unsupported:
-	kfree(buf);
-	return false;
-
-exit_supported:
-	kfree(buf);
-	return true;
-}
-
-static int pqi_get_device_id(struct pqi_ctrl_info *ctrl_info,
-	u8 *scsi3addr, u8 *device_id, int buflen)
-{
-	int rc;
-	unsigned char *buf;
-
-	if (!pqi_vpd_page_supported(ctrl_info, scsi3addr, SCSI_VPD_DEVICE_ID))
-		return 1; /* function not supported */
-
-	buf = kzalloc(64, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	rc = pqi_scsi_inquiry(ctrl_info, scsi3addr,
-				VPD_PAGE | SCSI_VPD_DEVICE_ID,
-				buf, 64);
-	if (rc == 0) {
-		if (buflen > 16)
-			buflen = 16;
-		memcpy(device_id, &buf[SCSI_VPD_DEVICE_ID_IDX], buflen);
-	}
-
-	kfree(buf);
-
-	return rc;
-}
-
 static int pqi_identify_physical_device(struct pqi_ctrl_info *ctrl_info,
 	struct pqi_scsi_dev *device,
 	struct bmic_identify_physical_device *buffer,
@@ -1364,14 +1311,6 @@ static int pqi_get_device_info(struct pqi_ctrl_info *ctrl_info,
 		}
 	}
 
-	if (pqi_get_device_id(ctrl_info, device->scsi3addr,
-		device->unique_id, sizeof(device->unique_id)) < 0)
-		dev_warn(&ctrl_info->pci_dev->dev,
-			"Can't get device id for scsi %d:%d:%d:%d\n",
-			ctrl_info->scsi_host->host_no,
-			device->bus, device->target,
-			device->lun);
-
 out:
 	kfree(buffer);
 
@@ -4068,6 +4007,8 @@ static int pqi_submit_raid_request_synchronous(struct pqi_ctrl_info *ctrl_info,
 		goto out;
 	}
 
+	atomic_inc(&ctrl_info->sync_cmds_outstanding);
+
 	io_request = pqi_alloc_io_request(ctrl_info);
 
 	put_unaligned_le16(io_request->index,
@@ -4114,6 +4055,7 @@ static int pqi_submit_raid_request_synchronous(struct pqi_ctrl_info *ctrl_info,
 
 	pqi_free_io_request(io_request);
 
+	atomic_dec(&ctrl_info->sync_cmds_outstanding);
 out:
 	up(&ctrl_info->sync_request_sem);
 
@@ -5348,7 +5290,7 @@ static int pqi_scsi_queue_command(struct Scsi_Host *shost,
 
 	pqi_ctrl_busy(ctrl_info);
 	if (pqi_ctrl_blocked(ctrl_info) || pqi_device_in_reset(device) ||
-	    pqi_ctrl_in_ofa(ctrl_info)) {
+	    pqi_ctrl_in_ofa(ctrl_info) || pqi_ctrl_in_shutdown(ctrl_info)) {
 		rc = SCSI_MLQUEUE_HOST_BUSY;
 		goto out;
 	}
@@ -5596,6 +5538,18 @@ static int pqi_ctrl_wait_for_pending_io(struct pqi_ctrl_info *ctrl_info,
 	return 0;
 }
 
+static int pqi_ctrl_wait_for_pending_sync_cmds(struct pqi_ctrl_info *ctrl_info)
+{
+	while (atomic_read(&ctrl_info->sync_cmds_outstanding)) {
+		pqi_check_ctrl_health(ctrl_info);
+		if (pqi_ctrl_offline(ctrl_info))
+			return -ENXIO;
+		usleep_range(1000, 2000);
+	}
+
+	return 0;
+}
+
 static void pqi_lun_reset_complete(struct pqi_io_request *io_request,
 	void *context)
 {
@@ -5733,17 +5687,17 @@ static int pqi_eh_device_reset_handler(struct scsi_cmnd *scmd)
 		shost->host_no, device->bus, device->target, device->lun);
 
 	pqi_check_ctrl_health(ctrl_info);
-	if (pqi_ctrl_offline(ctrl_info)) {
-		dev_err(&ctrl_info->pci_dev->dev,
-			"controller %u offlined - cannot send device reset\n",
-			ctrl_info->ctrl_id);
+	if (pqi_ctrl_offline(ctrl_info) ||
+		pqi_device_reset_blocked(ctrl_info)) {
 		rc = FAILED;
 		goto out;
 	}
 
 	pqi_wait_until_ofa_finished(ctrl_info);
 
+	atomic_inc(&ctrl_info->sync_cmds_outstanding);
 	rc = pqi_device_reset(ctrl_info, device);
+	atomic_dec(&ctrl_info->sync_cmds_outstanding);
 
 out:
 	dev_err(&ctrl_info->pci_dev->dev,
@@ -6065,7 +6019,8 @@ static int pqi_ioctl(struct scsi_device *sdev, unsigned int cmd,
 
 	ctrl_info = shost_to_hba(sdev->host);
 
-	if (pqi_ctrl_in_ofa(ctrl_info))
+	if (pqi_ctrl_in_ofa(ctrl_info) ||
+		pqi_ctrl_in_shutdown(ctrl_info))
 		return -EBUSY;
 
 	switch (cmd) {
@@ -6179,7 +6134,7 @@ static ssize_t pqi_unique_id_show(struct device *dev,
 	struct scsi_device *sdev;
 	struct pqi_scsi_dev *device;
 	unsigned long flags;
-	unsigned char uid[16];
+	u8 unique_id[16];
 
 	sdev = to_scsi_device(dev);
 	ctrl_info = shost_to_hba(sdev->host);
@@ -6192,16 +6147,22 @@ static ssize_t pqi_unique_id_show(struct device *dev,
 			flags);
 		return -ENODEV;
 	}
-	memcpy(uid, device->unique_id, sizeof(uid));
+
+	if (device->is_physical_device) {
+		memset(unique_id, 0, 8);
+		memcpy(unique_id + 8, &device->wwid, sizeof(device->wwid));
+	} else {
+		memcpy(unique_id, device->volume_id, sizeof(device->volume_id));
+	}
 
 	spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags);
 
 	return snprintf(buffer, PAGE_SIZE,
 		"%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X\n",
-		uid[0], uid[1], uid[2], uid[3],
-		uid[4], uid[5], uid[6], uid[7],
-		uid[8], uid[9], uid[10], uid[11],
-		uid[12], uid[13], uid[14], uid[15]);
+		unique_id[0], unique_id[1], unique_id[2], unique_id[3],
+		unique_id[4], unique_id[5], unique_id[6], unique_id[7],
+		unique_id[8], unique_id[9], unique_id[10], unique_id[11],
+		unique_id[12], unique_id[13], unique_id[14], unique_id[15]);
 }
 
 static ssize_t pqi_lunid_show(struct device *dev,
@@ -6939,13 +6900,20 @@ static int pqi_force_sis_mode(struct pqi_ctrl_info *ctrl_info)
 	return pqi_revert_to_sis_mode(ctrl_info);
 }
 
+#define PQI_POST_RESET_DELAY_B4_MSGU_READY	5000
+
 static int pqi_ctrl_init(struct pqi_ctrl_info *ctrl_info)
 {
 	int rc;
 
-	rc = pqi_force_sis_mode(ctrl_info);
-	if (rc)
-		return rc;
+	if (reset_devices) {
+		sis_soft_reset(ctrl_info);
+		msleep(PQI_POST_RESET_DELAY_B4_MSGU_READY);
+	} else {
+		rc = pqi_force_sis_mode(ctrl_info);
+		if (rc)
+			return rc;
+	}
 
 	/*
 	 * Wait until the controller is ready to start accepting SIS
@@ -7372,6 +7340,7 @@ static struct pqi_ctrl_info *pqi_alloc_ctrl_info(int numa_node)
 
 	INIT_WORK(&ctrl_info->event_work, pqi_event_worker);
 	atomic_set(&ctrl_info->num_interrupts, 0);
+	atomic_set(&ctrl_info->sync_cmds_outstanding, 0);
 
 	INIT_DELAYED_WORK(&ctrl_info->rescan_work, pqi_rescan_worker);
 	INIT_DELAYED_WORK(&ctrl_info->update_time_work, pqi_update_time_worker);
@@ -7645,8 +7614,6 @@ static int pqi_ofa_host_memory_update(struct pqi_ctrl_info *ctrl_info)
 		0, NULL, NO_TIMEOUT);
 }
 
-#define PQI_POST_RESET_DELAY_B4_MSGU_READY	5000
-
 static int pqi_ofa_ctrl_restart(struct pqi_ctrl_info *ctrl_info)
 {
 	msleep(PQI_POST_RESET_DELAY_B4_MSGU_READY);
@@ -7814,28 +7781,74 @@ static void pqi_pci_remove(struct pci_dev *pci_dev)
 	pqi_remove_ctrl(ctrl_info);
 }
 
+static void pqi_crash_if_pending_command(struct pqi_ctrl_info *ctrl_info)
+{
+	unsigned int i;
+	struct pqi_io_request *io_request;
+	struct scsi_cmnd *scmd;
+
+	for (i = 0; i < ctrl_info->max_io_slots; i++) {
+		io_request = &ctrl_info->io_request_pool[i];
+		if (atomic_read(&io_request->refcount) == 0)
+			continue;
+		scmd = io_request->scmd;
+		WARN_ON(scmd != NULL); /* IO command from SML */
+		WARN_ON(scmd == NULL); /* Non-IO cmd or driver initiated*/
+	}
+}
+
 static void pqi_shutdown(struct pci_dev *pci_dev)
 {
 	int rc;
 	struct pqi_ctrl_info *ctrl_info;
 
 	ctrl_info = pci_get_drvdata(pci_dev);
-	if (!ctrl_info)
-		goto error;
+	if (!ctrl_info) {
+		dev_err(&pci_dev->dev,
+			"cache could not be flushed\n");
+		return;
+	}
+
+	pqi_disable_events(ctrl_info);
+	pqi_wait_until_ofa_finished(ctrl_info);
+	pqi_cancel_update_time_worker(ctrl_info);
+	pqi_cancel_rescan_worker(ctrl_info);
+	pqi_cancel_event_worker(ctrl_info);
+
+	pqi_ctrl_shutdown_start(ctrl_info);
+	pqi_ctrl_wait_until_quiesced(ctrl_info);
+
+	rc = pqi_ctrl_wait_for_pending_io(ctrl_info, NO_TIMEOUT);
+	if (rc) {
+		dev_err(&pci_dev->dev,
+			"wait for pending I/O failed\n");
+		return;
+	}
+
+	pqi_ctrl_block_device_reset(ctrl_info);
+	pqi_wait_until_lun_reset_finished(ctrl_info);
 
 	/*
 	 * Write all data in the controller's battery-backed cache to
 	 * storage.
 	 */
 	rc = pqi_flush_cache(ctrl_info, SHUTDOWN);
-	pqi_free_interrupts(ctrl_info);
-	pqi_reset(ctrl_info);
-	if (rc == 0)
+	if (rc)
+		dev_err(&pci_dev->dev,
+			"unable to flush controller cache\n");
+
+	pqi_ctrl_block_requests(ctrl_info);
+
+	rc = pqi_ctrl_wait_for_pending_sync_cmds(ctrl_info);
+	if (rc) {
+		dev_err(&pci_dev->dev,
+			"wait for pending sync cmds failed\n");
 		return;
+	}
+
+	pqi_crash_if_pending_command(ctrl_info);
+	pqi_reset(ctrl_info);
 
-error:
-	dev_warn(&pci_dev->dev,
-		"unable to flush controller cache\n");
 }
 
 static void pqi_process_lockup_action_param(void)
diff --git a/drivers/scsi/smartpqi/smartpqi_sas_transport.c b/drivers/scsi/smartpqi/smartpqi_sas_transport.c
index 5cca1b9ef1f1..977655d622e4 100644
--- a/drivers/scsi/smartpqi/smartpqi_sas_transport.c
+++ b/drivers/scsi/smartpqi/smartpqi_sas_transport.c
@@ -45,9 +45,9 @@ static void pqi_free_sas_phy(struct pqi_sas_phy *pqi_sas_phy)
 	struct sas_phy *phy = pqi_sas_phy->phy;
 
 	sas_port_delete_phy(pqi_sas_phy->parent_port->port, phy);
-	sas_phy_free(phy);
 	if (pqi_sas_phy->added_to_port)
 		list_del(&pqi_sas_phy->phy_list_entry);
+	sas_phy_delete(phy);
 	kfree(pqi_sas_phy);
 }
 
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index 4664fdf75c0f..70a28f6fb1d0 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -750,7 +750,7 @@ static int sr_probe(struct device *dev)
 	cd->cdi.disk = disk;
 
 	if (register_cdrom(&cd->cdi))
-		goto fail_put;
+		goto fail_minor;
 
 	/*
 	 * Initialize block layer runtime PM stuffs before the
@@ -768,6 +768,10 @@ static int sr_probe(struct device *dev)
 
 	return 0;
 
+fail_minor:
+	spin_lock(&sr_index_lock);
+	clear_bit(minor, sr_index_bits);
+	spin_unlock(&sr_index_lock);
 fail_put:
 	put_disk(disk);
 fail_free:
diff --git a/drivers/scsi/ufs/ufs-mediatek.c b/drivers/scsi/ufs/ufs-mediatek.c
index 0f6ff33ce52e..d4a8be5ffd52 100644
--- a/drivers/scsi/ufs/ufs-mediatek.c
+++ b/drivers/scsi/ufs/ufs-mediatek.c
@@ -13,6 +13,7 @@
 
 #include "ufshcd.h"
 #include "ufshcd-pltfrm.h"
+#include "ufs_quirks.h"
 #include "unipro.h"
 #include "ufs-mediatek.h"
 
@@ -286,6 +287,15 @@ static int ufs_mtk_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 	return 0;
 }
 
+static int ufs_mtk_apply_dev_quirks(struct ufs_hba *hba,
+				    struct ufs_dev_desc *card)
+{
+	if (card->wmanufacturerid == UFS_VENDOR_SAMSUNG)
+		ufshcd_dme_set(hba, UIC_ARG_MIB(PA_TACTIVATE), 6);
+
+	return 0;
+}
+
 /**
  * struct ufs_hba_mtk_vops - UFS MTK specific variant operations
  *
@@ -298,6 +308,7 @@ static struct ufs_hba_variant_ops ufs_hba_mtk_vops = {
 	.setup_clocks        = ufs_mtk_setup_clocks,
 	.link_startup_notify = ufs_mtk_link_startup_notify,
 	.pwr_change_notify   = ufs_mtk_pwr_change_notify,
+	.apply_dev_quirks    = ufs_mtk_apply_dev_quirks,
 	.suspend             = ufs_mtk_suspend,
 	.resume              = ufs_mtk_resume,
 };
diff --git a/drivers/scsi/ufs/ufs-qcom.c b/drivers/scsi/ufs/ufs-qcom.c
index b4d1b5c22987..6aa8d2fb16a9 100644
--- a/drivers/scsi/ufs/ufs-qcom.c
+++ b/drivers/scsi/ufs/ufs-qcom.c
@@ -903,7 +903,8 @@ out:
 	return err;
 }
 
-static int ufs_qcom_apply_dev_quirks(struct ufs_hba *hba)
+static int ufs_qcom_apply_dev_quirks(struct ufs_hba *hba,
+				     struct ufs_dev_desc *card)
 {
 	int err = 0;
 
@@ -1530,11 +1531,11 @@ static void ufs_qcom_dump_dbg_regs(struct ufs_hba *hba)
 
 	/* sleep a bit intermittently as we are dumping too much data */
 	ufs_qcom_print_hw_debug_reg_all(hba, NULL, ufs_qcom_dump_regs_wrapper);
-	usleep_range(1000, 1100);
+	udelay(1000);
 	ufs_qcom_testbus_read(hba);
-	usleep_range(1000, 1100);
+	udelay(1000);
 	ufs_qcom_print_unipro_testbus(hba);
-	usleep_range(1000, 1100);
+	udelay(1000);
 }
 
 /**
diff --git a/drivers/scsi/ufs/ufs_bsg.c b/drivers/scsi/ufs/ufs_bsg.c
index f0d7df41497f..5e1bbf87f482 100644
--- a/drivers/scsi/ufs/ufs_bsg.c
+++ b/drivers/scsi/ufs/ufs_bsg.c
@@ -106,8 +106,10 @@ static int ufs_bsg_request(struct bsg_job *job)
 		desc_op = bsg_request->upiu_req.qr.opcode;
 		ret = ufs_bsg_alloc_desc_buffer(hba, job, &desc_buff,
 						&desc_len, desc_op);
-		if (ret)
+		if (ret) {
+			pm_runtime_put_sync(hba->dev);
 			goto out;
+		}
 
 		/* fall through */
 	case UPIU_TRANSACTION_NOP_OUT:
@@ -200,7 +202,7 @@ int ufs_bsg_probe(struct ufs_hba *hba)
 	bsg_dev->parent = get_device(parent);
 	bsg_dev->release = ufs_bsg_node_release;
 
-	dev_set_name(bsg_dev, "ufs-bsg");
+	dev_set_name(bsg_dev, "ufs-bsg%u", shost->host_no);
 
 	ret = device_add(bsg_dev);
 	if (ret)
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 50f5f7298e65..aa7d02d8c440 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -492,8 +492,8 @@ static void ufshcd_print_tmrs(struct ufs_hba *hba, unsigned long bitmap)
 static void ufshcd_print_host_state(struct ufs_hba *hba)
 {
 	dev_err(hba->dev, "UFS Host state=%d\n", hba->ufshcd_state);
-	dev_err(hba->dev, "lrb in use=0x%lx, outstanding reqs=0x%lx tasks=0x%lx\n",
-		hba->lrb_in_use, hba->outstanding_reqs, hba->outstanding_tasks);
+	dev_err(hba->dev, "outstanding reqs=0x%lx tasks=0x%lx\n",
+		hba->outstanding_reqs, hba->outstanding_tasks);
 	dev_err(hba->dev, "saved_err=0x%x, saved_uic_err=0x%x\n",
 		hba->saved_err, hba->saved_uic_err);
 	dev_err(hba->dev, "Device power mode=%d, UIC link state=%d\n",
@@ -1268,6 +1268,24 @@ out:
 	return ret;
 }
 
+static bool ufshcd_is_busy(struct request *req, void *priv, bool reserved)
+{
+	int *busy = priv;
+
+	WARN_ON_ONCE(reserved);
+	(*busy)++;
+	return false;
+}
+
+/* Whether or not any tag is in use by a request that is in progress. */
+static bool ufshcd_any_tag_in_use(struct ufs_hba *hba)
+{
+	struct request_queue *q = hba->cmd_queue;
+	int busy = 0;
+
+	blk_mq_tagset_busy_iter(q->tag_set, ufshcd_is_busy, &busy);
+	return busy;
+}
 
 static int ufshcd_devfreq_get_dev_status(struct device *dev,
 		struct devfreq_dev_status *stat)
@@ -1537,6 +1555,11 @@ start:
 		 */
 		if (ufshcd_can_hibern8_during_gating(hba) &&
 		    ufshcd_is_link_hibern8(hba)) {
+			if (async) {
+				rc = -EAGAIN;
+				hba->clk_gating.active_reqs--;
+				break;
+			}
 			spin_unlock_irqrestore(hba->host->host_lock, flags);
 			flush_work(&hba->clk_gating.ungate_work);
 			spin_lock_irqsave(hba->host->host_lock, flags);
@@ -1614,7 +1637,7 @@ static void ufshcd_gate_work(struct work_struct *work)
 
 	if (hba->clk_gating.active_reqs
 		|| hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL
-		|| hba->lrb_in_use || hba->outstanding_tasks
+		|| ufshcd_any_tag_in_use(hba) || hba->outstanding_tasks
 		|| hba->active_uic_cmd || hba->uic_async_done)
 		goto rel_lock;
 
@@ -1668,7 +1691,7 @@ static void __ufshcd_release(struct ufs_hba *hba)
 
 	if (hba->clk_gating.active_reqs || hba->clk_gating.is_suspended
 		|| hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL
-		|| hba->lrb_in_use || hba->outstanding_tasks
+		|| ufshcd_any_tag_in_use(hba) || hba->outstanding_tasks
 		|| hba->active_uic_cmd || hba->uic_async_done
 		|| ufshcd_eh_in_progress(hba))
 		return;
@@ -2438,22 +2461,9 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 
 	hba->req_abort_count = 0;
 
-	/* acquire the tag to make sure device cmds don't use it */
-	if (test_and_set_bit_lock(tag, &hba->lrb_in_use)) {
-		/*
-		 * Dev manage command in progress, requeue the command.
-		 * Requeuing the command helps in cases where the request *may*
-		 * find different tag instead of waiting for dev manage command
-		 * completion.
-		 */
-		err = SCSI_MLQUEUE_HOST_BUSY;
-		goto out;
-	}
-
 	err = ufshcd_hold(hba, true);
 	if (err) {
 		err = SCSI_MLQUEUE_HOST_BUSY;
-		clear_bit_unlock(tag, &hba->lrb_in_use);
 		goto out;
 	}
 	WARN_ON(hba->clk_gating.state != CLKS_ON);
@@ -2474,7 +2484,7 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 	err = ufshcd_map_sg(hba, lrbp);
 	if (err) {
 		lrbp->cmd = NULL;
-		clear_bit_unlock(tag, &hba->lrb_in_use);
+		ufshcd_release(hba);
 		goto out;
 	}
 	/* Make sure descriptors are ready before ringing the doorbell */
@@ -2622,44 +2632,6 @@ static int ufshcd_wait_for_dev_cmd(struct ufs_hba *hba,
 }
 
 /**
- * ufshcd_get_dev_cmd_tag - Get device management command tag
- * @hba: per-adapter instance
- * @tag_out: pointer to variable with available slot value
- *
- * Get a free slot and lock it until device management command
- * completes.
- *
- * Returns false if free slot is unavailable for locking, else
- * return true with tag value in @tag.
- */
-static bool ufshcd_get_dev_cmd_tag(struct ufs_hba *hba, int *tag_out)
-{
-	int tag;
-	bool ret = false;
-	unsigned long tmp;
-
-	if (!tag_out)
-		goto out;
-
-	do {
-		tmp = ~hba->lrb_in_use;
-		tag = find_last_bit(&tmp, hba->nutrs);
-		if (tag >= hba->nutrs)
-			goto out;
-	} while (test_and_set_bit_lock(tag, &hba->lrb_in_use));
-
-	*tag_out = tag;
-	ret = true;
-out:
-	return ret;
-}
-
-static inline void ufshcd_put_dev_cmd_tag(struct ufs_hba *hba, int tag)
-{
-	clear_bit_unlock(tag, &hba->lrb_in_use);
-}
-
-/**
  * ufshcd_exec_dev_cmd - API for sending device management requests
  * @hba: UFS hba
  * @cmd_type: specifies the type (NOP, Query...)
@@ -2671,6 +2643,8 @@ static inline void ufshcd_put_dev_cmd_tag(struct ufs_hba *hba, int tag)
 static int ufshcd_exec_dev_cmd(struct ufs_hba *hba,
 		enum dev_cmd_type cmd_type, int timeout)
 {
+	struct request_queue *q = hba->cmd_queue;
+	struct request *req;
 	struct ufshcd_lrb *lrbp;
 	int err;
 	int tag;
@@ -2684,7 +2658,11 @@ static int ufshcd_exec_dev_cmd(struct ufs_hba *hba,
 	 * Even though we use wait_event() which sleeps indefinitely,
 	 * the maximum wait time is bounded by SCSI request timeout.
 	 */
-	wait_event(hba->dev_cmd.tag_wq, ufshcd_get_dev_cmd_tag(hba, &tag));
+	req = blk_get_request(q, REQ_OP_DRV_OUT, 0);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+	tag = req->tag;
+	WARN_ON_ONCE(!ufshcd_valid_tag(hba, tag));
 
 	init_completion(&wait);
 	lrbp = &hba->lrb[tag];
@@ -2709,8 +2687,7 @@ static int ufshcd_exec_dev_cmd(struct ufs_hba *hba,
 			err ? "query_complete_err" : "query_complete");
 
 out_put_tag:
-	ufshcd_put_dev_cmd_tag(hba, tag);
-	wake_up(&hba->dev_cmd.tag_wq);
+	blk_put_request(req);
 	up_read(&hba->clk_scaling_lock);
 	return err;
 }
@@ -4743,7 +4720,7 @@ ufshcd_transfer_rsp_status(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
 		break;
 	} /* end of switch */
 
-	if (host_byte(result) != DID_OK)
+	if ((host_byte(result) != DID_OK) && !hba->silence_err_logs)
 		ufshcd_print_trs(hba, 1 << lrbp->task_tag, true);
 	return result;
 }
@@ -4790,7 +4767,6 @@ static void __ufshcd_transfer_req_compl(struct ufs_hba *hba,
 			cmd->result = result;
 			/* Mark completed command as NULL in LRB */
 			lrbp->cmd = NULL;
-			clear_bit_unlock(index, &hba->lrb_in_use);
 			/* Do not touch lrbp after scsi done */
 			cmd->scsi_done(cmd);
 			__ufshcd_release(hba);
@@ -4812,9 +4788,6 @@ static void __ufshcd_transfer_req_compl(struct ufs_hba *hba,
 	hba->outstanding_reqs ^= completed_reqs;
 
 	ufshcd_clk_scaling_update_busy(hba);
-
-	/* we might have free'd some tags above */
-	wake_up(&hba->dev_cmd.tag_wq);
 }
 
 /**
@@ -4978,6 +4951,7 @@ static int ufshcd_disable_auto_bkops(struct ufs_hba *hba)
 
 	hba->auto_bkops_enabled = false;
 	trace_ufshcd_auto_bkops_state(dev_name(hba->dev), "Disabled");
+	hba->is_urgent_bkops_lvl_checked = false;
 out:
 	return err;
 }
@@ -5002,6 +4976,7 @@ static void ufshcd_force_reset_auto_bkops(struct ufs_hba *hba)
 		hba->ee_ctrl_mask &= ~MASK_EE_URGENT_BKOPS;
 		ufshcd_disable_auto_bkops(hba);
 	}
+	hba->is_urgent_bkops_lvl_checked = false;
 }
 
 static inline int ufshcd_get_bkops_status(struct ufs_hba *hba, u32 *status)
@@ -5272,8 +5247,8 @@ static void ufshcd_err_handler(struct work_struct *work)
 
 	/*
 	 * if host reset is required then skip clearing the pending
-	 * transfers forcefully because they will automatically get
-	 * cleared after link startup.
+	 * transfers forcefully because they will get cleared during
+	 * host reset and restore
 	 */
 	if (needs_reset)
 		goto skip_pending_xfer_clear;
@@ -5717,6 +5692,8 @@ static int ufshcd_issue_devman_upiu_cmd(struct ufs_hba *hba,
 					int cmd_type,
 					enum query_opcode desc_op)
 {
+	struct request_queue *q = hba->cmd_queue;
+	struct request *req;
 	struct ufshcd_lrb *lrbp;
 	int err = 0;
 	int tag;
@@ -5726,7 +5703,11 @@ static int ufshcd_issue_devman_upiu_cmd(struct ufs_hba *hba,
 
 	down_read(&hba->clk_scaling_lock);
 
-	wait_event(hba->dev_cmd.tag_wq, ufshcd_get_dev_cmd_tag(hba, &tag));
+	req = blk_get_request(q, REQ_OP_DRV_OUT, 0);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+	tag = req->tag;
+	WARN_ON_ONCE(!ufshcd_valid_tag(hba, tag));
 
 	init_completion(&wait);
 	lrbp = &hba->lrb[tag];
@@ -5800,8 +5781,7 @@ static int ufshcd_issue_devman_upiu_cmd(struct ufs_hba *hba,
 		}
 	}
 
-	ufshcd_put_dev_cmd_tag(hba, tag);
-	wake_up(&hba->dev_cmd.tag_wq);
+	blk_put_request(req);
 	up_read(&hba->clk_scaling_lock);
 	return err;
 }
@@ -6094,9 +6074,6 @@ static int ufshcd_abort(struct scsi_cmnd *cmd)
 	hba->lrb[tag].cmd = NULL;
 	spin_unlock_irqrestore(host->host_lock, flags);
 
-	clear_bit_unlock(tag, &hba->lrb_in_use);
-	wake_up(&hba->dev_cmd.tag_wq);
-
 out:
 	if (!err) {
 		err = SUCCESS;
@@ -6129,9 +6106,15 @@ static int ufshcd_host_reset_and_restore(struct ufs_hba *hba)
 	int err;
 	unsigned long flags;
 
-	/* Reset the host controller */
+	/*
+	 * Stop the host controller and complete the requests
+	 * cleared by h/w
+	 */
 	spin_lock_irqsave(hba->host->host_lock, flags);
 	ufshcd_hba_stop(hba, false);
+	hba->silence_err_logs = true;
+	ufshcd_complete_requests(hba);
+	hba->silence_err_logs = false;
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 
 	/* scale up clocks to max frequency before full reinitialization */
@@ -6165,22 +6148,15 @@ out:
 static int ufshcd_reset_and_restore(struct ufs_hba *hba)
 {
 	int err = 0;
-	unsigned long flags;
 	int retries = MAX_HOST_RESET_RETRIES;
 
 	do {
+		/* Reset the attached device */
+		ufshcd_vops_device_reset(hba);
+
 		err = ufshcd_host_reset_and_restore(hba);
 	} while (err && --retries);
 
-	/*
-	 * After reset the door-bell might be cleared, complete
-	 * outstanding requests in s/w here.
-	 */
-	spin_lock_irqsave(hba->host->host_lock, flags);
-	ufshcd_transfer_req_compl(hba);
-	ufshcd_tmc_handler(hba);
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
-
 	return err;
 }
 
@@ -6642,7 +6618,8 @@ out:
 	return ret;
 }
 
-static void ufshcd_tune_unipro_params(struct ufs_hba *hba)
+static void ufshcd_tune_unipro_params(struct ufs_hba *hba,
+				      struct ufs_dev_desc *card)
 {
 	if (ufshcd_is_unipro_pa_params_tuning_req(hba)) {
 		ufshcd_tune_pa_tactivate(hba);
@@ -6656,7 +6633,7 @@ static void ufshcd_tune_unipro_params(struct ufs_hba *hba)
 	if (hba->dev_quirks & UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE)
 		ufshcd_quirk_tune_host_pa_tactivate(hba);
 
-	ufshcd_vops_apply_dev_quirks(hba);
+	ufshcd_vops_apply_dev_quirks(hba, card);
 }
 
 static void ufshcd_clear_dbg_ufs_stats(struct ufs_hba *hba)
@@ -6708,23 +6685,13 @@ static void ufshcd_init_desc_sizes(struct ufs_hba *hba)
 		&hba->desc_size.geom_desc);
 	if (err)
 		hba->desc_size.geom_desc = QUERY_DESC_GEOMETRY_DEF_SIZE;
+
 	err = ufshcd_read_desc_length(hba, QUERY_DESC_IDN_HEALTH, 0,
 		&hba->desc_size.hlth_desc);
 	if (err)
 		hba->desc_size.hlth_desc = QUERY_DESC_HEALTH_DEF_SIZE;
 }
 
-static void ufshcd_def_desc_sizes(struct ufs_hba *hba)
-{
-	hba->desc_size.dev_desc = QUERY_DESC_DEVICE_DEF_SIZE;
-	hba->desc_size.pwr_desc = QUERY_DESC_POWER_DEF_SIZE;
-	hba->desc_size.interc_desc = QUERY_DESC_INTERCONNECT_DEF_SIZE;
-	hba->desc_size.conf_desc = QUERY_DESC_CONFIGURATION_DEF_SIZE;
-	hba->desc_size.unit_desc = QUERY_DESC_UNIT_DEF_SIZE;
-	hba->desc_size.geom_desc = QUERY_DESC_GEOMETRY_DEF_SIZE;
-	hba->desc_size.hlth_desc = QUERY_DESC_HEALTH_DEF_SIZE;
-}
-
 static struct ufs_ref_clk ufs_ref_clk_freqs[] = {
 	{19200000, REF_CLK_FREQ_19_2_MHZ},
 	{26000000, REF_CLK_FREQ_26_MHZ},
@@ -6838,7 +6805,7 @@ static int ufshcd_probe_hba(struct ufs_hba *hba)
 	}
 
 	ufs_fixup_device_setup(hba, &card);
-	ufshcd_tune_unipro_params(hba);
+	ufshcd_tune_unipro_params(hba, &card);
 
 	/* UFS device is also active now */
 	ufshcd_set_ufs_dev_active(hba);
@@ -6887,7 +6854,8 @@ static int ufshcd_probe_hba(struct ufs_hba *hba)
 			ufshcd_init_icc_levels(hba);
 
 		/* Add required well known logical units to scsi mid layer */
-		if (ufshcd_scsi_add_wlus(hba))
+		ret = ufshcd_scsi_add_wlus(hba);
+		if (ret)
 			goto out;
 
 		/* Initialize devfreq after UFS device is detected */
@@ -8104,6 +8072,7 @@ void ufshcd_remove(struct ufs_hba *hba)
 {
 	ufs_bsg_remove(hba);
 	ufs_sysfs_remove_nodes(hba->dev);
+	blk_cleanup_queue(hba->cmd_queue);
 	scsi_remove_host(hba->host);
 	/* disable interrupts */
 	ufshcd_disable_intr(hba, hba->intr_mask);
@@ -8205,9 +8174,6 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	hba->mmio_base = mmio_base;
 	hba->irq = irq;
 
-	/* Set descriptor lengths to specification defaults */
-	ufshcd_def_desc_sizes(hba);
-
 	err = ufshcd_hba_init(hba);
 	if (err)
 		goto out_error;
@@ -8270,9 +8236,6 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 
 	init_rwsem(&hba->clk_scaling_lock);
 
-	/* Initialize device management tag acquire wait queue */
-	init_waitqueue_head(&hba->dev_cmd.tag_wq);
-
 	ufshcd_init_clk_gating(hba);
 
 	ufshcd_init_clk_scaling(hba);
@@ -8306,13 +8269,22 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 		goto exit_gating;
 	}
 
+	hba->cmd_queue = blk_mq_init_queue(&hba->host->tag_set);
+	if (IS_ERR(hba->cmd_queue)) {
+		err = PTR_ERR(hba->cmd_queue);
+		goto out_remove_scsi_host;
+	}
+
+	/* Reset the attached device */
+	ufshcd_vops_device_reset(hba);
+
 	/* Host controller enable */
 	err = ufshcd_hba_enable(hba);
 	if (err) {
 		dev_err(hba->dev, "Host controller enable failed\n");
 		ufshcd_print_host_regs(hba);
 		ufshcd_print_host_state(hba);
-		goto out_remove_scsi_host;
+		goto free_cmd_queue;
 	}
 
 	/*
@@ -8349,6 +8321,8 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 
 	return 0;
 
+free_cmd_queue:
+	blk_cleanup_queue(hba->cmd_queue);
 out_remove_scsi_host:
 	scsi_remove_host(hba->host);
 exit_gating:
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index 3e815fe3af67..32a0ea443406 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -212,13 +212,11 @@ struct ufs_query {
  * @type: device management command type - Query, NOP OUT
  * @lock: lock to allow one command at a time
  * @complete: internal commands completion
- * @tag_wq: wait queue until free command slot is available
  */
 struct ufs_dev_cmd {
 	enum dev_cmd_type type;
 	struct mutex lock;
 	struct completion *complete;
-	wait_queue_head_t tag_wq;
 	struct ufs_query query;
 };
 
@@ -298,6 +296,7 @@ struct ufs_pwr_mode_info {
  * @resume: called during host controller PM callback
  * @dbg_register_dump: used to dump controller debug information
  * @phy_initialization: used to initialize phys
+ * @device_reset: called to issue a reset pulse on the UFS device
  */
 struct ufs_hba_variant_ops {
 	const char *name;
@@ -321,11 +320,12 @@ struct ufs_hba_variant_ops {
 	void	(*setup_task_mgmt)(struct ufs_hba *, int, u8);
 	void    (*hibern8_notify)(struct ufs_hba *, enum uic_cmd_dme,
 					enum ufs_notify_change_status);
-	int	(*apply_dev_quirks)(struct ufs_hba *);
+	int	(*apply_dev_quirks)(struct ufs_hba *, struct ufs_dev_desc *);
 	int     (*suspend)(struct ufs_hba *, enum ufs_pm_op);
 	int     (*resume)(struct ufs_hba *, enum ufs_pm_op);
 	void	(*dbg_register_dump)(struct ufs_hba *hba);
 	int	(*phy_initialization)(struct ufs_hba *);
+	void	(*device_reset)(struct ufs_hba *hba);
 };
 
 /* clock gating state  */
@@ -459,7 +459,7 @@ struct ufs_stats {
  * @host: Scsi_Host instance of the driver
  * @dev: device handle
  * @lrb: local reference block
- * @lrb_in_use: lrb in use
+ * @cmd_queue: Used to allocate command tags from hba->host->tag_set.
  * @outstanding_tasks: Bits representing outstanding task requests
  * @outstanding_reqs: Bits representing outstanding transfer requests
  * @capabilities: UFS Controller Capabilities
@@ -489,6 +489,7 @@ struct ufs_stats {
  * @uic_error: UFS interconnect layer error status
  * @saved_err: sticky error mask
  * @saved_uic_err: sticky UIC error mask
+ * @silence_err_logs: flag to silence error logs
  * @dev_cmd: ufs device management command information
  * @last_dme_cmd_tstamp: time stamp of the last completed DME command
  * @auto_bkops_enabled: to track whether bkops is enabled in device
@@ -517,6 +518,7 @@ struct ufs_hba {
 
 	struct Scsi_Host *host;
 	struct device *dev;
+	struct request_queue *cmd_queue;
 	/*
 	 * This field is to keep a reference to "scsi_device" corresponding to
 	 * "UFS device" W-LU.
@@ -537,7 +539,6 @@ struct ufs_hba {
 	u32 ahit;
 
 	struct ufshcd_lrb *lrb;
-	unsigned long lrb_in_use;
 
 	unsigned long outstanding_tasks;
 	unsigned long outstanding_reqs;
@@ -646,6 +647,7 @@ struct ufs_hba {
 	u32 saved_err;
 	u32 saved_uic_err;
 	struct ufs_stats ufs_stats;
+	bool silence_err_logs;
 
 	/* Device management request data */
 	struct ufs_dev_cmd dev_cmd;
@@ -1012,10 +1014,11 @@ static inline void ufshcd_vops_hibern8_notify(struct ufs_hba *hba,
 		return hba->vops->hibern8_notify(hba, cmd, status);
 }
 
-static inline int ufshcd_vops_apply_dev_quirks(struct ufs_hba *hba)
+static inline int ufshcd_vops_apply_dev_quirks(struct ufs_hba *hba,
+					       struct ufs_dev_desc *card)
 {
 	if (hba->vops && hba->vops->apply_dev_quirks)
-		return hba->vops->apply_dev_quirks(hba);
+		return hba->vops->apply_dev_quirks(hba, card);
 	return 0;
 }
 
@@ -1041,6 +1044,12 @@ static inline void ufshcd_vops_dbg_register_dump(struct ufs_hba *hba)
 		hba->vops->dbg_register_dump(hba);
 }
 
+static inline void ufshcd_vops_device_reset(struct ufs_hba *hba)
+{
+	if (hba->vops && hba->vops->device_reset)
+		hba->vops->device_reset(hba);
+}
+
 extern struct ufs_pm_lvl_states ufs_pm_lvl_states[];
 
 /*
diff --git a/drivers/slimbus/core.c b/drivers/slimbus/core.c
index b2f07d2043eb..bdfbe64b4641 100644
--- a/drivers/slimbus/core.c
+++ b/drivers/slimbus/core.c
@@ -288,6 +288,7 @@ EXPORT_SYMBOL_GPL(slim_register_controller);
 /* slim_remove_device: Remove the effect of slim_add_device() */
 static void slim_remove_device(struct slim_device *sbdev)
 {
+	of_node_put(sbdev->dev.of_node);
 	device_unregister(&sbdev->dev);
 }
 
diff --git a/drivers/slimbus/qcom-ngd-ctrl.c b/drivers/slimbus/qcom-ngd-ctrl.c
index f3585777324c..34c1d4e73518 100644
--- a/drivers/slimbus/qcom-ngd-ctrl.c
+++ b/drivers/slimbus/qcom-ngd-ctrl.c
@@ -1351,7 +1351,6 @@ static int of_qcom_slim_ngd_register(struct device *parent,
 		ngd->pdev->driver_override = QCOM_SLIM_NGD_DRV_NAME;
 		ngd->pdev->dev.of_node = node;
 		ctrl->ngd = ngd;
-		platform_set_drvdata(ngd->pdev, ctrl);
 
 		platform_device_add(ngd->pdev);
 		ngd->base = ctrl->base + ngd->id * data->offset +
@@ -1366,12 +1365,13 @@ static int of_qcom_slim_ngd_register(struct device *parent,
 
 static int qcom_slim_ngd_probe(struct platform_device *pdev)
 {
-	struct qcom_slim_ngd_ctrl *ctrl = platform_get_drvdata(pdev);
 	struct device *dev = &pdev->dev;
+	struct qcom_slim_ngd_ctrl *ctrl = dev_get_drvdata(dev->parent);
 	int ret;
 
 	ctrl->ctrl.dev = dev;
 
+	platform_set_drvdata(pdev, ctrl);
 	pm_runtime_use_autosuspend(dev);
 	pm_runtime_set_autosuspend_delay(dev, QCOM_SLIM_NGD_AUTOSUSPEND);
 	pm_runtime_set_suspended(dev);
diff --git a/drivers/soc/aspeed/aspeed-lpc-snoop.c b/drivers/soc/aspeed/aspeed-lpc-snoop.c
index 48f7ac238861..f3d8d53ab84d 100644
--- a/drivers/soc/aspeed/aspeed-lpc-snoop.c
+++ b/drivers/soc/aspeed/aspeed-lpc-snoop.c
@@ -97,13 +97,13 @@ static ssize_t snoop_file_read(struct file *file, char __user *buffer,
 	return ret ? ret : copied;
 }
 
-static unsigned int snoop_file_poll(struct file *file,
+static __poll_t snoop_file_poll(struct file *file,
 				    struct poll_table_struct *pt)
 {
 	struct aspeed_lpc_snoop_channel *chan = snoop_file_to_chan(file);
 
 	poll_wait(file, &chan->wq, pt);
-	return !kfifo_is_empty(&chan->fifo) ? POLLIN : 0;
+	return !kfifo_is_empty(&chan->fifo) ? EPOLLIN : 0;
 }
 
 static const struct file_operations snoop_fops = {
diff --git a/drivers/soc/fsl/dpio/dpio-driver.c b/drivers/soc/fsl/dpio/dpio-driver.c
index c0cdc8946031..9e5346197774 100644
--- a/drivers/soc/fsl/dpio/dpio-driver.c
+++ b/drivers/soc/fsl/dpio/dpio-driver.c
@@ -224,10 +224,6 @@ static int dpaa2_dpio_probe(struct fsl_mc_device *dpio_dev)
 		goto err_allocate_irqs;
 	}
 
-	err = register_dpio_irq_handlers(dpio_dev, desc.cpu);
-	if (err)
-		goto err_register_dpio_irq;
-
 	priv->io = dpaa2_io_create(&desc, dev);
 	if (!priv->io) {
 		dev_err(dev, "dpaa2_io_create failed\n");
@@ -235,6 +231,10 @@ static int dpaa2_dpio_probe(struct fsl_mc_device *dpio_dev)
 		goto err_dpaa2_io_create;
 	}
 
+	err = register_dpio_irq_handlers(dpio_dev, desc.cpu);
+	if (err)
+		goto err_register_dpio_irq;
+
 	dev_info(dev, "probed\n");
 	dev_dbg(dev, "   receives_notifications = %d\n",
 		desc.receives_notifications);
diff --git a/drivers/soc/imx/gpc.c b/drivers/soc/imx/gpc.c
index 98b9d9a902ae..90a8b2c0676f 100644
--- a/drivers/soc/imx/gpc.c
+++ b/drivers/soc/imx/gpc.c
@@ -87,8 +87,8 @@ static int imx6_pm_domain_power_off(struct generic_pm_domain *genpd)
 static int imx6_pm_domain_power_on(struct generic_pm_domain *genpd)
 {
 	struct imx_pm_domain *pd = to_imx_pm_domain(genpd);
-	int i, ret, sw, sw2iso;
-	u32 val;
+	int i, ret;
+	u32 val, req;
 
 	if (pd->supply) {
 		ret = regulator_enable(pd->supply);
@@ -107,17 +107,18 @@ static int imx6_pm_domain_power_on(struct generic_pm_domain *genpd)
 	regmap_update_bits(pd->regmap, pd->reg_offs + GPC_PGC_CTRL_OFFS,
 			   0x1, 0x1);
 
-	/* Read ISO and ISO2SW power up delays */
-	regmap_read(pd->regmap, pd->reg_offs + GPC_PGC_PUPSCR_OFFS, &val);
-	sw = val & 0x3f;
-	sw2iso = (val >> 8) & 0x3f;
-
 	/* Request GPC to power up domain */
-	val = BIT(pd->cntr_pdn_bit + 1);
-	regmap_update_bits(pd->regmap, GPC_CNTR, val, val);
+	req = BIT(pd->cntr_pdn_bit + 1);
+	regmap_update_bits(pd->regmap, GPC_CNTR, req, req);
 
-	/* Wait ISO + ISO2SW IPG clock cycles */
-	udelay(DIV_ROUND_UP(sw + sw2iso, pd->ipg_rate_mhz));
+	/* Wait for the PGC to handle the request */
+	ret = regmap_read_poll_timeout(pd->regmap, GPC_CNTR, val, !(val & req),
+				       1, 50);
+	if (ret)
+		pr_err("powerup request on domain %s timed out\n", genpd->name);
+
+	/* Wait for reset to propagate through peripherals */
+	usleep_range(5, 10);
 
 	/* Disable reset clocks for all devices in the domain */
 	for (i = 0; i < pd->num_clks; i++)
@@ -343,6 +344,7 @@ static const struct regmap_config imx_gpc_regmap_config = {
 	.rd_table = &access_table,
 	.wr_table = &access_table,
 	.max_register = 0x2ac,
+	.fast_io = true,
 };
 
 static struct generic_pm_domain *imx_gpc_onecell_domains[] = {
diff --git a/drivers/soc/ixp4xx/Kconfig b/drivers/soc/ixp4xx/Kconfig
index de2e62c3310a..e3eb19b85fa4 100644
--- a/drivers/soc/ixp4xx/Kconfig
+++ b/drivers/soc/ixp4xx/Kconfig
@@ -1,4 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
+if ARCH_IXP4XX || COMPILE_TEST
+
 menu "IXP4xx SoC drivers"
 
 config IXP4XX_QMGR
@@ -15,3 +17,5 @@ config IXP4XX_NPE
 	  and is automatically selected by Ethernet and HSS drivers.
 
 endmenu
+
+endif
diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c
index ff9fef5a032b..c4fbd34e0dff 100644
--- a/drivers/soc/mediatek/mtk-cmdq-helper.c
+++ b/drivers/soc/mediatek/mtk-cmdq-helper.c
@@ -38,6 +38,7 @@ struct cmdq_client *cmdq_mbox_create(struct device *dev, int index, u32 timeout)
 	client->pkt_cnt = 0;
 	client->client.dev = dev;
 	client->client.tx_block = false;
+	client->client.knows_txdone = true;
 	client->chan = mbox_request_channel(&client->client, index);
 
 	if (IS_ERR(client->chan)) {
@@ -257,7 +258,9 @@ int cmdq_pkt_flush_async(struct cmdq_pkt *pkt, cmdq_async_flush_cb cb,
 		spin_unlock_irqrestore(&client->lock, flags);
 	}
 
-	mbox_send_message(client->chan, pkt);
+	err = mbox_send_message(client->chan, pkt);
+	if (err < 0)
+		return err;
 	/* We can send next packet immediately, so just call txdone. */
 	mbox_client_txdone(client->chan, 0);
 
diff --git a/drivers/soc/qcom/llcc-slice.c b/drivers/soc/qcom/llcc-slice.c
index 9090ea12eaf3..4a6111635f82 100644
--- a/drivers/soc/qcom/llcc-slice.c
+++ b/drivers/soc/qcom/llcc-slice.c
@@ -48,7 +48,7 @@
 
 static struct llcc_drv_data *drv_data = (void *) -EPROBE_DEFER;
 
-static const struct regmap_config llcc_regmap_config = {
+static struct regmap_config llcc_regmap_config = {
 	.reg_bits = 32,
 	.reg_stride = 4,
 	.val_bits = 32,
@@ -323,6 +323,7 @@ static struct regmap *qcom_llcc_init_mmio(struct platform_device *pdev,
 	if (IS_ERR(base))
 		return ERR_CAST(base);
 
+	llcc_regmap_config.name = name;
 	return devm_regmap_init_mmio(&pdev->dev, base, &llcc_regmap_config);
 }
 
diff --git a/drivers/soc/qcom/mdt_loader.c b/drivers/soc/qcom/mdt_loader.c
index 9ca7d9484de0..24cd193dec55 100644
--- a/drivers/soc/qcom/mdt_loader.c
+++ b/drivers/soc/qcom/mdt_loader.c
@@ -66,6 +66,66 @@ ssize_t qcom_mdt_get_size(const struct firmware *fw)
 }
 EXPORT_SYMBOL_GPL(qcom_mdt_get_size);
 
+/**
+ * qcom_mdt_read_metadata() - read header and metadata from mdt or mbn
+ * @fw:		firmware of mdt header or mbn
+ * @data_len:	length of the read metadata blob
+ *
+ * The mechanism that performs the authentication of the loading firmware
+ * expects an ELF header directly followed by the segment of hashes, with no
+ * padding inbetween. This function allocates a chunk of memory for this pair
+ * and copy the two pieces into the buffer.
+ *
+ * In the case of split firmware the hash is found directly following the ELF
+ * header, rather than at p_offset described by the second program header.
+ *
+ * The caller is responsible to free (kfree()) the returned pointer.
+ *
+ * Return: pointer to data, or ERR_PTR()
+ */
+void *qcom_mdt_read_metadata(const struct firmware *fw, size_t *data_len)
+{
+	const struct elf32_phdr *phdrs;
+	const struct elf32_hdr *ehdr;
+	size_t hash_offset;
+	size_t hash_size;
+	size_t ehdr_size;
+	void *data;
+
+	ehdr = (struct elf32_hdr *)fw->data;
+	phdrs = (struct elf32_phdr *)(ehdr + 1);
+
+	if (ehdr->e_phnum < 2)
+		return ERR_PTR(-EINVAL);
+
+	if (phdrs[0].p_type == PT_LOAD || phdrs[1].p_type == PT_LOAD)
+		return ERR_PTR(-EINVAL);
+
+	if ((phdrs[1].p_flags & QCOM_MDT_TYPE_MASK) != QCOM_MDT_TYPE_HASH)
+		return ERR_PTR(-EINVAL);
+
+	ehdr_size = phdrs[0].p_filesz;
+	hash_size = phdrs[1].p_filesz;
+
+	data = kmalloc(ehdr_size + hash_size, GFP_KERNEL);
+	if (!data)
+		return ERR_PTR(-ENOMEM);
+
+	/* Is the header and hash already packed */
+	if (ehdr_size + hash_size == fw->size)
+		hash_offset = phdrs[0].p_filesz;
+	else
+		hash_offset = phdrs[1].p_offset;
+
+	memcpy(data, fw->data, ehdr_size);
+	memcpy(data + ehdr_size, fw->data + hash_offset, hash_size);
+
+	*data_len = ehdr_size + hash_size;
+
+	return data;
+}
+EXPORT_SYMBOL_GPL(qcom_mdt_read_metadata);
+
 static int __qcom_mdt_load(struct device *dev, const struct firmware *fw,
 			   const char *firmware, int pas_id, void *mem_region,
 			   phys_addr_t mem_phys, size_t mem_size,
@@ -78,12 +138,14 @@ static int __qcom_mdt_load(struct device *dev, const struct firmware *fw,
 	phys_addr_t mem_reloc;
 	phys_addr_t min_addr = PHYS_ADDR_MAX;
 	phys_addr_t max_addr = 0;
+	size_t metadata_len;
 	size_t fw_name_len;
 	ssize_t offset;
+	void *metadata;
 	char *fw_name;
 	bool relocate = false;
 	void *ptr;
-	int ret;
+	int ret = 0;
 	int i;
 
 	if (!fw || !mem_region || !mem_phys || !mem_size)
@@ -101,7 +163,15 @@ static int __qcom_mdt_load(struct device *dev, const struct firmware *fw,
 		return -ENOMEM;
 
 	if (pas_init) {
-		ret = qcom_scm_pas_init_image(pas_id, fw->data, fw->size);
+		metadata = qcom_mdt_read_metadata(fw, &metadata_len);
+		if (IS_ERR(metadata)) {
+			ret = PTR_ERR(metadata);
+			goto out;
+		}
+
+		ret = qcom_scm_pas_init_image(pas_id, metadata, metadata_len);
+
+		kfree(metadata);
 		if (ret) {
 			dev_err(dev, "invalid firmware metadata\n");
 			goto out;
@@ -162,7 +232,19 @@ static int __qcom_mdt_load(struct device *dev, const struct firmware *fw,
 
 		ptr = mem_region + offset;
 
-		if (phdr->p_filesz) {
+		if (phdr->p_filesz && phdr->p_offset < fw->size) {
+			/* Firmware is large enough to be non-split */
+			if (phdr->p_offset + phdr->p_filesz > fw->size) {
+				dev_err(dev,
+					"failed to load segment %d from truncated file %s\n",
+					i, firmware);
+				ret = -EINVAL;
+				break;
+			}
+
+			memcpy(ptr, fw->data + phdr->p_offset, phdr->p_filesz);
+		} else if (phdr->p_filesz) {
+			/* Firmware not large enough, load split-out segments */
 			sprintf(fw_name + fw_name_len - 3, "b%02d", i);
 			ret = request_firmware_into_buf(&seg_fw, fw_name, dev,
 							ptr, phdr->p_filesz);
diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c
index e278fc11fe5c..8924fcd9f5f5 100644
--- a/drivers/soc/qcom/rpmh-rsc.c
+++ b/drivers/soc/qcom/rpmh-rsc.c
@@ -148,7 +148,7 @@ int rpmh_rsc_invalidate(struct rsc_drv *drv)
 static struct tcs_group *get_tcs_for_msg(struct rsc_drv *drv,
 					 const struct tcs_request *msg)
 {
-	int type, ret;
+	int type;
 	struct tcs_group *tcs;
 
 	switch (msg->state) {
@@ -169,19 +169,10 @@ static struct tcs_group *get_tcs_for_msg(struct rsc_drv *drv,
 	 * If we are making an active request on a RSC that does not have a
 	 * dedicated TCS for active state use, then re-purpose a wake TCS to
 	 * send active votes.
-	 * NOTE: The driver must be aware that this RSC does not have a
-	 * dedicated AMC, and therefore would invalidate the sleep and wake
-	 * TCSes before making an active state request.
 	 */
 	tcs = get_tcs_of_type(drv, type);
-	if (msg->state == RPMH_ACTIVE_ONLY_STATE && !tcs->num_tcs) {
+	if (msg->state == RPMH_ACTIVE_ONLY_STATE && !tcs->num_tcs)
 		tcs = get_tcs_of_type(drv, WAKE_TCS);
-		if (tcs->num_tcs) {
-			ret = rpmh_rsc_invalidate(drv);
-			if (ret)
-				return ERR_PTR(ret);
-		}
-	}
 
 	return tcs;
 }
@@ -201,6 +192,42 @@ static const struct tcs_request *get_req_from_tcs(struct rsc_drv *drv,
 	return NULL;
 }
 
+static void __tcs_set_trigger(struct rsc_drv *drv, int tcs_id, bool trigger)
+{
+	u32 enable;
+
+	/*
+	 * HW req: Clear the DRV_CONTROL and enable TCS again
+	 * While clearing ensure that the AMC mode trigger is cleared
+	 * and then the mode enable is cleared.
+	 */
+	enable = read_tcs_reg(drv, RSC_DRV_CONTROL, tcs_id, 0);
+	enable &= ~TCS_AMC_MODE_TRIGGER;
+	write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
+	enable &= ~TCS_AMC_MODE_ENABLE;
+	write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
+
+	if (trigger) {
+		/* Enable the AMC mode on the TCS and then trigger the TCS */
+		enable = TCS_AMC_MODE_ENABLE;
+		write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
+		enable |= TCS_AMC_MODE_TRIGGER;
+		write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
+	}
+}
+
+static void enable_tcs_irq(struct rsc_drv *drv, int tcs_id, bool enable)
+{
+	u32 data;
+
+	data = read_tcs_reg(drv, RSC_DRV_IRQ_ENABLE, 0, 0);
+	if (enable)
+		data |= BIT(tcs_id);
+	else
+		data &= ~BIT(tcs_id);
+	write_tcs_reg(drv, RSC_DRV_IRQ_ENABLE, 0, data);
+}
+
 /**
  * tcs_tx_done: TX Done interrupt handler
  */
@@ -237,6 +264,14 @@ static irqreturn_t tcs_tx_done(int irq, void *p)
 		}
 
 		trace_rpmh_tx_done(drv, i, req, err);
+
+		/*
+		 * If wake tcs was re-purposed for sending active
+		 * votes, clear AMC trigger & enable modes and
+		 * disable interrupt for this TCS
+		 */
+		if (!drv->tcs[ACTIVE_TCS].num_tcs)
+			__tcs_set_trigger(drv, i, false);
 skip:
 		/* Reclaim the TCS */
 		write_tcs_reg(drv, RSC_DRV_CMD_ENABLE, i, 0);
@@ -244,6 +279,13 @@ skip:
 		write_tcs_reg(drv, RSC_DRV_IRQ_CLEAR, 0, BIT(i));
 		spin_lock(&drv->lock);
 		clear_bit(i, drv->tcs_in_use);
+		/*
+		 * Disable interrupt for WAKE TCS to avoid being
+		 * spammed with interrupts coming when the solver
+		 * sends its wake votes.
+		 */
+		if (!drv->tcs[ACTIVE_TCS].num_tcs)
+			enable_tcs_irq(drv, i, false);
 		spin_unlock(&drv->lock);
 		if (req)
 			rpmh_tx_done(req, err);
@@ -285,28 +327,6 @@ static void __tcs_buffer_write(struct rsc_drv *drv, int tcs_id, int cmd_id,
 	write_tcs_reg(drv, RSC_DRV_CMD_ENABLE, tcs_id, cmd_enable);
 }
 
-static void __tcs_trigger(struct rsc_drv *drv, int tcs_id)
-{
-	u32 enable;
-
-	/*
-	 * HW req: Clear the DRV_CONTROL and enable TCS again
-	 * While clearing ensure that the AMC mode trigger is cleared
-	 * and then the mode enable is cleared.
-	 */
-	enable = read_tcs_reg(drv, RSC_DRV_CONTROL, tcs_id, 0);
-	enable &= ~TCS_AMC_MODE_TRIGGER;
-	write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
-	enable &= ~TCS_AMC_MODE_ENABLE;
-	write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
-
-	/* Enable the AMC mode on the TCS and then trigger the TCS */
-	enable = TCS_AMC_MODE_ENABLE;
-	write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
-	enable |= TCS_AMC_MODE_TRIGGER;
-	write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
-}
-
 static int check_for_req_inflight(struct rsc_drv *drv, struct tcs_group *tcs,
 				  const struct tcs_request *msg)
 {
@@ -377,10 +397,20 @@ static int tcs_write(struct rsc_drv *drv, const struct tcs_request *msg)
 
 	tcs->req[tcs_id - tcs->offset] = msg;
 	set_bit(tcs_id, drv->tcs_in_use);
+	if (msg->state == RPMH_ACTIVE_ONLY_STATE && tcs->type != ACTIVE_TCS) {
+		/*
+		 * Clear previously programmed WAKE commands in selected
+		 * repurposed TCS to avoid triggering them. tcs->slots will be
+		 * cleaned from rpmh_flush() by invoking rpmh_rsc_invalidate()
+		 */
+		write_tcs_reg_sync(drv, RSC_DRV_CMD_ENABLE, tcs_id, 0);
+		write_tcs_reg_sync(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, tcs_id, 0);
+		enable_tcs_irq(drv, tcs_id, true);
+	}
 	spin_unlock(&drv->lock);
 
 	__tcs_buffer_write(drv, tcs_id, 0, msg);
-	__tcs_trigger(drv, tcs_id);
+	__tcs_set_trigger(drv, tcs_id, true);
 
 done_write:
 	spin_unlock_irqrestore(&tcs->lock, flags);
@@ -685,6 +715,7 @@ static struct platform_driver rpmh_driver = {
 	.driver = {
 		  .name = "rpmh",
 		  .of_match_table = rpmh_drv_match,
+		  .suppress_bind_attrs = true,
 	},
 };
 
diff --git a/drivers/soc/qcom/rpmh.c b/drivers/soc/qcom/rpmh.c
index 035091fd44b8..13e1b450f296 100644
--- a/drivers/soc/qcom/rpmh.c
+++ b/drivers/soc/qcom/rpmh.c
@@ -119,6 +119,7 @@ static struct cache_req *cache_rpm_request(struct rpmh_ctrlr *ctrlr,
 {
 	struct cache_req *req;
 	unsigned long flags;
+	u32 old_sleep_val, old_wake_val;
 
 	spin_lock_irqsave(&ctrlr->cache_lock, flags);
 	req = __find_req(ctrlr, cmd->addr);
@@ -133,26 +134,27 @@ static struct cache_req *cache_rpm_request(struct rpmh_ctrlr *ctrlr,
 
 	req->addr = cmd->addr;
 	req->sleep_val = req->wake_val = UINT_MAX;
-	INIT_LIST_HEAD(&req->list);
 	list_add_tail(&req->list, &ctrlr->cache);
 
 existing:
+	old_sleep_val = req->sleep_val;
+	old_wake_val = req->wake_val;
+
 	switch (state) {
 	case RPMH_ACTIVE_ONLY_STATE:
-		if (req->sleep_val != UINT_MAX)
-			req->wake_val = cmd->data;
-		break;
 	case RPMH_WAKE_ONLY_STATE:
 		req->wake_val = cmd->data;
 		break;
 	case RPMH_SLEEP_STATE:
 		req->sleep_val = cmd->data;
 		break;
-	default:
-		break;
 	}
 
-	ctrlr->dirty = true;
+	ctrlr->dirty |= (req->sleep_val != old_sleep_val ||
+			 req->wake_val != old_wake_val) &&
+			 req->sleep_val != UINT_MAX &&
+			 req->wake_val != UINT_MAX;
+
 unlock:
 	spin_unlock_irqrestore(&ctrlr->cache_lock, flags);
 
@@ -287,6 +289,7 @@ static void cache_batch(struct rpmh_ctrlr *ctrlr, struct batch_cache_req *req)
 
 	spin_lock_irqsave(&ctrlr->cache_lock, flags);
 	list_add_tail(&req->list, &ctrlr->batch_cache);
+	ctrlr->dirty = true;
 	spin_unlock_irqrestore(&ctrlr->cache_lock, flags);
 }
 
@@ -314,18 +317,6 @@ static int flush_batch(struct rpmh_ctrlr *ctrlr)
 	return ret;
 }
 
-static void invalidate_batch(struct rpmh_ctrlr *ctrlr)
-{
-	struct batch_cache_req *req, *tmp;
-	unsigned long flags;
-
-	spin_lock_irqsave(&ctrlr->cache_lock, flags);
-	list_for_each_entry_safe(req, tmp, &ctrlr->batch_cache, list)
-		kfree(req);
-	INIT_LIST_HEAD(&ctrlr->batch_cache);
-	spin_unlock_irqrestore(&ctrlr->cache_lock, flags);
-}
-
 /**
  * rpmh_write_batch: Write multiple sets of RPMH commands and wait for the
  * batch to finish.
@@ -465,6 +456,13 @@ int rpmh_flush(const struct device *dev)
 		return 0;
 	}
 
+	/* Invalidate the TCSes first to avoid stale data */
+	do {
+		ret = rpmh_rsc_invalidate(ctrlr_to_drv(ctrlr));
+	} while (ret == -EAGAIN);
+	if (ret)
+		return ret;
+
 	/* First flush the cached batch requests */
 	ret = flush_batch(ctrlr);
 	if (ret)
@@ -496,25 +494,25 @@ int rpmh_flush(const struct device *dev)
 EXPORT_SYMBOL(rpmh_flush);
 
 /**
- * rpmh_invalidate: Invalidate all sleep and active sets
- * sets.
+ * rpmh_invalidate: Invalidate sleep and wake sets in batch_cache
  *
  * @dev: The device making the request
  *
- * Invalidate the sleep and active values in the TCS blocks.
+ * Invalidate the sleep and wake values in batch_cache.
  */
 int rpmh_invalidate(const struct device *dev)
 {
 	struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev);
-	int ret;
+	struct batch_cache_req *req, *tmp;
+	unsigned long flags;
 
-	invalidate_batch(ctrlr);
+	spin_lock_irqsave(&ctrlr->cache_lock, flags);
+	list_for_each_entry_safe(req, tmp, &ctrlr->batch_cache, list)
+		kfree(req);
+	INIT_LIST_HEAD(&ctrlr->batch_cache);
 	ctrlr->dirty = true;
+	spin_unlock_irqrestore(&ctrlr->cache_lock, flags);
 
-	do {
-		ret = rpmh_rsc_invalidate(ctrlr_to_drv(ctrlr));
-	} while (ret == -EAGAIN);
-
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL(rpmh_invalidate);
diff --git a/drivers/soc/qcom/rpmhpd.c b/drivers/soc/qcom/rpmhpd.c
index 5741ec3fa814..51850cc68b70 100644
--- a/drivers/soc/qcom/rpmhpd.c
+++ b/drivers/soc/qcom/rpmhpd.c
@@ -93,6 +93,7 @@ static struct rpmhpd sdm845_mx = {
 
 static struct rpmhpd sdm845_mx_ao = {
 	.pd = { .name = "mx_ao", },
+	.active_only = true,
 	.peer = &sdm845_mx,
 	.res_name = "mx.lvl",
 };
@@ -107,6 +108,7 @@ static struct rpmhpd sdm845_cx = {
 
 static struct rpmhpd sdm845_cx_ao = {
 	.pd = { .name = "cx_ao", },
+	.active_only = true,
 	.peer = &sdm845_cx,
 	.parent = &sdm845_mx_ao.pd,
 	.res_name = "cx.lvl",
diff --git a/drivers/soc/renesas/renesas-soc.c b/drivers/soc/renesas/renesas-soc.c
index 3299cf5365f3..6651755e9f20 100644
--- a/drivers/soc/renesas/renesas-soc.c
+++ b/drivers/soc/renesas/renesas-soc.c
@@ -326,7 +326,7 @@ static int __init renesas_soc_init(void)
 	if (np) {
 		chipid = of_iomap(np, 0);
 		of_node_put(np);
-	} else if (soc->id) {
+	} else if (soc->id && family->reg) {
 		chipid = ioremap(family->reg, 4);
 	}
 	if (chipid) {
diff --git a/drivers/soc/tegra/Kconfig b/drivers/soc/tegra/Kconfig
index fbfce48ffb0d..32351b13daa9 100644
--- a/drivers/soc/tegra/Kconfig
+++ b/drivers/soc/tegra/Kconfig
@@ -129,6 +129,7 @@ config SOC_TEGRA_FLOWCTRL
 
 config SOC_TEGRA_PMC
 	bool
+	select GENERIC_PINCONF
 
 config SOC_TEGRA_POWERGATE_BPMP
 	def_bool y
diff --git a/drivers/soc/tegra/fuse/fuse-tegra30.c b/drivers/soc/tegra/fuse/fuse-tegra30.c
index be9424a87173..9c3ef0a02fd4 100644
--- a/drivers/soc/tegra/fuse/fuse-tegra30.c
+++ b/drivers/soc/tegra/fuse/fuse-tegra30.c
@@ -35,7 +35,8 @@
     defined(CONFIG_ARCH_TEGRA_124_SOC) || \
     defined(CONFIG_ARCH_TEGRA_132_SOC) || \
     defined(CONFIG_ARCH_TEGRA_210_SOC) || \
-    defined(CONFIG_ARCH_TEGRA_186_SOC)
+    defined(CONFIG_ARCH_TEGRA_186_SOC) || \
+    defined(CONFIG_ARCH_TEGRA_194_SOC)
 static u32 tegra30_fuse_read_early(struct tegra_fuse *fuse, unsigned int offset)
 {
 	if (WARN_ON(!fuse->base))
diff --git a/drivers/soc/tegra/fuse/tegra-apbmisc.c b/drivers/soc/tegra/fuse/tegra-apbmisc.c
index df76778af601..f8b9c4058926 100644
--- a/drivers/soc/tegra/fuse/tegra-apbmisc.c
+++ b/drivers/soc/tegra/fuse/tegra-apbmisc.c
@@ -123,7 +123,7 @@ void __init tegra_init_apbmisc(void)
 			apbmisc.flags = IORESOURCE_MEM;
 
 			/* strapping options */
-			if (tegra_get_chip_id() == TEGRA124) {
+			if (of_machine_is_compatible("nvidia,tegra124")) {
 				straps.start = 0x7000e864;
 				straps.end = 0x7000e867;
 			} else {
diff --git a/drivers/soc/tegra/pmc.c b/drivers/soc/tegra/pmc.c
index 8878720dd779..ff8a2a6258d5 100644
--- a/drivers/soc/tegra/pmc.c
+++ b/drivers/soc/tegra/pmc.c
@@ -1890,14 +1890,40 @@ static int tegra_pmc_irq_alloc(struct irq_domain *domain, unsigned int virq,
 							    event->id,
 							    &pmc->irq, pmc);
 
+			/*
+			 * GPIOs don't have an equivalent interrupt in the
+			 * parent controller (GIC). However some code, such
+			 * as the one in irq_get_irqchip_state(), require a
+			 * valid IRQ chip to be set. Make sure that's the
+			 * case by passing NULL here, which will install a
+			 * dummy IRQ chip for the interrupt in the parent
+			 * domain.
+			 */
+			if (domain->parent)
+				irq_domain_set_hwirq_and_chip(domain->parent,
+							      virq, 0, NULL,
+							      NULL);
+
 			break;
 		}
 	}
 
-	if (i == soc->num_wake_events)
+	if (i == soc->num_wake_events) {
 		err = irq_domain_set_hwirq_and_chip(domain, virq, ULONG_MAX,
 						    &pmc->irq, pmc);
 
+		/*
+		 * Interrupts without a wake event don't have a corresponding
+		 * interrupt in the parent controller (GIC). Pass NULL for the
+		 * chip here, which causes a dummy IRQ chip to be installed
+		 * for the interrupt in the parent domain, to make this
+		 * explicit.
+		 */
+		if (domain->parent)
+			irq_domain_set_hwirq_and_chip(domain->parent, virq, 0,
+						      NULL, NULL);
+	}
+
 	return err;
 }
 
diff --git a/drivers/soc/ti/wkup_m3_ipc.c b/drivers/soc/ti/wkup_m3_ipc.c
index 378369d9364a..e9ece45d7a33 100644
--- a/drivers/soc/ti/wkup_m3_ipc.c
+++ b/drivers/soc/ti/wkup_m3_ipc.c
@@ -419,6 +419,8 @@ static void wkup_m3_rproc_boot_thread(struct wkup_m3_ipc *m3_ipc)
 	ret = rproc_boot(m3_ipc->rproc);
 	if (ret)
 		dev_err(dev, "rproc_boot failed\n");
+	else
+		m3_ipc_state = m3_ipc;
 
 	do_exit(0);
 }
@@ -505,8 +507,6 @@ static int wkup_m3_ipc_probe(struct platform_device *pdev)
 		goto err_put_rproc;
 	}
 
-	m3_ipc_state = m3_ipc;
-
 	return 0;
 
 err_put_rproc:
diff --git a/drivers/soc/xilinx/Kconfig b/drivers/soc/xilinx/Kconfig
index 01e76b58dd78..3fa162c1fde7 100644
--- a/drivers/soc/xilinx/Kconfig
+++ b/drivers/soc/xilinx/Kconfig
@@ -19,7 +19,7 @@ config XILINX_VCU
 
 config ZYNQMP_POWER
 	bool "Enable Xilinx Zynq MPSoC Power Management driver"
-	depends on PM && ARCH_ZYNQMP
+	depends on PM && ZYNQMP_FIRMWARE
 	default y
 	help
 	  Say yes to enable power management support for ZyqnMP SoC.
@@ -31,7 +31,7 @@ config ZYNQMP_POWER
 config ZYNQMP_PM_DOMAINS
 	bool "Enable Zynq MPSoC generic PM domains"
 	default y
-	depends on PM && ARCH_ZYNQMP && ZYNQMP_FIRMWARE
+	depends on PM && ZYNQMP_FIRMWARE
 	select PM_GENERIC_DOMAINS
 	help
 	  Say yes to enable device power management through PM domains
diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c
index f83f3b4ed6b1..412a64b29b09 100644
--- a/drivers/soundwire/intel.c
+++ b/drivers/soundwire/intel.c
@@ -701,8 +701,9 @@ static int intel_create_dai(struct sdw_cdns *cdns,
 
 	 /* TODO: Read supported rates/formats from hardware */
 	for (i = off; i < (off + num); i++) {
-		dais[i].name = kasprintf(GFP_KERNEL, "SDW%d Pin%d",
-					 cdns->instance, i);
+		dais[i].name = devm_kasprintf(cdns->dev, GFP_KERNEL,
+					      "SDW%d Pin%d",
+					      cdns->instance, i);
 		if (!dais[i].name)
 			return -ENOMEM;
 
diff --git a/drivers/soundwire/slave.c b/drivers/soundwire/slave.c
index f39a5815e25d..6a3060d89ccc 100644
--- a/drivers/soundwire/slave.c
+++ b/drivers/soundwire/slave.c
@@ -55,6 +55,8 @@ static int sdw_slave_add(struct sdw_bus *bus,
 		list_del(&slave->node);
 		mutex_unlock(&bus->bus_lock);
 		put_device(&slave->dev);
+
+		return ret;
 	}
 
 	return ret;
diff --git a/drivers/spi/atmel-quadspi.c b/drivers/spi/atmel-quadspi.c
index 9f24d5f0b431..a9023f26efc3 100644
--- a/drivers/spi/atmel-quadspi.c
+++ b/drivers/spi/atmel-quadspi.c
@@ -149,6 +149,7 @@ struct atmel_qspi {
 	struct clk		*qspick;
 	struct platform_device	*pdev;
 	const struct atmel_qspi_caps *caps;
+	resource_size_t		mmap_size;
 	u32			pending;
 	u32			mr;
 	struct completion	cmd_completion;
@@ -328,6 +329,14 @@ static int atmel_qspi_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 	u32 sr, offset;
 	int err;
 
+	/*
+	 * Check if the address exceeds the MMIO window size. An improvement
+	 * would be to add support for regular SPI mode and fall back to it
+	 * when the flash memories overrun the controller's memory space.
+	 */
+	if (op->addr.val + op->data.nbytes > aq->mmap_size)
+		return -ENOTSUPP;
+
 	err = atmel_qspi_set_cfg(aq, op, &offset);
 	if (err)
 		return err;
@@ -481,6 +490,8 @@ static int atmel_qspi_probe(struct platform_device *pdev)
 		goto exit;
 	}
 
+	aq->mmap_size = resource_size(res);
+
 	/* Get the peripheral clock */
 	aq->pclk = devm_clk_get(&pdev->dev, "pclk");
 	if (IS_ERR(aq->pclk))
diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c
index 6a4540ba65ba..b80692cfd4b9 100644
--- a/drivers/spi/spi-atmel.c
+++ b/drivers/spi/spi-atmel.c
@@ -301,7 +301,6 @@ struct atmel_spi {
 	bool			use_cs_gpios;
 
 	bool			keep_cs;
-	bool			cs_active;
 
 	u32			fifo_size;
 };
@@ -1373,11 +1372,9 @@ static int atmel_spi_one_transfer(struct spi_master *master,
 				 &msg->transfers)) {
 			as->keep_cs = true;
 		} else {
-			as->cs_active = !as->cs_active;
-			if (as->cs_active)
-				cs_activate(as, msg->spi);
-			else
-				cs_deactivate(as, msg->spi);
+			cs_deactivate(as, msg->spi);
+			udelay(10);
+			cs_activate(as, msg->spi);
 		}
 	}
 
@@ -1400,7 +1397,6 @@ static int atmel_spi_transfer_one_message(struct spi_master *master,
 	atmel_spi_lock(as);
 	cs_activate(as, spi);
 
-	as->cs_active = true;
 	as->keep_cs = false;
 
 	msg->status = 0;
diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c
index 902bdbfedea8..1808bfc400f8 100644
--- a/drivers/spi/spi-bcm-qspi.c
+++ b/drivers/spi/spi-bcm-qspi.c
@@ -670,7 +670,7 @@ static void read_from_hw(struct bcm_qspi *qspi, int slots)
 			if (buf)
 				buf[tp.byte] = read_rxram_slot_u8(qspi, slot);
 			dev_dbg(&qspi->pdev->dev, "RD %02x\n",
-				buf ? buf[tp.byte] : 0xff);
+				buf ? buf[tp.byte] : 0x0);
 		} else {
 			u16 *buf = tp.trans->rx_buf;
 
@@ -678,7 +678,7 @@ static void read_from_hw(struct bcm_qspi *qspi, int slots)
 				buf[tp.byte / 2] = read_rxram_slot_u16(qspi,
 								      slot);
 			dev_dbg(&qspi->pdev->dev, "RD %04x\n",
-				buf ? buf[tp.byte] : 0xffff);
+				buf ? buf[tp.byte / 2] : 0x0);
 		}
 
 		update_qspi_trans_byte_count(qspi, &tp,
@@ -733,13 +733,13 @@ static int write_to_hw(struct bcm_qspi *qspi, struct spi_device *spi)
 	while (!tstatus && slot < MSPI_NUM_CDRAM) {
 		if (tp.trans->bits_per_word <= 8) {
 			const u8 *buf = tp.trans->tx_buf;
-			u8 val = buf ? buf[tp.byte] : 0xff;
+			u8 val = buf ? buf[tp.byte] : 0x00;
 
 			write_txram_slot_u8(qspi, slot, val);
 			dev_dbg(&qspi->pdev->dev, "WR %02x\n", val);
 		} else {
 			const u16 *buf = tp.trans->tx_buf;
-			u16 val = buf ? buf[tp.byte / 2] : 0xffff;
+			u16 val = buf ? buf[tp.byte / 2] : 0x0000;
 
 			write_txram_slot_u16(qspi, slot, val);
 			dev_dbg(&qspi->pdev->dev, "WR %04x\n", val);
@@ -1219,6 +1219,11 @@ int bcm_qspi_probe(struct platform_device *pdev,
 	}
 
 	qspi = spi_master_get_devdata(master);
+
+	qspi->clk = devm_clk_get_optional(&pdev->dev, NULL);
+	if (IS_ERR(qspi->clk))
+		return PTR_ERR(qspi->clk);
+
 	qspi->pdev = pdev;
 	qspi->trans_pos.trans = NULL;
 	qspi->trans_pos.byte = 0;
@@ -1331,13 +1336,6 @@ int bcm_qspi_probe(struct platform_device *pdev,
 		qspi->soc_intc = NULL;
 	}
 
-	qspi->clk = devm_clk_get(&pdev->dev, NULL);
-	if (IS_ERR(qspi->clk)) {
-		dev_warn(dev, "unable to get clock\n");
-		ret = PTR_ERR(qspi->clk);
-		goto qspi_probe_err;
-	}
-
 	ret = clk_prepare_enable(qspi->clk);
 	if (ret) {
 		dev_err(dev, "failed to prepare clock\n");
diff --git a/drivers/spi/spi-bcm2835aux.c b/drivers/spi/spi-bcm2835aux.c
index 40dfb7f58efe..bc2a85ad8e89 100644
--- a/drivers/spi/spi-bcm2835aux.c
+++ b/drivers/spi/spi-bcm2835aux.c
@@ -574,7 +574,7 @@ static int bcm2835aux_spi_probe(struct platform_device *pdev)
 		goto out_clk_disable;
 	}
 
-	err = devm_spi_register_master(&pdev->dev, master);
+	err = spi_register_master(master);
 	if (err) {
 		dev_err(&pdev->dev, "could not register SPI master: %d\n", err);
 		goto out_clk_disable;
@@ -598,6 +598,8 @@ static int bcm2835aux_spi_remove(struct platform_device *pdev)
 
 	bcm2835aux_debugfs_remove(bs);
 
+	spi_unregister_master(master);
+
 	bcm2835aux_spi_reset_hw(bs);
 
 	/* disable the HW block by releasing the clock */
diff --git a/drivers/spi/spi-bcm63xx-hsspi.c b/drivers/spi/spi-bcm63xx-hsspi.c
index 9a06ffdb73b8..1669c554ea34 100644
--- a/drivers/spi/spi-bcm63xx-hsspi.c
+++ b/drivers/spi/spi-bcm63xx-hsspi.c
@@ -371,7 +371,6 @@ static int bcm63xx_hsspi_probe(struct platform_device *pdev)
 			goto out_disable_clk;
 
 		rate = clk_get_rate(pll_clk);
-		clk_disable_unprepare(pll_clk);
 		if (!rate) {
 			ret = -EINVAL;
 			goto out_disable_pll_clk;
diff --git a/drivers/spi/spi-cavium-thunderx.c b/drivers/spi/spi-cavium-thunderx.c
index ff8b71163569..ce588b47c0f0 100644
--- a/drivers/spi/spi-cavium-thunderx.c
+++ b/drivers/spi/spi-cavium-thunderx.c
@@ -87,6 +87,7 @@ static int thunderx_spi_probe(struct pci_dev *pdev,
 
 error:
 	clk_disable_unprepare(p->clk);
+	pci_release_regions(pdev);
 	spi_master_put(master);
 	return ret;
 }
@@ -101,6 +102,7 @@ static void thunderx_spi_remove(struct pci_dev *pdev)
 		return;
 
 	clk_disable_unprepare(p->clk);
+	pci_release_regions(pdev);
 	/* Put everything in a known state. */
 	writeq(0, p->register_base + OCTEON_SPI_CFG(p));
 }
diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c
index 2663bb12d9ce..b07710c76fc9 100644
--- a/drivers/spi/spi-dw-mid.c
+++ b/drivers/spi/spi-dw-mid.c
@@ -147,6 +147,7 @@ static struct dma_async_tx_descriptor *dw_spi_dma_prepare_tx(struct dw_spi *dws,
 	if (!xfer->tx_buf)
 		return NULL;
 
+	memset(&txconf, 0, sizeof(txconf));
 	txconf.direction = DMA_MEM_TO_DEV;
 	txconf.dst_addr = dws->dma_addr;
 	txconf.dst_maxburst = 16;
@@ -193,6 +194,7 @@ static struct dma_async_tx_descriptor *dw_spi_dma_prepare_rx(struct dw_spi *dws,
 	if (!xfer->rx_buf)
 		return NULL;
 
+	memset(&rxconf, 0, sizeof(rxconf));
 	rxconf.direction = DMA_DEV_TO_MEM;
 	rxconf.src_addr = dws->dma_addr;
 	rxconf.src_maxburst = 16;
@@ -218,19 +220,23 @@ static struct dma_async_tx_descriptor *dw_spi_dma_prepare_rx(struct dw_spi *dws,
 
 static int mid_spi_dma_setup(struct dw_spi *dws, struct spi_transfer *xfer)
 {
-	u16 dma_ctrl = 0;
+	u16 imr = 0, dma_ctrl = 0;
 
 	dw_writel(dws, DW_SPI_DMARDLR, 0xf);
 	dw_writel(dws, DW_SPI_DMATDLR, 0x10);
 
-	if (xfer->tx_buf)
+	if (xfer->tx_buf) {
 		dma_ctrl |= SPI_DMA_TDMAE;
-	if (xfer->rx_buf)
+		imr |= SPI_INT_TXOI;
+	}
+	if (xfer->rx_buf) {
 		dma_ctrl |= SPI_DMA_RDMAE;
+		imr |= SPI_INT_RXUI | SPI_INT_RXOI;
+	}
 	dw_writel(dws, DW_SPI_DMACR, dma_ctrl);
 
 	/* Set the interrupt mask */
-	spi_umask_intr(dws, SPI_INT_TXOI | SPI_INT_RXUI | SPI_INT_RXOI);
+	spi_umask_intr(dws, imr);
 
 	dws->transfer_handler = dma_transfer;
 
@@ -260,7 +266,7 @@ static int mid_spi_dma_transfer(struct dw_spi *dws, struct spi_transfer *xfer)
 		dma_async_issue_pending(dws->txchan);
 	}
 
-	return 0;
+	return 1;
 }
 
 static void mid_spi_dma_stop(struct dw_spi *dws)
diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c
index 45972056ed8c..c2f96941ad04 100644
--- a/drivers/spi/spi-dw.c
+++ b/drivers/spi/spi-dw.c
@@ -128,12 +128,20 @@ void dw_spi_set_cs(struct spi_device *spi, bool enable)
 {
 	struct dw_spi *dws = spi_controller_get_devdata(spi->controller);
 	struct chip_data *chip = spi_get_ctldata(spi);
+	bool cs_high = !!(spi->mode & SPI_CS_HIGH);
 
 	/* Chip select logic is inverted from spi_set_cs() */
 	if (chip && chip->cs_control)
 		chip->cs_control(!enable);
 
-	if (!enable)
+	/*
+	 * DW SPI controller demands any native CS being set in order to
+	 * proceed with data transfer. So in order to activate the SPI
+	 * communications we must set a corresponding bit in the Slave
+	 * Enable register no matter whether the SPI core is configured to
+	 * support active-high or active-low CS level.
+	 */
+	if (cs_high == enable)
 		dw_writel(dws, DW_SPI_SER, BIT(spi->chip_select));
 	else if (dws->cs_override)
 		dw_writel(dws, DW_SPI_SER, 0);
@@ -172,9 +180,11 @@ static inline u32 rx_max(struct dw_spi *dws)
 
 static void dw_writer(struct dw_spi *dws)
 {
-	u32 max = tx_max(dws);
+	u32 max;
 	u16 txw = 0;
 
+	spin_lock(&dws->buf_lock);
+	max = tx_max(dws);
 	while (max--) {
 		/* Set the tx word if the transfer's original "tx" is not null */
 		if (dws->tx_end - dws->len) {
@@ -186,13 +196,16 @@ static void dw_writer(struct dw_spi *dws)
 		dw_write_io_reg(dws, DW_SPI_DR, txw);
 		dws->tx += dws->n_bytes;
 	}
+	spin_unlock(&dws->buf_lock);
 }
 
 static void dw_reader(struct dw_spi *dws)
 {
-	u32 max = rx_max(dws);
+	u32 max;
 	u16 rxw;
 
+	spin_lock(&dws->buf_lock);
+	max = rx_max(dws);
 	while (max--) {
 		rxw = dw_read_io_reg(dws, DW_SPI_DR);
 		/* Care rx only if the transfer's original "rx" is not null */
@@ -204,6 +217,7 @@ static void dw_reader(struct dw_spi *dws)
 		}
 		dws->rx += dws->n_bytes;
 	}
+	spin_unlock(&dws->buf_lock);
 }
 
 static void int_error_stop(struct dw_spi *dws, const char *msg)
@@ -276,18 +290,23 @@ static int dw_spi_transfer_one(struct spi_controller *master,
 {
 	struct dw_spi *dws = spi_controller_get_devdata(master);
 	struct chip_data *chip = spi_get_ctldata(spi);
+	unsigned long flags;
 	u8 imask = 0;
 	u16 txlevel = 0;
 	u32 cr0;
 	int ret;
 
 	dws->dma_mapped = 0;
-
+	spin_lock_irqsave(&dws->buf_lock, flags);
 	dws->tx = (void *)transfer->tx_buf;
 	dws->tx_end = dws->tx + transfer->len;
 	dws->rx = transfer->rx_buf;
 	dws->rx_end = dws->rx + transfer->len;
 	dws->len = transfer->len;
+	spin_unlock_irqrestore(&dws->buf_lock, flags);
+
+	/* Ensure dw->rx and dw->rx_end are visible */
+	smp_mb();
 
 	spi_enable_chip(dws, 0);
 
@@ -362,11 +381,8 @@ static int dw_spi_transfer_one(struct spi_controller *master,
 
 	spi_enable_chip(dws, 1);
 
-	if (dws->dma_mapped) {
-		ret = dws->dma_ops->dma_transfer(dws, transfer);
-		if (ret < 0)
-			return ret;
-	}
+	if (dws->dma_mapped)
+		return dws->dma_ops->dma_transfer(dws, transfer);
 
 	if (chip->poll_mode)
 		return poll_transfer(dws);
@@ -471,6 +487,7 @@ int dw_spi_add_host(struct device *dev, struct dw_spi *dws)
 	dws->type = SSI_MOTO_SPI;
 	dws->dma_inited = 0;
 	dws->dma_addr = (dma_addr_t)(dws->paddr + DW_SPI_DR);
+	spin_lock_init(&dws->buf_lock);
 
 	spi_controller_set_devdata(master, dws);
 
@@ -509,10 +526,11 @@ int dw_spi_add_host(struct device *dev, struct dw_spi *dws)
 			dws->dma_inited = 0;
 		} else {
 			master->can_dma = dws->dma_ops->can_dma;
+			master->flags |= SPI_CONTROLLER_MUST_TX;
 		}
 	}
 
-	ret = devm_spi_register_controller(dev, master);
+	ret = spi_register_controller(master);
 	if (ret) {
 		dev_err(&master->dev, "problem registering spi master\n");
 		goto err_dma_exit;
@@ -536,6 +554,8 @@ void dw_spi_remove_host(struct dw_spi *dws)
 {
 	dw_spi_debugfs_remove(dws);
 
+	spi_unregister_controller(dws->master);
+
 	if (dws->dma_ops && dws->dma_ops->dma_exit)
 		dws->dma_ops->dma_exit(dws);
 
diff --git a/drivers/spi/spi-dw.h b/drivers/spi/spi-dw.h
index c9c15881e982..f3a2f157a2b1 100644
--- a/drivers/spi/spi-dw.h
+++ b/drivers/spi/spi-dw.h
@@ -120,6 +120,7 @@ struct dw_spi {
 	size_t			len;
 	void			*tx;
 	void			*tx_end;
+	spinlock_t		buf_lock;
 	void			*rx;
 	void			*rx_end;
 	int			dma_mapped;
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 545fc8189fb0..874d15555db5 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0+
 //
 // Copyright 2013 Freescale Semiconductor, Inc.
+// Copyright 2020 NXP
 //
 // Freescale DSPI driver
 // This file contains a driver for the Freescale DSPI
@@ -43,6 +44,9 @@
 #define SPI_MCR_CLR_TXF	(1 << 11)
 #define SPI_MCR_CLR_RXF	(1 << 10)
 #define SPI_MCR_XSPI		(1 << 3)
+#define SPI_MCR_DIS_TXF		(1 << 13)
+#define SPI_MCR_DIS_RXF		(1 << 12)
+#define SPI_MCR_HALT		(1 << 0)
 
 #define SPI_TCR			0x08
 #define SPI_TCR_GET_TCNT(x)	(((x) & 0xffff0000) >> 16)
@@ -185,7 +189,7 @@ struct fsl_dspi_dma {
 };
 
 struct fsl_dspi {
-	struct spi_master	*master;
+	struct spi_controller	*ctlr;
 	struct platform_device	*pdev;
 
 	struct regmap		*regmap;
@@ -233,7 +237,7 @@ static u32 dspi_pop_tx_pushr(struct fsl_dspi *dspi)
 {
 	u16 cmd = dspi->tx_cmd, data = dspi_pop_tx(dspi);
 
-	if (spi_controller_is_slave(dspi->master))
+	if (spi_controller_is_slave(dspi->ctlr))
 		return data;
 
 	if (dspi->len > 0)
@@ -332,7 +336,7 @@ static int dspi_next_xfer_dma_submit(struct fsl_dspi *dspi)
 	dma_async_issue_pending(dma->chan_rx);
 	dma_async_issue_pending(dma->chan_tx);
 
-	if (spi_controller_is_slave(dspi->master)) {
+	if (spi_controller_is_slave(dspi->ctlr)) {
 		wait_for_completion_interruptible(&dspi->dma->cmd_rx_complete);
 		return 0;
 	}
@@ -596,21 +600,14 @@ static void dspi_tcfq_write(struct fsl_dspi *dspi)
 	dspi->tx_cmd |= SPI_PUSHR_CMD_CTCNT;
 
 	if (dspi->devtype_data->xspi_mode && dspi->bits_per_word > 16) {
-		/* Write two TX FIFO entries first, and then the corresponding
-		 * CMD FIFO entry.
+		/* Write the CMD FIFO entry first, and then the two
+		 * corresponding TX FIFO entries.
 		 */
 		u32 data = dspi_pop_tx(dspi);
 
-		if (dspi->cur_chip->ctar_val & SPI_CTAR_LSBFE(1)) {
-			/* LSB */
-			tx_fifo_write(dspi, data & 0xFFFF);
-			tx_fifo_write(dspi, data >> 16);
-		} else {
-			/* MSB */
-			tx_fifo_write(dspi, data >> 16);
-			tx_fifo_write(dspi, data & 0xFFFF);
-		}
 		cmd_fifo_write(dspi);
+		tx_fifo_write(dspi, data & 0xFFFF);
+		tx_fifo_write(dspi, data >> 16);
 	} else {
 		/* Write one entry to both TX FIFO and CMD FIFO
 		 * simultaneously.
@@ -660,10 +657,10 @@ static void dspi_eoq_read(struct fsl_dspi *dspi)
 		dspi_push_rx(dspi, fifo_read(dspi));
 }
 
-static int dspi_transfer_one_message(struct spi_master *master,
+static int dspi_transfer_one_message(struct spi_controller *ctlr,
 		struct spi_message *message)
 {
-	struct fsl_dspi *dspi = spi_master_get_devdata(master);
+	struct fsl_dspi *dspi = spi_controller_get_devdata(ctlr);
 	struct spi_device *spi = message->spi;
 	struct spi_transfer *transfer;
 	int status = 0;
@@ -758,7 +755,7 @@ static int dspi_transfer_one_message(struct spi_master *master,
 
 out:
 	message->status = status;
-	spi_finalize_current_message(master);
+	spi_finalize_current_message(ctlr);
 
 	return status;
 }
@@ -766,7 +763,7 @@ out:
 static int dspi_setup(struct spi_device *spi)
 {
 	struct chip_data *chip;
-	struct fsl_dspi *dspi = spi_master_get_devdata(spi->master);
+	struct fsl_dspi *dspi = spi_controller_get_devdata(spi->controller);
 	struct fsl_dspi_platform_data *pdata;
 	u32 cs_sck_delay = 0, sck_cs_delay = 0;
 	unsigned char br = 0, pbr = 0, pcssck = 0, cssck = 0;
@@ -808,7 +805,7 @@ static int dspi_setup(struct spi_device *spi)
 	chip->ctar_val = SPI_CTAR_CPOL(spi->mode & SPI_CPOL ? 1 : 0)
 		| SPI_CTAR_CPHA(spi->mode & SPI_CPHA ? 1 : 0);
 
-	if (!spi_controller_is_slave(dspi->master)) {
+	if (!spi_controller_is_slave(dspi->ctlr)) {
 		chip->ctar_val |= SPI_CTAR_LSBFE(spi->mode &
 						 SPI_LSB_FIRST ? 1 : 0)
 			| SPI_CTAR_PCSSCK(pcssck)
@@ -829,7 +826,7 @@ static void dspi_cleanup(struct spi_device *spi)
 	struct chip_data *chip = spi_get_ctldata((struct spi_device *)spi);
 
 	dev_dbg(&spi->dev, "spi_device %u.%u cleanup\n",
-			spi->master->bus_num, spi->chip_select);
+			spi->controller->bus_num, spi->chip_select);
 
 	kfree(chip);
 }
@@ -904,10 +901,10 @@ MODULE_DEVICE_TABLE(of, fsl_dspi_dt_ids);
 #ifdef CONFIG_PM_SLEEP
 static int dspi_suspend(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct fsl_dspi *dspi = spi_master_get_devdata(master);
+	struct spi_controller *ctlr = dev_get_drvdata(dev);
+	struct fsl_dspi *dspi = spi_controller_get_devdata(ctlr);
 
-	spi_master_suspend(master);
+	spi_controller_suspend(ctlr);
 	clk_disable_unprepare(dspi->clk);
 
 	pinctrl_pm_select_sleep_state(dev);
@@ -917,8 +914,8 @@ static int dspi_suspend(struct device *dev)
 
 static int dspi_resume(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct fsl_dspi *dspi = spi_master_get_devdata(master);
+	struct spi_controller *ctlr = dev_get_drvdata(dev);
+	struct fsl_dspi *dspi = spi_controller_get_devdata(ctlr);
 	int ret;
 
 	pinctrl_pm_select_default_state(dev);
@@ -926,7 +923,7 @@ static int dspi_resume(struct device *dev)
 	ret = clk_prepare_enable(dspi->clk);
 	if (ret)
 		return ret;
-	spi_master_resume(master);
+	spi_controller_resume(ctlr);
 
 	return 0;
 }
@@ -987,7 +984,7 @@ static void dspi_init(struct fsl_dspi *dspi)
 	unsigned int mcr = SPI_MCR_PCSIS |
 		(dspi->devtype_data->xspi_mode ? SPI_MCR_XSPI : 0);
 
-	if (!spi_controller_is_slave(dspi->master))
+	if (!spi_controller_is_slave(dspi->ctlr))
 		mcr |= SPI_MCR_MASTER;
 
 	regmap_write(dspi->regmap, SPI_MCR, mcr);
@@ -1000,7 +997,7 @@ static void dspi_init(struct fsl_dspi *dspi)
 static int dspi_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
-	struct spi_master *master;
+	struct spi_controller *ctlr;
 	struct fsl_dspi *dspi;
 	struct resource *res;
 	const struct regmap_config *regmap_config;
@@ -1008,26 +1005,25 @@ static int dspi_probe(struct platform_device *pdev)
 	struct fsl_dspi_platform_data *pdata;
 	int ret = 0, cs_num, bus_num;
 
-	master = spi_alloc_master(&pdev->dev, sizeof(struct fsl_dspi));
-	if (!master)
+	ctlr = spi_alloc_master(&pdev->dev, sizeof(struct fsl_dspi));
+	if (!ctlr)
 		return -ENOMEM;
 
-	dspi = spi_master_get_devdata(master);
+	dspi = spi_controller_get_devdata(ctlr);
 	dspi->pdev = pdev;
-	dspi->master = master;
+	dspi->ctlr = ctlr;
 
-	master->transfer = NULL;
-	master->setup = dspi_setup;
-	master->transfer_one_message = dspi_transfer_one_message;
-	master->dev.of_node = pdev->dev.of_node;
+	ctlr->setup = dspi_setup;
+	ctlr->transfer_one_message = dspi_transfer_one_message;
+	ctlr->dev.of_node = pdev->dev.of_node;
 
-	master->cleanup = dspi_cleanup;
-	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_LSB_FIRST;
+	ctlr->cleanup = dspi_cleanup;
+	ctlr->mode_bits = SPI_CPOL | SPI_CPHA | SPI_LSB_FIRST;
 
 	pdata = dev_get_platdata(&pdev->dev);
 	if (pdata) {
-		master->num_chipselect = pdata->cs_num;
-		master->bus_num = pdata->bus_num;
+		ctlr->num_chipselect = pdata->cs_num;
+		ctlr->bus_num = pdata->bus_num;
 
 		dspi->devtype_data = &coldfire_data;
 	} else {
@@ -1035,38 +1031,38 @@ static int dspi_probe(struct platform_device *pdev)
 		ret = of_property_read_u32(np, "spi-num-chipselects", &cs_num);
 		if (ret < 0) {
 			dev_err(&pdev->dev, "can't get spi-num-chipselects\n");
-			goto out_master_put;
+			goto out_ctlr_put;
 		}
-		master->num_chipselect = cs_num;
+		ctlr->num_chipselect = cs_num;
 
 		ret = of_property_read_u32(np, "bus-num", &bus_num);
 		if (ret < 0) {
 			dev_err(&pdev->dev, "can't get bus-num\n");
-			goto out_master_put;
+			goto out_ctlr_put;
 		}
-		master->bus_num = bus_num;
+		ctlr->bus_num = bus_num;
 
 		if (of_property_read_bool(np, "spi-slave"))
-			master->slave = true;
+			ctlr->slave = true;
 
 		dspi->devtype_data = of_device_get_match_data(&pdev->dev);
 		if (!dspi->devtype_data) {
 			dev_err(&pdev->dev, "can't get devtype_data\n");
 			ret = -EFAULT;
-			goto out_master_put;
+			goto out_ctlr_put;
 		}
 	}
 
 	if (dspi->devtype_data->xspi_mode)
-		master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 32);
+		ctlr->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 32);
 	else
-		master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 16);
+		ctlr->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 16);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	base = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(base)) {
 		ret = PTR_ERR(base);
-		goto out_master_put;
+		goto out_ctlr_put;
 	}
 
 	if (dspi->devtype_data->xspi_mode)
@@ -1078,7 +1074,7 @@ static int dspi_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev, "failed to init regmap: %ld\n",
 				PTR_ERR(dspi->regmap));
 		ret = PTR_ERR(dspi->regmap);
-		goto out_master_put;
+		goto out_ctlr_put;
 	}
 
 	if (dspi->devtype_data->xspi_mode) {
@@ -1090,7 +1086,7 @@ static int dspi_probe(struct platform_device *pdev)
 				"failed to init pushr regmap: %ld\n",
 				PTR_ERR(dspi->regmap_pushr));
 			ret = PTR_ERR(dspi->regmap_pushr);
-			goto out_master_put;
+			goto out_ctlr_put;
 		}
 	}
 
@@ -1098,11 +1094,11 @@ static int dspi_probe(struct platform_device *pdev)
 	if (IS_ERR(dspi->clk)) {
 		ret = PTR_ERR(dspi->clk);
 		dev_err(&pdev->dev, "unable to get clock\n");
-		goto out_master_put;
+		goto out_ctlr_put;
 	}
 	ret = clk_prepare_enable(dspi->clk);
 	if (ret)
-		goto out_master_put;
+		goto out_ctlr_put;
 
 	dspi_init(dspi);
 	dspi->irq = platform_get_irq(pdev, 0);
@@ -1127,15 +1123,15 @@ static int dspi_probe(struct platform_device *pdev)
 		}
 	}
 
-	master->max_speed_hz =
+	ctlr->max_speed_hz =
 		clk_get_rate(dspi->clk) / dspi->devtype_data->max_clock_factor;
 
 	init_waitqueue_head(&dspi->waitq);
-	platform_set_drvdata(pdev, master);
+	platform_set_drvdata(pdev, ctlr);
 
-	ret = spi_register_master(master);
+	ret = spi_register_controller(ctlr);
 	if (ret != 0) {
-		dev_err(&pdev->dev, "Problem registering DSPI master\n");
+		dev_err(&pdev->dev, "Problem registering DSPI ctlr\n");
 		goto out_clk_put;
 	}
 
@@ -1143,25 +1139,39 @@ static int dspi_probe(struct platform_device *pdev)
 
 out_clk_put:
 	clk_disable_unprepare(dspi->clk);
-out_master_put:
-	spi_master_put(master);
+out_ctlr_put:
+	spi_controller_put(ctlr);
 
 	return ret;
 }
 
 static int dspi_remove(struct platform_device *pdev)
 {
-	struct spi_master *master = platform_get_drvdata(pdev);
-	struct fsl_dspi *dspi = spi_master_get_devdata(master);
+	struct spi_controller *ctlr = platform_get_drvdata(pdev);
+	struct fsl_dspi *dspi = spi_controller_get_devdata(ctlr);
 
 	/* Disconnect from the SPI framework */
+	spi_unregister_controller(dspi->ctlr);
+
+	/* Disable RX and TX */
+	regmap_update_bits(dspi->regmap, SPI_MCR,
+			   SPI_MCR_DIS_TXF | SPI_MCR_DIS_RXF,
+			   SPI_MCR_DIS_TXF | SPI_MCR_DIS_RXF);
+
+	/* Stop Running */
+	regmap_update_bits(dspi->regmap, SPI_MCR, SPI_MCR_HALT, SPI_MCR_HALT);
+
 	dspi_release_dma(dspi);
 	clk_disable_unprepare(dspi->clk);
-	spi_unregister_master(dspi->master);
 
 	return 0;
 }
 
+static void dspi_shutdown(struct platform_device *pdev)
+{
+	dspi_remove(pdev);
+}
+
 static struct platform_driver fsl_dspi_driver = {
 	.driver.name    = DRIVER_NAME,
 	.driver.of_match_table = fsl_dspi_dt_ids,
@@ -1169,6 +1179,7 @@ static struct platform_driver fsl_dspi_driver = {
 	.driver.pm = &dspi_pm,
 	.probe          = dspi_probe,
 	.remove		= dspi_remove,
+	.shutdown		= dspi_shutdown,
 };
 module_platform_driver(fsl_dspi_driver);
 
diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index 3528ed5eea9b..92e460d4f3d1 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -862,6 +862,22 @@ static int fsl_lpspi_probe(struct platform_device *pdev)
 	fsl_lpspi->dev = &pdev->dev;
 	fsl_lpspi->is_slave = is_slave;
 
+	controller->bits_per_word_mask = SPI_BPW_RANGE_MASK(8, 32);
+	controller->transfer_one = fsl_lpspi_transfer_one;
+	controller->prepare_transfer_hardware = lpspi_prepare_xfer_hardware;
+	controller->unprepare_transfer_hardware = lpspi_unprepare_xfer_hardware;
+	controller->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
+	controller->flags = SPI_MASTER_MUST_RX | SPI_MASTER_MUST_TX;
+	controller->dev.of_node = pdev->dev.of_node;
+	controller->bus_num = pdev->id;
+	controller->slave_abort = fsl_lpspi_slave_abort;
+
+	ret = devm_spi_register_controller(&pdev->dev, controller);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "spi_register_controller error.\n");
+		goto out_controller_put;
+	}
+
 	if (!fsl_lpspi->is_slave) {
 		for (i = 0; i < controller->num_chipselect; i++) {
 			int cs_gpio = of_get_named_gpio(np, "cs-gpios", i);
@@ -885,16 +901,6 @@ static int fsl_lpspi_probe(struct platform_device *pdev)
 		controller->prepare_message = fsl_lpspi_prepare_message;
 	}
 
-	controller->bits_per_word_mask = SPI_BPW_RANGE_MASK(8, 32);
-	controller->transfer_one = fsl_lpspi_transfer_one;
-	controller->prepare_transfer_hardware = lpspi_prepare_xfer_hardware;
-	controller->unprepare_transfer_hardware = lpspi_unprepare_xfer_hardware;
-	controller->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
-	controller->flags = SPI_MASTER_MUST_RX | SPI_MASTER_MUST_TX;
-	controller->dev.of_node = pdev->dev.of_node;
-	controller->bus_num = pdev->id;
-	controller->slave_abort = fsl_lpspi_slave_abort;
-
 	init_completion(&fsl_lpspi->xfer_done);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -952,12 +958,6 @@ static int fsl_lpspi_probe(struct platform_device *pdev)
 	if (ret < 0)
 		dev_err(&pdev->dev, "dma setup error %d, use pio\n", ret);
 
-	ret = devm_spi_register_controller(&pdev->dev, controller);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "spi_register_controller error.\n");
-		goto out_controller_put;
-	}
-
 	return 0;
 
 out_controller_put:
diff --git a/drivers/spi/spi-fsl-qspi.c b/drivers/spi/spi-fsl-qspi.c
index 609e10aa2535..e1cf5a711c9d 100644
--- a/drivers/spi/spi-fsl-qspi.c
+++ b/drivers/spi/spi-fsl-qspi.c
@@ -398,7 +398,7 @@ static bool fsl_qspi_supports_op(struct spi_mem *mem,
 	    op->data.nbytes > q->devtype_data->txfifo)
 		return false;
 
-	return true;
+	return spi_mem_default_supports_op(mem, op);
 }
 
 static void fsl_qspi_prepare_lut(struct fsl_qspi *q,
diff --git a/drivers/spi/spi-gpio.c b/drivers/spi/spi-gpio.c
index cb111e6c4df3..49c99fcbbaf3 100644
--- a/drivers/spi/spi-gpio.c
+++ b/drivers/spi/spi-gpio.c
@@ -412,6 +412,12 @@ static int spi_gpio_probe(struct platform_device *pdev)
 
 	bb = &spi_gpio->bitbang;
 	bb->master = master;
+	/*
+	 * There is some additional business, apart from driving the CS GPIO
+	 * line, that we need to do on selection. This makes the local
+	 * callback for chipselect always get called.
+	 */
+	master->flags |= SPI_MASTER_GPIO_SS;
 	bb->chipselect = spi_gpio_chipselect;
 	bb->set_line_direction = spi_gpio_set_direction;
 
diff --git a/drivers/spi/spi-lantiq-ssc.c b/drivers/spi/spi-lantiq-ssc.c
index 8f01858c0ae6..365008d304f5 100644
--- a/drivers/spi/spi-lantiq-ssc.c
+++ b/drivers/spi/spi-lantiq-ssc.c
@@ -184,6 +184,7 @@ struct lantiq_ssc_spi {
 	unsigned int			tx_fifo_size;
 	unsigned int			rx_fifo_size;
 	unsigned int			base_cs;
+	unsigned int			fdx_tx_level;
 };
 
 static u32 lantiq_ssc_readl(const struct lantiq_ssc_spi *spi, u32 reg)
@@ -481,6 +482,7 @@ static void tx_fifo_write(struct lantiq_ssc_spi *spi)
 	u32 data;
 	unsigned int tx_free = tx_fifo_free(spi);
 
+	spi->fdx_tx_level = 0;
 	while (spi->tx_todo && tx_free) {
 		switch (spi->bits_per_word) {
 		case 2 ... 8:
@@ -509,6 +511,7 @@ static void tx_fifo_write(struct lantiq_ssc_spi *spi)
 
 		lantiq_ssc_writel(spi, data, LTQ_SPI_TB);
 		tx_free--;
+		spi->fdx_tx_level++;
 	}
 }
 
@@ -520,6 +523,13 @@ static void rx_fifo_read_full_duplex(struct lantiq_ssc_spi *spi)
 	u32 data;
 	unsigned int rx_fill = rx_fifo_level(spi);
 
+	/*
+	 * Wait until all expected data to be shifted in.
+	 * Otherwise, rx overrun may occur.
+	 */
+	while (rx_fill != spi->fdx_tx_level)
+		rx_fill = rx_fifo_level(spi);
+
 	while (rx_fill) {
 		data = lantiq_ssc_readl(spi, LTQ_SPI_RB);
 
@@ -913,7 +923,7 @@ static int lantiq_ssc_probe(struct platform_device *pdev)
 	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(2, 8) |
 				     SPI_BPW_MASK(16) | SPI_BPW_MASK(32);
 
-	spi->wq = alloc_ordered_workqueue(dev_name(dev), 0);
+	spi->wq = alloc_ordered_workqueue(dev_name(dev), WQ_MEM_RECLAIM);
 	if (!spi->wq) {
 		err = -ENOMEM;
 		goto err_clk_put;
diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c
index 9f0fa9f3116d..de0ba3e5449f 100644
--- a/drivers/spi/spi-mem.c
+++ b/drivers/spi/spi-mem.c
@@ -108,15 +108,17 @@ static int spi_check_buswidth_req(struct spi_mem *mem, u8 buswidth, bool tx)
 		return 0;
 
 	case 2:
-		if ((tx && (mode & (SPI_TX_DUAL | SPI_TX_QUAD))) ||
-		    (!tx && (mode & (SPI_RX_DUAL | SPI_RX_QUAD))))
+		if ((tx &&
+		     (mode & (SPI_TX_DUAL | SPI_TX_QUAD | SPI_TX_OCTAL))) ||
+		    (!tx &&
+		     (mode & (SPI_RX_DUAL | SPI_RX_QUAD | SPI_RX_OCTAL))))
 			return 0;
 
 		break;
 
 	case 4:
-		if ((tx && (mode & SPI_TX_QUAD)) ||
-		    (!tx && (mode & SPI_RX_QUAD)))
+		if ((tx && (mode & (SPI_TX_QUAD | SPI_TX_OCTAL))) ||
+		    (!tx && (mode & (SPI_RX_QUAD | SPI_RX_OCTAL))))
 			return 0;
 
 		break;
diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c
index 10041eab36a2..ea737f69a870 100644
--- a/drivers/spi/spi-mt65xx.c
+++ b/drivers/spi/spi-mt65xx.c
@@ -33,7 +33,6 @@
 #define SPI_CFG0_SCK_LOW_OFFSET           8
 #define SPI_CFG0_CS_HOLD_OFFSET           16
 #define SPI_CFG0_CS_SETUP_OFFSET          24
-#define SPI_ADJUST_CFG0_SCK_LOW_OFFSET    16
 #define SPI_ADJUST_CFG0_CS_HOLD_OFFSET    0
 #define SPI_ADJUST_CFG0_CS_SETUP_OFFSET   16
 
@@ -45,6 +44,8 @@
 #define SPI_CFG1_CS_IDLE_MASK             0xff
 #define SPI_CFG1_PACKET_LOOP_MASK         0xff00
 #define SPI_CFG1_PACKET_LENGTH_MASK       0x3ff0000
+#define SPI_CFG2_SCK_HIGH_OFFSET          0
+#define SPI_CFG2_SCK_LOW_OFFSET           16
 
 #define SPI_CMD_ACT                  BIT(0)
 #define SPI_CMD_RESUME               BIT(1)
@@ -263,7 +264,7 @@ static void mtk_spi_set_cs(struct spi_device *spi, bool enable)
 static void mtk_spi_prepare_transfer(struct spi_master *master,
 				     struct spi_transfer *xfer)
 {
-	u32 spi_clk_hz, div, sck_time, cs_time, reg_val = 0;
+	u32 spi_clk_hz, div, sck_time, cs_time, reg_val;
 	struct mtk_spi *mdata = spi_master_get_devdata(master);
 
 	spi_clk_hz = clk_get_rate(mdata->spi_clk);
@@ -276,18 +277,18 @@ static void mtk_spi_prepare_transfer(struct spi_master *master,
 	cs_time = sck_time * 2;
 
 	if (mdata->dev_comp->enhance_timing) {
+		reg_val = (((sck_time - 1) & 0xffff)
+			   << SPI_CFG2_SCK_HIGH_OFFSET);
 		reg_val |= (((sck_time - 1) & 0xffff)
-			   << SPI_CFG0_SCK_HIGH_OFFSET);
-		reg_val |= (((sck_time - 1) & 0xffff)
-			   << SPI_ADJUST_CFG0_SCK_LOW_OFFSET);
+			   << SPI_CFG2_SCK_LOW_OFFSET);
 		writel(reg_val, mdata->base + SPI_CFG2_REG);
-		reg_val |= (((cs_time - 1) & 0xffff)
+		reg_val = (((cs_time - 1) & 0xffff)
 			   << SPI_ADJUST_CFG0_CS_HOLD_OFFSET);
 		reg_val |= (((cs_time - 1) & 0xffff)
 			   << SPI_ADJUST_CFG0_CS_SETUP_OFFSET);
 		writel(reg_val, mdata->base + SPI_CFG0_REG);
 	} else {
-		reg_val |= (((sck_time - 1) & 0xff)
+		reg_val = (((sck_time - 1) & 0xff)
 			   << SPI_CFG0_SCK_HIGH_OFFSET);
 		reg_val |= (((sck_time - 1) & 0xff) << SPI_CFG0_SCK_LOW_OFFSET);
 		reg_val |= (((cs_time - 1) & 0xff) << SPI_CFG0_CS_HOLD_OFFSET);
diff --git a/drivers/spi/spi-nxp-fspi.c b/drivers/spi/spi-nxp-fspi.c
index 8894f98cc99c..c834cf75175d 100644
--- a/drivers/spi/spi-nxp-fspi.c
+++ b/drivers/spi/spi-nxp-fspi.c
@@ -439,7 +439,7 @@ static bool nxp_fspi_supports_op(struct spi_mem *mem,
 	    op->data.nbytes > f->devtype_data->txfifo)
 		return false;
 
-	return true;
+	return spi_mem_default_supports_op(mem, op);
 }
 
 /* Instead of busy looping invoke readl_poll_timeout functionality. */
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index 848e03e5f42d..4433cb4de564 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -985,20 +985,12 @@ static int omap2_mcspi_setup_transfer(struct spi_device *spi,
  * Note that we currently allow DMA only if we get a channel
  * for both rx and tx. Otherwise we'll do PIO for both rx and tx.
  */
-static int omap2_mcspi_request_dma(struct spi_device *spi)
+static int omap2_mcspi_request_dma(struct omap2_mcspi *mcspi,
+				   struct omap2_mcspi_dma *mcspi_dma)
 {
-	struct spi_master	*master = spi->master;
-	struct omap2_mcspi	*mcspi;
-	struct omap2_mcspi_dma	*mcspi_dma;
 	int ret = 0;
 
-	mcspi = spi_master_get_devdata(master);
-	mcspi_dma = mcspi->dma_channels + spi->chip_select;
-
-	init_completion(&mcspi_dma->dma_rx_completion);
-	init_completion(&mcspi_dma->dma_tx_completion);
-
-	mcspi_dma->dma_rx = dma_request_chan(&master->dev,
+	mcspi_dma->dma_rx = dma_request_chan(mcspi->dev,
 					     mcspi_dma->dma_rx_ch_name);
 	if (IS_ERR(mcspi_dma->dma_rx)) {
 		ret = PTR_ERR(mcspi_dma->dma_rx);
@@ -1006,7 +998,7 @@ static int omap2_mcspi_request_dma(struct spi_device *spi)
 		goto no_dma;
 	}
 
-	mcspi_dma->dma_tx = dma_request_chan(&master->dev,
+	mcspi_dma->dma_tx = dma_request_chan(mcspi->dev,
 					     mcspi_dma->dma_tx_ch_name);
 	if (IS_ERR(mcspi_dma->dma_tx)) {
 		ret = PTR_ERR(mcspi_dma->dma_tx);
@@ -1015,20 +1007,40 @@ static int omap2_mcspi_request_dma(struct spi_device *spi)
 		mcspi_dma->dma_rx = NULL;
 	}
 
+	init_completion(&mcspi_dma->dma_rx_completion);
+	init_completion(&mcspi_dma->dma_tx_completion);
+
 no_dma:
 	return ret;
 }
 
+static void omap2_mcspi_release_dma(struct spi_master *master)
+{
+	struct omap2_mcspi *mcspi = spi_master_get_devdata(master);
+	struct omap2_mcspi_dma	*mcspi_dma;
+	int i;
+
+	for (i = 0; i < master->num_chipselect; i++) {
+		mcspi_dma = &mcspi->dma_channels[i];
+
+		if (mcspi_dma->dma_rx) {
+			dma_release_channel(mcspi_dma->dma_rx);
+			mcspi_dma->dma_rx = NULL;
+		}
+		if (mcspi_dma->dma_tx) {
+			dma_release_channel(mcspi_dma->dma_tx);
+			mcspi_dma->dma_tx = NULL;
+		}
+	}
+}
+
 static int omap2_mcspi_setup(struct spi_device *spi)
 {
 	int			ret;
 	struct omap2_mcspi	*mcspi = spi_master_get_devdata(spi->master);
 	struct omap2_mcspi_regs	*ctx = &mcspi->ctx;
-	struct omap2_mcspi_dma	*mcspi_dma;
 	struct omap2_mcspi_cs	*cs = spi->controller_state;
 
-	mcspi_dma = &mcspi->dma_channels[spi->chip_select];
-
 	if (!cs) {
 		cs = kzalloc(sizeof *cs, GFP_KERNEL);
 		if (!cs)
@@ -1053,13 +1065,6 @@ static int omap2_mcspi_setup(struct spi_device *spi)
 		}
 	}
 
-	if (!mcspi_dma->dma_rx || !mcspi_dma->dma_tx) {
-		ret = omap2_mcspi_request_dma(spi);
-		if (ret)
-			dev_warn(&spi->dev, "not using DMA for McSPI (%d)\n",
-				 ret);
-	}
-
 	ret = pm_runtime_get_sync(mcspi->dev);
 	if (ret < 0) {
 		pm_runtime_put_noidle(mcspi->dev);
@@ -1076,12 +1081,8 @@ static int omap2_mcspi_setup(struct spi_device *spi)
 
 static void omap2_mcspi_cleanup(struct spi_device *spi)
 {
-	struct omap2_mcspi	*mcspi;
-	struct omap2_mcspi_dma	*mcspi_dma;
 	struct omap2_mcspi_cs	*cs;
 
-	mcspi = spi_master_get_devdata(spi->master);
-
 	if (spi->controller_state) {
 		/* Unlink controller state from context save list */
 		cs = spi->controller_state;
@@ -1090,19 +1091,6 @@ static void omap2_mcspi_cleanup(struct spi_device *spi)
 		kfree(cs);
 	}
 
-	if (spi->chip_select < spi->master->num_chipselect) {
-		mcspi_dma = &mcspi->dma_channels[spi->chip_select];
-
-		if (mcspi_dma->dma_rx) {
-			dma_release_channel(mcspi_dma->dma_rx);
-			mcspi_dma->dma_rx = NULL;
-		}
-		if (mcspi_dma->dma_tx) {
-			dma_release_channel(mcspi_dma->dma_tx);
-			mcspi_dma->dma_tx = NULL;
-		}
-	}
-
 	if (gpio_is_valid(spi->cs_gpio))
 		gpio_free(spi->cs_gpio);
 }
@@ -1313,6 +1301,9 @@ static bool omap2_mcspi_can_dma(struct spi_master *master,
 	if (spi_controller_is_slave(master))
 		return true;
 
+	master->dma_rx = mcspi_dma->dma_rx;
+	master->dma_tx = mcspi_dma->dma_tx;
+
 	return (xfer->len >= DMA_MIN_BYTES);
 }
 
@@ -1475,6 +1466,11 @@ static int omap2_mcspi_probe(struct platform_device *pdev)
 	for (i = 0; i < master->num_chipselect; i++) {
 		sprintf(mcspi->dma_channels[i].dma_rx_ch_name, "rx%d", i);
 		sprintf(mcspi->dma_channels[i].dma_tx_ch_name, "tx%d", i);
+
+		status = omap2_mcspi_request_dma(mcspi,
+						 &mcspi->dma_channels[i]);
+		if (status == -EPROBE_DEFER)
+			goto free_master;
 	}
 
 	status = platform_get_irq(pdev, 0);
@@ -1512,6 +1508,7 @@ disable_pm:
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 free_master:
+	omap2_mcspi_release_dma(master);
 	spi_master_put(master);
 	return status;
 }
@@ -1521,6 +1518,8 @@ static int omap2_mcspi_remove(struct platform_device *pdev)
 	struct spi_master *master = platform_get_drvdata(pdev);
 	struct omap2_mcspi *mcspi = spi_master_get_devdata(master);
 
+	omap2_mcspi_release_dma(master);
+
 	pm_runtime_dont_use_autosuspend(mcspi->dev);
 	pm_runtime_put_sync(mcspi->dev);
 	pm_runtime_disable(&pdev->dev);
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index cf459b79d81c..197d64228c7c 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -68,6 +68,10 @@ MODULE_ALIAS("platform:pxa2xx-spi");
 #define LPSS_CAPS_CS_EN_SHIFT			9
 #define LPSS_CAPS_CS_EN_MASK			(0xf << LPSS_CAPS_CS_EN_SHIFT)
 
+#define LPSS_PRIV_CLOCK_GATE 0x38
+#define LPSS_PRIV_CLOCK_GATE_CLK_CTL_MASK 0x3
+#define LPSS_PRIV_CLOCK_GATE_CLK_CTL_FORCE_ON 0x3
+
 struct lpss_config {
 	/* LPSS offset from drv_data->ioaddr */
 	unsigned offset;
@@ -84,6 +88,8 @@ struct lpss_config {
 	unsigned cs_sel_shift;
 	unsigned cs_sel_mask;
 	unsigned cs_num;
+	/* Quirks */
+	unsigned cs_clk_stays_gated : 1;
 };
 
 /* Keep these sorted with enum pxa_ssp_type */
@@ -142,6 +148,7 @@ static const struct lpss_config lpss_platforms[] = {
 		.tx_threshold_hi = 48,
 		.cs_sel_shift = 8,
 		.cs_sel_mask = 3 << 8,
+		.cs_clk_stays_gated = true,
 	},
 	{	/* LPSS_CNL_SSP */
 		.offset = 0x200,
@@ -154,6 +161,7 @@ static const struct lpss_config lpss_platforms[] = {
 		.tx_threshold_hi = 56,
 		.cs_sel_shift = 8,
 		.cs_sel_mask = 3 << 8,
+		.cs_clk_stays_gated = true,
 	},
 };
 
@@ -381,6 +389,22 @@ static void lpss_ssp_cs_control(struct spi_device *spi, bool enable)
 	else
 		value |= LPSS_CS_CONTROL_CS_HIGH;
 	__lpss_ssp_write_priv(drv_data, config->reg_cs_ctrl, value);
+	if (config->cs_clk_stays_gated) {
+		u32 clkgate;
+
+		/*
+		 * Changing CS alone when dynamic clock gating is on won't
+		 * actually flip CS at that time. This ruins SPI transfers
+		 * that specify delays, or have no data. Toggle the clock mode
+		 * to force on briefly to poke the CS pin to move.
+		 */
+		clkgate = __lpss_ssp_read_priv(drv_data, LPSS_PRIV_CLOCK_GATE);
+		value = (clkgate & ~LPSS_PRIV_CLOCK_GATE_CLK_CTL_MASK) |
+			LPSS_PRIV_CLOCK_GATE_CLK_CTL_FORCE_ON;
+
+		__lpss_ssp_write_priv(drv_data, LPSS_PRIV_CLOCK_GATE, value);
+		__lpss_ssp_write_priv(drv_data, LPSS_PRIV_CLOCK_GATE, clkgate);
+	}
 }
 
 static void cs_assert(struct spi_device *spi)
@@ -1437,6 +1461,10 @@ static const struct pci_device_id pxa2xx_spi_pci_compound_match[] = {
 	{ PCI_VDEVICE(INTEL, 0x34aa), LPSS_CNL_SSP },
 	{ PCI_VDEVICE(INTEL, 0x34ab), LPSS_CNL_SSP },
 	{ PCI_VDEVICE(INTEL, 0x34fb), LPSS_CNL_SSP },
+	/* JSL */
+	{ PCI_VDEVICE(INTEL, 0x4daa), LPSS_CNL_SSP },
+	{ PCI_VDEVICE(INTEL, 0x4dab), LPSS_CNL_SSP },
+	{ PCI_VDEVICE(INTEL, 0x4dfb), LPSS_CNL_SSP },
 	/* APL */
 	{ PCI_VDEVICE(INTEL, 0x5ac2), LPSS_BXT_SSP },
 	{ PCI_VDEVICE(INTEL, 0x5ac4), LPSS_BXT_SSP },
@@ -1453,6 +1481,10 @@ static const struct pci_device_id pxa2xx_spi_pci_compound_match[] = {
 	{ PCI_VDEVICE(INTEL, 0x02aa), LPSS_CNL_SSP },
 	{ PCI_VDEVICE(INTEL, 0x02ab), LPSS_CNL_SSP },
 	{ PCI_VDEVICE(INTEL, 0x02fb), LPSS_CNL_SSP },
+	/* CML-H */
+	{ PCI_VDEVICE(INTEL, 0x06aa), LPSS_CNL_SSP },
+	{ PCI_VDEVICE(INTEL, 0x06ab), LPSS_CNL_SSP },
+	{ PCI_VDEVICE(INTEL, 0x06fb), LPSS_CNL_SSP },
 	/* TGL-LP */
 	{ PCI_VDEVICE(INTEL, 0xa0aa), LPSS_CNL_SSP },
 	{ PCI_VDEVICE(INTEL, 0xa0ab), LPSS_CNL_SSP },
@@ -1604,6 +1636,11 @@ static int pxa2xx_spi_fw_translate_cs(struct spi_controller *controller,
 	return cs;
 }
 
+static size_t pxa2xx_spi_max_dma_transfer_size(struct spi_device *spi)
+{
+	return MAX_DMA_LEN;
+}
+
 static int pxa2xx_spi_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -1709,6 +1746,8 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
 		} else {
 			controller->can_dma = pxa2xx_spi_can_dma;
 			controller->max_dma_len = MAX_DMA_LEN;
+			controller->max_transfer_size =
+				pxa2xx_spi_max_dma_transfer_size;
 		}
 	}
 
@@ -1828,7 +1867,7 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
 
 	/* Register with the SPI framework */
 	platform_set_drvdata(pdev, drv_data);
-	status = devm_spi_register_controller(&pdev->dev, controller);
+	status = spi_register_controller(controller);
 	if (status != 0) {
 		dev_err(&pdev->dev, "problem registering spi controller\n");
 		goto out_error_pm_runtime_enabled;
@@ -1837,7 +1876,6 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
 	return status;
 
 out_error_pm_runtime_enabled:
-	pm_runtime_put_noidle(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 
 out_error_clock_enabled:
@@ -1864,6 +1902,8 @@ static int pxa2xx_spi_remove(struct platform_device *pdev)
 
 	pm_runtime_get_sync(&pdev->dev);
 
+	spi_unregister_controller(drv_data->controller);
+
 	/* Disable the SSP at the peripheral and SOC level */
 	pxa2xx_spi_write(drv_data, SSCR0, 0);
 	clk_disable_unprepare(ssp->clk);
diff --git a/drivers/spi/spi-qup.c b/drivers/spi/spi-qup.c
index f22dbb4b87a5..33d195f06f7a 100644
--- a/drivers/spi/spi-qup.c
+++ b/drivers/spi/spi-qup.c
@@ -1182,6 +1182,11 @@ static int spi_qup_suspend(struct device *device)
 	struct spi_qup *controller = spi_master_get_devdata(master);
 	int ret;
 
+	if (pm_runtime_suspended(device)) {
+		ret = spi_qup_pm_resume_runtime(device);
+		if (ret)
+			return ret;
+	}
 	ret = spi_master_suspend(master);
 	if (ret)
 		return ret;
@@ -1190,10 +1195,8 @@ static int spi_qup_suspend(struct device *device)
 	if (ret)
 		return ret;
 
-	if (!pm_runtime_suspended(device)) {
-		clk_disable_unprepare(controller->cclk);
-		clk_disable_unprepare(controller->iclk);
-	}
+	clk_disable_unprepare(controller->cclk);
+	clk_disable_unprepare(controller->iclk);
 	return 0;
 }
 
diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c
index 2cc6d9951b52..008b64f4e031 100644
--- a/drivers/spi/spi-rockchip.c
+++ b/drivers/spi/spi-rockchip.c
@@ -286,7 +286,7 @@ static void rockchip_spi_pio_writer(struct rockchip_spi *rs)
 static void rockchip_spi_pio_reader(struct rockchip_spi *rs)
 {
 	u32 words = readl_relaxed(rs->regs + ROCKCHIP_SPI_RXFLR);
-	u32 rx_left = rs->rx_left - words;
+	u32 rx_left = (rs->rx_left > words) ? rs->rx_left - words : 0;
 
 	/* the hardware doesn't allow us to change fifo threshold
 	 * level while spi is enabled, so instead make sure to leave
diff --git a/drivers/spi/spi-rspi.c b/drivers/spi/spi-rspi.c
index 15f5723d9f95..7222c7689c3c 100644
--- a/drivers/spi/spi-rspi.c
+++ b/drivers/spi/spi-rspi.c
@@ -1257,9 +1257,9 @@ static int rspi_probe(struct platform_device *pdev)
 	ctlr->flags = ops->flags;
 	ctlr->dev.of_node = pdev->dev.of_node;
 
-	ret = platform_get_irq_byname(pdev, "rx");
+	ret = platform_get_irq_byname_optional(pdev, "rx");
 	if (ret < 0) {
-		ret = platform_get_irq_byname(pdev, "mux");
+		ret = platform_get_irq_byname_optional(pdev, "mux");
 		if (ret < 0)
 			ret = platform_get_irq(pdev, 0);
 		if (ret >= 0)
@@ -1270,10 +1270,6 @@ static int rspi_probe(struct platform_device *pdev)
 		if (ret >= 0)
 			rspi->tx_irq = ret;
 	}
-	if (ret < 0) {
-		dev_err(&pdev->dev, "platform_get_irq error\n");
-		goto error2;
-	}
 
 	if (rspi->rx_irq == rspi->tx_irq) {
 		/* Single multiplexed interrupt */
diff --git a/drivers/spi/spi-sprd-adi.c b/drivers/spi/spi-sprd-adi.c
index f1fc2bde6ef3..e41976010dc4 100644
--- a/drivers/spi/spi-sprd-adi.c
+++ b/drivers/spi/spi-sprd-adi.c
@@ -358,9 +358,9 @@ static int sprd_adi_restart_handler(struct notifier_block *this,
 	sprd_adi_write(sadi, sadi->slave_pbase + REG_WDG_LOCK, WDG_UNLOCK_KEY);
 
 	/* Load the watchdog timeout value, 50ms is always enough. */
+	sprd_adi_write(sadi, sadi->slave_pbase + REG_WDG_LOAD_HIGH, 0);
 	sprd_adi_write(sadi, sadi->slave_pbase + REG_WDG_LOAD_LOW,
 		       WDG_LOAD_VAL & WDG_LOAD_MASK);
-	sprd_adi_write(sadi, sadi->slave_pbase + REG_WDG_LOAD_HIGH, 0);
 
 	/* Start the watchdog to reset system */
 	sprd_adi_read(sadi, sadi->slave_pbase + REG_WDG_CTRL, &val);
diff --git a/drivers/spi/spi-sprd.c b/drivers/spi/spi-sprd.c
index 1b7eebb72c07..12ee921204d8 100644
--- a/drivers/spi/spi-sprd.c
+++ b/drivers/spi/spi-sprd.c
@@ -674,7 +674,7 @@ static void sprd_spi_init_hw(struct sprd_spi *ss, struct spi_transfer *t)
 	u16 word_delay, interval;
 	u32 val;
 
-	val = readl_relaxed(ss->base + SPRD_SPI_CTL7);
+	val = readl_relaxed(ss->base + SPRD_SPI_CTL0);
 	val &= ~(SPRD_SPI_SCK_REV | SPRD_SPI_NG_TX | SPRD_SPI_NG_RX);
 	/* Set default chip selection, clock phase and clock polarity */
 	val |= ss->hw_mode & SPI_CPHA ? SPRD_SPI_NG_RX : SPRD_SPI_NG_TX;
diff --git a/drivers/spi/spi-sun6i.c b/drivers/spi/spi-sun6i.c
index ee2bdaf5b856..2d361af9140e 100644
--- a/drivers/spi/spi-sun6i.c
+++ b/drivers/spi/spi-sun6i.c
@@ -198,7 +198,7 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 				  struct spi_transfer *tfr)
 {
 	struct sun6i_spi *sspi = spi_master_get_devdata(master);
-	unsigned int mclk_rate, div, timeout;
+	unsigned int mclk_rate, div, div_cdr1, div_cdr2, timeout;
 	unsigned int start, end, tx_time;
 	unsigned int trig_level;
 	unsigned int tx_len = 0;
@@ -287,14 +287,12 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 	 * First try CDR2, and if we can't reach the expected
 	 * frequency, fall back to CDR1.
 	 */
-	div = mclk_rate / (2 * tfr->speed_hz);
-	if (div <= (SUN6I_CLK_CTL_CDR2_MASK + 1)) {
-		if (div > 0)
-			div--;
-
-		reg = SUN6I_CLK_CTL_CDR2(div) | SUN6I_CLK_CTL_DRS;
+	div_cdr1 = DIV_ROUND_UP(mclk_rate, tfr->speed_hz);
+	div_cdr2 = DIV_ROUND_UP(div_cdr1, 2);
+	if (div_cdr2 <= (SUN6I_CLK_CTL_CDR2_MASK + 1)) {
+		reg = SUN6I_CLK_CTL_CDR2(div_cdr2 - 1) | SUN6I_CLK_CTL_DRS;
 	} else {
-		div = ilog2(mclk_rate) - ilog2(tfr->speed_hz);
+		div = min(SUN6I_CLK_CTL_CDR1_MASK, order_base_2(div_cdr1));
 		reg = SUN6I_CLK_CTL_CDR1(div);
 	}
 
diff --git a/drivers/spi/spi-ti-qspi.c b/drivers/spi/spi-ti-qspi.c
index 6ca600702470..dd698b99ce03 100644
--- a/drivers/spi/spi-ti-qspi.c
+++ b/drivers/spi/spi-ti-qspi.c
@@ -62,6 +62,7 @@ struct ti_qspi {
 	u32 dc;
 
 	bool mmap_enabled;
+	int current_cs;
 };
 
 #define QSPI_PID			(0x0)
@@ -487,6 +488,7 @@ static void ti_qspi_enable_memory_map(struct spi_device *spi)
 				   MEM_CS_EN(spi->chip_select));
 	}
 	qspi->mmap_enabled = true;
+	qspi->current_cs = spi->chip_select;
 }
 
 static void ti_qspi_disable_memory_map(struct spi_device *spi)
@@ -498,6 +500,7 @@ static void ti_qspi_disable_memory_map(struct spi_device *spi)
 		regmap_update_bits(qspi->ctrl_base, qspi->ctrl_reg,
 				   MEM_CS_MASK, 0);
 	qspi->mmap_enabled = false;
+	qspi->current_cs = -1;
 }
 
 static void ti_qspi_setup_mmap_read(struct spi_device *spi, u8 opcode,
@@ -543,7 +546,7 @@ static int ti_qspi_exec_mem_op(struct spi_mem *mem,
 
 	mutex_lock(&qspi->list_lock);
 
-	if (!qspi->mmap_enabled)
+	if (!qspi->mmap_enabled || qspi->current_cs != mem->spi->chip_select)
 		ti_qspi_enable_memory_map(mem->spi);
 	ti_qspi_setup_mmap_read(mem->spi, op->cmd.opcode, op->data.buswidth,
 				op->addr.nbytes, op->dummy.nbytes);
@@ -800,6 +803,7 @@ no_dma:
 		}
 	}
 	qspi->mmap_enabled = false;
+	qspi->current_cs = -1;
 
 	ret = devm_spi_register_master(&pdev->dev, master);
 	if (!ret)
diff --git a/drivers/spi/spi-zynqmp-gqspi.c b/drivers/spi/spi-zynqmp-gqspi.c
index 07a83ca164c2..ddf408a6b60c 100644
--- a/drivers/spi/spi-zynqmp-gqspi.c
+++ b/drivers/spi/spi-zynqmp-gqspi.c
@@ -401,9 +401,6 @@ static void zynqmp_qspi_chipselect(struct spi_device *qspi, bool is_high)
 
 	zynqmp_gqspi_write(xqspi, GQSPI_GEN_FIFO_OFST, genfifoentry);
 
-	/* Dummy generic FIFO entry */
-	zynqmp_gqspi_write(xqspi, GQSPI_GEN_FIFO_OFST, 0x0);
-
 	/* Manually start the generic FIFO command */
 	zynqmp_gqspi_write(xqspi, GQSPI_CONFIG_OFST,
 			zynqmp_gqspi_read(xqspi, GQSPI_CONFIG_OFST) |
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 6ae55113672f..be5b4b65c016 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1862,6 +1862,7 @@ static int acpi_spi_add_resource(struct acpi_resource *ares, void *data)
 			}
 
 			spi->max_speed_hz = sb->connection_speed;
+			spi->bits_per_word = sb->data_bit_length;
 
 			if (sb->clock_phase == ACPI_SPI_SECOND_PHASE)
 				spi->mode |= SPI_CPHA;
@@ -2343,7 +2344,7 @@ int spi_register_controller(struct spi_controller *ctlr)
 		if (ctlr->use_gpio_descriptors) {
 			status = spi_get_gpio_descs(ctlr);
 			if (status)
-				return status;
+				goto free_bus_id;
 			/*
 			 * A controller using GPIO descriptors always
 			 * supports SPI_CS_HIGH if need be.
@@ -2353,7 +2354,7 @@ int spi_register_controller(struct spi_controller *ctlr)
 			/* Legacy code path for GPIOs from DT */
 			status = of_spi_register_master(ctlr);
 			if (status)
-				return status;
+				goto free_bus_id;
 		}
 	}
 
@@ -2361,17 +2362,14 @@ int spi_register_controller(struct spi_controller *ctlr)
 	 * Even if it's just one always-selected device, there must
 	 * be at least one chipselect.
 	 */
-	if (!ctlr->num_chipselect)
-		return -EINVAL;
+	if (!ctlr->num_chipselect) {
+		status = -EINVAL;
+		goto free_bus_id;
+	}
 
 	status = device_add(&ctlr->dev);
-	if (status < 0) {
-		/* free bus id */
-		mutex_lock(&board_lock);
-		idr_remove(&spi_master_idr, ctlr->bus_num);
-		mutex_unlock(&board_lock);
-		goto done;
-	}
+	if (status < 0)
+		goto free_bus_id;
 	dev_dbg(dev, "registered %s %s\n",
 			spi_controller_is_slave(ctlr) ? "slave" : "master",
 			dev_name(&ctlr->dev));
@@ -2387,11 +2385,7 @@ int spi_register_controller(struct spi_controller *ctlr)
 		status = spi_controller_initialize_queue(ctlr);
 		if (status) {
 			device_del(&ctlr->dev);
-			/* free bus id */
-			mutex_lock(&board_lock);
-			idr_remove(&spi_master_idr, ctlr->bus_num);
-			mutex_unlock(&board_lock);
-			goto done;
+			goto free_bus_id;
 		}
 	}
 	/* add statistics */
@@ -2406,7 +2400,12 @@ int spi_register_controller(struct spi_controller *ctlr)
 	/* Register devices from the device tree and ACPI */
 	of_register_spi_devices(ctlr);
 	acpi_register_spi_devices(ctlr);
-done:
+	return status;
+
+free_bus_id:
+	mutex_lock(&board_lock);
+	idr_remove(&spi_master_idr, ctlr->bus_num);
+	mutex_unlock(&board_lock);
 	return status;
 }
 EXPORT_SYMBOL_GPL(spi_register_controller);
@@ -2473,7 +2472,8 @@ void spi_unregister_controller(struct spi_controller *ctlr)
 {
 	struct spi_controller *found;
 	int id = ctlr->bus_num;
-	int dummy;
+
+	device_for_each_child(&ctlr->dev, NULL, __unregister);
 
 	/* First make sure that this controller was ever added */
 	mutex_lock(&board_lock);
@@ -2487,7 +2487,6 @@ void spi_unregister_controller(struct spi_controller *ctlr)
 	list_del(&ctlr->list);
 	mutex_unlock(&board_lock);
 
-	dummy = device_for_each_child(&ctlr->dev, NULL, __unregister);
 	device_unregister(&ctlr->dev);
 	/* free bus id */
 	mutex_lock(&board_lock);
diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
index 8368a30413a2..c62576ce2a88 100644
--- a/drivers/spi/spidev.c
+++ b/drivers/spi/spidev.c
@@ -223,6 +223,11 @@ static int spidev_message(struct spidev_data *spidev,
 	for (n = n_xfers, k_tmp = k_xfers, u_tmp = u_xfers;
 			n;
 			n--, k_tmp++, u_tmp++) {
+		/* Ensure that also following allocations from rx_buf/tx_buf will meet
+		 * DMA alignment requirements.
+		 */
+		unsigned int len_aligned = ALIGN(u_tmp->len, ARCH_KMALLOC_MINALIGN);
+
 		k_tmp->len = u_tmp->len;
 
 		total += k_tmp->len;
@@ -238,17 +243,17 @@ static int spidev_message(struct spidev_data *spidev,
 
 		if (u_tmp->rx_buf) {
 			/* this transfer needs space in RX bounce buffer */
-			rx_total += k_tmp->len;
+			rx_total += len_aligned;
 			if (rx_total > bufsiz) {
 				status = -EMSGSIZE;
 				goto done;
 			}
 			k_tmp->rx_buf = rx_buf;
-			rx_buf += k_tmp->len;
+			rx_buf += len_aligned;
 		}
 		if (u_tmp->tx_buf) {
 			/* this transfer needs space in TX bounce buffer */
-			tx_total += k_tmp->len;
+			tx_total += len_aligned;
 			if (tx_total > bufsiz) {
 				status = -EMSGSIZE;
 				goto done;
@@ -258,7 +263,7 @@ static int spidev_message(struct spidev_data *spidev,
 						(uintptr_t) u_tmp->tx_buf,
 					u_tmp->len))
 				goto done;
-			tx_buf += k_tmp->len;
+			tx_buf += len_aligned;
 		}
 
 		k_tmp->cs_change = !!u_tmp->cs_change;
@@ -290,16 +295,16 @@ static int spidev_message(struct spidev_data *spidev,
 		goto done;
 
 	/* copy any rx data out of bounce buffer */
-	rx_buf = spidev->rx_buffer;
-	for (n = n_xfers, u_tmp = u_xfers; n; n--, u_tmp++) {
+	for (n = n_xfers, k_tmp = k_xfers, u_tmp = u_xfers;
+			n;
+			n--, k_tmp++, u_tmp++) {
 		if (u_tmp->rx_buf) {
 			if (copy_to_user((u8 __user *)
-					(uintptr_t) u_tmp->rx_buf, rx_buf,
+					(uintptr_t) u_tmp->rx_buf, k_tmp->rx_buf,
 					u_tmp->len)) {
 				status = -EFAULT;
 				goto done;
 			}
-			rx_buf += u_tmp->len;
 		}
 	}
 	status = total;
@@ -394,6 +399,7 @@ spidev_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		else
 			retval = get_user(tmp, (u32 __user *)arg);
 		if (retval == 0) {
+			struct spi_controller *ctlr = spi->controller;
 			u32	save = spi->mode;
 
 			if (tmp & ~SPI_MODE_MASK) {
@@ -401,6 +407,10 @@ spidev_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 				break;
 			}
 
+			if (ctlr->use_gpio_descriptors && ctlr->cs_gpiods &&
+			    ctlr->cs_gpiods[spi->chip_select])
+				tmp |= SPI_CS_HIGH;
+
 			tmp |= spi->mode & ~SPI_MODE_MASK;
 			spi->mode = (u16)tmp;
 			retval = spi_setup(spi);
@@ -600,15 +610,20 @@ err_find_dev:
 static int spidev_release(struct inode *inode, struct file *filp)
 {
 	struct spidev_data	*spidev;
+	int			dofree;
 
 	mutex_lock(&device_list_lock);
 	spidev = filp->private_data;
 	filp->private_data = NULL;
 
+	spin_lock_irq(&spidev->spi_lock);
+	/* ... after we unbound from the underlying device? */
+	dofree = (spidev->spi == NULL);
+	spin_unlock_irq(&spidev->spi_lock);
+
 	/* last close? */
 	spidev->users--;
 	if (!spidev->users) {
-		int		dofree;
 
 		kfree(spidev->tx_buffer);
 		spidev->tx_buffer = NULL;
@@ -616,19 +631,14 @@ static int spidev_release(struct inode *inode, struct file *filp)
 		kfree(spidev->rx_buffer);
 		spidev->rx_buffer = NULL;
 
-		spin_lock_irq(&spidev->spi_lock);
-		if (spidev->spi)
-			spidev->speed_hz = spidev->spi->max_speed_hz;
-
-		/* ... after we unbound from the underlying device? */
-		dofree = (spidev->spi == NULL);
-		spin_unlock_irq(&spidev->spi_lock);
-
 		if (dofree)
 			kfree(spidev);
+		else
+			spidev->speed_hz = spidev->spi->max_speed_hz;
 	}
 #ifdef CONFIG_SPI_SLAVE
-	spi_slave_abort(spidev->spi);
+	if (!dofree)
+		spi_slave_abort(spidev->spi);
 #endif
 	mutex_unlock(&device_list_lock);
 
@@ -776,13 +786,13 @@ static int spidev_remove(struct spi_device *spi)
 {
 	struct spidev_data	*spidev = spi_get_drvdata(spi);
 
+	/* prevent new opens */
+	mutex_lock(&device_list_lock);
 	/* make sure ops on existing fds can abort cleanly */
 	spin_lock_irq(&spidev->spi_lock);
 	spidev->spi = NULL;
 	spin_unlock_irq(&spidev->spi_lock);
 
-	/* prevent new opens */
-	mutex_lock(&device_list_lock);
 	list_del(&spidev->device_entry);
 	device_destroy(spidev_class, spidev->devt);
 	clear_bit(MINOR(spidev->devt), minors);
diff --git a/drivers/spmi/spmi-pmic-arb.c b/drivers/spmi/spmi-pmic-arb.c
index 97acc2ba2912..de844b412110 100644
--- a/drivers/spmi/spmi-pmic-arb.c
+++ b/drivers/spmi/spmi-pmic-arb.c
@@ -731,6 +731,7 @@ static int qpnpint_irq_domain_translate(struct irq_domain *d,
 	return 0;
 }
 
+static struct lock_class_key qpnpint_irq_lock_class, qpnpint_irq_request_class;
 
 static void qpnpint_irq_domain_map(struct spmi_pmic_arb *pmic_arb,
 				   struct irq_domain *domain, unsigned int virq,
@@ -746,6 +747,9 @@ static void qpnpint_irq_domain_map(struct spmi_pmic_arb *pmic_arb,
 	else
 		handler = handle_level_irq;
 
+
+	irq_set_lockdep_class(virq, &qpnpint_irq_lock_class,
+			      &qpnpint_irq_request_class);
 	irq_domain_set_info(domain, virq, hwirq, &pmic_arb_irqchip, pmic_arb,
 			    handler, NULL, NULL);
 }
diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c
index 74d497d39c5a..19b0cc5ea33f 100644
--- a/drivers/staging/android/ashmem.c
+++ b/drivers/staging/android/ashmem.c
@@ -95,6 +95,15 @@ static DEFINE_MUTEX(ashmem_mutex);
 static struct kmem_cache *ashmem_area_cachep __read_mostly;
 static struct kmem_cache *ashmem_range_cachep __read_mostly;
 
+/*
+ * A separate lockdep class for the backing shmem inodes to resolve the lockdep
+ * warning about the race between kswapd taking fs_reclaim before inode_lock
+ * and write syscall taking inode_lock and then fs_reclaim.
+ * Note that such race is impossible because ashmem does not support write
+ * syscalls operating on the backing shmem.
+ */
+static struct lock_class_key backing_shmem_inode_class;
+
 static inline unsigned long range_size(struct ashmem_range *range)
 {
 	return range->pgend - range->pgstart + 1;
@@ -351,8 +360,23 @@ static inline vm_flags_t calc_vm_may_flags(unsigned long prot)
 	       _calc_vm_trans(prot, PROT_EXEC,  VM_MAYEXEC);
 }
 
+static int ashmem_vmfile_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	/* do not allow to mmap ashmem backing shmem file directly */
+	return -EPERM;
+}
+
+static unsigned long
+ashmem_vmfile_get_unmapped_area(struct file *file, unsigned long addr,
+				unsigned long len, unsigned long pgoff,
+				unsigned long flags)
+{
+	return current->mm->get_unmapped_area(file, addr, len, pgoff, flags);
+}
+
 static int ashmem_mmap(struct file *file, struct vm_area_struct *vma)
 {
+	static struct file_operations vmfile_fops;
 	struct ashmem_area *asma = file->private_data;
 	int ret = 0;
 
@@ -381,6 +405,7 @@ static int ashmem_mmap(struct file *file, struct vm_area_struct *vma)
 	if (!asma->file) {
 		char *name = ASHMEM_NAME_DEF;
 		struct file *vmfile;
+		struct inode *inode;
 
 		if (asma->name[ASHMEM_NAME_PREFIX_LEN] != '\0')
 			name = asma->name;
@@ -392,7 +417,22 @@ static int ashmem_mmap(struct file *file, struct vm_area_struct *vma)
 			goto out;
 		}
 		vmfile->f_mode |= FMODE_LSEEK;
+		inode = file_inode(vmfile);
+		lockdep_set_class(&inode->i_rwsem, &backing_shmem_inode_class);
 		asma->file = vmfile;
+		/*
+		 * override mmap operation of the vmfile so that it can't be
+		 * remapped which would lead to creation of a new vma with no
+		 * asma permission checks. Have to override get_unmapped_area
+		 * as well to prevent VM_BUG_ON check for f_ops modification.
+		 */
+		if (!vmfile_fops.mmap) {
+			vmfile_fops = *vmfile->f_op;
+			vmfile_fops.mmap = ashmem_vmfile_mmap;
+			vmfile_fops.get_unmapped_area =
+					ashmem_vmfile_get_unmapped_area;
+		}
+		vmfile->f_op = &vmfile_fops;
 	}
 	get_file(asma->file);
 
diff --git a/drivers/staging/android/ion/ion_heap.c b/drivers/staging/android/ion/ion_heap.c
index 473b465724f1..0755b11348ed 100644
--- a/drivers/staging/android/ion/ion_heap.c
+++ b/drivers/staging/android/ion/ion_heap.c
@@ -99,12 +99,12 @@ int ion_heap_map_user(struct ion_heap *heap, struct ion_buffer *buffer,
 
 static int ion_heap_clear_pages(struct page **pages, int num, pgprot_t pgprot)
 {
-	void *addr = vm_map_ram(pages, num, -1, pgprot);
+	void *addr = vmap(pages, num, VM_MAP, pgprot);
 
 	if (!addr)
 		return -ENOMEM;
 	memset(addr, 0, PAGE_SIZE * num);
-	vm_unmap_ram(addr, num);
+	vunmap(addr);
 
 	return 0;
 }
diff --git a/drivers/staging/axis-fifo/Kconfig b/drivers/staging/axis-fifo/Kconfig
index 3fffe4d6f327..f180a8e9f58a 100644
--- a/drivers/staging/axis-fifo/Kconfig
+++ b/drivers/staging/axis-fifo/Kconfig
@@ -4,7 +4,7 @@
 #
 config XIL_AXIS_FIFO
 	tristate "Xilinx AXI-Stream FIFO IP core driver"
-	depends on OF
+	depends on OF && HAS_IOMEM
 	help
 	  This adds support for the Xilinx AXI-Stream FIFO IP core driver.
 	  The AXI Streaming FIFO allows memory mapped access to a AXI Streaming
diff --git a/drivers/staging/comedi/comedi_fops.c b/drivers/staging/comedi/comedi_fops.c
index f6d1287c7b83..549eac18d0aa 100644
--- a/drivers/staging/comedi/comedi_fops.c
+++ b/drivers/staging/comedi/comedi_fops.c
@@ -2712,8 +2712,10 @@ static int comedi_open(struct inode *inode, struct file *file)
 	}
 
 	cfp = kzalloc(sizeof(*cfp), GFP_KERNEL);
-	if (!cfp)
+	if (!cfp) {
+		comedi_dev_put(dev);
 		return -ENOMEM;
+	}
 
 	cfp->dev = dev;
 
diff --git a/drivers/staging/comedi/drivers/addi_apci_1032.c b/drivers/staging/comedi/drivers/addi_apci_1032.c
index 560649be9d13..e035c9f757a1 100644
--- a/drivers/staging/comedi/drivers/addi_apci_1032.c
+++ b/drivers/staging/comedi/drivers/addi_apci_1032.c
@@ -106,14 +106,22 @@ static int apci1032_cos_insn_config(struct comedi_device *dev,
 				    unsigned int *data)
 {
 	struct apci1032_private *devpriv = dev->private;
-	unsigned int shift, oldmask;
+	unsigned int shift, oldmask, himask, lomask;
 
 	switch (data[0]) {
 	case INSN_CONFIG_DIGITAL_TRIG:
 		if (data[1] != 0)
 			return -EINVAL;
 		shift = data[3];
-		oldmask = (1U << shift) - 1;
+		if (shift < 32) {
+			oldmask = (1U << shift) - 1;
+			himask = data[4] << shift;
+			lomask = data[5] << shift;
+		} else {
+			oldmask = 0xffffffffu;
+			himask = 0;
+			lomask = 0;
+		}
 		switch (data[2]) {
 		case COMEDI_DIGITAL_TRIG_DISABLE:
 			devpriv->ctrl = 0;
@@ -136,8 +144,8 @@ static int apci1032_cos_insn_config(struct comedi_device *dev,
 				devpriv->mode2 &= oldmask;
 			}
 			/* configure specified channels */
-			devpriv->mode1 |= data[4] << shift;
-			devpriv->mode2 |= data[5] << shift;
+			devpriv->mode1 |= himask;
+			devpriv->mode2 |= lomask;
 			break;
 		case COMEDI_DIGITAL_TRIG_ENABLE_LEVELS:
 			if (devpriv->ctrl != (APCI1032_CTRL_INT_ENA |
@@ -154,8 +162,8 @@ static int apci1032_cos_insn_config(struct comedi_device *dev,
 				devpriv->mode2 &= oldmask;
 			}
 			/* configure specified channels */
-			devpriv->mode1 |= data[4] << shift;
-			devpriv->mode2 |= data[5] << shift;
+			devpriv->mode1 |= himask;
+			devpriv->mode2 |= lomask;
 			break;
 		default:
 			return -EINVAL;
diff --git a/drivers/staging/comedi/drivers/addi_apci_1500.c b/drivers/staging/comedi/drivers/addi_apci_1500.c
index 45ad4ba92f94..816dd25b9d0e 100644
--- a/drivers/staging/comedi/drivers/addi_apci_1500.c
+++ b/drivers/staging/comedi/drivers/addi_apci_1500.c
@@ -452,13 +452,14 @@ static int apci1500_di_cfg_trig(struct comedi_device *dev,
 	struct apci1500_private *devpriv = dev->private;
 	unsigned int trig = data[1];
 	unsigned int shift = data[3];
-	unsigned int hi_mask = data[4] << shift;
-	unsigned int lo_mask = data[5] << shift;
-	unsigned int chan_mask = hi_mask | lo_mask;
-	unsigned int old_mask = (1 << shift) - 1;
-	unsigned int pm = devpriv->pm[trig] & old_mask;
-	unsigned int pt = devpriv->pt[trig] & old_mask;
-	unsigned int pp = devpriv->pp[trig] & old_mask;
+	unsigned int hi_mask;
+	unsigned int lo_mask;
+	unsigned int chan_mask;
+	unsigned int old_mask;
+	unsigned int pm;
+	unsigned int pt;
+	unsigned int pp;
+	unsigned int invalid_chan;
 
 	if (trig > 1) {
 		dev_dbg(dev->class_dev,
@@ -466,11 +467,28 @@ static int apci1500_di_cfg_trig(struct comedi_device *dev,
 		return -EINVAL;
 	}
 
-	if (chan_mask > 0xffff) {
+	if (shift <= 16) {
+		hi_mask = data[4] << shift;
+		lo_mask = data[5] << shift;
+		old_mask = (1U << shift) - 1;
+		invalid_chan = (data[4] | data[5]) >> (16 - shift);
+	} else {
+		hi_mask = 0;
+		lo_mask = 0;
+		old_mask = 0xffff;
+		invalid_chan = data[4] | data[5];
+	}
+	chan_mask = hi_mask | lo_mask;
+
+	if (invalid_chan) {
 		dev_dbg(dev->class_dev, "invalid digital trigger channel\n");
 		return -EINVAL;
 	}
 
+	pm = devpriv->pm[trig] & old_mask;
+	pt = devpriv->pt[trig] & old_mask;
+	pp = devpriv->pp[trig] & old_mask;
+
 	switch (data[2]) {
 	case COMEDI_DIGITAL_TRIG_DISABLE:
 		/* clear trigger configuration */
diff --git a/drivers/staging/comedi/drivers/addi_apci_1564.c b/drivers/staging/comedi/drivers/addi_apci_1564.c
index 10501fe6bb25..1268ba34be5f 100644
--- a/drivers/staging/comedi/drivers/addi_apci_1564.c
+++ b/drivers/staging/comedi/drivers/addi_apci_1564.c
@@ -331,14 +331,22 @@ static int apci1564_cos_insn_config(struct comedi_device *dev,
 				    unsigned int *data)
 {
 	struct apci1564_private *devpriv = dev->private;
-	unsigned int shift, oldmask;
+	unsigned int shift, oldmask, himask, lomask;
 
 	switch (data[0]) {
 	case INSN_CONFIG_DIGITAL_TRIG:
 		if (data[1] != 0)
 			return -EINVAL;
 		shift = data[3];
-		oldmask = (1U << shift) - 1;
+		if (shift < 32) {
+			oldmask = (1U << shift) - 1;
+			himask = data[4] << shift;
+			lomask = data[5] << shift;
+		} else {
+			oldmask = 0xffffffffu;
+			himask = 0;
+			lomask = 0;
+		}
 		switch (data[2]) {
 		case COMEDI_DIGITAL_TRIG_DISABLE:
 			devpriv->ctrl = 0;
@@ -362,8 +370,8 @@ static int apci1564_cos_insn_config(struct comedi_device *dev,
 				devpriv->mode2 &= oldmask;
 			}
 			/* configure specified channels */
-			devpriv->mode1 |= data[4] << shift;
-			devpriv->mode2 |= data[5] << shift;
+			devpriv->mode1 |= himask;
+			devpriv->mode2 |= lomask;
 			break;
 		case COMEDI_DIGITAL_TRIG_ENABLE_LEVELS:
 			if (devpriv->ctrl != (APCI1564_DI_IRQ_ENA |
@@ -380,8 +388,8 @@ static int apci1564_cos_insn_config(struct comedi_device *dev,
 				devpriv->mode2 &= oldmask;
 			}
 			/* configure specified channels */
-			devpriv->mode1 |= data[4] << shift;
-			devpriv->mode2 |= data[5] << shift;
+			devpriv->mode1 |= himask;
+			devpriv->mode2 |= lomask;
 			break;
 		default:
 			return -EINVAL;
diff --git a/drivers/staging/comedi/drivers/adv_pci1710.c b/drivers/staging/comedi/drivers/adv_pci1710.c
index dbff0f7e7cf5..ddc0dc93d08b 100644
--- a/drivers/staging/comedi/drivers/adv_pci1710.c
+++ b/drivers/staging/comedi/drivers/adv_pci1710.c
@@ -46,8 +46,8 @@
 #define PCI171X_RANGE_UNI	BIT(4)
 #define PCI171X_RANGE_GAIN(x)	(((x) & 0x7) << 0)
 #define PCI171X_MUX_REG		0x04	/* W:   A/D multiplexor control */
-#define PCI171X_MUX_CHANH(x)	(((x) & 0xf) << 8)
-#define PCI171X_MUX_CHANL(x)	(((x) & 0xf) << 0)
+#define PCI171X_MUX_CHANH(x)	(((x) & 0xff) << 8)
+#define PCI171X_MUX_CHANL(x)	(((x) & 0xff) << 0)
 #define PCI171X_MUX_CHAN(x)	(PCI171X_MUX_CHANH(x) | PCI171X_MUX_CHANL(x))
 #define PCI171X_STATUS_REG	0x06	/* R:   status register */
 #define PCI171X_STATUS_IRQ	BIT(11)	/* 1=IRQ occurred */
diff --git a/drivers/staging/comedi/drivers/dt2815.c b/drivers/staging/comedi/drivers/dt2815.c
index 83026ba63d1c..78a7c1b3448a 100644
--- a/drivers/staging/comedi/drivers/dt2815.c
+++ b/drivers/staging/comedi/drivers/dt2815.c
@@ -92,6 +92,7 @@ static int dt2815_ao_insn(struct comedi_device *dev, struct comedi_subdevice *s,
 	int ret;
 
 	for (i = 0; i < insn->n; i++) {
+		/* FIXME: lo bit 0 chooses voltage output or current output */
 		lo = ((data[i] & 0x0f) << 4) | (chan << 1) | 0x01;
 		hi = (data[i] & 0xff0) >> 4;
 
@@ -105,6 +106,8 @@ static int dt2815_ao_insn(struct comedi_device *dev, struct comedi_subdevice *s,
 		if (ret)
 			return ret;
 
+		outb(hi, dev->iobase + DT2815_DATA);
+
 		devpriv->ao_readback[chan] = data[i];
 	}
 	return i;
diff --git a/drivers/staging/comedi/drivers/ni_6527.c b/drivers/staging/comedi/drivers/ni_6527.c
index 4d1eccb5041d..4518c2680b7c 100644
--- a/drivers/staging/comedi/drivers/ni_6527.c
+++ b/drivers/staging/comedi/drivers/ni_6527.c
@@ -332,7 +332,7 @@ static int ni6527_intr_insn_config(struct comedi_device *dev,
 		case COMEDI_DIGITAL_TRIG_ENABLE_EDGES:
 			/* check shift amount */
 			shift = data[3];
-			if (shift >= s->n_chan) {
+			if (shift >= 32) {
 				mask = 0;
 				rising = 0;
 				falling = 0;
diff --git a/drivers/staging/comedi/drivers/ni_routes.c b/drivers/staging/comedi/drivers/ni_routes.c
index eb61494dc2bd..88beb0d6c42b 100644
--- a/drivers/staging/comedi/drivers/ni_routes.c
+++ b/drivers/staging/comedi/drivers/ni_routes.c
@@ -74,9 +74,6 @@ static int ni_find_device_routes(const char *device_family,
 		}
 	}
 
-	if (!rv)
-		return -ENODATA;
-
 	/* Second, find the set of routes valid for this device. */
 	for (i = 0; ni_device_routes_list[i]; ++i) {
 		if (memcmp(ni_device_routes_list[i]->device, board_name,
@@ -86,12 +83,12 @@ static int ni_find_device_routes(const char *device_family,
 		}
 	}
 
-	if (!dr)
-		return -ENODATA;
-
 	tables->route_values = rv;
 	tables->valid_routes = dr;
 
+	if (!rv || !dr)
+		return -ENODATA;
+
 	return 0;
 }
 
@@ -489,6 +486,9 @@ int ni_find_route_source(const u8 src_sel_reg_value, int dest,
 {
 	int src;
 
+	if (!tables->route_values)
+		return -EINVAL;
+
 	dest = B(dest); /* subtract NI names offset */
 	/* ensure we are not going to under/over run the route value table */
 	if (dest < 0 || dest >= NI_NUM_NAMES)
diff --git a/drivers/staging/erofs/unzip_vle.h b/drivers/staging/erofs/unzip_vle.h
index 517e5ce8c5e9..3a096836cde0 100644
--- a/drivers/staging/erofs/unzip_vle.h
+++ b/drivers/staging/erofs/unzip_vle.h
@@ -169,22 +169,22 @@ static inline void z_erofs_onlinepage_init(struct page *page)
 static inline void z_erofs_onlinepage_fixup(struct page *page,
 	uintptr_t index, bool down)
 {
-	unsigned long *p, o, v, id;
-repeat:
-	p = &page_private(page);
-	o = READ_ONCE(*p);
+	union z_erofs_onlinepage_converter u = { .v = &page_private(page) };
+	int orig, orig_index, val;
 
-	id = o >> Z_EROFS_ONLINEPAGE_INDEX_SHIFT;
-	if (id) {
+repeat:
+	orig = atomic_read(u.o);
+	orig_index = orig >> Z_EROFS_ONLINEPAGE_INDEX_SHIFT;
+	if (orig_index) {
 		if (!index)
 			return;
 
-		BUG_ON(id != index);
+		DBG_BUGON(orig_index != index);
 	}
 
-	v = (index << Z_EROFS_ONLINEPAGE_INDEX_SHIFT) |
-		((o & Z_EROFS_ONLINEPAGE_COUNT_MASK) + (unsigned)down);
-	if (cmpxchg(p, o, v) != o)
+	val = (index << Z_EROFS_ONLINEPAGE_INDEX_SHIFT) |
+		((orig & Z_EROFS_ONLINEPAGE_COUNT_MASK) + (unsigned int)down);
+	if (atomic_cmpxchg(u.o, orig, val) != orig)
 		goto repeat;
 }
 
diff --git a/drivers/staging/erofs/utils.c b/drivers/staging/erofs/utils.c
index 3e7d30b6de1d..c6a7d0733eaa 100644
--- a/drivers/staging/erofs/utils.c
+++ b/drivers/staging/erofs/utils.c
@@ -312,7 +312,7 @@ static unsigned long erofs_shrink_scan(struct shrinker *shrink,
 		sbi->shrinker_run_no = run_no;
 
 #ifdef CONFIG_EROFS_FS_ZIP
-		freed += erofs_shrink_workstation(sbi, nr, false);
+		freed += erofs_shrink_workstation(sbi, nr - freed, false);
 #endif
 
 		spin_lock(&erofs_sb_list_lock);
diff --git a/Documentation/devicetree/bindings/fieldbus/arcx,anybus-controller.txt b/drivers/staging/fieldbus/Documentation/devicetree/bindings/fieldbus/arcx,anybus-controller.txt
index b1f9474f36d5..b1f9474f36d5 100644
--- a/Documentation/devicetree/bindings/fieldbus/arcx,anybus-controller.txt
+++ b/drivers/staging/fieldbus/Documentation/devicetree/bindings/fieldbus/arcx,anybus-controller.txt
diff --git a/drivers/staging/gasket/apex_driver.c b/drivers/staging/gasket/apex_driver.c
index 464648ee2036..0139c1e67341 100644
--- a/drivers/staging/gasket/apex_driver.c
+++ b/drivers/staging/gasket/apex_driver.c
@@ -572,13 +572,6 @@ static const struct pci_device_id apex_pci_ids[] = {
 	{ PCI_DEVICE(APEX_PCI_VENDOR_ID, APEX_PCI_DEVICE_ID) }, { 0 }
 };
 
-static void apex_pci_fixup_class(struct pci_dev *pdev)
-{
-	pdev->class = (PCI_CLASS_SYSTEM_OTHER << 8) | pdev->class;
-}
-DECLARE_PCI_FIXUP_CLASS_HEADER(APEX_PCI_VENDOR_ID, APEX_PCI_DEVICE_ID,
-			       PCI_CLASS_NOT_DEFINED, 8, apex_pci_fixup_class);
-
 static int apex_pci_probe(struct pci_dev *pci_dev,
 			  const struct pci_device_id *id)
 {
diff --git a/drivers/staging/gasket/gasket_core.c b/drivers/staging/gasket/gasket_core.c
index a445d58fb399..93deb8a1f39b 100644
--- a/drivers/staging/gasket/gasket_core.c
+++ b/drivers/staging/gasket/gasket_core.c
@@ -927,6 +927,10 @@ do_map_region(const struct gasket_dev *gasket_dev, struct vm_area_struct *vma,
 		gasket_get_bar_index(gasket_dev,
 				     (vma->vm_pgoff << PAGE_SHIFT) +
 				     driver_desc->legacy_mmap_address_offset);
+
+	if (bar_index < 0)
+		return DO_MAP_REGION_INVALID;
+
 	phys_base = gasket_dev->bar_data[bar_index].phys_base + phys_offset;
 	while (mapped_bytes < map_length) {
 		/*
diff --git a/drivers/staging/gasket/gasket_sysfs.c b/drivers/staging/gasket/gasket_sysfs.c
index a2d67c28f530..af26bc9f184a 100644
--- a/drivers/staging/gasket/gasket_sysfs.c
+++ b/drivers/staging/gasket/gasket_sysfs.c
@@ -228,8 +228,7 @@ int gasket_sysfs_create_entries(struct device *device,
 	}
 
 	mutex_lock(&mapping->mutex);
-	for (i = 0; strcmp(attrs[i].attr.attr.name, GASKET_ARRAY_END_MARKER);
-		i++) {
+	for (i = 0; attrs[i].attr.attr.name != NULL; i++) {
 		if (mapping->attribute_count == GASKET_SYSFS_MAX_NODES) {
 			dev_err(device,
 				"Maximum number of sysfs nodes reached for device\n");
@@ -340,6 +339,7 @@ void gasket_sysfs_put_attr(struct device *device,
 
 	dev_err(device, "Unable to put unknown attribute: %s\n",
 		attr->attr.attr.name);
+	put_mapping(mapping);
 }
 EXPORT_SYMBOL(gasket_sysfs_put_attr);
 
@@ -373,6 +373,7 @@ ssize_t gasket_sysfs_register_store(struct device *device,
 	gasket_dev = mapping->gasket_dev;
 	if (!gasket_dev) {
 		dev_err(device, "Device driver may have been removed\n");
+		put_mapping(mapping);
 		return 0;
 	}
 
diff --git a/drivers/staging/gasket/gasket_sysfs.h b/drivers/staging/gasket/gasket_sysfs.h
index 1d0eed66a7f4..ab5aa351d555 100644
--- a/drivers/staging/gasket/gasket_sysfs.h
+++ b/drivers/staging/gasket/gasket_sysfs.h
@@ -30,10 +30,6 @@
  */
 #define GASKET_SYSFS_MAX_NODES 196
 
-/* End markers for sysfs struct arrays. */
-#define GASKET_ARRAY_END_TOKEN GASKET_RESERVED_ARRAY_END
-#define GASKET_ARRAY_END_MARKER __stringify(GASKET_ARRAY_END_TOKEN)
-
 /*
  * Terminator struct for a gasket_sysfs_attr array. Must be at the end of
  * all gasket_sysfs_attribute arrays.
diff --git a/drivers/staging/greybus/audio_manager.c b/drivers/staging/greybus/audio_manager.c
index c2a4af4c1d06..57b293c0720d 100644
--- a/drivers/staging/greybus/audio_manager.c
+++ b/drivers/staging/greybus/audio_manager.c
@@ -92,8 +92,8 @@ void gb_audio_manager_remove_all(void)
 
 	list_for_each_entry_safe(module, next, &modules_list, list) {
 		list_del(&module->list);
-		kobject_put(&module->kobj);
 		ida_simple_remove(&module_id, module->id);
+		kobject_put(&module->kobj);
 	}
 
 	is_empty = list_empty(&modules_list);
diff --git a/drivers/staging/greybus/light.c b/drivers/staging/greybus/light.c
index 010ae1e9c7fb..3bd6e0f05bf0 100644
--- a/drivers/staging/greybus/light.c
+++ b/drivers/staging/greybus/light.c
@@ -1028,7 +1028,8 @@ static int gb_lights_light_config(struct gb_lights *glights, u8 id)
 
 	light->channels_count = conf.channel_count;
 	light->name = kstrndup(conf.name, NAMES_MAX, GFP_KERNEL);
-
+	if (!light->name)
+		return -ENOMEM;
 	light->channels = kcalloc(light->channels_count,
 				  sizeof(struct gb_channel), GFP_KERNEL);
 	if (!light->channels)
diff --git a/drivers/staging/greybus/sdio.c b/drivers/staging/greybus/sdio.c
index a097a8916b3b..3c321345d683 100644
--- a/drivers/staging/greybus/sdio.c
+++ b/drivers/staging/greybus/sdio.c
@@ -411,6 +411,7 @@ static int gb_sdio_command(struct gb_sdio_host *host, struct mmc_command *cmd)
 	struct gb_sdio_command_request request = {0};
 	struct gb_sdio_command_response response;
 	struct mmc_data *data = host->mrq->data;
+	unsigned int timeout_ms;
 	u8 cmd_flags;
 	u8 cmd_type;
 	int i;
@@ -469,9 +470,12 @@ static int gb_sdio_command(struct gb_sdio_host *host, struct mmc_command *cmd)
 		request.data_blksz = cpu_to_le16(data->blksz);
 	}
 
-	ret = gb_operation_sync(host->connection, GB_SDIO_TYPE_COMMAND,
-				&request, sizeof(request), &response,
-				sizeof(response));
+	timeout_ms = cmd->busy_timeout ? cmd->busy_timeout :
+		GB_OPERATION_TIMEOUT_DEFAULT;
+
+	ret = gb_operation_sync_timeout(host->connection, GB_SDIO_TYPE_COMMAND,
+					&request, sizeof(request), &response,
+					sizeof(response), timeout_ms);
 	if (ret < 0)
 		goto out;
 
diff --git a/drivers/staging/greybus/tools/loopback_test.c b/drivers/staging/greybus/tools/loopback_test.c
index 2fa88092514d..fadb5735fd39 100644
--- a/drivers/staging/greybus/tools/loopback_test.c
+++ b/drivers/staging/greybus/tools/loopback_test.c
@@ -21,6 +21,7 @@
 #include <signal.h>
 
 #define MAX_NUM_DEVICES 10
+#define MAX_SYSFS_PREFIX 0x80
 #define MAX_SYSFS_PATH	0x200
 #define CSV_MAX_LINE	0x1000
 #define SYSFS_MAX_INT	0x20
@@ -69,7 +70,7 @@ struct loopback_results {
 };
 
 struct loopback_device {
-	char name[MAX_SYSFS_PATH];
+	char name[MAX_STR_LEN];
 	char sysfs_entry[MAX_SYSFS_PATH];
 	char debugfs_entry[MAX_SYSFS_PATH];
 	struct loopback_results results;
@@ -95,8 +96,8 @@ struct loopback_test {
 	int stop_all;
 	int poll_count;
 	char test_name[MAX_STR_LEN];
-	char sysfs_prefix[MAX_SYSFS_PATH];
-	char debugfs_prefix[MAX_SYSFS_PATH];
+	char sysfs_prefix[MAX_SYSFS_PREFIX];
+	char debugfs_prefix[MAX_SYSFS_PREFIX];
 	struct timespec poll_timeout;
 	struct loopback_device devices[MAX_NUM_DEVICES];
 	struct loopback_results aggregate_results;
@@ -645,7 +646,7 @@ baddir:
 static int open_poll_files(struct loopback_test *t)
 {
 	struct loopback_device *dev;
-	char buf[MAX_STR_LEN];
+	char buf[MAX_SYSFS_PATH + MAX_STR_LEN];
 	char dummy;
 	int fds_idx = 0;
 	int i;
@@ -663,7 +664,7 @@ static int open_poll_files(struct loopback_test *t)
 			goto err;
 		}
 		read(t->fds[fds_idx].fd, &dummy, 1);
-		t->fds[fds_idx].events = EPOLLERR|EPOLLPRI;
+		t->fds[fds_idx].events = POLLERR | POLLPRI;
 		t->fds[fds_idx].revents = 0;
 		fds_idx++;
 	}
@@ -756,7 +757,7 @@ static int wait_for_complete(struct loopback_test *t)
 		}
 
 		for (i = 0; i < t->poll_count; i++) {
-			if (t->fds[i].revents & EPOLLPRI) {
+			if (t->fds[i].revents & POLLPRI) {
 				/* Dummy read to clear the event */
 				read(t->fds[i].fd, &dummy, 1);
 				number_of_events++;
@@ -915,10 +916,10 @@ int main(int argc, char *argv[])
 			t.iteration_max = atoi(optarg);
 			break;
 		case 'S':
-			snprintf(t.sysfs_prefix, MAX_SYSFS_PATH, "%s", optarg);
+			snprintf(t.sysfs_prefix, MAX_SYSFS_PREFIX, "%s", optarg);
 			break;
 		case 'D':
-			snprintf(t.debugfs_prefix, MAX_SYSFS_PATH, "%s", optarg);
+			snprintf(t.debugfs_prefix, MAX_SYSFS_PREFIX, "%s", optarg);
 			break;
 		case 'm':
 			t.mask = atol(optarg);
@@ -969,10 +970,10 @@ int main(int argc, char *argv[])
 	}
 
 	if (!strcmp(t.sysfs_prefix, ""))
-		snprintf(t.sysfs_prefix, MAX_SYSFS_PATH, "%s", sysfs_prefix);
+		snprintf(t.sysfs_prefix, MAX_SYSFS_PREFIX, "%s", sysfs_prefix);
 
 	if (!strcmp(t.debugfs_prefix, ""))
-		snprintf(t.debugfs_prefix, MAX_SYSFS_PATH, "%s", debugfs_prefix);
+		snprintf(t.debugfs_prefix, MAX_SYSFS_PREFIX, "%s", debugfs_prefix);
 
 	ret = find_loopback_devices(&t);
 	if (ret)
diff --git a/drivers/staging/greybus/uart.c b/drivers/staging/greybus/uart.c
index b3bffe91ae99..19fc8913081a 100644
--- a/drivers/staging/greybus/uart.c
+++ b/drivers/staging/greybus/uart.c
@@ -537,9 +537,9 @@ static void gb_tty_set_termios(struct tty_struct *tty,
 	}
 
 	if (C_CRTSCTS(tty) && C_BAUD(tty) != B0)
-		newline.flow_control |= GB_SERIAL_AUTO_RTSCTS_EN;
+		newline.flow_control = GB_SERIAL_AUTO_RTSCTS_EN;
 	else
-		newline.flow_control &= ~GB_SERIAL_AUTO_RTSCTS_EN;
+		newline.flow_control = 0;
 
 	if (memcmp(&gb_tty->line_coding, &newline, sizeof(newline))) {
 		memcpy(&gb_tty->line_coding, &newline, sizeof(newline));
diff --git a/drivers/staging/iio/resolver/ad2s1210.c b/drivers/staging/iio/resolver/ad2s1210.c
index b6be0bc202f5..bd3d12b76863 100644
--- a/drivers/staging/iio/resolver/ad2s1210.c
+++ b/drivers/staging/iio/resolver/ad2s1210.c
@@ -130,17 +130,24 @@ static int ad2s1210_config_write(struct ad2s1210_state *st, u8 data)
 static int ad2s1210_config_read(struct ad2s1210_state *st,
 				unsigned char address)
 {
-	struct spi_transfer xfer = {
-		.len = 2,
-		.rx_buf = st->rx,
-		.tx_buf = st->tx,
+	struct spi_transfer xfers[] = {
+		{
+			.len = 1,
+			.rx_buf = &st->rx[0],
+			.tx_buf = &st->tx[0],
+			.cs_change = 1,
+		}, {
+			.len = 1,
+			.rx_buf = &st->rx[1],
+			.tx_buf = &st->tx[1],
+		},
 	};
 	int ret = 0;
 
 	ad2s1210_set_mode(MOD_CONFIG, st);
 	st->tx[0] = address | AD2S1210_MSB_IS_HIGH;
 	st->tx[1] = AD2S1210_REG_FAULT;
-	ret = spi_sync_transfer(st->sdev, &xfer, 1);
+	ret = spi_sync_transfer(st->sdev, xfers, 2);
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/staging/kpc2000/kpc2000/core.c b/drivers/staging/kpc2000/kpc2000/core.c
index 40390cdd3c8d..adf5dfa0c552 100644
--- a/drivers/staging/kpc2000/kpc2000/core.c
+++ b/drivers/staging/kpc2000/kpc2000/core.c
@@ -60,7 +60,7 @@ static ssize_t  show_cpld_config_reg(struct device *dev, struct device_attribute
 static ssize_t cpld_reconfigure(struct device *dev, struct device_attribute *attr, const char *buf, size_t count)
 {
     struct pci_dev *pdev = to_pci_dev(dev);
-    long wr_val;
+    unsigned long wr_val;
     struct kp2000_device *pcard;
     int rv;
 
@@ -68,7 +68,7 @@ static ssize_t cpld_reconfigure(struct device *dev, struct device_attribute *att
     pcard = pci_get_drvdata(pdev);
     if (!pcard)  return -ENXIO;
     
-    rv = kstrtol(buf, 0, &wr_val);
+    rv = kstrtoul(buf, 0, &wr_val);
     if (rv < 0)  return rv;
     if (wr_val > 7)  return -EINVAL;
     
@@ -203,7 +203,6 @@ int  kp2000_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id)
     int err = 0;
     struct kp2000_device *pcard;
     static int card_count = 1;
-    int rv;
     unsigned long reg_bar_phys_addr;
     unsigned long reg_bar_phys_len;
     unsigned long dma_bar_phys_addr;
@@ -336,9 +335,9 @@ int  kp2000_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id)
     if (err < 0)
         goto out8a;
     
-    rv = request_irq(pcard->pdev->irq, kp2000_irq_handler, IRQF_SHARED, pcard->name, pcard);
-    if (rv){
-        dev_err(&pcard->pdev->dev, "kp2000_pcie_probe: failed to request_irq: %d\n", rv);
+    err = request_irq(pcard->pdev->irq, kp2000_irq_handler, IRQF_SHARED, pcard->name, pcard);
+    if (err){
+        dev_err(&pcard->pdev->dev, "kp2000_pcie_probe: failed to request_irq: %d\n", err);
         goto out8b;
     }
     //}
diff --git a/drivers/staging/media/imx/imx7-mipi-csis.c b/drivers/staging/media/imx/imx7-mipi-csis.c
index 44dc140fcfbe..0e95390d499f 100644
--- a/drivers/staging/media/imx/imx7-mipi-csis.c
+++ b/drivers/staging/media/imx/imx7-mipi-csis.c
@@ -579,7 +579,7 @@ static int mipi_csis_s_stream(struct v4l2_subdev *mipi_sd, int enable)
 		state->flags |= ST_STREAMING;
 	} else {
 		v4l2_subdev_call(state->src_sd, video, s_stream, 0);
-		ret = v4l2_subdev_call(state->src_sd, core, s_power, 1);
+		ret = v4l2_subdev_call(state->src_sd, core, s_power, 0);
 		mipi_csis_stop_stream(state);
 		state->flags &= ~ST_STREAMING;
 		if (state->debug)
@@ -657,28 +657,6 @@ static int mipi_csis_init_cfg(struct v4l2_subdev *mipi_sd,
 	return 0;
 }
 
-static struct csis_pix_format const *
-mipi_csis_try_format(struct v4l2_subdev *mipi_sd, struct v4l2_mbus_framefmt *mf)
-{
-	struct csi_state *state = mipi_sd_to_csis_state(mipi_sd);
-	struct csis_pix_format const *csis_fmt;
-
-	csis_fmt = find_csis_format(mf->code);
-	if (!csis_fmt)
-		csis_fmt = &mipi_csis_formats[0];
-
-	v4l_bound_align_image(&mf->width, 1, CSIS_MAX_PIX_WIDTH,
-			      csis_fmt->pix_width_alignment,
-			      &mf->height, 1, CSIS_MAX_PIX_HEIGHT, 1,
-			      0);
-
-	state->format_mbus.code = csis_fmt->code;
-	state->format_mbus.width = mf->width;
-	state->format_mbus.height = mf->height;
-
-	return csis_fmt;
-}
-
 static struct v4l2_mbus_framefmt *
 mipi_csis_get_format(struct csi_state *state,
 		     struct v4l2_subdev_pad_config *cfg,
@@ -691,53 +669,67 @@ mipi_csis_get_format(struct csi_state *state,
 	return &state->format_mbus;
 }
 
-static int mipi_csis_set_fmt(struct v4l2_subdev *mipi_sd,
+static int mipi_csis_get_fmt(struct v4l2_subdev *mipi_sd,
 			     struct v4l2_subdev_pad_config *cfg,
 			     struct v4l2_subdev_format *sdformat)
 {
 	struct csi_state *state = mipi_sd_to_csis_state(mipi_sd);
-	struct csis_pix_format const *csis_fmt;
 	struct v4l2_mbus_framefmt *fmt;
 
-	if (sdformat->pad >= CSIS_PADS_NUM)
-		return -EINVAL;
-
-	fmt = mipi_csis_get_format(state, cfg, sdformat->which, sdformat->pad);
-
 	mutex_lock(&state->lock);
-	if (sdformat->pad == CSIS_PAD_SOURCE) {
-		sdformat->format = *fmt;
-		goto unlock;
-	}
-
-	csis_fmt = mipi_csis_try_format(mipi_sd, &sdformat->format);
-
+	fmt = mipi_csis_get_format(state, cfg, sdformat->which, sdformat->pad);
 	sdformat->format = *fmt;
-
-	if (csis_fmt && sdformat->which == V4L2_SUBDEV_FORMAT_ACTIVE)
-		state->csis_fmt = csis_fmt;
-	else
-		cfg->try_fmt = sdformat->format;
-
-unlock:
 	mutex_unlock(&state->lock);
 
 	return 0;
 }
 
-static int mipi_csis_get_fmt(struct v4l2_subdev *mipi_sd,
+static int mipi_csis_set_fmt(struct v4l2_subdev *mipi_sd,
 			     struct v4l2_subdev_pad_config *cfg,
 			     struct v4l2_subdev_format *sdformat)
 {
 	struct csi_state *state = mipi_sd_to_csis_state(mipi_sd);
+	struct csis_pix_format const *csis_fmt;
 	struct v4l2_mbus_framefmt *fmt;
 
-	mutex_lock(&state->lock);
+	/*
+	 * The CSIS can't transcode in any way, the source format can't be
+	 * modified.
+	 */
+	if (sdformat->pad == CSIS_PAD_SOURCE)
+		return mipi_csis_get_fmt(mipi_sd, cfg, sdformat);
+
+	if (sdformat->pad != CSIS_PAD_SINK)
+		return -EINVAL;
 
 	fmt = mipi_csis_get_format(state, cfg, sdformat->which, sdformat->pad);
 
+	mutex_lock(&state->lock);
+
+	/* Validate the media bus code and clamp the size. */
+	csis_fmt = find_csis_format(sdformat->format.code);
+	if (!csis_fmt)
+		csis_fmt = &mipi_csis_formats[0];
+
+	fmt->code = csis_fmt->code;
+	fmt->width = sdformat->format.width;
+	fmt->height = sdformat->format.height;
+
+	v4l_bound_align_image(&fmt->width, 1, CSIS_MAX_PIX_WIDTH,
+			      csis_fmt->pix_width_alignment,
+			      &fmt->height, 1, CSIS_MAX_PIX_HEIGHT, 1, 0);
+
 	sdformat->format = *fmt;
 
+	/* Propagate the format from sink to source. */
+	fmt = mipi_csis_get_format(state, cfg, sdformat->which,
+				   CSIS_PAD_SOURCE);
+	*fmt = sdformat->format;
+
+	/* Store the CSIS format descriptor for active formats. */
+	if (sdformat->which == V4L2_SUBDEV_FORMAT_ACTIVE)
+		state->csis_fmt = csis_fmt;
+
 	mutex_unlock(&state->lock);
 
 	return 0;
diff --git a/drivers/staging/media/ipu3/include/intel-ipu3.h b/drivers/staging/media/ipu3/include/intel-ipu3.h
index 1e7184e4311d..8cc46903040b 100644
--- a/drivers/staging/media/ipu3/include/intel-ipu3.h
+++ b/drivers/staging/media/ipu3/include/intel-ipu3.h
@@ -449,7 +449,7 @@ struct ipu3_uapi_awb_fr_config_s {
 	__u16 reserved1;
 	__u32 bayer_sign;
 	__u8 bayer_nf;
-	__u8 reserved2[3];
+	__u8 reserved2[7];
 } __attribute__((aligned(32))) __packed;
 
 /**
diff --git a/drivers/staging/media/ipu3/ipu3-mmu.c b/drivers/staging/media/ipu3/ipu3-mmu.c
index cfc2bdfb14b3..ccc4704082f4 100644
--- a/drivers/staging/media/ipu3/ipu3-mmu.c
+++ b/drivers/staging/media/ipu3/ipu3-mmu.c
@@ -177,8 +177,10 @@ static u32 *imgu_mmu_get_l2pt(struct imgu_mmu *mmu, u32 l1pt_idx)
 	spin_lock_irqsave(&mmu->lock, flags);
 
 	l2pt = mmu->l2pts[l1pt_idx];
-	if (l2pt)
-		goto done;
+	if (l2pt) {
+		spin_unlock_irqrestore(&mmu->lock, flags);
+		return l2pt;
+	}
 
 	spin_unlock_irqrestore(&mmu->lock, flags);
 
@@ -193,8 +195,9 @@ static u32 *imgu_mmu_get_l2pt(struct imgu_mmu *mmu, u32 l1pt_idx)
 
 	l2pt = mmu->l2pts[l1pt_idx];
 	if (l2pt) {
+		spin_unlock_irqrestore(&mmu->lock, flags);
 		imgu_mmu_free_page_table(new_l2pt);
-		goto done;
+		return l2pt;
 	}
 
 	l2pt = new_l2pt;
@@ -203,7 +206,6 @@ static u32 *imgu_mmu_get_l2pt(struct imgu_mmu *mmu, u32 l1pt_idx)
 	pteval = IPU3_ADDR2PTE(virt_to_phys(new_l2pt));
 	mmu->l1pt[l1pt_idx] = pteval;
 
-done:
 	spin_unlock_irqrestore(&mmu->lock, flags);
 	return l2pt;
 }
diff --git a/drivers/staging/media/ipu3/ipu3-v4l2.c b/drivers/staging/media/ipu3/ipu3-v4l2.c
index a7bc22040ed8..3d69177c1373 100644
--- a/drivers/staging/media/ipu3/ipu3-v4l2.c
+++ b/drivers/staging/media/ipu3/ipu3-v4l2.c
@@ -367,8 +367,10 @@ static void imgu_vb2_buf_queue(struct vb2_buffer *vb)
 
 	vb2_set_plane_payload(vb, 0, need_bytes);
 
+	mutex_lock(&imgu->streaming_lock);
 	if (imgu->streaming)
 		imgu_queue_buffers(imgu, false, node->pipe);
+	mutex_unlock(&imgu->streaming_lock);
 
 	dev_dbg(&imgu->pci_dev->dev, "%s for pipe %u node %u", __func__,
 		node->pipe, node->id);
@@ -468,10 +470,13 @@ static int imgu_vb2_start_streaming(struct vb2_queue *vq, unsigned int count)
 	dev_dbg(dev, "%s node name %s pipe %u id %u", __func__,
 		node->name, node->pipe, node->id);
 
+	mutex_lock(&imgu->streaming_lock);
 	if (imgu->streaming) {
 		r = -EBUSY;
+		mutex_unlock(&imgu->streaming_lock);
 		goto fail_return_bufs;
 	}
+	mutex_unlock(&imgu->streaming_lock);
 
 	if (!node->enabled) {
 		dev_err(dev, "IMGU node is not enabled");
@@ -498,9 +503,11 @@ static int imgu_vb2_start_streaming(struct vb2_queue *vq, unsigned int count)
 
 	/* Start streaming of the whole pipeline now */
 	dev_dbg(dev, "IMGU streaming is ready to start");
+	mutex_lock(&imgu->streaming_lock);
 	r = imgu_s_stream(imgu, true);
 	if (!r)
 		imgu->streaming = true;
+	mutex_unlock(&imgu->streaming_lock);
 
 	return 0;
 
@@ -532,6 +539,7 @@ static void imgu_vb2_stop_streaming(struct vb2_queue *vq)
 		dev_err(&imgu->pci_dev->dev,
 			"failed to stop subdev streaming\n");
 
+	mutex_lock(&imgu->streaming_lock);
 	/* Was this the first node with streaming disabled? */
 	if (imgu->streaming && imgu_all_nodes_streaming(imgu, node)) {
 		/* Yes, really stop streaming now */
@@ -542,6 +550,8 @@ static void imgu_vb2_stop_streaming(struct vb2_queue *vq)
 	}
 
 	imgu_return_all_buffers(imgu, node, VB2_BUF_STATE_ERROR);
+	mutex_unlock(&imgu->streaming_lock);
+
 	media_pipeline_stop(&node->vdev.entity);
 }
 
diff --git a/drivers/staging/media/ipu3/ipu3.c b/drivers/staging/media/ipu3/ipu3.c
index a7372395a101..8cc38a8fcf5d 100644
--- a/drivers/staging/media/ipu3/ipu3.c
+++ b/drivers/staging/media/ipu3/ipu3.c
@@ -261,6 +261,7 @@ int imgu_queue_buffers(struct imgu_device *imgu, bool initial, unsigned int pipe
 
 			ivb = list_first_entry(&imgu_pipe->nodes[node].buffers,
 					       struct imgu_vb2_buffer, list);
+			list_del(&ivb->list);
 			vb = &ivb->vbb.vb2_buf;
 			r = imgu_css_set_parameters(&imgu->css, pipe,
 						    vb2_plane_vaddr(vb, 0));
@@ -274,7 +275,6 @@ int imgu_queue_buffers(struct imgu_device *imgu, bool initial, unsigned int pipe
 			vb2_buffer_done(vb, VB2_BUF_STATE_DONE);
 			dev_dbg(&imgu->pci_dev->dev,
 				"queue user parameters %d to css.", vb->index);
-			list_del(&ivb->list);
 		} else if (imgu_pipe->queue_enabled[node]) {
 			struct imgu_css_buffer *buf =
 				imgu_queue_getbuf(imgu, node, pipe);
@@ -663,6 +663,7 @@ static int imgu_pci_probe(struct pci_dev *pci_dev,
 		return r;
 
 	mutex_init(&imgu->lock);
+	mutex_init(&imgu->streaming_lock);
 	atomic_set(&imgu->qbuf_barrier, 0);
 	init_waitqueue_head(&imgu->buf_drain_wq);
 
@@ -726,6 +727,7 @@ out_mmu_exit:
 out_css_powerdown:
 	imgu_css_set_powerdown(&pci_dev->dev, imgu->base);
 out_mutex_destroy:
+	mutex_destroy(&imgu->streaming_lock);
 	mutex_destroy(&imgu->lock);
 
 	return r;
@@ -743,6 +745,7 @@ static void imgu_pci_remove(struct pci_dev *pci_dev)
 	imgu_css_set_powerdown(&pci_dev->dev, imgu->base);
 	imgu_dmamap_exit(imgu);
 	imgu_mmu_exit(imgu->mmu);
+	mutex_destroy(&imgu->streaming_lock);
 	mutex_destroy(&imgu->lock);
 }
 
diff --git a/drivers/staging/media/ipu3/ipu3.h b/drivers/staging/media/ipu3/ipu3.h
index 73b123b2b8a2..8cd6a0077d99 100644
--- a/drivers/staging/media/ipu3/ipu3.h
+++ b/drivers/staging/media/ipu3/ipu3.h
@@ -146,6 +146,10 @@ struct imgu_device {
 	 * vid_buf.list and css->queue
 	 */
 	struct mutex lock;
+
+	/* Lock to protect writes to streaming flag in this struct */
+	struct mutex streaming_lock;
+
 	/* Forbid streaming and buffer queuing during system suspend. */
 	atomic_t qbuf_barrier;
 	/* Indicate if system suspend take place while imgu is streaming. */
diff --git a/drivers/staging/media/rockchip/vpu/rk3288_vpu_hw_jpeg_enc.c b/drivers/staging/media/rockchip/vpu/rk3288_vpu_hw_jpeg_enc.c
index 06daea66fb49..5db74a0b0e58 100644
--- a/drivers/staging/media/rockchip/vpu/rk3288_vpu_hw_jpeg_enc.c
+++ b/drivers/staging/media/rockchip/vpu/rk3288_vpu_hw_jpeg_enc.c
@@ -67,12 +67,17 @@ rk3288_vpu_jpeg_enc_set_qtable(struct rockchip_vpu_dev *vpu,
 			       unsigned char *chroma_qtable)
 {
 	u32 reg, i;
+	__be32 *luma_qtable_p;
+	__be32 *chroma_qtable_p;
+
+	luma_qtable_p = (__be32 *)luma_qtable;
+	chroma_qtable_p = (__be32 *)chroma_qtable;
 
 	for (i = 0; i < VEPU_JPEG_QUANT_TABLE_COUNT; i++) {
-		reg = get_unaligned_be32(&luma_qtable[i]);
+		reg = get_unaligned_be32(&luma_qtable_p[i]);
 		vepu_write_relaxed(vpu, reg, VEPU_REG_JPEG_LUMA_QUAT(i));
 
-		reg = get_unaligned_be32(&chroma_qtable[i]);
+		reg = get_unaligned_be32(&chroma_qtable_p[i]);
 		vepu_write_relaxed(vpu, reg, VEPU_REG_JPEG_CHROMA_QUAT(i));
 	}
 }
diff --git a/drivers/staging/media/rockchip/vpu/rk3399_vpu_hw_jpeg_enc.c b/drivers/staging/media/rockchip/vpu/rk3399_vpu_hw_jpeg_enc.c
index 3d438797692e..93c63f05a885 100644
--- a/drivers/staging/media/rockchip/vpu/rk3399_vpu_hw_jpeg_enc.c
+++ b/drivers/staging/media/rockchip/vpu/rk3399_vpu_hw_jpeg_enc.c
@@ -98,12 +98,17 @@ rk3399_vpu_jpeg_enc_set_qtable(struct rockchip_vpu_dev *vpu,
 			       unsigned char *chroma_qtable)
 {
 	u32 reg, i;
+	__be32 *luma_qtable_p;
+	__be32 *chroma_qtable_p;
+
+	luma_qtable_p = (__be32 *)luma_qtable;
+	chroma_qtable_p = (__be32 *)chroma_qtable;
 
 	for (i = 0; i < VEPU_JPEG_QUANT_TABLE_COUNT; i++) {
-		reg = get_unaligned_be32(&luma_qtable[i]);
+		reg = get_unaligned_be32(&luma_qtable_p[i]);
 		vepu_write_relaxed(vpu, reg, VEPU_REG_JPEG_LUMA_QUAT(i));
 
-		reg = get_unaligned_be32(&chroma_qtable[i]);
+		reg = get_unaligned_be32(&chroma_qtable_p[i]);
 		vepu_write_relaxed(vpu, reg, VEPU_REG_JPEG_CHROMA_QUAT(i));
 	}
 }
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_dec.c b/drivers/staging/media/sunxi/cedrus/cedrus_dec.c
index 4d6d602cdde6..986c04c82530 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_dec.c
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_dec.c
@@ -52,6 +52,8 @@ void cedrus_device_run(void *priv)
 
 	v4l2_m2m_buf_copy_metadata(run.src, run.dst, true);
 
+	cedrus_dst_format_set(dev, &ctx->dst_fmt);
+
 	dev->dec_ops[ctx->current_codec]->setup(ctx, &run);
 
 	/* Complete request(s) controls if needed. */
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_video.c b/drivers/staging/media/sunxi/cedrus/cedrus_video.c
index 9673874ece10..8bd2fd03b710 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_video.c
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_video.c
@@ -281,7 +281,6 @@ static int cedrus_s_fmt_vid_cap(struct file *file, void *priv,
 				struct v4l2_format *f)
 {
 	struct cedrus_ctx *ctx = cedrus_file2ctx(file);
-	struct cedrus_dev *dev = ctx->dev;
 	struct vb2_queue *vq;
 	int ret;
 
@@ -295,8 +294,6 @@ static int cedrus_s_fmt_vid_cap(struct file *file, void *priv,
 
 	ctx->dst_fmt = f->fmt.pix;
 
-	cedrus_dst_format_set(dev, &ctx->dst_fmt);
-
 	return 0;
 }
 
diff --git a/drivers/staging/most/net/net.c b/drivers/staging/most/net/net.c
index c8a64e209027..cc680c08c342 100644
--- a/drivers/staging/most/net/net.c
+++ b/drivers/staging/most/net/net.c
@@ -81,6 +81,11 @@ static int skb_to_mamac(const struct sk_buff *skb, struct mbo *mbo)
 	unsigned int payload_len = skb->len - ETH_HLEN;
 	unsigned int mdp_len = payload_len + MDP_HDR_LEN;
 
+	if (mdp_len < skb->len) {
+		pr_err("drop: too large packet! (%u)\n", skb->len);
+		return -EINVAL;
+	}
+
 	if (mbo->buffer_length < mdp_len) {
 		pr_err("drop: too small buffer! (%d for %d)\n",
 		       mbo->buffer_length, mdp_len);
@@ -128,6 +133,11 @@ static int skb_to_mep(const struct sk_buff *skb, struct mbo *mbo)
 	u8 *buff = mbo->virt_address;
 	unsigned int mep_len = skb->len + MEP_HDR_LEN;
 
+	if (mep_len < skb->len) {
+		pr_err("drop: too large packet! (%u)\n", skb->len);
+		return -EINVAL;
+	}
+
 	if (mbo->buffer_length < mep_len) {
 		pr_err("drop: too small buffer! (%d for %d)\n",
 		       mbo->buffer_length, mep_len);
diff --git a/drivers/staging/most/sound/sound.c b/drivers/staging/most/sound/sound.c
index 342f390d68b3..79817061fcfa 100644
--- a/drivers/staging/most/sound/sound.c
+++ b/drivers/staging/most/sound/sound.c
@@ -802,8 +802,11 @@ static int __init audio_init(void)
 	if (ret)
 		pr_err("Failed to register %s\n", comp.name);
 	ret = most_register_configfs_subsys(&comp);
-	if (ret)
+	if (ret) {
 		pr_err("Failed to register %s configfs subsys\n", comp.name);
+		most_deregister_component(&comp);
+	}
+
 	return ret;
 }
 
diff --git a/drivers/staging/mt7621-pci/pci-mt7621.c b/drivers/staging/mt7621-pci/pci-mt7621.c
index 93763d40e3a1..68cac6e8b5ef 100644
--- a/drivers/staging/mt7621-pci/pci-mt7621.c
+++ b/drivers/staging/mt7621-pci/pci-mt7621.c
@@ -28,14 +28,13 @@
 #include <linux/phy/phy.h>
 #include <linux/platform_device.h>
 #include <linux/reset.h>
+#include <linux/sys_soc.h>
 #include <mt7621.h>
 #include <ralink_regs.h>
 
 #include "../../pci/pci.h"
 
 /* sysctl */
-#define MT7621_CHIP_REV_ID		0x0c
-#define CHIP_REV_MT7621_E2		0x0101
 
 /* MediaTek specific configuration registers */
 #define PCIE_FTS_NUM			0x70c
@@ -120,6 +119,8 @@ struct mt7621_pcie_port {
  * @dev: Pointer to PCIe device
  * @ports: pointer to PCIe port information
  * @rst: pointer to pcie reset
+ * @resets_inverted: depends on chip revision
+ * reset lines are inverted.
  */
 struct mt7621_pcie {
 	void __iomem *base;
@@ -133,6 +134,7 @@ struct mt7621_pcie {
 	} offset;
 	struct list_head ports;
 	struct reset_control *rst;
+	bool resets_inverted;
 };
 
 static inline u32 pcie_read(struct mt7621_pcie *pcie, u32 reg)
@@ -200,9 +202,9 @@ static void write_config(struct mt7621_pcie *pcie, unsigned int dev,
 
 static inline void mt7621_control_assert(struct mt7621_pcie_port *port)
 {
-	u32 chip_rev_id = rt_sysc_r32(MT7621_CHIP_REV_ID);
+	struct mt7621_pcie *pcie = port->pcie;
 
-	if ((chip_rev_id & 0xFFFF) == CHIP_REV_MT7621_E2)
+	if (pcie->resets_inverted)
 		reset_control_assert(port->pcie_rst);
 	else
 		reset_control_deassert(port->pcie_rst);
@@ -210,9 +212,9 @@ static inline void mt7621_control_assert(struct mt7621_pcie_port *port)
 
 static inline void mt7621_control_deassert(struct mt7621_pcie_port *port)
 {
-	u32 chip_rev_id = rt_sysc_r32(MT7621_CHIP_REV_ID);
+	struct mt7621_pcie *pcie = port->pcie;
 
-	if ((chip_rev_id & 0xFFFF) == CHIP_REV_MT7621_E2)
+	if (pcie->resets_inverted)
 		reset_control_deassert(port->pcie_rst);
 	else
 		reset_control_assert(port->pcie_rst);
@@ -625,9 +627,14 @@ static int mt7621_pcie_register_host(struct pci_host_bridge *host,
 	return pci_host_probe(host);
 }
 
+static const struct soc_device_attribute mt7621_pci_quirks_match[] = {
+	{ .soc_id = "mt7621", .revision = "E2" }
+};
+
 static int mt7621_pci_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
+	const struct soc_device_attribute *attr;
 	struct mt7621_pcie *pcie;
 	struct pci_host_bridge *bridge;
 	int err;
@@ -645,6 +652,10 @@ static int mt7621_pci_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, pcie);
 	INIT_LIST_HEAD(&pcie->ports);
 
+	attr = soc_device_match(mt7621_pci_quirks_match);
+	if (attr)
+		pcie->resets_inverted = true;
+
 	err = mt7621_pcie_parse_dt(pcie);
 	if (err) {
 		dev_err(dev, "Parsing DT failed\n");
diff --git a/drivers/staging/rtl8188eu/core/rtw_mlme.c b/drivers/staging/rtl8188eu/core/rtw_mlme.c
index 9a4aad5ec365..24c0ec1674b1 100644
--- a/drivers/staging/rtl8188eu/core/rtw_mlme.c
+++ b/drivers/staging/rtl8188eu/core/rtw_mlme.c
@@ -1740,9 +1740,11 @@ int rtw_restruct_sec_ie(struct adapter *adapter, u8 *in_ie, u8 *out_ie, uint in_
 	if ((ndisauthmode == Ndis802_11AuthModeWPA) ||
 	    (ndisauthmode == Ndis802_11AuthModeWPAPSK))
 		authmode = _WPA_IE_ID_;
-	if ((ndisauthmode == Ndis802_11AuthModeWPA2) ||
+	else if ((ndisauthmode == Ndis802_11AuthModeWPA2) ||
 	    (ndisauthmode == Ndis802_11AuthModeWPA2PSK))
 		authmode = _WPA2_IE_ID_;
+	else
+		authmode = 0x0;
 
 	if (check_fwstate(pmlmepriv, WIFI_UNDER_WPS)) {
 		memcpy(out_ie+ielength, psecuritypriv->wps_ie, psecuritypriv->wps_ie_len);
diff --git a/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c b/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c
index eaa4adb32a0d..5a8f4f168a75 100644
--- a/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c
+++ b/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c
@@ -229,18 +229,21 @@ static char *translate_scan(struct adapter *padapter,
 
 	/* parsing WPA/WPA2 IE */
 	{
-		u8 buf[MAX_WPA_IE_LEN];
+		u8 *buf;
 		u8 wpa_ie[255], rsn_ie[255];
 		u16 wpa_len = 0, rsn_len = 0;
 		u8 *p;
 
+		buf = kzalloc(MAX_WPA_IE_LEN, GFP_ATOMIC);
+		if (!buf)
+			return start;
+
 		rtw_get_sec_ie(pnetwork->network.ies, pnetwork->network.ie_length, rsn_ie, &rsn_len, wpa_ie, &wpa_len);
 		RT_TRACE(_module_rtl871x_mlme_c_, _drv_info_, ("rtw_wx_get_scan: ssid =%s\n", pnetwork->network.ssid.ssid));
 		RT_TRACE(_module_rtl871x_mlme_c_, _drv_info_, ("rtw_wx_get_scan: wpa_len =%d rsn_len =%d\n", wpa_len, rsn_len));
 
 		if (wpa_len > 0) {
 			p = buf;
-			memset(buf, 0, MAX_WPA_IE_LEN);
 			p += sprintf(p, "wpa_ie=");
 			for (i = 0; i < wpa_len; i++)
 				p += sprintf(p, "%02x", wpa_ie[i]);
@@ -257,7 +260,6 @@ static char *translate_scan(struct adapter *padapter,
 		}
 		if (rsn_len > 0) {
 			p = buf;
-			memset(buf, 0, MAX_WPA_IE_LEN);
 			p += sprintf(p, "rsn_ie=");
 			for (i = 0; i < rsn_len; i++)
 				p += sprintf(p, "%02x", rsn_ie[i]);
@@ -271,6 +273,7 @@ static char *translate_scan(struct adapter *padapter,
 			iwe.u.data.length = rsn_len;
 			start = iwe_stream_add_point(info, start, stop, &iwe, rsn_ie);
 		}
+		kfree(buf);
 	}
 
 	{/* parsing WPS IE */
@@ -2022,7 +2025,7 @@ static int wpa_supplicant_ioctl(struct net_device *dev, struct iw_point *p)
 	struct ieee_param *param;
 	uint ret = 0;
 
-	if (p->length < sizeof(struct ieee_param) || !p->pointer) {
+	if (!p->pointer || p->length != sizeof(struct ieee_param)) {
 		ret = -EINVAL;
 		goto out;
 	}
@@ -2815,7 +2818,7 @@ static int rtw_hostapd_ioctl(struct net_device *dev, struct iw_point *p)
 		goto out;
 	}
 
-	if (!p->pointer) {
+	if (!p->pointer || p->length != sizeof(struct ieee_param)) {
 		ret = -EINVAL;
 		goto out;
 	}
diff --git a/drivers/staging/rtl8188eu/os_dep/usb_intf.c b/drivers/staging/rtl8188eu/os_dep/usb_intf.c
index a7cac0719b8b..f7f09c0d273f 100644
--- a/drivers/staging/rtl8188eu/os_dep/usb_intf.c
+++ b/drivers/staging/rtl8188eu/os_dep/usb_intf.c
@@ -32,11 +32,14 @@ static const struct usb_device_id rtw_usb_id_tbl[] = {
 	/****** 8188EUS ********/
 	{USB_DEVICE(0x056e, 0x4008)}, /* Elecom WDC-150SU2M */
 	{USB_DEVICE(0x07b8, 0x8179)}, /* Abocom - Abocom */
+	{USB_DEVICE(0x0B05, 0x18F0)}, /* ASUS USB-N10 Nano B1 */
 	{USB_DEVICE(0x2001, 0x330F)}, /* DLink DWA-125 REV D1 */
 	{USB_DEVICE(0x2001, 0x3310)}, /* Dlink DWA-123 REV D1 */
 	{USB_DEVICE(0x2001, 0x3311)}, /* DLink GO-USB-N150 REV B1 */
 	{USB_DEVICE(0x2001, 0x331B)}, /* D-Link DWA-121 rev B1 */
 	{USB_DEVICE(0x2357, 0x010c)}, /* TP-Link TL-WN722N v2 */
+	{USB_DEVICE(0x2357, 0x0111)}, /* TP-Link TL-WN727N v5.21 */
+	{USB_DEVICE(0x2C4E, 0x0102)}, /* MERCUSYS MW150US v2 */
 	{USB_DEVICE(0x0df6, 0x0076)}, /* Sitecom N150 v2 */
 	{USB_DEVICE(USB_VENDER_ID_REALTEK, 0xffef)}, /* Rosewill RNX-N150NUB */
 	{}	/* Terminating entry */
diff --git a/drivers/staging/rtl8192u/r8192U_core.c b/drivers/staging/rtl8192u/r8192U_core.c
index 309f06439a23..001157e7fa57 100644
--- a/drivers/staging/rtl8192u/r8192U_core.c
+++ b/drivers/staging/rtl8192u/r8192U_core.c
@@ -2447,7 +2447,7 @@ static int rtl8192_read_eeprom_info(struct net_device *dev)
 				ret = eprom_read(dev, (EEPROM_TX_PW_INDEX_CCK >> 1));
 				if (ret < 0)
 					return ret;
-				priv->EEPROMTxPowerLevelCCK = ((u16)ret & 0xff) >> 8;
+				priv->EEPROMTxPowerLevelCCK = ((u16)ret & 0xff00) >> 8;
 			} else
 				priv->EEPROMTxPowerLevelCCK = 0x10;
 			RT_TRACE(COMP_EPROM, "CCK Tx Power Levl: 0x%02x\n", priv->EEPROMTxPowerLevelCCK);
diff --git a/drivers/staging/rtl8712/hal_init.c b/drivers/staging/rtl8712/hal_init.c
index 401f0e442bcf..fd220c284c01 100644
--- a/drivers/staging/rtl8712/hal_init.c
+++ b/drivers/staging/rtl8712/hal_init.c
@@ -33,7 +33,6 @@ static void rtl871x_load_fw_cb(const struct firmware *firmware, void *context)
 {
 	struct _adapter *padapter = context;
 
-	complete(&padapter->rtl8712_fw_ready);
 	if (!firmware) {
 		struct usb_device *udev = padapter->dvobjpriv.pusbdev;
 		struct usb_interface *pusb_intf = padapter->pusb_intf;
@@ -41,11 +40,13 @@ static void rtl871x_load_fw_cb(const struct firmware *firmware, void *context)
 		dev_err(&udev->dev, "r8712u: Firmware request failed\n");
 		usb_put_dev(udev);
 		usb_set_intfdata(pusb_intf, NULL);
+		complete(&padapter->rtl8712_fw_ready);
 		return;
 	}
 	padapter->fw = firmware;
 	/* firmware available - start netdev */
 	register_netdev(padapter->pnetdev);
+	complete(&padapter->rtl8712_fw_ready);
 }
 
 static const char firmware_file[] = "rtlwifi/rtl8712u.bin";
diff --git a/drivers/staging/rtl8712/usb_intf.c b/drivers/staging/rtl8712/usb_intf.c
index d6fd4b9a9105..7c4678859ebd 100644
--- a/drivers/staging/rtl8712/usb_intf.c
+++ b/drivers/staging/rtl8712/usb_intf.c
@@ -595,13 +595,17 @@ static void r871xu_dev_remove(struct usb_interface *pusb_intf)
 	if (pnetdev) {
 		struct _adapter *padapter = netdev_priv(pnetdev);
 
-		usb_set_intfdata(pusb_intf, NULL);
-		release_firmware(padapter->fw);
 		/* never exit with a firmware callback pending */
 		wait_for_completion(&padapter->rtl8712_fw_ready);
+		pnetdev = usb_get_intfdata(pusb_intf);
+		usb_set_intfdata(pusb_intf, NULL);
+		if (!pnetdev)
+			goto firmware_load_fail;
+		release_firmware(padapter->fw);
 		if (drvpriv.drv_registered)
 			padapter->surprise_removed = true;
-		unregister_netdev(pnetdev); /* will call netdev_close() */
+		if (pnetdev->reg_state != NETREG_UNINITIALIZED)
+			unregister_netdev(pnetdev); /* will call netdev_close() */
 		flush_scheduled_work();
 		udelay(1);
 		/* Stop driver mlme relation timer */
@@ -614,6 +618,7 @@ static void r871xu_dev_remove(struct usb_interface *pusb_intf)
 		 */
 		usb_put_dev(udev);
 	}
+firmware_load_fail:
 	/* If we didn't unplug usb dongle and remove/insert module, driver
 	 * fails on sitesurvey for the first time when device is up.
 	 * Reset usb port for sitesurvey fail issue.
diff --git a/drivers/staging/rtl8712/wifi.h b/drivers/staging/rtl8712/wifi.h
index 77346debea03..2c35a3828c79 100644
--- a/drivers/staging/rtl8712/wifi.h
+++ b/drivers/staging/rtl8712/wifi.h
@@ -456,7 +456,7 @@ static inline unsigned char *get_hdr_bssid(unsigned char *pframe)
 /* block-ack parameters */
 #define IEEE80211_ADDBA_PARAM_POLICY_MASK 0x0002
 #define IEEE80211_ADDBA_PARAM_TID_MASK 0x003C
-#define IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK 0xFFA0
+#define IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK 0xFFC0
 #define IEEE80211_DELBA_PARAM_TID_MASK 0xF000
 #define IEEE80211_DELBA_PARAM_INITIATOR_MASK 0x0800
 
@@ -550,13 +550,6 @@ struct ieee80211_ht_addt_info {
 #define IEEE80211_HT_IE_NON_GF_STA_PRSNT	0x0004
 #define IEEE80211_HT_IE_NON_HT_STA_PRSNT	0x0010
 
-/* block-ack parameters */
-#define IEEE80211_ADDBA_PARAM_POLICY_MASK 0x0002
-#define IEEE80211_ADDBA_PARAM_TID_MASK 0x003C
-#define IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK 0xFFA0
-#define IEEE80211_DELBA_PARAM_TID_MASK 0xF000
-#define IEEE80211_DELBA_PARAM_INITIATOR_MASK 0x0800
-
 /*
  * A-PMDU buffer sizes
  * According to IEEE802.11n spec size varies from 8K to 64K (in powers of 2)
diff --git a/drivers/staging/rtl8723bs/core/rtw_wlan_util.c b/drivers/staging/rtl8723bs/core/rtw_wlan_util.c
index fdbf967812f9..9c0623ef5374 100644
--- a/drivers/staging/rtl8723bs/core/rtw_wlan_util.c
+++ b/drivers/staging/rtl8723bs/core/rtw_wlan_util.c
@@ -1856,12 +1856,14 @@ int update_sta_support_rate(struct adapter *padapter, u8 *pvar_ie, uint var_ie_l
 	pIE = (struct ndis_80211_var_ie *)rtw_get_ie(pvar_ie, _SUPPORTEDRATES_IE_, &ie_len, var_ie_len);
 	if (!pIE)
 		return _FAIL;
+	if (ie_len > sizeof(pmlmeinfo->FW_sta_info[cam_idx].SupportedRates))
+		return _FAIL;
 
 	memcpy(pmlmeinfo->FW_sta_info[cam_idx].SupportedRates, pIE->data, ie_len);
 	supportRateNum = ie_len;
 
 	pIE = (struct ndis_80211_var_ie *)rtw_get_ie(pvar_ie, _EXT_SUPPORTEDRATES_IE_, &ie_len, var_ie_len);
-	if (pIE)
+	if (pIE && (ie_len <= sizeof(pmlmeinfo->FW_sta_info[cam_idx].SupportedRates) - supportRateNum))
 		memcpy((pmlmeinfo->FW_sta_info[cam_idx].SupportedRates + supportRateNum), pIE->data, ie_len);
 
 	return _SUCCESS;
diff --git a/drivers/staging/rtl8723bs/hal/rtl8723bs_xmit.c b/drivers/staging/rtl8723bs/hal/rtl8723bs_xmit.c
index 7b06aab04ee6..a6a246dcb52a 100644
--- a/drivers/staging/rtl8723bs/hal/rtl8723bs_xmit.c
+++ b/drivers/staging/rtl8723bs/hal/rtl8723bs_xmit.c
@@ -477,14 +477,13 @@ int rtl8723bs_xmit_thread(void *context)
 	s32 ret;
 	struct adapter *padapter;
 	struct xmit_priv *pxmitpriv;
-	u8 thread_name[20] = "RTWHALXT";
-
+	u8 thread_name[20];
 
 	ret = _SUCCESS;
 	padapter = context;
 	pxmitpriv = &padapter->xmitpriv;
 
-	rtw_sprintf(thread_name, 20, "%s-"ADPT_FMT, thread_name, ADPT_ARG(padapter));
+	rtw_sprintf(thread_name, 20, "RTWHALXT-" ADPT_FMT, ADPT_ARG(padapter));
 	thread_enter(thread_name);
 
 	DBG_871X("start "FUNC_ADPT_FMT"\n", FUNC_ADPT_ARG(padapter));
diff --git a/drivers/staging/rtl8723bs/os_dep/ioctl_linux.c b/drivers/staging/rtl8723bs/os_dep/ioctl_linux.c
index e3d356952875..5dea816351d1 100644
--- a/drivers/staging/rtl8723bs/os_dep/ioctl_linux.c
+++ b/drivers/staging/rtl8723bs/os_dep/ioctl_linux.c
@@ -3396,7 +3396,7 @@ static int wpa_supplicant_ioctl(struct net_device *dev, struct iw_point *p)
 
 	/* down(&ieee->wx_sem); */
 
-	if (p->length < sizeof(struct ieee_param) || !p->pointer) {
+	if (!p->pointer || p->length != sizeof(struct ieee_param)) {
 		ret = -EINVAL;
 		goto out;
 	}
@@ -4232,7 +4232,7 @@ static int rtw_hostapd_ioctl(struct net_device *dev, struct iw_point *p)
 
 
 	/* if (p->length < sizeof(struct ieee_param) || !p->pointer) { */
-	if (!p->pointer) {
+	if (!p->pointer || p->length != sizeof(*param)) {
 		ret = -EINVAL;
 		goto out;
 	}
diff --git a/drivers/staging/sm750fb/sm750.c b/drivers/staging/sm750fb/sm750.c
index 59568d18ce23..5b72aa81d94c 100644
--- a/drivers/staging/sm750fb/sm750.c
+++ b/drivers/staging/sm750fb/sm750.c
@@ -898,6 +898,7 @@ static int lynxfb_set_fbinfo(struct fb_info *info, int index)
 		fix->visual = FB_VISUAL_PSEUDOCOLOR;
 		break;
 	case 16:
+	case 24:
 	case 32:
 		fix->visual = FB_VISUAL_TRUECOLOR;
 		break;
diff --git a/drivers/staging/speakup/main.c b/drivers/staging/speakup/main.c
index 488f2539aa9a..81ecfd1a200d 100644
--- a/drivers/staging/speakup/main.c
+++ b/drivers/staging/speakup/main.c
@@ -561,7 +561,7 @@ static u_long get_word(struct vc_data *vc)
 		return 0;
 	} else if (tmpx < vc->vc_cols - 2 &&
 		   (ch == SPACE || ch == 0 || (ch < 0x100 && IS_WDLM(ch))) &&
-		   get_char(vc, (u_short *)&tmp_pos + 1, &temp) > SPACE) {
+		   get_char(vc, (u_short *)tmp_pos + 1, &temp) > SPACE) {
 		tmp_pos += 2;
 		tmpx++;
 	} else {
diff --git a/drivers/staging/vc04_services/bcm2835-camera/mmal-vchiq.c b/drivers/staging/vc04_services/bcm2835-camera/mmal-vchiq.c
index 29761f6c3b55..27a7b67510a1 100644
--- a/drivers/staging/vc04_services/bcm2835-camera/mmal-vchiq.c
+++ b/drivers/staging/vc04_services/bcm2835-camera/mmal-vchiq.c
@@ -420,6 +420,8 @@ buffer_from_host(struct vchiq_mmal_instance *instance,
 					&m,
 					sizeof(struct mmal_msg_header) +
 					sizeof(m.u.buffer_from_host));
+	if (ret)
+		atomic_dec(&port->buffers_with_vpu);
 
 	vchi_service_release(instance->handle);
 
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
index 6f6388c96bf6..4cf59696ac6f 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
@@ -3545,6 +3545,7 @@ failed_platform_init:
 
 static int vchiq_remove(struct platform_device *pdev)
 {
+	platform_device_unregister(bcm2835_audio);
 	platform_device_unregister(bcm2835_camera);
 	vchiq_debugfs_deinit();
 	device_destroy(vchiq_class, vchiq_devid);
diff --git a/drivers/staging/vt6656/card.c b/drivers/staging/vt6656/card.c
index 501f482b41c4..e8fd8c5b8b69 100644
--- a/drivers/staging/vt6656/card.c
+++ b/drivers/staging/vt6656/card.c
@@ -711,7 +711,7 @@ int vnt_radio_power_off(struct vnt_private *priv)
  */
 int vnt_radio_power_on(struct vnt_private *priv)
 {
-	int ret = true;
+	int ret = 0;
 
 	vnt_exit_deep_sleep(priv);
 
diff --git a/drivers/staging/vt6656/device.h b/drivers/staging/vt6656/device.h
index 6074ceda78bf..e2fabe818b19 100644
--- a/drivers/staging/vt6656/device.h
+++ b/drivers/staging/vt6656/device.h
@@ -52,6 +52,8 @@
 #define RATE_AUTO	12
 
 #define MAX_RATE			12
+#define VNT_B_RATES	(BIT(RATE_1M) | BIT(RATE_2M) |\
+			BIT(RATE_5M) | BIT(RATE_11M))
 
 /*
  * device specific
@@ -259,6 +261,7 @@ struct vnt_private {
 	u8 mac_hw;
 	/* netdev */
 	struct usb_device *usb;
+	struct usb_interface *intf;
 
 	u64 tsf_time;
 	u8 rx_rate;
diff --git a/drivers/staging/vt6656/dpc.c b/drivers/staging/vt6656/dpc.c
index 3b94e80f1d5e..879ceef517fb 100644
--- a/drivers/staging/vt6656/dpc.c
+++ b/drivers/staging/vt6656/dpc.c
@@ -130,7 +130,7 @@ int vnt_rx_data(struct vnt_private *priv, struct vnt_rcb *ptr_rcb,
 
 	vnt_rf_rssi_to_dbm(priv, *rssi, &rx_dbm);
 
-	priv->bb_pre_ed_rssi = (u8)rx_dbm + 1;
+	priv->bb_pre_ed_rssi = (u8)-rx_dbm + 1;
 	priv->current_rssi = priv->bb_pre_ed_rssi;
 
 	skb_pull(skb, 8);
diff --git a/drivers/staging/vt6656/int.c b/drivers/staging/vt6656/int.c
index 504424b19fcf..af0060c74530 100644
--- a/drivers/staging/vt6656/int.c
+++ b/drivers/staging/vt6656/int.c
@@ -97,9 +97,11 @@ static int vnt_int_report_rate(struct vnt_private *priv, u8 pkt_no, u8 tsr)
 
 	info->status.rates[0].count = tx_retry;
 
-	if (!(tsr & (TSR_TMO | TSR_RETRYTMO))) {
+	if (!(tsr & TSR_TMO)) {
 		info->status.rates[0].idx = idx;
-		info->flags |= IEEE80211_TX_STAT_ACK;
+
+		if (!(info->flags & IEEE80211_TX_CTL_NO_ACK))
+			info->flags |= IEEE80211_TX_STAT_ACK;
 	}
 
 	ieee80211_tx_status_irqsafe(priv->hw, context->skb);
diff --git a/drivers/staging/vt6656/key.c b/drivers/staging/vt6656/key.c
index dcd933a6b66e..40c58ac4e209 100644
--- a/drivers/staging/vt6656/key.c
+++ b/drivers/staging/vt6656/key.c
@@ -83,9 +83,6 @@ static int vnt_set_keymode(struct ieee80211_hw *hw, u8 *mac_addr,
 	case  VNT_KEY_PAIRWISE:
 		key_mode |= mode;
 		key_inx = 4;
-		/* Don't save entry for pairwise key for station mode */
-		if (priv->op_mode == NL80211_IFTYPE_STATION)
-			clear_bit(entry, &priv->key_entry_inuse);
 		break;
 	default:
 		return -EINVAL;
@@ -109,7 +106,6 @@ static int vnt_set_keymode(struct ieee80211_hw *hw, u8 *mac_addr,
 int vnt_set_keys(struct ieee80211_hw *hw, struct ieee80211_sta *sta,
 		 struct ieee80211_vif *vif, struct ieee80211_key_conf *key)
 {
-	struct ieee80211_bss_conf *conf = &vif->bss_conf;
 	struct vnt_private *priv = hw->priv;
 	u8 *mac_addr = NULL;
 	u8 key_dec_mode = 0;
@@ -151,16 +147,12 @@ int vnt_set_keys(struct ieee80211_hw *hw, struct ieee80211_sta *sta,
 		key->flags |= IEEE80211_KEY_FLAG_GENERATE_IV;
 	}
 
-	if (key->flags & IEEE80211_KEY_FLAG_PAIRWISE) {
+	if (key->flags & IEEE80211_KEY_FLAG_PAIRWISE)
 		vnt_set_keymode(hw, mac_addr, key, VNT_KEY_PAIRWISE,
 				key_dec_mode, true);
-	} else {
-		vnt_set_keymode(hw, mac_addr, key, VNT_KEY_DEFAULTKEY,
+	else
+		vnt_set_keymode(hw, mac_addr, key, VNT_KEY_GROUP_ADDRESS,
 				key_dec_mode, true);
 
-		vnt_set_keymode(hw, (u8 *)conf->bssid, key,
-				VNT_KEY_GROUP_ADDRESS, key_dec_mode, true);
-	}
-
 	return 0;
 }
diff --git a/drivers/staging/vt6656/main_usb.c b/drivers/staging/vt6656/main_usb.c
index 70433f756d8e..ecc96d1a1ed3 100644
--- a/drivers/staging/vt6656/main_usb.c
+++ b/drivers/staging/vt6656/main_usb.c
@@ -595,8 +595,6 @@ static int vnt_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 
 	priv->op_mode = vif->type;
 
-	vnt_set_bss_mode(priv);
-
 	/* LED blink on TX */
 	vnt_mac_set_led(priv, LEDSTS_STS, LEDSTS_INTER);
 
@@ -683,7 +681,6 @@ static void vnt_bss_info_changed(struct ieee80211_hw *hw,
 		priv->basic_rates = conf->basic_rates;
 
 		vnt_update_top_rates(priv);
-		vnt_set_bss_mode(priv);
 
 		dev_dbg(&priv->usb->dev, "basic rates %x\n", conf->basic_rates);
 	}
@@ -712,11 +709,14 @@ static void vnt_bss_info_changed(struct ieee80211_hw *hw,
 			priv->short_slot_time = false;
 
 		vnt_set_short_slot_time(priv);
-		vnt_update_ifs(priv);
 		vnt_set_vga_gain_offset(priv, priv->bb_vga[0]);
 		vnt_update_pre_ed_threshold(priv, false);
 	}
 
+	if (changed & (BSS_CHANGED_BASIC_RATES | BSS_CHANGED_ERP_PREAMBLE |
+		       BSS_CHANGED_ERP_SLOT))
+		vnt_set_bss_mode(priv);
+
 	if (changed & BSS_CHANGED_TXPOWER)
 		vnt_rf_setpower(priv, priv->current_rate,
 				conf->chandef.chan->hw_value);
@@ -740,12 +740,15 @@ static void vnt_bss_info_changed(struct ieee80211_hw *hw,
 			vnt_mac_reg_bits_on(priv, MAC_REG_TFTCTL,
 					    TFTCTL_TSFCNTREN);
 
-			vnt_adjust_tsf(priv, conf->beacon_rate->hw_value,
-				       conf->sync_tsf, priv->current_tsf);
-
 			vnt_mac_set_beacon_interval(priv, conf->beacon_int);
 
 			vnt_reset_next_tbtt(priv, conf->beacon_int);
+
+			vnt_adjust_tsf(priv, conf->beacon_rate->hw_value,
+				       conf->sync_tsf, priv->current_tsf);
+
+			vnt_update_next_tbtt(priv,
+					     conf->sync_tsf, conf->beacon_int);
 		} else {
 			vnt_clear_current_tsf(priv);
 
@@ -780,15 +783,11 @@ static void vnt_configure(struct ieee80211_hw *hw,
 {
 	struct vnt_private *priv = hw->priv;
 	u8 rx_mode = 0;
-	int rc;
 
 	*total_flags &= FIF_ALLMULTI | FIF_OTHER_BSS | FIF_BCN_PRBRESP_PROMISC;
 
-	rc = vnt_control_in(priv, MESSAGE_TYPE_READ, MAC_REG_RCR,
-			    MESSAGE_REQUEST_MACREG, sizeof(u8), &rx_mode);
-
-	if (!rc)
-		rx_mode = RCR_MULTICAST | RCR_BROADCAST;
+	vnt_control_in(priv, MESSAGE_TYPE_READ, MAC_REG_RCR,
+		       MESSAGE_REQUEST_MACREG, sizeof(u8), &rx_mode);
 
 	dev_dbg(&priv->usb->dev, "rx mode in = %x\n", rx_mode);
 
@@ -829,8 +828,12 @@ static int vnt_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 			return -EOPNOTSUPP;
 		break;
 	case DISABLE_KEY:
-		if (test_bit(key->hw_key_idx, &priv->key_entry_inuse))
+		if (test_bit(key->hw_key_idx, &priv->key_entry_inuse)) {
 			clear_bit(key->hw_key_idx, &priv->key_entry_inuse);
+
+			vnt_mac_disable_keyentry(priv, key->hw_key_idx);
+		}
+
 	default:
 		break;
 	}
@@ -912,7 +915,7 @@ static const struct ieee80211_ops vnt_mac_ops = {
 
 int vnt_init(struct vnt_private *priv)
 {
-	if (!(vnt_init_registers(priv)))
+	if (vnt_init_registers(priv))
 		return -EAGAIN;
 
 	SET_IEEE80211_PERM_ADDR(priv->hw, priv->permanent_net_addr);
@@ -955,6 +958,7 @@ vt6656_probe(struct usb_interface *intf, const struct usb_device_id *id)
 	priv = hw->priv;
 	priv->hw = hw;
 	priv->usb = udev;
+	priv->intf = intf;
 
 	vnt_set_options(priv);
 
@@ -977,6 +981,7 @@ vt6656_probe(struct usb_interface *intf, const struct usb_device_id *id)
 	ieee80211_hw_set(priv->hw, RX_INCLUDES_FCS);
 	ieee80211_hw_set(priv->hw, REPORTS_TX_ACK_STATUS);
 	ieee80211_hw_set(priv->hw, SUPPORTS_PS);
+	ieee80211_hw_set(priv->hw, PS_NULLFUNC_STACK);
 
 	priv->hw->max_signal = 100;
 
diff --git a/drivers/staging/vt6656/rxtx.c b/drivers/staging/vt6656/rxtx.c
index 9def0748ffee..4b4f07fbb9bf 100644
--- a/drivers/staging/vt6656/rxtx.c
+++ b/drivers/staging/vt6656/rxtx.c
@@ -278,11 +278,9 @@ static u16 vnt_rxtx_datahead_g(struct vnt_usb_send_context *tx_context,
 			  PK_TYPE_11B, &buf->b);
 
 	/* Get Duration and TimeStamp */
-	if (ieee80211_is_pspoll(hdr->frame_control)) {
-		__le16 dur = cpu_to_le16(priv->current_aid | BIT(14) | BIT(15));
-
-		buf->duration_a = dur;
-		buf->duration_b = dur;
+	if (ieee80211_is_nullfunc(hdr->frame_control)) {
+		buf->duration_a = hdr->duration_id;
+		buf->duration_b = hdr->duration_id;
 	} else {
 		buf->duration_a = vnt_get_duration_le(priv,
 						tx_context->pkt_type, need_ack);
@@ -371,10 +369,8 @@ static u16 vnt_rxtx_datahead_ab(struct vnt_usb_send_context *tx_context,
 			  tx_context->pkt_type, &buf->ab);
 
 	/* Get Duration and TimeStampOff */
-	if (ieee80211_is_pspoll(hdr->frame_control)) {
-		__le16 dur = cpu_to_le16(priv->current_aid | BIT(14) | BIT(15));
-
-		buf->duration = dur;
+	if (ieee80211_is_nullfunc(hdr->frame_control)) {
+		buf->duration = hdr->duration_id;
 	} else {
 		buf->duration = vnt_get_duration_le(priv, tx_context->pkt_type,
 						    need_ack);
@@ -815,10 +811,14 @@ int vnt_tx_packet(struct vnt_private *priv, struct sk_buff *skb)
 		if (info->band == NL80211_BAND_5GHZ) {
 			pkt_type = PK_TYPE_11A;
 		} else {
-			if (tx_rate->flags & IEEE80211_TX_RC_USE_CTS_PROTECT)
-				pkt_type = PK_TYPE_11GB;
-			else
-				pkt_type = PK_TYPE_11GA;
+			if (tx_rate->flags & IEEE80211_TX_RC_USE_CTS_PROTECT) {
+				if (priv->basic_rates & VNT_B_RATES)
+					pkt_type = PK_TYPE_11GB;
+				else
+					pkt_type = PK_TYPE_11GA;
+			} else {
+				pkt_type = PK_TYPE_11A;
+			}
 		}
 	} else {
 		pkt_type = PK_TYPE_11B;
diff --git a/drivers/staging/vt6656/wcmd.c b/drivers/staging/vt6656/wcmd.c
index 3eb2f11a5de1..2c5250ca2801 100644
--- a/drivers/staging/vt6656/wcmd.c
+++ b/drivers/staging/vt6656/wcmd.c
@@ -99,6 +99,7 @@ void vnt_run_command(struct work_struct *work)
 		if (vnt_init(priv)) {
 			/* If fail all ends TODO retry */
 			dev_err(&priv->usb->dev, "failed to start\n");
+			usb_set_intfdata(priv->intf, NULL);
 			ieee80211_free_hw(priv->hw);
 			return;
 		}
diff --git a/drivers/staging/wilc1000/wilc_wlan.c b/drivers/staging/wilc1000/wilc_wlan.c
index 95eaf8fdf4f2..c38a0023b1f1 100644
--- a/drivers/staging/wilc1000/wilc_wlan.c
+++ b/drivers/staging/wilc1000/wilc_wlan.c
@@ -586,7 +586,6 @@ int wilc_wlan_handle_txq(struct net_device *dev, u32 *txq_count)
 				entries = ((reg >> 3) & 0x3f);
 				break;
 			}
-			release_bus(wilc, WILC_BUS_RELEASE_ALLOW_SLEEP);
 		} while (--timeout);
 		if (timeout <= 0) {
 			ret = func->hif_write_reg(wilc, WILC_HOST_VMM_CTL, 0x0);
diff --git a/drivers/staging/wlan-ng/Kconfig b/drivers/staging/wlan-ng/Kconfig
index ac136663fa8e..082c16a31616 100644
--- a/drivers/staging/wlan-ng/Kconfig
+++ b/drivers/staging/wlan-ng/Kconfig
@@ -4,6 +4,7 @@ config PRISM2_USB
 	depends on WLAN && USB && CFG80211
 	select WIRELESS_EXT
 	select WEXT_PRIV
+	select CRC32
 	help
 	  This is the wlan-ng prism 2.5/3 USB driver for a wide range of
 	  old USB wireless devices.
diff --git a/drivers/staging/wlan-ng/hfa384x_usb.c b/drivers/staging/wlan-ng/hfa384x_usb.c
index ab734534093b..a93370af5426 100644
--- a/drivers/staging/wlan-ng/hfa384x_usb.c
+++ b/drivers/staging/wlan-ng/hfa384x_usb.c
@@ -532,13 +532,8 @@ static void hfa384x_usb_defer(struct work_struct *data)
  */
 void hfa384x_create(struct hfa384x *hw, struct usb_device *usb)
 {
-	memset(hw, 0, sizeof(*hw));
 	hw->usb = usb;
 
-	/* set up the endpoints */
-	hw->endp_in = usb_rcvbulkpipe(usb, 1);
-	hw->endp_out = usb_sndbulkpipe(usb, 2);
-
 	/* Set up the waitq */
 	init_waitqueue_head(&hw->cmdq);
 
@@ -3494,6 +3489,8 @@ static void hfa384x_int_rxmonitor(struct wlandevice *wlandev,
 	     WLAN_HDR_A4_LEN + WLAN_DATA_MAXLEN + WLAN_CRC_LEN)) {
 		pr_debug("overlen frm: len=%zd\n",
 			 skblen - sizeof(struct p80211_caphdr));
+
+		return;
 	}
 
 	skb = dev_alloc_skb(skblen);
diff --git a/drivers/staging/wlan-ng/prism2mgmt.c b/drivers/staging/wlan-ng/prism2mgmt.c
index 7350fe5d96a3..a8860d2aee68 100644
--- a/drivers/staging/wlan-ng/prism2mgmt.c
+++ b/drivers/staging/wlan-ng/prism2mgmt.c
@@ -959,7 +959,7 @@ int prism2mgmt_flashdl_state(struct wlandevice *wlandev, void *msgp)
 		}
 	}
 
-	return 0;
+	return result;
 }
 
 /*----------------------------------------------------------------
diff --git a/drivers/staging/wlan-ng/prism2usb.c b/drivers/staging/wlan-ng/prism2usb.c
index b5ba176004c1..9eee72aff723 100644
--- a/drivers/staging/wlan-ng/prism2usb.c
+++ b/drivers/staging/wlan-ng/prism2usb.c
@@ -61,11 +61,16 @@ static int prism2sta_probe_usb(struct usb_interface *interface,
 			       const struct usb_device_id *id)
 {
 	struct usb_device *dev;
-
+	struct usb_endpoint_descriptor *bulk_in, *bulk_out;
+	struct usb_host_interface *iface_desc = interface->cur_altsetting;
 	struct wlandevice *wlandev = NULL;
 	struct hfa384x *hw = NULL;
 	int result = 0;
 
+	result = usb_find_common_endpoints(iface_desc, &bulk_in, &bulk_out, NULL, NULL);
+	if (result)
+		goto failed;
+
 	dev = interface_to_usbdev(interface);
 	wlandev = create_wlan();
 	if (!wlandev) {
@@ -82,6 +87,8 @@ static int prism2sta_probe_usb(struct usb_interface *interface,
 	}
 
 	/* Initialize the hw data */
+	hw->endp_in = usb_rcvbulkpipe(dev, bulk_in->bEndpointAddress);
+	hw->endp_out = usb_sndbulkpipe(dev, bulk_out->bEndpointAddress);
 	hfa384x_create(hw, dev);
 	hw->wlandev = wlandev;
 
@@ -180,6 +187,7 @@ static void prism2sta_disconnect_usb(struct usb_interface *interface)
 
 		cancel_work_sync(&hw->link_bh);
 		cancel_work_sync(&hw->commsqual_bh);
+		cancel_work_sync(&hw->usb_work);
 
 		/* Now we complete any outstanding commands
 		 * and tell everyone who is waiting for their
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index d19e051f2bc2..d1ce94c608a9 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -4303,30 +4303,37 @@ int iscsit_close_connection(
 	if (!atomic_read(&sess->session_reinstatement) &&
 	     atomic_read(&sess->session_fall_back_to_erl0)) {
 		spin_unlock_bh(&sess->conn_lock);
+		complete_all(&sess->session_wait_comp);
 		iscsit_close_session(sess);
 
 		return 0;
 	} else if (atomic_read(&sess->session_logout)) {
 		pr_debug("Moving to TARG_SESS_STATE_FREE.\n");
 		sess->session_state = TARG_SESS_STATE_FREE;
-		spin_unlock_bh(&sess->conn_lock);
 
-		if (atomic_read(&sess->sleep_on_sess_wait_comp))
-			complete(&sess->session_wait_comp);
+		if (atomic_read(&sess->session_close)) {
+			spin_unlock_bh(&sess->conn_lock);
+			complete_all(&sess->session_wait_comp);
+			iscsit_close_session(sess);
+		} else {
+			spin_unlock_bh(&sess->conn_lock);
+		}
 
 		return 0;
 	} else {
 		pr_debug("Moving to TARG_SESS_STATE_FAILED.\n");
 		sess->session_state = TARG_SESS_STATE_FAILED;
 
-		if (!atomic_read(&sess->session_continuation)) {
-			spin_unlock_bh(&sess->conn_lock);
+		if (!atomic_read(&sess->session_continuation))
 			iscsit_start_time2retain_handler(sess);
-		} else
-			spin_unlock_bh(&sess->conn_lock);
 
-		if (atomic_read(&sess->sleep_on_sess_wait_comp))
-			complete(&sess->session_wait_comp);
+		if (atomic_read(&sess->session_close)) {
+			spin_unlock_bh(&sess->conn_lock);
+			complete_all(&sess->session_wait_comp);
+			iscsit_close_session(sess);
+		} else {
+			spin_unlock_bh(&sess->conn_lock);
+		}
 
 		return 0;
 	}
@@ -4432,9 +4439,9 @@ static void iscsit_logout_post_handler_closesession(
 	complete(&conn->conn_logout_comp);
 
 	iscsit_dec_conn_usage_count(conn);
+	atomic_set(&sess->session_close, 1);
 	iscsit_stop_session(sess, sleep, sleep);
 	iscsit_dec_session_usage_count(sess);
-	iscsit_close_session(sess);
 }
 
 static void iscsit_logout_post_handler_samecid(
@@ -4569,49 +4576,6 @@ void iscsit_fail_session(struct iscsi_session *sess)
 	sess->session_state = TARG_SESS_STATE_FAILED;
 }
 
-int iscsit_free_session(struct iscsi_session *sess)
-{
-	u16 conn_count = atomic_read(&sess->nconn);
-	struct iscsi_conn *conn, *conn_tmp = NULL;
-	int is_last;
-
-	spin_lock_bh(&sess->conn_lock);
-	atomic_set(&sess->sleep_on_sess_wait_comp, 1);
-
-	list_for_each_entry_safe(conn, conn_tmp, &sess->sess_conn_list,
-			conn_list) {
-		if (conn_count == 0)
-			break;
-
-		if (list_is_last(&conn->conn_list, &sess->sess_conn_list)) {
-			is_last = 1;
-		} else {
-			iscsit_inc_conn_usage_count(conn_tmp);
-			is_last = 0;
-		}
-		iscsit_inc_conn_usage_count(conn);
-
-		spin_unlock_bh(&sess->conn_lock);
-		iscsit_cause_connection_reinstatement(conn, 1);
-		spin_lock_bh(&sess->conn_lock);
-
-		iscsit_dec_conn_usage_count(conn);
-		if (is_last == 0)
-			iscsit_dec_conn_usage_count(conn_tmp);
-
-		conn_count--;
-	}
-
-	if (atomic_read(&sess->nconn)) {
-		spin_unlock_bh(&sess->conn_lock);
-		wait_for_completion(&sess->session_wait_comp);
-	} else
-		spin_unlock_bh(&sess->conn_lock);
-
-	iscsit_close_session(sess);
-	return 0;
-}
-
 void iscsit_stop_session(
 	struct iscsi_session *sess,
 	int session_sleep,
@@ -4622,8 +4586,6 @@ void iscsit_stop_session(
 	int is_last;
 
 	spin_lock_bh(&sess->conn_lock);
-	if (session_sleep)
-		atomic_set(&sess->sleep_on_sess_wait_comp, 1);
 
 	if (connection_sleep) {
 		list_for_each_entry_safe(conn, conn_tmp, &sess->sess_conn_list,
@@ -4681,12 +4643,15 @@ int iscsit_release_sessions_for_tpg(struct iscsi_portal_group *tpg, int force)
 		spin_lock(&sess->conn_lock);
 		if (atomic_read(&sess->session_fall_back_to_erl0) ||
 		    atomic_read(&sess->session_logout) ||
+		    atomic_read(&sess->session_close) ||
 		    (sess->time2retain_timer_flags & ISCSI_TF_EXPIRED)) {
 			spin_unlock(&sess->conn_lock);
 			continue;
 		}
+		iscsit_inc_session_usage_count(sess);
 		atomic_set(&sess->session_reinstatement, 1);
 		atomic_set(&sess->session_fall_back_to_erl0, 1);
+		atomic_set(&sess->session_close, 1);
 		spin_unlock(&sess->conn_lock);
 
 		list_move_tail(&se_sess->sess_list, &free_list);
@@ -4696,7 +4661,9 @@ int iscsit_release_sessions_for_tpg(struct iscsi_portal_group *tpg, int force)
 	list_for_each_entry_safe(se_sess, se_sess_tmp, &free_list, sess_list) {
 		sess = (struct iscsi_session *)se_sess->fabric_sess_ptr;
 
-		iscsit_free_session(sess);
+		list_del_init(&se_sess->sess_list);
+		iscsit_stop_session(sess, 1, 1);
+		iscsit_dec_session_usage_count(sess);
 		session_count++;
 	}
 
diff --git a/drivers/target/iscsi/iscsi_target.h b/drivers/target/iscsi/iscsi_target.h
index c95f56a3ce31..7409ce2a6607 100644
--- a/drivers/target/iscsi/iscsi_target.h
+++ b/drivers/target/iscsi/iscsi_target.h
@@ -43,7 +43,6 @@ extern int iscsi_target_rx_thread(void *);
 extern int iscsit_close_connection(struct iscsi_conn *);
 extern int iscsit_close_session(struct iscsi_session *);
 extern void iscsit_fail_session(struct iscsi_session *);
-extern int iscsit_free_session(struct iscsi_session *);
 extern void iscsit_stop_session(struct iscsi_session *, int, int);
 extern int iscsit_release_sessions_for_tpg(struct iscsi_portal_group *, int);
 
diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c
index 42b369fc415e..0fa1d57b26fa 100644
--- a/drivers/target/iscsi/iscsi_target_configfs.c
+++ b/drivers/target/iscsi/iscsi_target_configfs.c
@@ -1476,20 +1476,23 @@ static void lio_tpg_close_session(struct se_session *se_sess)
 	spin_lock(&sess->conn_lock);
 	if (atomic_read(&sess->session_fall_back_to_erl0) ||
 	    atomic_read(&sess->session_logout) ||
+	    atomic_read(&sess->session_close) ||
 	    (sess->time2retain_timer_flags & ISCSI_TF_EXPIRED)) {
 		spin_unlock(&sess->conn_lock);
 		spin_unlock_bh(&se_tpg->session_lock);
 		return;
 	}
+	iscsit_inc_session_usage_count(sess);
 	atomic_set(&sess->session_reinstatement, 1);
 	atomic_set(&sess->session_fall_back_to_erl0, 1);
+	atomic_set(&sess->session_close, 1);
 	spin_unlock(&sess->conn_lock);
 
 	iscsit_stop_time2retain_timer(sess);
 	spin_unlock_bh(&se_tpg->session_lock);
 
 	iscsit_stop_session(sess, 1, 1);
-	iscsit_close_session(sess);
+	iscsit_dec_session_usage_count(sess);
 }
 
 static u32 lio_tpg_get_inst_index(struct se_portal_group *se_tpg)
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index f53330813207..731ee67fe914 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -156,6 +156,7 @@ int iscsi_check_for_session_reinstatement(struct iscsi_conn *conn)
 		spin_lock(&sess_p->conn_lock);
 		if (atomic_read(&sess_p->session_fall_back_to_erl0) ||
 		    atomic_read(&sess_p->session_logout) ||
+		    atomic_read(&sess_p->session_close) ||
 		    (sess_p->time2retain_timer_flags & ISCSI_TF_EXPIRED)) {
 			spin_unlock(&sess_p->conn_lock);
 			continue;
@@ -166,6 +167,7 @@ int iscsi_check_for_session_reinstatement(struct iscsi_conn *conn)
 		   (sess_p->sess_ops->SessionType == sessiontype))) {
 			atomic_set(&sess_p->session_reinstatement, 1);
 			atomic_set(&sess_p->session_fall_back_to_erl0, 1);
+			atomic_set(&sess_p->session_close, 1);
 			spin_unlock(&sess_p->conn_lock);
 			iscsit_inc_session_usage_count(sess_p);
 			iscsit_stop_time2retain_timer(sess_p);
@@ -190,7 +192,6 @@ int iscsi_check_for_session_reinstatement(struct iscsi_conn *conn)
 	if (sess->session_state == TARG_SESS_STATE_FAILED) {
 		spin_unlock_bh(&sess->conn_lock);
 		iscsit_dec_session_usage_count(sess);
-		iscsit_close_session(sess);
 		return 0;
 	}
 	spin_unlock_bh(&sess->conn_lock);
@@ -198,7 +199,6 @@ int iscsi_check_for_session_reinstatement(struct iscsi_conn *conn)
 	iscsit_stop_session(sess, 1, 1);
 	iscsit_dec_session_usage_count(sess);
 
-	iscsit_close_session(sess);
 	return 0;
 }
 
@@ -486,6 +486,7 @@ static int iscsi_login_non_zero_tsih_s2(
 		sess_p = (struct iscsi_session *)se_sess->fabric_sess_ptr;
 		if (atomic_read(&sess_p->session_fall_back_to_erl0) ||
 		    atomic_read(&sess_p->session_logout) ||
+		    atomic_read(&sess_p->session_close) ||
 		   (sess_p->time2retain_timer_flags & ISCSI_TF_EXPIRED))
 			continue;
 		if (!memcmp(sess_p->isid, pdu->isid, 6) &&
diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index 3305b47fdf53..16d5a4e117a2 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -545,32 +545,15 @@ static int tcm_loop_write_pending(struct se_cmd *se_cmd)
 	return 0;
 }
 
-static int tcm_loop_queue_data_in(struct se_cmd *se_cmd)
+static int tcm_loop_queue_data_or_status(const char *func,
+		struct se_cmd *se_cmd, u8 scsi_status)
 {
 	struct tcm_loop_cmd *tl_cmd = container_of(se_cmd,
 				struct tcm_loop_cmd, tl_se_cmd);
 	struct scsi_cmnd *sc = tl_cmd->sc;
 
 	pr_debug("%s() called for scsi_cmnd: %p cdb: 0x%02x\n",
-		 __func__, sc, sc->cmnd[0]);
-
-	sc->result = SAM_STAT_GOOD;
-	set_host_byte(sc, DID_OK);
-	if ((se_cmd->se_cmd_flags & SCF_OVERFLOW_BIT) ||
-	    (se_cmd->se_cmd_flags & SCF_UNDERFLOW_BIT))
-		scsi_set_resid(sc, se_cmd->residual_count);
-	sc->scsi_done(sc);
-	return 0;
-}
-
-static int tcm_loop_queue_status(struct se_cmd *se_cmd)
-{
-	struct tcm_loop_cmd *tl_cmd = container_of(se_cmd,
-				struct tcm_loop_cmd, tl_se_cmd);
-	struct scsi_cmnd *sc = tl_cmd->sc;
-
-	pr_debug("%s() called for scsi_cmnd: %p cdb: 0x%02x\n",
-		 __func__, sc, sc->cmnd[0]);
+		 func, sc, sc->cmnd[0]);
 
 	if (se_cmd->sense_buffer &&
 	   ((se_cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE) ||
@@ -581,7 +564,7 @@ static int tcm_loop_queue_status(struct se_cmd *se_cmd)
 		sc->result = SAM_STAT_CHECK_CONDITION;
 		set_driver_byte(sc, DRIVER_SENSE);
 	} else
-		sc->result = se_cmd->scsi_status;
+		sc->result = scsi_status;
 
 	set_host_byte(sc, DID_OK);
 	if ((se_cmd->se_cmd_flags & SCF_OVERFLOW_BIT) ||
@@ -591,6 +574,17 @@ static int tcm_loop_queue_status(struct se_cmd *se_cmd)
 	return 0;
 }
 
+static int tcm_loop_queue_data_in(struct se_cmd *se_cmd)
+{
+	return tcm_loop_queue_data_or_status(__func__, se_cmd, SAM_STAT_GOOD);
+}
+
+static int tcm_loop_queue_status(struct se_cmd *se_cmd)
+{
+	return tcm_loop_queue_data_or_status(__func__,
+					     se_cmd, se_cmd->scsi_status);
+}
+
 static void tcm_loop_queue_tm_rsp(struct se_cmd *se_cmd)
 {
 	struct tcm_loop_cmd *tl_cmd = container_of(se_cmd,
diff --git a/drivers/target/target_core_fabric_lib.c b/drivers/target/target_core_fabric_lib.c
index 3c79411c4cd0..b5c970faf585 100644
--- a/drivers/target/target_core_fabric_lib.c
+++ b/drivers/target/target_core_fabric_lib.c
@@ -63,7 +63,7 @@ static int fc_get_pr_transport_id(
 	 * encoded TransportID.
 	 */
 	ptr = &se_nacl->initiatorname[0];
-	for (i = 0; i < 24; ) {
+	for (i = 0; i < 23; ) {
 		if (!strncmp(&ptr[i], ":", 1)) {
 			i++;
 			continue;
@@ -118,7 +118,7 @@ static int srp_get_pr_transport_id(
 	memset(buf + 8, 0, leading_zero_bytes);
 	rc = hex2bin(buf + 8 + leading_zero_bytes, p, count);
 	if (rc < 0) {
-		pr_debug("hex2bin failed for %s: %d\n", __func__, rc);
+		pr_debug("hex2bin failed for %s: %d\n", p, rc);
 		return rc;
 	}
 
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 6949ea8bc387..1c181d31f4c8 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -432,7 +432,7 @@ iblock_execute_zero_out(struct block_device *bdev, struct se_cmd *cmd)
 				target_to_linux_sector(dev, cmd->t_task_lba),
 				target_to_linux_sector(dev,
 					sbc_get_write_same_sectors(cmd)),
-				GFP_KERNEL, false);
+				GFP_KERNEL, BLKDEV_ZERO_NOUNMAP);
 	if (ret)
 		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 
@@ -646,7 +646,9 @@ iblock_alloc_bip(struct se_cmd *cmd, struct bio *bio,
 	}
 
 	bip->bip_iter.bi_size = bio_integrity_bytes(bi, bio_sectors(bio));
-	bip_set_seed(bip, bio->bi_iter.bi_sector);
+	/* virtual start sector must be in integrity interval units */
+	bip_set_seed(bip, bio->bi_iter.bi_sector >>
+				  (bi->interval_exp - SECTOR_SHIFT));
 
 	pr_debug("IBLOCK BIP Size: %u Sector: %llu\n", bip->bip_iter.bi_size,
 		 (unsigned long long)bip->bip_iter.bi_sector);
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index eda8b4736c15..7c78a5d02c08 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -666,6 +666,11 @@ static int transport_cmd_check_stop_to_fabric(struct se_cmd *cmd)
 
 	target_remove_from_state_list(cmd);
 
+	/*
+	 * Clear struct se_cmd->se_lun before the handoff to FE.
+	 */
+	cmd->se_lun = NULL;
+
 	spin_lock_irqsave(&cmd->t_state_lock, flags);
 	/*
 	 * Determine if frontend context caller is requesting the stopping of
@@ -693,6 +698,17 @@ static int transport_cmd_check_stop_to_fabric(struct se_cmd *cmd)
 	return cmd->se_tfo->check_stop_free(cmd);
 }
 
+static void transport_lun_remove_cmd(struct se_cmd *cmd)
+{
+	struct se_lun *lun = cmd->se_lun;
+
+	if (!lun)
+		return;
+
+	if (cmpxchg(&cmd->lun_ref_active, true, false))
+		percpu_ref_put(&lun->lun_ref);
+}
+
 static void target_complete_failure_work(struct work_struct *work)
 {
 	struct se_cmd *cmd = container_of(work, struct se_cmd, work);
@@ -783,6 +799,8 @@ static void target_handle_abort(struct se_cmd *cmd)
 
 	WARN_ON_ONCE(kref_read(&cmd->cmd_kref) == 0);
 
+	transport_lun_remove_cmd(cmd);
+
 	transport_cmd_check_stop_to_fabric(cmd);
 }
 
@@ -1695,6 +1713,7 @@ static void target_complete_tmr_failure(struct work_struct *work)
 	se_cmd->se_tmr_req->response = TMR_LUN_DOES_NOT_EXIST;
 	se_cmd->se_tfo->queue_tm_rsp(se_cmd);
 
+	transport_lun_remove_cmd(se_cmd);
 	transport_cmd_check_stop_to_fabric(se_cmd);
 }
 
@@ -1885,6 +1904,7 @@ void transport_generic_request_failure(struct se_cmd *cmd,
 		goto queue_full;
 
 check_stop:
+	transport_lun_remove_cmd(cmd);
 	transport_cmd_check_stop_to_fabric(cmd);
 	return;
 
@@ -2182,6 +2202,7 @@ queue_status:
 		transport_handle_queue_full(cmd, cmd->se_dev, ret, false);
 		return;
 	}
+	transport_lun_remove_cmd(cmd);
 	transport_cmd_check_stop_to_fabric(cmd);
 }
 
@@ -2276,6 +2297,7 @@ static void target_complete_ok_work(struct work_struct *work)
 		if (ret)
 			goto queue_full;
 
+		transport_lun_remove_cmd(cmd);
 		transport_cmd_check_stop_to_fabric(cmd);
 		return;
 	}
@@ -2301,6 +2323,7 @@ static void target_complete_ok_work(struct work_struct *work)
 			if (ret)
 				goto queue_full;
 
+			transport_lun_remove_cmd(cmd);
 			transport_cmd_check_stop_to_fabric(cmd);
 			return;
 		}
@@ -2336,6 +2359,7 @@ queue_rsp:
 			if (ret)
 				goto queue_full;
 
+			transport_lun_remove_cmd(cmd);
 			transport_cmd_check_stop_to_fabric(cmd);
 			return;
 		}
@@ -2371,6 +2395,7 @@ queue_status:
 		break;
 	}
 
+	transport_lun_remove_cmd(cmd);
 	transport_cmd_check_stop_to_fabric(cmd);
 	return;
 
@@ -2697,6 +2722,9 @@ int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks)
 		 */
 		if (cmd->state_active)
 			target_remove_from_state_list(cmd);
+
+		if (cmd->se_lun)
+			transport_lun_remove_cmd(cmd);
 	}
 	if (aborted)
 		cmd->free_compl = &compl;
@@ -2768,9 +2796,6 @@ static void target_release_cmd_kref(struct kref *kref)
 	struct completion *abrt_compl = se_cmd->abrt_compl;
 	unsigned long flags;
 
-	if (se_cmd->lun_ref_active)
-		percpu_ref_put(&se_cmd->se_lun->lun_ref);
-
 	if (se_sess) {
 		spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
 		list_del_init(&se_cmd->se_cmd_list);
@@ -3311,6 +3336,7 @@ static void target_tmr_work(struct work_struct *work)
 
 	cmd->se_tfo->queue_tm_rsp(cmd);
 
+	transport_lun_remove_cmd(cmd);
 	transport_cmd_check_stop_to_fabric(cmd);
 	return;
 
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 95b2371fb67b..e68c20ee140a 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -882,41 +882,24 @@ static inline size_t tcmu_cmd_get_cmd_size(struct tcmu_cmd *tcmu_cmd,
 	return command_size;
 }
 
-static int tcmu_setup_cmd_timer(struct tcmu_cmd *tcmu_cmd, unsigned int tmo,
-				struct timer_list *timer)
+static void tcmu_setup_cmd_timer(struct tcmu_cmd *tcmu_cmd, unsigned int tmo,
+				 struct timer_list *timer)
 {
-	struct tcmu_dev *udev = tcmu_cmd->tcmu_dev;
-	int cmd_id;
-
-	if (tcmu_cmd->cmd_id)
-		goto setup_timer;
-
-	cmd_id = idr_alloc(&udev->commands, tcmu_cmd, 1, USHRT_MAX, GFP_NOWAIT);
-	if (cmd_id < 0) {
-		pr_err("tcmu: Could not allocate cmd id.\n");
-		return cmd_id;
-	}
-	tcmu_cmd->cmd_id = cmd_id;
-
-	pr_debug("allocated cmd %u for dev %s tmo %lu\n", tcmu_cmd->cmd_id,
-		 udev->name, tmo / MSEC_PER_SEC);
-
-setup_timer:
 	if (!tmo)
-		return 0;
+		return;
 
 	tcmu_cmd->deadline = round_jiffies_up(jiffies + msecs_to_jiffies(tmo));
 	if (!timer_pending(timer))
 		mod_timer(timer, tcmu_cmd->deadline);
 
-	return 0;
+	pr_debug("Timeout set up for cmd %p, dev = %s, tmo = %lu\n", tcmu_cmd,
+		 tcmu_cmd->tcmu_dev->name, tmo / MSEC_PER_SEC);
 }
 
 static int add_to_qfull_queue(struct tcmu_cmd *tcmu_cmd)
 {
 	struct tcmu_dev *udev = tcmu_cmd->tcmu_dev;
 	unsigned int tmo;
-	int ret;
 
 	/*
 	 * For backwards compat if qfull_time_out is not set use
@@ -931,13 +914,11 @@ static int add_to_qfull_queue(struct tcmu_cmd *tcmu_cmd)
 	else
 		tmo = TCMU_TIME_OUT;
 
-	ret = tcmu_setup_cmd_timer(tcmu_cmd, tmo, &udev->qfull_timer);
-	if (ret)
-		return ret;
+	tcmu_setup_cmd_timer(tcmu_cmd, tmo, &udev->qfull_timer);
 
 	list_add_tail(&tcmu_cmd->queue_entry, &udev->qfull_queue);
-	pr_debug("adding cmd %u on dev %s to ring space wait queue\n",
-		 tcmu_cmd->cmd_id, udev->name);
+	pr_debug("adding cmd %p on dev %s to ring space wait queue\n",
+		 tcmu_cmd, udev->name);
 	return 0;
 }
 
@@ -959,7 +940,7 @@ static int queue_cmd_ring(struct tcmu_cmd *tcmu_cmd, sense_reason_t *scsi_err)
 	struct tcmu_mailbox *mb;
 	struct tcmu_cmd_entry *entry;
 	struct iovec *iov;
-	int iov_cnt, ret;
+	int iov_cnt, cmd_id;
 	uint32_t cmd_head;
 	uint64_t cdb_off;
 	bool copy_to_data_area;
@@ -1060,14 +1041,21 @@ static int queue_cmd_ring(struct tcmu_cmd *tcmu_cmd, sense_reason_t *scsi_err)
 	}
 	entry->req.iov_bidi_cnt = iov_cnt;
 
-	ret = tcmu_setup_cmd_timer(tcmu_cmd, udev->cmd_time_out,
-				   &udev->cmd_timer);
-	if (ret) {
-		tcmu_cmd_free_data(tcmu_cmd, tcmu_cmd->dbi_cnt);
+	cmd_id = idr_alloc(&udev->commands, tcmu_cmd, 1, USHRT_MAX, GFP_NOWAIT);
+	if (cmd_id < 0) {
+		pr_err("tcmu: Could not allocate cmd id.\n");
 
+		tcmu_cmd_free_data(tcmu_cmd, tcmu_cmd->dbi_cnt);
 		*scsi_err = TCM_OUT_OF_RESOURCES;
 		return -1;
 	}
+	tcmu_cmd->cmd_id = cmd_id;
+
+	pr_debug("allocated cmd id %u for cmd %p dev %s\n", tcmu_cmd->cmd_id,
+		 tcmu_cmd, udev->name);
+
+	tcmu_setup_cmd_timer(tcmu_cmd, udev->cmd_time_out, &udev->cmd_timer);
+
 	entry->hdr.cmd_id = tcmu_cmd->cmd_id;
 
 	/*
@@ -1279,50 +1267,39 @@ static unsigned int tcmu_handle_completions(struct tcmu_dev *udev)
 	return handled;
 }
 
-static int tcmu_check_expired_cmd(int id, void *p, void *data)
+static void tcmu_check_expired_ring_cmd(struct tcmu_cmd *cmd)
 {
-	struct tcmu_cmd *cmd = p;
-	struct tcmu_dev *udev = cmd->tcmu_dev;
-	u8 scsi_status;
 	struct se_cmd *se_cmd;
-	bool is_running;
-
-	if (test_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags))
-		return 0;
 
 	if (!time_after(jiffies, cmd->deadline))
-		return 0;
+		return;
 
-	is_running = test_bit(TCMU_CMD_BIT_INFLIGHT, &cmd->flags);
+	set_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags);
+	list_del_init(&cmd->queue_entry);
 	se_cmd = cmd->se_cmd;
+	cmd->se_cmd = NULL;
 
-	if (is_running) {
-		/*
-		 * If cmd_time_out is disabled but qfull is set deadline
-		 * will only reflect the qfull timeout. Ignore it.
-		 */
-		if (!udev->cmd_time_out)
-			return 0;
+	pr_debug("Timing out inflight cmd %u on dev %s.\n",
+		 cmd->cmd_id, cmd->tcmu_dev->name);
 
-		set_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags);
-		/*
-		 * target_complete_cmd will translate this to LUN COMM FAILURE
-		 */
-		scsi_status = SAM_STAT_CHECK_CONDITION;
-		list_del_init(&cmd->queue_entry);
-		cmd->se_cmd = NULL;
-	} else {
-		list_del_init(&cmd->queue_entry);
-		idr_remove(&udev->commands, id);
-		tcmu_free_cmd(cmd);
-		scsi_status = SAM_STAT_TASK_SET_FULL;
-	}
+	target_complete_cmd(se_cmd, SAM_STAT_CHECK_CONDITION);
+}
 
-	pr_debug("Timing out cmd %u on dev %s that is %s.\n",
-		 id, udev->name, is_running ? "inflight" : "queued");
+static void tcmu_check_expired_queue_cmd(struct tcmu_cmd *cmd)
+{
+	struct se_cmd *se_cmd;
 
-	target_complete_cmd(se_cmd, scsi_status);
-	return 0;
+	if (!time_after(jiffies, cmd->deadline))
+		return;
+
+	pr_debug("Timing out queued cmd %p on dev %s.\n",
+		  cmd, cmd->tcmu_dev->name);
+
+	list_del_init(&cmd->queue_entry);
+	se_cmd = cmd->se_cmd;
+	tcmu_free_cmd(cmd);
+
+	target_complete_cmd(se_cmd, SAM_STAT_TASK_SET_FULL);
 }
 
 static void tcmu_device_timedout(struct tcmu_dev *udev)
@@ -1407,16 +1384,15 @@ static struct se_device *tcmu_alloc_device(struct se_hba *hba, const char *name)
 	return &udev->se_dev;
 }
 
-static bool run_qfull_queue(struct tcmu_dev *udev, bool fail)
+static void run_qfull_queue(struct tcmu_dev *udev, bool fail)
 {
 	struct tcmu_cmd *tcmu_cmd, *tmp_cmd;
 	LIST_HEAD(cmds);
-	bool drained = true;
 	sense_reason_t scsi_ret;
 	int ret;
 
 	if (list_empty(&udev->qfull_queue))
-		return true;
+		return;
 
 	pr_debug("running %s's cmdr queue forcefail %d\n", udev->name, fail);
 
@@ -1425,11 +1401,10 @@ static bool run_qfull_queue(struct tcmu_dev *udev, bool fail)
 	list_for_each_entry_safe(tcmu_cmd, tmp_cmd, &cmds, queue_entry) {
 		list_del_init(&tcmu_cmd->queue_entry);
 
-	        pr_debug("removing cmd %u on dev %s from queue\n",
-		         tcmu_cmd->cmd_id, udev->name);
+		pr_debug("removing cmd %p on dev %s from queue\n",
+			 tcmu_cmd, udev->name);
 
 		if (fail) {
-			idr_remove(&udev->commands, tcmu_cmd->cmd_id);
 			/*
 			 * We were not able to even start the command, so
 			 * fail with busy to allow a retry in case runner
@@ -1444,10 +1419,8 @@ static bool run_qfull_queue(struct tcmu_dev *udev, bool fail)
 
 		ret = queue_cmd_ring(tcmu_cmd, &scsi_ret);
 		if (ret < 0) {
-		        pr_debug("cmd %u on dev %s failed with %u\n",
-			         tcmu_cmd->cmd_id, udev->name, scsi_ret);
-
-			idr_remove(&udev->commands, tcmu_cmd->cmd_id);
+			pr_debug("cmd %p on dev %s failed with %u\n",
+				 tcmu_cmd, udev->name, scsi_ret);
 			/*
 			 * Ignore scsi_ret for now. target_complete_cmd
 			 * drops it.
@@ -1462,13 +1435,11 @@ static bool run_qfull_queue(struct tcmu_dev *udev, bool fail)
 			 * the queue
 			 */
 			list_splice_tail(&cmds, &udev->qfull_queue);
-			drained = false;
 			break;
 		}
 	}
 
 	tcmu_set_next_deadline(&udev->qfull_queue, &udev->qfull_timer);
-	return drained;
 }
 
 static int tcmu_irqcontrol(struct uio_info *info, s32 irq_on)
@@ -1652,6 +1623,8 @@ static void tcmu_dev_kref_release(struct kref *kref)
 		if (tcmu_check_and_free_pending_cmd(cmd) != 0)
 			all_expired = false;
 	}
+	if (!list_empty(&udev->qfull_queue))
+		all_expired = false;
 	idr_destroy(&udev->commands);
 	WARN_ON(!all_expired);
 
@@ -2019,9 +1992,6 @@ static void tcmu_reset_ring(struct tcmu_dev *udev, u8 err_level)
 	mutex_lock(&udev->cmdr_lock);
 
 	idr_for_each_entry(&udev->commands, cmd, i) {
-		if (!test_bit(TCMU_CMD_BIT_INFLIGHT, &cmd->flags))
-			continue;
-
 		pr_debug("removing cmd %u on dev %s from ring (is expired %d)\n",
 			  cmd->cmd_id, udev->name,
 			  test_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags));
@@ -2055,9 +2025,12 @@ static void tcmu_reset_ring(struct tcmu_dev *udev, u8 err_level)
 	mb->cmd_tail = 0;
 	mb->cmd_head = 0;
 	tcmu_flush_dcache_range(mb, sizeof(*mb));
+	clear_bit(TCMU_DEV_BIT_BROKEN, &udev->flags);
 
 	del_timer(&udev->cmd_timer);
 
+	run_qfull_queue(udev, false);
+
 	mutex_unlock(&udev->cmdr_lock);
 }
 
@@ -2679,6 +2652,7 @@ static void find_free_blocks(void)
 static void check_timedout_devices(void)
 {
 	struct tcmu_dev *udev, *tmp_dev;
+	struct tcmu_cmd *cmd, *tmp_cmd;
 	LIST_HEAD(devs);
 
 	spin_lock_bh(&timed_out_udevs_lock);
@@ -2689,9 +2663,24 @@ static void check_timedout_devices(void)
 		spin_unlock_bh(&timed_out_udevs_lock);
 
 		mutex_lock(&udev->cmdr_lock);
-		idr_for_each(&udev->commands, tcmu_check_expired_cmd, NULL);
 
-		tcmu_set_next_deadline(&udev->inflight_queue, &udev->cmd_timer);
+		/*
+		 * If cmd_time_out is disabled but qfull is set deadline
+		 * will only reflect the qfull timeout. Ignore it.
+		 */
+		if (udev->cmd_time_out) {
+			list_for_each_entry_safe(cmd, tmp_cmd,
+						 &udev->inflight_queue,
+						 queue_entry) {
+				tcmu_check_expired_ring_cmd(cmd);
+			}
+			tcmu_set_next_deadline(&udev->inflight_queue,
+					       &udev->cmd_timer);
+		}
+		list_for_each_entry_safe(cmd, tmp_cmd, &udev->qfull_queue,
+					 queue_entry) {
+			tcmu_check_expired_queue_cmd(cmd);
+		}
 		tcmu_set_next_deadline(&udev->qfull_queue, &udev->qfull_timer);
 
 		mutex_unlock(&udev->cmdr_lock);
diff --git a/drivers/tee/optee/Kconfig b/drivers/tee/optee/Kconfig
index d1ad512e1708..3ca71e3812ed 100644
--- a/drivers/tee/optee/Kconfig
+++ b/drivers/tee/optee/Kconfig
@@ -3,6 +3,7 @@
 config OPTEE
 	tristate "OP-TEE"
 	depends on HAVE_ARM_SMCCC
+	depends on MMU
 	help
 	  This implements the OP-TEE Trusted Execution Environment (TEE)
 	  driver.
diff --git a/drivers/tee/optee/call.c b/drivers/tee/optee/call.c
index aa942703ae65..bce45b16d46c 100644
--- a/drivers/tee/optee/call.c
+++ b/drivers/tee/optee/call.c
@@ -553,6 +553,13 @@ static int check_mem_type(unsigned long start, size_t num_pages)
 	struct mm_struct *mm = current->mm;
 	int rc;
 
+	/*
+	 * Allow kernel address to register with OP-TEE as kernel
+	 * pages are configured as normal memory only.
+	 */
+	if (virt_addr_valid(start))
+		return 0;
+
 	down_read(&mm->mmap_sem);
 	rc = __check_mem_type(find_vma(mm, start),
 			      start + num_pages * PAGE_SIZE);
diff --git a/drivers/tee/optee/core.c b/drivers/tee/optee/core.c
index 1854a3db7345..b830e0a87fba 100644
--- a/drivers/tee/optee/core.c
+++ b/drivers/tee/optee/core.c
@@ -643,11 +643,6 @@ static struct optee *optee_probe(struct device_node *np)
 	if (optee->sec_caps & OPTEE_SMC_SEC_CAP_DYNAMIC_SHM)
 		pr_info("dynamic shared memory is enabled\n");
 
-	rc = optee_enumerate_devices();
-	if (rc)
-		goto err;
-
-	pr_info("initialized driver\n");
 	return optee;
 err:
 	if (optee) {
@@ -702,9 +697,10 @@ static struct optee *optee_svc;
 
 static int __init optee_driver_init(void)
 {
-	struct device_node *fw_np;
-	struct device_node *np;
-	struct optee *optee;
+	struct device_node *fw_np = NULL;
+	struct device_node *np = NULL;
+	struct optee *optee = NULL;
+	int rc = 0;
 
 	/* Node is supposed to be below /firmware */
 	fw_np = of_find_node_by_name(NULL, "firmware");
@@ -723,6 +719,14 @@ static int __init optee_driver_init(void)
 	if (IS_ERR(optee))
 		return PTR_ERR(optee);
 
+	rc = optee_enumerate_devices();
+	if (rc) {
+		optee_remove(optee);
+		return rc;
+	}
+
+	pr_info("initialized driver\n");
+
 	optee_svc = optee;
 
 	return 0;
diff --git a/drivers/tee/optee/shm_pool.c b/drivers/tee/optee/shm_pool.c
index de1d9b8fad90..d767eebf30bd 100644
--- a/drivers/tee/optee/shm_pool.c
+++ b/drivers/tee/optee/shm_pool.c
@@ -17,6 +17,7 @@ static int pool_op_alloc(struct tee_shm_pool_mgr *poolm,
 {
 	unsigned int order = get_order(size);
 	struct page *page;
+	int rc = 0;
 
 	page = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
 	if (!page)
@@ -26,12 +27,34 @@ static int pool_op_alloc(struct tee_shm_pool_mgr *poolm,
 	shm->paddr = page_to_phys(page);
 	shm->size = PAGE_SIZE << order;
 
-	return 0;
+	if (shm->flags & TEE_SHM_DMA_BUF) {
+		unsigned int nr_pages = 1 << order, i;
+		struct page **pages;
+
+		pages = kcalloc(nr_pages, sizeof(pages), GFP_KERNEL);
+		if (!pages)
+			return -ENOMEM;
+
+		for (i = 0; i < nr_pages; i++) {
+			pages[i] = page;
+			page++;
+		}
+
+		shm->flags |= TEE_SHM_REGISTER;
+		rc = optee_shm_register(shm->ctx, shm, pages, nr_pages,
+					(unsigned long)shm->kaddr);
+		kfree(pages);
+	}
+
+	return rc;
 }
 
 static void pool_op_free(struct tee_shm_pool_mgr *poolm,
 			 struct tee_shm *shm)
 {
+	if (shm->flags & TEE_SHM_DMA_BUF)
+		optee_shm_unregister(shm->ctx, shm);
+
 	free_pages((unsigned long)shm->kaddr, get_order(shm->size));
 	shm->kaddr = NULL;
 }
diff --git a/drivers/thermal/broadcom/brcmstb_thermal.c b/drivers/thermal/broadcom/brcmstb_thermal.c
index 5825ac581f56..680f1a070606 100644
--- a/drivers/thermal/broadcom/brcmstb_thermal.c
+++ b/drivers/thermal/broadcom/brcmstb_thermal.c
@@ -49,7 +49,7 @@
 #define AVS_TMON_TP_TEST_ENABLE		0x20
 
 /* Default coefficients */
-#define AVS_TMON_TEMP_SLOPE		-487
+#define AVS_TMON_TEMP_SLOPE		487
 #define AVS_TMON_TEMP_OFFSET		410040
 
 /* HW related temperature constants */
@@ -108,23 +108,12 @@ struct brcmstb_thermal_priv {
 	struct thermal_zone_device *thermal;
 };
 
-static void avs_tmon_get_coeffs(struct thermal_zone_device *tz, int *slope,
-				int *offset)
-{
-	*slope = thermal_zone_get_slope(tz);
-	*offset = thermal_zone_get_offset(tz);
-}
-
 /* Convert a HW code to a temperature reading (millidegree celsius) */
 static inline int avs_tmon_code_to_temp(struct thermal_zone_device *tz,
 					u32 code)
 {
-	const int val = code & AVS_TMON_TEMP_MASK;
-	int slope, offset;
-
-	avs_tmon_get_coeffs(tz, &slope, &offset);
-
-	return slope * val + offset;
+	return (AVS_TMON_TEMP_OFFSET -
+		(int)((code & AVS_TMON_TEMP_MAX) * AVS_TMON_TEMP_SLOPE));
 }
 
 /*
@@ -136,20 +125,18 @@ static inline int avs_tmon_code_to_temp(struct thermal_zone_device *tz,
 static inline u32 avs_tmon_temp_to_code(struct thermal_zone_device *tz,
 					int temp, bool low)
 {
-	int slope, offset;
-
 	if (temp < AVS_TMON_TEMP_MIN)
-		return AVS_TMON_TEMP_MAX; /* Maximum code value */
-
-	avs_tmon_get_coeffs(tz, &slope, &offset);
+		return AVS_TMON_TEMP_MAX;	/* Maximum code value */
 
-	if (temp >= offset)
+	if (temp >= AVS_TMON_TEMP_OFFSET)
 		return 0;	/* Minimum code value */
 
 	if (low)
-		return (u32)(DIV_ROUND_UP(offset - temp, abs(slope)));
+		return (u32)(DIV_ROUND_UP(AVS_TMON_TEMP_OFFSET - temp,
+					  AVS_TMON_TEMP_SLOPE));
 	else
-		return (u32)((offset - temp) / abs(slope));
+		return (u32)((AVS_TMON_TEMP_OFFSET - temp) /
+			      AVS_TMON_TEMP_SLOPE);
 }
 
 static int brcmstb_get_temp(void *data, int *temp)
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 4c5db59a619b..a4baa5d21ecd 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -264,11 +264,11 @@ static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_cdev,
 	int i;
 	struct freq_table *freq_table = cpufreq_cdev->freq_table;
 
-	for (i = 1; i <= cpufreq_cdev->max_level; i++)
-		if (power > freq_table[i].power)
+	for (i = 0; i < cpufreq_cdev->max_level; i++)
+		if (power >= freq_table[i].power)
 			break;
 
-	return freq_table[i - 1].frequency;
+	return freq_table[i].frequency;
 }
 
 /**
diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c
index bb6754a5342c..85511c1160b7 100644
--- a/drivers/thermal/imx_thermal.c
+++ b/drivers/thermal/imx_thermal.c
@@ -656,7 +656,7 @@ MODULE_DEVICE_TABLE(of, of_imx_thermal_match);
 static int imx_thermal_register_legacy_cooling(struct imx_thermal_data *data)
 {
 	struct device_node *np;
-	int ret;
+	int ret = 0;
 
 	data->policy = cpufreq_cpu_get(0);
 	if (!data->policy) {
@@ -671,11 +671,12 @@ static int imx_thermal_register_legacy_cooling(struct imx_thermal_data *data)
 		if (IS_ERR(data->cdev)) {
 			ret = PTR_ERR(data->cdev);
 			cpufreq_cpu_put(data->policy);
-			return ret;
 		}
 	}
 
-	return 0;
+	of_node_put(np);
+
+	return ret;
 }
 
 static void imx_thermal_unregister_legacy_cooling(struct imx_thermal_data *data)
diff --git a/drivers/thermal/intel/int340x_thermal/int3403_thermal.c b/drivers/thermal/intel/int340x_thermal/int3403_thermal.c
index f5749d4418ae..ff94d7f95216 100644
--- a/drivers/thermal/intel/int340x_thermal/int3403_thermal.c
+++ b/drivers/thermal/intel/int340x_thermal/int3403_thermal.c
@@ -74,7 +74,7 @@ static void int3403_notify(acpi_handle handle,
 						   THERMAL_TRIP_CHANGED);
 		break;
 	default:
-		dev_err(&priv->pdev->dev, "Unsupported event [0x%x]\n", event);
+		dev_dbg(&priv->pdev->dev, "Unsupported event [0x%x]\n", event);
 		break;
 	}
 }
diff --git a/drivers/thermal/mtk_thermal.c b/drivers/thermal/mtk_thermal.c
index acf4854cbb8b..2783973b101c 100644
--- a/drivers/thermal/mtk_thermal.c
+++ b/drivers/thermal/mtk_thermal.c
@@ -211,6 +211,9 @@ enum {
 /* The total number of temperature sensors in the MT8183 */
 #define MT8183_NUM_SENSORS	6
 
+/* The number of banks in the MT8183 */
+#define MT8183_NUM_ZONES               1
+
 /* The number of sensing points per bank */
 #define MT8183_NUM_SENSORS_PER_ZONE	 6
 
@@ -498,7 +501,7 @@ static const struct mtk_thermal_data mt7622_thermal_data = {
 
 static const struct mtk_thermal_data mt8183_thermal_data = {
 	.auxadc_channel = MT8183_TEMP_AUXADC_CHANNEL,
-	.num_banks = MT8183_NUM_SENSORS_PER_ZONE,
+	.num_banks = MT8183_NUM_ZONES,
 	.num_sensors = MT8183_NUM_SENSORS,
 	.vts_index = mt8183_vts_index,
 	.cali_val = MT8183_CALIBRATION,
@@ -591,8 +594,7 @@ static int mtk_thermal_bank_temperature(struct mtk_thermal_bank *bank)
 	u32 raw;
 
 	for (i = 0; i < conf->bank_data[bank->id].num_sensors; i++) {
-		raw = readl(mt->thermal_base +
-			    conf->msr[conf->bank_data[bank->id].sensors[i]]);
+		raw = readl(mt->thermal_base + conf->msr[i]);
 
 		temp = raw_to_mcelsius(mt,
 				       conf->bank_data[bank->id].sensors[i],
@@ -733,8 +735,7 @@ static void mtk_thermal_init_bank(struct mtk_thermal *mt, int num,
 
 	for (i = 0; i < conf->bank_data[num].num_sensors; i++)
 		writel(conf->sensor_mux_values[conf->bank_data[num].sensors[i]],
-		       mt->thermal_base +
-		       conf->adcpnp[conf->bank_data[num].sensors[i]]);
+		       mt->thermal_base + conf->adcpnp[i]);
 
 	writel((1 << conf->bank_data[num].num_sensors) - 1,
 	       controller_base + TEMP_MONCTL0);
diff --git a/drivers/thermal/rcar_gen3_thermal.c b/drivers/thermal/rcar_gen3_thermal.c
index a56463308694..7a890bde4cff 100644
--- a/drivers/thermal/rcar_gen3_thermal.c
+++ b/drivers/thermal/rcar_gen3_thermal.c
@@ -169,7 +169,7 @@ static int rcar_gen3_thermal_get_temp(void *devdata, int *temp)
 {
 	struct rcar_gen3_thermal_tsc *tsc = devdata;
 	int mcelsius, val;
-	u32 reg;
+	int reg;
 
 	/* Read register and convert to mili Celsius */
 	reg = rcar_gen3_thermal_read(tsc, REG_GEN3_TEMP) & CTEMP_MASK;
diff --git a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
index d3e959d01606..2ce4b19f312a 100644
--- a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
+++ b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
@@ -169,7 +169,7 @@ int ti_thermal_expose_sensor(struct ti_bandgap *bgp, int id,
 
 	data = ti_bandgap_get_sensor_data(bgp, id);
 
-	if (!data || IS_ERR(data))
+	if (IS_ERR_OR_NULL(data))
 		data = ti_thermal_build_data(bgp, id);
 
 	if (!data)
@@ -196,7 +196,7 @@ int ti_thermal_remove_sensor(struct ti_bandgap *bgp, int id)
 
 	data = ti_bandgap_get_sensor_data(bgp, id);
 
-	if (data && data->ti_thermal) {
+	if (!IS_ERR_OR_NULL(data) && data->ti_thermal) {
 		if (data->our_zone)
 			thermal_zone_device_unregister(data->ti_thermal);
 	}
@@ -262,7 +262,7 @@ int ti_thermal_unregister_cpu_cooling(struct ti_bandgap *bgp, int id)
 
 	data = ti_bandgap_get_sensor_data(bgp, id);
 
-	if (data) {
+	if (!IS_ERR_OR_NULL(data)) {
 		cpufreq_cooling_unregister(data->cool_dev);
 		if (data->policy)
 			cpufreq_cpu_put(data->policy);
diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c
index 416058218b16..e73ae636515f 100644
--- a/drivers/thunderbolt/switch.c
+++ b/drivers/thunderbolt/switch.c
@@ -274,6 +274,12 @@ out:
 	return ret;
 }
 
+static int tb_switch_nvm_no_read(void *priv, unsigned int offset, void *val,
+				 size_t bytes)
+{
+	return -EPERM;
+}
+
 static int tb_switch_nvm_write(void *priv, unsigned int offset, void *val,
 			       size_t bytes)
 {
@@ -319,6 +325,7 @@ static struct nvmem_device *register_nvmem(struct tb_switch *sw, int id,
 		config.read_only = true;
 	} else {
 		config.name = "nvm_non_active";
+		config.reg_read = tb_switch_nvm_no_read;
 		config.reg_write = tb_switch_nvm_write;
 		config.root_only = true;
 	}
diff --git a/drivers/tty/ehv_bytechan.c b/drivers/tty/ehv_bytechan.c
index 769e0a5d1dfc..3c6dd06ec5fb 100644
--- a/drivers/tty/ehv_bytechan.c
+++ b/drivers/tty/ehv_bytechan.c
@@ -136,6 +136,21 @@ static int find_console_handle(void)
 	return 1;
 }
 
+static unsigned int local_ev_byte_channel_send(unsigned int handle,
+					       unsigned int *count,
+					       const char *p)
+{
+	char buffer[EV_BYTE_CHANNEL_MAX_BYTES];
+	unsigned int c = *count;
+
+	if (c < sizeof(buffer)) {
+		memcpy(buffer, p, c);
+		memset(&buffer[c], 0, sizeof(buffer) - c);
+		p = buffer;
+	}
+	return ev_byte_channel_send(handle, count, p);
+}
+
 /*************************** EARLY CONSOLE DRIVER ***************************/
 
 #ifdef CONFIG_PPC_EARLY_DEBUG_EHV_BC
@@ -154,7 +169,7 @@ static void byte_channel_spin_send(const char data)
 
 	do {
 		count = 1;
-		ret = ev_byte_channel_send(CONFIG_PPC_EARLY_DEBUG_EHV_BC_HANDLE,
+		ret = local_ev_byte_channel_send(CONFIG_PPC_EARLY_DEBUG_EHV_BC_HANDLE,
 					   &count, &data);
 	} while (ret == EV_EAGAIN);
 }
@@ -221,7 +236,7 @@ static int ehv_bc_console_byte_channel_send(unsigned int handle, const char *s,
 	while (count) {
 		len = min_t(unsigned int, count, EV_BYTE_CHANNEL_MAX_BYTES);
 		do {
-			ret = ev_byte_channel_send(handle, &len, s);
+			ret = local_ev_byte_channel_send(handle, &len, s);
 		} while (ret == EV_EAGAIN);
 		count -= len;
 		s += len;
@@ -401,7 +416,7 @@ static void ehv_bc_tx_dequeue(struct ehv_bc_data *bc)
 			    CIRC_CNT_TO_END(bc->head, bc->tail, BUF_SIZE),
 			    EV_BYTE_CHANNEL_MAX_BYTES);
 
-		ret = ev_byte_channel_send(bc->handle, &len, bc->buf + bc->tail);
+		ret = local_ev_byte_channel_send(bc->handle, &len, bc->buf + bc->tail);
 
 		/* 'len' is valid only if the return code is 0 or EV_EAGAIN */
 		if (!ret || (ret == EV_EAGAIN))
diff --git a/drivers/tty/hvc/hvc_console.c b/drivers/tty/hvc/hvc_console.c
index 27284a2dcd2b..cdcc64ea2554 100644
--- a/drivers/tty/hvc/hvc_console.c
+++ b/drivers/tty/hvc/hvc_console.c
@@ -302,10 +302,6 @@ int hvc_instantiate(uint32_t vtermno, int index, const struct hv_ops *ops)
 	vtermnos[index] = vtermno;
 	cons_ops[index] = ops;
 
-	/* reserve all indices up to and including this index */
-	if (last_hvc < index)
-		last_hvc = index;
-
 	/* check if we need to re-register the kernel console */
 	hvc_check_console(index);
 
@@ -375,15 +371,14 @@ static int hvc_open(struct tty_struct *tty, struct file * filp)
 	 * tty fields and return the kref reference.
 	 */
 	if (rc) {
-		tty_port_tty_set(&hp->port, NULL);
-		tty->driver_data = NULL;
-		tty_port_put(&hp->port);
 		printk(KERN_ERR "hvc_open: request_irq failed with rc %d.\n", rc);
-	} else
+	} else {
 		/* We are ready... raise DTR/RTS */
 		if (C_BAUD(tty))
 			if (hp->ops->dtr_rts)
 				hp->ops->dtr_rts(hp, 1);
+		tty_port_set_initialized(&hp->port, true);
+	}
 
 	/* Force wakeup of the polling thread */
 	hvc_kick();
@@ -393,22 +388,12 @@ static int hvc_open(struct tty_struct *tty, struct file * filp)
 
 static void hvc_close(struct tty_struct *tty, struct file * filp)
 {
-	struct hvc_struct *hp;
+	struct hvc_struct *hp = tty->driver_data;
 	unsigned long flags;
 
 	if (tty_hung_up_p(filp))
 		return;
 
-	/*
-	 * No driver_data means that this close was issued after a failed
-	 * hvc_open by the tty layer's release_dev() function and we can just
-	 * exit cleanly because the kref reference wasn't made.
-	 */
-	if (!tty->driver_data)
-		return;
-
-	hp = tty->driver_data;
-
 	spin_lock_irqsave(&hp->port.lock, flags);
 
 	if (--hp->port.count == 0) {
@@ -416,6 +401,9 @@ static void hvc_close(struct tty_struct *tty, struct file * filp)
 		/* We are done with the tty pointer now. */
 		tty_port_tty_set(&hp->port, NULL);
 
+		if (!tty_port_initialized(&hp->port))
+			return;
+
 		if (C_HUPCL(tty))
 			if (hp->ops->dtr_rts)
 				hp->ops->dtr_rts(hp, 0);
@@ -432,6 +420,7 @@ static void hvc_close(struct tty_struct *tty, struct file * filp)
 		 * waking periodically to check chars_in_buffer().
 		 */
 		tty_wait_until_sent(tty, HVC_CLOSE_WAIT);
+		tty_port_set_initialized(&hp->port, false);
 	} else {
 		if (hp->port.count < 0)
 			printk(KERN_ERR "hvc_close %X: oops, count is %d\n",
@@ -960,13 +949,22 @@ struct hvc_struct *hvc_alloc(uint32_t vtermno, int data,
 		    cons_ops[i] == hp->ops)
 			break;
 
-	/* no matching slot, just use a counter */
-	if (i >= MAX_NR_HVC_CONSOLES)
-		i = ++last_hvc;
+	if (i >= MAX_NR_HVC_CONSOLES) {
+
+		/* find 'empty' slot for console */
+		for (i = 0; i < MAX_NR_HVC_CONSOLES && vtermnos[i] != -1; i++) {
+		}
+
+		/* no matching slot, just use a counter */
+		if (i == MAX_NR_HVC_CONSOLES)
+			i = ++last_hvc + MAX_NR_HVC_CONSOLES;
+	}
 
 	hp->index = i;
-	cons_ops[i] = ops;
-	vtermnos[i] = vtermno;
+	if (i < MAX_NR_HVC_CONSOLES) {
+		cons_ops[i] = ops;
+		vtermnos[i] = vtermno;
+	}
 
 	list_add_tail(&(hp->next), &hvc_structs);
 	mutex_unlock(&hvc_structs_mutex);
diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
index c4e16b31f9ab..18241a78e172 100644
--- a/drivers/tty/n_gsm.c
+++ b/drivers/tty/n_gsm.c
@@ -665,11 +665,10 @@ static struct gsm_msg *gsm_data_alloc(struct gsm_mux *gsm, u8 addr, int len,
  *	FIXME: lock against link layer control transmissions
  */
 
-static void gsm_data_kick(struct gsm_mux *gsm)
+static void gsm_data_kick(struct gsm_mux *gsm, struct gsm_dlci *dlci)
 {
 	struct gsm_msg *msg, *nmsg;
 	int len;
-	int skip_sof = 0;
 
 	list_for_each_entry_safe(msg, nmsg, &gsm->tx_list, list) {
 		if (gsm->constipated && msg->addr)
@@ -691,18 +690,23 @@ static void gsm_data_kick(struct gsm_mux *gsm)
 			print_hex_dump_bytes("gsm_data_kick: ",
 					     DUMP_PREFIX_OFFSET,
 					     gsm->txframe, len);
-
-		if (gsm->output(gsm, gsm->txframe + skip_sof,
-						len - skip_sof) < 0)
+		if (gsm->output(gsm, gsm->txframe, len) < 0)
 			break;
 		/* FIXME: Can eliminate one SOF in many more cases */
 		gsm->tx_bytes -= msg->len;
-		/* For a burst of frames skip the extra SOF within the
-		   burst */
-		skip_sof = 1;
 
 		list_del(&msg->list);
 		kfree(msg);
+
+		if (dlci) {
+			tty_port_tty_wakeup(&dlci->port);
+		} else {
+			int i = 0;
+
+			for (i = 0; i < NUM_DLCI; i++)
+				if (gsm->dlci[i])
+					tty_port_tty_wakeup(&gsm->dlci[i]->port);
+		}
 	}
 }
 
@@ -754,7 +758,7 @@ static void __gsm_data_queue(struct gsm_dlci *dlci, struct gsm_msg *msg)
 	/* Add to the actual output queue */
 	list_add_tail(&msg->list, &gsm->tx_list);
 	gsm->tx_bytes += msg->len;
-	gsm_data_kick(gsm);
+	gsm_data_kick(gsm, dlci);
 }
 
 /**
@@ -1215,7 +1219,7 @@ static void gsm_control_message(struct gsm_mux *gsm, unsigned int command,
 		gsm_control_reply(gsm, CMD_FCON, NULL, 0);
 		/* Kick the link in case it is idling */
 		spin_lock_irqsave(&gsm->tx_lock, flags);
-		gsm_data_kick(gsm);
+		gsm_data_kick(gsm, NULL);
 		spin_unlock_irqrestore(&gsm->tx_lock, flags);
 		break;
 	case CMD_FCOFF:
@@ -2514,7 +2518,7 @@ static void gsmld_write_wakeup(struct tty_struct *tty)
 	/* Queue poll */
 	clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags);
 	spin_lock_irqsave(&gsm->tx_lock, flags);
-	gsm_data_kick(gsm);
+	gsm_data_kick(gsm, NULL);
 	if (gsm->tx_bytes < TX_THRESH_LO) {
 		gsm_dlci_data_sweep(gsm);
 	}
diff --git a/drivers/tty/rocket.c b/drivers/tty/rocket.c
index 5ba6816ebf81..bbaad2887ce7 100644
--- a/drivers/tty/rocket.c
+++ b/drivers/tty/rocket.c
@@ -632,18 +632,21 @@ init_r_port(int board, int aiop, int chan, struct pci_dev *pci_dev)
 	tty_port_init(&info->port);
 	info->port.ops = &rocket_port_ops;
 	info->flags &= ~ROCKET_MODE_MASK;
-	switch (pc104[board][line]) {
-	case 422:
-		info->flags |= ROCKET_MODE_RS422;
-		break;
-	case 485:
-		info->flags |= ROCKET_MODE_RS485;
-		break;
-	case 232:
-	default:
+	if (board < ARRAY_SIZE(pc104) && line < ARRAY_SIZE(pc104_1))
+		switch (pc104[board][line]) {
+		case 422:
+			info->flags |= ROCKET_MODE_RS422;
+			break;
+		case 485:
+			info->flags |= ROCKET_MODE_RS485;
+			break;
+		case 232:
+		default:
+			info->flags |= ROCKET_MODE_RS232;
+			break;
+		}
+	else
 		info->flags |= ROCKET_MODE_RS232;
-		break;
-	}
 
 	info->intmask = RXF_TRIG | TXFIFO_MT | SRC_INT | DELTA_CD | DELTA_CTS | DELTA_DSR;
 	if (sInitChan(ctlp, &info->channel, aiop, chan) == 0) {
diff --git a/drivers/tty/serdev/core.c b/drivers/tty/serdev/core.c
index a0ac16ee6575..a9719858c950 100644
--- a/drivers/tty/serdev/core.c
+++ b/drivers/tty/serdev/core.c
@@ -582,6 +582,12 @@ static acpi_status acpi_serdev_register_device(struct serdev_controller *ctrl,
 	return AE_OK;
 }
 
+static const struct acpi_device_id serdev_acpi_devices_blacklist[] = {
+	{ "INT3511", 0 },
+	{ "INT3512", 0 },
+	{ },
+};
+
 static acpi_status acpi_serdev_add_device(acpi_handle handle, u32 level,
 				       void *data, void **return_value)
 {
@@ -591,6 +597,10 @@ static acpi_status acpi_serdev_add_device(acpi_handle handle, u32 level,
 	if (acpi_bus_get_device(handle, &adev))
 		return AE_OK;
 
+	/* Skip if black listed */
+	if (!acpi_match_device_ids(adev, serdev_acpi_devices_blacklist))
+		return AE_OK;
+
 	return acpi_serdev_register_device(ctrl, adev);
 }
 
diff --git a/drivers/tty/serdev/serdev-ttyport.c b/drivers/tty/serdev/serdev-ttyport.c
index d1cdd2ab8b4c..d367803e2044 100644
--- a/drivers/tty/serdev/serdev-ttyport.c
+++ b/drivers/tty/serdev/serdev-ttyport.c
@@ -265,7 +265,6 @@ struct device *serdev_tty_port_register(struct tty_port *port,
 					struct device *parent,
 					struct tty_driver *drv, int idx)
 {
-	const struct tty_port_client_operations *old_ops;
 	struct serdev_controller *ctrl;
 	struct serport *serport;
 	int ret;
@@ -284,7 +283,6 @@ struct device *serdev_tty_port_register(struct tty_port *port,
 
 	ctrl->ops = &ctrl_ops;
 
-	old_ops = port->client_ops;
 	port->client_ops = &client_ops;
 	port->client_data = ctrl;
 
@@ -297,7 +295,7 @@ struct device *serdev_tty_port_register(struct tty_port *port,
 
 err_reset_data:
 	port->client_data = NULL;
-	port->client_ops = old_ops;
+	port->client_ops = &tty_port_default_client_ops;
 	serdev_controller_put(ctrl);
 
 	return ERR_PTR(ret);
@@ -312,8 +310,8 @@ int serdev_tty_port_unregister(struct tty_port *port)
 		return -ENODEV;
 
 	serdev_controller_remove(ctrl);
-	port->client_ops = NULL;
 	port->client_data = NULL;
+	port->client_ops = &tty_port_default_client_ops;
 	serdev_controller_put(ctrl);
 
 	return 0;
diff --git a/drivers/tty/serial/8250/8250_aspeed_vuart.c b/drivers/tty/serial/8250/8250_aspeed_vuart.c
index 0438d9a905ce..6ba2efde7252 100644
--- a/drivers/tty/serial/8250/8250_aspeed_vuart.c
+++ b/drivers/tty/serial/8250/8250_aspeed_vuart.c
@@ -379,7 +379,6 @@ static int aspeed_vuart_probe(struct platform_device *pdev)
 		port.port.line = rc;
 
 	port.port.irq = irq_of_parse_and_map(np, 0);
-	port.port.irqflags = IRQF_SHARED;
 	port.port.handle_irq = aspeed_vuart_handle_irq;
 	port.port.iotype = UPIO_MEM;
 	port.port.type = PORT_16550A;
diff --git a/drivers/tty/serial/8250/8250_bcm2835aux.c b/drivers/tty/serial/8250/8250_bcm2835aux.c
index bd53661103eb..3173d98cb42d 100644
--- a/drivers/tty/serial/8250/8250_bcm2835aux.c
+++ b/drivers/tty/serial/8250/8250_bcm2835aux.c
@@ -115,7 +115,7 @@ static int bcm2835aux_serial_remove(struct platform_device *pdev)
 {
 	struct bcm2835aux_data *data = platform_get_drvdata(pdev);
 
-	serial8250_unregister_port(data->uart.port.line);
+	serial8250_unregister_port(data->line);
 	clk_disable_unprepare(data->clk);
 
 	return 0;
diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index e441221e04b9..0c4451f7c4b9 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -173,7 +173,7 @@ static int serial_link_irq_chain(struct uart_8250_port *up)
 	struct hlist_head *h;
 	struct hlist_node *n;
 	struct irq_info *i;
-	int ret, irq_flags = up->port.flags & UPF_SHARE_IRQ ? IRQF_SHARED : 0;
+	int ret;
 
 	mutex_lock(&hash_mutex);
 
@@ -208,9 +208,8 @@ static int serial_link_irq_chain(struct uart_8250_port *up)
 		INIT_LIST_HEAD(&up->list);
 		i->head = &up->list;
 		spin_unlock_irq(&i->lock);
-		irq_flags |= up->port.irqflags;
 		ret = request_irq(up->port.irq, serial8250_interrupt,
-				  irq_flags, up->port.name, i);
+				  up->port.irqflags, up->port.name, i);
 		if (ret < 0)
 			serial_do_unlink(i, up);
 	}
@@ -524,6 +523,7 @@ static void __init serial8250_isa_init_ports(void)
 		 */
 		up->mcr_mask = ~ALPHA_KLUDGE_MCR;
 		up->mcr_force = ALPHA_KLUDGE_MCR;
+		serial8250_set_defaults(up);
 	}
 
 	/* chain base port ops to support Remote Supervisor Adapter */
@@ -547,7 +547,6 @@ static void __init serial8250_isa_init_ports(void)
 		port->membase  = old_serial_port[i].iomem_base;
 		port->iotype   = old_serial_port[i].io_type;
 		port->regshift = old_serial_port[i].iomem_reg_shift;
-		serial8250_set_defaults(up);
 
 		port->irqflags |= irqflag;
 		if (serial8250_isa_config != NULL)
diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c
index 284e8d052fc3..7af6697b760f 100644
--- a/drivers/tty/serial/8250/8250_dw.c
+++ b/drivers/tty/serial/8250/8250_dw.c
@@ -494,10 +494,10 @@ static int dw8250_probe(struct platform_device *pdev)
 {
 	struct uart_8250_port uart = {};
 	struct resource *regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	int irq = platform_get_irq(pdev, 0);
 	struct uart_port *p = &uart.port;
 	struct device *dev = &pdev->dev;
 	struct dw8250_data *data;
+	int irq;
 	int err;
 	u32 val;
 
@@ -506,11 +506,9 @@ static int dw8250_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	if (irq < 0) {
-		if (irq != -EPROBE_DEFER)
-			dev_err(dev, "cannot get irq\n");
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
 		return irq;
-	}
 
 	spin_lock_init(&p->lock);
 	p->mapbase	= regs->start;
diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c
index edd6dfe055bf..4c183889f65e 100644
--- a/drivers/tty/serial/8250/8250_exar.c
+++ b/drivers/tty/serial/8250/8250_exar.c
@@ -24,6 +24,14 @@
 
 #include "8250.h"
 
+#define PCI_DEVICE_ID_ACCES_COM_2S		0x1052
+#define PCI_DEVICE_ID_ACCES_COM_4S		0x105d
+#define PCI_DEVICE_ID_ACCES_COM_8S		0x106c
+#define PCI_DEVICE_ID_ACCES_COM232_8		0x10a8
+#define PCI_DEVICE_ID_ACCES_COM_2SM		0x10d2
+#define PCI_DEVICE_ID_ACCES_COM_4SM		0x10db
+#define PCI_DEVICE_ID_ACCES_COM_8SM		0x10ea
+
 #define PCI_DEVICE_ID_COMMTECH_4224PCI335	0x0002
 #define PCI_DEVICE_ID_COMMTECH_4222PCI335	0x0004
 #define PCI_DEVICE_ID_COMMTECH_2324PCI335	0x000a
@@ -219,7 +227,17 @@ static void setup_gpio(struct pci_dev *pcidev, u8 __iomem *p)
 	 * devices will export them as GPIOs, so we pre-configure them safely
 	 * as inputs.
 	 */
-	u8 dir = pcidev->vendor == PCI_VENDOR_ID_EXAR ? 0xff : 0x00;
+
+	u8 dir = 0x00;
+
+	if  ((pcidev->vendor == PCI_VENDOR_ID_EXAR) &&
+		(pcidev->subsystem_vendor != PCI_VENDOR_ID_SEALEVEL)) {
+		// Configure GPIO as inputs for Commtech adapters
+		dir = 0xff;
+	} else {
+		// Configure GPIO as outputs for SeaLevel adapters
+		dir = 0x00;
+	}
 
 	writeb(0x00, p + UART_EXAR_MPIOINT_7_0);
 	writeb(0x00, p + UART_EXAR_MPIOLVL_7_0);
@@ -574,6 +592,22 @@ static int __maybe_unused exar_resume(struct device *dev)
 
 static SIMPLE_DEV_PM_OPS(exar_pci_pm, exar_suspend, exar_resume);
 
+static const struct exar8250_board acces_com_2x = {
+	.num_ports	= 2,
+	.setup		= pci_xr17c154_setup,
+};
+
+static const struct exar8250_board acces_com_4x = {
+	.num_ports	= 4,
+	.setup		= pci_xr17c154_setup,
+};
+
+static const struct exar8250_board acces_com_8x = {
+	.num_ports	= 8,
+	.setup		= pci_xr17c154_setup,
+};
+
+
 static const struct exar8250_board pbn_fastcom335_2 = {
 	.num_ports	= 2,
 	.setup		= pci_fastcom335_setup,
@@ -642,6 +676,15 @@ static const struct exar8250_board pbn_exar_XR17V8358 = {
 	}
 
 static const struct pci_device_id exar_pci_tbl[] = {
+	EXAR_DEVICE(ACCESSIO, ACCES_COM_2S, acces_com_2x),
+	EXAR_DEVICE(ACCESSIO, ACCES_COM_4S, acces_com_4x),
+	EXAR_DEVICE(ACCESSIO, ACCES_COM_8S, acces_com_8x),
+	EXAR_DEVICE(ACCESSIO, ACCES_COM232_8, acces_com_8x),
+	EXAR_DEVICE(ACCESSIO, ACCES_COM_2SM, acces_com_2x),
+	EXAR_DEVICE(ACCESSIO, ACCES_COM_4SM, acces_com_4x),
+	EXAR_DEVICE(ACCESSIO, ACCES_COM_8SM, acces_com_8x),
+
+
 	CONNECT_DEVICE(XR17C152, UART_2_232, pbn_connect),
 	CONNECT_DEVICE(XR17C154, UART_4_232, pbn_connect),
 	CONNECT_DEVICE(XR17C158, UART_8_232, pbn_connect),
diff --git a/drivers/tty/serial/8250/8250_mtk.c b/drivers/tty/serial/8250/8250_mtk.c
index 417c7c810df9..211c483db9a7 100644
--- a/drivers/tty/serial/8250/8250_mtk.c
+++ b/drivers/tty/serial/8250/8250_mtk.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/serial_8250.h>
@@ -70,6 +71,7 @@ struct mtk8250_data {
 #ifdef CONFIG_SERIAL_8250_DMA
 	enum dma_rx_status	rx_status;
 #endif
+	int			rx_wakeup_irq;
 };
 
 /* flow control mode */
@@ -312,8 +314,21 @@ mtk8250_set_termios(struct uart_port *port, struct ktermios *termios,
 	}
 #endif
 
+	/*
+	 * Store the requested baud rate before calling the generic 8250
+	 * set_termios method. Standard 8250 port expects bauds to be
+	 * no higher than (uartclk / 16) so the baud will be clamped if it
+	 * gets out of that bound. Mediatek 8250 port supports speed
+	 * higher than that, therefore we'll get original baud rate back
+	 * after calling the generic set_termios method and recalculate
+	 * the speed later in this method.
+	 */
+	baud = tty_termios_baud_rate(termios);
+
 	serial8250_do_set_termios(port, termios, old);
 
+	tty_termios_encode_baud_rate(termios, baud, baud);
+
 	/*
 	 * Mediatek UARTs use an extra highspeed register (MTK_UART_HIGHS)
 	 *
@@ -345,6 +360,11 @@ mtk8250_set_termios(struct uart_port *port, struct ktermios *termios,
 	 */
 	spin_lock_irqsave(&port->lock, flags);
 
+	/*
+	 * Update the per-port timeout.
+	 */
+	uart_update_timeout(port, termios->c_cflag, baud);
+
 	/* set DLAB we have cval saved in up->lcr from the call to the core */
 	serial_port_out(port, UART_LCR, up->lcr | UART_LCR_DLAB);
 	serial_dl_write(up, quot);
@@ -551,6 +571,8 @@ static int mtk8250_probe(struct platform_device *pdev)
 	pm_runtime_set_active(&pdev->dev);
 	pm_runtime_enable(&pdev->dev);
 
+	data->rx_wakeup_irq = platform_get_irq_optional(pdev, 1);
+
 	return 0;
 }
 
@@ -572,15 +594,35 @@ static int mtk8250_remove(struct platform_device *pdev)
 static int __maybe_unused mtk8250_suspend(struct device *dev)
 {
 	struct mtk8250_data *data = dev_get_drvdata(dev);
+	int irq = data->rx_wakeup_irq;
+	int err;
 
 	serial8250_suspend_port(data->line);
 
+	pinctrl_pm_select_sleep_state(dev);
+	if (irq >= 0) {
+		err = enable_irq_wake(irq);
+		if (err) {
+			dev_err(dev,
+				"failed to enable irq wake on IRQ %d: %d\n",
+				irq, err);
+			pinctrl_pm_select_default_state(dev);
+			serial8250_resume_port(data->line);
+			return err;
+		}
+	}
+
 	return 0;
 }
 
 static int __maybe_unused mtk8250_resume(struct device *dev)
 {
 	struct mtk8250_data *data = dev_get_drvdata(dev);
+	int irq = data->rx_wakeup_irq;
+
+	if (irq >= 0)
+		disable_irq_wake(irq);
+	pinctrl_pm_select_default_state(dev);
 
 	serial8250_resume_port(data->line);
 
diff --git a/drivers/tty/serial/8250/8250_of.c b/drivers/tty/serial/8250/8250_of.c
index 0277479c87e9..c15c0cf059e2 100644
--- a/drivers/tty/serial/8250/8250_of.c
+++ b/drivers/tty/serial/8250/8250_of.c
@@ -171,7 +171,6 @@ static int of_platform_serial_setup(struct platform_device *ofdev,
 
 	port->type = type;
 	port->uartclk = clk;
-	port->irqflags |= IRQF_SHARED;
 
 	if (of_property_read_bool(np, "no-loopback-test"))
 		port->flags |= UPF_SKIP_TEST;
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index df41397de478..bf6118a2f82f 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -1690,12 +1690,6 @@ pci_wch_ch38x_setup(struct serial_private *priv,
 #define PCIE_DEVICE_ID_WCH_CH384_4S	0x3470
 #define PCIE_DEVICE_ID_WCH_CH382_2S	0x3253
 
-#define PCI_VENDOR_ID_PERICOM			0x12D8
-#define PCI_DEVICE_ID_PERICOM_PI7C9X7951	0x7951
-#define PCI_DEVICE_ID_PERICOM_PI7C9X7952	0x7952
-#define PCI_DEVICE_ID_PERICOM_PI7C9X7954	0x7954
-#define PCI_DEVICE_ID_PERICOM_PI7C9X7958	0x7958
-
 #define PCI_VENDOR_ID_ACCESIO			0x494f
 #define PCI_DEVICE_ID_ACCESIO_PCIE_COM_2SDB	0x1051
 #define PCI_DEVICE_ID_ACCESIO_MPCIE_COM_2S	0x1053
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index eb2e2d141c01..5fdeec6089bb 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -2253,6 +2253,10 @@ int serial8250_do_startup(struct uart_port *port)
 		}
 	}
 
+	/* Check if we need to have shared IRQs */
+	if (port->irq && (up->port.flags & UPF_SHARE_IRQ))
+		up->port.irqflags |= IRQF_SHARED;
+
 	if (port->irq && !(up->port.flags & UPF_NO_THRE_TEST)) {
 		unsigned char iir1;
 		/*
@@ -2624,6 +2628,8 @@ static unsigned int serial8250_get_baud_rate(struct uart_port *port,
 					     struct ktermios *termios,
 					     struct ktermios *old)
 {
+	unsigned int tolerance = port->uartclk / 100;
+
 	/*
 	 * Ask the core to calculate the divisor for us.
 	 * Allow 1% tolerance at the upper limit so uart clks marginally
@@ -2632,7 +2638,7 @@ static unsigned int serial8250_get_baud_rate(struct uart_port *port,
 	 */
 	return uart_get_baud_rate(port, termios, old,
 				  port->uartclk / 16 / UART_DIV_MAX,
-				  port->uartclk);
+				  (port->uartclk + tolerance) / 16);
 }
 
 void
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index af21122dfade..1d501154e9f7 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -2585,6 +2585,7 @@ static int pl011_setup_port(struct device *dev, struct uart_amba_port *uap,
 	uap->port.fifosize = uap->fifosize;
 	uap->port.flags = UPF_BOOT_AUTOCONF;
 	uap->port.line = index;
+	spin_lock_init(&uap->port.lock);
 
 	amba_ports[index] = uap;
 
diff --git a/drivers/tty/serial/ar933x_uart.c b/drivers/tty/serial/ar933x_uart.c
index 3bdd56a1021b..ea12f10610b6 100644
--- a/drivers/tty/serial/ar933x_uart.c
+++ b/drivers/tty/serial/ar933x_uart.c
@@ -286,6 +286,10 @@ static void ar933x_uart_set_termios(struct uart_port *port,
 	ar933x_uart_rmw_set(up, AR933X_UART_CS_REG,
 			    AR933X_UART_CS_HOST_INT_EN);
 
+	/* enable RX and TX ready overide */
+	ar933x_uart_rmw_set(up, AR933X_UART_CS_REG,
+		AR933X_UART_CS_TX_READY_ORIDE | AR933X_UART_CS_RX_READY_ORIDE);
+
 	/* reenable the UART */
 	ar933x_uart_rmw(up, AR933X_UART_CS_REG,
 			AR933X_UART_CS_IF_MODE_M << AR933X_UART_CS_IF_MODE_S,
@@ -418,6 +422,10 @@ static int ar933x_uart_startup(struct uart_port *port)
 	ar933x_uart_rmw_set(up, AR933X_UART_CS_REG,
 			    AR933X_UART_CS_HOST_INT_EN);
 
+	/* enable RX and TX ready overide */
+	ar933x_uart_rmw_set(up, AR933X_UART_CS_REG,
+		AR933X_UART_CS_TX_READY_ORIDE | AR933X_UART_CS_RX_READY_ORIDE);
+
 	/* Enable RX interrupts */
 	up->ier = AR933X_UART_INT_RX_VALID;
 	ar933x_uart_write(up, AR933X_UART_INT_EN_REG, up->ier);
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index d21754a1afde..dec24d85a2e3 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -618,7 +618,8 @@ static void atmel_stop_tx(struct uart_port *port)
 	atmel_uart_writel(port, ATMEL_US_IDR, atmel_port->tx_done_mask);
 
 	if (atmel_uart_is_half_duplex(port))
-		atmel_start_rx(port);
+		if (!atomic_read(&atmel_port->tasklet_shutdown))
+			atmel_start_rx(port);
 
 }
 
diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c
index 10db3e54ac9e..3a7ad301ee8c 100644
--- a/drivers/tty/serial/imx.c
+++ b/drivers/tty/serial/imx.c
@@ -609,7 +609,7 @@ static void imx_uart_dma_tx(struct imx_port *sport)
 
 	sport->tx_bytes = uart_circ_chars_pending(xmit);
 
-	if (xmit->tail < xmit->head) {
+	if (xmit->tail < xmit->head || xmit->head == 0) {
 		sport->dma_tx_nents = 1;
 		sg_init_one(sgl, xmit->buf + xmit->tail, sport->tx_bytes);
 	} else {
@@ -625,7 +625,7 @@ static void imx_uart_dma_tx(struct imx_port *sport)
 		dev_err(dev, "DMA mapping error for TX.\n");
 		return;
 	}
-	desc = dmaengine_prep_slave_sg(chan, sgl, sport->dma_tx_nents,
+	desc = dmaengine_prep_slave_sg(chan, sgl, ret,
 					DMA_MEM_TO_DEV, DMA_PREP_INTERRUPT);
 	if (!desc) {
 		dma_unmap_sg(dev, sgl, sport->dma_tx_nents,
@@ -706,22 +706,33 @@ static void imx_uart_start_tx(struct uart_port *port)
 	}
 }
 
-static irqreturn_t imx_uart_rtsint(int irq, void *dev_id)
+static irqreturn_t __imx_uart_rtsint(int irq, void *dev_id)
 {
 	struct imx_port *sport = dev_id;
 	u32 usr1;
 
-	spin_lock(&sport->port.lock);
-
 	imx_uart_writel(sport, USR1_RTSD, USR1);
 	usr1 = imx_uart_readl(sport, USR1) & USR1_RTSS;
 	uart_handle_cts_change(&sport->port, !!usr1);
 	wake_up_interruptible(&sport->port.state->port.delta_msr_wait);
 
-	spin_unlock(&sport->port.lock);
 	return IRQ_HANDLED;
 }
 
+static irqreturn_t imx_uart_rtsint(int irq, void *dev_id)
+{
+	struct imx_port *sport = dev_id;
+	irqreturn_t ret;
+
+	spin_lock(&sport->port.lock);
+
+	ret = __imx_uart_rtsint(irq, dev_id);
+
+	spin_unlock(&sport->port.lock);
+
+	return ret;
+}
+
 static irqreturn_t imx_uart_txint(int irq, void *dev_id)
 {
 	struct imx_port *sport = dev_id;
@@ -732,14 +743,12 @@ static irqreturn_t imx_uart_txint(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t imx_uart_rxint(int irq, void *dev_id)
+static irqreturn_t __imx_uart_rxint(int irq, void *dev_id)
 {
 	struct imx_port *sport = dev_id;
 	unsigned int rx, flg, ignored = 0;
 	struct tty_port *port = &sport->port.state->port;
 
-	spin_lock(&sport->port.lock);
-
 	while (imx_uart_readl(sport, USR2) & USR2_RDR) {
 		u32 usr2;
 
@@ -798,11 +807,25 @@ static irqreturn_t imx_uart_rxint(int irq, void *dev_id)
 	}
 
 out:
-	spin_unlock(&sport->port.lock);
 	tty_flip_buffer_push(port);
+
 	return IRQ_HANDLED;
 }
 
+static irqreturn_t imx_uart_rxint(int irq, void *dev_id)
+{
+	struct imx_port *sport = dev_id;
+	irqreturn_t ret;
+
+	spin_lock(&sport->port.lock);
+
+	ret = __imx_uart_rxint(irq, dev_id);
+
+	spin_unlock(&sport->port.lock);
+
+	return ret;
+}
+
 static void imx_uart_clear_rx_errors(struct imx_port *sport);
 
 /*
@@ -861,6 +884,8 @@ static irqreturn_t imx_uart_int(int irq, void *dev_id)
 	unsigned int usr1, usr2, ucr1, ucr2, ucr3, ucr4;
 	irqreturn_t ret = IRQ_NONE;
 
+	spin_lock(&sport->port.lock);
+
 	usr1 = imx_uart_readl(sport, USR1);
 	usr2 = imx_uart_readl(sport, USR2);
 	ucr1 = imx_uart_readl(sport, UCR1);
@@ -894,27 +919,25 @@ static irqreturn_t imx_uart_int(int irq, void *dev_id)
 		usr2 &= ~USR2_ORE;
 
 	if (usr1 & (USR1_RRDY | USR1_AGTIM)) {
-		imx_uart_rxint(irq, dev_id);
+		__imx_uart_rxint(irq, dev_id);
 		ret = IRQ_HANDLED;
 	}
 
 	if ((usr1 & USR1_TRDY) || (usr2 & USR2_TXDC)) {
-		imx_uart_txint(irq, dev_id);
+		imx_uart_transmit_buffer(sport);
 		ret = IRQ_HANDLED;
 	}
 
 	if (usr1 & USR1_DTRD) {
 		imx_uart_writel(sport, USR1_DTRD, USR1);
 
-		spin_lock(&sport->port.lock);
 		imx_uart_mctrl_check(sport);
-		spin_unlock(&sport->port.lock);
 
 		ret = IRQ_HANDLED;
 	}
 
 	if (usr1 & USR1_RTSD) {
-		imx_uart_rtsint(irq, dev_id);
+		__imx_uart_rtsint(irq, dev_id);
 		ret = IRQ_HANDLED;
 	}
 
@@ -929,6 +952,8 @@ static irqreturn_t imx_uart_int(int irq, void *dev_id)
 		ret = IRQ_HANDLED;
 	}
 
+	spin_unlock(&sport->port.lock);
+
 	return ret;
 }
 
@@ -2221,8 +2246,8 @@ static int imx_uart_probe(struct platform_device *pdev)
 		return PTR_ERR(base);
 
 	rxirq = platform_get_irq(pdev, 0);
-	txirq = platform_get_irq(pdev, 1);
-	rtsirq = platform_get_irq(pdev, 2);
+	txirq = platform_get_irq_optional(pdev, 1);
+	rtsirq = platform_get_irq_optional(pdev, 2);
 
 	sport->port.dev = &pdev->dev;
 	sport->port.mapbase = res->start;
diff --git a/drivers/tty/serial/kgdboc.c b/drivers/tty/serial/kgdboc.c
index bfe5e9e034ec..53e7e43cc596 100644
--- a/drivers/tty/serial/kgdboc.c
+++ b/drivers/tty/serial/kgdboc.c
@@ -20,6 +20,7 @@
 #include <linux/vt_kern.h>
 #include <linux/input.h>
 #include <linux/module.h>
+#include <linux/platform_device.h>
 
 #define MAX_CONFIG_LEN		40
 
@@ -27,6 +28,7 @@ static struct kgdb_io		kgdboc_io_ops;
 
 /* -1 = init not run yet, 0 = unconfigured, 1 = configured. */
 static int configured		= -1;
+static DEFINE_MUTEX(config_mutex);
 
 static char config[MAX_CONFIG_LEN];
 static struct kparam_string kps = {
@@ -38,6 +40,8 @@ static int kgdboc_use_kms;  /* 1 if we use kernel mode switching */
 static struct tty_driver	*kgdb_tty_driver;
 static int			kgdb_tty_line;
 
+static struct platform_device *kgdboc_pdev;
+
 #ifdef CONFIG_KDB_KEYBOARD
 static int kgdboc_reset_connect(struct input_handler *handler,
 				struct input_dev *dev,
@@ -133,11 +137,13 @@ static void kgdboc_unregister_kbd(void)
 
 static void cleanup_kgdboc(void)
 {
+	if (configured != 1)
+		return;
+
 	if (kgdb_unregister_nmi_console())
 		return;
 	kgdboc_unregister_kbd();
-	if (configured == 1)
-		kgdb_unregister_io_module(&kgdboc_io_ops);
+	kgdb_unregister_io_module(&kgdboc_io_ops);
 }
 
 static int configure_kgdboc(void)
@@ -200,20 +206,79 @@ nmi_con_failed:
 	kgdb_unregister_io_module(&kgdboc_io_ops);
 noconfig:
 	kgdboc_unregister_kbd();
-	config[0] = 0;
 	configured = 0;
-	cleanup_kgdboc();
 
 	return err;
 }
 
+static int kgdboc_probe(struct platform_device *pdev)
+{
+	int ret = 0;
+
+	mutex_lock(&config_mutex);
+	if (configured != 1) {
+		ret = configure_kgdboc();
+
+		/* Convert "no device" to "defer" so we'll keep trying */
+		if (ret == -ENODEV)
+			ret = -EPROBE_DEFER;
+	}
+	mutex_unlock(&config_mutex);
+
+	return ret;
+}
+
+static struct platform_driver kgdboc_platform_driver = {
+	.probe = kgdboc_probe,
+	.driver = {
+		.name = "kgdboc",
+		.suppress_bind_attrs = true,
+	},
+};
+
 static int __init init_kgdboc(void)
 {
-	/* Already configured? */
-	if (configured == 1)
+	int ret;
+
+	/*
+	 * kgdboc is a little bit of an odd "platform_driver".  It can be
+	 * up and running long before the platform_driver object is
+	 * created and thus doesn't actually store anything in it.  There's
+	 * only one instance of kgdb so anything is stored as global state.
+	 * The platform_driver is only created so that we can leverage the
+	 * kernel's mechanisms (like -EPROBE_DEFER) to call us when our
+	 * underlying tty is ready.  Here we init our platform driver and
+	 * then create the single kgdboc instance.
+	 */
+	ret = platform_driver_register(&kgdboc_platform_driver);
+	if (ret)
+		return ret;
+
+	kgdboc_pdev = platform_device_alloc("kgdboc", PLATFORM_DEVID_NONE);
+	if (!kgdboc_pdev) {
+		ret = -ENOMEM;
+		goto err_did_register;
+	}
+
+	ret = platform_device_add(kgdboc_pdev);
+	if (!ret)
 		return 0;
 
-	return configure_kgdboc();
+	platform_device_put(kgdboc_pdev);
+
+err_did_register:
+	platform_driver_unregister(&kgdboc_platform_driver);
+	return ret;
+}
+
+static void exit_kgdboc(void)
+{
+	mutex_lock(&config_mutex);
+	cleanup_kgdboc();
+	mutex_unlock(&config_mutex);
+
+	platform_device_unregister(kgdboc_pdev);
+	platform_driver_unregister(&kgdboc_platform_driver);
 }
 
 static int kgdboc_get_char(void)
@@ -236,24 +301,20 @@ static int param_set_kgdboc_var(const char *kmessage,
 				const struct kernel_param *kp)
 {
 	size_t len = strlen(kmessage);
+	int ret = 0;
 
 	if (len >= MAX_CONFIG_LEN) {
 		pr_err("config string too long\n");
 		return -ENOSPC;
 	}
 
-	/* Only copy in the string if the init function has not run yet */
-	if (configured < 0) {
-		strcpy(config, kmessage);
-		return 0;
-	}
-
 	if (kgdb_connected) {
 		pr_err("Cannot reconfigure while KGDB is connected.\n");
-
 		return -EBUSY;
 	}
 
+	mutex_lock(&config_mutex);
+
 	strcpy(config, kmessage);
 	/* Chop out \n char as a result of echo */
 	if (len && config[len - 1] == '\n')
@@ -262,8 +323,30 @@ static int param_set_kgdboc_var(const char *kmessage,
 	if (configured == 1)
 		cleanup_kgdboc();
 
-	/* Go and configure with the new params. */
-	return configure_kgdboc();
+	/*
+	 * Configure with the new params as long as init already ran.
+	 * Note that we can get called before init if someone loads us
+	 * with "modprobe kgdboc kgdboc=..." or if they happen to use the
+	 * the odd syntax of "kgdboc.kgdboc=..." on the kernel command.
+	 */
+	if (configured >= 0)
+		ret = configure_kgdboc();
+
+	/*
+	 * If we couldn't configure then clear out the config.  Note that
+	 * specifying an invalid config on the kernel command line vs.
+	 * through sysfs have slightly different behaviors.  If we fail
+	 * to configure what was specified on the kernel command line
+	 * we'll leave it in the 'config' and return -EPROBE_DEFER from
+	 * our probe.  When specified through sysfs userspace is
+	 * responsible for loading the tty driver before setting up.
+	 */
+	if (ret)
+		config[0] = '\0';
+
+	mutex_unlock(&config_mutex);
+
+	return ret;
 }
 
 static int dbg_restore_graphics;
@@ -322,15 +405,8 @@ __setup("kgdboc=", kgdboc_option_setup);
 /* This is only available if kgdboc is a built in for early debugging */
 static int __init kgdboc_early_init(char *opt)
 {
-	/* save the first character of the config string because the
-	 * init routine can destroy it.
-	 */
-	char save_ch;
-
 	kgdboc_option_setup(opt);
-	save_ch = config[0];
-	init_kgdboc();
-	config[0] = save_ch;
+	configure_kgdboc();
 	return 0;
 }
 
@@ -338,7 +414,7 @@ early_param("ekgdboc", kgdboc_early_init);
 #endif /* CONFIG_KGDB_SERIAL_CONSOLE */
 
 module_init(init_kgdboc);
-module_exit(cleanup_kgdboc);
+module_exit(exit_kgdboc);
 module_param_call(kgdboc, param_set_kgdboc_var, param_get_string, &kps, 0644);
 MODULE_PARM_DESC(kgdboc, "<serial_device>[,baud]");
 MODULE_DESCRIPTION("KGDB Console TTY Driver");
diff --git a/drivers/tty/serial/msm_serial.c b/drivers/tty/serial/msm_serial.c
index 00964b6e4ac1..e0718ee5d42a 100644
--- a/drivers/tty/serial/msm_serial.c
+++ b/drivers/tty/serial/msm_serial.c
@@ -1580,6 +1580,7 @@ static void __msm_console_write(struct uart_port *port, const char *s,
 	int num_newlines = 0;
 	bool replaced = false;
 	void __iomem *tf;
+	int locked = 1;
 
 	if (is_uartdm)
 		tf = port->membase + UARTDM_TF;
@@ -1592,7 +1593,13 @@ static void __msm_console_write(struct uart_port *port, const char *s,
 			num_newlines++;
 	count += num_newlines;
 
-	spin_lock(&port->lock);
+	if (port->sysrq)
+		locked = 0;
+	else if (oops_in_progress)
+		locked = spin_trylock(&port->lock);
+	else
+		spin_lock(&port->lock);
+
 	if (is_uartdm)
 		msm_reset_dm_count(port, count);
 
@@ -1628,7 +1635,9 @@ static void __msm_console_write(struct uart_port *port, const char *s,
 		iowrite32_rep(tf, buf, 1);
 		i += num_chars;
 	}
-	spin_unlock(&port->lock);
+
+	if (locked)
+		spin_unlock(&port->lock);
 }
 
 static void msm_console_write(struct console *co, const char *s,
diff --git a/drivers/tty/serial/mvebu-uart.c b/drivers/tty/serial/mvebu-uart.c
index 7e7b1559fa36..c310e2e7c647 100644
--- a/drivers/tty/serial/mvebu-uart.c
+++ b/drivers/tty/serial/mvebu-uart.c
@@ -851,7 +851,7 @@ static int mvebu_uart_probe(struct platform_device *pdev)
 
 	port->membase = devm_ioremap_resource(&pdev->dev, reg);
 	if (IS_ERR(port->membase))
-		return -PTR_ERR(port->membase);
+		return PTR_ERR(port->membase);
 
 	mvuart = devm_kzalloc(&pdev->dev, sizeof(struct mvebu_uart),
 			      GFP_KERNEL);
diff --git a/drivers/tty/serial/mxs-auart.c b/drivers/tty/serial/mxs-auart.c
index 4c188f4079b3..63810eefa44b 100644
--- a/drivers/tty/serial/mxs-auart.c
+++ b/drivers/tty/serial/mxs-auart.c
@@ -1703,21 +1703,21 @@ static int mxs_auart_probe(struct platform_device *pdev)
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
 		ret = irq;
-		goto out_disable_clks;
+		goto out_iounmap;
 	}
 
 	s->port.irq = irq;
 	ret = devm_request_irq(&pdev->dev, irq, mxs_auart_irq_handle, 0,
 			       dev_name(&pdev->dev), s);
 	if (ret)
-		goto out_disable_clks;
+		goto out_iounmap;
 
 	platform_set_drvdata(pdev, s);
 
 	ret = mxs_auart_init_gpios(s, &pdev->dev);
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to initialize GPIOs.\n");
-		goto out_disable_clks;
+		goto out_iounmap;
 	}
 
 	/*
@@ -1725,7 +1725,7 @@ static int mxs_auart_probe(struct platform_device *pdev)
 	 */
 	ret = mxs_auart_request_gpio_irq(s);
 	if (ret)
-		goto out_disable_clks;
+		goto out_iounmap;
 
 	auart_port[s->port.line] = s;
 
@@ -1751,6 +1751,9 @@ out_free_qpio_irq:
 	mxs_auart_free_gpio_irq(s);
 	auart_port[pdev->id] = NULL;
 
+out_iounmap:
+	iounmap(s->port.membase);
+
 out_disable_clks:
 	if (is_asm9260_auart(s)) {
 		clk_disable_unprepare(s->clk);
@@ -1766,6 +1769,7 @@ static int mxs_auart_remove(struct platform_device *pdev)
 	uart_remove_one_port(&auart_driver, &s->port);
 	auart_port[pdev->id] = NULL;
 	mxs_auart_free_gpio_irq(s);
+	iounmap(s->port.membase);
 	if (is_asm9260_auart(s)) {
 		clk_disable_unprepare(s->clk);
 		clk_disable_unprepare(s->clk_ahb);
diff --git a/drivers/tty/serial/owl-uart.c b/drivers/tty/serial/owl-uart.c
index 73fcc6bdb031..6a0a1cdfe0a0 100644
--- a/drivers/tty/serial/owl-uart.c
+++ b/drivers/tty/serial/owl-uart.c
@@ -682,6 +682,12 @@ static int owl_uart_probe(struct platform_device *pdev)
 		return PTR_ERR(owl_port->clk);
 	}
 
+	ret = clk_prepare_enable(owl_port->clk);
+	if (ret) {
+		dev_err(&pdev->dev, "could not enable clk\n");
+		return ret;
+	}
+
 	owl_port->port.dev = &pdev->dev;
 	owl_port->port.line = pdev->id;
 	owl_port->port.type = PORT_OWL;
@@ -714,6 +720,7 @@ static int owl_uart_remove(struct platform_device *pdev)
 
 	uart_remove_one_port(&owl_uart_driver, &owl_port->port);
 	owl_uart_ports[pdev->id] = NULL;
+	clk_disable_unprepare(owl_port->clk);
 
 	return 0;
 }
diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c
index 6157213a8359..c16234bca78f 100644
--- a/drivers/tty/serial/pch_uart.c
+++ b/drivers/tty/serial/pch_uart.c
@@ -233,6 +233,7 @@ struct eg20t_port {
 	struct dma_chan			*chan_rx;
 	struct scatterlist		*sg_tx_p;
 	int				nent;
+	int				orig_nent;
 	struct scatterlist		sg_rx;
 	int				tx_dma_use;
 	void				*rx_buf_virt;
@@ -787,9 +788,10 @@ static void pch_dma_tx_complete(void *arg)
 	}
 	xmit->tail &= UART_XMIT_SIZE - 1;
 	async_tx_ack(priv->desc_tx);
-	dma_unmap_sg(port->dev, sg, priv->nent, DMA_TO_DEVICE);
+	dma_unmap_sg(port->dev, sg, priv->orig_nent, DMA_TO_DEVICE);
 	priv->tx_dma_use = 0;
 	priv->nent = 0;
+	priv->orig_nent = 0;
 	kfree(priv->sg_tx_p);
 	pch_uart_hal_enable_interrupt(priv, PCH_UART_HAL_TX_INT);
 }
@@ -1010,6 +1012,7 @@ static unsigned int dma_handle_tx(struct eg20t_port *priv)
 		dev_err(priv->port.dev, "%s:dma_map_sg Failed\n", __func__);
 		return 0;
 	}
+	priv->orig_nent = num;
 	priv->nent = nent;
 
 	for (i = 0; i < nent; i++, sg++) {
diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c
index 35e5f9c5d5be..6b34833bb3d0 100644
--- a/drivers/tty/serial/qcom_geni_serial.c
+++ b/drivers/tty/serial/qcom_geni_serial.c
@@ -125,6 +125,7 @@ static int handle_rx_console(struct uart_port *uport, u32 bytes, bool drop);
 static int handle_rx_uart(struct uart_port *uport, u32 bytes, bool drop);
 static unsigned int qcom_geni_serial_tx_empty(struct uart_port *port);
 static void qcom_geni_serial_stop_rx(struct uart_port *uport);
+static void qcom_geni_serial_handle_rx(struct uart_port *uport, bool drop);
 
 static const unsigned long root_freq[] = {7372800, 14745600, 19200000, 29491200,
 					32000000, 48000000, 64000000, 80000000,
@@ -617,7 +618,7 @@ static void qcom_geni_serial_stop_rx(struct uart_port *uport)
 	u32 irq_en;
 	u32 status;
 	struct qcom_geni_serial_port *port = to_dev_port(uport, uport);
-	u32 irq_clear = S_CMD_DONE_EN;
+	u32 s_irq_status;
 
 	irq_en = readl(uport->membase + SE_GENI_S_IRQ_EN);
 	irq_en &= ~(S_RX_FIFO_WATERMARK_EN | S_RX_FIFO_LAST_EN);
@@ -633,10 +634,19 @@ static void qcom_geni_serial_stop_rx(struct uart_port *uport)
 		return;
 
 	geni_se_cancel_s_cmd(&port->se);
-	qcom_geni_serial_poll_bit(uport, SE_GENI_S_CMD_CTRL_REG,
-					S_GENI_CMD_CANCEL, false);
+	qcom_geni_serial_poll_bit(uport, SE_GENI_S_IRQ_STATUS,
+					S_CMD_CANCEL_EN, true);
+	/*
+	 * If timeout occurs secondary engine remains active
+	 * and Abort sequence is executed.
+	 */
+	s_irq_status = readl(uport->membase + SE_GENI_S_IRQ_STATUS);
+	/* Flush the Rx buffer */
+	if (s_irq_status & S_RX_FIFO_LAST_EN)
+		qcom_geni_serial_handle_rx(uport, true);
+	writel(s_irq_status, uport->membase + SE_GENI_S_IRQ_CLEAR);
+
 	status = readl(uport->membase + SE_GENI_STATUS);
-	writel(irq_clear, uport->membase + SE_GENI_S_IRQ_CLEAR);
 	if (status & S_GENI_CMD_ACTIVE)
 		qcom_geni_serial_abort_rx(uport);
 }
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index efaf6f9ca17f..d6aa0aafc6c4 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -2827,6 +2827,7 @@ int uart_add_one_port(struct uart_driver *drv, struct uart_port *uport)
 	if (uport->cons && uport->dev)
 		of_console_check(uport->dev->of_node, uport->cons->name, uport->line);
 
+	tty_port_link_device(port, drv->tty_driver, uport->line);
 	uart_configure_port(drv, state, uport);
 
 	port->console = uart_console(uport);
diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c
index d18c680aa64b..ab92562d4ea8 100644
--- a/drivers/tty/serial/sh-sci.c
+++ b/drivers/tty/serial/sh-sci.c
@@ -873,9 +873,16 @@ static void sci_receive_chars(struct uart_port *port)
 				tty_insert_flip_char(tport, c, TTY_NORMAL);
 		} else {
 			for (i = 0; i < count; i++) {
-				char c = serial_port_in(port, SCxRDR);
-
-				status = serial_port_in(port, SCxSR);
+				char c;
+
+				if (port->type == PORT_SCIF ||
+				    port->type == PORT_HSCIF) {
+					status = serial_port_in(port, SCxSR);
+					c = serial_port_in(port, SCxRDR);
+				} else {
+					c = serial_port_in(port, SCxRDR);
+					status = serial_port_in(port, SCxSR);
+				}
 				if (uart_handle_sysrq_char(port, c)) {
 					count--; i--;
 					continue;
@@ -2896,8 +2903,12 @@ static int sci_init_single(struct platform_device *dev,
 	port->mapbase = res->start;
 	sci_port->reg_size = resource_size(res);
 
-	for (i = 0; i < ARRAY_SIZE(sci_port->irqs); ++i)
-		sci_port->irqs[i] = platform_get_irq(dev, i);
+	for (i = 0; i < ARRAY_SIZE(sci_port->irqs); ++i) {
+		if (i)
+			sci_port->irqs[i] = platform_get_irq_optional(dev, i);
+		else
+			sci_port->irqs[i] = platform_get_irq(dev, i);
+	}
 
 	/* The SCI generates several interrupts. They can be muxed together or
 	 * connected to different interrupt lines. In the muxed case only one
diff --git a/drivers/tty/serial/sifive.c b/drivers/tty/serial/sifive.c
index be4687814353..3d56fb06c96d 100644
--- a/drivers/tty/serial/sifive.c
+++ b/drivers/tty/serial/sifive.c
@@ -840,6 +840,7 @@ console_initcall(sifive_console_init);
 
 static void __ssp_add_console_port(struct sifive_serial_port *ssp)
 {
+	spin_lock_init(&ssp->port.lock);
 	sifive_serial_console_ports[ssp->port.line] = ssp;
 }
 
diff --git a/drivers/tty/serial/sprd_serial.c b/drivers/tty/serial/sprd_serial.c
index 6f267662bd83..538d7c588cf0 100644
--- a/drivers/tty/serial/sprd_serial.c
+++ b/drivers/tty/serial/sprd_serial.c
@@ -1086,14 +1086,13 @@ static int sprd_remove(struct platform_device *dev)
 	if (sup) {
 		uart_remove_one_port(&sprd_uart_driver, &sup->port);
 		sprd_port[sup->port.line] = NULL;
+		sprd_rx_free_buf(sup);
 		sprd_ports_num--;
 	}
 
 	if (!sprd_ports_num)
 		uart_unregister_driver(&sprd_uart_driver);
 
-	sprd_rx_free_buf(sup);
-
 	return 0;
 }
 
diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c
index efd54a010243..4265f7a696be 100644
--- a/drivers/tty/serial/xilinx_uartps.c
+++ b/drivers/tty/serial/xilinx_uartps.c
@@ -29,12 +29,14 @@
 
 #define CDNS_UART_TTY_NAME	"ttyPS"
 #define CDNS_UART_NAME		"xuartps"
+#define CDNS_UART_MAJOR		0	/* use dynamic node allocation */
+#define CDNS_UART_MINOR		0	/* works best with devtmpfs */
+#define CDNS_UART_NR_PORTS	16
 #define CDNS_UART_FIFO_SIZE	64	/* FIFO size */
 #define CDNS_UART_REGISTER_SPACE	0x1000
 
 /* Rx Trigger level */
 static int rx_trigger_level = 56;
-static int uartps_major;
 module_param(rx_trigger_level, uint, S_IRUGO);
 MODULE_PARM_DESC(rx_trigger_level, "Rx trigger level, 1-63 bytes");
 
@@ -180,7 +182,6 @@ MODULE_PARM_DESC(rx_timeout, "Rx timeout, 1-255");
  * @pclk:		APB clock
  * @cdns_uart_driver:	Pointer to UART driver
  * @baud:		Current baud rate
- * @id:			Port ID
  * @clk_rate_change_nb:	Notifier block for clock changes
  * @quirks:		Flags for RXBS support.
  */
@@ -190,7 +191,6 @@ struct cdns_uart {
 	struct clk		*pclk;
 	struct uart_driver	*cdns_uart_driver;
 	unsigned int		baud;
-	int			id;
 	struct notifier_block	clk_rate_change_nb;
 	u32			quirks;
 	bool cts_override;
@@ -1115,6 +1115,8 @@ static const struct uart_ops cdns_uart_ops = {
 #endif
 };
 
+static struct uart_driver cdns_uart_uart_driver;
+
 #ifdef CONFIG_SERIAL_XILINX_PS_UART_CONSOLE
 /**
  * cdns_uart_console_putchar - write the character to the FIFO buffer
@@ -1254,6 +1256,16 @@ static int cdns_uart_console_setup(struct console *co, char *options)
 
 	return uart_set_options(port, co, baud, parity, bits, flow);
 }
+
+static struct console cdns_uart_console = {
+	.name	= CDNS_UART_TTY_NAME,
+	.write	= cdns_uart_console_write,
+	.device	= uart_console_device,
+	.setup	= cdns_uart_console_setup,
+	.flags	= CON_PRINTBUFFER,
+	.index	= -1, /* Specified on the cmdline (e.g. console=ttyPS ) */
+	.data	= &cdns_uart_uart_driver,
+};
 #endif /* CONFIG_SERIAL_XILINX_PS_UART_CONSOLE */
 
 #ifdef CONFIG_PM_SLEEP
@@ -1385,89 +1397,8 @@ static const struct of_device_id cdns_uart_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, cdns_uart_of_match);
 
-/*
- * Maximum number of instances without alias IDs but if there is alias
- * which target "< MAX_UART_INSTANCES" range this ID can't be used.
- */
-#define MAX_UART_INSTANCES	32
-
-/* Stores static aliases list */
-static DECLARE_BITMAP(alias_bitmap, MAX_UART_INSTANCES);
-static int alias_bitmap_initialized;
-
-/* Stores actual bitmap of allocated IDs with alias IDs together */
-static DECLARE_BITMAP(bitmap, MAX_UART_INSTANCES);
-/* Protect bitmap operations to have unique IDs */
-static DEFINE_MUTEX(bitmap_lock);
-
-static int cdns_get_id(struct platform_device *pdev)
-{
-	int id, ret;
-
-	mutex_lock(&bitmap_lock);
-
-	/* Alias list is stable that's why get alias bitmap only once */
-	if (!alias_bitmap_initialized) {
-		ret = of_alias_get_alias_list(cdns_uart_of_match, "serial",
-					      alias_bitmap, MAX_UART_INSTANCES);
-		if (ret && ret != -EOVERFLOW) {
-			mutex_unlock(&bitmap_lock);
-			return ret;
-		}
-
-		alias_bitmap_initialized++;
-	}
-
-	/* Make sure that alias ID is not taken by instance without alias */
-	bitmap_or(bitmap, bitmap, alias_bitmap, MAX_UART_INSTANCES);
-
-	dev_dbg(&pdev->dev, "Alias bitmap: %*pb\n",
-		MAX_UART_INSTANCES, bitmap);
-
-	/* Look for a serialN alias */
-	id = of_alias_get_id(pdev->dev.of_node, "serial");
-	if (id < 0) {
-		dev_warn(&pdev->dev,
-			 "No serial alias passed. Using the first free id\n");
-
-		/*
-		 * Start with id 0 and check if there is no serial0 alias
-		 * which points to device which is compatible with this driver.
-		 * If alias exists then try next free position.
-		 */
-		id = 0;
-
-		for (;;) {
-			dev_info(&pdev->dev, "Checking id %d\n", id);
-			id = find_next_zero_bit(bitmap, MAX_UART_INSTANCES, id);
-
-			/* No free empty instance */
-			if (id == MAX_UART_INSTANCES) {
-				dev_err(&pdev->dev, "No free ID\n");
-				mutex_unlock(&bitmap_lock);
-				return -EINVAL;
-			}
-
-			dev_dbg(&pdev->dev, "The empty id is %d\n", id);
-			/* Check if ID is empty */
-			if (!test_and_set_bit(id, bitmap)) {
-				/* Break the loop if bit is taken */
-				dev_dbg(&pdev->dev,
-					"Selected ID %d allocation passed\n",
-					id);
-				break;
-			}
-			dev_dbg(&pdev->dev,
-				"Selected ID %d allocation failed\n", id);
-			/* if taking bit fails then try next one */
-			id++;
-		}
-	}
-
-	mutex_unlock(&bitmap_lock);
-
-	return id;
-}
+/* Temporary variable for storing number of instances */
+static int instances;
 
 /**
  * cdns_uart_probe - Platform driver probe
@@ -1477,16 +1408,11 @@ static int cdns_get_id(struct platform_device *pdev)
  */
 static int cdns_uart_probe(struct platform_device *pdev)
 {
-	int rc, irq;
+	int rc, id, irq;
 	struct uart_port *port;
 	struct resource *res;
 	struct cdns_uart *cdns_uart_data;
 	const struct of_device_id *match;
-	struct uart_driver *cdns_uart_uart_driver;
-	char *driver_name;
-#ifdef CONFIG_SERIAL_XILINX_PS_UART_CONSOLE
-	struct console *cdns_uart_console;
-#endif
 
 	cdns_uart_data = devm_kzalloc(&pdev->dev, sizeof(*cdns_uart_data),
 			GFP_KERNEL);
@@ -1496,64 +1422,35 @@ static int cdns_uart_probe(struct platform_device *pdev)
 	if (!port)
 		return -ENOMEM;
 
-	cdns_uart_uart_driver = devm_kzalloc(&pdev->dev,
-					     sizeof(*cdns_uart_uart_driver),
-					     GFP_KERNEL);
-	if (!cdns_uart_uart_driver)
-		return -ENOMEM;
-
-	cdns_uart_data->id = cdns_get_id(pdev);
-	if (cdns_uart_data->id < 0)
-		return cdns_uart_data->id;
+	/* Look for a serialN alias */
+	id = of_alias_get_id(pdev->dev.of_node, "serial");
+	if (id < 0)
+		id = 0;
 
-	/* There is a need to use unique driver name */
-	driver_name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s%d",
-				     CDNS_UART_NAME, cdns_uart_data->id);
-	if (!driver_name) {
-		rc = -ENOMEM;
-		goto err_out_id;
+	if (id >= CDNS_UART_NR_PORTS) {
+		dev_err(&pdev->dev, "Cannot get uart_port structure\n");
+		return -ENODEV;
 	}
 
-	cdns_uart_uart_driver->owner = THIS_MODULE;
-	cdns_uart_uart_driver->driver_name = driver_name;
-	cdns_uart_uart_driver->dev_name	= CDNS_UART_TTY_NAME;
-	cdns_uart_uart_driver->major = uartps_major;
-	cdns_uart_uart_driver->minor = cdns_uart_data->id;
-	cdns_uart_uart_driver->nr = 1;
-
+	if (!cdns_uart_uart_driver.state) {
+		cdns_uart_uart_driver.owner = THIS_MODULE;
+		cdns_uart_uart_driver.driver_name = CDNS_UART_NAME;
+		cdns_uart_uart_driver.dev_name = CDNS_UART_TTY_NAME;
+		cdns_uart_uart_driver.major = CDNS_UART_MAJOR;
+		cdns_uart_uart_driver.minor = CDNS_UART_MINOR;
+		cdns_uart_uart_driver.nr = CDNS_UART_NR_PORTS;
 #ifdef CONFIG_SERIAL_XILINX_PS_UART_CONSOLE
-	cdns_uart_console = devm_kzalloc(&pdev->dev, sizeof(*cdns_uart_console),
-					 GFP_KERNEL);
-	if (!cdns_uart_console) {
-		rc = -ENOMEM;
-		goto err_out_id;
-	}
-
-	strncpy(cdns_uart_console->name, CDNS_UART_TTY_NAME,
-		sizeof(cdns_uart_console->name));
-	cdns_uart_console->index = cdns_uart_data->id;
-	cdns_uart_console->write = cdns_uart_console_write;
-	cdns_uart_console->device = uart_console_device;
-	cdns_uart_console->setup = cdns_uart_console_setup;
-	cdns_uart_console->flags = CON_PRINTBUFFER;
-	cdns_uart_console->data = cdns_uart_uart_driver;
-	cdns_uart_uart_driver->cons = cdns_uart_console;
+		cdns_uart_uart_driver.cons = &cdns_uart_console;
 #endif
 
-	rc = uart_register_driver(cdns_uart_uart_driver);
-	if (rc < 0) {
-		dev_err(&pdev->dev, "Failed to register driver\n");
-		goto err_out_id;
+		rc = uart_register_driver(&cdns_uart_uart_driver);
+		if (rc < 0) {
+			dev_err(&pdev->dev, "Failed to register driver\n");
+			return rc;
+		}
 	}
 
-	cdns_uart_data->cdns_uart_driver = cdns_uart_uart_driver;
-
-	/*
-	 * Setting up proper name_base needs to be done after uart
-	 * registration because tty_driver structure is not filled.
-	 * name_base is 0 by default.
-	 */
-	cdns_uart_uart_driver->tty_driver->name_base = cdns_uart_data->id;
+	cdns_uart_data->cdns_uart_driver = &cdns_uart_uart_driver;
 
 	match = of_match_node(cdns_uart_of_match, pdev->dev.of_node);
 	if (match && match->data) {
@@ -1630,6 +1527,7 @@ static int cdns_uart_probe(struct platform_device *pdev)
 	port->flags	= UPF_BOOT_AUTOCONF;
 	port->ops	= &cdns_uart_ops;
 	port->fifosize	= CDNS_UART_FIFO_SIZE;
+	port->line	= id;
 
 	/*
 	 * Register the port.
@@ -1657,11 +1555,13 @@ static int cdns_uart_probe(struct platform_device *pdev)
 	 * If register_console() don't assign value, then console_port pointer
 	 * is cleanup.
 	 */
-	if (!console_port)
+	if (!console_port) {
+		cdns_uart_console.index = id;
 		console_port = port;
+	}
 #endif
 
-	rc = uart_add_one_port(cdns_uart_uart_driver, port);
+	rc = uart_add_one_port(&cdns_uart_uart_driver, port);
 	if (rc) {
 		dev_err(&pdev->dev,
 			"uart_add_one_port() failed; err=%i\n", rc);
@@ -1671,13 +1571,17 @@ static int cdns_uart_probe(struct platform_device *pdev)
 #ifdef CONFIG_SERIAL_XILINX_PS_UART_CONSOLE
 	/* This is not port which is used for console that's why clean it up */
 	if (console_port == port &&
-	    !(cdns_uart_uart_driver->cons->flags & CON_ENABLED))
+	    !(cdns_uart_uart_driver.cons->flags & CON_ENABLED)) {
 		console_port = NULL;
+		cdns_uart_console.index = -1;
+	}
 #endif
 
-	uartps_major = cdns_uart_uart_driver->tty_driver->major;
 	cdns_uart_data->cts_override = of_property_read_bool(pdev->dev.of_node,
 							     "cts-override");
+
+	instances++;
+
 	return 0;
 
 err_out_pm_disable:
@@ -1693,12 +1597,8 @@ err_out_clk_disable:
 err_out_clk_dis_pclk:
 	clk_disable_unprepare(cdns_uart_data->pclk);
 err_out_unregister_driver:
-	uart_unregister_driver(cdns_uart_data->cdns_uart_driver);
-err_out_id:
-	mutex_lock(&bitmap_lock);
-	if (cdns_uart_data->id < MAX_UART_INSTANCES)
-		clear_bit(cdns_uart_data->id, bitmap);
-	mutex_unlock(&bitmap_lock);
+	if (!instances)
+		uart_unregister_driver(cdns_uart_data->cdns_uart_driver);
 	return rc;
 }
 
@@ -1721,10 +1621,6 @@ static int cdns_uart_remove(struct platform_device *pdev)
 #endif
 	rc = uart_remove_one_port(cdns_uart_data->cdns_uart_driver, port);
 	port->mapbase = 0;
-	mutex_lock(&bitmap_lock);
-	if (cdns_uart_data->id < MAX_UART_INSTANCES)
-		clear_bit(cdns_uart_data->id, bitmap);
-	mutex_unlock(&bitmap_lock);
 	clk_disable_unprepare(cdns_uart_data->uartclk);
 	clk_disable_unprepare(cdns_uart_data->pclk);
 	pm_runtime_disable(&pdev->dev);
@@ -1737,13 +1633,8 @@ static int cdns_uart_remove(struct platform_device *pdev)
 		console_port = NULL;
 #endif
 
-	/* If this is last instance major number should be initialized */
-	mutex_lock(&bitmap_lock);
-	if (bitmap_empty(bitmap, MAX_UART_INSTANCES))
-		uartps_major = 0;
-	mutex_unlock(&bitmap_lock);
-
-	uart_unregister_driver(cdns_uart_data->cdns_uart_driver);
+	if (!--instances)
+		uart_unregister_driver(cdns_uart_data->cdns_uart_driver);
 	return rc;
 }
 
diff --git a/drivers/tty/synclink_gt.c b/drivers/tty/synclink_gt.c
index e8a9047de451..36f1a4d870eb 100644
--- a/drivers/tty/synclink_gt.c
+++ b/drivers/tty/synclink_gt.c
@@ -1334,10 +1334,10 @@ static void throttle(struct tty_struct * tty)
 	DBGINFO(("%s throttle\n", info->device_name));
 	if (I_IXOFF(tty))
 		send_xchar(tty, STOP_CHAR(tty));
- 	if (C_CRTSCTS(tty)) {
+	if (C_CRTSCTS(tty)) {
 		spin_lock_irqsave(&info->lock,flags);
 		info->signals &= ~SerialSignal_RTS;
-	 	set_signals(info);
+		set_signals(info);
 		spin_unlock_irqrestore(&info->lock,flags);
 	}
 }
@@ -1359,10 +1359,10 @@ static void unthrottle(struct tty_struct * tty)
 		else
 			send_xchar(tty, START_CHAR(tty));
 	}
- 	if (C_CRTSCTS(tty)) {
+	if (C_CRTSCTS(tty)) {
 		spin_lock_irqsave(&info->lock,flags);
 		info->signals |= SerialSignal_RTS;
-	 	set_signals(info);
+		set_signals(info);
 		spin_unlock_irqrestore(&info->lock,flags);
 	}
 }
@@ -2560,8 +2560,8 @@ static void change_params(struct slgt_info *info)
 	info->read_status_mask = IRQ_RXOVER;
 	if (I_INPCK(info->port.tty))
 		info->read_status_mask |= MASK_PARITY | MASK_FRAMING;
- 	if (I_BRKINT(info->port.tty) || I_PARMRK(info->port.tty))
- 		info->read_status_mask |= MASK_BREAK;
+	if (I_BRKINT(info->port.tty) || I_PARMRK(info->port.tty))
+		info->read_status_mask |= MASK_BREAK;
 	if (I_IGNPAR(info->port.tty))
 		info->ignore_status_mask |= MASK_PARITY | MASK_FRAMING;
 	if (I_IGNBRK(info->port.tty)) {
@@ -3192,7 +3192,7 @@ static int tiocmset(struct tty_struct *tty,
 		info->signals &= ~SerialSignal_DTR;
 
 	spin_lock_irqsave(&info->lock,flags);
- 	set_signals(info);
+	set_signals(info);
 	spin_unlock_irqrestore(&info->lock,flags);
 	return 0;
 }
@@ -3203,7 +3203,7 @@ static int carrier_raised(struct tty_port *port)
 	struct slgt_info *info = container_of(port, struct slgt_info, port);
 
 	spin_lock_irqsave(&info->lock,flags);
- 	get_signals(info);
+	get_signals(info);
 	spin_unlock_irqrestore(&info->lock,flags);
 	return (info->signals & SerialSignal_DCD) ? 1 : 0;
 }
@@ -3218,7 +3218,7 @@ static void dtr_rts(struct tty_port *port, int on)
 		info->signals |= SerialSignal_RTS | SerialSignal_DTR;
 	else
 		info->signals &= ~(SerialSignal_RTS | SerialSignal_DTR);
- 	set_signals(info);
+	set_signals(info);
 	spin_unlock_irqrestore(&info->lock,flags);
 }
 
diff --git a/drivers/tty/synclinkmp.c b/drivers/tty/synclinkmp.c
index fcb91bf7a15b..54b897a646d0 100644
--- a/drivers/tty/synclinkmp.c
+++ b/drivers/tty/synclinkmp.c
@@ -1453,10 +1453,10 @@ static void throttle(struct tty_struct * tty)
 	if (I_IXOFF(tty))
 		send_xchar(tty, STOP_CHAR(tty));
 
- 	if (C_CRTSCTS(tty)) {
+	if (C_CRTSCTS(tty)) {
 		spin_lock_irqsave(&info->lock,flags);
 		info->serial_signals &= ~SerialSignal_RTS;
-	 	set_signals(info);
+		set_signals(info);
 		spin_unlock_irqrestore(&info->lock,flags);
 	}
 }
@@ -1482,10 +1482,10 @@ static void unthrottle(struct tty_struct * tty)
 			send_xchar(tty, START_CHAR(tty));
 	}
 
- 	if (C_CRTSCTS(tty)) {
+	if (C_CRTSCTS(tty)) {
 		spin_lock_irqsave(&info->lock,flags);
 		info->serial_signals |= SerialSignal_RTS;
-	 	set_signals(info);
+		set_signals(info);
 		spin_unlock_irqrestore(&info->lock,flags);
 	}
 }
@@ -2470,7 +2470,7 @@ static void isr_io_pin( SLMP_INFO *info, u16 status )
 					if (status & SerialSignal_CTS) {
 						if ( debug_level >= DEBUG_LEVEL_ISR )
 							printk("CTS tx start...");
-			 			info->port.tty->hw_stopped = 0;
+						info->port.tty->hw_stopped = 0;
 						tx_start(info);
 						info->pending_bh |= BH_TRANSMIT;
 						return;
@@ -2479,7 +2479,7 @@ static void isr_io_pin( SLMP_INFO *info, u16 status )
 					if (!(status & SerialSignal_CTS)) {
 						if ( debug_level >= DEBUG_LEVEL_ISR )
 							printk("CTS tx stop...");
-			 			info->port.tty->hw_stopped = 1;
+						info->port.tty->hw_stopped = 1;
 						tx_stop(info);
 					}
 				}
@@ -2806,8 +2806,8 @@ static void change_params(SLMP_INFO *info)
 	info->read_status_mask2 = OVRN;
 	if (I_INPCK(info->port.tty))
 		info->read_status_mask2 |= PE | FRME;
- 	if (I_BRKINT(info->port.tty) || I_PARMRK(info->port.tty))
- 		info->read_status_mask1 |= BRKD;
+	if (I_BRKINT(info->port.tty) || I_PARMRK(info->port.tty))
+		info->read_status_mask1 |= BRKD;
 	if (I_IGNPAR(info->port.tty))
 		info->ignore_status_mask2 |= PE | FRME;
 	if (I_IGNBRK(info->port.tty)) {
@@ -3177,7 +3177,7 @@ static int tiocmget(struct tty_struct *tty)
  	unsigned long flags;
 
 	spin_lock_irqsave(&info->lock,flags);
- 	get_signals(info);
+	get_signals(info);
 	spin_unlock_irqrestore(&info->lock,flags);
 
 	result = ((info->serial_signals & SerialSignal_RTS) ? TIOCM_RTS : 0) |
@@ -3215,7 +3215,7 @@ static int tiocmset(struct tty_struct *tty,
 		info->serial_signals &= ~SerialSignal_DTR;
 
 	spin_lock_irqsave(&info->lock,flags);
- 	set_signals(info);
+	set_signals(info);
 	spin_unlock_irqrestore(&info->lock,flags);
 
 	return 0;
@@ -3227,7 +3227,7 @@ static int carrier_raised(struct tty_port *port)
 	unsigned long flags;
 
 	spin_lock_irqsave(&info->lock,flags);
- 	get_signals(info);
+	get_signals(info);
 	spin_unlock_irqrestore(&info->lock,flags);
 
 	return (info->serial_signals & SerialSignal_DCD) ? 1 : 0;
@@ -3243,7 +3243,7 @@ static void dtr_rts(struct tty_port *port, int on)
 		info->serial_signals |= SerialSignal_RTS | SerialSignal_DTR;
 	else
 		info->serial_signals &= ~(SerialSignal_RTS | SerialSignal_DTR);
- 	set_signals(info);
+	set_signals(info);
 	spin_unlock_irqrestore(&info->lock,flags);
 }
 
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 033ac7e6a70d..d266dd4bdff1 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -2729,9 +2729,11 @@ static int compat_tty_tiocgserial(struct tty_struct *tty,
 	struct serial_struct32 v32;
 	struct serial_struct v;
 	int err;
-	memset(&v, 0, sizeof(struct serial_struct));
 
-	if (!tty->ops->set_serial)
+	memset(&v, 0, sizeof(v));
+	memset(&v32, 0, sizeof(v32));
+
+	if (!tty->ops->get_serial)
 		return -ENOTTY;
 	err = tty->ops->get_serial(tty, &v);
 	if (!err) {
diff --git a/drivers/tty/tty_port.c b/drivers/tty/tty_port.c
index 044c3cbdcfa4..ea80bf872f54 100644
--- a/drivers/tty/tty_port.c
+++ b/drivers/tty/tty_port.c
@@ -52,10 +52,11 @@ static void tty_port_default_wakeup(struct tty_port *port)
 	}
 }
 
-static const struct tty_port_client_operations default_client_ops = {
+const struct tty_port_client_operations tty_port_default_client_ops = {
 	.receive_buf = tty_port_default_receive_buf,
 	.write_wakeup = tty_port_default_wakeup,
 };
+EXPORT_SYMBOL_GPL(tty_port_default_client_ops);
 
 void tty_port_init(struct tty_port *port)
 {
@@ -68,7 +69,7 @@ void tty_port_init(struct tty_port *port)
 	spin_lock_init(&port->lock);
 	port->close_delay = (50 * HZ) / 100;
 	port->closing_wait = (3000 * HZ) / 100;
-	port->client_ops = &default_client_ops;
+	port->client_ops = &tty_port_default_client_ops;
 	kref_init(&port->kref);
 }
 EXPORT_SYMBOL(tty_port_init);
diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c
index 15d33fa0c925..568b2171f335 100644
--- a/drivers/tty/vt/keyboard.c
+++ b/drivers/tty/vt/keyboard.c
@@ -127,7 +127,11 @@ static DEFINE_SPINLOCK(func_buf_lock); /* guard 'func_buf'  and friends */
 static unsigned long key_down[BITS_TO_LONGS(KEY_CNT)];	/* keyboard key bitmap */
 static unsigned char shift_down[NR_SHIFT];		/* shift state counters.. */
 static bool dead_key_next;
-static int npadch = -1;					/* -1 or number assembled on pad */
+
+/* Handles a number being assembled on the number pad */
+static bool npadch_active;
+static unsigned int npadch_value;
+
 static unsigned int diacr;
 static char rep;					/* flag telling character repeat */
 
@@ -845,12 +849,12 @@ static void k_shift(struct vc_data *vc, unsigned char value, char up_flag)
 		shift_state &= ~(1 << value);
 
 	/* kludge */
-	if (up_flag && shift_state != old_state && npadch != -1) {
+	if (up_flag && shift_state != old_state && npadch_active) {
 		if (kbd->kbdmode == VC_UNICODE)
-			to_utf8(vc, npadch);
+			to_utf8(vc, npadch_value);
 		else
-			put_queue(vc, npadch & 0xff);
-		npadch = -1;
+			put_queue(vc, npadch_value & 0xff);
+		npadch_active = false;
 	}
 }
 
@@ -868,7 +872,7 @@ static void k_meta(struct vc_data *vc, unsigned char value, char up_flag)
 
 static void k_ascii(struct vc_data *vc, unsigned char value, char up_flag)
 {
-	int base;
+	unsigned int base;
 
 	if (up_flag)
 		return;
@@ -882,10 +886,12 @@ static void k_ascii(struct vc_data *vc, unsigned char value, char up_flag)
 		base = 16;
 	}
 
-	if (npadch == -1)
-		npadch = value;
-	else
-		npadch = npadch * base + value;
+	if (!npadch_active) {
+		npadch_value = 0;
+		npadch_active = true;
+	}
+
+	npadch_value = npadch_value * base + value;
 }
 
 static void k_lock(struct vc_data *vc, unsigned char value, char up_flag)
diff --git a/drivers/tty/vt/selection.c b/drivers/tty/vt/selection.c
index 0233b34e49d5..7556139cd0da 100644
--- a/drivers/tty/vt/selection.c
+++ b/drivers/tty/vt/selection.c
@@ -30,6 +30,8 @@
 #include <linux/console.h>
 #include <linux/tty_flip.h>
 
+#include <linux/sched/signal.h>
+
 /* Don't take this from <ctype.h>: 011-015 on the screen aren't spaces */
 #define isspace(c)	((c) == ' ')
 
@@ -86,6 +88,11 @@ void clear_selection(void)
 }
 EXPORT_SYMBOL_GPL(clear_selection);
 
+bool vc_is_sel(struct vc_data *vc)
+{
+	return vc == sel_cons;
+}
+
 /*
  * User settable table: what characters are to be considered alphabetic?
  * 128 bits. Locked by the console lock.
@@ -366,6 +373,7 @@ int paste_selection(struct tty_struct *tty)
 	unsigned int count;
 	struct  tty_ldisc *ld;
 	DECLARE_WAITQUEUE(wait, current);
+	int ret = 0;
 
 	console_lock();
 	poke_blanked_console();
@@ -380,6 +388,10 @@ int paste_selection(struct tty_struct *tty)
 	mutex_lock(&sel_lock);
 	while (sel_buffer && sel_buffer_lth > pasted) {
 		set_current_state(TASK_INTERRUPTIBLE);
+		if (signal_pending(current)) {
+			ret = -EINTR;
+			break;
+		}
 		if (tty_throttled(tty)) {
 			mutex_unlock(&sel_lock);
 			schedule();
@@ -398,6 +410,6 @@ int paste_selection(struct tty_struct *tty)
 
 	tty_buffer_unlock_exclusive(&vc->port);
 	tty_ldisc_deref(ld);
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(paste_selection);
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 1a85d94d89f2..ec3b59f9bcb3 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -81,6 +81,7 @@
 #include <linux/errno.h>
 #include <linux/kd.h>
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
 #include <linux/major.h>
 #include <linux/mm.h>
 #include <linux/console.h>
@@ -350,7 +351,7 @@ static struct uni_screen *vc_uniscr_alloc(unsigned int cols, unsigned int rows)
 	/* allocate everything in one go */
 	memsize = cols * rows * sizeof(char32_t);
 	memsize += rows * sizeof(char32_t *);
-	p = kmalloc(memsize, GFP_KERNEL);
+	p = vmalloc(memsize);
 	if (!p)
 		return NULL;
 
@@ -364,9 +365,14 @@ static struct uni_screen *vc_uniscr_alloc(unsigned int cols, unsigned int rows)
 	return uniscr;
 }
 
+static void vc_uniscr_free(struct uni_screen *uniscr)
+{
+	vfree(uniscr);
+}
+
 static void vc_uniscr_set(struct vc_data *vc, struct uni_screen *new_uniscr)
 {
-	kfree(vc->vc_uni_screen);
+	vc_uniscr_free(vc->vc_uni_screen);
 	vc->vc_uni_screen = new_uniscr;
 }
 
@@ -890,8 +896,9 @@ static void hide_softcursor(struct vc_data *vc)
 
 static void hide_cursor(struct vc_data *vc)
 {
-	if (vc == sel_cons)
+	if (vc_is_sel(vc))
 		clear_selection();
+
 	vc->vc_sw->con_cursor(vc, CM_ERASE);
 	hide_softcursor(vc);
 }
@@ -901,7 +908,7 @@ static void set_cursor(struct vc_data *vc)
 	if (!con_is_fg(vc) || console_blanked || vc->vc_mode == KD_GRAPHICS)
 		return;
 	if (vc->vc_deccm) {
-		if (vc == sel_cons)
+		if (vc_is_sel(vc))
 			clear_selection();
 		add_softcursor(vc);
 		if ((vc->vc_cursor_type & 0x0f) != 1)
@@ -936,10 +943,21 @@ static void flush_scrollback(struct vc_data *vc)
 	WARN_CONSOLE_UNLOCKED();
 
 	set_origin(vc);
-	if (vc->vc_sw->con_flush_scrollback)
+	if (vc->vc_sw->con_flush_scrollback) {
 		vc->vc_sw->con_flush_scrollback(vc);
-	else
+	} else if (con_is_visible(vc)) {
+		/*
+		 * When no con_flush_scrollback method is provided then the
+		 * legacy way for flushing the scrollback buffer is to use
+		 * a side effect of the con_switch method. We do it only on
+		 * the foreground console as background consoles have no
+		 * scrollback buffers in that case and we obviously don't
+		 * want to switch to them.
+		 */
+		hide_cursor(vc);
 		vc->vc_sw->con_switch(vc);
+		set_cursor(vc);
+	}
 }
 
 /*
@@ -1063,10 +1081,30 @@ static void visual_deinit(struct vc_data *vc)
 	module_put(vc->vc_sw->owner);
 }
 
+static void vc_port_destruct(struct tty_port *port)
+{
+	struct vc_data *vc = container_of(port, struct vc_data, port);
+
+	kfree(vc);
+}
+
+static const struct tty_port_operations vc_port_ops = {
+	.destruct = vc_port_destruct,
+};
+
+/*
+ * Change # of rows and columns (0 means unchanged/the size of fg_console)
+ * [this is to be used together with some user program
+ * like resize that changes the hardware videomode]
+ */
+#define VC_MAXCOL (32767)
+#define VC_MAXROW (32767)
+
 int vc_allocate(unsigned int currcons)	/* return 0 on success */
 {
 	struct vt_notifier_param param;
 	struct vc_data *vc;
+	int err;
 
 	WARN_CONSOLE_UNLOCKED();
 
@@ -1088,6 +1126,7 @@ int vc_allocate(unsigned int currcons)	/* return 0 on success */
 
 	vc_cons[currcons].d = vc;
 	tty_port_init(&vc->port);
+	vc->port.ops = &vc_port_ops;
 	INIT_WORK(&vc_cons[currcons].SAK_work, vc_SAK);
 
 	visual_init(vc, currcons, 1);
@@ -1095,6 +1134,11 @@ int vc_allocate(unsigned int currcons)	/* return 0 on success */
 	if (!*vc->vc_uni_pagedir_loc)
 		con_set_default_unimap(vc);
 
+	err = -EINVAL;
+	if (vc->vc_cols > VC_MAXCOL || vc->vc_rows > VC_MAXROW ||
+	    vc->vc_screenbuf_size > KMALLOC_MAX_SIZE || !vc->vc_screenbuf_size)
+		goto err_free;
+	err = -ENOMEM;
 	vc->vc_screenbuf = kzalloc(vc->vc_screenbuf_size, GFP_KERNEL);
 	if (!vc->vc_screenbuf)
 		goto err_free;
@@ -1113,7 +1157,7 @@ err_free:
 	visual_deinit(vc);
 	kfree(vc);
 	vc_cons[currcons].d = NULL;
-	return -ENOMEM;
+	return err;
 }
 
 static inline int resize_screen(struct vc_data *vc, int width, int height,
@@ -1128,14 +1172,6 @@ static inline int resize_screen(struct vc_data *vc, int width, int height,
 	return err;
 }
 
-/*
- * Change # of rows and columns (0 means unchanged/the size of fg_console)
- * [this is to be used together with some user program
- * like resize that changes the hardware videomode]
- */
-#define VC_RESIZE_MAXCOL (32767)
-#define VC_RESIZE_MAXROW (32767)
-
 /**
  *	vc_do_resize	-	resizing method for the tty
  *	@tty: tty being resized
@@ -1171,7 +1207,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc,
 	user = vc->vc_resize_user;
 	vc->vc_resize_user = 0;
 
-	if (cols > VC_RESIZE_MAXCOL || lines > VC_RESIZE_MAXROW)
+	if (cols > VC_MAXCOL || lines > VC_MAXROW)
 		return -EINVAL;
 
 	new_cols = (cols ? cols : vc->vc_cols);
@@ -1182,7 +1218,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc,
 	if (new_cols == vc->vc_cols && new_rows == vc->vc_rows)
 		return 0;
 
-	if (new_screen_size > (4 << 20))
+	if (new_screen_size > KMALLOC_MAX_SIZE || !new_screen_size)
 		return -EINVAL;
 	newscreen = kzalloc(new_screen_size, GFP_USER);
 	if (!newscreen)
@@ -1196,7 +1232,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc,
 		}
 	}
 
-	if (vc == sel_cons)
+	if (vc_is_sel(vc))
 		clear_selection();
 
 	old_rows = vc->vc_rows;
@@ -1205,7 +1241,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc,
 	err = resize_screen(vc, new_cols, new_rows, user);
 	if (err) {
 		kfree(newscreen);
-		kfree(new_uniscr);
+		vc_uniscr_free(new_uniscr);
 		return err;
 	}
 
@@ -3242,6 +3278,7 @@ static int con_install(struct tty_driver *driver, struct tty_struct *tty)
 
 	tty->driver_data = vc;
 	vc->port.tty = tty;
+	tty_port_get(&vc->port);
 
 	if (!tty->winsize.ws_row && !tty->winsize.ws_col) {
 		tty->winsize.ws_row = vc_cons[currcons].d->vc_rows;
@@ -3277,6 +3314,13 @@ static void con_shutdown(struct tty_struct *tty)
 	console_unlock();
 }
 
+static void con_cleanup(struct tty_struct *tty)
+{
+	struct vc_data *vc = tty->driver_data;
+
+	tty_port_put(&vc->port);
+}
+
 static int default_color           = 7; /* white */
 static int default_italic_color    = 2; // green (ASCII)
 static int default_underline_color = 3; // cyan (ASCII)
@@ -3358,6 +3402,7 @@ static int __init con_init(void)
 		INIT_WORK(&vc_cons[currcons].SAK_work, vc_SAK);
 		tty_port_init(&vc->port);
 		visual_init(vc, currcons, 1);
+		/* Assuming vc->vc_{cols,rows,screenbuf_size} are sane here. */
 		vc->vc_screenbuf = kzalloc(vc->vc_screenbuf_size, GFP_NOWAIT);
 		vc_init(vc, vc->vc_rows, vc->vc_cols,
 			currcons || !vc->vc_sw->con_save_screen);
@@ -3401,7 +3446,8 @@ static const struct tty_operations con_ops = {
 	.throttle = con_throttle,
 	.unthrottle = con_unthrottle,
 	.resize = vt_resize,
-	.shutdown = con_shutdown
+	.shutdown = con_shutdown,
+	.cleanup = con_cleanup,
 };
 
 static struct cdev vc0_cdev;
diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c
index 8b0ed139592f..daf61c28ba76 100644
--- a/drivers/tty/vt/vt_ioctl.c
+++ b/drivers/tty/vt/vt_ioctl.c
@@ -39,11 +39,32 @@
 #include <linux/kbd_diacr.h>
 #include <linux/selection.h>
 
-char vt_dont_switch;
-extern struct tty_driver *console_driver;
+bool vt_dont_switch;
 
-#define VT_IS_IN_USE(i)	(console_driver->ttys[i] && console_driver->ttys[i]->count)
-#define VT_BUSY(i)	(VT_IS_IN_USE(i) || i == fg_console || vc_cons[i].d == sel_cons)
+static inline bool vt_in_use(unsigned int i)
+{
+	const struct vc_data *vc = vc_cons[i].d;
+
+	/*
+	 * console_lock must be held to prevent the vc from being deallocated
+	 * while we're checking whether it's in-use.
+	 */
+	WARN_CONSOLE_UNLOCKED();
+
+	return vc && kref_read(&vc->port.kref) > 1;
+}
+
+static inline bool vt_busy(int i)
+{
+	if (vt_in_use(i))
+		return true;
+	if (i == fg_console)
+		return true;
+	if (vc_is_sel(vc_cons[i].d))
+		return true;
+
+	return false;
+}
 
 /*
  * Console (vt and kd) routines, as defined by USL SVR4 manual, and by
@@ -289,16 +310,14 @@ static int vt_disallocate(unsigned int vc_num)
 	int ret = 0;
 
 	console_lock();
-	if (VT_BUSY(vc_num))
+	if (vt_busy(vc_num))
 		ret = -EBUSY;
 	else if (vc_num)
 		vc = vc_deallocate(vc_num);
 	console_unlock();
 
-	if (vc && vc_num >= MIN_NR_CONSOLES) {
-		tty_port_destroy(&vc->port);
-		kfree(vc);
-	}
+	if (vc && vc_num >= MIN_NR_CONSOLES)
+		tty_port_put(&vc->port);
 
 	return ret;
 }
@@ -311,17 +330,15 @@ static void vt_disallocate_all(void)
 
 	console_lock();
 	for (i = 1; i < MAX_NR_CONSOLES; i++)
-		if (!VT_BUSY(i))
+		if (!vt_busy(i))
 			vc[i] = vc_deallocate(i);
 		else
 			vc[i] = NULL;
 	console_unlock();
 
 	for (i = 1; i < MAX_NR_CONSOLES; i++) {
-		if (vc[i] && i >= MIN_NR_CONSOLES) {
-			tty_port_destroy(&vc[i]->port);
-			kfree(vc[i]);
-		}
+		if (vc[i] && i >= MIN_NR_CONSOLES)
+			tty_port_put(&vc[i]->port);
 	}
 }
 
@@ -335,22 +352,13 @@ int vt_ioctl(struct tty_struct *tty,
 {
 	struct vc_data *vc = tty->driver_data;
 	struct console_font_op op;	/* used in multiple places here */
-	unsigned int console;
+	unsigned int console = vc->vc_num;
 	unsigned char ucval;
 	unsigned int uival;
 	void __user *up = (void __user *)arg;
 	int i, perm;
 	int ret = 0;
 
-	console = vc->vc_num;
-
-
-	if (!vc_cons_allocated(console)) { 	/* impossible? */
-		ret = -ENOIOCTLCMD;
-		goto out;
-	}
-
-
 	/*
 	 * To have permissions to do most of the vt ioctls, we either have
 	 * to be the owner of the tty, or have CAP_SYS_TTY_CONFIG.
@@ -641,15 +649,16 @@ int vt_ioctl(struct tty_struct *tty,
 		struct vt_stat __user *vtstat = up;
 		unsigned short state, mask;
 
-		/* Review: FIXME: Console lock ? */
 		if (put_user(fg_console + 1, &vtstat->v_active))
 			ret = -EFAULT;
 		else {
 			state = 1;	/* /dev/tty0 is always open */
+			console_lock(); /* required by vt_in_use() */
 			for (i = 0, mask = 2; i < MAX_NR_CONSOLES && mask;
 							++i, mask <<= 1)
-				if (VT_IS_IN_USE(i))
+				if (vt_in_use(i))
 					state |= mask;
+			console_unlock();
 			ret = put_user(state, &vtstat->v_state);
 		}
 		break;
@@ -659,10 +668,11 @@ int vt_ioctl(struct tty_struct *tty,
 	 * Returns the first available (non-opened) console.
 	 */
 	case VT_OPENQRY:
-		/* FIXME: locking ? - but then this is a stupid API */
+		console_lock(); /* required by vt_in_use() */
 		for (i = 0; i < MAX_NR_CONSOLES; ++i)
-			if (! VT_IS_IN_USE(i))
+			if (!vt_in_use(i))
 				break;
+		console_unlock();
 		uival = i < MAX_NR_CONSOLES ? (i+1) : -1;
 		goto setint;		 
 
@@ -876,15 +886,20 @@ int vt_ioctl(struct tty_struct *tty,
 			return -EINVAL;
 
 		for (i = 0; i < MAX_NR_CONSOLES; i++) {
+			struct vc_data *vcp;
+
 			if (!vc_cons[i].d)
 				continue;
 			console_lock();
-			if (v.v_vlin)
-				vc_cons[i].d->vc_scan_lines = v.v_vlin;
-			if (v.v_clin)
-				vc_cons[i].d->vc_font.height = v.v_clin;
-			vc_cons[i].d->vc_resize_user = 1;
-			vc_resize(vc_cons[i].d, v.v_cols, v.v_rows);
+			vcp = vc_cons[i].d;
+			if (vcp) {
+				if (v.v_vlin)
+					vcp->vc_scan_lines = v.v_vlin;
+				if (v.v_clin)
+					vcp->vc_font.height = v.v_clin;
+				vcp->vc_resize_user = 1;
+				vc_resize(vcp, v.v_cols, v.v_rows);
+			}
 			console_unlock();
 		}
 		break;
@@ -1006,12 +1021,12 @@ int vt_ioctl(struct tty_struct *tty,
 	case VT_LOCKSWITCH:
 		if (!capable(CAP_SYS_TTY_CONFIG))
 			return -EPERM;
-		vt_dont_switch = 1;
+		vt_dont_switch = true;
 		break;
 	case VT_UNLOCKSWITCH:
 		if (!capable(CAP_SYS_TTY_CONFIG))
 			return -EPERM;
-		vt_dont_switch = 0;
+		vt_dont_switch = false;
 		break;
 	case VT_GETHIFONTMASK:
 		ret = put_user(vc->vc_hi_font_mask,
@@ -1175,14 +1190,9 @@ long vt_compat_ioctl(struct tty_struct *tty,
 {
 	struct vc_data *vc = tty->driver_data;
 	struct console_font_op op;	/* used in multiple places here */
-	unsigned int console = vc->vc_num;
 	void __user *up = compat_ptr(arg);
 	int perm;
 
-
-	if (!vc_cons_allocated(console)) 	/* impossible? */
-		return -ENOIOCTLCMD;
-
 	/*
 	 * To have permissions to do most of the vt ioctls, we either have
 	 * to be the owner of the tty, or have CAP_SYS_TTY_CONFIG.
diff --git a/drivers/uio/uio_dmem_genirq.c b/drivers/uio/uio_dmem_genirq.c
index f32cef94aa82..53c58813ec08 100644
--- a/drivers/uio/uio_dmem_genirq.c
+++ b/drivers/uio/uio_dmem_genirq.c
@@ -132,11 +132,13 @@ static int uio_dmem_genirq_irqcontrol(struct uio_info *dev_info, s32 irq_on)
 	if (irq_on) {
 		if (test_and_clear_bit(0, &priv->flags))
 			enable_irq(dev_info->irq);
+		spin_unlock_irqrestore(&priv->lock, flags);
 	} else {
-		if (!test_and_set_bit(0, &priv->flags))
+		if (!test_and_set_bit(0, &priv->flags)) {
+			spin_unlock_irqrestore(&priv->lock, flags);
 			disable_irq(dev_info->irq);
+		}
 	}
-	spin_unlock_irqrestore(&priv->lock, flags);
 
 	return 0;
 }
diff --git a/drivers/uio/uio_pdrv_genirq.c b/drivers/uio/uio_pdrv_genirq.c
index 10688d79d180..6dea4fc1fc59 100644
--- a/drivers/uio/uio_pdrv_genirq.c
+++ b/drivers/uio/uio_pdrv_genirq.c
@@ -144,9 +144,9 @@ static int uio_pdrv_genirq_probe(struct platform_device *pdev)
 	priv->pdev = pdev;
 
 	if (!uioinfo->irq) {
-		ret = platform_get_irq(pdev, 0);
+		ret = platform_get_irq_optional(pdev, 0);
 		uioinfo->irq = ret;
-		if (ret == -ENXIO && pdev->dev.of_node)
+		if (ret == -ENXIO)
 			uioinfo->irq = UIO_IRQ_NONE;
 		else if (ret < 0) {
 			dev_err(&pdev->dev, "failed to get IRQ\n");
diff --git a/drivers/usb/c67x00/c67x00-sched.c b/drivers/usb/c67x00/c67x00-sched.c
index 633c52de3bb3..9865750bc31e 100644
--- a/drivers/usb/c67x00/c67x00-sched.c
+++ b/drivers/usb/c67x00/c67x00-sched.c
@@ -486,7 +486,7 @@ c67x00_giveback_urb(struct c67x00_hcd *c67x00, struct urb *urb, int status)
 	c67x00_release_urb(c67x00, urb);
 	usb_hcd_unlink_urb_from_ep(c67x00_hcd_to_hcd(c67x00), urb);
 	spin_unlock(&c67x00->lock);
-	usb_hcd_giveback_urb(c67x00_hcd_to_hcd(c67x00), urb, urbp->status);
+	usb_hcd_giveback_urb(c67x00_hcd_to_hcd(c67x00), urb, status);
 	spin_lock(&c67x00->lock);
 }
 
diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c
index 27749ace2d93..fb2e7a611eb4 100644
--- a/drivers/usb/chipidea/core.c
+++ b/drivers/usb/chipidea/core.c
@@ -1188,6 +1188,29 @@ static void ci_controller_suspend(struct ci_hdrc *ci)
 	enable_irq(ci->irq);
 }
 
+/*
+ * Handle the wakeup interrupt triggered by extcon connector
+ * We need to call ci_irq again for extcon since the first
+ * interrupt (wakeup int) only let the controller be out of
+ * low power mode, but not handle any interrupts.
+ */
+static void ci_extcon_wakeup_int(struct ci_hdrc *ci)
+{
+	struct ci_hdrc_cable *cable_id, *cable_vbus;
+	u32 otgsc = hw_read_otgsc(ci, ~0);
+
+	cable_id = &ci->platdata->id_extcon;
+	cable_vbus = &ci->platdata->vbus_extcon;
+
+	if (!IS_ERR(cable_id->edev) && ci->is_otg &&
+		(otgsc & OTGSC_IDIE) && (otgsc & OTGSC_IDIS))
+		ci_irq(ci->irq, ci);
+
+	if (!IS_ERR(cable_vbus->edev) && ci->is_otg &&
+		(otgsc & OTGSC_BSVIE) && (otgsc & OTGSC_BSVIS))
+		ci_irq(ci->irq, ci);
+}
+
 static int ci_controller_resume(struct device *dev)
 {
 	struct ci_hdrc *ci = dev_get_drvdata(dev);
@@ -1220,6 +1243,7 @@ static int ci_controller_resume(struct device *dev)
 		enable_irq(ci->irq);
 		if (ci_otg_is_fsm_mode(ci))
 			ci_otg_fsm_wakeup_by_srp(ci);
+		ci_extcon_wakeup_int(ci);
 	}
 
 	return 0;
diff --git a/drivers/usb/chipidea/host.c b/drivers/usb/chipidea/host.c
index b45ceb91c735..48e4a5ca1835 100644
--- a/drivers/usb/chipidea/host.c
+++ b/drivers/usb/chipidea/host.c
@@ -26,6 +26,7 @@ static int (*orig_bus_suspend)(struct usb_hcd *hcd);
 
 struct ehci_ci_priv {
 	struct regulator *reg_vbus;
+	bool enabled;
 };
 
 static int ehci_ci_portpower(struct usb_hcd *hcd, int portnum, bool enable)
@@ -37,7 +38,7 @@ static int ehci_ci_portpower(struct usb_hcd *hcd, int portnum, bool enable)
 	int ret = 0;
 	int port = HCS_N_PORTS(ehci->hcs_params);
 
-	if (priv->reg_vbus) {
+	if (priv->reg_vbus && enable != priv->enabled) {
 		if (port > 1) {
 			dev_warn(dev,
 				"Not support multi-port regulator control\n");
@@ -53,6 +54,7 @@ static int ehci_ci_portpower(struct usb_hcd *hcd, int portnum, bool enable)
 				enable ? "enable" : "disable", ret);
 			return ret;
 		}
+		priv->enabled = enable;
 	}
 
 	if (enable && (ci->platdata->phy_mode == USBPHY_INTERFACE_MODE_HSIC)) {
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 62f4fb9b362f..d5187b50fc82 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -412,9 +412,12 @@ static void acm_ctrl_irq(struct urb *urb)
 
 exit:
 	retval = usb_submit_urb(urb, GFP_ATOMIC);
-	if (retval && retval != -EPERM)
+	if (retval && retval != -EPERM && retval != -ENODEV)
 		dev_err(&acm->control->dev,
 			"%s - usb_submit_urb failed: %d\n", __func__, retval);
+	else
+		dev_vdbg(&acm->control->dev,
+			"control resubmission terminated %d\n", retval);
 }
 
 static int acm_submit_read_urb(struct acm *acm, int index, gfp_t mem_flags)
@@ -430,6 +433,8 @@ static int acm_submit_read_urb(struct acm *acm, int index, gfp_t mem_flags)
 			dev_err(&acm->data->dev,
 				"urb %d failed submission with %d\n",
 				index, res);
+		} else {
+			dev_vdbg(&acm->data->dev, "intended failure %d\n", res);
 		}
 		set_bit(index, &acm->read_urbs_free);
 		return res;
@@ -471,6 +476,7 @@ static void acm_read_bulk_callback(struct urb *urb)
 	int status = urb->status;
 	bool stopped = false;
 	bool stalled = false;
+	bool cooldown = false;
 
 	dev_vdbg(&acm->data->dev, "got urb %d, len %d, status %d\n",
 		rb->index, urb->actual_length, status);
@@ -497,6 +503,14 @@ static void acm_read_bulk_callback(struct urb *urb)
 			__func__, status);
 		stopped = true;
 		break;
+	case -EOVERFLOW:
+	case -EPROTO:
+		dev_dbg(&acm->data->dev,
+			"%s - cooling babbling device\n", __func__);
+		usb_mark_last_busy(acm->dev);
+		set_bit(rb->index, &acm->urbs_in_error_delay);
+		cooldown = true;
+		break;
 	default:
 		dev_dbg(&acm->data->dev,
 			"%s - nonzero urb status received: %d\n",
@@ -518,9 +532,11 @@ static void acm_read_bulk_callback(struct urb *urb)
 	 */
 	smp_mb__after_atomic();
 
-	if (stopped || stalled) {
+	if (stopped || stalled || cooldown) {
 		if (stalled)
 			schedule_work(&acm->work);
+		else if (cooldown)
+			schedule_delayed_work(&acm->dwork, HZ / 2);
 		return;
 	}
 
@@ -557,14 +573,20 @@ static void acm_softint(struct work_struct *work)
 	struct acm *acm = container_of(work, struct acm, work);
 
 	if (test_bit(EVENT_RX_STALL, &acm->flags)) {
-		if (!(usb_autopm_get_interface(acm->data))) {
+		smp_mb(); /* against acm_suspend() */
+		if (!acm->susp_count) {
 			for (i = 0; i < acm->rx_buflimit; i++)
 				usb_kill_urb(acm->read_urbs[i]);
 			usb_clear_halt(acm->dev, acm->in);
 			acm_submit_read_urbs(acm, GFP_KERNEL);
-			usb_autopm_put_interface(acm->data);
+			clear_bit(EVENT_RX_STALL, &acm->flags);
 		}
-		clear_bit(EVENT_RX_STALL, &acm->flags);
+	}
+
+	if (test_and_clear_bit(ACM_ERROR_DELAY, &acm->flags)) {
+		for (i = 0; i < acm->rx_buflimit; i++)
+			if (test_and_clear_bit(i, &acm->urbs_in_error_delay))
+					acm_submit_read_urb(acm, i, GFP_NOIO);
 	}
 
 	if (test_and_clear_bit(EVENT_TTY_WAKEUP, &acm->flags))
@@ -896,10 +918,10 @@ static int get_serial_info(struct tty_struct *tty, struct serial_struct *ss)
 
 	ss->xmit_fifo_size = acm->writesize;
 	ss->baud_base = le32_to_cpu(acm->line.dwDTERate);
-	ss->close_delay	= acm->port.close_delay / 10;
+	ss->close_delay	= jiffies_to_msecs(acm->port.close_delay) / 10;
 	ss->closing_wait = acm->port.closing_wait == ASYNC_CLOSING_WAIT_NONE ?
 				ASYNC_CLOSING_WAIT_NONE :
-				acm->port.closing_wait / 10;
+				jiffies_to_msecs(acm->port.closing_wait) / 10;
 	return 0;
 }
 
@@ -907,17 +929,25 @@ static int set_serial_info(struct tty_struct *tty, struct serial_struct *ss)
 {
 	struct acm *acm = tty->driver_data;
 	unsigned int closing_wait, close_delay;
+	unsigned int old_closing_wait, old_close_delay;
 	int retval = 0;
 
-	close_delay = ss->close_delay * 10;
+	close_delay = msecs_to_jiffies(ss->close_delay * 10);
 	closing_wait = ss->closing_wait == ASYNC_CLOSING_WAIT_NONE ?
-			ASYNC_CLOSING_WAIT_NONE : ss->closing_wait * 10;
+			ASYNC_CLOSING_WAIT_NONE :
+			msecs_to_jiffies(ss->closing_wait * 10);
+
+	/* we must redo the rounding here, so that the values match */
+	old_close_delay	= jiffies_to_msecs(acm->port.close_delay) / 10;
+	old_closing_wait = acm->port.closing_wait == ASYNC_CLOSING_WAIT_NONE ?
+				ASYNC_CLOSING_WAIT_NONE :
+				jiffies_to_msecs(acm->port.closing_wait) / 10;
 
 	mutex_lock(&acm->port.mutex);
 
 	if (!capable(CAP_SYS_ADMIN)) {
-		if ((close_delay != acm->port.close_delay) ||
-		    (closing_wait != acm->port.closing_wait))
+		if ((ss->close_delay != old_close_delay) ||
+		    (ss->closing_wait != old_closing_wait))
 			retval = -EPERM;
 		else
 			retval = -EOPNOTSUPP;
@@ -1325,6 +1355,7 @@ made_compressed_probe:
 	acm->readsize = readsize;
 	acm->rx_buflimit = num_rx_buf;
 	INIT_WORK(&acm->work, acm_softint);
+	INIT_DELAYED_WORK(&acm->dwork, acm_softint);
 	init_waitqueue_head(&acm->wioctl);
 	spin_lock_init(&acm->write_lock);
 	spin_lock_init(&acm->read_lock);
@@ -1534,6 +1565,7 @@ static void acm_disconnect(struct usb_interface *intf)
 
 	acm_kill_urbs(acm);
 	cancel_work_sync(&acm->work);
+	cancel_delayed_work_sync(&acm->dwork);
 
 	tty_unregister_device(acm_tty_driver, acm->minor);
 
@@ -1576,6 +1608,8 @@ static int acm_suspend(struct usb_interface *intf, pm_message_t message)
 
 	acm_kill_urbs(acm);
 	cancel_work_sync(&acm->work);
+	cancel_delayed_work_sync(&acm->dwork);
+	acm->urbs_in_error_delay = 0;
 
 	return 0;
 }
@@ -1655,6 +1689,8 @@ static int acm_pre_reset(struct usb_interface *intf)
 
 static const struct usb_device_id acm_ids[] = {
 	/* quirky and broken devices */
+	{ USB_DEVICE(0x0424, 0x274e), /* Microchip Technology, Inc. (formerly SMSC) */
+	  .driver_info = DISABLE_ECHO, }, /* DISABLE ECHO in termios flag */
 	{ USB_DEVICE(0x076d, 0x0006), /* Denso Cradle CU-321 */
 	.driver_info = NO_UNION_NORMAL, },/* has no union descriptor */
 	{ USB_DEVICE(0x17ef, 0x7000), /* Lenovo USB modem */
diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h
index ca1c026382c2..cd5e9d8ab237 100644
--- a/drivers/usb/class/cdc-acm.h
+++ b/drivers/usb/class/cdc-acm.h
@@ -109,8 +109,11 @@ struct acm {
 #		define EVENT_TTY_WAKEUP	0
 #		define EVENT_RX_STALL	1
 #		define ACM_THROTTLED	2
+#		define ACM_ERROR_DELAY	3
+	unsigned long urbs_in_error_delay;		/* these need to be restarted after a delay */
 	struct usb_cdc_line_coding line;		/* bits, stop, parity */
-	struct work_struct work;			/* work queue entry for line discipline waking up */
+	struct work_struct work;			/* work queue entry for various purposes*/
+	struct delayed_work dwork;			/* for cool downs needed in error recovery */
 	unsigned int ctrlin;				/* input control lines (DCD, DSR, RI, break, overruns) */
 	unsigned int ctrlout;				/* output control lines (DTR, RTS) */
 	struct async_icount iocount;			/* counters for control line changes */
diff --git a/drivers/usb/class/usblp.c b/drivers/usb/class/usblp.c
index 4a80103675d5..419804c9c974 100644
--- a/drivers/usb/class/usblp.c
+++ b/drivers/usb/class/usblp.c
@@ -468,7 +468,8 @@ static int usblp_release(struct inode *inode, struct file *file)
 	usb_autopm_put_interface(usblp->intf);
 
 	if (!usblp->present)		/* finish cleanup from disconnect */
-		usblp_cleanup(usblp);
+		usblp_cleanup(usblp);	/* any URBs must be dead */
+
 	mutex_unlock(&usblp_mutex);
 	return 0;
 }
@@ -1375,9 +1376,11 @@ static void usblp_disconnect(struct usb_interface *intf)
 
 	usblp_unlink_urbs(usblp);
 	mutex_unlock(&usblp->mut);
+	usb_poison_anchored_urbs(&usblp->urbs);
 
 	if (!usblp->used)
 		usblp_cleanup(usblp);
+
 	mutex_unlock(&usblp_mutex);
 }
 
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index 1ac1095bfeac..a0c5569300cf 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -203,10 +203,60 @@ static const unsigned short super_speed_maxpacket_maxes[4] = {
 	[USB_ENDPOINT_XFER_INT] = 1024,
 };
 
-static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum,
-    int asnum, struct usb_host_interface *ifp, int num_ep,
-    unsigned char *buffer, int size)
+static bool endpoint_is_duplicate(struct usb_endpoint_descriptor *e1,
+		struct usb_endpoint_descriptor *e2)
 {
+	if (e1->bEndpointAddress == e2->bEndpointAddress)
+		return true;
+
+	if (usb_endpoint_xfer_control(e1) || usb_endpoint_xfer_control(e2)) {
+		if (usb_endpoint_num(e1) == usb_endpoint_num(e2))
+			return true;
+	}
+
+	return false;
+}
+
+/*
+ * Check for duplicate endpoint addresses in other interfaces and in the
+ * altsetting currently being parsed.
+ */
+static bool config_endpoint_is_duplicate(struct usb_host_config *config,
+		int inum, int asnum, struct usb_endpoint_descriptor *d)
+{
+	struct usb_endpoint_descriptor *epd;
+	struct usb_interface_cache *intfc;
+	struct usb_host_interface *alt;
+	int i, j, k;
+
+	for (i = 0; i < config->desc.bNumInterfaces; ++i) {
+		intfc = config->intf_cache[i];
+
+		for (j = 0; j < intfc->num_altsetting; ++j) {
+			alt = &intfc->altsetting[j];
+
+			if (alt->desc.bInterfaceNumber == inum &&
+					alt->desc.bAlternateSetting != asnum)
+				continue;
+
+			for (k = 0; k < alt->desc.bNumEndpoints; ++k) {
+				epd = &alt->endpoint[k].desc;
+
+				if (endpoint_is_duplicate(epd, d))
+					return true;
+			}
+		}
+	}
+
+	return false;
+}
+
+static int usb_parse_endpoint(struct device *ddev, int cfgno,
+		struct usb_host_config *config, int inum, int asnum,
+		struct usb_host_interface *ifp, int num_ep,
+		unsigned char *buffer, int size)
+{
+	struct usb_device *udev = to_usb_device(ddev);
 	unsigned char *buffer0 = buffer;
 	struct usb_endpoint_descriptor *d;
 	struct usb_host_endpoint *endpoint;
@@ -242,11 +292,18 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum,
 		goto skip_to_next_endpoint_or_interface_descriptor;
 
 	/* Check for duplicate endpoint addresses */
-	for (i = 0; i < ifp->desc.bNumEndpoints; ++i) {
-		if (ifp->endpoint[i].desc.bEndpointAddress ==
-		    d->bEndpointAddress) {
-			dev_warn(ddev, "config %d interface %d altsetting %d has a duplicate endpoint with address 0x%X, skipping\n",
-			    cfgno, inum, asnum, d->bEndpointAddress);
+	if (config_endpoint_is_duplicate(config, inum, asnum, d)) {
+		dev_warn(ddev, "config %d interface %d altsetting %d has a duplicate endpoint with address 0x%X, skipping\n",
+				cfgno, inum, asnum, d->bEndpointAddress);
+		goto skip_to_next_endpoint_or_interface_descriptor;
+	}
+
+	/* Ignore some endpoints */
+	if (udev->quirks & USB_QUIRK_ENDPOINT_IGNORE) {
+		if (usb_endpoint_is_ignored(udev, ifp, d)) {
+			dev_warn(ddev, "config %d interface %d altsetting %d has an ignored endpoint with address 0x%X, skipping\n",
+					cfgno, inum, asnum,
+					d->bEndpointAddress);
 			goto skip_to_next_endpoint_or_interface_descriptor;
 		}
 	}
@@ -346,12 +403,16 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum,
 			endpoint->desc.wMaxPacketSize = cpu_to_le16(8);
 	}
 
-	/* Validate the wMaxPacketSize field */
+	/*
+	 * Validate the wMaxPacketSize field.
+	 * Some devices have isochronous endpoints in altsetting 0;
+	 * the USB-2 spec requires such endpoints to have wMaxPacketSize = 0
+	 * (see the end of section 5.6.3), so don't warn about them.
+	 */
 	maxp = usb_endpoint_maxp(&endpoint->desc);
-	if (maxp == 0) {
-		dev_warn(ddev, "config %d interface %d altsetting %d endpoint 0x%X has wMaxPacketSize 0, skipping\n",
+	if (maxp == 0 && !(usb_endpoint_xfer_isoc(d) && asnum == 0)) {
+		dev_warn(ddev, "config %d interface %d altsetting %d endpoint 0x%X has invalid wMaxPacketSize 0\n",
 		    cfgno, inum, asnum, d->bEndpointAddress);
-		goto skip_to_next_endpoint_or_interface_descriptor;
 	}
 
 	/* Find the highest legal maxpacket size for this endpoint */
@@ -522,8 +583,8 @@ static int usb_parse_interface(struct device *ddev, int cfgno,
 		if (((struct usb_descriptor_header *) buffer)->bDescriptorType
 		     == USB_DT_INTERFACE)
 			break;
-		retval = usb_parse_endpoint(ddev, cfgno, inum, asnum, alt,
-		    num_ep, buffer, size);
+		retval = usb_parse_endpoint(ddev, cfgno, config, inum, asnum,
+				alt, num_ep, buffer, size);
 		if (retval < 0)
 			return retval;
 		++n;
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 0e7f98a32aad..c857354e0076 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -37,7 +37,10 @@
 #include "otg_whitelist.h"
 
 #define USB_VENDOR_GENESYS_LOGIC		0x05e3
+#define USB_VENDOR_SMSC				0x0424
+#define USB_PRODUCT_USB5534B			0x5534
 #define HUB_QUIRK_CHECK_PORT_AUTOSUSPEND	0x01
+#define HUB_QUIRK_DISABLE_AUTOSUSPEND		0x02
 
 #define USB_TP_TRANSMISSION_DELAY	40	/* ns */
 #define USB_TP_TRANSMISSION_DELAY_MAX	65535	/* ns */
@@ -985,13 +988,17 @@ int usb_remove_device(struct usb_device *udev)
 {
 	struct usb_hub *hub;
 	struct usb_interface *intf;
+	int ret;
 
 	if (!udev->parent)	/* Can't remove a root hub */
 		return -EINVAL;
 	hub = usb_hub_to_struct_hub(udev->parent);
 	intf = to_usb_interface(hub->intfdev);
 
-	usb_autopm_get_interface(intf);
+	ret = usb_autopm_get_interface(intf);
+	if (ret < 0)
+		return ret;
+
 	set_bit(udev->portnum, hub->removed_bits);
 	hub_port_logical_disconnect(hub, udev->portnum);
 	usb_autopm_put_interface(intf);
@@ -1191,6 +1198,7 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type)
 			 * PORT_OVER_CURRENT is not. So check for any of them.
 			 */
 			if (udev || (portstatus & USB_PORT_STAT_CONNECTION) ||
+			    (portchange & USB_PORT_STAT_C_CONNECTION) ||
 			    (portstatus & USB_PORT_STAT_OVERCURRENT) ||
 			    (portchange & USB_PORT_STAT_C_OVERCURRENT))
 				set_bit(port1, hub->change_bits);
@@ -1729,6 +1737,10 @@ static void hub_disconnect(struct usb_interface *intf)
 	kfree(hub->buffer);
 
 	pm_suspend_ignore_children(&intf->dev, false);
+
+	if (hub->quirk_disable_autosuspend)
+		usb_autopm_put_interface(intf);
+
 	kref_put(&hub->kref, hub_release);
 }
 
@@ -1861,6 +1873,11 @@ static int hub_probe(struct usb_interface *intf, const struct usb_device_id *id)
 	if (id->driver_info & HUB_QUIRK_CHECK_PORT_AUTOSUSPEND)
 		hub->quirk_check_port_auto_suspend = 1;
 
+	if (id->driver_info & HUB_QUIRK_DISABLE_AUTOSUSPEND) {
+		hub->quirk_disable_autosuspend = 1;
+		usb_autopm_get_interface_no_resume(intf);
+	}
+
 	if (hub_configure(hub, &desc->endpoint[0].desc) >= 0)
 		return 0;
 
@@ -2689,7 +2706,7 @@ static unsigned hub_is_wusb(struct usb_hub *hub)
 #define SET_ADDRESS_TRIES	2
 #define GET_DESCRIPTOR_TRIES	2
 #define SET_CONFIG_TRIES	(2 * (use_both_schemes + 1))
-#define USE_NEW_SCHEME(i, scheme)	((i) / 2 == (int)scheme)
+#define USE_NEW_SCHEME(i, scheme)	((i) / 2 == (int)(scheme))
 
 #define HUB_ROOT_RESET_TIME	60	/* times are in msec */
 #define HUB_SHORT_RESET_TIME	10
@@ -2709,13 +2726,11 @@ static bool use_new_scheme(struct usb_device *udev, int retry,
 {
 	int old_scheme_first_port =
 		port_dev->quirks & USB_PORT_QUIRK_OLD_SCHEME;
-	int quick_enumeration = (udev->speed == USB_SPEED_HIGH);
 
 	if (udev->speed >= USB_SPEED_SUPER)
 		return false;
 
-	return USE_NEW_SCHEME(retry, old_scheme_first_port || old_scheme_first
-			      || quick_enumeration);
+	return USE_NEW_SCHEME(retry, old_scheme_first_port || old_scheme_first);
 }
 
 /* Is a USB 3.0 port in the Inactive or Compliance Mode state?
@@ -3074,6 +3089,15 @@ static int check_port_resume_type(struct usb_device *udev,
 		if (portchange & USB_PORT_STAT_C_ENABLE)
 			usb_clear_port_feature(hub->hdev, port1,
 					USB_PORT_FEAT_C_ENABLE);
+
+		/*
+		 * Whatever made this reset-resume necessary may have
+		 * turned on the port1 bit in hub->change_bits.  But after
+		 * a successful reset-resume we want the bit to be clear;
+		 * if it was on it would indicate that something happened
+		 * following the reset-resume.
+		 */
+		clear_bit(port1, hub->change_bits);
 	}
 
 	return status;
@@ -5482,6 +5506,13 @@ out_hdev_lock:
 
 static const struct usb_device_id hub_id_table[] = {
     { .match_flags = USB_DEVICE_ID_MATCH_VENDOR
+                   | USB_DEVICE_ID_MATCH_PRODUCT
+                   | USB_DEVICE_ID_MATCH_INT_CLASS,
+      .idVendor = USB_VENDOR_SMSC,
+      .idProduct = USB_PRODUCT_USB5534B,
+      .bInterfaceClass = USB_CLASS_HUB,
+      .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND},
+    { .match_flags = USB_DEVICE_ID_MATCH_VENDOR
 			| USB_DEVICE_ID_MATCH_INT_CLASS,
       .idVendor = USB_VENDOR_GENESYS_LOGIC,
       .bInterfaceClass = USB_CLASS_HUB,
diff --git a/drivers/usb/core/hub.h b/drivers/usb/core/hub.h
index a9e24e4b8df1..a97dd1ba964e 100644
--- a/drivers/usb/core/hub.h
+++ b/drivers/usb/core/hub.h
@@ -61,6 +61,7 @@ struct usb_hub {
 	unsigned		quiescing:1;
 	unsigned		disconnected:1;
 	unsigned		in_reset:1;
+	unsigned		quirk_disable_autosuspend:1;
 
 	unsigned		quirk_check_port_auto_suspend:1;
 
diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index 5adf489428aa..a1ac2f0723b0 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -588,12 +588,13 @@ void usb_sg_cancel(struct usb_sg_request *io)
 	int i, retval;
 
 	spin_lock_irqsave(&io->lock, flags);
-	if (io->status) {
+	if (io->status || io->count == 0) {
 		spin_unlock_irqrestore(&io->lock, flags);
 		return;
 	}
 	/* shut everything down */
 	io->status = -ECONNRESET;
+	io->count++;		/* Keep the request alive until we're done */
 	spin_unlock_irqrestore(&io->lock, flags);
 
 	for (i = io->entries - 1; i >= 0; --i) {
@@ -607,6 +608,12 @@ void usb_sg_cancel(struct usb_sg_request *io)
 			dev_warn(&io->dev->dev, "%s, unlink --> %d\n",
 				 __func__, retval);
 	}
+
+	spin_lock_irqsave(&io->lock, flags);
+	io->count--;
+	if (!io->count)
+		complete(&io->complete);
+	spin_unlock_irqrestore(&io->lock, flags);
 }
 EXPORT_SYMBOL_GPL(usb_sg_cancel);
 
@@ -1136,11 +1143,11 @@ void usb_disable_endpoint(struct usb_device *dev, unsigned int epaddr,
 
 	if (usb_endpoint_out(epaddr)) {
 		ep = dev->ep_out[epnum];
-		if (reset_hardware)
+		if (reset_hardware && epnum != 0)
 			dev->ep_out[epnum] = NULL;
 	} else {
 		ep = dev->ep_in[epnum];
-		if (reset_hardware)
+		if (reset_hardware && epnum != 0)
 			dev->ep_in[epnum] = NULL;
 	}
 	if (ep) {
diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c
index 1a06a4b5fbb1..ae25d3aa7560 100644
--- a/drivers/usb/core/port.c
+++ b/drivers/usb/core/port.c
@@ -213,7 +213,10 @@ static int usb_port_runtime_resume(struct device *dev)
 	if (!port_dev->is_superspeed && peer)
 		pm_runtime_get_sync(&peer->dev);
 
-	usb_autopm_get_interface(intf);
+	retval = usb_autopm_get_interface(intf);
+	if (retval < 0)
+		return retval;
+
 	retval = usb_hub_set_port_power(hdev, hub, port1, true);
 	msleep(hub_power_on_good_delay(hub));
 	if (udev && !retval) {
@@ -266,7 +269,10 @@ static int usb_port_runtime_suspend(struct device *dev)
 	if (usb_port_block_power_off)
 		return -EBUSY;
 
-	usb_autopm_get_interface(intf);
+	retval = usb_autopm_get_interface(intf);
+	if (retval < 0)
+		return retval;
+
 	retval = usb_hub_set_port_power(hdev, hub, port1, false);
 	usb_clear_port_feature(hdev, port1, USB_PORT_FEAT_C_CONNECTION);
 	if (!port_dev->is_superspeed)
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 6b6413073584..1dae4d88fd69 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -25,17 +25,23 @@ static unsigned int quirk_count;
 
 static char quirks_param[128];
 
-static int quirks_param_set(const char *val, const struct kernel_param *kp)
+static int quirks_param_set(const char *value, const struct kernel_param *kp)
 {
-	char *p, *field;
+	char *val, *p, *field;
 	u16 vid, pid;
 	u32 flags;
 	size_t i;
 	int err;
 
+	val = kstrdup(value, GFP_KERNEL);
+	if (!val)
+		return -ENOMEM;
+
 	err = param_set_copystring(val, kp);
-	if (err)
+	if (err) {
+		kfree(val);
 		return err;
+	}
 
 	mutex_lock(&quirk_mutex);
 
@@ -60,10 +66,11 @@ static int quirks_param_set(const char *val, const struct kernel_param *kp)
 	if (!quirk_list) {
 		quirk_count = 0;
 		mutex_unlock(&quirk_mutex);
+		kfree(val);
 		return -ENOMEM;
 	}
 
-	for (i = 0, p = (char *)val; p && *p;) {
+	for (i = 0, p = val; p && *p;) {
 		/* Each entry consists of VID:PID:flags */
 		field = strsep(&p, ":");
 		if (!field)
@@ -144,6 +151,7 @@ static int quirks_param_set(const char *val, const struct kernel_param *kp)
 
 unlock:
 	mutex_unlock(&quirk_mutex);
+	kfree(val);
 
 	return 0;
 }
@@ -218,11 +226,12 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Logitech HD Webcam C270 */
 	{ USB_DEVICE(0x046d, 0x0825), .driver_info = USB_QUIRK_RESET_RESUME },
 
-	/* Logitech HD Pro Webcams C920, C920-C, C925e and C930e */
+	/* Logitech HD Pro Webcams C920, C920-C, C922, C925e and C930e */
 	{ USB_DEVICE(0x046d, 0x082d), .driver_info = USB_QUIRK_DELAY_INIT },
 	{ USB_DEVICE(0x046d, 0x0841), .driver_info = USB_QUIRK_DELAY_INIT },
 	{ USB_DEVICE(0x046d, 0x0843), .driver_info = USB_QUIRK_DELAY_INIT },
 	{ USB_DEVICE(0x046d, 0x085b), .driver_info = USB_QUIRK_DELAY_INIT },
+	{ USB_DEVICE(0x046d, 0x085c), .driver_info = USB_QUIRK_DELAY_INIT },
 
 	/* Logitech ConferenceCam CC3000e */
 	{ USB_DEVICE(0x046d, 0x0847), .driver_info = USB_QUIRK_DELAY_INIT },
@@ -231,6 +240,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Logitech PTZ Pro Camera */
 	{ USB_DEVICE(0x046d, 0x0853), .driver_info = USB_QUIRK_DELAY_INIT },
 
+	/* Logitech Screen Share */
+	{ USB_DEVICE(0x046d, 0x086c), .driver_info = USB_QUIRK_NO_LPM },
+
 	/* Logitech Quickcam Fusion */
 	{ USB_DEVICE(0x046d, 0x08c1), .driver_info = USB_QUIRK_RESET_RESUME },
 
@@ -354,6 +366,14 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x0904, 0x6103), .driver_info =
 			USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL },
 
+	/* Sound Devices USBPre2 */
+	{ USB_DEVICE(0x0926, 0x0202), .driver_info =
+			USB_QUIRK_ENDPOINT_IGNORE },
+
+	/* Sound Devices MixPre-D */
+	{ USB_DEVICE(0x0926, 0x0208), .driver_info =
+			USB_QUIRK_ENDPOINT_IGNORE },
+
 	/* Keytouch QWERTY Panel keyboard */
 	{ USB_DEVICE(0x0926, 0x3333), .driver_info =
 			USB_QUIRK_CONFIG_INTF_STRINGS },
@@ -371,6 +391,12 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x0b05, 0x17e0), .driver_info =
 			USB_QUIRK_IGNORE_REMOTE_WAKEUP },
 
+	/* Realtek hub in Dell WD19 (Type-C) */
+	{ USB_DEVICE(0x0bda, 0x0487), .driver_info = USB_QUIRK_NO_LPM },
+
+	/* Generic RTL8153 based ethernet adapters */
+	{ USB_DEVICE(0x0bda, 0x8153), .driver_info = USB_QUIRK_NO_LPM },
+
 	/* Action Semiconductor flash disk */
 	{ USB_DEVICE(0x10d6, 0x2200), .driver_info =
 			USB_QUIRK_STRING_FETCH_255 },
@@ -417,6 +443,10 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Corsair K70 LUX */
 	{ USB_DEVICE(0x1b1c, 0x1b36), .driver_info = USB_QUIRK_DELAY_INIT },
 
+	/* Corsair K70 RGB RAPDIFIRE */
+	{ USB_DEVICE(0x1b1c, 0x1b38), .driver_info = USB_QUIRK_DELAY_INIT |
+	  USB_QUIRK_DELAY_CTRL_MSG },
+
 	/* MIDI keyboard WORLDE MINI */
 	{ USB_DEVICE(0x1c75, 0x0204), .driver_info =
 			USB_QUIRK_CONFIG_INTF_STRINGS },
@@ -445,6 +475,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* INTEL VALUE SSD */
 	{ USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* novation SoundControl XL */
+	{ USB_DEVICE(0x1235, 0x0061), .driver_info = USB_QUIRK_RESET_RESUME },
+
 	{ }  /* terminating entry must be last */
 };
 
@@ -472,6 +505,40 @@ static const struct usb_device_id usb_amd_resume_quirk_list[] = {
 	{ }  /* terminating entry must be last */
 };
 
+/*
+ * Entries for endpoints that should be ignored when parsing configuration
+ * descriptors.
+ *
+ * Matched for devices with USB_QUIRK_ENDPOINT_IGNORE.
+ */
+static const struct usb_device_id usb_endpoint_ignore[] = {
+	{ USB_DEVICE_INTERFACE_NUMBER(0x0926, 0x0202, 1), .driver_info = 0x85 },
+	{ USB_DEVICE_INTERFACE_NUMBER(0x0926, 0x0208, 1), .driver_info = 0x85 },
+	{ }
+};
+
+bool usb_endpoint_is_ignored(struct usb_device *udev,
+			     struct usb_host_interface *intf,
+			     struct usb_endpoint_descriptor *epd)
+{
+	const struct usb_device_id *id;
+	unsigned int address;
+
+	for (id = usb_endpoint_ignore; id->match_flags; ++id) {
+		if (!usb_match_device(udev, id))
+			continue;
+
+		if (!usb_match_one_id_intf(udev, intf, id))
+			continue;
+
+		address = id->driver_info;
+		if (address == epd->bEndpointAddress)
+			return true;
+	}
+
+	return false;
+}
+
 static bool usb_match_any_interface(struct usb_device *udev,
 				    const struct usb_device_id *id)
 {
diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h
index d5ac492f441b..642a37653ac7 100644
--- a/drivers/usb/core/usb.h
+++ b/drivers/usb/core/usb.h
@@ -37,6 +37,9 @@ extern void usb_authorize_interface(struct usb_interface *);
 extern void usb_detect_quirks(struct usb_device *udev);
 extern void usb_detect_interface_quirks(struct usb_device *udev);
 extern void usb_release_quirk_list(void);
+extern bool usb_endpoint_is_ignored(struct usb_device *udev,
+		struct usb_host_interface *intf,
+		struct usb_endpoint_descriptor *epd);
 extern int usb_remove_device(struct usb_device *udev);
 
 extern int usb_get_device_descriptor(struct usb_device *dev,
diff --git a/drivers/usb/dwc2/core_intr.c b/drivers/usb/dwc2/core_intr.c
index 6af6add3d4c0..6272b4ae4740 100644
--- a/drivers/usb/dwc2/core_intr.c
+++ b/drivers/usb/dwc2/core_intr.c
@@ -421,10 +421,13 @@ static void dwc2_handle_wakeup_detected_intr(struct dwc2_hsotg *hsotg)
 			if (ret && (ret != -ENOTSUPP))
 				dev_err(hsotg->dev, "exit power_down failed\n");
 
+			/* Change to L0 state */
+			hsotg->lx_state = DWC2_L0;
 			call_gadget(hsotg, resume);
+		} else {
+			/* Change to L0 state */
+			hsotg->lx_state = DWC2_L0;
 		}
-		/* Change to L0 state */
-		hsotg->lx_state = DWC2_L0;
 	} else {
 		if (hsotg->params.power_down)
 			return;
diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c
index bff48a8a1984..322b859ba165 100644
--- a/drivers/usb/dwc2/gadget.c
+++ b/drivers/usb/dwc2/gadget.c
@@ -1083,11 +1083,6 @@ static void dwc2_hsotg_start_req(struct dwc2_hsotg *hsotg,
 	else
 		packets = 1;	/* send one packet if length is zero. */
 
-	if (hs_ep->isochronous && length > (hs_ep->mc * hs_ep->ep.maxpacket)) {
-		dev_err(hsotg->dev, "req length > maxpacket*mc\n");
-		return;
-	}
-
 	if (dir_in && index != 0)
 		if (hs_ep->isochronous)
 			epsize = DXEPTSIZ_MC(packets);
@@ -1391,6 +1386,13 @@ static int dwc2_hsotg_ep_queue(struct usb_ep *ep, struct usb_request *req,
 	req->actual = 0;
 	req->status = -EINPROGRESS;
 
+	/* Don't queue ISOC request if length greater than mps*mc */
+	if (hs_ep->isochronous &&
+	    req->length > (hs_ep->mc * hs_ep->ep.maxpacket)) {
+		dev_err(hs->dev, "req length > maxpacket*mc\n");
+		return -EINVAL;
+	}
+
 	/* In DDMA mode for ISOC's don't queue request if length greater
 	 * than descriptor limits.
 	 */
@@ -1632,6 +1634,7 @@ static int dwc2_hsotg_process_req_status(struct dwc2_hsotg *hsotg,
 	struct dwc2_hsotg_ep *ep0 = hsotg->eps_out[0];
 	struct dwc2_hsotg_ep *ep;
 	__le16 reply;
+	u16 status;
 	int ret;
 
 	dev_dbg(hsotg->dev, "%s: USB_REQ_GET_STATUS\n", __func__);
@@ -1643,11 +1646,10 @@ static int dwc2_hsotg_process_req_status(struct dwc2_hsotg *hsotg,
 
 	switch (ctrl->bRequestType & USB_RECIP_MASK) {
 	case USB_RECIP_DEVICE:
-		/*
-		 * bit 0 => self powered
-		 * bit 1 => remote wakeup
-		 */
-		reply = cpu_to_le16(0);
+		status = 1 << USB_DEVICE_SELF_POWERED;
+		status |= hsotg->remote_wakeup_allowed <<
+			  USB_DEVICE_REMOTE_WAKEUP;
+		reply = cpu_to_le16(status);
 		break;
 
 	case USB_RECIP_INTERFACE:
@@ -1758,7 +1760,10 @@ static int dwc2_hsotg_process_req_feature(struct dwc2_hsotg *hsotg,
 	case USB_RECIP_DEVICE:
 		switch (wValue) {
 		case USB_DEVICE_REMOTE_WAKEUP:
-			hsotg->remote_wakeup_allowed = 1;
+			if (set)
+				hsotg->remote_wakeup_allowed = 1;
+			else
+				hsotg->remote_wakeup_allowed = 0;
 			break;
 
 		case USB_DEVICE_TEST_MODE:
@@ -1768,16 +1773,17 @@ static int dwc2_hsotg_process_req_feature(struct dwc2_hsotg *hsotg,
 				return -EINVAL;
 
 			hsotg->test_mode = wIndex >> 8;
-			ret = dwc2_hsotg_send_reply(hsotg, ep0, NULL, 0);
-			if (ret) {
-				dev_err(hsotg->dev,
-					"%s: failed to send reply\n", __func__);
-				return ret;
-			}
 			break;
 		default:
 			return -ENOENT;
 		}
+
+		ret = dwc2_hsotg_send_reply(hsotg, ep0, NULL, 0);
+		if (ret) {
+			dev_err(hsotg->dev,
+				"%s: failed to send reply\n", __func__);
+			return ret;
+		}
 		break;
 
 	case USB_RECIP_ENDPOINT:
@@ -4055,11 +4061,12 @@ static int dwc2_hsotg_ep_enable(struct usb_ep *ep,
 	 * a unique tx-fifo even if it is non-periodic.
 	 */
 	if (dir_in && hsotg->dedicated_fifos) {
+		unsigned fifo_count = dwc2_hsotg_tx_fifo_count(hsotg);
 		u32 fifo_index = 0;
 		u32 fifo_size = UINT_MAX;
 
 		size = hs_ep->ep.maxpacket * hs_ep->mc;
-		for (i = 1; i < hsotg->num_of_eps; ++i) {
+		for (i = 1; i <= fifo_count; ++i) {
 			if (hsotg->fifo_map & (1 << i))
 				continue;
 			val = dwc2_readl(hsotg, DPTXFSIZN(i));
@@ -4878,12 +4885,6 @@ int dwc2_gadget_init(struct dwc2_hsotg *hsotg)
 					  epnum, 0);
 	}
 
-	ret = usb_add_gadget_udc(dev, &hsotg->gadget);
-	if (ret) {
-		dwc2_hsotg_ep_free_request(&hsotg->eps_out[0]->ep,
-					   hsotg->ctrl_req);
-		return ret;
-	}
 	dwc2_hsotg_dump(hsotg);
 
 	return 0;
diff --git a/drivers/usb/dwc2/params.c b/drivers/usb/dwc2/params.c
index 5949262ff669..55f841a54015 100644
--- a/drivers/usb/dwc2/params.c
+++ b/drivers/usb/dwc2/params.c
@@ -76,6 +76,7 @@ static void dwc2_set_s3c6400_params(struct dwc2_hsotg *hsotg)
 	struct dwc2_core_params *p = &hsotg->params;
 
 	p->power_down = 0;
+	p->phy_utmi_width = 8;
 }
 
 static void dwc2_set_rk_params(struct dwc2_hsotg *hsotg)
diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c
index e98d7812da2d..05a6fb4c2273 100644
--- a/drivers/usb/dwc2/platform.c
+++ b/drivers/usb/dwc2/platform.c
@@ -337,7 +337,8 @@ static void dwc2_driver_shutdown(struct platform_device *dev)
 {
 	struct dwc2_hsotg *hsotg = platform_get_drvdata(dev);
 
-	disable_irq(hsotg->irq);
+	dwc2_disable_global_interrupts(hsotg);
+	synchronize_irq(hsotg->irq);
 }
 
 /**
@@ -497,10 +498,23 @@ static int dwc2_driver_probe(struct platform_device *dev)
 	if (hsotg->dr_mode == USB_DR_MODE_PERIPHERAL)
 		dwc2_lowlevel_hw_disable(hsotg);
 
+#if IS_ENABLED(CONFIG_USB_DWC2_PERIPHERAL) || \
+	IS_ENABLED(CONFIG_USB_DWC2_DUAL_ROLE)
+	/* Postponed adding a new gadget to the udc class driver list */
+	if (hsotg->gadget_enabled) {
+		retval = usb_add_gadget_udc(hsotg->dev, &hsotg->gadget);
+		if (retval) {
+			hsotg->gadget.udc = NULL;
+			dwc2_hsotg_remove(hsotg);
+			goto error;
+		}
+	}
+#endif /* CONFIG_USB_DWC2_PERIPHERAL || CONFIG_USB_DWC2_DUAL_ROLE */
 	return 0;
 
 error:
-	dwc2_lowlevel_hw_disable(hsotg);
+	if (hsotg->dr_mode != USB_DR_MODE_PERIPHERAL)
+		dwc2_lowlevel_hw_disable(hsotg);
 	return retval;
 }
 
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index 2e763fd618b3..c91596efa3e8 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -982,6 +982,9 @@ static int dwc3_core_init(struct dwc3 *dwc)
 		if (dwc->dis_tx_ipgap_linecheck_quirk)
 			reg |= DWC3_GUCTL1_TX_IPGAP_LINECHECK_DIS;
 
+		if (dwc->parkmode_disable_ss_quirk)
+			reg |= DWC3_GUCTL1_PARKMODE_DISABLE_SS;
+
 		dwc3_writel(dwc->regs, DWC3_GUCTL1, reg);
 	}
 
@@ -1200,6 +1203,9 @@ static void dwc3_core_exit_mode(struct dwc3 *dwc)
 		/* do nothing */
 		break;
 	}
+
+	/* de-assert DRVVBUS for HOST and OTG mode */
+	dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE);
 }
 
 static void dwc3_get_properties(struct dwc3 *dwc)
@@ -1289,6 +1295,8 @@ static void dwc3_get_properties(struct dwc3 *dwc)
 				"snps,dis-del-phy-power-chg-quirk");
 	dwc->dis_tx_ipgap_linecheck_quirk = device_property_read_bool(dev,
 				"snps,dis-tx-ipgap-linecheck-quirk");
+	dwc->parkmode_disable_ss_quirk = device_property_read_bool(dev,
+				"snps,parkmode-disable-ss-quirk");
 
 	dwc->tx_de_emphasis_quirk = device_property_read_bool(dev,
 				"snps,tx_de_emphasis_quirk");
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index f19cbeb01087..679c9f25640c 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -249,6 +249,7 @@
 #define DWC3_GUCTL_HSTINAUTORETRY	BIT(14)
 
 /* Global User Control 1 Register */
+#define DWC3_GUCTL1_PARKMODE_DISABLE_SS	BIT(17)
 #define DWC3_GUCTL1_TX_IPGAP_LINECHECK_DIS	BIT(28)
 #define DWC3_GUCTL1_DEV_L1_EXIT_BY_HW	BIT(24)
 
@@ -309,6 +310,10 @@
 #define DWC3_GTXFIFOSIZ_TXFDEF(n)	((n) & 0xffff)
 #define DWC3_GTXFIFOSIZ_TXFSTADDR(n)	((n) & 0xffff0000)
 
+/* Global RX Fifo Size Register */
+#define DWC31_GRXFIFOSIZ_RXFDEP(n)	((n) & 0x7fff)	/* DWC_usb31 only */
+#define DWC3_GRXFIFOSIZ_RXFDEP(n)	((n) & 0xffff)
+
 /* Global Event Size Registers */
 #define DWC3_GEVNTSIZ_INTMASK		BIT(31)
 #define DWC3_GEVNTSIZ_SIZE(n)		((n) & 0xffff)
@@ -690,7 +695,9 @@ struct dwc3_ep {
 #define DWC3_EP_STALL		BIT(1)
 #define DWC3_EP_WEDGE		BIT(2)
 #define DWC3_EP_TRANSFER_STARTED BIT(3)
+#define DWC3_EP_END_TRANSFER_PENDING BIT(4)
 #define DWC3_EP_PENDING_REQUEST	BIT(5)
+#define DWC3_EP_DELAY_START	BIT(6)
 
 	/* This last one is specific to EP0 */
 #define DWC3_EP0_DIR_IN		BIT(31)
@@ -1022,6 +1029,8 @@ struct dwc3_scratchpad_array {
  *			change quirk.
  * @dis_tx_ipgap_linecheck_quirk: set if we disable u2mac linestate
  *			check during HS transmit.
+ * @parkmode_disable_ss_quirk: set if we need to disable all SuperSpeed
+ *			instances in park mode.
  * @tx_de_emphasis_quirk: set if we enable Tx de-emphasis quirk
  * @tx_de_emphasis: Tx de-emphasis value
  * 	0	- -6dB de-emphasis
@@ -1209,6 +1218,7 @@ struct dwc3 {
 	unsigned		dis_u2_freeclk_exists_quirk:1;
 	unsigned		dis_del_phy_power_chg_quirk:1;
 	unsigned		dis_tx_ipgap_linecheck_quirk:1;
+	unsigned		parkmode_disable_ss_quirk:1;
 
 	unsigned		tx_de_emphasis_quirk:1;
 	unsigned		tx_de_emphasis:2;
diff --git a/drivers/usb/dwc3/debug.h b/drivers/usb/dwc3/debug.h
index 068259fdfb0c..9ba137b55664 100644
--- a/drivers/usb/dwc3/debug.h
+++ b/drivers/usb/dwc3/debug.h
@@ -508,86 +508,77 @@ static inline const char *dwc3_ep_event_string(char *str, size_t size,
 	u8 epnum = event->endpoint_number;
 	size_t len;
 	int status;
-	int ret;
 
-	ret = snprintf(str, size, "ep%d%s: ", epnum >> 1,
+	len = scnprintf(str, size, "ep%d%s: ", epnum >> 1,
 			(epnum & 1) ? "in" : "out");
-	if (ret < 0)
-		return "UNKNOWN";
 
 	status = event->status;
 
 	switch (event->endpoint_event) {
 	case DWC3_DEPEVT_XFERCOMPLETE:
-		len = strlen(str);
-		snprintf(str + len, size - len, "Transfer Complete (%c%c%c)",
+		len += scnprintf(str + len, size - len,
+				"Transfer Complete (%c%c%c)",
 				status & DEPEVT_STATUS_SHORT ? 'S' : 's',
 				status & DEPEVT_STATUS_IOC ? 'I' : 'i',
 				status & DEPEVT_STATUS_LST ? 'L' : 'l');
 
-		len = strlen(str);
-
 		if (epnum <= 1)
-			snprintf(str + len, size - len, " [%s]",
+			scnprintf(str + len, size - len, " [%s]",
 					dwc3_ep0_state_string(ep0state));
 		break;
 	case DWC3_DEPEVT_XFERINPROGRESS:
-		len = strlen(str);
-
-		snprintf(str + len, size - len, "Transfer In Progress [%d] (%c%c%c)",
+		scnprintf(str + len, size - len,
+				"Transfer In Progress [%d] (%c%c%c)",
 				event->parameters,
 				status & DEPEVT_STATUS_SHORT ? 'S' : 's',
 				status & DEPEVT_STATUS_IOC ? 'I' : 'i',
 				status & DEPEVT_STATUS_LST ? 'M' : 'm');
 		break;
 	case DWC3_DEPEVT_XFERNOTREADY:
-		len = strlen(str);
-
-		snprintf(str + len, size - len, "Transfer Not Ready [%d]%s",
+		len += scnprintf(str + len, size - len,
+				"Transfer Not Ready [%d]%s",
 				event->parameters,
 				status & DEPEVT_STATUS_TRANSFER_ACTIVE ?
 				" (Active)" : " (Not Active)");
 
-		len = strlen(str);
-
 		/* Control Endpoints */
 		if (epnum <= 1) {
 			int phase = DEPEVT_STATUS_CONTROL_PHASE(event->status);
 
 			switch (phase) {
 			case DEPEVT_STATUS_CONTROL_DATA:
-				snprintf(str + ret, size - ret,
+				scnprintf(str + len, size - len,
 						" [Data Phase]");
 				break;
 			case DEPEVT_STATUS_CONTROL_STATUS:
-				snprintf(str + ret, size - ret,
+				scnprintf(str + len, size - len,
 						" [Status Phase]");
 			}
 		}
 		break;
 	case DWC3_DEPEVT_RXTXFIFOEVT:
-		snprintf(str + ret, size - ret, "FIFO");
+		scnprintf(str + len, size - len, "FIFO");
 		break;
 	case DWC3_DEPEVT_STREAMEVT:
 		status = event->status;
 
 		switch (status) {
 		case DEPEVT_STREAMEVT_FOUND:
-			snprintf(str + ret, size - ret, " Stream %d Found",
+			scnprintf(str + len, size - len, " Stream %d Found",
 					event->parameters);
 			break;
 		case DEPEVT_STREAMEVT_NOTFOUND:
 		default:
-			snprintf(str + ret, size - ret, " Stream Not Found");
+			scnprintf(str + len, size - len, " Stream Not Found");
 			break;
 		}
 
 		break;
 	case DWC3_DEPEVT_EPCMDCMPLT:
-		snprintf(str + ret, size - ret, "Endpoint Command Complete");
+		scnprintf(str + len, size - len, "Endpoint Command Complete");
 		break;
 	default:
-		snprintf(str, size, "UNKNOWN");
+		scnprintf(str + len, size - len, "UNKNOWN");
 	}
 
 	return str;
diff --git a/drivers/usb/dwc3/dwc3-meson-g12a.c b/drivers/usb/dwc3/dwc3-meson-g12a.c
index 2aec31a2eacb..6c6a7a0b0b35 100644
--- a/drivers/usb/dwc3/dwc3-meson-g12a.c
+++ b/drivers/usb/dwc3/dwc3-meson-g12a.c
@@ -538,7 +538,13 @@ static int __maybe_unused dwc3_meson_g12a_runtime_resume(struct device *dev)
 static int __maybe_unused dwc3_meson_g12a_suspend(struct device *dev)
 {
 	struct dwc3_meson_g12a *priv = dev_get_drvdata(dev);
-	int i;
+	int i, ret;
+
+	if (priv->vbus && priv->otg_phy_mode == PHY_MODE_USB_HOST) {
+		ret = regulator_disable(priv->vbus);
+		if (ret)
+			return ret;
+	}
 
 	for (i = 0 ; i < PHY_COUNT ; ++i) {
 		phy_power_off(priv->phys[i]);
@@ -573,6 +579,12 @@ static int __maybe_unused dwc3_meson_g12a_resume(struct device *dev)
 			return ret;
 	}
 
+       if (priv->vbus && priv->otg_phy_mode == PHY_MODE_USB_HOST) {
+               ret = regulator_enable(priv->vbus);
+		if (ret)
+			return ret;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c
index 8fa39e664940..de8e5e971f70 100644
--- a/drivers/usb/dwc3/dwc3-pci.c
+++ b/drivers/usb/dwc3/dwc3-pci.c
@@ -34,7 +34,10 @@
 #define PCI_DEVICE_ID_INTEL_GLK			0x31aa
 #define PCI_DEVICE_ID_INTEL_CNPLP		0x9dee
 #define PCI_DEVICE_ID_INTEL_CNPH		0xa36e
+#define PCI_DEVICE_ID_INTEL_CNPV		0xa3b0
 #define PCI_DEVICE_ID_INTEL_ICLLP		0x34ee
+#define PCI_DEVICE_ID_INTEL_TGPH		0x43ee
+#define PCI_DEVICE_ID_INTEL_JSP			0x4dee
 
 #define PCI_INTEL_BXT_DSM_GUID		"732b85d5-b7a7-4a1b-9ba0-4bbd00ffd511"
 #define PCI_INTEL_BXT_FUNC_PMU_PWR	4
@@ -111,6 +114,7 @@ static const struct property_entry dwc3_pci_intel_properties[] = {
 
 static const struct property_entry dwc3_pci_mrfld_properties[] = {
 	PROPERTY_ENTRY_STRING("dr_mode", "otg"),
+	PROPERTY_ENTRY_STRING("linux,extcon-name", "mrfld_bcove_pwrsrc"),
 	PROPERTY_ENTRY_BOOL("linux,sysdev_is_parent"),
 	{}
 };
@@ -202,8 +206,10 @@ static void dwc3_pci_resume_work(struct work_struct *work)
 	int ret;
 
 	ret = pm_runtime_get_sync(&dwc3->dev);
-	if (ret)
+	if (ret) {
+		pm_runtime_put_sync_autosuspend(&dwc3->dev);
 		return;
+	}
 
 	pm_runtime_mark_last_busy(&dwc3->dev);
 	pm_runtime_put_sync_autosuspend(&dwc3->dev);
@@ -340,9 +346,18 @@ static const struct pci_device_id dwc3_pci_id_table[] = {
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_CNPH),
 	  (kernel_ulong_t) &dwc3_pci_intel_properties, },
 
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_CNPV),
+	  (kernel_ulong_t) &dwc3_pci_intel_properties, },
+
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ICLLP),
 	  (kernel_ulong_t) &dwc3_pci_intel_properties, },
 
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGPH),
+	  (kernel_ulong_t) &dwc3_pci_intel_properties, },
+
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_JSP),
+	  (kernel_ulong_t) &dwc3_pci_intel_properties, },
+
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_NL_USB),
 	  (kernel_ulong_t) &dwc3_pci_amd_properties, },
 	{  }	/* Terminating Entry */
diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c
index 2fb02f877401..e8be2049a416 100644
--- a/drivers/usb/dwc3/ep0.c
+++ b/drivers/usb/dwc3/ep0.c
@@ -1129,8 +1129,10 @@ void dwc3_ep0_interrupt(struct dwc3 *dwc,
 	case DWC3_DEPEVT_EPCMDCMPLT:
 		cmd = DEPEVT_PARAMETER_CMD(event->parameters);
 
-		if (cmd == DWC3_DEPCMD_ENDTRANSFER)
+		if (cmd == DWC3_DEPCMD_ENDTRANSFER) {
+			dep->flags &= ~DWC3_EP_END_TRANSFER_PENDING;
 			dep->flags &= ~DWC3_EP_TRANSFER_STARTED;
+		}
 		break;
 	}
 }
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 9239b117751d..7a28048faa3e 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -1068,7 +1068,14 @@ static void dwc3_prepare_one_trb_sg(struct dwc3_ep *dep,
 		unsigned int rem = length % maxp;
 		unsigned chain = true;
 
-		if (sg_is_last(s))
+		/*
+		 * IOMMU driver is coalescing the list of sgs which shares a
+		 * page boundary into one and giving it to USB driver. With
+		 * this the number of sgs mapped is not equal to the number of
+		 * sgs passed. So mark the chain bit to false if it isthe last
+		 * mapped sg.
+		 */
+		if (i == remaining - 1)
 			chain = false;
 
 		if (rem && usb_endpoint_dir_out(dep->endpoint.desc) && !chain) {
@@ -1210,6 +1217,8 @@ static void dwc3_prepare_trbs(struct dwc3_ep *dep)
 	}
 }
 
+static void dwc3_gadget_ep_cleanup_cancelled_requests(struct dwc3_ep *dep);
+
 static int __dwc3_gadget_kick_transfer(struct dwc3_ep *dep)
 {
 	struct dwc3_gadget_ep_cmd_params params;
@@ -1249,14 +1258,20 @@ static int __dwc3_gadget_kick_transfer(struct dwc3_ep *dep)
 
 	ret = dwc3_send_gadget_ep_cmd(dep, cmd, &params);
 	if (ret < 0) {
-		/*
-		 * FIXME we need to iterate over the list of requests
-		 * here and stop, unmap, free and del each of the linked
-		 * requests instead of what we do now.
-		 */
-		if (req->trb)
-			memset(req->trb, 0, sizeof(struct dwc3_trb));
-		dwc3_gadget_del_and_unmap_request(dep, req, ret);
+		struct dwc3_request *tmp;
+
+		if (ret == -EAGAIN)
+			return ret;
+
+		dwc3_stop_active_transfer(dep, true, true);
+
+		list_for_each_entry_safe(req, tmp, &dep->started_list, list)
+			dwc3_gadget_move_cancelled_request(req);
+
+		/* If ep isn't started, then there's no end transfer pending */
+		if (!(dep->flags & DWC3_EP_END_TRANSFER_PENDING))
+			dwc3_gadget_ep_cleanup_cancelled_requests(dep);
+
 		return ret;
 	}
 
@@ -1447,6 +1462,12 @@ static int __dwc3_gadget_ep_queue(struct dwc3_ep *dep, struct dwc3_request *req)
 	list_add_tail(&req->list, &dep->pending_list);
 	req->status = DWC3_REQUEST_STATUS_QUEUED;
 
+	/* Start the transfer only after the END_TRANSFER is completed */
+	if (dep->flags & DWC3_EP_END_TRANSFER_PENDING) {
+		dep->flags |= DWC3_EP_DELAY_START;
+		return 0;
+	}
+
 	/*
 	 * NOTICE: Isochronous endpoints should NEVER be prestarted. We must
 	 * wait for a XferNotReady event so we will know what's the current
@@ -1492,6 +1513,10 @@ static void dwc3_gadget_ep_skip_trbs(struct dwc3_ep *dep, struct dwc3_request *r
 {
 	int i;
 
+	/* If req->trb is not set, then the request has not started */
+	if (!req->trb)
+		return;
+
 	/*
 	 * If request was already started, this means we had to
 	 * stop the transfer. With that we also need to ignore
@@ -1505,7 +1530,7 @@ static void dwc3_gadget_ep_skip_trbs(struct dwc3_ep *dep, struct dwc3_request *r
 	for (i = 0; i < req->num_trbs; i++) {
 		struct dwc3_trb *trb;
 
-		trb = req->trb + i;
+		trb = &dep->trb_pool[dep->trb_dequeue];
 		trb->ctrl &= ~DWC3_TRB_CTRL_HWO;
 		dwc3_ep_inc_deq(dep);
 	}
@@ -1582,6 +1607,8 @@ int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol)
 {
 	struct dwc3_gadget_ep_cmd_params	params;
 	struct dwc3				*dwc = dep->dwc;
+	struct dwc3_request			*req;
+	struct dwc3_request			*tmp;
 	int					ret;
 
 	if (usb_endpoint_xfer_isoc(dep->endpoint.desc)) {
@@ -1618,13 +1645,37 @@ int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol)
 		else
 			dep->flags |= DWC3_EP_STALL;
 	} else {
+		/*
+		 * Don't issue CLEAR_STALL command to control endpoints. The
+		 * controller automatically clears the STALL when it receives
+		 * the SETUP token.
+		 */
+		if (dep->number <= 1) {
+			dep->flags &= ~(DWC3_EP_STALL | DWC3_EP_WEDGE);
+			return 0;
+		}
 
 		ret = dwc3_send_clear_stall_ep_cmd(dep);
-		if (ret)
+		if (ret) {
 			dev_err(dwc->dev, "failed to clear STALL on %s\n",
 					dep->name);
-		else
-			dep->flags &= ~(DWC3_EP_STALL | DWC3_EP_WEDGE);
+			return ret;
+		}
+
+		dep->flags &= ~(DWC3_EP_STALL | DWC3_EP_WEDGE);
+
+		dwc3_stop_active_transfer(dep, true, true);
+
+		list_for_each_entry_safe(req, tmp, &dep->started_list, list)
+			dwc3_gadget_move_cancelled_request(req);
+
+		list_for_each_entry_safe(req, tmp, &dep->pending_list, list)
+			dwc3_gadget_move_cancelled_request(req);
+
+		if (!(dep->flags & DWC3_EP_END_TRANSFER_PENDING)) {
+			dep->flags &= ~DWC3_EP_DELAY_START;
+			dwc3_gadget_ep_cleanup_cancelled_requests(dep);
+		}
 	}
 
 	return ret;
@@ -1712,7 +1763,6 @@ static int __dwc3_gadget_wakeup(struct dwc3 *dwc)
 	u32			reg;
 
 	u8			link_state;
-	u8			speed;
 
 	/*
 	 * According to the Databook Remote wakeup request should
@@ -1722,16 +1772,13 @@ static int __dwc3_gadget_wakeup(struct dwc3 *dwc)
 	 */
 	reg = dwc3_readl(dwc->regs, DWC3_DSTS);
 
-	speed = reg & DWC3_DSTS_CONNECTSPD;
-	if ((speed == DWC3_DSTS_SUPERSPEED) ||
-	    (speed == DWC3_DSTS_SUPERSPEED_PLUS))
-		return 0;
-
 	link_state = DWC3_DSTS_USBLNKST(reg);
 
 	switch (link_state) {
+	case DWC3_LINK_STATE_RESET:
 	case DWC3_LINK_STATE_RX_DET:	/* in HS, means Early Suspend */
 	case DWC3_LINK_STATE_U3:	/* in HS, means SUSPEND */
+	case DWC3_LINK_STATE_RESUME:
 		break;
 	default:
 		return -EINVAL;
@@ -2171,7 +2218,6 @@ static int dwc3_gadget_init_in_endpoint(struct dwc3_ep *dep)
 {
 	struct dwc3 *dwc = dep->dwc;
 	int mdwidth;
-	int kbytes;
 	int size;
 
 	mdwidth = DWC3_MDWIDTH(dwc->hwparams.hwparams0);
@@ -2187,17 +2233,17 @@ static int dwc3_gadget_init_in_endpoint(struct dwc3_ep *dep)
 	/* FIFO Depth is in MDWDITH bytes. Multiply */
 	size *= mdwidth;
 
-	kbytes = size / 1024;
-	if (kbytes == 0)
-		kbytes = 1;
-
 	/*
-	 * FIFO sizes account an extra MDWIDTH * (kbytes + 1) bytes for
-	 * internal overhead. We don't really know how these are used,
-	 * but documentation say it exists.
+	 * To meet performance requirement, a minimum TxFIFO size of 3x
+	 * MaxPacketSize is recommended for endpoints that support burst and a
+	 * minimum TxFIFO size of 2x MaxPacketSize for endpoints that don't
+	 * support burst. Use those numbers and we can calculate the max packet
+	 * limit as below.
 	 */
-	size -= mdwidth * (kbytes + 1);
-	size /= kbytes;
+	if (dwc->maximum_speed >= USB_SPEED_SUPER)
+		size /= 3;
+	else
+		size /= 2;
 
 	usb_ep_set_maxpacket_limit(&dep->endpoint, size);
 
@@ -2215,8 +2261,39 @@ static int dwc3_gadget_init_in_endpoint(struct dwc3_ep *dep)
 static int dwc3_gadget_init_out_endpoint(struct dwc3_ep *dep)
 {
 	struct dwc3 *dwc = dep->dwc;
+	int mdwidth;
+	int size;
+
+	mdwidth = DWC3_MDWIDTH(dwc->hwparams.hwparams0);
+
+	/* MDWIDTH is represented in bits, convert to bytes */
+	mdwidth /= 8;
 
-	usb_ep_set_maxpacket_limit(&dep->endpoint, 1024);
+	/* All OUT endpoints share a single RxFIFO space */
+	size = dwc3_readl(dwc->regs, DWC3_GRXFIFOSIZ(0));
+	if (dwc3_is_usb31(dwc))
+		size = DWC31_GRXFIFOSIZ_RXFDEP(size);
+	else
+		size = DWC3_GRXFIFOSIZ_RXFDEP(size);
+
+	/* FIFO depth is in MDWDITH bytes */
+	size *= mdwidth;
+
+	/*
+	 * To meet performance requirement, a minimum recommended RxFIFO size
+	 * is defined as follow:
+	 * RxFIFO size >= (3 x MaxPacketSize) +
+	 * (3 x 8 bytes setup packets size) + (16 bytes clock crossing margin)
+	 *
+	 * Then calculate the max packet limit as below.
+	 */
+	size -= (3 * 8) + 16;
+	if (size < 0)
+		size = 0;
+	else
+		size /= 3;
+
+	usb_ep_set_maxpacket_limit(&dep->endpoint, size);
 	dep->endpoint.max_streams = 15;
 	dep->endpoint.ops = &dwc3_gadget_ep_ops;
 	list_add_tail(&dep->endpoint.ep_list,
@@ -2382,7 +2459,8 @@ static int dwc3_gadget_ep_reclaim_completed_trb(struct dwc3_ep *dep,
 	if (event->status & DEPEVT_STATUS_SHORT && !chain)
 		return 1;
 
-	if (event->status & DEPEVT_STATUS_IOC)
+	if ((trb->ctrl & DWC3_TRB_CTRL_IOC) ||
+	    (trb->ctrl & DWC3_TRB_CTRL_LST))
 		return 1;
 
 	return 0;
@@ -2402,9 +2480,6 @@ static int dwc3_gadget_ep_reclaim_trb_sg(struct dwc3_ep *dep,
 	for_each_sg(sg, s, pending, i) {
 		trb = &dep->trb_pool[dep->trb_dequeue];
 
-		if (trb->ctrl & DWC3_TRB_CTRL_HWO)
-			break;
-
 		req->sg = sg_next(s);
 		req->num_pending_sgs--;
 
@@ -2429,7 +2504,7 @@ static int dwc3_gadget_ep_reclaim_trb_linear(struct dwc3_ep *dep,
 
 static bool dwc3_gadget_ep_request_completed(struct dwc3_request *req)
 {
-	return req->request.actual == req->request.length;
+	return req->num_pending_sgs == 0;
 }
 
 static int dwc3_gadget_ep_cleanup_completed_request(struct dwc3_ep *dep,
@@ -2453,8 +2528,7 @@ static int dwc3_gadget_ep_cleanup_completed_request(struct dwc3_ep *dep,
 
 	req->request.actual = req->request.length - req->remaining;
 
-	if (!dwc3_gadget_ep_request_completed(req) ||
-			req->num_pending_sgs) {
+	if (!dwc3_gadget_ep_request_completed(req)) {
 		__dwc3_gadget_kick_transfer(dep);
 		goto out;
 	}
@@ -2508,10 +2582,8 @@ static void dwc3_gadget_endpoint_transfer_in_progress(struct dwc3_ep *dep,
 
 	dwc3_gadget_ep_cleanup_completed_requests(dep, event, status);
 
-	if (stop) {
+	if (stop)
 		dwc3_stop_active_transfer(dep, true, true);
-		dep->flags = DWC3_EP_ENABLED;
-	}
 
 	/*
 	 * WORKAROUND: This is the 2nd half of U1/U2 -> U0 workaround.
@@ -2580,8 +2652,14 @@ static void dwc3_endpoint_interrupt(struct dwc3 *dwc,
 		cmd = DEPEVT_PARAMETER_CMD(event->parameters);
 
 		if (cmd == DWC3_DEPCMD_ENDTRANSFER) {
+			dep->flags &= ~DWC3_EP_END_TRANSFER_PENDING;
 			dep->flags &= ~DWC3_EP_TRANSFER_STARTED;
 			dwc3_gadget_ep_cleanup_cancelled_requests(dep);
+			if ((dep->flags & DWC3_EP_DELAY_START) &&
+			    !usb_endpoint_xfer_isoc(dep->endpoint.desc))
+				__dwc3_gadget_kick_transfer(dep);
+
+			dep->flags &= ~DWC3_EP_DELAY_START;
 		}
 		break;
 	case DWC3_DEPEVT_STREAMEVT:
@@ -2638,7 +2716,8 @@ static void dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force,
 	u32 cmd;
 	int ret;
 
-	if (!(dep->flags & DWC3_EP_TRANSFER_STARTED))
+	if (!(dep->flags & DWC3_EP_TRANSFER_STARTED) ||
+	    (dep->flags & DWC3_EP_END_TRANSFER_PENDING))
 		return;
 
 	/*
@@ -2683,6 +2762,8 @@ static void dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force,
 
 	if (!interrupt)
 		dep->flags &= ~DWC3_EP_TRANSFER_STARTED;
+	else
+		dep->flags |= DWC3_EP_END_TRANSFER_PENDING;
 
 	if (dwc3_is_usb31(dwc) || dwc->revision < DWC3_REVISION_310A)
 		udelay(100);
diff --git a/drivers/usb/dwc3/host.c b/drivers/usb/dwc3/host.c
index f55947294f7c..4252fad1d184 100644
--- a/drivers/usb/dwc3/host.c
+++ b/drivers/usb/dwc3/host.c
@@ -91,10 +91,10 @@ int dwc3_host_init(struct dwc3 *dwc)
 	memset(props, 0, sizeof(struct property_entry) * ARRAY_SIZE(props));
 
 	if (dwc->usb3_lpm_capable)
-		props[prop_idx++].name = "usb3-lpm-capable";
+		props[prop_idx++] = PROPERTY_ENTRY_BOOL("usb3-lpm-capable");
 
 	if (dwc->usb2_lpm_disable)
-		props[prop_idx++].name = "usb2-lpm-disable";
+		props[prop_idx++] = PROPERTY_ENTRY_BOOL("usb2-lpm-disable");
 
 	/**
 	 * WORKAROUND: dwc3 revisions <=3.00a have a limitation
@@ -106,7 +106,7 @@ int dwc3_host_init(struct dwc3 *dwc)
 	 * This following flag tells XHCI to do just that.
 	 */
 	if (dwc->revision <= DWC3_REVISION_300A)
-		props[prop_idx++].name = "quirk-broken-port-ped";
+		props[prop_idx++] = PROPERTY_ENTRY_BOOL("quirk-broken-port-ped");
 
 	if (prop_idx) {
 		ret = platform_device_add_properties(xhci, props);
diff --git a/drivers/usb/early/xhci-dbc.c b/drivers/usb/early/xhci-dbc.c
index cac991173ac0..5a462a1d1896 100644
--- a/drivers/usb/early/xhci-dbc.c
+++ b/drivers/usb/early/xhci-dbc.c
@@ -728,19 +728,19 @@ static void xdbc_handle_tx_event(struct xdbc_trb *evt_trb)
 	case COMP_USB_TRANSACTION_ERROR:
 	case COMP_STALL_ERROR:
 	default:
-		if (ep_id == XDBC_EPID_OUT)
+		if (ep_id == XDBC_EPID_OUT || ep_id == XDBC_EPID_OUT_INTEL)
 			xdbc.flags |= XDBC_FLAGS_OUT_STALL;
-		if (ep_id == XDBC_EPID_IN)
+		if (ep_id == XDBC_EPID_IN || ep_id == XDBC_EPID_IN_INTEL)
 			xdbc.flags |= XDBC_FLAGS_IN_STALL;
 
 		xdbc_trace("endpoint %d stalled\n", ep_id);
 		break;
 	}
 
-	if (ep_id == XDBC_EPID_IN) {
+	if (ep_id == XDBC_EPID_IN || ep_id == XDBC_EPID_IN_INTEL) {
 		xdbc.flags &= ~XDBC_FLAGS_IN_PROCESS;
 		xdbc_bulk_transfer(NULL, XDBC_MAX_PACKET, true);
-	} else if (ep_id == XDBC_EPID_OUT) {
+	} else if (ep_id == XDBC_EPID_OUT || ep_id == XDBC_EPID_OUT_INTEL) {
 		xdbc.flags &= ~XDBC_FLAGS_OUT_PROCESS;
 	} else {
 		xdbc_trace("invalid endpoint id %d\n", ep_id);
diff --git a/drivers/usb/early/xhci-dbc.h b/drivers/usb/early/xhci-dbc.h
index 673686eeddd7..6e2b7266a695 100644
--- a/drivers/usb/early/xhci-dbc.h
+++ b/drivers/usb/early/xhci-dbc.h
@@ -120,8 +120,22 @@ struct xdbc_ring {
 	u32			cycle_state;
 };
 
-#define XDBC_EPID_OUT		2
-#define XDBC_EPID_IN		3
+/*
+ * These are the "Endpoint ID" (also known as "Context Index") values for the
+ * OUT Transfer Ring and the IN Transfer Ring of a Debug Capability Context data
+ * structure.
+ * According to the "eXtensible Host Controller Interface for Universal Serial
+ * Bus (xHCI)" specification, section "7.6.3.2 Endpoint Contexts and Transfer
+ * Rings", these should be 0 and 1, and those are the values AMD machines give
+ * you; but Intel machines seem to use the formula from section "4.5.1 Device
+ * Context Index", which is supposed to be used for the Device Context only.
+ * Luckily the values from Intel don't overlap with those from AMD, so we can
+ * just test for both.
+ */
+#define XDBC_EPID_OUT		0
+#define XDBC_EPID_IN		1
+#define XDBC_EPID_OUT_INTEL	2
+#define XDBC_EPID_IN_INTEL	3
 
 struct xdbc_state {
 	u16			vendor;
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 33115e19756c..40b3ed93596a 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -96,40 +96,43 @@ function_descriptors(struct usb_function *f,
 }
 
 /**
- * next_ep_desc() - advance to the next EP descriptor
+ * next_desc() - advance to the next desc_type descriptor
  * @t: currect pointer within descriptor array
+ * @desc_type: descriptor type
  *
- * Return: next EP descriptor or NULL
+ * Return: next desc_type descriptor or NULL
  *
- * Iterate over @t until either EP descriptor found or
+ * Iterate over @t until either desc_type descriptor found or
  * NULL (that indicates end of list) encountered
  */
 static struct usb_descriptor_header**
-next_ep_desc(struct usb_descriptor_header **t)
+next_desc(struct usb_descriptor_header **t, u8 desc_type)
 {
 	for (; *t; t++) {
-		if ((*t)->bDescriptorType == USB_DT_ENDPOINT)
+		if ((*t)->bDescriptorType == desc_type)
 			return t;
 	}
 	return NULL;
 }
 
 /*
- * for_each_ep_desc()- iterate over endpoint descriptors in the
- *		descriptors list
- * @start:	pointer within descriptor array.
- * @ep_desc:	endpoint descriptor to use as the loop cursor
+ * for_each_desc() - iterate over desc_type descriptors in the
+ * descriptors list
+ * @start: pointer within descriptor array.
+ * @iter_desc: desc_type descriptor to use as the loop cursor
+ * @desc_type: wanted descriptr type
  */
-#define for_each_ep_desc(start, ep_desc) \
-	for (ep_desc = next_ep_desc(start); \
-	      ep_desc; ep_desc = next_ep_desc(ep_desc+1))
+#define for_each_desc(start, iter_desc, desc_type) \
+	for (iter_desc = next_desc(start, desc_type); \
+	     iter_desc; iter_desc = next_desc(iter_desc + 1, desc_type))
 
 /**
- * config_ep_by_speed() - configures the given endpoint
+ * config_ep_by_speed_and_alt() - configures the given endpoint
  * according to gadget speed.
  * @g: pointer to the gadget
  * @f: usb function
  * @_ep: the endpoint to configure
+ * @alt: alternate setting number
  *
  * Return: error code, 0 on success
  *
@@ -142,11 +145,13 @@ next_ep_desc(struct usb_descriptor_header **t)
  * Note: the supplied function should hold all the descriptors
  * for supported speeds
  */
-int config_ep_by_speed(struct usb_gadget *g,
-			struct usb_function *f,
-			struct usb_ep *_ep)
+int config_ep_by_speed_and_alt(struct usb_gadget *g,
+				struct usb_function *f,
+				struct usb_ep *_ep,
+				u8 alt)
 {
 	struct usb_endpoint_descriptor *chosen_desc = NULL;
+	struct usb_interface_descriptor *int_desc = NULL;
 	struct usb_descriptor_header **speed_desc = NULL;
 
 	struct usb_ss_ep_comp_descriptor *comp_desc = NULL;
@@ -182,8 +187,21 @@ int config_ep_by_speed(struct usb_gadget *g,
 	default:
 		speed_desc = f->fs_descriptors;
 	}
+
+	/* find correct alternate setting descriptor */
+	for_each_desc(speed_desc, d_spd, USB_DT_INTERFACE) {
+		int_desc = (struct usb_interface_descriptor *)*d_spd;
+
+		if (int_desc->bAlternateSetting == alt) {
+			speed_desc = d_spd;
+			goto intf_found;
+		}
+	}
+	return -EIO;
+
+intf_found:
 	/* find descriptors */
-	for_each_ep_desc(speed_desc, d_spd) {
+	for_each_desc(speed_desc, d_spd, USB_DT_ENDPOINT) {
 		chosen_desc = (struct usb_endpoint_descriptor *)*d_spd;
 		if (chosen_desc->bEndpointAddress == _ep->address)
 			goto ep_found;
@@ -237,6 +255,32 @@ ep_found:
 	}
 	return 0;
 }
+EXPORT_SYMBOL_GPL(config_ep_by_speed_and_alt);
+
+/**
+ * config_ep_by_speed() - configures the given endpoint
+ * according to gadget speed.
+ * @g: pointer to the gadget
+ * @f: usb function
+ * @_ep: the endpoint to configure
+ *
+ * Return: error code, 0 on success
+ *
+ * This function chooses the right descriptors for a given
+ * endpoint according to gadget speed and saves it in the
+ * endpoint desc field. If the endpoint already has a descriptor
+ * assigned to it - overwrites it with currently corresponding
+ * descriptor. The endpoint maxpacket field is updated according
+ * to the chosen descriptor.
+ * Note: the supplied function should hold all the descriptors
+ * for supported speeds
+ */
+int config_ep_by_speed(struct usb_gadget *g,
+			struct usb_function *f,
+			struct usb_ep *_ep)
+{
+	return config_ep_by_speed_and_alt(g, f, _ep, 0);
+}
 EXPORT_SYMBOL_GPL(config_ep_by_speed);
 
 /**
@@ -437,12 +481,14 @@ static u8 encode_bMaxPower(enum usb_device_speed speed,
 		val = CONFIG_USB_GADGET_VBUS_DRAW;
 	if (!val)
 		return 0;
-	switch (speed) {
-	case USB_SPEED_SUPER:
-		return DIV_ROUND_UP(val, 8);
-	default:
-		return DIV_ROUND_UP(val, 2);
-	}
+	if (speed < USB_SPEED_SUPER)
+		return min(val, 500U) / 2;
+	else
+		/*
+		 * USB 3.x supports up to 900mA, but since 900 isn't divisible
+		 * by 8 the integral division will effectively cap to 896mA.
+		 */
+		return min(val, 900U) / 8;
 }
 
 static int config_buf(struct usb_configuration *config,
@@ -840,7 +886,16 @@ static int set_config(struct usb_composite_dev *cdev,
 
 	/* when we return, be sure our power usage is valid */
 	power = c->MaxPower ? c->MaxPower : CONFIG_USB_GADGET_VBUS_DRAW;
+	if (gadget->speed < USB_SPEED_SUPER)
+		power = min(power, 500U);
+	else
+		power = min(power, 900U);
 done:
+	if (power <= USB_SELF_POWER_VBUS_MAX_DRAW)
+		usb_gadget_set_selfpowered(gadget);
+	else
+		usb_gadget_clear_selfpowered(gadget);
+
 	usb_gadget_vbus_draw(gadget, power);
 	if (result >= 0 && cdev->delayed_status)
 		result = USB_GADGET_DELAYED_STATUS;
@@ -2259,6 +2314,7 @@ void composite_suspend(struct usb_gadget *gadget)
 
 	cdev->suspended = 1;
 
+	usb_gadget_set_selfpowered(gadget);
 	usb_gadget_vbus_draw(gadget, 2);
 }
 
@@ -2266,7 +2322,7 @@ void composite_resume(struct usb_gadget *gadget)
 {
 	struct usb_composite_dev	*cdev = get_gadget_data(gadget);
 	struct usb_function		*f;
-	u16				maxpower;
+	unsigned			maxpower;
 
 	/* REVISIT:  should we have config level
 	 * suspend/resume callbacks?
@@ -2280,10 +2336,17 @@ void composite_resume(struct usb_gadget *gadget)
 				f->resume(f);
 		}
 
-		maxpower = cdev->config->MaxPower;
+		maxpower = cdev->config->MaxPower ?
+			cdev->config->MaxPower : CONFIG_USB_GADGET_VBUS_DRAW;
+		if (gadget->speed < USB_SPEED_SUPER)
+			maxpower = min(maxpower, 500U);
+		else
+			maxpower = min(maxpower, 900U);
+
+		if (maxpower > USB_SELF_POWER_VBUS_MAX_DRAW)
+			usb_gadget_clear_selfpowered(gadget);
 
-		usb_gadget_vbus_draw(gadget, maxpower ?
-			maxpower : CONFIG_USB_GADGET_VBUS_DRAW);
+		usb_gadget_vbus_draw(gadget, maxpower);
 	}
 
 	cdev->suspended = 0;
diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c
index ab9ac48a751a..a7709d126b29 100644
--- a/drivers/usb/gadget/configfs.c
+++ b/drivers/usb/gadget/configfs.c
@@ -260,6 +260,9 @@ static ssize_t gadget_dev_desc_UDC_store(struct config_item *item,
 	char *name;
 	int ret;
 
+	if (strlen(page) < len)
+		return -EOVERFLOW;
+
 	name = kstrdup(page, GFP_KERNEL);
 	if (!name)
 		return -ENOMEM;
diff --git a/drivers/usb/gadget/function/f_ecm.c b/drivers/usb/gadget/function/f_ecm.c
index 6ce044008cf6..7f5cf488b2b1 100644
--- a/drivers/usb/gadget/function/f_ecm.c
+++ b/drivers/usb/gadget/function/f_ecm.c
@@ -52,6 +52,7 @@ struct f_ecm {
 	struct usb_ep			*notify;
 	struct usb_request		*notify_req;
 	u8				notify_state;
+	atomic_t			notify_count;
 	bool				is_open;
 
 	/* FIXME is_open needs some irq-ish locking
@@ -380,7 +381,7 @@ static void ecm_do_notify(struct f_ecm *ecm)
 	int				status;
 
 	/* notification already in flight? */
-	if (!req)
+	if (atomic_read(&ecm->notify_count))
 		return;
 
 	event = req->buf;
@@ -420,10 +421,10 @@ static void ecm_do_notify(struct f_ecm *ecm)
 	event->bmRequestType = 0xA1;
 	event->wIndex = cpu_to_le16(ecm->ctrl_id);
 
-	ecm->notify_req = NULL;
+	atomic_inc(&ecm->notify_count);
 	status = usb_ep_queue(ecm->notify, req, GFP_ATOMIC);
 	if (status < 0) {
-		ecm->notify_req = req;
+		atomic_dec(&ecm->notify_count);
 		DBG(cdev, "notify --> %d\n", status);
 	}
 }
@@ -448,17 +449,19 @@ static void ecm_notify_complete(struct usb_ep *ep, struct usb_request *req)
 	switch (req->status) {
 	case 0:
 		/* no fault */
+		atomic_dec(&ecm->notify_count);
 		break;
 	case -ECONNRESET:
 	case -ESHUTDOWN:
+		atomic_set(&ecm->notify_count, 0);
 		ecm->notify_state = ECM_NOTIFY_NONE;
 		break;
 	default:
 		DBG(cdev, "event %02x --> %d\n",
 			event->bNotificationType, req->status);
+		atomic_dec(&ecm->notify_count);
 		break;
 	}
-	ecm->notify_req = req;
 	ecm_do_notify(ecm);
 }
 
@@ -621,8 +624,12 @@ static void ecm_disable(struct usb_function *f)
 
 	DBG(cdev, "ecm deactivated\n");
 
-	if (ecm->port.in_ep->enabled)
+	if (ecm->port.in_ep->enabled) {
 		gether_disconnect(&ecm->port);
+	} else {
+		ecm->port.in_ep->desc = NULL;
+		ecm->port.out_ep->desc = NULL;
+	}
 
 	usb_ep_disable(ecm->notify);
 	ecm->notify->desc = NULL;
@@ -903,6 +910,11 @@ static void ecm_unbind(struct usb_configuration *c, struct usb_function *f)
 
 	usb_free_all_descriptors(f);
 
+	if (atomic_read(&ecm->notify_count)) {
+		usb_ep_dequeue(ecm->notify, ecm->notify_req);
+		atomic_set(&ecm->notify_count, 0);
+	}
+
 	kfree(ecm->notify_req->buf);
 	usb_ep_free_request(ecm->notify, ecm->notify_req);
 }
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 213ff03c8a9f..74410d42c6a7 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -1061,6 +1061,7 @@ static ssize_t ffs_epfile_io(struct file *file, struct ffs_io_data *io_data)
 			req->num_sgs = io_data->sgt.nents;
 		} else {
 			req->buf = data;
+			req->num_sgs = 0;
 		}
 		req->length = data_len;
 
@@ -1104,6 +1105,7 @@ static ssize_t ffs_epfile_io(struct file *file, struct ffs_io_data *io_data)
 			req->num_sgs = io_data->sgt.nents;
 		} else {
 			req->buf = data;
+			req->num_sgs = 0;
 		}
 		req->length = data_len;
 
@@ -1117,6 +1119,7 @@ static ssize_t ffs_epfile_io(struct file *file, struct ffs_io_data *io_data)
 
 		ret = usb_ep_queue(ep->ep, req, GFP_ATOMIC);
 		if (unlikely(ret)) {
+			io_data->req = NULL;
 			usb_ep_free_request(ep->ep, req);
 			goto error_lock;
 		}
@@ -1159,18 +1162,19 @@ static int ffs_aio_cancel(struct kiocb *kiocb)
 {
 	struct ffs_io_data *io_data = kiocb->private;
 	struct ffs_epfile *epfile = kiocb->ki_filp->private_data;
+	unsigned long flags;
 	int value;
 
 	ENTER();
 
-	spin_lock_irq(&epfile->ffs->eps_lock);
+	spin_lock_irqsave(&epfile->ffs->eps_lock, flags);
 
 	if (likely(io_data && io_data->ep && io_data->req))
 		value = usb_ep_dequeue(io_data->ep, io_data->req);
 	else
 		value = -EINVAL;
 
-	spin_unlock_irq(&epfile->ffs->eps_lock);
+	spin_unlock_irqrestore(&epfile->ffs->eps_lock, flags);
 
 	return value;
 }
@@ -1817,6 +1821,10 @@ static void ffs_data_reset(struct ffs_data *ffs)
 	ffs->state = FFS_READ_DESCRIPTORS;
 	ffs->setup_state = FFS_NO_SETUP;
 	ffs->flags = 0;
+
+	ffs->ms_os_descs_ext_prop_count = 0;
+	ffs->ms_os_descs_ext_prop_name_len = 0;
+	ffs->ms_os_descs_ext_prop_data_len = 0;
 }
 
 
diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c
index f2bc8d037067..492f0d70510f 100644
--- a/drivers/usb/gadget/function/f_mass_storage.c
+++ b/drivers/usb/gadget/function/f_mass_storage.c
@@ -216,6 +216,7 @@
 #include <linux/freezer.h>
 #include <linux/module.h>
 #include <linux/uaccess.h>
+#include <asm/unaligned.h>
 
 #include <linux/usb/ch9.h>
 #include <linux/usb/gadget.h>
diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index 2d6e76e4cffa..1d900081b1f0 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -53,6 +53,7 @@ struct f_ncm {
 	struct usb_ep			*notify;
 	struct usb_request		*notify_req;
 	u8				notify_state;
+	atomic_t			notify_count;
 	bool				is_open;
 
 	const struct ndp_parser_opts	*parser_opts;
@@ -547,7 +548,7 @@ static void ncm_do_notify(struct f_ncm *ncm)
 	int				status;
 
 	/* notification already in flight? */
-	if (!req)
+	if (atomic_read(&ncm->notify_count))
 		return;
 
 	event = req->buf;
@@ -587,7 +588,8 @@ static void ncm_do_notify(struct f_ncm *ncm)
 	event->bmRequestType = 0xA1;
 	event->wIndex = cpu_to_le16(ncm->ctrl_id);
 
-	ncm->notify_req = NULL;
+	atomic_inc(&ncm->notify_count);
+
 	/*
 	 * In double buffering if there is a space in FIFO,
 	 * completion callback can be called right after the call,
@@ -597,7 +599,7 @@ static void ncm_do_notify(struct f_ncm *ncm)
 	status = usb_ep_queue(ncm->notify, req, GFP_ATOMIC);
 	spin_lock(&ncm->lock);
 	if (status < 0) {
-		ncm->notify_req = req;
+		atomic_dec(&ncm->notify_count);
 		DBG(cdev, "notify --> %d\n", status);
 	}
 }
@@ -632,17 +634,19 @@ static void ncm_notify_complete(struct usb_ep *ep, struct usb_request *req)
 	case 0:
 		VDBG(cdev, "Notification %02x sent\n",
 		     event->bNotificationType);
+		atomic_dec(&ncm->notify_count);
 		break;
 	case -ECONNRESET:
 	case -ESHUTDOWN:
+		atomic_set(&ncm->notify_count, 0);
 		ncm->notify_state = NCM_NOTIFY_NONE;
 		break;
 	default:
 		DBG(cdev, "event %02x --> %d\n",
 			event->bNotificationType, req->status);
+		atomic_dec(&ncm->notify_count);
 		break;
 	}
-	ncm->notify_req = req;
 	ncm_do_notify(ncm);
 	spin_unlock(&ncm->lock);
 }
@@ -1649,6 +1653,11 @@ static void ncm_unbind(struct usb_configuration *c, struct usb_function *f)
 	ncm_string_defs[0].id = 0;
 	usb_free_all_descriptors(f);
 
+	if (atomic_read(&ncm->notify_count)) {
+		usb_ep_dequeue(ncm->notify, ncm->notify_req);
+		atomic_set(&ncm->notify_count, 0);
+	}
+
 	kfree(ncm->notify_req->buf);
 	usb_ep_free_request(ncm->notify, ncm->notify_req);
 }
diff --git a/drivers/usb/gadget/function/f_rndis.c b/drivers/usb/gadget/function/f_rndis.c
index d48df36622b7..0d8e4a364ca6 100644
--- a/drivers/usb/gadget/function/f_rndis.c
+++ b/drivers/usb/gadget/function/f_rndis.c
@@ -618,6 +618,7 @@ static void rndis_disable(struct usb_function *f)
 	gether_disconnect(&rndis->port);
 
 	usb_ep_disable(rndis->notify);
+	rndis->notify->desc = NULL;
 }
 
 /*-------------------------------------------------------------------------*/
diff --git a/drivers/usb/gadget/function/f_uac1_legacy.c b/drivers/usb/gadget/function/f_uac1_legacy.c
index 6677ae932de0..06ee6e901808 100644
--- a/drivers/usb/gadget/function/f_uac1_legacy.c
+++ b/drivers/usb/gadget/function/f_uac1_legacy.c
@@ -336,7 +336,9 @@ static int f_audio_out_ep_complete(struct usb_ep *ep, struct usb_request *req)
 
 	/* Copy buffer is full, add it to the play_queue */
 	if (audio_buf_size - copy_buf->actual < req->actual) {
+		spin_lock_irq(&audio->lock);
 		list_add_tail(&copy_buf->list, &audio->play_queue);
+		spin_unlock_irq(&audio->lock);
 		schedule_work(&audio->playback_work);
 		copy_buf = f_audio_buffer_alloc(audio_buf_size);
 		if (IS_ERR(copy_buf))
diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c
index db2d4980cb35..3633df6d7610 100644
--- a/drivers/usb/gadget/function/f_uac2.c
+++ b/drivers/usb/gadget/function/f_uac2.c
@@ -215,10 +215,7 @@ static struct uac2_ac_header_descriptor ac_hdr_desc = {
 	.bDescriptorSubtype = UAC_MS_HEADER,
 	.bcdADC = cpu_to_le16(0x200),
 	.bCategory = UAC2_FUNCTION_IO_BOX,
-	.wTotalLength = cpu_to_le16(sizeof in_clk_src_desc
-			+ sizeof out_clk_src_desc + sizeof usb_out_it_desc
-			+ sizeof io_in_it_desc + sizeof usb_in_ot_desc
-			+ sizeof io_out_ot_desc),
+	/* .wTotalLength = DYNAMIC */
 	.bmControls = 0,
 };
 
@@ -501,7 +498,7 @@ static void setup_descriptor(struct f_uac2_opts *opts)
 	as_in_hdr_desc.bTerminalLink = usb_in_ot_desc.bTerminalID;
 
 	iad_desc.bInterfaceCount = 1;
-	ac_hdr_desc.wTotalLength = 0;
+	ac_hdr_desc.wTotalLength = cpu_to_le16(sizeof(ac_hdr_desc));
 
 	if (EPIN_EN(opts)) {
 		u16 len = le16_to_cpu(ac_hdr_desc.wTotalLength);
diff --git a/drivers/usb/gadget/function/storage_common.h b/drivers/usb/gadget/function/storage_common.h
index e5e3a2553aaa..bdeb1e233fc9 100644
--- a/drivers/usb/gadget/function/storage_common.h
+++ b/drivers/usb/gadget/function/storage_common.h
@@ -172,11 +172,6 @@ enum data_direction {
 	DATA_DIR_NONE
 };
 
-static inline u32 get_unaligned_be24(u8 *buf)
-{
-	return 0xffffff & (u32) get_unaligned_be32(buf - 1);
-}
-
 static inline struct fsg_lun *fsg_lun_from_dev(struct device *dev)
 {
 	return container_of(dev, struct fsg_lun, dev);
diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c
index bb1e2e1d0076..038c445a4e9b 100644
--- a/drivers/usb/gadget/function/u_serial.c
+++ b/drivers/usb/gadget/function/u_serial.c
@@ -560,8 +560,10 @@ static int gs_start_io(struct gs_port *port)
 	port->n_read = 0;
 	started = gs_start_rx(port);
 
-	/* unblock any pending writes into our circular buffer */
 	if (started) {
+		gs_start_tx(port);
+		/* Unblock any pending writes into our circular buffer, in case
+		 * we didn't in gs_start_tx() */
 		tty_wakeup(port->port.tty);
 	} else {
 		gs_free_requests(ep, head, &port->read_allocated);
diff --git a/drivers/usb/gadget/legacy/audio.c b/drivers/usb/gadget/legacy/audio.c
index dd81fd538cb8..a748ed0842e8 100644
--- a/drivers/usb/gadget/legacy/audio.c
+++ b/drivers/usb/gadget/legacy/audio.c
@@ -300,8 +300,10 @@ static int audio_bind(struct usb_composite_dev *cdev)
 		struct usb_descriptor_header *usb_desc;
 
 		usb_desc = usb_otg_descriptor_alloc(cdev->gadget);
-		if (!usb_desc)
+		if (!usb_desc) {
+			status = -ENOMEM;
 			goto fail;
+		}
 		usb_otg_descriptor_init(cdev->gadget, usb_desc);
 		otg_desc[0] = usb_desc;
 		otg_desc[1] = NULL;
diff --git a/drivers/usb/gadget/legacy/cdc2.c b/drivers/usb/gadget/legacy/cdc2.c
index da1c37933ca1..563363aba48f 100644
--- a/drivers/usb/gadget/legacy/cdc2.c
+++ b/drivers/usb/gadget/legacy/cdc2.c
@@ -179,8 +179,10 @@ static int cdc_bind(struct usb_composite_dev *cdev)
 		struct usb_descriptor_header *usb_desc;
 
 		usb_desc = usb_otg_descriptor_alloc(gadget);
-		if (!usb_desc)
+		if (!usb_desc) {
+			status = -ENOMEM;
 			goto fail1;
+		}
 		usb_otg_descriptor_init(gadget, usb_desc);
 		otg_desc[0] = usb_desc;
 		otg_desc[1] = NULL;
@@ -225,7 +227,7 @@ static struct usb_composite_driver cdc_driver = {
 	.name		= "g_cdc",
 	.dev		= &device_desc,
 	.strings	= dev_strings,
-	.max_speed	= USB_SPEED_HIGH,
+	.max_speed	= USB_SPEED_SUPER,
 	.bind		= cdc_bind,
 	.unbind		= cdc_unbind,
 };
diff --git a/drivers/usb/gadget/legacy/g_ffs.c b/drivers/usb/gadget/legacy/g_ffs.c
index b640ed3fcf70..ae6d8f7092b8 100644
--- a/drivers/usb/gadget/legacy/g_ffs.c
+++ b/drivers/usb/gadget/legacy/g_ffs.c
@@ -149,7 +149,7 @@ static struct usb_composite_driver gfs_driver = {
 	.name		= DRIVER_NAME,
 	.dev		= &gfs_dev_desc,
 	.strings	= gfs_dev_strings,
-	.max_speed	= USB_SPEED_HIGH,
+	.max_speed	= USB_SPEED_SUPER,
 	.bind		= gfs_bind,
 	.unbind		= gfs_unbind,
 };
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index 249277d0e53f..1df9e9427c12 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -1360,7 +1360,6 @@ gadgetfs_setup (struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl)
 
 	req->buf = dev->rbuf;
 	req->context = NULL;
-	value = -EOPNOTSUPP;
 	switch (ctrl->bRequest) {
 
 	case USB_REQ_GET_DESCRIPTOR:
@@ -1783,7 +1782,7 @@ static ssize_t
 dev_config (struct file *fd, const char __user *buf, size_t len, loff_t *ptr)
 {
 	struct dev_data		*dev = fd->private_data;
-	ssize_t			value = len, length = len;
+	ssize_t			value, length = len;
 	unsigned		total;
 	u32			tag;
 	char			*kbuf;
diff --git a/drivers/usb/gadget/legacy/multi.c b/drivers/usb/gadget/legacy/multi.c
index 50515f9e1022..ec9749845660 100644
--- a/drivers/usb/gadget/legacy/multi.c
+++ b/drivers/usb/gadget/legacy/multi.c
@@ -482,7 +482,7 @@ static struct usb_composite_driver multi_driver = {
 	.name		= "g_multi",
 	.dev		= &device_desc,
 	.strings	= dev_strings,
-	.max_speed	= USB_SPEED_HIGH,
+	.max_speed	= USB_SPEED_SUPER,
 	.bind		= multi_bind,
 	.unbind		= multi_unbind,
 	.needs_serial	= 1,
diff --git a/drivers/usb/gadget/legacy/ncm.c b/drivers/usb/gadget/legacy/ncm.c
index 8465f081e921..0f1b45e3abd1 100644
--- a/drivers/usb/gadget/legacy/ncm.c
+++ b/drivers/usb/gadget/legacy/ncm.c
@@ -156,8 +156,10 @@ static int gncm_bind(struct usb_composite_dev *cdev)
 		struct usb_descriptor_header *usb_desc;
 
 		usb_desc = usb_otg_descriptor_alloc(gadget);
-		if (!usb_desc)
+		if (!usb_desc) {
+			status = -ENOMEM;
 			goto fail;
+		}
 		usb_otg_descriptor_init(gadget, usb_desc);
 		otg_desc[0] = usb_desc;
 		otg_desc[1] = NULL;
@@ -197,7 +199,7 @@ static struct usb_composite_driver ncm_driver = {
 	.name		= "g_ncm",
 	.dev		= &device_desc,
 	.strings	= dev_strings,
-	.max_speed	= USB_SPEED_HIGH,
+	.max_speed	= USB_SPEED_SUPER,
 	.bind		= gncm_bind,
 	.unbind		= gncm_unbind,
 };
diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c
index 761e8a808857..2d969b7185d4 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.c
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.c
@@ -869,7 +869,7 @@ static int usba_ep_dequeue(struct usb_ep *_ep, struct usb_request *_req)
 	u32 status;
 
 	DBG(DBG_GADGET | DBG_QUEUE, "ep_dequeue: %s, req %p\n",
-			ep->ep.name, req);
+			ep->ep.name, _req);
 
 	spin_lock_irqsave(&udc->lock, flags);
 
@@ -1949,10 +1949,10 @@ static irqreturn_t usba_vbus_irq_thread(int irq, void *devid)
 			usba_start(udc);
 		} else {
 			udc->suspended = false;
-			usba_stop(udc);
-
 			if (udc->driver->disconnect)
 				udc->driver->disconnect(&udc->gadget);
+
+			usba_stop(udc);
 		}
 		udc->vbus_prev = vbus;
 	}
diff --git a/drivers/usb/gadget/udc/bdc/bdc_core.c b/drivers/usb/gadget/udc/bdc/bdc_core.c
index ccbd1d34eb2a..b157a7abd39f 100644
--- a/drivers/usb/gadget/udc/bdc/bdc_core.c
+++ b/drivers/usb/gadget/udc/bdc/bdc_core.c
@@ -282,6 +282,7 @@ static void bdc_mem_init(struct bdc *bdc, bool reinit)
 	 * in that case reinit is passed as 1
 	 */
 	if (reinit) {
+		int i;
 		/* Enable interrupts */
 		temp = bdc_readl(bdc->regs, BDC_BDCSC);
 		temp |= BDC_GIE;
@@ -291,6 +292,9 @@ static void bdc_mem_init(struct bdc *bdc, bool reinit)
 		/* Initialize SRR to 0 */
 		memset(bdc->srr.sr_bds, 0,
 					NUM_SR_ENTRIES * sizeof(struct bdc_bd));
+		/* clear ep flags to avoid post disconnect stops/deconfigs */
+		for (i = 1; i < bdc->num_eps; ++i)
+			bdc->bdc_ep_array[i]->flags = 0;
 	} else {
 		/* One time initiaization only */
 		/* Enable status report function pointers */
@@ -603,9 +607,14 @@ static int bdc_remove(struct platform_device *pdev)
 static int bdc_suspend(struct device *dev)
 {
 	struct bdc *bdc = dev_get_drvdata(dev);
+	int ret;
 
-	clk_disable_unprepare(bdc->clk);
-	return 0;
+	/* Halt the controller */
+	ret = bdc_stop(bdc);
+	if (!ret)
+		clk_disable_unprepare(bdc->clk);
+
+	return ret;
 }
 
 static int bdc_resume(struct device *dev)
diff --git a/drivers/usb/gadget/udc/bdc/bdc_ep.c b/drivers/usb/gadget/udc/bdc/bdc_ep.c
index a4d9b5e1e50e..9ddc0b4e92c9 100644
--- a/drivers/usb/gadget/udc/bdc/bdc_ep.c
+++ b/drivers/usb/gadget/udc/bdc/bdc_ep.c
@@ -540,7 +540,7 @@ static void bdc_req_complete(struct bdc_ep *ep, struct bdc_req *req,
 {
 	struct bdc *bdc = ep->bdc;
 
-	if (req == NULL  || &req->queue == NULL || &req->usb_req == NULL)
+	if (req == NULL)
 		return;
 
 	dev_dbg(bdc->dev, "%s ep:%s status:%d\n", __func__, ep->name, status);
@@ -615,7 +615,6 @@ int bdc_ep_enable(struct bdc_ep *ep)
 	}
 	bdc_dbg_bd_list(bdc, ep);
 	/* only for ep0: config ep is called for ep0 from connect event */
-	ep->flags |= BDC_EP_ENABLED;
 	if (ep->ep_num == 1)
 		return ret;
 
@@ -759,10 +758,13 @@ static int ep_dequeue(struct bdc_ep *ep, struct bdc_req *req)
 					__func__, ep->name, start_bdi, end_bdi);
 	dev_dbg(bdc->dev, "ep_dequeue ep=%p ep->desc=%p\n",
 						ep, (void *)ep->usb_ep.desc);
-	/* Stop the ep to see where the HW is ? */
-	ret = bdc_stop_ep(bdc, ep->ep_num);
-	/* if there is an issue with stopping ep, then no need to go further */
-	if (ret)
+	/* if still connected, stop the ep to see where the HW is ? */
+	if (!(bdc_readl(bdc->regs, BDC_USPC) & BDC_PST_MASK)) {
+		ret = bdc_stop_ep(bdc, ep->ep_num);
+		/* if there is an issue, then no need to go further */
+		if (ret)
+			return 0;
+	} else
 		return 0;
 
 	/*
@@ -1911,7 +1913,9 @@ static int bdc_gadget_ep_disable(struct usb_ep *_ep)
 		__func__, ep->name, ep->flags);
 
 	if (!(ep->flags & BDC_EP_ENABLED)) {
-		dev_warn(bdc->dev, "%s is already disabled\n", ep->name);
+		if (bdc->gadget.speed != USB_SPEED_UNKNOWN)
+			dev_warn(bdc->dev, "%s is already disabled\n",
+				 ep->name);
 		return 0;
 	}
 	spin_lock_irqsave(&bdc->lock, flags);
diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c
index 51fa614b4079..0e7820158aaa 100644
--- a/drivers/usb/gadget/udc/core.c
+++ b/drivers/usb/gadget/udc/core.c
@@ -1297,6 +1297,8 @@ static void usb_gadget_remove_driver(struct usb_udc *udc)
 	kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE);
 
 	usb_gadget_disconnect(udc->gadget);
+	if (udc->gadget->irq)
+		synchronize_irq(udc->gadget->irq);
 	udc->driver->unbind(udc->gadget);
 	usb_gadget_udc_stop(udc);
 
diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c
index 3d499d93c083..4b726f669b53 100644
--- a/drivers/usb/gadget/udc/dummy_hcd.c
+++ b/drivers/usb/gadget/udc/dummy_hcd.c
@@ -1321,7 +1321,7 @@ static int dummy_perform_transfer(struct urb *urb, struct dummy_request *req,
 	u32 this_sg;
 	bool next_sg;
 
-	to_host = usb_pipein(urb->pipe);
+	to_host = usb_urb_dir_in(urb);
 	rbuf = req->req.buf + req->req.actual;
 
 	if (!urb->num_sgs) {
@@ -1409,7 +1409,7 @@ top:
 
 		/* FIXME update emulated data toggle too */
 
-		to_host = usb_pipein(urb->pipe);
+		to_host = usb_urb_dir_in(urb);
 		if (unlikely(len == 0))
 			is_short = 1;
 		else {
@@ -1830,7 +1830,7 @@ restart:
 
 		/* find the gadget's ep for this request (if configured) */
 		address = usb_pipeendpoint (urb->pipe);
-		if (usb_pipein(urb->pipe))
+		if (usb_urb_dir_in(urb))
 			address |= USB_DIR_IN;
 		ep = find_endpoint(dum, address);
 		if (!ep) {
@@ -2385,7 +2385,7 @@ static inline ssize_t show_urb(char *buf, size_t size, struct urb *urb)
 			s = "?";
 			break;
 		 } s; }),
-		ep, ep ? (usb_pipein(urb->pipe) ? "in" : "out") : "",
+		ep, ep ? (usb_urb_dir_in(urb) ? "in" : "out") : "",
 		({ char *s; \
 		switch (usb_pipetype(urb->pipe)) { \
 		case PIPE_CONTROL: \
diff --git a/drivers/usb/gadget/udc/gr_udc.c b/drivers/usb/gadget/udc/gr_udc.c
index 729e60e49564..e0b2fb33ed0d 100644
--- a/drivers/usb/gadget/udc/gr_udc.c
+++ b/drivers/usb/gadget/udc/gr_udc.c
@@ -1980,9 +1980,12 @@ static int gr_ep_init(struct gr_udc *dev, int num, int is_in, u32 maxplimit)
 
 	if (num == 0) {
 		_req = gr_alloc_request(&ep->ep, GFP_ATOMIC);
+		if (!_req)
+			return -ENOMEM;
+
 		buf = devm_kzalloc(dev->dev, PAGE_SIZE, GFP_DMA | GFP_ATOMIC);
-		if (!_req || !buf) {
-			/* possible _req freed by gr_probe via gr_remove */
+		if (!buf) {
+			gr_free_request(&ep->ep, _req);
 			return -ENOMEM;
 		}
 
@@ -2180,8 +2183,6 @@ static int gr_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
-	spin_lock(&dev->lock);
-
 	/* Inside lock so that no gadget can use this udc until probe is done */
 	retval = usb_add_gadget_udc(dev->dev, &dev->gadget);
 	if (retval) {
@@ -2190,15 +2191,21 @@ static int gr_probe(struct platform_device *pdev)
 	}
 	dev->added = 1;
 
+	spin_lock(&dev->lock);
+
 	retval = gr_udc_init(dev);
-	if (retval)
+	if (retval) {
+		spin_unlock(&dev->lock);
 		goto out;
-
-	gr_dfs_create(dev);
+	}
 
 	/* Clear all interrupt enables that might be left on since last boot */
 	gr_disable_interrupts_and_pullup(dev);
 
+	spin_unlock(&dev->lock);
+
+	gr_dfs_create(dev);
+
 	retval = gr_request_irq(dev, dev->irq);
 	if (retval) {
 		dev_err(dev->dev, "Failed to request irq %d\n", dev->irq);
@@ -2227,8 +2234,6 @@ static int gr_probe(struct platform_device *pdev)
 		dev_info(dev->dev, "regs: %p, irq %d\n", dev->regs, dev->irq);
 
 out:
-	spin_unlock(&dev->lock);
-
 	if (retval)
 		gr_remove(pdev);
 
diff --git a/drivers/usb/gadget/udc/lpc32xx_udc.c b/drivers/usb/gadget/udc/lpc32xx_udc.c
index 36b7dd7bebf6..69f5b32ead28 100644
--- a/drivers/usb/gadget/udc/lpc32xx_udc.c
+++ b/drivers/usb/gadget/udc/lpc32xx_udc.c
@@ -1617,17 +1617,17 @@ static int lpc32xx_ep_enable(struct usb_ep *_ep,
 			     const struct usb_endpoint_descriptor *desc)
 {
 	struct lpc32xx_ep *ep = container_of(_ep, struct lpc32xx_ep, ep);
-	struct lpc32xx_udc *udc = ep->udc;
+	struct lpc32xx_udc *udc;
 	u16 maxpacket;
 	u32 tmp;
 	unsigned long flags;
 
 	/* Verify EP data */
 	if ((!_ep) || (!ep) || (!desc) ||
-	    (desc->bDescriptorType != USB_DT_ENDPOINT)) {
-		dev_dbg(udc->dev, "bad ep or descriptor\n");
+	    (desc->bDescriptorType != USB_DT_ENDPOINT))
 		return -EINVAL;
-	}
+
+	udc = ep->udc;
 	maxpacket = usb_endpoint_maxp(desc);
 	if ((maxpacket == 0) || (maxpacket > ep->maxpacket)) {
 		dev_dbg(udc->dev, "bad ep descriptor's packet size\n");
@@ -1875,7 +1875,7 @@ static int lpc32xx_ep_dequeue(struct usb_ep *_ep, struct usb_request *_req)
 static int lpc32xx_ep_set_halt(struct usb_ep *_ep, int value)
 {
 	struct lpc32xx_ep *ep = container_of(_ep, struct lpc32xx_ep, ep);
-	struct lpc32xx_udc *udc = ep->udc;
+	struct lpc32xx_udc *udc;
 	unsigned long flags;
 
 	if ((!ep) || (ep->hwep_num <= 1))
@@ -1885,6 +1885,7 @@ static int lpc32xx_ep_set_halt(struct usb_ep *_ep, int value)
 	if (ep->is_in)
 		return -EAGAIN;
 
+	udc = ep->udc;
 	spin_lock_irqsave(&udc->lock, flags);
 
 	if (value == 1) {
diff --git a/drivers/usb/gadget/udc/m66592-udc.c b/drivers/usb/gadget/udc/m66592-udc.c
index a8288df6aadf..ea59b56e5402 100644
--- a/drivers/usb/gadget/udc/m66592-udc.c
+++ b/drivers/usb/gadget/udc/m66592-udc.c
@@ -1667,7 +1667,7 @@ static int m66592_probe(struct platform_device *pdev)
 
 err_add_udc:
 	m66592_free_request(&m66592->ep[0].ep, m66592->ep0_req);
-
+	m66592->ep0_req = NULL;
 clean_up3:
 	if (m66592->pdata->on_chip) {
 		clk_disable(m66592->clk);
diff --git a/drivers/usb/gadget/udc/mv_udc_core.c b/drivers/usb/gadget/udc/mv_udc_core.c
index cafde053788b..80a1b52c656e 100644
--- a/drivers/usb/gadget/udc/mv_udc_core.c
+++ b/drivers/usb/gadget/udc/mv_udc_core.c
@@ -2313,7 +2313,8 @@ static int mv_udc_probe(struct platform_device *pdev)
 	return 0;
 
 err_create_workqueue:
-	destroy_workqueue(udc->qwork);
+	if (udc->qwork)
+		destroy_workqueue(udc->qwork);
 err_destroy_dma:
 	dma_pool_destroy(udc->dtd_pool);
 err_free_dma:
diff --git a/drivers/usb/gadget/udc/net2272.c b/drivers/usb/gadget/udc/net2272.c
index 564aeee1a1fe..286354e741f3 100644
--- a/drivers/usb/gadget/udc/net2272.c
+++ b/drivers/usb/gadget/udc/net2272.c
@@ -2652,6 +2652,8 @@ net2272_plat_probe(struct platform_device *pdev)
  err_req:
 	release_mem_region(base, len);
  err:
+	kfree(dev);
+
 	return ret;
 }
 
diff --git a/drivers/usb/gadget/udc/net2280.c b/drivers/usb/gadget/udc/net2280.c
index b6bbe2e448ba..19de7392e17f 100644
--- a/drivers/usb/gadget/udc/net2280.c
+++ b/drivers/usb/gadget/udc/net2280.c
@@ -3778,8 +3778,10 @@ static int net2280_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	return 0;
 
 done:
-	if (dev)
+	if (dev) {
 		net2280_remove(pdev);
+		kfree(dev);
+	}
 	return retval;
 }
 
diff --git a/drivers/usb/gadget/udc/s3c2410_udc.c b/drivers/usb/gadget/udc/s3c2410_udc.c
index af3e63316ace..a8adc234def3 100644
--- a/drivers/usb/gadget/udc/s3c2410_udc.c
+++ b/drivers/usb/gadget/udc/s3c2410_udc.c
@@ -251,10 +251,6 @@ static void s3c2410_udc_done(struct s3c2410_ep *ep,
 static void s3c2410_udc_nuke(struct s3c2410_udc *udc,
 		struct s3c2410_ep *ep, int status)
 {
-	/* Sanity check */
-	if (&ep->queue == NULL)
-		return;
-
 	while (!list_empty(&ep->queue)) {
 		struct s3c2410_request *req;
 		req = list_entry(ep->queue.next, struct s3c2410_request,
diff --git a/drivers/usb/host/ehci-exynos.c b/drivers/usb/host/ehci-exynos.c
index 8e3bab1e0c1f..f433883ca2bf 100644
--- a/drivers/usb/host/ehci-exynos.c
+++ b/drivers/usb/host/ehci-exynos.c
@@ -188,9 +188,8 @@ static int exynos_ehci_probe(struct platform_device *pdev)
 	hcd->rsrc_len = resource_size(res);
 
 	irq = platform_get_irq(pdev, 0);
-	if (!irq) {
-		dev_err(&pdev->dev, "Failed to get IRQ\n");
-		err = -ENODEV;
+	if (irq < 0) {
+		err = irq;
 		goto fail_io;
 	}
 
diff --git a/drivers/usb/host/ehci-mxc.c b/drivers/usb/host/ehci-mxc.c
index c9f91e6c72b6..7f65c86047dd 100644
--- a/drivers/usb/host/ehci-mxc.c
+++ b/drivers/usb/host/ehci-mxc.c
@@ -50,6 +50,8 @@ static int ehci_mxc_drv_probe(struct platform_device *pdev)
 	}
 
 	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
 
 	hcd = usb_create_hcd(&ehci_mxc_hc_driver, dev, dev_name(dev));
 	if (!hcd)
diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c
index fe9422d3bcdc..fcfad5c298a9 100644
--- a/drivers/usb/host/ehci-pci.c
+++ b/drivers/usb/host/ehci-pci.c
@@ -216,6 +216,13 @@ static int ehci_pci_setup(struct usb_hcd *hcd)
 		ehci_info(ehci, "applying MosChip frame-index workaround\n");
 		ehci->frame_index_bug = 1;
 		break;
+	case PCI_VENDOR_ID_HUAWEI:
+		/* Synopsys HC bug */
+		if (pdev->device == 0xa239) {
+			ehci_info(ehci, "applying Synopsys HC workaround\n");
+			ehci->has_synopsys_hc_bug = 1;
+		}
+		break;
 	}
 
 	/* optional debug port, normally in the first BAR */
diff --git a/drivers/usb/host/ehci-platform.c b/drivers/usb/host/ehci-platform.c
index 4c306fb6b069..8a45362155c5 100644
--- a/drivers/usb/host/ehci-platform.c
+++ b/drivers/usb/host/ehci-platform.c
@@ -29,6 +29,8 @@
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/reset.h>
+#include <linux/sys_soc.h>
+#include <linux/timer.h>
 #include <linux/usb.h>
 #include <linux/usb/hcd.h>
 #include <linux/usb/ehci_pdriver.h>
@@ -44,6 +46,9 @@ struct ehci_platform_priv {
 	struct clk *clks[EHCI_MAX_CLKS];
 	struct reset_control *rsts;
 	bool reset_on_resume;
+	bool quirk_poll;
+	struct timer_list poll_timer;
+	struct delayed_work poll_work;
 };
 
 static const char hcd_name[] = "ehci-platform";
@@ -118,6 +123,111 @@ static struct usb_ehci_pdata ehci_platform_defaults = {
 	.power_off =		ehci_platform_power_off,
 };
 
+/**
+ * quirk_poll_check_port_status - Poll port_status if the device sticks
+ * @ehci: the ehci hcd pointer
+ *
+ * Since EHCI/OHCI controllers on R-Car Gen3 SoCs are possible to be getting
+ * stuck very rarely after a full/low usb device was disconnected. To
+ * detect such a situation, the controllers require a special way which poll
+ * the EHCI PORTSC register.
+ *
+ * Return: true if the controller's port_status indicated getting stuck
+ */
+static bool quirk_poll_check_port_status(struct ehci_hcd *ehci)
+{
+	u32 port_status = ehci_readl(ehci, &ehci->regs->port_status[0]);
+
+	if (!(port_status & PORT_OWNER) &&
+	     (port_status & PORT_POWER) &&
+	    !(port_status & PORT_CONNECT) &&
+	     (port_status & PORT_LS_MASK))
+		return true;
+
+	return false;
+}
+
+/**
+ * quirk_poll_rebind_companion - rebind comanion device to recover
+ * @ehci: the ehci hcd pointer
+ *
+ * Since EHCI/OHCI controllers on R-Car Gen3 SoCs are possible to be getting
+ * stuck very rarely after a full/low usb device was disconnected. To
+ * recover from such a situation, the controllers require changing the OHCI
+ * functional state.
+ */
+static void quirk_poll_rebind_companion(struct ehci_hcd *ehci)
+{
+	struct device *companion_dev;
+	struct usb_hcd *hcd = ehci_to_hcd(ehci);
+
+	companion_dev = usb_of_get_companion_dev(hcd->self.controller);
+	if (!companion_dev)
+		return;
+
+	device_release_driver(companion_dev);
+	if (device_attach(companion_dev) < 0)
+		ehci_err(ehci, "%s: failed\n", __func__);
+
+	put_device(companion_dev);
+}
+
+static void quirk_poll_work(struct work_struct *work)
+{
+	struct ehci_platform_priv *priv =
+		container_of(to_delayed_work(work), struct ehci_platform_priv,
+			     poll_work);
+	struct ehci_hcd *ehci = container_of((void *)priv, struct ehci_hcd,
+					     priv);
+
+	/* check the status twice to reduce misdetection rate */
+	if (!quirk_poll_check_port_status(ehci))
+		return;
+	udelay(10);
+	if (!quirk_poll_check_port_status(ehci))
+		return;
+
+	ehci_dbg(ehci, "%s: detected getting stuck. rebind now!\n", __func__);
+	quirk_poll_rebind_companion(ehci);
+}
+
+static void quirk_poll_timer(struct timer_list *t)
+{
+	struct ehci_platform_priv *priv = from_timer(priv, t, poll_timer);
+	struct ehci_hcd *ehci = container_of((void *)priv, struct ehci_hcd,
+					     priv);
+
+	if (quirk_poll_check_port_status(ehci)) {
+		/*
+		 * Now scheduling the work for testing the port more. Note that
+		 * updating the status is possible to be delayed when
+		 * reconnection. So, this uses delayed work with 5 ms delay
+		 * to avoid misdetection.
+		 */
+		schedule_delayed_work(&priv->poll_work, msecs_to_jiffies(5));
+	}
+
+	mod_timer(&priv->poll_timer, jiffies + HZ);
+}
+
+static void quirk_poll_init(struct ehci_platform_priv *priv)
+{
+	INIT_DELAYED_WORK(&priv->poll_work, quirk_poll_work);
+	timer_setup(&priv->poll_timer, quirk_poll_timer, 0);
+	mod_timer(&priv->poll_timer, jiffies + HZ);
+}
+
+static void quirk_poll_end(struct ehci_platform_priv *priv)
+{
+	del_timer_sync(&priv->poll_timer);
+	cancel_delayed_work(&priv->poll_work);
+}
+
+static const struct soc_device_attribute quirk_poll_match[] = {
+	{ .family = "R-Car Gen3" },
+	{ /* sentinel*/ }
+};
+
 static int ehci_platform_probe(struct platform_device *dev)
 {
 	struct usb_hcd *hcd;
@@ -178,6 +288,9 @@ static int ehci_platform_probe(struct platform_device *dev)
 					  "has-transaction-translator"))
 			hcd->has_tt = 1;
 
+		if (soc_device_match(quirk_poll_match))
+			priv->quirk_poll = true;
+
 		for (clk = 0; clk < EHCI_MAX_CLKS; clk++) {
 			priv->clks[clk] = of_clk_get(dev->dev.of_node, clk);
 			if (IS_ERR(priv->clks[clk])) {
@@ -249,6 +362,9 @@ static int ehci_platform_probe(struct platform_device *dev)
 	device_enable_async_suspend(hcd->self.controller);
 	platform_set_drvdata(dev, hcd);
 
+	if (priv->quirk_poll)
+		quirk_poll_init(priv);
+
 	return err;
 
 err_power:
@@ -275,6 +391,9 @@ static int ehci_platform_remove(struct platform_device *dev)
 	struct ehci_platform_priv *priv = hcd_to_ehci_priv(hcd);
 	int clk;
 
+	if (priv->quirk_poll)
+		quirk_poll_end(priv);
+
 	usb_remove_hcd(hcd);
 
 	if (pdata->power_off)
@@ -299,9 +418,13 @@ static int ehci_platform_suspend(struct device *dev)
 	struct usb_hcd *hcd = dev_get_drvdata(dev);
 	struct usb_ehci_pdata *pdata = dev_get_platdata(dev);
 	struct platform_device *pdev = to_platform_device(dev);
+	struct ehci_platform_priv *priv = hcd_to_ehci_priv(hcd);
 	bool do_wakeup = device_may_wakeup(dev);
 	int ret;
 
+	if (priv->quirk_poll)
+		quirk_poll_end(priv);
+
 	ret = ehci_suspend(hcd, do_wakeup);
 	if (ret)
 		return ret;
@@ -333,6 +456,10 @@ static int ehci_platform_resume(struct device *dev)
 	}
 
 	ehci_resume(hcd, priv->reset_on_resume);
+
+	if (priv->quirk_poll)
+		quirk_poll_init(priv);
+
 	return 0;
 }
 #endif /* CONFIG_PM_SLEEP */
diff --git a/drivers/usb/host/ohci-da8xx.c b/drivers/usb/host/ohci-da8xx.c
index 38183ac438c6..1371b0c249ec 100644
--- a/drivers/usb/host/ohci-da8xx.c
+++ b/drivers/usb/host/ohci-da8xx.c
@@ -415,13 +415,17 @@ static int ohci_da8xx_probe(struct platform_device *pdev)
 	}
 
 	da8xx_ohci->oc_gpio = devm_gpiod_get_optional(dev, "oc", GPIOD_IN);
-	if (IS_ERR(da8xx_ohci->oc_gpio))
+	if (IS_ERR(da8xx_ohci->oc_gpio)) {
+		error = PTR_ERR(da8xx_ohci->oc_gpio);
 		goto err;
+	}
 
 	if (da8xx_ohci->oc_gpio) {
 		oc_irq = gpiod_to_irq(da8xx_ohci->oc_gpio);
-		if (oc_irq < 0)
+		if (oc_irq < 0) {
+			error = oc_irq;
 			goto err;
+		}
 
 		error = devm_request_threaded_irq(dev, oc_irq, NULL,
 				ohci_da8xx_oc_thread, IRQF_TRIGGER_RISING |
diff --git a/drivers/usb/host/ohci-sm501.c b/drivers/usb/host/ohci-sm501.c
index c26228c25f99..6b3f1a0bb311 100644
--- a/drivers/usb/host/ohci-sm501.c
+++ b/drivers/usb/host/ohci-sm501.c
@@ -195,6 +195,7 @@ static int ohci_hcd_sm501_drv_remove(struct platform_device *pdev)
 	struct resource	*mem;
 
 	usb_remove_hcd(hcd);
+	iounmap(hcd->regs);
 	release_mem_region(hcd->rsrc_start, hcd->rsrc_len);
 	usb_put_hcd(hcd);
 	dma_release_declared_memory(&pdev->dev);
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 1711113d1eb8..4ba0576bafa1 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -55,6 +55,7 @@ static u8 usb_bos_descriptor [] = {
 static int xhci_create_usb3_bos_desc(struct xhci_hcd *xhci, char *buf,
 				     u16 wLength)
 {
+	struct xhci_port_cap *port_cap = NULL;
 	int i, ssa_count;
 	u32 temp;
 	u16 desc_size, ssp_cap_size, ssa_size = 0;
@@ -64,16 +65,24 @@ static int xhci_create_usb3_bos_desc(struct xhci_hcd *xhci, char *buf,
 	ssp_cap_size = sizeof(usb_bos_descriptor) - desc_size;
 
 	/* does xhci support USB 3.1 Enhanced SuperSpeed */
-	if (xhci->usb3_rhub.min_rev >= 0x01) {
+	for (i = 0; i < xhci->num_port_caps; i++) {
+		if (xhci->port_caps[i].maj_rev == 0x03 &&
+		    xhci->port_caps[i].min_rev >= 0x01) {
+			usb3_1 = true;
+			port_cap = &xhci->port_caps[i];
+			break;
+		}
+	}
+
+	if (usb3_1) {
 		/* does xhci provide a PSI table for SSA speed attributes? */
-		if (xhci->usb3_rhub.psi_count) {
+		if (port_cap->psi_count) {
 			/* two SSA entries for each unique PSI ID, RX and TX */
-			ssa_count = xhci->usb3_rhub.psi_uid_count * 2;
+			ssa_count = port_cap->psi_uid_count * 2;
 			ssa_size = ssa_count * sizeof(u32);
 			ssp_cap_size -= 16; /* skip copying the default SSA */
 		}
 		desc_size += ssp_cap_size;
-		usb3_1 = true;
 	}
 	memcpy(buf, &usb_bos_descriptor, min(desc_size, wLength));
 
@@ -99,7 +108,7 @@ static int xhci_create_usb3_bos_desc(struct xhci_hcd *xhci, char *buf,
 	}
 
 	/* If PSI table exists, add the custom speed attributes from it */
-	if (usb3_1 && xhci->usb3_rhub.psi_count) {
+	if (usb3_1 && port_cap->psi_count) {
 		u32 ssp_cap_base, bm_attrib, psi, psi_mant, psi_exp;
 		int offset;
 
@@ -111,7 +120,7 @@ static int xhci_create_usb3_bos_desc(struct xhci_hcd *xhci, char *buf,
 
 		/* attribute count SSAC bits 4:0 and ID count SSIC bits 8:5 */
 		bm_attrib = (ssa_count - 1) & 0x1f;
-		bm_attrib |= (xhci->usb3_rhub.psi_uid_count - 1) << 5;
+		bm_attrib |= (port_cap->psi_uid_count - 1) << 5;
 		put_unaligned_le32(bm_attrib, &buf[ssp_cap_base + 4]);
 
 		if (wLength < desc_size + ssa_size)
@@ -124,8 +133,8 @@ static int xhci_create_usb3_bos_desc(struct xhci_hcd *xhci, char *buf,
 		 * USB 3.1 requires two SSA entries (RX and TX) for every link
 		 */
 		offset = desc_size;
-		for (i = 0; i < xhci->usb3_rhub.psi_count; i++) {
-			psi = xhci->usb3_rhub.psi[i];
+		for (i = 0; i < port_cap->psi_count; i++) {
+			psi = port_cap->psi[i];
 			psi &= ~USB_SSP_SUBLINK_SPEED_RSVD;
 			psi_exp = XHCI_EXT_PORT_PSIE(psi);
 			psi_mant = XHCI_EXT_PORT_PSIM(psi);
@@ -1297,7 +1306,47 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 					 wIndex, link_state);
 				goto error;
 			}
+
+			/*
+			 * set link to U0, steps depend on current link state.
+			 * U3: set link to U0 and wait for u3exit completion.
+			 * U1/U2:  no PLC complete event, only set link to U0.
+			 * Resume/Recovery: device initiated U0, only wait for
+			 * completion
+			 */
+			if (link_state == USB_SS_PORT_LS_U0) {
+				u32 pls = temp & PORT_PLS_MASK;
+				bool wait_u0 = false;
+
+				/* already in U0 */
+				if (pls == XDEV_U0)
+					break;
+				if (pls == XDEV_U3 ||
+				    pls == XDEV_RESUME ||
+				    pls == XDEV_RECOVERY) {
+					wait_u0 = true;
+					reinit_completion(&bus_state->u3exit_done[wIndex]);
+				}
+				if (pls <= XDEV_U3) /* U1, U2, U3 */
+					xhci_set_link_state(xhci, ports[wIndex],
+							    USB_SS_PORT_LS_U0);
+				if (!wait_u0) {
+					if (pls > XDEV_U3)
+						goto error;
+					break;
+				}
+				spin_unlock_irqrestore(&xhci->lock, flags);
+				if (!wait_for_completion_timeout(&bus_state->u3exit_done[wIndex],
+								 msecs_to_jiffies(100)))
+					xhci_dbg(xhci, "missing U0 port change event for port %d\n",
+						 wIndex);
+				spin_lock_irqsave(&xhci->lock, flags);
+				temp = readl(ports[wIndex]->addr);
+				break;
+			}
+
 			if (link_state == USB_SS_PORT_LS_U3) {
+				int retries = 16;
 				slot_id = xhci_find_slot_id_by_port(hcd, xhci,
 						wIndex + 1);
 				if (slot_id) {
@@ -1308,17 +1357,18 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 					xhci_stop_device(xhci, slot_id, 1);
 					spin_lock_irqsave(&xhci->lock, flags);
 				}
-			}
-
-			xhci_set_link_state(xhci, ports[wIndex], link_state);
-
-			spin_unlock_irqrestore(&xhci->lock, flags);
-			msleep(20); /* wait device to enter */
-			spin_lock_irqsave(&xhci->lock, flags);
-
-			temp = readl(ports[wIndex]->addr);
-			if (link_state == USB_SS_PORT_LS_U3)
+				xhci_set_link_state(xhci, ports[wIndex], USB_SS_PORT_LS_U3);
+				spin_unlock_irqrestore(&xhci->lock, flags);
+				while (retries--) {
+					usleep_range(4000, 8000);
+					temp = readl(ports[wIndex]->addr);
+					if ((temp & PORT_PLS_MASK) == XDEV_U3)
+						break;
+				}
+				spin_lock_irqsave(&xhci->lock, flags);
+				temp = readl(ports[wIndex]->addr);
 				bus_state->suspended_ports |= 1 << wIndex;
+			}
 			break;
 		case USB_PORT_FEAT_POWER:
 			/*
@@ -1519,6 +1569,8 @@ int xhci_hub_status_data(struct usb_hcd *hcd, char *buf)
 		}
 		if ((temp & PORT_RC))
 			reset_change = true;
+		if (temp & PORT_OC)
+			status = 1;
 	}
 	if (!status && !reset_change) {
 		xhci_dbg(xhci, "%s: stopping port polling.\n", __func__);
@@ -1584,6 +1636,13 @@ retry:
 				 port_index);
 			goto retry;
 		}
+		/* bail out if port detected a over-current condition */
+		if (t1 & PORT_OC) {
+			bus_state->bus_suspended = 0;
+			spin_unlock_irqrestore(&xhci->lock, flags);
+			xhci_dbg(xhci, "Bus suspend bailout, port over-current detected\n");
+			return -EBUSY;
+		}
 		/* suspend ports in U0, or bail out for new connect changes */
 		if ((t1 & PORT_PE) && (t1 & PORT_PLS_MASK) == XDEV_U0) {
 			if ((t1 & PORT_CSC) && wake_enabled) {
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index cd18c1ce0f71..4e168de8944d 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -1475,9 +1475,15 @@ int xhci_endpoint_init(struct xhci_hcd *xhci,
 	/* Allow 3 retries for everything but isoc, set CErr = 3 */
 	if (!usb_endpoint_xfer_isoc(&ep->desc))
 		err_count = 3;
-	/* Some devices get this wrong */
-	if (usb_endpoint_xfer_bulk(&ep->desc) && udev->speed == USB_SPEED_HIGH)
-		max_packet = 512;
+	/* HS bulk max packet should be 512, FS bulk supports 8, 16, 32 or 64 */
+	if (usb_endpoint_xfer_bulk(&ep->desc)) {
+		if (udev->speed == USB_SPEED_HIGH)
+			max_packet = 512;
+		if (udev->speed == USB_SPEED_FULL) {
+			max_packet = rounddown_pow_of_two(max_packet);
+			max_packet = clamp_val(max_packet, 8, 64);
+		}
+	}
 	/* xHCI 1.0 and 1.1 indicates that ctrl ep avg TRB Length should be 8 */
 	if (usb_endpoint_xfer_control(&ep->desc) && xhci->hci_version >= 0x100)
 		avg_trb_len = 8;
@@ -1909,17 +1915,17 @@ no_bw:
 	xhci->usb3_rhub.num_ports = 0;
 	xhci->num_active_eps = 0;
 	kfree(xhci->usb2_rhub.ports);
-	kfree(xhci->usb2_rhub.psi);
 	kfree(xhci->usb3_rhub.ports);
-	kfree(xhci->usb3_rhub.psi);
 	kfree(xhci->hw_ports);
 	kfree(xhci->rh_bw);
 	kfree(xhci->ext_caps);
+	for (i = 0; i < xhci->num_port_caps; i++)
+		kfree(xhci->port_caps[i].psi);
+	kfree(xhci->port_caps);
+	xhci->num_port_caps = 0;
 
 	xhci->usb2_rhub.ports = NULL;
-	xhci->usb2_rhub.psi = NULL;
 	xhci->usb3_rhub.ports = NULL;
-	xhci->usb3_rhub.psi = NULL;
 	xhci->hw_ports = NULL;
 	xhci->rh_bw = NULL;
 	xhci->ext_caps = NULL;
@@ -2120,6 +2126,7 @@ static void xhci_add_in_port(struct xhci_hcd *xhci, unsigned int num_ports,
 	u8 major_revision, minor_revision;
 	struct xhci_hub *rhub;
 	struct device *dev = xhci_to_hcd(xhci)->self.sysdev;
+	struct xhci_port_cap *port_cap;
 
 	temp = readl(addr);
 	major_revision = XHCI_EXT_PORT_MAJOR(temp);
@@ -2154,31 +2161,39 @@ static void xhci_add_in_port(struct xhci_hcd *xhci, unsigned int num_ports,
 		/* WTF? "Valid values are ‘1’ to MaxPorts" */
 		return;
 
-	rhub->psi_count = XHCI_EXT_PORT_PSIC(temp);
-	if (rhub->psi_count) {
-		rhub->psi = kcalloc_node(rhub->psi_count, sizeof(*rhub->psi),
-				    GFP_KERNEL, dev_to_node(dev));
-		if (!rhub->psi)
-			rhub->psi_count = 0;
+	port_cap = &xhci->port_caps[xhci->num_port_caps++];
+	if (xhci->num_port_caps > max_caps)
+		return;
+
+	port_cap->maj_rev = major_revision;
+	port_cap->min_rev = minor_revision;
+	port_cap->psi_count = XHCI_EXT_PORT_PSIC(temp);
 
-		rhub->psi_uid_count++;
-		for (i = 0; i < rhub->psi_count; i++) {
-			rhub->psi[i] = readl(addr + 4 + i);
+	if (port_cap->psi_count) {
+		port_cap->psi = kcalloc_node(port_cap->psi_count,
+					     sizeof(*port_cap->psi),
+					     GFP_KERNEL, dev_to_node(dev));
+		if (!port_cap->psi)
+			port_cap->psi_count = 0;
+
+		port_cap->psi_uid_count++;
+		for (i = 0; i < port_cap->psi_count; i++) {
+			port_cap->psi[i] = readl(addr + 4 + i);
 
 			/* count unique ID values, two consecutive entries can
 			 * have the same ID if link is assymetric
 			 */
-			if (i && (XHCI_EXT_PORT_PSIV(rhub->psi[i]) !=
-				  XHCI_EXT_PORT_PSIV(rhub->psi[i - 1])))
-				rhub->psi_uid_count++;
+			if (i && (XHCI_EXT_PORT_PSIV(port_cap->psi[i]) !=
+				  XHCI_EXT_PORT_PSIV(port_cap->psi[i - 1])))
+				port_cap->psi_uid_count++;
 
 			xhci_dbg(xhci, "PSIV:%d PSIE:%d PLT:%d PFD:%d LP:%d PSIM:%d\n",
-				  XHCI_EXT_PORT_PSIV(rhub->psi[i]),
-				  XHCI_EXT_PORT_PSIE(rhub->psi[i]),
-				  XHCI_EXT_PORT_PLT(rhub->psi[i]),
-				  XHCI_EXT_PORT_PFD(rhub->psi[i]),
-				  XHCI_EXT_PORT_LP(rhub->psi[i]),
-				  XHCI_EXT_PORT_PSIM(rhub->psi[i]));
+				  XHCI_EXT_PORT_PSIV(port_cap->psi[i]),
+				  XHCI_EXT_PORT_PSIE(port_cap->psi[i]),
+				  XHCI_EXT_PORT_PLT(port_cap->psi[i]),
+				  XHCI_EXT_PORT_PFD(port_cap->psi[i]),
+				  XHCI_EXT_PORT_LP(port_cap->psi[i]),
+				  XHCI_EXT_PORT_PSIM(port_cap->psi[i]));
 		}
 	}
 	/* cache usb2 port capabilities */
@@ -2213,6 +2228,7 @@ static void xhci_add_in_port(struct xhci_hcd *xhci, unsigned int num_ports,
 			continue;
 		}
 		hw_port->rhub = rhub;
+		hw_port->port_cap = port_cap;
 		rhub->num_ports++;
 	}
 	/* FIXME: Should we disable ports not in the Extended Capabilities? */
@@ -2303,6 +2319,11 @@ static int xhci_setup_port_arrays(struct xhci_hcd *xhci, gfp_t flags)
 	if (!xhci->ext_caps)
 		return -ENOMEM;
 
+	xhci->port_caps = kcalloc_node(cap_count, sizeof(*xhci->port_caps),
+				flags, dev_to_node(dev));
+	if (!xhci->port_caps)
+		return -ENOMEM;
+
 	offset = cap_start;
 
 	while (offset) {
@@ -2532,6 +2553,7 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 		xhci->usb3_rhub.bus_state.resume_done[i] = 0;
 		/* Only the USB 2.0 completions will ever be used. */
 		init_completion(&xhci->usb2_rhub.bus_state.rexit_done[i]);
+		init_completion(&xhci->usb3_rhub.bus_state.u3exit_done[i]);
 	}
 
 	if (scratchpad_alloc(xhci, flags))
diff --git a/drivers/usb/host/xhci-mtk-sch.c b/drivers/usb/host/xhci-mtk-sch.c
index fea555570ad4..45c54d56ecbd 100644
--- a/drivers/usb/host/xhci-mtk-sch.c
+++ b/drivers/usb/host/xhci-mtk-sch.c
@@ -557,6 +557,10 @@ static bool need_bw_sch(struct usb_host_endpoint *ep,
 	if (is_fs_or_ls(speed) && !has_tt)
 		return false;
 
+	/* skip endpoint with zero maxpkt */
+	if (usb_endpoint_maxp(&ep->desc) == 0)
+		return false;
+
 	return true;
 }
 
diff --git a/drivers/usb/host/xhci-mtk.c b/drivers/usb/host/xhci-mtk.c
index 026fe18972d3..e3555db3f61f 100644
--- a/drivers/usb/host/xhci-mtk.c
+++ b/drivers/usb/host/xhci-mtk.c
@@ -579,6 +579,9 @@ static int xhci_mtk_remove(struct platform_device *dev)
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
 	struct usb_hcd  *shared_hcd = xhci->shared_hcd;
 
+	pm_runtime_put_noidle(&dev->dev);
+	pm_runtime_disable(&dev->dev);
+
 	usb_remove_hcd(shared_hcd);
 	xhci->shared_hcd = NULL;
 	device_init_wakeup(&dev->dev, false);
@@ -589,8 +592,6 @@ static int xhci_mtk_remove(struct platform_device *dev)
 	xhci_mtk_sch_exit(mtk);
 	xhci_mtk_clks_disable(mtk);
 	xhci_mtk_ldos_disable(mtk);
-	pm_runtime_put_sync(&dev->dev);
-	pm_runtime_disable(&dev->dev);
 
 	return 0;
 }
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index bd25a036e18f..ec24b6ae22d6 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -49,12 +49,16 @@
 #define PCI_DEVICE_ID_INTEL_TITAN_RIDGE_4C_XHCI		0x15ec
 #define PCI_DEVICE_ID_INTEL_TITAN_RIDGE_DD_XHCI		0x15f0
 #define PCI_DEVICE_ID_INTEL_ICE_LAKE_XHCI		0x8a13
+#define PCI_DEVICE_ID_INTEL_CML_XHCI			0xa3af
 
 #define PCI_DEVICE_ID_AMD_PROMONTORYA_4			0x43b9
 #define PCI_DEVICE_ID_AMD_PROMONTORYA_3			0x43ba
 #define PCI_DEVICE_ID_AMD_PROMONTORYA_2			0x43bb
 #define PCI_DEVICE_ID_AMD_PROMONTORYA_1			0x43bc
+#define PCI_DEVICE_ID_ASMEDIA_1042_XHCI			0x1042
 #define PCI_DEVICE_ID_ASMEDIA_1042A_XHCI		0x1142
+#define PCI_DEVICE_ID_ASMEDIA_1142_XHCI			0x1242
+#define PCI_DEVICE_ID_ASMEDIA_2142_XHCI			0x2142
 
 static const char hcd_name[] = "xhci_hcd";
 
@@ -135,7 +139,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 		xhci->quirks |= XHCI_AMD_PLL_FIX;
 
 	if (pdev->vendor == PCI_VENDOR_ID_AMD &&
-		(pdev->device == 0x15e0 ||
+		(pdev->device == 0x145c ||
+		 pdev->device == 0x15e0 ||
 		 pdev->device == 0x15e1 ||
 		 pdev->device == 0x43bb))
 		xhci->quirks |= XHCI_SUSPEND_DELAY;
@@ -187,7 +192,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 		 pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_M_XHCI ||
 		 pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_B_XHCI ||
 		 pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI ||
-		 pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI)) {
+		 pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI ||
+		 pdev->device == PCI_DEVICE_ID_INTEL_CML_XHCI)) {
 		xhci->quirks |= XHCI_PME_STUCK_QUIRK;
 	}
 	if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
@@ -242,11 +248,15 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 		xhci->quirks |= XHCI_BROKEN_STREAMS;
 
 	if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA &&
-			pdev->device == 0x1042)
+		pdev->device == PCI_DEVICE_ID_ASMEDIA_1042_XHCI)
 		xhci->quirks |= XHCI_BROKEN_STREAMS;
 	if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA &&
-			pdev->device == 0x1142)
+		pdev->device == PCI_DEVICE_ID_ASMEDIA_1042A_XHCI)
 		xhci->quirks |= XHCI_TRUST_TX_LENGTH;
+	if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA &&
+	    (pdev->device == PCI_DEVICE_ID_ASMEDIA_1142_XHCI ||
+	     pdev->device == PCI_DEVICE_ID_ASMEDIA_2142_XHCI))
+		xhci->quirks |= XHCI_NO_64BIT_SUPPORT;
 
 	if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA &&
 		pdev->device == PCI_DEVICE_ID_ASMEDIA_1042A_XHCI)
@@ -302,6 +312,9 @@ static int xhci_pci_setup(struct usb_hcd *hcd)
 	if (!usb_hcd_is_primary_hcd(hcd))
 		return 0;
 
+	if (xhci->quirks & XHCI_PME_STUCK_QUIRK)
+		xhci_pme_acpi_rtd3_enable(pdev);
+
 	xhci_dbg(xhci, "Got SBRN %u\n", (unsigned int) xhci->sbrn);
 
 	/* Find any debug ports */
@@ -359,9 +372,6 @@ static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 			HCC_MAX_PSA(xhci->hcc_params) >= 4)
 		xhci->shared_hcd->can_do_streams = 1;
 
-	if (xhci->quirks & XHCI_PME_STUCK_QUIRK)
-		xhci_pme_acpi_rtd3_enable(dev);
-
 	/* USB-2 and USB-3 roothubs initialized, allow runtime pm suspend */
 	pm_runtime_put_noidle(&dev->dev);
 
diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index 998241f5fce3..19c5eee20eb4 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -368,6 +368,7 @@ static int xhci_plat_remove(struct platform_device *dev)
 	struct clk *reg_clk = xhci->reg_clk;
 	struct usb_hcd *shared_hcd = xhci->shared_hcd;
 
+	pm_runtime_get_sync(&dev->dev);
 	xhci->xhc_state |= XHCI_STATE_REMOVING;
 
 	usb_remove_hcd(shared_hcd);
@@ -381,8 +382,9 @@ static int xhci_plat_remove(struct platform_device *dev)
 	clk_disable_unprepare(reg_clk);
 	usb_put_hcd(hcd);
 
-	pm_runtime_set_suspended(&dev->dev);
 	pm_runtime_disable(&dev->dev);
+	pm_runtime_put_noidle(&dev->dev);
+	pm_runtime_set_suspended(&dev->dev);
 
 	return 0;
 }
@@ -450,6 +452,7 @@ MODULE_DEVICE_TABLE(acpi, usb_xhci_acpi_match);
 static struct platform_driver usb_xhci_driver = {
 	.probe	= xhci_plat_probe,
 	.remove	= xhci_plat_remove,
+	.shutdown = usb_hcd_platform_shutdown,
 	.driver	= {
 		.name = "xhci-hcd",
 		.pm = &xhci_plat_pm_ops,
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 2de4b2d16dd1..5a93a225c97e 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -534,6 +534,23 @@ void xhci_find_new_dequeue_state(struct xhci_hcd *xhci,
 				stream_id);
 		return;
 	}
+	/*
+	 * A cancelled TD can complete with a stall if HW cached the trb.
+	 * In this case driver can't find cur_td, but if the ring is empty we
+	 * can move the dequeue pointer to the current enqueue position.
+	 */
+	if (!cur_td) {
+		if (list_empty(&ep_ring->td_list)) {
+			state->new_deq_seg = ep_ring->enq_seg;
+			state->new_deq_ptr = ep_ring->enqueue;
+			state->new_cycle_state = ep_ring->cycle_state;
+			goto done;
+		} else {
+			xhci_warn(xhci, "Can't find new dequeue state, missing cur_td\n");
+			return;
+		}
+	}
+
 	/* Dig out the cycle state saved by the xHC during the stop ep cmd */
 	xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
 			"Finding endpoint context");
@@ -579,6 +596,7 @@ void xhci_find_new_dequeue_state(struct xhci_hcd *xhci,
 	state->new_deq_seg = new_seg;
 	state->new_deq_ptr = new_deq;
 
+done:
 	/* Don't update the ring cycle state for the producer (us). */
 	xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
 			"Cycle state = 0x%x", state->new_cycle_state);
@@ -1666,6 +1684,7 @@ static void handle_port_status(struct xhci_hcd *xhci,
 	     (portsc & PORT_PLS_MASK) == XDEV_U1 ||
 	     (portsc & PORT_PLS_MASK) == XDEV_U2)) {
 		xhci_dbg(xhci, "resume SS port %d finished\n", port_id);
+		complete(&bus_state->u3exit_done[hcd_portnum]);
 		/* We've just brought the device into U0/1/2 through either the
 		 * Resume state after a device remote wakeup, or through the
 		 * U3Exit state after a host-initiated resume.  If it's a device
@@ -1823,7 +1842,8 @@ static void xhci_cleanup_halted_endpoint(struct xhci_hcd *xhci,
 
 	if (reset_type == EP_HARD_RESET) {
 		ep->ep_state |= EP_HARD_CLEAR_TOGGLE;
-		xhci_cleanup_stalled_ring(xhci, ep_index, stream_id, td);
+		xhci_cleanup_stalled_ring(xhci, slot_id, ep_index, stream_id,
+					  td);
 	}
 	xhci_ring_cmd_db(xhci);
 }
@@ -2501,6 +2521,15 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 				xhci_dbg(xhci, "td_list is empty while skip flag set. Clear skip flag for slot %u ep %u.\n",
 					 slot_id, ep_index);
 			}
+			if (trb_comp_code == COMP_STALL_ERROR ||
+			    xhci_requires_manual_halt_cleanup(xhci, ep_ctx,
+							      trb_comp_code)) {
+				xhci_cleanup_halted_endpoint(xhci, slot_id,
+							     ep_index,
+							     ep_ring->stream_id,
+							     NULL,
+							     EP_HARD_RESET);
+			}
 			goto cleanup;
 		}
 
@@ -2716,6 +2745,42 @@ static int xhci_handle_event(struct xhci_hcd *xhci)
 }
 
 /*
+ * Update Event Ring Dequeue Pointer:
+ * - When all events have finished
+ * - To avoid "Event Ring Full Error" condition
+ */
+static void xhci_update_erst_dequeue(struct xhci_hcd *xhci,
+		union xhci_trb *event_ring_deq)
+{
+	u64 temp_64;
+	dma_addr_t deq;
+
+	temp_64 = xhci_read_64(xhci, &xhci->ir_set->erst_dequeue);
+	/* If necessary, update the HW's version of the event ring deq ptr. */
+	if (event_ring_deq != xhci->event_ring->dequeue) {
+		deq = xhci_trb_virt_to_dma(xhci->event_ring->deq_seg,
+				xhci->event_ring->dequeue);
+		if (deq == 0)
+			xhci_warn(xhci, "WARN something wrong with SW event ring dequeue ptr\n");
+		/*
+		 * Per 4.9.4, Software writes to the ERDP register shall
+		 * always advance the Event Ring Dequeue Pointer value.
+		 */
+		if ((temp_64 & (u64) ~ERST_PTR_MASK) ==
+				((u64) deq & (u64) ~ERST_PTR_MASK))
+			return;
+
+		/* Update HC event ring dequeue pointer */
+		temp_64 &= ERST_PTR_MASK;
+		temp_64 |= ((u64) deq & (u64) ~ERST_PTR_MASK);
+	}
+
+	/* Clear the event handler busy flag (RW1C) */
+	temp_64 |= ERST_EHB;
+	xhci_write_64(xhci, temp_64, &xhci->ir_set->erst_dequeue);
+}
+
+/*
  * xHCI spec says we can get an interrupt, and if the HC has an error condition,
  * we might get bad data out of the event ring.  Section 4.10.2.7 has a list of
  * indicators of an event TRB error, but we check the status *first* to be safe.
@@ -2726,9 +2791,9 @@ irqreturn_t xhci_irq(struct usb_hcd *hcd)
 	union xhci_trb *event_ring_deq;
 	irqreturn_t ret = IRQ_NONE;
 	unsigned long flags;
-	dma_addr_t deq;
 	u64 temp_64;
 	u32 status;
+	int event_loop = 0;
 
 	spin_lock_irqsave(&xhci->lock, flags);
 	/* Check if the xHC generated the interrupt, or the irq is shared */
@@ -2782,24 +2847,14 @@ irqreturn_t xhci_irq(struct usb_hcd *hcd)
 	/* FIXME this should be a delayed service routine
 	 * that clears the EHB.
 	 */
-	while (xhci_handle_event(xhci) > 0) {}
-
-	temp_64 = xhci_read_64(xhci, &xhci->ir_set->erst_dequeue);
-	/* If necessary, update the HW's version of the event ring deq ptr. */
-	if (event_ring_deq != xhci->event_ring->dequeue) {
-		deq = xhci_trb_virt_to_dma(xhci->event_ring->deq_seg,
-				xhci->event_ring->dequeue);
-		if (deq == 0)
-			xhci_warn(xhci, "WARN something wrong with SW event "
-					"ring dequeue ptr.\n");
-		/* Update HC event ring dequeue pointer */
-		temp_64 &= ERST_PTR_MASK;
-		temp_64 |= ((u64) deq & (u64) ~ERST_PTR_MASK);
+	while (xhci_handle_event(xhci) > 0) {
+		if (event_loop++ < TRBS_PER_SEGMENT / 2)
+			continue;
+		xhci_update_erst_dequeue(xhci, event_ring_deq);
+		event_loop = 0;
 	}
 
-	/* Clear the event handler busy flag (RW1C); event ring is empty. */
-	temp_64 |= ERST_EHB;
-	xhci_write_64(xhci, temp_64, &xhci->ir_set->erst_dequeue);
+	xhci_update_erst_dequeue(xhci, event_ring_deq);
 	ret = IRQ_HANDLED;
 
 out:
@@ -3335,8 +3390,8 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 			/* New sg entry */
 			--num_sgs;
 			sent_len -= block_len;
-			if (num_sgs != 0) {
-				sg = sg_next(sg);
+			sg = sg_next(sg);
+			if (num_sgs != 0 && sg) {
 				block_len = sg_dma_len(sg);
 				addr = (u64) sg_dma_address(sg);
 				addr += sent_len;
diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c
index ef3023eaf1ef..69745bf11158 100644
--- a/drivers/usb/host/xhci-tegra.c
+++ b/drivers/usb/host/xhci-tegra.c
@@ -1436,6 +1436,7 @@ MODULE_FIRMWARE("nvidia/tegra210/xusb.bin");
 
 static const char * const tegra186_supply_names[] = {
 };
+MODULE_FIRMWARE("nvidia/tegra186/xusb.bin");
 
 static const struct tegra_xusb_phy_type tegra186_phy_types[] = {
 	{ .name = "usb3", .num = 3, },
diff --git a/drivers/usb/host/xhci-trace.h b/drivers/usb/host/xhci-trace.h
index 052a269d86f2..87da9098fb34 100644
--- a/drivers/usb/host/xhci-trace.h
+++ b/drivers/usb/host/xhci-trace.h
@@ -289,23 +289,12 @@ DECLARE_EVENT_CLASS(xhci_log_urb,
 	),
 	TP_printk("ep%d%s-%s: urb %p pipe %u slot %d length %d/%d sgs %d/%d stream %d flags %08x",
 			__entry->epnum, __entry->dir_in ? "in" : "out",
-			({ char *s;
-			switch (__entry->type) {
-			case USB_ENDPOINT_XFER_INT:
-				s = "intr";
-				break;
-			case USB_ENDPOINT_XFER_CONTROL:
-				s = "control";
-				break;
-			case USB_ENDPOINT_XFER_BULK:
-				s = "bulk";
-				break;
-			case USB_ENDPOINT_XFER_ISOC:
-				s = "isoc";
-				break;
-			default:
-				s = "UNKNOWN";
-			} s; }), __entry->urb, __entry->pipe, __entry->slot_id,
+			__print_symbolic(__entry->type,
+				   { USB_ENDPOINT_XFER_INT,	"intr" },
+				   { USB_ENDPOINT_XFER_CONTROL,	"control" },
+				   { USB_ENDPOINT_XFER_BULK,	"bulk" },
+				   { USB_ENDPOINT_XFER_ISOC,	"isoc" }),
+			__entry->urb, __entry->pipe, __entry->slot_id,
 			__entry->actual, __entry->length, __entry->num_mapped_sgs,
 			__entry->num_sgs, __entry->stream, __entry->flags
 		)
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index d3dd7264c928..1f7d35b3a937 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -1157,8 +1157,10 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
 		xhci_dbg(xhci, "Stop HCD\n");
 		xhci_halt(xhci);
 		xhci_zero_64b_regs(xhci);
-		xhci_reset(xhci);
+		retval = xhci_reset(xhci);
 		spin_unlock_irq(&xhci->lock);
+		if (retval)
+			return retval;
 		xhci_cleanup_msix(xhci);
 
 		xhci_dbg(xhci, "// Disabling event ring interrupts\n");
@@ -1428,6 +1430,7 @@ static int xhci_check_maxpacket(struct xhci_hcd *xhci, unsigned int slot_id,
 				xhci->devs[slot_id]->out_ctx, ep_index);
 
 		ep_ctx = xhci_get_ep_ctx(xhci, command->in_ctx, ep_index);
+		ep_ctx->ep_info &= cpu_to_le32(~EP_STATE_MASK);/* must clear */
 		ep_ctx->ep_info2 &= cpu_to_le32(~MAX_PACKET_MASK);
 		ep_ctx->ep_info2 |= cpu_to_le32(MAX_PACKET(max_packet_size));
 
@@ -3029,19 +3032,19 @@ static void xhci_setup_input_ctx_for_quirk(struct xhci_hcd *xhci,
 			added_ctxs, added_ctxs);
 }
 
-void xhci_cleanup_stalled_ring(struct xhci_hcd *xhci, unsigned int ep_index,
-			       unsigned int stream_id, struct xhci_td *td)
+void xhci_cleanup_stalled_ring(struct xhci_hcd *xhci, unsigned int slot_id,
+			       unsigned int ep_index, unsigned int stream_id,
+			       struct xhci_td *td)
 {
 	struct xhci_dequeue_state deq_state;
-	struct usb_device *udev = td->urb->dev;
 
 	xhci_dbg_trace(xhci, trace_xhci_dbg_reset_ep,
 			"Cleaning up stalled endpoint ring");
 	/* We need to move the HW's dequeue pointer past this TD,
 	 * or it will attempt to resend it on the next doorbell ring.
 	 */
-	xhci_find_new_dequeue_state(xhci, udev->slot_id,
-			ep_index, stream_id, td, &deq_state);
+	xhci_find_new_dequeue_state(xhci, slot_id, ep_index, stream_id, td,
+				    &deq_state);
 
 	if (!deq_state.new_deq_ptr || !deq_state.new_deq_seg)
 		return;
@@ -3052,7 +3055,7 @@ void xhci_cleanup_stalled_ring(struct xhci_hcd *xhci, unsigned int ep_index,
 	if (!(xhci->quirks & XHCI_RESET_EP_QUIRK)) {
 		xhci_dbg_trace(xhci, trace_xhci_dbg_reset_ep,
 				"Queueing new dequeue state");
-		xhci_queue_new_dequeue_state(xhci, udev->slot_id,
+		xhci_queue_new_dequeue_state(xhci, slot_id,
 				ep_index, &deq_state);
 	} else {
 		/* Better hope no one uses the input context between now and the
@@ -3063,7 +3066,7 @@ void xhci_cleanup_stalled_ring(struct xhci_hcd *xhci, unsigned int ep_index,
 		xhci_dbg_trace(xhci, trace_xhci_dbg_quirks,
 				"Setting up input context for "
 				"configure endpoint command");
-		xhci_setup_input_ctx_for_quirk(xhci, udev->slot_id,
+		xhci_setup_input_ctx_for_quirk(xhci, slot_id,
 				ep_index, &deq_state);
 	}
 }
@@ -4333,6 +4336,9 @@ static int xhci_set_usb2_hardware_lpm(struct usb_hcd *hcd,
 	int		hird, exit_latency;
 	int		ret;
 
+	if (xhci->quirks & XHCI_HW_LPM_DISABLE)
+		return -EPERM;
+
 	if (hcd->speed >= HCD_USB3 || !xhci->hw_lpm_support ||
 			!udev->lpm_capable)
 		return -EPERM;
@@ -4355,7 +4361,7 @@ static int xhci_set_usb2_hardware_lpm(struct usb_hcd *hcd,
 	xhci_dbg(xhci, "%s port %d USB2 hardware LPM\n",
 			enable ? "enable" : "disable", port_num + 1);
 
-	if (enable && !(xhci->quirks & XHCI_HW_LPM_DISABLE)) {
+	if (enable) {
 		/* Host supports BESL timeout instead of HIRD */
 		if (udev->usb2_hw_lpm_besl_capable) {
 			/* if device doesn't have a preferred BESL value use a
@@ -4414,6 +4420,9 @@ static int xhci_set_usb2_hardware_lpm(struct usb_hcd *hcd,
 			mutex_lock(hcd->bandwidth_mutex);
 			xhci_change_max_exit_latency(xhci, udev, 0);
 			mutex_unlock(hcd->bandwidth_mutex);
+			readl_poll_timeout(ports[port_num]->addr, pm_val,
+					   (pm_val & PORT_PLS_MASK) == XDEV_U0,
+					   100, 10000);
 			return 0;
 		}
 	}
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 08be89398126..b3afc7b76662 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -716,7 +716,7 @@ struct xhci_ep_ctx {
  * 4 - TRB error
  * 5-7 - reserved
  */
-#define EP_STATE_MASK		(0xf)
+#define EP_STATE_MASK		(0x7)
 #define EP_STATE_DISABLED	0
 #define EP_STATE_RUNNING	1
 #define EP_STATE_HALTED		2
@@ -1692,6 +1692,7 @@ struct xhci_bus_state {
 	/* Which ports are waiting on RExit to U0 transition. */
 	unsigned long		rexit_ports;
 	struct completion	rexit_done[USB_MAXCHILDREN];
+	struct completion	u3exit_done[USB_MAXCHILDREN];
 };
 
 
@@ -1700,12 +1701,20 @@ struct xhci_bus_state {
  * Intel Lynx Point LP xHCI host.
  */
 #define	XHCI_MAX_REXIT_TIMEOUT_MS	20
+struct xhci_port_cap {
+	u32			*psi;	/* array of protocol speed ID entries */
+	u8			psi_count;
+	u8			psi_uid_count;
+	u8			maj_rev;
+	u8			min_rev;
+};
 
 struct xhci_port {
 	__le32 __iomem		*addr;
 	int			hw_portnum;
 	int			hcd_portnum;
 	struct xhci_hub		*rhub;
+	struct xhci_port_cap	*port_cap;
 };
 
 struct xhci_hub {
@@ -1717,9 +1726,6 @@ struct xhci_hub {
 	/* supported prococol extended capabiliy values */
 	u8			maj_rev;
 	u8			min_rev;
-	u32			*psi;	/* array of protocol speed ID entries */
-	u8			psi_count;
-	u8			psi_uid_count;
 };
 
 /* There is one xhci_hcd structure per controller */
@@ -1878,6 +1884,9 @@ struct xhci_hcd {
 	/* cached usb2 extened protocol capabilites */
 	u32                     *ext_caps;
 	unsigned int            num_ext_caps;
+	/* cached extended protocol port capabilities */
+	struct xhci_port_cap	*port_caps;
+	unsigned int		num_port_caps;
 	/* Compliance Mode Recovery Data */
 	struct timer_list	comp_mode_recovery_timer;
 	u32			port_status_u0;
@@ -2105,8 +2114,9 @@ void xhci_find_new_dequeue_state(struct xhci_hcd *xhci,
 void xhci_queue_new_dequeue_state(struct xhci_hcd *xhci,
 		unsigned int slot_id, unsigned int ep_index,
 		struct xhci_dequeue_state *deq_state);
-void xhci_cleanup_stalled_ring(struct xhci_hcd *xhci, unsigned int ep_index,
-		unsigned int stream_id, struct xhci_td *td);
+void xhci_cleanup_stalled_ring(struct xhci_hcd *xhci, unsigned int slot_id,
+			       unsigned int ep_index, unsigned int stream_id,
+			       struct xhci_td *td);
 void xhci_stop_endpoint_command_watchdog(struct timer_list *t);
 void xhci_handle_command_timeout(struct work_struct *work);
 
diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c
index f405fa734bcc..871cdb2897a9 100644
--- a/drivers/usb/misc/iowarrior.c
+++ b/drivers/usb/misc/iowarrior.c
@@ -2,8 +2,9 @@
 /*
  *  Native support for the I/O-Warrior USB devices
  *
- *  Copyright (c) 2003-2005  Code Mercenaries GmbH
- *  written by Christian Lucht <lucht@codemercs.com>
+ *  Copyright (c) 2003-2005, 2020  Code Mercenaries GmbH
+ *  written by Christian Lucht <lucht@codemercs.com> and
+ *  Christoph Jung <jung@codemercs.com>
  *
  *  based on
 
@@ -33,6 +34,14 @@
 #define USB_DEVICE_ID_CODEMERCS_IOWPV2	0x1512
 /* full speed iowarrior */
 #define USB_DEVICE_ID_CODEMERCS_IOW56	0x1503
+/* fuller speed iowarrior */
+#define USB_DEVICE_ID_CODEMERCS_IOW28	0x1504
+#define USB_DEVICE_ID_CODEMERCS_IOW28L	0x1505
+#define USB_DEVICE_ID_CODEMERCS_IOW100	0x1506
+
+/* OEMed devices */
+#define USB_DEVICE_ID_CODEMERCS_IOW24SAG	0x158a
+#define USB_DEVICE_ID_CODEMERCS_IOW56AM		0x158b
 
 /* Get a minor range for your devices from the usb maintainer */
 #ifdef CONFIG_USB_DYNAMIC_MINORS
@@ -137,6 +146,11 @@ static const struct usb_device_id iowarrior_ids[] = {
 	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOWPV1)},
 	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOWPV2)},
 	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW56)},
+	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW24SAG)},
+	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW56AM)},
+	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW28)},
+	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW28L)},
+	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW100)},
 	{}			/* Terminating entry */
 };
 MODULE_DEVICE_TABLE(usb, iowarrior_ids);
@@ -361,6 +375,7 @@ static ssize_t iowarrior_write(struct file *file,
 	}
 	switch (dev->product_id) {
 	case USB_DEVICE_ID_CODEMERCS_IOW24:
+	case USB_DEVICE_ID_CODEMERCS_IOW24SAG:
 	case USB_DEVICE_ID_CODEMERCS_IOWPV1:
 	case USB_DEVICE_ID_CODEMERCS_IOWPV2:
 	case USB_DEVICE_ID_CODEMERCS_IOW40:
@@ -375,6 +390,10 @@ static ssize_t iowarrior_write(struct file *file,
 		goto exit;
 		break;
 	case USB_DEVICE_ID_CODEMERCS_IOW56:
+	case USB_DEVICE_ID_CODEMERCS_IOW56AM:
+	case USB_DEVICE_ID_CODEMERCS_IOW28:
+	case USB_DEVICE_ID_CODEMERCS_IOW28L:
+	case USB_DEVICE_ID_CODEMERCS_IOW100:
 		/* The IOW56 uses asynchronous IO and more urbs */
 		if (atomic_read(&dev->write_busy) == MAX_WRITES_IN_FLIGHT) {
 			/* Wait until we are below the limit for submitted urbs */
@@ -499,6 +518,7 @@ static long iowarrior_ioctl(struct file *file, unsigned int cmd,
 	switch (cmd) {
 	case IOW_WRITE:
 		if (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW24 ||
+		    dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW24SAG ||
 		    dev->product_id == USB_DEVICE_ID_CODEMERCS_IOWPV1 ||
 		    dev->product_id == USB_DEVICE_ID_CODEMERCS_IOWPV2 ||
 		    dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW40) {
@@ -782,7 +802,11 @@ static int iowarrior_probe(struct usb_interface *interface,
 		goto error;
 	}
 
-	if (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) {
+	if ((dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) ||
+	    (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56AM) ||
+	    (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28) ||
+	    (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28L) ||
+	    (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW100)) {
 		res = usb_find_last_int_out_endpoint(iface_desc,
 				&dev->int_out_endpoint);
 		if (res) {
@@ -794,10 +818,28 @@ static int iowarrior_probe(struct usb_interface *interface,
 
 	/* we have to check the report_size often, so remember it in the endianness suitable for our machine */
 	dev->report_size = usb_endpoint_maxp(dev->int_in_endpoint);
-	if ((dev->interface->cur_altsetting->desc.bInterfaceNumber == 0) &&
-	    (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56))
-		/* IOWarrior56 has wMaxPacketSize different from report size */
-		dev->report_size = 7;
+
+	/*
+	 * Some devices need the report size to be different than the
+	 * endpoint size.
+	 */
+	if (dev->interface->cur_altsetting->desc.bInterfaceNumber == 0) {
+		switch (dev->product_id) {
+		case USB_DEVICE_ID_CODEMERCS_IOW56:
+		case USB_DEVICE_ID_CODEMERCS_IOW56AM:
+			dev->report_size = 7;
+			break;
+
+		case USB_DEVICE_ID_CODEMERCS_IOW28:
+		case USB_DEVICE_ID_CODEMERCS_IOW28L:
+			dev->report_size = 4;
+			break;
+
+		case USB_DEVICE_ID_CODEMERCS_IOW100:
+			dev->report_size = 13;
+			break;
+		}
+	}
 
 	/* create the urb and buffer for reading */
 	dev->int_in_urb = usb_alloc_urb(0, GFP_KERNEL);
diff --git a/drivers/usb/misc/sisusbvga/sisusb.c b/drivers/usb/misc/sisusbvga/sisusb.c
index ea06f1fed6fa..e453008a3abd 100644
--- a/drivers/usb/misc/sisusbvga/sisusb.c
+++ b/drivers/usb/misc/sisusbvga/sisusb.c
@@ -1199,18 +1199,18 @@ static int sisusb_read_mem_bulk(struct sisusb_usb_data *sisusb, u32 addr,
 /* High level: Gfx (indexed) register access */
 
 #ifdef CONFIG_USB_SISUSBVGA_CON
-int sisusb_setreg(struct sisusb_usb_data *sisusb, int port, u8 data)
+int sisusb_setreg(struct sisusb_usb_data *sisusb, u32 port, u8 data)
 {
 	return sisusb_write_memio_byte(sisusb, SISUSB_TYPE_IO, port, data);
 }
 
-int sisusb_getreg(struct sisusb_usb_data *sisusb, int port, u8 *data)
+int sisusb_getreg(struct sisusb_usb_data *sisusb, u32 port, u8 *data)
 {
 	return sisusb_read_memio_byte(sisusb, SISUSB_TYPE_IO, port, data);
 }
 #endif
 
-int sisusb_setidxreg(struct sisusb_usb_data *sisusb, int port,
+int sisusb_setidxreg(struct sisusb_usb_data *sisusb, u32 port,
 		u8 index, u8 data)
 {
 	int ret;
@@ -1220,7 +1220,7 @@ int sisusb_setidxreg(struct sisusb_usb_data *sisusb, int port,
 	return ret;
 }
 
-int sisusb_getidxreg(struct sisusb_usb_data *sisusb, int port,
+int sisusb_getidxreg(struct sisusb_usb_data *sisusb, u32 port,
 		u8 index, u8 *data)
 {
 	int ret;
@@ -1230,7 +1230,7 @@ int sisusb_getidxreg(struct sisusb_usb_data *sisusb, int port,
 	return ret;
 }
 
-int sisusb_setidxregandor(struct sisusb_usb_data *sisusb, int port, u8 idx,
+int sisusb_setidxregandor(struct sisusb_usb_data *sisusb, u32 port, u8 idx,
 		u8 myand, u8 myor)
 {
 	int ret;
@@ -1245,7 +1245,7 @@ int sisusb_setidxregandor(struct sisusb_usb_data *sisusb, int port, u8 idx,
 }
 
 static int sisusb_setidxregmask(struct sisusb_usb_data *sisusb,
-		int port, u8 idx, u8 data, u8 mask)
+		u32 port, u8 idx, u8 data, u8 mask)
 {
 	int ret;
 	u8 tmp;
@@ -1258,13 +1258,13 @@ static int sisusb_setidxregmask(struct sisusb_usb_data *sisusb,
 	return ret;
 }
 
-int sisusb_setidxregor(struct sisusb_usb_data *sisusb, int port,
+int sisusb_setidxregor(struct sisusb_usb_data *sisusb, u32 port,
 		u8 index, u8 myor)
 {
 	return sisusb_setidxregandor(sisusb, port, index, 0xff, myor);
 }
 
-int sisusb_setidxregand(struct sisusb_usb_data *sisusb, int port,
+int sisusb_setidxregand(struct sisusb_usb_data *sisusb, u32 port,
 		u8 idx, u8 myand)
 {
 	return sisusb_setidxregandor(sisusb, port, idx, myand, 0x00);
@@ -2787,8 +2787,8 @@ static loff_t sisusb_lseek(struct file *file, loff_t offset, int orig)
 static int sisusb_handle_command(struct sisusb_usb_data *sisusb,
 		struct sisusb_command *y, unsigned long arg)
 {
-	int	retval, port, length;
-	u32	address;
+	int	retval, length;
+	u32	port, address;
 
 	/* All our commands require the device
 	 * to be initialized.
diff --git a/drivers/usb/misc/sisusbvga/sisusb_init.h b/drivers/usb/misc/sisusbvga/sisusb_init.h
index 1782c759c4ad..ace09985dae4 100644
--- a/drivers/usb/misc/sisusbvga/sisusb_init.h
+++ b/drivers/usb/misc/sisusbvga/sisusb_init.h
@@ -812,17 +812,17 @@ static const struct SiS_VCLKData SiSUSB_VCLKData[] = {
 int SiSUSBSetMode(struct SiS_Private *SiS_Pr, unsigned short ModeNo);
 int SiSUSBSetVESAMode(struct SiS_Private *SiS_Pr, unsigned short VModeNo);
 
-extern int sisusb_setreg(struct sisusb_usb_data *sisusb, int port, u8 data);
-extern int sisusb_getreg(struct sisusb_usb_data *sisusb, int port, u8 * data);
-extern int sisusb_setidxreg(struct sisusb_usb_data *sisusb, int port,
+extern int sisusb_setreg(struct sisusb_usb_data *sisusb, u32 port, u8 data);
+extern int sisusb_getreg(struct sisusb_usb_data *sisusb, u32 port, u8 * data);
+extern int sisusb_setidxreg(struct sisusb_usb_data *sisusb, u32 port,
 			    u8 index, u8 data);
-extern int sisusb_getidxreg(struct sisusb_usb_data *sisusb, int port,
+extern int sisusb_getidxreg(struct sisusb_usb_data *sisusb, u32 port,
 			    u8 index, u8 * data);
-extern int sisusb_setidxregandor(struct sisusb_usb_data *sisusb, int port,
+extern int sisusb_setidxregandor(struct sisusb_usb_data *sisusb, u32 port,
 				 u8 idx, u8 myand, u8 myor);
-extern int sisusb_setidxregor(struct sisusb_usb_data *sisusb, int port,
+extern int sisusb_setidxregor(struct sisusb_usb_data *sisusb, u32 port,
 			      u8 index, u8 myor);
-extern int sisusb_setidxregand(struct sisusb_usb_data *sisusb, int port,
+extern int sisusb_setidxregand(struct sisusb_usb_data *sisusb, u32 port,
 			       u8 idx, u8 myand);
 
 void sisusb_delete(struct kref *kref);
diff --git a/drivers/usb/misc/usbtest.c b/drivers/usb/misc/usbtest.c
index 98ada1a3425c..bae88893ee8e 100644
--- a/drivers/usb/misc/usbtest.c
+++ b/drivers/usb/misc/usbtest.c
@@ -2873,6 +2873,7 @@ static void usbtest_disconnect(struct usb_interface *intf)
 
 	usb_set_intfdata(intf, NULL);
 	dev_dbg(&intf->dev, "disconnect\n");
+	kfree(dev->buf);
 	kfree(dev);
 }
 
diff --git a/drivers/usb/mtu3/mtu3_core.c b/drivers/usb/mtu3/mtu3_core.c
index f8bd1d57e795..98b6b17fca64 100644
--- a/drivers/usb/mtu3/mtu3_core.c
+++ b/drivers/usb/mtu3/mtu3_core.c
@@ -130,8 +130,12 @@ static void mtu3_device_disable(struct mtu3 *mtu)
 	mtu3_setbits(ibase, SSUSB_U2_CTRL(0),
 		SSUSB_U2_PORT_DIS | SSUSB_U2_PORT_PDN);
 
-	if (mtu->ssusb->dr_mode == USB_DR_MODE_OTG)
+	if (mtu->ssusb->dr_mode == USB_DR_MODE_OTG) {
 		mtu3_clrbits(ibase, SSUSB_U2_CTRL(0), SSUSB_U2_PORT_OTG_SEL);
+		if (mtu->is_u3_ip)
+			mtu3_clrbits(ibase, SSUSB_U3_CTRL(0),
+				     SSUSB_U3_PORT_DUAL_MODE);
+	}
 
 	mtu3_setbits(ibase, U3D_SSUSB_IP_PW_CTRL2, SSUSB_IP_DEV_PDN);
 }
diff --git a/drivers/usb/musb/jz4740.c b/drivers/usb/musb/jz4740.c
index 5261f8dfedec..e3b8c84ccdb8 100644
--- a/drivers/usb/musb/jz4740.c
+++ b/drivers/usb/musb/jz4740.c
@@ -75,14 +75,17 @@ static struct musb_hdrc_platform_data jz4740_musb_platform_data = {
 static int jz4740_musb_init(struct musb *musb)
 {
 	struct device *dev = musb->controller->parent;
+	int err;
 
 	if (dev->of_node)
 		musb->xceiv = devm_usb_get_phy_by_phandle(dev, "phys", 0);
 	else
 		musb->xceiv = devm_usb_get_phy(dev, USB_PHY_TYPE_USB2);
 	if (IS_ERR(musb->xceiv)) {
-		dev_err(dev, "No transceiver configured\n");
-		return PTR_ERR(musb->xceiv);
+		err = PTR_ERR(musb->xceiv);
+		if (err != -EPROBE_DEFER)
+			dev_err(dev, "No transceiver configured: %d", err);
+		return err;
 	}
 
 	/* Silicon does not implement ConfigData register.
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index 9f5a4819a744..2e97abe51556 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -1843,6 +1843,9 @@ static const struct attribute_group musb_attr_group = {
 #define MUSB_QUIRK_B_INVALID_VBUS_91	(MUSB_DEVCTL_BDEVICE | \
 					 (2 << MUSB_DEVCTL_VBUS_SHIFT) | \
 					 MUSB_DEVCTL_SESSION)
+#define MUSB_QUIRK_B_DISCONNECT_99	(MUSB_DEVCTL_BDEVICE | \
+					 (3 << MUSB_DEVCTL_VBUS_SHIFT) | \
+					 MUSB_DEVCTL_SESSION)
 #define MUSB_QUIRK_A_DISCONNECT_19	((3 << MUSB_DEVCTL_VBUS_SHIFT) | \
 					 MUSB_DEVCTL_SESSION)
 
@@ -1865,6 +1868,11 @@ static void musb_pm_runtime_check_session(struct musb *musb)
 	s = MUSB_DEVCTL_FSDEV | MUSB_DEVCTL_LSDEV |
 		MUSB_DEVCTL_HR;
 	switch (devctl & ~s) {
+	case MUSB_QUIRK_B_DISCONNECT_99:
+		musb_dbg(musb, "Poll devctl in case of suspend after disconnect\n");
+		schedule_delayed_work(&musb->irq_work,
+				      msecs_to_jiffies(1000));
+		break;
 	case MUSB_QUIRK_B_INVALID_VBUS_91:
 		if (musb->quirk_retries && !musb->flush_irq_work) {
 			musb_dbg(musb,
@@ -2317,6 +2325,9 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl)
 	musb_disable_interrupts(musb);
 	musb_writeb(musb->mregs, MUSB_DEVCTL, 0);
 
+	/* MUSB_POWER_SOFTCONN might be already set, JZ4740 does this. */
+	musb_writeb(musb->mregs, MUSB_POWER, 0);
+
 	/* Init IRQ workqueue before request_irq */
 	INIT_DELAYED_WORK(&musb->irq_work, musb_irq_work);
 	INIT_DELAYED_WORK(&musb->deassert_reset_work, musb_deassert_reset);
@@ -2727,6 +2738,13 @@ static int musb_resume(struct device *dev)
 	musb_enable_interrupts(musb);
 	musb_platform_enable(musb);
 
+	/* session might be disabled in suspend */
+	if (musb->port_mode == MUSB_HOST &&
+	    !(musb->ops->quirks & MUSB_PRESERVE_SESSION)) {
+		devctl |= MUSB_DEVCTL_SESSION;
+		musb_writeb(musb->mregs, MUSB_DEVCTL, devctl);
+	}
+
 	spin_lock_irqsave(&musb->lock, flags);
 	error = musb_run_resume_work(musb);
 	if (error)
diff --git a/drivers/usb/musb/musb_debugfs.c b/drivers/usb/musb/musb_debugfs.c
index f42858e2b54c..0c6204add616 100644
--- a/drivers/usb/musb/musb_debugfs.c
+++ b/drivers/usb/musb/musb_debugfs.c
@@ -168,6 +168,11 @@ static ssize_t musb_test_mode_write(struct file *file,
 	u8			test;
 	char			buf[24];
 
+	memset(buf, 0x00, sizeof(buf));
+
+	if (copy_from_user(buf, ubuf, min_t(size_t, sizeof(buf) - 1, count)))
+		return -EFAULT;
+
 	pm_runtime_get_sync(musb->controller);
 	test = musb_readb(musb->mregs, MUSB_TESTMODE);
 	if (test) {
@@ -176,11 +181,6 @@ static ssize_t musb_test_mode_write(struct file *file,
 		goto ret;
 	}
 
-	memset(buf, 0x00, sizeof(buf));
-
-	if (copy_from_user(buf, ubuf, min_t(size_t, sizeof(buf) - 1, count)))
-		return -EFAULT;
-
 	if (strstarts(buf, "force host full-speed"))
 		test = MUSB_TEST_FORCE_HOST | MUSB_TEST_FORCE_FS;
 
diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c
index eb308ec35c66..cb3d7f857d7e 100644
--- a/drivers/usb/musb/musb_host.c
+++ b/drivers/usb/musb/musb_host.c
@@ -1462,10 +1462,7 @@ done:
 	 * We need to map sg if the transfer_buffer is
 	 * NULL.
 	 */
-	if (!urb->transfer_buffer)
-		qh->use_sg = true;
-
-	if (qh->use_sg) {
+	if (!urb->transfer_buffer) {
 		/* sg_miter_start is already done in musb_ep_program */
 		if (!sg_miter_next(&qh->sg_miter)) {
 			dev_err(musb->controller, "error: sg list empty\n");
@@ -1473,9 +1470,8 @@ done:
 			status = -EINVAL;
 			goto done;
 		}
-		urb->transfer_buffer = qh->sg_miter.addr;
 		length = min_t(u32, length, qh->sg_miter.length);
-		musb_write_fifo(hw_ep, length, urb->transfer_buffer);
+		musb_write_fifo(hw_ep, length, qh->sg_miter.addr);
 		qh->sg_miter.consumed = length;
 		sg_miter_stop(&qh->sg_miter);
 	} else {
@@ -1484,11 +1480,6 @@ done:
 
 	qh->segsize = length;
 
-	if (qh->use_sg) {
-		if (offset + length >= urb->transfer_buffer_length)
-			qh->use_sg = false;
-	}
-
 	musb_ep_select(mbase, epnum);
 	musb_writew(epio, MUSB_TXCSR,
 			MUSB_TXCSR_H_WZC_BITS | MUSB_TXCSR_TXPKTRDY);
@@ -2003,8 +1994,10 @@ finish:
 	urb->actual_length += xfer_len;
 	qh->offset += xfer_len;
 	if (done) {
-		if (qh->use_sg)
+		if (qh->use_sg) {
 			qh->use_sg = false;
+			urb->transfer_buffer = NULL;
+		}
 
 		if (urb->status == -EINPROGRESS)
 			urb->status = status;
diff --git a/drivers/usb/musb/musbhsdma.c b/drivers/usb/musb/musbhsdma.c
index 5fc6825745f2..2d3751d885b4 100644
--- a/drivers/usb/musb/musbhsdma.c
+++ b/drivers/usb/musb/musbhsdma.c
@@ -425,7 +425,7 @@ struct dma_controller *musbhs_dma_controller_create(struct musb *musb,
 	controller->controller.channel_abort = dma_channel_abort;
 
 	if (request_irq(irq, dma_controller_irq, 0,
-			dev_name(musb->controller), &controller->controller)) {
+			dev_name(musb->controller), controller)) {
 		dev_err(dev, "request_irq %d failed!\n", irq);
 		musb_dma_controller_destroy(&controller->controller);
 
diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c
index a3d2fef67746..5c93226e0e20 100644
--- a/drivers/usb/musb/omap2430.c
+++ b/drivers/usb/musb/omap2430.c
@@ -361,8 +361,6 @@ static const struct musb_platform_ops omap2430_ops = {
 	.init		= omap2430_musb_init,
 	.exit		= omap2430_musb_exit,
 
-	.set_vbus	= omap2430_musb_set_vbus,
-
 	.enable		= omap2430_musb_enable,
 	.disable	= omap2430_musb_disable,
 
diff --git a/drivers/usb/phy/phy-twl6030-usb.c b/drivers/usb/phy/phy-twl6030-usb.c
index dade34d70419..d6e3ebb70e40 100644
--- a/drivers/usb/phy/phy-twl6030-usb.c
+++ b/drivers/usb/phy/phy-twl6030-usb.c
@@ -374,7 +374,7 @@ static int twl6030_usb_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev, "can't get IRQ %d, err %d\n",
 			twl->irq1, status);
 		device_remove_file(twl->dev, &dev_attr_vbus);
-		return status;
+		goto err_put_regulator;
 	}
 
 	status = request_threaded_irq(twl->irq2, NULL, twl6030_usb_irq,
@@ -383,9 +383,8 @@ static int twl6030_usb_probe(struct platform_device *pdev)
 	if (status < 0) {
 		dev_err(&pdev->dev, "can't get IRQ %d, err %d\n",
 			twl->irq2, status);
-		free_irq(twl->irq1, twl);
 		device_remove_file(twl->dev, &dev_attr_vbus);
-		return status;
+		goto err_free_irq1;
 	}
 
 	twl->asleep = 0;
@@ -394,6 +393,13 @@ static int twl6030_usb_probe(struct platform_device *pdev)
 	dev_info(&pdev->dev, "Initialized TWL6030 USB module\n");
 
 	return 0;
+
+err_free_irq1:
+	free_irq(twl->irq1, twl);
+err_put_regulator:
+	regulator_put(twl->usb3v3);
+
+	return status;
 }
 
 static int twl6030_usb_remove(struct platform_device *pdev)
diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c
index 3bb1fff02bed..390bc4b25045 100644
--- a/drivers/usb/serial/ch341.c
+++ b/drivers/usb/serial/ch341.c
@@ -81,6 +81,7 @@
 
 static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x4348, 0x5523) },
+	{ USB_DEVICE(0x1a86, 0x7522) },
 	{ USB_DEVICE(0x1a86, 0x7523) },
 	{ USB_DEVICE(0x1a86, 0x5523) },
 	{ },
@@ -93,6 +94,7 @@ struct ch341_private {
 	u8 mcr;
 	u8 msr;
 	u8 lcr;
+	unsigned long quirks;
 };
 
 static void ch341_set_termios(struct tty_struct *tty,
@@ -245,6 +247,53 @@ out:	kfree(buffer);
 	return r;
 }
 
+static int ch341_detect_quirks(struct usb_serial_port *port)
+{
+	struct ch341_private *priv = usb_get_serial_port_data(port);
+	struct usb_device *udev = port->serial->dev;
+	const unsigned int size = 2;
+	unsigned long quirks = 0;
+	char *buffer;
+	int r;
+
+	buffer = kmalloc(size, GFP_KERNEL);
+	if (!buffer)
+		return -ENOMEM;
+
+	/*
+	 * A subset of CH34x devices does not support all features. The
+	 * prescaler is limited and there is no support for sending a RS232
+	 * break condition. A read failure when trying to set up the latter is
+	 * used to detect these devices.
+	 */
+	r = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0), CH341_REQ_READ_REG,
+			    USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_IN,
+			    CH341_REG_BREAK, 0, buffer, size, DEFAULT_TIMEOUT);
+	if (r == -EPIPE) {
+		dev_dbg(&port->dev, "break control not supported\n");
+		r = 0;
+		goto out;
+	}
+
+	if (r != size) {
+		if (r >= 0)
+			r = -EIO;
+		dev_err(&port->dev, "failed to read break control: %d\n", r);
+		goto out;
+	}
+
+	r = 0;
+out:
+	kfree(buffer);
+
+	if (quirks) {
+		dev_dbg(&port->dev, "enabling quirk flags: 0x%02lx\n", quirks);
+		priv->quirks |= quirks;
+	}
+
+	return r;
+}
+
 static int ch341_port_probe(struct usb_serial_port *port)
 {
 	struct ch341_private *priv;
@@ -267,6 +316,11 @@ static int ch341_port_probe(struct usb_serial_port *port)
 		goto error;
 
 	usb_set_serial_port_data(port, priv);
+
+	r = ch341_detect_quirks(port);
+	if (r < 0)
+		goto error;
+
 	return 0;
 
 error:	kfree(priv);
@@ -589,9 +643,13 @@ static int ch341_tiocmget(struct tty_struct *tty)
 static int ch341_reset_resume(struct usb_serial *serial)
 {
 	struct usb_serial_port *port = serial->port[0];
-	struct ch341_private *priv = usb_get_serial_port_data(port);
+	struct ch341_private *priv;
 	int ret;
 
+	priv = usb_get_serial_port_data(port);
+	if (!priv)
+		return 0;
+
 	/* reconfigure ch341 serial port after bus-reset */
 	ch341_configure(serial->dev, priv);
 
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index f5143eedbc48..a90801ef0055 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -272,6 +272,8 @@ static struct usb_serial_driver cp210x_device = {
 	.break_ctl		= cp210x_break_ctl,
 	.set_termios		= cp210x_set_termios,
 	.tx_empty		= cp210x_tx_empty,
+	.throttle		= usb_serial_generic_throttle,
+	.unthrottle		= usb_serial_generic_unthrottle,
 	.tiocmget		= cp210x_tiocmget,
 	.tiocmset		= cp210x_tiocmset,
 	.attach			= cp210x_attach,
@@ -915,6 +917,7 @@ static void cp210x_get_termios_port(struct usb_serial_port *port,
 	u32 baud;
 	u16 bits;
 	u32 ctl_hs;
+	u32 flow_repl;
 
 	cp210x_read_u32_reg(port, CP210X_GET_BAUDRATE, &baud);
 
@@ -1015,6 +1018,22 @@ static void cp210x_get_termios_port(struct usb_serial_port *port,
 	ctl_hs = le32_to_cpu(flow_ctl.ulControlHandshake);
 	if (ctl_hs & CP210X_SERIAL_CTS_HANDSHAKE) {
 		dev_dbg(dev, "%s - flow control = CRTSCTS\n", __func__);
+		/*
+		 * When the port is closed, the CP210x hardware disables
+		 * auto-RTS and RTS is deasserted but it leaves auto-CTS when
+		 * in hardware flow control mode. When re-opening the port, if
+		 * auto-CTS is enabled on the cp210x, then auto-RTS must be
+		 * re-enabled in the driver.
+		 */
+		flow_repl = le32_to_cpu(flow_ctl.ulFlowReplace);
+		flow_repl &= ~CP210X_SERIAL_RTS_MASK;
+		flow_repl |= CP210X_SERIAL_RTS_SHIFT(CP210X_SERIAL_RTS_FLOW_CTL);
+		flow_ctl.ulFlowReplace = cpu_to_le32(flow_repl);
+		cp210x_write_reg_block(port,
+				CP210X_SET_FLOW,
+				&flow_ctl,
+				sizeof(flow_ctl));
+
 		cflag |= CRTSCTS;
 	} else {
 		dev_dbg(dev, "%s - flow control = NONE\n", __func__);
diff --git a/drivers/usb/serial/cypress_m8.c b/drivers/usb/serial/cypress_m8.c
index 72d3ae1ebc64..77681229486e 100644
--- a/drivers/usb/serial/cypress_m8.c
+++ b/drivers/usb/serial/cypress_m8.c
@@ -59,6 +59,7 @@ static const struct usb_device_id id_table_earthmate[] = {
 
 static const struct usb_device_id id_table_cyphidcomrs232[] = {
 	{ USB_DEVICE(VENDOR_ID_CYPRESS, PRODUCT_ID_CYPHIDCOM) },
+	{ USB_DEVICE(VENDOR_ID_SAI, PRODUCT_ID_CYPHIDCOM) },
 	{ USB_DEVICE(VENDOR_ID_POWERCOM, PRODUCT_ID_UPS) },
 	{ USB_DEVICE(VENDOR_ID_FRWD, PRODUCT_ID_CYPHIDCOM_FRWD) },
 	{ }						/* Terminating entry */
@@ -73,6 +74,7 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(VENDOR_ID_DELORME, PRODUCT_ID_EARTHMATEUSB) },
 	{ USB_DEVICE(VENDOR_ID_DELORME, PRODUCT_ID_EARTHMATEUSB_LT20) },
 	{ USB_DEVICE(VENDOR_ID_CYPRESS, PRODUCT_ID_CYPHIDCOM) },
+	{ USB_DEVICE(VENDOR_ID_SAI, PRODUCT_ID_CYPHIDCOM) },
 	{ USB_DEVICE(VENDOR_ID_POWERCOM, PRODUCT_ID_UPS) },
 	{ USB_DEVICE(VENDOR_ID_FRWD, PRODUCT_ID_CYPHIDCOM_FRWD) },
 	{ USB_DEVICE(VENDOR_ID_DAZZLE, PRODUCT_ID_CA42) },
diff --git a/drivers/usb/serial/cypress_m8.h b/drivers/usb/serial/cypress_m8.h
index 35e223751c0e..16b7410ad057 100644
--- a/drivers/usb/serial/cypress_m8.h
+++ b/drivers/usb/serial/cypress_m8.h
@@ -25,6 +25,9 @@
 #define VENDOR_ID_CYPRESS		0x04b4
 #define PRODUCT_ID_CYPHIDCOM		0x5500
 
+/* Simply Automated HID->COM UPB PIM (using Cypress PID 0x5500) */
+#define VENDOR_ID_SAI			0x17dd
+
 /* FRWD Dongle - a GPS sports watch */
 #define VENDOR_ID_FRWD			0x6737
 #define PRODUCT_ID_CYPHIDCOM_FRWD	0x0001
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 0346b046cca2..13aaf0687367 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -2437,12 +2437,11 @@ static int ftdi_prepare_write_buffer(struct usb_serial_port *port,
 #define FTDI_RS_ERR_MASK (FTDI_RS_BI | FTDI_RS_PE | FTDI_RS_FE | FTDI_RS_OE)
 
 static int ftdi_process_packet(struct usb_serial_port *port,
-		struct ftdi_private *priv, char *packet, int len)
+		struct ftdi_private *priv, unsigned char *buf, int len)
 {
+	unsigned char status;
 	int i;
-	char status;
 	char flag;
-	char *ch;
 
 	if (len < 2) {
 		dev_dbg(&port->dev, "malformed packet\n");
@@ -2452,7 +2451,7 @@ static int ftdi_process_packet(struct usb_serial_port *port,
 	/* Compare new line status to the old one, signal if different/
 	   N.B. packet may be processed more than once, but differences
 	   are only processed once.  */
-	status = packet[0] & FTDI_STATUS_B0_MASK;
+	status = buf[0] & FTDI_STATUS_B0_MASK;
 	if (status != priv->prev_status) {
 		char diff_status = status ^ priv->prev_status;
 
@@ -2478,13 +2477,12 @@ static int ftdi_process_packet(struct usb_serial_port *port,
 	}
 
 	/* save if the transmitter is empty or not */
-	if (packet[1] & FTDI_RS_TEMT)
+	if (buf[1] & FTDI_RS_TEMT)
 		priv->transmit_empty = 1;
 	else
 		priv->transmit_empty = 0;
 
-	len -= 2;
-	if (!len)
+	if (len == 2)
 		return 0;	/* status only */
 
 	/*
@@ -2492,40 +2490,41 @@ static int ftdi_process_packet(struct usb_serial_port *port,
 	 * data payload to avoid over-reporting.
 	 */
 	flag = TTY_NORMAL;
-	if (packet[1] & FTDI_RS_ERR_MASK) {
+	if (buf[1] & FTDI_RS_ERR_MASK) {
 		/* Break takes precedence over parity, which takes precedence
 		 * over framing errors */
-		if (packet[1] & FTDI_RS_BI) {
+		if (buf[1] & FTDI_RS_BI) {
 			flag = TTY_BREAK;
 			port->icount.brk++;
 			usb_serial_handle_break(port);
-		} else if (packet[1] & FTDI_RS_PE) {
+		} else if (buf[1] & FTDI_RS_PE) {
 			flag = TTY_PARITY;
 			port->icount.parity++;
-		} else if (packet[1] & FTDI_RS_FE) {
+		} else if (buf[1] & FTDI_RS_FE) {
 			flag = TTY_FRAME;
 			port->icount.frame++;
 		}
 		/* Overrun is special, not associated with a char */
-		if (packet[1] & FTDI_RS_OE) {
+		if (buf[1] & FTDI_RS_OE) {
 			port->icount.overrun++;
 			tty_insert_flip_char(&port->port, 0, TTY_OVERRUN);
 		}
 	}
 
-	port->icount.rx += len;
-	ch = packet + 2;
+	port->icount.rx += len - 2;
 
 	if (port->port.console && port->sysrq) {
-		for (i = 0; i < len; i++, ch++) {
-			if (!usb_serial_handle_sysrq_char(port, *ch))
-				tty_insert_flip_char(&port->port, *ch, flag);
+		for (i = 2; i < len; i++) {
+			if (usb_serial_handle_sysrq_char(port, buf[i]))
+				continue;
+			tty_insert_flip_char(&port->port, buf[i], flag);
 		}
 	} else {
-		tty_insert_flip_string_fixed_flag(&port->port, ch, flag, len);
+		tty_insert_flip_string_fixed_flag(&port->port, buf + 2, flag,
+				len - 2);
 	}
 
-	return len;
+	return len - 2;
 }
 
 static void ftdi_process_read_urb(struct urb *urb)
diff --git a/drivers/usb/serial/garmin_gps.c b/drivers/usb/serial/garmin_gps.c
index 633550ec3025..f29c3a936a08 100644
--- a/drivers/usb/serial/garmin_gps.c
+++ b/drivers/usb/serial/garmin_gps.c
@@ -1138,8 +1138,8 @@ static void garmin_read_process(struct garmin_data *garmin_data_p,
 		   send it directly to the tty port */
 		if (garmin_data_p->flags & FLAGS_QUEUING) {
 			pkt_add(garmin_data_p, data, data_length);
-		} else if (bulk_data ||
-			   getLayerId(data) == GARMIN_LAYERID_APPL) {
+		} else if (bulk_data || (data_length >= sizeof(u32) &&
+				getLayerId(data) == GARMIN_LAYERID_APPL)) {
 
 			spin_lock_irqsave(&garmin_data_p->lock, flags);
 			garmin_data_p->flags |= APP_RESP_SEEN;
diff --git a/drivers/usb/serial/io_edgeport.c b/drivers/usb/serial/io_edgeport.c
index 9690a5f4b9d6..4cca0b836f43 100644
--- a/drivers/usb/serial/io_edgeport.c
+++ b/drivers/usb/serial/io_edgeport.c
@@ -710,13 +710,13 @@ static void edge_interrupt_callback(struct urb *urb)
 		/* grab the txcredits for the ports if available */
 		position = 2;
 		portNumber = 0;
-		while ((position < length) &&
+		while ((position < length - 1) &&
 				(portNumber < edge_serial->serial->num_ports)) {
 			txCredits = data[position] | (data[position+1] << 8);
 			if (txCredits) {
 				port = edge_serial->serial->port[portNumber];
 				edge_port = usb_get_serial_port_data(port);
-				if (edge_port->open) {
+				if (edge_port && edge_port->open) {
 					spin_lock_irqsave(&edge_port->ep_lock,
 							  flags);
 					edge_port->txCredits += txCredits;
@@ -1725,7 +1725,8 @@ static void edge_break(struct tty_struct *tty, int break_state)
 static void process_rcvd_data(struct edgeport_serial *edge_serial,
 				unsigned char *buffer, __u16 bufferLength)
 {
-	struct device *dev = &edge_serial->serial->dev->dev;
+	struct usb_serial *serial = edge_serial->serial;
+	struct device *dev = &serial->dev->dev;
 	struct usb_serial_port *port;
 	struct edgeport_port *edge_port;
 	__u16 lastBufferLength;
@@ -1821,11 +1822,10 @@ static void process_rcvd_data(struct edgeport_serial *edge_serial,
 
 			/* spit this data back into the tty driver if this
 			   port is open */
-			if (rxLen) {
-				port = edge_serial->serial->port[
-							edge_serial->rxPort];
+			if (rxLen && edge_serial->rxPort < serial->num_ports) {
+				port = serial->port[edge_serial->rxPort];
 				edge_port = usb_get_serial_port_data(port);
-				if (edge_port->open) {
+				if (edge_port && edge_port->open) {
 					dev_dbg(dev, "%s - Sending %d bytes to TTY for port %d\n",
 						__func__, rxLen,
 						edge_serial->rxPort);
@@ -1833,8 +1833,8 @@ static void process_rcvd_data(struct edgeport_serial *edge_serial,
 							rxLen);
 					edge_port->port->icount.rx += rxLen;
 				}
-				buffer += rxLen;
 			}
+			buffer += rxLen;
 			break;
 
 		case EXPECT_HDR3:	/* Expect 3rd byte of status header */
@@ -1869,6 +1869,8 @@ static void process_rcvd_status(struct edgeport_serial *edge_serial,
 	__u8 code = edge_serial->rxStatusCode;
 
 	/* switch the port pointer to the one being currently talked about */
+	if (edge_serial->rxPort >= edge_serial->serial->num_ports)
+		return;
 	port = edge_serial->serial->port[edge_serial->rxPort];
 	edge_port = usb_get_serial_port_data(port);
 	if (edge_port == NULL) {
diff --git a/drivers/usb/serial/ir-usb.c b/drivers/usb/serial/ir-usb.c
index 7643716b5299..badd38586b54 100644
--- a/drivers/usb/serial/ir-usb.c
+++ b/drivers/usb/serial/ir-usb.c
@@ -45,9 +45,10 @@ static int buffer_size;
 static int xbof = -1;
 
 static int  ir_startup (struct usb_serial *serial);
-static int  ir_open(struct tty_struct *tty, struct usb_serial_port *port);
-static int ir_prepare_write_buffer(struct usb_serial_port *port,
-						void *dest, size_t size);
+static int ir_write(struct tty_struct *tty, struct usb_serial_port *port,
+		const unsigned char *buf, int count);
+static int ir_write_room(struct tty_struct *tty);
+static void ir_write_bulk_callback(struct urb *urb);
 static void ir_process_read_urb(struct urb *urb);
 static void ir_set_termios(struct tty_struct *tty,
 		struct usb_serial_port *port, struct ktermios *old_termios);
@@ -77,8 +78,9 @@ static struct usb_serial_driver ir_device = {
 	.num_ports		= 1,
 	.set_termios		= ir_set_termios,
 	.attach			= ir_startup,
-	.open			= ir_open,
-	.prepare_write_buffer	= ir_prepare_write_buffer,
+	.write			= ir_write,
+	.write_room		= ir_write_room,
+	.write_bulk_callback	= ir_write_bulk_callback,
 	.process_read_urb	= ir_process_read_urb,
 };
 
@@ -195,6 +197,9 @@ static int ir_startup(struct usb_serial *serial)
 	struct usb_irda_cs_descriptor *irda_desc;
 	int rates;
 
+	if (serial->num_bulk_in < 1 || serial->num_bulk_out < 1)
+		return -ENODEV;
+
 	irda_desc = irda_usb_find_class_desc(serial, 0);
 	if (!irda_desc) {
 		dev_err(&serial->dev->dev,
@@ -251,35 +256,102 @@ static int ir_startup(struct usb_serial *serial)
 	return 0;
 }
 
-static int ir_open(struct tty_struct *tty, struct usb_serial_port *port)
+static int ir_write(struct tty_struct *tty, struct usb_serial_port *port,
+		const unsigned char *buf, int count)
 {
-	int i;
+	struct urb *urb = NULL;
+	unsigned long flags;
+	int ret;
 
-	for (i = 0; i < ARRAY_SIZE(port->write_urbs); ++i)
-		port->write_urbs[i]->transfer_flags = URB_ZERO_PACKET;
+	if (port->bulk_out_size == 0)
+		return -EINVAL;
 
-	/* Start reading from the device */
-	return usb_serial_generic_open(tty, port);
-}
+	if (count == 0)
+		return 0;
 
-static int ir_prepare_write_buffer(struct usb_serial_port *port,
-						void *dest, size_t size)
-{
-	unsigned char *buf = dest;
-	int count;
+	count = min(count, port->bulk_out_size - 1);
+
+	spin_lock_irqsave(&port->lock, flags);
+	if (__test_and_clear_bit(0, &port->write_urbs_free)) {
+		urb = port->write_urbs[0];
+		port->tx_bytes += count;
+	}
+	spin_unlock_irqrestore(&port->lock, flags);
+
+	if (!urb)
+		return 0;
 
 	/*
 	 * The first byte of the packet we send to the device contains an
-	 * inbound header which indicates an additional number of BOFs and
+	 * outbound header which indicates an additional number of BOFs and
 	 * a baud rate change.
 	 *
 	 * See section 5.4.2.2 of the USB IrDA spec.
 	 */
-	*buf = ir_xbof | ir_baud;
+	*(u8 *)urb->transfer_buffer = ir_xbof | ir_baud;
+
+	memcpy(urb->transfer_buffer + 1, buf, count);
+
+	urb->transfer_buffer_length = count + 1;
+	urb->transfer_flags = URB_ZERO_PACKET;
+
+	ret = usb_submit_urb(urb, GFP_ATOMIC);
+	if (ret) {
+		dev_err(&port->dev, "failed to submit write urb: %d\n", ret);
+
+		spin_lock_irqsave(&port->lock, flags);
+		__set_bit(0, &port->write_urbs_free);
+		port->tx_bytes -= count;
+		spin_unlock_irqrestore(&port->lock, flags);
+
+		return ret;
+	}
+
+	return count;
+}
+
+static void ir_write_bulk_callback(struct urb *urb)
+{
+	struct usb_serial_port *port = urb->context;
+	int status = urb->status;
+	unsigned long flags;
+
+	spin_lock_irqsave(&port->lock, flags);
+	__set_bit(0, &port->write_urbs_free);
+	port->tx_bytes -= urb->transfer_buffer_length - 1;
+	spin_unlock_irqrestore(&port->lock, flags);
+
+	switch (status) {
+	case 0:
+		break;
+	case -ENOENT:
+	case -ECONNRESET:
+	case -ESHUTDOWN:
+		dev_dbg(&port->dev, "write urb stopped: %d\n", status);
+		return;
+	case -EPIPE:
+		dev_err(&port->dev, "write urb stopped: %d\n", status);
+		return;
+	default:
+		dev_err(&port->dev, "nonzero write-urb status: %d\n", status);
+		break;
+	}
+
+	usb_serial_port_softint(port);
+}
+
+static int ir_write_room(struct tty_struct *tty)
+{
+	struct usb_serial_port *port = tty->driver_data;
+	int count = 0;
+
+	if (port->bulk_out_size == 0)
+		return 0;
+
+	if (test_bit(0, &port->write_urbs_free))
+		count = port->bulk_out_size - 1;
 
-	count = kfifo_out_locked(&port->write_fifo, buf + 1, size - 1,
-								&port->lock);
-	return count + 1;
+	return count;
 }
 
 static void ir_process_read_urb(struct urb *urb)
@@ -332,34 +404,34 @@ static void ir_set_termios(struct tty_struct *tty,
 
 	switch (baud) {
 	case 2400:
-		ir_baud = USB_IRDA_BR_2400;
+		ir_baud = USB_IRDA_LS_2400;
 		break;
 	case 9600:
-		ir_baud = USB_IRDA_BR_9600;
+		ir_baud = USB_IRDA_LS_9600;
 		break;
 	case 19200:
-		ir_baud = USB_IRDA_BR_19200;
+		ir_baud = USB_IRDA_LS_19200;
 		break;
 	case 38400:
-		ir_baud = USB_IRDA_BR_38400;
+		ir_baud = USB_IRDA_LS_38400;
 		break;
 	case 57600:
-		ir_baud = USB_IRDA_BR_57600;
+		ir_baud = USB_IRDA_LS_57600;
 		break;
 	case 115200:
-		ir_baud = USB_IRDA_BR_115200;
+		ir_baud = USB_IRDA_LS_115200;
 		break;
 	case 576000:
-		ir_baud = USB_IRDA_BR_576000;
+		ir_baud = USB_IRDA_LS_576000;
 		break;
 	case 1152000:
-		ir_baud = USB_IRDA_BR_1152000;
+		ir_baud = USB_IRDA_LS_1152000;
 		break;
 	case 4000000:
-		ir_baud = USB_IRDA_BR_4000000;
+		ir_baud = USB_IRDA_LS_4000000;
 		break;
 	default:
-		ir_baud = USB_IRDA_BR_9600;
+		ir_baud = USB_IRDA_LS_9600;
 		baud = 9600;
 	}
 
diff --git a/drivers/usb/serial/iuu_phoenix.c b/drivers/usb/serial/iuu_phoenix.c
index d5bff69b1769..ffbb2a8901b2 100644
--- a/drivers/usb/serial/iuu_phoenix.c
+++ b/drivers/usb/serial/iuu_phoenix.c
@@ -353,10 +353,11 @@ static void iuu_led_activity_on(struct urb *urb)
 	struct usb_serial_port *port = urb->context;
 	int result;
 	char *buf_ptr = port->write_urb->transfer_buffer;
-	*buf_ptr++ = IUU_SET_LED;
+
 	if (xmas) {
-		get_random_bytes(buf_ptr, 6);
-		*(buf_ptr+7) = 1;
+		buf_ptr[0] = IUU_SET_LED;
+		get_random_bytes(buf_ptr + 1, 6);
+		buf_ptr[7] = 1;
 	} else {
 		iuu_rgbf_fill_buffer(buf_ptr, 255, 255, 0, 0, 0, 0, 255);
 	}
@@ -374,13 +375,14 @@ static void iuu_led_activity_off(struct urb *urb)
 	struct usb_serial_port *port = urb->context;
 	int result;
 	char *buf_ptr = port->write_urb->transfer_buffer;
+
 	if (xmas) {
 		iuu_rxcmd(urb);
 		return;
-	} else {
-		*buf_ptr++ = IUU_SET_LED;
-		iuu_rgbf_fill_buffer(buf_ptr, 0, 0, 255, 255, 0, 0, 255);
 	}
+
+	iuu_rgbf_fill_buffer(buf_ptr, 0, 0, 255, 255, 0, 0, 255);
+
 	usb_fill_bulk_urb(port->write_urb, port->serial->dev,
 			  usb_sndbulkpipe(port->serial->dev,
 					  port->bulk_out_endpointAddress),
@@ -697,14 +699,16 @@ static int iuu_uart_write(struct tty_struct *tty, struct usb_serial_port *port,
 	struct iuu_private *priv = usb_get_serial_port_data(port);
 	unsigned long flags;
 
-	if (count > 256)
-		return -ENOMEM;
-
 	spin_lock_irqsave(&priv->lock, flags);
 
+	count = min(count, 256 - priv->writelen);
+	if (count == 0)
+		goto out;
+
 	/* fill the buffer */
 	memcpy(priv->writebuf + priv->writelen, buf, count);
 	priv->writelen += count;
+out:
 	spin_unlock_irqrestore(&priv->lock, flags);
 
 	return count;
diff --git a/drivers/usb/serial/keyspan.c b/drivers/usb/serial/keyspan.c
index e66a59ef43a1..aa3dbce22cfb 100644
--- a/drivers/usb/serial/keyspan.c
+++ b/drivers/usb/serial/keyspan.c
@@ -1058,6 +1058,8 @@ static void	usa49_glocont_callback(struct urb *urb)
 	for (i = 0; i < serial->num_ports; ++i) {
 		port = serial->port[i];
 		p_priv = usb_get_serial_port_data(port);
+		if (!p_priv)
+			continue;
 
 		if (p_priv->resend_cont) {
 			dev_dbg(&port->dev, "%s - sending setup\n", __func__);
@@ -1459,6 +1461,8 @@ static void usa67_glocont_callback(struct urb *urb)
 	for (i = 0; i < serial->num_ports; ++i) {
 		port = serial->port[i];
 		p_priv = usb_get_serial_port_data(port);
+		if (!p_priv)
+			continue;
 
 		if (p_priv->resend_cont) {
 			dev_dbg(&port->dev, "%s - sending setup\n", __func__);
diff --git a/drivers/usb/serial/opticon.c b/drivers/usb/serial/opticon.c
index cb7aac9cd9e7..ed2b4e6dca38 100644
--- a/drivers/usb/serial/opticon.c
+++ b/drivers/usb/serial/opticon.c
@@ -113,7 +113,7 @@ static int send_control_msg(struct usb_serial_port *port, u8 requesttype,
 	retval = usb_control_msg(serial->dev, usb_sndctrlpipe(serial->dev, 0),
 				requesttype,
 				USB_DIR_OUT|USB_TYPE_VENDOR|USB_RECIP_INTERFACE,
-				0, 0, buffer, 1, 0);
+				0, 0, buffer, 1, USB_CTRL_SET_TIMEOUT);
 	kfree(buffer);
 
 	if (retval < 0)
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index e9491d400a24..9b7cee98ea60 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -245,9 +245,11 @@ static void option_instat_callback(struct urb *urb);
 /* These Quectel products use Quectel's vendor ID */
 #define QUECTEL_PRODUCT_EC21			0x0121
 #define QUECTEL_PRODUCT_EC25			0x0125
+#define QUECTEL_PRODUCT_EG95			0x0195
 #define QUECTEL_PRODUCT_BG96			0x0296
 #define QUECTEL_PRODUCT_EP06			0x0306
 #define QUECTEL_PRODUCT_EM12			0x0512
+#define QUECTEL_PRODUCT_RM500Q			0x0800
 
 #define CMOTECH_VENDOR_ID			0x16d8
 #define CMOTECH_PRODUCT_6001			0x6001
@@ -567,6 +569,9 @@ static void option_instat_callback(struct urb *urb);
 /* Interface must have two endpoints */
 #define NUMEP2		BIT(16)
 
+/* Device needs ZLP */
+#define ZLP		BIT(17)
+
 
 static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_COLT) },
@@ -1093,6 +1098,8 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = RSVD(4) },
 	{ USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC25),
 	  .driver_info = RSVD(4) },
+	{ USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG95),
+	  .driver_info = RSVD(4) },
 	{ USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_BG96),
 	  .driver_info = RSVD(4) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0xff, 0xff),
@@ -1101,6 +1108,11 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM12, 0xff, 0xff, 0xff),
 	  .driver_info = RSVD(1) | RSVD(2) | RSVD(3) | RSVD(4) | NUMEP2 },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM12, 0xff, 0, 0) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0xff, 0x30) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0, 0) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0xff, 0x10),
+	  .driver_info = ZLP },
+
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) },
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) },
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6003),
@@ -1148,6 +1160,10 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_CC864_SINGLE) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_DE910_DUAL) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_UE910_V2) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1031, 0xff),	/* Telit LE910C1-EUX */
+	 .driver_info = NCTRL(0) | RSVD(3) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1033, 0xff),	/* Telit LE910C1-EUX (ECM) */
+	 .driver_info = NCTRL(0) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG0),
 	  .driver_info = RSVD(0) | RSVD(1) | NCTRL(2) | RSVD(3) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG1),
@@ -1172,6 +1188,10 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = NCTRL(0) | RSVD(3) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1102, 0xff),	/* Telit ME910 (ECM) */
 	  .driver_info = NCTRL(0) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x110a, 0xff),	/* Telit ME910G1 */
+	  .driver_info = NCTRL(0) | RSVD(3) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x110b, 0xff),	/* Telit ME910G1 (ECM) */
+	  .driver_info = NCTRL(0) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910),
 	  .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910_USBCFG4),
@@ -1196,6 +1216,8 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = NCTRL(0) | RSVD(1) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1901, 0xff),	/* Telit LN940 (MBIM) */
 	  .driver_info = NCTRL(0) },
+	{ USB_DEVICE(TELIT_VENDOR_ID, 0x9010),				/* Telit SBL FN980 flashing device */
+	  .driver_info = NCTRL(0) | ZLP },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF622, 0xff, 0xff, 0xff) }, /* ZTE WCDMA products */
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0002, 0xff, 0xff, 0xff),
 	  .driver_info = RSVD(1) },
@@ -1977,8 +1999,14 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) },	/* D-Link DWM-152/C1 */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) },	/* D-Link DWM-156/C1 */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x7e11, 0xff, 0xff, 0xff) },	/* D-Link DWM-156/A3 */
+	{ USB_DEVICE_INTERFACE_CLASS(0x1435, 0xd191, 0xff),			/* Wistron Neweb D19Q1 */
+	  .driver_info = RSVD(1) | RSVD(4) },
+	{ USB_DEVICE_INTERFACE_CLASS(0x1690, 0x7588, 0xff),			/* ASKEY WWHC050 */
+	  .driver_info = RSVD(1) | RSVD(4) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x2020, 0x2031, 0xff),			/* Olicard 600 */
 	  .driver_info = RSVD(4) },
+	{ USB_DEVICE_INTERFACE_CLASS(0x2020, 0x2033, 0xff),			/* BroadMobi BM806U */
+	  .driver_info = RSVD(4) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x2020, 0x2060, 0xff),			/* BroadMobi BM818 */
 	  .driver_info = RSVD(4) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x2020, 0x4000, 0xff) },			/* OLICARD300 - MT6225 */
@@ -2003,6 +2031,9 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = RSVD(4) | RSVD(5) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0105, 0xff),			/* Fibocom NL678 series */
 	  .driver_info = RSVD(6) },
+	{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1404, 0xff) },			/* GosunCn GM500 RNDIS */
+	{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1405, 0xff) },			/* GosunCn GM500 MBIM */
+	{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1406, 0xff) },			/* GosunCn GM500 ECM/NCM */
 	{ } /* Terminating entry */
 };
 MODULE_DEVICE_TABLE(usb, option_ids);
@@ -2097,6 +2128,9 @@ static int option_attach(struct usb_serial *serial)
 	if (!(device_flags & NCTRL(iface_desc->bInterfaceNumber)))
 		data->use_send_setup = 1;
 
+	if (device_flags & ZLP)
+		data->use_zlp = 1;
+
 	spin_lock_init(&data->susp_lock);
 
 	usb_set_serial_data(serial, data);
diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c
index d7abde14b3cf..1322c657b951 100644
--- a/drivers/usb/serial/pl2303.c
+++ b/drivers/usb/serial/pl2303.c
@@ -93,6 +93,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(SUPERIAL_VENDOR_ID, SUPERIAL_PRODUCT_ID) },
 	{ USB_DEVICE(HP_VENDOR_ID, HP_LD220_PRODUCT_ID) },
 	{ USB_DEVICE(HP_VENDOR_ID, HP_LD220TA_PRODUCT_ID) },
+	{ USB_DEVICE(HP_VENDOR_ID, HP_LD381_PRODUCT_ID) },
 	{ USB_DEVICE(HP_VENDOR_ID, HP_LD960_PRODUCT_ID) },
 	{ USB_DEVICE(HP_VENDOR_ID, HP_LD960TA_PRODUCT_ID) },
 	{ USB_DEVICE(HP_VENDOR_ID, HP_LCM220_PRODUCT_ID) },
diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h
index b0175f17d1a2..c98db6b650a5 100644
--- a/drivers/usb/serial/pl2303.h
+++ b/drivers/usb/serial/pl2303.h
@@ -124,6 +124,7 @@
 #define HP_LM920_PRODUCT_ID	0x026b
 #define HP_TD620_PRODUCT_ID	0x0956
 #define HP_LD960_PRODUCT_ID	0x0b39
+#define HP_LD381_PRODUCT_ID	0x0f7f
 #define HP_LCM220_PRODUCT_ID	0x3139
 #define HP_LCM960_PRODUCT_ID	0x3239
 #define HP_LD220_PRODUCT_ID	0x3524
diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index 613f91add03d..0f60363c1bbc 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -155,6 +155,7 @@ static const struct usb_device_id id_table[] = {
 	{DEVICE_SWI(0x1199, 0x9056)},	/* Sierra Wireless Modem */
 	{DEVICE_SWI(0x1199, 0x9060)},	/* Sierra Wireless Modem */
 	{DEVICE_SWI(0x1199, 0x9061)},	/* Sierra Wireless Modem */
+	{DEVICE_SWI(0x1199, 0x9062)},	/* Sierra Wireless EM7305 QDL */
 	{DEVICE_SWI(0x1199, 0x9063)},	/* Sierra Wireless EM7305 */
 	{DEVICE_SWI(0x1199, 0x9070)},	/* Sierra Wireless MC74xx */
 	{DEVICE_SWI(0x1199, 0x9071)},	/* Sierra Wireless MC74xx */
@@ -173,6 +174,8 @@ static const struct usb_device_id id_table[] = {
 	{DEVICE_SWI(0x413c, 0x81b3)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
 	{DEVICE_SWI(0x413c, 0x81b5)},	/* Dell Wireless 5811e QDL */
 	{DEVICE_SWI(0x413c, 0x81b6)},	/* Dell Wireless 5811e QDL */
+	{DEVICE_SWI(0x413c, 0x81cb)},	/* Dell Wireless 5816e QDL */
+	{DEVICE_SWI(0x413c, 0x81cc)},	/* Dell Wireless 5816e */
 	{DEVICE_SWI(0x413c, 0x81cf)},   /* Dell Wireless 5819 */
 	{DEVICE_SWI(0x413c, 0x81d0)},   /* Dell Wireless 5819 */
 	{DEVICE_SWI(0x413c, 0x81d1)},   /* Dell Wireless 5818 */
diff --git a/drivers/usb/serial/quatech2.c b/drivers/usb/serial/quatech2.c
index a62981ca7a73..f93b81a297d6 100644
--- a/drivers/usb/serial/quatech2.c
+++ b/drivers/usb/serial/quatech2.c
@@ -841,7 +841,10 @@ static void qt2_update_msr(struct usb_serial_port *port, unsigned char *ch)
 	u8 newMSR = (u8) *ch;
 	unsigned long flags;
 
+	/* May be called from qt2_process_read_urb() for an unbound port. */
 	port_priv = usb_get_serial_port_data(port);
+	if (!port_priv)
+		return;
 
 	spin_lock_irqsave(&port_priv->lock, flags);
 	port_priv->shadowMSR = newMSR;
@@ -869,7 +872,10 @@ static void qt2_update_lsr(struct usb_serial_port *port, unsigned char *ch)
 	unsigned long flags;
 	u8 newLSR = (u8) *ch;
 
+	/* May be called from qt2_process_read_urb() for an unbound port. */
 	port_priv = usb_get_serial_port_data(port);
+	if (!port_priv)
+		return;
 
 	if (newLSR & UART_LSR_BI)
 		newLSR &= (u8) (UART_LSR_OE | UART_LSR_BI);
diff --git a/drivers/usb/serial/usb-serial-simple.c b/drivers/usb/serial/usb-serial-simple.c
index edbbb13d6de6..bd23a7cb1be2 100644
--- a/drivers/usb/serial/usb-serial-simple.c
+++ b/drivers/usb/serial/usb-serial-simple.c
@@ -86,6 +86,8 @@ DEVICE(moto_modem, MOTO_IDS);
 #define MOTOROLA_TETRA_IDS()			\
 	{ USB_DEVICE(0x0cad, 0x9011) },	/* Motorola Solutions TETRA PEI */ \
 	{ USB_DEVICE(0x0cad, 0x9012) },	/* MTP6550 */ \
+	{ USB_DEVICE(0x0cad, 0x9013) },	/* MTP3xxx */ \
+	{ USB_DEVICE(0x0cad, 0x9015) },	/* MTP85xx */ \
 	{ USB_DEVICE(0x0cad, 0x9016) }	/* TPG2200 */
 DEVICE(motorola_tetra, MOTOROLA_TETRA_IDS);
 
diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index 270fb4e2ca1c..320479dec1a3 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -1317,6 +1317,9 @@ static int usb_serial_register(struct usb_serial_driver *driver)
 		return -EINVAL;
 	}
 
+	/* Prevent individual ports from being unbound. */
+	driver->driver.suppress_bind_attrs = true;
+
 	usb_serial_operations_init(driver);
 
 	/* Add this device to our list of devices */
diff --git a/drivers/usb/serial/usb-wwan.h b/drivers/usb/serial/usb-wwan.h
index 1c120eaf4091..934e9361cf6b 100644
--- a/drivers/usb/serial/usb-wwan.h
+++ b/drivers/usb/serial/usb-wwan.h
@@ -38,6 +38,7 @@ struct usb_wwan_intf_private {
 	spinlock_t susp_lock;
 	unsigned int suspended:1;
 	unsigned int use_send_setup:1;
+	unsigned int use_zlp:1;
 	int in_flight;
 	unsigned int open_ports;
 	void *private;
diff --git a/drivers/usb/serial/usb_wwan.c b/drivers/usb/serial/usb_wwan.c
index 7e855c87e4f7..4b9845807bee 100644
--- a/drivers/usb/serial/usb_wwan.c
+++ b/drivers/usb/serial/usb_wwan.c
@@ -270,6 +270,10 @@ static void usb_wwan_indat_callback(struct urb *urb)
 	if (status) {
 		dev_dbg(dev, "%s: nonzero status: %d on endpoint %02x.\n",
 			__func__, status, endpoint);
+
+		/* don't resubmit on fatal errors */
+		if (status == -ESHUTDOWN || status == -ENOENT)
+			return;
 	} else {
 		if (urb->actual_length) {
 			tty_insert_flip_string(&port->port, data,
@@ -461,6 +465,7 @@ static struct urb *usb_wwan_setup_urb(struct usb_serial_port *port,
 				      void (*callback) (struct urb *))
 {
 	struct usb_serial *serial = port->serial;
+	struct usb_wwan_intf_private *intfdata = usb_get_serial_data(serial);
 	struct urb *urb;
 
 	urb = usb_alloc_urb(0, GFP_KERNEL);	/* No ISO */
@@ -471,6 +476,9 @@ static struct urb *usb_wwan_setup_urb(struct usb_serial_port *port,
 			  usb_sndbulkpipe(serial->dev, endpoint) | dir,
 			  buf, len, callback, ctx);
 
+	if (intfdata->use_zlp && dir == USB_DIR_OUT)
+		urb->transfer_flags |= URB_ZERO_PACKET;
+
 	return urb;
 }
 
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index 80448ecf6b6a..de4d33fbf6b8 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -45,6 +45,7 @@ struct uas_dev_info {
 	struct scsi_cmnd *cmnd[MAX_CMNDS];
 	spinlock_t lock;
 	struct work_struct work;
+	struct work_struct scan_work;      /* for async scanning */
 };
 
 enum {
@@ -80,6 +81,19 @@ static void uas_free_streams(struct uas_dev_info *devinfo);
 static void uas_log_cmd_state(struct scsi_cmnd *cmnd, const char *prefix,
 				int status);
 
+/*
+ * This driver needs its own workqueue, as we need to control memory allocation.
+ *
+ * In the course of error handling and power management uas_wait_for_pending_cmnds()
+ * needs to flush pending work items. In these contexts we cannot allocate memory
+ * by doing block IO as we would deadlock. For the same reason we cannot wait
+ * for anything allocating memory not heeding these constraints.
+ *
+ * So we have to control all work items that can be on the workqueue we flush.
+ * Hence we cannot share a queue and need our own.
+ */
+static struct workqueue_struct *workqueue;
+
 static void uas_do_work(struct work_struct *work)
 {
 	struct uas_dev_info *devinfo =
@@ -108,12 +122,23 @@ static void uas_do_work(struct work_struct *work)
 		if (!err)
 			cmdinfo->state &= ~IS_IN_WORK_LIST;
 		else
-			schedule_work(&devinfo->work);
+			queue_work(workqueue, &devinfo->work);
 	}
 out:
 	spin_unlock_irqrestore(&devinfo->lock, flags);
 }
 
+static void uas_scan_work(struct work_struct *work)
+{
+	struct uas_dev_info *devinfo =
+		container_of(work, struct uas_dev_info, scan_work);
+	struct Scsi_Host *shost = usb_get_intfdata(devinfo->intf);
+
+	dev_dbg(&devinfo->intf->dev, "starting scan\n");
+	scsi_scan_host(shost);
+	dev_dbg(&devinfo->intf->dev, "scan complete\n");
+}
+
 static void uas_add_work(struct uas_cmd_info *cmdinfo)
 {
 	struct scsi_pointer *scp = (void *)cmdinfo;
@@ -122,7 +147,7 @@ static void uas_add_work(struct uas_cmd_info *cmdinfo)
 
 	lockdep_assert_held(&devinfo->lock);
 	cmdinfo->state |= IS_IN_WORK_LIST;
-	schedule_work(&devinfo->work);
+	queue_work(workqueue, &devinfo->work);
 }
 
 static void uas_zap_pending(struct uas_dev_info *devinfo, int result)
@@ -178,6 +203,9 @@ static void uas_log_cmd_state(struct scsi_cmnd *cmnd, const char *prefix,
 	struct uas_cmd_info *ci = (void *)&cmnd->SCp;
 	struct uas_cmd_info *cmdinfo = (void *)&cmnd->SCp;
 
+	if (status == -ENODEV) /* too late */
+		return;
+
 	scmd_printk(KERN_INFO, cmnd,
 		    "%s %d uas-tag %d inflight:%s%s%s%s%s%s%s%s%s%s%s%s ",
 		    prefix, status, cmdinfo->uas_tag,
@@ -983,6 +1011,7 @@ static int uas_probe(struct usb_interface *intf, const struct usb_device_id *id)
 	init_usb_anchor(&devinfo->data_urbs);
 	spin_lock_init(&devinfo->lock);
 	INIT_WORK(&devinfo->work, uas_do_work);
+	INIT_WORK(&devinfo->scan_work, uas_scan_work);
 
 	result = uas_configure_endpoints(devinfo);
 	if (result)
@@ -999,7 +1028,9 @@ static int uas_probe(struct usb_interface *intf, const struct usb_device_id *id)
 	if (result)
 		goto free_streams;
 
-	scsi_scan_host(shost);
+	/* Submit the delayed_work for SCSI-device scanning */
+	schedule_work(&devinfo->scan_work);
+
 	return result;
 
 free_streams:
@@ -1167,6 +1198,12 @@ static void uas_disconnect(struct usb_interface *intf)
 	usb_kill_anchored_urbs(&devinfo->data_urbs);
 	uas_zap_pending(devinfo, DID_NO_CONNECT);
 
+	/*
+	 * Prevent SCSI scanning (if it hasn't started yet)
+	 * or wait for the SCSI-scanning routine to stop.
+	 */
+	cancel_work_sync(&devinfo->scan_work);
+
 	scsi_remove_host(shost);
 	uas_free_streams(devinfo);
 	scsi_host_put(shost);
@@ -1206,7 +1243,31 @@ static struct usb_driver uas_driver = {
 	.id_table = uas_usb_ids,
 };
 
-module_usb_driver(uas_driver);
+static int __init uas_init(void)
+{
+	int rv;
+
+	workqueue = alloc_workqueue("uas", WQ_MEM_RECLAIM, 0);
+	if (!workqueue)
+		return -ENOMEM;
+
+	rv = usb_register(&uas_driver);
+	if (rv) {
+		destroy_workqueue(workqueue);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void __exit uas_exit(void)
+{
+	usb_deregister(&uas_driver);
+	destroy_workqueue(workqueue);
+}
+
+module_init(uas_init);
+module_exit(uas_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR(
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index 1cd9b6305b06..88275842219e 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -1258,6 +1258,12 @@ UNUSUAL_DEV( 0x090a, 0x1200, 0x0000, 0x9999,
 		USB_SC_RBC, USB_PR_BULK, NULL,
 		0 ),
 
+UNUSUAL_DEV(0x090c, 0x1000, 0x1100, 0x1100,
+		"Samsung",
+		"Flash Drive FIT",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_MAX_SECTORS_64),
+
 /* aeb */
 UNUSUAL_DEV( 0x090c, 0x1132, 0x0000, 0xffff,
 		"Feiya",
@@ -2317,6 +2323,13 @@ UNUSUAL_DEV(  0x3340, 0xffff, 0x0000, 0x0000,
 		USB_SC_DEVICE,USB_PR_DEVICE,NULL,
 		US_FL_MAX_SECTORS_64 ),
 
+/* Reported by Cyril Roelandt <tipecaml@gmail.com> */
+UNUSUAL_DEV(  0x357d, 0x7788, 0x0114, 0x0114,
+		"JMicron",
+		"USB to ATA/ATAPI Bridge",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_BROKEN_FUA | US_FL_IGNORE_UAS ),
+
 /* Reported by Andrey Rahmatullin <wrar@altlinux.org> */
 UNUSUAL_DEV(  0x4102, 0x1020, 0x0100,  0x0100,
 		"iRiver",
diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h
index d0bdebd87ce3..37157ed9a881 100644
--- a/drivers/usb/storage/unusual_uas.h
+++ b/drivers/usb/storage/unusual_uas.h
@@ -28,6 +28,13 @@
  * and don't forget to CC: the USB development list <linux-usb@vger.kernel.org>
  */
 
+/* Reported-by: Julian Groß <julian.g@posteo.de> */
+UNUSUAL_DEV(0x059f, 0x105f, 0x0000, 0x9999,
+		"LaCie",
+		"2Big Quadra USB3",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_REPORT_OPCODES),
+
 /*
  * Apricorn USB3 dongle sometimes returns "USBSUSBSUSBS" in response to SCSI
  * commands in UAS mode.  Observed with the 1.28 firmware; are there others?
@@ -87,12 +94,15 @@ UNUSUAL_DEV(0x2537, 0x1068, 0x0000, 0x9999,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_IGNORE_UAS),
 
-/* Reported-by: Takeo Nakayama <javhera@gmx.com> */
+/*
+ * Initially Reported-by: Takeo Nakayama <javhera@gmx.com>
+ * UAS Ignore Reported by Steven Ellis <sellis@redhat.com>
+ */
 UNUSUAL_DEV(0x357d, 0x7788, 0x0000, 0x9999,
 		"JMicron",
 		"JMS566",
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
-		US_FL_NO_REPORT_OPCODES),
+		US_FL_NO_REPORT_OPCODES | US_FL_IGNORE_UAS),
 
 /* Reported-by: Hans de Goede <hdegoede@redhat.com> */
 UNUSUAL_DEV(0x4971, 0x1012, 0x0000, 0x9999,
diff --git a/drivers/usb/typec/bus.c b/drivers/usb/typec/bus.c
index 74cb3c2ecb34..c950171556d8 100644
--- a/drivers/usb/typec/bus.c
+++ b/drivers/usb/typec/bus.c
@@ -192,7 +192,10 @@ EXPORT_SYMBOL_GPL(typec_altmode_vdm);
 const struct typec_altmode *
 typec_altmode_get_partner(struct typec_altmode *adev)
 {
-	return adev ? &to_altmode(adev)->partner->adev : NULL;
+	if (!adev || !to_altmode(adev)->partner)
+		return NULL;
+
+	return &to_altmode(adev)->partner->adev;
 }
 EXPORT_SYMBOL_GPL(typec_altmode_get_partner);
 
diff --git a/drivers/usb/typec/tcpm/Kconfig b/drivers/usb/typec/tcpm/Kconfig
index 72481bbb2af3..5b986d6c801d 100644
--- a/drivers/usb/typec/tcpm/Kconfig
+++ b/drivers/usb/typec/tcpm/Kconfig
@@ -32,6 +32,7 @@ endif # TYPEC_TCPCI
 config TYPEC_FUSB302
 	tristate "Fairchild FUSB302 Type-C chip driver"
 	depends on I2C
+	depends on EXTCON || !EXTCON
 	help
 	  The Fairchild FUSB302 Type-C chip driver that works with
 	  Type-C Port Controller Manager to provide USB PD and USB
diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c
index c1f7073a56de..753645bb2527 100644
--- a/drivers/usb/typec/tcpm/tcpci.c
+++ b/drivers/usb/typec/tcpm/tcpci.c
@@ -432,20 +432,30 @@ irqreturn_t tcpci_irq(struct tcpci *tcpci)
 
 	if (status & TCPC_ALERT_RX_STATUS) {
 		struct pd_message msg;
-		unsigned int cnt;
+		unsigned int cnt, payload_cnt;
 		u16 header;
 
 		regmap_read(tcpci->regmap, TCPC_RX_BYTE_CNT, &cnt);
+		/*
+		 * 'cnt' corresponds to READABLE_BYTE_COUNT in section 4.4.14
+		 * of the TCPCI spec [Rev 2.0 Ver 1.0 October 2017] and is
+		 * defined in table 4-36 as one greater than the number of
+		 * bytes received. And that number includes the header. So:
+		 */
+		if (cnt > 3)
+			payload_cnt = cnt - (1 + sizeof(msg.header));
+		else
+			payload_cnt = 0;
 
 		tcpci_read16(tcpci, TCPC_RX_HDR, &header);
 		msg.header = cpu_to_le16(header);
 
-		if (WARN_ON(cnt > sizeof(msg.payload)))
-			cnt = sizeof(msg.payload);
+		if (WARN_ON(payload_cnt > sizeof(msg.payload)))
+			payload_cnt = sizeof(msg.payload);
 
-		if (cnt > 0)
+		if (payload_cnt > 0)
 			regmap_raw_read(tcpci->regmap, TCPC_RX_DATA,
-					&msg.payload, cnt);
+					&msg.payload, payload_cnt);
 
 		/* Read complete, clear RX status alert bit */
 		tcpci_write16(tcpci, TCPC_ALERT, TCPC_ALERT_RX_STATUS);
@@ -581,6 +591,12 @@ static int tcpci_probe(struct i2c_client *client,
 static int tcpci_remove(struct i2c_client *client)
 {
 	struct tcpci_chip *chip = i2c_get_clientdata(client);
+	int err;
+
+	/* Disable chip interrupts before unregistering port */
+	err = tcpci_write16(chip->tcpci, TCPC_ALERT_MASK, 0);
+	if (err < 0)
+		return err;
 
 	tcpci_unregister_port(chip->tcpci);
 
diff --git a/drivers/usb/typec/tcpm/tcpci_rt1711h.c b/drivers/usb/typec/tcpm/tcpci_rt1711h.c
index 017389021b96..b56a0880a044 100644
--- a/drivers/usb/typec/tcpm/tcpci_rt1711h.c
+++ b/drivers/usb/typec/tcpm/tcpci_rt1711h.c
@@ -179,26 +179,6 @@ out:
 	return tcpci_irq(chip->tcpci);
 }
 
-static int rt1711h_init_alert(struct rt1711h_chip *chip,
-			      struct i2c_client *client)
-{
-	int ret;
-
-	/* Disable chip interrupts before requesting irq */
-	ret = rt1711h_write16(chip, TCPC_ALERT_MASK, 0);
-	if (ret < 0)
-		return ret;
-
-	ret = devm_request_threaded_irq(chip->dev, client->irq, NULL,
-					rt1711h_irq,
-					IRQF_ONESHOT | IRQF_TRIGGER_LOW,
-					dev_name(chip->dev), chip);
-	if (ret < 0)
-		return ret;
-	enable_irq_wake(client->irq);
-	return 0;
-}
-
 static int rt1711h_sw_reset(struct rt1711h_chip *chip)
 {
 	int ret;
@@ -260,7 +240,8 @@ static int rt1711h_probe(struct i2c_client *client,
 	if (ret < 0)
 		return ret;
 
-	ret = rt1711h_init_alert(chip, client);
+	/* Disable chip interrupts before requesting irq */
+	ret = rt1711h_write16(chip, TCPC_ALERT_MASK, 0);
 	if (ret < 0)
 		return ret;
 
@@ -271,6 +252,14 @@ static int rt1711h_probe(struct i2c_client *client,
 	if (IS_ERR_OR_NULL(chip->tcpci))
 		return PTR_ERR(chip->tcpci);
 
+	ret = devm_request_threaded_irq(chip->dev, client->irq, NULL,
+					rt1711h_irq,
+					IRQF_ONESHOT | IRQF_TRIGGER_LOW,
+					dev_name(chip->dev), chip);
+	if (ret < 0)
+		return ret;
+	enable_irq_wake(client->irq);
+
 	return 0;
 }
 
diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index a3cf27120164..d780fe6c5579 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -3775,6 +3775,14 @@ static void _tcpm_cc_change(struct tcpm_port *port, enum typec_cc_status cc1,
 		 */
 		break;
 
+	case PORT_RESET:
+	case PORT_RESET_WAIT_OFF:
+		/*
+		 * State set back to default mode once the timer completes.
+		 * Ignore CC changes here.
+		 */
+		break;
+
 	default:
 		if (tcpm_port_is_disconnected(port))
 			tcpm_set_state(port, unattached_state(port), 0);
@@ -3836,6 +3844,15 @@ static void _tcpm_pd_vbus_on(struct tcpm_port *port)
 	case SRC_TRY_DEBOUNCE:
 		/* Do nothing, waiting for sink detection */
 		break;
+
+	case PORT_RESET:
+	case PORT_RESET_WAIT_OFF:
+		/*
+		 * State set back to default mode once the timer completes.
+		 * Ignore vbus changes here.
+		 */
+		break;
+
 	default:
 		break;
 	}
@@ -3889,10 +3906,19 @@ static void _tcpm_pd_vbus_off(struct tcpm_port *port)
 	case PORT_RESET_WAIT_OFF:
 		tcpm_set_state(port, tcpm_default_state(port), 0);
 		break;
+
 	case SRC_TRY_WAIT:
 	case SRC_TRY_DEBOUNCE:
 		/* Do nothing, waiting for sink detection */
 		break;
+
+	case PORT_RESET:
+		/*
+		 * State set back to default mode once the timer completes.
+		 * Ignore vbus changes here.
+		 */
+		break;
+
 	default:
 		if (port->pwr_role == TYPEC_SINK &&
 		    port->attached)
diff --git a/drivers/usb/typec/tcpm/wcove.c b/drivers/usb/typec/tcpm/wcove.c
index 6b317c150bdd..a24595b94963 100644
--- a/drivers/usb/typec/tcpm/wcove.c
+++ b/drivers/usb/typec/tcpm/wcove.c
@@ -597,7 +597,7 @@ static const struct property_entry wcove_props[] = {
 	PROPERTY_ENTRY_STRING("try-power-role", "sink"),
 	PROPERTY_ENTRY_U32_ARRAY("source-pdos", src_pdo),
 	PROPERTY_ENTRY_U32_ARRAY("sink-pdos", snk_pdo),
-	PROPERTY_ENTRY_U32("op-sink-microwatt", 15000),
+	PROPERTY_ENTRY_U32("op-sink-microwatt", 15000000),
 	{ }
 };
 
diff --git a/drivers/usb/typec/ucsi/displayport.c b/drivers/usb/typec/ucsi/displayport.c
index d99700cb4dca..166c2aabb512 100644
--- a/drivers/usb/typec/ucsi/displayport.c
+++ b/drivers/usb/typec/ucsi/displayport.c
@@ -273,6 +273,9 @@ void ucsi_displayport_remove_partner(struct typec_altmode *alt)
 		return;
 
 	dp = typec_altmode_get_drvdata(alt);
+	if (!dp)
+		return;
+
 	dp->data.conf = 0;
 	dp->data.status = 0;
 	dp->initialized = false;
@@ -287,6 +290,8 @@ struct typec_altmode *ucsi_register_displayport(struct ucsi_connector *con,
 	struct typec_altmode *alt;
 	struct ucsi_dp *dp;
 
+	mutex_lock(&con->lock);
+
 	/* We can't rely on the firmware with the capabilities. */
 	desc->vdo |= DP_CAP_DP_SIGNALING | DP_CAP_RECEPTACLE;
 
@@ -295,12 +300,15 @@ struct typec_altmode *ucsi_register_displayport(struct ucsi_connector *con,
 	desc->vdo |= all_assignments << 16;
 
 	alt = typec_port_register_altmode(con->port, desc);
-	if (IS_ERR(alt))
+	if (IS_ERR(alt)) {
+		mutex_unlock(&con->lock);
 		return alt;
+	}
 
 	dp = devm_kzalloc(&alt->dev, sizeof(*dp), GFP_KERNEL);
 	if (!dp) {
 		typec_unregister_altmode(alt);
+		mutex_unlock(&con->lock);
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -313,5 +321,7 @@ struct typec_altmode *ucsi_register_displayport(struct ucsi_connector *con,
 	alt->ops = &ucsi_displayport_ops;
 	typec_altmode_set_drvdata(alt, dp);
 
+	mutex_unlock(&con->lock);
+
 	return alt;
 }
diff --git a/drivers/vfio/mdev/mdev_sysfs.c b/drivers/vfio/mdev/mdev_sysfs.c
index 7570c7602ab4..f32c582611eb 100644
--- a/drivers/vfio/mdev/mdev_sysfs.c
+++ b/drivers/vfio/mdev/mdev_sysfs.c
@@ -110,7 +110,7 @@ static struct mdev_type *add_mdev_supported_type(struct mdev_parent *parent,
 				   "%s-%s", dev_driver_string(parent->dev),
 				   group->name);
 	if (ret) {
-		kfree(type);
+		kobject_put(&type->kobj);
 		return ERR_PTR(ret);
 	}
 
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 02206162eaa9..0d16f9806655 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -27,6 +27,7 @@
 #include <linux/vfio.h>
 #include <linux/vgaarb.h>
 #include <linux/nospec.h>
+#include <linux/sched/mm.h>
 
 #include "vfio_pci_private.h"
 
@@ -177,6 +178,7 @@ no_mmap:
 
 static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev);
 static void vfio_pci_disable(struct vfio_pci_device *vdev);
+static int vfio_pci_try_zap_and_vma_lock_cb(struct pci_dev *pdev, void *data);
 
 /*
  * INTx masking requires the ability to disable INTx signaling via PCI_COMMAND
@@ -688,6 +690,12 @@ int vfio_pci_register_dev_region(struct vfio_pci_device *vdev,
 	return 0;
 }
 
+struct vfio_devices {
+	struct vfio_device **devices;
+	int cur_index;
+	int max_index;
+};
+
 static long vfio_pci_ioctl(void *device_data,
 			   unsigned int cmd, unsigned long arg)
 {
@@ -761,7 +769,7 @@ static long vfio_pci_ioctl(void *device_data,
 		{
 			void __iomem *io;
 			size_t size;
-			u16 orig_cmd;
+			u16 cmd;
 
 			info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
 			info.flags = 0;
@@ -781,10 +789,7 @@ static long vfio_pci_ioctl(void *device_data,
 			 * Is it really there?  Enable memory decode for
 			 * implicit access in pci_map_rom().
 			 */
-			pci_read_config_word(pdev, PCI_COMMAND, &orig_cmd);
-			pci_write_config_word(pdev, PCI_COMMAND,
-					      orig_cmd | PCI_COMMAND_MEMORY);
-
+			cmd = vfio_pci_memory_lock_and_enable(vdev);
 			io = pci_map_rom(pdev, &size);
 			if (io) {
 				info.flags = VFIO_REGION_INFO_FLAG_READ;
@@ -792,8 +797,8 @@ static long vfio_pci_ioctl(void *device_data,
 			} else {
 				info.size = 0;
 			}
+			vfio_pci_memory_unlock_and_restore(vdev, cmd);
 
-			pci_write_config_word(pdev, PCI_COMMAND, orig_cmd);
 			break;
 		}
 		case VFIO_PCI_VGA_REGION_INDEX:
@@ -936,8 +941,16 @@ static long vfio_pci_ioctl(void *device_data,
 		return ret;
 
 	} else if (cmd == VFIO_DEVICE_RESET) {
-		return vdev->reset_works ?
-			pci_try_reset_function(vdev->pdev) : -EINVAL;
+		int ret;
+
+		if (!vdev->reset_works)
+			return -EINVAL;
+
+		vfio_pci_zap_and_down_write_memory_lock(vdev);
+		ret = pci_try_reset_function(vdev->pdev);
+		up_write(&vdev->memory_lock);
+
+		return ret;
 
 	} else if (cmd == VFIO_DEVICE_GET_PCI_HOT_RESET_INFO) {
 		struct vfio_pci_hot_reset_info hdr;
@@ -1017,8 +1030,9 @@ reset_info_exit:
 		int32_t *group_fds;
 		struct vfio_pci_group_entry *groups;
 		struct vfio_pci_group_info info;
+		struct vfio_devices devs = { .cur_index = 0 };
 		bool slot = false;
-		int i, count = 0, ret = 0;
+		int i, group_idx, mem_idx = 0, count = 0, ret = 0;
 
 		minsz = offsetofend(struct vfio_pci_hot_reset, count);
 
@@ -1070,9 +1084,9 @@ reset_info_exit:
 		 * user interface and store the group and iommu ID.  This
 		 * ensures the group is held across the reset.
 		 */
-		for (i = 0; i < hdr.count; i++) {
+		for (group_idx = 0; group_idx < hdr.count; group_idx++) {
 			struct vfio_group *group;
-			struct fd f = fdget(group_fds[i]);
+			struct fd f = fdget(group_fds[group_idx]);
 			if (!f.file) {
 				ret = -EBADF;
 				break;
@@ -1085,8 +1099,9 @@ reset_info_exit:
 				break;
 			}
 
-			groups[i].group = group;
-			groups[i].id = vfio_external_user_iommu_id(group);
+			groups[group_idx].group = group;
+			groups[group_idx].id =
+					vfio_external_user_iommu_id(group);
 		}
 
 		kfree(group_fds);
@@ -1105,13 +1120,63 @@ reset_info_exit:
 		ret = vfio_pci_for_each_slot_or_bus(vdev->pdev,
 						    vfio_pci_validate_devs,
 						    &info, slot);
-		if (!ret)
-			/* User has access, do the reset */
-			ret = pci_reset_bus(vdev->pdev);
+		if (ret)
+			goto hot_reset_release;
+
+		devs.max_index = count;
+		devs.devices = kcalloc(count, sizeof(struct vfio_device *),
+				       GFP_KERNEL);
+		if (!devs.devices) {
+			ret = -ENOMEM;
+			goto hot_reset_release;
+		}
+
+		/*
+		 * We need to get memory_lock for each device, but devices
+		 * can share mmap_sem, therefore we need to zap and hold
+		 * the vma_lock for each device, and only then get each
+		 * memory_lock.
+		 */
+		ret = vfio_pci_for_each_slot_or_bus(vdev->pdev,
+					    vfio_pci_try_zap_and_vma_lock_cb,
+					    &devs, slot);
+		if (ret)
+			goto hot_reset_release;
+
+		for (; mem_idx < devs.cur_index; mem_idx++) {
+			struct vfio_pci_device *tmp;
+
+			tmp = vfio_device_data(devs.devices[mem_idx]);
+
+			ret = down_write_trylock(&tmp->memory_lock);
+			if (!ret) {
+				ret = -EBUSY;
+				goto hot_reset_release;
+			}
+			mutex_unlock(&tmp->vma_lock);
+		}
+
+		/* User has access, do the reset */
+		ret = pci_reset_bus(vdev->pdev);
 
 hot_reset_release:
-		for (i--; i >= 0; i--)
-			vfio_group_put_external_user(groups[i].group);
+		for (i = 0; i < devs.cur_index; i++) {
+			struct vfio_device *device;
+			struct vfio_pci_device *tmp;
+
+			device = devs.devices[i];
+			tmp = vfio_device_data(device);
+
+			if (i < mem_idx)
+				up_write(&tmp->memory_lock);
+			else
+				mutex_unlock(&tmp->vma_lock);
+			vfio_device_put(device);
+		}
+		kfree(devs.devices);
+
+		for (group_idx--; group_idx >= 0; group_idx--)
+			vfio_group_put_external_user(groups[group_idx].group);
 
 		kfree(groups);
 		return ret;
@@ -1192,6 +1257,202 @@ static ssize_t vfio_pci_write(void *device_data, const char __user *buf,
 	return vfio_pci_rw(device_data, (char __user *)buf, count, ppos, true);
 }
 
+/* Return 1 on zap and vma_lock acquired, 0 on contention (only with @try) */
+static int vfio_pci_zap_and_vma_lock(struct vfio_pci_device *vdev, bool try)
+{
+	struct vfio_pci_mmap_vma *mmap_vma, *tmp;
+
+	/*
+	 * Lock ordering:
+	 * vma_lock is nested under mmap_sem for vm_ops callback paths.
+	 * The memory_lock semaphore is used by both code paths calling
+	 * into this function to zap vmas and the vm_ops.fault callback
+	 * to protect the memory enable state of the device.
+	 *
+	 * When zapping vmas we need to maintain the mmap_sem => vma_lock
+	 * ordering, which requires using vma_lock to walk vma_list to
+	 * acquire an mm, then dropping vma_lock to get the mmap_sem and
+	 * reacquiring vma_lock.  This logic is derived from similar
+	 * requirements in uverbs_user_mmap_disassociate().
+	 *
+	 * mmap_sem must always be the top-level lock when it is taken.
+	 * Therefore we can only hold the memory_lock write lock when
+	 * vma_list is empty, as we'd need to take mmap_sem to clear
+	 * entries.  vma_list can only be guaranteed empty when holding
+	 * vma_lock, thus memory_lock is nested under vma_lock.
+	 *
+	 * This enables the vm_ops.fault callback to acquire vma_lock,
+	 * followed by memory_lock read lock, while already holding
+	 * mmap_sem without risk of deadlock.
+	 */
+	while (1) {
+		struct mm_struct *mm = NULL;
+
+		if (try) {
+			if (!mutex_trylock(&vdev->vma_lock))
+				return 0;
+		} else {
+			mutex_lock(&vdev->vma_lock);
+		}
+		while (!list_empty(&vdev->vma_list)) {
+			mmap_vma = list_first_entry(&vdev->vma_list,
+						    struct vfio_pci_mmap_vma,
+						    vma_next);
+			mm = mmap_vma->vma->vm_mm;
+			if (mmget_not_zero(mm))
+				break;
+
+			list_del(&mmap_vma->vma_next);
+			kfree(mmap_vma);
+			mm = NULL;
+		}
+		if (!mm)
+			return 1;
+		mutex_unlock(&vdev->vma_lock);
+
+		if (try) {
+			if (!down_read_trylock(&mm->mmap_sem)) {
+				mmput(mm);
+				return 0;
+			}
+		} else {
+			down_read(&mm->mmap_sem);
+		}
+		if (mmget_still_valid(mm)) {
+			if (try) {
+				if (!mutex_trylock(&vdev->vma_lock)) {
+					up_read(&mm->mmap_sem);
+					mmput(mm);
+					return 0;
+				}
+			} else {
+				mutex_lock(&vdev->vma_lock);
+			}
+			list_for_each_entry_safe(mmap_vma, tmp,
+						 &vdev->vma_list, vma_next) {
+				struct vm_area_struct *vma = mmap_vma->vma;
+
+				if (vma->vm_mm != mm)
+					continue;
+
+				list_del(&mmap_vma->vma_next);
+				kfree(mmap_vma);
+
+				zap_vma_ptes(vma, vma->vm_start,
+					     vma->vm_end - vma->vm_start);
+			}
+			mutex_unlock(&vdev->vma_lock);
+		}
+		up_read(&mm->mmap_sem);
+		mmput(mm);
+	}
+}
+
+void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_device *vdev)
+{
+	vfio_pci_zap_and_vma_lock(vdev, false);
+	down_write(&vdev->memory_lock);
+	mutex_unlock(&vdev->vma_lock);
+}
+
+u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_device *vdev)
+{
+	u16 cmd;
+
+	down_write(&vdev->memory_lock);
+	pci_read_config_word(vdev->pdev, PCI_COMMAND, &cmd);
+	if (!(cmd & PCI_COMMAND_MEMORY))
+		pci_write_config_word(vdev->pdev, PCI_COMMAND,
+				      cmd | PCI_COMMAND_MEMORY);
+
+	return cmd;
+}
+
+void vfio_pci_memory_unlock_and_restore(struct vfio_pci_device *vdev, u16 cmd)
+{
+	pci_write_config_word(vdev->pdev, PCI_COMMAND, cmd);
+	up_write(&vdev->memory_lock);
+}
+
+/* Caller holds vma_lock */
+static int __vfio_pci_add_vma(struct vfio_pci_device *vdev,
+			      struct vm_area_struct *vma)
+{
+	struct vfio_pci_mmap_vma *mmap_vma;
+
+	mmap_vma = kmalloc(sizeof(*mmap_vma), GFP_KERNEL);
+	if (!mmap_vma)
+		return -ENOMEM;
+
+	mmap_vma->vma = vma;
+	list_add(&mmap_vma->vma_next, &vdev->vma_list);
+
+	return 0;
+}
+
+/*
+ * Zap mmaps on open so that we can fault them in on access and therefore
+ * our vma_list only tracks mappings accessed since last zap.
+ */
+static void vfio_pci_mmap_open(struct vm_area_struct *vma)
+{
+	zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start);
+}
+
+static void vfio_pci_mmap_close(struct vm_area_struct *vma)
+{
+	struct vfio_pci_device *vdev = vma->vm_private_data;
+	struct vfio_pci_mmap_vma *mmap_vma;
+
+	mutex_lock(&vdev->vma_lock);
+	list_for_each_entry(mmap_vma, &vdev->vma_list, vma_next) {
+		if (mmap_vma->vma == vma) {
+			list_del(&mmap_vma->vma_next);
+			kfree(mmap_vma);
+			break;
+		}
+	}
+	mutex_unlock(&vdev->vma_lock);
+}
+
+static vm_fault_t vfio_pci_mmap_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct vfio_pci_device *vdev = vma->vm_private_data;
+	vm_fault_t ret = VM_FAULT_NOPAGE;
+
+	mutex_lock(&vdev->vma_lock);
+	down_read(&vdev->memory_lock);
+
+	if (!__vfio_pci_memory_enabled(vdev)) {
+		ret = VM_FAULT_SIGBUS;
+		mutex_unlock(&vdev->vma_lock);
+		goto up_out;
+	}
+
+	if (__vfio_pci_add_vma(vdev, vma)) {
+		ret = VM_FAULT_OOM;
+		mutex_unlock(&vdev->vma_lock);
+		goto up_out;
+	}
+
+	mutex_unlock(&vdev->vma_lock);
+
+	if (remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+			    vma->vm_end - vma->vm_start, vma->vm_page_prot))
+		ret = VM_FAULT_SIGBUS;
+
+up_out:
+	up_read(&vdev->memory_lock);
+	return ret;
+}
+
+static const struct vm_operations_struct vfio_pci_mmap_ops = {
+	.open = vfio_pci_mmap_open,
+	.close = vfio_pci_mmap_close,
+	.fault = vfio_pci_mmap_fault,
+};
+
 static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
 {
 	struct vfio_pci_device *vdev = device_data;
@@ -1250,8 +1511,14 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 	vma->vm_pgoff = (pci_resource_start(pdev, index) >> PAGE_SHIFT) + pgoff;
 
-	return remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
-			       req_len, vma->vm_page_prot);
+	/*
+	 * See remap_pfn_range(), called from vfio_pci_fault() but we can't
+	 * change vm_flags within the fault handler.  Set them now.
+	 */
+	vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;
+	vma->vm_ops = &vfio_pci_mmap_ops;
+
+	return 0;
 }
 
 static void vfio_pci_request(void *device_data, unsigned int count)
@@ -1327,6 +1594,9 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	spin_lock_init(&vdev->irqlock);
 	mutex_init(&vdev->ioeventfds_lock);
 	INIT_LIST_HEAD(&vdev->ioeventfds_list);
+	mutex_init(&vdev->vma_lock);
+	INIT_LIST_HEAD(&vdev->vma_list);
+	init_rwsem(&vdev->memory_lock);
 
 	ret = vfio_add_group_dev(&pdev->dev, &vfio_pci_ops, vdev);
 	if (ret) {
@@ -1516,12 +1786,6 @@ static void vfio_pci_reflck_put(struct vfio_pci_reflck *reflck)
 	kref_put_mutex(&reflck->kref, vfio_pci_reflck_release, &reflck_lock);
 }
 
-struct vfio_devices {
-	struct vfio_device **devices;
-	int cur_index;
-	int max_index;
-};
-
 static int vfio_pci_get_unused_devs(struct pci_dev *pdev, void *data)
 {
 	struct vfio_devices *devs = data;
@@ -1552,6 +1816,39 @@ static int vfio_pci_get_unused_devs(struct pci_dev *pdev, void *data)
 	return 0;
 }
 
+static int vfio_pci_try_zap_and_vma_lock_cb(struct pci_dev *pdev, void *data)
+{
+	struct vfio_devices *devs = data;
+	struct vfio_device *device;
+	struct vfio_pci_device *vdev;
+
+	if (devs->cur_index == devs->max_index)
+		return -ENOSPC;
+
+	device = vfio_device_get_from_dev(&pdev->dev);
+	if (!device)
+		return -EINVAL;
+
+	if (pci_dev_driver(pdev) != &vfio_pci_driver) {
+		vfio_device_put(device);
+		return -EBUSY;
+	}
+
+	vdev = vfio_device_data(device);
+
+	/*
+	 * Locking multiple devices is prone to deadlock, runaway and
+	 * unwind if we hit contention.
+	 */
+	if (!vfio_pci_zap_and_vma_lock(vdev, true)) {
+		vfio_device_put(device);
+		return -EBUSY;
+	}
+
+	devs->devices[devs->cur_index++] = device;
+	return 0;
+}
+
 /*
  * If a bus or slot reset is available for the provided device and:
  *  - All of the devices affected by that bus or slot reset are unused
diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index f0891bd8444c..927b608461c8 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -395,6 +395,20 @@ static inline void p_setd(struct perm_bits *p, int off, u32 virt, u32 write)
 	*(__le32 *)(&p->write[off]) = cpu_to_le32(write);
 }
 
+/* Caller should hold memory_lock semaphore */
+bool __vfio_pci_memory_enabled(struct vfio_pci_device *vdev)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	u16 cmd = le16_to_cpu(*(__le16 *)&vdev->vconfig[PCI_COMMAND]);
+
+	/*
+	 * SR-IOV VF memory enable is handled by the MSE bit in the
+	 * PF SR-IOV capability, there's therefore no need to trigger
+	 * faults based on the virtual value.
+	 */
+	return pdev->is_virtfn || (cmd & PCI_COMMAND_MEMORY);
+}
+
 /*
  * Restore the *real* BARs after we detect a FLR or backdoor reset.
  * (backdoor = some device specific technique that we didn't catch)
@@ -554,13 +568,18 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos,
 
 		new_cmd = le32_to_cpu(val);
 
+		phys_io = !!(phys_cmd & PCI_COMMAND_IO);
+		virt_io = !!(le16_to_cpu(*virt_cmd) & PCI_COMMAND_IO);
+		new_io = !!(new_cmd & PCI_COMMAND_IO);
+
 		phys_mem = !!(phys_cmd & PCI_COMMAND_MEMORY);
 		virt_mem = !!(le16_to_cpu(*virt_cmd) & PCI_COMMAND_MEMORY);
 		new_mem = !!(new_cmd & PCI_COMMAND_MEMORY);
 
-		phys_io = !!(phys_cmd & PCI_COMMAND_IO);
-		virt_io = !!(le16_to_cpu(*virt_cmd) & PCI_COMMAND_IO);
-		new_io = !!(new_cmd & PCI_COMMAND_IO);
+		if (!new_mem)
+			vfio_pci_zap_and_down_write_memory_lock(vdev);
+		else
+			down_write(&vdev->memory_lock);
 
 		/*
 		 * If the user is writing mem/io enable (new_mem/io) and we
@@ -577,8 +596,11 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos,
 	}
 
 	count = vfio_default_config_write(vdev, pos, count, perm, offset, val);
-	if (count < 0)
+	if (count < 0) {
+		if (offset == PCI_COMMAND)
+			up_write(&vdev->memory_lock);
 		return count;
+	}
 
 	/*
 	 * Save current memory/io enable bits in vconfig to allow for
@@ -589,6 +611,8 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos,
 
 		*virt_cmd &= cpu_to_le16(~mask);
 		*virt_cmd |= cpu_to_le16(new_cmd & mask);
+
+		up_write(&vdev->memory_lock);
 	}
 
 	/* Emulate INTx disable */
@@ -826,8 +850,11 @@ static int vfio_exp_config_write(struct vfio_pci_device *vdev, int pos,
 						 pos - offset + PCI_EXP_DEVCAP,
 						 &cap);
 
-		if (!ret && (cap & PCI_EXP_DEVCAP_FLR))
+		if (!ret && (cap & PCI_EXP_DEVCAP_FLR)) {
+			vfio_pci_zap_and_down_write_memory_lock(vdev);
 			pci_try_reset_function(vdev->pdev);
+			up_write(&vdev->memory_lock);
+		}
 	}
 
 	/*
@@ -905,8 +932,11 @@ static int vfio_af_config_write(struct vfio_pci_device *vdev, int pos,
 						pos - offset + PCI_AF_CAP,
 						&cap);
 
-		if (!ret && (cap & PCI_AF_CAP_FLR) && (cap & PCI_AF_CAP_TP))
+		if (!ret && (cap & PCI_AF_CAP_FLR) && (cap & PCI_AF_CAP_TP)) {
+			vfio_pci_zap_and_down_write_memory_lock(vdev);
 			pci_try_reset_function(vdev->pdev);
+			up_write(&vdev->memory_lock);
+		}
 	}
 
 	return count;
@@ -1460,7 +1490,12 @@ static int vfio_cap_init(struct vfio_pci_device *vdev)
 		if (ret)
 			return ret;
 
-		if (cap <= PCI_CAP_ID_MAX) {
+		/*
+		 * ID 0 is a NULL capability, conflicting with our fake
+		 * PCI_CAP_ID_BASIC.  As it has no content, consider it
+		 * hidden for now.
+		 */
+		if (cap && cap <= PCI_CAP_ID_MAX) {
 			len = pci_cap_length[cap];
 			if (len == 0xFF) { /* Variable length */
 				len = vfio_cap_len(vdev, cap, pos);
@@ -1697,6 +1732,15 @@ int vfio_config_init(struct vfio_pci_device *vdev)
 				 vconfig[PCI_INTERRUPT_PIN]);
 
 		vconfig[PCI_INTERRUPT_PIN] = 0; /* Gratuitous for good VFs */
+
+		/*
+		 * VFs do no implement the memory enable bit of the COMMAND
+		 * register therefore we'll not have it set in our initial
+		 * copy of config space after pci_enable_device().  For
+		 * consistency with PFs, set the virtual enable bit here.
+		 */
+		*(__le16 *)&vconfig[PCI_COMMAND] |=
+					cpu_to_le16(PCI_COMMAND_MEMORY);
 	}
 
 	if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX) || vdev->nointx)
@@ -1726,8 +1770,11 @@ void vfio_config_free(struct vfio_pci_device *vdev)
 	vdev->vconfig = NULL;
 	kfree(vdev->pci_config_map);
 	vdev->pci_config_map = NULL;
-	kfree(vdev->msi_perm);
-	vdev->msi_perm = NULL;
+	if (vdev->msi_perm) {
+		free_perm_bits(vdev->msi_perm);
+		kfree(vdev->msi_perm);
+		vdev->msi_perm = NULL;
+	}
 }
 
 /*
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index 2056f3f85f59..1d9fb2592945 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -249,6 +249,7 @@ static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix)
 	struct pci_dev *pdev = vdev->pdev;
 	unsigned int flag = msix ? PCI_IRQ_MSIX : PCI_IRQ_MSI;
 	int ret;
+	u16 cmd;
 
 	if (!is_irq_none(vdev))
 		return -EINVAL;
@@ -258,13 +259,16 @@ static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix)
 		return -ENOMEM;
 
 	/* return the number of supported vectors if we can't get all: */
+	cmd = vfio_pci_memory_lock_and_enable(vdev);
 	ret = pci_alloc_irq_vectors(pdev, 1, nvec, flag);
 	if (ret < nvec) {
 		if (ret > 0)
 			pci_free_irq_vectors(pdev);
+		vfio_pci_memory_unlock_and_restore(vdev, cmd);
 		kfree(vdev->ctx);
 		return ret;
 	}
+	vfio_pci_memory_unlock_and_restore(vdev, cmd);
 
 	vdev->num_ctx = nvec;
 	vdev->irq_type = msix ? VFIO_PCI_MSIX_IRQ_INDEX :
@@ -287,6 +291,7 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
 	struct pci_dev *pdev = vdev->pdev;
 	struct eventfd_ctx *trigger;
 	int irq, ret;
+	u16 cmd;
 
 	if (vector < 0 || vector >= vdev->num_ctx)
 		return -EINVAL;
@@ -295,7 +300,11 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
 
 	if (vdev->ctx[vector].trigger) {
 		irq_bypass_unregister_producer(&vdev->ctx[vector].producer);
+
+		cmd = vfio_pci_memory_lock_and_enable(vdev);
 		free_irq(irq, vdev->ctx[vector].trigger);
+		vfio_pci_memory_unlock_and_restore(vdev, cmd);
+
 		kfree(vdev->ctx[vector].name);
 		eventfd_ctx_put(vdev->ctx[vector].trigger);
 		vdev->ctx[vector].trigger = NULL;
@@ -323,6 +332,7 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
 	 * such a reset it would be unsuccessful. To avoid this, restore the
 	 * cached value of the message prior to enabling.
 	 */
+	cmd = vfio_pci_memory_lock_and_enable(vdev);
 	if (msix) {
 		struct msi_msg msg;
 
@@ -332,6 +342,7 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
 
 	ret = request_irq(irq, vfio_msihandler, 0,
 			  vdev->ctx[vector].name, trigger);
+	vfio_pci_memory_unlock_and_restore(vdev, cmd);
 	if (ret) {
 		kfree(vdev->ctx[vector].name);
 		eventfd_ctx_put(trigger);
@@ -376,6 +387,7 @@ static void vfio_msi_disable(struct vfio_pci_device *vdev, bool msix)
 {
 	struct pci_dev *pdev = vdev->pdev;
 	int i;
+	u16 cmd;
 
 	for (i = 0; i < vdev->num_ctx; i++) {
 		vfio_virqfd_disable(&vdev->ctx[i].unmask);
@@ -384,7 +396,9 @@ static void vfio_msi_disable(struct vfio_pci_device *vdev, bool msix)
 
 	vfio_msi_set_block(vdev, 0, vdev->num_ctx, NULL, msix);
 
+	cmd = vfio_pci_memory_lock_and_enable(vdev);
 	pci_free_irq_vectors(pdev);
+	vfio_pci_memory_unlock_and_restore(vdev, cmd);
 
 	/*
 	 * Both disable paths above use pci_intx_for_msi() to clear DisINTx
diff --git a/drivers/vfio/pci/vfio_pci_nvlink2.c b/drivers/vfio/pci/vfio_pci_nvlink2.c
index 50fe3c4f7feb..a22340c5e7d0 100644
--- a/drivers/vfio/pci/vfio_pci_nvlink2.c
+++ b/drivers/vfio/pci/vfio_pci_nvlink2.c
@@ -97,8 +97,10 @@ static void vfio_pci_nvgpu_release(struct vfio_pci_device *vdev,
 
 	/* If there were any mappings at all... */
 	if (data->mm) {
-		ret = mm_iommu_put(data->mm, data->mem);
-		WARN_ON(ret);
+		if (data->mem) {
+			ret = mm_iommu_put(data->mm, data->mem);
+			WARN_ON(ret);
+		}
 
 		mmdrop(data->mm);
 	}
diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h
index ee6ee91718a4..de7ac0cd6c5c 100644
--- a/drivers/vfio/pci/vfio_pci_private.h
+++ b/drivers/vfio/pci/vfio_pci_private.h
@@ -31,12 +31,14 @@
 
 struct vfio_pci_ioeventfd {
 	struct list_head	next;
+	struct vfio_pci_device	*vdev;
 	struct virqfd		*virqfd;
 	void __iomem		*addr;
 	uint64_t		data;
 	loff_t			pos;
 	int			bar;
 	int			count;
+	bool			test_mem;
 };
 
 struct vfio_pci_irq_ctx {
@@ -84,6 +86,11 @@ struct vfio_pci_reflck {
 	struct mutex		lock;
 };
 
+struct vfio_pci_mmap_vma {
+	struct vm_area_struct	*vma;
+	struct list_head	vma_next;
+};
+
 struct vfio_pci_device {
 	struct pci_dev		*pdev;
 	void __iomem		*barmap[PCI_STD_RESOURCE_END + 1];
@@ -122,6 +129,9 @@ struct vfio_pci_device {
 	struct list_head	dummy_resources_list;
 	struct mutex		ioeventfds_lock;
 	struct list_head	ioeventfds_list;
+	struct mutex		vma_lock;
+	struct list_head	vma_list;
+	struct rw_semaphore	memory_lock;
 };
 
 #define is_intx(vdev) (vdev->irq_type == VFIO_PCI_INTX_IRQ_INDEX)
@@ -164,6 +174,13 @@ extern int vfio_pci_register_dev_region(struct vfio_pci_device *vdev,
 extern int vfio_pci_set_power_state(struct vfio_pci_device *vdev,
 				    pci_power_t state);
 
+extern bool __vfio_pci_memory_enabled(struct vfio_pci_device *vdev);
+extern void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_device
+						    *vdev);
+extern u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_device *vdev);
+extern void vfio_pci_memory_unlock_and_restore(struct vfio_pci_device *vdev,
+					       u16 cmd);
+
 #ifdef CONFIG_VFIO_PCI_IGD
 extern int vfio_pci_igd_init(struct vfio_pci_device *vdev);
 #else
diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index 0120d8324a40..eaa1975ebae2 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -37,17 +37,70 @@
 #define vfio_ioread8	ioread8
 #define vfio_iowrite8	iowrite8
 
+#define VFIO_IOWRITE(size) \
+static int vfio_pci_iowrite##size(struct vfio_pci_device *vdev,		\
+			bool test_mem, u##size val, void __iomem *io)	\
+{									\
+	if (test_mem) {							\
+		down_read(&vdev->memory_lock);				\
+		if (!__vfio_pci_memory_enabled(vdev)) {			\
+			up_read(&vdev->memory_lock);			\
+			return -EIO;					\
+		}							\
+	}								\
+									\
+	vfio_iowrite##size(val, io);					\
+									\
+	if (test_mem)							\
+		up_read(&vdev->memory_lock);				\
+									\
+	return 0;							\
+}
+
+VFIO_IOWRITE(8)
+VFIO_IOWRITE(16)
+VFIO_IOWRITE(32)
+#ifdef iowrite64
+VFIO_IOWRITE(64)
+#endif
+
+#define VFIO_IOREAD(size) \
+static int vfio_pci_ioread##size(struct vfio_pci_device *vdev,		\
+			bool test_mem, u##size *val, void __iomem *io)	\
+{									\
+	if (test_mem) {							\
+		down_read(&vdev->memory_lock);				\
+		if (!__vfio_pci_memory_enabled(vdev)) {			\
+			up_read(&vdev->memory_lock);			\
+			return -EIO;					\
+		}							\
+	}								\
+									\
+	*val = vfio_ioread##size(io);					\
+									\
+	if (test_mem)							\
+		up_read(&vdev->memory_lock);				\
+									\
+	return 0;							\
+}
+
+VFIO_IOREAD(8)
+VFIO_IOREAD(16)
+VFIO_IOREAD(32)
+
 /*
  * Read or write from an __iomem region (MMIO or I/O port) with an excluded
  * range which is inaccessible.  The excluded range drops writes and fills
  * reads with -1.  This is intended for handling MSI-X vector tables and
  * leftover space for ROM BARs.
  */
-static ssize_t do_io_rw(void __iomem *io, char __user *buf,
+static ssize_t do_io_rw(struct vfio_pci_device *vdev, bool test_mem,
+			void __iomem *io, char __user *buf,
 			loff_t off, size_t count, size_t x_start,
 			size_t x_end, bool iswrite)
 {
 	ssize_t done = 0;
+	int ret;
 
 	while (count) {
 		size_t fillable, filled;
@@ -66,9 +119,15 @@ static ssize_t do_io_rw(void __iomem *io, char __user *buf,
 				if (copy_from_user(&val, buf, 4))
 					return -EFAULT;
 
-				vfio_iowrite32(val, io + off);
+				ret = vfio_pci_iowrite32(vdev, test_mem,
+							 val, io + off);
+				if (ret)
+					return ret;
 			} else {
-				val = vfio_ioread32(io + off);
+				ret = vfio_pci_ioread32(vdev, test_mem,
+							&val, io + off);
+				if (ret)
+					return ret;
 
 				if (copy_to_user(buf, &val, 4))
 					return -EFAULT;
@@ -82,9 +141,15 @@ static ssize_t do_io_rw(void __iomem *io, char __user *buf,
 				if (copy_from_user(&val, buf, 2))
 					return -EFAULT;
 
-				vfio_iowrite16(val, io + off);
+				ret = vfio_pci_iowrite16(vdev, test_mem,
+							 val, io + off);
+				if (ret)
+					return ret;
 			} else {
-				val = vfio_ioread16(io + off);
+				ret = vfio_pci_ioread16(vdev, test_mem,
+							&val, io + off);
+				if (ret)
+					return ret;
 
 				if (copy_to_user(buf, &val, 2))
 					return -EFAULT;
@@ -98,9 +163,15 @@ static ssize_t do_io_rw(void __iomem *io, char __user *buf,
 				if (copy_from_user(&val, buf, 1))
 					return -EFAULT;
 
-				vfio_iowrite8(val, io + off);
+				ret = vfio_pci_iowrite8(vdev, test_mem,
+							val, io + off);
+				if (ret)
+					return ret;
 			} else {
-				val = vfio_ioread8(io + off);
+				ret = vfio_pci_ioread8(vdev, test_mem,
+						       &val, io + off);
+				if (ret)
+					return ret;
 
 				if (copy_to_user(buf, &val, 1))
 					return -EFAULT;
@@ -162,6 +233,7 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf,
 	size_t x_start = 0, x_end = 0;
 	resource_size_t end;
 	void __iomem *io;
+	struct resource *res = &vdev->pdev->resource[bar];
 	ssize_t done;
 
 	if (pci_resource_start(pdev, bar))
@@ -184,13 +256,17 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf,
 		 * filling large ROM BARs much faster.
 		 */
 		io = pci_map_rom(pdev, &x_start);
-		if (!io)
-			return -ENOMEM;
+		if (!io) {
+			done = -ENOMEM;
+			goto out;
+		}
 		x_end = end;
 	} else {
 		int ret = vfio_pci_setup_barmap(vdev, bar);
-		if (ret)
-			return ret;
+		if (ret) {
+			done = ret;
+			goto out;
+		}
 
 		io = vdev->barmap[bar];
 	}
@@ -200,14 +276,15 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf,
 		x_end = vdev->msix_offset + vdev->msix_size;
 	}
 
-	done = do_io_rw(io, buf, pos, count, x_start, x_end, iswrite);
+	done = do_io_rw(vdev, res->flags & IORESOURCE_MEM, io, buf, pos,
+			count, x_start, x_end, iswrite);
 
 	if (done >= 0)
 		*ppos += done;
 
 	if (bar == PCI_ROM_RESOURCE)
 		pci_unmap_rom(pdev, io);
-
+out:
 	return done;
 }
 
@@ -262,7 +339,12 @@ ssize_t vfio_pci_vga_rw(struct vfio_pci_device *vdev, char __user *buf,
 		return ret;
 	}
 
-	done = do_io_rw(iomem, buf, off, count, 0, 0, iswrite);
+	/*
+	 * VGA MMIO is a legacy, non-BAR resource that hopefully allows
+	 * probing, so we don't currently worry about access in relation
+	 * to the memory enable bit in the command register.
+	 */
+	done = do_io_rw(vdev, false, iomem, buf, off, count, 0, 0, iswrite);
 
 	vga_put(vdev->pdev, rsrc);
 
@@ -280,17 +362,21 @@ static int vfio_pci_ioeventfd_handler(void *opaque, void *unused)
 
 	switch (ioeventfd->count) {
 	case 1:
-		vfio_iowrite8(ioeventfd->data, ioeventfd->addr);
+		vfio_pci_iowrite8(ioeventfd->vdev, ioeventfd->test_mem,
+				  ioeventfd->data, ioeventfd->addr);
 		break;
 	case 2:
-		vfio_iowrite16(ioeventfd->data, ioeventfd->addr);
+		vfio_pci_iowrite16(ioeventfd->vdev, ioeventfd->test_mem,
+				   ioeventfd->data, ioeventfd->addr);
 		break;
 	case 4:
-		vfio_iowrite32(ioeventfd->data, ioeventfd->addr);
+		vfio_pci_iowrite32(ioeventfd->vdev, ioeventfd->test_mem,
+				   ioeventfd->data, ioeventfd->addr);
 		break;
 #ifdef iowrite64
 	case 8:
-		vfio_iowrite64(ioeventfd->data, ioeventfd->addr);
+		vfio_pci_iowrite64(ioeventfd->vdev, ioeventfd->test_mem,
+				   ioeventfd->data, ioeventfd->addr);
 		break;
 #endif
 	}
@@ -362,11 +448,13 @@ long vfio_pci_ioeventfd(struct vfio_pci_device *vdev, loff_t offset,
 		goto out_unlock;
 	}
 
+	ioeventfd->vdev = vdev;
 	ioeventfd->addr = vdev->barmap[bar] + pos;
 	ioeventfd->data = data;
 	ioeventfd->pos = pos;
 	ioeventfd->bar = bar;
 	ioeventfd->count = count;
+	ioeventfd->test_mem = vdev->pdev->resource[bar].flags & IORESOURCE_MEM;
 
 	ret = vfio_virqfd_enable(ioeventfd, vfio_pci_ioeventfd_handler,
 				 NULL, NULL, &ioeventfd->virqfd, fd);
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index add34adfadc7..2329d161aed3 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -341,6 +341,32 @@ static int put_pfn(unsigned long pfn, int prot)
 	return 0;
 }
 
+static int follow_fault_pfn(struct vm_area_struct *vma, struct mm_struct *mm,
+			    unsigned long vaddr, unsigned long *pfn,
+			    bool write_fault)
+{
+	int ret;
+
+	ret = follow_pfn(vma, vaddr, pfn);
+	if (ret) {
+		bool unlocked = false;
+
+		ret = fixup_user_fault(NULL, mm, vaddr,
+				       FAULT_FLAG_REMOTE |
+				       (write_fault ?  FAULT_FLAG_WRITE : 0),
+				       &unlocked);
+		if (unlocked)
+			return -EAGAIN;
+
+		if (ret)
+			return ret;
+
+		ret = follow_pfn(vma, vaddr, pfn);
+	}
+
+	return ret;
+}
+
 static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 			 int prot, unsigned long *pfn)
 {
@@ -381,12 +407,16 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 
 	down_read(&mm->mmap_sem);
 
+retry:
 	vma = find_vma_intersection(mm, vaddr, vaddr + 1);
 
 	if (vma && vma->vm_flags & VM_PFNMAP) {
-		*pfn = ((vaddr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
-		if (is_invalid_reserved_pfn(*pfn))
-			ret = 0;
+		ret = follow_fault_pfn(vma, mm, vaddr, pfn, prot & IOMMU_WRITE);
+		if (ret == -EAGAIN)
+			goto retry;
+
+		if (!ret && !is_invalid_reserved_pfn(*pfn))
+			ret = -EFAULT;
 	}
 
 	up_read(&mm->mmap_sem);
@@ -597,7 +627,7 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data,
 			continue;
 		}
 
-		remote_vaddr = dma->vaddr + iova - dma->iova;
+		remote_vaddr = dma->vaddr + (iova - dma->iova);
 		ret = vfio_pin_page_external(dma, remote_vaddr, &phys_pfn[i],
 					     do_accounting);
 		if (ret)
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 247e5585af5d..873a692478c4 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -1414,10 +1414,6 @@ static int vhost_net_release(struct inode *inode, struct file *f)
 
 static struct socket *get_raw_socket(int fd)
 {
-	struct {
-		struct sockaddr_ll sa;
-		char  buf[MAX_ADDR_LEN];
-	} uaddr;
 	int r;
 	struct socket *sock = sockfd_lookup(fd, &r);
 
@@ -1430,11 +1426,7 @@ static struct socket *get_raw_socket(int fd)
 		goto err;
 	}
 
-	r = sock->ops->getname(sock, (struct sockaddr *)&uaddr.sa, 0);
-	if (r < 0)
-		goto err;
-
-	if (uaddr.sa.sll_family != AF_PACKET) {
+	if (sock->sk->sk_family != AF_PACKET) {
 		r = -EPFNOSUPPORT;
 		goto err;
 	}
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index a9caf1bc3c3e..f63f84a25725 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1215,7 +1215,7 @@ vhost_scsi_ctl_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 			continue;
 		}
 
-		switch (v_req.type) {
+		switch (vhost32_to_cpu(vq, v_req.type)) {
 		case VIRTIO_SCSI_T_TMF:
 			vc.req = &v_req.tmf;
 			vc.req_size = sizeof(struct virtio_scsi_ctrl_tmf_req);
@@ -2290,6 +2290,7 @@ static struct configfs_attribute *vhost_scsi_wwn_attrs[] = {
 static const struct target_core_fabric_ops vhost_scsi_ops = {
 	.module				= THIS_MODULE,
 	.fabric_name			= "vhost",
+	.max_data_sg_nents		= VHOST_SCSI_PREALLOC_SGLS,
 	.tpg_get_wwn			= vhost_scsi_get_fabric_wwn,
 	.tpg_get_tag			= vhost_scsi_get_tpgt,
 	.tpg_check_demo_mode		= vhost_scsi_check_true,
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index c053af8822da..c9bb2bd2d494 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -181,14 +181,14 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 			break;
 		}
 
-		vhost_add_used(vq, head, sizeof(pkt->hdr) + payload_len);
-		added = true;
-
-		/* Deliver to monitoring devices all correctly transmitted
-		 * packets.
+		/* Deliver to monitoring devices all packets that we
+		 * will transmit.
 		 */
 		virtio_transport_deliver_tap_pkt(pkt);
 
+		vhost_add_used(vq, head, sizeof(pkt->hdr) + payload_len);
+		added = true;
+
 		pkt->off += payload_len;
 		total_len += payload_len;
 
@@ -498,6 +498,11 @@ static int vhost_vsock_start(struct vhost_vsock *vsock)
 		mutex_unlock(&vq->mutex);
 	}
 
+	/* Some packets may have been queued before the device was started,
+	 * let's kick the send worker to send them.
+	 */
+	vhost_work_queue(&vsock->dev, &vsock->send_pkt_work);
+
 	mutex_unlock(&vsock->dev.mutex);
 	return 0;
 
diff --git a/drivers/video/backlight/Kconfig b/drivers/video/backlight/Kconfig
index 8b081d61773e..40676be2e46a 100644
--- a/drivers/video/backlight/Kconfig
+++ b/drivers/video/backlight/Kconfig
@@ -10,7 +10,6 @@ menu "Backlight & LCD device support"
 #
 config LCD_CLASS_DEVICE
         tristate "Lowlevel LCD controls"
-	default m
 	help
 	  This framework adds support for low-level control of LCD.
 	  Some framebuffer devices connect to platform-specific LCD modules
@@ -143,7 +142,6 @@ endif # LCD_CLASS_DEVICE
 #
 config BACKLIGHT_CLASS_DEVICE
         tristate "Lowlevel Backlight controls"
-	default m
 	help
 	  This framework adds support for low-level control of the LCD
           backlight. This includes support for brightness and power.
diff --git a/drivers/video/backlight/lp855x_bl.c b/drivers/video/backlight/lp855x_bl.c
index f68920131a4a..e94932c69f54 100644
--- a/drivers/video/backlight/lp855x_bl.c
+++ b/drivers/video/backlight/lp855x_bl.c
@@ -456,7 +456,7 @@ static int lp855x_probe(struct i2c_client *cl, const struct i2c_device_id *id)
 		ret = regulator_enable(lp->enable);
 		if (ret < 0) {
 			dev_err(lp->dev, "failed to enable vddio: %d\n", ret);
-			return ret;
+			goto disable_supply;
 		}
 
 		/*
@@ -471,24 +471,34 @@ static int lp855x_probe(struct i2c_client *cl, const struct i2c_device_id *id)
 	ret = lp855x_configure(lp);
 	if (ret) {
 		dev_err(lp->dev, "device config err: %d", ret);
-		return ret;
+		goto disable_vddio;
 	}
 
 	ret = lp855x_backlight_register(lp);
 	if (ret) {
 		dev_err(lp->dev,
 			"failed to register backlight. err: %d\n", ret);
-		return ret;
+		goto disable_vddio;
 	}
 
 	ret = sysfs_create_group(&lp->dev->kobj, &lp855x_attr_group);
 	if (ret) {
 		dev_err(lp->dev, "failed to register sysfs. err: %d\n", ret);
-		return ret;
+		goto disable_vddio;
 	}
 
 	backlight_update_status(lp->bl);
+
 	return 0;
+
+disable_vddio:
+	if (lp->enable)
+		regulator_disable(lp->enable);
+disable_supply:
+	if (lp->supply)
+		regulator_disable(lp->supply);
+
+	return ret;
 }
 
 static int lp855x_remove(struct i2c_client *cl)
@@ -497,6 +507,8 @@ static int lp855x_remove(struct i2c_client *cl)
 
 	lp->bl->props.brightness = 0;
 	backlight_update_status(lp->bl);
+	if (lp->enable)
+		regulator_disable(lp->enable);
 	if (lp->supply)
 		regulator_disable(lp->supply);
 	sysfs_remove_group(&lp->dev->kobj, &lp855x_attr_group);
diff --git a/drivers/video/console/newport_con.c b/drivers/video/console/newport_con.c
index 00dddf6e08b0..2d2ee17052e8 100644
--- a/drivers/video/console/newport_con.c
+++ b/drivers/video/console/newport_con.c
@@ -32,6 +32,8 @@
 #include <linux/linux_logo.h>
 #include <linux/font.h>
 
+#define NEWPORT_LEN	0x10000
+
 #define FONT_DATA ((unsigned char *)font_vga_8x16.data)
 
 /* borrowed from fbcon.c */
@@ -43,6 +45,7 @@
 static unsigned char *font_data[MAX_NR_CONSOLES];
 
 static struct newport_regs *npregs;
+static unsigned long newport_addr;
 
 static int logo_active;
 static int topscan;
@@ -702,7 +705,6 @@ const struct consw newport_con = {
 static int newport_probe(struct gio_device *dev,
 			 const struct gio_device_id *id)
 {
-	unsigned long newport_addr;
 	int err;
 
 	if (!dev->resource.start)
@@ -712,7 +714,7 @@ static int newport_probe(struct gio_device *dev,
 		return -EBUSY; /* we only support one Newport as console */
 
 	newport_addr = dev->resource.start + 0xF0000;
-	if (!request_mem_region(newport_addr, 0x10000, "Newport"))
+	if (!request_mem_region(newport_addr, NEWPORT_LEN, "Newport"))
 		return -ENODEV;
 
 	npregs = (struct newport_regs *)/* ioremap cannot fail */
@@ -720,6 +722,11 @@ static int newport_probe(struct gio_device *dev,
 	console_lock();
 	err = do_take_over_console(&newport_con, 0, MAX_NR_CONSOLES - 1, 1);
 	console_unlock();
+
+	if (err) {
+		iounmap((void *)npregs);
+		release_mem_region(newport_addr, NEWPORT_LEN);
+	}
 	return err;
 }
 
@@ -727,6 +734,7 @@ static void newport_remove(struct gio_device *dev)
 {
 	give_up_console(&newport_con);
 	iounmap((void *)npregs);
+	release_mem_region(newport_addr, NEWPORT_LEN);
 }
 
 static struct gio_device_id newport_ids[] = {
diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c
index c6b3bdbbdbc9..e079b910feb2 100644
--- a/drivers/video/console/vgacon.c
+++ b/drivers/video/console/vgacon.c
@@ -251,6 +251,10 @@ static void vgacon_scrollback_update(struct vc_data *c, int t, int count)
 	p = (void *) (c->vc_origin + t * c->vc_size_row);
 
 	while (count--) {
+		if ((vgacon_scrollback_cur->tail + c->vc_size_row) >
+		    vgacon_scrollback_cur->size)
+			vgacon_scrollback_cur->tail = 0;
+
 		scr_memcpyw(vgacon_scrollback_cur->data +
 			    vgacon_scrollback_cur->tail,
 			    p, c->vc_size_row);
@@ -1316,6 +1320,9 @@ static int vgacon_font_get(struct vc_data *c, struct console_font *font)
 static int vgacon_resize(struct vc_data *c, unsigned int width,
 			 unsigned int height, unsigned int user)
 {
+	if ((width << 1) * height > vga_vram_size)
+		return -EINVAL;
+
 	if (width % 2 || width > screen_info.orig_video_cols ||
 	    height > (screen_info.orig_video_lines * vga_default_font_height)/
 	    c->vc_font.height)
diff --git a/drivers/video/fbdev/core/bitblit.c b/drivers/video/fbdev/core/bitblit.c
index ca935c09a261..35ebeeccde4d 100644
--- a/drivers/video/fbdev/core/bitblit.c
+++ b/drivers/video/fbdev/core/bitblit.c
@@ -216,7 +216,7 @@ static void bit_clear_margins(struct vc_data *vc, struct fb_info *info,
 	region.color = color;
 	region.rop = ROP_COPY;
 
-	if (rw && !bottom_only) {
+	if ((int) rw > 0 && !bottom_only) {
 		region.dx = info->var.xoffset + rs;
 		region.dy = 0;
 		region.width = rw;
@@ -224,7 +224,7 @@ static void bit_clear_margins(struct vc_data *vc, struct fb_info *info,
 		info->fbops->fb_fillrect(info, &region);
 	}
 
-	if (bh) {
+	if ((int) bh > 0) {
 		region.dx = info->var.xoffset;
 		region.dy = info->var.yoffset + bs;
 		region.width = rs;
diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c
index a9c69ae30878..405ce0357f1b 100644
--- a/drivers/video/fbdev/core/fbcon.c
+++ b/drivers/video/fbdev/core/fbcon.c
@@ -1254,6 +1254,9 @@ finished:
 	if (!con_is_bound(&fb_con))
 		fbcon_exit();
 
+	if (vc->vc_num == logo_shown)
+		logo_shown = FBCON_LOGO_CANSHOW;
+
 	return;
 }
 
diff --git a/drivers/video/fbdev/core/fbcon_ccw.c b/drivers/video/fbdev/core/fbcon_ccw.c
index dfa9a8aa4509..78f3a5621478 100644
--- a/drivers/video/fbdev/core/fbcon_ccw.c
+++ b/drivers/video/fbdev/core/fbcon_ccw.c
@@ -201,7 +201,7 @@ static void ccw_clear_margins(struct vc_data *vc, struct fb_info *info,
 	region.color = color;
 	region.rop = ROP_COPY;
 
-	if (rw && !bottom_only) {
+	if ((int) rw > 0 && !bottom_only) {
 		region.dx = 0;
 		region.dy = info->var.yoffset;
 		region.height = rw;
@@ -209,7 +209,7 @@ static void ccw_clear_margins(struct vc_data *vc, struct fb_info *info,
 		info->fbops->fb_fillrect(info, &region);
 	}
 
-	if (bh) {
+	if ((int) bh > 0) {
 		region.dx = info->var.xoffset + bs;
 		region.dy = 0;
                 region.height = info->var.yres_virtual;
diff --git a/drivers/video/fbdev/core/fbcon_cw.c b/drivers/video/fbdev/core/fbcon_cw.c
index ce08251bfd38..fd098ff17574 100644
--- a/drivers/video/fbdev/core/fbcon_cw.c
+++ b/drivers/video/fbdev/core/fbcon_cw.c
@@ -184,7 +184,7 @@ static void cw_clear_margins(struct vc_data *vc, struct fb_info *info,
 	region.color = color;
 	region.rop = ROP_COPY;
 
-	if (rw && !bottom_only) {
+	if ((int) rw > 0 && !bottom_only) {
 		region.dx = 0;
 		region.dy = info->var.yoffset + rs;
 		region.height = rw;
@@ -192,7 +192,7 @@ static void cw_clear_margins(struct vc_data *vc, struct fb_info *info,
 		info->fbops->fb_fillrect(info, &region);
 	}
 
-	if (bh) {
+	if ((int) bh > 0) {
 		region.dx = info->var.xoffset;
 		region.dy = info->var.yoffset;
                 region.height = info->var.yres;
diff --git a/drivers/video/fbdev/core/fbcon_ud.c b/drivers/video/fbdev/core/fbcon_ud.c
index 1936afc78fec..e165a3fad29a 100644
--- a/drivers/video/fbdev/core/fbcon_ud.c
+++ b/drivers/video/fbdev/core/fbcon_ud.c
@@ -231,7 +231,7 @@ static void ud_clear_margins(struct vc_data *vc, struct fb_info *info,
 	region.color = color;
 	region.rop = ROP_COPY;
 
-	if (rw && !bottom_only) {
+	if ((int) rw > 0 && !bottom_only) {
 		region.dy = 0;
 		region.dx = info->var.xoffset;
 		region.width  = rw;
@@ -239,7 +239,7 @@ static void ud_clear_margins(struct vc_data *vc, struct fb_info *info,
 		info->fbops->fb_fillrect(info, &region);
 	}
 
-	if (bh) {
+	if ((int) bh > 0) {
 		region.dy = info->var.yoffset;
 		region.dx = info->var.xoffset;
                 region.height  = bh;
diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c
index d1949c92be98..aecc5f696f9b 100644
--- a/drivers/video/fbdev/core/fbmem.c
+++ b/drivers/video/fbdev/core/fbmem.c
@@ -673,20 +673,20 @@ int fb_prepare_logo(struct fb_info *info, int rotate)
 		fb_logo.depth = 1;
 
 
- 	if (fb_logo.depth > 4 && depth > 4) {
- 		switch (info->fix.visual) {
- 		case FB_VISUAL_TRUECOLOR:
- 			fb_logo.needs_truepalette = 1;
- 			break;
- 		case FB_VISUAL_DIRECTCOLOR:
- 			fb_logo.needs_directpalette = 1;
- 			fb_logo.needs_cmapreset = 1;
- 			break;
- 		case FB_VISUAL_PSEUDOCOLOR:
- 			fb_logo.needs_cmapreset = 1;
- 			break;
- 		}
- 	}
+	if (fb_logo.depth > 4 && depth > 4) {
+		switch (info->fix.visual) {
+		case FB_VISUAL_TRUECOLOR:
+			fb_logo.needs_truepalette = 1;
+			break;
+		case FB_VISUAL_DIRECTCOLOR:
+			fb_logo.needs_directpalette = 1;
+			fb_logo.needs_cmapreset = 1;
+			break;
+		case FB_VISUAL_PSEUDOCOLOR:
+			fb_logo.needs_cmapreset = 1;
+			break;
+		}
+	}
 
 	height = fb_logo.logo->height;
 	if (fb_center_logo)
@@ -1080,8 +1080,8 @@ fb_blank(struct fb_info *info, int blank)
 	struct fb_event event;
 	int ret = -EINVAL, early_ret;
 
- 	if (blank > FB_BLANK_POWERDOWN)
- 		blank = FB_BLANK_POWERDOWN;
+	if (blank > FB_BLANK_POWERDOWN)
+		blank = FB_BLANK_POWERDOWN;
 
 	event.info = info;
 	event.data = &blank;
@@ -1089,7 +1089,7 @@ fb_blank(struct fb_info *info, int blank)
 	early_ret = fb_notifier_call_chain(FB_EARLY_EVENT_BLANK, &event);
 
 	if (info->fbops->fb_blank)
- 		ret = info->fbops->fb_blank(blank, info);
+		ret = info->fbops->fb_blank(blank, info);
 
 	if (!ret)
 		fb_notifier_call_chain(FB_EVENT_BLANK, &event);
@@ -1102,7 +1102,7 @@ fb_blank(struct fb_info *info, int blank)
 			fb_notifier_call_chain(FB_R_EARLY_EVENT_BLANK, &event);
 	}
 
- 	return ret;
+	return ret;
 }
 EXPORT_SYMBOL(fb_blank);
 
@@ -1147,7 +1147,7 @@ static long do_fb_ioctl(struct fb_info *info, unsigned int cmd,
 	case FBIOGET_FSCREENINFO:
 		if (!lock_fb_info(info))
 			return -ENODEV;
-		fix = info->fix;
+		memcpy(&fix, &info->fix, sizeof(fix));
 		if (info->flags & FBINFO_HIDE_SMEM_START)
 			fix.smem_start = 0;
 		unlock_fb_info(info);
diff --git a/drivers/video/fbdev/neofb.c b/drivers/video/fbdev/neofb.c
index 5d3a444083f7..2018e1ca33eb 100644
--- a/drivers/video/fbdev/neofb.c
+++ b/drivers/video/fbdev/neofb.c
@@ -1820,6 +1820,7 @@ static int neo_scan_monitor(struct fb_info *info)
 #else
 		printk(KERN_ERR
 		       "neofb: Only 640x480, 800x600/480 and 1024x768 panels are currently supported\n");
+		kfree(info->monspecs.modedb);
 		return -1;
 #endif
 	default:
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dss.c b/drivers/video/fbdev/omap2/omapfb/dss/dss.c
index 7252d22dd117..bfc5c4c5a26a 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/dss.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/dss.c
@@ -833,7 +833,7 @@ static const struct dss_features omap34xx_dss_feats = {
 };
 
 static const struct dss_features omap3630_dss_feats = {
-	.fck_div_max		=	32,
+	.fck_div_max		=	31,
 	.dss_fck_multiplier	=	1,
 	.parent_clk_name	=	"dpll4_ck",
 	.dpi_select_source	=	&dss_dpi_select_source_omap2_omap3,
diff --git a/drivers/video/fbdev/pxa168fb.c b/drivers/video/fbdev/pxa168fb.c
index 1410f476e135..1fc50fc0694b 100644
--- a/drivers/video/fbdev/pxa168fb.c
+++ b/drivers/video/fbdev/pxa168fb.c
@@ -766,8 +766,8 @@ failed_free_cmap:
 failed_free_clk:
 	clk_disable_unprepare(fbi->clk);
 failed_free_fbmem:
-	dma_free_coherent(fbi->dev, info->fix.smem_len,
-			info->screen_base, fbi->fb_start_dma);
+	dma_free_wc(fbi->dev, info->fix.smem_len,
+		    info->screen_base, fbi->fb_start_dma);
 failed_free_info:
 	kfree(info);
 
@@ -801,7 +801,7 @@ static int pxa168fb_remove(struct platform_device *pdev)
 
 	irq = platform_get_irq(pdev, 0);
 
-	dma_free_wc(fbi->dev, PAGE_ALIGN(info->fix.smem_len),
+	dma_free_wc(fbi->dev, info->fix.smem_len,
 		    info->screen_base, info->fix.smem_start);
 
 	clk_disable_unprepare(fbi->clk);
diff --git a/drivers/video/fbdev/pxafb.c b/drivers/video/fbdev/pxafb.c
index d59c8a59f582..90dee3e6f8bc 100644
--- a/drivers/video/fbdev/pxafb.c
+++ b/drivers/video/fbdev/pxafb.c
@@ -2446,8 +2446,8 @@ static int pxafb_remove(struct platform_device *dev)
 
 	free_pages_exact(fbi->video_mem, fbi->video_mem_size);
 
-	dma_free_wc(&dev->dev, fbi->dma_buff_size, fbi->dma_buff,
-		    fbi->dma_buff_phys);
+	dma_free_coherent(&dev->dev, fbi->dma_buff_size, fbi->dma_buff,
+			  fbi->dma_buff_phys);
 
 	return 0;
 }
diff --git a/drivers/video/fbdev/savage/savagefb_driver.c b/drivers/video/fbdev/savage/savagefb_driver.c
index 47b78f0138c3..cb608b76cc40 100644
--- a/drivers/video/fbdev/savage/savagefb_driver.c
+++ b/drivers/video/fbdev/savage/savagefb_driver.c
@@ -2158,6 +2158,8 @@ static int savage_init_fb_info(struct fb_info *info, struct pci_dev *dev,
 			info->flags |= FBINFO_HWACCEL_COPYAREA |
 				       FBINFO_HWACCEL_FILLRECT |
 				       FBINFO_HWACCEL_IMAGEBLIT;
+		else
+			kfree(info->pixmap.addr);
 	}
 #endif
 	return err;
diff --git a/drivers/video/fbdev/sm712fb.c b/drivers/video/fbdev/sm712fb.c
index f1dcc6766d1e..1781ca697f66 100644
--- a/drivers/video/fbdev/sm712fb.c
+++ b/drivers/video/fbdev/sm712fb.c
@@ -1429,6 +1429,8 @@ static int smtc_map_smem(struct smtcfb_info *sfb,
 static void smtc_unmap_smem(struct smtcfb_info *sfb)
 {
 	if (sfb && sfb->fb->screen_base) {
+		if (sfb->chip_id == 0x720)
+			sfb->fb->screen_base -= 0x00200000;
 		iounmap(sfb->fb->screen_base);
 		sfb->fb->screen_base = NULL;
 	}
diff --git a/drivers/video/fbdev/vt8500lcdfb.c b/drivers/video/fbdev/vt8500lcdfb.c
index be8d9702cbb2..4b84fd4483e1 100644
--- a/drivers/video/fbdev/vt8500lcdfb.c
+++ b/drivers/video/fbdev/vt8500lcdfb.c
@@ -230,6 +230,7 @@ static int vt8500lcd_blank(int blank, struct fb_info *info)
 		    info->fix.visual == FB_VISUAL_STATIC_PSEUDOCOLOR)
 			for (i = 0; i < 256; i++)
 				vt8500lcd_setcolreg(i, 0, 0, 0, 0, info);
+		fallthrough;
 	case FB_BLANK_UNBLANK:
 		if (info->fix.visual == FB_VISUAL_PSEUDOCOLOR ||
 		    info->fix.visual == FB_VISUAL_STATIC_PSEUDOCOLOR)
diff --git a/drivers/video/fbdev/w100fb.c b/drivers/video/fbdev/w100fb.c
index 597ffaa13cd2..5b4c6a84e84d 100644
--- a/drivers/video/fbdev/w100fb.c
+++ b/drivers/video/fbdev/w100fb.c
@@ -579,6 +579,7 @@ static void w100fb_restore_vidmem(struct w100fb_par *par)
 		memsize=par->mach->mem->size;
 		memcpy_toio(remapped_fbuf + (W100_FB_BASE-MEM_WINDOW_BASE), par->saved_extmem, memsize);
 		vfree(par->saved_extmem);
+		par->saved_extmem = NULL;
 	}
 	if (par->saved_intmem) {
 		memsize=MEM_INT_SIZE;
@@ -587,6 +588,7 @@ static void w100fb_restore_vidmem(struct w100fb_par *par)
 		else
 			memcpy_toio(remapped_fbuf + (W100_FB_BASE-MEM_WINDOW_BASE), par->saved_intmem, memsize);
 		vfree(par->saved_intmem);
+		par->saved_intmem = NULL;
 	}
 }
 
diff --git a/drivers/virt/vboxguest/vboxguest_core.c b/drivers/virt/vboxguest/vboxguest_core.c
index 2307b0329aec..95bfdb8ac8a2 100644
--- a/drivers/virt/vboxguest/vboxguest_core.c
+++ b/drivers/virt/vboxguest/vboxguest_core.c
@@ -1443,7 +1443,7 @@ static int vbg_ioctl_change_guest_capabilities(struct vbg_dev *gdev,
 	or_mask = caps->u.in.or_mask;
 	not_mask = caps->u.in.not_mask;
 
-	if ((or_mask | not_mask) & ~VMMDEV_EVENT_VALID_EVENT_MASK)
+	if ((or_mask | not_mask) & ~VMMDEV_GUEST_CAPABILITIES_MASK)
 		return -EINVAL;
 
 	ret = vbg_set_session_capabilities(gdev, session, or_mask, not_mask,
@@ -1519,7 +1519,8 @@ int vbg_core_ioctl(struct vbg_session *session, unsigned int req, void *data)
 
 	/* For VMMDEV_REQUEST hdr->type != VBG_IOCTL_HDR_TYPE_DEFAULT */
 	if (req_no_size == VBG_IOCTL_VMMDEV_REQUEST(0) ||
-	    req == VBG_IOCTL_VMMDEV_REQUEST_BIG)
+	    req == VBG_IOCTL_VMMDEV_REQUEST_BIG ||
+	    req == VBG_IOCTL_VMMDEV_REQUEST_BIG_ALT)
 		return vbg_ioctl_vmmrequest(gdev, session, data);
 
 	if (hdr->type != VBG_IOCTL_HDR_TYPE_DEFAULT)
@@ -1557,6 +1558,7 @@ int vbg_core_ioctl(struct vbg_session *session, unsigned int req, void *data)
 	case VBG_IOCTL_HGCM_CALL(0):
 		return vbg_ioctl_hgcm_call(gdev, session, f32bit, data);
 	case VBG_IOCTL_LOG(0):
+	case VBG_IOCTL_LOG_ALT(0):
 		return vbg_ioctl_log(data);
 	}
 
diff --git a/drivers/virt/vboxguest/vboxguest_core.h b/drivers/virt/vboxguest/vboxguest_core.h
index 4188c12b839f..77c3a9c8255d 100644
--- a/drivers/virt/vboxguest/vboxguest_core.h
+++ b/drivers/virt/vboxguest/vboxguest_core.h
@@ -15,6 +15,21 @@
 #include <linux/vboxguest.h>
 #include "vmmdev.h"
 
+/*
+ * The mainline kernel version (this version) of the vboxguest module
+ * contained a bug where it defined VBGL_IOCTL_VMMDEV_REQUEST_BIG and
+ * VBGL_IOCTL_LOG using _IOC(_IOC_READ | _IOC_WRITE, 'V', ...) instead
+ * of _IO(V, ...) as the out of tree VirtualBox upstream version does.
+ *
+ * These _ALT definitions keep compatibility with the wrong defines the
+ * mainline kernel version used for a while.
+ * Note the VirtualBox userspace bits have always been built against
+ * VirtualBox upstream's headers, so this is likely not necessary. But
+ * we must never break our ABI so we keep these around to be 100% sure.
+ */
+#define VBG_IOCTL_VMMDEV_REQUEST_BIG_ALT _IOC(_IOC_READ | _IOC_WRITE, 'V', 3, 0)
+#define VBG_IOCTL_LOG_ALT(s)             _IOC(_IOC_READ | _IOC_WRITE, 'V', 9, s)
+
 struct vbg_session;
 
 /** VBox guest memory balloon. */
diff --git a/drivers/virt/vboxguest/vboxguest_linux.c b/drivers/virt/vboxguest/vboxguest_linux.c
index 6e8c0f1c1056..32c2c52f7e84 100644
--- a/drivers/virt/vboxguest/vboxguest_linux.c
+++ b/drivers/virt/vboxguest/vboxguest_linux.c
@@ -131,7 +131,8 @@ static long vbg_misc_device_ioctl(struct file *filp, unsigned int req,
 	 * the need for a bounce-buffer and another copy later on.
 	 */
 	is_vmmdev_req = (req & ~IOCSIZE_MASK) == VBG_IOCTL_VMMDEV_REQUEST(0) ||
-			 req == VBG_IOCTL_VMMDEV_REQUEST_BIG;
+			 req == VBG_IOCTL_VMMDEV_REQUEST_BIG ||
+			 req == VBG_IOCTL_VMMDEV_REQUEST_BIG_ALT;
 
 	if (is_vmmdev_req)
 		buf = vbg_req_alloc(size, VBG_IOCTL_HDR_TYPE_DEFAULT,
diff --git a/drivers/virt/vboxguest/vmmdev.h b/drivers/virt/vboxguest/vmmdev.h
index 6337b8d75d96..21f408120e3f 100644
--- a/drivers/virt/vboxguest/vmmdev.h
+++ b/drivers/virt/vboxguest/vmmdev.h
@@ -206,6 +206,8 @@ VMMDEV_ASSERT_SIZE(vmmdev_mask, 24 + 8);
  * not.
  */
 #define VMMDEV_GUEST_SUPPORTS_GRAPHICS                      BIT(2)
+/* The mask of valid capabilities, for sanity checking. */
+#define VMMDEV_GUEST_CAPABILITIES_MASK                      0x00000007U
 
 /** struct vmmdev_hypervisorinfo - Hypervisor info structure. */
 struct vmmdev_hypervisorinfo {
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 848383ebe19f..d3e0c2182111 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -156,6 +156,8 @@ static void set_page_pfns(struct virtio_balloon *vb,
 {
 	unsigned int i;
 
+	BUILD_BUG_ON(VIRTIO_BALLOON_PAGES_PER_PAGE > VIRTIO_BALLOON_ARRAY_PFNS_MAX);
+
 	/*
 	 * Set balloon pfns pointing at this page.
 	 * Note that the first pfn points at start of the page.
@@ -473,7 +475,9 @@ static int init_vqs(struct virtio_balloon *vb)
 	names[VIRTIO_BALLOON_VQ_INFLATE] = "inflate";
 	callbacks[VIRTIO_BALLOON_VQ_DEFLATE] = balloon_ack;
 	names[VIRTIO_BALLOON_VQ_DEFLATE] = "deflate";
+	callbacks[VIRTIO_BALLOON_VQ_STATS] = NULL;
 	names[VIRTIO_BALLOON_VQ_STATS] = NULL;
+	callbacks[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL;
 	names[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL;
 
 	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
@@ -524,10 +528,14 @@ static int init_vqs(struct virtio_balloon *vb)
 static u32 virtio_balloon_cmd_id_received(struct virtio_balloon *vb)
 {
 	if (test_and_clear_bit(VIRTIO_BALLOON_CONFIG_READ_CMD_ID,
-			       &vb->config_read_bitmap))
+			       &vb->config_read_bitmap)) {
 		virtio_cread(vb->vdev, struct virtio_balloon_config,
 			     free_page_report_cmd_id,
 			     &vb->cmd_id_received_cache);
+		/* Legacy balloon config space is LE, unlike all other devices. */
+		if (!virtio_has_feature(vb->vdev, VIRTIO_F_VERSION_1))
+			vb->cmd_id_received_cache = le32_to_cpu((__force __le32)vb->cmd_id_received_cache);
+	}
 
 	return vb->cmd_id_received_cache;
 }
@@ -897,8 +905,7 @@ static int virtballoon_probe(struct virtio_device *vdev)
 	vb->vb_dev_info.inode = alloc_anon_inode(balloon_mnt->mnt_sb);
 	if (IS_ERR(vb->vb_dev_info.inode)) {
 		err = PTR_ERR(vb->vb_dev_info.inode);
-		kern_unmount(balloon_mnt);
-		goto out_del_vqs;
+		goto out_kern_unmount;
 	}
 	vb->vb_dev_info.inode->i_mapping->a_ops = &balloon_aops;
 #endif
@@ -909,13 +916,13 @@ static int virtballoon_probe(struct virtio_device *vdev)
 		 */
 		if (virtqueue_get_vring_size(vb->free_page_vq) < 2) {
 			err = -ENOSPC;
-			goto out_del_vqs;
+			goto out_iput;
 		}
 		vb->balloon_wq = alloc_workqueue("balloon-wq",
 					WQ_FREEZABLE | WQ_CPU_INTENSIVE, 0);
 		if (!vb->balloon_wq) {
 			err = -ENOMEM;
-			goto out_del_vqs;
+			goto out_iput;
 		}
 		INIT_WORK(&vb->report_free_page_work, report_free_page_func);
 		vb->cmd_id_received_cache = VIRTIO_BALLOON_CMD_ID_STOP;
@@ -949,7 +956,13 @@ static int virtballoon_probe(struct virtio_device *vdev)
 out_del_balloon_wq:
 	if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
 		destroy_workqueue(vb->balloon_wq);
+out_iput:
+#ifdef CONFIG_BALLOON_COMPACTION
+	iput(vb->vb_dev_info.inode);
+out_kern_unmount:
+	kern_unmount(balloon_mnt);
 out_del_vqs:
+#endif
 	vdev->config->del_vqs(vdev);
 out_free_vb:
 	kfree(vb);
@@ -964,6 +977,10 @@ static void remove_common(struct virtio_balloon *vb)
 		leak_balloon(vb, vb->num_pages);
 	update_balloon_size(vb);
 
+	/* There might be free pages that are being reported: release them. */
+	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
+		return_free_pages_to_mm(vb, ULONG_MAX);
+
 	/* Now we reset the device so we can clean up the queues. */
 	vb->vdev->config->reset(vb->vdev);
 
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index e09edb5c5e06..45a06d81ca75 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -652,11 +652,11 @@ static int vm_cmdline_set(const char *device,
 			&vm_cmdline_id, &consumed);
 
 	/*
-	 * sscanf() must processes at least 2 chunks; also there
+	 * sscanf() must process at least 2 chunks; also there
 	 * must be no extra characters after the last chunk, so
 	 * str[consumed] must be '\0'
 	 */
-	if (processed < 2 || str[consumed])
+	if (processed < 2 || str[consumed] || irq == 0)
 		return -EINVAL;
 
 	resources[0].flags = IORESOURCE_MEM;
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index f2862f66c2ac..222d630c41fc 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -294,7 +294,7 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs,
 		/* Best option: one for change interrupt, one per vq. */
 		nvectors = 1;
 		for (i = 0; i < nvqs; ++i)
-			if (callbacks[i])
+			if (names[i] && callbacks[i])
 				++nvectors;
 	} else {
 		/* Second best: one for change, shared for all vqs. */
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 4ff48b8e5924..f1ce14ba186d 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -2199,10 +2199,10 @@ void vring_del_virtqueue(struct virtqueue *_vq)
 					 vq->split.queue_size_in_bytes,
 					 vq->split.vring.desc,
 					 vq->split.queue_dma_addr);
-
-			kfree(vq->split.desc_state);
 		}
 	}
+	if (!vq->packed_ring)
+		kfree(vq->split.desc_state);
 	list_del(&_vq->list);
 	kfree(vq);
 }
diff --git a/drivers/visorbus/visorchipset.c b/drivers/visorbus/visorchipset.c
index ca752b8f495f..cb1eb7e05f87 100644
--- a/drivers/visorbus/visorchipset.c
+++ b/drivers/visorbus/visorchipset.c
@@ -1210,14 +1210,17 @@ static void setup_crash_devices_work_queue(struct work_struct *work)
 {
 	struct controlvm_message local_crash_bus_msg;
 	struct controlvm_message local_crash_dev_msg;
-	struct controlvm_message msg;
+	struct controlvm_message msg = {
+		.hdr.id = CONTROLVM_CHIPSET_INIT,
+		.cmd.init_chipset = {
+			.bus_count = 23,
+			.switch_count = 0,
+		},
+	};
 	u32 local_crash_msg_offset;
 	u16 local_crash_msg_count;
 
 	/* send init chipset msg */
-	msg.hdr.id = CONTROLVM_CHIPSET_INIT;
-	msg.cmd.init_chipset.bus_count = 23;
-	msg.cmd.init_chipset.switch_count = 0;
 	chipset_init(&msg);
 	/* get saved message count */
 	if (visorchannel_read(chipset_dev->controlvm_channel,
diff --git a/drivers/vme/bridges/vme_fake.c b/drivers/vme/bridges/vme_fake.c
index 3208a4409e44..6a1bc284f297 100644
--- a/drivers/vme/bridges/vme_fake.c
+++ b/drivers/vme/bridges/vme_fake.c
@@ -414,8 +414,9 @@ static void fake_lm_check(struct fake_driver *bridge, unsigned long long addr,
 	}
 }
 
-static u8 fake_vmeread8(struct fake_driver *bridge, unsigned long long addr,
-		u32 aspace, u32 cycle)
+static noinline_for_stack u8 fake_vmeread8(struct fake_driver *bridge,
+					   unsigned long long addr,
+					   u32 aspace, u32 cycle)
 {
 	u8 retval = 0xff;
 	int i;
@@ -446,8 +447,9 @@ static u8 fake_vmeread8(struct fake_driver *bridge, unsigned long long addr,
 	return retval;
 }
 
-static u16 fake_vmeread16(struct fake_driver *bridge, unsigned long long addr,
-		u32 aspace, u32 cycle)
+static noinline_for_stack u16 fake_vmeread16(struct fake_driver *bridge,
+					     unsigned long long addr,
+					     u32 aspace, u32 cycle)
 {
 	u16 retval = 0xffff;
 	int i;
@@ -478,8 +480,9 @@ static u16 fake_vmeread16(struct fake_driver *bridge, unsigned long long addr,
 	return retval;
 }
 
-static u32 fake_vmeread32(struct fake_driver *bridge, unsigned long long addr,
-		u32 aspace, u32 cycle)
+static noinline_for_stack u32 fake_vmeread32(struct fake_driver *bridge,
+					     unsigned long long addr,
+					     u32 aspace, u32 cycle)
 {
 	u32 retval = 0xffffffff;
 	int i;
@@ -609,8 +612,9 @@ out:
 	return retval;
 }
 
-static void fake_vmewrite8(struct fake_driver *bridge, u8 *buf,
-			   unsigned long long addr, u32 aspace, u32 cycle)
+static noinline_for_stack void fake_vmewrite8(struct fake_driver *bridge,
+					      u8 *buf, unsigned long long addr,
+					      u32 aspace, u32 cycle)
 {
 	int i;
 	unsigned long long start, end, offset;
@@ -639,8 +643,9 @@ static void fake_vmewrite8(struct fake_driver *bridge, u8 *buf,
 
 }
 
-static void fake_vmewrite16(struct fake_driver *bridge, u16 *buf,
-			    unsigned long long addr, u32 aspace, u32 cycle)
+static noinline_for_stack void fake_vmewrite16(struct fake_driver *bridge,
+					       u16 *buf, unsigned long long addr,
+					       u32 aspace, u32 cycle)
 {
 	int i;
 	unsigned long long start, end, offset;
@@ -669,8 +674,9 @@ static void fake_vmewrite16(struct fake_driver *bridge, u16 *buf,
 
 }
 
-static void fake_vmewrite32(struct fake_driver *bridge, u32 *buf,
-			    unsigned long long addr, u32 aspace, u32 cycle)
+static noinline_for_stack void fake_vmewrite32(struct fake_driver *bridge,
+					       u32 *buf, unsigned long long addr,
+					       u32 aspace, u32 cycle)
 {
 	int i;
 	unsigned long long start, end, offset;
diff --git a/drivers/w1/masters/omap_hdq.c b/drivers/w1/masters/omap_hdq.c
index 3099052e1243..0667bc6e7d23 100644
--- a/drivers/w1/masters/omap_hdq.c
+++ b/drivers/w1/masters/omap_hdq.c
@@ -176,7 +176,7 @@ static int hdq_write_byte(struct hdq_data *hdq_data, u8 val, u8 *status)
 	/* check irqstatus */
 	if (!(*status & OMAP_HDQ_INT_STATUS_TXCOMPLETE)) {
 		dev_dbg(hdq_data->dev, "timeout waiting for"
-			" TXCOMPLETE/RXCOMPLETE, %x", *status);
+			" TXCOMPLETE/RXCOMPLETE, %x\n", *status);
 		ret = -ETIMEDOUT;
 		goto out;
 	}
@@ -187,7 +187,7 @@ static int hdq_write_byte(struct hdq_data *hdq_data, u8 val, u8 *status)
 			OMAP_HDQ_FLAG_CLEAR, &tmp_status);
 	if (ret) {
 		dev_dbg(hdq_data->dev, "timeout waiting GO bit"
-			" return to zero, %x", tmp_status);
+			" return to zero, %x\n", tmp_status);
 	}
 
 out:
@@ -203,7 +203,7 @@ static irqreturn_t hdq_isr(int irq, void *_hdq)
 	spin_lock_irqsave(&hdq_data->hdq_spinlock, irqflags);
 	hdq_data->hdq_irqstatus = hdq_reg_in(hdq_data, OMAP_HDQ_INT_STATUS);
 	spin_unlock_irqrestore(&hdq_data->hdq_spinlock, irqflags);
-	dev_dbg(hdq_data->dev, "hdq_isr: %x", hdq_data->hdq_irqstatus);
+	dev_dbg(hdq_data->dev, "hdq_isr: %x\n", hdq_data->hdq_irqstatus);
 
 	if (hdq_data->hdq_irqstatus &
 		(OMAP_HDQ_INT_STATUS_TXCOMPLETE | OMAP_HDQ_INT_STATUS_RXCOMPLETE
@@ -311,7 +311,7 @@ static int omap_hdq_break(struct hdq_data *hdq_data)
 	tmp_status = hdq_data->hdq_irqstatus;
 	/* check irqstatus */
 	if (!(tmp_status & OMAP_HDQ_INT_STATUS_TIMEOUT)) {
-		dev_dbg(hdq_data->dev, "timeout waiting for TIMEOUT, %x",
+		dev_dbg(hdq_data->dev, "timeout waiting for TIMEOUT, %x\n",
 				tmp_status);
 		ret = -ETIMEDOUT;
 		goto out;
@@ -338,7 +338,7 @@ static int omap_hdq_break(struct hdq_data *hdq_data)
 			&tmp_status);
 	if (ret)
 		dev_dbg(hdq_data->dev, "timeout waiting INIT&GO bits"
-			" return to zero, %x", tmp_status);
+			" return to zero, %x\n", tmp_status);
 
 out:
 	mutex_unlock(&hdq_data->hdq_mutex);
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index ffe754539f5a..44d2a41cd2d3 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -694,6 +694,7 @@ config MAX63XX_WATCHDOG
 config MAX77620_WATCHDOG
 	tristate "Maxim Max77620 Watchdog Timer"
 	depends on MFD_MAX77620 || COMPILE_TEST
+	select WATCHDOG_CORE
 	help
 	 This is the driver for the Max77620 watchdog timer.
 	 Say 'Y' here to enable the watchdog timer support for
@@ -1437,6 +1438,7 @@ config SMSC37B787_WDT
 config TQMX86_WDT
 	tristate "TQ-Systems TQMX86 Watchdog Timer"
 	depends on X86
+	select WATCHDOG_CORE
 	help
 	This is the driver for the hardware watchdog timer in the TQMX86 IO
 	controller found on some of their ComExpress Modules.
diff --git a/drivers/watchdog/da9062_wdt.c b/drivers/watchdog/da9062_wdt.c
index aac749cfaccb..7929797edcdb 100644
--- a/drivers/watchdog/da9062_wdt.c
+++ b/drivers/watchdog/da9062_wdt.c
@@ -55,11 +55,6 @@ static int da9062_wdt_update_timeout_register(struct da9062_watchdog *wdt,
 					      unsigned int regval)
 {
 	struct da9062 *chip = wdt->hw;
-	int ret;
-
-	ret = da9062_reset_watchdog_timer(wdt);
-	if (ret)
-		return ret;
 
 	regmap_update_bits(chip->regmap,
 				  DA9062AA_CONTROL_D,
@@ -94,13 +89,6 @@ static int da9062_wdt_stop(struct watchdog_device *wdd)
 	struct da9062_watchdog *wdt = watchdog_get_drvdata(wdd);
 	int ret;
 
-	ret = da9062_reset_watchdog_timer(wdt);
-	if (ret) {
-		dev_err(wdt->hw->dev, "Failed to ping the watchdog (err = %d)\n",
-			ret);
-		return ret;
-	}
-
 	ret = regmap_update_bits(wdt->hw->regmap,
 				 DA9062AA_CONTROL_D,
 				 DA9062AA_TWDSCALE_MASK,
diff --git a/drivers/watchdog/f71808e_wdt.c b/drivers/watchdog/f71808e_wdt.c
index ff5cf1b48a4d..491ba2d973ac 100644
--- a/drivers/watchdog/f71808e_wdt.c
+++ b/drivers/watchdog/f71808e_wdt.c
@@ -677,9 +677,9 @@ static int __init watchdog_init(int sioaddr)
 	 * into the module have been registered yet.
 	 */
 	watchdog.sioaddr = sioaddr;
-	watchdog.ident.options = WDIOC_SETTIMEOUT
-				| WDIOF_MAGICCLOSE
-				| WDIOF_KEEPALIVEPING;
+	watchdog.ident.options = WDIOF_MAGICCLOSE
+				| WDIOF_KEEPALIVEPING
+				| WDIOF_CARDRESET;
 
 	snprintf(watchdog.ident.identity,
 		sizeof(watchdog.ident.identity), "%s watchdog",
@@ -693,6 +693,13 @@ static int __init watchdog_init(int sioaddr)
 	wdt_conf = superio_inb(sioaddr, F71808FG_REG_WDT_CONF);
 	watchdog.caused_reboot = wdt_conf & BIT(F71808FG_FLAG_WDTMOUT_STS);
 
+	/*
+	 * We don't want WDTMOUT_STS to stick around till regular reboot.
+	 * Write 1 to the bit to clear it to zero.
+	 */
+	superio_outb(sioaddr, F71808FG_REG_WDT_CONF,
+		     wdt_conf | BIT(F71808FG_FLAG_WDTMOUT_STS));
+
 	superio_exit(sioaddr);
 
 	err = watchdog_set_timeout(timeout);
diff --git a/drivers/watchdog/iTCO_vendor.h b/drivers/watchdog/iTCO_vendor.h
index 0f7373ba10d5..69e92e692ae0 100644
--- a/drivers/watchdog/iTCO_vendor.h
+++ b/drivers/watchdog/iTCO_vendor.h
@@ -1,10 +1,12 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* iTCO Vendor Specific Support hooks */
 #ifdef CONFIG_ITCO_VENDOR_SUPPORT
+extern int iTCO_vendorsupport;
 extern void iTCO_vendor_pre_start(struct resource *, unsigned int);
 extern void iTCO_vendor_pre_stop(struct resource *);
 extern int iTCO_vendor_check_noreboot_on(void);
 #else
+#define iTCO_vendorsupport				0
 #define iTCO_vendor_pre_start(acpibase, heartbeat)	{}
 #define iTCO_vendor_pre_stop(acpibase)			{}
 #define iTCO_vendor_check_noreboot_on()			1
diff --git a/drivers/watchdog/iTCO_vendor_support.c b/drivers/watchdog/iTCO_vendor_support.c
index 68a9d9cc2eb8..0075e9351caa 100644
--- a/drivers/watchdog/iTCO_vendor_support.c
+++ b/drivers/watchdog/iTCO_vendor_support.c
@@ -43,8 +43,10 @@
 /* Broken BIOS */
 #define BROKEN_BIOS		911
 
-static int vendorsupport;
-module_param(vendorsupport, int, 0);
+int iTCO_vendorsupport;
+EXPORT_SYMBOL(iTCO_vendorsupport);
+
+module_param_named(vendorsupport, iTCO_vendorsupport, int, 0);
 MODULE_PARM_DESC(vendorsupport, "iTCO vendor specific support mode, default="
 			"0 (none), 1=SuperMicro Pent3, 911=Broken SMI BIOS");
 
@@ -156,7 +158,7 @@ static void broken_bios_stop(struct resource *smires)
 void iTCO_vendor_pre_start(struct resource *smires,
 			   unsigned int heartbeat)
 {
-	switch (vendorsupport) {
+	switch (iTCO_vendorsupport) {
 	case SUPERMICRO_OLD_BOARD:
 		supermicro_old_pre_start(smires);
 		break;
@@ -169,7 +171,7 @@ EXPORT_SYMBOL(iTCO_vendor_pre_start);
 
 void iTCO_vendor_pre_stop(struct resource *smires)
 {
-	switch (vendorsupport) {
+	switch (iTCO_vendorsupport) {
 	case SUPERMICRO_OLD_BOARD:
 		supermicro_old_pre_stop(smires);
 		break;
@@ -182,7 +184,7 @@ EXPORT_SYMBOL(iTCO_vendor_pre_stop);
 
 int iTCO_vendor_check_noreboot_on(void)
 {
-	switch (vendorsupport) {
+	switch (iTCO_vendorsupport) {
 	case SUPERMICRO_OLD_BOARD:
 		return 0;
 	default:
@@ -193,13 +195,13 @@ EXPORT_SYMBOL(iTCO_vendor_check_noreboot_on);
 
 static int __init iTCO_vendor_init_module(void)
 {
-	if (vendorsupport == SUPERMICRO_NEW_BOARD) {
+	if (iTCO_vendorsupport == SUPERMICRO_NEW_BOARD) {
 		pr_warn("Option vendorsupport=%d is no longer supported, "
 			"please use the w83627hf_wdt driver instead\n",
 			SUPERMICRO_NEW_BOARD);
 		return -EINVAL;
 	}
-	pr_info("vendor-support=%d\n", vendorsupport);
+	pr_info("vendor-support=%d\n", iTCO_vendorsupport);
 	return 0;
 }
 
diff --git a/drivers/watchdog/iTCO_wdt.c b/drivers/watchdog/iTCO_wdt.c
index 89cea6ce9a08..d21e9761e4ac 100644
--- a/drivers/watchdog/iTCO_wdt.c
+++ b/drivers/watchdog/iTCO_wdt.c
@@ -443,13 +443,25 @@ static int iTCO_wdt_probe(struct platform_device *pdev)
 	if (!p->tco_res)
 		return -ENODEV;
 
-	p->smi_res = platform_get_resource(pdev, IORESOURCE_IO, ICH_RES_IO_SMI);
-	if (!p->smi_res)
-		return -ENODEV;
-
 	p->iTCO_version = pdata->version;
 	p->pci_dev = to_pci_dev(dev->parent);
 
+	p->smi_res = platform_get_resource(pdev, IORESOURCE_IO, ICH_RES_IO_SMI);
+	if (p->smi_res) {
+		/* The TCO logic uses the TCO_EN bit in the SMI_EN register */
+		if (!devm_request_region(dev, p->smi_res->start,
+					 resource_size(p->smi_res),
+					 pdev->name)) {
+			pr_err("I/O address 0x%04llx already in use, device disabled\n",
+			       (u64)SMI_EN(p));
+			return -EBUSY;
+		}
+	} else if (iTCO_vendorsupport ||
+		   turn_SMI_watchdog_clear_off >= p->iTCO_version) {
+		pr_err("SMI I/O resource is missing\n");
+		return -ENODEV;
+	}
+
 	iTCO_wdt_no_reboot_bit_setup(p, pdata);
 
 	/*
@@ -475,14 +487,6 @@ static int iTCO_wdt_probe(struct platform_device *pdev)
 	/* Set the NO_REBOOT bit to prevent later reboots, just for sure */
 	p->update_no_reboot_bit(p->no_reboot_priv, true);
 
-	/* The TCO logic uses the TCO_EN bit in the SMI_EN register */
-	if (!devm_request_region(dev, p->smi_res->start,
-				 resource_size(p->smi_res),
-				 pdev->name)) {
-		pr_err("I/O address 0x%04llx already in use, device disabled\n",
-		       (u64)SMI_EN(p));
-		return -EBUSY;
-	}
 	if (turn_SMI_watchdog_clear_off >= p->iTCO_version) {
 		/*
 		 * Bit 13: TCO_EN -> 0
diff --git a/drivers/watchdog/imx_sc_wdt.c b/drivers/watchdog/imx_sc_wdt.c
index 49848b66186c..ed8adad5c16f 100644
--- a/drivers/watchdog/imx_sc_wdt.c
+++ b/drivers/watchdog/imx_sc_wdt.c
@@ -119,6 +119,11 @@ static int imx_sc_wdt_probe(struct platform_device *pdev)
 	imx_sc_wdd->timeout = DEFAULT_TIMEOUT;
 
 	watchdog_init_timeout(imx_sc_wdd, 0, dev);
+
+	ret = imx_sc_wdt_set_timeout(imx_sc_wdd, imx_sc_wdd->timeout);
+	if (ret)
+		return ret;
+
 	watchdog_stop_on_reboot(imx_sc_wdd);
 	watchdog_stop_on_unregister(imx_sc_wdd);
 
diff --git a/drivers/watchdog/orion_wdt.c b/drivers/watchdog/orion_wdt.c
index cdb0d174c5e2..8e6dfe76f9c9 100644
--- a/drivers/watchdog/orion_wdt.c
+++ b/drivers/watchdog/orion_wdt.c
@@ -35,7 +35,15 @@
  * Watchdog timer block registers.
  */
 #define TIMER_CTRL		0x0000
-#define TIMER_A370_STATUS	0x04
+#define TIMER1_FIXED_ENABLE_BIT	BIT(12)
+#define WDT_AXP_FIXED_ENABLE_BIT BIT(10)
+#define TIMER1_ENABLE_BIT	BIT(2)
+
+#define TIMER_A370_STATUS	0x0004
+#define WDT_A370_EXPIRED	BIT(31)
+#define TIMER1_STATUS_BIT	BIT(8)
+
+#define TIMER1_VAL_OFF		0x001c
 
 #define WDT_MAX_CYCLE_COUNT	0xffffffff
 
@@ -43,9 +51,6 @@
 #define WDT_A370_RATIO_SHIFT	5
 #define WDT_A370_RATIO		(1 << WDT_A370_RATIO_SHIFT)
 
-#define WDT_AXP_FIXED_ENABLE_BIT BIT(10)
-#define WDT_A370_EXPIRED	BIT(31)
-
 static bool nowayout = WATCHDOG_NOWAYOUT;
 static int heartbeat = -1;		/* module parameter (seconds) */
 
@@ -158,6 +163,7 @@ static int armadaxp_wdt_clock_init(struct platform_device *pdev,
 				   struct orion_watchdog *dev)
 {
 	int ret;
+	u32 val;
 
 	dev->clk = of_clk_get_by_name(pdev->dev.of_node, "fixed");
 	if (IS_ERR(dev->clk))
@@ -168,10 +174,9 @@ static int armadaxp_wdt_clock_init(struct platform_device *pdev,
 		return ret;
 	}
 
-	/* Enable the fixed watchdog clock input */
-	atomic_io_modify(dev->reg + TIMER_CTRL,
-			 WDT_AXP_FIXED_ENABLE_BIT,
-			 WDT_AXP_FIXED_ENABLE_BIT);
+	/* Fix the wdt and timer1 clock freqency to 25MHz */
+	val = WDT_AXP_FIXED_ENABLE_BIT | TIMER1_FIXED_ENABLE_BIT;
+	atomic_io_modify(dev->reg + TIMER_CTRL, val, val);
 
 	dev->clk_rate = clk_get_rate(dev->clk);
 	return 0;
@@ -183,6 +188,10 @@ static int orion_wdt_ping(struct watchdog_device *wdt_dev)
 	/* Reload watchdog duration */
 	writel(dev->clk_rate * wdt_dev->timeout,
 	       dev->reg + dev->data->wdt_counter_offset);
+	if (dev->wdt.info->options & WDIOF_PRETIMEOUT)
+		writel(dev->clk_rate * (wdt_dev->timeout - wdt_dev->pretimeout),
+		       dev->reg + TIMER1_VAL_OFF);
+
 	return 0;
 }
 
@@ -194,13 +203,18 @@ static int armada375_start(struct watchdog_device *wdt_dev)
 	/* Set watchdog duration */
 	writel(dev->clk_rate * wdt_dev->timeout,
 	       dev->reg + dev->data->wdt_counter_offset);
+	if (dev->wdt.info->options & WDIOF_PRETIMEOUT)
+		writel(dev->clk_rate * (wdt_dev->timeout - wdt_dev->pretimeout),
+		       dev->reg + TIMER1_VAL_OFF);
 
 	/* Clear the watchdog expiration bit */
 	atomic_io_modify(dev->reg + TIMER_A370_STATUS, WDT_A370_EXPIRED, 0);
 
 	/* Enable watchdog timer */
-	atomic_io_modify(dev->reg + TIMER_CTRL, dev->data->wdt_enable_bit,
-						dev->data->wdt_enable_bit);
+	reg = dev->data->wdt_enable_bit;
+	if (dev->wdt.info->options & WDIOF_PRETIMEOUT)
+		reg |= TIMER1_ENABLE_BIT;
+	atomic_io_modify(dev->reg + TIMER_CTRL, reg, reg);
 
 	/* Enable reset on watchdog */
 	reg = readl(dev->rstout);
@@ -277,7 +291,7 @@ static int orion_stop(struct watchdog_device *wdt_dev)
 static int armada375_stop(struct watchdog_device *wdt_dev)
 {
 	struct orion_watchdog *dev = watchdog_get_drvdata(wdt_dev);
-	u32 reg;
+	u32 reg, mask;
 
 	/* Disable reset on watchdog */
 	atomic_io_modify(dev->rstout_mask, dev->data->rstout_mask_bit,
@@ -287,7 +301,10 @@ static int armada375_stop(struct watchdog_device *wdt_dev)
 	writel(reg, dev->rstout);
 
 	/* Disable watchdog timer */
-	atomic_io_modify(dev->reg + TIMER_CTRL, dev->data->wdt_enable_bit, 0);
+	mask = dev->data->wdt_enable_bit;
+	if (wdt_dev->info->options & WDIOF_PRETIMEOUT)
+		mask |= TIMER1_ENABLE_BIT;
+	atomic_io_modify(dev->reg + TIMER_CTRL, mask, 0);
 
 	return 0;
 }
@@ -349,7 +366,7 @@ static unsigned int orion_wdt_get_timeleft(struct watchdog_device *wdt_dev)
 	return readl(dev->reg + dev->data->wdt_counter_offset) / dev->clk_rate;
 }
 
-static const struct watchdog_info orion_wdt_info = {
+static struct watchdog_info orion_wdt_info = {
 	.options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE,
 	.identity = "Orion Watchdog",
 };
@@ -368,6 +385,16 @@ static irqreturn_t orion_wdt_irq(int irq, void *devid)
 	return IRQ_HANDLED;
 }
 
+static irqreturn_t orion_wdt_pre_irq(int irq, void *devid)
+{
+	struct orion_watchdog *dev = devid;
+
+	atomic_io_modify(dev->reg + TIMER_A370_STATUS,
+			 TIMER1_STATUS_BIT, 0);
+	watchdog_notify_pretimeout(&dev->wdt);
+	return IRQ_HANDLED;
+}
+
 /*
  * The original devicetree binding for this driver specified only
  * one memory resource, so in order to keep DT backwards compatibility
@@ -575,7 +602,7 @@ static int orion_wdt_probe(struct platform_device *pdev)
 		set_bit(WDOG_HW_RUNNING, &dev->wdt.status);
 
 	/* Request the IRQ only after the watchdog is disabled */
-	irq = platform_get_irq(pdev, 0);
+	irq = platform_get_irq_optional(pdev, 0);
 	if (irq > 0) {
 		/*
 		 * Not all supported platforms specify an interrupt for the
@@ -589,6 +616,19 @@ static int orion_wdt_probe(struct platform_device *pdev)
 		}
 	}
 
+	/* Optional 2nd interrupt for pretimeout */
+	irq = platform_get_irq_optional(pdev, 1);
+	if (irq > 0) {
+		orion_wdt_info.options |= WDIOF_PRETIMEOUT;
+		ret = devm_request_irq(&pdev->dev, irq, orion_wdt_pre_irq,
+				       0, pdev->name, dev);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "failed to request IRQ\n");
+			goto disable_clk;
+		}
+	}
+
+
 	watchdog_set_nowayout(&dev->wdt, nowayout);
 	ret = watchdog_register_device(&dev->wdt);
 	if (ret)
diff --git a/drivers/watchdog/rn5t618_wdt.c b/drivers/watchdog/rn5t618_wdt.c
index 234876047431..6e524c8e26a8 100644
--- a/drivers/watchdog/rn5t618_wdt.c
+++ b/drivers/watchdog/rn5t618_wdt.c
@@ -188,6 +188,7 @@ static struct platform_driver rn5t618_wdt_driver = {
 
 module_platform_driver(rn5t618_wdt_driver);
 
+MODULE_ALIAS("platform:rn5t618-wdt");
 MODULE_AUTHOR("Beniamino Galvani <b.galvani@gmail.com>");
 MODULE_DESCRIPTION("RN5T618 watchdog driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/watchdog/sp805_wdt.c b/drivers/watchdog/sp805_wdt.c
index 072986d461b7..d8876fba686d 100644
--- a/drivers/watchdog/sp805_wdt.c
+++ b/drivers/watchdog/sp805_wdt.c
@@ -137,10 +137,14 @@ wdt_restart(struct watchdog_device *wdd, unsigned long mode, void *cmd)
 {
 	struct sp805_wdt *wdt = watchdog_get_drvdata(wdd);
 
+	writel_relaxed(UNLOCK, wdt->base + WDTLOCK);
 	writel_relaxed(0, wdt->base + WDTCONTROL);
 	writel_relaxed(0, wdt->base + WDTLOAD);
 	writel_relaxed(INT_ENABLE | RESET_ENABLE, wdt->base + WDTCONTROL);
 
+	/* Flush posted writes. */
+	readl_relaxed(wdt->base + WDTLOCK);
+
 	return 0;
 }
 
diff --git a/drivers/watchdog/sprd_wdt.c b/drivers/watchdog/sprd_wdt.c
index 916fb3f96bdc..fb9214c54afe 100644
--- a/drivers/watchdog/sprd_wdt.c
+++ b/drivers/watchdog/sprd_wdt.c
@@ -330,10 +330,9 @@ static int sprd_wdt_probe(struct platform_device *pdev)
 
 static int __maybe_unused sprd_wdt_pm_suspend(struct device *dev)
 {
-	struct watchdog_device *wdd = dev_get_drvdata(dev);
 	struct sprd_wdt *wdt = dev_get_drvdata(dev);
 
-	if (watchdog_active(wdd))
+	if (watchdog_active(&wdt->wdd))
 		sprd_wdt_stop(&wdt->wdd);
 	sprd_wdt_disable(wdt);
 
@@ -342,7 +341,6 @@ static int __maybe_unused sprd_wdt_pm_suspend(struct device *dev)
 
 static int __maybe_unused sprd_wdt_pm_resume(struct device *dev)
 {
-	struct watchdog_device *wdd = dev_get_drvdata(dev);
 	struct sprd_wdt *wdt = dev_get_drvdata(dev);
 	int ret;
 
@@ -350,7 +348,7 @@ static int __maybe_unused sprd_wdt_pm_resume(struct device *dev)
 	if (ret)
 		return ret;
 
-	if (watchdog_active(wdd)) {
+	if (watchdog_active(&wdt->wdd)) {
 		ret = sprd_wdt_start(&wdt->wdd);
 		if (ret) {
 			sprd_wdt_disable(wdt);
diff --git a/drivers/watchdog/stm32_iwdg.c b/drivers/watchdog/stm32_iwdg.c
index d569a3634d9b..8caf732b9133 100644
--- a/drivers/watchdog/stm32_iwdg.c
+++ b/drivers/watchdog/stm32_iwdg.c
@@ -262,6 +262,24 @@ static int stm32_iwdg_probe(struct platform_device *pdev)
 	watchdog_set_nowayout(wdd, WATCHDOG_NOWAYOUT);
 	watchdog_init_timeout(wdd, 0, dev);
 
+	/*
+	 * In case of CONFIG_WATCHDOG_HANDLE_BOOT_ENABLED is set
+	 * (Means U-Boot/bootloaders leaves the watchdog running)
+	 * When we get here we should make a decision to prevent
+	 * any side effects before user space daemon will take care of it.
+	 * The best option, taking into consideration that there is no
+	 * way to read values back from hardware, is to enforce watchdog
+	 * being run with deterministic values.
+	 */
+	if (IS_ENABLED(CONFIG_WATCHDOG_HANDLE_BOOT_ENABLED)) {
+		ret = stm32_iwdg_start(wdd);
+		if (ret)
+			return ret;
+
+		/* Make sure the watchdog is serviced */
+		set_bit(WDOG_HW_RUNNING, &wdd->status);
+	}
+
 	ret = devm_watchdog_register_device(dev, wdd);
 	if (ret) {
 		dev_err(dev, "failed to register watchdog device\n");
diff --git a/drivers/watchdog/watchdog_core.c b/drivers/watchdog/watchdog_core.c
index 62be9e52a4de..9bfeae3cc90e 100644
--- a/drivers/watchdog/watchdog_core.c
+++ b/drivers/watchdog/watchdog_core.c
@@ -152,6 +152,25 @@ int watchdog_init_timeout(struct watchdog_device *wdd,
 }
 EXPORT_SYMBOL_GPL(watchdog_init_timeout);
 
+static int watchdog_reboot_notifier(struct notifier_block *nb,
+				    unsigned long code, void *data)
+{
+	struct watchdog_device *wdd;
+
+	wdd = container_of(nb, struct watchdog_device, reboot_nb);
+	if (code == SYS_DOWN || code == SYS_HALT) {
+		if (watchdog_active(wdd)) {
+			int ret;
+
+			ret = wdd->ops->stop(wdd);
+			if (ret)
+				return NOTIFY_BAD;
+		}
+	}
+
+	return NOTIFY_DONE;
+}
+
 static int watchdog_restart_notifier(struct notifier_block *nb,
 				     unsigned long action, void *data)
 {
@@ -240,6 +259,19 @@ static int __watchdog_register_device(struct watchdog_device *wdd)
 		}
 	}
 
+	if (test_bit(WDOG_STOP_ON_REBOOT, &wdd->status)) {
+		wdd->reboot_nb.notifier_call = watchdog_reboot_notifier;
+
+		ret = register_reboot_notifier(&wdd->reboot_nb);
+		if (ret) {
+			pr_err("watchdog%d: Cannot register reboot notifier (%d)\n",
+			       wdd->id, ret);
+			watchdog_dev_unregister(wdd);
+			ida_simple_remove(&watchdog_ida, id);
+			return ret;
+		}
+	}
+
 	if (wdd->ops->restart) {
 		wdd->restart_nb.notifier_call = watchdog_restart_notifier;
 
@@ -285,6 +317,9 @@ static void __watchdog_unregister_device(struct watchdog_device *wdd)
 	if (wdd->ops->restart)
 		unregister_restart_handler(&wdd->restart_nb);
 
+	if (test_bit(WDOG_STOP_ON_REBOOT, &wdd->status))
+		unregister_reboot_notifier(&wdd->reboot_nb);
+
 	watchdog_dev_unregister(wdd);
 	ida_simple_remove(&watchdog_ida, wdd->id);
 }
diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c
index ac76f36e447a..00bba772afbc 100644
--- a/drivers/watchdog/watchdog_dev.c
+++ b/drivers/watchdog/watchdog_dev.c
@@ -42,7 +42,6 @@
 #include <linux/miscdevice.h>	/* For handling misc devices */
 #include <linux/module.h>	/* For module stuff/... */
 #include <linux/mutex.h>	/* For mutexes */
-#include <linux/reboot.h>	/* For reboot notifier */
 #include <linux/slab.h>		/* For memory functions */
 #include <linux/types.h>	/* For standard types (like size_t) */
 #include <linux/watchdog.h>	/* For watchdog specific items */
@@ -265,6 +264,7 @@ static int watchdog_start(struct watchdog_device *wdd)
 	if (err == 0) {
 		set_bit(WDOG_ACTIVE, &wdd->status);
 		wd_data->last_keepalive = started_at;
+		wd_data->last_hw_keepalive = started_at;
 		watchdog_update_worker(wdd);
 	}
 
@@ -947,6 +947,15 @@ static int watchdog_cdev_register(struct watchdog_device *wdd)
 	if (IS_ERR_OR_NULL(watchdog_kworker))
 		return -ENODEV;
 
+	device_initialize(&wd_data->dev);
+	wd_data->dev.devt = MKDEV(MAJOR(watchdog_devt), wdd->id);
+	wd_data->dev.class = &watchdog_class;
+	wd_data->dev.parent = wdd->parent;
+	wd_data->dev.groups = wdd->groups;
+	wd_data->dev.release = watchdog_core_data_release;
+	dev_set_drvdata(&wd_data->dev, wdd);
+	dev_set_name(&wd_data->dev, "watchdog%d", wdd->id);
+
 	kthread_init_work(&wd_data->work, watchdog_ping_work);
 	hrtimer_init(&wd_data->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	wd_data->timer.function = watchdog_timer_expired;
@@ -967,15 +976,6 @@ static int watchdog_cdev_register(struct watchdog_device *wdd)
 		}
 	}
 
-	device_initialize(&wd_data->dev);
-	wd_data->dev.devt = MKDEV(MAJOR(watchdog_devt), wdd->id);
-	wd_data->dev.class = &watchdog_class;
-	wd_data->dev.parent = wdd->parent;
-	wd_data->dev.groups = wdd->groups;
-	wd_data->dev.release = watchdog_core_data_release;
-	dev_set_drvdata(&wd_data->dev, wdd);
-	dev_set_name(&wd_data->dev, "watchdog%d", wdd->id);
-
 	/* Fill in the data structures */
 	cdev_init(&wd_data->cdev, &watchdog_fops);
 
@@ -1048,25 +1048,6 @@ static void watchdog_cdev_unregister(struct watchdog_device *wdd)
 	put_device(&wd_data->dev);
 }
 
-static int watchdog_reboot_notifier(struct notifier_block *nb,
-				    unsigned long code, void *data)
-{
-	struct watchdog_device *wdd;
-
-	wdd = container_of(nb, struct watchdog_device, reboot_nb);
-	if (code == SYS_DOWN || code == SYS_HALT) {
-		if (watchdog_active(wdd)) {
-			int ret;
-
-			ret = wdd->ops->stop(wdd);
-			if (ret)
-				return NOTIFY_BAD;
-		}
-	}
-
-	return NOTIFY_DONE;
-}
-
 /*
  *	watchdog_dev_register: register a watchdog device
  *	@wdd: watchdog device
@@ -1085,22 +1066,8 @@ int watchdog_dev_register(struct watchdog_device *wdd)
 		return ret;
 
 	ret = watchdog_register_pretimeout(wdd);
-	if (ret) {
+	if (ret)
 		watchdog_cdev_unregister(wdd);
-		return ret;
-	}
-
-	if (test_bit(WDOG_STOP_ON_REBOOT, &wdd->status)) {
-		wdd->reboot_nb.notifier_call = watchdog_reboot_notifier;
-
-		ret = devm_register_reboot_notifier(&wdd->wd_data->dev,
-						    &wdd->reboot_nb);
-		if (ret) {
-			pr_err("watchdog%d: Cannot register reboot notifier (%d)\n",
-			       wdd->id, ret);
-			watchdog_dev_unregister(wdd);
-		}
-	}
 
 	return ret;
 }
diff --git a/drivers/watchdog/wdat_wdt.c b/drivers/watchdog/wdat_wdt.c
index e7cf41aa26c3..88c5e6361aa0 100644
--- a/drivers/watchdog/wdat_wdt.c
+++ b/drivers/watchdog/wdat_wdt.c
@@ -54,6 +54,13 @@ module_param(nowayout, bool, 0);
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
 		 __MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
+#define WDAT_DEFAULT_TIMEOUT	30
+
+static int timeout = WDAT_DEFAULT_TIMEOUT;
+module_param(timeout, int, 0);
+MODULE_PARM_DESC(timeout, "Watchdog timeout in seconds (default="
+		 __MODULE_STRING(WDAT_DEFAULT_TIMEOUT) ")");
+
 static int wdat_wdt_read(struct wdat_wdt *wdat,
 	 const struct wdat_instruction *instr, u32 *value)
 {
@@ -389,7 +396,7 @@ static int wdat_wdt_probe(struct platform_device *pdev)
 
 		memset(&r, 0, sizeof(r));
 		r.start = gas->address;
-		r.end = r.start + gas->access_width - 1;
+		r.end = r.start + ACPI_ACCESS_BYTE_WIDTH(gas->access_width) - 1;
 		if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) {
 			r.flags = IORESOURCE_MEM;
 		} else if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_IO) {
@@ -438,6 +445,22 @@ static int wdat_wdt_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, wdat);
 
+	/*
+	 * Set initial timeout so that userspace has time to configure the
+	 * watchdog properly after it has opened the device. In some cases
+	 * the BIOS default is too short and causes immediate reboot.
+	 */
+	if (timeout * 1000 < wdat->wdd.min_hw_heartbeat_ms ||
+	    timeout * 1000 > wdat->wdd.max_hw_heartbeat_ms) {
+		dev_warn(dev, "Invalid timeout %d given, using %d\n",
+			 timeout, WDAT_DEFAULT_TIMEOUT);
+		timeout = WDAT_DEFAULT_TIMEOUT;
+	}
+
+	ret = wdat_wdt_set_timeout(&wdat->wdd, timeout);
+	if (ret)
+		return ret;
+
 	watchdog_set_nowayout(&wdat->wdd, nowayout);
 	return devm_watchdog_register_device(dev, &wdat->wdd);
 }
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 8300982b1da1..dcc255226e21 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -401,7 +401,8 @@ static struct notifier_block xen_memory_nb = {
 #else
 static enum bp_state reserve_additional_memory(void)
 {
-	balloon_stats.target_pages = balloon_stats.current_pages;
+	balloon_stats.target_pages = balloon_stats.current_pages +
+				     balloon_stats.target_unpopulated;
 	return BP_ECANCELED;
 }
 #endif /* CONFIG_XEN_BALLOON_MEMORY_HOTPLUG */
@@ -577,11 +578,13 @@ static int add_ballooned_pages(int nr_pages)
 	if (xen_hotplug_unpopulated) {
 		st = reserve_additional_memory();
 		if (st != BP_ECANCELED) {
+			int rc;
+
 			mutex_unlock(&balloon_mutex);
-			wait_event(balloon_wq,
+			rc = wait_event_interruptible(balloon_wq,
 				   !list_empty(&ballooned_pages));
 			mutex_lock(&balloon_mutex);
-			return 0;
+			return rc ? -ENOMEM : 0;
 		}
 	}
 
@@ -640,6 +643,12 @@ int alloc_xenballooned_pages(int nr_pages, struct page **pages)
  out_undo:
 	mutex_unlock(&balloon_mutex);
 	free_xenballooned_pages(pgno, pages);
+	/*
+	 * NB: free_xenballooned_pages will only subtract pgno pages, but since
+	 * target_unpopulated is incremented with nr_pages at the start we need
+	 * to remove the remaining ones also, or accounting will be screwed.
+	 */
+	balloon_stats.target_unpopulated -= nr_pages - pgno;
 	return ret;
 }
 EXPORT_SYMBOL(alloc_xenballooned_pages);
diff --git a/drivers/xen/gntdev-dmabuf.c b/drivers/xen/gntdev-dmabuf.c
index 2c4f324f8626..da799929087d 100644
--- a/drivers/xen/gntdev-dmabuf.c
+++ b/drivers/xen/gntdev-dmabuf.c
@@ -641,6 +641,14 @@ dmabuf_imp_to_refs(struct gntdev_dmabuf_priv *priv, struct device *dev,
 		goto fail_detach;
 	}
 
+	/* Check that we have zero offset. */
+	if (sgt->sgl->offset) {
+		ret = ERR_PTR(-EINVAL);
+		pr_debug("DMA buffer has %d bytes offset, user-space expects 0\n",
+			 sgt->sgl->offset);
+		goto fail_unmap;
+	}
+
 	/* Check number of pages that imported buffer has. */
 	if (attach->dmabuf->size != gntdev_dmabuf->nr_pages << PAGE_SHIFT) {
 		ret = ERR_PTR(-EINVAL);
diff --git a/drivers/xen/preempt.c b/drivers/xen/preempt.c
index 8b9919c26095..456a164364a2 100644
--- a/drivers/xen/preempt.c
+++ b/drivers/xen/preempt.c
@@ -33,7 +33,9 @@ asmlinkage __visible void xen_maybe_preempt_hcall(void)
 		 * cpu.
 		 */
 		__this_cpu_write(xen_in_preemptible_hcall, false);
-		_cond_resched();
+		local_irq_enable();
+		cond_resched();
+		local_irq_disable();
 		__this_cpu_write(xen_in_preemptible_hcall, true);
 	}
 }
diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c
index 69a626b0e594..f39ddeceff43 100644
--- a/drivers/xen/pvcalls-back.c
+++ b/drivers/xen/pvcalls-back.c
@@ -1087,7 +1087,8 @@ static void set_backend_state(struct xenbus_device *dev,
 		case XenbusStateInitialised:
 			switch (state) {
 			case XenbusStateConnected:
-				backend_connect(dev);
+				if (backend_connect(dev))
+					return;
 				xenbus_switch_state(dev, XenbusStateConnected);
 				break;
 			case XenbusStateClosing:
diff --git a/drivers/xen/xen-balloon.c b/drivers/xen/xen-balloon.c
index a67236b02452..a5494eb9fe73 100644
--- a/drivers/xen/xen-balloon.c
+++ b/drivers/xen/xen-balloon.c
@@ -94,7 +94,7 @@ static void watch_target(struct xenbus_watch *watch,
 				  "%llu", &static_max) == 1))
 			static_max >>= PAGE_SHIFT - 10;
 		else
-			static_max = new_target;
+			static_max = balloon_stats.current_pages;
 
 		target_diff = (xen_pv_domain() || xen_initial_domain()) ? 0
 				: static_max - balloon_stats.target_pages;
diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
index e17ca8156171..a38292ef79f6 100644
--- a/drivers/xen/xenbus/xenbus_client.c
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -448,7 +448,14 @@ EXPORT_SYMBOL_GPL(xenbus_free_evtchn);
 int xenbus_map_ring_valloc(struct xenbus_device *dev, grant_ref_t *gnt_refs,
 			   unsigned int nr_grefs, void **vaddr)
 {
-	return ring_ops->map(dev, gnt_refs, nr_grefs, vaddr);
+	int err;
+
+	err = ring_ops->map(dev, gnt_refs, nr_grefs, vaddr);
+	/* Some hypervisors are buggy and can return 1. */
+	if (err > 0)
+		err = GNTST_general_error;
+
+	return err;
 }
 EXPORT_SYMBOL_GPL(xenbus_map_ring_valloc);
 
diff --git a/drivers/xen/xenbus/xenbus_comms.c b/drivers/xen/xenbus/xenbus_comms.c
index d239fc3c5e3d..eb5151fc8efa 100644
--- a/drivers/xen/xenbus/xenbus_comms.c
+++ b/drivers/xen/xenbus/xenbus_comms.c
@@ -313,6 +313,8 @@ static int process_msg(void)
 			req->msg.type = state.msg.type;
 			req->msg.len = state.msg.len;
 			req->body = state.body;
+			/* write body, then update state */
+			virt_wmb();
 			req->state = xb_req_state_got_reply;
 			req->cb(req);
 		} else
@@ -395,6 +397,8 @@ static int process_writes(void)
 	if (state.req->state == xb_req_state_aborted)
 		kfree(state.req);
 	else {
+		/* write err, then update state */
+		virt_wmb();
 		state.req->state = xb_req_state_got_reply;
 		wake_up(&state.req->wq);
 	}
diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c
index ddc18da61834..3a06eb699f33 100644
--- a/drivers/xen/xenbus/xenbus_xs.c
+++ b/drivers/xen/xenbus/xenbus_xs.c
@@ -191,8 +191,11 @@ static bool xenbus_ok(void)
 
 static bool test_reply(struct xb_req_data *req)
 {
-	if (req->state == xb_req_state_got_reply || !xenbus_ok())
+	if (req->state == xb_req_state_got_reply || !xenbus_ok()) {
+		/* read req->state before all other fields */
+		virt_rmb();
 		return true;
+	}
 
 	/* Make sure to reread req->state each time. */
 	barrier();
@@ -202,7 +205,7 @@ static bool test_reply(struct xb_req_data *req)
 
 static void *read_reply(struct xb_req_data *req)
 {
-	while (req->state != xb_req_state_got_reply) {
+	do {
 		wait_event(req->wq, test_reply(req));
 
 		if (!xenbus_ok())
@@ -216,7 +219,7 @@ static void *read_reply(struct xb_req_data *req)
 		if (req->err)
 			return ERR_PTR(req->err);
 
-	}
+	} while (req->state != xb_req_state_got_reply);
 
 	return req->body;
 }
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 15a99f9c7253..39def020a074 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -500,10 +500,9 @@ void v9fs_session_close(struct v9fs_session_info *v9ses)
 	}
 
 #ifdef CONFIG_9P_FSCACHE
-	if (v9ses->fscache) {
+	if (v9ses->fscache)
 		v9fs_cache_session_put_cookie(v9ses);
-		kfree(v9ses->cachetag);
-	}
+	kfree(v9ses->cachetag);
 #endif
 	kfree(v9ses->uname);
 	kfree(v9ses->aname);
diff --git a/fs/affs/super.c b/fs/affs/super.c
index e7d036efbaa1..7050d463cdb2 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -557,14 +557,9 @@ affs_remount(struct super_block *sb, int *flags, char *data)
 	int			 root_block;
 	unsigned long		 mount_flags;
 	int			 res = 0;
-	char			*new_opts;
 	char			 volume[32];
 	char			*prefix = NULL;
 
-	new_opts = kstrdup(data, GFP_KERNEL);
-	if (data && !new_opts)
-		return -ENOMEM;
-
 	pr_debug("%s(flags=0x%x,opts=\"%s\")\n", __func__, *flags, data);
 
 	sync_filesystem(sb);
@@ -575,7 +570,6 @@ affs_remount(struct super_block *sb, int *flags, char *data)
 			   &blocksize, &prefix, volume,
 			   &mount_flags)) {
 		kfree(prefix);
-		kfree(new_opts);
 		return -EINVAL;
 	}
 
diff --git a/fs/afs/cell.c b/fs/afs/cell.c
index fd5133e26a38..296b489861a9 100644
--- a/fs/afs/cell.c
+++ b/fs/afs/cell.c
@@ -134,8 +134,17 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net,
 		_leave(" = -ENAMETOOLONG");
 		return ERR_PTR(-ENAMETOOLONG);
 	}
-	if (namelen == 5 && memcmp(name, "@cell", 5) == 0)
+
+	/* Prohibit cell names that contain unprintable chars, '/' and '@' or
+	 * that begin with a dot.  This also precludes "@cell".
+	 */
+	if (name[0] == '.')
 		return ERR_PTR(-EINVAL);
+	for (i = 0; i < namelen; i++) {
+		char ch = name[i];
+		if (!isprint(ch) || ch == '/' || ch == '@')
+			return ERR_PTR(-EINVAL);
+	}
 
 	_enter("%*.*s,%s", namelen, namelen, name, addresses);
 
@@ -145,10 +154,17 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net,
 		return ERR_PTR(-ENOMEM);
 	}
 
+	cell->name = kmalloc(namelen + 1, GFP_KERNEL);
+	if (!cell->name) {
+		kfree(cell);
+		return ERR_PTR(-ENOMEM);
+	}
+
 	cell->net = net;
 	cell->name_len = namelen;
 	for (i = 0; i < namelen; i++)
 		cell->name[i] = tolower(name[i]);
+	cell->name[i] = 0;
 
 	atomic_set(&cell->usage, 2);
 	INIT_WORK(&cell->manager, afs_manage_cell);
@@ -194,6 +210,7 @@ parse_failed:
 	if (ret == -EINVAL)
 		printk(KERN_ERR "kAFS: bad VL server IP address\n");
 error:
+	kfree(cell->name);
 	kfree(cell);
 	_leave(" = %d", ret);
 	return ERR_PTR(ret);
@@ -474,6 +491,7 @@ static void afs_cell_destroy(struct rcu_head *rcu)
 
 	afs_put_vlserverlist(cell->net, rcu_access_pointer(cell->vl_servers));
 	key_put(cell->anonymous_key);
+	kfree(cell->name);
 	kfree(cell);
 
 	_leave(" [destroyed]");
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index 00033a481ba0..5778a9b9e9bf 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -169,7 +169,7 @@ static int afs_record_cm_probe(struct afs_call *call, struct afs_server *server)
 
 	spin_lock(&server->probe_lock);
 
-	if (!test_bit(AFS_SERVER_FL_HAVE_EPOCH, &server->flags)) {
+	if (!test_and_set_bit(AFS_SERVER_FL_HAVE_EPOCH, &server->flags)) {
 		server->cm_epoch = call->epoch;
 		server->probe.cm_epoch = call->epoch;
 		goto out;
@@ -244,6 +244,17 @@ static void afs_cm_destructor(struct afs_call *call)
 }
 
 /*
+ * Abort a service call from within an action function.
+ */
+static void afs_abort_service_call(struct afs_call *call, u32 abort_code, int error,
+				   const char *why)
+{
+	rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
+				abort_code, error, why);
+	afs_set_call_complete(call, error, 0);
+}
+
+/*
  * The server supplied a list of callbacks that it wanted to break.
  */
 static void SRXAFSCB_CallBack(struct work_struct *work)
@@ -507,8 +518,7 @@ static void SRXAFSCB_ProbeUuid(struct work_struct *work)
 	if (memcmp(r, &call->net->uuid, sizeof(call->net->uuid)) == 0)
 		afs_send_empty_reply(call);
 	else
-		rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
-					1, 1, "K-1");
+		afs_abort_service_call(call, 1, 1, "K-1");
 
 	afs_put_call(call);
 	_leave("");
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index e26c901877ea..429698d0a596 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -659,7 +659,8 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry,
 
 	cookie->ctx.actor = afs_lookup_filldir;
 	cookie->name = dentry->d_name;
-	cookie->nr_fids = 1; /* slot 0 is saved for the fid we actually want */
+	cookie->nr_fids = 2; /* slot 0 is saved for the fid we actually want
+			      * and slot 1 for the directory */
 
 	read_seqlock_excl(&dvnode->cb_lock);
 	dcbi = rcu_dereference_protected(dvnode->cb_interest,
@@ -710,7 +711,11 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry,
 	if (!cookie->inodes)
 		goto out_s;
 
-	for (i = 1; i < cookie->nr_fids; i++) {
+	cookie->fids[1] = dvnode->fid;
+	cookie->statuses[1].cb_break = afs_calc_vnode_cb_break(dvnode);
+	cookie->inodes[1] = igrab(&dvnode->vfs_inode);
+
+	for (i = 2; i < cookie->nr_fids; i++) {
 		scb = &cookie->statuses[i];
 
 		/* Find any inodes that already exist and get their
@@ -909,6 +914,7 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
 				 unsigned int flags)
 {
 	struct afs_vnode *dvnode = AFS_FS_I(dir);
+	struct afs_fid fid = {};
 	struct inode *inode;
 	struct dentry *d;
 	struct key *key;
@@ -952,21 +958,18 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
 	afs_stat_v(dvnode, n_lookup);
 	inode = afs_do_lookup(dir, dentry, key);
 	key_put(key);
-	if (inode == ERR_PTR(-ENOENT)) {
+	if (inode == ERR_PTR(-ENOENT))
 		inode = afs_try_auto_mntpt(dentry, dir);
-	} else {
-		dentry->d_fsdata =
-			(void *)(unsigned long)dvnode->status.data_version;
-	}
+
+	if (!IS_ERR_OR_NULL(inode))
+		fid = AFS_FS_I(inode)->fid;
+
 	d = d_splice_alias(inode, dentry);
 	if (!IS_ERR_OR_NULL(d)) {
 		d->d_fsdata = dentry->d_fsdata;
-		trace_afs_lookup(dvnode, &d->d_name,
-				 inode ? AFS_FS_I(inode) : NULL);
+		trace_afs_lookup(dvnode, &d->d_name, &fid);
 	} else {
-		trace_afs_lookup(dvnode, &dentry->d_name,
-				 IS_ERR_OR_NULL(inode) ? NULL
-				 : AFS_FS_I(inode));
+		trace_afs_lookup(dvnode, &dentry->d_name, &fid);
 	}
 	return d;
 }
@@ -983,7 +986,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
 	struct dentry *parent;
 	struct inode *inode;
 	struct key *key;
-	afs_dataversion_t dir_version;
+	afs_dataversion_t dir_version, invalid_before;
 	long de_version;
 	int ret;
 
@@ -1035,8 +1038,8 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
 	if (de_version == (long)dir_version)
 		goto out_valid_noupdate;
 
-	dir_version = dir->invalid_before;
-	if (de_version - (long)dir_version >= 0)
+	invalid_before = dir->invalid_before;
+	if (de_version - (long)invalid_before >= 0)
 		goto out_valid;
 
 	_debug("dir modified");
@@ -1226,6 +1229,7 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	struct afs_fs_cursor fc;
 	struct afs_vnode *dvnode = AFS_FS_I(dir);
 	struct key *key;
+	afs_dataversion_t data_version;
 	int ret;
 
 	mode |= S_IFDIR;
@@ -1246,7 +1250,7 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 	ret = -ERESTARTSYS;
 	if (afs_begin_vnode_operation(&fc, dvnode, key, true)) {
-		afs_dataversion_t data_version = dvnode->status.data_version + 1;
+		data_version = dvnode->status.data_version + 1;
 
 		while (afs_select_fileserver(&fc)) {
 			fc.cb_break = afs_calc_vnode_cb_break(dvnode);
@@ -1267,10 +1271,14 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 		goto error_key;
 	}
 
-	if (ret == 0 &&
-	    test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
-		afs_edit_dir_add(dvnode, &dentry->d_name, &iget_data.fid,
-				 afs_edit_dir_for_create);
+	if (ret == 0) {
+		down_write(&dvnode->validate_lock);
+		if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) &&
+		    dvnode->status.data_version == data_version)
+			afs_edit_dir_add(dvnode, &dentry->d_name, &iget_data.fid,
+					 afs_edit_dir_for_create);
+		up_write(&dvnode->validate_lock);
+	}
 
 	key_put(key);
 	kfree(scb);
@@ -1311,6 +1319,7 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry)
 	struct afs_fs_cursor fc;
 	struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode = NULL;
 	struct key *key;
+	afs_dataversion_t data_version;
 	int ret;
 
 	_enter("{%llx:%llu},{%pd}",
@@ -1342,7 +1351,7 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry)
 
 	ret = -ERESTARTSYS;
 	if (afs_begin_vnode_operation(&fc, dvnode, key, true)) {
-		afs_dataversion_t data_version = dvnode->status.data_version + 1;
+		data_version = dvnode->status.data_version + 1;
 
 		while (afs_select_fileserver(&fc)) {
 			fc.cb_break = afs_calc_vnode_cb_break(dvnode);
@@ -1355,9 +1364,12 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry)
 		ret = afs_end_vnode_operation(&fc);
 		if (ret == 0) {
 			afs_dir_remove_subdir(dentry);
-			if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
+			down_write(&dvnode->validate_lock);
+			if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) &&
+			    dvnode->status.data_version == data_version)
 				afs_edit_dir_remove(dvnode, &dentry->d_name,
 						    afs_edit_dir_for_rmdir);
+			up_write(&dvnode->validate_lock);
 		}
 	}
 
@@ -1497,10 +1509,15 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry)
 		ret = afs_end_vnode_operation(&fc);
 		if (ret == 0 && !(scb[1].have_status || scb[1].have_error))
 			ret = afs_dir_remove_link(dvnode, dentry, key);
-		if (ret == 0 &&
-		    test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
-			afs_edit_dir_remove(dvnode, &dentry->d_name,
-					    afs_edit_dir_for_unlink);
+
+		if (ret == 0) {
+			down_write(&dvnode->validate_lock);
+			if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) &&
+			    dvnode->status.data_version == data_version)
+				afs_edit_dir_remove(dvnode, &dentry->d_name,
+						    afs_edit_dir_for_unlink);
+			up_write(&dvnode->validate_lock);
+		}
 	}
 
 	if (need_rehash && ret < 0 && ret != -ENOENT)
@@ -1526,6 +1543,7 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	struct afs_status_cb *scb;
 	struct afs_vnode *dvnode = AFS_FS_I(dir);
 	struct key *key;
+	afs_dataversion_t data_version;
 	int ret;
 
 	mode |= S_IFREG;
@@ -1550,7 +1568,7 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 
 	ret = -ERESTARTSYS;
 	if (afs_begin_vnode_operation(&fc, dvnode, key, true)) {
-		afs_dataversion_t data_version = dvnode->status.data_version + 1;
+		data_version = dvnode->status.data_version + 1;
 
 		while (afs_select_fileserver(&fc)) {
 			fc.cb_break = afs_calc_vnode_cb_break(dvnode);
@@ -1571,9 +1589,12 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 		goto error_key;
 	}
 
-	if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
+	down_write(&dvnode->validate_lock);
+	if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) &&
+	    dvnode->status.data_version == data_version)
 		afs_edit_dir_add(dvnode, &dentry->d_name, &iget_data.fid,
 				 afs_edit_dir_for_create);
+	up_write(&dvnode->validate_lock);
 
 	kfree(scb);
 	key_put(key);
@@ -1601,6 +1622,7 @@ static int afs_link(struct dentry *from, struct inode *dir,
 	struct afs_vnode *dvnode = AFS_FS_I(dir);
 	struct afs_vnode *vnode = AFS_FS_I(d_inode(from));
 	struct key *key;
+	afs_dataversion_t data_version;
 	int ret;
 
 	_enter("{%llx:%llu},{%llx:%llu},{%pd}",
@@ -1625,7 +1647,7 @@ static int afs_link(struct dentry *from, struct inode *dir,
 
 	ret = -ERESTARTSYS;
 	if (afs_begin_vnode_operation(&fc, dvnode, key, true)) {
-		afs_dataversion_t data_version = dvnode->status.data_version + 1;
+		data_version = dvnode->status.data_version + 1;
 
 		if (mutex_lock_interruptible_nested(&vnode->io_lock, 1) < 0) {
 			afs_end_vnode_operation(&fc);
@@ -1655,9 +1677,12 @@ static int afs_link(struct dentry *from, struct inode *dir,
 		goto error_key;
 	}
 
-	if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
+	down_write(&dvnode->validate_lock);
+	if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) &&
+	    dvnode->status.data_version == data_version)
 		afs_edit_dir_add(dvnode, &dentry->d_name, &vnode->fid,
 				 afs_edit_dir_for_link);
+	up_write(&dvnode->validate_lock);
 
 	key_put(key);
 	kfree(scb);
@@ -1685,6 +1710,7 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry,
 	struct afs_status_cb *scb;
 	struct afs_vnode *dvnode = AFS_FS_I(dir);
 	struct key *key;
+	afs_dataversion_t data_version;
 	int ret;
 
 	_enter("{%llx:%llu},{%pd},%s",
@@ -1712,7 +1738,7 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry,
 
 	ret = -ERESTARTSYS;
 	if (afs_begin_vnode_operation(&fc, dvnode, key, true)) {
-		afs_dataversion_t data_version = dvnode->status.data_version + 1;
+		data_version = dvnode->status.data_version + 1;
 
 		while (afs_select_fileserver(&fc)) {
 			fc.cb_break = afs_calc_vnode_cb_break(dvnode);
@@ -1733,9 +1759,12 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry,
 		goto error_key;
 	}
 
-	if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
+	down_write(&dvnode->validate_lock);
+	if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) &&
+	    dvnode->status.data_version == data_version)
 		afs_edit_dir_add(dvnode, &dentry->d_name, &iget_data.fid,
 				 afs_edit_dir_for_symlink);
+	up_write(&dvnode->validate_lock);
 
 	key_put(key);
 	kfree(scb);
@@ -1765,6 +1794,8 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct dentry *tmp = NULL, *rehash = NULL;
 	struct inode *new_inode;
 	struct key *key;
+	afs_dataversion_t orig_data_version;
+	afs_dataversion_t new_data_version;
 	bool new_negative = d_is_negative(new_dentry);
 	int ret;
 
@@ -1843,10 +1874,6 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 	ret = -ERESTARTSYS;
 	if (afs_begin_vnode_operation(&fc, orig_dvnode, key, true)) {
-		afs_dataversion_t orig_data_version;
-		afs_dataversion_t new_data_version;
-		struct afs_status_cb *new_scb = &scb[1];
-
 		orig_data_version = orig_dvnode->status.data_version + 1;
 
 		if (orig_dvnode != new_dvnode) {
@@ -1857,7 +1884,6 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			new_data_version = new_dvnode->status.data_version + 1;
 		} else {
 			new_data_version = orig_data_version;
-			new_scb = &scb[0];
 		}
 
 		while (afs_select_fileserver(&fc)) {
@@ -1865,7 +1891,7 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			fc.cb_break_2 = afs_calc_vnode_cb_break(new_dvnode);
 			afs_fs_rename(&fc, old_dentry->d_name.name,
 				      new_dvnode, new_dentry->d_name.name,
-				      &scb[0], new_scb);
+				      &scb[0], &scb[1]);
 		}
 
 		afs_vnode_commit_status(&fc, orig_dvnode, fc.cb_break,
@@ -1883,18 +1909,25 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (ret == 0) {
 		if (rehash)
 			d_rehash(rehash);
-		if (test_bit(AFS_VNODE_DIR_VALID, &orig_dvnode->flags))
-		    afs_edit_dir_remove(orig_dvnode, &old_dentry->d_name,
-					afs_edit_dir_for_rename_0);
+		down_write(&orig_dvnode->validate_lock);
+		if (test_bit(AFS_VNODE_DIR_VALID, &orig_dvnode->flags) &&
+		    orig_dvnode->status.data_version == orig_data_version)
+			afs_edit_dir_remove(orig_dvnode, &old_dentry->d_name,
+					    afs_edit_dir_for_rename_0);
+		if (orig_dvnode != new_dvnode) {
+			up_write(&orig_dvnode->validate_lock);
 
-		if (!new_negative &&
-		    test_bit(AFS_VNODE_DIR_VALID, &new_dvnode->flags))
-			afs_edit_dir_remove(new_dvnode, &new_dentry->d_name,
-					    afs_edit_dir_for_rename_1);
+			down_write(&new_dvnode->validate_lock);
+		}
+		if (test_bit(AFS_VNODE_DIR_VALID, &new_dvnode->flags) &&
+		    orig_dvnode->status.data_version == new_data_version) {
+			if (!new_negative)
+				afs_edit_dir_remove(new_dvnode, &new_dentry->d_name,
+						    afs_edit_dir_for_rename_1);
 
-		if (test_bit(AFS_VNODE_DIR_VALID, &new_dvnode->flags))
 			afs_edit_dir_add(new_dvnode, &new_dentry->d_name,
 					 &vnode->fid, afs_edit_dir_for_rename_2);
+		}
 
 		new_inode = d_inode(new_dentry);
 		if (new_inode) {
@@ -1910,14 +1943,10 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		 * Note that if we ever implement RENAME_EXCHANGE, we'll have
 		 * to update both dentries with opposing dir versions.
 		 */
-		if (new_dvnode != orig_dvnode) {
-			afs_update_dentry_version(&fc, old_dentry, &scb[1]);
-			afs_update_dentry_version(&fc, new_dentry, &scb[1]);
-		} else {
-			afs_update_dentry_version(&fc, old_dentry, &scb[0]);
-			afs_update_dentry_version(&fc, new_dentry, &scb[0]);
-		}
+		afs_update_dentry_version(&fc, old_dentry, &scb[1]);
+		afs_update_dentry_version(&fc, new_dentry, &scb[1]);
 		d_move(old_dentry, new_dentry);
+		up_write(&new_dvnode->validate_lock);
 		goto error_tmp;
 	}
 
diff --git a/fs/afs/dir_edit.c b/fs/afs/dir_edit.c
index d4fbe5f85f1b..b108528bf010 100644
--- a/fs/afs/dir_edit.c
+++ b/fs/afs/dir_edit.c
@@ -68,13 +68,11 @@ static int afs_find_contig_bits(union afs_xdr_dir_block *block, unsigned int nr_
 static void afs_set_contig_bits(union afs_xdr_dir_block *block,
 				int bit, unsigned int nr_slots)
 {
-	u64 mask, before, after;
+	u64 mask;
 
 	mask = (1 << nr_slots) - 1;
 	mask <<= bit;
 
-	before = *(u64 *)block->hdr.bitmap;
-
 	block->hdr.bitmap[0] |= (u8)(mask >> 0 * 8);
 	block->hdr.bitmap[1] |= (u8)(mask >> 1 * 8);
 	block->hdr.bitmap[2] |= (u8)(mask >> 2 * 8);
@@ -83,8 +81,6 @@ static void afs_set_contig_bits(union afs_xdr_dir_block *block,
 	block->hdr.bitmap[5] |= (u8)(mask >> 5 * 8);
 	block->hdr.bitmap[6] |= (u8)(mask >> 6 * 8);
 	block->hdr.bitmap[7] |= (u8)(mask >> 7 * 8);
-
-	after = *(u64 *)block->hdr.bitmap;
 }
 
 /*
@@ -93,13 +89,11 @@ static void afs_set_contig_bits(union afs_xdr_dir_block *block,
 static void afs_clear_contig_bits(union afs_xdr_dir_block *block,
 				  int bit, unsigned int nr_slots)
 {
-	u64 mask, before, after;
+	u64 mask;
 
 	mask = (1 << nr_slots) - 1;
 	mask <<= bit;
 
-	before = *(u64 *)block->hdr.bitmap;
-
 	block->hdr.bitmap[0] &= ~(u8)(mask >> 0 * 8);
 	block->hdr.bitmap[1] &= ~(u8)(mask >> 1 * 8);
 	block->hdr.bitmap[2] &= ~(u8)(mask >> 2 * 8);
@@ -108,8 +102,6 @@ static void afs_clear_contig_bits(union afs_xdr_dir_block *block,
 	block->hdr.bitmap[5] &= ~(u8)(mask >> 5 * 8);
 	block->hdr.bitmap[6] &= ~(u8)(mask >> 6 * 8);
 	block->hdr.bitmap[7] &= ~(u8)(mask >> 7 * 8);
-
-	after = *(u64 *)block->hdr.bitmap;
 }
 
 /*
diff --git a/fs/afs/dir_silly.c b/fs/afs/dir_silly.c
index 057b8d322422..bb3fcbfd3afc 100644
--- a/fs/afs/dir_silly.c
+++ b/fs/afs/dir_silly.c
@@ -21,6 +21,7 @@ static int afs_do_silly_rename(struct afs_vnode *dvnode, struct afs_vnode *vnode
 {
 	struct afs_fs_cursor fc;
 	struct afs_status_cb *scb;
+	afs_dataversion_t dir_data_version;
 	int ret = -ERESTARTSYS;
 
 	_enter("%pd,%pd", old, new);
@@ -31,7 +32,7 @@ static int afs_do_silly_rename(struct afs_vnode *dvnode, struct afs_vnode *vnode
 
 	trace_afs_silly_rename(vnode, false);
 	if (afs_begin_vnode_operation(&fc, dvnode, key, true)) {
-		afs_dataversion_t dir_data_version = dvnode->status.data_version + 1;
+		dir_data_version = dvnode->status.data_version + 1;
 
 		while (afs_select_fileserver(&fc)) {
 			fc.cb_break = afs_calc_vnode_cb_break(dvnode);
@@ -54,13 +55,17 @@ static int afs_do_silly_rename(struct afs_vnode *dvnode, struct afs_vnode *vnode
 			dvnode->silly_key = key_get(key);
 		}
 
-		if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
+		down_write(&dvnode->validate_lock);
+		if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) &&
+		    dvnode->status.data_version == dir_data_version) {
 			afs_edit_dir_remove(dvnode, &old->d_name,
 					    afs_edit_dir_for_silly_0);
-		if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
 			afs_edit_dir_add(dvnode, &new->d_name,
 					 &vnode->fid, afs_edit_dir_for_silly_1);
 
+		}
+		up_write(&dvnode->validate_lock);
+
 		/* vfs_unlink and the like do not issue this when a file is
 		 * sillyrenamed, so do it here.
 		 */
@@ -186,10 +191,14 @@ static int afs_do_silly_unlink(struct afs_vnode *dvnode, struct afs_vnode *vnode
 				clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
 			}
 		}
-		if (ret == 0 &&
-		    test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
-			afs_edit_dir_remove(dvnode, &dentry->d_name,
-					    afs_edit_dir_for_unlink);
+		if (ret == 0) {
+			down_write(&dvnode->validate_lock);
+			if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) &&
+			    dvnode->status.data_version == dir_data_version)
+				afs_edit_dir_remove(dvnode, &dentry->d_name,
+						    afs_edit_dir_for_unlink);
+			up_write(&dvnode->validate_lock);
+		}
 	}
 
 	kfree(scb);
diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c
index 9b3b2f1f1fc0..13522d2b0ec9 100644
--- a/fs/afs/dynroot.c
+++ b/fs/afs/dynroot.c
@@ -141,6 +141,9 @@ static struct dentry *afs_dynroot_lookup(struct inode *dir, struct dentry *dentr
 
 	ASSERTCMP(d_inode(dentry), ==, NULL);
 
+	if (flags & LOOKUP_CREATE)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	if (dentry->d_name.len >= AFSNAMEMAX) {
 		_leave(" = -ENAMETOOLONG");
 		return ERR_PTR(-ENAMETOOLONG);
diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c
index cfe62b154f68..51ee3dd79700 100644
--- a/fs/afs/fs_probe.c
+++ b/fs/afs/fs_probe.c
@@ -32,9 +32,8 @@ void afs_fileserver_probe_result(struct afs_call *call)
 	struct afs_server *server = call->server;
 	unsigned int server_index = call->server_index;
 	unsigned int index = call->addr_ix;
-	unsigned int rtt = UINT_MAX;
+	unsigned int rtt_us;
 	bool have_result = false;
-	u64 _rtt;
 	int ret = call->error;
 
 	_enter("%pU,%u", &server->uuid, index);
@@ -93,15 +92,9 @@ responded:
 		}
 	}
 
-	/* Get the RTT and scale it to fit into a 32-bit value that represents
-	 * over a minute of time so that we can access it with one instruction
-	 * on a 32-bit system.
-	 */
-	_rtt = rxrpc_kernel_get_rtt(call->net->socket, call->rxcall);
-	_rtt /= 64;
-	rtt = (_rtt > UINT_MAX) ? UINT_MAX : _rtt;
-	if (rtt < server->probe.rtt) {
-		server->probe.rtt = rtt;
+	if (rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us) &&
+	    rtt_us < server->probe.rtt) {
+		server->probe.rtt = rtt_us;
 		alist->preferred = index;
 		have_result = true;
 	}
@@ -113,8 +106,7 @@ out:
 	spin_unlock(&server->probe_lock);
 
 	_debug("probe [%u][%u] %pISpc rtt=%u ret=%d",
-	       server_index, index, &alist->addrs[index].transport,
-	       (unsigned int)rtt, ret);
+	       server_index, index, &alist->addrs[index].transport, rtt_us, ret);
 
 	have_result |= afs_fs_probe_done(server);
 	if (have_result) {
@@ -145,6 +137,7 @@ static int afs_do_probe_fileserver(struct afs_net *net,
 	read_lock(&server->fs_lock);
 	ac.alist = rcu_dereference_protected(server->addresses,
 					     lockdep_is_held(&server->fs_lock));
+	afs_get_addrlist(ac.alist);
 	read_unlock(&server->fs_lock);
 
 	atomic_set(&server->probe_outstanding, ac.alist->nr_addrs);
@@ -163,6 +156,7 @@ static int afs_do_probe_fileserver(struct afs_net *net,
 
 	if (!in_progress)
 		afs_fs_probe_done(server);
+	afs_put_addrlist(ac.alist);
 	return in_progress;
 }
 
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index a1ef0266422a..1a6f22700811 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -58,9 +58,9 @@ static void xdr_dump_bad(const __be32 *bp)
 /*
  * decode an AFSFetchStatus block
  */
-static int xdr_decode_AFSFetchStatus(const __be32 **_bp,
-				     struct afs_call *call,
-				     struct afs_status_cb *scb)
+static void xdr_decode_AFSFetchStatus(const __be32 **_bp,
+				      struct afs_call *call,
+				      struct afs_status_cb *scb)
 {
 	const struct afs_xdr_AFSFetchStatus *xdr = (const void *)*_bp;
 	struct afs_file_status *status = &scb->status;
@@ -80,7 +80,7 @@ static int xdr_decode_AFSFetchStatus(const __be32 **_bp,
 			 */
 			status->abort_code = abort_code;
 			scb->have_error = true;
-			return 0;
+			goto advance;
 		}
 
 		pr_warn("Unknown AFSFetchStatus version %u\n", ntohl(xdr->if_version));
@@ -89,7 +89,8 @@ static int xdr_decode_AFSFetchStatus(const __be32 **_bp,
 
 	if (abort_code != 0 && inline_error) {
 		status->abort_code = abort_code;
-		return 0;
+		scb->have_error = true;
+		goto advance;
 	}
 
 	type = ntohl(xdr->type);
@@ -125,13 +126,14 @@ static int xdr_decode_AFSFetchStatus(const __be32 **_bp,
 	data_version |= (u64)ntohl(xdr->data_version_hi) << 32;
 	status->data_version = data_version;
 	scb->have_status = true;
-
+advance:
 	*_bp = (const void *)*_bp + sizeof(*xdr);
-	return 0;
+	return;
 
 bad:
 	xdr_dump_bad(*_bp);
-	return afs_protocol_error(call, -EBADMSG, afs_eproto_bad_status);
+	afs_protocol_error(call, -EBADMSG, afs_eproto_bad_status);
+	goto advance;
 }
 
 static time64_t xdr_decode_expiry(struct afs_call *call, u32 expiry)
@@ -251,9 +253,7 @@ static int afs_deliver_fs_fetch_status_vnode(struct afs_call *call)
 
 	/* unmarshall the reply once we've received all of it */
 	bp = call->buffer;
-	ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb);
-	if (ret < 0)
-		return ret;
+	xdr_decode_AFSFetchStatus(&bp, call, call->out_scb);
 	xdr_decode_AFSCallBack(&bp, call, call->out_scb);
 	xdr_decode_AFSVolSync(&bp, call->out_volsync);
 
@@ -380,8 +380,6 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 		ASSERTCMP(req->offset, <=, PAGE_SIZE);
 		if (req->offset == PAGE_SIZE) {
 			req->offset = 0;
-			if (req->page_done)
-				req->page_done(req);
 			req->index++;
 			if (req->remain > 0)
 				goto begin_page;
@@ -415,9 +413,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 			return ret;
 
 		bp = call->buffer;
-		ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb);
-		if (ret < 0)
-			return ret;
+		xdr_decode_AFSFetchStatus(&bp, call, call->out_scb);
 		xdr_decode_AFSCallBack(&bp, call, call->out_scb);
 		xdr_decode_AFSVolSync(&bp, call->out_volsync);
 
@@ -434,11 +430,13 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 		if (req->offset < PAGE_SIZE)
 			zero_user_segment(req->pages[req->index],
 					  req->offset, PAGE_SIZE);
-		if (req->page_done)
-			req->page_done(req);
 		req->offset = 0;
 	}
 
+	if (req->page_done)
+		for (req->index = 0; req->index < req->nr_pages; req->index++)
+			req->page_done(req);
+
 	_leave(" = 0 [done]");
 	return 0;
 }
@@ -573,12 +571,8 @@ static int afs_deliver_fs_create_vnode(struct afs_call *call)
 	/* unmarshall the reply once we've received all of it */
 	bp = call->buffer;
 	xdr_decode_AFSFid(&bp, call->out_fid);
-	ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb);
-	if (ret < 0)
-		return ret;
-	ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb);
-	if (ret < 0)
-		return ret;
+	xdr_decode_AFSFetchStatus(&bp, call, call->out_scb);
+	xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb);
 	xdr_decode_AFSCallBack(&bp, call, call->out_scb);
 	xdr_decode_AFSVolSync(&bp, call->out_volsync);
 
@@ -687,9 +681,7 @@ static int afs_deliver_fs_dir_status_and_vol(struct afs_call *call)
 
 	/* unmarshall the reply once we've received all of it */
 	bp = call->buffer;
-	ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb);
-	if (ret < 0)
-		return ret;
+	xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb);
 	xdr_decode_AFSVolSync(&bp, call->out_volsync);
 
 	_leave(" = 0 [done]");
@@ -780,12 +772,8 @@ static int afs_deliver_fs_link(struct afs_call *call)
 
 	/* unmarshall the reply once we've received all of it */
 	bp = call->buffer;
-	ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb);
-	if (ret < 0)
-		return ret;
-	ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb);
-	if (ret < 0)
-		return ret;
+	xdr_decode_AFSFetchStatus(&bp, call, call->out_scb);
+	xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb);
 	xdr_decode_AFSVolSync(&bp, call->out_volsync);
 
 	_leave(" = 0 [done]");
@@ -874,12 +862,8 @@ static int afs_deliver_fs_symlink(struct afs_call *call)
 	/* unmarshall the reply once we've received all of it */
 	bp = call->buffer;
 	xdr_decode_AFSFid(&bp, call->out_fid);
-	ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb);
-	if (ret < 0)
-		return ret;
-	ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb);
-	if (ret < 0)
-		return ret;
+	xdr_decode_AFSFetchStatus(&bp, call, call->out_scb);
+	xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb);
 	xdr_decode_AFSVolSync(&bp, call->out_volsync);
 
 	_leave(" = 0 [done]");
@@ -982,16 +966,12 @@ static int afs_deliver_fs_rename(struct afs_call *call)
 	if (ret < 0)
 		return ret;
 
-	/* unmarshall the reply once we've received all of it */
 	bp = call->buffer;
-	ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb);
-	if (ret < 0)
-		return ret;
-	if (call->out_dir_scb != call->out_scb) {
-		ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb);
-		if (ret < 0)
-			return ret;
-	}
+	/* If the two dirs are the same, we have two copies of the same status
+	 * report, so we just decode it twice.
+	 */
+	xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb);
+	xdr_decode_AFSFetchStatus(&bp, call, call->out_scb);
 	xdr_decode_AFSVolSync(&bp, call->out_volsync);
 
 	_leave(" = 0 [done]");
@@ -1099,9 +1079,7 @@ static int afs_deliver_fs_store_data(struct afs_call *call)
 
 	/* unmarshall the reply once we've received all of it */
 	bp = call->buffer;
-	ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb);
-	if (ret < 0)
-		return ret;
+	xdr_decode_AFSFetchStatus(&bp, call, call->out_scb);
 	xdr_decode_AFSVolSync(&bp, call->out_volsync);
 
 	_leave(" = 0 [done]");
@@ -1279,9 +1257,7 @@ static int afs_deliver_fs_store_status(struct afs_call *call)
 
 	/* unmarshall the reply once we've received all of it */
 	bp = call->buffer;
-	ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb);
-	if (ret < 0)
-		return ret;
+	xdr_decode_AFSFetchStatus(&bp, call, call->out_scb);
 	xdr_decode_AFSVolSync(&bp, call->out_volsync);
 
 	_leave(" = 0 [done]");
@@ -1941,9 +1917,7 @@ static int afs_deliver_fs_fetch_status(struct afs_call *call)
 
 	/* unmarshall the reply once we've received all of it */
 	bp = call->buffer;
-	ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb);
-	if (ret < 0)
-		return ret;
+	xdr_decode_AFSFetchStatus(&bp, call, call->out_scb);
 	xdr_decode_AFSCallBack(&bp, call, call->out_scb);
 	xdr_decode_AFSVolSync(&bp, call->out_volsync);
 
@@ -2049,10 +2023,7 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call)
 
 		bp = call->buffer;
 		scb = &call->out_scb[call->count];
-		ret = xdr_decode_AFSFetchStatus(&bp, call, scb);
-		if (ret < 0)
-			return ret;
-
+		xdr_decode_AFSFetchStatus(&bp, call, scb);
 		call->count++;
 		if (call->count < call->count2)
 			goto more_counts;
@@ -2227,9 +2198,7 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call)
 			return ret;
 
 		bp = call->buffer;
-		ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb);
-		if (ret < 0)
-			return ret;
+		xdr_decode_AFSFetchStatus(&bp, call, call->out_scb);
 		xdr_decode_AFSVolSync(&bp, call->out_volsync);
 
 		call->unmarshall++;
@@ -2310,9 +2279,7 @@ static int afs_deliver_fs_file_status_and_vol(struct afs_call *call)
 		return ret;
 
 	bp = call->buffer;
-	ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb);
-	if (ret < 0)
-		return ret;
+	xdr_decode_AFSFetchStatus(&bp, call, call->out_scb);
 	xdr_decode_AFSVolSync(&bp, call->out_volsync);
 
 	_leave(" = 0 [done]");
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 18a50d4febcf..ae7a69112c43 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -171,6 +171,7 @@ static void afs_apply_status(struct afs_fs_cursor *fc,
 	struct timespec64 t;
 	umode_t mode;
 	bool data_changed = false;
+	bool change_size = false;
 
 	BUG_ON(test_bit(AFS_VNODE_UNSET, &vnode->flags));
 
@@ -226,6 +227,7 @@ static void afs_apply_status(struct afs_fs_cursor *fc,
 		} else {
 			set_bit(AFS_VNODE_ZAP_DATA, &vnode->flags);
 		}
+		change_size = true;
 	} else if (vnode->status.type == AFS_FTYPE_DIR) {
 		/* Expected directory change is handled elsewhere so
 		 * that we can locally edit the directory and save on a
@@ -233,11 +235,19 @@ static void afs_apply_status(struct afs_fs_cursor *fc,
 		 */
 		if (test_bit(AFS_VNODE_DIR_VALID, &vnode->flags))
 			data_changed = false;
+		change_size = true;
 	}
 
 	if (data_changed) {
 		inode_set_iversion_raw(&vnode->vfs_inode, status->data_version);
-		afs_set_i_size(vnode, status->size);
+
+		/* Only update the size if the data version jumped.  If the
+		 * file is being modified locally, then we might have our own
+		 * idea of what the size should be that's not the same as
+		 * what's on the server.
+		 */
+		if (change_size)
+			afs_set_i_size(vnode, status->size);
 	}
 }
 
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 7ee63526c6a2..e16b413d133e 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -154,13 +154,14 @@ struct afs_call {
 	};
 	unsigned char		unmarshall;	/* unmarshalling phase */
 	unsigned char		addr_ix;	/* Address in ->alist */
-	bool			incoming;	/* T if incoming call */
+	bool			drop_ref;	/* T if need to drop ref for incoming call */
 	bool			send_pages;	/* T if data from mapping should be sent */
 	bool			need_attention;	/* T if RxRPC poked us */
 	bool			async;		/* T if asynchronous */
 	bool			upgrade;	/* T to request service upgrade */
 	bool			have_reply_time; /* T if have got reply_time */
 	bool			intr;		/* T if interruptible */
+	bool			unmarshalling_error; /* T if an unmarshalling error occurred */
 	u16			service_id;	/* Actual service ID (after upgrade) */
 	unsigned int		debug_id;	/* Trace ID */
 	u32			operation_ID;	/* operation ID for an incoming call */
@@ -396,7 +397,7 @@ struct afs_cell {
 	struct afs_vlserver_list __rcu *vl_servers;
 
 	u8			name_len;	/* Length of name */
-	char			name[64 + 1];	/* Cell name, case-flattened and NUL-padded */
+	char			*name;		/* Cell name, case-flattened and NUL-padded */
 };
 
 /*
@@ -1218,8 +1219,16 @@ static inline void afs_set_call_complete(struct afs_call *call,
 		ok = true;
 	}
 	spin_unlock_bh(&call->state_lock);
-	if (ok)
+	if (ok) {
 		trace_afs_call_done(call);
+
+		/* Asynchronous calls have two refs to release - one from the alloc and
+		 * one queued with the work item - and we can't just deallocate the
+		 * call because the work item may be queued again.
+		 */
+		if (call->drop_ref)
+			afs_put_call(call);
+	}
 }
 
 /*
@@ -1340,7 +1349,7 @@ extern struct afs_volume *afs_create_volume(struct afs_fs_context *);
 extern void afs_activate_volume(struct afs_volume *);
 extern void afs_deactivate_volume(struct afs_volume *);
 extern void afs_put_volume(struct afs_cell *, struct afs_volume *);
-extern int afs_check_volume_status(struct afs_volume *, struct key *);
+extern int afs_check_volume_status(struct afs_volume *, struct afs_fs_cursor *);
 
 /*
  * write.c
diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index f532d6d3bd28..79bc5f1338ed 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -126,7 +126,7 @@ static int afs_mntpt_set_params(struct fs_context *fc, struct dentry *mntpt)
 		if (src_as->cell)
 			ctx->cell = afs_get_cell(src_as->cell);
 
-		if (size > PAGE_SIZE - 1)
+		if (size < 2 || size > PAGE_SIZE - 1)
 			return -EINVAL;
 
 		page = read_mapping_page(d_inode(mntpt)->i_mapping, 0, NULL);
@@ -140,7 +140,9 @@ static int afs_mntpt_set_params(struct fs_context *fc, struct dentry *mntpt)
 		}
 
 		buf = kmap(page);
-		ret = vfs_parse_fs_string(fc, "source", buf, size);
+		ret = -EINVAL;
+		if (buf[size - 1] == '.')
+			ret = vfs_parse_fs_string(fc, "source", buf, size - 1);
 		kunmap(page);
 		put_page(page);
 		if (ret < 0)
diff --git a/fs/afs/proc.c b/fs/afs/proc.c
index fba2ec3a3a9c..106b27011f6d 100644
--- a/fs/afs/proc.c
+++ b/fs/afs/proc.c
@@ -562,6 +562,7 @@ void afs_put_sysnames(struct afs_sysnames *sysnames)
 			if (sysnames->subs[i] != afs_init_sysname &&
 			    sysnames->subs[i] != sysnames->blank)
 				kfree(sysnames->subs[i]);
+		kfree(sysnames);
 	}
 }
 
diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c
index 172ba569cd60..2a3305e42b14 100644
--- a/fs/afs/rotate.c
+++ b/fs/afs/rotate.c
@@ -192,7 +192,7 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
 			write_unlock(&vnode->volume->servers_lock);
 
 			set_bit(AFS_VOLUME_NEEDS_UPDATE, &vnode->volume->flags);
-			error = afs_check_volume_status(vnode->volume, fc->key);
+			error = afs_check_volume_status(vnode->volume, fc);
 			if (error < 0)
 				goto failed_set_error;
 
@@ -281,7 +281,7 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
 
 			set_bit(AFS_VOLUME_WAIT, &vnode->volume->flags);
 			set_bit(AFS_VOLUME_NEEDS_UPDATE, &vnode->volume->flags);
-			error = afs_check_volume_status(vnode->volume, fc->key);
+			error = afs_check_volume_status(vnode->volume, fc);
 			if (error < 0)
 				goto failed_set_error;
 
@@ -341,7 +341,7 @@ start:
 	/* See if we need to do an update of the volume record.  Note that the
 	 * volume may have moved or even have been deleted.
 	 */
-	error = afs_check_volume_status(vnode->volume, fc->key);
+	error = afs_check_volume_status(vnode->volume, fc);
 	if (error < 0)
 		goto failed_set_error;
 
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index d1dde2834b6d..b4a589a17c99 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -18,7 +18,6 @@ struct workqueue_struct *afs_async_calls;
 
 static void afs_wake_up_call_waiter(struct sock *, struct rxrpc_call *, unsigned long);
 static void afs_wake_up_async_call(struct sock *, struct rxrpc_call *, unsigned long);
-static void afs_delete_async_call(struct work_struct *);
 static void afs_process_async_call(struct work_struct *);
 static void afs_rx_new_call(struct sock *, struct rxrpc_call *, unsigned long);
 static void afs_rx_discard_new_call(struct rxrpc_call *, unsigned long);
@@ -169,7 +168,7 @@ void afs_put_call(struct afs_call *call)
 	int n = atomic_dec_return(&call->usage);
 	int o = atomic_read(&net->nr_outstanding_calls);
 
-	trace_afs_call(call, afs_call_trace_put, n + 1, o,
+	trace_afs_call(call, afs_call_trace_put, n, o,
 		       __builtin_return_address(0));
 
 	ASSERTCMP(n, >=, 0);
@@ -402,8 +401,10 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
 	/* If the call is going to be asynchronous, we need an extra ref for
 	 * the call to hold itself so the caller need not hang on to its ref.
 	 */
-	if (call->async)
+	if (call->async) {
 		afs_get_call(call, afs_call_trace_get);
+		call->drop_ref = true;
+	}
 
 	/* create a call */
 	rxcall = rxrpc_kernel_begin_call(call->net->socket, srx, call->key,
@@ -413,7 +414,8 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
 					  afs_wake_up_async_call :
 					  afs_wake_up_call_waiter),
 					 call->upgrade,
-					 call->intr,
+					 (call->intr ? RXRPC_PREINTERRUPTIBLE :
+					  RXRPC_UNINTERRUPTIBLE),
 					 call->debug_id);
 	if (IS_ERR(rxcall)) {
 		ret = PTR_ERR(rxcall);
@@ -538,6 +540,8 @@ static void afs_deliver_to_call(struct afs_call *call)
 
 		ret = call->type->deliver(call);
 		state = READ_ONCE(call->state);
+		if (ret == 0 && call->unmarshalling_error)
+			ret = -EBADMSG;
 		switch (ret) {
 		case 0:
 			afs_queue_call_work(call);
@@ -584,8 +588,6 @@ static void afs_deliver_to_call(struct afs_call *call)
 done:
 	if (call->type->done)
 		call->type->done(call);
-	if (state == AFS_CALL_COMPLETE && call->incoming)
-		afs_put_call(call);
 out:
 	_leave("");
 	return;
@@ -604,11 +606,7 @@ call_complete:
 long afs_wait_for_call_to_complete(struct afs_call *call,
 				   struct afs_addr_cursor *ac)
 {
-	signed long rtt2, timeout;
 	long ret;
-	bool stalled = false;
-	u64 rtt;
-	u32 life, last_life;
 	bool rxrpc_complete = false;
 
 	DECLARE_WAITQUEUE(myself, current);
@@ -619,14 +617,6 @@ long afs_wait_for_call_to_complete(struct afs_call *call,
 	if (ret < 0)
 		goto out;
 
-	rtt = rxrpc_kernel_get_rtt(call->net->socket, call->rxcall);
-	rtt2 = nsecs_to_jiffies64(rtt) * 2;
-	if (rtt2 < 2)
-		rtt2 = 2;
-
-	timeout = rtt2;
-	rxrpc_kernel_check_life(call->net->socket, call->rxcall, &last_life);
-
 	add_wait_queue(&call->waitq, &myself);
 	for (;;) {
 		set_current_state(TASK_UNINTERRUPTIBLE);
@@ -643,30 +633,13 @@ long afs_wait_for_call_to_complete(struct afs_call *call,
 		if (afs_check_call_state(call, AFS_CALL_COMPLETE))
 			break;
 
-		if (!rxrpc_kernel_check_life(call->net->socket, call->rxcall, &life)) {
+		if (!rxrpc_kernel_check_life(call->net->socket, call->rxcall)) {
 			/* rxrpc terminated the call. */
 			rxrpc_complete = true;
 			break;
 		}
 
-		if (call->intr && timeout == 0 &&
-		    life == last_life && signal_pending(current)) {
-			if (stalled)
-				break;
-			__set_current_state(TASK_RUNNING);
-			rxrpc_kernel_probe_life(call->net->socket, call->rxcall);
-			timeout = rtt2;
-			stalled = true;
-			continue;
-		}
-
-		if (life != last_life) {
-			timeout = rtt2;
-			last_life = life;
-			stalled = false;
-		}
-
-		timeout = schedule_timeout(timeout);
+		schedule();
 	}
 
 	remove_wait_queue(&call->waitq, &myself);
@@ -734,7 +707,7 @@ static void afs_wake_up_async_call(struct sock *sk, struct rxrpc_call *rxcall,
 
 	u = atomic_fetch_add_unless(&call->usage, 1, 0);
 	if (u != 0) {
-		trace_afs_call(call, afs_call_trace_wake, u,
+		trace_afs_call(call, afs_call_trace_wake, u + 1,
 			       atomic_read(&call->net->nr_outstanding_calls),
 			       __builtin_return_address(0));
 
@@ -744,21 +717,6 @@ static void afs_wake_up_async_call(struct sock *sk, struct rxrpc_call *rxcall,
 }
 
 /*
- * Delete an asynchronous call.  The work item carries a ref to the call struct
- * that we need to release.
- */
-static void afs_delete_async_call(struct work_struct *work)
-{
-	struct afs_call *call = container_of(work, struct afs_call, async_work);
-
-	_enter("");
-
-	afs_put_call(call);
-
-	_leave("");
-}
-
-/*
  * Perform I/O processing on an asynchronous call.  The work item carries a ref
  * to the call struct that we either need to release or to pass on.
  */
@@ -773,16 +731,6 @@ static void afs_process_async_call(struct work_struct *work)
 		afs_deliver_to_call(call);
 	}
 
-	if (call->state == AFS_CALL_COMPLETE) {
-		/* We have two refs to release - one from the alloc and one
-		 * queued with the work item - and we can't just deallocate the
-		 * call because the work item may be queued again.
-		 */
-		call->async_work.func = afs_delete_async_call;
-		if (!queue_work(afs_async_calls, &call->async_work))
-			afs_put_call(call);
-	}
-
 	afs_put_call(call);
 	_leave("");
 }
@@ -809,6 +757,7 @@ void afs_charge_preallocation(struct work_struct *work)
 			if (!call)
 				break;
 
+			call->drop_ref = true;
 			call->async = true;
 			call->state = AFS_CALL_SV_AWAIT_OP_ID;
 			init_waitqueue_head(&call->waitq);
@@ -1016,5 +965,7 @@ noinline int afs_protocol_error(struct afs_call *call, int error,
 				enum afs_eproto_cause cause)
 {
 	trace_afs_protocol_error(call, error, cause);
+	if (call)
+		call->unmarshalling_error = true;
 	return error;
 }
diff --git a/fs/afs/server.c b/fs/afs/server.c
index e900cd74361b..1caea74b8c11 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -31,18 +31,11 @@ static void afs_dec_servers_outstanding(struct afs_net *net)
 struct afs_server *afs_find_server(struct afs_net *net,
 				   const struct sockaddr_rxrpc *srx)
 {
-	const struct sockaddr_in6 *a = &srx->transport.sin6, *b;
 	const struct afs_addr_list *alist;
 	struct afs_server *server = NULL;
 	unsigned int i;
-	bool ipv6 = true;
 	int seq = 0, diff;
 
-	if (srx->transport.sin6.sin6_addr.s6_addr32[0] == 0 ||
-	    srx->transport.sin6.sin6_addr.s6_addr32[1] == 0 ||
-	    srx->transport.sin6.sin6_addr.s6_addr32[2] == htonl(0xffff))
-		ipv6 = false;
-
 	rcu_read_lock();
 
 	do {
@@ -51,7 +44,8 @@ struct afs_server *afs_find_server(struct afs_net *net,
 		server = NULL;
 		read_seqbegin_or_lock(&net->fs_addr_lock, &seq);
 
-		if (ipv6) {
+		if (srx->transport.family == AF_INET6) {
+			const struct sockaddr_in6 *a = &srx->transport.sin6, *b;
 			hlist_for_each_entry_rcu(server, &net->fs_addresses6, addr6_link) {
 				alist = rcu_dereference(server->addresses);
 				for (i = alist->nr_ipv4; i < alist->nr_addrs; i++) {
@@ -67,15 +61,16 @@ struct afs_server *afs_find_server(struct afs_net *net,
 				}
 			}
 		} else {
+			const struct sockaddr_in *a = &srx->transport.sin, *b;
 			hlist_for_each_entry_rcu(server, &net->fs_addresses4, addr4_link) {
 				alist = rcu_dereference(server->addresses);
 				for (i = 0; i < alist->nr_ipv4; i++) {
-					b = &alist->addrs[i].transport.sin6;
-					diff = ((u16 __force)a->sin6_port -
-						(u16 __force)b->sin6_port);
+					b = &alist->addrs[i].transport.sin;
+					diff = ((u16 __force)a->sin_port -
+						(u16 __force)b->sin_port);
 					if (diff == 0)
-						diff = ((u32 __force)a->sin6_addr.s6_addr32[3] -
-							(u32 __force)b->sin6_addr.s6_addr32[3]);
+						diff = ((u32 __force)a->sin_addr.s_addr -
+							(u32 __force)b->sin_addr.s_addr);
 					if (diff == 0)
 						goto found;
 				}
@@ -575,12 +570,9 @@ retry:
 	}
 
 	ret = wait_on_bit(&server->flags, AFS_SERVER_FL_UPDATING,
-			  TASK_INTERRUPTIBLE);
+			  (fc->flags & AFS_FS_CURSOR_INTR) ?
+			  TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE);
 	if (ret == -ERESTARTSYS) {
-		if (!(fc->flags & AFS_FS_CURSOR_INTR) && server->addresses) {
-			_leave(" = t [intr]");
-			return true;
-		}
 		fc->error = ret;
 		_leave(" = f [intr]");
 		return false;
diff --git a/fs/afs/super.c b/fs/afs/super.c
index f18911e8d770..ce61340b5de6 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -404,6 +404,7 @@ static int afs_test_super(struct super_block *sb, struct fs_context *fc)
 	return (as->net_ns == fc->net_ns &&
 		as->volume &&
 		as->volume->vid == ctx->volume->vid &&
+		as->cell == ctx->cell &&
 		!as->dyn_root);
 }
 
@@ -447,7 +448,6 @@ static int afs_fill_super(struct super_block *sb, struct afs_fs_context *ctx)
 	/* allocate the root inode and dentry */
 	if (as->dyn_root) {
 		inode = afs_iget_pseudo_dir(sb, true);
-		sb->s_flags	|= SB_RDONLY;
 	} else {
 		sprintf(sb->s_id, "%llu", as->volume->vid);
 		afs_activate_volume(as->volume);
diff --git a/fs/afs/vl_probe.c b/fs/afs/vl_probe.c
index 858498cc1b05..081b7e5b13f5 100644
--- a/fs/afs/vl_probe.c
+++ b/fs/afs/vl_probe.c
@@ -31,10 +31,9 @@ void afs_vlserver_probe_result(struct afs_call *call)
 	struct afs_addr_list *alist = call->alist;
 	struct afs_vlserver *server = call->vlserver;
 	unsigned int server_index = call->server_index;
+	unsigned int rtt_us = 0;
 	unsigned int index = call->addr_ix;
-	unsigned int rtt = UINT_MAX;
 	bool have_result = false;
-	u64 _rtt;
 	int ret = call->error;
 
 	_enter("%s,%u,%u,%d,%d", server->name, server_index, index, ret, call->abort_code);
@@ -93,15 +92,9 @@ responded:
 		}
 	}
 
-	/* Get the RTT and scale it to fit into a 32-bit value that represents
-	 * over a minute of time so that we can access it with one instruction
-	 * on a 32-bit system.
-	 */
-	_rtt = rxrpc_kernel_get_rtt(call->net->socket, call->rxcall);
-	_rtt /= 64;
-	rtt = (_rtt > UINT_MAX) ? UINT_MAX : _rtt;
-	if (rtt < server->probe.rtt) {
-		server->probe.rtt = rtt;
+	if (rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us) &&
+	    rtt_us < server->probe.rtt) {
+		server->probe.rtt = rtt_us;
 		alist->preferred = index;
 		have_result = true;
 	}
@@ -113,8 +106,7 @@ out:
 	spin_unlock(&server->probe_lock);
 
 	_debug("probe [%u][%u] %pISpc rtt=%u ret=%d",
-	       server_index, index, &alist->addrs[index].transport,
-	       (unsigned int)rtt, ret);
+	       server_index, index, &alist->addrs[index].transport, rtt_us, ret);
 
 	have_result |= afs_vl_probe_done(server);
 	if (have_result) {
diff --git a/fs/afs/volume.c b/fs/afs/volume.c
index 1a414300b654..9e03e593b548 100644
--- a/fs/afs/volume.c
+++ b/fs/afs/volume.c
@@ -283,7 +283,7 @@ error:
 /*
  * Make sure the volume record is up to date.
  */
-int afs_check_volume_status(struct afs_volume *volume, struct key *key)
+int afs_check_volume_status(struct afs_volume *volume, struct afs_fs_cursor *fc)
 {
 	time64_t now = ktime_get_real_seconds();
 	int ret, retries = 0;
@@ -301,7 +301,7 @@ retry:
 	}
 
 	if (!test_and_set_bit_lock(AFS_VOLUME_UPDATING, &volume->flags)) {
-		ret = afs_update_volume_status(volume, key);
+		ret = afs_update_volume_status(volume, fc->key);
 		clear_bit_unlock(AFS_VOLUME_WAIT, &volume->flags);
 		clear_bit_unlock(AFS_VOLUME_UPDATING, &volume->flags);
 		wake_up_bit(&volume->flags, AFS_VOLUME_WAIT);
@@ -314,7 +314,9 @@ retry:
 		return 0;
 	}
 
-	ret = wait_on_bit(&volume->flags, AFS_VOLUME_WAIT, TASK_INTERRUPTIBLE);
+	ret = wait_on_bit(&volume->flags, AFS_VOLUME_WAIT,
+			  (fc->flags & AFS_FS_CURSOR_INTR) ?
+			  TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE);
 	if (ret == -ERESTARTSYS) {
 		_leave(" = %d", ret);
 		return ret;
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 98eb7adbce91..34b50b2eeb97 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -195,11 +195,11 @@ int afs_write_end(struct file *file, struct address_space *mapping,
 
 	i_size = i_size_read(&vnode->vfs_inode);
 	if (maybe_i_size > i_size) {
-		spin_lock(&vnode->wb_lock);
+		write_seqlock(&vnode->cb_lock);
 		i_size = i_size_read(&vnode->vfs_inode);
 		if (maybe_i_size > i_size)
 			i_size_write(&vnode->vfs_inode, maybe_i_size);
-		spin_unlock(&vnode->wb_lock);
+		write_sequnlock(&vnode->cb_lock);
 	}
 
 	if (!PageUptodate(page)) {
@@ -812,6 +812,7 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf)
 			     vmf->page->index, priv);
 	SetPagePrivate(vmf->page);
 	set_page_private(vmf->page, priv);
+	file_update_time(file);
 
 	sb_end_pagefault(inode->i_sb);
 	return VM_FAULT_LOCKED;
diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c
index a1baf3f1f14d..1f94278f3bca 100644
--- a/fs/afs/yfsclient.c
+++ b/fs/afs/yfsclient.c
@@ -165,23 +165,23 @@ static void xdr_dump_bad(const __be32 *bp)
 	int i;
 
 	pr_notice("YFS XDR: Bad status record\n");
-	for (i = 0; i < 5 * 4 * 4; i += 16) {
+	for (i = 0; i < 6 * 4 * 4; i += 16) {
 		memcpy(x, bp, 16);
 		bp += 4;
 		pr_notice("%03x: %08x %08x %08x %08x\n",
 			  i, ntohl(x[0]), ntohl(x[1]), ntohl(x[2]), ntohl(x[3]));
 	}
 
-	memcpy(x, bp, 4);
-	pr_notice("0x50: %08x\n", ntohl(x[0]));
+	memcpy(x, bp, 8);
+	pr_notice("0x60: %08x %08x\n", ntohl(x[0]), ntohl(x[1]));
 }
 
 /*
  * Decode a YFSFetchStatus block
  */
-static int xdr_decode_YFSFetchStatus(const __be32 **_bp,
-				     struct afs_call *call,
-				     struct afs_status_cb *scb)
+static void xdr_decode_YFSFetchStatus(const __be32 **_bp,
+				      struct afs_call *call,
+				      struct afs_status_cb *scb)
 {
 	const struct yfs_xdr_YFSFetchStatus *xdr = (const void *)*_bp;
 	struct afs_file_status *status = &scb->status;
@@ -192,7 +192,7 @@ static int xdr_decode_YFSFetchStatus(const __be32 **_bp,
 		if (status->abort_code == VNOVNODE)
 			status->nlink = 0;
 		scb->have_error = true;
-		return 0;
+		goto advance;
 	}
 
 	type = ntohl(xdr->type);
@@ -220,13 +220,14 @@ static int xdr_decode_YFSFetchStatus(const __be32 **_bp,
 	status->size		= xdr_to_u64(xdr->size);
 	status->data_version	= xdr_to_u64(xdr->data_version);
 	scb->have_status	= true;
-
+advance:
 	*_bp += xdr_size(xdr);
-	return 0;
+	return;
 
 bad:
 	xdr_dump_bad(*_bp);
-	return afs_protocol_error(call, -EBADMSG, afs_eproto_bad_status);
+	afs_protocol_error(call, -EBADMSG, afs_eproto_bad_status);
+	goto advance;
 }
 
 /*
@@ -344,9 +345,7 @@ static int yfs_deliver_fs_status_cb_and_volsync(struct afs_call *call)
 
 	/* unmarshall the reply once we've received all of it */
 	bp = call->buffer;
-	ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb);
-	if (ret < 0)
-		return ret;
+	xdr_decode_YFSFetchStatus(&bp, call, call->out_scb);
 	xdr_decode_YFSCallBack(&bp, call, call->out_scb);
 	xdr_decode_YFSVolSync(&bp, call->out_volsync);
 
@@ -368,9 +367,7 @@ static int yfs_deliver_status_and_volsync(struct afs_call *call)
 		return ret;
 
 	bp = call->buffer;
-	ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb);
-	if (ret < 0)
-		return ret;
+	xdr_decode_YFSFetchStatus(&bp, call, call->out_scb);
 	xdr_decode_YFSVolSync(&bp, call->out_volsync);
 
 	_leave(" = 0 [done]");
@@ -491,8 +488,6 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call)
 		ASSERTCMP(req->offset, <=, PAGE_SIZE);
 		if (req->offset == PAGE_SIZE) {
 			req->offset = 0;
-			if (req->page_done)
-				req->page_done(req);
 			req->index++;
 			if (req->remain > 0)
 				goto begin_page;
@@ -529,9 +524,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call)
 			return ret;
 
 		bp = call->buffer;
-		ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb);
-		if (ret < 0)
-			return ret;
+		xdr_decode_YFSFetchStatus(&bp, call, call->out_scb);
 		xdr_decode_YFSCallBack(&bp, call, call->out_scb);
 		xdr_decode_YFSVolSync(&bp, call->out_volsync);
 
@@ -549,11 +542,13 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call)
 		if (req->offset < PAGE_SIZE)
 			zero_user_segment(req->pages[req->index],
 					  req->offset, PAGE_SIZE);
-		if (req->page_done)
-			req->page_done(req);
 		req->offset = 0;
 	}
 
+	if (req->page_done)
+		for (req->index = 0; req->index < req->nr_pages; req->index++)
+			req->page_done(req);
+
 	_leave(" = 0 [done]");
 	return 0;
 }
@@ -638,12 +633,8 @@ static int yfs_deliver_fs_create_vnode(struct afs_call *call)
 	/* unmarshall the reply once we've received all of it */
 	bp = call->buffer;
 	xdr_decode_YFSFid(&bp, call->out_fid);
-	ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb);
-	if (ret < 0)
-		return ret;
-	ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb);
-	if (ret < 0)
-		return ret;
+	xdr_decode_YFSFetchStatus(&bp, call, call->out_scb);
+	xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb);
 	xdr_decode_YFSCallBack(&bp, call, call->out_scb);
 	xdr_decode_YFSVolSync(&bp, call->out_volsync);
 
@@ -796,14 +787,9 @@ static int yfs_deliver_fs_remove_file2(struct afs_call *call)
 		return ret;
 
 	bp = call->buffer;
-	ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb);
-	if (ret < 0)
-		return ret;
-
+	xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb);
 	xdr_decode_YFSFid(&bp, &fid);
-	ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb);
-	if (ret < 0)
-		return ret;
+	xdr_decode_YFSFetchStatus(&bp, call, call->out_scb);
 	/* Was deleted if vnode->status.abort_code == VNOVNODE. */
 
 	xdr_decode_YFSVolSync(&bp, call->out_volsync);
@@ -883,10 +869,7 @@ static int yfs_deliver_fs_remove(struct afs_call *call)
 		return ret;
 
 	bp = call->buffer;
-	ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb);
-	if (ret < 0)
-		return ret;
-
+	xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb);
 	xdr_decode_YFSVolSync(&bp, call->out_volsync);
 	return 0;
 }
@@ -968,12 +951,8 @@ static int yfs_deliver_fs_link(struct afs_call *call)
 		return ret;
 
 	bp = call->buffer;
-	ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb);
-	if (ret < 0)
-		return ret;
-	ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb);
-	if (ret < 0)
-		return ret;
+	xdr_decode_YFSFetchStatus(&bp, call, call->out_scb);
+	xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb);
 	xdr_decode_YFSVolSync(&bp, call->out_volsync);
 	_leave(" = 0 [done]");
 	return 0;
@@ -1055,12 +1034,8 @@ static int yfs_deliver_fs_symlink(struct afs_call *call)
 	/* unmarshall the reply once we've received all of it */
 	bp = call->buffer;
 	xdr_decode_YFSFid(&bp, call->out_fid);
-	ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb);
-	if (ret < 0)
-		return ret;
-	ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb);
-	if (ret < 0)
-		return ret;
+	xdr_decode_YFSFetchStatus(&bp, call, call->out_scb);
+	xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb);
 	xdr_decode_YFSVolSync(&bp, call->out_volsync);
 
 	_leave(" = 0 [done]");
@@ -1148,15 +1123,11 @@ static int yfs_deliver_fs_rename(struct afs_call *call)
 		return ret;
 
 	bp = call->buffer;
-	ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb);
-	if (ret < 0)
-		return ret;
-	if (call->out_dir_scb != call->out_scb) {
-		ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb);
-		if (ret < 0)
-			return ret;
-	}
-
+	/* If the two dirs are the same, we have two copies of the same status
+	 * report, so we just decode it twice.
+	 */
+	xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb);
+	xdr_decode_YFSFetchStatus(&bp, call, call->out_scb);
 	xdr_decode_YFSVolSync(&bp, call->out_volsync);
 	_leave(" = 0 [done]");
 	return 0;
@@ -1834,9 +1805,7 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call)
 
 		bp = call->buffer;
 		scb = &call->out_scb[call->count];
-		ret = xdr_decode_YFSFetchStatus(&bp, call, scb);
-		if (ret < 0)
-			return ret;
+		xdr_decode_YFSFetchStatus(&bp, call, scb);
 
 		call->count++;
 		if (call->count < call->count2)
@@ -2051,9 +2020,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call)
 		bp = call->buffer;
 		yacl->inherit_flag = ntohl(*bp++);
 		yacl->num_cleaned = ntohl(*bp++);
-		ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb);
-		if (ret < 0)
-			return ret;
+		xdr_decode_YFSFetchStatus(&bp, call, call->out_scb);
 		xdr_decode_YFSVolSync(&bp, call->out_volsync);
 
 		call->unmarshall++;
diff --git a/fs/aio.c b/fs/aio.c
index 53ce4bffc289..9bc3ffabd775 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -175,6 +175,7 @@ struct fsync_iocb {
 	struct file		*file;
 	struct work_struct	work;
 	bool			datasync;
+	struct cred		*creds;
 };
 
 struct poll_iocb {
@@ -1590,8 +1591,11 @@ static int aio_write(struct kiocb *req, const struct iocb *iocb,
 static void aio_fsync_work(struct work_struct *work)
 {
 	struct aio_kiocb *iocb = container_of(work, struct aio_kiocb, fsync.work);
+	const struct cred *old_cred = override_creds(iocb->fsync.creds);
 
 	iocb->ki_res.res = vfs_fsync(iocb->fsync.file, iocb->fsync.datasync);
+	revert_creds(old_cred);
+	put_cred(iocb->fsync.creds);
 	iocb_put(iocb);
 }
 
@@ -1605,12 +1609,24 @@ static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb,
 	if (unlikely(!req->file->f_op->fsync))
 		return -EINVAL;
 
+	req->creds = prepare_creds();
+	if (!req->creds)
+		return -ENOMEM;
+
 	req->datasync = datasync;
 	INIT_WORK(&req->work, aio_fsync_work);
 	schedule_work(&req->work);
 	return 0;
 }
 
+static void aio_poll_put_work(struct work_struct *work)
+{
+	struct poll_iocb *req = container_of(work, struct poll_iocb, work);
+	struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll);
+
+	iocb_put(iocb);
+}
+
 static void aio_poll_complete_work(struct work_struct *work)
 {
 	struct poll_iocb *req = container_of(work, struct poll_iocb, work);
@@ -1675,6 +1691,8 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
 	list_del_init(&req->wait.entry);
 
 	if (mask && spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) {
+		struct kioctx *ctx = iocb->ki_ctx;
+
 		/*
 		 * Try to complete the iocb inline if we can. Use
 		 * irqsave/irqrestore because not all filesystems (e.g. fuse)
@@ -1684,8 +1702,14 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
 		list_del(&iocb->ki_list);
 		iocb->ki_res.res = mangle_poll(mask);
 		req->done = true;
-		spin_unlock_irqrestore(&iocb->ki_ctx->ctx_lock, flags);
-		iocb_put(iocb);
+		if (iocb->ki_eventfd && eventfd_signal_count()) {
+			iocb = NULL;
+			INIT_WORK(&req->work, aio_poll_put_work);
+			schedule_work(&req->work);
+		}
+		spin_unlock_irqrestore(&ctx->ctx_lock, flags);
+		if (iocb)
+			iocb_put(iocb);
 	} else {
 		schedule_work(&req->work);
 	}
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 1f95ed1ad2ee..1ec2fa94d236 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1752,7 +1752,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
 		    (!regset->active || regset->active(t->task, regset) > 0)) {
 			int ret;
 			size_t size = regset_size(t->task, regset);
-			void *data = kmalloc(size, GFP_KERNEL);
+			void *data = kzalloc(size, GFP_KERNEL);
 			if (unlikely(!data))
 				return 0;
 			ret = regset->get(t->task, regset,
diff --git a/fs/block_dev.c b/fs/block_dev.c
index a9e7c1b69437..ff09b7be4878 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1548,10 +1548,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 	 */
 	if (!for_part) {
 		ret = devcgroup_inode_permission(bdev->bd_inode, perm);
-		if (ret != 0) {
-			bdput(bdev);
+		if (ret != 0)
 			return ret;
-		}
 	}
 
  restart:
@@ -1623,8 +1621,10 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 				goto out_clear;
 			BUG_ON(for_part);
 			ret = __blkdev_get(whole, mode, 1);
-			if (ret)
+			if (ret) {
+				bdput(whole);
 				goto out_clear;
+			}
 			bdev->bd_contains = whole;
 			bdev->bd_part = disk_get_part(disk, partno);
 			if (!(disk->flags & GENHD_FL_UP) ||
@@ -1677,7 +1677,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 	disk_unblock_events(disk);
 	put_disk_and_module(disk);
  out:
-	bdput(bdev);
 
 	return ret;
 }
@@ -1744,6 +1743,9 @@ int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
 		bdput(whole);
 	}
 
+	if (res)
+		bdput(bdev);
+
 	return res;
 }
 EXPORT_SYMBOL(blkdev_get);
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index f6435c0f01cf..29e28cee0e3e 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -51,16 +51,6 @@ struct btrfs_workqueue {
 	struct __btrfs_workqueue *high;
 };
 
-static void normal_work_helper(struct btrfs_work *work);
-
-#define BTRFS_WORK_HELPER(name)					\
-noinline_for_stack void btrfs_##name(struct work_struct *arg)		\
-{									\
-	struct btrfs_work *work = container_of(arg, struct btrfs_work,	\
-					       normal_work);		\
-	normal_work_helper(work);					\
-}
-
 struct btrfs_fs_info *
 btrfs_workqueue_owner(const struct __btrfs_workqueue *wq)
 {
@@ -87,29 +77,6 @@ bool btrfs_workqueue_normal_congested(const struct btrfs_workqueue *wq)
 	return atomic_read(&wq->normal->pending) > wq->normal->thresh * 2;
 }
 
-BTRFS_WORK_HELPER(worker_helper);
-BTRFS_WORK_HELPER(delalloc_helper);
-BTRFS_WORK_HELPER(flush_delalloc_helper);
-BTRFS_WORK_HELPER(cache_helper);
-BTRFS_WORK_HELPER(submit_helper);
-BTRFS_WORK_HELPER(fixup_helper);
-BTRFS_WORK_HELPER(endio_helper);
-BTRFS_WORK_HELPER(endio_meta_helper);
-BTRFS_WORK_HELPER(endio_meta_write_helper);
-BTRFS_WORK_HELPER(endio_raid56_helper);
-BTRFS_WORK_HELPER(endio_repair_helper);
-BTRFS_WORK_HELPER(rmw_helper);
-BTRFS_WORK_HELPER(endio_write_helper);
-BTRFS_WORK_HELPER(freespace_write_helper);
-BTRFS_WORK_HELPER(delayed_meta_helper);
-BTRFS_WORK_HELPER(readahead_helper);
-BTRFS_WORK_HELPER(qgroup_rescan_helper);
-BTRFS_WORK_HELPER(extent_refs_helper);
-BTRFS_WORK_HELPER(scrub_helper);
-BTRFS_WORK_HELPER(scrubwrc_helper);
-BTRFS_WORK_HELPER(scrubnc_helper);
-BTRFS_WORK_HELPER(scrubparity_helper);
-
 static struct __btrfs_workqueue *
 __btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info, const char *name,
 			unsigned int flags, int limit_active, int thresh)
@@ -300,12 +267,13 @@ static void run_ordered_work(struct __btrfs_workqueue *wq,
 			 * original work item cannot depend on the recycled work
 			 * item in that case (see find_worker_executing_work()).
 			 *
-			 * Note that the work of one Btrfs filesystem may depend
-			 * on the work of another Btrfs filesystem via, e.g., a
-			 * loop device. Therefore, we must not allow the current
-			 * work item to be recycled until we are really done,
-			 * otherwise we break the above assumption and can
-			 * deadlock.
+			 * Note that different types of Btrfs work can depend on
+			 * each other, and one type of work on one Btrfs
+			 * filesystem may even depend on the same type of work
+			 * on another Btrfs filesystem via, e.g., a loop device.
+			 * Therefore, we must not allow the current work item to
+			 * be recycled until we are really done, otherwise we
+			 * break the above assumption and can deadlock.
 			 */
 			free_self = true;
 		} else {
@@ -329,8 +297,10 @@ static void run_ordered_work(struct __btrfs_workqueue *wq,
 	}
 }
 
-static void normal_work_helper(struct btrfs_work *work)
+static void btrfs_work_helper(struct work_struct *normal_work)
 {
+	struct btrfs_work *work = container_of(normal_work, struct btrfs_work,
+					       normal_work);
 	struct __btrfs_workqueue *wq;
 	void *wtag;
 	int need_order = 0;
@@ -360,15 +330,13 @@ static void normal_work_helper(struct btrfs_work *work)
 		trace_btrfs_all_work_done(wq->fs_info, wtag);
 }
 
-void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t uniq_func,
-		     btrfs_func_t func,
-		     btrfs_func_t ordered_func,
-		     btrfs_func_t ordered_free)
+void btrfs_init_work(struct btrfs_work *work, btrfs_func_t func,
+		     btrfs_func_t ordered_func, btrfs_func_t ordered_free)
 {
 	work->func = func;
 	work->ordered_func = ordered_func;
 	work->ordered_free = ordered_free;
-	INIT_WORK(&work->normal_work, uniq_func);
+	INIT_WORK(&work->normal_work, btrfs_work_helper);
 	INIT_LIST_HEAD(&work->ordered_list);
 	work->flags = 0;
 }
@@ -432,3 +400,11 @@ void btrfs_set_work_high_priority(struct btrfs_work *work)
 {
 	set_bit(WORK_HIGH_PRIO_BIT, &work->flags);
 }
+
+void btrfs_flush_workqueue(struct btrfs_workqueue *wq)
+{
+	if (wq->high)
+		flush_workqueue(wq->high->normal_wq);
+
+	flush_workqueue(wq->normal->normal_wq);
+}
diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h
index 7861c9feba5f..714ab6855423 100644
--- a/fs/btrfs/async-thread.h
+++ b/fs/btrfs/async-thread.h
@@ -29,42 +29,13 @@ struct btrfs_work {
 	unsigned long flags;
 };
 
-#define BTRFS_WORK_HELPER_PROTO(name)					\
-void btrfs_##name(struct work_struct *arg)
-
-BTRFS_WORK_HELPER_PROTO(worker_helper);
-BTRFS_WORK_HELPER_PROTO(delalloc_helper);
-BTRFS_WORK_HELPER_PROTO(flush_delalloc_helper);
-BTRFS_WORK_HELPER_PROTO(cache_helper);
-BTRFS_WORK_HELPER_PROTO(submit_helper);
-BTRFS_WORK_HELPER_PROTO(fixup_helper);
-BTRFS_WORK_HELPER_PROTO(endio_helper);
-BTRFS_WORK_HELPER_PROTO(endio_meta_helper);
-BTRFS_WORK_HELPER_PROTO(endio_meta_write_helper);
-BTRFS_WORK_HELPER_PROTO(endio_raid56_helper);
-BTRFS_WORK_HELPER_PROTO(endio_repair_helper);
-BTRFS_WORK_HELPER_PROTO(rmw_helper);
-BTRFS_WORK_HELPER_PROTO(endio_write_helper);
-BTRFS_WORK_HELPER_PROTO(freespace_write_helper);
-BTRFS_WORK_HELPER_PROTO(delayed_meta_helper);
-BTRFS_WORK_HELPER_PROTO(readahead_helper);
-BTRFS_WORK_HELPER_PROTO(qgroup_rescan_helper);
-BTRFS_WORK_HELPER_PROTO(extent_refs_helper);
-BTRFS_WORK_HELPER_PROTO(scrub_helper);
-BTRFS_WORK_HELPER_PROTO(scrubwrc_helper);
-BTRFS_WORK_HELPER_PROTO(scrubnc_helper);
-BTRFS_WORK_HELPER_PROTO(scrubparity_helper);
-
-
 struct btrfs_workqueue *btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info,
 					      const char *name,
 					      unsigned int flags,
 					      int limit_active,
 					      int thresh);
-void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t helper,
-		     btrfs_func_t func,
-		     btrfs_func_t ordered_func,
-		     btrfs_func_t ordered_free);
+void btrfs_init_work(struct btrfs_work *work, btrfs_func_t func,
+		     btrfs_func_t ordered_func, btrfs_func_t ordered_free);
 void btrfs_queue_work(struct btrfs_workqueue *wq,
 		      struct btrfs_work *work);
 void btrfs_destroy_workqueue(struct btrfs_workqueue *wq);
@@ -73,5 +44,6 @@ void btrfs_set_work_high_priority(struct btrfs_work *work);
 struct btrfs_fs_info *btrfs_work_owner(const struct btrfs_work *work);
 struct btrfs_fs_info *btrfs_workqueue_owner(const struct __btrfs_workqueue *wq);
 bool btrfs_workqueue_normal_congested(const struct btrfs_workqueue *wq);
+void btrfs_flush_workqueue(struct btrfs_workqueue *wq);
 
 #endif
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 69f8ab4d91f2..110636757d95 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1422,6 +1422,7 @@ static int btrfs_find_all_roots_safe(struct btrfs_trans_handle *trans,
 		if (ret < 0 && ret != -ENOENT) {
 			ulist_free(tmp);
 			ulist_free(*roots);
+			*roots = NULL;
 			return ret;
 		}
 		node = ulist_next(tmp, &uiter);
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index b0c8094528d1..3d2e2fdbdfb6 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -629,7 +629,6 @@ static struct btrfsic_dev_state *btrfsic_dev_state_hashtable_lookup(dev_t dev,
 static int btrfsic_process_superblock(struct btrfsic_state *state,
 				      struct btrfs_fs_devices *fs_devices)
 {
-	struct btrfs_fs_info *fs_info = state->fs_info;
 	struct btrfs_super_block *selected_super;
 	struct list_head *dev_head = &fs_devices->devices;
 	struct btrfs_device *device;
@@ -700,7 +699,7 @@ static int btrfsic_process_superblock(struct btrfsic_state *state,
 			break;
 		}
 
-		num_copies = btrfs_num_copies(fs_info, next_bytenr,
+		num_copies = btrfs_num_copies(state->fs_info, next_bytenr,
 					      state->metablock_size);
 		if (state->print_mask & BTRFSIC_PRINT_MASK_NUM_COPIES)
 			pr_info("num_copies(log_bytenr=%llu) = %d\n",
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 966d379c45bd..ebd2ab53e00d 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -308,12 +308,10 @@ u64 btrfs_get_tree_mod_seq(struct btrfs_fs_info *fs_info,
 			   struct seq_list *elem)
 {
 	write_lock(&fs_info->tree_mod_log_lock);
-	spin_lock(&fs_info->tree_mod_seq_lock);
 	if (!elem->seq) {
 		elem->seq = btrfs_inc_tree_mod_seq(fs_info);
 		list_add_tail(&elem->list, &fs_info->tree_mod_seq_list);
 	}
-	spin_unlock(&fs_info->tree_mod_seq_lock);
 	write_unlock(&fs_info->tree_mod_log_lock);
 
 	return elem->seq;
@@ -333,7 +331,7 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
 	if (!seq_putting)
 		return;
 
-	spin_lock(&fs_info->tree_mod_seq_lock);
+	write_lock(&fs_info->tree_mod_log_lock);
 	list_del(&elem->list);
 	elem->seq = 0;
 
@@ -344,19 +342,17 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
 				 * blocker with lower sequence number exists, we
 				 * cannot remove anything from the log
 				 */
-				spin_unlock(&fs_info->tree_mod_seq_lock);
+				write_unlock(&fs_info->tree_mod_log_lock);
 				return;
 			}
 			min_seq = cur_elem->seq;
 		}
 	}
-	spin_unlock(&fs_info->tree_mod_seq_lock);
 
 	/*
 	 * anything that's lower than the lowest existing (read: blocked)
 	 * sequence number can be removed from the tree.
 	 */
-	write_lock(&fs_info->tree_mod_log_lock);
 	tm_root = &fs_info->tree_mod_log;
 	for (node = rb_first(tm_root); node; node = next) {
 		next = rb_next(node);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 9804bcc5ae52..5d8b7a9820e1 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -939,14 +939,12 @@ struct btrfs_fs_info {
 	atomic_t nr_delayed_iputs;
 	wait_queue_head_t delayed_iputs_wait;
 
-	/* this protects tree_mod_seq_list */
-	spinlock_t tree_mod_seq_lock;
 	atomic64_t tree_mod_seq;
-	struct list_head tree_mod_seq_list;
 
-	/* this protects tree_mod_log */
+	/* this protects tree_mod_log and tree_mod_seq_list */
 	rwlock_t tree_mod_log_lock;
 	struct rb_root tree_mod_log;
+	struct list_head tree_mod_seq_list;
 
 	atomic_t async_delalloc_pages;
 
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 8235ac0db4b1..1c8dd934bac9 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -6,6 +6,7 @@
 
 #include <linux/slab.h>
 #include <linux/iversion.h>
+#include <linux/sched/mm.h>
 #include "delayed-inode.h"
 #include "disk-io.h"
 #include "transaction.h"
@@ -803,11 +804,14 @@ static int btrfs_insert_delayed_item(struct btrfs_trans_handle *trans,
 				     struct btrfs_delayed_item *delayed_item)
 {
 	struct extent_buffer *leaf;
+	unsigned int nofs_flag;
 	char *ptr;
 	int ret;
 
+	nofs_flag = memalloc_nofs_save();
 	ret = btrfs_insert_empty_item(trans, root, path, &delayed_item->key,
 				      delayed_item->data_len);
+	memalloc_nofs_restore(nofs_flag);
 	if (ret < 0 && ret != -EEXIST)
 		return ret;
 
@@ -935,6 +939,7 @@ static int btrfs_delete_delayed_items(struct btrfs_trans_handle *trans,
 				      struct btrfs_delayed_node *node)
 {
 	struct btrfs_delayed_item *curr, *prev;
+	unsigned int nofs_flag;
 	int ret = 0;
 
 do_again:
@@ -943,7 +948,9 @@ do_again:
 	if (!curr)
 		goto delete_fail;
 
+	nofs_flag = memalloc_nofs_save();
 	ret = btrfs_search_slot(trans, root, &curr->key, path, -1, 1);
+	memalloc_nofs_restore(nofs_flag);
 	if (ret < 0)
 		goto delete_fail;
 	else if (ret > 0) {
@@ -1010,6 +1017,7 @@ static int __btrfs_update_delayed_inode(struct btrfs_trans_handle *trans,
 	struct btrfs_key key;
 	struct btrfs_inode_item *inode_item;
 	struct extent_buffer *leaf;
+	unsigned int nofs_flag;
 	int mod;
 	int ret;
 
@@ -1022,7 +1030,9 @@ static int __btrfs_update_delayed_inode(struct btrfs_trans_handle *trans,
 	else
 		mod = 1;
 
+	nofs_flag = memalloc_nofs_save();
 	ret = btrfs_lookup_inode(trans, root, path, &key, mod);
+	memalloc_nofs_restore(nofs_flag);
 	if (ret > 0) {
 		btrfs_release_path(path);
 		return -ENOENT;
@@ -1073,7 +1083,10 @@ search:
 
 	key.type = BTRFS_INODE_EXTREF_KEY;
 	key.offset = -1;
+
+	nofs_flag = memalloc_nofs_save();
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+	memalloc_nofs_restore(nofs_flag);
 	if (ret < 0)
 		goto err_out;
 	ASSERT(ret);
@@ -1366,8 +1379,8 @@ static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root,
 		return -ENOMEM;
 
 	async_work->delayed_root = delayed_root;
-	btrfs_init_work(&async_work->work, btrfs_delayed_meta_helper,
-			btrfs_async_run_delayed_root, NULL, NULL);
+	btrfs_init_work(&async_work->work, btrfs_async_run_delayed_root, NULL,
+			NULL);
 	async_work->nr = nr;
 
 	btrfs_queue_work(fs_info->delayed_workers, &async_work->work);
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index a73fc23e2961..26aa22ce0c70 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -318,7 +318,7 @@ void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans,
 	if (head->is_data)
 		return;
 
-	spin_lock(&fs_info->tree_mod_seq_lock);
+	read_lock(&fs_info->tree_mod_log_lock);
 	if (!list_empty(&fs_info->tree_mod_seq_list)) {
 		struct seq_list *elem;
 
@@ -326,7 +326,7 @@ void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans,
 					struct seq_list, list);
 		seq = elem->seq;
 	}
-	spin_unlock(&fs_info->tree_mod_seq_lock);
+	read_unlock(&fs_info->tree_mod_log_lock);
 
 again:
 	for (node = rb_first_cached(&head->ref_tree); node;
@@ -344,7 +344,7 @@ int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info, u64 seq)
 	struct seq_list *elem;
 	int ret = 0;
 
-	spin_lock(&fs_info->tree_mod_seq_lock);
+	read_lock(&fs_info->tree_mod_log_lock);
 	if (!list_empty(&fs_info->tree_mod_seq_list)) {
 		elem = list_first_entry(&fs_info->tree_mod_seq_list,
 					struct seq_list, list);
@@ -357,7 +357,7 @@ int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info, u64 seq)
 		}
 	}
 
-	spin_unlock(&fs_info->tree_mod_seq_lock);
+	read_unlock(&fs_info->tree_mod_log_lock);
 	return ret;
 }
 
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index c30d6169287e..fc5c9b797e31 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -712,43 +712,31 @@ static void end_workqueue_bio(struct bio *bio)
 	struct btrfs_end_io_wq *end_io_wq = bio->bi_private;
 	struct btrfs_fs_info *fs_info;
 	struct btrfs_workqueue *wq;
-	btrfs_work_func_t func;
 
 	fs_info = end_io_wq->info;
 	end_io_wq->status = bio->bi_status;
 
 	if (bio_op(bio) == REQ_OP_WRITE) {
-		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) {
+		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA)
 			wq = fs_info->endio_meta_write_workers;
-			func = btrfs_endio_meta_write_helper;
-		} else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE) {
+		else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE)
 			wq = fs_info->endio_freespace_worker;
-			func = btrfs_freespace_write_helper;
-		} else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) {
+		else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
 			wq = fs_info->endio_raid56_workers;
-			func = btrfs_endio_raid56_helper;
-		} else {
+		else
 			wq = fs_info->endio_write_workers;
-			func = btrfs_endio_write_helper;
-		}
 	} else {
-		if (unlikely(end_io_wq->metadata ==
-			     BTRFS_WQ_ENDIO_DIO_REPAIR)) {
+		if (unlikely(end_io_wq->metadata == BTRFS_WQ_ENDIO_DIO_REPAIR))
 			wq = fs_info->endio_repair_workers;
-			func = btrfs_endio_repair_helper;
-		} else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) {
+		else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
 			wq = fs_info->endio_raid56_workers;
-			func = btrfs_endio_raid56_helper;
-		} else if (end_io_wq->metadata) {
+		else if (end_io_wq->metadata)
 			wq = fs_info->endio_meta_workers;
-			func = btrfs_endio_meta_helper;
-		} else {
+		else
 			wq = fs_info->endio_workers;
-			func = btrfs_endio_helper;
-		}
 	}
 
-	btrfs_init_work(&end_io_wq->work, func, end_workqueue_fn, NULL, NULL);
+	btrfs_init_work(&end_io_wq->work, end_workqueue_fn, NULL, NULL);
 	btrfs_queue_work(wq, &end_io_wq->work);
 }
 
@@ -841,8 +829,8 @@ blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 	async->mirror_num = mirror_num;
 	async->submit_bio_start = submit_bio_start;
 
-	btrfs_init_work(&async->work, btrfs_worker_helper, run_one_async_start,
-			run_one_async_done, run_one_async_free);
+	btrfs_init_work(&async->work, run_one_async_start, run_one_async_done,
+			run_one_async_free);
 
 	async->bio_offset = bio_offset;
 
@@ -1523,9 +1511,16 @@ int btrfs_init_fs_root(struct btrfs_root *root)
 	spin_lock_init(&root->ino_cache_lock);
 	init_waitqueue_head(&root->ino_cache_wait);
 
-	ret = get_anon_bdev(&root->anon_dev);
-	if (ret)
-		goto fail;
+	/*
+	 * Don't assign anonymous block device to roots that are not exposed to
+	 * userspace, the id pool is limited to 1M
+	 */
+	if (is_fstree(root->root_key.objectid) &&
+	    btrfs_root_refs(&root->root_item) > 0) {
+		ret = get_anon_bdev(&root->anon_dev);
+		if (ret)
+			goto fail;
+	}
 
 	mutex_lock(&root->objectid_mutex);
 	ret = btrfs_find_highest_objectid(root,
@@ -2064,7 +2059,7 @@ static void free_root_extent_buffers(struct btrfs_root *root)
 }
 
 /* helper to cleanup tree roots */
-static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root)
+static void free_root_pointers(struct btrfs_fs_info *info, bool free_chunk_root)
 {
 	free_root_extent_buffers(info->tree_root);
 
@@ -2073,7 +2068,7 @@ static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root)
 	free_root_extent_buffers(info->csum_root);
 	free_root_extent_buffers(info->quota_root);
 	free_root_extent_buffers(info->uuid_root);
-	if (chunk_root)
+	if (free_chunk_root)
 		free_root_extent_buffers(info->chunk_root);
 	free_root_extent_buffers(info->free_space_root);
 }
@@ -2678,7 +2673,6 @@ int open_ctree(struct super_block *sb,
 	spin_lock_init(&fs_info->fs_roots_radix_lock);
 	spin_lock_init(&fs_info->delayed_iput_lock);
 	spin_lock_init(&fs_info->defrag_inodes_lock);
-	spin_lock_init(&fs_info->tree_mod_seq_lock);
 	spin_lock_init(&fs_info->super_lock);
 	spin_lock_init(&fs_info->buffer_lock);
 	spin_lock_init(&fs_info->unused_bgs_lock);
@@ -3063,6 +3057,18 @@ retry_root_backup:
 	fs_info->generation = generation;
 	fs_info->last_trans_committed = generation;
 
+	/*
+	 * If we have a uuid root and we're not being told to rescan we need to
+	 * check the generation here so we can set the
+	 * BTRFS_FS_UPDATE_UUID_TREE_GEN bit.  Otherwise we could commit the
+	 * transaction during a balance or the log replay without updating the
+	 * uuid generation, and then if we crash we would rescan the uuid tree,
+	 * even though it was perfectly fine.
+	 */
+	if (fs_info->uuid_root && !btrfs_test_opt(fs_info, RESCAN_UUID_TREE) &&
+	    fs_info->generation == btrfs_super_uuid_tree_generation(disk_super))
+		set_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags);
+
 	ret = btrfs_verify_dev_extents(fs_info);
 	if (ret) {
 		btrfs_err(fs_info,
@@ -3173,6 +3179,7 @@ retry_root_backup:
 	/* do not make disk changes in broken FS or nologreplay is given */
 	if (btrfs_super_log_root(disk_super) != 0 &&
 	    !btrfs_test_opt(fs_info, NOLOGREPLAY)) {
+		btrfs_info(fs_info, "start tree-log replay");
 		ret = btrfs_replay_log(fs_info, fs_devices);
 		if (ret) {
 			err = ret;
@@ -3208,6 +3215,7 @@ retry_root_backup:
 	if (IS_ERR(fs_info->fs_root)) {
 		err = PTR_ERR(fs_info->fs_root);
 		btrfs_warn(fs_info, "failed to read fs tree: %d", err);
+		fs_info->fs_root = NULL;
 		goto fail_qgroup;
 	}
 
@@ -3291,8 +3299,6 @@ retry_root_backup:
 			close_ctree(fs_info);
 			return ret;
 		}
-	} else {
-		set_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags);
 	}
 	set_bit(BTRFS_FS_OPEN, &fs_info->flags);
 
@@ -3329,7 +3335,7 @@ fail_block_groups:
 	btrfs_put_block_group_cache(fs_info);
 
 fail_tree_roots:
-	free_root_pointers(fs_info, 1);
+	free_root_pointers(fs_info, true);
 	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
 
 fail_sb_buffer:
@@ -3359,7 +3365,7 @@ recovery_tree_root:
 	if (!btrfs_test_opt(fs_info, USEBACKUPROOT))
 		goto fail_tree_roots;
 
-	free_root_pointers(fs_info, 0);
+	free_root_pointers(fs_info, false);
 
 	/* don't use the log in recovery mode, it won't be valid */
 	btrfs_set_super_log_root(disk_super, 0);
@@ -4006,6 +4012,19 @@ void close_ctree(struct btrfs_fs_info *fs_info)
 		 */
 		btrfs_delete_unused_bgs(fs_info);
 
+		/*
+		 * There might be existing delayed inode workers still running
+		 * and holding an empty delayed inode item. We must wait for
+		 * them to complete first because they can create a transaction.
+		 * This happens when someone calls btrfs_balance_delayed_items()
+		 * and then a transaction commit runs the same delayed nodes
+		 * before any delayed worker has done something with the nodes.
+		 * We must wait for any worker here and not at transaction
+		 * commit time since that could cause a deadlock.
+		 * This is a very rare case.
+		 */
+		btrfs_flush_workqueue(fs_info->delayed_workers);
+
 		ret = btrfs_commit_super(fs_info);
 		if (ret)
 			btrfs_err(fs_info, "commit super ret %d", ret);
@@ -4047,10 +4066,17 @@ void close_ctree(struct btrfs_fs_info *fs_info)
 	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
 	btrfs_stop_all_workers(fs_info);
 
-	btrfs_free_block_groups(fs_info);
-
 	clear_bit(BTRFS_FS_OPEN, &fs_info->flags);
-	free_root_pointers(fs_info, 1);
+	free_root_pointers(fs_info, true);
+
+	/*
+	 * We must free the block groups after dropping the fs_roots as we could
+	 * have had an IO error and have left over tree log blocks that aren't
+	 * cleaned up until the fs roots are freed.  This makes the block group
+	 * accounting appear to be wrong because there's pending reserved bytes,
+	 * so make sure we do the block group cleanup afterwards.
+	 */
+	btrfs_free_block_groups(fs_info);
 
 	iput(fs_info->btree_inode);
 
@@ -4285,6 +4311,7 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 		cond_resched();
 		spin_lock(&delayed_refs->lock);
 	}
+	btrfs_qgroup_destroy_extent_records(trans);
 
 	spin_unlock(&delayed_refs->lock);
 
@@ -4510,7 +4537,6 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
 	wake_up(&fs_info->transaction_wait);
 
 	btrfs_destroy_delayed_inodes(fs_info);
-	btrfs_assert_delayed_root_empty(fs_info);
 
 	btrfs_destroy_marked_extents(fs_info, &cur_trans->dirty_pages,
 				     EXTENT_DIRTY);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index bb0c1eb292b6..bcf6329cf3a1 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -600,8 +600,7 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
 	caching_ctl->block_group = cache;
 	caching_ctl->progress = cache->key.objectid;
 	refcount_set(&caching_ctl->count, 1);
-	btrfs_init_work(&caching_ctl->work, btrfs_cache_helper,
-			caching_thread, NULL, NULL);
+	btrfs_init_work(&caching_ctl->work, caching_thread, NULL, NULL);
 
 	spin_lock(&cache->lock);
 	/*
@@ -4746,6 +4745,7 @@ static int may_commit_transaction(struct btrfs_fs_info *fs_info,
 	struct reserve_ticket *ticket = NULL;
 	struct btrfs_block_rsv *delayed_rsv = &fs_info->delayed_block_rsv;
 	struct btrfs_block_rsv *delayed_refs_rsv = &fs_info->delayed_refs_rsv;
+	struct btrfs_block_rsv *trans_rsv = &fs_info->trans_block_rsv;
 	struct btrfs_trans_handle *trans;
 	u64 bytes_needed;
 	u64 reclaim_bytes = 0;
@@ -4796,6 +4796,11 @@ static int may_commit_transaction(struct btrfs_fs_info *fs_info,
 	spin_lock(&delayed_refs_rsv->lock);
 	reclaim_bytes += delayed_refs_rsv->reserved;
 	spin_unlock(&delayed_refs_rsv->lock);
+
+	spin_lock(&trans_rsv->lock);
+	reclaim_bytes += trans_rsv->reserved;
+	spin_unlock(&trans_rsv->lock);
+
 	if (reclaim_bytes >= bytes_needed)
 		goto commit;
 	bytes_needed -= reclaim_bytes;
@@ -7728,6 +7733,7 @@ static noinline int find_free_extent(struct btrfs_fs_info *fs_info,
 				u64 flags, int delalloc)
 {
 	int ret = 0;
+	int cache_block_group_error = 0;
 	struct btrfs_free_cluster *last_ptr = NULL;
 	struct btrfs_block_group_cache *block_group = NULL;
 	struct find_free_extent_ctl ffe_ctl = {0};
@@ -7888,7 +7894,20 @@ have_block_group:
 		if (unlikely(!ffe_ctl.cached)) {
 			ffe_ctl.have_caching_bg = true;
 			ret = cache_block_group(block_group, 0);
-			BUG_ON(ret < 0);
+
+			/*
+			 * If we get ENOMEM here or something else we want to
+			 * try other block groups, because it may not be fatal.
+			 * However if we can't find anything else we need to
+			 * save our return here so that we return the actual
+			 * error that caused problems, not ENOSPC.
+			 */
+			if (ret < 0) {
+				if (!cache_block_group_error)
+					cache_block_group_error = ret;
+				ret = 0;
+				goto loop;
+			}
 			ret = 0;
 		}
 
@@ -7975,7 +7994,7 @@ loop:
 	if (ret > 0)
 		goto search;
 
-	if (ret == -ENOSPC) {
+	if (ret == -ENOSPC && !cache_block_group_error) {
 		/*
 		 * Use ffe_ctl->total_free_space as fallback if we can't find
 		 * any contiguous hole.
@@ -7986,6 +8005,8 @@ loop:
 		space_info->max_extent_size = ffe_ctl.max_extent_size;
 		spin_unlock(&space_info->lock);
 		ins->offset = ffe_ctl.max_extent_size;
+	} else if (ret == -ENOSPC) {
+		ret = cache_block_group_error;
 	}
 	return ret;
 }
@@ -10735,6 +10756,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 		 &fs_info->block_group_cache_tree);
 	RB_CLEAR_NODE(&block_group->cache_node);
 
+	/* Once for the block groups rbtree */
+	btrfs_put_block_group(block_group);
+
 	if (fs_info->first_logical_byte == block_group->key.objectid)
 		fs_info->first_logical_byte = (u64)-1;
 	spin_unlock(&fs_info->block_group_cache_lock);
@@ -10844,9 +10868,6 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	if (ret)
 		goto out;
 
-	btrfs_put_block_group(block_group);
-	btrfs_put_block_group(block_group);
-
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
 	if (ret > 0)
 		ret = -EIO;
@@ -10867,7 +10888,10 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 		/* once for the tree */
 		free_extent_map(em);
 	}
+
 out:
+	/* Once for the lookup reference */
+	btrfs_put_block_group(block_group);
 	if (remove_rsv)
 		btrfs_delayed_refs_rsv_release(fs_info, 1);
 	btrfs_free_path(path);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 927bb4ce3fa1..38ac638665a6 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1537,8 +1537,8 @@ out:
 }
 
 /**
- * find_first_clear_extent_bit - finds the first range that has @bits not set
- * and that starts after @start
+ * find_first_clear_extent_bit - find the first range that has @bits not set.
+ * This range could start before @start.
  *
  * @tree - the tree to search
  * @start - the offset at/after which the found extent should start
@@ -1562,28 +1562,72 @@ void find_first_clear_extent_bit(struct extent_io_tree *tree, u64 start,
 	/* Find first extent with bits cleared */
 	while (1) {
 		node = __etree_search(tree, start, &next, &prev, NULL, NULL);
-		if (!node) {
+		if (!node && !next && !prev) {
+			/*
+			 * Tree is completely empty, send full range and let
+			 * caller deal with it
+			 */
+			*start_ret = 0;
+			*end_ret = -1;
+			goto out;
+		} else if (!node && !next) {
+			/*
+			 * We are past the last allocated chunk, set start at
+			 * the end of the last extent.
+			 */
+			state = rb_entry(prev, struct extent_state, rb_node);
+			*start_ret = state->end + 1;
+			*end_ret = -1;
+			goto out;
+		} else if (!node) {
 			node = next;
-			if (!node) {
+		}
+		/*
+		 * At this point 'node' either contains 'start' or start is
+		 * before 'node'
+		 */
+		state = rb_entry(node, struct extent_state, rb_node);
+
+		if (in_range(start, state->start, state->end - state->start + 1)) {
+			if (state->state & bits) {
 				/*
-				 * We are past the last allocated chunk,
-				 * set start at the end of the last extent. The
-				 * device alloc tree should never be empty so
-				 * prev is always set.
+				 * |--range with bits sets--|
+				 *    |
+				 *    start
 				 */
-				ASSERT(prev);
-				state = rb_entry(prev, struct extent_state, rb_node);
-				*start_ret = state->end + 1;
-				*end_ret = -1;
-				goto out;
+				start = state->end + 1;
+			} else {
+				/*
+				 * 'start' falls within a range that doesn't
+				 * have the bits set, so take its start as
+				 * the beginning of the desired range
+				 *
+				 * |--range with bits cleared----|
+				 *      |
+				 *      start
+				 */
+				*start_ret = state->start;
+				break;
 			}
-		}
-		state = rb_entry(node, struct extent_state, rb_node);
-		if (in_range(start, state->start, state->end - state->start + 1) &&
-			(state->state & bits)) {
-			start = state->end + 1;
 		} else {
-			*start_ret = start;
+			/*
+			 * |---prev range---|---hole/unset---|---node range---|
+			 *                          |
+			 *                        start
+			 *
+			 *                        or
+			 *
+			 * |---hole/unset--||--first node--|
+			 * 0   |
+			 *    start
+			 */
+			if (prev) {
+				state = rb_entry(prev, struct extent_state,
+						 rb_node);
+				*start_ret = state->end + 1;
+			} else {
+				*start_ret = 0;
+			}
 			break;
 		}
 	}
@@ -1838,7 +1882,7 @@ static int __process_pages_contig(struct address_space *mapping,
 			if (page_ops & PAGE_SET_PRIVATE2)
 				SetPagePrivate2(pages[i]);
 
-			if (pages[i] == locked_page) {
+			if (locked_page && pages[i] == locked_page) {
 				put_page(pages[i]);
 				pages_locked++;
 				continue;
@@ -1858,7 +1902,8 @@ static int __process_pages_contig(struct address_space *mapping,
 				if (!PageDirty(pages[i]) ||
 				    pages[i]->mapping != mapping) {
 					unlock_page(pages[i]);
-					put_page(pages[i]);
+					for (; i < ret; i++)
+						put_page(pages[i]);
 					err = -EAGAIN;
 					goto out;
 				}
@@ -3901,6 +3946,11 @@ int btree_write_cache_pages(struct address_space *mapping,
 	if (wbc->range_cyclic) {
 		index = mapping->writeback_index; /* Start from prev offset */
 		end = -1;
+		/*
+		 * Start from the beginning does not need to cycle over the
+		 * range, mark it as scanned.
+		 */
+		scanned = (index == 0);
 	} else {
 		index = wbc->range_start >> PAGE_SHIFT;
 		end = wbc->range_end >> PAGE_SHIFT;
@@ -3918,7 +3968,6 @@ retry:
 			tag))) {
 		unsigned i;
 
-		scanned = 1;
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 
@@ -4043,6 +4092,11 @@ static int extent_write_cache_pages(struct address_space *mapping,
 	if (wbc->range_cyclic) {
 		index = mapping->writeback_index; /* Start from prev offset */
 		end = -1;
+		/*
+		 * Start from the beginning does not need to cycle over the
+		 * range, mark it as scanned.
+		 */
+		scanned = (index == 0);
 	} else {
 		index = wbc->range_start >> PAGE_SHIFT;
 		end = wbc->range_end >> PAGE_SHIFT;
@@ -4076,7 +4130,6 @@ retry:
 						&index, end, tag))) {
 		unsigned i;
 
-		scanned = 1;
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 
@@ -4136,7 +4189,16 @@ retry:
 		 */
 		scanned = 1;
 		index = 0;
-		goto retry;
+
+		/*
+		 * If we're looping we could run into a page that is locked by a
+		 * writer and that writer could be waiting on writeback for a
+		 * page in our current bio, and thus deadlock, so flush the
+		 * write bio here.
+		 */
+		ret = flush_write_bio(epd);
+		if (!ret)
+			goto retry;
 	}
 
 	if (wbc->range_cyclic || (wbc->nr_to_write > 0 && range_whole))
@@ -4387,6 +4449,8 @@ int try_release_extent_mapping(struct page *page, gfp_t mask)
 
 			/* once for us */
 			free_extent_map(em);
+
+			cond_resched(); /* Allow large-extent preemption. */
 		}
 	}
 	return try_release_extent_state(tree, page, mask);
@@ -4920,25 +4984,28 @@ struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
 static void check_buffer_tree_ref(struct extent_buffer *eb)
 {
 	int refs;
-	/* the ref bit is tricky.  We have to make sure it is set
-	 * if we have the buffer dirty.   Otherwise the
-	 * code to free a buffer can end up dropping a dirty
-	 * page
+	/*
+	 * The TREE_REF bit is first set when the extent_buffer is added
+	 * to the radix tree. It is also reset, if unset, when a new reference
+	 * is created by find_extent_buffer.
 	 *
-	 * Once the ref bit is set, it won't go away while the
-	 * buffer is dirty or in writeback, and it also won't
-	 * go away while we have the reference count on the
-	 * eb bumped.
+	 * It is only cleared in two cases: freeing the last non-tree
+	 * reference to the extent_buffer when its STALE bit is set or
+	 * calling releasepage when the tree reference is the only reference.
 	 *
-	 * We can't just set the ref bit without bumping the
-	 * ref on the eb because free_extent_buffer might
-	 * see the ref bit and try to clear it.  If this happens
-	 * free_extent_buffer might end up dropping our original
-	 * ref by mistake and freeing the page before we are able
-	 * to add one more ref.
+	 * In both cases, care is taken to ensure that the extent_buffer's
+	 * pages are not under io. However, releasepage can be concurrently
+	 * called with creating new references, which is prone to race
+	 * conditions between the calls to check_buffer_tree_ref in those
+	 * codepaths and clearing TREE_REF in try_release_extent_buffer.
 	 *
-	 * So bump the ref count first, then set the bit.  If someone
-	 * beat us to it, drop the ref we added.
+	 * The actual lifetime of the extent_buffer in the radix tree is
+	 * adequately protected by the refcount, but the TREE_REF bit and
+	 * its corresponding reference are not. To protect against this
+	 * class of races, we call check_buffer_tree_ref from the codepaths
+	 * which trigger io after they set eb->io_pages. Note that once io is
+	 * initiated, TREE_REF can no longer be cleared, so that is the
+	 * moment at which any such race is best fixed.
 	 */
 	refs = atomic_read(&eb->refs);
 	if (refs >= 2 && test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
@@ -5388,6 +5455,11 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num)
 	clear_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
 	eb->read_mirror = 0;
 	atomic_set(&eb->io_pages, num_reads);
+	/*
+	 * It is possible for releasepage to clear the TREE_REF bit before we
+	 * set io_pages. See check_buffer_tree_ref for a more detailed comment.
+	 */
+	check_buffer_tree_ref(eb);
 	for (i = 0; i < num_pages; i++) {
 		page = eb->pages[i];
 
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 9558d79faf1e..11f39d975525 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -233,6 +233,17 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em)
 	struct extent_map *merge = NULL;
 	struct rb_node *rb;
 
+	/*
+	 * We can't modify an extent map that is in the tree and that is being
+	 * used by another task, as it can cause that other task to see it in
+	 * inconsistent state during the merging. We always have 1 reference for
+	 * the tree and 1 for this task (which is unpinning the extent map or
+	 * clearing the logging flag), so anything > 2 means it's being used by
+	 * other tasks too.
+	 */
+	if (refcount_read(&em->refs) > 2)
+		return;
+
 	if (em->start != 0) {
 		rb = rb_prev(&em->rb_node);
 		if (rb)
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index cee1cd7d2ae5..ce5a413d334f 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -269,7 +269,8 @@ found:
 		csum += count * csum_size;
 		nblocks -= count;
 next:
-		while (count--) {
+		while (count > 0) {
+			count--;
 			disk_bytenr += fs_info->sectorsize;
 			offset += fs_info->sectorsize;
 			page_bytes_left -= fs_info->sectorsize;
@@ -790,10 +791,12 @@ again:
 		nritems = btrfs_header_nritems(path->nodes[0]);
 		if (!nritems || (path->slots[0] >= nritems - 1)) {
 			ret = btrfs_next_leaf(root, path);
-			if (ret == 1)
+			if (ret < 0) {
+				goto out;
+			} else if (ret > 0) {
 				found_next = 1;
-			if (ret != 0)
 				goto insert;
+			}
 			slot = path->slots[0];
 		}
 		btrfs_item_key_to_cpu(path->nodes[0], &found_key, slot);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index f77c4f0aaf3e..6dd68197419d 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1912,9 +1912,10 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	    (iocb->ki_flags & IOCB_NOWAIT))
 		return -EOPNOTSUPP;
 
-	if (!inode_trylock(inode)) {
-		if (iocb->ki_flags & IOCB_NOWAIT)
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!inode_trylock(inode))
 			return -EAGAIN;
+	} else {
 		inode_lock(inode);
 	}
 
@@ -2081,6 +2082,16 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	btrfs_init_log_ctx(&ctx, inode);
 
 	/*
+	 * Set the range to full if the NO_HOLES feature is not enabled.
+	 * This is to avoid missing file extent items representing holes after
+	 * replaying the log.
+	 */
+	if (!btrfs_fs_incompat(fs_info, NO_HOLES)) {
+		start = 0;
+		end = LLONG_MAX;
+	}
+
+	/*
 	 * We write the dirty pages in the range and wait until they complete
 	 * out of the ->i_mutex. If so, we can flush the dirty pages by
 	 * multi-task, and make the performance up.  See
@@ -2134,6 +2145,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	 */
 	ret = start_ordered_ops(inode, start, end);
 	if (ret) {
+		up_write(&BTRFS_I(inode)->dio_sem);
 		inode_unlock(inode);
 		goto out;
 	}
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 4efc36c35dd9..eaf1a31ceaf2 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -2166,7 +2166,7 @@ out:
 static bool try_merge_free_space(struct btrfs_free_space_ctl *ctl,
 			  struct btrfs_free_space *info, bool update_stat)
 {
-	struct btrfs_free_space *left_info;
+	struct btrfs_free_space *left_info = NULL;
 	struct btrfs_free_space *right_info;
 	bool merged = false;
 	u64 offset = info->offset;
@@ -2181,7 +2181,7 @@ static bool try_merge_free_space(struct btrfs_free_space_ctl *ctl,
 	if (right_info && rb_prev(&right_info->offset_index))
 		left_info = rb_entry(rb_prev(&right_info->offset_index),
 				     struct btrfs_free_space, offset_index);
-	else
+	else if (!right_info)
 		left_info = tree_search_offset(ctl, offset - 1, 0, 0);
 
 	if (right_info && !right_info->bitmap) {
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 6e0266b7f347..fe10da44a4d2 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -701,10 +701,12 @@ cleanup_and_bail_uncompressed:
 	 * to our extent and set things up for the async work queue to run
 	 * cow_file_range to do the normal delalloc dance.
 	 */
-	if (page_offset(async_chunk->locked_page) >= start &&
-	    page_offset(async_chunk->locked_page) <= end)
+	if (async_chunk->locked_page &&
+	    (page_offset(async_chunk->locked_page) >= start &&
+	     page_offset(async_chunk->locked_page)) <= end) {
 		__set_page_dirty_nobuffers(async_chunk->locked_page);
 		/* unlocked later on in the async handlers */
+	}
 
 	if (redirty)
 		extent_range_redirty_for_io(inode, start, end);
@@ -794,7 +796,7 @@ retry:
 						  async_extent->start +
 						  async_extent->ram_size - 1,
 						  WB_SYNC_ALL);
-			else if (ret)
+			else if (ret && async_chunk->locked_page)
 				unlock_page(async_chunk->locked_page);
 			kfree(async_extent);
 			cond_resched();
@@ -976,6 +978,7 @@ static noinline int cow_file_range(struct inode *inode,
 	u64 num_bytes;
 	unsigned long ram_size;
 	u64 cur_alloc_size = 0;
+	u64 min_alloc_size;
 	u64 blocksize = fs_info->sectorsize;
 	struct btrfs_key ins;
 	struct extent_map *em;
@@ -1027,10 +1030,26 @@ static noinline int cow_file_range(struct inode *inode,
 	btrfs_drop_extent_cache(BTRFS_I(inode), start,
 			start + num_bytes - 1, 0);
 
+	/*
+	 * Relocation relies on the relocated extents to have exactly the same
+	 * size as the original extents. Normally writeback for relocation data
+	 * extents follows a NOCOW path because relocation preallocates the
+	 * extents. However, due to an operation such as scrub turning a block
+	 * group to RO mode, it may fallback to COW mode, so we must make sure
+	 * an extent allocated during COW has exactly the requested size and can
+	 * not be split into smaller extents, otherwise relocation breaks and
+	 * fails during the stage where it updates the bytenr of file extent
+	 * items.
+	 */
+	if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID)
+		min_alloc_size = num_bytes;
+	else
+		min_alloc_size = fs_info->sectorsize;
+
 	while (num_bytes > 0) {
 		cur_alloc_size = num_bytes;
 		ret = btrfs_reserve_extent(root, cur_alloc_size, cur_alloc_size,
-					   fs_info->sectorsize, 0, alloc_hint,
+					   min_alloc_size, 0, alloc_hint,
 					   &ins, 1, 1);
 		if (ret < 0)
 			goto out_unlock;
@@ -1135,7 +1154,7 @@ out_unlock:
 	 */
 	if (extent_reserved) {
 		extent_clear_unlock_delalloc(inode, start,
-					     start + cur_alloc_size,
+					     start + cur_alloc_size - 1,
 					     start + cur_alloc_size,
 					     locked_page,
 					     clear_bits,
@@ -1271,14 +1290,27 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
 		async_chunk[i].inode = inode;
 		async_chunk[i].start = start;
 		async_chunk[i].end = cur_end;
-		async_chunk[i].locked_page = locked_page;
 		async_chunk[i].write_flags = write_flags;
 		INIT_LIST_HEAD(&async_chunk[i].extents);
 
-		btrfs_init_work(&async_chunk[i].work,
-				btrfs_delalloc_helper,
-				async_cow_start, async_cow_submit,
-				async_cow_free);
+		/*
+		 * The locked_page comes all the way from writepage and its
+		 * the original page we were actually given.  As we spread
+		 * this large delalloc region across multiple async_chunk
+		 * structs, only the first struct needs a pointer to locked_page
+		 *
+		 * This way we don't need racey decisions about who is supposed
+		 * to unlock it.
+		 */
+		if (locked_page) {
+			async_chunk[i].locked_page = locked_page;
+			locked_page = NULL;
+		} else {
+			async_chunk[i].locked_page = NULL;
+		}
+
+		btrfs_init_work(&async_chunk[i].work, async_cow_start,
+				async_cow_submit, async_cow_free);
 
 		nr_pages = DIV_ROUND_UP(cur_end - start, PAGE_SIZE);
 		atomic_add(nr_pages, &fs_info->async_delalloc_pages);
@@ -1429,7 +1461,7 @@ next_slot:
 				btrfs_file_extent_num_bytes(leaf, fi);
 			disk_num_bytes =
 				btrfs_file_extent_disk_num_bytes(leaf, fi);
-			if (extent_end <= start) {
+			if (extent_end <= cur_offset) {
 				path->slots[0]++;
 				goto next_slot;
 			}
@@ -2111,6 +2143,7 @@ int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
 /* see btrfs_writepage_start_hook for details on why this is required */
 struct btrfs_writepage_fixup {
 	struct page *page;
+	struct inode *inode;
 	struct btrfs_work work;
 };
 
@@ -2124,27 +2157,71 @@ static void btrfs_writepage_fixup_worker(struct btrfs_work *work)
 	struct inode *inode;
 	u64 page_start;
 	u64 page_end;
-	int ret;
+	int ret = 0;
+	bool free_delalloc_space = true;
 
 	fixup = container_of(work, struct btrfs_writepage_fixup, work);
 	page = fixup->page;
+	inode = fixup->inode;
+	page_start = page_offset(page);
+	page_end = page_offset(page) + PAGE_SIZE - 1;
+
+	/*
+	 * This is similar to page_mkwrite, we need to reserve the space before
+	 * we take the page lock.
+	 */
+	ret = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start,
+					   PAGE_SIZE);
 again:
 	lock_page(page);
+
+	/*
+	 * Before we queued this fixup, we took a reference on the page.
+	 * page->mapping may go NULL, but it shouldn't be moved to a different
+	 * address space.
+	 */
 	if (!page->mapping || !PageDirty(page) || !PageChecked(page)) {
-		ClearPageChecked(page);
+		/*
+		 * Unfortunately this is a little tricky, either
+		 *
+		 * 1) We got here and our page had already been dealt with and
+		 *    we reserved our space, thus ret == 0, so we need to just
+		 *    drop our space reservation and bail.  This can happen the
+		 *    first time we come into the fixup worker, or could happen
+		 *    while waiting for the ordered extent.
+		 * 2) Our page was already dealt with, but we happened to get an
+		 *    ENOSPC above from the btrfs_delalloc_reserve_space.  In
+		 *    this case we obviously don't have anything to release, but
+		 *    because the page was already dealt with we don't want to
+		 *    mark the page with an error, so make sure we're resetting
+		 *    ret to 0.  This is why we have this check _before_ the ret
+		 *    check, because we do not want to have a surprise ENOSPC
+		 *    when the page was already properly dealt with.
+		 */
+		if (!ret) {
+			btrfs_delalloc_release_extents(BTRFS_I(inode),
+						       PAGE_SIZE);
+			btrfs_delalloc_release_space(inode, data_reserved,
+						     page_start, PAGE_SIZE,
+						     true);
+		}
+		ret = 0;
 		goto out_page;
 	}
 
-	inode = page->mapping->host;
-	page_start = page_offset(page);
-	page_end = page_offset(page) + PAGE_SIZE - 1;
+	/*
+	 * We can't mess with the page state unless it is locked, so now that
+	 * it is locked bail if we failed to make our space reservation.
+	 */
+	if (ret)
+		goto out_page;
 
 	lock_extent_bits(&BTRFS_I(inode)->io_tree, page_start, page_end,
 			 &cached_state);
 
 	/* already ordered? We're done */
 	if (PagePrivate2(page))
-		goto out;
+		goto out_reserved;
 
 	ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), page_start,
 					PAGE_SIZE);
@@ -2157,39 +2234,49 @@ again:
 		goto again;
 	}
 
-	ret = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start,
-					   PAGE_SIZE);
-	if (ret) {
-		mapping_set_error(page->mapping, ret);
-		end_extent_writepage(page, ret, page_start, page_end);
-		ClearPageChecked(page);
-		goto out;
-	 }
-
 	ret = btrfs_set_extent_delalloc(inode, page_start, page_end, 0,
 					&cached_state, 0);
-	if (ret) {
-		mapping_set_error(page->mapping, ret);
-		end_extent_writepage(page, ret, page_start, page_end);
-		ClearPageChecked(page);
+	if (ret)
 		goto out_reserved;
-	}
 
-	ClearPageChecked(page);
-	set_page_dirty(page);
+	/*
+	 * Everything went as planned, we're now the owner of a dirty page with
+	 * delayed allocation bits set and space reserved for our COW
+	 * destination.
+	 *
+	 * The page was dirty when we started, nothing should have cleaned it.
+	 */
+	BUG_ON(!PageDirty(page));
+	free_delalloc_space = false;
 out_reserved:
 	btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
-	if (ret)
+	if (free_delalloc_space)
 		btrfs_delalloc_release_space(inode, data_reserved, page_start,
 					     PAGE_SIZE, true);
-out:
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start, page_end,
 			     &cached_state);
 out_page:
+	if (ret) {
+		/*
+		 * We hit ENOSPC or other errors.  Update the mapping and page
+		 * to reflect the errors and clean the page.
+		 */
+		mapping_set_error(page->mapping, ret);
+		end_extent_writepage(page, ret, page_start, page_end);
+		clear_page_dirty_for_io(page);
+		SetPageError(page);
+	}
+	ClearPageChecked(page);
 	unlock_page(page);
 	put_page(page);
 	kfree(fixup);
 	extent_changeset_free(data_reserved);
+	/*
+	 * As a precaution, do a delayed iput in case it would be the last iput
+	 * that could need flushing space. Recursing back to fixup worker would
+	 * deadlock.
+	 */
+	btrfs_add_delayed_iput(inode);
 }
 
 /*
@@ -2213,6 +2300,13 @@ int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end)
 	if (TestClearPagePrivate2(page))
 		return 0;
 
+	/*
+	 * PageChecked is set below when we create a fixup worker for this page,
+	 * don't try to create another one if we're already PageChecked()
+	 *
+	 * The extent_io writepage code will redirty the page if we send back
+	 * EAGAIN.
+	 */
 	if (PageChecked(page))
 		return -EAGAIN;
 
@@ -2220,13 +2314,21 @@ int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end)
 	if (!fixup)
 		return -EAGAIN;
 
+	/*
+	 * We are already holding a reference to this inode from
+	 * write_cache_pages.  We need to hold it because the space reservation
+	 * takes place outside of the page lock, and we can't trust
+	 * page->mapping outside of the page lock.
+	 */
+	ihold(inode);
 	SetPageChecked(page);
 	get_page(page);
-	btrfs_init_work(&fixup->work, btrfs_fixup_helper,
-			btrfs_writepage_fixup_worker, NULL, NULL);
+	btrfs_init_work(&fixup->work, btrfs_writepage_fixup_worker, NULL, NULL);
 	fixup->page = page;
+	fixup->inode = inode;
 	btrfs_queue_work(fs_info->fixup_workers, &fixup->work);
-	return -EBUSY;
+
+	return -EAGAIN;
 }
 
 static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
@@ -3216,7 +3318,6 @@ void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_ordered_extent *ordered_extent = NULL;
 	struct btrfs_workqueue *wq;
-	btrfs_work_func_t func;
 
 	trace_btrfs_writepage_end_io_hook(page, start, end, uptodate);
 
@@ -3225,16 +3326,12 @@ void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
 					    end - start + 1, uptodate))
 		return;
 
-	if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
+	if (btrfs_is_free_space_inode(BTRFS_I(inode)))
 		wq = fs_info->endio_freespace_worker;
-		func = btrfs_freespace_write_helper;
-	} else {
+	else
 		wq = fs_info->endio_write_workers;
-		func = btrfs_endio_write_helper;
-	}
 
-	btrfs_init_work(&ordered_extent->work, func, finish_ordered_fn, NULL,
-			NULL);
+	btrfs_init_work(&ordered_extent->work, finish_ordered_fn, NULL, NULL);
 	btrfs_queue_work(wq, &ordered_extent->work);
 }
 
@@ -4133,18 +4230,30 @@ out:
 }
 
 static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
-			       struct inode *dir, u64 objectid,
-			       const char *name, int name_len)
+			       struct inode *dir, struct dentry *dentry)
 {
 	struct btrfs_root *root = BTRFS_I(dir)->root;
+	struct btrfs_inode *inode = BTRFS_I(d_inode(dentry));
 	struct btrfs_path *path;
 	struct extent_buffer *leaf;
 	struct btrfs_dir_item *di;
 	struct btrfs_key key;
+	const char *name = dentry->d_name.name;
+	int name_len = dentry->d_name.len;
 	u64 index;
 	int ret;
+	u64 objectid;
 	u64 dir_ino = btrfs_ino(BTRFS_I(dir));
 
+	if (btrfs_ino(inode) == BTRFS_FIRST_FREE_OBJECTID) {
+		objectid = inode->root->root_key.objectid;
+	} else if (btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) {
+		objectid = inode->location.objectid;
+	} else {
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
@@ -4166,13 +4275,16 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 	}
 	btrfs_release_path(path);
 
-	ret = btrfs_del_root_ref(trans, objectid, root->root_key.objectid,
-				 dir_ino, &index, name, name_len);
-	if (ret < 0) {
-		if (ret != -ENOENT) {
-			btrfs_abort_transaction(trans, ret);
-			goto out;
-		}
+	/*
+	 * This is a placeholder inode for a subvolume we didn't have a
+	 * reference to at the time of the snapshot creation.  In the meantime
+	 * we could have renamed the real subvol link into our snapshot, so
+	 * depending on btrfs_del_root_ref to return -ENOENT here is incorret.
+	 * Instead simply lookup the dir_index_item for this entry so we can
+	 * remove it.  Otherwise we know we have a ref to the root and we can
+	 * call btrfs_del_root_ref, and it _shouldn't_ fail.
+	 */
+	if (btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) {
 		di = btrfs_search_dir_index_item(root, path, dir_ino,
 						 name, name_len);
 		if (IS_ERR_OR_NULL(di)) {
@@ -4187,8 +4299,16 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 		leaf = path->nodes[0];
 		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
 		index = key.offset;
+		btrfs_release_path(path);
+	} else {
+		ret = btrfs_del_root_ref(trans, objectid,
+					 root->root_key.objectid, dir_ino,
+					 &index, name, name_len);
+		if (ret) {
+			btrfs_abort_transaction(trans, ret);
+			goto out;
+		}
 	}
-	btrfs_release_path(path);
 
 	ret = btrfs_delete_delayed_dir_index(trans, BTRFS_I(dir), index);
 	if (ret) {
@@ -4382,8 +4502,7 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry)
 
 	btrfs_record_snapshot_destroy(trans, BTRFS_I(dir));
 
-	ret = btrfs_unlink_subvol(trans, dir, dest->root_key.objectid,
-				  dentry->d_name.name, dentry->d_name.len);
+	ret = btrfs_unlink_subvol(trans, dir, dentry);
 	if (ret) {
 		err = ret;
 		btrfs_abort_transaction(trans, ret);
@@ -4428,6 +4547,8 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry)
 		}
 	}
 
+	free_anon_bdev(dest->anon_dev);
+	dest->anon_dev = 0;
 out_end_trans:
 	trans->block_rsv = NULL;
 	trans->bytes_reserved = 0;
@@ -4478,10 +4599,7 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
 		return PTR_ERR(trans);
 
 	if (unlikely(btrfs_ino(BTRFS_I(inode)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
-		err = btrfs_unlink_subvol(trans, dir,
-					  BTRFS_I(inode)->location.objectid,
-					  dentry->d_name.name,
-					  dentry->d_name.len);
+		err = btrfs_unlink_subvol(trans, dir, dentry);
 		goto out;
 	}
 
@@ -4562,6 +4680,8 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 	u64 bytes_deleted = 0;
 	bool be_nice = false;
 	bool should_throttle = false;
+	const u64 lock_start = ALIGN_DOWN(new_size, fs_info->sectorsize);
+	struct extent_state *cached_state = NULL;
 
 	BUG_ON(new_size > 0 && min_type != BTRFS_EXTENT_DATA_KEY);
 
@@ -4578,6 +4698,10 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 		return -ENOMEM;
 	path->reada = READA_BACK;
 
+	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID)
+		lock_extent_bits(&BTRFS_I(inode)->io_tree, lock_start, (u64)-1,
+				 &cached_state);
+
 	/*
 	 * We want to drop from the next block forward in case this new size is
 	 * not block aligned since we will be keeping the last block of the
@@ -4614,7 +4738,6 @@ search_again:
 		goto out;
 	}
 
-	path->leave_spinning = 1;
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
 	if (ret < 0)
 		goto out;
@@ -4766,7 +4889,6 @@ delete:
 		     root == fs_info->tree_root)) {
 			struct btrfs_ref ref = { 0 };
 
-			btrfs_set_path_blocking(path);
 			bytes_deleted += extent_num_bytes;
 
 			btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF,
@@ -4842,6 +4964,8 @@ out:
 		if (!ret && last_size > new_size)
 			last_size = new_size;
 		btrfs_ordered_update_i_size(inode, last_size, NULL);
+		unlock_extent_cached(&BTRFS_I(inode)->io_tree, lock_start,
+				     (u64)-1, &cached_state);
 	}
 
 	btrfs_free_path(path);
@@ -8168,18 +8292,14 @@ static void __endio_write_update_ordered(struct inode *inode,
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_ordered_extent *ordered = NULL;
 	struct btrfs_workqueue *wq;
-	btrfs_work_func_t func;
 	u64 ordered_offset = offset;
 	u64 ordered_bytes = bytes;
 	u64 last_offset;
 
-	if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
+	if (btrfs_is_free_space_inode(BTRFS_I(inode)))
 		wq = fs_info->endio_freespace_worker;
-		func = btrfs_freespace_write_helper;
-	} else {
+	else
 		wq = fs_info->endio_write_workers;
-		func = btrfs_endio_write_helper;
-	}
 
 	while (ordered_offset < offset + bytes) {
 		last_offset = ordered_offset;
@@ -8187,9 +8307,8 @@ static void __endio_write_update_ordered(struct inode *inode,
 							   &ordered_offset,
 							   ordered_bytes,
 							   uptodate)) {
-			btrfs_init_work(&ordered->work, func,
-					finish_ordered_fn,
-					NULL, NULL);
+			btrfs_init_work(&ordered->work, finish_ordered_fn, NULL,
+					NULL);
 			btrfs_queue_work(wq, &ordered->work);
 		}
 		/*
@@ -8388,7 +8507,6 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip)
 
 	/* bio split */
 	ASSERT(map_length <= INT_MAX);
-	atomic_inc(&dip->pending_bios);
 	do {
 		clone_len = min_t(int, submit_len, map_length);
 
@@ -8439,7 +8557,8 @@ submit:
 	if (!status)
 		return 0;
 
-	bio_put(bio);
+	if (bio != orig_bio)
+		bio_put(bio);
 out_err:
 	dip->errors = 1;
 	/*
@@ -8480,7 +8599,7 @@ static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
 	bio->bi_private = dip;
 	dip->orig_bio = bio;
 	dip->dio_bio = dio_bio;
-	atomic_set(&dip->pending_bios, 0);
+	atomic_set(&dip->pending_bios, 1);
 	io_bio = btrfs_io_bio(bio);
 	io_bio->logical = file_offset;
 
@@ -8627,9 +8746,6 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 			dio_data.overwrite = 1;
 			inode_unlock(inode);
 			relock = true;
-		} else if (iocb->ki_flags & IOCB_NOWAIT) {
-			ret = -EAGAIN;
-			goto out;
 		}
 		ret = btrfs_delalloc_reserve_space(inode, &data_reserved,
 						   offset, count);
@@ -9475,7 +9591,6 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 	u64 new_ino = btrfs_ino(BTRFS_I(new_inode));
 	u64 old_idx = 0;
 	u64 new_idx = 0;
-	u64 root_objectid;
 	int ret;
 	bool root_log_pinned = false;
 	bool dest_log_pinned = false;
@@ -9581,10 +9696,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 
 	/* src is a subvolume */
 	if (old_ino == BTRFS_FIRST_FREE_OBJECTID) {
-		root_objectid = BTRFS_I(old_inode)->root->root_key.objectid;
-		ret = btrfs_unlink_subvol(trans, old_dir, root_objectid,
-					  old_dentry->d_name.name,
-					  old_dentry->d_name.len);
+		ret = btrfs_unlink_subvol(trans, old_dir, old_dentry);
 	} else { /* src is an inode */
 		ret = __btrfs_unlink_inode(trans, root, BTRFS_I(old_dir),
 					   BTRFS_I(old_dentry->d_inode),
@@ -9600,10 +9712,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 
 	/* dest is a subvolume */
 	if (new_ino == BTRFS_FIRST_FREE_OBJECTID) {
-		root_objectid = BTRFS_I(new_inode)->root->root_key.objectid;
-		ret = btrfs_unlink_subvol(trans, new_dir, root_objectid,
-					  new_dentry->d_name.name,
-					  new_dentry->d_name.len);
+		ret = btrfs_unlink_subvol(trans, new_dir, new_dentry);
 	} else { /* dest is an inode */
 		ret = __btrfs_unlink_inode(trans, dest, BTRFS_I(new_dir),
 					   BTRFS_I(new_dentry->d_inode),
@@ -9801,7 +9910,6 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct inode *new_inode = d_inode(new_dentry);
 	struct inode *old_inode = d_inode(old_dentry);
 	u64 index = 0;
-	u64 root_objectid;
 	int ret;
 	u64 old_ino = btrfs_ino(BTRFS_I(old_inode));
 	bool log_pinned = false;
@@ -9909,10 +10017,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 				BTRFS_I(old_inode), 1);
 
 	if (unlikely(old_ino == BTRFS_FIRST_FREE_OBJECTID)) {
-		root_objectid = BTRFS_I(old_inode)->root->root_key.objectid;
-		ret = btrfs_unlink_subvol(trans, old_dir, root_objectid,
-					old_dentry->d_name.name,
-					old_dentry->d_name.len);
+		ret = btrfs_unlink_subvol(trans, old_dir, old_dentry);
 	} else {
 		ret = __btrfs_unlink_inode(trans, root, BTRFS_I(old_dir),
 					BTRFS_I(d_inode(old_dentry)),
@@ -9931,10 +10036,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		new_inode->i_ctime = current_time(new_inode);
 		if (unlikely(btrfs_ino(BTRFS_I(new_inode)) ==
 			     BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
-			root_objectid = BTRFS_I(new_inode)->location.objectid;
-			ret = btrfs_unlink_subvol(trans, new_dir, root_objectid,
-						new_dentry->d_name.name,
-						new_dentry->d_name.len);
+			ret = btrfs_unlink_subvol(trans, new_dir, new_dentry);
 			BUG_ON(new_inode->i_nlink == 0);
 		} else {
 			ret = btrfs_unlink_inode(trans, dest, BTRFS_I(new_dir),
@@ -10014,6 +10116,10 @@ out_fail:
 		ret = btrfs_sync_log(trans, BTRFS_I(old_inode)->root, &ctx);
 		if (ret)
 			commit_transaction = true;
+	} else if (sync_log) {
+		mutex_lock(&root->log_mutex);
+		list_del(&ctx.list);
+		mutex_unlock(&root->log_mutex);
 	}
 	if (commit_transaction) {
 		ret = btrfs_commit_transaction(trans);
@@ -10079,8 +10185,7 @@ static struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode
 	init_completion(&work->completion);
 	INIT_LIST_HEAD(&work->list);
 	work->inode = inode;
-	btrfs_init_work(&work->work, btrfs_flush_delalloc_helper,
-			btrfs_run_delalloc_work, NULL, NULL);
+	btrfs_init_work(&work->work, btrfs_run_delalloc_work, NULL, NULL);
 
 	return work;
 }
@@ -10345,6 +10450,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_key ins;
 	u64 cur_offset = start;
+	u64 clear_offset = start;
 	u64 i_size;
 	u64 cur_bytes;
 	u64 last_alloc = (u64)-1;
@@ -10379,6 +10485,15 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 				btrfs_end_transaction(trans);
 			break;
 		}
+
+		/*
+		 * We've reserved this space, and thus converted it from
+		 * ->bytes_may_use to ->bytes_reserved.  Any error that happens
+		 * from here on out we will only need to clear our reservation
+		 * for the remaining unreserved area, so advance our
+		 * clear_offset by our extent size.
+		 */
+		clear_offset += ins.offset;
 		btrfs_dec_block_group_reservations(fs_info, ins.objectid);
 
 		last_alloc = ins.offset;
@@ -10459,9 +10574,9 @@ next:
 		if (own_trans)
 			btrfs_end_transaction(trans);
 	}
-	if (cur_offset < end)
-		btrfs_free_reserved_data_space(inode, NULL, cur_offset,
-			end - cur_offset + 1);
+	if (clear_offset < end)
+		btrfs_free_reserved_data_space(inode, NULL, clear_offset,
+			end - clear_offset + 1);
 	return ret;
 }
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 69f969d849c0..524821b437d0 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3241,6 +3241,7 @@ static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
 static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 len,
 				   struct inode *dst, u64 dst_loff)
 {
+	const u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize;
 	int ret;
 
 	/*
@@ -3248,7 +3249,7 @@ static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 len,
 	 * source range to serialize with relocation.
 	 */
 	btrfs_double_extent_lock(src, loff, dst, dst_loff, len);
-	ret = btrfs_clone(src, dst, loff, len, len, dst_loff, 1);
+	ret = btrfs_clone(src, dst, loff, len, ALIGN(len, bs), dst_loff, 1);
 	btrfs_double_extent_unlock(src, loff, dst, dst_loff, len);
 
 	return ret;
@@ -4380,7 +4381,19 @@ static long btrfs_ioctl_scrub(struct file *file, void __user *arg)
 			      &sa->progress, sa->flags & BTRFS_SCRUB_READONLY,
 			      0);
 
-	if (ret == 0 && copy_to_user(arg, sa, sizeof(*sa)))
+	/*
+	 * Copy scrub args to user space even if btrfs_scrub_dev() returned an
+	 * error. This is important as it allows user space to know how much
+	 * progress scrub has done. For example, if scrub is canceled we get
+	 * -ECANCELED from btrfs_scrub_dev() and return that error back to user
+	 * space. Later user space can inspect the progress from the structure
+	 * btrfs_ioctl_scrub_args and resume scrub from where it left off
+	 * previously (btrfs-progs does this).
+	 * If we fail to copy the btrfs_ioctl_scrub_args structure to user space
+	 * then return -EFAULT to signal the structure was not copied or it may
+	 * be corrupt and unreliable due to a partial copy.
+	 */
+	if (copy_to_user(arg, sa, sizeof(*sa)))
 		ret = -EFAULT;
 
 	if (!(sa->flags & BTRFS_SCRUB_READONLY))
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 52889da69113..6755e6966da6 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -545,7 +545,6 @@ u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr,
 		spin_unlock(&root->ordered_extent_lock);
 
 		btrfs_init_work(&ordered->flush_work,
-				btrfs_flush_delalloc_helper,
 				btrfs_run_ordered_extent_work, NULL, NULL);
 		list_add_tail(&ordered->work_list, &works);
 		btrfs_queue_work(fs_info->flush_workers, &ordered->flush_work);
@@ -689,10 +688,15 @@ int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len)
 		}
 		btrfs_start_ordered_extent(inode, ordered, 1);
 		end = ordered->file_offset;
+		/*
+		 * If the ordered extent had an error save the error but don't
+		 * exit without waiting first for all other ordered extents in
+		 * the range to complete.
+		 */
 		if (test_bit(BTRFS_ORDERED_IOERR, &ordered->flags))
 			ret = -EIO;
 		btrfs_put_ordered_extent(ordered);
-		if (ret || end == 0 || end == start)
+		if (end == 0 || end == start)
 			break;
 		end--;
 	}
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 60a00f6ca18f..297554cd03d6 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1030,6 +1030,7 @@ out_add_root:
 	ret = qgroup_rescan_init(fs_info, 0, 1);
 	if (!ret) {
 	        qgroup_rescan_zero_tracking(fs_info);
+		fs_info->qgroup_rescan_running = true;
 	        btrfs_queue_work(fs_info->qgroup_rescan_workers,
 	                         &fs_info->qgroup_rescan_work);
 	}
@@ -2411,8 +2412,12 @@ int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr,
 	u64 nr_old_roots = 0;
 	int ret = 0;
 
+	/*
+	 * If quotas get disabled meanwhile, the resouces need to be freed and
+	 * we can't just exit here.
+	 */
 	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
-		return 0;
+		goto out_free;
 
 	if (new_roots) {
 		if (!maybe_fs_roots(new_roots))
@@ -2619,6 +2624,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
 	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *srcgroup;
 	struct btrfs_qgroup *dstgroup;
+	bool need_rescan = false;
 	u32 level_size = 0;
 	u64 nums;
 
@@ -2762,6 +2768,13 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
 				goto unlock;
 		}
 		++i_qgroups;
+
+		/*
+		 * If we're doing a snapshot, and adding the snapshot to a new
+		 * qgroup, the numbers are guaranteed to be incorrect.
+		 */
+		if (srcid)
+			need_rescan = true;
 	}
 
 	for (i = 0; i <  inherit->num_ref_copies; ++i, i_qgroups += 2) {
@@ -2781,6 +2794,9 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
 
 		dst->rfer = src->rfer - level_size;
 		dst->rfer_cmpr = src->rfer_cmpr - level_size;
+
+		/* Manually tweaking numbers certainly needs a rescan */
+		need_rescan = true;
 	}
 	for (i = 0; i <  inherit->num_excl_copies; ++i, i_qgroups += 2) {
 		struct btrfs_qgroup *src;
@@ -2799,6 +2815,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
 
 		dst->excl = src->excl + level_size;
 		dst->excl_cmpr = src->excl_cmpr + level_size;
+		need_rescan = true;
 	}
 
 unlock:
@@ -2806,6 +2823,8 @@ unlock:
 out:
 	if (!committing)
 		mutex_unlock(&fs_info->qgroup_ioctl_lock);
+	if (need_rescan)
+		fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
 	return ret;
 }
 
@@ -3220,12 +3239,12 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 		if (!(fs_info->qgroup_flags &
 		      BTRFS_QGROUP_STATUS_FLAG_RESCAN)) {
 			btrfs_warn(fs_info,
-			"qgroup rescan init failed, qgroup is not enabled");
+			"qgroup rescan init failed, qgroup rescan is not queued");
 			ret = -EINVAL;
 		} else if (!(fs_info->qgroup_flags &
 			     BTRFS_QGROUP_STATUS_FLAG_ON)) {
 			btrfs_warn(fs_info,
-			"qgroup rescan init failed, qgroup rescan is not queued");
+			"qgroup rescan init failed, qgroup is not enabled");
 			ret = -EINVAL;
 		}
 
@@ -3260,7 +3279,6 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 		sizeof(fs_info->qgroup_rescan_progress));
 	fs_info->qgroup_rescan_progress.objectid = progress_objectid;
 	init_completion(&fs_info->qgroup_rescan_completion);
-	fs_info->qgroup_rescan_running = true;
 
 	spin_unlock(&fs_info->qgroup_lock);
 	mutex_unlock(&fs_info->qgroup_rescan_lock);
@@ -3268,7 +3286,6 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 	memset(&fs_info->qgroup_rescan_work, 0,
 	       sizeof(fs_info->qgroup_rescan_work));
 	btrfs_init_work(&fs_info->qgroup_rescan_work,
-			btrfs_qgroup_rescan_helper,
 			btrfs_qgroup_rescan_worker, NULL, NULL);
 	return 0;
 }
@@ -3326,8 +3343,11 @@ btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info)
 
 	qgroup_rescan_zero_tracking(fs_info);
 
+	mutex_lock(&fs_info->qgroup_rescan_lock);
+	fs_info->qgroup_rescan_running = true;
 	btrfs_queue_work(fs_info->qgroup_rescan_workers,
 			 &fs_info->qgroup_rescan_work);
+	mutex_unlock(&fs_info->qgroup_rescan_lock);
 
 	return 0;
 }
@@ -3363,9 +3383,13 @@ int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
 void
 btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info)
 {
-	if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN)
+	if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) {
+		mutex_lock(&fs_info->qgroup_rescan_lock);
+		fs_info->qgroup_rescan_running = true;
 		btrfs_queue_work(fs_info->qgroup_rescan_workers,
 				 &fs_info->qgroup_rescan_work);
+		mutex_unlock(&fs_info->qgroup_rescan_lock);
+	}
 }
 
 /*
@@ -4003,3 +4027,16 @@ out:
 	}
 	return ret;
 }
+
+void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans)
+{
+	struct btrfs_qgroup_extent_record *entry;
+	struct btrfs_qgroup_extent_record *next;
+	struct rb_root *root;
+
+	root = &trans->delayed_refs.dirty_extent_root;
+	rbtree_postorder_for_each_entry_safe(entry, next, root, node) {
+		ulist_free(entry->old_roots);
+		kfree(entry);
+	}
+}
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 46ba7bd2961c..17e8ac992c50 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -414,5 +414,6 @@ int btrfs_qgroup_add_swapped_blocks(struct btrfs_trans_handle *trans,
 		u64 last_snapshot);
 int btrfs_qgroup_trace_subtree_after_cow(struct btrfs_trans_handle *trans,
 		struct btrfs_root *root, struct extent_buffer *eb);
+void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans);
 
 #endif
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index f3d0576dd327..16c8af21b3fb 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -174,7 +174,7 @@ static void scrub_parity_work(struct btrfs_work *work);
 
 static void start_async_work(struct btrfs_raid_bio *rbio, btrfs_func_t work_func)
 {
-	btrfs_init_work(&rbio->work, btrfs_rmw_helper, work_func, NULL, NULL);
+	btrfs_init_work(&rbio->work, work_func, NULL, NULL);
 	btrfs_queue_work(rbio->fs_info->rmw_workers, &rbio->work);
 }
 
@@ -1727,8 +1727,7 @@ static void btrfs_raid_unplug(struct blk_plug_cb *cb, bool from_schedule)
 	plug = container_of(cb, struct btrfs_plug_cb, cb);
 
 	if (from_schedule) {
-		btrfs_init_work(&plug->work, btrfs_rmw_helper,
-				unplug_work, NULL, NULL);
+		btrfs_init_work(&plug->work, unplug_work, NULL, NULL);
 		btrfs_queue_work(plug->info->rmw_workers,
 				 &plug->work);
 		return;
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index c0ff034b5e4d..6f5397e018cb 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -789,8 +789,7 @@ static void reada_start_machine(struct btrfs_fs_info *fs_info)
 		/* FIXME we cannot handle this properly right now */
 		BUG();
 	}
-	btrfs_init_work(&rmw->work, btrfs_readahead_helper,
-			reada_start_machine_worker, NULL, NULL);
+	btrfs_init_work(&rmw->work, reada_start_machine_worker, NULL, NULL);
 	rmw->fs_info = fs_info;
 
 	btrfs_queue_work(fs_info->readahead_workers, &rmw->work);
diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c
index b57f3618e58e..9a2f15f4c80e 100644
--- a/fs/btrfs/ref-verify.c
+++ b/fs/btrfs/ref-verify.c
@@ -286,6 +286,8 @@ static struct block_entry *add_block_entry(struct btrfs_fs_info *fs_info,
 			exist_re = insert_root_entry(&exist->roots, re);
 			if (exist_re)
 				kfree(re);
+		} else {
+			kfree(re);
 		}
 		kfree(be);
 		return exist;
@@ -744,6 +746,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info,
 		 */
 		be = add_block_entry(fs_info, bytenr, num_bytes, ref_root);
 		if (IS_ERR(be)) {
+			kfree(ref);
 			kfree(ra);
 			ret = PTR_ERR(be);
 			goto out;
@@ -757,6 +760,8 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info,
 			"re-allocated a block that still has references to it!");
 			dump_block_entry(fs_info, be);
 			dump_ref_action(fs_info, ra);
+			kfree(ref);
+			kfree(ra);
 			goto out_unlock;
 		}
 
@@ -819,6 +824,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info,
 "dropping a ref for a existing root that doesn't have a ref on the block");
 				dump_block_entry(fs_info, be);
 				dump_ref_action(fs_info, ra);
+				kfree(ref);
 				kfree(ra);
 				goto out_unlock;
 			}
@@ -834,6 +840,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info,
 "attempting to add another ref for an existing ref on a tree block");
 			dump_block_entry(fs_info, be);
 			dump_ref_action(fs_info, ra);
+			kfree(ref);
 			kfree(ra);
 			goto out_unlock;
 		}
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 2a2426e0e765..4147b569c64c 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -527,8 +527,8 @@ static int should_ignore_root(struct btrfs_root *root)
 	if (!reloc_root)
 		return 0;
 
-	if (btrfs_root_last_snapshot(&reloc_root->root_item) ==
-	    root->fs_info->running_transaction->transid - 1)
+	if (btrfs_header_generation(reloc_root->commit_root) ==
+	    root->fs_info->running_transaction->transid)
 		return 0;
 	/*
 	 * if there is reloc tree and it was created in previous
@@ -1152,7 +1152,7 @@ out:
 			free_backref_node(cache, lower);
 		}
 
-		free_backref_node(cache, node);
+		remove_backref_node(cache, node);
 		return ERR_PTR(err);
 	}
 	ASSERT(!node || !node->detached);
@@ -1264,7 +1264,7 @@ static int __must_check __add_reloc_root(struct btrfs_root *root)
 	if (!node)
 		return -ENOMEM;
 
-	node->bytenr = root->node->start;
+	node->bytenr = root->commit_root->start;
 	node->data = root;
 
 	spin_lock(&rc->reloc_root_tree.lock);
@@ -1295,10 +1295,11 @@ static void __del_reloc_root(struct btrfs_root *root)
 	if (rc && root->node) {
 		spin_lock(&rc->reloc_root_tree.lock);
 		rb_node = tree_search(&rc->reloc_root_tree.rb_root,
-				      root->node->start);
+				      root->commit_root->start);
 		if (rb_node) {
 			node = rb_entry(rb_node, struct mapping_node, rb_node);
 			rb_erase(&node->rb_node, &rc->reloc_root_tree.rb_root);
+			RB_CLEAR_NODE(&node->rb_node);
 		}
 		spin_unlock(&rc->reloc_root_tree.lock);
 		if (!node)
@@ -1316,7 +1317,7 @@ static void __del_reloc_root(struct btrfs_root *root)
  * helper to update the 'address of tree root -> reloc tree'
  * mapping
  */
-static int __update_reloc_root(struct btrfs_root *root, u64 new_bytenr)
+static int __update_reloc_root(struct btrfs_root *root)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct rb_node *rb_node;
@@ -1325,7 +1326,7 @@ static int __update_reloc_root(struct btrfs_root *root, u64 new_bytenr)
 
 	spin_lock(&rc->reloc_root_tree.lock);
 	rb_node = tree_search(&rc->reloc_root_tree.rb_root,
-			      root->node->start);
+			      root->commit_root->start);
 	if (rb_node) {
 		node = rb_entry(rb_node, struct mapping_node, rb_node);
 		rb_erase(&node->rb_node, &rc->reloc_root_tree.rb_root);
@@ -1337,7 +1338,7 @@ static int __update_reloc_root(struct btrfs_root *root, u64 new_bytenr)
 	BUG_ON((struct btrfs_root *)node->data != root);
 
 	spin_lock(&rc->reloc_root_tree.lock);
-	node->bytenr = new_bytenr;
+	node->bytenr = root->node->start;
 	rb_node = tree_insert(&rc->reloc_root_tree.rb_root,
 			      node->bytenr, &node->rb_node);
 	spin_unlock(&rc->reloc_root_tree.lock);
@@ -1491,6 +1492,7 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans,
 	}
 
 	if (reloc_root->commit_root != reloc_root->node) {
+		__update_reloc_root(reloc_root);
 		btrfs_set_root_node(root_item, reloc_root->node);
 		free_extent_buffer(reloc_root->commit_root);
 		reloc_root->commit_root = btrfs_root_node(reloc_root);
@@ -2480,12 +2482,10 @@ again:
 		reloc_root = list_entry(reloc_roots.next,
 					struct btrfs_root, root_list);
 
+		root = read_fs_root(fs_info, reloc_root->root_key.offset);
 		if (btrfs_root_refs(&reloc_root->root_item) > 0) {
-			root = read_fs_root(fs_info,
-					    reloc_root->root_key.offset);
 			BUG_ON(IS_ERR(root));
 			BUG_ON(root->reloc_root != reloc_root);
-
 			ret = merge_reloc_root(rc, root);
 			if (ret) {
 				if (list_empty(&reloc_root->root_list))
@@ -2494,6 +2494,13 @@ again:
 				goto out;
 			}
 		} else {
+			if (!IS_ERR(root)) {
+				if (root->reloc_root == reloc_root)
+					root->reloc_root = NULL;
+				clear_bit(BTRFS_ROOT_DEAD_RELOC_TREE,
+					  &root->state);
+			}
+
 			list_del_init(&reloc_root->root_list);
 			/* Don't forget to queue this reloc root for cleanup */
 			list_add_tail(&reloc_root->reloc_dirty_list,
@@ -2519,7 +2526,21 @@ out:
 			free_reloc_roots(&reloc_roots);
 	}
 
-	BUG_ON(!RB_EMPTY_ROOT(&rc->reloc_root_tree.rb_root));
+	/*
+	 * We used to have
+	 *
+	 * BUG_ON(!RB_EMPTY_ROOT(&rc->reloc_root_tree.rb_root));
+	 *
+	 * here, but it's wrong.  If we fail to start the transaction in
+	 * prepare_to_merge() we will have only 0 ref reloc roots, none of which
+	 * have actually been removed from the reloc_root_tree rb tree.  This is
+	 * fine because we're bailing here, and we hold a reference on the root
+	 * for the list that holds it, so these roots will be cleaned up when we
+	 * do the reloc_dirty_list afterwards.  Meanwhile the root->reloc_root
+	 * will be cleaned up on unmount.
+	 *
+	 * The remaining nodes will be cleaned up by free_reloc_control.
+	 */
 }
 
 static void free_block_list(struct rb_root *blocks)
@@ -3119,9 +3140,8 @@ int relocate_tree_blocks(struct btrfs_trans_handle *trans,
 		ret = relocate_tree_block(trans, rc, node, &block->key,
 					  path);
 		if (ret < 0) {
-			if (ret != -EAGAIN || &block->rb_node == rb_first(blocks))
-				err = ret;
-			goto out;
+			err = ret;
+			break;
 		}
 	}
 out:
@@ -4097,12 +4117,6 @@ restart:
 		if (!RB_EMPTY_ROOT(&blocks)) {
 			ret = relocate_tree_blocks(trans, rc, &blocks);
 			if (ret < 0) {
-				/*
-				 * if we fail to relocate tree blocks, force to update
-				 * backref cache when committing transaction.
-				 */
-				rc->backref_cache.last_trans = trans->transid - 1;
-
 				if (ret != -EAGAIN) {
 					err = ret;
 					break;
@@ -4554,6 +4568,7 @@ int btrfs_recover_relocation(struct btrfs_root *root)
 		if (IS_ERR(fs_root)) {
 			err = PTR_ERR(fs_root);
 			list_add_tail(&reloc_root->root_list, &reloc_roots);
+			btrfs_end_transaction(trans);
 			goto out_free;
 		}
 
@@ -4668,11 +4683,6 @@ int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans,
 	BUG_ON(rc->stage == UPDATE_DATA_PTRS &&
 	       root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID);
 
-	if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) {
-		if (buf == root->node)
-			__update_reloc_root(root, cow->start);
-	}
-
 	level = btrfs_header_level(buf);
 	if (btrfs_header_generation(buf) <=
 	    btrfs_root_last_snapshot(&root->root_item))
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 22124122728c..24a581030840 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -374,11 +374,13 @@ again:
 		leaf = path->nodes[0];
 		ref = btrfs_item_ptr(leaf, path->slots[0],
 				     struct btrfs_root_ref);
-
-		WARN_ON(btrfs_root_ref_dirid(leaf, ref) != dirid);
-		WARN_ON(btrfs_root_ref_name_len(leaf, ref) != name_len);
 		ptr = (unsigned long)(ref + 1);
-		WARN_ON(memcmp_extent_buffer(leaf, name, ptr, name_len));
+		if ((btrfs_root_ref_dirid(leaf, ref) != dirid) ||
+		    (btrfs_root_ref_name_len(leaf, ref) != name_len) ||
+		    memcmp_extent_buffer(leaf, name, ptr, name_len)) {
+			err = -ENOENT;
+			goto out;
+		}
 		*sequence = btrfs_root_ref_sequence(leaf, ref);
 
 		ret = btrfs_del_item(trans, tree_root, path);
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index b9a953356e8d..ba4247349ed4 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -596,8 +596,8 @@ static noinline_for_stack struct scrub_ctx *scrub_setup_ctx(
 		sbio->index = i;
 		sbio->sctx = sctx;
 		sbio->page_count = 0;
-		btrfs_init_work(&sbio->work, btrfs_scrub_helper,
-				scrub_bio_end_io_worker, NULL, NULL);
+		btrfs_init_work(&sbio->work, scrub_bio_end_io_worker, NULL,
+				NULL);
 
 		if (i != SCRUB_BIOS_PER_SCTX - 1)
 			sctx->bios[i]->next_free = i + 1;
@@ -1718,8 +1718,7 @@ static void scrub_wr_bio_end_io(struct bio *bio)
 	sbio->status = bio->bi_status;
 	sbio->bio = bio;
 
-	btrfs_init_work(&sbio->work, btrfs_scrubwrc_helper,
-			 scrub_wr_bio_end_io_worker, NULL, NULL);
+	btrfs_init_work(&sbio->work, scrub_wr_bio_end_io_worker, NULL, NULL);
 	btrfs_queue_work(fs_info->scrub_wr_completion_workers, &sbio->work);
 }
 
@@ -2190,8 +2189,7 @@ static void scrub_missing_raid56_pages(struct scrub_block *sblock)
 		raid56_add_scrub_pages(rbio, spage->page, spage->logical);
 	}
 
-	btrfs_init_work(&sblock->work, btrfs_scrub_helper,
-			scrub_missing_raid56_worker, NULL, NULL);
+	btrfs_init_work(&sblock->work, scrub_missing_raid56_worker, NULL, NULL);
 	scrub_block_get(sblock);
 	scrub_pending_bio_inc(sctx);
 	raid56_submit_missing_rbio(rbio);
@@ -2729,8 +2727,8 @@ static void scrub_parity_bio_endio(struct bio *bio)
 
 	bio_put(bio);
 
-	btrfs_init_work(&sparity->work, btrfs_scrubparity_helper,
-			scrub_parity_bio_endio_worker, NULL, NULL);
+	btrfs_init_work(&sparity->work, scrub_parity_bio_endio_worker, NULL,
+			NULL);
 	btrfs_queue_work(fs_info->scrub_parity_workers, &sparity->work);
 }
 
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 5031ad789f49..577a3a6e5bed 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -23,6 +23,7 @@
 #include "btrfs_inode.h"
 #include "transaction.h"
 #include "compression.h"
+#include "xattr.h"
 
 /*
  * Maximum number of references an extent can have in order for us to attempt to
@@ -4521,6 +4522,10 @@ static int __process_new_xattr(int num, struct btrfs_key *di_key,
 	struct fs_path *p;
 	struct posix_acl_xattr_header dummy_acl;
 
+	/* Capabilities are emitted by finish_inode_if_needed */
+	if (!strncmp(name, XATTR_NAME_CAPS, name_len))
+		return 0;
+
 	p = fs_path_alloc();
 	if (!p)
 		return -ENOMEM;
@@ -5083,6 +5088,64 @@ static int send_extent_data(struct send_ctx *sctx,
 	return 0;
 }
 
+/*
+ * Search for a capability xattr related to sctx->cur_ino. If the capability is
+ * found, call send_set_xattr function to emit it.
+ *
+ * Return 0 if there isn't a capability, or when the capability was emitted
+ * successfully, or < 0 if an error occurred.
+ */
+static int send_capabilities(struct send_ctx *sctx)
+{
+	struct fs_path *fspath = NULL;
+	struct btrfs_path *path;
+	struct btrfs_dir_item *di;
+	struct extent_buffer *leaf;
+	unsigned long data_ptr;
+	char *buf = NULL;
+	int buf_len;
+	int ret = 0;
+
+	path = alloc_path_for_send();
+	if (!path)
+		return -ENOMEM;
+
+	di = btrfs_lookup_xattr(NULL, sctx->send_root, path, sctx->cur_ino,
+				XATTR_NAME_CAPS, strlen(XATTR_NAME_CAPS), 0);
+	if (!di) {
+		/* There is no xattr for this inode */
+		goto out;
+	} else if (IS_ERR(di)) {
+		ret = PTR_ERR(di);
+		goto out;
+	}
+
+	leaf = path->nodes[0];
+	buf_len = btrfs_dir_data_len(leaf, di);
+
+	fspath = fs_path_alloc();
+	buf = kmalloc(buf_len, GFP_KERNEL);
+	if (!fspath || !buf) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen, fspath);
+	if (ret < 0)
+		goto out;
+
+	data_ptr = (unsigned long)(di + 1) + btrfs_dir_name_len(leaf, di);
+	read_extent_buffer(leaf, buf, data_ptr, buf_len);
+
+	ret = send_set_xattr(sctx, fspath, XATTR_NAME_CAPS,
+			strlen(XATTR_NAME_CAPS), buf, buf_len);
+out:
+	kfree(buf);
+	fs_path_free(fspath);
+	btrfs_free_path(path);
+	return ret;
+}
+
 static int clone_range(struct send_ctx *sctx,
 		       struct clone_root *clone_root,
 		       const u64 disk_byte,
@@ -5986,6 +6049,10 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end)
 			goto out;
 	}
 
+	ret = send_capabilities(sctx);
+	if (ret < 0)
+		goto out;
+
 	/*
 	 * If other directory inodes depended on our current directory
 	 * inode's move/rename, now do their move/rename operations.
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 0645ec428b4f..0050eb146b96 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -432,6 +432,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 	char *compress_type;
 	bool compress_force = false;
 	enum btrfs_compression_type saved_compress_type;
+	int saved_compress_level;
 	bool saved_compress_force;
 	int no_compress = 0;
 
@@ -514,6 +515,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 				info->compress_type : BTRFS_COMPRESS_NONE;
 			saved_compress_force =
 				btrfs_test_opt(info, FORCE_COMPRESS);
+			saved_compress_level = info->compress_level;
 			if (token == Opt_compress ||
 			    token == Opt_compress_force ||
 			    strncmp(args[0].from, "zlib", 4) == 0) {
@@ -558,6 +560,8 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 				no_compress = 0;
 			} else if (strncmp(args[0].from, "no", 2) == 0) {
 				compress_type = "no";
+				info->compress_level = 0;
+				info->compress_type = 0;
 				btrfs_clear_opt(info->mount_opt, COMPRESS);
 				btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
 				compress_force = false;
@@ -578,11 +582,11 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 				 */
 				btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
 			}
-			if ((btrfs_test_opt(info, COMPRESS) &&
-			     (info->compress_type != saved_compress_type ||
-			      compress_force != saved_compress_force)) ||
-			    (!btrfs_test_opt(info, COMPRESS) &&
-			     no_compress == 1)) {
+			if (no_compress == 1) {
+				btrfs_info(info, "use no compression");
+			} else if ((info->compress_type != saved_compress_type) ||
+				   (compress_force != saved_compress_force) ||
+				   (info->compress_level != saved_compress_level)) {
 				btrfs_info(info, "%s %s compression, level %d",
 					   (compress_force) ? "force" : "use",
 					   compress_type, info->compress_level);
@@ -1803,6 +1807,8 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 		}
 
 		if (btrfs_super_log_root(fs_info->super_copy) != 0) {
+			btrfs_warn(fs_info,
+		"mount required to replay tree-log, cannot remount read-write");
 			ret = -EINVAL;
 			goto restore;
 		}
@@ -2113,7 +2119,15 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	 */
 	thresh = SZ_4M;
 
-	if (!mixed && total_free_meta - thresh < block_rsv->size)
+	/*
+	 * We only want to claim there's no available space if we can no longer
+	 * allocate chunks for our metadata profile and our global reserve will
+	 * not fit in the free metadata space.  If we aren't ->full then we
+	 * still can allocate chunks and thus are fine using the currently
+	 * calculated f_bavail.
+	 */
+	if (!mixed && block_rsv->space_info->full &&
+	    total_free_meta - thresh < block_rsv->size)
 		buf->f_bavail = 0;
 
 	buf->f_type = BTRFS_SUPER_MAGIC;
@@ -2255,9 +2269,7 @@ static int btrfs_unfreeze(struct super_block *sb)
 static int btrfs_show_devname(struct seq_file *m, struct dentry *root)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(root->d_sb);
-	struct btrfs_fs_devices *cur_devices;
 	struct btrfs_device *dev, *first_dev = NULL;
-	struct list_head *head;
 
 	/*
 	 * Lightweight locking of the devices. We should not need
@@ -2267,18 +2279,13 @@ static int btrfs_show_devname(struct seq_file *m, struct dentry *root)
 	 * least until the rcu_read_unlock.
 	 */
 	rcu_read_lock();
-	cur_devices = fs_info->fs_devices;
-	while (cur_devices) {
-		head = &cur_devices->devices;
-		list_for_each_entry_rcu(dev, head, dev_list) {
-			if (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state))
-				continue;
-			if (!dev->name)
-				continue;
-			if (!first_dev || dev->devid < first_dev->devid)
-				first_dev = dev;
-		}
-		cur_devices = cur_devices->seed;
+	list_for_each_entry_rcu(dev, &fs_info->fs_devices->devices, dev_list) {
+		if (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state))
+			continue;
+		if (!dev->name)
+			continue;
+		if (!first_dev || dev->devid < first_dev->devid)
+			first_dev = dev;
 	}
 
 	if (first_dev)
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index 41f41540382e..69971540797e 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -117,7 +117,6 @@ struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(u32 nodesize, u32 sectorsize)
 	spin_lock_init(&fs_info->qgroup_lock);
 	spin_lock_init(&fs_info->super_lock);
 	spin_lock_init(&fs_info->fs_roots_radix_lock);
-	spin_lock_init(&fs_info->tree_mod_seq_lock);
 	mutex_init(&fs_info->qgroup_ioctl_lock);
 	mutex_init(&fs_info->qgroup_rescan_lock);
 	rwlock_init(&fs_info->tree_mod_log_lock);
diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c
index 7bf4d5734dbe..b9c7a92bd1cc 100644
--- a/fs/btrfs/tests/extent-io-tests.c
+++ b/fs/btrfs/tests/extent-io-tests.c
@@ -432,6 +432,114 @@ out:
 	return ret;
 }
 
+static int test_find_first_clear_extent_bit(void)
+{
+	struct extent_io_tree tree;
+	u64 start, end;
+	int ret = -EINVAL;
+
+	test_msg("running find_first_clear_extent_bit test");
+
+	extent_io_tree_init(NULL, &tree, IO_TREE_SELFTEST, NULL);
+
+	/* Test correct handling of empty tree */
+	find_first_clear_extent_bit(&tree, 0, &start, &end, CHUNK_TRIMMED);
+	if (start != 0 || end != -1) {
+		test_err(
+	"error getting a range from completely empty tree: start %llu end %llu",
+			 start, end);
+		goto out;
+	}
+	/*
+	 * Set 1M-4M alloc/discard and 32M-64M thus leaving a hole between
+	 * 4M-32M
+	 */
+	set_extent_bits(&tree, SZ_1M, SZ_4M - 1,
+			CHUNK_TRIMMED | CHUNK_ALLOCATED);
+
+	find_first_clear_extent_bit(&tree, SZ_512K, &start, &end,
+				    CHUNK_TRIMMED | CHUNK_ALLOCATED);
+
+	if (start != 0 || end != SZ_1M - 1) {
+		test_err("error finding beginning range: start %llu end %llu",
+			 start, end);
+		goto out;
+	}
+
+	/* Now add 32M-64M so that we have a hole between 4M-32M */
+	set_extent_bits(&tree, SZ_32M, SZ_64M - 1,
+			CHUNK_TRIMMED | CHUNK_ALLOCATED);
+
+	/*
+	 * Request first hole starting at 12M, we should get 4M-32M
+	 */
+	find_first_clear_extent_bit(&tree, 12 * SZ_1M, &start, &end,
+				    CHUNK_TRIMMED | CHUNK_ALLOCATED);
+
+	if (start != SZ_4M || end != SZ_32M - 1) {
+		test_err("error finding trimmed range: start %llu end %llu",
+			 start, end);
+		goto out;
+	}
+
+	/*
+	 * Search in the middle of allocated range, should get the next one
+	 * available, which happens to be unallocated -> 4M-32M
+	 */
+	find_first_clear_extent_bit(&tree, SZ_2M, &start, &end,
+				    CHUNK_TRIMMED | CHUNK_ALLOCATED);
+
+	if (start != SZ_4M || end != SZ_32M - 1) {
+		test_err("error finding next unalloc range: start %llu end %llu",
+			 start, end);
+		goto out;
+	}
+
+	/*
+	 * Set 64M-72M with CHUNK_ALLOC flag, then search for CHUNK_TRIMMED flag
+	 * being unset in this range, we should get the entry in range 64M-72M
+	 */
+	set_extent_bits(&tree, SZ_64M, SZ_64M + SZ_8M - 1, CHUNK_ALLOCATED);
+	find_first_clear_extent_bit(&tree, SZ_64M + SZ_1M, &start, &end,
+				    CHUNK_TRIMMED);
+
+	if (start != SZ_64M || end != SZ_64M + SZ_8M - 1) {
+		test_err("error finding exact range: start %llu end %llu",
+			 start, end);
+		goto out;
+	}
+
+	find_first_clear_extent_bit(&tree, SZ_64M - SZ_8M, &start, &end,
+				    CHUNK_TRIMMED);
+
+	/*
+	 * Search in the middle of set range whose immediate neighbour doesn't
+	 * have the bits set so it must be returned
+	 */
+	if (start != SZ_64M || end != SZ_64M + SZ_8M - 1) {
+		test_err("error finding next alloc range: start %llu end %llu",
+			 start, end);
+		goto out;
+	}
+
+	/*
+	 * Search beyond any known range, shall return after last known range
+	 * and end should be -1
+	 */
+	find_first_clear_extent_bit(&tree, -1, &start, &end, CHUNK_TRIMMED);
+	if (start != SZ_64M + SZ_8M || end != -1) {
+		test_err(
+		"error handling beyond end of range search: start %llu end %llu",
+			start, end);
+		goto out;
+	}
+
+	ret = 0;
+out:
+	clear_extent_bits(&tree, 0, (u64)-1, CHUNK_TRIMMED | CHUNK_ALLOCATED);
+	return ret;
+}
+
 int btrfs_test_extent_io(u32 sectorsize, u32 nodesize)
 {
 	int ret;
@@ -442,6 +550,10 @@ int btrfs_test_extent_io(u32 sectorsize, u32 nodesize)
 	if (ret)
 		goto out;
 
+	ret = test_find_first_clear_extent_bit();
+	if (ret)
+		goto out;
+
 	ret = test_eb_bitmaps(sectorsize, nodesize);
 out:
 	return ret;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 2db14fdd6bff..553c6631ba8b 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -49,6 +49,8 @@ void btrfs_put_transaction(struct btrfs_transaction *transaction)
 		BUG_ON(!list_empty(&transaction->list));
 		WARN_ON(!RB_EMPTY_ROOT(
 				&transaction->delayed_refs.href_root.rb_root));
+		WARN_ON(!RB_EMPTY_ROOT(
+				&transaction->delayed_refs.dirty_extent_root));
 		if (transaction->delayed_refs.pending_csums)
 			btrfs_err(transaction->fs_info,
 				  "pending csums is %llu",
@@ -566,10 +568,19 @@ again:
 	}
 
 got_it:
-	btrfs_record_root_in_trans(h, root);
-
 	if (!current->journal_info)
 		current->journal_info = h;
+
+	/*
+	 * btrfs_record_root_in_trans() needs to alloc new extents, and may
+	 * call btrfs_join_transaction() while we're also starting a
+	 * transaction.
+	 *
+	 * Thus it need to be called after current->journal_info initialized,
+	 * or we can deadlock.
+	 */
+	btrfs_record_root_in_trans(h, root);
+
 	return h;
 
 join_fail:
@@ -1929,6 +1940,14 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 	struct btrfs_transaction *prev_trans = NULL;
 	int ret;
 
+	/*
+	 * Some places just start a transaction to commit it.  We need to make
+	 * sure that if this commit fails that the abort code actually marks the
+	 * transaction as failed, so set trans->dirty to make the abort code do
+	 * the right thing.
+	 */
+	trans->dirty = true;
+
 	/* Stop the commit early if ->aborted is set */
 	if (unlikely(READ_ONCE(cur_trans->aborted))) {
 		ret = cur_trans->aborted;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 5c3de2b1a761..e2e361d09959 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3953,7 +3953,7 @@ static int log_csums(struct btrfs_trans_handle *trans,
 static noinline int copy_items(struct btrfs_trans_handle *trans,
 			       struct btrfs_inode *inode,
 			       struct btrfs_path *dst_path,
-			       struct btrfs_path *src_path, u64 *last_extent,
+			       struct btrfs_path *src_path,
 			       int start_slot, int nr, int inode_only,
 			       u64 logged_isize)
 {
@@ -3964,7 +3964,6 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 	struct btrfs_file_extent_item *extent;
 	struct btrfs_inode_item *inode_item;
 	struct extent_buffer *src = src_path->nodes[0];
-	struct btrfs_key first_key, last_key, key;
 	int ret;
 	struct btrfs_key *ins_keys;
 	u32 *ins_sizes;
@@ -3972,9 +3971,6 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 	int i;
 	struct list_head ordered_sums;
 	int skip_csum = inode->flags & BTRFS_INODE_NODATASUM;
-	bool has_extents = false;
-	bool need_find_last_extent = true;
-	bool done = false;
 
 	INIT_LIST_HEAD(&ordered_sums);
 
@@ -3983,8 +3979,6 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 	if (!ins_data)
 		return -ENOMEM;
 
-	first_key.objectid = (u64)-1;
-
 	ins_sizes = (u32 *)ins_data;
 	ins_keys = (struct btrfs_key *)(ins_data + nr * sizeof(u32));
 
@@ -4005,9 +3999,6 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 
 		src_offset = btrfs_item_ptr_offset(src, start_slot + i);
 
-		if (i == nr - 1)
-			last_key = ins_keys[i];
-
 		if (ins_keys[i].type == BTRFS_INODE_ITEM_KEY) {
 			inode_item = btrfs_item_ptr(dst_path->nodes[0],
 						    dst_path->slots[0],
@@ -4021,20 +4012,6 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 					   src_offset, ins_sizes[i]);
 		}
 
-		/*
-		 * We set need_find_last_extent here in case we know we were
-		 * processing other items and then walk into the first extent in
-		 * the inode.  If we don't hit an extent then nothing changes,
-		 * we'll do the last search the next time around.
-		 */
-		if (ins_keys[i].type == BTRFS_EXTENT_DATA_KEY) {
-			has_extents = true;
-			if (first_key.objectid == (u64)-1)
-				first_key = ins_keys[i];
-		} else {
-			need_find_last_extent = false;
-		}
-
 		/* take a reference on file data extents so that truncates
 		 * or deletes of this inode don't have to relog the inode
 		 * again
@@ -4072,11 +4049,8 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 						fs_info->csum_root,
 						ds + cs, ds + cs + cl - 1,
 						&ordered_sums, 0);
-				if (ret) {
-					btrfs_release_path(dst_path);
-					kfree(ins_data);
-					return ret;
-				}
+				if (ret)
+					break;
 			}
 		}
 	}
@@ -4089,7 +4063,6 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 	 * we have to do this after the loop above to avoid changing the
 	 * log tree while trying to change the log tree.
 	 */
-	ret = 0;
 	while (!list_empty(&ordered_sums)) {
 		struct btrfs_ordered_sum *sums = list_entry(ordered_sums.next,
 						   struct btrfs_ordered_sum,
@@ -4100,167 +4073,6 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 		kfree(sums);
 	}
 
-	if (!has_extents)
-		return ret;
-
-	if (need_find_last_extent && *last_extent == first_key.offset) {
-		/*
-		 * We don't have any leafs between our current one and the one
-		 * we processed before that can have file extent items for our
-		 * inode (and have a generation number smaller than our current
-		 * transaction id).
-		 */
-		need_find_last_extent = false;
-	}
-
-	/*
-	 * Because we use btrfs_search_forward we could skip leaves that were
-	 * not modified and then assume *last_extent is valid when it really
-	 * isn't.  So back up to the previous leaf and read the end of the last
-	 * extent before we go and fill in holes.
-	 */
-	if (need_find_last_extent) {
-		u64 len;
-
-		ret = btrfs_prev_leaf(inode->root, src_path);
-		if (ret < 0)
-			return ret;
-		if (ret)
-			goto fill_holes;
-		if (src_path->slots[0])
-			src_path->slots[0]--;
-		src = src_path->nodes[0];
-		btrfs_item_key_to_cpu(src, &key, src_path->slots[0]);
-		if (key.objectid != btrfs_ino(inode) ||
-		    key.type != BTRFS_EXTENT_DATA_KEY)
-			goto fill_holes;
-		extent = btrfs_item_ptr(src, src_path->slots[0],
-					struct btrfs_file_extent_item);
-		if (btrfs_file_extent_type(src, extent) ==
-		    BTRFS_FILE_EXTENT_INLINE) {
-			len = btrfs_file_extent_ram_bytes(src, extent);
-			*last_extent = ALIGN(key.offset + len,
-					     fs_info->sectorsize);
-		} else {
-			len = btrfs_file_extent_num_bytes(src, extent);
-			*last_extent = key.offset + len;
-		}
-	}
-fill_holes:
-	/* So we did prev_leaf, now we need to move to the next leaf, but a few
-	 * things could have happened
-	 *
-	 * 1) A merge could have happened, so we could currently be on a leaf
-	 * that holds what we were copying in the first place.
-	 * 2) A split could have happened, and now not all of the items we want
-	 * are on the same leaf.
-	 *
-	 * So we need to adjust how we search for holes, we need to drop the
-	 * path and re-search for the first extent key we found, and then walk
-	 * forward until we hit the last one we copied.
-	 */
-	if (need_find_last_extent) {
-		/* btrfs_prev_leaf could return 1 without releasing the path */
-		btrfs_release_path(src_path);
-		ret = btrfs_search_slot(NULL, inode->root, &first_key,
-				src_path, 0, 0);
-		if (ret < 0)
-			return ret;
-		ASSERT(ret == 0);
-		src = src_path->nodes[0];
-		i = src_path->slots[0];
-	} else {
-		i = start_slot;
-	}
-
-	/*
-	 * Ok so here we need to go through and fill in any holes we may have
-	 * to make sure that holes are punched for those areas in case they had
-	 * extents previously.
-	 */
-	while (!done) {
-		u64 offset, len;
-		u64 extent_end;
-
-		if (i >= btrfs_header_nritems(src_path->nodes[0])) {
-			ret = btrfs_next_leaf(inode->root, src_path);
-			if (ret < 0)
-				return ret;
-			ASSERT(ret == 0);
-			src = src_path->nodes[0];
-			i = 0;
-			need_find_last_extent = true;
-		}
-
-		btrfs_item_key_to_cpu(src, &key, i);
-		if (!btrfs_comp_cpu_keys(&key, &last_key))
-			done = true;
-		if (key.objectid != btrfs_ino(inode) ||
-		    key.type != BTRFS_EXTENT_DATA_KEY) {
-			i++;
-			continue;
-		}
-		extent = btrfs_item_ptr(src, i, struct btrfs_file_extent_item);
-		if (btrfs_file_extent_type(src, extent) ==
-		    BTRFS_FILE_EXTENT_INLINE) {
-			len = btrfs_file_extent_ram_bytes(src, extent);
-			extent_end = ALIGN(key.offset + len,
-					   fs_info->sectorsize);
-		} else {
-			len = btrfs_file_extent_num_bytes(src, extent);
-			extent_end = key.offset + len;
-		}
-		i++;
-
-		if (*last_extent == key.offset) {
-			*last_extent = extent_end;
-			continue;
-		}
-		offset = *last_extent;
-		len = key.offset - *last_extent;
-		ret = btrfs_insert_file_extent(trans, log, btrfs_ino(inode),
-				offset, 0, 0, len, 0, len, 0, 0, 0);
-		if (ret)
-			break;
-		*last_extent = extent_end;
-	}
-
-	/*
-	 * Check if there is a hole between the last extent found in our leaf
-	 * and the first extent in the next leaf. If there is one, we need to
-	 * log an explicit hole so that at replay time we can punch the hole.
-	 */
-	if (ret == 0 &&
-	    key.objectid == btrfs_ino(inode) &&
-	    key.type == BTRFS_EXTENT_DATA_KEY &&
-	    i == btrfs_header_nritems(src_path->nodes[0])) {
-		ret = btrfs_next_leaf(inode->root, src_path);
-		need_find_last_extent = true;
-		if (ret > 0) {
-			ret = 0;
-		} else if (ret == 0) {
-			btrfs_item_key_to_cpu(src_path->nodes[0], &key,
-					      src_path->slots[0]);
-			if (key.objectid == btrfs_ino(inode) &&
-			    key.type == BTRFS_EXTENT_DATA_KEY &&
-			    *last_extent < key.offset) {
-				const u64 len = key.offset - *last_extent;
-
-				ret = btrfs_insert_file_extent(trans, log,
-							       btrfs_ino(inode),
-							       *last_extent, 0,
-							       0, len, 0, len,
-							       0, 0, 0);
-				*last_extent += len;
-			}
-		}
-	}
-	/*
-	 * Need to let the callers know we dropped the path so they should
-	 * re-search.
-	 */
-	if (!ret && need_find_last_extent)
-		ret = 1;
 	return ret;
 }
 
@@ -4426,7 +4238,10 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
 	const u64 i_size = i_size_read(&inode->vfs_inode);
 	const u64 ino = btrfs_ino(inode);
 	struct btrfs_path *dst_path = NULL;
-	u64 last_extent = (u64)-1;
+	bool dropped_extents = false;
+	u64 truncate_offset = i_size;
+	struct extent_buffer *leaf;
+	int slot;
 	int ins_nr = 0;
 	int start_slot;
 	int ret;
@@ -4441,15 +4256,48 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
 	if (ret < 0)
 		goto out;
 
+	/*
+	 * We must check if there is a prealloc extent that starts before the
+	 * i_size and crosses the i_size boundary. This is to ensure later we
+	 * truncate down to the end of that extent and not to the i_size, as
+	 * otherwise we end up losing part of the prealloc extent after a log
+	 * replay and with an implicit hole if there is another prealloc extent
+	 * that starts at an offset beyond i_size.
+	 */
+	ret = btrfs_previous_item(root, path, ino, BTRFS_EXTENT_DATA_KEY);
+	if (ret < 0)
+		goto out;
+
+	if (ret == 0) {
+		struct btrfs_file_extent_item *ei;
+
+		leaf = path->nodes[0];
+		slot = path->slots[0];
+		ei = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
+
+		if (btrfs_file_extent_type(leaf, ei) ==
+		    BTRFS_FILE_EXTENT_PREALLOC) {
+			u64 extent_end;
+
+			btrfs_item_key_to_cpu(leaf, &key, slot);
+			extent_end = key.offset +
+				btrfs_file_extent_num_bytes(leaf, ei);
+
+			if (extent_end > i_size)
+				truncate_offset = extent_end;
+		}
+	} else {
+		ret = 0;
+	}
+
 	while (true) {
-		struct extent_buffer *leaf = path->nodes[0];
-		int slot = path->slots[0];
+		leaf = path->nodes[0];
+		slot = path->slots[0];
 
 		if (slot >= btrfs_header_nritems(leaf)) {
 			if (ins_nr > 0) {
 				ret = copy_items(trans, inode, dst_path, path,
-						 &last_extent, start_slot,
-						 ins_nr, 1, 0);
+						 start_slot, ins_nr, 1, 0);
 				if (ret < 0)
 					goto out;
 				ins_nr = 0;
@@ -4473,8 +4321,7 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
 			path->slots[0]++;
 			continue;
 		}
-		if (last_extent == (u64)-1) {
-			last_extent = key.offset;
+		if (!dropped_extents) {
 			/*
 			 * Avoid logging extent items logged in past fsync calls
 			 * and leading to duplicate keys in the log tree.
@@ -4483,11 +4330,12 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
 				ret = btrfs_truncate_inode_items(trans,
 							 root->log_root,
 							 &inode->vfs_inode,
-							 i_size,
+							 truncate_offset,
 							 BTRFS_EXTENT_DATA_KEY);
 			} while (ret == -EAGAIN);
 			if (ret)
 				goto out;
+			dropped_extents = true;
 		}
 		if (ins_nr == 0)
 			start_slot = slot;
@@ -4502,7 +4350,7 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
 		}
 	}
 	if (ins_nr > 0) {
-		ret = copy_items(trans, inode, dst_path, path, &last_extent,
+		ret = copy_items(trans, inode, dst_path, path,
 				 start_slot, ins_nr, 1, 0);
 		if (ret > 0)
 			ret = 0;
@@ -4689,13 +4537,8 @@ static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans,
 
 		if (slot >= nritems) {
 			if (ins_nr > 0) {
-				u64 last_extent = 0;
-
 				ret = copy_items(trans, inode, dst_path, path,
-						 &last_extent, start_slot,
-						 ins_nr, 1, 0);
-				/* can't be 1, extent items aren't processed */
-				ASSERT(ret <= 0);
+						 start_slot, ins_nr, 1, 0);
 				if (ret < 0)
 					return ret;
 				ins_nr = 0;
@@ -4719,13 +4562,8 @@ static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans,
 		cond_resched();
 	}
 	if (ins_nr > 0) {
-		u64 last_extent = 0;
-
 		ret = copy_items(trans, inode, dst_path, path,
-				 &last_extent, start_slot,
-				 ins_nr, 1, 0);
-		/* can't be 1, extent items aren't processed */
-		ASSERT(ret <= 0);
+				 start_slot, ins_nr, 1, 0);
 		if (ret < 0)
 			return ret;
 	}
@@ -4734,100 +4572,119 @@ static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans,
 }
 
 /*
- * If the no holes feature is enabled we need to make sure any hole between the
- * last extent and the i_size of our inode is explicitly marked in the log. This
- * is to make sure that doing something like:
- *
- *      1) create file with 128Kb of data
- *      2) truncate file to 64Kb
- *      3) truncate file to 256Kb
- *      4) fsync file
- *      5) <crash/power failure>
- *      6) mount fs and trigger log replay
- *
- * Will give us a file with a size of 256Kb, the first 64Kb of data match what
- * the file had in its first 64Kb of data at step 1 and the last 192Kb of the
- * file correspond to a hole. The presence of explicit holes in a log tree is
- * what guarantees that log replay will remove/adjust file extent items in the
- * fs/subvol tree.
- *
- * Here we do not need to care about holes between extents, that is already done
- * by copy_items(). We also only need to do this in the full sync path, where we
- * lookup for extents from the fs/subvol tree only. In the fast path case, we
- * lookup the list of modified extent maps and if any represents a hole, we
- * insert a corresponding extent representing a hole in the log tree.
+ * When using the NO_HOLES feature if we punched a hole that causes the
+ * deletion of entire leafs or all the extent items of the first leaf (the one
+ * that contains the inode item and references) we may end up not processing
+ * any extents, because there are no leafs with a generation matching the
+ * current transaction that have extent items for our inode. So we need to find
+ * if any holes exist and then log them. We also need to log holes after any
+ * truncate operation that changes the inode's size.
  */
-static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans,
-				   struct btrfs_root *root,
-				   struct btrfs_inode *inode,
-				   struct btrfs_path *path)
+static int btrfs_log_holes(struct btrfs_trans_handle *trans,
+			   struct btrfs_root *root,
+			   struct btrfs_inode *inode,
+			   struct btrfs_path *path)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
-	int ret;
 	struct btrfs_key key;
-	u64 hole_start;
-	u64 hole_size;
-	struct extent_buffer *leaf;
-	struct btrfs_root *log = root->log_root;
 	const u64 ino = btrfs_ino(inode);
 	const u64 i_size = i_size_read(&inode->vfs_inode);
+	u64 prev_extent_end = 0;
+	int ret;
 
-	if (!btrfs_fs_incompat(fs_info, NO_HOLES))
+	if (!btrfs_fs_incompat(fs_info, NO_HOLES) || i_size == 0)
 		return 0;
 
 	key.objectid = ino;
 	key.type = BTRFS_EXTENT_DATA_KEY;
-	key.offset = (u64)-1;
+	key.offset = 0;
 
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
-	ASSERT(ret != 0);
 	if (ret < 0)
 		return ret;
 
-	ASSERT(path->slots[0] > 0);
-	path->slots[0]--;
-	leaf = path->nodes[0];
-	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
-
-	if (key.objectid != ino || key.type != BTRFS_EXTENT_DATA_KEY) {
-		/* inode does not have any extents */
-		hole_start = 0;
-		hole_size = i_size;
-	} else {
+	while (true) {
 		struct btrfs_file_extent_item *extent;
+		struct extent_buffer *leaf = path->nodes[0];
 		u64 len;
 
-		/*
-		 * If there's an extent beyond i_size, an explicit hole was
-		 * already inserted by copy_items().
-		 */
-		if (key.offset >= i_size)
-			return 0;
+		if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
+			ret = btrfs_next_leaf(root, path);
+			if (ret < 0)
+				return ret;
+			if (ret > 0) {
+				ret = 0;
+				break;
+			}
+			leaf = path->nodes[0];
+		}
+
+		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
+		if (key.objectid != ino || key.type != BTRFS_EXTENT_DATA_KEY)
+			break;
+
+		/* We have a hole, log it. */
+		if (prev_extent_end < key.offset) {
+			const u64 hole_len = key.offset - prev_extent_end;
+
+			/*
+			 * Release the path to avoid deadlocks with other code
+			 * paths that search the root while holding locks on
+			 * leafs from the log root.
+			 */
+			btrfs_release_path(path);
+			ret = btrfs_insert_file_extent(trans, root->log_root,
+						       ino, prev_extent_end, 0,
+						       0, hole_len, 0, hole_len,
+						       0, 0, 0);
+			if (ret < 0)
+				return ret;
+
+			/*
+			 * Search for the same key again in the root. Since it's
+			 * an extent item and we are holding the inode lock, the
+			 * key must still exist. If it doesn't just emit warning
+			 * and return an error to fall back to a transaction
+			 * commit.
+			 */
+			ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+			if (ret < 0)
+				return ret;
+			if (WARN_ON(ret > 0))
+				return -ENOENT;
+			leaf = path->nodes[0];
+		}
 
 		extent = btrfs_item_ptr(leaf, path->slots[0],
 					struct btrfs_file_extent_item);
-
 		if (btrfs_file_extent_type(leaf, extent) ==
-		    BTRFS_FILE_EXTENT_INLINE)
-			return 0;
+		    BTRFS_FILE_EXTENT_INLINE) {
+			len = btrfs_file_extent_ram_bytes(leaf, extent);
+			prev_extent_end = ALIGN(key.offset + len,
+						fs_info->sectorsize);
+		} else {
+			len = btrfs_file_extent_num_bytes(leaf, extent);
+			prev_extent_end = key.offset + len;
+		}
 
-		len = btrfs_file_extent_num_bytes(leaf, extent);
-		/* Last extent goes beyond i_size, no need to log a hole. */
-		if (key.offset + len > i_size)
-			return 0;
-		hole_start = key.offset + len;
-		hole_size = i_size - hole_start;
+		path->slots[0]++;
+		cond_resched();
 	}
-	btrfs_release_path(path);
 
-	/* Last extent ends at i_size. */
-	if (hole_size == 0)
-		return 0;
+	if (prev_extent_end < i_size) {
+		u64 hole_len;
 
-	hole_size = ALIGN(hole_size, fs_info->sectorsize);
-	ret = btrfs_insert_file_extent(trans, log, ino, hole_start, 0, 0,
-				       hole_size, 0, hole_size, 0, 0, 0);
-	return ret;
+		btrfs_release_path(path);
+		hole_len = ALIGN(i_size - prev_extent_end, fs_info->sectorsize);
+		ret = btrfs_insert_file_extent(trans, root->log_root,
+					       ino, prev_extent_end, 0, 0,
+					       hole_len, 0, hole_len,
+					       0, 0, 0);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
 }
 
 /*
@@ -5032,6 +4889,50 @@ static int log_conflicting_inodes(struct btrfs_trans_handle *trans,
 			continue;
 		}
 		/*
+		 * If the inode was already logged skip it - otherwise we can
+		 * hit an infinite loop. Example:
+		 *
+		 * From the commit root (previous transaction) we have the
+		 * following inodes:
+		 *
+		 * inode 257 a directory
+		 * inode 258 with references "zz" and "zz_link" on inode 257
+		 * inode 259 with reference "a" on inode 257
+		 *
+		 * And in the current (uncommitted) transaction we have:
+		 *
+		 * inode 257 a directory, unchanged
+		 * inode 258 with references "a" and "a2" on inode 257
+		 * inode 259 with reference "zz_link" on inode 257
+		 * inode 261 with reference "zz" on inode 257
+		 *
+		 * When logging inode 261 the following infinite loop could
+		 * happen if we don't skip already logged inodes:
+		 *
+		 * - we detect inode 258 as a conflicting inode, with inode 261
+		 *   on reference "zz", and log it;
+		 *
+		 * - we detect inode 259 as a conflicting inode, with inode 258
+		 *   on reference "a", and log it;
+		 *
+		 * - we detect inode 258 as a conflicting inode, with inode 259
+		 *   on reference "zz_link", and log it - again! After this we
+		 *   repeat the above steps forever.
+		 */
+		spin_lock(&BTRFS_I(inode)->lock);
+		/*
+		 * Check the inode's logged_trans only instead of
+		 * btrfs_inode_in_log(). This is because the last_log_commit of
+		 * the inode is not updated when we only log that it exists and
+		 * and it has the full sync bit set (see btrfs_log_inode()).
+		 */
+		if (BTRFS_I(inode)->logged_trans == trans->transid) {
+			spin_unlock(&BTRFS_I(inode)->lock);
+			btrfs_add_delayed_iput(inode);
+			continue;
+		}
+		spin_unlock(&BTRFS_I(inode)->lock);
+		/*
 		 * We are safe logging the other inode without acquiring its
 		 * lock as long as we log with the LOG_INODE_EXISTS mode. We
 		 * are safe against concurrent renames of the other inode as
@@ -5130,7 +5031,6 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 	struct btrfs_key min_key;
 	struct btrfs_key max_key;
 	struct btrfs_root *log = root->log_root;
-	u64 last_extent = 0;
 	int err = 0;
 	int ret;
 	int nritems;
@@ -5308,7 +5208,7 @@ again:
 					ins_start_slot = path->slots[0];
 				}
 				ret = copy_items(trans, inode, dst_path, path,
-						 &last_extent, ins_start_slot,
+						 ins_start_slot,
 						 ins_nr, inode_only,
 						 logged_isize);
 				if (ret < 0) {
@@ -5331,17 +5231,13 @@ again:
 			if (ins_nr == 0)
 				goto next_slot;
 			ret = copy_items(trans, inode, dst_path, path,
-					 &last_extent, ins_start_slot,
+					 ins_start_slot,
 					 ins_nr, inode_only, logged_isize);
 			if (ret < 0) {
 				err = ret;
 				goto out_unlock;
 			}
 			ins_nr = 0;
-			if (ret) {
-				btrfs_release_path(path);
-				continue;
-			}
 			goto next_slot;
 		}
 
@@ -5354,18 +5250,13 @@ again:
 			goto next_slot;
 		}
 
-		ret = copy_items(trans, inode, dst_path, path, &last_extent,
+		ret = copy_items(trans, inode, dst_path, path,
 				 ins_start_slot, ins_nr, inode_only,
 				 logged_isize);
 		if (ret < 0) {
 			err = ret;
 			goto out_unlock;
 		}
-		if (ret) {
-			ins_nr = 0;
-			btrfs_release_path(path);
-			continue;
-		}
 		ins_nr = 1;
 		ins_start_slot = path->slots[0];
 next_slot:
@@ -5379,13 +5270,12 @@ next_slot:
 		}
 		if (ins_nr) {
 			ret = copy_items(trans, inode, dst_path, path,
-					 &last_extent, ins_start_slot,
+					 ins_start_slot,
 					 ins_nr, inode_only, logged_isize);
 			if (ret < 0) {
 				err = ret;
 				goto out_unlock;
 			}
-			ret = 0;
 			ins_nr = 0;
 		}
 		btrfs_release_path(path);
@@ -5400,14 +5290,13 @@ next_key:
 		}
 	}
 	if (ins_nr) {
-		ret = copy_items(trans, inode, dst_path, path, &last_extent,
+		ret = copy_items(trans, inode, dst_path, path,
 				 ins_start_slot, ins_nr, inode_only,
 				 logged_isize);
 		if (ret < 0) {
 			err = ret;
 			goto out_unlock;
 		}
-		ret = 0;
 		ins_nr = 0;
 	}
 
@@ -5420,7 +5309,7 @@ next_key:
 	if (max_key.type >= BTRFS_EXTENT_DATA_KEY && !fast_search) {
 		btrfs_release_path(path);
 		btrfs_release_path(dst_path);
-		err = btrfs_log_trailing_hole(trans, root, inode, path);
+		err = btrfs_log_holes(trans, root, inode, path);
 		if (err)
 			goto out_unlock;
 	}
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 4075b1b95105..81edabb2524d 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -216,7 +216,9 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
  *
  * global::fs_devs - add, remove, updates to the global list
  *
- * does not protect: manipulation of the fs_devices::devices list!
+ * does not protect: manipulation of the fs_devices::devices list in general
+ * but in mount context it could be used to exclude list modifications by eg.
+ * scan ioctl
  *
  * btrfs_device::name - renames (write side), read is RCU
  *
@@ -229,6 +231,9 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
  * may be used to exclude some operations from running concurrently without any
  * modifications to the list (see write_all_supers)
  *
+ * Is not required at mount and close times, because our device list is
+ * protected by the uuid_mutex at that point.
+ *
  * balance_mutex
  * -------------
  * protects balance structures (status, state) and context accessed from
@@ -786,6 +791,11 @@ static int btrfs_free_stale_devices(const char *path,
 	return ret;
 }
 
+/*
+ * This is only used on mount, and we are protected from competing things
+ * messing with our fs_devices by the uuid_mutex, thus we do not need the
+ * fs_devices->device_list_mutex here.
+ */
 static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 			struct btrfs_device *device, fmode_t flags,
 			void *holder)
@@ -889,17 +899,54 @@ static struct btrfs_fs_devices *find_fsid_changed(
 	/*
 	 * Handles the case where scanned device is part of an fs that had
 	 * multiple successful changes of FSID but curently device didn't
-	 * observe it. Meaning our fsid will be different than theirs.
+	 * observe it. Meaning our fsid will be different than theirs. We need
+	 * to handle two subcases :
+	 *  1 - The fs still continues to have different METADATA/FSID uuids.
+	 *  2 - The fs is switched back to its original FSID (METADATA/FSID
+	 *  are equal).
 	 */
 	list_for_each_entry(fs_devices, &fs_uuids, fs_list) {
+		/* Changed UUIDs */
 		if (memcmp(fs_devices->metadata_uuid, fs_devices->fsid,
 			   BTRFS_FSID_SIZE) != 0 &&
 		    memcmp(fs_devices->metadata_uuid, disk_super->metadata_uuid,
 			   BTRFS_FSID_SIZE) == 0 &&
 		    memcmp(fs_devices->fsid, disk_super->fsid,
-			   BTRFS_FSID_SIZE) != 0) {
+			   BTRFS_FSID_SIZE) != 0)
+			return fs_devices;
+
+		/* Unchanged UUIDs */
+		if (memcmp(fs_devices->metadata_uuid, fs_devices->fsid,
+			   BTRFS_FSID_SIZE) == 0 &&
+		    memcmp(fs_devices->fsid, disk_super->metadata_uuid,
+			   BTRFS_FSID_SIZE) == 0)
+			return fs_devices;
+	}
+
+	return NULL;
+}
+
+static struct btrfs_fs_devices *find_fsid_reverted_metadata(
+				struct btrfs_super_block *disk_super)
+{
+	struct btrfs_fs_devices *fs_devices;
+
+	/*
+	 * Handle the case where the scanned device is part of an fs whose last
+	 * metadata UUID change reverted it to the original FSID. At the same
+	 * time * fs_devices was first created by another constitutent device
+	 * which didn't fully observe the operation. This results in an
+	 * btrfs_fs_devices created with metadata/fsid different AND
+	 * btrfs_fs_devices::fsid_change set AND the metadata_uuid of the
+	 * fs_devices equal to the FSID of the disk.
+	 */
+	list_for_each_entry(fs_devices, &fs_uuids, fs_list) {
+		if (memcmp(fs_devices->fsid, fs_devices->metadata_uuid,
+			   BTRFS_FSID_SIZE) != 0 &&
+		    memcmp(fs_devices->metadata_uuid, disk_super->fsid,
+			   BTRFS_FSID_SIZE) == 0 &&
+		    fs_devices->fsid_change)
 			return fs_devices;
-		}
 	}
 
 	return NULL;
@@ -943,7 +990,9 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 		fs_devices = find_fsid(disk_super->fsid,
 				       disk_super->metadata_uuid);
 	} else {
-		fs_devices = find_fsid(disk_super->fsid, NULL);
+		fs_devices = find_fsid_reverted_metadata(disk_super);
+		if (!fs_devices)
+			fs_devices = find_fsid(disk_super->fsid, NULL);
 	}
 
 
@@ -973,12 +1022,18 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 		 * a device which had the CHANGING_FSID_V2 flag then replace the
 		 * metadata_uuid/fsid values of the fs_devices.
 		 */
-		if (has_metadata_uuid && fs_devices->fsid_change &&
+		if (fs_devices->fsid_change &&
 		    found_transid > fs_devices->latest_generation) {
 			memcpy(fs_devices->fsid, disk_super->fsid,
 					BTRFS_FSID_SIZE);
-			memcpy(fs_devices->metadata_uuid,
-					disk_super->metadata_uuid, BTRFS_FSID_SIZE);
+
+			if (has_metadata_uuid)
+				memcpy(fs_devices->metadata_uuid,
+				       disk_super->metadata_uuid,
+				       BTRFS_FSID_SIZE);
+			else
+				memcpy(fs_devices->metadata_uuid,
+				       disk_super->fsid, BTRFS_FSID_SIZE);
 
 			fs_devices->fsid_change = false;
 		}
@@ -1182,6 +1237,8 @@ again:
 							&device->dev_state)) {
 			if (!test_bit(BTRFS_DEV_STATE_REPLACE_TGT,
 			     &device->dev_state) &&
+			    !test_bit(BTRFS_DEV_STATE_MISSING,
+				      &device->dev_state) &&
 			     (!latest_dev ||
 			      device->generation > latest_dev->generation)) {
 				latest_dev = device;
@@ -1375,8 +1432,14 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 	int ret;
 
 	lockdep_assert_held(&uuid_mutex);
+	/*
+	 * The device_list_mutex cannot be taken here in case opening the
+	 * underlying device takes further locks like bd_mutex.
+	 *
+	 * We also don't need the lock here as this is called during mount and
+	 * exclusion is provided by uuid_mutex
+	 */
 
-	mutex_lock(&fs_devices->device_list_mutex);
 	if (fs_devices->opened) {
 		fs_devices->opened++;
 		ret = 0;
@@ -1384,7 +1447,6 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 		list_sort(NULL, &fs_devices->devices, devid_cmp);
 		ret = open_fs_devices(fs_devices, flags, holder);
 	}
-	mutex_unlock(&fs_devices->device_list_mutex);
 
 	return ret;
 }
@@ -4079,7 +4141,11 @@ int btrfs_balance(struct btrfs_fs_info *fs_info,
 		}
 	}
 
-	num_devices = btrfs_num_devices(fs_info);
+	/*
+	 * rw_devices will not change at the moment, device add/delete/replace
+	 * are excluded by EXCL_OP
+	 */
+	num_devices = fs_info->fs_devices->rw_devices;
 
 	allowed = BTRFS_AVAIL_ALLOC_BIT_SINGLE | BTRFS_BLOCK_GROUP_DUP;
 	if (num_devices > 1)
@@ -6649,8 +6715,7 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
 	else
 		generate_random_uuid(dev->uuid);
 
-	btrfs_init_work(&dev->work, btrfs_submit_helper,
-			pending_bios_fn, NULL, NULL);
+	btrfs_init_work(&dev->work, pending_bios_fn, NULL, NULL);
 
 	return dev;
 }
@@ -7180,7 +7245,14 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info)
 	 * otherwise we don't need it.
 	 */
 	mutex_lock(&uuid_mutex);
-	mutex_lock(&fs_info->chunk_mutex);
+
+	/*
+	 * It is possible for mount and umount to race in such a way that
+	 * we execute this code path, but open_fs_devices failed to clear
+	 * total_rw_bytes. We certainly want it cleared before reading the
+	 * device items, so clear it here.
+	 */
+	fs_info->fs_devices->total_rw_bytes = 0;
 
 	/*
 	 * Read all device items, and then all the chunk items. All
@@ -7217,7 +7289,9 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info)
 		} else if (found_key.type == BTRFS_CHUNK_ITEM_KEY) {
 			struct btrfs_chunk *chunk;
 			chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk);
+			mutex_lock(&fs_info->chunk_mutex);
 			ret = read_one_chunk(&found_key, leaf, chunk);
+			mutex_unlock(&fs_info->chunk_mutex);
 			if (ret)
 				goto error;
 		}
@@ -7247,7 +7321,6 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info)
 	}
 	ret = 0;
 error:
-	mutex_unlock(&fs_info->chunk_mutex);
 	mutex_unlock(&uuid_mutex);
 
 	btrfs_free_path(path);
@@ -7509,6 +7582,8 @@ int btrfs_get_dev_stats(struct btrfs_fs_info *fs_info,
 			else
 				btrfs_dev_stat_reset(dev, i);
 		}
+		btrfs_info(fs_info, "device stats zeroed by %s (%d)",
+			   current->comm, task_pid_nr(current));
 	} else {
 		for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++)
 			if (stats->nr_items > i)
diff --git a/fs/buffer.c b/fs/buffer.c
index e450c55f6434..3a4b88555ca1 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1337,6 +1337,17 @@ void __breadahead(struct block_device *bdev, sector_t block, unsigned size)
 }
 EXPORT_SYMBOL(__breadahead);
 
+void __breadahead_gfp(struct block_device *bdev, sector_t block, unsigned size,
+		      gfp_t gfp)
+{
+	struct buffer_head *bh = __getblk_gfp(bdev, block, size, gfp);
+	if (likely(bh)) {
+		ll_rw_block(REQ_OP_READ, REQ_RAHEAD, 1, &bh);
+		brelse(bh);
+	}
+}
+EXPORT_SYMBOL(__breadahead_gfp);
+
 /**
  *  __bread_gfp() - reads a specified block and returns the bh
  *  @bdev: the block_device to read from
@@ -2995,11 +3006,9 @@ static void end_bio_bh_io_sync(struct bio *bio)
  * errors, this only handles the "we need to be able to
  * do IO at the final sector" case.
  */
-void guard_bio_eod(int op, struct bio *bio)
+void guard_bio_eod(struct bio *bio)
 {
 	sector_t maxsector;
-	struct bio_vec *bvec = bio_last_bvec_all(bio);
-	unsigned truncated_bytes;
 	struct hd_struct *part;
 
 	rcu_read_lock();
@@ -3025,28 +3034,7 @@ void guard_bio_eod(int op, struct bio *bio)
 	if (likely((bio->bi_iter.bi_size >> 9) <= maxsector))
 		return;
 
-	/* Uhhuh. We've got a bio that straddles the device size! */
-	truncated_bytes = bio->bi_iter.bi_size - (maxsector << 9);
-
-	/*
-	 * The bio contains more than one segment which spans EOD, just return
-	 * and let IO layer turn it into an EIO
-	 */
-	if (truncated_bytes > bvec->bv_len)
-		return;
-
-	/* Truncate the bio.. */
-	bio->bi_iter.bi_size -= truncated_bytes;
-	bvec->bv_len -= truncated_bytes;
-
-	/* ..and clear the end of the buffer for reads */
-	if (op == REQ_OP_READ) {
-		struct bio_vec bv;
-
-		mp_bvec_last_segment(bvec, &bv);
-		zero_user(bv.bv_page, bv.bv_offset + bv.bv_len,
-				truncated_bytes);
-	}
+	bio_truncate(bio, maxsector << 9);
 }
 
 static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
@@ -3082,15 +3070,15 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
 	bio->bi_end_io = end_bio_bh_io_sync;
 	bio->bi_private = bh;
 
-	/* Take care of bh's that straddle the end of the device */
-	guard_bio_eod(op, bio);
-
 	if (buffer_meta(bh))
 		op_flags |= REQ_META;
 	if (buffer_prio(bh))
 		op_flags |= REQ_PRIO;
 	bio_set_op_attrs(bio, op, op_flags);
 
+	/* Take care of bh's that straddle the end of the device */
+	guard_bio_eod(bio);
+
 	if (wbc) {
 		wbc_init_bio(wbc, bio);
 		wbc_account_io(wbc, bh->b_page, bh->b_size);
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index 44a3ce1e4ce4..ad057ed2b30b 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -60,9 +60,9 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode,
 	object = container_of(op->op.object, struct cachefiles_object, fscache);
 	spin_lock(&object->work_lock);
 	list_add_tail(&monitor->op_link, &op->to_do);
+	fscache_enqueue_retrieval(op);
 	spin_unlock(&object->work_lock);
 
-	fscache_enqueue_retrieval(op);
 	fscache_put_retrieval(op);
 	return 0;
 }
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 2c577bca577c..9e06a42fa672 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2005,8 +2005,12 @@ retry_locked:
 		}
 
 		/* want more caps from mds? */
-		if (want & ~(cap->mds_wanted | cap->issued))
-			goto ack;
+		if (want & ~cap->mds_wanted) {
+			if (want & ~(cap->mds_wanted | cap->issued))
+				goto ack;
+			if (!__cap_is_valid(cap))
+				goto ack;
+		}
 
 		/* things we might delay */
 		if ((cap->issued & ~retain) == 0)
@@ -3661,6 +3665,7 @@ retry:
 		WARN_ON(1);
 		tsession = NULL;
 		target = -1;
+		mutex_lock(&session->s_mutex);
 	}
 	goto retry;
 
@@ -3903,7 +3908,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 			__ceph_queue_cap_release(session, cap);
 			spin_unlock(&session->s_cap_lock);
 		}
-		goto done;
+		goto flush_cap_releases;
 	}
 
 	/* these will work even if we don't have a cap yet */
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index d3ef7ee429ec..8982e0c2c6a5 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -172,9 +172,16 @@ struct inode *ceph_lookup_inode(struct super_block *sb, u64 ino)
 static struct dentry *__fh_to_dentry(struct super_block *sb, u64 ino)
 {
 	struct inode *inode = __lookup_inode(sb, ino);
+	int err;
+
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
-	if (inode->i_nlink == 0) {
+	/* We need LINK caps to reliably check i_nlink */
+	err = ceph_do_getattr(inode, CEPH_CAP_LINK_SHARED, false);
+	if (err)
+		return ERR_PTR(err);
+	/* -ESTALE if inode as been unlinked and no file is open */
+	if ((inode->i_nlink == 0) && (atomic_read(&inode->i_count) == 1)) {
 		iput(inode);
 		return ERR_PTR(-ESTALE);
 	}
@@ -315,6 +322,11 @@ static struct dentry *__get_parent(struct super_block *sb,
 
 	req->r_num_caps = 1;
 	err = ceph_mdsc_do_request(mdsc, NULL, req);
+	if (err) {
+		ceph_mdsc_put_request(req);
+		return ERR_PTR(err);
+	}
+
 	inode = req->r_target_inode;
 	if (inode)
 		ihold(inode);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 8eb5f973744f..2595052d5eef 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1384,9 +1384,12 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_osd_client *osdc = &fsc->client->osdc;
 	struct ceph_cap_flush *prealloc_cf;
 	ssize_t count, written = 0;
 	int err, want, got;
+	u32 map_flags;
+	u64 pool_flags;
 	loff_t pos;
 	loff_t limit = max(i_size_read(inode), fsc->max_file_size);
 
@@ -1441,8 +1444,12 @@ retry_snap:
 			goto out;
 	}
 
-	/* FIXME: not complete since it doesn't account for being at quota */
-	if (ceph_osdmap_flag(&fsc->client->osdc, CEPH_OSDMAP_FULL)) {
+	down_read(&osdc->lock);
+	map_flags = osdc->osdmap->flags;
+	pool_flags = ceph_pg_pool_flags(osdc->osdmap, ci->i_layout.pool_id);
+	up_read(&osdc->lock);
+	if ((map_flags & CEPH_OSDMAP_FULL) ||
+	    (pool_flags & CEPH_POOL_FLAG_FULL)) {
 		err = -ENOSPC;
 		goto out;
 	}
@@ -1532,7 +1539,8 @@ retry_snap:
 	}
 
 	if (written >= 0) {
-		if (ceph_osdmap_flag(&fsc->client->osdc, CEPH_OSDMAP_NEARFULL))
+		if ((map_flags & CEPH_OSDMAP_NEARFULL) ||
+		    (pool_flags & CEPH_POOL_FLAG_NEARFULL))
 			iocb->ki_flags |= IOCB_DSYNC;
 		written = generic_write_sync(iocb, written);
 	}
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index ef58306df674..6eddc935d8ce 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -694,8 +694,10 @@ void ceph_mdsc_release_request(struct kref *kref)
 		/* avoid calling iput_final() in mds dispatch threads */
 		ceph_async_iput(req->r_inode);
 	}
-	if (req->r_parent)
+	if (req->r_parent) {
 		ceph_put_cap_refs(ceph_inode(req->r_parent), CEPH_CAP_PIN);
+		ceph_async_iput(req->r_parent);
+	}
 	ceph_async_iput(req->r_target_inode);
 	if (req->r_dentry)
 		dput(req->r_dentry);
@@ -2518,8 +2520,7 @@ static void __do_request(struct ceph_mds_client *mdsc,
 		if (!(mdsc->fsc->mount_options->flags &
 		      CEPH_MOUNT_OPT_MOUNTWAIT) &&
 		    !ceph_mdsmap_is_cluster_available(mdsc->mdsmap)) {
-			err = -ENOENT;
-			pr_info("probably no mds server is up\n");
+			err = -EHOSTUNREACH;
 			goto finish;
 		}
 	}
@@ -2638,8 +2639,10 @@ int ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, struct inode *dir,
 	/* take CAP_PIN refs for r_inode, r_parent, r_old_dentry */
 	if (req->r_inode)
 		ceph_get_cap_refs(ceph_inode(req->r_inode), CEPH_CAP_PIN);
-	if (req->r_parent)
+	if (req->r_parent) {
 		ceph_get_cap_refs(ceph_inode(req->r_parent), CEPH_CAP_PIN);
+		ihold(req->r_parent);
+	}
 	if (req->r_old_dentry_dir)
 		ceph_get_cap_refs(ceph_inode(req->r_old_dentry_dir),
 				  CEPH_CAP_PIN);
@@ -3032,8 +3035,7 @@ static void handle_session(struct ceph_mds_session *session,
 	void *end = p + msg->front.iov_len;
 	struct ceph_mds_session_head *h;
 	u32 op;
-	u64 seq;
-	unsigned long features = 0;
+	u64 seq, features = 0;
 	int wake = 0;
 
 	/* decode */
@@ -3051,9 +3053,10 @@ static void handle_session(struct ceph_mds_session *session,
 			goto bad;
 		/* version >= 3, feature bits */
 		ceph_decode_32_safe(&p, end, len, bad);
-		ceph_decode_need(&p, end, len, bad);
-		memcpy(&features, p, min_t(size_t, len, sizeof(features)));
-		p += len;
+		if (len) {
+			ceph_decode_64_safe(&p, end, features, bad);
+			p += len - sizeof(features);
+		}
 	}
 
 	mutex_lock(&mdsc->mutex);
diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c
index d629fc857450..8534920aefa7 100644
--- a/fs/ceph/quota.c
+++ b/fs/ceph/quota.c
@@ -148,8 +148,8 @@ static struct inode *lookup_quotarealm_inode(struct ceph_mds_client *mdsc,
 	}
 	in = ceph_lookup_inode(sb, realm->ino);
 	if (IS_ERR(in)) {
-		pr_warn("Can't lookup inode %llx (err: %ld)\n",
-			realm->ino, PTR_ERR(in));
+		dout("Can't lookup inode %llx (err: %ld)\n",
+		     realm->ino, PTR_ERR(in));
 		qri->timeout = jiffies + msecs_to_jiffies(60 * 1000); /* XXX */
 	} else {
 		qri->timeout = 0;
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 213bc1475e91..e630762175a4 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -1152,5 +1152,6 @@ void ceph_cleanup_snapid_map(struct ceph_mds_client *mdsc)
 			pr_err("snapid map %llx -> %x still in use\n",
 			       sm->snap, sm->dev);
 		}
+		kfree(sm);
 	}
 }
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 4ce55e0a14da..e7b2f6038428 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -106,7 +106,6 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
 	return 0;
 }
 
-
 static int ceph_sync_fs(struct super_block *sb, int wait)
 {
 	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
@@ -213,6 +212,26 @@ static match_table_t fsopt_tokens = {
 	{-1, NULL}
 };
 
+/*
+ * Remove adjacent slashes and then the trailing slash, unless it is
+ * the only remaining character.
+ *
+ * E.g. "//dir1////dir2///" --> "/dir1/dir2", "///" --> "/".
+ */
+static void canonicalize_path(char *path)
+{
+	int i, j = 0;
+
+	for (i = 0; path[i] != '\0'; i++) {
+		if (path[i] != '/' || j < 1 || path[j - 1] != '/')
+			path[j++] = path[i];
+	}
+
+	if (j > 1 && path[j - 1] == '/')
+		j--;
+	path[j] = '\0';
+}
+
 static int parse_fsopt_token(char *c, void *private)
 {
 	struct ceph_mount_options *fsopt = private;
@@ -433,12 +452,15 @@ static int compare_mount_options(struct ceph_mount_options *new_fsopt,
 	ret = strcmp_null(fsopt1->snapdir_name, fsopt2->snapdir_name);
 	if (ret)
 		return ret;
+
 	ret = strcmp_null(fsopt1->mds_namespace, fsopt2->mds_namespace);
 	if (ret)
 		return ret;
+
 	ret = strcmp_null(fsopt1->server_path, fsopt2->server_path);
 	if (ret)
 		return ret;
+
 	ret = strcmp_null(fsopt1->fscache_uniq, fsopt2->fscache_uniq);
 	if (ret)
 		return ret;
@@ -494,13 +516,17 @@ static int parse_mount_options(struct ceph_mount_options **pfsopt,
 	 */
 	dev_name_end = strchr(dev_name, '/');
 	if (dev_name_end) {
-		if (strlen(dev_name_end) > 1) {
-			fsopt->server_path = kstrdup(dev_name_end, GFP_KERNEL);
-			if (!fsopt->server_path) {
-				err = -ENOMEM;
-				goto out;
-			}
+		/*
+		 * The server_path will include the whole chars from userland
+		 * including the leading '/'.
+		 */
+		fsopt->server_path = kstrdup(dev_name_end, GFP_KERNEL);
+		if (!fsopt->server_path) {
+			err = -ENOMEM;
+			goto out;
 		}
+
+		canonicalize_path(fsopt->server_path);
 	} else {
 		dev_name_end = dev_name + strlen(dev_name);
 	}
@@ -823,7 +849,6 @@ static void destroy_caches(void)
 	ceph_fscache_unregister();
 }
 
-
 /*
  * ceph_umount_begin - initiate forced umount.  Tear down down the
  * mount, skipping steps that may hang while waiting for server(s).
@@ -910,9 +935,6 @@ out:
 	return root;
 }
 
-
-
-
 /*
  * mount: join the ceph cluster, and open root directory.
  */
@@ -926,7 +948,9 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc)
 	mutex_lock(&fsc->client->mount_mutex);
 
 	if (!fsc->sb->s_root) {
-		const char *path;
+		const char *path = fsc->mount_options->server_path ?
+				     fsc->mount_options->server_path + 1 : "";
+
 		err = __ceph_open_session(fsc->client, started);
 		if (err < 0)
 			goto out;
@@ -938,13 +962,7 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc)
 				goto out;
 		}
 
-		if (!fsc->mount_options->server_path) {
-			path = "";
-			dout("mount opening path \\t\n");
-		} else {
-			path = fsc->mount_options->server_path + 1;
-			dout("mount opening path %s\n", path);
-		}
+		dout("mount opening path '%s'\n", path);
 
 		err = ceph_fs_debugfs_init(fsc);
 		if (err < 0)
@@ -1119,6 +1137,11 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type,
 	return res;
 
 out_splat:
+	if (!ceph_mdsmap_is_cluster_available(fsc->mdsc->mdsmap)) {
+		pr_info("No mds server is up or the cluster is laggy\n");
+		err = -EHOSTUNREACH;
+	}
+
 	ceph_mdsc_close_sessions(fsc->mdsc);
 	deactivate_locked_super(sb);
 	goto out_final;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 38b42d7594b6..1283a5774920 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -90,7 +90,7 @@ struct ceph_mount_options {
 
 	char *snapdir_name;   /* default ".snap" */
 	char *mds_namespace;  /* default NULL */
-	char *server_path;    /* default  "/" */
+	char *server_path;    /* default NULL (means "/") */
 	char *fscache_uniq;   /* default NULL */
 };
 
diff --git a/fs/char_dev.c b/fs/char_dev.c
index d18cad28c1c3..a4eee26c5a50 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -351,7 +351,7 @@ static struct kobject *cdev_get(struct cdev *p)
 
 	if (owner && !try_module_get(owner))
 		return NULL;
-	kobj = kobject_get(&p->kobj);
+	kobj = kobject_get_unless_zero(&p->kobj);
 	if (!kobj)
 		module_put(owner);
 	return kobj;
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index 41957b82d796..cc3ada12848d 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -120,17 +120,17 @@ cifs_build_devname(char *nodename, const char *prepath)
 
 
 /**
- * cifs_compose_mount_options	-	creates mount options for refferral
+ * cifs_compose_mount_options	-	creates mount options for referral
  * @sb_mountdata:	parent/root DFS mount options (template)
  * @fullpath:		full path in UNC format
- * @ref:		server's referral
+ * @ref:		optional server's referral
  * @devname:		optional pointer for saving device name
  *
  * creates mount options for submount based on template options sb_mountdata
  * and replacing unc,ip,prefixpath options with ones we've got form ref_unc.
  *
  * Returns: pointer to new mount options or ERR_PTR.
- * Caller is responcible for freeing retunrned value if it is not error.
+ * Caller is responsible for freeing returned value if it is not error.
  */
 char *cifs_compose_mount_options(const char *sb_mountdata,
 				   const char *fullpath,
@@ -150,18 +150,27 @@ char *cifs_compose_mount_options(const char *sb_mountdata,
 	if (sb_mountdata == NULL)
 		return ERR_PTR(-EINVAL);
 
-	if (strlen(fullpath) - ref->path_consumed) {
-		prepath = fullpath + ref->path_consumed;
-		/* skip initial delimiter */
-		if (*prepath == '/' || *prepath == '\\')
-			prepath++;
-	}
+	if (ref) {
+		if (strlen(fullpath) - ref->path_consumed) {
+			prepath = fullpath + ref->path_consumed;
+			/* skip initial delimiter */
+			if (*prepath == '/' || *prepath == '\\')
+				prepath++;
+		}
 
-	name = cifs_build_devname(ref->node_name, prepath);
-	if (IS_ERR(name)) {
-		rc = PTR_ERR(name);
-		name = NULL;
-		goto compose_mount_options_err;
+		name = cifs_build_devname(ref->node_name, prepath);
+		if (IS_ERR(name)) {
+			rc = PTR_ERR(name);
+			name = NULL;
+			goto compose_mount_options_err;
+		}
+	} else {
+		name = cifs_build_devname((char *)fullpath, NULL);
+		if (IS_ERR(name)) {
+			rc = PTR_ERR(name);
+			name = NULL;
+			goto compose_mount_options_err;
+		}
 	}
 
 	rc = dns_resolve_server_name_to_ip(name, &srvIP);
@@ -225,6 +234,8 @@ char *cifs_compose_mount_options(const char *sb_mountdata,
 
 	if (devname)
 		*devname = name;
+	else
+		kfree(name);
 
 	/*cifs_dbg(FYI, "%s: parent mountdata: %s\n", __func__, sb_mountdata);*/
 	/*cifs_dbg(FYI, "%s: submount mountdata: %s\n", __func__, mountdata );*/
@@ -241,23 +252,23 @@ compose_mount_options_err:
 }
 
 /**
- * cifs_dfs_do_refmount - mounts specified path using provided refferal
+ * cifs_dfs_do_mount - mounts specified path using DFS full path
+ *
+ * Always pass down @fullpath to smb3_do_mount() so we can use the root server
+ * to perform failover in case we failed to connect to the first target in the
+ * referral.
+ *
  * @cifs_sb:		parent/root superblock
  * @fullpath:		full path in UNC format
- * @ref:		server's referral
  */
-static struct vfsmount *cifs_dfs_do_refmount(struct dentry *mntpt,
-		struct cifs_sb_info *cifs_sb,
-		const char *fullpath, const struct dfs_info3_param *ref)
+static struct vfsmount *cifs_dfs_do_mount(struct dentry *mntpt,
+					  struct cifs_sb_info *cifs_sb,
+					  const char *fullpath)
 {
 	struct vfsmount *mnt;
 	char *mountdata;
 	char *devname;
 
-	/*
-	 * Always pass down the DFS full path to smb3_do_mount() so we
-	 * can use it later for failover.
-	 */
 	devname = kstrndup(fullpath, strlen(fullpath), GFP_KERNEL);
 	if (!devname)
 		return ERR_PTR(-ENOMEM);
@@ -266,7 +277,7 @@ static struct vfsmount *cifs_dfs_do_refmount(struct dentry *mntpt,
 
 	/* strip first '\' from fullpath */
 	mountdata = cifs_compose_mount_options(cifs_sb->mountdata,
-					       fullpath + 1, ref, NULL);
+					       fullpath + 1, NULL, NULL);
 	if (IS_ERR(mountdata)) {
 		kfree(devname);
 		return (struct vfsmount *)mountdata;
@@ -278,28 +289,16 @@ static struct vfsmount *cifs_dfs_do_refmount(struct dentry *mntpt,
 	return mnt;
 }
 
-static void dump_referral(const struct dfs_info3_param *ref)
-{
-	cifs_dbg(FYI, "DFS: ref path: %s\n", ref->path_name);
-	cifs_dbg(FYI, "DFS: node path: %s\n", ref->node_name);
-	cifs_dbg(FYI, "DFS: fl: %d, srv_type: %d\n",
-		 ref->flags, ref->server_type);
-	cifs_dbg(FYI, "DFS: ref_flags: %d, path_consumed: %d\n",
-		 ref->ref_flag, ref->path_consumed);
-}
-
 /*
  * Create a vfsmount that we can automount
  */
 static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt)
 {
-	struct dfs_info3_param referral = {0};
 	struct cifs_sb_info *cifs_sb;
 	struct cifs_ses *ses;
 	struct cifs_tcon *tcon;
 	char *full_path, *root_path;
 	unsigned int xid;
-	int len;
 	int rc;
 	struct vfsmount *mnt;
 
@@ -325,6 +324,8 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt)
 	if (full_path == NULL)
 		goto cdda_exit;
 
+	convert_delimiter(full_path, '\\');
+
 	cifs_dbg(FYI, "%s: full_path: %s\n", __func__, full_path);
 
 	if (!cifs_sb_master_tlink(cifs_sb)) {
@@ -357,7 +358,7 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt)
 	if (!rc) {
 		rc = dfs_cache_find(xid, ses, cifs_sb->local_nls,
 				    cifs_remap(cifs_sb), full_path + 1,
-				    &referral, NULL);
+				    NULL, NULL);
 	}
 
 	free_xid(xid);
@@ -366,26 +367,16 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt)
 		mnt = ERR_PTR(rc);
 		goto free_root_path;
 	}
-
-	dump_referral(&referral);
-
-	len = strlen(referral.node_name);
-	if (len < 2) {
-		cifs_dbg(VFS, "%s: Net Address path too short: %s\n",
-			 __func__, referral.node_name);
-		mnt = ERR_PTR(-EINVAL);
-		goto free_dfs_ref;
-	}
 	/*
-	 * cifs_mount() will retry every available node server in case
-	 * of failures.
+	 * OK - we were able to get and cache a referral for @full_path.
+	 *
+	 * Now, pass it down to cifs_mount() and it will retry every available
+	 * node server in case of failures - no need to do it here.
 	 */
-	mnt = cifs_dfs_do_refmount(mntpt, cifs_sb, full_path, &referral);
-	cifs_dbg(FYI, "%s: cifs_dfs_do_refmount:%s , mnt:%p\n", __func__,
-		 referral.node_name, mnt);
+	mnt = cifs_dfs_do_mount(mntpt, cifs_sb, full_path);
+	cifs_dbg(FYI, "%s: cifs_dfs_do_mount:%s , mnt:%p\n", __func__,
+		 full_path + 1, mnt);
 
-free_dfs_ref:
-	free_dfs_info_param(&referral);
 free_root_path:
 	kfree(root_path);
 free_full_path:
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 1d377b7f2860..130bdca9e568 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -603,7 +603,7 @@ static void access_flags_to_mode(__le32 ace_flags, int type, umode_t *pmode,
 			((flags & FILE_EXEC_RIGHTS) == FILE_EXEC_RIGHTS))
 		*pmode |= (S_IXUGO & (*pbits_to_set));
 
-	cifs_dbg(NOISY, "access flags 0x%x mode now 0x%x\n", flags, *pmode);
+	cifs_dbg(NOISY, "access flags 0x%x mode now %04o\n", flags, *pmode);
 	return;
 }
 
@@ -632,7 +632,7 @@ static void mode_to_access_flags(umode_t mode, umode_t bits_to_use,
 	if (mode & S_IXUGO)
 		*pace_flags |= SET_FILE_EXEC_RIGHTS;
 
-	cifs_dbg(NOISY, "mode: 0x%x, access flags now 0x%x\n",
+	cifs_dbg(NOISY, "mode: %04o, access flags now 0x%x\n",
 		 mode, *pace_flags);
 	return;
 }
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index bd34ea0d27e9..dd19556c835f 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -376,7 +376,7 @@ cifs_show_security(struct seq_file *s, struct cifs_ses *ses)
 		seq_puts(s, "ntlm");
 		break;
 	case Kerberos:
-		seq_printf(s, "krb5,cruid=%u", from_kuid_munged(&init_user_ns,ses->cred_uid));
+		seq_puts(s, "krb5");
 		break;
 	case RawNTLMSSP:
 		seq_puts(s, "ntlmssp");
@@ -389,6 +389,10 @@ cifs_show_security(struct seq_file *s, struct cifs_ses *ses)
 
 	if (ses->sign)
 		seq_puts(s, "i");
+
+	if (ses->sectype == Kerberos)
+		seq_printf(s, ",cruid=%u",
+			   from_kuid_munged(&init_user_ns, ses->cred_uid));
 }
 
 static void
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 507c5e6a6ffd..6ccff44dbd4b 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -1521,6 +1521,7 @@ struct mid_q_entry {
 	mid_callback_t *callback; /* call completion callback */
 	mid_handle_t *handle; /* call handle mid callback */
 	void *callback_data;	  /* general purpose pointer for callback */
+	struct task_struct *creator;
 	void *resp_buf;		/* pointer to received SMB header */
 	unsigned int resp_buf_size;
 	int mid_state;	/* wish this were enum but can not pass to wait_event */
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 1fbd92843a73..0f40811a481b 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -2148,8 +2148,8 @@ cifs_writev_requeue(struct cifs_writedata *wdata)
 			}
 		}
 
+		kref_put(&wdata2->refcount, cifs_writedata_release);
 		if (rc) {
-			kref_put(&wdata2->refcount, cifs_writedata_release);
 			if (is_retryable_error(rc))
 				continue;
 			i += nr_pages;
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index eb619b3bce8f..8924f1427472 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -360,8 +360,10 @@ static int reconn_set_ipaddr(struct TCP_Server_Info *server)
 		return rc;
 	}
 
+	spin_lock(&cifs_tcp_ses_lock);
 	rc = cifs_convert_address((struct sockaddr *)&server->dstaddr, ipaddr,
 				  strlen(ipaddr));
+	spin_unlock(&cifs_tcp_ses_lock);
 	kfree(ipaddr);
 
 	return !rc ? -1 : 0;
@@ -601,26 +603,26 @@ cifs_reconnect(struct TCP_Server_Info *server)
 		try_to_freeze();
 
 		mutex_lock(&server->srv_mutex);
+#ifdef CONFIG_CIFS_DFS_UPCALL
 		/*
 		 * Set up next DFS target server (if any) for reconnect. If DFS
 		 * feature is disabled, then we will retry last server we
 		 * connected to before.
 		 */
+		reconn_inval_dfs_target(server, cifs_sb, &tgt_list, &tgt_it);
+#endif
+		rc = reconn_set_ipaddr(server);
+		if (rc) {
+			cifs_dbg(FYI, "%s: failed to resolve hostname: %d\n",
+				 __func__, rc);
+		}
+
 		if (cifs_rdma_enabled(server))
 			rc = smbd_reconnect(server);
 		else
 			rc = generic_ip_connect(server);
 		if (rc) {
 			cifs_dbg(FYI, "reconnect error %d\n", rc);
-#ifdef CONFIG_CIFS_DFS_UPCALL
-			reconn_inval_dfs_target(server, cifs_sb, &tgt_list,
-						&tgt_it);
-#endif
-			rc = reconn_set_ipaddr(server);
-			if (rc) {
-				cifs_dbg(FYI, "%s: failed to resolve hostname: %d\n",
-					 __func__, rc);
-			}
 			mutex_unlock(&server->srv_mutex);
 			msleep(3000);
 		} else {
@@ -3289,6 +3291,10 @@ cifs_find_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 	spin_lock(&cifs_tcp_ses_lock);
 	list_for_each(tmp, &ses->tcon_list) {
 		tcon = list_entry(tmp, struct cifs_tcon, tcon_list);
+#ifdef CONFIG_CIFS_DFS_UPCALL
+		if (tcon->dfs_path)
+			continue;
+#endif
 		if (!match_tcon(tcon, volume_info))
 			continue;
 		++tcon->tc_count;
@@ -3573,8 +3579,10 @@ match_prepath(struct super_block *sb, struct cifs_mnt_data *mnt_data)
 {
 	struct cifs_sb_info *old = CIFS_SB(sb);
 	struct cifs_sb_info *new = mnt_data->cifs_sb;
-	bool old_set = old->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH;
-	bool new_set = new->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH;
+	bool old_set = (old->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) &&
+		old->prepath;
+	bool new_set = (new->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) &&
+		new->prepath;
 
 	if (old_set && new_set && !strcmp(new->prepath, old->prepath))
 		return 1;
@@ -4005,7 +4013,7 @@ int cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
 	cifs_sb->mnt_gid = pvolume_info->linux_gid;
 	cifs_sb->mnt_file_mode = pvolume_info->file_mode;
 	cifs_sb->mnt_dir_mode = pvolume_info->dir_mode;
-	cifs_dbg(FYI, "file mode: 0x%hx  dir mode: 0x%hx\n",
+	cifs_dbg(FYI, "file mode: %04ho  dir mode: %04ho\n",
 		 cifs_sb->mnt_file_mode, cifs_sb->mnt_dir_mode);
 
 	cifs_sb->actimeo = pvolume_info->actimeo;
@@ -5163,9 +5171,15 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
 	vol_info->nocase = master_tcon->nocase;
 	vol_info->nohandlecache = master_tcon->nohandlecache;
 	vol_info->local_lease = master_tcon->local_lease;
+	vol_info->no_lease = master_tcon->no_lease;
+	vol_info->resilient = master_tcon->use_resilient;
+	vol_info->persistent = master_tcon->use_persistent;
+	vol_info->handle_timeout = master_tcon->handle_timeout;
 	vol_info->no_linux_ext = !master_tcon->unix_ext;
+	vol_info->linux_ext = master_tcon->posix_extensions;
 	vol_info->sectype = master_tcon->ses->sectype;
 	vol_info->sign = master_tcon->ses->sign;
+	vol_info->seal = master_tcon->seal;
 
 	rc = cifs_set_vol_auth(vol_info, master_tcon->ses);
 	if (rc) {
@@ -5191,10 +5205,6 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
 		goto out;
 	}
 
-	/* if new SMB3.11 POSIX extensions are supported do not remap / and \ */
-	if (tcon->posix_extensions)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS;
-
 	if (cap_unix(ses))
 		reset_cifs_unix_caps(0, tcon, NULL, vol_info);
 
diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c
index e3e1c13df439..24e2e22103a1 100644
--- a/fs/cifs/dfs_cache.c
+++ b/fs/cifs/dfs_cache.c
@@ -1317,10 +1317,9 @@ static struct cifs_ses *find_root_ses(struct dfs_cache_vol_info *vi,
 	int rc;
 	struct dfs_info3_param ref = {0};
 	char *mdata = NULL, *devname = NULL;
-	bool is_smb3 = tcon->ses->server->vals->header_preamble_size == 0;
 	struct TCP_Server_Info *server;
 	struct cifs_ses *ses;
-	struct smb_vol vol;
+	struct smb_vol vol = {NULL};
 
 	rpath = get_dfs_root(path);
 	if (IS_ERR(rpath))
@@ -1344,7 +1343,7 @@ static struct cifs_ses *find_root_ses(struct dfs_cache_vol_info *vi,
 		goto out;
 	}
 
-	rc = cifs_setup_volume_info(&vol, mdata, devname, is_smb3);
+	rc = cifs_setup_volume_info(&vol, mdata, devname, false);
 	kfree(devname);
 
 	if (rc) {
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 53b5bdf465e0..bf7644bf0605 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -561,7 +561,6 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry,
 		if (server->ops->close)
 			server->ops->close(xid, tcon, &fid);
 		cifs_del_pending_open(&open);
-		fput(file);
 		rc = -ENOMEM;
 	}
 
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index b971f7a79481..076105389a63 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1149,7 +1149,8 @@ try_again:
 	rc = posix_lock_file(file, flock, NULL);
 	up_write(&cinode->lock_sem);
 	if (rc == FILE_LOCK_DEFERRED) {
-		rc = wait_event_interruptible(flock->fl_wait, !flock->fl_blocker);
+		rc = wait_event_interruptible(flock->fl_wait,
+					list_empty(&flock->fl_blocked_member));
 		if (!rc)
 			goto try_again;
 		locks_delete_block(flock);
@@ -3686,7 +3687,7 @@ again:
 	if (rc == -ENODATA)
 		rc = 0;
 
-	ctx->rc = (rc == 0) ? ctx->total_len : rc;
+	ctx->rc = (rc == 0) ? (ssize_t)ctx->total_len : rc;
 
 	mutex_unlock(&ctx->aio_mutex);
 
@@ -3905,7 +3906,7 @@ cifs_read(struct file *file, char *read_data, size_t read_size, loff_t *offset)
 			 * than it negotiated since it will refuse the read
 			 * then.
 			 */
-			if ((tcon->ses) && !(tcon->ses->capabilities &
+			if (!(tcon->ses->capabilities &
 				tcon->ses->server->vals->cap_large_files)) {
 				current_read_size = min_t(uint,
 					current_read_size, CIFSMaxBufSize);
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index f2042d1a1cc4..97d826a26478 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -163,7 +163,7 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
 
 	spin_lock(&inode->i_lock);
 	/* we do not want atime to be less than mtime, it broke some apps */
-	if (timespec64_compare(&fattr->cf_atime, &fattr->cf_mtime))
+	if (timespec64_compare(&fattr->cf_atime, &fattr->cf_mtime) < 0)
 		inode->i_atime = fattr->cf_mtime;
 	else
 		inode->i_atime = fattr->cf_atime;
@@ -1579,7 +1579,7 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, umode_t mode)
 	struct TCP_Server_Info *server;
 	char *full_path;
 
-	cifs_dbg(FYI, "In cifs_mkdir, mode = 0x%hx inode = 0x%p\n",
+	cifs_dbg(FYI, "In cifs_mkdir, mode = %04ho inode = 0x%p\n",
 		 mode, inode);
 
 	cifs_sb = CIFS_SB(inode->i_sb);
@@ -2003,6 +2003,7 @@ int cifs_revalidate_dentry_attr(struct dentry *dentry)
 	struct inode *inode = d_inode(dentry);
 	struct super_block *sb = dentry->d_sb;
 	char *full_path = NULL;
+	int count = 0;
 
 	if (inode == NULL)
 		return -ENOENT;
@@ -2024,15 +2025,18 @@ int cifs_revalidate_dentry_attr(struct dentry *dentry)
 		 full_path, inode, inode->i_count.counter,
 		 dentry, cifs_get_time(dentry), jiffies);
 
+again:
 	if (cifs_sb_master_tcon(CIFS_SB(sb))->unix_ext)
 		rc = cifs_get_inode_info_unix(&inode, full_path, sb, xid);
 	else
 		rc = cifs_get_inode_info(&inode, full_path, NULL, sb,
 					 xid, NULL);
-
+	if (rc == -EAGAIN && count++ < 10)
+		goto again;
 out:
 	kfree(full_path);
 	free_xid(xid);
+
 	return rc;
 }
 
@@ -2252,6 +2256,15 @@ set_size_out:
 	if (rc == 0) {
 		cifsInode->server_eof = attrs->ia_size;
 		cifs_setsize(inode, attrs->ia_size);
+
+		/*
+		 * The man page of truncate says if the size changed,
+		 * then the st_ctime and st_mtime fields for the file
+		 * are updated.
+		 */
+		attrs->ia_ctime = attrs->ia_mtime = current_time(inode);
+		attrs->ia_valid |= ATTR_CTIME | ATTR_MTIME;
+
 		cifs_truncate_page(inode->i_mapping, inode->i_size);
 	}
 
@@ -2442,25 +2455,26 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
 
 	/*
 	 * Attempt to flush data before changing attributes. We need to do
-	 * this for ATTR_SIZE and ATTR_MTIME for sure, and if we change the
-	 * ownership or mode then we may also need to do this. Here, we take
-	 * the safe way out and just do the flush on all setattr requests. If
-	 * the flush returns error, store it to report later and continue.
+	 * this for ATTR_SIZE and ATTR_MTIME.  If the flush of the data
+	 * returns error, store it to report later and continue.
 	 *
 	 * BB: This should be smarter. Why bother flushing pages that
 	 * will be truncated anyway? Also, should we error out here if
-	 * the flush returns error?
+	 * the flush returns error? Do we need to check for ATTR_MTIME_SET flag?
 	 */
-	rc = filemap_write_and_wait(inode->i_mapping);
-	if (is_interrupt_error(rc)) {
-		rc = -ERESTARTSYS;
-		goto cifs_setattr_exit;
+	if (attrs->ia_valid & (ATTR_MTIME | ATTR_SIZE | ATTR_CTIME)) {
+		rc = filemap_write_and_wait(inode->i_mapping);
+		if (is_interrupt_error(rc)) {
+			rc = -ERESTARTSYS;
+			goto cifs_setattr_exit;
+		}
+		mapping_set_error(inode->i_mapping, rc);
 	}
 
-	mapping_set_error(inode->i_mapping, rc);
 	rc = 0;
 
-	if (attrs->ia_valid & ATTR_MTIME) {
+	if ((attrs->ia_valid & ATTR_MTIME) &&
+	    !(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) {
 		rc = cifs_get_writable_file(cifsInode, false, &wfile);
 		if (!rc) {
 			tcon = tlink_tcon(wfile->tlink);
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index 2abfa2703060..060fbe1e005b 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -67,7 +67,7 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms,
 		goto out;
 
 
-	 if (oparms->tcon->use_resilient) {
+	if (oparms->tcon->use_resilient) {
 		/* default timeout is 0, servers pick default (120 seconds) */
 		nr_ioctl_req.Timeout =
 			cpu_to_le32(oparms->tcon->handle_timeout);
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 14265b4bbcc0..2fc96f7923ee 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -509,15 +509,31 @@ cifs_ses_oplock_break(struct work_struct *work)
 	kfree(lw);
 }
 
+static void
+smb2_queue_pending_open_break(struct tcon_link *tlink, __u8 *lease_key,
+			      __le32 new_lease_state)
+{
+	struct smb2_lease_break_work *lw;
+
+	lw = kmalloc(sizeof(struct smb2_lease_break_work), GFP_KERNEL);
+	if (!lw) {
+		cifs_put_tlink(tlink);
+		return;
+	}
+
+	INIT_WORK(&lw->lease_break, cifs_ses_oplock_break);
+	lw->tlink = tlink;
+	lw->lease_state = new_lease_state;
+	memcpy(lw->lease_key, lease_key, SMB2_LEASE_KEY_SIZE);
+	queue_work(cifsiod_wq, &lw->lease_break);
+}
+
 static bool
-smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp,
-		    struct smb2_lease_break_work *lw)
+smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp)
 {
-	bool found;
 	__u8 lease_state;
 	struct list_head *tmp;
 	struct cifsFileInfo *cfile;
-	struct cifs_pending_open *open;
 	struct cifsInodeInfo *cinode;
 	int ack_req = le32_to_cpu(rsp->Flags &
 				  SMB2_NOTIFY_BREAK_LEASE_FLAG_ACK_REQUIRED);
@@ -556,22 +572,29 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp,
 				  &cinode->flags);
 
 		cifs_queue_oplock_break(cfile);
-		kfree(lw);
 		return true;
 	}
 
-	found = false;
+	return false;
+}
+
+static struct cifs_pending_open *
+smb2_tcon_find_pending_open_lease(struct cifs_tcon *tcon,
+				  struct smb2_lease_break *rsp)
+{
+	__u8 lease_state = le32_to_cpu(rsp->NewLeaseState);
+	int ack_req = le32_to_cpu(rsp->Flags &
+				  SMB2_NOTIFY_BREAK_LEASE_FLAG_ACK_REQUIRED);
+	struct cifs_pending_open *open;
+	struct cifs_pending_open *found = NULL;
+
 	list_for_each_entry(open, &tcon->pending_opens, olist) {
 		if (memcmp(open->lease_key, rsp->LeaseKey,
 			   SMB2_LEASE_KEY_SIZE))
 			continue;
 
 		if (!found && ack_req) {
-			found = true;
-			memcpy(lw->lease_key, open->lease_key,
-			       SMB2_LEASE_KEY_SIZE);
-			lw->tlink = cifs_get_tlink(open->tlink);
-			queue_work(cifsiod_wq, &lw->lease_break);
+			found = open;
 		}
 
 		cifs_dbg(FYI, "found in the pending open list\n");
@@ -592,14 +615,7 @@ smb2_is_valid_lease_break(char *buffer)
 	struct TCP_Server_Info *server;
 	struct cifs_ses *ses;
 	struct cifs_tcon *tcon;
-	struct smb2_lease_break_work *lw;
-
-	lw = kmalloc(sizeof(struct smb2_lease_break_work), GFP_KERNEL);
-	if (!lw)
-		return false;
-
-	INIT_WORK(&lw->lease_break, cifs_ses_oplock_break);
-	lw->lease_state = rsp->NewLeaseState;
+	struct cifs_pending_open *open;
 
 	cifs_dbg(FYI, "Checking for lease break\n");
 
@@ -617,11 +633,27 @@ smb2_is_valid_lease_break(char *buffer)
 				spin_lock(&tcon->open_file_lock);
 				cifs_stats_inc(
 				    &tcon->stats.cifs_stats.num_oplock_brks);
-				if (smb2_tcon_has_lease(tcon, rsp, lw)) {
+				if (smb2_tcon_has_lease(tcon, rsp)) {
 					spin_unlock(&tcon->open_file_lock);
 					spin_unlock(&cifs_tcp_ses_lock);
 					return true;
 				}
+				open = smb2_tcon_find_pending_open_lease(tcon,
+									 rsp);
+				if (open) {
+					__u8 lease_key[SMB2_LEASE_KEY_SIZE];
+					struct tcon_link *tlink;
+
+					tlink = cifs_get_tlink(open->tlink);
+					memcpy(lease_key, open->lease_key,
+					       SMB2_LEASE_KEY_SIZE);
+					spin_unlock(&tcon->open_file_lock);
+					spin_unlock(&cifs_tcp_ses_lock);
+					smb2_queue_pending_open_break(tlink,
+								      lease_key,
+								      rsp->NewLeaseState);
+					return true;
+				}
 				spin_unlock(&tcon->open_file_lock);
 
 				if (tcon->crfid.is_valid &&
@@ -639,7 +671,6 @@ smb2_is_valid_lease_break(char *buffer)
 		}
 	}
 	spin_unlock(&cifs_tcp_ses_lock);
-	kfree(lw);
 	cifs_dbg(FYI, "Can not process lease break - no lease matched\n");
 	return false;
 }
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 24a7618470ec..a71efe297244 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -662,6 +662,11 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid)
 	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
+	if (!server->ops->new_lease_key)
+		return -EIO;
+
+	server->ops->new_lease_key(pfid);
+
 	memset(rqst, 0, sizeof(rqst));
 	resp_buftype[0] = resp_buftype[1] = CIFS_NO_BUFFER;
 	memset(rsp_iov, 0, sizeof(rsp_iov));
@@ -729,6 +734,7 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid)
 			/* close extra handle outside of crit sec */
 			SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
 		}
+		rc = 0;
 		goto oshr_free;
 	}
 
@@ -1078,7 +1084,8 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon,
 	void *data[1];
 	struct smb2_file_full_ea_info *ea = NULL;
 	struct kvec close_iov[1];
-	int rc;
+	struct smb2_query_info_rsp *rsp;
+	int rc, used_len = 0;
 
 	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
@@ -1101,6 +1108,38 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon,
 							     cifs_sb);
 			if (rc == -ENODATA)
 				goto sea_exit;
+		} else {
+			/* If we are adding a attribute we should first check
+			 * if there will be enough space available to store
+			 * the new EA. If not we should not add it since we
+			 * would not be able to even read the EAs back.
+			 */
+			rc = smb2_query_info_compound(xid, tcon, utf16_path,
+				      FILE_READ_EA,
+				      FILE_FULL_EA_INFORMATION,
+				      SMB2_O_INFO_FILE,
+				      CIFSMaxBufSize -
+				      MAX_SMB2_CREATE_RESPONSE_SIZE -
+				      MAX_SMB2_CLOSE_RESPONSE_SIZE,
+				      &rsp_iov[1], &resp_buftype[1], cifs_sb);
+			if (rc == 0) {
+				rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base;
+				used_len = le32_to_cpu(rsp->OutputBufferLength);
+			}
+			free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base);
+			resp_buftype[1] = CIFS_NO_BUFFER;
+			memset(&rsp_iov[1], 0, sizeof(rsp_iov[1]));
+			rc = 0;
+
+			/* Use a fudge factor of 256 bytes in case we collide
+			 * with a different set_EAs command.
+			 */
+			if(CIFSMaxBufSize - MAX_SMB2_CREATE_RESPONSE_SIZE -
+			   MAX_SMB2_CLOSE_RESPONSE_SIZE - 256 <
+			   used_len + ea_name_len + ea_value_len + 1) {
+				rc = -ENOSPC;
+				goto sea_exit;
+			}
 		}
 	}
 
@@ -1449,7 +1488,9 @@ smb2_ioctl_query_info(const unsigned int xid,
 					     COMPOUND_FID, COMPOUND_FID,
 					     qi.info_type, true, buffer,
 					     qi.output_buffer_length,
-					     CIFSMaxBufSize);
+					     CIFSMaxBufSize -
+					     MAX_SMB2_CREATE_RESPONSE_SIZE -
+					     MAX_SMB2_CLOSE_RESPONSE_SIZE);
 		}
 	} else if (qi.flags == PASSTHRU_QUERY_INFO) {
 		memset(&qi_iov, 0, sizeof(qi_iov));
@@ -2540,7 +2581,10 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rc = SMB2_ioctl_init(tcon, &rqst[1], fid.persistent_fid,
 			     fid.volatile_fid, FSCTL_GET_REPARSE_POINT,
-			     true /* is_fctl */, NULL, 0, CIFSMaxBufSize);
+			     true /* is_fctl */, NULL, 0,
+			     CIFSMaxBufSize -
+			     MAX_SMB2_CREATE_RESPONSE_SIZE -
+			     MAX_SMB2_CLOSE_RESPONSE_SIZE);
 	if (rc)
 		goto querty_exit;
 
@@ -2844,6 +2888,11 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 	trace_smb3_zero_enter(xid, cfile->fid.persistent_fid, tcon->tid,
 			      ses->Suid, offset, len);
 
+	/*
+	 * We zero the range through ioctl, so we need remove the page caches
+	 * first, otherwise the data may be inconsistent with the server.
+	 */
+	truncate_pagecache_range(inode, offset, offset + len - 1);
 
 	/* if file not oplocked can't be sure whether asking to extend size */
 	if (!CIFS_CACHE_READ(cifsi))
@@ -2912,6 +2961,12 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
 		return rc;
 	}
 
+	/*
+	 * We implement the punch hole through ioctl, so we need remove the page
+	 * caches first, otherwise the data may be inconsistent with the server.
+	 */
+	truncate_pagecache_range(inode, offset, offset + len - 1);
+
 	cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len);
 
 	fsctl_buf.FileOffset = cpu_to_le64(offset);
@@ -3134,7 +3189,7 @@ static int smb3_fiemap(struct cifs_tcon *tcon,
 	if (rc)
 		goto out;
 
-	if (out_data_len < sizeof(struct file_allocated_range_buffer)) {
+	if (out_data_len && out_data_len < sizeof(struct file_allocated_range_buffer)) {
 		rc = -EINVAL;
 		goto out;
 	}
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index f63ec88cc292..78f4cd690dc2 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -252,7 +252,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon)
 	if (tcon == NULL)
 		return 0;
 
-	if (smb2_command == SMB2_TREE_CONNECT || smb2_command == SMB2_IOCTL)
+	if (smb2_command == SMB2_TREE_CONNECT)
 		return 0;
 
 	if (tcon->tidStatus == CifsExiting) {
@@ -312,7 +312,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon)
 		if (server->tcpStatus != CifsNeedReconnect)
 			break;
 
-		if (--retries)
+		if (retries && --retries)
 			continue;
 
 		/*
@@ -350,9 +350,14 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon)
 	}
 
 	rc = cifs_negotiate_protocol(0, tcon->ses);
-	if (!rc && tcon->ses->need_reconnect)
+	if (!rc && tcon->ses->need_reconnect) {
 		rc = cifs_setup_session(0, tcon->ses, nls_codepage);
-
+		if ((rc == -EACCES) && !tcon->retry) {
+			rc = -EHOSTDOWN;
+			mutex_unlock(&tcon->ses->session_mutex);
+			goto failed;
+		}
+	}
 	if (rc || !tcon->need_reconnect) {
 		mutex_unlock(&tcon->ses->session_mutex);
 		goto out;
@@ -397,6 +402,7 @@ out:
 	case SMB2_SET_INFO:
 		rc = -EAGAIN;
 	}
+failed:
 	unload_nls(nls_codepage);
 	return rc;
 }
@@ -426,16 +432,9 @@ fill_small_buf(__le16 smb2_command, struct cifs_tcon *tcon, void *buf,
  * SMB information in the SMB header. If the return code is zero, this
  * function must have filled in request_buf pointer.
  */
-static int
-smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon,
-		    void **request_buf, unsigned int *total_len)
+static int __smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon,
+				  void **request_buf, unsigned int *total_len)
 {
-	int rc;
-
-	rc = smb2_reconnect(smb2_command, tcon);
-	if (rc)
-		return rc;
-
 	/* BB eventually switch this to SMB2 specific small buf size */
 	if (smb2_command == SMB2_SET_INFO)
 		*request_buf = cifs_buf_get();
@@ -456,7 +455,31 @@ smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon,
 		cifs_stats_inc(&tcon->num_smbs_sent);
 	}
 
-	return rc;
+	return 0;
+}
+
+static int smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon,
+			       void **request_buf, unsigned int *total_len)
+{
+	int rc;
+
+	rc = smb2_reconnect(smb2_command, tcon);
+	if (rc)
+		return rc;
+
+	return __smb2_plain_req_init(smb2_command, tcon, request_buf,
+				     total_len);
+}
+
+static int smb2_ioctl_req_init(u32 opcode, struct cifs_tcon *tcon,
+			       void **request_buf, unsigned int *total_len)
+{
+	/* Skip reconnect only for FSCTL_VALIDATE_NEGOTIATE_INFO IOCTLs */
+	if (opcode == FSCTL_VALIDATE_NEGOTIATE_INFO) {
+		return __smb2_plain_req_init(SMB2_IOCTL, tcon, request_buf,
+					     total_len);
+	}
+	return smb2_plain_req_init(SMB2_IOCTL, tcon, request_buf, total_len);
 }
 
 /* For explanation of negotiate contexts see MS-SMB2 section 2.2.3.1 */
@@ -1275,6 +1298,8 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data)
 	spnego_key = cifs_get_spnego_key(ses);
 	if (IS_ERR(spnego_key)) {
 		rc = PTR_ERR(spnego_key);
+		if (rc == -ENOKEY)
+			cifs_dbg(VFS, "Verify user has a krb5 ticket and keyutils is installed\n");
 		spnego_key = NULL;
 		goto out;
 	}
@@ -2547,7 +2572,7 @@ SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
 	int rc;
 	char *in_data_buf;
 
-	rc = smb2_plain_req_init(SMB2_IOCTL, tcon, (void **) &req, &total_len);
+	rc = smb2_ioctl_req_init(opcode, tcon, (void **) &req, &total_len);
 	if (rc)
 		return rc;
 
@@ -2610,7 +2635,9 @@ SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
 	 * response size smaller.
 	 */
 	req->MaxOutputResponse = cpu_to_le32(max_response_size);
-
+	req->sync_hdr.CreditCharge =
+		cpu_to_le16(DIV_ROUND_UP(max(indatalen, max_response_size),
+					 SMB2_MAX_BUFFER_SIZE));
 	if (is_fsctl)
 		req->Flags = cpu_to_le32(SMB2_0_IOCTL_IS_FSCTL);
 	else
@@ -3659,6 +3686,9 @@ smb2_writev_callback(struct mid_q_entry *mid)
 				     wdata->cfile->fid.persistent_fid,
 				     tcon->tid, tcon->ses->Suid, wdata->offset,
 				     wdata->bytes, wdata->result);
+		if (wdata->result == -ENOSPC)
+			printk_once(KERN_WARNING "Out of space writing to %s\n",
+				    tcon->treeName);
 	} else
 		trace_smb3_write_done(0 /* no xid */,
 				      wdata->cfile->fid.persistent_fid,
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index d1181572758b..b9ccef97406d 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -597,6 +597,8 @@ smb2_mid_entry_alloc(const struct smb2_sync_hdr *shdr,
 	 * The default is for the mid to be synchronous, so the
 	 * default callback just wakes up the current task.
 	 */
+	get_task_struct(current);
+	temp->creator = current;
 	temp->callback = cifs_wake_up_task;
 	temp->callback_data = current;
 
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index ff2dcb6663cf..44079b1a0456 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -76,6 +76,8 @@ AllocMidQEntry(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server)
 	 * The default is for the mid to be synchronous, so the
 	 * default callback just wakes up the current task.
 	 */
+	get_task_struct(current);
+	temp->creator = current;
 	temp->callback = cifs_wake_up_task;
 	temp->callback_data = current;
 
@@ -158,6 +160,7 @@ static void _cifs_mid_q_entry_release(struct kref *refcount)
 		}
 	}
 #endif
+	put_task_struct(midEntry->creator);
 
 	mempool_free(midEntry, cifs_mid_poolp);
 }
@@ -463,7 +466,7 @@ smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
 	      struct smb_rqst *rqst, int flags)
 {
 	struct kvec iov;
-	struct smb2_transform_hdr tr_hdr;
+	struct smb2_transform_hdr *tr_hdr;
 	struct smb_rqst cur_rqst[MAX_COMPOUND];
 	int rc;
 
@@ -473,28 +476,34 @@ smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
 	if (num_rqst > MAX_COMPOUND - 1)
 		return -ENOMEM;
 
-	memset(&cur_rqst[0], 0, sizeof(cur_rqst));
-	memset(&iov, 0, sizeof(iov));
-	memset(&tr_hdr, 0, sizeof(tr_hdr));
-
-	iov.iov_base = &tr_hdr;
-	iov.iov_len = sizeof(tr_hdr);
-	cur_rqst[0].rq_iov = &iov;
-	cur_rqst[0].rq_nvec = 1;
-
 	if (!server->ops->init_transform_rq) {
 		cifs_dbg(VFS, "Encryption requested but transform callback "
 			 "is missing\n");
 		return -EIO;
 	}
 
+	tr_hdr = kmalloc(sizeof(*tr_hdr), GFP_NOFS);
+	if (!tr_hdr)
+		return -ENOMEM;
+
+	memset(&cur_rqst[0], 0, sizeof(cur_rqst));
+	memset(&iov, 0, sizeof(iov));
+	memset(tr_hdr, 0, sizeof(*tr_hdr));
+
+	iov.iov_base = tr_hdr;
+	iov.iov_len = sizeof(*tr_hdr);
+	cur_rqst[0].rq_iov = &iov;
+	cur_rqst[0].rq_nvec = 1;
+
 	rc = server->ops->init_transform_rq(server, num_rqst + 1,
 					    &cur_rqst[0], rqst);
 	if (rc)
-		return rc;
+		goto out;
 
 	rc = __smb_send_rqst(server, num_rqst + 1, &cur_rqst[0]);
 	smb3_free_compound_rqst(num_rqst, &cur_rqst[1]);
+out:
+	kfree(tr_hdr);
 	return rc;
 }
 
@@ -519,7 +528,7 @@ wait_for_free_credits(struct TCP_Server_Info *server, const int num_credits,
 		      const int timeout, const int flags,
 		      unsigned int *instance)
 {
-	int rc;
+	long rc;
 	int *credits;
 	int optype;
 	long int t;
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index a7ec2d3dff92..e0226b2138d6 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -1032,10 +1032,11 @@ COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd,
 #endif
 
 	case FICLONE:
+		goto do_ioctl;
 	case FICLONERANGE:
 	case FIDEDUPERANGE:
 	case FS_IOC_FIEMAP:
-		goto do_ioctl;
+		goto found_handler;
 
 	case FIBMAP:
 	case FIGETBSZ:
diff --git a/fs/coredump.c b/fs/coredump.c
index e42e17e55bfd..b24396625848 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -753,6 +753,14 @@ void do_coredump(const kernel_siginfo_t *siginfo)
 	if (displaced)
 		put_files_struct(displaced);
 	if (!dump_interrupted()) {
+		/*
+		 * umh disabled with CONFIG_STATIC_USERMODEHELPER_PATH="" would
+		 * have this set to NULL.
+		 */
+		if (!cprm.file) {
+			pr_info("Core dump to |%s disabled\n", cn.corename);
+			goto close_fail;
+		}
 		file_start_write(cprm.file);
 		core_dumped = binfmt->core_dump(&cprm);
 		file_end_write(cprm.file);
diff --git a/fs/dax.c b/fs/dax.c
index 36538f5ecc31..aaa16945ef8a 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1208,6 +1208,9 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 		lockdep_assert_held(&inode->i_rwsem);
 	}
 
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		flags |= IOMAP_NOWAIT;
+
 	while (iov_iter_count(iter)) {
 		ret = iomap_apply(inode, pos, iov_iter_count(iter), flags, ops,
 				iter, dax_iomap_actor);
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index ddd708b09fa1..6cfe9c175977 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -147,8 +147,13 @@ static int open_proxy_open(struct inode *inode, struct file *filp)
 		return r == -EIO ? -ENOENT : r;
 
 	real_fops = debugfs_real_fops(filp);
-	real_fops = fops_get(real_fops);
-	if (!real_fops) {
+	if (!fops_get(real_fops)) {
+#ifdef CONFIG_MODULES
+		if (real_fops->owner &&
+		    real_fops->owner->state == MODULE_STATE_GOING)
+			goto out;
+#endif
+
 		/* Huh? Module did not clean up after itself at exit? */
 		WARN(1, "debugfs file owner did not clean up at exit: %pd",
 			dentry);
@@ -272,8 +277,13 @@ static int full_proxy_open(struct inode *inode, struct file *filp)
 		return r == -EIO ? -ENOENT : r;
 
 	real_fops = debugfs_real_fops(filp);
-	real_fops = fops_get(real_fops);
-	if (!real_fops) {
+	if (!fops_get(real_fops)) {
+#ifdef CONFIG_MODULES
+		if (real_fops->owner &&
+		    real_fops->owner->state == MODULE_STATE_GOING)
+			goto out;
+#endif
+
 		/* Huh? Module did not cleanup after itself at exit? */
 		WARN(1, "debugfs file owner did not clean up at exit: %pd",
 			dentry);
diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h
index da1173a0b274..db09bed48153 100644
--- a/fs/dlm/dlm_internal.h
+++ b/fs/dlm/dlm_internal.h
@@ -97,7 +97,6 @@ do { \
                __LINE__, __FILE__, #x, jiffies); \
     {do} \
     printk("\n"); \
-    BUG(); \
     panic("DLM:  Record message above and reboot.\n"); \
   } \
 }
diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c
index 4c2c85a223ac..3dd6e0189d39 100644
--- a/fs/dlm/lockspace.c
+++ b/fs/dlm/lockspace.c
@@ -631,6 +631,9 @@ static int new_lockspace(const char *name, const char *cluster,
 	wait_event(ls->ls_recover_lock_wait,
 		   test_bit(LSFL_RECOVER_LOCK, &ls->ls_flags));
 
+	/* let kobject handle freeing of ls if there's an error */
+	do_unreg = 1;
+
 	ls->ls_kobj.kset = dlm_kset;
 	error = kobject_init_and_add(&ls->ls_kobj, &dlm_ktype, NULL,
 				     "%s", ls->ls_name);
@@ -638,9 +641,6 @@ static int new_lockspace(const char *name, const char *cluster,
 		goto out_recoverd;
 	kobject_uevent(&ls->ls_kobj, KOBJ_ADD);
 
-	/* let kobject handle freeing of ls if there's an error */
-	do_unreg = 1;
-
 	/* This uevent triggers dlm_controld in userspace to add us to the
 	   group of nodes that are members of this lockspace (managed by the
 	   cluster infrastructure.)  Once it's done that, it tells us who the
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index d31b6c72b476..dc1a1d5d825b 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -35,11 +35,11 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
 		spin_unlock(&inode->i_lock);
 		spin_unlock(&sb->s_inode_list_lock);
 
-		cond_resched();
 		invalidate_mapping_pages(inode->i_mapping, 0, -1);
 		iput(toput_inode);
 		toput_inode = inode;
 
+		cond_resched();
 		spin_lock(&sb->s_inode_list_lock);
 	}
 	spin_unlock(&sb->s_inode_list_lock);
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 54bfa71ffdad..9a85905ccf98 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -310,8 +310,10 @@ static int crypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat,
 	struct extent_crypt_result ecr;
 	int rc = 0;
 
-	BUG_ON(!crypt_stat || !crypt_stat->tfm
-	       || !(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED));
+	if (!crypt_stat || !crypt_stat->tfm
+	       || !(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED))
+		return -EINVAL;
+
 	if (unlikely(ecryptfs_verbosity > 0)) {
 		ecryptfs_printk(KERN_DEBUG, "Key size [%zd]; key:\n",
 				crypt_stat->key_size);
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index 9536e592e25a..7cd6db598e9f 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -1303,7 +1303,7 @@ parse_tag_1_packet(struct ecryptfs_crypt_stat *crypt_stat,
 		printk(KERN_WARNING "Tag 1 packet contains key larger "
 		       "than ECRYPTFS_MAX_ENCRYPTED_KEY_BYTES\n");
 		rc = -EINVAL;
-		goto out;
+		goto out_free;
 	}
 	memcpy((*new_auth_tok)->session_key.encrypted_key,
 	       &data[(*packet_size)], (body_size - (ECRYPTFS_SIG_SIZE + 2)));
diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c
index d668e60b85b5..c05ca39aa449 100644
--- a/fs/ecryptfs/messaging.c
+++ b/fs/ecryptfs/messaging.c
@@ -379,6 +379,7 @@ int __init ecryptfs_init_messaging(void)
 					* ecryptfs_message_buf_len),
 				       GFP_KERNEL);
 	if (!ecryptfs_msg_ctx_arr) {
+		kfree(ecryptfs_daemon_hash);
 		rc = -ENOMEM;
 		goto out;
 	}
diff --git a/fs/eventfd.c b/fs/eventfd.c
index 8aa0ea8c55e8..78e41c7c3d05 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -24,6 +24,8 @@
 #include <linux/seq_file.h>
 #include <linux/idr.h>
 
+DEFINE_PER_CPU(int, eventfd_wake_count);
+
 static DEFINE_IDA(eventfd_ida);
 
 struct eventfd_ctx {
@@ -60,12 +62,25 @@ __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n)
 {
 	unsigned long flags;
 
+	/*
+	 * Deadlock or stack overflow issues can happen if we recurse here
+	 * through waitqueue wakeup handlers. If the caller users potentially
+	 * nested waitqueues with custom wakeup handlers, then it should
+	 * check eventfd_signal_count() before calling this function. If
+	 * it returns true, the eventfd_signal() call should be deferred to a
+	 * safe context.
+	 */
+	if (WARN_ON_ONCE(this_cpu_read(eventfd_wake_count)))
+		return 0;
+
 	spin_lock_irqsave(&ctx->wqh.lock, flags);
+	this_cpu_inc(eventfd_wake_count);
 	if (ULLONG_MAX - ctx->count < n)
 		n = ULLONG_MAX - ctx->count;
 	ctx->count += n;
 	if (waitqueue_active(&ctx->wqh))
 		wake_up_locked_poll(&ctx->wqh, EPOLLIN);
+	this_cpu_dec(eventfd_wake_count);
 	spin_unlock_irqrestore(&ctx->wqh.lock, flags);
 
 	return n;
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 0f9c073d78d5..70ecf02cdca2 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1827,7 +1827,6 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 {
 	int res = 0, eavail, timed_out = 0;
 	u64 slack = 0;
-	bool waiter = false;
 	wait_queue_entry_t wait;
 	ktime_t expires, *to = NULL;
 
@@ -1872,21 +1871,23 @@ fetch_events:
 	 */
 	ep_reset_busy_poll_napi_id(ep);
 
-	/*
-	 * We don't have any available event to return to the caller.  We need
-	 * to sleep here, and we will be woken by ep_poll_callback() when events
-	 * become available.
-	 */
-	if (!waiter) {
-		waiter = true;
-		init_waitqueue_entry(&wait, current);
-
-		spin_lock_irq(&ep->wq.lock);
+	do {
+		/*
+		 * Internally init_wait() uses autoremove_wake_function(),
+		 * thus wait entry is removed from the wait queue on each
+		 * wakeup. Why it is important? In case of several waiters
+		 * each new wakeup will hit the next waiter, giving it the
+		 * chance to harvest new event. Otherwise wakeup can be
+		 * lost. This is also good performance-wise, because on
+		 * normal wakeup path no need to call __remove_wait_queue()
+		 * explicitly, thus ep->lock is not taken, which halts the
+		 * event delivery.
+		 */
+		init_wait(&wait);
+		write_lock_irq(&ep->lock);
 		__add_wait_queue_exclusive(&ep->wq, &wait);
-		spin_unlock_irq(&ep->wq.lock);
-	}
+		write_unlock_irq(&ep->lock);
 
-	for (;;) {
 		/*
 		 * We don't want to sleep if the ep_poll_callback() sends us
 		 * a wakeup in between. That's why we set the task state
@@ -1916,10 +1917,20 @@ fetch_events:
 			timed_out = 1;
 			break;
 		}
-	}
+
+		/* We were woken up, thus go and try to harvest some events */
+		eavail = 1;
+
+	} while (0);
 
 	__set_current_state(TASK_RUNNING);
 
+	if (!list_empty_careful(&wait.entry)) {
+		write_lock_irq(&ep->lock);
+		__remove_wait_queue(&ep->wq, &wait);
+		write_unlock_irq(&ep->lock);
+	}
+
 send_events:
 	/*
 	 * Try to transfer events to user space. In case we get 0 events and
@@ -1930,12 +1941,6 @@ send_events:
 	    !(res = ep_send_events(ep, events, maxevents)) && !timed_out)
 		goto fetch_events;
 
-	if (waiter) {
-		spin_lock_irq(&ep->wq.lock);
-		__remove_wait_queue(&ep->wq, &wait);
-		spin_unlock_irq(&ep->wq.lock);
-	}
-
 	return res;
 }
 
diff --git a/fs/exec.c b/fs/exec.c
index ed8f4957a4a6..fa3faa50b592 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1274,6 +1274,8 @@ int flush_old_exec(struct linux_binprm * bprm)
 	 */
 	set_mm_exe_file(bprm->mm, bprm->file);
 
+	would_dump(bprm, bprm->file);
+
 	/*
 	 * Release all of the old mmap stuff
 	 */
@@ -1383,7 +1385,7 @@ void setup_new_exec(struct linux_binprm * bprm)
 
 	/* An exec changes our domain. We are no longer part of the thread
 	   group */
-	current->self_exec_id++;
+	WRITE_ONCE(current->self_exec_id, current->self_exec_id + 1);
 	flush_signal_handlers(current, 0);
 }
 EXPORT_SYMBOL(setup_new_exec);
@@ -1817,8 +1819,6 @@ static int __do_execve_file(int fd, struct filename *filename,
 	if (retval < 0)
 		goto out;
 
-	would_dump(bprm, bprm->file);
-
 	retval = exec_binprm(bprm);
 	if (retval < 0)
 		goto out;
diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c
index a0c5ea91fcd4..8c29d4d6bfd5 100644
--- a/fs/ext2/ialloc.c
+++ b/fs/ext2/ialloc.c
@@ -80,6 +80,7 @@ static void ext2_release_inode(struct super_block *sb, int group, int dir)
 	if (dir)
 		le16_add_cpu(&desc->bg_used_dirs_count, -1);
 	spin_unlock(sb_bgl_lock(EXT2_SB(sb), group));
+	percpu_counter_inc(&EXT2_SB(sb)->s_freeinodes_counter);
 	if (dir)
 		percpu_counter_dec(&EXT2_SB(sb)->s_dirs_counter);
 	mark_buffer_dirty(bh);
@@ -529,7 +530,7 @@ got:
 		goto fail;
 	}
 
-	percpu_counter_add(&sbi->s_freeinodes_counter, -1);
+	percpu_counter_dec(&sbi->s_freeinodes_counter);
 	if (S_ISDIR(mode))
 		percpu_counter_inc(&sbi->s_dirs_counter);
 
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 1d7ab73b1014..ecf756630c22 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -1082,9 +1082,9 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 
 	if (EXT2_BLOCKS_PER_GROUP(sb) == 0)
 		goto cantfind_ext2;
- 	sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) -
- 				le32_to_cpu(es->s_first_data_block) - 1)
- 					/ EXT2_BLOCKS_PER_GROUP(sb)) + 1;
+	sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) -
+				le32_to_cpu(es->s_first_data_block) - 1)
+					/ EXT2_BLOCKS_PER_GROUP(sb)) + 1;
 	db_count = (sbi->s_groups_count + EXT2_DESC_PER_BLOCK(sb) - 1) /
 		   EXT2_DESC_PER_BLOCK(sb);
 	sbi->s_group_desc = kmalloc_array (db_count,
diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c
index 1e33e0ac8cf1..4dc725d8b0c7 100644
--- a/fs/ext2/xattr.c
+++ b/fs/ext2/xattr.c
@@ -56,6 +56,7 @@
 
 #include <linux/buffer_head.h>
 #include <linux/init.h>
+#include <linux/printk.h>
 #include <linux/slab.h>
 #include <linux/mbcache.h>
 #include <linux/quotaops.h>
@@ -84,8 +85,8 @@
 		printk("\n"); \
 	} while (0)
 #else
-# define ea_idebug(f...)
-# define ea_bdebug(f...)
+# define ea_idebug(inode, f...)	no_printk(f)
+# define ea_bdebug(bh, f...)	no_printk(f)
 #endif
 
 static int ext2_xattr_set2(struct inode *, struct buffer_head *,
@@ -840,8 +841,7 @@ ext2_xattr_cache_insert(struct mb_cache *cache, struct buffer_head *bh)
 				      true);
 	if (error) {
 		if (error == -EBUSY) {
-			ea_bdebug(bh, "already in cache (%d cache entries)",
-				atomic_read(&ext2_xattr_cache->c_entry_count));
+			ea_bdebug(bh, "already in cache");
 			error = 0;
 		}
 	} else
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index e5d6ee61ff48..f9645de9d04c 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -270,6 +270,7 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb,
 	ext4_group_t ngroups = ext4_get_groups_count(sb);
 	struct ext4_group_desc *desc;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct buffer_head *bh_p;
 
 	if (block_group >= ngroups) {
 		ext4_error(sb, "block_group >= groups_count - block_group = %u,"
@@ -280,7 +281,14 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb,
 
 	group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb);
 	offset = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1);
-	if (!sbi->s_group_desc[group_desc]) {
+	bh_p = sbi_array_rcu_deref(sbi, s_group_desc, group_desc);
+	/*
+	 * sbi_array_rcu_deref returns with rcu unlocked, this is ok since
+	 * the pointer being dereferenced won't be dereferenced again. By
+	 * looking at the usage in add_new_gdb() the value isn't modified,
+	 * just the pointer, and so it remains valid.
+	 */
+	if (!bh_p) {
 		ext4_error(sb, "Group descriptor not loaded - "
 			   "block_group = %u, group_desc = %u, desc = %u",
 			   block_group, group_desc, offset);
@@ -288,10 +296,10 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb,
 	}
 
 	desc = (struct ext4_group_desc *)(
-		(__u8 *)sbi->s_group_desc[group_desc]->b_data +
+		(__u8 *)bh_p->b_data +
 		offset * EXT4_DESC_SIZE(sb));
 	if (bh)
-		*bh = sbi->s_group_desc[group_desc];
+		*bh = bh_p;
 	return desc;
 }
 
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 83899b890e61..dd8bc705f0e3 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -127,12 +127,14 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 		if (err != ERR_BAD_DX_DIR) {
 			return err;
 		}
-		/*
-		 * We don't set the inode dirty flag since it's not
-		 * critical that it get flushed back to the disk.
-		 */
-		ext4_clear_inode_flag(file_inode(file),
-				      EXT4_INODE_INDEX);
+		/* Can we just clear INDEX flag to ignore htree information? */
+		if (!ext4_has_metadata_csum(sb)) {
+			/*
+			 * We don't set the inode dirty flag since it's not
+			 * critical that it gets flushed back to the disk.
+			 */
+			ext4_clear_inode_flag(inode, EXT4_INODE_INDEX);
+		}
 	}
 
 	if (ext4_has_inline_data(inode)) {
@@ -671,24 +673,44 @@ static int ext4_d_compare(const struct dentry *dentry, unsigned int len,
 			  const char *str, const struct qstr *name)
 {
 	struct qstr qstr = {.name = str, .len = len };
+	const struct dentry *parent = READ_ONCE(dentry->d_parent);
+	const struct inode *inode = READ_ONCE(parent->d_inode);
+	char strbuf[DNAME_INLINE_LEN];
 
-	if (!IS_CASEFOLDED(dentry->d_parent->d_inode)) {
+	if (!inode || !IS_CASEFOLDED(inode) ||
+	    !EXT4_SB(inode->i_sb)->s_encoding) {
 		if (len != name->len)
 			return -1;
 		return memcmp(str, name->name, len);
 	}
 
-	return ext4_ci_compare(dentry->d_parent->d_inode, name, &qstr);
+	/*
+	 * If the dentry name is stored in-line, then it may be concurrently
+	 * modified by a rename.  If this happens, the VFS will eventually retry
+	 * the lookup, so it doesn't matter what ->d_compare() returns.
+	 * However, it's unsafe to call utf8_strncasecmp() with an unstable
+	 * string.  Therefore, we have to copy the name into a temporary buffer.
+	 */
+	if (len <= DNAME_INLINE_LEN - 1) {
+		memcpy(strbuf, str, len);
+		strbuf[len] = 0;
+		qstr.name = strbuf;
+		/* prevent compiler from optimizing out the temporary buffer */
+		barrier();
+	}
+
+	return ext4_ci_compare(inode, name, &qstr, false);
 }
 
 static int ext4_d_hash(const struct dentry *dentry, struct qstr *str)
 {
 	const struct ext4_sb_info *sbi = EXT4_SB(dentry->d_sb);
 	const struct unicode_map *um = sbi->s_encoding;
+	const struct inode *inode = READ_ONCE(dentry->d_inode);
 	unsigned char *norm;
 	int len, ret = 0;
 
-	if (!IS_CASEFOLDED(dentry->d_inode))
+	if (!inode || !IS_CASEFOLDED(inode) || !um)
 		return 0;
 
 	norm = kmalloc(PATH_MAX, GFP_ATOMIC);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 0014b1c5e6be..490e34ad927c 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1379,7 +1379,7 @@ struct ext4_sb_info {
 	loff_t s_bitmap_maxbytes;	/* max bytes for bitmap files */
 	struct buffer_head * s_sbh;	/* Buffer containing the super block */
 	struct ext4_super_block *s_es;	/* Pointer to the super block in the buffer */
-	struct buffer_head **s_group_desc;
+	struct buffer_head * __rcu *s_group_desc;
 	unsigned int s_mount_opt;
 	unsigned int s_mount_opt2;
 	unsigned int s_mount_flags;
@@ -1441,7 +1441,7 @@ struct ext4_sb_info {
 #endif
 
 	/* for buddy allocator */
-	struct ext4_group_info ***s_group_info;
+	struct ext4_group_info ** __rcu *s_group_info;
 	struct inode *s_buddy_cache;
 	spinlock_t s_md_lock;
 	unsigned short *s_mb_offsets;
@@ -1491,7 +1491,7 @@ struct ext4_sb_info {
 	unsigned int s_extent_max_zeroout_kb;
 
 	unsigned int s_log_groups_per_flex;
-	struct flex_groups *s_flex_groups;
+	struct flex_groups * __rcu *s_flex_groups;
 	ext4_group_t s_flex_groups_allocated;
 
 	/* workqueue for reserved extent conversions (buffered io) */
@@ -1531,8 +1531,11 @@ struct ext4_sb_info {
 	struct ratelimit_state s_warning_ratelimit_state;
 	struct ratelimit_state s_msg_ratelimit_state;
 
-	/* Barrier between changing inodes' journal flags and writepages ops. */
-	struct percpu_rw_semaphore s_journal_flag_rwsem;
+	/*
+	 * Barrier between writepages ops and changing any inode's JOURNAL_DATA
+	 * or EXTENTS flag.
+	 */
+	struct percpu_rw_semaphore s_writepages_rwsem;
 	struct dax_device *s_daxdev;
 };
 
@@ -2074,6 +2077,23 @@ struct dx_hash_info
 
 
 /*
+ * Returns: sbi->field[index]
+ * Used to access an array element from the following sbi fields which require
+ * rcu protection to avoid dereferencing an invalid pointer due to reassignment
+ * - s_group_desc
+ * - s_group_info
+ * - s_flex_group
+ */
+#define sbi_array_rcu_deref(sbi, field, index)				   \
+({									   \
+	typeof(*((sbi)->field)) _v;					   \
+	rcu_read_lock();						   \
+	_v = ((typeof(_v)*)rcu_dereference((sbi)->field))[index];	   \
+	rcu_read_unlock();						   \
+	_v;								   \
+})
+
+/*
  * Control parameters used by ext4_htree_next_block
  */
 #define HASH_NB_ALWAYS		1
@@ -2085,6 +2105,9 @@ struct ext4_filename {
 #ifdef CONFIG_FS_ENCRYPTION
 	struct fscrypt_str crypto_buf;
 #endif
+#ifdef CONFIG_UNICODE
+	struct fscrypt_str cf_name;
+#endif
 };
 
 #define fname_name(p) ((p)->disk_name.name)
@@ -2310,6 +2333,12 @@ extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
 					      struct ext4_group_desc *gdp);
 ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
 
+#ifdef CONFIG_UNICODE
+extern void ext4_fname_setup_ci_filename(struct inode *dir,
+					 const struct qstr *iname,
+					 struct fscrypt_str *fname);
+#endif
+
 #ifdef CONFIG_FS_ENCRYPTION
 static inline void ext4_fname_from_fscrypt_name(struct ext4_filename *dst,
 						const struct fscrypt_name *src)
@@ -2336,6 +2365,10 @@ static inline int ext4_fname_setup_filename(struct inode *dir,
 		return err;
 
 	ext4_fname_from_fscrypt_name(fname, &name);
+
+#ifdef CONFIG_UNICODE
+	ext4_fname_setup_ci_filename(dir, iname, &fname->cf_name);
+#endif
 	return 0;
 }
 
@@ -2351,6 +2384,10 @@ static inline int ext4_fname_prepare_lookup(struct inode *dir,
 		return err;
 
 	ext4_fname_from_fscrypt_name(fname, &name);
+
+#ifdef CONFIG_UNICODE
+	ext4_fname_setup_ci_filename(dir, &dentry->d_name, &fname->cf_name);
+#endif
 	return 0;
 }
 
@@ -2364,6 +2401,11 @@ static inline void ext4_fname_free_filename(struct ext4_filename *fname)
 	fname->crypto_buf.name = NULL;
 	fname->usr_fname = NULL;
 	fname->disk_name.name = NULL;
+
+#ifdef CONFIG_UNICODE
+	kfree(fname->cf_name.name);
+	fname->cf_name.name = NULL;
+#endif
 }
 #else /* !CONFIG_FS_ENCRYPTION */
 static inline int ext4_fname_setup_filename(struct inode *dir,
@@ -2374,6 +2416,11 @@ static inline int ext4_fname_setup_filename(struct inode *dir,
 	fname->usr_fname = iname;
 	fname->disk_name.name = (unsigned char *) iname->name;
 	fname->disk_name.len = iname->len;
+
+#ifdef CONFIG_UNICODE
+	ext4_fname_setup_ci_filename(dir, iname, &fname->cf_name);
+#endif
+
 	return 0;
 }
 
@@ -2384,7 +2431,13 @@ static inline int ext4_fname_prepare_lookup(struct inode *dir,
 	return ext4_fname_setup_filename(dir, &dentry->d_name, 1, fname);
 }
 
-static inline void ext4_fname_free_filename(struct ext4_filename *fname) { }
+static inline void ext4_fname_free_filename(struct ext4_filename *fname)
+{
+#ifdef CONFIG_UNICODE
+	kfree(fname->cf_name.name);
+	fname->cf_name.name = NULL;
+#endif
+}
 #endif /* !CONFIG_FS_ENCRYPTION */
 
 /* dir.c */
@@ -2412,8 +2465,11 @@ void ext4_insert_dentry(struct inode *inode,
 			struct ext4_filename *fname);
 static inline void ext4_update_dx_flag(struct inode *inode)
 {
-	if (!ext4_has_feature_dir_index(inode->i_sb))
+	if (!ext4_has_feature_dir_index(inode->i_sb)) {
+		/* ext4_iget() should have caught this... */
+		WARN_ON_ONCE(ext4_has_feature_metadata_csum(inode->i_sb));
 		ext4_clear_inode_flag(inode, EXT4_INODE_INDEX);
+	}
 }
 static const unsigned char ext4_filetype_table[] = {
 	DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
@@ -2599,6 +2655,7 @@ extern int ext4_generic_delete_entry(handle_t *handle,
 extern bool ext4_empty_dir(struct inode *inode);
 
 /* resize.c */
+extern void ext4_kvfree_array_rcu(void *to_free);
 extern int ext4_group_add(struct super_block *sb,
 				struct ext4_new_group_data *input);
 extern int ext4_group_extend(struct super_block *sb,
@@ -2846,13 +2903,13 @@ static inline
 struct ext4_group_info *ext4_get_group_info(struct super_block *sb,
 					    ext4_group_t group)
 {
-	 struct ext4_group_info ***grp_info;
+	 struct ext4_group_info **grp_info;
 	 long indexv, indexh;
 	 BUG_ON(group >= EXT4_SB(sb)->s_groups_count);
-	 grp_info = EXT4_SB(sb)->s_group_info;
 	 indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb));
 	 indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1);
-	 return grp_info[indexv][indexh];
+	 grp_info = sbi_array_rcu_deref(EXT4_SB(sb), s_group_info, indexv);
+	 return grp_info[indexh];
 }
 
 /*
@@ -2902,7 +2959,7 @@ static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
 		     !inode_is_locked(inode));
 	down_write(&EXT4_I(inode)->i_data_sem);
 	if (newsize > EXT4_I(inode)->i_disksize)
-		EXT4_I(inode)->i_disksize = newsize;
+		WRITE_ONCE(EXT4_I(inode)->i_disksize, newsize);
 	up_write(&EXT4_I(inode)->i_data_sem);
 }
 
@@ -3127,8 +3184,8 @@ extern int ext4_handle_dirty_dirent_node(handle_t *handle,
 					 struct inode *inode,
 					 struct buffer_head *bh);
 extern int ext4_ci_compare(const struct inode *parent,
-			   const struct qstr *name,
-			   const struct qstr *entry);
+			   const struct qstr *fname,
+			   const struct qstr *entry, bool quick);
 
 #define S_SHIFT 12
 static const unsigned char ext4_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = {
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 98bd0e9ee7df..ca78fd709845 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -170,10 +170,13 @@ struct partial_cluster {
 	(EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1)
 #define EXT_LAST_INDEX(__hdr__) \
 	(EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1)
-#define EXT_MAX_EXTENT(__hdr__) \
-	(EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)
+#define EXT_MAX_EXTENT(__hdr__)	\
+	((le16_to_cpu((__hdr__)->eh_max)) ? \
+	((EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)) \
+					: 0)
 #define EXT_MAX_INDEX(__hdr__) \
-	(EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)
+	((le16_to_cpu((__hdr__)->eh_max)) ? \
+	((EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)) : 0)
 
 static inline struct ext4_extent_header *ext_inode_hdr(struct inode *inode)
 {
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 7a72cde366f7..cfcdc7f0d19e 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -498,6 +498,30 @@ int ext4_ext_check_inode(struct inode *inode)
 	return ext4_ext_check(inode, ext_inode_hdr(inode), ext_depth(inode), 0);
 }
 
+static void ext4_cache_extents(struct inode *inode,
+			       struct ext4_extent_header *eh)
+{
+	struct ext4_extent *ex = EXT_FIRST_EXTENT(eh);
+	ext4_lblk_t prev = 0;
+	int i;
+
+	for (i = le16_to_cpu(eh->eh_entries); i > 0; i--, ex++) {
+		unsigned int status = EXTENT_STATUS_WRITTEN;
+		ext4_lblk_t lblk = le32_to_cpu(ex->ee_block);
+		int len = ext4_ext_get_actual_len(ex);
+
+		if (prev && (prev != lblk))
+			ext4_es_cache_extent(inode, prev, lblk - prev, ~0,
+					     EXTENT_STATUS_HOLE);
+
+		if (ext4_ext_is_unwritten(ex))
+			status = EXTENT_STATUS_UNWRITTEN;
+		ext4_es_cache_extent(inode, lblk, len,
+				     ext4_ext_pblock(ex), status);
+		prev = lblk + len;
+	}
+}
+
 static struct buffer_head *
 __read_extent_tree_block(const char *function, unsigned int line,
 			 struct inode *inode, ext4_fsblk_t pblk, int depth,
@@ -532,26 +556,7 @@ __read_extent_tree_block(const char *function, unsigned int line,
 	 */
 	if (!(flags & EXT4_EX_NOCACHE) && depth == 0) {
 		struct ext4_extent_header *eh = ext_block_hdr(bh);
-		struct ext4_extent *ex = EXT_FIRST_EXTENT(eh);
-		ext4_lblk_t prev = 0;
-		int i;
-
-		for (i = le16_to_cpu(eh->eh_entries); i > 0; i--, ex++) {
-			unsigned int status = EXTENT_STATUS_WRITTEN;
-			ext4_lblk_t lblk = le32_to_cpu(ex->ee_block);
-			int len = ext4_ext_get_actual_len(ex);
-
-			if (prev && (prev != lblk))
-				ext4_es_cache_extent(inode, prev,
-						     lblk - prev, ~0,
-						     EXTENT_STATUS_HOLE);
-
-			if (ext4_ext_is_unwritten(ex))
-				status = EXTENT_STATUS_UNWRITTEN;
-			ext4_es_cache_extent(inode, lblk, len,
-					     ext4_ext_pblock(ex), status);
-			prev = lblk + len;
-		}
+		ext4_cache_extents(inode, eh);
 	}
 	return bh;
 errout:
@@ -899,6 +904,8 @@ ext4_find_extent(struct inode *inode, ext4_lblk_t block,
 	path[0].p_bh = NULL;
 
 	i = depth;
+	if (!(flags & EXT4_EX_NOCACHE) && depth == 0)
+		ext4_cache_extents(inode, eh);
 	/* walk through the tree */
 	while (i) {
 		ext_debug("depth %d: num %d, max %d\n",
@@ -2957,7 +2964,7 @@ again:
 			 * in use to avoid freeing it when removing blocks.
 			 */
 			if (sbi->s_cluster_ratio > 1) {
-				pblk = ext4_ext_pblock(ex) + end - ee_block + 2;
+				pblk = ext4_ext_pblock(ex) + end - ee_block + 1;
 				partial.pclu = EXT4_B2C(sbi, pblk);
 				partial.state = nofree;
 			}
@@ -3503,8 +3510,8 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 		(unsigned long long)map->m_lblk, map_len);
 
 	sbi = EXT4_SB(inode->i_sb);
-	eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >>
-		inode->i_sb->s_blocksize_bits;
+	eof_block = (EXT4_I(inode)->i_disksize + inode->i_sb->s_blocksize - 1)
+			>> inode->i_sb->s_blocksize_bits;
 	if (eof_block < map->m_lblk + map_len)
 		eof_block = map->m_lblk + map_len;
 
@@ -3759,8 +3766,8 @@ static int ext4_split_convert_extents(handle_t *handle,
 		  __func__, inode->i_ino,
 		  (unsigned long long)map->m_lblk, map->m_len);
 
-	eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >>
-		inode->i_sb->s_blocksize_bits;
+	eof_block = (EXT4_I(inode)->i_disksize + inode->i_sb->s_blocksize - 1)
+			>> inode->i_sb->s_blocksize_bits;
 	if (eof_block < map->m_lblk + map->m_len)
 		eof_block = map->m_lblk + map->m_len;
 	/*
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index f4a24a46245e..52d155b4e733 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -40,9 +40,10 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	struct inode *inode = file_inode(iocb->ki_filp);
 	ssize_t ret;
 
-	if (!inode_trylock_shared(inode)) {
-		if (iocb->ki_flags & IOCB_NOWAIT)
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!inode_trylock_shared(inode))
 			return -EAGAIN;
+	} else {
 		inode_lock_shared(inode);
 	}
 	/*
@@ -190,9 +191,10 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct inode *inode = file_inode(iocb->ki_filp);
 	ssize_t ret;
 
-	if (!inode_trylock(inode)) {
-		if (iocb->ki_flags & IOCB_NOWAIT)
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!inode_trylock(inode))
 			return -EAGAIN;
+	} else {
 		inode_lock(inode);
 	}
 	ret = ext4_write_checks(iocb, from);
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 5508baa11bb6..8a28d47bd502 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -44,30 +44,28 @@
  */
 static int ext4_sync_parent(struct inode *inode)
 {
-	struct dentry *dentry = NULL;
-	struct inode *next;
+	struct dentry *dentry, *next;
 	int ret = 0;
 
 	if (!ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY))
 		return 0;
-	inode = igrab(inode);
+	dentry = d_find_any_alias(inode);
+	if (!dentry)
+		return 0;
 	while (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
 		ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY);
-		dentry = d_find_any_alias(inode);
-		if (!dentry)
-			break;
-		next = igrab(d_inode(dentry->d_parent));
+
+		next = dget_parent(dentry);
 		dput(dentry);
-		if (!next)
-			break;
-		iput(inode);
-		inode = next;
+		dentry = next;
+		inode = dentry->d_inode;
+
 		/*
 		 * The directory inode may have gone through rmdir by now. But
 		 * the inode itself and its blocks are still allocated (we hold
-		 * a reference to the inode so it didn't go through
-		 * ext4_evict_inode()) and so we are safe to flush metadata
-		 * blocks and the inode.
+		 * a reference to the inode via its dentry), so it didn't go
+		 * through ext4_evict_inode()) and so we are safe to flush
+		 * metadata blocks and the inode.
 		 */
 		ret = sync_mapping_buffers(inode->i_mapping);
 		if (ret)
@@ -76,7 +74,7 @@ static int ext4_sync_parent(struct inode *inode)
 		if (ret)
 			break;
 	}
-	iput(inode);
+	dput(dentry);
 	return ret;
 }
 
diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c
index d358bfcb6b3f..3e133793a5a3 100644
--- a/fs/ext4/hash.c
+++ b/fs/ext4/hash.c
@@ -280,7 +280,7 @@ int ext4fs_dirhash(const struct inode *dir, const char *name, int len,
 	unsigned char *buff;
 	struct qstr qstr = {.name = name, .len = len };
 
-	if (len && IS_CASEFOLDED(dir)) {
+	if (len && IS_CASEFOLDED(dir) && um) {
 		buff = kzalloc(sizeof(char) * PATH_MAX, GFP_KERNEL);
 		if (!buff)
 			return -ENOMEM;
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 764ff4c56233..c5590ffc44b5 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -330,11 +330,13 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 
 	percpu_counter_inc(&sbi->s_freeinodes_counter);
 	if (sbi->s_log_groups_per_flex) {
-		ext4_group_t f = ext4_flex_group(sbi, block_group);
+		struct flex_groups *fg;
 
-		atomic_inc(&sbi->s_flex_groups[f].free_inodes);
+		fg = sbi_array_rcu_deref(sbi, s_flex_groups,
+					 ext4_flex_group(sbi, block_group));
+		atomic_inc(&fg->free_inodes);
 		if (is_directory)
-			atomic_dec(&sbi->s_flex_groups[f].used_dirs);
+			atomic_dec(&fg->used_dirs);
 	}
 	BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata");
 	fatal = ext4_handle_dirty_metadata(handle, NULL, bh2);
@@ -370,12 +372,13 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g,
 			    int flex_size, struct orlov_stats *stats)
 {
 	struct ext4_group_desc *desc;
-	struct flex_groups *flex_group = EXT4_SB(sb)->s_flex_groups;
 
 	if (flex_size > 1) {
-		stats->free_inodes = atomic_read(&flex_group[g].free_inodes);
-		stats->free_clusters = atomic64_read(&flex_group[g].free_clusters);
-		stats->used_dirs = atomic_read(&flex_group[g].used_dirs);
+		struct flex_groups *fg = sbi_array_rcu_deref(EXT4_SB(sb),
+							     s_flex_groups, g);
+		stats->free_inodes = atomic_read(&fg->free_inodes);
+		stats->free_clusters = atomic64_read(&fg->free_clusters);
+		stats->used_dirs = atomic_read(&fg->used_dirs);
 		return;
 	}
 
@@ -662,7 +665,7 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
  * block has been written back to disk.  (Yes, these values are
  * somewhat arbitrary...)
  */
-#define RECENTCY_MIN	5
+#define RECENTCY_MIN	60
 #define RECENTCY_DIRTY	300
 
 static int recently_deleted(struct super_block *sb, ext4_group_t group, int ino)
@@ -1056,7 +1059,8 @@ got:
 		if (sbi->s_log_groups_per_flex) {
 			ext4_group_t f = ext4_flex_group(sbi, group);
 
-			atomic_inc(&sbi->s_flex_groups[f].used_dirs);
+			atomic_inc(&sbi_array_rcu_deref(sbi, s_flex_groups,
+							f)->used_dirs);
 		}
 	}
 	if (ext4_has_group_desc_csum(sb)) {
@@ -1079,7 +1083,8 @@ got:
 
 	if (sbi->s_log_groups_per_flex) {
 		flex_group = ext4_flex_group(sbi, group);
-		atomic_dec(&sbi->s_flex_groups[flex_group].free_inodes);
+		atomic_dec(&sbi_array_rcu_deref(sbi, s_flex_groups,
+						flex_group)->free_inodes);
 	}
 
 	inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 3092b2ef0614..7335cff90a7d 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2154,7 +2154,7 @@ static int ext4_writepage(struct page *page,
 	bool keep_towrite = false;
 
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) {
-		ext4_invalidatepage(page, 0, PAGE_SIZE);
+		inode->i_mapping->a_ops->invalidatepage(page, 0, PAGE_SIZE);
 		unlock_page(page);
 		return -EIO;
 	}
@@ -2591,7 +2591,7 @@ update_disksize:
 	 * truncate are avoided by checking i_size under i_data_sem.
 	 */
 	disksize = ((loff_t)mpd->first_page) << PAGE_SHIFT;
-	if (disksize > EXT4_I(inode)->i_disksize) {
+	if (disksize > READ_ONCE(EXT4_I(inode)->i_disksize)) {
 		int err2;
 		loff_t i_size;
 
@@ -2752,7 +2752,7 @@ static int ext4_writepages(struct address_space *mapping,
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
 		return -EIO;
 
-	percpu_down_read(&sbi->s_journal_flag_rwsem);
+	percpu_down_read(&sbi->s_writepages_rwsem);
 	trace_ext4_writepages(inode, wbc);
 
 	/*
@@ -2973,7 +2973,7 @@ unplug:
 out_writepages:
 	trace_ext4_writepages_result(inode, wbc, ret,
 				     nr_to_write - wbc->nr_to_write);
-	percpu_up_read(&sbi->s_journal_flag_rwsem);
+	percpu_up_read(&sbi->s_writepages_rwsem);
 	return ret;
 }
 
@@ -2988,13 +2988,13 @@ static int ext4_dax_writepages(struct address_space *mapping,
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
 		return -EIO;
 
-	percpu_down_read(&sbi->s_journal_flag_rwsem);
+	percpu_down_read(&sbi->s_writepages_rwsem);
 	trace_ext4_writepages(inode, wbc);
 
 	ret = dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev, wbc);
 	trace_ext4_writepages_result(inode, wbc, ret,
 				     nr_to_write - wbc->nr_to_write);
-	percpu_up_read(&sbi->s_journal_flag_rwsem);
+	percpu_up_read(&sbi->s_writepages_rwsem);
 	return ret;
 }
 
@@ -3872,6 +3872,11 @@ static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter)
 	struct inode *inode = mapping->host;
 	size_t count = iov_iter_count(iter);
 	ssize_t ret;
+	loff_t offset = iocb->ki_pos;
+	loff_t size = i_size_read(inode);
+
+	if (offset >= size)
+		return 0;
 
 	/*
 	 * Shared inode_lock is enough for us - it protects against concurrent
@@ -4713,7 +4718,7 @@ make_io:
 			if (end > table)
 				end = table;
 			while (b <= end)
-				sb_breadahead(sb, b++);
+				sb_breadahead_unmovable(sb, b++);
 		}
 
 		/*
@@ -5000,6 +5005,18 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 		ret = -EFSCORRUPTED;
 		goto bad_inode;
 	}
+	/*
+	 * If dir_index is not enabled but there's dir with INDEX flag set,
+	 * we'd normally treat htree data as empty space. But with metadata
+	 * checksumming that corrupts checksums so forbid that.
+	 */
+	if (!ext4_has_feature_dir_index(sb) && ext4_has_metadata_csum(sb) &&
+	    ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) {
+		ext4_error_inode(inode, function, line, 0,
+			 "iget: Dir with htree data on filesystem without dir_index feature.");
+		ret = -EFSCORRUPTED;
+		goto bad_inode;
+	}
 	ei->i_disksize = inode->i_size;
 #ifdef CONFIG_QUOTA
 	ei->i_reserved_quota = 0;
@@ -5137,6 +5154,9 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 				 "iget: bogus i_mode (%o)", inode->i_mode);
 		goto bad_inode;
 	}
+	if (IS_CASEFOLDED(inode) && !ext4_has_feature_casefold(inode->i_sb))
+		ext4_error_inode(inode, function, line, 0,
+				 "casefold flag without casefold feature");
 	brelse(iloc.bh);
 
 	unlock_new_inode(inode);
@@ -5153,7 +5173,7 @@ static int ext4_inode_blocks_set(handle_t *handle,
 				struct ext4_inode_info *ei)
 {
 	struct inode *inode = &(ei->vfs_inode);
-	u64 i_blocks = inode->i_blocks;
+	u64 i_blocks = READ_ONCE(inode->i_blocks);
 	struct super_block *sb = inode->i_sb;
 
 	if (i_blocks <= ~0U) {
@@ -6190,7 +6210,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 		}
 	}
 
-	percpu_down_write(&sbi->s_journal_flag_rwsem);
+	percpu_down_write(&sbi->s_writepages_rwsem);
 	jbd2_journal_lock_updates(journal);
 
 	/*
@@ -6207,7 +6227,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 		err = jbd2_journal_flush(journal);
 		if (err < 0) {
 			jbd2_journal_unlock_updates(journal);
-			percpu_up_write(&sbi->s_journal_flag_rwsem);
+			percpu_up_write(&sbi->s_writepages_rwsem);
 			return err;
 		}
 		ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
@@ -6215,7 +6235,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 	ext4_set_aops(inode);
 
 	jbd2_journal_unlock_updates(journal);
-	percpu_up_write(&sbi->s_journal_flag_rwsem);
+	percpu_up_write(&sbi->s_writepages_rwsem);
 
 	if (val)
 		up_write(&EXT4_I(inode)->i_mmap_sem);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 99ba720dbb7a..baf0cd18f17c 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1936,7 +1936,8 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
 	int free;
 
 	free = e4b->bd_info->bb_free;
-	BUG_ON(free <= 0);
+	if (WARN_ON(free <= 0))
+		return;
 
 	i = e4b->bd_info->bb_first_free;
 
@@ -1959,7 +1960,8 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
 		}
 
 		mb_find_extent(e4b, i, ac->ac_g_ex.fe_len, &ex);
-		BUG_ON(ex.fe_len <= 0);
+		if (WARN_ON(ex.fe_len <= 0))
+			break;
 		if (free < ex.fe_len) {
 			ext4_grp_locked_error(sb, e4b->bd_group, 0, 0,
 					"%d free clusters as per "
@@ -2356,7 +2358,7 @@ int ext4_mb_alloc_groupinfo(struct super_block *sb, ext4_group_t ngroups)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	unsigned size;
-	struct ext4_group_info ***new_groupinfo;
+	struct ext4_group_info ***old_groupinfo, ***new_groupinfo;
 
 	size = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >>
 		EXT4_DESC_PER_BLOCK_BITS(sb);
@@ -2369,13 +2371,16 @@ int ext4_mb_alloc_groupinfo(struct super_block *sb, ext4_group_t ngroups)
 		ext4_msg(sb, KERN_ERR, "can't allocate buddy meta group");
 		return -ENOMEM;
 	}
-	if (sbi->s_group_info) {
-		memcpy(new_groupinfo, sbi->s_group_info,
+	rcu_read_lock();
+	old_groupinfo = rcu_dereference(sbi->s_group_info);
+	if (old_groupinfo)
+		memcpy(new_groupinfo, old_groupinfo,
 		       sbi->s_group_info_size * sizeof(*sbi->s_group_info));
-		kvfree(sbi->s_group_info);
-	}
-	sbi->s_group_info = new_groupinfo;
+	rcu_read_unlock();
+	rcu_assign_pointer(sbi->s_group_info, new_groupinfo);
 	sbi->s_group_info_size = size / sizeof(*sbi->s_group_info);
+	if (old_groupinfo)
+		ext4_kvfree_array_rcu(old_groupinfo);
 	ext4_debug("allocated s_groupinfo array for %d meta_bg's\n", 
 		   sbi->s_group_info_size);
 	return 0;
@@ -2387,6 +2392,7 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
 {
 	int i;
 	int metalen = 0;
+	int idx = group >> EXT4_DESC_PER_BLOCK_BITS(sb);
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_group_info **meta_group_info;
 	struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits);
@@ -2405,12 +2411,12 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
 				 "for a buddy group");
 			goto exit_meta_group_info;
 		}
-		sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)] =
-			meta_group_info;
+		rcu_read_lock();
+		rcu_dereference(sbi->s_group_info)[idx] = meta_group_info;
+		rcu_read_unlock();
 	}
 
-	meta_group_info =
-		sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)];
+	meta_group_info = sbi_array_rcu_deref(sbi, s_group_info, idx);
 	i = group & (EXT4_DESC_PER_BLOCK(sb) - 1);
 
 	meta_group_info[i] = kmem_cache_zalloc(cachep, GFP_NOFS);
@@ -2458,8 +2464,13 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
 exit_group_info:
 	/* If a meta_group_info table has been allocated, release it now */
 	if (group % EXT4_DESC_PER_BLOCK(sb) == 0) {
-		kfree(sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)]);
-		sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)] = NULL;
+		struct ext4_group_info ***group_info;
+
+		rcu_read_lock();
+		group_info = rcu_dereference(sbi->s_group_info);
+		kfree(group_info[idx]);
+		group_info[idx] = NULL;
+		rcu_read_unlock();
 	}
 exit_meta_group_info:
 	return -ENOMEM;
@@ -2472,6 +2483,7 @@ static int ext4_mb_init_backend(struct super_block *sb)
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	int err;
 	struct ext4_group_desc *desc;
+	struct ext4_group_info ***group_info;
 	struct kmem_cache *cachep;
 
 	err = ext4_mb_alloc_groupinfo(sb, ngroups);
@@ -2507,11 +2519,16 @@ err_freebuddy:
 	while (i-- > 0)
 		kmem_cache_free(cachep, ext4_get_group_info(sb, i));
 	i = sbi->s_group_info_size;
+	rcu_read_lock();
+	group_info = rcu_dereference(sbi->s_group_info);
 	while (i-- > 0)
-		kfree(sbi->s_group_info[i]);
+		kfree(group_info[i]);
+	rcu_read_unlock();
 	iput(sbi->s_buddy_cache);
 err_freesgi:
-	kvfree(sbi->s_group_info);
+	rcu_read_lock();
+	kvfree(rcu_dereference(sbi->s_group_info));
+	rcu_read_unlock();
 	return -ENOMEM;
 }
 
@@ -2700,7 +2717,7 @@ int ext4_mb_release(struct super_block *sb)
 	ext4_group_t ngroups = ext4_get_groups_count(sb);
 	ext4_group_t i;
 	int num_meta_group_infos;
-	struct ext4_group_info *grinfo;
+	struct ext4_group_info *grinfo, ***group_info;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits);
 
@@ -2719,9 +2736,12 @@ int ext4_mb_release(struct super_block *sb)
 		num_meta_group_infos = (ngroups +
 				EXT4_DESC_PER_BLOCK(sb) - 1) >>
 			EXT4_DESC_PER_BLOCK_BITS(sb);
+		rcu_read_lock();
+		group_info = rcu_dereference(sbi->s_group_info);
 		for (i = 0; i < num_meta_group_infos; i++)
-			kfree(sbi->s_group_info[i]);
-		kvfree(sbi->s_group_info);
+			kfree(group_info[i]);
+		kvfree(group_info);
+		rcu_read_unlock();
 	}
 	kfree(sbi->s_mb_offsets);
 	kfree(sbi->s_mb_maxs);
@@ -3020,7 +3040,8 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 		ext4_group_t flex_group = ext4_flex_group(sbi,
 							  ac->ac_b_ex.fe_group);
 		atomic64_sub(ac->ac_b_ex.fe_len,
-			     &sbi->s_flex_groups[flex_group].free_clusters);
+			     &sbi_array_rcu_deref(sbi, s_flex_groups,
+						  flex_group)->free_clusters);
 	}
 
 	err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
@@ -4913,7 +4934,8 @@ do_more:
 	if (sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
 		atomic64_add(count_clusters,
-			     &sbi->s_flex_groups[flex_group].free_clusters);
+			     &sbi_array_rcu_deref(sbi, s_flex_groups,
+						  flex_group)->free_clusters);
 	}
 
 	/*
@@ -5070,7 +5092,8 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
 	if (sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
 		atomic64_add(clusters_freed,
-			     &sbi->s_flex_groups[flex_group].free_clusters);
+			     &sbi_array_rcu_deref(sbi, s_flex_groups,
+						  flex_group)->free_clusters);
 	}
 
 	ext4_mb_unload_buddy(&e4b);
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index b1e4d359f73b..be4ee3dcc5cf 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -427,6 +427,7 @@ static int free_ext_block(handle_t *handle, struct inode *inode)
 
 int ext4_ext_migrate(struct inode *inode)
 {
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	handle_t *handle;
 	int retval = 0, i;
 	__le32 *i_data;
@@ -451,6 +452,8 @@ int ext4_ext_migrate(struct inode *inode)
 		 */
 		return retval;
 
+	percpu_down_write(&sbi->s_writepages_rwsem);
+
 	/*
 	 * Worst case we can touch the allocation bitmaps, a bgd
 	 * block, and a block to link in the orphan list.  We do need
@@ -461,7 +464,7 @@ int ext4_ext_migrate(struct inode *inode)
 
 	if (IS_ERR(handle)) {
 		retval = PTR_ERR(handle);
-		return retval;
+		goto out_unlock;
 	}
 	goal = (((inode->i_ino - 1) / EXT4_INODES_PER_GROUP(inode->i_sb)) *
 		EXT4_INODES_PER_GROUP(inode->i_sb)) + 1;
@@ -472,7 +475,7 @@ int ext4_ext_migrate(struct inode *inode)
 	if (IS_ERR(tmp_inode)) {
 		retval = PTR_ERR(tmp_inode);
 		ext4_journal_stop(handle);
-		return retval;
+		goto out_unlock;
 	}
 	i_size_write(tmp_inode, i_size_read(inode));
 	/*
@@ -514,7 +517,7 @@ int ext4_ext_migrate(struct inode *inode)
 		 */
 		ext4_orphan_del(NULL, tmp_inode);
 		retval = PTR_ERR(handle);
-		goto out;
+		goto out_tmp_inode;
 	}
 
 	ei = EXT4_I(inode);
@@ -595,10 +598,11 @@ err_out:
 	/* Reset the extent details */
 	ext4_ext_tree_init(handle, tmp_inode);
 	ext4_journal_stop(handle);
-out:
+out_tmp_inode:
 	unlock_new_inode(tmp_inode);
 	iput(tmp_inode);
-
+out_unlock:
+	percpu_up_write(&sbi->s_writepages_rwsem);
 	return retval;
 }
 
@@ -608,7 +612,8 @@ out:
 int ext4_ind_migrate(struct inode *inode)
 {
 	struct ext4_extent_header	*eh;
-	struct ext4_super_block		*es = EXT4_SB(inode->i_sb)->s_es;
+	struct ext4_sb_info		*sbi = EXT4_SB(inode->i_sb);
+	struct ext4_super_block		*es = sbi->s_es;
 	struct ext4_inode_info		*ei = EXT4_I(inode);
 	struct ext4_extent		*ex;
 	unsigned int			i, len;
@@ -632,9 +637,13 @@ int ext4_ind_migrate(struct inode *inode)
 	if (test_opt(inode->i_sb, DELALLOC))
 		ext4_alloc_da_blocks(inode);
 
+	percpu_down_write(&sbi->s_writepages_rwsem);
+
 	handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1);
-	if (IS_ERR(handle))
-		return PTR_ERR(handle);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		goto out_unlock;
+	}
 
 	down_write(&EXT4_I(inode)->i_data_sem);
 	ret = ext4_ext_check_inode(inode);
@@ -669,5 +678,7 @@ int ext4_ind_migrate(struct inode *inode)
 errout:
 	ext4_journal_stop(handle);
 	up_write(&EXT4_I(inode)->i_data_sem);
+out_unlock:
+	percpu_up_write(&sbi->s_writepages_rwsem);
 	return ret;
 }
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 2305b4374fd3..9d00e0dd2ba9 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -120,10 +120,10 @@ void __dump_mmp_msg(struct super_block *sb, struct mmp_struct *mmp,
 {
 	__ext4_warning(sb, function, line, "%s", msg);
 	__ext4_warning(sb, function, line,
-		       "MMP failure info: last update time: %llu, last update "
-		       "node: %s, last update device: %s",
-		       (long long unsigned int) le64_to_cpu(mmp->mmp_time),
-		       mmp->mmp_nodename, mmp->mmp_bdevname);
+		       "MMP failure info: last update time: %llu, last update node: %.*s, last update device: %.*s",
+		       (unsigned long long)le64_to_cpu(mmp->mmp_time),
+		       (int)sizeof(mmp->mmp_nodename), mmp->mmp_nodename,
+		       (int)sizeof(mmp->mmp_bdevname), mmp->mmp_bdevname);
 }
 
 /*
@@ -154,6 +154,7 @@ static int kmmpd(void *data)
 	mmp_check_interval = max(EXT4_MMP_CHECK_MULT * mmp_update_interval,
 				 EXT4_MMP_MIN_CHECK_INTERVAL);
 	mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
+	BUILD_BUG_ON(sizeof(mmp->mmp_bdevname) < BDEVNAME_SIZE);
 	bdevname(bh->b_bdev, mmp->mmp_bdevname);
 
 	memcpy(mmp->mmp_nodename, init_utsname()->nodename,
@@ -375,7 +376,8 @@ skip:
 	/*
 	 * Start a kernel thread to update the MMP block periodically.
 	 */
-	EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, mmpd_data, "kmmpd-%s",
+	EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, mmpd_data, "kmmpd-%.*s",
+					     (int)sizeof(mmp->mmp_bdevname),
 					     bdevname(bh->b_bdev,
 						      mmp->mmp_bdevname));
 	if (IS_ERR(EXT4_SB(sb)->s_mmp_tsk)) {
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 0146ceb40631..8e1d5912556a 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1272,19 +1272,24 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block)
 #ifdef CONFIG_UNICODE
 /*
  * Test whether a case-insensitive directory entry matches the filename
- * being searched for.
+ * being searched for.  If quick is set, assume the name being looked up
+ * is already in the casefolded form.
  *
  * Returns: 0 if the directory entry matches, more than 0 if it
  * doesn't match or less than zero on error.
  */
 int ext4_ci_compare(const struct inode *parent, const struct qstr *name,
-		    const struct qstr *entry)
+		    const struct qstr *entry, bool quick)
 {
 	const struct ext4_sb_info *sbi = EXT4_SB(parent->i_sb);
 	const struct unicode_map *um = sbi->s_encoding;
 	int ret;
 
-	ret = utf8_strncasecmp(um, name, entry);
+	if (quick)
+		ret = utf8_strncasecmp_folded(um, name, entry);
+	else
+		ret = utf8_strncasecmp(um, name, entry);
+
 	if (ret < 0) {
 		/* Handle invalid character sequence as either an error
 		 * or as an opaque byte sequence.
@@ -1300,6 +1305,32 @@ int ext4_ci_compare(const struct inode *parent, const struct qstr *name,
 
 	return ret;
 }
+
+void ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname,
+				  struct fscrypt_str *cf_name)
+{
+	int len;
+
+	if (!IS_CASEFOLDED(dir) || !EXT4_SB(dir->i_sb)->s_encoding) {
+		cf_name->name = NULL;
+		return;
+	}
+
+	cf_name->name = kmalloc(EXT4_NAME_LEN, GFP_NOFS);
+	if (!cf_name->name)
+		return;
+
+	len = utf8_casefold(EXT4_SB(dir->i_sb)->s_encoding,
+			    iname, cf_name->name,
+			    EXT4_NAME_LEN);
+	if (len <= 0) {
+		kfree(cf_name->name);
+		cf_name->name = NULL;
+		return;
+	}
+	cf_name->len = (unsigned) len;
+
+}
 #endif
 
 /*
@@ -1326,8 +1357,15 @@ static inline bool ext4_match(const struct inode *parent,
 #endif
 
 #ifdef CONFIG_UNICODE
-	if (EXT4_SB(parent->i_sb)->s_encoding && IS_CASEFOLDED(parent))
-		return (ext4_ci_compare(parent, fname->usr_fname, &entry) == 0);
+	if (EXT4_SB(parent->i_sb)->s_encoding && IS_CASEFOLDED(parent)) {
+		if (fname->cf_name.name) {
+			struct qstr cf = {.name = fname->cf_name.name,
+					  .len = fname->cf_name.len};
+			return !ext4_ci_compare(parent, &cf, &entry, true);
+		}
+		return !ext4_ci_compare(parent, fname->usr_fname, &entry,
+					false);
+	}
 #endif
 
 	return fscrypt_match_name(&f, de->name, de->name_len);
@@ -1353,8 +1391,8 @@ int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size,
 		    ext4_match(dir, fname, de)) {
 			/* found a match - just to be sure, do
 			 * a full check */
-			if (ext4_check_dir_entry(dir, NULL, de, bh, bh->b_data,
-						 bh->b_size, offset))
+			if (ext4_check_dir_entry(dir, NULL, de, bh, search_buf,
+						 buf_size, offset))
 				return -1;
 			*res_dir = de;
 			return 1;
@@ -1468,6 +1506,7 @@ restart:
 		/*
 		 * We deal with the read-ahead logic here.
 		 */
+		cond_resched();
 		if (ra_ptr >= ra_max) {
 			/* Refill the readahead buffer */
 			ra_ptr = 0;
@@ -1814,7 +1853,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 			     blocksize, hinfo, map);
 	map -= count;
 	dx_sort_map(map, count);
-	/* Split the existing block in the middle, size-wise */
+	/* Ensure that neither split block is over half full */
 	size = 0;
 	move = 0;
 	for (i = count-1; i >= 0; i--) {
@@ -1824,8 +1863,18 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 		size += map[i].size;
 		move++;
 	}
-	/* map index at which we will split */
-	split = count - move;
+	/*
+	 * map index at which we will split
+	 *
+	 * If the sum of active entries didn't exceed half the block size, just
+	 * split it in half by count; each resulting block will have at least
+	 * half the space free.
+	 */
+	if (i > 0)
+		split = count - move;
+	else
+		split = count/2;
+
 	hash2 = map[split].hash;
 	continued = hash2 == map[split - 1].hash;
 	dxtrace(printk(KERN_INFO "Split block %lu at %x, %i/%i\n",
@@ -2154,7 +2203,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
 
 #ifdef CONFIG_UNICODE
 	if (ext4_has_strict_mode(sbi) && IS_CASEFOLDED(dir) &&
-	    utf8_validate(sbi->s_encoding, &dentry->d_name))
+	    sbi->s_encoding && utf8_validate(sbi->s_encoding, &dentry->d_name))
 		return -EINVAL;
 #endif
 
@@ -2176,6 +2225,13 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
 		retval = ext4_dx_add_entry(handle, &fname, dir, inode);
 		if (!retval || (retval != ERR_BAD_DX_DIR))
 			goto out;
+		/* Can we just ignore htree data? */
+		if (ext4_has_metadata_csum(sb)) {
+			EXT4_ERROR_INODE(dir,
+				"Directory has corrupted htree index.");
+			retval = -EFSCORRUPTED;
+			goto out;
+		}
 		ext4_clear_inode_flag(dir, EXT4_INODE_INDEX);
 		dx_fallback++;
 		ext4_mark_inode_dirty(handle, dir);
@@ -2427,7 +2483,7 @@ int ext4_generic_delete_entry(handle_t *handle,
 	de = (struct ext4_dir_entry_2 *)entry_buf;
 	while (i < buf_size - csum_size) {
 		if (ext4_check_dir_entry(dir, NULL, de, bh,
-					 bh->b_data, bh->b_size, i))
+					 entry_buf, buf_size, i))
 			return -EFSCORRUPTED;
 		if (de == de_del)  {
 			if (pde)
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 4690618a92e9..6ef6f3134cc3 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -478,17 +478,26 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 	if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode) && nr_to_submit) {
 		gfp_t gfp_flags = GFP_NOFS;
 
+		/*
+		 * Since bounce page allocation uses a mempool, we can only use
+		 * a waiting mask (i.e. request guaranteed allocation) on the
+		 * first page of the bio.  Otherwise it can deadlock.
+		 */
+		if (io->io_bio)
+			gfp_flags = GFP_NOWAIT | __GFP_NOWARN;
 	retry_encrypt:
 		data_page = fscrypt_encrypt_page(inode, page, PAGE_SIZE, 0,
 						page->index, gfp_flags);
 		if (IS_ERR(data_page)) {
 			ret = PTR_ERR(data_page);
-			if (ret == -ENOMEM && wbc->sync_mode == WB_SYNC_ALL) {
-				if (io->io_bio) {
+			if (ret == -ENOMEM &&
+			    (io->io_bio || wbc->sync_mode == WB_SYNC_ALL)) {
+				gfp_flags = GFP_NOFS;
+				if (io->io_bio)
 					ext4_io_submit(io);
-					congestion_wait(BLK_RW_ASYNC, HZ/50);
-				}
-				gfp_flags |= __GFP_NOFAIL;
+				else
+					gfp_flags |= __GFP_NOFAIL;
+				congestion_wait(BLK_RW_ASYNC, HZ/50);
 				goto retry_encrypt;
 			}
 			data_page = NULL;
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index c0e9aef376a7..080e25f6ef56 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -17,6 +17,33 @@
 
 #include "ext4_jbd2.h"
 
+struct ext4_rcu_ptr {
+	struct rcu_head rcu;
+	void *ptr;
+};
+
+static void ext4_rcu_ptr_callback(struct rcu_head *head)
+{
+	struct ext4_rcu_ptr *ptr;
+
+	ptr = container_of(head, struct ext4_rcu_ptr, rcu);
+	kvfree(ptr->ptr);
+	kfree(ptr);
+}
+
+void ext4_kvfree_array_rcu(void *to_free)
+{
+	struct ext4_rcu_ptr *ptr = kzalloc(sizeof(*ptr), GFP_KERNEL);
+
+	if (ptr) {
+		ptr->ptr = to_free;
+		call_rcu(&ptr->rcu, ext4_rcu_ptr_callback);
+		return;
+	}
+	synchronize_rcu();
+	kvfree(to_free);
+}
+
 int ext4_resize_begin(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -560,8 +587,8 @@ static int setup_new_flex_group_blocks(struct super_block *sb,
 				brelse(gdb);
 				goto out;
 			}
-			memcpy(gdb->b_data, sbi->s_group_desc[j]->b_data,
-			       gdb->b_size);
+			memcpy(gdb->b_data, sbi_array_rcu_deref(sbi,
+				s_group_desc, j)->b_data, gdb->b_size);
 			set_buffer_uptodate(gdb);
 
 			err = ext4_handle_dirty_metadata(handle, NULL, gdb);
@@ -879,13 +906,15 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
 	}
 	brelse(dind);
 
-	o_group_desc = EXT4_SB(sb)->s_group_desc;
+	rcu_read_lock();
+	o_group_desc = rcu_dereference(EXT4_SB(sb)->s_group_desc);
 	memcpy(n_group_desc, o_group_desc,
 	       EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *));
+	rcu_read_unlock();
 	n_group_desc[gdb_num] = gdb_bh;
-	EXT4_SB(sb)->s_group_desc = n_group_desc;
+	rcu_assign_pointer(EXT4_SB(sb)->s_group_desc, n_group_desc);
 	EXT4_SB(sb)->s_gdb_count++;
-	kvfree(o_group_desc);
+	ext4_kvfree_array_rcu(o_group_desc);
 
 	le16_add_cpu(&es->s_reserved_gdt_blocks, -1);
 	err = ext4_handle_dirty_super(handle, sb);
@@ -929,9 +958,11 @@ static int add_new_gdb_meta_bg(struct super_block *sb,
 		return err;
 	}
 
-	o_group_desc = EXT4_SB(sb)->s_group_desc;
+	rcu_read_lock();
+	o_group_desc = rcu_dereference(EXT4_SB(sb)->s_group_desc);
 	memcpy(n_group_desc, o_group_desc,
 	       EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *));
+	rcu_read_unlock();
 	n_group_desc[gdb_num] = gdb_bh;
 
 	BUFFER_TRACE(gdb_bh, "get_write_access");
@@ -942,9 +973,9 @@ static int add_new_gdb_meta_bg(struct super_block *sb,
 		return err;
 	}
 
-	EXT4_SB(sb)->s_group_desc = n_group_desc;
+	rcu_assign_pointer(EXT4_SB(sb)->s_group_desc, n_group_desc);
 	EXT4_SB(sb)->s_gdb_count++;
-	kvfree(o_group_desc);
+	ext4_kvfree_array_rcu(o_group_desc);
 	return err;
 }
 
@@ -1210,7 +1241,8 @@ static int ext4_add_new_descs(handle_t *handle, struct super_block *sb,
 		 * use non-sparse filesystems anymore.  This is already checked above.
 		 */
 		if (gdb_off) {
-			gdb_bh = sbi->s_group_desc[gdb_num];
+			gdb_bh = sbi_array_rcu_deref(sbi, s_group_desc,
+						     gdb_num);
 			BUFFER_TRACE(gdb_bh, "get_write_access");
 			err = ext4_journal_get_write_access(handle, gdb_bh);
 
@@ -1292,7 +1324,7 @@ static int ext4_setup_new_descs(handle_t *handle, struct super_block *sb,
 		/*
 		 * get_write_access() has been called on gdb_bh by ext4_add_new_desc().
 		 */
-		gdb_bh = sbi->s_group_desc[gdb_num];
+		gdb_bh = sbi_array_rcu_deref(sbi, s_group_desc, gdb_num);
 		/* Update group descriptor block for new group */
 		gdp = (struct ext4_group_desc *)(gdb_bh->b_data +
 						 gdb_off * EXT4_DESC_SIZE(sb));
@@ -1420,11 +1452,14 @@ static void ext4_update_super(struct super_block *sb,
 		   percpu_counter_read(&sbi->s_freeclusters_counter));
 	if (ext4_has_feature_flex_bg(sb) && sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group;
+		struct flex_groups *fg;
+
 		flex_group = ext4_flex_group(sbi, group_data[0].group);
+		fg = sbi_array_rcu_deref(sbi, s_flex_groups, flex_group);
 		atomic64_add(EXT4_NUM_B2C(sbi, free_blocks),
-			     &sbi->s_flex_groups[flex_group].free_clusters);
+			     &fg->free_clusters);
 		atomic_add(EXT4_INODES_PER_GROUP(sb) * flex_gd->count,
-			   &sbi->s_flex_groups[flex_group].free_inodes);
+			   &fg->free_inodes);
 	}
 
 	/*
@@ -1519,7 +1554,8 @@ exit_journal:
 		for (; gdb_num <= gdb_num_end; gdb_num++) {
 			struct buffer_head *gdb_bh;
 
-			gdb_bh = sbi->s_group_desc[gdb_num];
+			gdb_bh = sbi_array_rcu_deref(sbi, s_group_desc,
+						     gdb_num);
 			if (old_gdb == gdb_bh->b_blocknr)
 				continue;
 			update_backups(sb, gdb_bh->b_blocknr, gdb_bh->b_data,
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 5cbd566444bc..19f2e7c77be8 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -365,12 +365,12 @@ static void __save_error_info(struct super_block *sb, const char *func,
 		return;
 	es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
 	ext4_update_tstamp(es, s_last_error_time);
-	strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func));
+	strscpy_pad(es->s_last_error_func, func, sizeof(es->s_last_error_func));
 	es->s_last_error_line = cpu_to_le32(line);
 	if (!es->s_first_error_time) {
 		es->s_first_error_time = es->s_last_error_time;
 		es->s_first_error_time_hi = es->s_last_error_time_hi;
-		strncpy(es->s_first_error_func, func,
+		strscpy_pad(es->s_first_error_func, func,
 			sizeof(es->s_first_error_func));
 		es->s_first_error_line = cpu_to_le32(line);
 		es->s_first_error_ino = es->s_last_error_ino;
@@ -389,7 +389,8 @@ static void save_error_info(struct super_block *sb, const char *func,
 			    unsigned int line)
 {
 	__save_error_info(sb, func, line);
-	ext4_commit_super(sb, 1);
+	if (!bdev_read_only(sb->s_bdev))
+		ext4_commit_super(sb, 1);
 }
 
 /*
@@ -970,6 +971,8 @@ static void ext4_put_super(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_super_block *es = sbi->s_es;
+	struct buffer_head **group_desc;
+	struct flex_groups **flex_groups;
 	int aborted = 0;
 	int i, err;
 
@@ -1000,15 +1003,23 @@ static void ext4_put_super(struct super_block *sb)
 	if (!sb_rdonly(sb))
 		ext4_commit_super(sb, 1);
 
+	rcu_read_lock();
+	group_desc = rcu_dereference(sbi->s_group_desc);
 	for (i = 0; i < sbi->s_gdb_count; i++)
-		brelse(sbi->s_group_desc[i]);
-	kvfree(sbi->s_group_desc);
-	kvfree(sbi->s_flex_groups);
+		brelse(group_desc[i]);
+	kvfree(group_desc);
+	flex_groups = rcu_dereference(sbi->s_flex_groups);
+	if (flex_groups) {
+		for (i = 0; i < sbi->s_flex_groups_allocated; i++)
+			kvfree(flex_groups[i]);
+		kvfree(flex_groups);
+	}
+	rcu_read_unlock();
 	percpu_counter_destroy(&sbi->s_freeclusters_counter);
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
 	percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
-	percpu_free_rwsem(&sbi->s_journal_flag_rwsem);
+	percpu_free_rwsem(&sbi->s_writepages_rwsem);
 #ifdef CONFIG_QUOTA
 	for (i = 0; i < EXT4_MAXQUOTAS; i++)
 		kfree(get_qf_name(sb, sbi, i));
@@ -2012,6 +2023,16 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 #endif
 	} else if (token == Opt_dax) {
 #ifdef CONFIG_FS_DAX
+		if (is_remount && test_opt(sb, DAX)) {
+			ext4_msg(sb, KERN_ERR, "can't mount with "
+				"both data=journal and dax");
+			return -1;
+		}
+		if (is_remount && !(sbi->s_mount_opt & EXT4_MOUNT_DAX)) {
+			ext4_msg(sb, KERN_ERR, "can't change "
+					"dax mount option while remounting");
+			return -1;
+		}
 		ext4_msg(sb, KERN_WARNING,
 		"DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
 		sbi->s_mount_opt |= m->mount_opt;
@@ -2272,6 +2293,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 		ext4_msg(sb, KERN_ERR, "revision level too high, "
 			 "forcing read-only mode");
 		err = -EROFS;
+		goto done;
 	}
 	if (read_only)
 		goto done;
@@ -2321,8 +2343,8 @@ done:
 int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	struct flex_groups *new_groups;
-	int size;
+	struct flex_groups **old_groups, **new_groups;
+	int size, i, j;
 
 	if (!sbi->s_log_groups_per_flex)
 		return 0;
@@ -2331,22 +2353,37 @@ int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup)
 	if (size <= sbi->s_flex_groups_allocated)
 		return 0;
 
-	size = roundup_pow_of_two(size * sizeof(struct flex_groups));
-	new_groups = kvzalloc(size, GFP_KERNEL);
+	new_groups = kvzalloc(roundup_pow_of_two(size *
+			      sizeof(*sbi->s_flex_groups)), GFP_KERNEL);
 	if (!new_groups) {
-		ext4_msg(sb, KERN_ERR, "not enough memory for %d flex groups",
-			 size / (int) sizeof(struct flex_groups));
+		ext4_msg(sb, KERN_ERR,
+			 "not enough memory for %d flex group pointers", size);
 		return -ENOMEM;
 	}
-
-	if (sbi->s_flex_groups) {
-		memcpy(new_groups, sbi->s_flex_groups,
-		       (sbi->s_flex_groups_allocated *
-			sizeof(struct flex_groups)));
-		kvfree(sbi->s_flex_groups);
+	for (i = sbi->s_flex_groups_allocated; i < size; i++) {
+		new_groups[i] = kvzalloc(roundup_pow_of_two(
+					 sizeof(struct flex_groups)),
+					 GFP_KERNEL);
+		if (!new_groups[i]) {
+			for (j = sbi->s_flex_groups_allocated; j < i; j++)
+				kvfree(new_groups[j]);
+			kvfree(new_groups);
+			ext4_msg(sb, KERN_ERR,
+				 "not enough memory for %d flex groups", size);
+			return -ENOMEM;
+		}
 	}
-	sbi->s_flex_groups = new_groups;
-	sbi->s_flex_groups_allocated = size / sizeof(struct flex_groups);
+	rcu_read_lock();
+	old_groups = rcu_dereference(sbi->s_flex_groups);
+	if (old_groups)
+		memcpy(new_groups, old_groups,
+		       (sbi->s_flex_groups_allocated *
+			sizeof(struct flex_groups *)));
+	rcu_read_unlock();
+	rcu_assign_pointer(sbi->s_flex_groups, new_groups);
+	sbi->s_flex_groups_allocated = size;
+	if (old_groups)
+		ext4_kvfree_array_rcu(old_groups);
 	return 0;
 }
 
@@ -2354,6 +2391,7 @@ static int ext4_fill_flex_info(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_group_desc *gdp = NULL;
+	struct flex_groups *fg;
 	ext4_group_t flex_group;
 	int i, err;
 
@@ -2371,12 +2409,11 @@ static int ext4_fill_flex_info(struct super_block *sb)
 		gdp = ext4_get_group_desc(sb, i, NULL);
 
 		flex_group = ext4_flex_group(sbi, i);
-		atomic_add(ext4_free_inodes_count(sb, gdp),
-			   &sbi->s_flex_groups[flex_group].free_inodes);
+		fg = sbi_array_rcu_deref(sbi, s_flex_groups, flex_group);
+		atomic_add(ext4_free_inodes_count(sb, gdp), &fg->free_inodes);
 		atomic64_add(ext4_free_group_clusters(sb, gdp),
-			     &sbi->s_flex_groups[flex_group].free_clusters);
-		atomic_add(ext4_used_dirs_count(sb, gdp),
-			   &sbi->s_flex_groups[flex_group].used_dirs);
+			     &fg->free_clusters);
+		atomic_add(ext4_used_dirs_count(sb, gdp), &fg->used_dirs);
 	}
 
 	return 1;
@@ -2950,17 +2987,11 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly)
 		return 0;
 	}
 
-#ifndef CONFIG_QUOTA
-	if (ext4_has_feature_quota(sb) && !readonly) {
-		ext4_msg(sb, KERN_ERR,
-			 "Filesystem with quota feature cannot be mounted RDWR "
-			 "without CONFIG_QUOTA");
-		return 0;
-	}
-	if (ext4_has_feature_project(sb) && !readonly) {
+#if !IS_ENABLED(CONFIG_QUOTA) || !IS_ENABLED(CONFIG_QFMT_V2)
+	if (!readonly && (ext4_has_feature_quota(sb) ||
+			  ext4_has_feature_project(sb))) {
 		ext4_msg(sb, KERN_ERR,
-			 "Filesystem with project quota feature cannot be mounted RDWR "
-			 "without CONFIG_QUOTA");
+			 "The kernel was not built with CONFIG_QUOTA and CONFIG_QFMT_V2");
 		return 0;
 	}
 #endif  /* CONFIG_QUOTA */
@@ -3531,7 +3562,8 @@ int ext4_calculate_overhead(struct super_block *sb)
 	 */
 	if (sbi->s_journal && !sbi->journal_bdev)
 		overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_maxlen);
-	else if (ext4_has_feature_journal(sb) && !sbi->s_journal) {
+	else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) {
+		/* j_inum for internal journal is non-zero */
 		j_inode = ext4_get_journal_inode(sb, j_inum);
 		if (j_inode) {
 			j_blocks = j_inode->i_size >> sb->s_blocksize_bits;
@@ -3581,9 +3613,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct dax_device *dax_dev = fs_dax_get_by_bdev(sb->s_bdev);
 	char *orig_data = kstrdup(data, GFP_KERNEL);
-	struct buffer_head *bh;
+	struct buffer_head *bh, **group_desc;
 	struct ext4_super_block *es = NULL;
 	struct ext4_sb_info *sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
+	struct flex_groups **flex_groups;
 	ext4_fsblk_t block;
 	ext4_fsblk_t sb_block = get_sb_block(&data);
 	ext4_fsblk_t logical_sb_block;
@@ -4075,7 +4108,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	if (sbi->s_inodes_per_group < sbi->s_inodes_per_block ||
 	    sbi->s_inodes_per_group > blocksize * 8) {
 		ext4_msg(sb, KERN_ERR, "invalid inodes per group: %lu\n",
-			 sbi->s_blocks_per_group);
+			 sbi->s_inodes_per_group);
 		goto failed_mount;
 	}
 	sbi->s_itb_per_group = sbi->s_inodes_per_group /
@@ -4204,9 +4237,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			EXT4_BLOCKS_PER_GROUP(sb) - 1);
 	do_div(blocks_count, EXT4_BLOCKS_PER_GROUP(sb));
 	if (blocks_count > ((uint64_t)1<<32) - EXT4_DESC_PER_BLOCK(sb)) {
-		ext4_msg(sb, KERN_WARNING, "groups count too large: %u "
+		ext4_msg(sb, KERN_WARNING, "groups count too large: %llu "
 		       "(block count %llu, first data block %u, "
-		       "blocks per group %lu)", sbi->s_groups_count,
+		       "blocks per group %lu)", blocks_count,
 		       ext4_blocks_count(es),
 		       le32_to_cpu(es->s_first_data_block),
 		       EXT4_BLOCKS_PER_GROUP(sb));
@@ -4234,9 +4267,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			goto failed_mount;
 		}
 	}
-	sbi->s_group_desc = kvmalloc_array(db_count,
-					   sizeof(struct buffer_head *),
-					   GFP_KERNEL);
+	rcu_assign_pointer(sbi->s_group_desc,
+			   kvmalloc_array(db_count,
+					  sizeof(struct buffer_head *),
+					  GFP_KERNEL));
 	if (sbi->s_group_desc == NULL) {
 		ext4_msg(sb, KERN_ERR, "not enough memory");
 		ret = -ENOMEM;
@@ -4248,18 +4282,23 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	/* Pre-read the descriptors into the buffer cache */
 	for (i = 0; i < db_count; i++) {
 		block = descriptor_loc(sb, logical_sb_block, i);
-		sb_breadahead(sb, block);
+		sb_breadahead_unmovable(sb, block);
 	}
 
 	for (i = 0; i < db_count; i++) {
+		struct buffer_head *bh;
+
 		block = descriptor_loc(sb, logical_sb_block, i);
-		sbi->s_group_desc[i] = sb_bread_unmovable(sb, block);
-		if (!sbi->s_group_desc[i]) {
+		bh = sb_bread_unmovable(sb, block);
+		if (!bh) {
 			ext4_msg(sb, KERN_ERR,
 			       "can't read group descriptor %d", i);
 			db_count = i;
 			goto failed_mount2;
 		}
+		rcu_read_lock();
+		rcu_dereference(sbi->s_group_desc)[i] = bh;
+		rcu_read_unlock();
 	}
 	sbi->s_gdb_count = db_count;
 	if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) {
@@ -4537,7 +4576,7 @@ no_journal:
 		err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0,
 					  GFP_KERNEL);
 	if (!err)
-		err = percpu_init_rwsem(&sbi->s_journal_flag_rwsem);
+		err = percpu_init_rwsem(&sbi->s_writepages_rwsem);
 
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "insufficient memory");
@@ -4625,13 +4664,19 @@ failed_mount7:
 	ext4_unregister_li_request(sb);
 failed_mount6:
 	ext4_mb_release(sb);
-	if (sbi->s_flex_groups)
-		kvfree(sbi->s_flex_groups);
+	rcu_read_lock();
+	flex_groups = rcu_dereference(sbi->s_flex_groups);
+	if (flex_groups) {
+		for (i = 0; i < sbi->s_flex_groups_allocated; i++)
+			kvfree(flex_groups[i]);
+		kvfree(flex_groups);
+	}
+	rcu_read_unlock();
 	percpu_counter_destroy(&sbi->s_freeclusters_counter);
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
 	percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
-	percpu_free_rwsem(&sbi->s_journal_flag_rwsem);
+	percpu_free_rwsem(&sbi->s_writepages_rwsem);
 failed_mount5:
 	ext4_ext_release(sb);
 	ext4_release_system_zone(sb);
@@ -4660,9 +4705,12 @@ failed_mount3:
 	if (sbi->s_mmp_tsk)
 		kthread_stop(sbi->s_mmp_tsk);
 failed_mount2:
+	rcu_read_lock();
+	group_desc = rcu_dereference(sbi->s_group_desc);
 	for (i = 0; i < db_count; i++)
-		brelse(sbi->s_group_desc[i]);
-	kvfree(sbi->s_group_desc);
+		brelse(group_desc[i]);
+	kvfree(group_desc);
+	rcu_read_unlock();
 failed_mount:
 	if (sbi->s_chksum_driver)
 		crypto_free_shash(sbi->s_chksum_driver);
@@ -5307,12 +5355,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 			err = -EINVAL;
 			goto restore_opts;
 		}
-		if (test_opt(sb, DAX)) {
-			ext4_msg(sb, KERN_ERR, "can't mount with "
-				 "both data=journal and dax");
-			err = -EINVAL;
-			goto restore_opts;
-		}
 	} else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) {
 		if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
 			ext4_msg(sb, KERN_ERR, "can't mount with "
@@ -5328,12 +5370,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 		goto restore_opts;
 	}
 
-	if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_DAX) {
-		ext4_msg(sb, KERN_WARNING, "warning: refusing change of "
-			"dax flag with busy inodes while remounting");
-		sbi->s_mount_opt ^= EXT4_MOUNT_DAX;
-	}
-
 	if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
 		ext4_abort(sb, "Abort forced by user");
 
@@ -5524,9 +5560,15 @@ static int ext4_statfs_project(struct super_block *sb,
 		return PTR_ERR(dquot);
 	spin_lock(&dquot->dq_dqb_lock);
 
-	limit = (dquot->dq_dqb.dqb_bsoftlimit ?
-		 dquot->dq_dqb.dqb_bsoftlimit :
-		 dquot->dq_dqb.dqb_bhardlimit) >> sb->s_blocksize_bits;
+	limit = 0;
+	if (dquot->dq_dqb.dqb_bsoftlimit &&
+	    (!limit || dquot->dq_dqb.dqb_bsoftlimit < limit))
+		limit = dquot->dq_dqb.dqb_bsoftlimit;
+	if (dquot->dq_dqb.dqb_bhardlimit &&
+	    (!limit || dquot->dq_dqb.dqb_bhardlimit < limit))
+		limit = dquot->dq_dqb.dqb_bhardlimit;
+	limit >>= sb->s_blocksize_bits;
+
 	if (limit && buf->f_blocks > limit) {
 		curblock = (dquot->dq_dqb.dqb_curspace +
 			    dquot->dq_dqb.dqb_rsvspace) >> sb->s_blocksize_bits;
@@ -5536,9 +5578,14 @@ static int ext4_statfs_project(struct super_block *sb,
 			 (buf->f_blocks - curblock) : 0;
 	}
 
-	limit = dquot->dq_dqb.dqb_isoftlimit ?
-		dquot->dq_dqb.dqb_isoftlimit :
-		dquot->dq_dqb.dqb_ihardlimit;
+	limit = 0;
+	if (dquot->dq_dqb.dqb_isoftlimit &&
+	    (!limit || dquot->dq_dqb.dqb_isoftlimit < limit))
+		limit = dquot->dq_dqb.dqb_isoftlimit;
+	if (dquot->dq_dqb.dqb_ihardlimit &&
+	    (!limit || dquot->dq_dqb.dqb_ihardlimit < limit))
+		limit = dquot->dq_dqb.dqb_ihardlimit;
+
 	if (limit && buf->f_files > limit) {
 		buf->f_files = limit;
 		buf->f_ffree =
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 491f9ee4040e..894a61010ae9 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -1820,8 +1820,11 @@ ext4_xattr_block_find(struct inode *inode, struct ext4_xattr_info *i,
 	if (EXT4_I(inode)->i_file_acl) {
 		/* The inode already has an extended attribute block. */
 		bs->bh = ext4_sb_bread(sb, EXT4_I(inode)->i_file_acl, REQ_PRIO);
-		if (IS_ERR(bs->bh))
-			return PTR_ERR(bs->bh);
+		if (IS_ERR(bs->bh)) {
+			error = PTR_ERR(bs->bh);
+			bs->bh = NULL;
+			return error;
+		}
 		ea_bdebug(bs->bh, "b_count=%d, refcount=%d",
 			atomic_read(&(bs->bh->b_count)),
 			le32_to_cpu(BHDR(bs->bh)->h_refcount));
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 7d9fce215f46..9889d9526ef9 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -896,8 +896,8 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi)
 	int i;
 	int err;
 
-	sbi->ckpt = f2fs_kzalloc(sbi, array_size(blk_size, cp_blks),
-				 GFP_KERNEL);
+	sbi->ckpt = f2fs_kvzalloc(sbi, array_size(blk_size, cp_blks),
+				  GFP_KERNEL);
 	if (!sbi->ckpt)
 		return -ENOMEM;
 	/*
@@ -1257,20 +1257,20 @@ static void unblock_operations(struct f2fs_sb_info *sbi)
 	f2fs_unlock_all(sbi);
 }
 
-void f2fs_wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
+void f2fs_wait_on_all_pages(struct f2fs_sb_info *sbi, int type)
 {
 	DEFINE_WAIT(wait);
 
 	for (;;) {
 		prepare_to_wait(&sbi->cp_wait, &wait, TASK_UNINTERRUPTIBLE);
 
-		if (!get_pages(sbi, F2FS_WB_CP_DATA))
+		if (!get_pages(sbi, type))
 			break;
 
 		if (unlikely(f2fs_cp_error(sbi)))
 			break;
 
-		io_schedule_timeout(5*HZ);
+		io_schedule_timeout(HZ/50);
 	}
 	finish_wait(&sbi->cp_wait, &wait);
 }
@@ -1392,8 +1392,6 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	/* Flush all the NAT/SIT pages */
 	f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
-	f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_META) &&
-					!f2fs_cp_error(sbi));
 
 	/*
 	 * modify checkpoint
@@ -1501,11 +1499,11 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	/* Here, we have one bio having CP pack except cp pack 2 page */
 	f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
-	f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_META) &&
-					!f2fs_cp_error(sbi));
+	/* Wait for all dirty meta pages to be submitted for IO */
+	f2fs_wait_on_all_pages(sbi, F2FS_DIRTY_META);
 
 	/* wait for previous submitted meta pages writeback */
-	f2fs_wait_on_all_pages_writeback(sbi);
+	f2fs_wait_on_all_pages(sbi, F2FS_WB_CP_DATA);
 
 	/* flush all device cache */
 	err = f2fs_flush_device_cache(sbi);
@@ -1514,7 +1512,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	/* barrier and flush checkpoint cp pack 2 page if it can */
 	commit_checkpoint(sbi, ckpt, start_blk);
-	f2fs_wait_on_all_pages_writeback(sbi);
+	f2fs_wait_on_all_pages(sbi, F2FS_WB_CP_DATA);
 
 	/*
 	 * invalidate intermediate page cache borrowed from meta inode
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 85f3879a31cb..facfcdbb8355 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -949,19 +949,6 @@ int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
 	int err = 0;
 	bool direct_io = iocb->ki_flags & IOCB_DIRECT;
 
-	/* convert inline data for Direct I/O*/
-	if (direct_io) {
-		err = f2fs_convert_inline_inode(inode);
-		if (err)
-			return err;
-	}
-
-	if (direct_io && allow_outplace_dio(inode, iocb, from))
-		return 0;
-
-	if (is_inode_flag_set(inode, FI_NO_PREALLOC))
-		return 0;
-
 	map.m_lblk = F2FS_BLK_ALIGN(iocb->ki_pos);
 	map.m_len = F2FS_BYTES_TO_BLK(iocb->ki_pos + iov_iter_count(from));
 	if (map.m_len > map.m_lblk)
@@ -1955,7 +1942,7 @@ static int __write_data_page(struct page *page, bool *submitted,
 	loff_t i_size = i_size_read(inode);
 	const pgoff_t end_index = ((unsigned long long) i_size)
 							>> PAGE_SHIFT;
-	loff_t psize = (page->index + 1) << PAGE_SHIFT;
+	loff_t psize = (loff_t)(page->index + 1) << PAGE_SHIFT;
 	unsigned offset = 0;
 	bool need_balance_fs = false;
 	int err = 0;
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 2341e29c1197..5a07de66b334 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -99,6 +99,7 @@ extern const char *f2fs_fault_name[FAULT_MAX];
 #define F2FS_MOUNT_INLINE_XATTR_SIZE	0x00800000
 #define F2FS_MOUNT_RESERVE_ROOT		0x01000000
 #define F2FS_MOUNT_DISABLE_CHECKPOINT	0x02000000
+#define F2FS_MOUNT_NORECOVERY		0x04000000
 
 #define F2FS_OPTION(sbi)	((sbi)->mount_opt)
 #define clear_opt(sbi, option)	(F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option)
@@ -2773,18 +2774,12 @@ static inline bool f2fs_may_extent_tree(struct inode *inode)
 static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi,
 					size_t size, gfp_t flags)
 {
-	void *ret;
-
 	if (time_to_inject(sbi, FAULT_KMALLOC)) {
 		f2fs_show_injection_info(FAULT_KMALLOC);
 		return NULL;
 	}
 
-	ret = kmalloc(size, flags);
-	if (ret)
-		return ret;
-
-	return kvmalloc(size, flags);
+	return kmalloc(size, flags);
 }
 
 static inline void *f2fs_kzalloc(struct f2fs_sb_info *sbi,
@@ -3165,7 +3160,7 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi);
 void f2fs_update_dirty_page(struct inode *inode, struct page *page);
 void f2fs_remove_dirty_inode(struct inode *inode);
 int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type);
-void f2fs_wait_on_all_pages_writeback(struct f2fs_sb_info *sbi);
+void f2fs_wait_on_all_pages(struct f2fs_sb_info *sbi, int type);
 int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc);
 void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi);
 int __init f2fs_create_checkpoint_caches(void);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 33c6e14d0c87..d676a18cb3fd 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -49,7 +49,7 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 	struct page *page = vmf->page;
 	struct inode *inode = file_inode(vmf->vma->vm_file);
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct dnode_of_data dn = { .node_changed = false };
+	struct dnode_of_data dn;
 	int err;
 
 	if (unlikely(f2fs_cp_error(sbi))) {
@@ -57,6 +57,9 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 		goto err;
 	}
 
+	/* should do out of any locked page */
+	f2fs_balance_fs(sbi, true);
+
 	sb_start_pagefault(inode->i_sb);
 
 	f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
@@ -114,8 +117,6 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 out_sem:
 	up_read(&F2FS_I(inode)->i_mmap_sem);
 
-	f2fs_balance_fs(sbi, dn.node_changed);
-
 	sb_end_pagefault(inode->i_sb);
 err:
 	return block_page_mkwrite_return(err);
@@ -1125,7 +1126,7 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
 				}
 				dn.ofs_in_node++;
 				i++;
-				new_size = (dst + i) << PAGE_SHIFT;
+				new_size = (loff_t)(dst + i) << PAGE_SHIFT;
 				if (dst_inode->i_size < new_size)
 					f2fs_i_size_write(dst_inode, new_size);
 			} while (--ilen && (do_replace[i] || blkaddr[i] == NULL_ADDR));
@@ -1943,8 +1944,15 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
 
 	if (in != F2FS_GOING_DOWN_FULLSYNC) {
 		ret = mnt_want_write_file(filp);
-		if (ret)
+		if (ret) {
+			if (ret == -EROFS) {
+				ret = 0;
+				f2fs_stop_checkpoint(sbi, false);
+				set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
+				trace_f2fs_shutdown(sbi, in, ret);
+			}
 			return ret;
+		}
 	}
 
 	switch (in) {
@@ -3084,18 +3092,41 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 				ret = -EAGAIN;
 				goto out;
 			}
-		} else {
-			preallocated = true;
-			target_size = iocb->ki_pos + iov_iter_count(from);
+			goto write;
+		}
 
-			err = f2fs_preallocate_blocks(iocb, from);
-			if (err) {
-				clear_inode_flag(inode, FI_NO_PREALLOC);
-				inode_unlock(inode);
-				ret = err;
-				goto out;
-			}
+		if (is_inode_flag_set(inode, FI_NO_PREALLOC))
+			goto write;
+
+		if (iocb->ki_flags & IOCB_DIRECT) {
+			/*
+			 * Convert inline data for Direct I/O before entering
+			 * f2fs_direct_IO().
+			 */
+			err = f2fs_convert_inline_inode(inode);
+			if (err)
+				goto out_err;
+			/*
+			 * If force_buffere_io() is true, we have to allocate
+			 * blocks all the time, since f2fs_direct_IO will fall
+			 * back to buffered IO.
+			 */
+			if (!f2fs_force_buffered_io(inode, iocb, from) &&
+					allow_outplace_dio(inode, iocb, from))
+				goto write;
+		}
+		preallocated = true;
+		target_size = iocb->ki_pos + iov_iter_count(from);
+
+		err = f2fs_preallocate_blocks(iocb, from);
+		if (err) {
+out_err:
+			clear_inode_flag(inode, FI_NO_PREALLOC);
+			inode_unlock(inode);
+			ret = err;
+			goto out;
 		}
+write:
 		ret = __generic_file_write_iter(iocb, from);
 		clear_inode_flag(inode, FI_NO_PREALLOC);
 
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 56d1da6d8333..6d44b7a9b0cc 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -782,6 +782,7 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
 
 	if (whiteout) {
 		f2fs_i_links_write(inode, false);
+		inode->i_state |= I_LINKABLE;
 		*whiteout = inode;
 	} else {
 		d_tmpfile(dentry, inode);
@@ -851,6 +852,12 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			F2FS_I(old_dentry->d_inode)->i_projid)))
 		return -EXDEV;
 
+	if (flags & RENAME_WHITEOUT) {
+		err = f2fs_create_whiteout(old_dir, &whiteout);
+		if (err)
+			return err;
+	}
+
 	err = dquot_initialize(old_dir);
 	if (err)
 		goto out;
@@ -882,17 +889,11 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		}
 	}
 
-	if (flags & RENAME_WHITEOUT) {
-		err = f2fs_create_whiteout(old_dir, &whiteout);
-		if (err)
-			goto out_dir;
-	}
-
 	if (new_inode) {
 
 		err = -ENOTEMPTY;
 		if (old_dir_entry && !f2fs_empty_dir(new_inode))
-			goto out_whiteout;
+			goto out_dir;
 
 		err = -ENOENT;
 		new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name,
@@ -900,7 +901,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		if (!new_entry) {
 			if (IS_ERR(new_page))
 				err = PTR_ERR(new_page);
-			goto out_whiteout;
+			goto out_dir;
 		}
 
 		f2fs_balance_fs(sbi, true);
@@ -932,7 +933,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		err = f2fs_add_link(new_dentry, old_inode);
 		if (err) {
 			f2fs_unlock_op(sbi);
-			goto out_whiteout;
+			goto out_dir;
 		}
 
 		if (old_dir_entry)
@@ -956,7 +957,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 				if (IS_ERR(old_page))
 					err = PTR_ERR(old_page);
 				f2fs_unlock_op(sbi);
-				goto out_whiteout;
+				goto out_dir;
 			}
 		}
 	}
@@ -975,7 +976,6 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	f2fs_delete_entry(old_entry, old_page, old_dir, NULL);
 
 	if (whiteout) {
-		whiteout->i_state |= I_LINKABLE;
 		set_inode_flag(whiteout, FI_INC_LINK);
 		err = f2fs_add_link(old_dentry, whiteout);
 		if (err)
@@ -1011,15 +1011,14 @@ put_out_dir:
 	f2fs_unlock_op(sbi);
 	if (new_page)
 		f2fs_put_page(new_page, 0);
-out_whiteout:
-	if (whiteout)
-		iput(whiteout);
 out_dir:
 	if (old_dir_entry)
 		f2fs_put_page(old_dir_page, 0);
 out_old:
 	f2fs_put_page(old_page, 0);
 out:
+	if (whiteout)
+		iput(whiteout);
 	return err;
 }
 
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index ad024b7b1d43..75fced457c24 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1565,15 +1565,16 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
 	if (atomic && !test_opt(sbi, NOBARRIER))
 		fio.op_flags |= REQ_PREFLUSH | REQ_FUA;
 
-	set_page_writeback(page);
-	ClearPageError(page);
-
+	/* should add to global list before clearing PAGECACHE status */
 	if (f2fs_in_warm_node_list(sbi, page)) {
 		seq = f2fs_add_fsync_node_entry(sbi, page);
 		if (seq_id)
 			*seq_id = seq;
 	}
 
+	set_page_writeback(page);
+	ClearPageError(page);
+
 	fio.old_blkaddr = ni.blk_addr;
 	f2fs_do_write_node_page(nid, &fio);
 	set_node_addr(sbi, &ni, fio.new_blkaddr, is_fsync_dnode(page));
@@ -2887,7 +2888,7 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi)
 		return 0;
 
 	nm_i->nat_bits_blocks = F2FS_BLK_ALIGN((nat_bits_bytes << 1) + 8);
-	nm_i->nat_bits = f2fs_kzalloc(sbi,
+	nm_i->nat_bits = f2fs_kvzalloc(sbi,
 			nm_i->nat_bits_blocks << F2FS_BLKSIZE_BITS, GFP_KERNEL);
 	if (!nm_i->nat_bits)
 		return -ENOMEM;
@@ -2970,7 +2971,7 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
 
 	/* not used nids: 0, node, meta, (and root counted as valid node) */
 	nm_i->available_nids = nm_i->max_nid - sbi->total_valid_node_count -
-				sbi->nquota_files - F2FS_RESERVED_NODE_NUM;
+						F2FS_RESERVED_NODE_NUM;
 	nm_i->nid_cnt[FREE_NID] = 0;
 	nm_i->nid_cnt[PREALLOC_NID] = 0;
 	nm_i->nat_cnt = 0;
@@ -3020,9 +3021,9 @@ static int init_free_nid_cache(struct f2fs_sb_info *sbi)
 	int i;
 
 	nm_i->free_nid_bitmap =
-		f2fs_kzalloc(sbi, array_size(sizeof(unsigned char *),
-					     nm_i->nat_blocks),
-			     GFP_KERNEL);
+		f2fs_kvzalloc(sbi, array_size(sizeof(unsigned char *),
+					      nm_i->nat_blocks),
+			      GFP_KERNEL);
 	if (!nm_i->free_nid_bitmap)
 		return -ENOMEM;
 
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 01038aff5d8e..b7539664c937 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -409,7 +409,7 @@ static int parse_options(struct super_block *sb, char *options)
 			break;
 		case Opt_norecovery:
 			/* this option mounts f2fs with ro */
-			set_opt(sbi, DISABLE_ROLL_FORWARD);
+			set_opt(sbi, NORECOVERY);
 			if (!f2fs_readonly(sb))
 				return -EINVAL;
 			break;
@@ -1086,7 +1086,7 @@ static void f2fs_put_super(struct super_block *sb)
 	/* our cp_error case, we can wait for any writeback page */
 	f2fs_flush_merged_writes(sbi);
 
-	f2fs_wait_on_all_pages_writeback(sbi);
+	f2fs_wait_on_all_pages(sbi, F2FS_WB_CP_DATA);
 
 	f2fs_bug_on(sbi, sbi->fsync_node_num);
 
@@ -1191,20 +1191,23 @@ static int f2fs_statfs_project(struct super_block *sb,
 		return PTR_ERR(dquot);
 	spin_lock(&dquot->dq_dqb_lock);
 
-	limit = (dquot->dq_dqb.dqb_bsoftlimit ?
-		 dquot->dq_dqb.dqb_bsoftlimit :
-		 dquot->dq_dqb.dqb_bhardlimit) >> sb->s_blocksize_bits;
+	limit = min_not_zero(dquot->dq_dqb.dqb_bsoftlimit,
+					dquot->dq_dqb.dqb_bhardlimit);
+	if (limit)
+		limit >>= sb->s_blocksize_bits;
+
 	if (limit && buf->f_blocks > limit) {
-		curblock = dquot->dq_dqb.dqb_curspace >> sb->s_blocksize_bits;
+		curblock = (dquot->dq_dqb.dqb_curspace +
+			    dquot->dq_dqb.dqb_rsvspace) >> sb->s_blocksize_bits;
 		buf->f_blocks = limit;
 		buf->f_bfree = buf->f_bavail =
 			(buf->f_blocks > curblock) ?
 			 (buf->f_blocks - curblock) : 0;
 	}
 
-	limit = dquot->dq_dqb.dqb_isoftlimit ?
-		dquot->dq_dqb.dqb_isoftlimit :
-		dquot->dq_dqb.dqb_ihardlimit;
+	limit = min_not_zero(dquot->dq_dqb.dqb_isoftlimit,
+					dquot->dq_dqb.dqb_ihardlimit);
+
 	if (limit && buf->f_files > limit) {
 		buf->f_files = limit;
 		buf->f_ffree =
@@ -1249,8 +1252,7 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	else
 		buf->f_bavail = 0;
 
-	avail_node_count = sbi->total_node_count - sbi->nquota_files -
-						F2FS_RESERVED_NODE_NUM;
+	avail_node_count = sbi->total_node_count - F2FS_RESERVED_NODE_NUM;
 
 	if (avail_node_count > user_block_count) {
 		buf->f_files = user_block_count;
@@ -1325,6 +1327,8 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 	}
 	if (test_opt(sbi, DISABLE_ROLL_FORWARD))
 		seq_puts(seq, ",disable_roll_forward");
+	if (test_opt(sbi, NORECOVERY))
+		seq_puts(seq, ",norecovery");
 	if (test_opt(sbi, DISCARD))
 		seq_puts(seq, ",discard");
 	if (test_opt(sbi, NOHEAP))
@@ -1793,6 +1797,7 @@ static ssize_t f2fs_quota_write(struct super_block *sb, int type,
 	int offset = off & (sb->s_blocksize - 1);
 	size_t towrite = len;
 	struct page *page;
+	void *fsdata = NULL;
 	char *kaddr;
 	int err = 0;
 	int tocopy;
@@ -1802,7 +1807,7 @@ static ssize_t f2fs_quota_write(struct super_block *sb, int type,
 								towrite);
 retry:
 		err = a_ops->write_begin(NULL, mapping, off, tocopy, 0,
-							&page, NULL);
+							&page, &fsdata);
 		if (unlikely(err)) {
 			if (err == -ENOMEM) {
 				congestion_wait(BLK_RW_ASYNC, HZ/50);
@@ -1818,7 +1823,7 @@ retry:
 		flush_dcache_page(page);
 
 		a_ops->write_end(NULL, mapping, off, tocopy, tocopy,
-						page, NULL);
+						page, fsdata);
 		offset = 0;
 		towrite -= tocopy;
 		off += tocopy;
@@ -2444,6 +2449,12 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 	size_t crc_offset = 0;
 	__u32 crc = 0;
 
+	if (le32_to_cpu(raw_super->magic) != F2FS_SUPER_MAGIC) {
+		f2fs_msg(sb, KERN_INFO, "Magic Mismatch, valid(0x%x) - read(0x%x)",
+			  F2FS_SUPER_MAGIC, le32_to_cpu(raw_super->magic));
+		return -EINVAL;
+	}
+
 	/* Check checksum_offset and crc in superblock */
 	if (__F2FS_HAS_FEATURE(raw_super, F2FS_FEATURE_SB_CHKSUM)) {
 		crc_offset = le32_to_cpu(raw_super->checksum_offset);
@@ -2452,29 +2463,22 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 			f2fs_msg(sb, KERN_INFO,
 				"Invalid SB checksum offset: %zu",
 				crc_offset);
-			return 1;
+			return -EFSCORRUPTED;
 		}
 		crc = le32_to_cpu(raw_super->crc);
 		if (!f2fs_crc_valid(sbi, crc, raw_super, crc_offset)) {
 			f2fs_msg(sb, KERN_INFO,
 				"Invalid SB checksum value: %u", crc);
-			return 1;
+			return -EFSCORRUPTED;
 		}
 	}
 
-	if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) {
-		f2fs_msg(sb, KERN_INFO,
-			"Magic Mismatch, valid(0x%x) - read(0x%x)",
-			F2FS_SUPER_MAGIC, le32_to_cpu(raw_super->magic));
-		return 1;
-	}
-
 	/* Currently, support only 4KB page cache size */
 	if (F2FS_BLKSIZE != PAGE_SIZE) {
 		f2fs_msg(sb, KERN_INFO,
 			"Invalid page_cache_size (%lu), supports only 4KB",
 			PAGE_SIZE);
-		return 1;
+		return -EFSCORRUPTED;
 	}
 
 	/* Currently, support only 4KB block size */
@@ -2483,7 +2487,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 		f2fs_msg(sb, KERN_INFO,
 			"Invalid blocksize (%u), supports only 4KB",
 			blocksize);
-		return 1;
+		return -EFSCORRUPTED;
 	}
 
 	/* check log blocks per segment */
@@ -2491,7 +2495,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 		f2fs_msg(sb, KERN_INFO,
 			"Invalid log blocks per segment (%u)",
 			le32_to_cpu(raw_super->log_blocks_per_seg));
-		return 1;
+		return -EFSCORRUPTED;
 	}
 
 	/* Currently, support 512/1024/2048/4096 bytes sector size */
@@ -2501,7 +2505,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 				F2FS_MIN_LOG_SECTOR_SIZE) {
 		f2fs_msg(sb, KERN_INFO, "Invalid log sectorsize (%u)",
 			le32_to_cpu(raw_super->log_sectorsize));
-		return 1;
+		return -EFSCORRUPTED;
 	}
 	if (le32_to_cpu(raw_super->log_sectors_per_block) +
 		le32_to_cpu(raw_super->log_sectorsize) !=
@@ -2510,7 +2514,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 			"Invalid log sectors per block(%u) log sectorsize(%u)",
 			le32_to_cpu(raw_super->log_sectors_per_block),
 			le32_to_cpu(raw_super->log_sectorsize));
-		return 1;
+		return -EFSCORRUPTED;
 	}
 
 	segment_count = le32_to_cpu(raw_super->segment_count);
@@ -2526,7 +2530,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 		f2fs_msg(sb, KERN_INFO,
 			"Invalid segment count (%u)",
 			segment_count);
-		return 1;
+		return -EFSCORRUPTED;
 	}
 
 	if (total_sections > segment_count ||
@@ -2535,28 +2539,28 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 		f2fs_msg(sb, KERN_INFO,
 			"Invalid segment/section count (%u, %u x %u)",
 			segment_count, total_sections, segs_per_sec);
-		return 1;
+		return -EFSCORRUPTED;
 	}
 
 	if ((segment_count / segs_per_sec) < total_sections) {
 		f2fs_msg(sb, KERN_INFO,
 			"Small segment_count (%u < %u * %u)",
 			segment_count, segs_per_sec, total_sections);
-		return 1;
+		return -EFSCORRUPTED;
 	}
 
 	if (segment_count > (le64_to_cpu(raw_super->block_count) >> 9)) {
 		f2fs_msg(sb, KERN_INFO,
 			"Wrong segment_count / block_count (%u > %llu)",
 			segment_count, le64_to_cpu(raw_super->block_count));
-		return 1;
+		return -EFSCORRUPTED;
 	}
 
 	if (secs_per_zone > total_sections || !secs_per_zone) {
 		f2fs_msg(sb, KERN_INFO,
 			"Wrong secs_per_zone / total_sections (%u, %u)",
 			secs_per_zone, total_sections);
-		return 1;
+		return -EFSCORRUPTED;
 	}
 	if (le32_to_cpu(raw_super->extension_count) > F2FS_MAX_EXTENSION ||
 			raw_super->hot_ext_count > F2FS_MAX_EXTENSION ||
@@ -2567,7 +2571,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 			le32_to_cpu(raw_super->extension_count),
 			raw_super->hot_ext_count,
 			F2FS_MAX_EXTENSION);
-		return 1;
+		return -EFSCORRUPTED;
 	}
 
 	if (le32_to_cpu(raw_super->cp_payload) >
@@ -2576,7 +2580,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 			"Insane cp_payload (%u > %u)",
 			le32_to_cpu(raw_super->cp_payload),
 			blocks_per_seg - F2FS_CP_PACKS);
-		return 1;
+		return -EFSCORRUPTED;
 	}
 
 	/* check reserved ino info */
@@ -2588,12 +2592,12 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 			le32_to_cpu(raw_super->node_ino),
 			le32_to_cpu(raw_super->meta_ino),
 			le32_to_cpu(raw_super->root_ino));
-		return 1;
+		return -EFSCORRUPTED;
 	}
 
 	/* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */
 	if (sanity_check_area_boundary(sbi, bh))
-		return 1;
+		return -EFSCORRUPTED;
 
 	return 0;
 }
@@ -2655,8 +2659,7 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi)
 	}
 
 	valid_node_count = le32_to_cpu(ckpt->valid_node_count);
-	avail_node_count = sbi->total_node_count - sbi->nquota_files -
-						F2FS_RESERVED_NODE_NUM;
+	avail_node_count = sbi->total_node_count - F2FS_RESERVED_NODE_NUM;
 	if (valid_node_count > avail_node_count) {
 		f2fs_msg(sbi->sb, KERN_ERR,
 			"Wrong valid_node_count: %u, avail_node_count: %u",
@@ -2844,7 +2847,7 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
 	if (nr_sectors & (bdev_zone_sectors(bdev) - 1))
 		FDEV(devi).nr_blkz++;
 
-	FDEV(devi).blkz_seq = f2fs_kzalloc(sbi,
+	FDEV(devi).blkz_seq = f2fs_kvzalloc(sbi,
 					BITS_TO_LONGS(FDEV(devi).nr_blkz)
 					* sizeof(unsigned long),
 					GFP_KERNEL);
@@ -2918,11 +2921,11 @@ static int read_raw_super_block(struct f2fs_sb_info *sbi,
 		}
 
 		/* sanity checking of raw super */
-		if (sanity_check_raw_super(sbi, bh)) {
+		err = sanity_check_raw_super(sbi, bh);
+		if (err) {
 			f2fs_msg(sb, KERN_ERR,
 				"Can't find valid F2FS filesystem in %dth superblock",
 				block + 1);
-			err = -EFSCORRUPTED;
 			brelse(bh);
 			continue;
 		}
@@ -3400,7 +3403,8 @@ try_onemore:
 		goto reset_checkpoint;
 
 	/* recover fsynced data */
-	if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) {
+	if (!test_opt(sbi, DISABLE_ROLL_FORWARD) &&
+			!test_opt(sbi, NORECOVERY)) {
 		/*
 		 * mount should be failed, when device has readonly mode, and
 		 * previous checkpoint was not done by clean system shutdown.
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index 729f46a3c9ee..85e3ed67e382 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -679,10 +679,12 @@ int __init f2fs_init_sysfs(void)
 
 	ret = kobject_init_and_add(&f2fs_feat, &f2fs_feat_ktype,
 				   NULL, "features");
-	if (ret)
+	if (ret) {
+		kobject_put(&f2fs_feat);
 		kset_unregister(&f2fs_kset);
-	else
+	} else {
 		f2fs_proc_root = proc_mkdir("fs/f2fs", NULL);
+	}
 	return ret;
 }
 
@@ -703,8 +705,11 @@ int f2fs_register_sysfs(struct f2fs_sb_info *sbi)
 	init_completion(&sbi->s_kobj_unregister);
 	err = kobject_init_and_add(&sbi->s_kobj, &f2fs_sb_ktype, NULL,
 				"%s", sb->s_id);
-	if (err)
+	if (err) {
+		kobject_put(&sbi->s_kobj);
+		wait_for_completion(&sbi->s_kobj_unregister);
 		return err;
+	}
 
 	if (f2fs_proc_root)
 		sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);
@@ -732,4 +737,5 @@ void f2fs_unregister_sysfs(struct f2fs_sb_info *sbi)
 		remove_proc_entry(sbi->sb->s_id, f2fs_proc_root);
 	}
 	kobject_del(&sbi->s_kobj);
+	kobject_put(&sbi->s_kobj);
 }
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index 963242018663..b5e49f2565f5 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -535,8 +535,9 @@ out:
 ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
 {
 	struct inode *inode = d_inode(dentry);
+	nid_t xnid = F2FS_I(inode)->i_xattr_nid;
 	struct f2fs_xattr_entry *entry;
-	void *base_addr;
+	void *base_addr, *last_base_addr;
 	int error = 0;
 	size_t rest = buffer_size;
 
@@ -546,6 +547,8 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
 	if (error)
 		return error;
 
+	last_base_addr = (void *)base_addr + XATTR_SIZE(xnid, inode);
+
 	list_for_each_xattr(entry, base_addr) {
 		const struct xattr_handler *handler =
 			f2fs_xattr_handler(entry->e_name_index);
@@ -553,6 +556,15 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
 		size_t prefix_len;
 		size_t size;
 
+		if ((void *)(entry) + sizeof(__u32) > last_base_addr ||
+			(void *)XATTR_NEXT_ENTRY(entry) > last_base_addr) {
+			f2fs_msg(F2FS_I_SB(inode)->sb, KERN_ERR, "inode (%lu) has corrupted xattr",
+						inode->i_ino);
+			set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
+			error = -EFSCORRUPTED;
+			goto cleanup;
+		}
+
 		if (!handler || (handler->list && !handler->list(dentry)))
 			continue;
 
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 05689198f5af..45b4aa8878c3 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -744,6 +744,13 @@ static struct inode *fat_alloc_inode(struct super_block *sb)
 		return NULL;
 
 	init_rwsem(&ei->truncate_lock);
+	/* Zeroing to allow iput() even if partial initialized inode. */
+	ei->mmu_private = 0;
+	ei->i_start = 0;
+	ei->i_logstart = 0;
+	ei->i_attrs = 0;
+	ei->i_pos = 0;
+
 	return &ei->vfs_inode;
 }
 
@@ -1368,16 +1375,6 @@ out:
 	return 0;
 }
 
-static void fat_dummy_inode_init(struct inode *inode)
-{
-	/* Initialize this dummy inode to work as no-op. */
-	MSDOS_I(inode)->mmu_private = 0;
-	MSDOS_I(inode)->i_start = 0;
-	MSDOS_I(inode)->i_logstart = 0;
-	MSDOS_I(inode)->i_attrs = 0;
-	MSDOS_I(inode)->i_pos = 0;
-}
-
 static int fat_read_root(struct inode *inode)
 {
 	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
@@ -1517,6 +1514,12 @@ static int fat_read_bpb(struct super_block *sb, struct fat_boot_sector *b,
 		goto out;
 	}
 
+	if (bpb->fat_fat_length == 0 && bpb->fat32_length == 0) {
+		if (!silent)
+			fat_msg(sb, KERN_ERR, "bogus number of FAT sectors");
+		goto out;
+	}
+
 	error = 0;
 
 out:
@@ -1831,13 +1834,11 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
 	fat_inode = new_inode(sb);
 	if (!fat_inode)
 		goto out_fail;
-	fat_dummy_inode_init(fat_inode);
 	sbi->fat_inode = fat_inode;
 
 	fsinfo_inode = new_inode(sb);
 	if (!fsinfo_inode)
 		goto out_fail;
-	fat_dummy_inode_init(fsinfo_inode);
 	fsinfo_inode->i_ino = MSDOS_FSINFO_INO;
 	sbi->fsinfo_inode = fsinfo_inode;
 	insert_inode_hash(fsinfo_inode);
diff --git a/fs/file.c b/fs/file.c
index 3da91a112bab..e5d328335f88 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -70,7 +70,7 @@ static void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt,
  */
 static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt)
 {
-	unsigned int cpy, set;
+	size_t cpy, set;
 
 	BUG_ON(nfdt->max_fds < ofdt->max_fds);
 
diff --git a/fs/filesystems.c b/fs/filesystems.c
index 9135646e41ac..5e1a19013373 100644
--- a/fs/filesystems.c
+++ b/fs/filesystems.c
@@ -271,7 +271,9 @@ struct file_system_type *get_fs_type(const char *name)
 	fs = __get_fs_type(name, len);
 	if (!fs && (request_module("fs-%.*s", len, name) == 0)) {
 		fs = __get_fs_type(name, len);
-		WARN_ONCE(!fs, "request_module fs-%.*s succeeded, but still no fs?\n", len, name);
+		if (!fs)
+			pr_warn_once("request_module fs-%.*s succeeded, but still no fs?\n",
+				     len, name);
 	}
 
 	if (dot && fs && !(fs->fs_flags & FS_HAS_SUBTYPE)) {
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 9f1c208f57da..76ff35d3a430 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -270,6 +270,7 @@ void __inode_attach_wb(struct inode *inode, struct page *page)
 	if (unlikely(cmpxchg(&inode->i_wb, NULL, wb)))
 		wb_put(wb);
 }
+EXPORT_SYMBOL_GPL(__inode_attach_wb);
 
 /**
  * locked_inode_to_wb_and_lock_list - determine a locked inode's wb and lock it
@@ -1975,7 +1976,7 @@ void wb_workfn(struct work_struct *work)
 						struct bdi_writeback, dwork);
 	long pages_written;
 
-	set_worker_desc("flush-%s", dev_name(wb->bdi->dev));
+	set_worker_desc("flush-%s", bdi_dev_name(wb->bdi));
 	current->flags |= PF_SWAPWRITE;
 
 	if (likely(!current_is_workqueue_rescuer() ||
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 186468fba82e..9b7ddd7f9691 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -905,7 +905,8 @@ static int fuse_check_page(struct page *page)
 	       1 << PG_uptodate |
 	       1 << PG_lru |
 	       1 << PG_active |
-	       1 << PG_reclaim))) {
+	       1 << PG_reclaim |
+	       1 << PG_waiters))) {
 		pr_warn("trying to steal weird page\n");
 		pr_warn("  page=%p index=%li flags=%08lx, count=%i, mapcount=%i, mapping=%p\n", page, page->index, page->flags, page_count(page), page_mapcount(page), page->mapping);
 		return 1;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 36530c98b8ca..c053266235e2 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -18,6 +18,7 @@
 #include <linux/swap.h>
 #include <linux/falloc.h>
 #include <linux/uio.h>
+#include <linux/fs.h>
 
 static int fuse_send_open(struct fuse_conn *fc, u64 nodeid, struct file *file,
 			  int opcode, struct fuse_open_out *outargp)
@@ -2006,10 +2007,8 @@ static int fuse_writepages(struct address_space *mapping,
 
 	err = write_cache_pages(mapping, wbc, fuse_writepages_fill, &data);
 	if (data.req) {
-		/* Ignore errors if we can write at least one page */
 		BUG_ON(!data.req->num_pages);
 		fuse_writepages_send(&data);
-		err = 0;
 	}
 	if (data.ff)
 		fuse_file_put(data.ff, false, false);
@@ -2616,7 +2615,16 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
 		struct iovec *iov = iov_page;
 
 		iov->iov_base = (void __user *)arg;
-		iov->iov_len = _IOC_SIZE(cmd);
+
+		switch (cmd) {
+		case FS_IOC_GETFLAGS:
+		case FS_IOC_SETFLAGS:
+			iov->iov_len = sizeof(int);
+			break;
+		default:
+			iov->iov_len = _IOC_SIZE(cmd);
+			break;
+		}
 
 		if (_IOC_DIR(cmd) & _IOC_WRITE) {
 			in_iov = iov;
@@ -3147,21 +3155,35 @@ static ssize_t fuse_copy_file_range(struct file *file_in, loff_t pos_in,
 	if (fc->no_copy_file_range)
 		return -EOPNOTSUPP;
 
-	if (fc->writeback_cache) {
-		inode_lock(inode_in);
-		err = fuse_writeback_range(inode_in, pos_in, pos_in + len);
-		inode_unlock(inode_in);
-		if (err)
-			return err;
-	}
+	inode_lock(inode_in);
+	err = fuse_writeback_range(inode_in, pos_in, pos_in + len - 1);
+	inode_unlock(inode_in);
+	if (err)
+		return err;
 
 	inode_lock(inode_out);
 
-	if (fc->writeback_cache) {
-		err = fuse_writeback_range(inode_out, pos_out, pos_out + len);
-		if (err)
-			goto out;
-	}
+	/*
+	 * Write out dirty pages in the destination file before sending the COPY
+	 * request to userspace.  After the request is completed, truncate off
+	 * pages (including partial ones) from the cache that have been copied,
+	 * since these contain stale data at that point.
+	 *
+	 * This should be mostly correct, but if the COPY writes to partial
+	 * pages (at the start or end) and the parts not covered by the COPY are
+	 * written through a memory map after calling fuse_writeback_range(),
+	 * then these partial page modifications will be lost on truncation.
+	 *
+	 * It is unlikely that someone would rely on such mixed style
+	 * modifications.  Yet this does give less guarantees than if the
+	 * copying was performed with write(2).
+	 *
+	 * To fix this a i_mmap_sem style lock could be used to prevent new
+	 * faults while the copy is ongoing.
+	 */
+	err = fuse_writeback_range(inode_out, pos_out, pos_out + len - 1);
+	if (err)
+		goto out;
 
 	if (is_unstable)
 		set_bit(FUSE_I_SIZE_UNSTABLE, &fi_out->state);
@@ -3182,6 +3204,10 @@ static ssize_t fuse_copy_file_range(struct file *file_in, loff_t pos_in,
 	if (err)
 		goto out;
 
+	truncate_inode_pages_range(inode_out->i_mapping,
+				   ALIGN_DOWN(pos_out, PAGE_SIZE),
+				   ALIGN(pos_out + outarg.size, PAGE_SIZE) - 1);
+
 	if (fc->writeback_cache) {
 		fuse_write_update_size(inode_out, pos_out + outarg.size);
 		file_update_time(file_out);
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index b47939900932..d33f1f6edd0a 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -528,10 +528,12 @@ lower_metapath:
 
 		/* Advance in metadata tree. */
 		(mp->mp_list[hgt])++;
-		if (mp->mp_list[hgt] >= sdp->sd_inptrs) {
-			if (!hgt)
+		if (hgt) {
+			if (mp->mp_list[hgt] >= sdp->sd_inptrs)
+				goto lower_metapath;
+		} else {
+			if (mp->mp_list[hgt] >= sdp->sd_diptrs)
 				break;
-			goto lower_metapath;
 		}
 
 fill_up_metapath:
@@ -877,10 +879,9 @@ static int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length,
 					ret = -ENOENT;
 					goto unlock;
 				} else {
-					/* report a hole */
 					iomap->offset = pos;
 					iomap->length = length;
-					goto do_alloc;
+					goto hole_found;
 				}
 			}
 			iomap->length = size;
@@ -934,8 +935,6 @@ unlock:
 	return ret;
 
 do_alloc:
-	iomap->addr = IOMAP_NULL_ADDR;
-	iomap->type = IOMAP_HOLE;
 	if (flags & IOMAP_REPORT) {
 		if (pos >= size)
 			ret = -ENOENT;
@@ -957,6 +956,9 @@ do_alloc:
 		if (pos < size && height == ip->i_height)
 			ret = gfs2_hole_size(inode, lblock, len, mp, iomap);
 	}
+hole_found:
+	iomap->addr = IOMAP_NULL_ADDR;
+	iomap->type = IOMAP_HOLE;
 	goto out;
 }
 
@@ -1041,11 +1043,16 @@ static void gfs2_iomap_page_done(struct inode *inode, loff_t pos,
 				 unsigned copied, struct page *page,
 				 struct iomap *iomap)
 {
+	struct gfs2_trans *tr = current->journal_info;
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 
 	if (page && !gfs2_is_stuffed(ip))
 		gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied);
+
+	if (tr->tr_num_buf_new)
+		__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
+
 	gfs2_trans_end(sdp);
 }
 
@@ -1138,8 +1145,6 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos,
 		tr = current->journal_info;
 		if (tr->tr_num_buf_new)
 			__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
-		else
-			gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[0]);
 
 		gfs2_trans_end(sdp);
 	}
@@ -1220,8 +1225,16 @@ static int gfs2_iomap_end(struct inode *inode, loff_t pos, loff_t length,
 
 	if (ip->i_qadata && ip->i_qadata->qa_qd_num)
 		gfs2_quota_unlock(ip);
-	gfs2_write_unlock(inode);
 
+	if (unlikely(!written))
+		goto out_unlock;
+
+	if (iomap->flags & IOMAP_F_SIZE_CHANGED)
+		mark_inode_dirty(inode);
+	set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);
+
+out_unlock:
+	gfs2_write_unlock(inode);
 out:
 	return 0;
 }
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index d174b1f8fd08..0cdc54258cab 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -6,6 +6,7 @@
 
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/compat.h>
 #include <linux/completion.h>
 #include <linux/buffer_head.h>
 #include <linux/pagemap.h>
@@ -338,6 +339,31 @@ static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	return -ENOTTY;
 }
 
+#ifdef CONFIG_COMPAT
+static long gfs2_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+	switch(cmd) {
+	/* These are just misnamed, they actually get/put from/to user an int */
+	case FS_IOC32_GETFLAGS:
+		cmd = FS_IOC_GETFLAGS;
+		break;
+	case FS_IOC32_SETFLAGS:
+		cmd = FS_IOC_SETFLAGS;
+		break;
+	/* Keep this list in sync with gfs2_ioctl */
+	case FITRIM:
+	case FS_IOC_GETFSLABEL:
+		break;
+	default:
+		return -ENOIOCTLCMD;
+	}
+
+	return gfs2_ioctl(filp, cmd, (unsigned long)compat_ptr(arg));
+}
+#else
+#define gfs2_compat_ioctl NULL
+#endif
+
 /**
  * gfs2_size_hint - Give a hint to the size of a write request
  * @filep: The struct file
@@ -791,7 +817,7 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
 	struct gfs2_inode *ip = GFS2_I(inode);
-	ssize_t written = 0, ret;
+	ssize_t ret;
 
 	ret = gfs2_rsqa_alloc(ip);
 	if (ret)
@@ -811,68 +837,58 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	inode_lock(inode);
 	ret = generic_write_checks(iocb, from);
 	if (ret <= 0)
-		goto out;
-
-	/* We can write back this queue in page reclaim */
-	current->backing_dev_info = inode_to_bdi(inode);
+		goto out_unlock;
 
 	ret = file_remove_privs(file);
 	if (ret)
-		goto out2;
+		goto out_unlock;
 
 	ret = file_update_time(file);
 	if (ret)
-		goto out2;
+		goto out_unlock;
 
 	if (iocb->ki_flags & IOCB_DIRECT) {
 		struct address_space *mapping = file->f_mapping;
-		loff_t pos, endbyte;
-		ssize_t buffered;
+		ssize_t buffered, ret2;
 
-		written = gfs2_file_direct_write(iocb, from);
-		if (written < 0 || !iov_iter_count(from))
-			goto out2;
+		ret = gfs2_file_direct_write(iocb, from);
+		if (ret < 0 || !iov_iter_count(from))
+			goto out_unlock;
 
-		ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
-		if (unlikely(ret < 0))
-			goto out2;
-		buffered = ret;
+		iocb->ki_flags |= IOCB_DSYNC;
+		current->backing_dev_info = inode_to_bdi(inode);
+		buffered = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
+		current->backing_dev_info = NULL;
+		if (unlikely(buffered <= 0))
+			goto out_unlock;
 
 		/*
 		 * We need to ensure that the page cache pages are written to
 		 * disk and invalidated to preserve the expected O_DIRECT
-		 * semantics.
+		 * semantics.  If the writeback or invalidate fails, only report
+		 * the direct I/O range as we don't know if the buffered pages
+		 * made it to disk.
 		 */
-		pos = iocb->ki_pos;
-		endbyte = pos + buffered - 1;
-		ret = filemap_write_and_wait_range(mapping, pos, endbyte);
-		if (!ret) {
-			iocb->ki_pos += buffered;
-			written += buffered;
-			invalidate_mapping_pages(mapping,
-						 pos >> PAGE_SHIFT,
-						 endbyte >> PAGE_SHIFT);
-		} else {
-			/*
-			 * We don't know how much we wrote, so just return
-			 * the number of bytes which were direct-written
-			 */
-		}
+		iocb->ki_pos += buffered;
+		ret2 = generic_write_sync(iocb, buffered);
+		invalidate_mapping_pages(mapping,
+				(iocb->ki_pos - buffered) >> PAGE_SHIFT,
+				(iocb->ki_pos - 1) >> PAGE_SHIFT);
+		if (!ret || ret2 > 0)
+			ret += ret2;
 	} else {
+		current->backing_dev_info = inode_to_bdi(inode);
 		ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
-		if (likely(ret > 0))
+		current->backing_dev_info = NULL;
+		if (likely(ret > 0)) {
 			iocb->ki_pos += ret;
+			ret = generic_write_sync(iocb, ret);
+		}
 	}
 
-out2:
-	current->backing_dev_info = NULL;
-out:
+out_unlock:
 	inode_unlock(inode);
-	if (likely(ret > 0)) {
-		/* Handle various SYNC-type writes */
-		ret = generic_write_sync(iocb, ret);
-	}
-	return written ? written : ret;
+	return ret;
 }
 
 static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
@@ -1279,6 +1295,7 @@ const struct file_operations gfs2_file_fops = {
 	.write_iter	= gfs2_file_write_iter,
 	.iopoll		= iomap_dio_iopoll,
 	.unlocked_ioctl	= gfs2_ioctl,
+	.compat_ioctl	= gfs2_compat_ioctl,
 	.mmap		= gfs2_mmap,
 	.open		= gfs2_open,
 	.release	= gfs2_release,
@@ -1294,6 +1311,7 @@ const struct file_operations gfs2_file_fops = {
 const struct file_operations gfs2_dir_fops = {
 	.iterate_shared	= gfs2_readdir,
 	.unlocked_ioctl	= gfs2_ioctl,
+	.compat_ioctl	= gfs2_compat_ioctl,
 	.open		= gfs2_open,
 	.release	= gfs2_release,
 	.fsync		= gfs2_fsync,
@@ -1310,6 +1328,7 @@ const struct file_operations gfs2_file_fops_nolock = {
 	.write_iter	= gfs2_file_write_iter,
 	.iopoll		= iomap_dio_iopoll,
 	.unlocked_ioctl	= gfs2_ioctl,
+	.compat_ioctl	= gfs2_compat_ioctl,
 	.mmap		= gfs2_mmap,
 	.open		= gfs2_open,
 	.release	= gfs2_release,
@@ -1323,6 +1342,7 @@ const struct file_operations gfs2_file_fops_nolock = {
 const struct file_operations gfs2_dir_fops_nolock = {
 	.iterate_shared	= gfs2_readdir,
 	.unlocked_ioctl	= gfs2_ioctl,
+	.compat_ioctl	= gfs2_compat_ioctl,
 	.open		= gfs2_open,
 	.release	= gfs2_release,
 	.fsync		= gfs2_fsync,
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index cf4c767005b1..02cb8dc2d76a 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -89,8 +89,32 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
 	INIT_LIST_HEAD(&tr.tr_databuf);
 	tr.tr_revokes = atomic_read(&gl->gl_ail_count);
 
-	if (!tr.tr_revokes)
+	if (!tr.tr_revokes) {
+		bool have_revokes;
+		bool log_in_flight;
+
+		/*
+		 * We have nothing on the ail, but there could be revokes on
+		 * the sdp revoke queue, in which case, we still want to flush
+		 * the log and wait for it to finish.
+		 *
+		 * If the sdp revoke list is empty too, we might still have an
+		 * io outstanding for writing revokes, so we should wait for
+		 * it before returning.
+		 *
+		 * If none of these conditions are true, our revokes are all
+		 * flushed and we can return.
+		 */
+		gfs2_log_lock(sdp);
+		have_revokes = !list_empty(&sdp->sd_log_revokes);
+		log_in_flight = atomic_read(&sdp->sd_log_in_flight);
+		gfs2_log_unlock(sdp);
+		if (have_revokes)
+			goto flush;
+		if (log_in_flight)
+			log_flush_wait(sdp);
 		return;
+	}
 
 	/* A shortened, inline version of gfs2_trans_begin()
          * tr->alloced is not set since the transaction structure is
@@ -105,6 +129,7 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
 	__gfs2_ail_flush(gl, 0, tr.tr_revokes);
 
 	gfs2_trans_end(sdp);
+flush:
 	gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL |
 		       GFS2_LFC_AIL_EMPTY_GL);
 }
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index b296c59832a7..abb8230324a0 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -1248,7 +1248,7 @@ static int gfs2_atomic_open(struct inode *dir, struct dentry *dentry,
 		if (!(file->f_mode & FMODE_OPENED))
 			return finish_no_open(file, d);
 		dput(d);
-		return 0;
+		return excl && (flags & O_CREAT) ? -EEXIST : 0;
 	}
 
 	BUG_ON(d != NULL);
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index d2a3bfdd350f..cc0b71d44a1a 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -513,7 +513,7 @@ static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail)
 }
 
 
-static void log_flush_wait(struct gfs2_sbd *sdp)
+void log_flush_wait(struct gfs2_sbd *sdp)
 {
 	DEFINE_WAIT(wait);
 
@@ -598,13 +598,13 @@ void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
 	struct buffer_head *bh = bd->bd_bh;
 	struct gfs2_glock *gl = bd->bd_gl;
 
+	sdp->sd_log_num_revoke++;
+	if (atomic_inc_return(&gl->gl_revokes) == 1)
+		gfs2_glock_hold(gl);
 	bh->b_private = NULL;
 	bd->bd_blkno = bh->b_blocknr;
 	gfs2_remove_from_ail(bd); /* drops ref on bh */
 	bd->bd_bh = NULL;
-	sdp->sd_log_num_revoke++;
-	if (atomic_inc_return(&gl->gl_revokes) == 1)
-		gfs2_glock_hold(gl);
 	set_bit(GLF_LFLUSH, &gl->gl_flags);
 	list_add(&bd->bd_list, &sdp->sd_log_revokes);
 }
@@ -881,8 +881,10 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags)
  * @new: New transaction to be merged
  */
 
-static void gfs2_merge_trans(struct gfs2_trans *old, struct gfs2_trans *new)
+static void gfs2_merge_trans(struct gfs2_sbd *sdp, struct gfs2_trans *new)
 {
+	struct gfs2_trans *old = sdp->sd_log_tr;
+
 	WARN_ON_ONCE(!test_bit(TR_ATTACHED, &old->tr_flags));
 
 	old->tr_num_buf_new	+= new->tr_num_buf_new;
@@ -894,6 +896,11 @@ static void gfs2_merge_trans(struct gfs2_trans *old, struct gfs2_trans *new)
 
 	list_splice_tail_init(&new->tr_databuf, &old->tr_databuf);
 	list_splice_tail_init(&new->tr_buf, &old->tr_buf);
+
+	spin_lock(&sdp->sd_ail_lock);
+	list_splice_tail_init(&new->tr_ail1_list, &old->tr_ail1_list);
+	list_splice_tail_init(&new->tr_ail2_list, &old->tr_ail2_list);
+	spin_unlock(&sdp->sd_ail_lock);
 }
 
 static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
@@ -905,7 +912,7 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 	gfs2_log_lock(sdp);
 
 	if (sdp->sd_log_tr) {
-		gfs2_merge_trans(sdp->sd_log_tr, tr);
+		gfs2_merge_trans(sdp, tr);
 	} else if (tr->tr_num_buf_new || tr->tr_num_databuf_new) {
 		gfs2_assert_withdraw(sdp, test_bit(TR_ALLOCED, &tr->tr_flags));
 		sdp->sd_log_tr = tr;
diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h
index c762da494546..52b9bf27e918 100644
--- a/fs/gfs2/log.h
+++ b/fs/gfs2/log.h
@@ -73,6 +73,7 @@ extern void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl,
 			   u32 type);
 extern void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *trans);
 extern void gfs2_ail1_flush(struct gfs2_sbd *sdp, struct writeback_control *wbc);
+extern void log_flush_wait(struct gfs2_sbd *sdp);
 
 extern void gfs2_log_shutdown(struct gfs2_sbd *sdp);
 extern int gfs2_logd(void *data);
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 3434294c9556..ab5d9fca73f6 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -264,7 +264,7 @@ static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno,
 	struct super_block *sb = sdp->sd_vfs;
 	struct bio *bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
 
-	bio->bi_iter.bi_sector = blkno * (sb->s_blocksize >> 9);
+	bio->bi_iter.bi_sector = blkno << sdp->sd_fsb2bb_shift;
 	bio_set_dev(bio, sb->s_bdev);
 	bio->bi_end_io = end_io;
 	bio->bi_private = sdp;
@@ -421,7 +421,7 @@ static bool gfs2_jhead_pg_srch(struct gfs2_jdesc *jd,
 
 	for (offset = 0; offset < PAGE_SIZE; offset += sdp->sd_sb.sb_bsize) {
 		if (!__get_log_header(sdp, kaddr + offset, 0, &lh)) {
-			if (lh.lh_sequence > head->lh_sequence)
+			if (lh.lh_sequence >= head->lh_sequence)
 				*head = lh;
 			else {
 				ret = true;
@@ -471,6 +471,20 @@ static void gfs2_jhead_process_page(struct gfs2_jdesc *jd, unsigned long index,
 	put_page(page); /* Once more for find_or_create_page */
 }
 
+static struct bio *gfs2_chain_bio(struct bio *prev, unsigned int nr_iovecs)
+{
+	struct bio *new;
+
+	new = bio_alloc(GFP_NOIO, nr_iovecs);
+	bio_copy_dev(new, prev);
+	new->bi_iter.bi_sector = bio_end_sector(prev);
+	new->bi_opf = prev->bi_opf;
+	new->bi_write_hint = prev->bi_write_hint;
+	bio_chain(new, prev);
+	submit_bio(prev);
+	return new;
+}
+
 /**
  * gfs2_find_jhead - find the head of a log
  * @jd: The journal descriptor
@@ -487,10 +501,10 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head,
 	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
 	struct address_space *mapping = jd->jd_inode->i_mapping;
 	unsigned int block = 0, blocks_submitted = 0, blocks_read = 0;
-	unsigned int bsize = sdp->sd_sb.sb_bsize;
+	unsigned int bsize = sdp->sd_sb.sb_bsize, off;
 	unsigned int bsize_shift = sdp->sd_sb.sb_bsize_shift;
 	unsigned int shift = PAGE_SHIFT - bsize_shift;
-	unsigned int readhead_blocks = BIO_MAX_PAGES << shift;
+	unsigned int max_blocks = 2 * 1024 * 1024 >> bsize_shift;
 	struct gfs2_journal_extent *je;
 	int sz, ret = 0;
 	struct bio *bio = NULL;
@@ -504,9 +518,9 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head,
 
 	since = filemap_sample_wb_err(mapping);
 	list_for_each_entry(je, &jd->extent_list, list) {
-		for (; block < je->lblock + je->blocks; block++) {
-			u64 dblock;
+		u64 dblock = je->dblock;
 
+		for (; block < je->lblock + je->blocks; block++, dblock++) {
 			if (!page) {
 				page = find_or_create_page(mapping,
 						block >> shift, GFP_NOFS);
@@ -515,35 +529,41 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head,
 					done = true;
 					goto out;
 				}
+				off = 0;
 			}
 
-			if (bio) {
-				unsigned int off;
-
-				off = (block << bsize_shift) & ~PAGE_MASK;
-				sz = bio_add_page(bio, page, bsize, off);
-				if (sz == bsize) { /* block added */
-					if (off + bsize == PAGE_SIZE) {
-						page = NULL;
-						goto page_added;
-					}
-					continue;
+			if (bio && (off || block < blocks_submitted + max_blocks)) {
+				sector_t sector = dblock << sdp->sd_fsb2bb_shift;
+
+				if (bio_end_sector(bio) == sector) {
+					sz = bio_add_page(bio, page, bsize, off);
+					if (sz == bsize)
+						goto block_added;
 				}
-				blocks_submitted = block + 1;
+				if (off) {
+					unsigned int blocks =
+						(PAGE_SIZE - off) >> bsize_shift;
+
+					bio = gfs2_chain_bio(bio, blocks);
+					goto add_block_to_new_bio;
+				}
+			}
+
+			if (bio) {
+				blocks_submitted = block;
 				submit_bio(bio);
-				bio = NULL;
 			}
 
-			dblock = je->dblock + (block - je->lblock);
 			bio = gfs2_log_alloc_bio(sdp, dblock, gfs2_end_log_read);
 			bio->bi_opf = REQ_OP_READ;
-			sz = bio_add_page(bio, page, bsize, 0);
-			gfs2_assert_warn(sdp, sz == bsize);
-			if (bsize == PAGE_SIZE)
+add_block_to_new_bio:
+			sz = bio_add_page(bio, page, bsize, off);
+			BUG_ON(sz != bsize);
+block_added:
+			off += bsize;
+			if (off == PAGE_SIZE)
 				page = NULL;
-
-page_added:
-			if (blocks_submitted < blocks_read + readhead_blocks) {
+			if (blocks_submitted <= blocks_read + max_blocks) {
 				/* Keep at least one bio in flight */
 				continue;
 			}
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 08823bb3b2d0..aa98abd177c3 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -901,7 +901,7 @@ fail:
 }
 
 static const match_table_t nolock_tokens = {
-	{ Opt_jid, "jid=%d\n", },
+	{ Opt_jid, "jid=%d", },
 	{ Opt_err, NULL },
 };
 
@@ -1158,7 +1158,17 @@ static int fill_super(struct super_block *sb, struct gfs2_args *args, int silent
 		goto fail_per_node;
 	}
 
-	if (!sb_rdonly(sb)) {
+	if (sb_rdonly(sb)) {
+		struct gfs2_holder freeze_gh;
+
+		error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED,
+					   GL_EXACT, &freeze_gh);
+		if (error) {
+			fs_err(sdp, "can't make FS RO: %d\n", error);
+			goto fail_per_node;
+		}
+		gfs2_glock_dq_uninit(&freeze_gh);
+	} else {
 		error = gfs2_make_fs_rw(sdp);
 		if (error) {
 			fs_err(sdp, "can't make FS RW: %d\n", error);
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 8189b581236d..43e117308279 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -1040,8 +1040,7 @@ int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
 	u32 x;
 	int error = 0;
 
-	if (capable(CAP_SYS_RESOURCE) ||
-	    sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
+	if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
 		return 0;
 
 	error = gfs2_quota_hold(ip, uid, gid);
diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h
index 765627d9a91e..fe68a91dc16f 100644
--- a/fs/gfs2/quota.h
+++ b/fs/gfs2/quota.h
@@ -44,7 +44,8 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip,
 	int ret;
 
 	ap->allowed = UINT_MAX; /* Assume we are permitted a whole lot */
-	if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
+	if (capable(CAP_SYS_RESOURCE) ||
+	    sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
 		return 0;
 	ret = gfs2_quota_lock(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE);
 	if (ret)
diff --git a/fs/hfsplus/attributes.c b/fs/hfsplus/attributes.c
index e6d554476db4..eeebe80c6be4 100644
--- a/fs/hfsplus/attributes.c
+++ b/fs/hfsplus/attributes.c
@@ -292,6 +292,10 @@ static int __hfsplus_delete_attr(struct inode *inode, u32 cnid,
 		return -ENOENT;
 	}
 
+	/* Avoid btree corruption */
+	hfs_bnode_read(fd->bnode, fd->search_key,
+			fd->keyoffset, fd->keylength);
+
 	err = hfs_brec_remove(fd);
 	if (err)
 		return err;
diff --git a/fs/inode.c b/fs/inode.c
index ed54d3759219..b6748888f140 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -137,6 +137,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	inode->i_sb = sb;
 	inode->i_blkbits = sb->s_blocksize_bits;
 	inode->i_flags = 0;
+	atomic64_set(&inode->i_sequence, 0);
 	atomic_set(&inode->i_count, 1);
 	inode->i_op = &empty_iops;
 	inode->i_fop = &no_open_fops;
@@ -673,6 +674,7 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty)
 	struct inode *inode, *next;
 	LIST_HEAD(dispose);
 
+again:
 	spin_lock(&sb->s_inode_list_lock);
 	list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
 		spin_lock(&inode->i_lock);
@@ -695,6 +697,12 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty)
 		inode_lru_list_del(inode);
 		spin_unlock(&inode->i_lock);
 		list_add(&inode->i_lru, &dispose);
+		if (need_resched()) {
+			spin_unlock(&sb->s_inode_list_lock);
+			cond_resched();
+			dispose_list(&dispose);
+			goto again;
+		}
 	}
 	spin_unlock(&sb->s_inode_list_lock);
 
diff --git a/fs/internal.h b/fs/internal.h
index a48ef81be37d..e891a8a8748e 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -37,7 +37,7 @@ static inline int __sync_blockdev(struct block_device *bdev, int wait)
 /*
  * buffer.c
  */
-extern void guard_bio_eod(int rw, struct bio *bio);
+extern void guard_bio_eod(struct bio *bio);
 extern int __block_write_begin_int(struct page *page, loff_t pos, unsigned len,
 		get_block_t *get_block, struct iomap *iomap);
 void __generic_write_end(struct inode *inode, loff_t pos, unsigned copied,
diff --git a/fs/io_uring.c b/fs/io_uring.c
index abfbc55e8782..98f43d0427bc 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -408,6 +408,7 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 	}
 
 	ctx->flags = p->flags;
+	init_waitqueue_head(&ctx->sqo_wait);
 	init_waitqueue_head(&ctx->cq_wait);
 	init_completion(&ctx->ctx_done);
 	init_completion(&ctx->sqo_thread_started);
@@ -756,11 +757,17 @@ static void io_iopoll_reap_events(struct io_ring_ctx *ctx)
 	mutex_unlock(&ctx->uring_lock);
 }
 
-static int __io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
-			    long min)
+static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
+			   long min)
 {
 	int iters = 0, ret = 0;
 
+	/*
+	 * We disallow the app entering submit/complete with polling, but we
+	 * still need to lock the ring to prevent racing with polled issue
+	 * that got punted to a workqueue.
+	 */
+	mutex_lock(&ctx->uring_lock);
 	do {
 		int tmin = 0;
 
@@ -796,21 +803,6 @@ static int __io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
 		ret = 0;
 	} while (min && !*nr_events && !need_resched());
 
-	return ret;
-}
-
-static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
-			   long min)
-{
-	int ret;
-
-	/*
-	 * We disallow the app entering submit/complete with polling, but we
-	 * still need to lock the ring to prevent racing with polled issue
-	 * that got punted to a workqueue.
-	 */
-	mutex_lock(&ctx->uring_lock);
-	ret = __io_iopoll_check(ctx, nr_events, min);
 	mutex_unlock(&ctx->uring_lock);
 	return ret;
 }
@@ -2150,7 +2142,7 @@ static int io_sq_thread(void *data)
 				 */
 				mutex_lock(&ctx->uring_lock);
 				if (!list_empty(&ctx->poll_list))
-					__io_iopoll_check(ctx, &nr_events, 0);
+					io_iopoll_getevents(ctx, &nr_events, 0);
 				else
 					inflight = 0;
 				mutex_unlock(&ctx->uring_lock);
@@ -2169,16 +2161,6 @@ static int io_sq_thread(void *data)
 
 		if (!io_get_sqring(ctx, &sqes[0])) {
 			/*
-			 * We're polling. If we're within the defined idle
-			 * period, then let us spin without work before going
-			 * to sleep.
-			 */
-			if (inflight || !time_after(jiffies, timeout)) {
-				cpu_relax();
-				continue;
-			}
-
-			/*
 			 * Drop cur_mm before scheduling, we can't hold it for
 			 * long periods (or over schedule()). Do this before
 			 * adding ourselves to the waitqueue, as the unuse/drop
@@ -2190,6 +2172,16 @@ static int io_sq_thread(void *data)
 				cur_mm = NULL;
 			}
 
+			/*
+			 * We're polling. If we're within the defined idle
+			 * period, then let us spin without work before going
+			 * to sleep.
+			 */
+			if (inflight || !time_after(jiffies, timeout)) {
+				cpu_relax();
+				continue;
+			}
+
 			prepare_to_wait(&ctx->sqo_wait, &wait,
 						TASK_INTERRUPTIBLE);
 
@@ -2400,13 +2392,6 @@ static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset)
 	struct sk_buff *skb;
 	int i;
 
-	if (!capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) {
-		unsigned long inflight = ctx->user->unix_inflight + nr;
-
-		if (inflight > task_rlimit(current, RLIMIT_NOFILE))
-			return -EMFILE;
-	}
-
 	fpl = kzalloc(sizeof(*fpl), GFP_KERNEL);
 	if (!fpl)
 		return -ENOMEM;
@@ -2541,7 +2526,6 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx,
 {
 	int ret;
 
-	init_waitqueue_head(&ctx->sqo_wait);
 	mmgrab(current->mm);
 	ctx->sqo_mm = current->mm;
 
@@ -2759,8 +2743,8 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
 
 		ret = 0;
 		if (!pages || nr_pages > got_pages) {
-			kfree(vmas);
-			kfree(pages);
+			kvfree(vmas);
+			kvfree(pages);
 			pages = kvmalloc_array(nr_pages, sizeof(struct page *),
 						GFP_KERNEL);
 			vmas = kvmalloc_array(nr_pages,
diff --git a/fs/ioctl.c b/fs/ioctl.c
index fef3a6bf7c78..3118da0de158 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -8,6 +8,7 @@
 #include <linux/syscalls.h>
 #include <linux/mm.h>
 #include <linux/capability.h>
+#include <linux/compat.h>
 #include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/security.h>
@@ -719,3 +720,37 @@ SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
 {
 	return ksys_ioctl(fd, cmd, arg);
 }
+
+#ifdef CONFIG_COMPAT
+/**
+ * compat_ptr_ioctl - generic implementation of .compat_ioctl file operation
+ *
+ * This is not normally called as a function, but instead set in struct
+ * file_operations as
+ *
+ *     .compat_ioctl = compat_ptr_ioctl,
+ *
+ * On most architectures, the compat_ptr_ioctl() just passes all arguments
+ * to the corresponding ->ioctl handler. The exception is arch/s390, where
+ * compat_ptr() clears the top bit of a 32-bit pointer value, so user space
+ * pointers to the second 2GB alias the first 2GB, as is the case for
+ * native 32-bit s390 user space.
+ *
+ * The compat_ptr_ioctl() function must therefore be used only with ioctl
+ * functions that either ignore the argument or pass a pointer to a
+ * compatible data type.
+ *
+ * If any ioctl command handled by fops->unlocked_ioctl passes a plain
+ * integer instead of a pointer, or any of the passed data types
+ * is incompatible between 32-bit and 64-bit architectures, a proper
+ * handler is required instead of compat_ptr_ioctl.
+ */
+long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	if (!file->f_op->unlocked_ioctl)
+		return -ENOIOCTLCMD;
+
+	return file->f_op->unlocked_ioctl(file, cmd, (unsigned long)compat_ptr(arg));
+}
+EXPORT_SYMBOL(compat_ptr_ioctl);
+#endif
diff --git a/fs/iomap.c b/fs/iomap.c
index 52d4f972ee5a..a486202b198f 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -777,6 +777,7 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
 		unsigned copied, struct page *page, struct iomap *iomap)
 {
 	const struct iomap_page_ops *page_ops = iomap->page_ops;
+	loff_t old_size = inode->i_size;
 	int ret;
 
 	if (iomap->type == IOMAP_INLINE) {
@@ -788,7 +789,19 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
 		ret = __iomap_write_end(inode, pos, len, copied, page, iomap);
 	}
 
-	__generic_write_end(inode, pos, ret, page);
+	/*
+	 * Update the in-memory inode size after copying the data into the page
+	 * cache.  It's up to the file system to write the updated size to disk,
+	 * preferably after I/O completion so that no stale data is exposed.
+	 */
+	if (pos + ret > old_size) {
+		i_size_write(inode, pos + ret);
+		iomap->flags |= IOMAP_F_SIZE_CHANGED;
+	}
+	unlock_page(page);
+
+	if (old_size < pos)
+		pagecache_isize_extended(inode, old_size, pos);
 	if (page_ops && page_ops->page_done)
 		page_ops->page_done(inode, pos, copied, page, iomap);
 	put_page(page);
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index a1909066bde6..62cf497f18eb 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -164,7 +164,7 @@ void __jbd2_log_wait_for_space(journal_t *journal)
 				       "journal space in %s\n", __func__,
 				       journal->j_devname);
 				WARN_ON(1);
-				jbd2_journal_abort(journal, 0);
+				jbd2_journal_abort(journal, -EIO);
 			}
 			write_lock(&journal->j_state_lock);
 		} else {
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 5443697164d0..5b99036b91e0 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -784,7 +784,7 @@ start_journal_io:
 		err = journal_submit_commit_record(journal, commit_transaction,
 						 &cbh, crc32_sum);
 		if (err)
-			__jbd2_journal_abort_hard(journal);
+			jbd2_journal_abort(journal, err);
 	}
 
 	blk_finish_plug(&plug);
@@ -877,7 +877,7 @@ start_journal_io:
 		err = journal_submit_commit_record(journal, commit_transaction,
 						&cbh, crc32_sum);
 		if (err)
-			__jbd2_journal_abort_hard(journal);
+			jbd2_journal_abort(journal, err);
 	}
 	if (cbh)
 		err = journal_wait_on_commit_record(journal, cbh);
@@ -974,29 +974,34 @@ restart_loop:
 		 * it. */
 
 		/*
-		* A buffer which has been freed while still being journaled by
-		* a previous transaction.
-		*/
-		if (buffer_freed(bh)) {
+		 * A buffer which has been freed while still being journaled
+		 * by a previous transaction, refile the buffer to BJ_Forget of
+		 * the running transaction. If the just committed transaction
+		 * contains "add to orphan" operation, we can completely
+		 * invalidate the buffer now. We are rather through in that
+		 * since the buffer may be still accessible when blocksize <
+		 * pagesize and it is attached to the last partial page.
+		 */
+		if (buffer_freed(bh) && !jh->b_next_transaction) {
+			struct address_space *mapping;
+
+			clear_buffer_freed(bh);
+			clear_buffer_jbddirty(bh);
+
 			/*
-			 * If the running transaction is the one containing
-			 * "add to orphan" operation (b_next_transaction !=
-			 * NULL), we have to wait for that transaction to
-			 * commit before we can really get rid of the buffer.
-			 * So just clear b_modified to not confuse transaction
-			 * credit accounting and refile the buffer to
-			 * BJ_Forget of the running transaction. If the just
-			 * committed transaction contains "add to orphan"
-			 * operation, we can completely invalidate the buffer
-			 * now. We are rather through in that since the
-			 * buffer may be still accessible when blocksize <
-			 * pagesize and it is attached to the last partial
-			 * page.
+			 * Block device buffers need to stay mapped all the
+			 * time, so it is enough to clear buffer_jbddirty and
+			 * buffer_freed bits. For the file mapping buffers (i.e.
+			 * journalled data) we need to unmap buffer and clear
+			 * more bits. We also need to be careful about the check
+			 * because the data page mapping can get cleared under
+			 * our hands. Note that if mapping == NULL, we don't
+			 * need to make buffer unmapped because the page is
+			 * already detached from the mapping and buffers cannot
+			 * get reused.
 			 */
-			jh->b_modified = 0;
-			if (!jh->b_next_transaction) {
-				clear_buffer_freed(bh);
-				clear_buffer_jbddirty(bh);
+			mapping = READ_ONCE(bh->b_page->mapping);
+			if (mapping && !sb_is_blkdev_sb(mapping->host->i_sb)) {
 				clear_buffer_mapped(bh);
 				clear_buffer_new(bh);
 				clear_buffer_req(bh);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index e0382067c824..92a1df0a9e56 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -101,7 +101,6 @@ EXPORT_SYMBOL(jbd2_journal_release_jbd_inode);
 EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate);
 EXPORT_SYMBOL(jbd2_inode_cache);
 
-static void __journal_abort_soft (journal_t *journal, int errno);
 static int jbd2_journal_create_slab(size_t slab_size);
 
 #ifdef CONFIG_JBD2_DEBUG
@@ -810,7 +809,7 @@ int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr,
 					"at offset %lu on %s\n",
 			       __func__, blocknr, journal->j_devname);
 			err = -EIO;
-			__journal_abort_soft(journal, err);
+			jbd2_journal_abort(journal, err);
 		}
 	} else {
 		*retp = blocknr; /* +journal->j_blk_offset */
@@ -986,6 +985,7 @@ static void *jbd2_seq_info_start(struct seq_file *seq, loff_t *pos)
 
 static void *jbd2_seq_info_next(struct seq_file *seq, void *v, loff_t *pos)
 {
+	(*pos)++;
 	return NULL;
 }
 
@@ -1353,8 +1353,10 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags)
 	int ret;
 
 	/* Buffer got discarded which means block device got invalidated */
-	if (!buffer_mapped(bh))
+	if (!buffer_mapped(bh)) {
+		unlock_buffer(bh);
 		return -EIO;
+	}
 
 	trace_jbd2_write_superblock(journal, write_flags);
 	if (!(journal->j_flags & JBD2_BARRIER))
@@ -1686,6 +1688,11 @@ int jbd2_journal_load(journal_t *journal)
 		       journal->j_devname);
 		return -EFSCORRUPTED;
 	}
+	/*
+	 * clear JBD2_ABORT flag initialized in journal_init_common
+	 * here to update log tail information with the newest seq.
+	 */
+	journal->j_flags &= ~JBD2_ABORT;
 
 	/* OK, we've finished with the dynamic journal bits:
 	 * reinitialise the dynamic contents of the superblock in memory
@@ -1693,7 +1700,6 @@ int jbd2_journal_load(journal_t *journal)
 	if (journal_reset(journal))
 		goto recovery_error;
 
-	journal->j_flags &= ~JBD2_ABORT;
 	journal->j_flags |= JBD2_LOADED;
 	return 0;
 
@@ -2070,67 +2076,6 @@ int jbd2_journal_wipe(journal_t *journal, int write)
 	return err;
 }
 
-/*
- * Journal abort has very specific semantics, which we describe
- * for journal abort.
- *
- * Two internal functions, which provide abort to the jbd layer
- * itself are here.
- */
-
-/*
- * Quick version for internal journal use (doesn't lock the journal).
- * Aborts hard --- we mark the abort as occurred, but do _nothing_ else,
- * and don't attempt to make any other journal updates.
- */
-void __jbd2_journal_abort_hard(journal_t *journal)
-{
-	transaction_t *transaction;
-
-	if (journal->j_flags & JBD2_ABORT)
-		return;
-
-	printk(KERN_ERR "Aborting journal on device %s.\n",
-	       journal->j_devname);
-
-	write_lock(&journal->j_state_lock);
-	journal->j_flags |= JBD2_ABORT;
-	transaction = journal->j_running_transaction;
-	if (transaction)
-		__jbd2_log_start_commit(journal, transaction->t_tid);
-	write_unlock(&journal->j_state_lock);
-}
-
-/* Soft abort: record the abort error status in the journal superblock,
- * but don't do any other IO. */
-static void __journal_abort_soft (journal_t *journal, int errno)
-{
-	int old_errno;
-
-	write_lock(&journal->j_state_lock);
-	old_errno = journal->j_errno;
-	if (!journal->j_errno || errno == -ESHUTDOWN)
-		journal->j_errno = errno;
-
-	if (journal->j_flags & JBD2_ABORT) {
-		write_unlock(&journal->j_state_lock);
-		if (!old_errno && old_errno != -ESHUTDOWN &&
-		    errno == -ESHUTDOWN)
-			jbd2_journal_update_sb_errno(journal);
-		return;
-	}
-	write_unlock(&journal->j_state_lock);
-
-	__jbd2_journal_abort_hard(journal);
-
-	if (errno) {
-		jbd2_journal_update_sb_errno(journal);
-		write_lock(&journal->j_state_lock);
-		journal->j_flags |= JBD2_REC_ERR;
-		write_unlock(&journal->j_state_lock);
-	}
-}
-
 /**
  * void jbd2_journal_abort () - Shutdown the journal immediately.
  * @journal: the journal to shutdown.
@@ -2170,16 +2115,51 @@ static void __journal_abort_soft (journal_t *journal, int errno)
  * failure to disk.  ext3_error, for example, now uses this
  * functionality.
  *
- * Errors which originate from within the journaling layer will NOT
- * supply an errno; a null errno implies that absolutely no further
- * writes are done to the journal (unless there are any already in
- * progress).
- *
  */
 
 void jbd2_journal_abort(journal_t *journal, int errno)
 {
-	__journal_abort_soft(journal, errno);
+	transaction_t *transaction;
+
+	/*
+	 * ESHUTDOWN always takes precedence because a file system check
+	 * caused by any other journal abort error is not required after
+	 * a shutdown triggered.
+	 */
+	write_lock(&journal->j_state_lock);
+	if (journal->j_flags & JBD2_ABORT) {
+		int old_errno = journal->j_errno;
+
+		write_unlock(&journal->j_state_lock);
+		if (old_errno != -ESHUTDOWN && errno == -ESHUTDOWN) {
+			journal->j_errno = errno;
+			jbd2_journal_update_sb_errno(journal);
+		}
+		return;
+	}
+
+	/*
+	 * Mark the abort as occurred and start current running transaction
+	 * to release all journaled buffer.
+	 */
+	pr_err("Aborting journal on device %s.\n", journal->j_devname);
+
+	journal->j_flags |= JBD2_ABORT;
+	journal->j_errno = errno;
+	transaction = journal->j_running_transaction;
+	if (transaction)
+		__jbd2_log_start_commit(journal, transaction->t_tid);
+	write_unlock(&journal->j_state_lock);
+
+	/*
+	 * Record errno to the journal super block, so that fsck and jbd2
+	 * layer could realise that a filesystem check is needed.
+	 */
+	jbd2_journal_update_sb_errno(journal);
+
+	write_lock(&journal->j_state_lock);
+	journal->j_flags |= JBD2_REC_ERR;
+	write_unlock(&journal->j_state_lock);
 }
 
 /**
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 990e7b5062e7..f6163da64bb5 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -862,8 +862,6 @@ do_get_write_access(handle_t *handle, struct journal_head *jh,
 	char *frozen_buffer = NULL;
 	unsigned long start_lock, time_lock;
 
-	if (is_handle_aborted(handle))
-		return -EROFS;
 	journal = transaction->t_journal;
 
 	jbd_debug(5, "journal_head %p, force_copy %d\n", jh, force_copy);
@@ -1078,8 +1076,8 @@ static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh,
 	/* For undo access buffer must have data copied */
 	if (undo && !jh->b_committed_data)
 		goto out;
-	if (jh->b_transaction != handle->h_transaction &&
-	    jh->b_next_transaction != handle->h_transaction)
+	if (READ_ONCE(jh->b_transaction) != handle->h_transaction &&
+	    READ_ONCE(jh->b_next_transaction) != handle->h_transaction)
 		goto out;
 	/*
 	 * There are two reasons for the barrier here:
@@ -1115,6 +1113,9 @@ int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh)
 	struct journal_head *jh;
 	int rc;
 
+	if (is_handle_aborted(handle))
+		return -EROFS;
+
 	if (jbd2_write_access_granted(handle, bh, false))
 		return 0;
 
@@ -1252,6 +1253,9 @@ int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh)
 	struct journal_head *jh;
 	char *committed_data = NULL;
 
+	if (is_handle_aborted(handle))
+		return -EROFS;
+
 	if (jbd2_write_access_granted(handle, bh, true))
 		return 0;
 
@@ -2293,14 +2297,16 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh,
 			return -EBUSY;
 		}
 		/*
-		 * OK, buffer won't be reachable after truncate. We just set
-		 * j_next_transaction to the running transaction (if there is
-		 * one) and mark buffer as freed so that commit code knows it
-		 * should clear dirty bits when it is done with the buffer.
+		 * OK, buffer won't be reachable after truncate. We just clear
+		 * b_modified to not confuse transaction credit accounting, and
+		 * set j_next_transaction to the running transaction (if there
+		 * is one) and mark buffer as freed so that commit code knows
+		 * it should clear dirty bits when it is done with the buffer.
 		 */
 		set_buffer_freed(bh);
 		if (journal->j_running_transaction && buffer_jbddirty(bh))
 			jh->b_next_transaction = journal->j_running_transaction;
+		jh->b_modified = 0;
 		jbd2_journal_put_journal_head(jh);
 		spin_unlock(&journal->j_list_lock);
 		jbd_unlock_bh_state(bh);
@@ -2526,8 +2532,8 @@ void __jbd2_journal_refile_buffer(struct journal_head *jh)
 	 * our jh reference and thus __jbd2_journal_file_buffer() must not
 	 * take a new one.
 	 */
-	jh->b_transaction = jh->b_next_transaction;
-	jh->b_next_transaction = NULL;
+	WRITE_ONCE(jh->b_transaction, jh->b_next_transaction);
+	WRITE_ONCE(jh->b_next_transaction, NULL);
 	if (buffer_freed(bh))
 		jlist = BJ_Forget;
 	else if (jh->b_modified)
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index e8c792b49616..c35bbaa19486 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -912,7 +912,7 @@ repeat:
 		}
 
 		fsnotify(inode, FS_MODIFY, inode, FSNOTIFY_EVENT_INODE,
-			 &name, 0);
+			 NULL, 0);
 		iput(inode);
 	}
 
diff --git a/fs/libfs.c b/fs/libfs.c
index 7ac2d4bb4735..0d95cc9d3f2f 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -805,7 +805,7 @@ int simple_attr_open(struct inode *inode, struct file *file,
 {
 	struct simple_attr *attr;
 
-	attr = kmalloc(sizeof(*attr), GFP_KERNEL);
+	attr = kzalloc(sizeof(*attr), GFP_KERNEL);
 	if (!attr)
 		return -ENOMEM;
 
@@ -845,9 +845,11 @@ ssize_t simple_attr_read(struct file *file, char __user *buf,
 	if (ret)
 		return ret;
 
-	if (*ppos) {		/* continued read */
+	if (*ppos && attr->get_buf[0]) {
+		/* continued read */
 		size = strlen(attr->get_buf);
-	} else {		/* first read */
+	} else {
+		/* first read */
 		u64 val;
 		ret = attr->get(attr->data, &val);
 		if (ret)
diff --git a/fs/locks.c b/fs/locks.c
index ec1e4a5df629..ceb202de1307 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -729,7 +729,6 @@ static void __locks_delete_block(struct file_lock *waiter)
 {
 	locks_delete_global_blocked(waiter);
 	list_del_init(&waiter->fl_blocked_member);
-	waiter->fl_blocker = NULL;
 }
 
 static void __locks_wake_up_blocks(struct file_lock *blocker)
@@ -744,6 +743,13 @@ static void __locks_wake_up_blocks(struct file_lock *blocker)
 			waiter->fl_lmops->lm_notify(waiter);
 		else
 			wake_up(&waiter->fl_wait);
+
+		/*
+		 * The setting of fl_blocker to NULL marks the "done"
+		 * point in deleting a block. Paired with acquire at the top
+		 * of locks_delete_block().
+		 */
+		smp_store_release(&waiter->fl_blocker, NULL);
 	}
 }
 
@@ -758,24 +764,41 @@ int locks_delete_block(struct file_lock *waiter)
 	int status = -ENOENT;
 
 	/*
-	 * If fl_blocker is NULL, it won't be set again as this thread
-	 * "owns" the lock and is the only one that might try to claim
-	 * the lock.  So it is safe to test fl_blocker locklessly.
-	 * Also if fl_blocker is NULL, this waiter is not listed on
-	 * fl_blocked_requests for some lock, so no other request can
-	 * be added to the list of fl_blocked_requests for this
-	 * request.  So if fl_blocker is NULL, it is safe to
-	 * locklessly check if fl_blocked_requests is empty.  If both
-	 * of these checks succeed, there is no need to take the lock.
+	 * If fl_blocker is NULL, it won't be set again as this thread "owns"
+	 * the lock and is the only one that might try to claim the lock.
+	 *
+	 * We use acquire/release to manage fl_blocker so that we can
+	 * optimize away taking the blocked_lock_lock in many cases.
+	 *
+	 * The smp_load_acquire guarantees two things:
+	 *
+	 * 1/ that fl_blocked_requests can be tested locklessly. If something
+	 * was recently added to that list it must have been in a locked region
+	 * *before* the locked region when fl_blocker was set to NULL.
+	 *
+	 * 2/ that no other thread is accessing 'waiter', so it is safe to free
+	 * it.  __locks_wake_up_blocks is careful not to touch waiter after
+	 * fl_blocker is released.
+	 *
+	 * If a lockless check of fl_blocker shows it to be NULL, we know that
+	 * no new locks can be inserted into its fl_blocked_requests list, and
+	 * can avoid doing anything further if the list is empty.
 	 */
-	if (waiter->fl_blocker == NULL &&
+	if (!smp_load_acquire(&waiter->fl_blocker) &&
 	    list_empty(&waiter->fl_blocked_requests))
 		return status;
+
 	spin_lock(&blocked_lock_lock);
 	if (waiter->fl_blocker)
 		status = 0;
 	__locks_wake_up_blocks(waiter);
 	__locks_delete_block(waiter);
+
+	/*
+	 * The setting of fl_blocker to NULL marks the "done" point in deleting
+	 * a block. Paired with acquire at the top of this function.
+	 */
+	smp_store_release(&waiter->fl_blocker, NULL);
 	spin_unlock(&blocked_lock_lock);
 	return status;
 }
@@ -1368,7 +1391,8 @@ static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl)
 		error = posix_lock_inode(inode, fl, NULL);
 		if (error != FILE_LOCK_DEFERRED)
 			break;
-		error = wait_event_interruptible(fl->fl_wait, !fl->fl_blocker);
+		error = wait_event_interruptible(fl->fl_wait,
+					list_empty(&fl->fl_blocked_member));
 		if (error)
 			break;
 	}
@@ -1453,7 +1477,8 @@ int locks_mandatory_area(struct inode *inode, struct file *filp, loff_t start,
 		error = posix_lock_inode(inode, &fl, NULL);
 		if (error != FILE_LOCK_DEFERRED)
 			break;
-		error = wait_event_interruptible(fl.fl_wait, !fl.fl_blocker);
+		error = wait_event_interruptible(fl.fl_wait,
+					list_empty(&fl.fl_blocked_member));
 		if (!error) {
 			/*
 			 * If we've been sleeping someone might have
@@ -1646,7 +1671,8 @@ restart:
 
 	locks_dispose_list(&dispose);
 	error = wait_event_interruptible_timeout(new_fl->fl_wait,
-						!new_fl->fl_blocker, break_time);
+					list_empty(&new_fl->fl_blocked_member),
+					break_time);
 
 	percpu_down_read(&file_rwsem);
 	spin_lock(&ctx->flc_lock);
@@ -2057,7 +2083,8 @@ static int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl)
 		error = flock_lock_inode(inode, fl);
 		if (error != FILE_LOCK_DEFERRED)
 			break;
-		error = wait_event_interruptible(fl->fl_wait, !fl->fl_blocker);
+		error = wait_event_interruptible(fl->fl_wait,
+				list_empty(&fl->fl_blocked_member));
 		if (error)
 			break;
 	}
@@ -2334,7 +2361,8 @@ static int do_lock_file_wait(struct file *filp, unsigned int cmd,
 		error = vfs_lock_file(filp, cmd, fl, NULL);
 		if (error != FILE_LOCK_DEFERRED)
 			break;
-		error = wait_event_interruptible(fl->fl_wait, !fl->fl_blocker);
+		error = wait_event_interruptible(fl->fl_wait,
+					list_empty(&fl->fl_blocked_member));
 		if (error)
 			break;
 	}
@@ -2774,7 +2802,7 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl,
 	}
 	if (inode) {
 		/* userspace relies on this representation of dev_t */
-		seq_printf(f, "%d %02x:%02x:%ld ", fl_pid,
+		seq_printf(f, "%d %02x:%02x:%lu ", fl_pid,
 				MAJOR(inode->i_sb->s_dev),
 				MINOR(inode->i_sb->s_dev), inode->i_ino);
 	} else {
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index f96073f25432..53337020d9d0 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -150,6 +150,25 @@ static int minix_remount (struct super_block * sb, int * flags, char * data)
 	return 0;
 }
 
+static bool minix_check_superblock(struct super_block *sb)
+{
+	struct minix_sb_info *sbi = minix_sb(sb);
+
+	if (sbi->s_imap_blocks == 0 || sbi->s_zmap_blocks == 0)
+		return false;
+
+	/*
+	 * s_max_size must not exceed the block mapping limitation.  This check
+	 * is only needed for V1 filesystems, since V2/V3 support an extra level
+	 * of indirect blocks which places the limit well above U32_MAX.
+	 */
+	if (sbi->s_version == MINIX_V1 &&
+	    sb->s_maxbytes > (7 + 512 + 512*512) * BLOCK_SIZE)
+		return false;
+
+	return true;
+}
+
 static int minix_fill_super(struct super_block *s, void *data, int silent)
 {
 	struct buffer_head *bh;
@@ -185,7 +204,7 @@ static int minix_fill_super(struct super_block *s, void *data, int silent)
 	sbi->s_zmap_blocks = ms->s_zmap_blocks;
 	sbi->s_firstdatazone = ms->s_firstdatazone;
 	sbi->s_log_zone_size = ms->s_log_zone_size;
-	sbi->s_max_size = ms->s_max_size;
+	s->s_maxbytes = ms->s_max_size;
 	s->s_magic = ms->s_magic;
 	if (s->s_magic == MINIX_SUPER_MAGIC) {
 		sbi->s_version = MINIX_V1;
@@ -216,7 +235,7 @@ static int minix_fill_super(struct super_block *s, void *data, int silent)
 		sbi->s_zmap_blocks = m3s->s_zmap_blocks;
 		sbi->s_firstdatazone = m3s->s_firstdatazone;
 		sbi->s_log_zone_size = m3s->s_log_zone_size;
-		sbi->s_max_size = m3s->s_max_size;
+		s->s_maxbytes = m3s->s_max_size;
 		sbi->s_ninodes = m3s->s_ninodes;
 		sbi->s_nzones = m3s->s_zones;
 		sbi->s_dirsize = 64;
@@ -228,11 +247,12 @@ static int minix_fill_super(struct super_block *s, void *data, int silent)
 	} else
 		goto out_no_fs;
 
+	if (!minix_check_superblock(s))
+		goto out_illegal_sb;
+
 	/*
 	 * Allocate the buffer map to keep the superblock small.
 	 */
-	if (sbi->s_imap_blocks == 0 || sbi->s_zmap_blocks == 0)
-		goto out_illegal_sb;
 	i = (sbi->s_imap_blocks + sbi->s_zmap_blocks) * sizeof(bh);
 	map = kzalloc(i, GFP_KERNEL);
 	if (!map)
@@ -466,6 +486,13 @@ static struct inode *V1_minix_iget(struct inode *inode)
 		iget_failed(inode);
 		return ERR_PTR(-EIO);
 	}
+	if (raw_inode->i_nlinks == 0) {
+		printk("MINIX-fs: deleted inode referenced: %lu\n",
+		       inode->i_ino);
+		brelse(bh);
+		iget_failed(inode);
+		return ERR_PTR(-ESTALE);
+	}
 	inode->i_mode = raw_inode->i_mode;
 	i_uid_write(inode, raw_inode->i_uid);
 	i_gid_write(inode, raw_inode->i_gid);
@@ -499,6 +526,13 @@ static struct inode *V2_minix_iget(struct inode *inode)
 		iget_failed(inode);
 		return ERR_PTR(-EIO);
 	}
+	if (raw_inode->i_nlinks == 0) {
+		printk("MINIX-fs: deleted inode referenced: %lu\n",
+		       inode->i_ino);
+		brelse(bh);
+		iget_failed(inode);
+		return ERR_PTR(-ESTALE);
+	}
 	inode->i_mode = raw_inode->i_mode;
 	i_uid_write(inode, raw_inode->i_uid);
 	i_gid_write(inode, raw_inode->i_gid);
diff --git a/fs/minix/itree_common.c b/fs/minix/itree_common.c
index 043c3fdbc8e7..446148792f41 100644
--- a/fs/minix/itree_common.c
+++ b/fs/minix/itree_common.c
@@ -75,6 +75,7 @@ static int alloc_branch(struct inode *inode,
 	int n = 0;
 	int i;
 	int parent = minix_new_block(inode);
+	int err = -ENOSPC;
 
 	branch[0].key = cpu_to_block(parent);
 	if (parent) for (n = 1; n < num; n++) {
@@ -85,6 +86,11 @@ static int alloc_branch(struct inode *inode,
 			break;
 		branch[n].key = cpu_to_block(nr);
 		bh = sb_getblk(inode->i_sb, parent);
+		if (!bh) {
+			minix_free_block(inode, nr);
+			err = -ENOMEM;
+			break;
+		}
 		lock_buffer(bh);
 		memset(bh->b_data, 0, bh->b_size);
 		branch[n].bh = bh;
@@ -103,7 +109,7 @@ static int alloc_branch(struct inode *inode,
 		bforget(branch[i].bh);
 	for (i = 0; i < n; i++)
 		minix_free_block(inode, block_to_cpu(branch[i].key));
-	return -ENOSPC;
+	return err;
 }
 
 static inline int splice_branch(struct inode *inode,
diff --git a/fs/minix/itree_v1.c b/fs/minix/itree_v1.c
index 046cc96ee7ad..1fed906042aa 100644
--- a/fs/minix/itree_v1.c
+++ b/fs/minix/itree_v1.c
@@ -29,12 +29,12 @@ static int block_to_path(struct inode * inode, long block, int offsets[DEPTH])
 	if (block < 0) {
 		printk("MINIX-fs: block_to_path: block %ld < 0 on dev %pg\n",
 			block, inode->i_sb->s_bdev);
-	} else if (block >= (minix_sb(inode->i_sb)->s_max_size/BLOCK_SIZE)) {
-		if (printk_ratelimit())
-			printk("MINIX-fs: block_to_path: "
-			       "block %ld too big on dev %pg\n",
-				block, inode->i_sb->s_bdev);
-	} else if (block < 7) {
+		return 0;
+	}
+	if ((u64)block * BLOCK_SIZE >= inode->i_sb->s_maxbytes)
+		return 0;
+
+	if (block < 7) {
 		offsets[n++] = block;
 	} else if ((block -= 7) < 512) {
 		offsets[n++] = 7;
diff --git a/fs/minix/itree_v2.c b/fs/minix/itree_v2.c
index f7fc7ecccccc..9d00f31a2d9d 100644
--- a/fs/minix/itree_v2.c
+++ b/fs/minix/itree_v2.c
@@ -32,13 +32,12 @@ static int block_to_path(struct inode * inode, long block, int offsets[DEPTH])
 	if (block < 0) {
 		printk("MINIX-fs: block_to_path: block %ld < 0 on dev %pg\n",
 			block, sb->s_bdev);
-	} else if ((u64)block * (u64)sb->s_blocksize >=
-			minix_sb(sb)->s_max_size) {
-		if (printk_ratelimit())
-			printk("MINIX-fs: block_to_path: "
-			       "block %ld too big on dev %pg\n",
-				block, sb->s_bdev);
-	} else if (block < DIRCOUNT) {
+		return 0;
+	}
+	if ((u64)block * (u64)sb->s_blocksize >= sb->s_maxbytes)
+		return 0;
+
+	if (block < DIRCOUNT) {
 		offsets[n++] = block;
 	} else if ((block -= DIRCOUNT) < INDIRCOUNT(sb)) {
 		offsets[n++] = DIRCOUNT;
diff --git a/fs/minix/minix.h b/fs/minix/minix.h
index df081e8afcc3..168d45d3de73 100644
--- a/fs/minix/minix.h
+++ b/fs/minix/minix.h
@@ -32,7 +32,6 @@ struct minix_sb_info {
 	unsigned long s_zmap_blocks;
 	unsigned long s_firstdatazone;
 	unsigned long s_log_zone_size;
-	unsigned long s_max_size;
 	int s_dirsize;
 	int s_namelen;
 	struct buffer_head ** s_imap;
diff --git a/fs/mpage.c b/fs/mpage.c
index 436a85260394..af6c93f3ef6b 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -62,7 +62,7 @@ static struct bio *mpage_bio_submit(int op, int op_flags, struct bio *bio)
 {
 	bio->bi_end_io = mpage_end_io;
 	bio_set_op_attrs(bio, op, op_flags);
-	guard_bio_eod(op, bio);
+	guard_bio_eod(bio);
 	submit_bio(bio);
 	return NULL;
 }
diff --git a/fs/namei.c b/fs/namei.c
index 797cacb8fdcd..3508a571d042 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1366,7 +1366,7 @@ static int follow_dotdot_rcu(struct nameidata *nd)
 			nd->path.dentry = parent;
 			nd->seq = seq;
 			if (unlikely(!path_connected(&nd->path)))
-				return -ENOENT;
+				return -ECHILD;
 			break;
 		} else {
 			struct mount *mnt = real_mount(nd->path.mnt);
diff --git a/fs/namespace.c b/fs/namespace.c
index 6cb11bd6ff9a..7083e1388150 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -3655,8 +3655,8 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
 	/* make certain new is below the root */
 	if (!is_path_reachable(new_mnt, new.dentry, &root))
 		goto out4;
-	root_mp->m_count++; /* pin it so it won't go away */
 	lock_mount_hash();
+	root_mp->m_count++; /* pin it so it won't go away */
 	detach_mnt(new_mnt, &parent_path);
 	detach_mnt(root_mnt, &root_parent);
 	if (root_mnt->mnt.mnt_flags & MNT_LOCKED) {
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 714ce5cbd08c..5b1b365939b5 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -103,7 +103,7 @@ config NFS_V4
 config NFS_SWAP
 	bool "Provide swap over NFS support"
 	default n
-	depends on NFS_FS
+	depends on NFS_FS && SWAP
 	select SUNRPC_SWAP
 	help
 	  This option enables swapon to work on files located on NFS mounts.
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 315967354954..bcc51f131a49 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -130,6 +130,8 @@ static struct inode *nfs_layout_find_inode_by_stateid(struct nfs_client *clp,
 
 	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
 		list_for_each_entry(lo, &server->layouts, plh_layouts) {
+			if (!pnfs_layout_is_valid(lo))
+				continue;
 			if (stateid != NULL &&
 			    !nfs4_stateid_match_other(stateid, &lo->plh_stateid))
 				continue;
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 2ec71d2450c7..913a37fc3e11 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -151,6 +151,7 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init)
 	if ((clp = kzalloc(sizeof(*clp), GFP_KERNEL)) == NULL)
 		goto error_0;
 
+	clp->cl_minorversion = cl_init->minorversion;
 	clp->cl_nfs_mod = cl_init->nfs_mod;
 	if (!try_module_get(clp->cl_nfs_mod->owner))
 		goto error_dealloc;
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 3321cc7a7ead..90d02dc8e15d 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -158,6 +158,17 @@ typedef struct {
 	bool eof;
 } nfs_readdir_descriptor_t;
 
+static
+void nfs_readdir_init_array(struct page *page)
+{
+	struct nfs_cache_array *array;
+
+	array = kmap_atomic(page);
+	memset(array, 0, sizeof(struct nfs_cache_array));
+	array->eof_index = -1;
+	kunmap_atomic(array);
+}
+
 /*
  * we are freeing strings created by nfs_add_to_readdir_array()
  */
@@ -170,6 +181,7 @@ void nfs_readdir_clear_array(struct page *page)
 	array = kmap_atomic(page);
 	for (i = 0; i < array->size; i++)
 		kfree(array->array[i].string.name);
+	array->size = 0;
 	kunmap_atomic(array);
 }
 
@@ -606,6 +618,8 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page,
 	int status = -ENOMEM;
 	unsigned int array_size = ARRAY_SIZE(pages);
 
+	nfs_readdir_init_array(page);
+
 	entry.prev_cookie = 0;
 	entry.cookie = desc->last_cookie;
 	entry.eof = 0;
@@ -622,8 +636,6 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page,
 	}
 
 	array = kmap(page);
-	memset(array, 0, sizeof(struct nfs_cache_array));
-	array->eof_index = -1;
 
 	status = nfs_readdir_alloc_pages(pages, array_size);
 	if (status < 0)
@@ -678,6 +690,7 @@ int nfs_readdir_filler(void *data, struct page* page)
 	unlock_page(page);
 	return 0;
  error:
+	nfs_readdir_clear_array(page);
 	unlock_page(page);
 	return ret;
 }
@@ -685,8 +698,6 @@ int nfs_readdir_filler(void *data, struct page* page)
 static
 void cache_page_release(nfs_readdir_descriptor_t *desc)
 {
-	if (!desc->page->mapping)
-		nfs_readdir_clear_array(desc->page);
 	put_page(desc->page);
 	desc->page = NULL;
 }
@@ -700,19 +711,28 @@ struct page *get_cache_page(nfs_readdir_descriptor_t *desc)
 
 /*
  * Returns 0 if desc->dir_cookie was found on page desc->page_index
+ * and locks the page to prevent removal from the page cache.
  */
 static
-int find_cache_page(nfs_readdir_descriptor_t *desc)
+int find_and_lock_cache_page(nfs_readdir_descriptor_t *desc)
 {
 	int res;
 
 	desc->page = get_cache_page(desc);
 	if (IS_ERR(desc->page))
 		return PTR_ERR(desc->page);
-
-	res = nfs_readdir_search_array(desc);
+	res = lock_page_killable(desc->page);
 	if (res != 0)
-		cache_page_release(desc);
+		goto error;
+	res = -EAGAIN;
+	if (desc->page->mapping != NULL) {
+		res = nfs_readdir_search_array(desc);
+		if (res == 0)
+			return 0;
+	}
+	unlock_page(desc->page);
+error:
+	cache_page_release(desc);
 	return res;
 }
 
@@ -727,7 +747,7 @@ int readdir_search_pagecache(nfs_readdir_descriptor_t *desc)
 		desc->last_cookie = 0;
 	}
 	do {
-		res = find_cache_page(desc);
+		res = find_and_lock_cache_page(desc);
 	} while (res == -EAGAIN);
 	return res;
 }
@@ -766,7 +786,6 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc)
 		desc->eof = true;
 
 	kunmap(desc->page);
-	cache_page_release(desc);
 	dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling ended @ cookie %Lu; returning = %d\n",
 			(unsigned long long)*desc->dir_cookie, res);
 	return res;
@@ -812,13 +831,13 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc)
 
 	status = nfs_do_filldir(desc);
 
+ out_release:
+	nfs_readdir_clear_array(desc->page);
+	cache_page_release(desc);
  out:
 	dfprintk(DIRCACHE, "NFS: %s: returns %d\n",
 			__func__, status);
 	return status;
- out_release:
-	cache_page_release(desc);
-	goto out;
 }
 
 /* The file offset position represents the dirent entry number.  A
@@ -883,6 +902,8 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 			break;
 
 		res = nfs_do_filldir(desc);
+		unlock_page(desc->page);
+		cache_page_release(desc);
 		if (res < 0)
 			break;
 	} while (!desc->eof);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 98a9a0bcdf38..1aae0606dd87 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -262,10 +262,10 @@ static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq,
 					 data->ds_commit_index);
 
 	/* verifier not set so always fail */
-	if (verfp->committed < 0)
+	if (verfp->committed < 0 || data->res.verf->committed <= NFS_UNSTABLE)
 		return 1;
 
-	return nfs_direct_cmp_verf(verfp, &data->verf);
+	return nfs_direct_cmp_verf(verfp, data->res.verf);
 }
 
 /**
@@ -601,6 +601,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter)
 	l_ctx = nfs_get_lock_context(dreq->ctx);
 	if (IS_ERR(l_ctx)) {
 		result = PTR_ERR(l_ctx);
+		nfs_direct_req_release(dreq);
 		goto out_release;
 	}
 	dreq->l_ctx = l_ctx;
@@ -1031,6 +1032,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
 	l_ctx = nfs_get_lock_context(dreq->ctx);
 	if (IS_ERR(l_ctx)) {
 		result = PTR_ERR(l_ctx);
+		nfs_direct_req_release(dreq);
 		goto out_release;
 	}
 	dreq->l_ctx = l_ctx;
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 95dc90570786..387a2cfa7e17 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -140,6 +140,7 @@ static int
 nfs_file_flush(struct file *file, fl_owner_t id)
 {
 	struct inode	*inode = file_inode(file);
+	errseq_t since;
 
 	dprintk("NFS: flush(%pD2)\n", file);
 
@@ -148,7 +149,9 @@ nfs_file_flush(struct file *file, fl_owner_t id)
 		return 0;
 
 	/* Flush writes to the server and return any errors */
-	return nfs_wb_all(inode);
+	since = filemap_sample_wb_err(file->f_mapping);
+	nfs_wb_all(inode);
+	return filemap_check_wb_err(file->f_mapping, since);
 }
 
 ssize_t
@@ -580,12 +583,14 @@ static const struct vm_operations_struct nfs_file_vm_ops = {
 	.page_mkwrite = nfs_vm_page_mkwrite,
 };
 
-static int nfs_need_check_write(struct file *filp, struct inode *inode)
+static int nfs_need_check_write(struct file *filp, struct inode *inode,
+				int error)
 {
 	struct nfs_open_context *ctx;
 
 	ctx = nfs_file_open_context(filp);
-	if (nfs_ctx_key_to_expire(ctx, inode))
+	if (nfs_error_is_fatal_on_server(error) ||
+	    nfs_ctx_key_to_expire(ctx, inode))
 		return 1;
 	return 0;
 }
@@ -596,6 +601,8 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 	struct inode *inode = file_inode(file);
 	unsigned long written = 0;
 	ssize_t result;
+	errseq_t since;
+	int error;
 
 	result = nfs_key_timeout_notify(file, inode);
 	if (result)
@@ -620,6 +627,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 	if (iocb->ki_pos > i_size_read(inode))
 		nfs_revalidate_mapping(inode, file->f_mapping);
 
+	since = filemap_sample_wb_err(file->f_mapping);
 	nfs_start_io_write(inode);
 	result = generic_write_checks(iocb, from);
 	if (result > 0) {
@@ -638,7 +646,8 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 		goto out;
 
 	/* Return error values */
-	if (nfs_need_check_write(file, inode)) {
+	error = filemap_check_wb_err(file->f_mapping, since);
+	if (nfs_need_check_write(file, inode, error)) {
 		int err = nfs_wb_all(inode);
 		if (err < 0)
 			result = err;
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 38d915814221..eebaa24e1cb7 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -980,9 +980,8 @@ retry:
 		goto out_mds;
 
 	/* Use a direct mapping of ds_idx to pgio mirror_idx */
-	if (WARN_ON_ONCE(pgio->pg_mirror_count !=
-	    FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg)))
-		goto out_mds;
+	if (pgio->pg_mirror_count != FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg))
+		goto out_eagain;
 
 	for (i = 0; i < pgio->pg_mirror_count; i++) {
 		mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i);
@@ -1004,12 +1003,16 @@ retry:
 			(NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR))
 		pgio->pg_maxretrans = io_maxretrans;
 	return;
-
+out_eagain:
+	pnfs_generic_pg_cleanup(pgio);
+	pgio->pg_error = -EAGAIN;
+	return;
 out_mds:
 	pnfs_put_lseg(pgio->pg_lseg);
 	pgio->pg_lseg = NULL;
 	pgio->pg_maxretrans = 0;
 	nfs_pageio_reset_write_mds(pgio);
+	pgio->pg_error = -EAGAIN;
 }
 
 static unsigned int
diff --git a/fs/nfs/fscache-index.c b/fs/nfs/fscache-index.c
index 15f271401dcc..573b1da9342c 100644
--- a/fs/nfs/fscache-index.c
+++ b/fs/nfs/fscache-index.c
@@ -84,8 +84,10 @@ enum fscache_checkaux nfs_fscache_inode_check_aux(void *cookie_netfs_data,
 		return FSCACHE_CHECKAUX_OBSOLETE;
 
 	memset(&auxdata, 0, sizeof(auxdata));
-	auxdata.mtime = timespec64_to_timespec(nfsi->vfs_inode.i_mtime);
-	auxdata.ctime = timespec64_to_timespec(nfsi->vfs_inode.i_ctime);
+	auxdata.mtime_sec  = nfsi->vfs_inode.i_mtime.tv_sec;
+	auxdata.mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec;
+	auxdata.ctime_sec  = nfsi->vfs_inode.i_ctime.tv_sec;
+	auxdata.ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec;
 
 	if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
 		auxdata.change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode);
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index 3800ab6f08fa..7d6721ec31d4 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -31,6 +31,7 @@ static DEFINE_SPINLOCK(nfs_fscache_keys_lock);
 struct nfs_server_key {
 	struct {
 		uint16_t	nfsversion;		/* NFS protocol version */
+		uint32_t	minorversion;		/* NFSv4 minor version */
 		uint16_t	family;			/* address family */
 		__be16		port;			/* IP port */
 	} hdr;
@@ -55,6 +56,7 @@ void nfs_fscache_get_client_cookie(struct nfs_client *clp)
 
 	memset(&key, 0, sizeof(key));
 	key.hdr.nfsversion = clp->rpc_ops->version;
+	key.hdr.minorversion = clp->cl_minorversion;
 	key.hdr.family = clp->cl_addr.ss_family;
 
 	switch (clp->cl_addr.ss_family) {
@@ -186,7 +188,8 @@ void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int
 	/* create a cache index for looking up filehandles */
 	nfss->fscache = fscache_acquire_cookie(nfss->nfs_client->fscache,
 					       &nfs_fscache_super_index_def,
-					       key, sizeof(*key) + ulen,
+					       &key->key,
+					       sizeof(key->key) + ulen,
 					       NULL, 0,
 					       nfss, 0, true);
 	dfprintk(FSCACHE, "NFS: get superblock cookie (0x%p/0x%p)\n",
@@ -224,6 +227,19 @@ void nfs_fscache_release_super_cookie(struct super_block *sb)
 	}
 }
 
+static void nfs_fscache_update_auxdata(struct nfs_fscache_inode_auxdata *auxdata,
+				  struct nfs_inode *nfsi)
+{
+	memset(auxdata, 0, sizeof(*auxdata));
+	auxdata->mtime_sec  = nfsi->vfs_inode.i_mtime.tv_sec;
+	auxdata->mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec;
+	auxdata->ctime_sec  = nfsi->vfs_inode.i_ctime.tv_sec;
+	auxdata->ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec;
+
+	if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
+		auxdata->change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode);
+}
+
 /*
  * Initialise the per-inode cache cookie pointer for an NFS inode.
  */
@@ -237,12 +253,7 @@ void nfs_fscache_init_inode(struct inode *inode)
 	if (!(nfss->fscache && S_ISREG(inode->i_mode)))
 		return;
 
-	memset(&auxdata, 0, sizeof(auxdata));
-	auxdata.mtime = timespec64_to_timespec(nfsi->vfs_inode.i_mtime);
-	auxdata.ctime = timespec64_to_timespec(nfsi->vfs_inode.i_ctime);
-
-	if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
-		auxdata.change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode);
+	nfs_fscache_update_auxdata(&auxdata, nfsi);
 
 	nfsi->fscache = fscache_acquire_cookie(NFS_SB(inode->i_sb)->fscache,
 					       &nfs_fscache_inode_object_def,
@@ -262,9 +273,7 @@ void nfs_fscache_clear_inode(struct inode *inode)
 
 	dfprintk(FSCACHE, "NFS: clear cookie (0x%p/0x%p)\n", nfsi, cookie);
 
-	memset(&auxdata, 0, sizeof(auxdata));
-	auxdata.mtime = timespec64_to_timespec(nfsi->vfs_inode.i_mtime);
-	auxdata.ctime = timespec64_to_timespec(nfsi->vfs_inode.i_ctime);
+	nfs_fscache_update_auxdata(&auxdata, nfsi);
 	fscache_relinquish_cookie(cookie, &auxdata, false);
 	nfsi->fscache = NULL;
 }
@@ -304,9 +313,7 @@ void nfs_fscache_open_file(struct inode *inode, struct file *filp)
 	if (!fscache_cookie_valid(cookie))
 		return;
 
-	memset(&auxdata, 0, sizeof(auxdata));
-	auxdata.mtime = timespec64_to_timespec(nfsi->vfs_inode.i_mtime);
-	auxdata.ctime = timespec64_to_timespec(nfsi->vfs_inode.i_ctime);
+	nfs_fscache_update_auxdata(&auxdata, nfsi);
 
 	if (inode_is_open_for_write(inode)) {
 		dfprintk(FSCACHE, "NFS: nfsi 0x%p disabling cache\n", nfsi);
diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h
index ad041cfbf9ec..6754c8607230 100644
--- a/fs/nfs/fscache.h
+++ b/fs/nfs/fscache.h
@@ -62,9 +62,11 @@ struct nfs_fscache_key {
  * cache object.
  */
 struct nfs_fscache_inode_auxdata {
-	struct timespec	mtime;
-	struct timespec	ctime;
-	u64		change_attr;
+	s64	mtime_sec;
+	s64	mtime_nsec;
+	s64	ctime_sec;
+	s64	ctime_nsec;
+	u64	change_attr;
 };
 
 /*
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 53777813ca95..82b440630d14 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -824,6 +824,8 @@ int nfs_getattr(const struct path *path, struct kstat *stat,
 		do_update |= cache_validity & NFS_INO_INVALID_ATIME;
 	if (request_mask & (STATX_CTIME|STATX_MTIME))
 		do_update |= cache_validity & NFS_INO_REVAL_PAGECACHE;
+	if (request_mask & STATX_BLOCKS)
+		do_update |= cache_validity & NFS_INO_INVALID_BLOCKS;
 	if (do_update) {
 		/* Update the attribute cache */
 		if (!(server->flags & NFS_MOUNT_NOAC))
@@ -957,16 +959,16 @@ struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry,
 						struct file *filp)
 {
 	struct nfs_open_context *ctx;
-	const struct cred *cred = get_current_cred();
 
 	ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
-	if (!ctx) {
-		put_cred(cred);
+	if (!ctx)
 		return ERR_PTR(-ENOMEM);
-	}
 	nfs_sb_active(dentry->d_sb);
 	ctx->dentry = dget(dentry);
-	ctx->cred = cred;
+	if (filp)
+		ctx->cred = get_cred(filp->f_cred);
+	else
+		ctx->cred = get_current_cred();
 	ctx->ll_cred = NULL;
 	ctx->state = NULL;
 	ctx->mode = f_mode;
@@ -1733,7 +1735,8 @@ out_noforce:
 	status = nfs_post_op_update_inode_locked(inode, fattr,
 			NFS_INO_INVALID_CHANGE
 			| NFS_INO_INVALID_CTIME
-			| NFS_INO_INVALID_MTIME);
+			| NFS_INO_INVALID_MTIME
+			| NFS_INO_INVALID_BLOCKS);
 	return status;
 }
 
@@ -1843,7 +1846,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR
 			| NFS_INO_INVALID_ATIME
 			| NFS_INO_REVAL_FORCED
-			| NFS_INO_REVAL_PAGECACHE);
+			| NFS_INO_REVAL_PAGECACHE
+			| NFS_INO_INVALID_BLOCKS);
 
 	/* Do atomic weak cache consistency updates */
 	nfs_wcc_update_inode(inode, fattr);
@@ -2004,8 +2008,12 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used);
 	} else if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED)
 		inode->i_blocks = fattr->du.nfs2.blocks;
-	else
+	else {
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_BLOCKS
+				| NFS_INO_REVAL_FORCED);
 		cache_revalidated = false;
+	}
 
 	/* Update attrtimeo value if we're out of the unstable period */
 	if (attr_changed) {
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index 266da4cac411..1f2f6f45e174 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -29,9 +29,8 @@
  */
 #define encode_dirpath_sz	(1 + XDR_QUADLEN(MNTPATHLEN))
 #define MNT_status_sz		(1)
-#define MNT_fhs_status_sz	(1)
 #define MNT_fhandle_sz		XDR_QUADLEN(NFS2_FHSIZE)
-#define MNT_fhandle3_sz		(1 + XDR_QUADLEN(NFS3_FHSIZE))
+#define MNT_fhandlev3_sz	XDR_QUADLEN(NFS3_FHSIZE)
 #define MNT_authflav3_sz	(1 + NFS_MAX_SECFLAVORS)
 
 /*
@@ -39,7 +38,7 @@
  */
 #define MNT_enc_dirpath_sz	encode_dirpath_sz
 #define MNT_dec_mountres_sz	(MNT_status_sz + MNT_fhandle_sz)
-#define MNT_dec_mountres3_sz	(MNT_status_sz + MNT_fhandle_sz + \
+#define MNT_dec_mountres3_sz	(MNT_status_sz + MNT_fhandlev3_sz + \
 				 MNT_authflav3_sz)
 
 /*
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index 572794dab4b1..696a13bfaff5 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -370,7 +370,7 @@ static void encode_sattr(struct xdr_stream *xdr, const struct iattr *attr,
 	} else
 		p = xdr_time_not_set(p);
 	if (attr->ia_valid & ATTR_MTIME_SET) {
-		ts = timespec64_to_timespec(attr->ia_atime);
+		ts = timespec64_to_timespec(attr->ia_mtime);
 		xdr_encode_time(p, &ts);
 	} else if (attr->ia_valid & ATTR_MTIME) {
 		ts = timespec64_to_timespec(attr->ia_mtime);
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index c5c3fc6e6c60..26c94b32d6f4 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -253,37 +253,45 @@ int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
 
 int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
-	struct posix_acl *alloc = NULL, *dfacl = NULL;
+	struct posix_acl *orig = acl, *dfacl = NULL, *alloc;
 	int status;
 
 	if (S_ISDIR(inode->i_mode)) {
 		switch(type) {
 		case ACL_TYPE_ACCESS:
-			alloc = dfacl = get_acl(inode, ACL_TYPE_DEFAULT);
+			alloc = get_acl(inode, ACL_TYPE_DEFAULT);
 			if (IS_ERR(alloc))
 				goto fail;
+			dfacl = alloc;
 			break;
 
 		case ACL_TYPE_DEFAULT:
-			dfacl = acl;
-			alloc = acl = get_acl(inode, ACL_TYPE_ACCESS);
+			alloc = get_acl(inode, ACL_TYPE_ACCESS);
 			if (IS_ERR(alloc))
 				goto fail;
+			dfacl = acl;
+			acl = alloc;
 			break;
 		}
 	}
 
 	if (acl == NULL) {
-		alloc = acl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
+		alloc = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
 		if (IS_ERR(alloc))
 			goto fail;
+		acl = alloc;
 	}
 	status = __nfs3_proc_setacls(inode, acl, dfacl);
-	posix_acl_release(alloc);
+out:
+	if (acl != orig)
+		posix_acl_release(acl);
+	if (dfacl != orig)
+		posix_acl_release(dfacl);
 	return status;
 
 fail:
-	return PTR_ERR(alloc);
+	status = PTR_ERR(alloc);
+	goto out;
 }
 
 const struct xattr_handler *nfs3_xattr_handlers[] = {
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index abbbdde97e31..45a6691f0893 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -2338,6 +2338,7 @@ static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req,
 				   void *data)
 {
 	struct nfs_commitres *result = data;
+	struct nfs_writeverf *verf = result->verf;
 	enum nfs_stat status;
 	int error;
 
@@ -2350,7 +2351,9 @@ static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req,
 	result->op_status = status;
 	if (status != NFS3_OK)
 		goto out_status;
-	error = decode_writeverf3(xdr, &result->verf->verifier);
+	error = decode_writeverf3(xdr, &verf->verifier);
+	if (!error)
+		verf->committed = NFS_FILE_SYNC;
 out:
 	return error;
 out_status:
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 5196bfa7894d..9b61c80a93e9 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -283,14 +283,14 @@ static ssize_t _nfs42_proc_copy(struct file *src,
 		status = handle_async_copy(res, server, src, dst,
 				&args->src_stateid);
 		if (status)
-			return status;
+			goto out;
 	}
 
 	if ((!res->synchronous || !args->sync) &&
 			res->write_res.verifier.committed != NFS_FILE_SYNC) {
 		status = process_copy_commit(dst, pos_dst, res);
 		if (status)
-			return status;
+			goto out;
 	}
 
 	truncate_pagecache_range(dst_inode, pos_dst,
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 235919156edd..c9113808e68e 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -439,9 +439,7 @@ extern void nfs4_schedule_state_renewal(struct nfs_client *);
 extern void nfs4_renewd_prepare_shutdown(struct nfs_server *);
 extern void nfs4_kill_renewd(struct nfs_client *);
 extern void nfs4_renew_state(struct work_struct *);
-extern void nfs4_set_lease_period(struct nfs_client *clp,
-		unsigned long lease,
-		unsigned long lastrenewed);
+extern void nfs4_set_lease_period(struct nfs_client *clp, unsigned long lease);
 
 
 /* nfs4state.c */
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 208a236dc235..8b96a4dd6c4a 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -216,7 +216,6 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init)
 	INIT_LIST_HEAD(&clp->cl_ds_clients);
 	rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS client");
 	clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED;
-	clp->cl_minorversion = cl_init->minorversion;
 	clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion];
 	clp->cl_mig_gen = 1;
 #if IS_ENABLED(CONFIG_NFS_V4_1)
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 336643b82188..f39651196a7e 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -86,7 +86,6 @@ nfs4_file_open(struct inode *inode, struct file *filp)
 	if (inode != d_inode(dentry))
 		goto out_drop;
 
-	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
 	nfs_file_set_open_context(filp, ctx);
 	nfs_fscache_open_file(inode, filp);
 	err = 0;
@@ -110,6 +109,7 @@ static int
 nfs4_file_flush(struct file *file, fl_owner_t id)
 {
 	struct inode	*inode = file_inode(file);
+	errseq_t since;
 
 	dprintk("NFS: flush(%pD2)\n", file);
 
@@ -125,7 +125,9 @@ nfs4_file_flush(struct file *file, fl_owner_t id)
 		return filemap_fdatawrite(file->f_mapping);
 
 	/* Flush writes to the server and return any errors */
-	return nfs_wb_all(inode);
+	since = filemap_sample_wb_err(file->f_mapping);
+	nfs_wb_all(inode);
+	return filemap_check_wb_err(file->f_mapping, since);
 }
 
 #ifdef CONFIG_NFS_V4_2
@@ -194,6 +196,9 @@ static loff_t nfs42_remap_file_range(struct file *src_file, loff_t src_off,
 	if (remap_flags & ~REMAP_FILE_ADVISORY)
 		return -EINVAL;
 
+	if (IS_SWAPFILE(dst_inode) || IS_SWAPFILE(src_inode))
+		return -ETXTBSY;
+
 	/* check alignment w.r.t. clone_blksize */
 	ret = -EINVAL;
 	if (bs) {
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 91cd512af4a2..f3c17c8fb022 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -504,9 +504,7 @@ static int nfs4_do_handle_exception(struct nfs_server *server,
 		case -NFS4ERR_DEADSESSION:
 		case -NFS4ERR_SEQ_FALSE_RETRY:
 		case -NFS4ERR_SEQ_MISORDERED:
-			dprintk("%s ERROR: %d Reset session\n", __func__,
-				errorcode);
-			nfs4_schedule_session_recovery(clp->cl_session, errorcode);
+			/* Handled in nfs41_sequence_process() */
 			goto wait_on_recovery;
 #endif /* defined(CONFIG_NFS_V4_1) */
 		case -NFS4ERR_FILE_OPEN:
@@ -759,12 +757,21 @@ static void nfs4_slot_sequence_acked(struct nfs4_slot *slot,
 	slot->seq_nr_last_acked = seqnr;
 }
 
+static void nfs4_probe_sequence(struct nfs_client *client, const struct cred *cred,
+				struct nfs4_slot *slot)
+{
+	struct rpc_task *task = _nfs41_proc_sequence(client, cred, slot, true);
+	if (!IS_ERR(task))
+		rpc_put_task_async(task);
+}
+
 static int nfs41_sequence_process(struct rpc_task *task,
 		struct nfs4_sequence_res *res)
 {
 	struct nfs4_session *session;
 	struct nfs4_slot *slot = res->sr_slot;
 	struct nfs_client *clp;
+	int status;
 	int ret = 1;
 
 	if (slot == NULL)
@@ -774,16 +781,21 @@ static int nfs41_sequence_process(struct rpc_task *task,
 		goto out;
 
 	session = slot->table->session;
+	clp = session->clp;
 
 	trace_nfs4_sequence_done(session, res);
+
+	status = res->sr_status;
+	if (task->tk_status == -NFS4ERR_DEADSESSION)
+		status = -NFS4ERR_DEADSESSION;
+
 	/* Check the SEQUENCE operation status */
-	switch (res->sr_status) {
+	switch (status) {
 	case 0:
 		/* Mark this sequence number as having been acked */
 		nfs4_slot_sequence_acked(slot, slot->seq_nr);
 		/* Update the slot's sequence and clientid lease timer */
 		slot->seq_done = 1;
-		clp = session->clp;
 		do_renew_lease(clp, res->sr_timestamp);
 		/* Check sequence flags */
 		nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags,
@@ -831,10 +843,18 @@ static int nfs41_sequence_process(struct rpc_task *task,
 		/*
 		 * Were one or more calls using this slot interrupted?
 		 * If the server never received the request, then our
-		 * transmitted slot sequence number may be too high.
+		 * transmitted slot sequence number may be too high. However,
+		 * if the server did receive the request then it might
+		 * accidentally give us a reply with a mismatched operation.
+		 * We can sort this out by sending a lone sequence operation
+		 * to the server on the same slot.
 		 */
 		if ((s32)(slot->seq_nr - slot->seq_nr_last_acked) > 1) {
 			slot->seq_nr--;
+			if (task->tk_msg.rpc_proc != &nfs4_procedures[NFSPROC4_CLNT_SEQUENCE]) {
+				nfs4_probe_sequence(clp, task->tk_msg.rpc_cred, slot);
+				res->sr_slot = NULL;
+			}
 			goto retry_nowait;
 		}
 		/*
@@ -849,6 +869,10 @@ static int nfs41_sequence_process(struct rpc_task *task,
 		 */
 		slot->seq_nr = slot->seq_nr_highest_sent;
 		goto out_retry;
+	case -NFS4ERR_BADSESSION:
+	case -NFS4ERR_DEADSESSION:
+	case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+		goto session_recover;
 	default:
 		/* Just update the slot sequence no. */
 		slot->seq_done = 1;
@@ -859,8 +883,10 @@ out:
 out_noaction:
 	return ret;
 session_recover:
-	nfs4_schedule_session_recovery(session, res->sr_status);
-	goto retry_nowait;
+	nfs4_schedule_session_recovery(session, status);
+	dprintk("%s ERROR: %d Reset session\n", __func__, status);
+	nfs41_sequence_free_slot(res);
+	goto out;
 retry_new_seq:
 	++slot->seq_nr;
 retry_nowait:
@@ -2154,7 +2180,6 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct
 		case -NFS4ERR_BAD_HIGH_SLOT:
 		case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
 		case -NFS4ERR_DEADSESSION:
-			nfs4_schedule_session_recovery(server->nfs_client->cl_session, err);
 			return -EAGAIN;
 		case -NFS4ERR_STALE_CLIENTID:
 		case -NFS4ERR_STALE_STATEID:
@@ -2920,10 +2945,13 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 	struct nfs_server *server = sp->so_server;
 	struct dentry *dentry;
 	struct nfs4_state *state;
+	struct inode *dir = d_inode(opendata->dir);
+	unsigned long dir_verifier;
 	unsigned int seq;
 	int ret;
 
 	seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);
+	dir_verifier = nfs_save_change_attribute(dir);
 
 	ret = _nfs4_proc_open(opendata, ctx);
 	if (ret != 0)
@@ -2951,8 +2979,19 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 			dput(ctx->dentry);
 			ctx->dentry = dentry = alias;
 		}
-		nfs_set_verifier(dentry,
-				nfs_save_change_attribute(d_inode(opendata->dir)));
+	}
+
+	switch(opendata->o_arg.claim) {
+	default:
+		break;
+	case NFS4_OPEN_CLAIM_NULL:
+	case NFS4_OPEN_CLAIM_DELEGATE_CUR:
+	case NFS4_OPEN_CLAIM_DELEGATE_PREV:
+		if (!opendata->rpc_done)
+			break;
+		if (opendata->o_res.delegation_type != 0)
+			dir_verifier = nfs_save_change_attribute(dir);
+		nfs_set_verifier(dentry, dir_verifier);
 	}
 
 	/* Parse layoutget results before we check for access */
@@ -3144,6 +3183,11 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir,
 			exception.retry = 1;
 			continue;
 		}
+		if (status == -NFS4ERR_EXPIRED) {
+			nfs4_schedule_lease_recovery(server->nfs_client);
+			exception.retry = 1;
+			continue;
+		}
 		if (status == -EAGAIN) {
 			/* We must have found a delegation */
 			exception.retry = 1;
@@ -4928,16 +4972,13 @@ static int nfs4_do_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, str
 	struct nfs4_exception exception = {
 		.interruptible = true,
 	};
-	unsigned long now = jiffies;
 	int err;
 
 	do {
 		err = _nfs4_do_fsinfo(server, fhandle, fsinfo);
 		trace_nfs4_fsinfo(server, fhandle, fsinfo->fattr, err);
 		if (err == 0) {
-			nfs4_set_lease_period(server->nfs_client,
-					fsinfo->lease_time * HZ,
-					now);
+			nfs4_set_lease_period(server->nfs_client, fsinfo->lease_time * HZ);
 			break;
 		}
 		err = nfs4_handle_exception(server, err, &exception);
@@ -5200,7 +5241,7 @@ static void nfs4_proc_write_setup(struct nfs_pgio_header *hdr,
 	hdr->timestamp   = jiffies;
 
 	msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_WRITE];
-	nfs4_init_sequence(&hdr->args.seq_args, &hdr->res.seq_res, 1, 0);
+	nfs4_init_sequence(&hdr->args.seq_args, &hdr->res.seq_res, 0, 0);
 	nfs4_state_protect_write(server->nfs_client, clnt, msg, hdr);
 }
 
@@ -5688,8 +5729,6 @@ static int _nfs4_get_security_label(struct inode *inode, void *buf,
 		return ret;
 	if (!(fattr.valid & NFS_ATTR_FATTR_V4_SECURITY_LABEL))
 		return -ENOENT;
-	if (buflen < label.len)
-		return -ERANGE;
 	return 0;
 }
 
@@ -5994,6 +6033,7 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program,
 		.callback_data = &setclientid,
 		.flags = RPC_TASK_TIMEOUT,
 	};
+	unsigned long now = jiffies;
 	int status;
 
 	/* nfs_client_id4 */
@@ -6031,6 +6071,9 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program,
 		put_rpccred(setclientid.sc_cred);
 	}
 	rpc_put_task(task);
+
+	if (status == 0)
+		do_renew_lease(clp, now);
 out:
 	trace_nfs4_setclientid(clp, status);
 	dprintk("NFS reply setclientid: %d\n", status);
@@ -6189,8 +6232,10 @@ static void nfs4_delegreturn_prepare(struct rpc_task *task, void *data)
 
 	d_data = (struct nfs4_delegreturndata *)data;
 
-	if (!d_data->lr.roc && nfs4_wait_on_layoutreturn(d_data->inode, task))
+	if (!d_data->lr.roc && nfs4_wait_on_layoutreturn(d_data->inode, task)) {
+		nfs4_sequence_done(task, &d_data->res.seq_res);
 		return;
+	}
 
 	lo = d_data->args.lr_args ? d_data->args.lr_args->layout : NULL;
 	if (lo && !pnfs_layout_is_valid(lo)) {
@@ -7710,10 +7755,26 @@ nfs41_same_server_scope(struct nfs41_server_scope *a,
 static void
 nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata)
 {
+	struct nfs41_bind_conn_to_session_args *args = task->tk_msg.rpc_argp;
+	struct nfs41_bind_conn_to_session_res *res = task->tk_msg.rpc_resp;
+	struct nfs_client *clp = args->client;
+
+	switch (task->tk_status) {
+	case -NFS4ERR_BADSESSION:
+	case -NFS4ERR_DEADSESSION:
+		nfs4_schedule_session_recovery(clp->cl_session,
+				task->tk_status);
+	}
+	if (args->dir == NFS4_CDFC4_FORE_OR_BOTH &&
+			res->dir != NFS4_CDFS4_BOTH) {
+		rpc_task_close_connection(task);
+		if (args->retries++ < MAX_BIND_CONN_TO_SESSION_RETRIES)
+			rpc_restart_call(task);
+	}
 }
 
 static const struct rpc_call_ops nfs4_bind_one_conn_to_session_ops = {
-	.rpc_call_done =  &nfs4_bind_one_conn_to_session_done,
+	.rpc_call_done =  nfs4_bind_one_conn_to_session_done,
 };
 
 /*
@@ -7732,6 +7793,7 @@ int nfs4_proc_bind_one_conn_to_session(struct rpc_clnt *clnt,
 	struct nfs41_bind_conn_to_session_args args = {
 		.client = clp,
 		.dir = NFS4_CDFC4_FORE_OR_BOTH,
+		.retries = 0,
 	};
 	struct nfs41_bind_conn_to_session_res res;
 	struct rpc_message msg = {
@@ -8069,6 +8131,7 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, const struct cred *cre
 	struct rpc_task *task;
 	struct nfs41_exchange_id_args *argp;
 	struct nfs41_exchange_id_res *resp;
+	unsigned long now = jiffies;
 	int status;
 
 	task = nfs4_run_exchange_id(clp, cred, sp4_how, NULL);
@@ -8089,6 +8152,8 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, const struct cred *cre
 	if (status != 0)
 		goto out;
 
+	do_renew_lease(clp, now);
+
 	clp->cl_clientid = resp->clientid;
 	clp->cl_exchange_flags = resp->flags;
 	clp->cl_seqid = resp->seqid;
@@ -8756,8 +8821,6 @@ static int nfs41_reclaim_complete_handle_errors(struct rpc_task *task, struct nf
 	case -NFS4ERR_BADSESSION:
 	case -NFS4ERR_DEADSESSION:
 	case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
-		nfs4_schedule_session_recovery(clp->cl_session,
-				task->tk_status);
 		break;
 	default:
 		nfs4_schedule_lease_recovery(clp);
diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c
index 6ea431b067dd..ff876dda7f06 100644
--- a/fs/nfs/nfs4renewd.c
+++ b/fs/nfs/nfs4renewd.c
@@ -138,15 +138,12 @@ nfs4_kill_renewd(struct nfs_client *clp)
  *
  * @clp: pointer to nfs_client
  * @lease: new value for lease period
- * @lastrenewed: time at which lease was last renewed
  */
 void nfs4_set_lease_period(struct nfs_client *clp,
-		unsigned long lease,
-		unsigned long lastrenewed)
+		unsigned long lease)
 {
 	spin_lock(&clp->cl_lock);
 	clp->cl_lease_time = lease;
-	clp->cl_last_renewal = lastrenewed;
 	spin_unlock(&clp->cl_lock);
 
 	/* Cap maximum reconnect timeout at 1/2 lease period */
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 0e69cd846afb..6f7d16086785 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -290,17 +290,15 @@ static int nfs41_setup_state_renewal(struct nfs_client *clp)
 {
 	int status;
 	struct nfs_fsinfo fsinfo;
-	unsigned long now;
 
 	if (!test_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state)) {
 		nfs4_schedule_state_renewal(clp);
 		return 0;
 	}
 
-	now = jiffies;
 	status = nfs4_proc_get_lease_time(clp, &fsinfo);
 	if (status == 0) {
-		nfs4_set_lease_period(clp, fsinfo.lease_time * HZ, now);
+		nfs4_set_lease_period(clp, fsinfo.lease_time * HZ);
 		nfs4_schedule_state_renewal(clp);
 	}
 
@@ -735,9 +733,9 @@ nfs4_get_open_state(struct inode *inode, struct nfs4_state_owner *owner)
 		state = new;
 		state->owner = owner;
 		atomic_inc(&owner->so_count);
-		list_add_rcu(&state->inode_states, &nfsi->open_states);
 		ihold(inode);
 		state->inode = inode;
+		list_add_rcu(&state->inode_states, &nfsi->open_states);
 		spin_unlock(&inode->i_lock);
 		/* Note: The reclaim code dictates that we add stateless
 		 * and read-only stateids to the end of the list */
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index ff06820b9efb..d554baabef3e 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -4163,7 +4163,11 @@ static int decode_attr_security_label(struct xdr_stream *xdr, uint32_t *bitmap,
 			return -EIO;
 		if (len < NFS4_MAXLABELLEN) {
 			if (label) {
-				memcpy(label->label, p, len);
+				if (label->len) {
+					if (label->len < len)
+						return -ERANGE;
+					memcpy(label->label, p, len);
+				}
 				label->len = len;
 				label->pi = pi;
 				label->lfs = lfs;
@@ -4310,11 +4314,14 @@ static int decode_write_verifier(struct xdr_stream *xdr, struct nfs_write_verifi
 
 static int decode_commit(struct xdr_stream *xdr, struct nfs_commitres *res)
 {
+	struct nfs_writeverf *verf = res->verf;
 	int status;
 
 	status = decode_op_hdr(xdr, OP_COMMIT);
 	if (!status)
-		status = decode_write_verifier(xdr, &res->verf->verifier);
+		status = decode_write_verifier(xdr, &verf->verifier);
+	if (!status)
+		verf->committed = NFS_FILE_SYNC;
 	return status;
 }
 
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index eae584dbfa08..64d87576a6c1 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -888,15 +888,6 @@ static void nfs_pageio_setup_mirroring(struct nfs_pageio_descriptor *pgio,
 	pgio->pg_mirror_count = mirror_count;
 }
 
-/*
- * nfs_pageio_stop_mirroring - stop using mirroring (set mirror count to 1)
- */
-void nfs_pageio_stop_mirroring(struct nfs_pageio_descriptor *pgio)
-{
-	pgio->pg_mirror_count = 1;
-	pgio->pg_mirror_idx = 0;
-}
-
 static void nfs_pageio_cleanup_mirroring(struct nfs_pageio_descriptor *pgio)
 {
 	pgio->pg_mirror_count = 1;
@@ -1179,38 +1170,38 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
 	if (desc->pg_error < 0)
 		goto out_failed;
 
-	for (midx = 0; midx < desc->pg_mirror_count; midx++) {
-		if (midx) {
-			nfs_page_group_lock(req);
+	/* Create the mirror instances first, and fire them off */
+	for (midx = 1; midx < desc->pg_mirror_count; midx++) {
+		nfs_page_group_lock(req);
 
-			/* find the last request */
-			for (lastreq = req->wb_head;
-			     lastreq->wb_this_page != req->wb_head;
-			     lastreq = lastreq->wb_this_page)
-				;
+		/* find the last request */
+		for (lastreq = req->wb_head;
+		     lastreq->wb_this_page != req->wb_head;
+		     lastreq = lastreq->wb_this_page)
+			;
 
-			dupreq = nfs_create_subreq(req, lastreq,
-					pgbase, offset, bytes);
+		dupreq = nfs_create_subreq(req, lastreq,
+				pgbase, offset, bytes);
 
-			nfs_page_group_unlock(req);
-			if (IS_ERR(dupreq)) {
-				desc->pg_error = PTR_ERR(dupreq);
-				goto out_failed;
-			}
-		} else
-			dupreq = req;
+		nfs_page_group_unlock(req);
+		if (IS_ERR(dupreq)) {
+			desc->pg_error = PTR_ERR(dupreq);
+			goto out_failed;
+		}
 
-		if (nfs_pgio_has_mirroring(desc))
-			desc->pg_mirror_idx = midx;
+		desc->pg_mirror_idx = midx;
 		if (!nfs_pageio_add_request_mirror(desc, dupreq))
 			goto out_cleanup_subreq;
 	}
 
+	desc->pg_mirror_idx = 0;
+	if (!nfs_pageio_add_request_mirror(desc, req))
+		goto out_failed;
+
 	return 1;
 
 out_cleanup_subreq:
-	if (req != dupreq)
-		nfs_pageio_cleanup_request(desc, dupreq);
+	nfs_pageio_cleanup_request(desc, dupreq);
 out_failed:
 	nfs_pageio_error_cleanup(desc);
 	return 0;
@@ -1322,6 +1313,14 @@ void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *desc, pgoff_t index)
 	}
 }
 
+/*
+ * nfs_pageio_stop_mirroring - stop using mirroring (set mirror count to 1)
+ */
+void nfs_pageio_stop_mirroring(struct nfs_pageio_descriptor *pgio)
+{
+	nfs_pageio_complete(pgio);
+}
+
 int __init nfs_init_nfspagecache(void)
 {
 	nfs_page_cachep = kmem_cache_create("nfs_page",
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 33c2ef416564..9b58894eb9b7 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1188,31 +1188,27 @@ out:
 	return status;
 }
 
+static bool
+pnfs_layout_segments_returnable(struct pnfs_layout_hdr *lo,
+				enum pnfs_iomode iomode,
+				u32 seq)
+{
+	struct pnfs_layout_range recall_range = {
+		.length = NFS4_MAX_UINT64,
+		.iomode = iomode,
+	};
+	return pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs,
+					       &recall_range, seq) != -EBUSY;
+}
+
 /* Return true if layoutreturn is needed */
 static bool
 pnfs_layout_need_return(struct pnfs_layout_hdr *lo)
 {
-	struct pnfs_layout_segment *s;
-	enum pnfs_iomode iomode;
-	u32 seq;
-
 	if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags))
 		return false;
-
-	seq = lo->plh_return_seq;
-	iomode = lo->plh_return_iomode;
-
-	/* Defer layoutreturn until all recalled lsegs are done */
-	list_for_each_entry(s, &lo->plh_segs, pls_list) {
-		if (seq && pnfs_seqid_is_newer(s->pls_seq, seq))
-			continue;
-		if (iomode != IOMODE_ANY && s->pls_range.iomode != iomode)
-			continue;
-		if (test_bit(NFS_LSEG_LAYOUTRETURN, &s->pls_flags))
-			return false;
-	}
-
-	return true;
+	return pnfs_layout_segments_returnable(lo, lo->plh_return_iomode,
+					       lo->plh_return_seq);
 }
 
 static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo)
@@ -1415,7 +1411,7 @@ retry:
 	/* lo ref dropped in pnfs_roc_release() */
 	layoutreturn = pnfs_prepare_layoutreturn(lo, &stateid, &iomode);
 	/* If the creds don't match, we can't compound the layoutreturn */
-	if (!layoutreturn || cred != lo->plh_lc_cred)
+	if (!layoutreturn || cred_fscmp(cred, lo->plh_lc_cred) != 0)
 		goto out_noroc;
 
 	roc = layoutreturn;
@@ -2301,16 +2297,6 @@ out_forget:
 	return ERR_PTR(-EAGAIN);
 }
 
-static int
-mark_lseg_invalid_or_return(struct pnfs_layout_segment *lseg,
-		struct list_head *tmp_list)
-{
-	if (!mark_lseg_invalid(lseg, tmp_list))
-		return 0;
-	pnfs_cache_lseg_for_layoutreturn(lseg->pls_layout, lseg);
-	return 1;
-}
-
 /**
  * pnfs_mark_matching_lsegs_return - Free or return matching layout segments
  * @lo: pointer to layout header
@@ -2347,7 +2333,7 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
 				lseg, lseg->pls_range.iomode,
 				lseg->pls_range.offset,
 				lseg->pls_range.length);
-			if (mark_lseg_invalid_or_return(lseg, tmp_list))
+			if (mark_lseg_invalid(lseg, tmp_list))
 				continue;
 			remaining++;
 			set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags);
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index c0046c348910..2cbe2bc99d1b 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -31,12 +31,11 @@ EXPORT_SYMBOL_GPL(pnfs_generic_rw_release);
 /* Fake up some data that will cause nfs_commit_release to retry the writes. */
 void pnfs_generic_prepare_to_resend_writes(struct nfs_commit_data *data)
 {
-	struct nfs_page *first = nfs_list_entry(data->pages.next);
+	struct nfs_writeverf *verf = data->res.verf;
 
 	data->task.tk_status = 0;
-	memcpy(&data->verf.verifier, &first->wb_verf,
-	       sizeof(data->verf.verifier));
-	data->verf.verifier.data[0]++; /* ensure verifier mismatch */
+	memset(&verf->verifier, 0, sizeof(verf->verifier));
+	verf->committed = NFS_UNSTABLE;
 }
 EXPORT_SYMBOL_GPL(pnfs_generic_prepare_to_resend_writes);
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 52b01508b9d5..0e6afe72f6ce 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -243,13 +243,24 @@ out:
 /* A writeback failed: mark the page as bad, and invalidate the page cache */
 static void nfs_set_pageerror(struct address_space *mapping)
 {
+	struct inode *inode = mapping->host;
+
 	nfs_zap_mapping(mapping->host, mapping);
+	/* Force file size revalidation */
+	spin_lock(&inode->i_lock);
+	NFS_I(inode)->cache_validity |= NFS_INO_REVAL_FORCED |
+					NFS_INO_REVAL_PAGECACHE |
+					NFS_INO_INVALID_SIZE;
+	spin_unlock(&inode->i_lock);
 }
 
 static void nfs_mapping_set_error(struct page *page, int error)
 {
+	struct address_space *mapping = page_file_mapping(page);
+
 	SetPageError(page);
-	mapping_set_error(page_file_mapping(page), error);
+	mapping_set_error(mapping, error);
+	nfs_set_pageerror(mapping);
 }
 
 /*
@@ -433,6 +444,7 @@ nfs_destroy_unlinked_subrequests(struct nfs_page *destroy_list,
 		}
 
 		subreq->wb_head = subreq;
+		nfs_release_request(old_head);
 
 		if (test_and_clear_bit(PG_INODE_REF, &subreq->wb_flags)) {
 			nfs_release_request(subreq);
@@ -592,7 +604,6 @@ release_request:
 
 static void nfs_write_error(struct nfs_page *req, int error)
 {
-	nfs_set_pageerror(page_file_mapping(req->wb_page));
 	nfs_mapping_set_error(req->wb_page, error);
 	nfs_inode_remove_request(req);
 	nfs_end_page_writeback(req);
@@ -1001,7 +1012,6 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr)
 		nfs_list_remove_request(req);
 		if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) &&
 		    (hdr->good_bytes < bytes)) {
-			nfs_set_pageerror(page_file_mapping(req->wb_page));
 			nfs_mapping_set_error(req->wb_page, hdr->error);
 			goto remove_req;
 		}
@@ -1832,6 +1842,7 @@ static void nfs_commit_done(struct rpc_task *task, void *calldata)
 
 static void nfs_commit_release_pages(struct nfs_commit_data *data)
 {
+	const struct nfs_writeverf *verf = data->res.verf;
 	struct nfs_page	*req;
 	int status = data->task.tk_status;
 	struct nfs_commit_info cinfo;
@@ -1859,7 +1870,8 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
 
 		/* Okay, COMMIT succeeded, apparently. Check the verifier
 		 * returned by the server against all stored verfs. */
-		if (!nfs_write_verifier_cmp(&req->wb_verf, &data->verf.verifier)) {
+		if (verf->committed > NFS_UNSTABLE &&
+		    !nfs_write_verifier_cmp(&req->wb_verf, &verf->verifier)) {
 			/* We have a match */
 			if (req->wb_page)
 				nfs_inode_remove_request(req);
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index d25f6bbe7006..5f6cad45dcee 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -72,6 +72,7 @@ config NFSD_V4
 	select NFSD_V3
 	select FS_POSIX_ACL
 	select SUNRPC_GSS
+	select CRYPTO_MD5
 	select CRYPTO
 	select GRACE_PERIOD
 	help
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 397eb7820929..5703e7898369 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -1235,6 +1235,8 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
 	err = setup_callback_client(clp, &conn, ses);
 	if (err) {
 		nfsd4_mark_cb_down(clp, err);
+		if (c)
+			svc_xprt_put(c->cn_xprt);
 		return;
 	}
 }
@@ -1246,6 +1248,7 @@ nfsd4_run_cb_work(struct work_struct *work)
 		container_of(work, struct nfsd4_callback, cb_work);
 	struct nfs4_client *clp = cb->cb_clp;
 	struct rpc_clnt *clnt;
+	int flags;
 
 	if (cb->cb_need_restart) {
 		cb->cb_need_restart = false;
@@ -1274,7 +1277,8 @@ nfsd4_run_cb_work(struct work_struct *work)
 	}
 
 	cb->cb_msg.rpc_cred = clp->cl_cb_cred;
-	rpc_call_async(clnt, &cb->cb_msg, RPC_TASK_SOFT | RPC_TASK_SOFTCONN,
+	flags = clp->cl_minorversion ? RPC_TASK_NOCONNECT : RPC_TASK_SOFTCONN;
+	rpc_call_async(clnt, &cb->cb_msg, RPC_TASK_SOFT | flags,
 			cb->cb_ops ? &nfsd4_cb_ops : &nfsd4_cb_probe_ops, cb);
 }
 
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index a79e24b79095..8ff07b13f685 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -675,7 +675,7 @@ nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task)
 
 		/* Client gets 2 lease periods to return it */
 		cutoff = ktime_add_ns(task->tk_start,
-					 nn->nfsd4_lease * NSEC_PER_SEC * 2);
+					 (u64)nn->nfsd4_lease * NSEC_PER_SEC * 2);
 
 		if (ktime_before(now, cutoff)) {
 			rpc_delay(task, HZ/100); /* 10 mili-seconds */
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index c187d892e656..bff38e0ff0cf 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1303,7 +1303,8 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 out:
 	return status;
 out_err:
-	cleanup_async_copy(async_copy);
+	if (async_copy)
+		cleanup_async_copy(async_copy);
 	goto out;
 }
 
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 1a0cdeb3b875..05a76b82df08 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -253,6 +253,8 @@ find_or_allocate_block(struct nfs4_lockowner *lo, struct knfsd_fh *fh,
 	if (!nbl) {
 		nbl= kmalloc(sizeof(*nbl), GFP_KERNEL);
 		if (nbl) {
+			INIT_LIST_HEAD(&nbl->nbl_list);
+			INIT_LIST_HEAD(&nbl->nbl_lru);
 			fh_copy_shallow(&nbl->nbl_fh, fh);
 			locks_init_lock(&nbl->nbl_lock);
 			nfsd4_init_cb(&nbl->nbl_cb, lo->lo_owner.so_client,
@@ -3128,12 +3130,17 @@ static bool replay_matches_cache(struct svc_rqst *rqstp,
 	    (bool)seq->cachethis)
 		return false;
 	/*
-	 * If there's an error than the reply can have fewer ops than
-	 * the call.  But if we cached a reply with *more* ops than the
-	 * call you're sending us now, then this new call is clearly not
-	 * really a replay of the old one:
+	 * If there's an error then the reply can have fewer ops than
+	 * the call.
 	 */
-	if (slot->sl_opcnt < argp->opcnt)
+	if (slot->sl_opcnt < argp->opcnt && !slot->sl_status)
+		return false;
+	/*
+	 * But if we cached a reply with *more* ops than the call you're
+	 * sending us now, then this new call is clearly not really a
+	 * replay of the old one:
+	 */
+	if (slot->sl_opcnt > argp->opcnt)
 		return false;
 	/* This is the only check explicitly called by spec: */
 	if (!same_creds(&rqstp->rq_cred, &slot->sl_cred))
@@ -6133,7 +6140,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	}
 
 	if (fl_flags & FL_SLEEP) {
-		nbl->nbl_time = jiffies;
+		nbl->nbl_time = get_seconds();
 		spin_lock(&nn->blocked_locks_lock);
 		list_add_tail(&nbl->nbl_list, &lock_sop->lo_blocked);
 		list_add_tail(&nbl->nbl_lru, &nn->blocked_locks_lru);
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 52c4f6daa649..7a1cc8b77d42 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3535,17 +3535,17 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,
 	u32 zzz = 0;
 	int pad;
 
+	/*
+	 * svcrdma requires every READ payload to start somewhere
+	 * in xdr->pages.
+	 */
+	if (xdr->iov == xdr->buf->head) {
+		xdr->iov = NULL;
+		xdr->end = xdr->p;
+	}
+
 	len = maxcount;
 	v = 0;
-
-	thislen = min_t(long, len, ((void *)xdr->end - (void *)xdr->p));
-	p = xdr_reserve_space(xdr, (thislen+3)&~3);
-	WARN_ON_ONCE(!p);
-	resp->rqstp->rq_vec[v].iov_base = p;
-	resp->rqstp->rq_vec[v].iov_len = thislen;
-	v++;
-	len -= thislen;
-
 	while (len) {
 		thislen = min_t(long, len, PAGE_SIZE);
 		p = xdr_reserve_space(xdr, (thislen+3)&~3);
@@ -3563,6 +3563,8 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,
 	read->rd_length = maxcount;
 	if (nfserr)
 		return nfserr;
+	if (svc_encode_read_payload(resp->rqstp, starting_len + 8, maxcount))
+		return nfserr_io;
 	xdr_truncate_encode(xdr, starting_len + 8 + ((maxcount+3)&~3));
 
 	eof = nfsd_eof_on_read(len, maxcount, read->rd_offset,
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index da52b594362a..f9dbb177b236 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -476,8 +476,7 @@ found_entry:
 		rtn = RC_REPLY;
 		break;
 	default:
-		printk(KERN_WARNING "nfsd: bad repcache type %d\n", rp->c_type);
-		nfsd_reply_cache_free_locked(b, rp);
+		WARN_ONCE(1, "nfsd: bad repcache type %d\n", rp->c_type);
 	}
 
 	goto out;
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 0b74d371ed67..1bd2882d7860 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -595,7 +595,7 @@ static inline bool nfsd4_stateid_generation_after(stateid_t *a, stateid_t *b)
 struct nfsd4_blocked_lock {
 	struct list_head	nbl_list;
 	struct list_head	nbl_lru;
-	unsigned long		nbl_time;
+	time_t			nbl_time;
 	struct file_lock	nbl_lock;
 	struct knfsd_fh		nbl_fh;
 	struct nfsd4_callback	nbl_cb;
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index f922ddc358d9..c238b0d50eff 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -307,19 +307,25 @@ out:
  * Commit metadata changes to stable storage.
  */
 static int
-commit_metadata(struct svc_fh *fhp)
+commit_inode_metadata(struct inode *inode)
 {
-	struct inode *inode = d_inode(fhp->fh_dentry);
 	const struct export_operations *export_ops = inode->i_sb->s_export_op;
 
-	if (!EX_ISSYNC(fhp->fh_export))
-		return 0;
-
 	if (export_ops->commit_metadata)
 		return export_ops->commit_metadata(inode);
 	return sync_inode_metadata(inode, 1);
 }
 
+static int
+commit_metadata(struct svc_fh *fhp)
+{
+	struct inode *inode = d_inode(fhp->fh_dentry);
+
+	if (!EX_ISSYNC(fhp->fh_export))
+		return 0;
+	return commit_inode_metadata(inode);
+}
+
 /*
  * Go over the attributes and take care of the small differences between
  * NFS semantics and what Linux expects.
@@ -564,6 +570,9 @@ __be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst,
 	if (sync) {
 		loff_t dst_end = count ? dst_pos + count - 1 : LLONG_MAX;
 		int status = vfs_fsync_range(dst, dst_pos, dst_end, 0);
+
+		if (!status)
+			status = commit_inode_metadata(file_inode(src));
 		if (status < 0)
 			return nfserrno(status);
 	}
@@ -1028,6 +1037,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 	host_err = vfs_iter_write(file, &iter, &pos, flags);
 	if (host_err < 0)
 		goto out_nfserr;
+	*cnt = host_err;
 	nfsdstats.io_write += *cnt;
 	fsnotify_modify(file);
 
@@ -1217,6 +1227,9 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		iap->ia_mode = 0;
 	iap->ia_mode = (iap->ia_mode & S_IALLUGO) | type;
 
+	if (!IS_POSIXACL(dirp))
+		iap->ia_mode &= ~current_umask();
+
 	err = 0;
 	host_err = 0;
 	switch (type) {
@@ -1449,6 +1462,9 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		goto out;
 	}
 
+	if (!IS_POSIXACL(dirp))
+		iap->ia_mode &= ~current_umask();
+
 	host_err = vfs_create(dirp, dchild, iap->ia_mode, true);
 	if (host_err < 0) {
 		fh_drop_write(fhp);
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 445eef41bfaf..91b58c897f92 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -2780,6 +2780,8 @@ int nilfs_attach_log_writer(struct super_block *sb, struct nilfs_root *root)
 	if (!nilfs->ns_writer)
 		return -ENOMEM;
 
+	inode_attach_wb(nilfs->ns_bdev->bd_inode, NULL);
+
 	err = nilfs_segctor_start_thread(nilfs->ns_writer);
 	if (err) {
 		kfree(nilfs->ns_writer);
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 5778d1347b35..d24548ed31b9 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -26,7 +26,7 @@ static bool should_merge(struct fsnotify_event *old_fsn,
 	old = FANOTIFY_E(old_fsn);
 	new = FANOTIFY_E(new_fsn);
 
-	if (old_fsn->inode != new_fsn->inode || old->pid != new->pid ||
+	if (old_fsn->objectid != new_fsn->objectid || old->pid != new->pid ||
 	    old->fh_type != new->fh_type || old->fh_len != new->fh_len)
 		return false;
 
@@ -171,6 +171,17 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group,
 		if (!fsnotify_iter_should_report_type(iter_info, type))
 			continue;
 		mark = iter_info->marks[type];
+
+		/* Apply ignore mask regardless of ISDIR and ON_CHILD flags */
+		marks_ignored_mask |= mark->ignored_mask;
+
+		/*
+		 * If the event is on dir and this mark doesn't care about
+		 * events on dir, don't send it!
+		 */
+		if (event_mask & FS_ISDIR && !(mark->mask & FS_ISDIR))
+			continue;
+
 		/*
 		 * If the event is for a child and this mark doesn't care about
 		 * events on a child, don't send it!
@@ -181,7 +192,6 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group,
 			continue;
 
 		marks_mask |= mark->mask;
-		marks_ignored_mask |= mark->ignored_mask;
 	}
 
 	test_mask = event_mask & marks_mask & ~marks_ignored_mask;
@@ -203,10 +213,6 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group,
 		user_mask &= ~FAN_ONDIR;
 	}
 
-	if (event_mask & FS_ISDIR &&
-	    !(marks_mask & FS_ISDIR & ~marks_ignored_mask))
-		return 0;
-
 	return test_mask & user_mask;
 }
 
@@ -314,7 +320,12 @@ struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
 	if (!event)
 		goto out;
 init: __maybe_unused
-	fsnotify_init_event(&event->fse, inode);
+	/*
+	 * Use the victim inode instead of the watching inode as the id for
+	 * event queue, so event reported on parent is merged with event
+	 * reported on child when both directory and child watches exist.
+	 */
+	fsnotify_init_event(&event->fse, (unsigned long)id);
 	event->mask = mask;
 	if (FAN_GROUP_FLAG(group, FAN_REPORT_TID))
 		event->pid = get_pid(task_pid(current));
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 4eb2ebfac468..ae9a4d1e4c71 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -57,6 +57,9 @@ static void fsnotify_unmount_inodes(struct super_block *sb)
 		 * doing an __iget/iput with SB_ACTIVE clear would actually
 		 * evict all inodes with zero i_count from icache which is
 		 * unnecessarily violent and may in fact be illegal to do.
+		 * However, we should have been called /after/ evict_inodes
+		 * removed all zero refcount inodes, in any case.  Test to
+		 * be sure.
 		 */
 		if (!atomic_read(&inode->i_count)) {
 			spin_unlock(&inode->i_lock);
@@ -77,6 +80,7 @@ static void fsnotify_unmount_inodes(struct super_block *sb)
 
 		iput_inode = inode;
 
+		cond_resched();
 		spin_lock(&sb->s_inode_list_lock);
 	}
 	spin_unlock(&sb->s_inode_list_lock);
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index d510223d302c..589dee962993 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -39,7 +39,7 @@ static bool event_compare(struct fsnotify_event *old_fsn,
 	if (old->mask & FS_IN_IGNORED)
 		return false;
 	if ((old->mask == new->mask) &&
-	    (old_fsn->inode == new_fsn->inode) &&
+	    (old_fsn->objectid == new_fsn->objectid) &&
 	    (old->name_len == new->name_len) &&
 	    (!old->name_len || !strcmp(old->name, new->name)))
 		return true;
@@ -118,7 +118,7 @@ int inotify_handle_event(struct fsnotify_group *group,
 		mask &= ~IN_ISDIR;
 
 	fsn_event = &event->fse;
-	fsnotify_init_event(fsn_event, inode);
+	fsnotify_init_event(fsn_event, (unsigned long)inode);
 	event->mask = mask;
 	event->wd = i_mark->wd;
 	event->sync_cookie = cookie;
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index cce8de32779f..3f8af1631fbf 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -628,7 +628,7 @@ static struct fsnotify_group *inotify_new_group(unsigned int max_events)
 		return ERR_PTR(-ENOMEM);
 	}
 	group->overflow_event = &oevent->fse;
-	fsnotify_init_event(group->overflow_event, NULL);
+	fsnotify_init_event(group->overflow_event, 0);
 	oevent->mask = FS_Q_OVERFLOW;
 	oevent->wd = -1;
 	oevent->sync_cookie = 0;
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index d1348fc4ca6d..6984ec05d8d5 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -7385,6 +7385,10 @@ int ocfs2_truncate_inline(struct inode *inode, struct buffer_head *di_bh,
 	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
 	struct ocfs2_inline_data *idata = &di->id2.i_data;
 
+	/* No need to punch hole beyond i_size. */
+	if (start >= i_size_read(inode))
+		return 0;
+
 	if (end > i_size_read(inode))
 		end = i_size_read(inode);
 
diff --git a/fs/ocfs2/dlm/Makefile b/fs/ocfs2/dlm/Makefile
index 38b224372776..5e700b45d32d 100644
--- a/fs/ocfs2/dlm/Makefile
+++ b/fs/ocfs2/dlm/Makefile
@@ -1,6 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-ccflags-y := -I $(srctree)/$(src)/..
-
 obj-$(CONFIG_OCFS2_FS_O2CB) += ocfs2_dlm.o
 
 ocfs2_dlm-objs := dlmdomain.o dlmdebug.o dlmthread.o dlmrecovery.o \
diff --git a/fs/ocfs2/dlm/dlmast.c b/fs/ocfs2/dlm/dlmast.c
index 4de89af96abf..6abaded3ff6b 100644
--- a/fs/ocfs2/dlm/dlmast.c
+++ b/fs/ocfs2/dlm/dlmast.c
@@ -23,15 +23,15 @@
 #include <linux/spinlock.h>
 
 
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
 
 #include "dlmapi.h"
 #include "dlmcommon.h"
 
 #define MLOG_MASK_PREFIX ML_DLM
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
 
 static void dlm_update_lvb(struct dlm_ctxt *dlm, struct dlm_lock_resource *res,
 			   struct dlm_lock *lock);
diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c
index 965f45dbe17b..6051edc33aef 100644
--- a/fs/ocfs2/dlm/dlmconvert.c
+++ b/fs/ocfs2/dlm/dlmconvert.c
@@ -23,9 +23,9 @@
 #include <linux/spinlock.h>
 
 
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
 
 #include "dlmapi.h"
 #include "dlmcommon.h"
@@ -33,7 +33,7 @@
 #include "dlmconvert.h"
 
 #define MLOG_MASK_PREFIX ML_DLM
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
 
 /* NOTE: __dlmconvert_master is the only function in here that
  * needs a spinlock held on entry (res->spinlock) and it is the
diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index c8af5bc9e980..c13b4856ab87 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -17,9 +17,9 @@
 #include <linux/debugfs.h>
 #include <linux/export.h>
 
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
 
 #include "dlmapi.h"
 #include "dlmcommon.h"
@@ -27,7 +27,7 @@
 #include "dlmdebug.h"
 
 #define MLOG_MASK_PREFIX ML_DLM
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
 
 static int stringify_lockname(const char *lockname, int locklen, char *buf,
 			      int len);
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 9021e72e1f98..8d08e6cb94f7 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -20,9 +20,9 @@
 #include <linux/debugfs.h>
 #include <linux/sched/signal.h>
 
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
 
 #include "dlmapi.h"
 #include "dlmcommon.h"
@@ -30,7 +30,7 @@
 #include "dlmdebug.h"
 
 #define MLOG_MASK_PREFIX (ML_DLM|ML_DLM_DOMAIN)
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
 
 /*
  * ocfs2 node maps are array of long int, which limits to send them freely
diff --git a/fs/ocfs2/dlm/dlmlock.c b/fs/ocfs2/dlm/dlmlock.c
index baff087f3863..83f0760e4fba 100644
--- a/fs/ocfs2/dlm/dlmlock.c
+++ b/fs/ocfs2/dlm/dlmlock.c
@@ -25,9 +25,9 @@
 #include <linux/delay.h>
 
 
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
 
 #include "dlmapi.h"
 #include "dlmcommon.h"
@@ -35,7 +35,7 @@
 #include "dlmconvert.h"
 
 #define MLOG_MASK_PREFIX ML_DLM
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
 
 static struct kmem_cache *dlm_lock_cache;
 
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 810f841494ef..f3b7c1f3ccbf 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -25,9 +25,9 @@
 #include <linux/delay.h>
 
 
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
 
 #include "dlmapi.h"
 #include "dlmcommon.h"
@@ -35,7 +35,7 @@
 #include "dlmdebug.h"
 
 #define MLOG_MASK_PREFIX (ML_DLM|ML_DLM_MASTER)
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
 
 static void dlm_mle_node_down(struct dlm_ctxt *dlm,
 			      struct dlm_master_list_entry *mle,
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index e22d6a115220..fb80d0cef78f 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -26,16 +26,16 @@
 #include <linux/delay.h>
 
 
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
 
 #include "dlmapi.h"
 #include "dlmcommon.h"
 #include "dlmdomain.h"
 
 #define MLOG_MASK_PREFIX (ML_DLM|ML_DLM_RECOVERY)
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
 
 static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node);
 
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index 61c51c268460..fd40c17cd022 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -25,16 +25,16 @@
 #include <linux/delay.h>
 
 
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
 
 #include "dlmapi.h"
 #include "dlmcommon.h"
 #include "dlmdomain.h"
 
 #define MLOG_MASK_PREFIX (ML_DLM|ML_DLM_THREAD)
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
 
 static int dlm_thread(void *data);
 static void dlm_flush_asts(struct dlm_ctxt *dlm);
diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c
index 3883633e82eb..dcb17ca8ae74 100644
--- a/fs/ocfs2/dlm/dlmunlock.c
+++ b/fs/ocfs2/dlm/dlmunlock.c
@@ -23,15 +23,15 @@
 #include <linux/spinlock.h>
 #include <linux/delay.h>
 
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
 
 #include "dlmapi.h"
 #include "dlmcommon.h"
 
 #define MLOG_MASK_PREFIX ML_DLM
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
 
 #define DLM_UNLOCK_FREE_LOCK           0x00000001
 #define DLM_UNLOCK_CALL_AST            0x00000002
diff --git a/fs/ocfs2/dlmfs/Makefile b/fs/ocfs2/dlmfs/Makefile
index a9874e441bd4..c7895f65be0e 100644
--- a/fs/ocfs2/dlmfs/Makefile
+++ b/fs/ocfs2/dlmfs/Makefile
@@ -1,6 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-ccflags-y := -I $(srctree)/$(src)/..
-
 obj-$(CONFIG_OCFS2_FS) += ocfs2_dlmfs.o
 
 ocfs2_dlmfs-objs := userdlm.o dlmfs.o
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index 4f1668c81e1f..1de77f1a600b 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -33,11 +33,11 @@
 
 #include <linux/uaccess.h>
 
-#include "stackglue.h"
+#include "../stackglue.h"
 #include "userdlm.h"
 
 #define MLOG_MASK_PREFIX ML_DLMFS
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
 
 
 static const struct super_operations dlmfs_ops;
@@ -275,7 +275,6 @@ static ssize_t dlmfs_file_write(struct file *filp,
 				loff_t *ppos)
 {
 	int bytes_left;
-	ssize_t writelen;
 	char *lvb_buf;
 	struct inode *inode = file_inode(filp);
 
@@ -285,32 +284,30 @@ static ssize_t dlmfs_file_write(struct file *filp,
 	if (*ppos >= i_size_read(inode))
 		return -ENOSPC;
 
+	/* don't write past the lvb */
+	if (count > i_size_read(inode) - *ppos)
+		count = i_size_read(inode) - *ppos;
+
 	if (!count)
 		return 0;
 
 	if (!access_ok(buf, count))
 		return -EFAULT;
 
-	/* don't write past the lvb */
-	if ((count + *ppos) > i_size_read(inode))
-		writelen = i_size_read(inode) - *ppos;
-	else
-		writelen = count - *ppos;
-
-	lvb_buf = kmalloc(writelen, GFP_NOFS);
+	lvb_buf = kmalloc(count, GFP_NOFS);
 	if (!lvb_buf)
 		return -ENOMEM;
 
-	bytes_left = copy_from_user(lvb_buf, buf, writelen);
-	writelen -= bytes_left;
-	if (writelen)
-		user_dlm_write_lvb(inode, lvb_buf, writelen);
+	bytes_left = copy_from_user(lvb_buf, buf, count);
+	count -= bytes_left;
+	if (count)
+		user_dlm_write_lvb(inode, lvb_buf, count);
 
 	kfree(lvb_buf);
 
-	*ppos = *ppos + writelen;
-	mlog(0, "wrote %zd bytes\n", writelen);
-	return writelen;
+	*ppos = *ppos + count;
+	mlog(0, "wrote %zu bytes\n", count);
+	return count;
 }
 
 static void dlmfs_init_once(void *foo)
diff --git a/fs/ocfs2/dlmfs/userdlm.c b/fs/ocfs2/dlmfs/userdlm.c
index 525b14ddfba5..3df5be25bfb1 100644
--- a/fs/ocfs2/dlmfs/userdlm.c
+++ b/fs/ocfs2/dlmfs/userdlm.c
@@ -21,12 +21,12 @@
 #include <linux/types.h>
 #include <linux/crc32.h>
 
-#include "ocfs2_lockingver.h"
-#include "stackglue.h"
+#include "../ocfs2_lockingver.h"
+#include "../stackglue.h"
 #include "userdlm.h"
 
 #define MLOG_MASK_PREFIX ML_DLMFS
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
 
 
 static inline struct user_lock_res *user_lksb_to_lock_res(struct ocfs2_dlm_lksb *lksb)
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index b5fc5d3c7525..b5934e995a69 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -668,6 +668,12 @@ static void ocfs2_nfs_sync_lock_res_init(struct ocfs2_lock_res *res,
 				   &ocfs2_nfs_sync_lops, osb);
 }
 
+static void ocfs2_nfs_sync_lock_init(struct ocfs2_super *osb)
+{
+	ocfs2_nfs_sync_lock_res_init(&osb->osb_nfs_sync_lockres, osb);
+	init_rwsem(&osb->nfs_sync_rwlock);
+}
+
 void ocfs2_trim_fs_lock_res_init(struct ocfs2_super *osb)
 {
 	struct ocfs2_lock_res *lockres = &osb->osb_trim_fs_lockres;
@@ -2834,14 +2840,25 @@ int ocfs2_nfs_sync_lock(struct ocfs2_super *osb, int ex)
 	if (ocfs2_is_hard_readonly(osb))
 		return -EROFS;
 
+	if (ex)
+		down_write(&osb->nfs_sync_rwlock);
+	else
+		down_read(&osb->nfs_sync_rwlock);
+
 	if (ocfs2_mount_local(osb))
 		return 0;
 
 	status = ocfs2_cluster_lock(osb, lockres, ex ? LKM_EXMODE : LKM_PRMODE,
 				    0, 0);
-	if (status < 0)
+	if (status < 0) {
 		mlog(ML_ERROR, "lock on nfs sync lock failed %d\n", status);
 
+		if (ex)
+			up_write(&osb->nfs_sync_rwlock);
+		else
+			up_read(&osb->nfs_sync_rwlock);
+	}
+
 	return status;
 }
 
@@ -2852,6 +2869,10 @@ void ocfs2_nfs_sync_unlock(struct ocfs2_super *osb, int ex)
 	if (!ocfs2_mount_local(osb))
 		ocfs2_cluster_unlock(osb, lockres,
 				     ex ? LKM_EXMODE : LKM_PRMODE);
+	if (ex)
+		up_write(&osb->nfs_sync_rwlock);
+	else
+		up_read(&osb->nfs_sync_rwlock);
 }
 
 int ocfs2_trim_fs_lock(struct ocfs2_super *osb,
@@ -3297,7 +3318,7 @@ int ocfs2_dlm_init(struct ocfs2_super *osb)
 local:
 	ocfs2_super_lock_res_init(&osb->osb_super_lockres, osb);
 	ocfs2_rename_lock_res_init(&osb->osb_rename_lockres, osb);
-	ocfs2_nfs_sync_lock_res_init(&osb->osb_nfs_sync_lockres, osb);
+	ocfs2_nfs_sync_lock_init(osb);
 	ocfs2_orphan_scan_lock_res_init(&osb->osb_orphan_scan.os_lockres, osb);
 
 	osb->cconn = conn;
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index f6d790b7f2e2..20c254807613 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2095,17 +2095,15 @@ static int ocfs2_is_io_unaligned(struct inode *inode, size_t count, loff_t pos)
 static int ocfs2_inode_lock_for_extent_tree(struct inode *inode,
 					    struct buffer_head **di_bh,
 					    int meta_level,
-					    int overwrite_io,
 					    int write_sem,
 					    int wait)
 {
 	int ret = 0;
 
 	if (wait)
-		ret = ocfs2_inode_lock(inode, NULL, meta_level);
+		ret = ocfs2_inode_lock(inode, di_bh, meta_level);
 	else
-		ret = ocfs2_try_inode_lock(inode,
-			overwrite_io ? NULL : di_bh, meta_level);
+		ret = ocfs2_try_inode_lock(inode, di_bh, meta_level);
 	if (ret < 0)
 		goto out;
 
@@ -2130,6 +2128,7 @@ static int ocfs2_inode_lock_for_extent_tree(struct inode *inode,
 
 out_unlock:
 	brelse(*di_bh);
+	*di_bh = NULL;
 	ocfs2_inode_unlock(inode, meta_level);
 out:
 	return ret;
@@ -2172,7 +2171,6 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 		ret = ocfs2_inode_lock_for_extent_tree(inode,
 						       &di_bh,
 						       meta_level,
-						       overwrite_io,
 						       write_sem,
 						       wait);
 		if (ret < 0) {
@@ -2230,13 +2228,13 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 							   &di_bh,
 							   meta_level,
 							   write_sem);
+			meta_level = 1;
+			write_sem = 1;
 			ret = ocfs2_inode_lock_for_extent_tree(inode,
 							       &di_bh,
 							       meta_level,
-							       overwrite_io,
-							       1,
+							       write_sem,
 							       wait);
-			write_sem = 1;
 			if (ret < 0) {
 				if (ret != -EAGAIN)
 					mlog_errno(ret);
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 699a560efbb0..900e4ef686bf 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -1066,6 +1066,14 @@ int ocfs2_journal_load(struct ocfs2_journal *journal, int local, int replayed)
 
 	ocfs2_clear_journal_error(osb->sb, journal->j_journal, osb->slot_num);
 
+	if (replayed) {
+		jbd2_journal_lock_updates(journal->j_journal);
+		status = jbd2_journal_flush(journal->j_journal);
+		jbd2_journal_unlock_updates(journal->j_journal);
+		if (status < 0)
+			mlog_errno(status);
+	}
+
 	status = ocfs2_journal_toggle_dirty(osb, 1, replayed);
 	if (status < 0) {
 		mlog_errno(status);
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index c0fe6ed08ab1..12359e2db942 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -623,9 +623,11 @@ static inline void ocfs2_update_inode_fsync_trans(handle_t *handle,
 {
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
 
-	oi->i_sync_tid = handle->h_transaction->t_tid;
-	if (datasync)
-		oi->i_datasync_tid = handle->h_transaction->t_tid;
+	if (!is_handle_aborted(handle)) {
+		oi->i_sync_tid = handle->h_transaction->t_tid;
+		if (datasync)
+			oi->i_datasync_tid = handle->h_transaction->t_tid;
+	}
 }
 
 #endif /* OCFS2_JOURNAL_H */
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index a4647a646f07..b07eb2a30be5 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -324,8 +324,8 @@ struct ocfs2_super
 	spinlock_t osb_lock;
 	u32 s_next_generation;
 	unsigned long osb_flags;
-	s16 s_inode_steal_slot;
-	s16 s_meta_steal_slot;
+	u16 s_inode_steal_slot;
+	u16 s_meta_steal_slot;
 	atomic_t s_num_inodes_stolen;
 	atomic_t s_num_meta_stolen;
 
@@ -392,6 +392,7 @@ struct ocfs2_super
 	struct ocfs2_lock_res osb_super_lockres;
 	struct ocfs2_lock_res osb_rename_lockres;
 	struct ocfs2_lock_res osb_nfs_sync_lockres;
+	struct rw_semaphore nfs_sync_rwlock;
 	struct ocfs2_lock_res osb_trim_fs_lockres;
 	struct mutex obs_trim_fs_mutex;
 	struct ocfs2_dlm_debug *osb_dlm_debug;
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index 0db4a7ec58a2..dcef83c8796d 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -290,7 +290,7 @@
 #define OCFS2_MAX_SLOTS			255
 
 /* Slot map indicator for an empty slot */
-#define OCFS2_INVALID_SLOT		-1
+#define OCFS2_INVALID_SLOT		((u16)-1)
 
 #define OCFS2_VOL_UUID_LEN		16
 #define OCFS2_MAX_VOL_LABEL_LEN		64
@@ -326,8 +326,8 @@ struct ocfs2_system_inode_info {
 enum {
 	BAD_BLOCK_SYSTEM_INODE = 0,
 	GLOBAL_INODE_ALLOC_SYSTEM_INODE,
+#define OCFS2_FIRST_ONLINE_SYSTEM_INODE GLOBAL_INODE_ALLOC_SYSTEM_INODE
 	SLOT_MAP_SYSTEM_INODE,
-#define OCFS2_FIRST_ONLINE_SYSTEM_INODE SLOT_MAP_SYSTEM_INODE
 	HEARTBEAT_SYSTEM_INODE,
 	GLOBAL_BITMAP_SYSTEM_INODE,
 	USER_QUOTA_SYSTEM_INODE,
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 69c21a3843af..5e0eaea47405 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -879,9 +879,9 @@ static void __ocfs2_set_steal_slot(struct ocfs2_super *osb, int slot, int type)
 {
 	spin_lock(&osb->osb_lock);
 	if (type == INODE_ALLOC_SYSTEM_INODE)
-		osb->s_inode_steal_slot = slot;
+		osb->s_inode_steal_slot = (u16)slot;
 	else if (type == EXTENT_ALLOC_SYSTEM_INODE)
-		osb->s_meta_steal_slot = slot;
+		osb->s_meta_steal_slot = (u16)slot;
 	spin_unlock(&osb->osb_lock);
 }
 
@@ -2827,9 +2827,12 @@ int ocfs2_test_inode_bit(struct ocfs2_super *osb, u64 blkno, int *res)
 		goto bail;
 	}
 
-	inode_alloc_inode =
-		ocfs2_get_system_file_inode(osb, INODE_ALLOC_SYSTEM_INODE,
-					    suballoc_slot);
+	if (suballoc_slot == (u16)OCFS2_INVALID_SLOT)
+		inode_alloc_inode = ocfs2_get_system_file_inode(osb,
+			GLOBAL_INODE_ALLOC_SYSTEM_INODE, suballoc_slot);
+	else
+		inode_alloc_inode = ocfs2_get_system_file_inode(osb,
+			INODE_ALLOC_SYSTEM_INODE, suballoc_slot);
 	if (!inode_alloc_inode) {
 		/* the error code could be inaccurate, but we are not able to
 		 * get the correct one. */
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index a201f9780b35..e9cb264c5aae 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -78,7 +78,7 @@ struct mount_options
 	unsigned long	commit_interval;
 	unsigned long	mount_opt;
 	unsigned int	atime_quantum;
-	signed short	slot;
+	unsigned short	slot;
 	int		localalloc_opt;
 	unsigned int	resv_level;
 	int		dir_resv_level;
@@ -1354,7 +1354,7 @@ static int ocfs2_parse_options(struct super_block *sb,
 				goto bail;
 			}
 			if (option)
-				mopt->slot = (s16)option;
+				mopt->slot = (u16)option;
 			break;
 		case Opt_commit:
 			if (match_int(&args[0], &option)) {
diff --git a/fs/open.c b/fs/open.c
index 78809163ba03..2941aa2c233e 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -853,9 +853,6 @@ cleanup_file:
  * the return value of d_splice_alias(), then the caller needs to perform dput()
  * on it after finish_open().
  *
- * On successful return @file is a fully instantiated open file.  After this, if
- * an error occurs in ->atomic_open(), it needs to clean up with fput().
- *
  * Returns zero on success or -errno if the open failed.
  */
 int finish_open(struct file *file, struct dentry *dentry,
diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c
index a35c17017210..59ec1cb0e158 100644
--- a/fs/orangefs/file.c
+++ b/fs/orangefs/file.c
@@ -313,23 +313,8 @@ static ssize_t orangefs_file_read_iter(struct kiocb *iocb,
     struct iov_iter *iter)
 {
 	int ret;
-	struct orangefs_read_options *ro;
-
 	orangefs_stats.reads++;
 
-	/*
-	 * Remember how they set "count" in read(2) or pread(2) or whatever -
-	 * users can use count as a knob to control orangefs io size and later
-	 * we can try to help them fill as many pages as possible in readpage.
-	 */
-	if (!iocb->ki_filp->private_data) {
-		iocb->ki_filp->private_data = kmalloc(sizeof *ro, GFP_KERNEL);
-		if (!iocb->ki_filp->private_data)
-			return(ENOMEM);
-		ro = iocb->ki_filp->private_data;
-		ro->blksiz = iter->count;
-	}
-
 	down_read(&file_inode(iocb->ki_filp)->i_rwsem);
 	ret = orangefs_revalidate_mapping(file_inode(iocb->ki_filp));
 	if (ret)
@@ -598,12 +583,6 @@ static int orangefs_lock(struct file *filp, int cmd, struct file_lock *fl)
 	return rc;
 }
 
-static int orangefs_file_open(struct inode * inode, struct file *file)
-{
-	file->private_data = NULL;
-	return generic_file_open(inode, file);
-}
-
 static int orangefs_flush(struct file *file, fl_owner_t id)
 {
 	/*
@@ -617,9 +596,6 @@ static int orangefs_flush(struct file *file, fl_owner_t id)
 	struct inode *inode = file->f_mapping->host;
 	int r;
 
-	kfree(file->private_data);
-	file->private_data = NULL;
-
 	if (inode->i_state & I_DIRTY_TIME) {
 		spin_lock(&inode->i_lock);
 		inode->i_state &= ~I_DIRTY_TIME;
@@ -642,7 +618,7 @@ const struct file_operations orangefs_file_operations = {
 	.lock		= orangefs_lock,
 	.unlocked_ioctl	= orangefs_ioctl,
 	.mmap		= orangefs_file_mmap,
-	.open		= orangefs_file_open,
+	.open		= generic_file_open,
 	.flush		= orangefs_flush,
 	.release	= orangefs_file_release,
 	.fsync		= orangefs_fsync,
diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c
index 0c337d8bdaab..c9b3e5ec8221 100644
--- a/fs/orangefs/inode.c
+++ b/fs/orangefs/inode.c
@@ -259,46 +259,19 @@ static int orangefs_readpage(struct file *file, struct page *page)
 	pgoff_t index; /* which page */
 	struct page *next_page;
 	char *kaddr;
-	struct orangefs_read_options *ro = file->private_data;
 	loff_t read_size;
-	loff_t roundedup;
 	int buffer_index = -1; /* orangefs shared memory slot */
 	int slot_index;   /* index into slot */
 	int remaining;
 
 	/*
-	 * If they set some miniscule size for "count" in read(2)
-	 * (for example) then let's try to read a page, or the whole file
-	 * if it is smaller than a page. Once "count" goes over a page
-	 * then lets round up to the highest page size multiple that is
-	 * less than or equal to "count" and do that much orangefs IO and
-	 * try to fill as many pages as we can from it.
-	 *
-	 * "count" should be represented in ro->blksiz.
-	 *
-	 * inode->i_size = file size.
+	 * Get up to this many bytes from Orangefs at a time and try
+	 * to fill them into the page cache at once. Tests with dd made
+	 * this seem like a reasonable static number, if there was
+	 * interest perhaps this number could be made setable through
+	 * sysfs...
 	 */
-	if (ro) {
-		if (ro->blksiz < PAGE_SIZE) {
-			if (inode->i_size < PAGE_SIZE)
-				read_size = inode->i_size;
-			else
-				read_size = PAGE_SIZE;
-		} else {
-			roundedup = ((PAGE_SIZE - 1) & ro->blksiz) ?
-				((ro->blksiz + PAGE_SIZE) & ~(PAGE_SIZE -1)) :
-				ro->blksiz;
-			if (roundedup > inode->i_size)
-				read_size = inode->i_size;
-			else
-				read_size = roundedup;
-
-		}
-	} else {
-		read_size = PAGE_SIZE;
-	}
-	if (!read_size)
-		read_size = PAGE_SIZE;
+	read_size = 524288;
 
 	if (PageDirty(page))
 		orangefs_launder_page(page);
diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c
index 87b1a6fce628..610e1dc112ea 100644
--- a/fs/orangefs/orangefs-debugfs.c
+++ b/fs/orangefs/orangefs-debugfs.c
@@ -305,6 +305,7 @@ static void *help_start(struct seq_file *m, loff_t *pos)
 
 static void *help_next(struct seq_file *m, void *v, loff_t *pos)
 {
+	(*pos)++;
 	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "help_next: start\n");
 
 	return NULL;
diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h
index 572dd29fbd54..884cdf134f3e 100644
--- a/fs/orangefs/orangefs-kernel.h
+++ b/fs/orangefs/orangefs-kernel.h
@@ -239,10 +239,6 @@ struct orangefs_write_range {
 	kgid_t gid;
 };
 
-struct orangefs_read_options {
-	ssize_t blksiz;
-};
-
 extern struct orangefs_stats orangefs_stats;
 
 /*
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index b801c6353100..ec5eca5a96f4 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -40,7 +40,7 @@ int ovl_copy_xattr(struct dentry *old, struct dentry *new)
 {
 	ssize_t list_size, size, value_size = 0;
 	char *buf, *name, *value = NULL;
-	int uninitialized_var(error);
+	int error = 0;
 	size_t slen;
 
 	if (!(old->d_inode->i_opflags & IOP_XATTR) ||
diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c
index 73c9775215b3..11dd8177770d 100644
--- a/fs/overlayfs/export.c
+++ b/fs/overlayfs/export.c
@@ -482,7 +482,7 @@ static struct dentry *ovl_lookup_real_inode(struct super_block *sb,
 	if (IS_ERR_OR_NULL(this))
 		return this;
 
-	if (WARN_ON(ovl_dentry_real_at(this, layer->idx) != real)) {
+	if (ovl_dentry_real_at(this, layer->idx) != real) {
 		dput(this);
 		this = ERR_PTR(-EIO);
 	}
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index e235a635d9ec..7a08a576f7b2 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -21,13 +21,16 @@ static char ovl_whatisit(struct inode *inode, struct inode *realinode)
 		return 'm';
 }
 
+/* No atime modificaton nor notify on underlying */
+#define OVL_OPEN_FLAGS (O_NOATIME | FMODE_NONOTIFY)
+
 static struct file *ovl_open_realfile(const struct file *file,
 				      struct inode *realinode)
 {
 	struct inode *inode = file_inode(file);
 	struct file *realfile;
 	const struct cred *old_cred;
-	int flags = file->f_flags | O_NOATIME | FMODE_NONOTIFY;
+	int flags = file->f_flags | OVL_OPEN_FLAGS;
 
 	old_cred = ovl_override_creds(inode->i_sb);
 	realfile = open_with_fake_path(&file->f_path, flags, realinode,
@@ -48,8 +51,7 @@ static int ovl_change_flags(struct file *file, unsigned int flags)
 	struct inode *inode = file_inode(file);
 	int err;
 
-	/* No atime modificaton on underlying */
-	flags |= O_NOATIME | FMODE_NONOTIFY;
+	flags |= OVL_OPEN_FLAGS;
 
 	/* If some flag changed that cannot be changed then something's amiss */
 	if (WARN_ON((file->f_flags ^ flags) & ~OVL_SETFL_MASK))
@@ -102,7 +104,7 @@ static int ovl_real_fdget_meta(const struct file *file, struct fd *real,
 	}
 
 	/* Did the flags change since open? */
-	if (unlikely((file->f_flags ^ real->file->f_flags) & ~O_NOATIME))
+	if (unlikely((file->f_flags ^ real->file->f_flags) & ~OVL_OPEN_FLAGS))
 		return ovl_change_flags(real->file, file->f_flags);
 
 	return 0;
@@ -146,7 +148,7 @@ static loff_t ovl_llseek(struct file *file, loff_t offset, int whence)
 	struct inode *inode = file_inode(file);
 	struct fd real;
 	const struct cred *old_cred;
-	ssize_t ret;
+	loff_t ret;
 
 	/*
 	 * The two special cases below do not need to involve real fs,
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index b045cf1826fc..bb980721502d 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -881,7 +881,7 @@ struct inode *ovl_get_inode(struct super_block *sb,
 	struct dentry *lowerdentry = lowerpath ? lowerpath->dentry : NULL;
 	bool bylower = ovl_hash_bylower(sb, upperdentry, lowerdentry,
 					oip->index);
-	int fsid = bylower ? oip->lowerpath->layer->fsid : 0;
+	int fsid = bylower ? lowerpath->layer->fsid : 0;
 	bool is_dir, metacopy = false;
 	unsigned long ino = 0;
 	int err = oip->newinode ? -EEXIST : -ENOMEM;
@@ -931,6 +931,8 @@ struct inode *ovl_get_inode(struct super_block *sb,
 			err = -ENOMEM;
 			goto out_err;
 		}
+		ino = realinode->i_ino;
+		fsid = lowerpath->layer->fsid;
 	}
 	ovl_fill_inode(inode, realinode->i_mode, realinode->i_rdev, ino, fsid);
 	ovl_inode_init(inode, upperdentry, lowerdentry, oip->lowerdata);
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 47a91c9733a5..7255e6a5838f 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -504,7 +504,13 @@ get:
 		if (err)
 			goto fail;
 
-		WARN_ON_ONCE(dir->d_sb->s_dev != stat.dev);
+		/*
+		 * Directory inode is always on overlay st_dev.
+		 * Non-dir with ovl_same_dev() could be on pseudo st_dev in case
+		 * of xino bits overflow.
+		 */
+		WARN_ON_ONCE(S_ISDIR(stat.mode) &&
+			     dir->d_sb->s_dev != stat.dev);
 		ino = stat.ino;
 	} else if (xinobits && !OVL_TYPE_UPPER(type)) {
 		ino = ovl_remap_lower_ino(ino, xinobits,
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 7621ff176d15..d6b724beb304 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -1258,6 +1258,18 @@ static bool ovl_lower_uuid_ok(struct ovl_fs *ofs, const uuid_t *uuid)
 	if (!ofs->config.nfs_export && !ofs->upper_mnt)
 		return true;
 
+	/*
+	 * We allow using single lower with null uuid for index and nfs_export
+	 * for example to support those features with single lower squashfs.
+	 * To avoid regressions in setups of overlay with re-formatted lower
+	 * squashfs, do not allow decoding origin with lower null uuid unless
+	 * user opted-in to one of the new features that require following the
+	 * lower inode of non-dir upper.
+	 */
+	if (!ofs->config.index && !ofs->config.metacopy && !ofs->config.xino &&
+	    uuid_is_null(uuid))
+		return false;
+
 	for (i = 0; i < ofs->numlowerfs; i++) {
 		/*
 		 * We use uuid to associate an overlay lower file handle with a
@@ -1344,14 +1356,23 @@ static int ovl_get_lower_layers(struct super_block *sb, struct ovl_fs *ofs,
 		if (err < 0)
 			goto out;
 
+		/*
+		 * Check if lower root conflicts with this overlay layers before
+		 * checking if it is in-use as upperdir/workdir of "another"
+		 * mount, because we do not bother to check in ovl_is_inuse() if
+		 * the upperdir/workdir is in fact in-use by our
+		 * upperdir/workdir.
+		 */
 		err = ovl_setup_trap(sb, stack[i].dentry, &trap, "lowerdir");
 		if (err)
 			goto out;
 
 		if (ovl_is_inuse(stack[i].dentry)) {
 			err = ovl_report_in_use(ofs, "lowerdir");
-			if (err)
+			if (err) {
+				iput(trap);
 				goto out;
+			}
 		}
 
 		mnt = clone_private_mount(&stack[i]);
diff --git a/fs/pnode.c b/fs/pnode.c
index 49f6d7ff2139..1106137c747a 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -261,14 +261,13 @@ static int propagate_one(struct mount *m)
 	child = copy_tree(last_source, last_source->mnt.mnt_root, type);
 	if (IS_ERR(child))
 		return PTR_ERR(child);
+	read_seqlock_excl(&mount_lock);
 	mnt_set_mountpoint(m, mp, child);
+	if (m->mnt_master != dest_master)
+		SET_MNT_MARK(m->mnt_master);
+	read_sequnlock_excl(&mount_lock);
 	last_dest = m;
 	last_source = child;
-	if (m->mnt_master != dest_master) {
-		read_seqlock_excl(&mount_lock);
-		SET_MNT_MARK(m->mnt_master);
-		read_sequnlock_excl(&mount_lock);
-	}
 	hlist_add_head(&child->mnt_hash, list);
 	return count_mounts(m->mnt_ns, child);
 }
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 5f8d215b3fd0..df6a5c0656df 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -441,7 +441,7 @@ const struct inode_operations proc_link_inode_operations = {
 
 struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
 {
-	struct inode *inode = new_inode_pseudo(sb);
+	struct inode *inode = new_inode(sb);
 
 	if (inode) {
 		inode->i_ino = de->low_ino;
diff --git a/fs/proc/self.c b/fs/proc/self.c
index 57c0a1047250..32af065397f8 100644
--- a/fs/proc/self.c
+++ b/fs/proc/self.c
@@ -43,7 +43,7 @@ int proc_setup_self(struct super_block *s)
 	inode_lock(root_inode);
 	self = d_alloc_name(s->s_root, "self");
 	if (self) {
-		struct inode *inode = new_inode_pseudo(s);
+		struct inode *inode = new_inode(s);
 		if (inode) {
 			inode->i_ino = self_inum;
 			inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c
index f61ae53533f5..fac9e50b33a6 100644
--- a/fs/proc/thread_self.c
+++ b/fs/proc/thread_self.c
@@ -43,7 +43,7 @@ int proc_setup_thread_self(struct super_block *s)
 	inode_lock(root_inode);
 	thread_self = d_alloc_name(s->s_root, "thread-self");
 	if (thread_self) {
-		struct inode *inode = new_inode_pseudo(s);
+		struct inode *inode = new_inode(s);
 		if (inode) {
 			inode->i_ino = thread_self_inum;
 			inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 7bb96fdd38ad..53e95afab2be 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -262,7 +262,8 @@ static int vmcoredd_mmap_dumps(struct vm_area_struct *vma, unsigned long dst,
 		if (start < offset + dump->size) {
 			tsz = min(offset + (u64)dump->size - start, (u64)size);
 			buf = dump->buf + start - offset;
-			if (remap_vmalloc_range_partial(vma, dst, buf, tsz)) {
+			if (remap_vmalloc_range_partial(vma, dst, buf, 0,
+							tsz)) {
 				ret = -EFAULT;
 				goto out_unlock;
 			}
@@ -620,7 +621,7 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
 		tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)start, size);
 		kaddr = elfnotes_buf + start - elfcorebuf_sz - vmcoredd_orig_sz;
 		if (remap_vmalloc_range_partial(vma, vma->vm_start + len,
-						kaddr, tsz))
+						kaddr, 0, tsz))
 			goto fail;
 
 		size -= tsz;
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index 7fbe8f058220..d99b5d39aa90 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -87,11 +87,11 @@ static void *pstore_ftrace_seq_next(struct seq_file *s, void *v, loff_t *pos)
 	struct pstore_private *ps = s->private;
 	struct pstore_ftrace_seq_data *data = v;
 
+	(*pos)++;
 	data->off += REC_SIZE;
 	if (data->off + REC_SIZE > ps->total_size)
 		return NULL;
 
-	(*pos)++;
 	return data;
 }
 
@@ -101,6 +101,9 @@ static int pstore_ftrace_seq_show(struct seq_file *s, void *v)
 	struct pstore_ftrace_seq_data *data = v;
 	struct pstore_ftrace_record *rec;
 
+	if (!data)
+		return 0;
+
 	rec = (struct pstore_ftrace_record *)(ps->record->buf + data->off);
 
 	seq_printf(s, "CPU:%d ts:%llu %08lx  %08lx  %ps <- %pS\n",
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index 3d7024662d29..74a60bae2b23 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -275,6 +275,9 @@ static int pstore_compress(const void *in, void *out,
 {
 	int ret;
 
+	if (!IS_ENABLED(CONFIG_PSTORE_COMPRESSION))
+		return -EINVAL;
+
 	ret = crypto_comp_compress(tfm, in, inlen, out, &outlen);
 	if (ret) {
 		pr_err("crypto_comp_compress failed, ret = %d!\n", ret);
@@ -661,7 +664,7 @@ static void decompress_record(struct pstore_record *record)
 	int unzipped_len;
 	char *unzipped, *workspace;
 
-	if (!record->compressed)
+	if (!IS_ENABLED(CONFIG_PSTORE_COMPRESSION) || !record->compressed)
 		return;
 
 	/* Only PSTORE_TYPE_DMESG support compression. */
@@ -823,9 +826,9 @@ static int __init pstore_init(void)
 
 	ret = pstore_init_fs();
 	if (ret)
-		return ret;
+		free_buf_for_compression();
 
-	return 0;
+	return ret;
 }
 late_initcall(pstore_init);
 
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index db9f67d34af3..2c549b5dd4aa 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -407,6 +407,17 @@ static int notrace ramoops_pstore_write(struct pstore_record *record)
 
 	prz = cxt->dprzs[cxt->dump_write_cnt];
 
+	/*
+	 * Since this is a new crash dump, we need to reset the buffer in
+	 * case it still has an old dump present. Without this, the new dump
+	 * will get appended, which would seriously confuse anything trying
+	 * to check dump file contents. Specifically, ramoops_read_kmsg_hdr()
+	 * expects to find a dump header in the beginning of buffer data, so
+	 * we must to reset the buffer values, in order to ensure that the
+	 * header will be written to the beginning of the buffer.
+	 */
+	persistent_ram_zap(prz);
+
 	/* Build header and append record contents. */
 	hlen = ramoops_write_kmsg_hdr(prz, record);
 	if (!hlen)
@@ -572,6 +583,7 @@ static int ramoops_init_przs(const char *name,
 		prz_ar[i] = persistent_ram_new(*paddr, zone_sz, sig,
 					       &cxt->ecc_info,
 					       cxt->memtype, flags, label);
+		kfree(label);
 		if (IS_ERR(prz_ar[i])) {
 			err = PTR_ERR(prz_ar[i]);
 			dev_err(dev, "failed to request %s mem region (0x%zx@0x%llx): %d\n",
@@ -617,6 +629,7 @@ static int ramoops_init_prz(const char *name,
 	label = kasprintf(GFP_KERNEL, "ramoops:%s", name);
 	*prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info,
 				  cxt->memtype, PRZ_FLAG_ZAP_OLD, label);
+	kfree(label);
 	if (IS_ERR(*prz)) {
 		int err = PTR_ERR(*prz);
 
diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c
index 8823f65888f0..1f4d8c06f9be 100644
--- a/fs/pstore/ram_core.c
+++ b/fs/pstore/ram_core.c
@@ -574,7 +574,7 @@ struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
 	/* Initialize general buffer state. */
 	raw_spin_lock_init(&prz->buffer_lock);
 	prz->flags = flags;
-	prz->label = label;
+	prz->label = kstrdup(label, GFP_KERNEL);
 
 	ret = persistent_ram_buffer_map(start, size, prz, memtype);
 	if (ret)
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 5eecc319246a..d7e54bc499f1 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -981,6 +981,7 @@ static int add_dquot_ref(struct super_block *sb, int type)
 		 * later.
 		 */
 		old_inode = inode;
+		cond_resched();
 		spin_lock(&sb->s_inode_list_lock);
 	}
 	spin_unlock(&sb->s_inode_list_lock);
diff --git a/fs/read_write.c b/fs/read_write.c
index 165befc4fd82..95b3f902fd19 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1768,10 +1768,9 @@ static int remap_verify_area(struct file *file, loff_t pos, loff_t len,
  * else.  Assume that the offsets have already been checked for block
  * alignment.
  *
- * For deduplication we always scale down to the previous block because we
- * can't meaningfully compare post-EOF contents.
- *
- * For clone we only link a partial EOF block above the destination file's EOF.
+ * For clone we only link a partial EOF block above or at the destination file's
+ * EOF.  For deduplication we accept a partial EOF block only if it ends at the
+ * destination file's EOF (can not link it into the middle of a file).
  *
  * Shorten the request if possible.
  */
@@ -1787,8 +1786,7 @@ static int generic_remap_check_len(struct inode *inode_in,
 	if ((*len & blkmask) == 0)
 		return 0;
 
-	if ((remap_flags & REMAP_FILE_DEDUP) ||
-	    pos_out + *len < i_size_read(inode_out))
+	if (pos_out + *len < i_size_read(inode_out))
 		new_len &= ~blkmask;
 
 	if (new_len == *len)
diff --git a/fs/readdir.c b/fs/readdir.c
index d26d5ea4de7b..de2eceffdee8 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -102,10 +102,14 @@ EXPORT_SYMBOL(iterate_dir);
  * filename length, and the above "soft error" worry means
  * that it's probably better left alone until we have that
  * issue clarified.
+ *
+ * Note the PATH_MAX check - it's arbitrary but the real
+ * kernel limit on a possible path component, not NAME_MAX,
+ * which is the technical standard limit.
  */
 static int verify_dirent_name(const char *name, int len)
 {
-	if (!len)
+	if (len <= 0 || len >= PATH_MAX)
 		return -EIO;
 	if (memchr(name, '/', len))
 		return -EIO;
@@ -206,7 +210,7 @@ struct linux_dirent {
 struct getdents_callback {
 	struct dir_context ctx;
 	struct linux_dirent __user * current_dir;
-	struct linux_dirent __user * previous;
+	int prev_reclen;
 	int count;
 	int error;
 };
@@ -214,12 +218,13 @@ struct getdents_callback {
 static int filldir(struct dir_context *ctx, const char *name, int namlen,
 		   loff_t offset, u64 ino, unsigned int d_type)
 {
-	struct linux_dirent __user * dirent;
+	struct linux_dirent __user *dirent, *prev;
 	struct getdents_callback *buf =
 		container_of(ctx, struct getdents_callback, ctx);
 	unsigned long d_ino;
 	int reclen = ALIGN(offsetof(struct linux_dirent, d_name) + namlen + 2,
 		sizeof(long));
+	int prev_reclen;
 
 	buf->error = verify_dirent_name(name, namlen);
 	if (unlikely(buf->error))
@@ -232,28 +237,24 @@ static int filldir(struct dir_context *ctx, const char *name, int namlen,
 		buf->error = -EOVERFLOW;
 		return -EOVERFLOW;
 	}
-	dirent = buf->previous;
-	if (dirent && signal_pending(current))
+	prev_reclen = buf->prev_reclen;
+	if (prev_reclen && signal_pending(current))
 		return -EINTR;
-
-	/*
-	 * Note! This range-checks 'previous' (which may be NULL).
-	 * The real range was checked in getdents
-	 */
-	if (!user_access_begin(dirent, sizeof(*dirent)))
-		goto efault;
-	if (dirent)
-		unsafe_put_user(offset, &dirent->d_off, efault_end);
 	dirent = buf->current_dir;
+	prev = (void __user *) dirent - prev_reclen;
+	if (!user_access_begin(prev, reclen + prev_reclen))
+		goto efault;
+
+	/* This might be 'dirent->d_off', but if so it will get overwritten */
+	unsafe_put_user(offset, &prev->d_off, efault_end);
 	unsafe_put_user(d_ino, &dirent->d_ino, efault_end);
 	unsafe_put_user(reclen, &dirent->d_reclen, efault_end);
 	unsafe_put_user(d_type, (char __user *) dirent + reclen - 1, efault_end);
 	unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end);
 	user_access_end();
 
-	buf->previous = dirent;
-	dirent = (void __user *)dirent + reclen;
-	buf->current_dir = dirent;
+	buf->current_dir = (void __user *)dirent + reclen;
+	buf->prev_reclen = reclen;
 	buf->count -= reclen;
 	return 0;
 efault_end:
@@ -267,7 +268,6 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd,
 		struct linux_dirent __user *, dirent, unsigned int, count)
 {
 	struct fd f;
-	struct linux_dirent __user * lastdirent;
 	struct getdents_callback buf = {
 		.ctx.actor = filldir,
 		.count = count,
@@ -285,8 +285,10 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd,
 	error = iterate_dir(f.file, &buf.ctx);
 	if (error >= 0)
 		error = buf.error;
-	lastdirent = buf.previous;
-	if (lastdirent) {
+	if (buf.prev_reclen) {
+		struct linux_dirent __user * lastdirent;
+		lastdirent = (void __user *)buf.current_dir - buf.prev_reclen;
+
 		if (put_user(buf.ctx.pos, &lastdirent->d_off))
 			error = -EFAULT;
 		else
@@ -299,7 +301,7 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd,
 struct getdents_callback64 {
 	struct dir_context ctx;
 	struct linux_dirent64 __user * current_dir;
-	struct linux_dirent64 __user * previous;
+	int prev_reclen;
 	int count;
 	int error;
 };
@@ -307,11 +309,12 @@ struct getdents_callback64 {
 static int filldir64(struct dir_context *ctx, const char *name, int namlen,
 		     loff_t offset, u64 ino, unsigned int d_type)
 {
-	struct linux_dirent64 __user *dirent;
+	struct linux_dirent64 __user *dirent, *prev;
 	struct getdents_callback64 *buf =
 		container_of(ctx, struct getdents_callback64, ctx);
 	int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1,
 		sizeof(u64));
+	int prev_reclen;
 
 	buf->error = verify_dirent_name(name, namlen);
 	if (unlikely(buf->error))
@@ -319,30 +322,27 @@ static int filldir64(struct dir_context *ctx, const char *name, int namlen,
 	buf->error = -EINVAL;	/* only used if we fail.. */
 	if (reclen > buf->count)
 		return -EINVAL;
-	dirent = buf->previous;
-	if (dirent && signal_pending(current))
+	prev_reclen = buf->prev_reclen;
+	if (prev_reclen && signal_pending(current))
 		return -EINTR;
-
-	/*
-	 * Note! This range-checks 'previous' (which may be NULL).
-	 * The real range was checked in getdents
-	 */
-	if (!user_access_begin(dirent, sizeof(*dirent)))
-		goto efault;
-	if (dirent)
-		unsafe_put_user(offset, &dirent->d_off, efault_end);
 	dirent = buf->current_dir;
+	prev = (void __user *)dirent - prev_reclen;
+	if (!user_access_begin(prev, reclen + prev_reclen))
+		goto efault;
+
+	/* This might be 'dirent->d_off', but if so it will get overwritten */
+	unsafe_put_user(offset, &prev->d_off, efault_end);
 	unsafe_put_user(ino, &dirent->d_ino, efault_end);
 	unsafe_put_user(reclen, &dirent->d_reclen, efault_end);
 	unsafe_put_user(d_type, &dirent->d_type, efault_end);
 	unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end);
 	user_access_end();
 
-	buf->previous = dirent;
-	dirent = (void __user *)dirent + reclen;
-	buf->current_dir = dirent;
+	buf->prev_reclen = reclen;
+	buf->current_dir = (void __user *)dirent + reclen;
 	buf->count -= reclen;
 	return 0;
+
 efault_end:
 	user_access_end();
 efault:
@@ -354,7 +354,6 @@ int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent,
 		    unsigned int count)
 {
 	struct fd f;
-	struct linux_dirent64 __user * lastdirent;
 	struct getdents_callback64 buf = {
 		.ctx.actor = filldir64,
 		.count = count,
@@ -372,9 +371,11 @@ int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent,
 	error = iterate_dir(f.file, &buf.ctx);
 	if (error >= 0)
 		error = buf.error;
-	lastdirent = buf.previous;
-	if (lastdirent) {
+	if (buf.prev_reclen) {
+		struct linux_dirent64 __user * lastdirent;
 		typeof(lastdirent->d_off) d_off = buf.ctx.pos;
+
+		lastdirent = (void __user *) buf.current_dir - buf.prev_reclen;
 		if (__put_user(d_off, &lastdirent->d_off))
 			error = -EFAULT;
 		else
diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c
index 0037aea97d39..2946713cb00d 100644
--- a/fs/reiserfs/stree.c
+++ b/fs/reiserfs/stree.c
@@ -2250,7 +2250,8 @@ error_out:
 	/* also releases the path */
 	unfix_nodes(&s_ins_balance);
 #ifdef REISERQUOTA_DEBUG
-	reiserfs_debug(th->t_super, REISERFS_DEBUG_CODE,
+	if (inode)
+		reiserfs_debug(th->t_super, REISERFS_DEBUG_CODE,
 		       "reiserquota insert_item(): freeing %u id=%u type=%c",
 		       quota_bytes, inode->i_uid, head2type(ih));
 #endif
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index c00a34b801b4..7a796b5b6643 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -629,6 +629,7 @@ static void reiserfs_put_super(struct super_block *s)
 	reiserfs_write_unlock(s);
 	mutex_destroy(&REISERFS_SB(s)->lock);
 	destroy_workqueue(REISERFS_SB(s)->commit_wq);
+	kfree(REISERFS_SB(s)->s_jdev);
 	kfree(s->s_fs_info);
 	s->s_fs_info = NULL;
 }
@@ -1947,7 +1948,7 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
 		if (!sbi->s_jdev) {
 			SWARN(silent, s, "", "Cannot allocate memory for "
 				"journal device name");
-			goto error;
+			goto error_unlocked;
 		}
 	}
 #ifdef CONFIG_QUOTA
@@ -2237,6 +2238,7 @@ error_unlocked:
 			kfree(qf_names[j]);
 	}
 #endif
+	kfree(sbi->s_jdev);
 	kfree(sbi);
 
 	s->s_fs_info = NULL;
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index 62b40df36c98..28b241cd6987 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -319,8 +319,12 @@ static int reiserfs_for_each_xattr(struct inode *inode,
 out_dir:
 	dput(dir);
 out:
-	/* -ENODATA isn't an error */
-	if (err == -ENODATA)
+	/*
+	 * -ENODATA: this object doesn't have any xattrs
+	 * -EOPNOTSUPP: this file system doesn't have xattrs enabled on disk.
+	 * Neither are errors
+	 */
+	if (err == -ENODATA || err == -EOPNOTSUPP)
 		err = 0;
 	return err;
 }
diff --git a/fs/super.c b/fs/super.c
index 2739f57515f8..691b202aa5c2 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -444,10 +444,12 @@ void generic_shutdown_super(struct super_block *sb)
 		sync_filesystem(sb);
 		sb->s_flags &= ~SB_ACTIVE;
 
-		fsnotify_sb_delete(sb);
 		cgroup_writeback_umount();
 
+		/* evict all inodes with zero refcount */
 		evict_inodes(sb);
+		/* only nonzero refcount inodes can have marks */
+		fsnotify_sb_delete(sb);
 
 		if (sb->s_dio_done_wq) {
 			destroy_workqueue(sb->s_dio_done_wq);
diff --git a/fs/ubifs/auth.c b/fs/ubifs/auth.c
index 60f43b93d06e..046fafbe1d38 100644
--- a/fs/ubifs/auth.c
+++ b/fs/ubifs/auth.c
@@ -77,13 +77,9 @@ int ubifs_prepare_auth_node(struct ubifs_info *c, void *node,
 			     struct shash_desc *inhash)
 {
 	struct ubifs_auth_node *auth = node;
-	u8 *hash;
+	u8 hash[UBIFS_HASH_ARR_SZ];
 	int err;
 
-	hash = kmalloc(crypto_shash_descsize(c->hash_tfm), GFP_NOFS);
-	if (!hash)
-		return -ENOMEM;
-
 	{
 		SHASH_DESC_ON_STACK(hash_desc, c->hash_tfm);
 
@@ -92,21 +88,16 @@ int ubifs_prepare_auth_node(struct ubifs_info *c, void *node,
 
 		err = crypto_shash_final(hash_desc, hash);
 		if (err)
-			goto out;
+			return err;
 	}
 
 	err = ubifs_hash_calc_hmac(c, hash, auth->hmac);
 	if (err)
-		goto out;
+		return err;
 
 	auth->ch.node_type = UBIFS_AUTH_NODE;
 	ubifs_prepare_node(c, auth, ubifs_auth_node_sz(c), 0);
-
-	err = 0;
-out:
-	kfree(hash);
-
-	return err;
+	return 0;
 }
 
 static struct shash_desc *ubifs_get_desc(const struct ubifs_info *c,
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index 0b98e3c8b461..6c0e19f7a21f 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -228,6 +228,8 @@ static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry,
 	if (nm.hash) {
 		ubifs_assert(c, fname_len(&nm) == 0);
 		ubifs_assert(c, fname_name(&nm) == NULL);
+		if (nm.hash & ~UBIFS_S_KEY_HASH_MASK)
+			goto done; /* ENOENT */
 		dent_key_init_hash(c, &key, dir->i_ino, nm.hash);
 		err = ubifs_tnc_lookup_dh(c, &key, dent, nm.minor_hash);
 	} else {
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index e5f8de62fc51..31ed4e957cc4 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -786,7 +786,9 @@ static int ubifs_do_bulk_read(struct ubifs_info *c, struct bu_info *bu,
 
 		if (page_offset > end_index)
 			break;
-		page = find_or_create_page(mapping, page_offset, ra_gfp_mask);
+		page = pagecache_get_page(mapping, page_offset,
+				 FGP_LOCK|FGP_ACCESSED|FGP_CREAT|FGP_NOWAIT,
+				 ra_gfp_mask);
 		if (!page)
 			break;
 		if (!PageUptodate(page))
@@ -1376,7 +1378,6 @@ int ubifs_update_time(struct inode *inode, struct timespec64 *time,
 	struct ubifs_info *c = inode->i_sb->s_fs_info;
 	struct ubifs_budget_req req = { .dirtied_ino = 1,
 			.dirtied_ino_d = ALIGN(ui->data_len, 8) };
-	int iflags = I_DIRTY_TIME;
 	int err, release;
 
 	if (!IS_ENABLED(CONFIG_UBIFS_ATIME_SUPPORT))
@@ -1394,11 +1395,8 @@ int ubifs_update_time(struct inode *inode, struct timespec64 *time,
 	if (flags & S_MTIME)
 		inode->i_mtime = *time;
 
-	if (!(inode->i_sb->s_flags & SB_LAZYTIME))
-		iflags |= I_DIRTY_SYNC;
-
 	release = ui->dirty;
-	__mark_inode_dirty(inode, iflags);
+	__mark_inode_dirty(inode, I_DIRTY_SYNC);
 	mutex_unlock(&ui->ui_mutex);
 	if (release)
 		ubifs_release_budget(c, &req);
diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c
index 4f1a397fda69..de65ba8a6ab4 100644
--- a/fs/ubifs/ioctl.c
+++ b/fs/ubifs/ioctl.c
@@ -120,7 +120,8 @@ static int setflags(struct inode *inode, int flags)
 		}
 	}
 
-	ui->flags = ioctl2ubifs(flags);
+	ui->flags &= ~ioctl2ubifs(UBIFS_SUPPORTED_IOCTL_FLAGS);
+	ui->flags |= ioctl2ubifs(flags);
 	ubifs_set_inode_flags(inode);
 	inode->i_ctime = current_time(inode);
 	release = ui->dirty;
diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c
index 4fd9683b8245..a6ae2428e4c9 100644
--- a/fs/ubifs/journal.c
+++ b/fs/ubifs/journal.c
@@ -539,7 +539,7 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir,
 		     const struct fscrypt_name *nm, const struct inode *inode,
 		     int deletion, int xent)
 {
-	int err, dlen, ilen, len, lnum, ino_offs, dent_offs;
+	int err, dlen, ilen, len, lnum, ino_offs, dent_offs, orphan_added = 0;
 	int aligned_dlen, aligned_ilen, sync = IS_DIRSYNC(dir);
 	int last_reference = !!(deletion && inode->i_nlink == 0);
 	struct ubifs_inode *ui = ubifs_inode(inode);
@@ -630,6 +630,7 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir,
 			goto out_finish;
 		}
 		ui->del_cmtno = c->cmt_no;
+		orphan_added = 1;
 	}
 
 	err = write_head(c, BASEHD, dent, len, &lnum, &dent_offs, sync);
@@ -702,7 +703,7 @@ out_release:
 	kfree(dent);
 out_ro:
 	ubifs_ro_mode(c, err);
-	if (last_reference)
+	if (orphan_added)
 		ubifs_delete_orphan(c, inode->i_ino);
 	finish_reservation(c);
 	return err;
@@ -899,7 +900,7 @@ int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode)
 			fname_name(&nm) = xent->name;
 			fname_len(&nm) = le16_to_cpu(xent->nlen);
 
-			xino = ubifs_iget(c->vfs_sb, xent->inum);
+			xino = ubifs_iget(c->vfs_sb, le64_to_cpu(xent->inum));
 			if (IS_ERR(xino)) {
 				err = PTR_ERR(xino);
 				ubifs_err(c, "dead directory entry '%s', error %d",
@@ -1217,7 +1218,7 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
 	void *p;
 	union ubifs_key key;
 	struct ubifs_dent_node *dent, *dent2;
-	int err, dlen1, dlen2, ilen, lnum, offs, len;
+	int err, dlen1, dlen2, ilen, lnum, offs, len, orphan_added = 0;
 	int aligned_dlen1, aligned_dlen2, plen = UBIFS_INO_NODE_SZ;
 	int last_reference = !!(new_inode && new_inode->i_nlink == 0);
 	int move = (old_dir != new_dir);
@@ -1333,6 +1334,7 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
 			goto out_finish;
 		}
 		new_ui->del_cmtno = c->cmt_no;
+		orphan_added = 1;
 	}
 
 	err = write_head(c, BASEHD, dent, len, &lnum, &offs, sync);
@@ -1414,7 +1416,7 @@ out_release:
 	release_head(c, BASEHD);
 out_ro:
 	ubifs_ro_mode(c, err);
-	if (last_reference)
+	if (orphan_added)
 		ubifs_delete_orphan(c, new_inode->i_ino);
 out_finish:
 	finish_reservation(c);
diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c
index cb72688032cd..868e64226439 100644
--- a/fs/ubifs/orphan.c
+++ b/fs/ubifs/orphan.c
@@ -126,25 +126,10 @@ static void __orphan_drop(struct ubifs_info *c, struct ubifs_orphan *o)
 	kfree(o);
 }
 
-static void orphan_delete(struct ubifs_info *c, ino_t inum)
+static void orphan_delete(struct ubifs_info *c, struct ubifs_orphan *orph)
 {
-	struct ubifs_orphan *orph, *child_orph, *tmp_o;
-
-	spin_lock(&c->orphan_lock);
-
-	orph = lookup_orphan(c, inum);
-	if (!orph) {
-		spin_unlock(&c->orphan_lock);
-		ubifs_err(c, "missing orphan ino %lu", (unsigned long)inum);
-		dump_stack();
-
-		return;
-	}
-
 	if (orph->del) {
-		spin_unlock(&c->orphan_lock);
-		dbg_gen("deleted twice ino %lu",
-			(unsigned long)inum);
+		dbg_gen("deleted twice ino %lu", (unsigned long)orph->inum);
 		return;
 	}
 
@@ -152,20 +137,11 @@ static void orphan_delete(struct ubifs_info *c, ino_t inum)
 		orph->del = 1;
 		orph->dnext = c->orph_dnext;
 		c->orph_dnext = orph;
-		spin_unlock(&c->orphan_lock);
-		dbg_gen("delete later ino %lu",
-			(unsigned long)inum);
+		dbg_gen("delete later ino %lu", (unsigned long)orph->inum);
 		return;
 	}
 
-	list_for_each_entry_safe(child_orph, tmp_o, &orph->child_list, child_list) {
-		list_del(&child_orph->child_list);
-		__orphan_drop(c, child_orph);
-	}
-
 	__orphan_drop(c, orph);
-
-	spin_unlock(&c->orphan_lock);
 }
 
 /**
@@ -223,7 +199,27 @@ int ubifs_add_orphan(struct ubifs_info *c, ino_t inum)
  */
 void ubifs_delete_orphan(struct ubifs_info *c, ino_t inum)
 {
-	orphan_delete(c, inum);
+	struct ubifs_orphan *orph, *child_orph, *tmp_o;
+
+	spin_lock(&c->orphan_lock);
+
+	orph = lookup_orphan(c, inum);
+	if (!orph) {
+		spin_unlock(&c->orphan_lock);
+		ubifs_err(c, "missing orphan ino %lu", (unsigned long)inum);
+		dump_stack();
+
+		return;
+	}
+
+	list_for_each_entry_safe(child_orph, tmp_o, &orph->child_list, child_list) {
+		list_del(&child_orph->child_list);
+		orphan_delete(c, child_orph);
+	}
+
+	orphan_delete(c, orph);
+
+	spin_unlock(&c->orphan_lock);
 }
 
 /**
diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c
index b28ac4dfb407..01fcf7975047 100644
--- a/fs/ubifs/replay.c
+++ b/fs/ubifs/replay.c
@@ -601,18 +601,12 @@ static int authenticate_sleb(struct ubifs_info *c, struct ubifs_scan_leb *sleb,
 	struct ubifs_scan_node *snod;
 	int n_nodes = 0;
 	int err;
-	u8 *hash, *hmac;
+	u8 hash[UBIFS_HASH_ARR_SZ];
+	u8 hmac[UBIFS_HMAC_ARR_SZ];
 
 	if (!ubifs_authenticated(c))
 		return sleb->nodes_cnt;
 
-	hash = kmalloc(crypto_shash_descsize(c->hash_tfm), GFP_NOFS);
-	hmac = kmalloc(c->hmac_desc_len, GFP_NOFS);
-	if (!hash || !hmac) {
-		err = -ENOMEM;
-		goto out;
-	}
-
 	list_for_each_entry(snod, &sleb->nodes, list) {
 
 		n_nodes++;
@@ -662,9 +656,6 @@ static int authenticate_sleb(struct ubifs_info *c, struct ubifs_scan_leb *sleb,
 		err = 0;
 	}
 out:
-	kfree(hash);
-	kfree(hmac);
-
 	return err ? err : n_nodes - n_not_auth;
 }
 
diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c
index 12c2afdb5804..87a4775e5076 100644
--- a/fs/ubifs/sb.c
+++ b/fs/ubifs/sb.c
@@ -161,7 +161,7 @@ static int create_default_filesystem(struct ubifs_info *c)
 	sup = kzalloc(ALIGN(UBIFS_SB_NODE_SZ, c->min_io_size), GFP_KERNEL);
 	mst = kzalloc(c->mst_node_alsz, GFP_KERNEL);
 	idx_node_size = ubifs_idx_node_sz(c, 1);
-	idx = kzalloc(ALIGN(tmp, c->min_io_size), GFP_KERNEL);
+	idx = kzalloc(ALIGN(idx_node_size, c->min_io_size), GFP_KERNEL);
 	ino = kzalloc(ALIGN(UBIFS_INO_NODE_SZ, c->min_io_size), GFP_KERNEL);
 	cs = kzalloc(ALIGN(UBIFS_CS_NODE_SZ, c->min_io_size), GFP_KERNEL);
 
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 6cfc494050be..4ccb448d29a6 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -1564,6 +1564,7 @@ out_free:
 	vfree(c->ileb_buf);
 	vfree(c->sbuf);
 	kfree(c->bottom_up_buf);
+	kfree(c->sup_node);
 	ubifs_debugging_exit(c);
 	return err;
 }
@@ -1606,6 +1607,7 @@ static void ubifs_umount(struct ubifs_info *c)
 	vfree(c->ileb_buf);
 	vfree(c->sbuf);
 	kfree(c->bottom_up_buf);
+	kfree(c->sup_node);
 	ubifs_debugging_exit(c);
 }
 
diff --git a/fs/ubifs/tnc_commit.c b/fs/ubifs/tnc_commit.c
index a384a0f9ff32..234be1c4dc87 100644
--- a/fs/ubifs/tnc_commit.c
+++ b/fs/ubifs/tnc_commit.c
@@ -212,7 +212,7 @@ static int is_idx_node_in_use(struct ubifs_info *c, union ubifs_key *key,
 /**
  * layout_leb_in_gaps - layout index nodes using in-the-gaps method.
  * @c: UBIFS file-system description object
- * @p: return LEB number here
+ * @p: return LEB number in @c->gap_lebs[p]
  *
  * This function lays out new index nodes for dirty znodes using in-the-gaps
  * method of TNC commit.
@@ -221,7 +221,7 @@ static int is_idx_node_in_use(struct ubifs_info *c, union ubifs_key *key,
  * This function returns the number of index nodes written into the gaps, or a
  * negative error code on failure.
  */
-static int layout_leb_in_gaps(struct ubifs_info *c, int *p)
+static int layout_leb_in_gaps(struct ubifs_info *c, int p)
 {
 	struct ubifs_scan_leb *sleb;
 	struct ubifs_scan_node *snod;
@@ -236,7 +236,7 @@ static int layout_leb_in_gaps(struct ubifs_info *c, int *p)
 		 * filled, however we do not check there at present.
 		 */
 		return lnum; /* Error code */
-	*p = lnum;
+	c->gap_lebs[p] = lnum;
 	dbg_gc("LEB %d", lnum);
 	/*
 	 * Scan the index LEB.  We use the generic scan for this even though
@@ -355,7 +355,7 @@ static int get_leb_cnt(struct ubifs_info *c, int cnt)
  */
 static int layout_in_gaps(struct ubifs_info *c, int cnt)
 {
-	int err, leb_needed_cnt, written, *p;
+	int err, leb_needed_cnt, written, p = 0, old_idx_lebs, *gap_lebs;
 
 	dbg_gc("%d znodes to write", cnt);
 
@@ -364,9 +364,9 @@ static int layout_in_gaps(struct ubifs_info *c, int cnt)
 	if (!c->gap_lebs)
 		return -ENOMEM;
 
-	p = c->gap_lebs;
+	old_idx_lebs = c->lst.idx_lebs;
 	do {
-		ubifs_assert(c, p < c->gap_lebs + c->lst.idx_lebs);
+		ubifs_assert(c, p < c->lst.idx_lebs);
 		written = layout_leb_in_gaps(c, p);
 		if (written < 0) {
 			err = written;
@@ -392,9 +392,29 @@ static int layout_in_gaps(struct ubifs_info *c, int cnt)
 		leb_needed_cnt = get_leb_cnt(c, cnt);
 		dbg_gc("%d znodes remaining, need %d LEBs, have %d", cnt,
 		       leb_needed_cnt, c->ileb_cnt);
+		/*
+		 * Dynamically change the size of @c->gap_lebs to prevent
+		 * oob, because @c->lst.idx_lebs could be increased by
+		 * function @get_idx_gc_leb (called by layout_leb_in_gaps->
+		 * ubifs_find_dirty_idx_leb) during loop. Only enlarge
+		 * @c->gap_lebs when needed.
+		 *
+		 */
+		if (leb_needed_cnt > c->ileb_cnt && p >= old_idx_lebs &&
+		    old_idx_lebs < c->lst.idx_lebs) {
+			old_idx_lebs = c->lst.idx_lebs;
+			gap_lebs = krealloc(c->gap_lebs, sizeof(int) *
+					       (old_idx_lebs + 1), GFP_NOFS);
+			if (!gap_lebs) {
+				kfree(c->gap_lebs);
+				c->gap_lebs = NULL;
+				return -ENOMEM;
+			}
+			c->gap_lebs = gap_lebs;
+		}
 	} while (leb_needed_cnt > c->ileb_cnt);
 
-	*p = -1;
+	c->gap_lebs[p] = -1;
 	return 0;
 }
 
diff --git a/fs/udf/super.c b/fs/udf/super.c
index a14346137361..d17bdacdda60 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -994,7 +994,6 @@ static int check_partition_desc(struct super_block *sb,
 	switch (le32_to_cpu(p->accessType)) {
 	case PD_ACCESS_TYPE_READ_ONLY:
 	case PD_ACCESS_TYPE_WRITE_ONCE:
-	case PD_ACCESS_TYPE_REWRITABLE:
 	case PD_ACCESS_TYPE_NONE:
 		goto force_ro;
 	}
@@ -2449,17 +2448,29 @@ static unsigned int udf_count_free_table(struct super_block *sb,
 static unsigned int udf_count_free(struct super_block *sb)
 {
 	unsigned int accum = 0;
-	struct udf_sb_info *sbi;
+	struct udf_sb_info *sbi = UDF_SB(sb);
 	struct udf_part_map *map;
+	unsigned int part = sbi->s_partition;
+	int ptype = sbi->s_partmaps[part].s_partition_type;
+
+	if (ptype == UDF_METADATA_MAP25) {
+		part = sbi->s_partmaps[part].s_type_specific.s_metadata.
+							s_phys_partition_ref;
+	} else if (ptype == UDF_VIRTUAL_MAP15 || ptype == UDF_VIRTUAL_MAP20) {
+		/*
+		 * Filesystems with VAT are append-only and we cannot write to
+		 * them. Let's just report 0 here.
+		 */
+		return 0;
+	}
 
-	sbi = UDF_SB(sb);
 	if (sbi->s_lvid_bh) {
 		struct logicalVolIntegrityDesc *lvid =
 			(struct logicalVolIntegrityDesc *)
 			sbi->s_lvid_bh->b_data;
-		if (le32_to_cpu(lvid->numOfPartitions) > sbi->s_partition) {
+		if (le32_to_cpu(lvid->numOfPartitions) > part) {
 			accum = le32_to_cpu(
-					lvid->freeSpaceTable[sbi->s_partition]);
+					lvid->freeSpaceTable[part]);
 			if (accum == 0xFFFFFFFF)
 				accum = 0;
 		}
@@ -2468,7 +2479,7 @@ static unsigned int udf_count_free(struct super_block *sb)
 	if (accum)
 		return accum;
 
-	map = &sbi->s_partmaps[sbi->s_partition];
+	map = &sbi->s_partmaps[part];
 	if (map->s_partition_flags & UDF_PART_FLAG_UNALLOC_BITMAP) {
 		accum += udf_count_free_bitmap(sb,
 					       map->s_uspace.s_bitmap);
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index 3d247c0d92aa..15677eebef4c 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -101,7 +101,7 @@ static struct inode *ufs_nfs_get_inode(struct super_block *sb, u64 ino, u32 gene
 	struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi;
 	struct inode *inode;
 
-	if (ino < UFS_ROOTINO || ino > uspi->s_ncg * uspi->s_ipg)
+	if (ino < UFS_ROOTINO || ino > (u64)uspi->s_ncg * uspi->s_ipg)
 		return ERR_PTR(-ESTALE);
 
 	inode = ufs_iget(sb, ino);
diff --git a/fs/unicode/utf8-core.c b/fs/unicode/utf8-core.c
index 6afab4fdce90..71ca4d047d65 100644
--- a/fs/unicode/utf8-core.c
+++ b/fs/unicode/utf8-core.c
@@ -73,6 +73,34 @@ int utf8_strncasecmp(const struct unicode_map *um,
 }
 EXPORT_SYMBOL(utf8_strncasecmp);
 
+/* String cf is expected to be a valid UTF-8 casefolded
+ * string.
+ */
+int utf8_strncasecmp_folded(const struct unicode_map *um,
+			    const struct qstr *cf,
+			    const struct qstr *s1)
+{
+	const struct utf8data *data = utf8nfdicf(um->version);
+	struct utf8cursor cur1;
+	int c1, c2;
+	int i = 0;
+
+	if (utf8ncursor(&cur1, data, s1->name, s1->len) < 0)
+		return -EINVAL;
+
+	do {
+		c1 = utf8byte(&cur1);
+		c2 = cf->name[i++];
+		if (c1 < 0)
+			return -EINVAL;
+		if (c1 != c2)
+			return 1;
+	} while (c1);
+
+	return 0;
+}
+EXPORT_SYMBOL(utf8_strncasecmp_folded);
+
 int utf8_casefold(const struct unicode_map *um, const struct qstr *str,
 		  unsigned char *dest, size_t dlen)
 {
diff --git a/fs/xattr.c b/fs/xattr.c
index 40b01dd1b14a..494313bce9cc 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -204,10 +204,22 @@ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name,
 	return error;
 }
 
-
+/**
+ * __vfs_setxattr_locked: set an extended attribute while holding the inode
+ * lock
+ *
+ *  @dentry - object to perform setxattr on
+ *  @name - xattr name to set
+ *  @value - value to set @name to
+ *  @size - size of @value
+ *  @flags - flags to pass into filesystem operations
+ *  @delegated_inode - on return, will contain an inode pointer that
+ *  a delegation was broken on, NULL if none.
+ */
 int
-vfs_setxattr(struct dentry *dentry, const char *name, const void *value,
-		size_t size, int flags)
+__vfs_setxattr_locked(struct dentry *dentry, const char *name,
+		const void *value, size_t size, int flags,
+		struct inode **delegated_inode)
 {
 	struct inode *inode = dentry->d_inode;
 	int error;
@@ -216,15 +228,40 @@ vfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 	if (error)
 		return error;
 
-	inode_lock(inode);
 	error = security_inode_setxattr(dentry, name, value, size, flags);
 	if (error)
 		goto out;
 
+	error = try_break_deleg(inode, delegated_inode);
+	if (error)
+		goto out;
+
 	error = __vfs_setxattr_noperm(dentry, name, value, size, flags);
 
 out:
+	return error;
+}
+EXPORT_SYMBOL_GPL(__vfs_setxattr_locked);
+
+int
+vfs_setxattr(struct dentry *dentry, const char *name, const void *value,
+		size_t size, int flags)
+{
+	struct inode *inode = dentry->d_inode;
+	struct inode *delegated_inode = NULL;
+	int error;
+
+retry_deleg:
+	inode_lock(inode);
+	error = __vfs_setxattr_locked(dentry, name, value, size, flags,
+	    &delegated_inode);
 	inode_unlock(inode);
+
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry_deleg;
+	}
 	return error;
 }
 EXPORT_SYMBOL_GPL(vfs_setxattr);
@@ -379,8 +416,18 @@ __vfs_removexattr(struct dentry *dentry, const char *name)
 }
 EXPORT_SYMBOL(__vfs_removexattr);
 
+/**
+ * __vfs_removexattr_locked: set an extended attribute while holding the inode
+ * lock
+ *
+ *  @dentry - object to perform setxattr on
+ *  @name - name of xattr to remove
+ *  @delegated_inode - on return, will contain an inode pointer that
+ *  a delegation was broken on, NULL if none.
+ */
 int
-vfs_removexattr(struct dentry *dentry, const char *name)
+__vfs_removexattr_locked(struct dentry *dentry, const char *name,
+		struct inode **delegated_inode)
 {
 	struct inode *inode = dentry->d_inode;
 	int error;
@@ -389,11 +436,14 @@ vfs_removexattr(struct dentry *dentry, const char *name)
 	if (error)
 		return error;
 
-	inode_lock(inode);
 	error = security_inode_removexattr(dentry, name);
 	if (error)
 		goto out;
 
+	error = try_break_deleg(inode, delegated_inode);
+	if (error)
+		goto out;
+
 	error = __vfs_removexattr(dentry, name);
 
 	if (!error) {
@@ -402,12 +452,32 @@ vfs_removexattr(struct dentry *dentry, const char *name)
 	}
 
 out:
+	return error;
+}
+EXPORT_SYMBOL_GPL(__vfs_removexattr_locked);
+
+int
+vfs_removexattr(struct dentry *dentry, const char *name)
+{
+	struct inode *inode = dentry->d_inode;
+	struct inode *delegated_inode = NULL;
+	int error;
+
+retry_deleg:
+	inode_lock(inode);
+	error = __vfs_removexattr_locked(dentry, name, &delegated_inode);
 	inode_unlock(inode);
+
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry_deleg;
+	}
+
 	return error;
 }
 EXPORT_SYMBOL_GPL(vfs_removexattr);
 
-
 /*
  * Extended attribute SET operations
  */
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index a9ff3cf82cce..3e6e7c368064 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -2607,6 +2607,13 @@ xfs_agf_verify(
 	      be32_to_cpu(agf->agf_flcount) <= xfs_agfl_size(mp)))
 		return __this_address;
 
+	if (be32_to_cpu(agf->agf_length) > mp->m_sb.sb_dblocks)
+		return __this_address;
+
+	if (be32_to_cpu(agf->agf_freeblks) < be32_to_cpu(agf->agf_longest) ||
+	    be32_to_cpu(agf->agf_freeblks) > be32_to_cpu(agf->agf_length))
+		return __this_address;
+
 	if (be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) < 1 ||
 	    be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]) < 1 ||
 	    be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) > XFS_BTREE_MAXLEVELS ||
@@ -2618,6 +2625,10 @@ xfs_agf_verify(
 	     be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) > XFS_BTREE_MAXLEVELS))
 		return __this_address;
 
+	if (xfs_sb_version_hasrmapbt(&mp->m_sb) &&
+	    be32_to_cpu(agf->agf_rmap_blocks) > be32_to_cpu(agf->agf_length))
+		return __this_address;
+
 	/*
 	 * during growfs operations, the perag is not fully initialised,
 	 * so we can't use it for any useful checking. growfs ensures we can't
@@ -2632,6 +2643,11 @@ xfs_agf_verify(
 		return __this_address;
 
 	if (xfs_sb_version_hasreflink(&mp->m_sb) &&
+	    be32_to_cpu(agf->agf_refcount_blocks) >
+	    be32_to_cpu(agf->agf_length))
+		return __this_address;
+
+	if (xfs_sb_version_hasreflink(&mp->m_sb) &&
 	    (be32_to_cpu(agf->agf_refcount_level) < 1 ||
 	     be32_to_cpu(agf->agf_refcount_level) > XFS_BTREE_MAXLEVELS))
 		return __this_address;
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 1f6e3965ff74..f09dcf9a96ee 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -926,8 +926,10 @@ xfs_attr_shortform_verify(
 		 * struct xfs_attr_sf_entry has a variable length.
 		 * Check the fixed-offset parts of the structure are
 		 * within the data buffer.
+		 * xfs_attr_sf_entry is defined with a 1-byte variable
+		 * array at the end, so we must subtract that off.
 		 */
-		if (((char *)sfep + sizeof(*sfep)) >= endp)
+		if (((char *)sfep + sizeof(*sfep) - 1) >= endp)
 			return __this_address;
 
 		/* Don't allow names with known bad length. */
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index d6fbe487d91a..628230bd7311 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -5322,7 +5322,7 @@ __xfs_bunmapi(
 		 * Make sure we don't touch multiple AGF headers out of order
 		 * in a single transaction, as that could cause AB-BA deadlocks.
 		 */
-		if (!wasdel) {
+		if (!wasdel && !isrt) {
 			agno = XFS_FSB_TO_AGNO(mp, del.br_startblock);
 			if (prev_agno != NULLAGNUMBER && prev_agno > agno)
 				break;
diff --git a/fs/xfs/libxfs/xfs_trans_space.h b/fs/xfs/libxfs/xfs_trans_space.h
index a62fb950bef1..0c02d76eeb4d 100644
--- a/fs/xfs/libxfs/xfs_trans_space.h
+++ b/fs/xfs/libxfs/xfs_trans_space.h
@@ -57,7 +57,7 @@
 	XFS_DAREMOVE_SPACE_RES(mp, XFS_DATA_FORK)
 #define	XFS_IALLOC_SPACE_RES(mp)	\
 	((mp)->m_ialloc_blks + \
-	 (xfs_sb_version_hasfinobt(&mp->m_sb) ? 2 : 1 * \
+	 ((xfs_sb_version_hasfinobt(&mp->m_sb) ? 2 : 1) * \
 	  ((mp)->m_in_maxlevels - 1)))
 
 /*
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index a703cd58a90e..3fe938968348 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -53,9 +53,27 @@ xchk_setup_inode_bmap(
 	 */
 	if (S_ISREG(VFS_I(sc->ip)->i_mode) &&
 	    sc->sm->sm_type == XFS_SCRUB_TYPE_BMBTD) {
+		struct address_space	*mapping = VFS_I(sc->ip)->i_mapping;
+
 		inode_dio_wait(VFS_I(sc->ip));
-		error = filemap_write_and_wait(VFS_I(sc->ip)->i_mapping);
-		if (error)
+
+		/*
+		 * Try to flush all incore state to disk before we examine the
+		 * space mappings for the data fork.  Leave accumulated errors
+		 * in the mapping for the writer threads to consume.
+		 *
+		 * On ENOSPC or EIO writeback errors, we continue into the
+		 * extent mapping checks because write failures do not
+		 * necessarily imply anything about the correctness of the file
+		 * metadata.  The metadata and the file data could be on
+		 * completely separate devices; a media failure might only
+		 * affect a subset of the disk, etc.  We can handle delalloc
+		 * extents in the scrubber, so leaving them in memory is fine.
+		 */
+		error = filemap_fdatawrite(mapping);
+		if (!error)
+			error = filemap_fdatawait_keep_errors(mapping);
+		if (error && (error != -ENOSPC && error != -EIO))
 			goto out;
 	}
 
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index 003a772cd26c..2e50d146105d 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -14,8 +14,15 @@
 static inline bool
 xchk_should_terminate(
 	struct xfs_scrub	*sc,
-	int				*error)
+	int			*error)
 {
+	/*
+	 * If preemption is disabled, we need to yield to the scheduler every
+	 * few seconds so that we don't run afoul of the soft lockup watchdog
+	 * or RCU stall detector.
+	 */
+	cond_resched();
+
 	if (fatal_signal_pending(current)) {
 		if (*error == 0)
 			*error = -EAGAIN;
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 06d07f1e310b..814239fac1b5 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1771,7 +1771,7 @@ xfs_swap_extents(
 	if (xfs_inode_has_cow_data(tip)) {
 		error = xfs_reflink_cancel_cow_range(tip, 0, NULLFILEOFF, true);
 		if (error)
-			return error;
+			goto out_unlock;
 	}
 
 	/*
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 548344e25128..a2e864c61401 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1243,8 +1243,10 @@ xfs_buf_ioend(
 		bp->b_ops->verify_read(bp);
 	}
 
-	if (!bp->b_error)
+	if (!bp->b_error) {
+		bp->b_flags &= ~XBF_WRITE_FAIL;
 		bp->b_flags |= XBF_DONE;
+	}
 
 	if (bp->b_iodone)
 		(*(bp->b_iodone))(bp);
@@ -1304,7 +1306,7 @@ xfs_bwrite(
 
 	bp->b_flags |= XBF_WRITE;
 	bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q |
-			 XBF_WRITE_FAIL | XBF_DONE);
+			 XBF_DONE);
 
 	error = xfs_buf_submit(bp);
 	if (error) {
@@ -2040,7 +2042,7 @@ xfs_buf_delwri_submit_buffers(
 		 * synchronously. Otherwise, drop the buffer from the delwri
 		 * queue and submit async.
 		 */
-		bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_WRITE_FAIL);
+		bp->b_flags &= ~_XBF_DELWRI_Q;
 		bp->b_flags |= XBF_WRITE;
 		if (wait_list) {
 			bp->b_flags &= ~XBF_ASYNC;
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index a1af984e4913..59b2b29542f4 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -1120,13 +1120,12 @@ xfs_qm_dqflush(
 	dqb = bp->b_addr + dqp->q_bufoffset;
 	ddqp = &dqb->dd_diskdq;
 
-	/*
-	 * A simple sanity check in case we got a corrupted dquot.
-	 */
-	fa = xfs_dqblk_verify(mp, dqb, be32_to_cpu(ddqp->d_id), 0);
+	/* sanity check the in-core structure before we flush */
+	fa = xfs_dquot_verify(mp, &dqp->q_core, be32_to_cpu(dqp->q_core.d_id),
+			      0);
 	if (fa) {
 		xfs_alert(mp, "corrupt dquot ID 0x%x in memory at %pS",
-				be32_to_cpu(ddqp->d_id), fa);
+				be32_to_cpu(dqp->q_core.d_id), fa);
 		xfs_buf_relse(bp);
 		xfs_dqfunlock(dqp);
 		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index a76b27565a18..39966f4e3ecb 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -909,7 +909,12 @@ xfs_eofblocks_worker(
 {
 	struct xfs_mount *mp = container_of(to_delayed_work(work),
 				struct xfs_mount, m_eofblocks_work);
+
+	if (!sb_start_write_trylock(mp->m_super))
+		return;
 	xfs_icache_free_eofblocks(mp, NULL);
+	sb_end_write(mp->m_super);
+
 	xfs_queue_eofblocks(mp);
 }
 
@@ -936,7 +941,12 @@ xfs_cowblocks_worker(
 {
 	struct xfs_mount *mp = container_of(to_delayed_work(work),
 				struct xfs_mount, m_cowblocks_work);
+
+	if (!sb_start_write_trylock(mp->m_super))
+		return;
 	xfs_icache_free_cowblocks(mp, NULL);
+	sb_end_write(mp->m_super);
+
 	xfs_queue_cowblocks(mp);
 }
 
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index d7dfc13f30f5..8a9719104a8f 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -2184,7 +2184,10 @@ xfs_file_ioctl(
 		if (error)
 			return error;
 
-		return xfs_icache_free_eofblocks(mp, &keofb);
+		sb_start_write(mp->m_super);
+		error = xfs_icache_free_eofblocks(mp, &keofb);
+		sb_end_write(mp->m_super);
+		return error;
 	}
 
 	default:
diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c
index a7c0c657dfaf..13ca7c16bfc7 100644
--- a/fs/xfs/xfs_quotaops.c
+++ b/fs/xfs/xfs_quotaops.c
@@ -202,6 +202,9 @@ xfs_fs_rm_xquota(
 	if (XFS_IS_QUOTA_ON(mp))
 		return -EINVAL;
 
+	if (uflags & ~(FS_USER_QUOTA | FS_GROUP_QUOTA | FS_PROJ_QUOTA))
+		return -EINVAL;
+
 	if (uflags & FS_USER_QUOTA)
 		flags |= XFS_DQ_USER;
 	if (uflags & FS_GROUP_QUOTA)
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 680ae7662a78..5919e1714d5f 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1023,6 +1023,7 @@ xfs_reflink_remap_extent(
 	xfs_filblks_t		rlen;
 	xfs_filblks_t		unmap_len;
 	xfs_off_t		newlen;
+	int64_t			qres;
 	int			error;
 
 	unmap_len = irec->br_startoff + irec->br_blockcount - destoff;
@@ -1045,13 +1046,19 @@ xfs_reflink_remap_extent(
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, 0);
 
-	/* If we're not just clearing space, then do we have enough quota? */
-	if (real_extent) {
-		error = xfs_trans_reserve_quota_nblks(tp, ip,
-				irec->br_blockcount, 0, XFS_QMOPT_RES_REGBLKS);
-		if (error)
-			goto out_cancel;
-	}
+	/*
+	 * Reserve quota for this operation.  We don't know if the first unmap
+	 * in the dest file will cause a bmap btree split, so we always reserve
+	 * at least enough blocks for that split.  If the extent being mapped
+	 * in is written, we need to reserve quota for that too.
+	 */
+	qres = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK);
+	if (real_extent)
+		qres += irec->br_blockcount;
+	error = xfs_trans_reserve_quota_nblks(tp, ip, qres, 0,
+			XFS_QMOPT_RES_REGBLKS);
+	if (error)
+		goto out_cancel;
 
 	trace_xfs_reflink_remap(ip, irec->br_startoff,
 				irec->br_blockcount, irec->br_startblock);
@@ -1071,6 +1078,7 @@ xfs_reflink_remap_extent(
 		uirec.br_startblock = irec->br_startblock + rlen;
 		uirec.br_startoff = irec->br_startoff + rlen;
 		uirec.br_blockcount = unmap_len - rlen;
+		uirec.br_state = irec->br_state;
 		unmap_len = rlen;
 
 		/* If this isn't a real mapping, we're done. */
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index d3a4e89bf4a0..66f167aefd94 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -520,8 +520,9 @@ xfsaild(
 {
 	struct xfs_ail	*ailp = data;
 	long		tout = 0;	/* milliseconds */
+	unsigned int	noreclaim_flag;
 
-	current->flags |= PF_MEMALLOC;
+	noreclaim_flag = memalloc_noreclaim_save();
 	set_freezable();
 
 	while (1) {
@@ -592,6 +593,7 @@ xfsaild(
 		tout = xfsaild_push(ailp);
 	}
 
+	memalloc_noreclaim_restore(noreclaim_flag);
 	return 0;
 }
 
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index ad6892a24015..1afd66e28645 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -532,11 +532,12 @@ typedef u64 acpi_integer;
 	 strnlen (a, ACPI_NAMESEG_SIZE) == ACPI_NAMESEG_SIZE)
 
 /*
- * Algorithm to obtain access bit width.
+ * Algorithm to obtain access bit or byte width.
  * Can be used with access_width of struct acpi_generic_address and access_size of
  * struct acpi_resource_generic_register.
  */
 #define ACPI_ACCESS_BIT_WIDTH(size)     (1 << ((size) + 2))
+#define ACPI_ACCESS_BYTE_WIDTH(size)    (1 << ((size) - 1))
 
 /*******************************************************************************
  *
diff --git a/include/acpi/processor.h b/include/acpi/processor.h
index 1194a4c78d55..5b9eab15a1e6 100644
--- a/include/acpi/processor.h
+++ b/include/acpi/processor.h
@@ -293,6 +293,14 @@ static inline void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx
 }
 #endif
 
+static inline int call_on_cpu(int cpu, long (*fn)(void *), void *arg,
+			      bool direct)
+{
+	if (direct || (is_percpu_thread() && cpu == smp_processor_id()))
+		return fn(arg);
+	return work_on_cpu(cpu, fn, arg);
+}
+
 /* in processor_perflib.c */
 
 #ifdef CONFIG_CPU_FREQ
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index aa6c093d9ce9..384b5c835ced 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -10,6 +10,7 @@
 #define BUGFLAG_WARNING		(1 << 0)
 #define BUGFLAG_ONCE		(1 << 1)
 #define BUGFLAG_DONE		(1 << 2)
+#define BUGFLAG_NO_CUT_HERE	(1 << 3)	/* CUT_HERE already sent */
 #define BUGFLAG_TAINT(taint)	((taint) << 8)
 #define BUG_GET_TAINT(bug)	((bug)->flags >> 8)
 #endif
@@ -61,18 +62,6 @@ struct bug_entry {
 #define BUG_ON(condition) do { if (unlikely(condition)) BUG(); } while (0)
 #endif
 
-#ifdef __WARN_FLAGS
-#define __WARN_TAINT(taint)		__WARN_FLAGS(BUGFLAG_TAINT(taint))
-#define __WARN_ONCE_TAINT(taint)	__WARN_FLAGS(BUGFLAG_ONCE|BUGFLAG_TAINT(taint))
-
-#define WARN_ON_ONCE(condition) ({				\
-	int __ret_warn_on = !!(condition);			\
-	if (unlikely(__ret_warn_on))				\
-		__WARN_ONCE_TAINT(TAINT_WARN);			\
-	unlikely(__ret_warn_on);				\
-})
-#endif
-
 /*
  * WARN(), WARN_ON(), WARN_ON_ONCE, and so on can be used to report
  * significant kernel issues that need prompt attention if they should ever
@@ -89,27 +78,27 @@ struct bug_entry {
  *
  * Use the versions with printk format strings to provide better diagnostics.
  */
-#ifndef __WARN_TAINT
-extern __printf(3, 4)
-void warn_slowpath_fmt(const char *file, const int line,
-		       const char *fmt, ...);
+#ifndef __WARN_FLAGS
 extern __printf(4, 5)
-void warn_slowpath_fmt_taint(const char *file, const int line, unsigned taint,
-			     const char *fmt, ...);
-extern void warn_slowpath_null(const char *file, const int line);
-#define WANT_WARN_ON_SLOWPATH
-#define __WARN()		warn_slowpath_null(__FILE__, __LINE__)
-#define __WARN_printf(arg...)	warn_slowpath_fmt(__FILE__, __LINE__, arg)
-#define __WARN_printf_taint(taint, arg...)				\
-	warn_slowpath_fmt_taint(__FILE__, __LINE__, taint, arg)
+void warn_slowpath_fmt(const char *file, const int line, unsigned taint,
+		       const char *fmt, ...);
+#define __WARN()		__WARN_printf(TAINT_WARN, NULL)
+#define __WARN_printf(taint, arg...)					\
+	warn_slowpath_fmt(__FILE__, __LINE__, taint, arg)
 #else
 extern __printf(1, 2) void __warn_printk(const char *fmt, ...);
-#define __WARN() do { \
-	printk(KERN_WARNING CUT_HERE); __WARN_TAINT(TAINT_WARN); \
-} while (0)
-#define __WARN_printf(arg...)	__WARN_printf_taint(TAINT_WARN, arg)
-#define __WARN_printf_taint(taint, arg...)				\
-	do { __warn_printk(arg); __WARN_TAINT(taint); } while (0)
+#define __WARN()		__WARN_FLAGS(BUGFLAG_TAINT(TAINT_WARN))
+#define __WARN_printf(taint, arg...) do {				\
+		__warn_printk(arg);					\
+		__WARN_FLAGS(BUGFLAG_NO_CUT_HERE | BUGFLAG_TAINT(taint));\
+	} while (0)
+#define WARN_ON_ONCE(condition) ({				\
+	int __ret_warn_on = !!(condition);			\
+	if (unlikely(__ret_warn_on))				\
+		__WARN_FLAGS(BUGFLAG_ONCE |			\
+			     BUGFLAG_TAINT(TAINT_WARN));	\
+	unlikely(__ret_warn_on);				\
+})
 #endif
 
 /* used internally by panic.c */
@@ -132,7 +121,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 #define WARN(condition, format...) ({					\
 	int __ret_warn_on = !!(condition);				\
 	if (unlikely(__ret_warn_on))					\
-		__WARN_printf(format);					\
+		__WARN_printf(TAINT_WARN, format);			\
 	unlikely(__ret_warn_on);					\
 })
 #endif
@@ -140,7 +129,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 #define WARN_TAINT(condition, taint, format...) ({			\
 	int __ret_warn_on = !!(condition);				\
 	if (unlikely(__ret_warn_on))					\
-		__WARN_printf_taint(taint, format);			\
+		__WARN_printf(taint, format);				\
 	unlikely(__ret_warn_on);					\
 })
 
@@ -185,7 +174,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 #endif
 
 #ifndef HAVE_ARCH_BUG_ON
-#define BUG_ON(condition) do { if (condition) BUG(); } while (0)
+#define BUG_ON(condition) do { if (unlikely(condition)) BUG(); } while (0)
 #endif
 
 #ifndef HAVE_ARCH_WARN_ON
diff --git a/include/asm-generic/mmiowb.h b/include/asm-generic/mmiowb.h
index 9439ff037b2d..5698fca3bf56 100644
--- a/include/asm-generic/mmiowb.h
+++ b/include/asm-generic/mmiowb.h
@@ -27,7 +27,7 @@
 #include <asm/smp.h>
 
 DECLARE_PER_CPU(struct mmiowb_state, __mmiowb_state);
-#define __mmiowb_state()	this_cpu_ptr(&__mmiowb_state)
+#define __mmiowb_state()	raw_cpu_ptr(&__mmiowb_state)
 #else
 #define __mmiowb_state()	arch_mmiowb_state()
 #endif	/* arch_mmiowb_state */
@@ -35,7 +35,9 @@ DECLARE_PER_CPU(struct mmiowb_state, __mmiowb_state);
 static inline void mmiowb_set_pending(void)
 {
 	struct mmiowb_state *ms = __mmiowb_state();
-	ms->mmiowb_pending = ms->nesting_count;
+
+	if (likely(ms->nesting_count))
+		ms->mmiowb_pending = ms->nesting_count;
 }
 
 static inline void mmiowb_spin_lock(void)
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 04c0644006fd..c716ea81e653 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -137,13 +137,6 @@
  *  When used, an architecture is expected to provide __tlb_remove_table()
  *  which does the actual freeing of these pages.
  *
- *  HAVE_RCU_TABLE_NO_INVALIDATE
- *
- *  This makes HAVE_RCU_TABLE_FREE avoid calling tlb_flush_mmu_tlbonly() before
- *  freeing the page-table pages. This can be avoided if you use
- *  HAVE_RCU_TABLE_FREE and your architecture does _NOT_ use the Linux
- *  page-tables natively.
- *
  *  MMU_GATHER_NO_RANGE
  *
  *  Use this if your architecture lacks an efficient flush_tlb_range().
@@ -189,8 +182,23 @@ struct mmu_table_batch {
 
 extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
 
+/*
+ * This allows an architecture that does not use the linux page-tables for
+ * hardware to skip the TLBI when freeing page tables.
+ */
+#ifndef tlb_needs_table_invalidate
+#define tlb_needs_table_invalidate() (true)
+#endif
+
+#else
+
+#ifdef tlb_needs_table_invalidate
+#error tlb_needs_table_invalidate() requires HAVE_RCU_TABLE_FREE
 #endif
 
+#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+
+
 #ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
 /*
  * If we can't allocate a page to make a big batch of page pointers
diff --git a/include/asm-generic/topology.h b/include/asm-generic/topology.h
index 238873739550..5aa8705df87e 100644
--- a/include/asm-generic/topology.h
+++ b/include/asm-generic/topology.h
@@ -48,7 +48,7 @@
   #ifdef CONFIG_NEED_MULTIPLE_NODES
     #define cpumask_of_node(node)	((node) == 0 ? cpu_online_mask : cpu_none_mask)
   #else
-    #define cpumask_of_node(node)	((void)node, cpu_online_mask)
+    #define cpumask_of_node(node)	((void)(node), cpu_online_mask)
   #endif
 #endif
 #ifndef pcibus_to_node
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 088987e9a3ea..6def18cb8238 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -284,7 +284,8 @@
 
 #define PAGE_ALIGNED_DATA(page_align)					\
 	. = ALIGN(page_align);						\
-	*(.data..page_aligned)
+	*(.data..page_aligned)						\
+	. = ALIGN(page_align);
 
 #define READ_MOSTLY_DATA(align)						\
 	. = ALIGN(align);						\
@@ -317,6 +318,7 @@
  */
 #ifndef RO_AFTER_INIT_DATA
 #define RO_AFTER_INIT_DATA						\
+	. = ALIGN(8);							\
 	__start_ro_after_init = .;					\
 	*(.data..ro_after_init)						\
 	JUMP_TABLE_DATA							\
@@ -655,7 +657,9 @@
 	. = ALIGN(bss_align);						\
 	.bss : AT(ADDR(.bss) - LOAD_OFFSET) {				\
 		BSS_FIRST_SECTIONS					\
+		. = ALIGN(PAGE_SIZE);					\
 		*(.bss..page_aligned)					\
+		. = ALIGN(PAGE_SIZE);					\
 		*(.dynbss)						\
 		*(BSS_MAIN)						\
 		*(COMMON)						\
diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index 743d626479ef..890329abaa5f 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -70,6 +70,7 @@ struct crypto_spawn {
 	struct crypto_instance *inst;
 	const struct crypto_type *frontend;
 	u32 mask;
+	bool dead;
 };
 
 struct crypto_queue {
diff --git a/include/crypto/arc4.h b/include/crypto/arc4.h
index 5b2c24ab0139..f3c22fe01704 100644
--- a/include/crypto/arc4.h
+++ b/include/crypto/arc4.h
@@ -6,8 +6,18 @@
 #ifndef _CRYPTO_ARC4_H
 #define _CRYPTO_ARC4_H
 
+#include <linux/types.h>
+
 #define ARC4_MIN_KEY_SIZE	1
 #define ARC4_MAX_KEY_SIZE	256
 #define ARC4_BLOCK_SIZE		1
 
+struct arc4_ctx {
+	u32 S[256];
+	u32 x, y;
+};
+
+int arc4_setkey(struct arc4_ctx *ctx, const u8 *in_key, unsigned int key_len);
+void arc4_crypt(struct arc4_ctx *ctx, u8 *out, const u8 *in, unsigned int len);
+
 #endif /* _CRYPTO_ARC4_H */
diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h
index 24cfa96f98ea..c1a8d4a41bb1 100644
--- a/include/crypto/if_alg.h
+++ b/include/crypto/if_alg.h
@@ -29,8 +29,8 @@ struct alg_sock {
 
 	struct sock *parent;
 
-	unsigned int refcnt;
-	unsigned int nokey_refcnt;
+	atomic_t refcnt;
+	atomic_t nokey_refcnt;
 
 	const struct af_alg_type *type;
 	void *private;
@@ -135,6 +135,7 @@ struct af_alg_async_req {
  *			SG?
  * @enc:		Cryptographic operation to be performed when
  *			recvmsg is invoked.
+ * @init:		True if metadata has been sent.
  * @len:		Length of memory allocated for this data structure.
  */
 struct af_alg_ctx {
@@ -151,6 +152,7 @@ struct af_alg_ctx {
 	bool more;
 	bool merge;
 	bool enc;
+	bool init;
 
 	unsigned int len;
 };
@@ -226,7 +228,7 @@ unsigned int af_alg_count_tsgl(struct sock *sk, size_t bytes, size_t offset);
 void af_alg_pull_tsgl(struct sock *sk, size_t used, struct scatterlist *dst,
 		      size_t dst_offset);
 void af_alg_wmem_wakeup(struct sock *sk);
-int af_alg_wait_for_data(struct sock *sk, unsigned flags);
+int af_alg_wait_for_data(struct sock *sk, unsigned flags, unsigned min);
 int af_alg_sendmsg(struct socket *sock, struct msghdr *msg, size_t size,
 		   unsigned int ivsize);
 ssize_t af_alg_sendpage(struct socket *sock, struct page *page,
diff --git a/include/crypto/internal/skcipher.h b/include/crypto/internal/skcipher.h
index fe0376d5a471..22348cd10849 100644
--- a/include/crypto/internal/skcipher.h
+++ b/include/crypto/internal/skcipher.h
@@ -200,6 +200,36 @@ static inline unsigned int crypto_skcipher_alg_max_keysize(
 	return alg->max_keysize;
 }
 
+static inline unsigned int crypto_skcipher_alg_walksize(
+	struct skcipher_alg *alg)
+{
+	if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) ==
+	    CRYPTO_ALG_TYPE_BLKCIPHER)
+		return alg->base.cra_blocksize;
+
+	if (alg->base.cra_ablkcipher.encrypt)
+		return alg->base.cra_blocksize;
+
+	return alg->walksize;
+}
+
+/**
+ * crypto_skcipher_walksize() - obtain walk size
+ * @tfm: cipher handle
+ *
+ * In some cases, algorithms can only perform optimally when operating on
+ * multiple blocks in parallel. This is reflected by the walksize, which
+ * must be a multiple of the chunksize (or equal if the concern does not
+ * apply)
+ *
+ * Return: walk size in bytes
+ */
+static inline unsigned int crypto_skcipher_walksize(
+	struct crypto_skcipher *tfm)
+{
+	return crypto_skcipher_alg_walksize(crypto_skcipher_alg(tfm));
+}
+
 /* Helpers for simple block cipher modes of operation */
 struct skcipher_ctx_simple {
 	struct crypto_cipher *cipher;	/* underlying block cipher */
diff --git a/include/crypto/skcipher.h b/include/crypto/skcipher.h
index ce7fa0973580..26be16cc46e3 100644
--- a/include/crypto/skcipher.h
+++ b/include/crypto/skcipher.h
@@ -288,20 +288,23 @@ static inline unsigned int crypto_sync_skcipher_ivsize(
 	return crypto_skcipher_ivsize(&tfm->base);
 }
 
-static inline unsigned int crypto_skcipher_alg_chunksize(
-	struct skcipher_alg *alg)
+/**
+ * crypto_skcipher_blocksize() - obtain block size of cipher
+ * @tfm: cipher handle
+ *
+ * The block size for the skcipher referenced with the cipher handle is
+ * returned. The caller may use that information to allocate appropriate
+ * memory for the data returned by the encryption or decryption operation
+ *
+ * Return: block size of cipher
+ */
+static inline unsigned int crypto_skcipher_blocksize(
+	struct crypto_skcipher *tfm)
 {
-	if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) ==
-	    CRYPTO_ALG_TYPE_BLKCIPHER)
-		return alg->base.cra_blocksize;
-
-	if (alg->base.cra_ablkcipher.encrypt)
-		return alg->base.cra_blocksize;
-
-	return alg->chunksize;
+	return crypto_tfm_alg_blocksize(crypto_skcipher_tfm(tfm));
 }
 
-static inline unsigned int crypto_skcipher_alg_walksize(
+static inline unsigned int crypto_skcipher_alg_chunksize(
 	struct skcipher_alg *alg)
 {
 	if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) ==
@@ -311,7 +314,7 @@ static inline unsigned int crypto_skcipher_alg_walksize(
 	if (alg->base.cra_ablkcipher.encrypt)
 		return alg->base.cra_blocksize;
 
-	return alg->walksize;
+	return alg->chunksize;
 }
 
 /**
@@ -331,39 +334,6 @@ static inline unsigned int crypto_skcipher_chunksize(
 	return crypto_skcipher_alg_chunksize(crypto_skcipher_alg(tfm));
 }
 
-/**
- * crypto_skcipher_walksize() - obtain walk size
- * @tfm: cipher handle
- *
- * In some cases, algorithms can only perform optimally when operating on
- * multiple blocks in parallel. This is reflected by the walksize, which
- * must be a multiple of the chunksize (or equal if the concern does not
- * apply)
- *
- * Return: walk size in bytes
- */
-static inline unsigned int crypto_skcipher_walksize(
-	struct crypto_skcipher *tfm)
-{
-	return crypto_skcipher_alg_walksize(crypto_skcipher_alg(tfm));
-}
-
-/**
- * crypto_skcipher_blocksize() - obtain block size of cipher
- * @tfm: cipher handle
- *
- * The block size for the skcipher referenced with the cipher handle is
- * returned. The caller may use that information to allocate appropriate
- * memory for the data returned by the encryption or decryption operation
- *
- * Return: block size of cipher
- */
-static inline unsigned int crypto_skcipher_blocksize(
-	struct crypto_skcipher *tfm)
-{
-	return crypto_tfm_alg_blocksize(crypto_skcipher_tfm(tfm));
-}
-
 static inline unsigned int crypto_sync_skcipher_blocksize(
 	struct crypto_sync_skcipher *tfm)
 {
diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h
index 7f60e8eb269a..f1cdea2d475c 100644
--- a/include/drm/drm_mode_config.h
+++ b/include/drm/drm_mode_config.h
@@ -868,6 +868,18 @@ struct drm_mode_config {
 	bool async_page_flip;
 
 	/**
+	 * @fbdev_use_iomem:
+	 *
+	 * Set to true if framebuffer reside in iomem.
+	 * When set to true memcpy_toio() is used when copying the framebuffer in
+	 * drm_fb_helper.drm_fb_helper_dirty_blit_real().
+	 *
+	 * FIXME: This should be replaced with a per-mapping is_iomem
+	 * flag (like ttm does), and then used everywhere in fbdev code.
+	 */
+	bool fbdev_use_iomem;
+
+	/**
 	 * @allow_fb_modifiers:
 	 *
 	 * Whether the driver supports fb modifiers in the ADDFB2.1 ioctl call.
diff --git a/include/dt-bindings/reset/amlogic,meson8b-reset.h b/include/dt-bindings/reset/amlogic,meson8b-reset.h
index 614aff2c7aff..a03e86fe2c57 100644
--- a/include/dt-bindings/reset/amlogic,meson8b-reset.h
+++ b/include/dt-bindings/reset/amlogic,meson8b-reset.h
@@ -95,9 +95,9 @@
 #define RESET_VD_RMEM			64
 #define RESET_AUDIN			65
 #define RESET_DBLK			66
-#define RESET_PIC_DC			66
-#define RESET_PSC			66
-#define RESET_NAND			66
+#define RESET_PIC_DC			67
+#define RESET_PSC			68
+#define RESET_NAND			69
 #define RESET_GE2D			70
 #define RESET_PARSER_REG		71
 #define RESET_PARSER_FETCH		72
diff --git a/include/keys/big_key-type.h b/include/keys/big_key-type.h
index f6a7ba4dccd4..3fee04f81439 100644
--- a/include/keys/big_key-type.h
+++ b/include/keys/big_key-type.h
@@ -17,6 +17,6 @@ extern void big_key_free_preparse(struct key_preparsed_payload *prep);
 extern void big_key_revoke(struct key *key);
 extern void big_key_destroy(struct key *key);
 extern void big_key_describe(const struct key *big_key, struct seq_file *m);
-extern long big_key_read(const struct key *key, char __user *buffer, size_t buflen);
+extern long big_key_read(const struct key *key, char *buffer, size_t buflen);
 
 #endif /* _KEYS_BIG_KEY_TYPE_H */
diff --git a/include/keys/user-type.h b/include/keys/user-type.h
index d5e73266a81a..be61fcddc02a 100644
--- a/include/keys/user-type.h
+++ b/include/keys/user-type.h
@@ -41,8 +41,7 @@ extern int user_update(struct key *key, struct key_preparsed_payload *prep);
 extern void user_revoke(struct key *key);
 extern void user_destroy(struct key *key);
 extern void user_describe(const struct key *user, struct seq_file *m);
-extern long user_read(const struct key *key,
-		      char __user *buffer, size_t buflen);
+extern long user_read(const struct key *key, char *buffer, size_t buflen);
 
 static inline const struct user_key_payload *user_key_payload_rcu(const struct key *key)
 {
diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h
index 6782f0d45ebe..49e5383d4222 100644
--- a/include/linux/ahci_platform.h
+++ b/include/linux/ahci_platform.h
@@ -19,6 +19,8 @@ struct ahci_host_priv;
 struct platform_device;
 struct scsi_host_template;
 
+int ahci_platform_enable_phys(struct ahci_host_priv *hpriv);
+void ahci_platform_disable_phys(struct ahci_host_priv *hpriv);
 int ahci_platform_enable_clks(struct ahci_host_priv *hpriv);
 void ahci_platform_disable_clks(struct ahci_host_priv *hpriv);
 int ahci_platform_enable_regulators(struct ahci_host_priv *hpriv);
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index 07e02d6df5ad..65d47522413c 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -197,6 +197,7 @@ struct backing_dev_info {
 	wait_queue_head_t wb_waitq;
 
 	struct device *dev;
+	char dev_name[64];
 	struct device *owner;
 
 	struct timer_list laptop_mode_wb_timer;
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index f9b029180241..6418319f042f 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -13,6 +13,7 @@
 #include <linux/fs.h>
 #include <linux/sched.h>
 #include <linux/blkdev.h>
+#include <linux/device.h>
 #include <linux/writeback.h>
 #include <linux/blk-cgroup.h>
 #include <linux/backing-dev-defs.h>
@@ -498,4 +499,6 @@ static inline int bdi_rw_congested(struct backing_dev_info *bdi)
 				  (1 << WB_async_congested));
 }
 
+const char *bdi_dev_name(struct backing_dev_info *bdi);
+
 #endif	/* _LINUX_BACKING_DEV_H */
diff --git a/include/linux/bio.h b/include/linux/bio.h
index e36b8fc1b1c3..11cc19ff9dc7 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -481,6 +481,7 @@ extern struct bio *bio_copy_user_iov(struct request_queue *,
 				     gfp_t);
 extern int bio_uncopy_user(struct bio *);
 void zero_fill_bio_iter(struct bio *bio, struct bvec_iter iter);
+void bio_truncate(struct bio *bio, unsigned new_size);
 
 static inline void zero_fill_bio(struct bio *bio)
 {
diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h
index 4bbb5f1c8b5b..4c0224ff0a14 100644
--- a/include/linux/bitfield.h
+++ b/include/linux/bitfield.h
@@ -64,7 +64,7 @@
  */
 #define FIELD_FIT(_mask, _val)						\
 	({								\
-		__BF_FIELD_CHECK(_mask, 0ULL, _val, "FIELD_FIT: ");	\
+		__BF_FIELD_CHECK(_mask, 0ULL, 0ULL, "FIELD_FIT: ");	\
 		!((((typeof(_mask))_val) << __bf_shf(_mask)) & ~(_mask)); \
 	})
 
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index cf074bce3eb3..458d0c6fa0e0 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -50,7 +50,7 @@ static inline int get_bitmask_order(unsigned int count)
 
 static __always_inline unsigned long hweight_long(unsigned long w)
 {
-	return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
+	return sizeof(w) == 4 ? hweight32(w) : hweight64((__u64)w);
 }
 
 /**
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 4c6754e53672..0db80f6327eb 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -324,6 +324,7 @@ struct queue_limits {
 	unsigned int		max_sectors;
 	unsigned int		max_segment_size;
 	unsigned int		physical_block_size;
+	unsigned int		logical_block_size;
 	unsigned int		alignment_offset;
 	unsigned int		io_min;
 	unsigned int		io_opt;
@@ -334,7 +335,6 @@ struct queue_limits {
 	unsigned int		discard_granularity;
 	unsigned int		discard_alignment;
 
-	unsigned short		logical_block_size;
 	unsigned short		max_segments;
 	unsigned short		max_integrity_segments;
 	unsigned short		max_discard_segments;
@@ -529,7 +529,7 @@ struct request_queue {
 	unsigned int		sg_reserved_size;
 	int			node;
 #ifdef CONFIG_BLK_DEV_IO_TRACE
-	struct blk_trace	*blk_trace;
+	struct blk_trace __rcu	*blk_trace;
 	struct mutex		blk_trace_mutex;
 #endif
 	/*
@@ -589,6 +589,7 @@ struct request_queue {
 	u64			write_hints[BLK_MAX_WRITE_HINTS];
 };
 
+/* Keep blk_queue_flag_name[] in sync with the definitions below */
 #define QUEUE_FLAG_STOPPED	0	/* queue is stopped */
 #define QUEUE_FLAG_DYING	1	/* queue being torn down */
 #define QUEUE_FLAG_NOMERGES     3	/* disable merge attempts */
@@ -1077,7 +1078,7 @@ extern void blk_queue_max_write_same_sectors(struct request_queue *q,
 		unsigned int max_write_same_sectors);
 extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q,
 		unsigned int max_write_same_sectors);
-extern void blk_queue_logical_block_size(struct request_queue *, unsigned short);
+extern void blk_queue_logical_block_size(struct request_queue *, unsigned int);
 extern void blk_queue_physical_block_size(struct request_queue *, unsigned int);
 extern void blk_queue_alignment_offset(struct request_queue *q,
 				       unsigned int alignment);
@@ -1287,7 +1288,7 @@ static inline unsigned int queue_max_segment_size(struct request_queue *q)
 	return q->limits.max_segment_size;
 }
 
-static inline unsigned short queue_logical_block_size(struct request_queue *q)
+static inline unsigned queue_logical_block_size(struct request_queue *q)
 {
 	int retval = 512;
 
@@ -1297,7 +1298,7 @@ static inline unsigned short queue_logical_block_size(struct request_queue *q)
 	return retval;
 }
 
-static inline unsigned short bdev_logical_block_size(struct block_device *bdev)
+static inline unsigned int bdev_logical_block_size(struct block_device *bdev)
 {
 	return queue_logical_block_size(bdev_get_queue(bdev));
 }
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index 7bb2d8de9f30..3b6ff5902edc 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -51,9 +51,13 @@ void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *f
  **/
 #define blk_add_cgroup_trace_msg(q, cg, fmt, ...)			\
 	do {								\
-		struct blk_trace *bt = (q)->blk_trace;			\
+		struct blk_trace *bt;					\
+									\
+		rcu_read_lock();					\
+		bt = rcu_dereference((q)->blk_trace);			\
 		if (unlikely(bt))					\
 			__trace_note_message(bt, cg, fmt, ##__VA_ARGS__);\
+		rcu_read_unlock();					\
 	} while (0)
 #define blk_add_trace_msg(q, fmt, ...)					\
 	blk_add_cgroup_trace_msg(q, NULL, fmt, ##__VA_ARGS__)
@@ -61,10 +65,14 @@ void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *f
 
 static inline bool blk_trace_note_message_enabled(struct request_queue *q)
 {
-	struct blk_trace *bt = q->blk_trace;
-	if (likely(!bt))
-		return false;
-	return bt->act_mask & BLK_TC_NOTIFY;
+	struct blk_trace *bt;
+	bool ret;
+
+	rcu_read_lock();
+	bt = rcu_dereference(q->blk_trace);
+	ret = bt && (bt->act_mask & BLK_TC_NOTIFY);
+	rcu_read_unlock();
+	return ret;
 }
 
 extern void blk_add_driver_data(struct request_queue *q, struct request *rq,
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 7b73ef7f902d..b56cc825f64d 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -189,6 +189,8 @@ struct buffer_head *__getblk_gfp(struct block_device *bdev, sector_t block,
 void __brelse(struct buffer_head *);
 void __bforget(struct buffer_head *);
 void __breadahead(struct block_device *, sector_t block, unsigned int size);
+void __breadahead_gfp(struct block_device *, sector_t block, unsigned int size,
+		  gfp_t gfp);
 struct buffer_head *__bread_gfp(struct block_device *,
 				sector_t block, unsigned size, gfp_t gfp);
 void invalidate_bh_lrus(void);
@@ -319,6 +321,12 @@ sb_breadahead(struct super_block *sb, sector_t block)
 	__breadahead(sb->s_bdev, block, sb->s_blocksize);
 }
 
+static inline void
+sb_breadahead_unmovable(struct super_block *sb, sector_t block)
+{
+	__breadahead_gfp(sb->s_bdev, block, sb->s_blocksize, 0);
+}
+
 static inline struct buffer_head *
 sb_getblk(struct super_block *sb, sector_t block)
 {
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index f01623aef2f7..73199facd5a4 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -18,6 +18,7 @@
 #include <linux/can/error.h>
 #include <linux/can/led.h>
 #include <linux/can/netlink.h>
+#include <linux/can/skb.h>
 #include <linux/netdevice.h>
 
 /*
@@ -91,6 +92,36 @@ struct can_priv {
 #define get_can_dlc(i)		(min_t(__u8, (i), CAN_MAX_DLC))
 #define get_canfd_dlc(i)	(min_t(__u8, (i), CANFD_MAX_DLC))
 
+/* Check for outgoing skbs that have not been created by the CAN subsystem */
+static inline bool can_skb_headroom_valid(struct net_device *dev,
+					  struct sk_buff *skb)
+{
+	/* af_packet creates a headroom of HH_DATA_MOD bytes which is fine */
+	if (WARN_ON_ONCE(skb_headroom(skb) < sizeof(struct can_skb_priv)))
+		return false;
+
+	/* af_packet does not apply CAN skb specific settings */
+	if (skb->ip_summed == CHECKSUM_NONE) {
+		/* init headroom */
+		can_skb_prv(skb)->ifindex = dev->ifindex;
+		can_skb_prv(skb)->skbcnt = 0;
+
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+		/* preform proper loopback on capable devices */
+		if (dev->flags & IFF_ECHO)
+			skb->pkt_type = PACKET_LOOPBACK;
+		else
+			skb->pkt_type = PACKET_HOST;
+
+		skb_reset_mac_header(skb);
+		skb_reset_network_header(skb);
+		skb_reset_transport_header(skb);
+	}
+
+	return true;
+}
+
 /* Drop a given socketbuffer if it does not contain a valid CAN frame. */
 static inline bool can_dropped_invalid_skb(struct net_device *dev,
 					  struct sk_buff *skb)
@@ -108,6 +139,9 @@ static inline bool can_dropped_invalid_skb(struct net_device *dev,
 	} else
 		goto inval_skb;
 
+	if (!can_skb_headroom_valid(dev, skb))
+		goto inval_skb;
+
 	return false;
 
 inval_skb:
diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 23895d178149..fa5fa8b5ce0b 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -175,9 +175,10 @@ struct ceph_msg_data {
 #endif /* CONFIG_BLOCK */
 		struct ceph_bvec_iter	bvec_pos;
 		struct {
-			struct page	**pages;	/* NOT OWNER. */
+			struct page	**pages;
 			size_t		length;		/* total # bytes */
 			unsigned int	alignment;	/* first page */
+			bool		own_pages;
 		};
 		struct ceph_pagelist	*pagelist;
 	};
@@ -355,8 +356,8 @@ extern void ceph_con_keepalive(struct ceph_connection *con);
 extern bool ceph_con_keepalive_expired(struct ceph_connection *con,
 				       unsigned long interval);
 
-extern void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages,
-				size_t length, size_t alignment);
+void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages,
+			     size_t length, size_t alignment, bool own_pages);
 extern void ceph_msg_data_add_pagelist(struct ceph_msg *msg,
 				struct ceph_pagelist *pagelist);
 #ifdef CONFIG_BLOCK
diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index e081b56f1c1d..5e601975745f 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -37,6 +37,9 @@ int ceph_spg_compare(const struct ceph_spg *lhs, const struct ceph_spg *rhs);
 #define CEPH_POOL_FLAG_HASHPSPOOL	(1ULL << 0) /* hash pg seed and pool id
 						       together */
 #define CEPH_POOL_FLAG_FULL		(1ULL << 1) /* pool is full */
+#define CEPH_POOL_FLAG_FULL_QUOTA	(1ULL << 10) /* pool ran out of quota,
+							will set FULL too */
+#define CEPH_POOL_FLAG_NEARFULL		(1ULL << 11) /* pool is nearfull */
 
 struct ceph_pg_pool_info {
 	struct rb_node node;
@@ -304,5 +307,6 @@ extern struct ceph_pg_pool_info *ceph_pg_pool_by_id(struct ceph_osdmap *map,
 
 extern const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id);
 extern int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name);
+u64 ceph_pg_pool_flags(struct ceph_osdmap *map, u64 id);
 
 #endif
diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h
index 3eb0e55665b4..c004bced9b91 100644
--- a/include/linux/ceph/rados.h
+++ b/include/linux/ceph/rados.h
@@ -143,8 +143,10 @@ extern const char *ceph_osd_state_name(int s);
 /*
  * osd map flag bits
  */
-#define CEPH_OSDMAP_NEARFULL (1<<0)  /* sync writes (near ENOSPC) */
-#define CEPH_OSDMAP_FULL     (1<<1)  /* no data writes (ENOSPC) */
+#define CEPH_OSDMAP_NEARFULL (1<<0)  /* sync writes (near ENOSPC),
+					not set since ~luminous */
+#define CEPH_OSDMAP_FULL     (1<<1)  /* no data writes (ENOSPC),
+					not set since ~luminous */
 #define CEPH_OSDMAP_PAUSERD  (1<<2)  /* pause all reads */
 #define CEPH_OSDMAP_PAUSEWR  (1<<3)  /* pause all writes */
 #define CEPH_OSDMAP_PAUSEREC (1<<4)  /* pause recovery */
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index b4e766e93f6e..6a5604d3ea24 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -797,7 +797,9 @@ struct sock_cgroup_data {
 	union {
 #ifdef __LITTLE_ENDIAN
 		struct {
-			u8	is_data;
+			u8	is_data : 1;
+			u8	no_refcnt : 1;
+			u8	unused : 6;
 			u8	padding;
 			u16	prioidx;
 			u32	classid;
@@ -807,7 +809,9 @@ struct sock_cgroup_data {
 			u32	classid;
 			u16	prioidx;
 			u8	padding;
-			u8	is_data;
+			u8	unused : 6;
+			u8	no_refcnt : 1;
+			u8	is_data : 1;
 		} __packed;
 #endif
 		u64		val;
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 0297f930a56e..b4409b3ce927 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -62,6 +62,7 @@ struct css_task_iter {
 	struct list_head		*mg_tasks_head;
 	struct list_head		*dying_tasks_head;
 
+	struct list_head		*cur_tasks_head;
 	struct css_set			*cur_cset;
 	struct css_set			*cur_dcset;
 	struct task_struct		*cur_task;
@@ -817,6 +818,7 @@ extern spinlock_t cgroup_sk_update_lock;
 
 void cgroup_sk_alloc_disable(void);
 void cgroup_sk_alloc(struct sock_cgroup_data *skcd);
+void cgroup_sk_clone(struct sock_cgroup_data *skcd);
 void cgroup_sk_free(struct sock_cgroup_data *skcd);
 
 static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
@@ -830,7 +832,7 @@ static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
 	 */
 	v = READ_ONCE(skcd->val);
 
-	if (v & 1)
+	if (v & 3)
 		return &cgrp_dfl_root.cgrp;
 
 	return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp;
@@ -842,6 +844,7 @@ static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
 #else	/* CONFIG_CGROUP_DATA */
 
 static inline void cgroup_sk_alloc(struct sock_cgroup_data *skcd) {}
+static inline void cgroup_sk_clone(struct sock_cgroup_data *skcd) {}
 static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {}
 
 #endif	/* CONFIG_CGROUP_DATA */
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 8aaf7cd026b0..dd0888417aac 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -342,7 +342,7 @@ static inline void *offset_to_ptr(const int *off)
  * compiler has support to do so.
  */
 #define compiletime_assert(condition, msg) \
-	_compiletime_assert(condition, msg, __compiletime_assert_, __LINE__)
+	_compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__)
 
 #define compiletime_assert_atomic_type(t)				\
 	compiletime_assert(__native_word(t),				\
@@ -351,4 +351,10 @@ static inline void *offset_to_ptr(const int *off)
 /* &a[0] degrades to a pointer: a different type from an array */
 #define __must_be_array(a)	BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
 
+/*
+ * This is needed in functions which generate the stack canary, see
+ * arch/x86/kernel/smpboot.c::start_secondary() for an example.
+ */
+#define prevent_tail_call_optimization()	mb()
+
 #endif /* __LINUX_COMPILER_H */
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 4643fcf55474..9842a2264d6e 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -64,6 +64,7 @@ extern ssize_t cpu_show_tsx_async_abort(struct device *dev,
 					char *buf);
 extern ssize_t cpu_show_itlb_multihit(struct device *dev,
 				      struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char *buf);
 
 extern __printf(4, 5)
 struct device *cpu_device_create(struct device *parent, void *drvdata,
diff --git a/include/linux/devfreq_cooling.h b/include/linux/devfreq_cooling.h
index 4635f95000a4..79a6e37a1d6f 100644
--- a/include/linux/devfreq_cooling.h
+++ b/include/linux/devfreq_cooling.h
@@ -75,7 +75,7 @@ void devfreq_cooling_unregister(struct thermal_cooling_device *dfc);
 
 #else /* !CONFIG_DEVFREQ_THERMAL */
 
-struct thermal_cooling_device *
+static inline struct thermal_cooling_device *
 of_devfreq_cooling_register_power(struct device_node *np, struct devfreq *df,
 				  struct devfreq_cooling_power *dfc_power)
 {
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index e1f51d607cc5..bb0ea4b343b5 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -421,6 +421,7 @@ const char *dm_device_name(struct mapped_device *md);
 int dm_copy_name_and_uuid(struct mapped_device *md, char *name, char *uuid);
 struct gendisk *dm_disk(struct mapped_device *md);
 int dm_suspended(struct dm_target *ti);
+int dm_post_suspending(struct dm_target *ti);
 int dm_noflush_suspending(struct dm_target *ti);
 void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors);
 void dm_remap_zone_report(struct dm_target *ti, sector_t start,
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index c952f987ee57..fa3e8f91b3f5 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -674,6 +674,7 @@ struct dma_filter {
  * @fill_align: alignment shift for memset operations
  * @dev_id: unique device ID
  * @dev: struct device reference for dma mapping api
+ * @owner: owner module (automatically set based on the provided dev)
  * @src_addr_widths: bit mask of src addr widths the device supports
  *	Width is specified in bytes, e.g. for a device supporting
  *	a width of 4 the mask should have BIT(4) set.
@@ -737,6 +738,7 @@ struct dma_device {
 
 	int dev_id;
 	struct device *dev;
+	struct module *owner;
 
 	u32 src_addr_widths;
 	u32 dst_addr_widths;
@@ -1361,8 +1363,11 @@ static inline int dma_get_slave_caps(struct dma_chan *chan,
 static inline int dmaengine_desc_set_reuse(struct dma_async_tx_descriptor *tx)
 {
 	struct dma_slave_caps caps;
+	int ret;
 
-	dma_get_slave_caps(tx->chan, &caps);
+	ret = dma_get_slave_caps(tx->chan, &caps);
+	if (ret)
+		return ret;
 
 	if (caps.descriptor_reuse) {
 		tx->flags |= DMA_CTRL_REUSE;
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index 28813c6f44b6..8f235b94a7d0 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -69,19 +69,23 @@ struct dmar_pci_notify_info {
 extern struct rw_semaphore dmar_global_lock;
 extern struct list_head dmar_drhd_units;
 
-#define for_each_drhd_unit(drhd) \
-	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list)
+#define for_each_drhd_unit(drhd)					\
+	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list,		\
+				dmar_rcu_check())
 
 #define for_each_active_drhd_unit(drhd)					\
-	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list)		\
+	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list,		\
+				dmar_rcu_check())			\
 		if (drhd->ignored) {} else
 
 #define for_each_active_iommu(i, drhd)					\
-	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list)		\
+	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list,		\
+				dmar_rcu_check())			\
 		if (i=drhd->iommu, drhd->ignored) {} else
 
 #define for_each_iommu(i, drhd)						\
-	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list)		\
+	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list,		\
+				dmar_rcu_check())			\
 		if (i=drhd->iommu, 0) {} else 
 
 static inline bool dmar_rcu_check(void)
diff --git a/include/linux/elfnote.h b/include/linux/elfnote.h
index f236f5b931b2..7fdd7f355b52 100644
--- a/include/linux/elfnote.h
+++ b/include/linux/elfnote.h
@@ -54,7 +54,7 @@
 .popsection				;
 
 #define ELFNOTE(name, type, desc)		\
-	ELFNOTE_START(name, type, "")		\
+	ELFNOTE_START(name, type, "a")		\
 		desc			;	\
 	ELFNOTE_END
 
diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h
index ffcc7724ca21..dc4fd8a6644d 100644
--- a/include/linux/eventfd.h
+++ b/include/linux/eventfd.h
@@ -12,6 +12,8 @@
 #include <linux/fcntl.h>
 #include <linux/wait.h>
 #include <linux/err.h>
+#include <linux/percpu-defs.h>
+#include <linux/percpu.h>
 
 /*
  * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining
@@ -40,6 +42,13 @@ __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n);
 int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait,
 				  __u64 *cnt);
 
+DECLARE_PER_CPU(int, eventfd_wake_count);
+
+static inline bool eventfd_signal_count(void)
+{
+	return this_cpu_read(eventfd_wake_count);
+}
+
 #else /* CONFIG_EVENTFD */
 
 /*
@@ -68,6 +77,11 @@ static inline int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx,
 	return -ENOSYS;
 }
 
+static inline bool eventfd_signal_count(void)
+{
+	return false;
+}
+
 #endif
 
 #endif /* _LINUX_EVENTFD_H */
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 206a62d07d9d..3c9d792aaf60 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -735,8 +735,12 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default)
 
 static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
 {
-	set_vm_flush_reset_perms(fp);
-	set_memory_ro((unsigned long)fp, fp->pages);
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
+	if (!fp->jited) {
+		set_vm_flush_reset_perms(fp);
+		set_memory_ro((unsigned long)fp, fp->pages);
+	}
+#endif
 }
 
 static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
@@ -818,7 +822,7 @@ static inline bool bpf_dump_raw_ok(void)
 	/* Reconstruction of call-sites is dependent on kallsyms,
 	 * thus make dump the same restriction.
 	 */
-	return kallsyms_show_value() == 1;
+	return kallsyms_show_value(current_cred());
 }
 
 struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 1d1cbe8f1a0e..60cd22b5c30f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -691,6 +691,7 @@ struct inode {
 		struct rcu_head		i_rcu;
 	};
 	atomic64_t		i_version;
+	atomic64_t		i_sequence; /* see futex */
 	atomic_t		i_count;
 	atomic_t		i_dio_count;
 	atomic_t		i_writecount;
@@ -964,7 +965,7 @@ struct file_handle {
 	__u32 handle_bytes;
 	int handle_type;
 	/* file identifier */
-	unsigned char f_handle[0];
+	unsigned char f_handle[];
 };
 
 static inline struct file *get_file(struct file *f)
@@ -1705,6 +1706,13 @@ int vfs_mkobj(struct dentry *, umode_t,
 
 extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 
+#ifdef CONFIG_COMPAT
+extern long compat_ptr_ioctl(struct file *file, unsigned int cmd,
+					unsigned long arg);
+#else
+#define compat_ptr_ioctl NULL
+#endif
+
 /*
  * VFS file helper functions.
  */
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index d4844cad2c2b..929255d4fdd5 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -133,8 +133,7 @@ struct fsnotify_ops {
  */
 struct fsnotify_event {
 	struct list_head list;
-	/* inode may ONLY be dereferenced during handle_event(). */
-	struct inode *inode;	/* either the inode the event happened to or its parent */
+	unsigned long objectid;	/* identifier for queue merges */
 };
 
 /*
@@ -499,10 +498,10 @@ extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info);
 extern bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info);
 
 static inline void fsnotify_init_event(struct fsnotify_event *event,
-				       struct inode *inode)
+				       unsigned long objectid)
 {
 	INIT_LIST_HEAD(&event->list);
-	event->inode = inode;
+	event->objectid = objectid;
 }
 
 #else
diff --git a/include/linux/futex.h b/include/linux/futex.h
index ccaef0097785..a61bf436dcf3 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -29,23 +29,26 @@ struct task_struct;
 
 union futex_key {
 	struct {
+		u64 i_seq;
 		unsigned long pgoff;
-		struct inode *inode;
-		int offset;
+		unsigned int offset;
 	} shared;
 	struct {
+		union {
+			struct mm_struct *mm;
+			u64 __tmp;
+		};
 		unsigned long address;
-		struct mm_struct *mm;
-		int offset;
+		unsigned int offset;
 	} private;
 	struct {
+		u64 ptr;
 		unsigned long word;
-		void *ptr;
-		int offset;
+		unsigned int offset;
 	} both;
 };
 
-#define FUTEX_KEY_INIT (union futex_key) { .both = { .ptr = NULL } }
+#define FUTEX_KEY_INIT (union futex_key) { .both = { .ptr = 0ULL } }
 
 #ifdef CONFIG_FUTEX
 extern void exit_robust_list(struct task_struct *curr);
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 8b5330dd5ac0..62a2ec9f17df 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -750,9 +750,11 @@ static inline sector_t part_nr_sects_read(struct hd_struct *part)
 static inline void part_nr_sects_write(struct hd_struct *part, sector_t size)
 {
 #if BITS_PER_LONG==32 && defined(CONFIG_SMP)
+	preempt_disable();
 	write_seqcount_begin(&part->nr_sects_seq);
 	part->nr_sects = size;
 	write_seqcount_end(&part->nr_sects_seq);
+	preempt_enable();
 #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
 	preempt_disable();
 	part->nr_sects = size;
diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h
index a7f08fb0f865..ae6c80c49443 100644
--- a/include/linux/gpio/consumer.h
+++ b/include/linux/gpio/consumer.h
@@ -158,6 +158,7 @@ int gpiod_set_raw_array_value_cansleep(unsigned int array_size,
 
 int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce);
 int gpiod_set_transitory(struct gpio_desc *desc, bool transitory);
+void gpiod_toggle_active_low(struct gpio_desc *desc);
 
 int gpiod_is_active_low(const struct gpio_desc *desc);
 int gpiod_cansleep(const struct gpio_desc *desc);
@@ -489,6 +490,12 @@ static inline int gpiod_set_transitory(struct gpio_desc *desc, bool transitory)
 	return -ENOSYS;
 }
 
+static inline void gpiod_toggle_active_low(struct gpio_desc *desc)
+{
+	/* GPIO can never have been requested */
+	WARN_ON(desc);
+}
+
 static inline int gpiod_is_active_low(const struct gpio_desc *desc)
 {
 	/* GPIO can never have been requested */
diff --git a/include/linux/hid.h b/include/linux/hid.h
index d770ab1a0479..6aff73cd7af6 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -492,7 +492,7 @@ struct hid_report_enum {
 };
 
 #define HID_MIN_BUFFER_SIZE	64		/* make sure there is at least a packet size of space */
-#define HID_MAX_BUFFER_SIZE	4096		/* 4kb */
+#define HID_MAX_BUFFER_SIZE	8192		/* 8kb */
 #define HID_CONTROL_FIFO_SIZE	256		/* to init devices with >100 reports */
 #define HID_OUTPUT_FIFO_SIZE	64
 
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 0b6f210ba92e..76af03604f62 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -32,12 +32,15 @@ struct hrtimer_cpu_base;
  *				  when starting the timer)
  * HRTIMER_MODE_SOFT		- Timer callback function will be executed in
  *				  soft irq context
+ * HRTIMER_MODE_HARD		- Timer callback function will be executed in
+ *				  hard irq context even on PREEMPT_RT.
  */
 enum hrtimer_mode {
 	HRTIMER_MODE_ABS	= 0x00,
 	HRTIMER_MODE_REL	= 0x01,
 	HRTIMER_MODE_PINNED	= 0x02,
 	HRTIMER_MODE_SOFT	= 0x04,
+	HRTIMER_MODE_HARD	= 0x08,
 
 	HRTIMER_MODE_ABS_PINNED = HRTIMER_MODE_ABS | HRTIMER_MODE_PINNED,
 	HRTIMER_MODE_REL_PINNED = HRTIMER_MODE_REL | HRTIMER_MODE_PINNED,
@@ -48,6 +51,11 @@ enum hrtimer_mode {
 	HRTIMER_MODE_ABS_PINNED_SOFT = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_SOFT,
 	HRTIMER_MODE_REL_PINNED_SOFT = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_SOFT,
 
+	HRTIMER_MODE_ABS_HARD	= HRTIMER_MODE_ABS | HRTIMER_MODE_HARD,
+	HRTIMER_MODE_REL_HARD	= HRTIMER_MODE_REL | HRTIMER_MODE_HARD,
+
+	HRTIMER_MODE_ABS_PINNED_HARD = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_HARD,
+	HRTIMER_MODE_REL_PINNED_HARD = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_HARD,
 };
 
 /*
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index edf476c8cfb9..9f585513afa6 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -16,29 +16,11 @@ struct user_struct;
 struct mmu_gather;
 
 #ifndef is_hugepd
-/*
- * Some architectures requires a hugepage directory format that is
- * required to support multiple hugepage sizes. For example
- * a4fe3ce76 "powerpc/mm: Allow more flexible layouts for hugepage pagetables"
- * introduced the same on powerpc. This allows for a more flexible hugepage
- * pagetable layout.
- */
 typedef struct { unsigned long pd; } hugepd_t;
 #define is_hugepd(hugepd) (0)
 #define __hugepd(x) ((hugepd_t) { (x) })
-static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
-			      unsigned pdshift, unsigned long end,
-			      int write, struct page **pages, int *nr)
-{
-	return 0;
-}
-#else
-extern int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
-		       unsigned pdshift, unsigned long end,
-		       int write, struct page **pages, int *nr);
 #endif
 
-
 #ifdef CONFIG_HUGETLB_PAGE
 
 #include <linux/mempolicy.h>
@@ -316,10 +298,15 @@ static inline bool is_file_hugepages(struct file *file)
 	return is_file_shm_hugepages(file);
 }
 
+static inline struct hstate *hstate_inode(struct inode *i)
+{
+	return HUGETLBFS_SB(i->i_sb)->hstate;
+}
 
 #else /* !CONFIG_HUGETLBFS */
 
 #define is_file_hugepages(file)			false
+#define hstate_inode(i)				NULL
 static inline struct file *
 hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag,
 		struct user_struct **user, int creat_flags,
@@ -397,11 +384,6 @@ extern unsigned int default_hstate_idx;
 
 #define default_hstate (hstates[default_hstate_idx])
 
-static inline struct hstate *hstate_inode(struct inode *i)
-{
-	return HUGETLBFS_SB(i->i_sb)->hstate;
-}
-
 static inline struct hstate *hstate_file(struct file *f)
 {
 	return hstate_inode(file_inode(f));
@@ -616,7 +598,6 @@ struct hstate {};
 #define hstate_file(f) NULL
 #define hstate_sizelog(s) NULL
 #define hstate_vma(v) NULL
-#define hstate_inode(i) NULL
 #define page_hstate(page) NULL
 #define huge_page_size(h) PAGE_SIZE
 #define huge_page_mask(h) PAGE_MASK
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 6256cc34c4a6..e02b3dd76242 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -420,6 +420,8 @@ enum vmbus_channel_message_type {
 	CHANNELMSG_19				= 19,
 	CHANNELMSG_20				= 20,
 	CHANNELMSG_TL_CONNECT_REQUEST		= 21,
+	CHANNELMSG_22				= 22,
+	CHANNELMSG_TL_CONNECT_RESULT		= 23,
 	CHANNELMSG_COUNT
 };
 
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 1308126fc384..79f0d4fd5036 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -436,6 +436,9 @@ struct i2c_board_info {
 extern struct i2c_client *
 i2c_new_device(struct i2c_adapter *adap, struct i2c_board_info const *info);
 
+extern struct i2c_client *
+i2c_new_client_device(struct i2c_adapter *adap, struct i2c_board_info const *info);
+
 /* If you don't know the exact address of an I2C device, use this variant
  * instead, which can probe for device presence in a list of possible
  * addresses. The "probe" callback function is optional. If it is provided,
@@ -458,6 +461,9 @@ extern struct i2c_client *
 i2c_new_dummy(struct i2c_adapter *adap, u16 address);
 
 extern struct i2c_client *
+i2c_new_dummy_device(struct i2c_adapter *adapter, u16 address);
+
+extern struct i2c_client *
 devm_i2c_new_dummy_device(struct device *dev, struct i2c_adapter *adap, u16 address);
 
 extern struct i2c_client *
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 42690007d612..eed1c21962a1 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -620,6 +620,15 @@ static inline bool ieee80211_is_qos_nullfunc(__le16 fc)
 }
 
 /**
+ * ieee80211_is_any_nullfunc - check if frame is regular or QoS nullfunc frame
+ * @fc: frame control bytes in little-endian byteorder
+ */
+static inline bool ieee80211_is_any_nullfunc(__le16 fc)
+{
+	return (ieee80211_is_nullfunc(fc) || ieee80211_is_qos_nullfunc(fc));
+}
+
+/**
  * ieee80211_is_bufferable_mmpdu - check if frame is bufferable MMPDU
  * @fc: frame control field in little-endian byteorder
  */
@@ -2016,7 +2025,7 @@ ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info)
 }
 
 /* HE Operation defines */
-#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK		0x00000003
+#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK		0x00000007
 #define IEEE80211_HE_OPERATION_TWT_REQUIRED			0x00000008
 #define IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK		0x00003ff0
 #define IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET		4
diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h
index 76cf11e905e1..8a9792a6427a 100644
--- a/include/linux/if_ether.h
+++ b/include/linux/if_ether.h
@@ -24,6 +24,14 @@ static inline struct ethhdr *eth_hdr(const struct sk_buff *skb)
 	return (struct ethhdr *)skb_mac_header(skb);
 }
 
+/* Prefer this version in TX path, instead of
+ * skb_reset_mac_header() + eth_hdr()
+ */
+static inline struct ethhdr *skb_eth_hdr(const struct sk_buff *skb)
+{
+	return (struct ethhdr *)skb->data;
+}
+
 static inline struct ethhdr *inner_eth_hdr(const struct sk_buff *skb)
 {
 	return (struct ethhdr *)skb_inner_mac_header(skb);
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 244278d5c222..077e74daf19a 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -25,6 +25,8 @@
 #define VLAN_ETH_DATA_LEN	1500	/* Max. octets in payload	 */
 #define VLAN_ETH_FRAME_LEN	1518	/* Max. octets in frame sans FCS */
 
+#define VLAN_MAX_DEPTH	8		/* Max. number of nested VLAN tags parsed */
+
 /*
  * 	struct vlan_hdr - vlan header
  * 	@h_vlan_TCI: priority and VLAN ID
@@ -588,10 +590,10 @@ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci)
  * Returns the EtherType of the packet, regardless of whether it is
  * vlan encapsulated (normal or hardware accelerated) or not.
  */
-static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type,
+static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type,
 					 int *depth)
 {
-	unsigned int vlan_depth = skb->mac_len;
+	unsigned int vlan_depth = skb->mac_len, parse_depth = VLAN_MAX_DEPTH;
 
 	/* if type is 802.1Q/AD then the header should already be
 	 * present at mac_len - VLAN_HLEN (if mac_len > 0), or at
@@ -606,13 +608,12 @@ static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type,
 			vlan_depth = ETH_HLEN;
 		}
 		do {
-			struct vlan_hdr *vh;
+			struct vlan_hdr vhdr, *vh;
 
-			if (unlikely(!pskb_may_pull(skb,
-						    vlan_depth + VLAN_HLEN)))
+			vh = skb_header_pointer(skb, vlan_depth, sizeof(vhdr), &vhdr);
+			if (unlikely(!vh || !--parse_depth))
 				return 0;
 
-			vh = (struct vlan_hdr *)(skb->data + vlan_depth);
 			type = vh->h_vlan_encapsulated_proto;
 			vlan_depth += VLAN_HLEN;
 		} while (eth_type_vlan(type));
@@ -631,11 +632,25 @@ static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type,
  * Returns the EtherType of the packet, regardless of whether it is
  * vlan encapsulated (normal or hardware accelerated) or not.
  */
-static inline __be16 vlan_get_protocol(struct sk_buff *skb)
+static inline __be16 vlan_get_protocol(const struct sk_buff *skb)
 {
 	return __vlan_get_protocol(skb, skb->protocol, NULL);
 }
 
+/* A getter for the SKB protocol field which will handle VLAN tags consistently
+ * whether VLAN acceleration is enabled or not.
+ */
+static inline __be16 skb_protocol(const struct sk_buff *skb, bool skip_vlan)
+{
+	if (!skip_vlan)
+		/* VLAN acceleration strips the VLAN header from the skb and
+		 * moves it to skb->vlan_proto
+		 */
+		return skb_vlan_tag_present(skb) ? skb->vlan_proto : skb->protocol;
+
+	return vlan_get_protocol(skb);
+}
+
 static inline void vlan_set_encap_proto(struct sk_buff *skb,
 					struct vlan_hdr *vhdr)
 {
diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index 8e132cf819e4..e5341847e3a0 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -596,7 +596,7 @@ void iio_device_unregister(struct iio_dev *indio_dev);
  * 0 on success, negative error number on failure.
  */
 #define devm_iio_device_register(dev, indio_dev) \
-	__devm_iio_device_register((dev), (indio_dev), THIS_MODULE);
+	__devm_iio_device_register((dev), (indio_dev), THIS_MODULE)
 int __devm_iio_device_register(struct device *dev, struct iio_dev *indio_dev,
 			       struct module *this_mod);
 void devm_iio_device_unregister(struct device *dev, struct iio_dev *indio_dev);
diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h
index 39faaaf843e1..c91cf2dee12a 100644
--- a/include/linux/inet_diag.h
+++ b/include/linux/inet_diag.h
@@ -2,15 +2,10 @@
 #ifndef _INET_DIAG_H_
 #define _INET_DIAG_H_ 1
 
+#include <net/netlink.h>
 #include <uapi/linux/inet_diag.h>
 
-struct net;
-struct sock;
 struct inet_hashinfo;
-struct nlattr;
-struct nlmsghdr;
-struct sk_buff;
-struct netlink_callback;
 
 struct inet_diag_handler {
 	void		(*dump)(struct sk_buff *skb,
@@ -62,6 +57,17 @@ int inet_diag_bc_sk(const struct nlattr *_bc, struct sock *sk);
 
 void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk);
 
+static inline size_t inet_diag_msg_attrs_size(void)
+{
+	return	  nla_total_size(1)  /* INET_DIAG_SHUTDOWN */
+		+ nla_total_size(1)  /* INET_DIAG_TOS */
+#if IS_ENABLED(CONFIG_IPV6)
+		+ nla_total_size(1)  /* INET_DIAG_TCLASS */
+		+ nla_total_size(1)  /* INET_DIAG_SKV6ONLY */
+#endif
+		+ nla_total_size(4)  /* INET_DIAG_MARK */
+		+ nla_total_size(4); /* INET_DIAG_CLASS_ID */
+}
 int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 			     struct inet_diag_msg *r, int ext,
 			     struct user_namespace *user_ns, bool net_admin);
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 1a1f77f77c0e..5f943486e405 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -120,6 +120,8 @@
 
 #define dmar_readq(a) readq(a)
 #define dmar_writeq(a,v) writeq(v,a)
+#define dmar_readl(a) readl(a)
+#define dmar_writel(a, v) writel(v, a)
 
 #define DMAR_VER_MAJOR(v)		(((v) & 0xf0) >> 4)
 #define DMAR_VER_MINOR(v)		((v) & 0x0f)
@@ -355,8 +357,8 @@ enum {
 
 #define QI_DEV_EIOTLB_ADDR(a)	((u64)(a) & VTD_PAGE_MASK)
 #define QI_DEV_EIOTLB_SIZE	(((u64)1) << 11)
-#define QI_DEV_EIOTLB_GLOB(g)	((u64)g)
-#define QI_DEV_EIOTLB_PASID(p)	(((u64)p) << 32)
+#define QI_DEV_EIOTLB_GLOB(g)	((u64)(g) & 0x1)
+#define QI_DEV_EIOTLB_PASID(p)	((u64)((p) & 0xfffff) << 32)
 #define QI_DEV_EIOTLB_SID(sid)	((u64)((sid) & 0xffff) << 16)
 #define QI_DEV_EIOTLB_QDEP(qd)	((u64)((qd) & 0x1f) << 4)
 #define QI_DEV_EIOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | \
diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h
index 54ffcc6a322e..cb0e8ee7eca4 100644
--- a/include/linux/intel-svm.h
+++ b/include/linux/intel-svm.h
@@ -122,7 +122,7 @@ static inline int intel_svm_unbind_mm(struct device *dev, int pasid)
 	BUG();
 }
 
-static int intel_svm_is_pasid_valid(struct device *dev, int pasid)
+static inline int intel_svm_is_pasid_valid(struct device *dev, int pasid)
 {
 	return -EINVAL;
 }
diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h
index 6e125e9b4187..b9c91d321240 100644
--- a/include/linux/io-mapping.h
+++ b/include/linux/io-mapping.h
@@ -108,9 +108,12 @@ io_mapping_init_wc(struct io_mapping *iomap,
 		   resource_size_t base,
 		   unsigned long size)
 {
+	iomap->iomem = ioremap_wc(base, size);
+	if (!iomap->iomem)
+		return NULL;
+
 	iomap->base = base;
 	iomap->size = size;
-	iomap->iomem = ioremap_wc(base, size);
 #if defined(pgprot_noncached_wc) /* archs can't agree on a name ... */
 	iomap->prot = pgprot_noncached_wc(PAGE_KERNEL);
 #elif defined(pgprot_writecombine)
diff --git a/include/linux/io.h b/include/linux/io.h
index 9876e5801a9d..715f41dbe315 100644
--- a/include/linux/io.h
+++ b/include/linux/io.h
@@ -63,6 +63,8 @@ static inline void devm_ioport_unmap(struct device *dev, void __iomem *addr)
 
 void __iomem *devm_ioremap(struct device *dev, resource_size_t offset,
 			   resource_size_t size);
+void __iomem *devm_ioremap_uc(struct device *dev, resource_size_t offset,
+				   resource_size_t size);
 void __iomem *devm_ioremap_nocache(struct device *dev, resource_size_t offset,
 				   resource_size_t size);
 void __iomem *devm_ioremap_wc(struct device *dev, resource_size_t offset,
diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h
index dba15ca8e60b..1dcd9198beb7 100644
--- a/include/linux/iocontext.h
+++ b/include/linux/iocontext.h
@@ -8,6 +8,7 @@
 
 enum {
 	ICQ_EXITED		= 1 << 2,
+	ICQ_DESTROYED		= 1 << 3,
 };
 
 /*
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 2103b94cb1bf..1df9ea187a9a 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -35,6 +35,7 @@ struct vm_fault;
 #define IOMAP_F_NEW		0x01	/* blocks have been newly allocated */
 #define IOMAP_F_DIRTY		0x02	/* uncommitted metadata */
 #define IOMAP_F_BUFFER_HEAD	0x04	/* file system requires buffer heads */
+#define IOMAP_F_SIZE_CHANGED	0x08	/* file size has changed */
 
 /*
  * Flags that only need to be reported for IOMAP_REPORT requests:
diff --git a/include/linux/irq.h b/include/linux/irq.h
index fb301cf29148..8060a53805a0 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -209,6 +209,12 @@ struct irq_data {
  * IRQD_SINGLE_TARGET		- IRQ allows only a single affinity target
  * IRQD_DEFAULT_TRIGGER_SET	- Expected trigger already been set
  * IRQD_CAN_RESERVE		- Can use reservation mode
+ * IRQD_MSI_NOMASK_QUIRK	- Non-maskable MSI quirk for affinity change
+ *				  required
+ * IRQD_HANDLE_ENFORCE_IRQCTX	- Enforce that handle_irq_*() is only invoked
+ *				  from actual interrupt context.
+ * IRQD_AFFINITY_ON_ACTIVATE	- Affinity is set on activation. Don't call
+ *				  irq_chip::irq_set_affinity() when deactivated.
  */
 enum {
 	IRQD_TRIGGER_MASK		= 0xf,
@@ -231,6 +237,9 @@ enum {
 	IRQD_SINGLE_TARGET		= (1 << 24),
 	IRQD_DEFAULT_TRIGGER_SET	= (1 << 25),
 	IRQD_CAN_RESERVE		= (1 << 26),
+	IRQD_MSI_NOMASK_QUIRK		= (1 << 27),
+	IRQD_HANDLE_ENFORCE_IRQCTX	= (1 << 28),
+	IRQD_AFFINITY_ON_ACTIVATE	= (1 << 29),
 };
 
 #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors)
@@ -300,6 +309,16 @@ static inline bool irqd_is_single_target(struct irq_data *d)
 	return __irqd_to_state(d) & IRQD_SINGLE_TARGET;
 }
 
+static inline void irqd_set_handle_enforce_irqctx(struct irq_data *d)
+{
+	__irqd_to_state(d) |= IRQD_HANDLE_ENFORCE_IRQCTX;
+}
+
+static inline bool irqd_is_handle_enforce_irqctx(struct irq_data *d)
+{
+	return __irqd_to_state(d) & IRQD_HANDLE_ENFORCE_IRQCTX;
+}
+
 static inline bool irqd_is_wakeup_set(struct irq_data *d)
 {
 	return __irqd_to_state(d) & IRQD_WAKEUP_STATE;
@@ -390,6 +409,31 @@ static inline bool irqd_can_reserve(struct irq_data *d)
 	return __irqd_to_state(d) & IRQD_CAN_RESERVE;
 }
 
+static inline void irqd_set_msi_nomask_quirk(struct irq_data *d)
+{
+	__irqd_to_state(d) |= IRQD_MSI_NOMASK_QUIRK;
+}
+
+static inline void irqd_clr_msi_nomask_quirk(struct irq_data *d)
+{
+	__irqd_to_state(d) &= ~IRQD_MSI_NOMASK_QUIRK;
+}
+
+static inline bool irqd_msi_nomask_quirk(struct irq_data *d)
+{
+	return __irqd_to_state(d) & IRQD_MSI_NOMASK_QUIRK;
+}
+
+static inline void irqd_set_affinity_on_activate(struct irq_data *d)
+{
+	__irqd_to_state(d) |= IRQD_AFFINITY_ON_ACTIVATE;
+}
+
+static inline bool irqd_affinity_on_activate(struct irq_data *d)
+{
+	return __irqd_to_state(d) & IRQD_AFFINITY_ON_ACTIVATE;
+}
+
 #undef __irqd_to_state
 
 static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 07ec8b390161..5495bc4582c1 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -191,7 +191,7 @@ enum {
 	IRQ_DOMAIN_FLAG_HIERARCHY	= (1 << 0),
 
 	/* Irq domain name was allocated in __irq_domain_add() */
-	IRQ_DOMAIN_NAME_ALLOCATED	= (1 << 6),
+	IRQ_DOMAIN_NAME_ALLOCATED	= (1 << 1),
 
 	/* Irq domain is an IPI domain with virq per cpu */
 	IRQ_DOMAIN_FLAG_IPI_PER_CPU	= (1 << 2),
@@ -206,6 +206,13 @@ enum {
 	IRQ_DOMAIN_FLAG_MSI_REMAP	= (1 << 5),
 
 	/*
+	 * Quirk to handle MSI implementations which do not provide
+	 * masking. Currently known to affect x86, but partially
+	 * handled in core code.
+	 */
+	IRQ_DOMAIN_MSI_NOMASK_QUIRK	= (1 << 6),
+
+	/*
 	 * Flags starting from IRQ_DOMAIN_FLAG_NONCORE are reserved
 	 * for implementation specific purposes and ignored by the
 	 * core code.
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 3fcb2fe739d0..cbf045e091f1 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1403,7 +1403,6 @@ extern int	   jbd2_journal_skip_recovery	(journal_t *);
 extern void	   jbd2_journal_update_sb_errno(journal_t *);
 extern int	   jbd2_journal_update_sb_log_tail	(journal_t *, tid_t,
 				unsigned long, int);
-extern void	   __jbd2_journal_abort_hard	(journal_t *);
 extern void	   jbd2_journal_abort      (journal_t *, int);
 extern int	   jbd2_journal_errno      (journal_t *);
 extern void	   jbd2_journal_ack_err    (journal_t *);
diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h
index 657a83b943f0..1f96ce2b47df 100644
--- a/include/linux/kallsyms.h
+++ b/include/linux/kallsyms.h
@@ -18,6 +18,7 @@
 #define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s]") + (KSYM_NAME_LEN - 1) + \
 			 2*(BITS_PER_LONG*3/10) + (MODULE_NAME_LEN - 1) + 1)
 
+struct cred;
 struct module;
 
 static inline int is_kernel_inittext(unsigned long addr)
@@ -98,7 +99,7 @@ int lookup_symbol_name(unsigned long addr, char *symname);
 int lookup_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name);
 
 /* How and when do we show kallsyms values? */
-extern int kallsyms_show_value(void);
+extern bool kallsyms_show_value(const struct cred *cred);
 
 #else /* !CONFIG_KALLSYMS */
 
@@ -158,7 +159,7 @@ static inline int lookup_symbol_attrs(unsigned long addr, unsigned long *size, u
 	return -ERANGE;
 }
 
-static inline int kallsyms_show_value(void)
+static inline bool kallsyms_show_value(const struct cred *cred)
 {
 	return false;
 }
diff --git a/include/linux/key-type.h b/include/linux/key-type.h
index 331cab70db09..0b0b8fa9d62f 100644
--- a/include/linux/key-type.h
+++ b/include/linux/key-type.h
@@ -124,7 +124,7 @@ struct key_type {
 	 *   much is copied into the buffer
 	 * - shouldn't do the copy if the buffer is NULL
 	 */
-	long (*read)(const struct key *key, char __user *buffer, size_t buflen);
+	long (*read)(const struct key *key, char *buffer, size_t buflen);
 
 	/* handle request_key() for this type instead of invoking
 	 * /sbin/request-key (optional)
diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h
index fbf144aaa749..011152258bef 100644
--- a/include/linux/kgdb.h
+++ b/include/linux/kgdb.h
@@ -323,7 +323,7 @@ extern void gdbstub_exit(int status);
 extern int			kgdb_single_step;
 extern atomic_t			kgdb_active;
 #define in_dbg_master() \
-	(raw_smp_processor_id() == atomic_read(&kgdb_active))
+	(irqs_disabled() && (smp_processor_id() == atomic_read(&kgdb_active)))
 extern bool dbg_is_early;
 extern void __init dbg_late_init(void);
 #else /* ! CONFIG_KGDB */
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 443d9800ca3f..1fa574fd485e 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -350,6 +350,10 @@ static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void)
 	return this_cpu_ptr(&kprobe_ctlblk);
 }
 
+extern struct kprobe kprobe_busy;
+void kprobe_busy_begin(void);
+void kprobe_busy_end(void);
+
 kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset);
 int register_kprobe(struct kprobe *p);
 void unregister_kprobe(struct kprobe *p);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index b79ea2e46a1c..f3f86a7f36ec 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -204,7 +204,7 @@ struct kvm_async_pf {
 	struct list_head queue;
 	struct kvm_vcpu *vcpu;
 	struct mm_struct *mm;
-	gva_t gva;
+	gpa_t cr2_or_gpa;
 	unsigned long addr;
 	struct kvm_arch_async_pf arch;
 	bool   wakeup_all;
@@ -212,8 +212,8 @@ struct kvm_async_pf {
 
 void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu);
 void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu);
-int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
-		       struct kvm_arch_async_pf *arch);
+int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+		       unsigned long hva, struct kvm_arch_async_pf *arch);
 int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
 #endif
 
@@ -750,7 +750,7 @@ int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len);
 int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len);
 struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
 bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn);
-unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn);
+unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn);
 void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
 
 struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu);
@@ -1024,7 +1024,7 @@ search_memslots(struct kvm_memslots *slots, gfn_t gfn)
 			start = slot + 1;
 	}
 
-	if (gfn >= memslots[start].base_gfn &&
+	if (start < slots->used_slots && gfn >= memslots[start].base_gfn &&
 	    gfn < memslots[start].base_gfn + memslots[start].npages) {
 		atomic_set(&slots->lru_slot, start);
 		return &memslots[start];
@@ -1373,8 +1373,8 @@ static inline long kvm_arch_vcpu_async_ioctl(struct file *filp,
 }
 #endif /* CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL */
 
-int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
-		unsigned long start, unsigned long end, bool blockable);
+void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
+					    unsigned long start, unsigned long end);
 
 #ifdef CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE
 int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu);
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 207e7ee764ce..b9970f5bab67 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -22,6 +22,7 @@
 #include <linux/acpi.h>
 #include <linux/cdrom.h>
 #include <linux/sched.h>
+#include <linux/async.h>
 
 /*
  * Define if arch has non-standard setup.  This is a _PCI_ standard
@@ -870,6 +871,8 @@ struct ata_port {
 	struct timer_list	fastdrain_timer;
 	unsigned long		fastdrain_cnt;
 
+	async_cookie_t		cookie;
+
 	int			em_message_type;
 	void			*private_data;
 
@@ -1174,6 +1177,7 @@ extern unsigned int ata_do_dev_read_id(struct ata_device *dev,
 					struct ata_taskfile *tf, u16 *id);
 extern void ata_qc_complete(struct ata_queued_cmd *qc);
 extern int ata_qc_complete_multiple(struct ata_port *ap, u64 qc_active);
+extern u64 ata_qc_get_active(struct ata_port *ap);
 extern void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd);
 extern int ata_std_bios_param(struct scsi_device *sdev,
 			      struct block_device *bdev,
@@ -1219,6 +1223,7 @@ struct pci_bits {
 };
 
 extern int pci_test_config_bits(struct pci_dev *pdev, const struct pci_bits *bits);
+extern void ata_pci_shutdown_one(struct pci_dev *pdev);
 extern void ata_pci_remove_one(struct pci_dev *pdev);
 
 #ifdef CONFIG_PM
diff --git a/include/linux/list_nulls.h b/include/linux/list_nulls.h
index 3ef96743db8d..1ecd35664e0d 100644
--- a/include/linux/list_nulls.h
+++ b/include/linux/list_nulls.h
@@ -72,10 +72,10 @@ static inline void hlist_nulls_add_head(struct hlist_nulls_node *n,
 	struct hlist_nulls_node *first = h->first;
 
 	n->next = first;
-	n->pprev = &h->first;
+	WRITE_ONCE(n->pprev, &h->first);
 	h->first = n;
 	if (!is_a_nulls(first))
-		first->pprev = &n->next;
+		WRITE_ONCE(first->pprev, &n->next);
 }
 
 static inline void __hlist_nulls_del(struct hlist_nulls_node *n)
@@ -85,13 +85,13 @@ static inline void __hlist_nulls_del(struct hlist_nulls_node *n)
 
 	WRITE_ONCE(*pprev, next);
 	if (!is_a_nulls(next))
-		next->pprev = pprev;
+		WRITE_ONCE(next->pprev, pprev);
 }
 
 static inline void hlist_nulls_del(struct hlist_nulls_node *n)
 {
 	__hlist_nulls_del(n);
-	n->pprev = LIST_POISON2;
+	WRITE_ONCE(n->pprev, LIST_POISON2);
 }
 
 /**
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 1dcb763bb610..776a377d13de 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -751,6 +751,8 @@ static inline void memcg_memory_event(struct mem_cgroup *memcg,
 		atomic_long_inc(&memcg->memory_events[event]);
 		cgroup_file_notify(&memcg->events_file);
 
+		if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
+			break;
 		if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS)
 			break;
 	} while ((memcg = parent_mem_cgroup(memcg)) &&
diff --git a/include/linux/mfd/stmfx.h b/include/linux/mfd/stmfx.h
index d890595b89b6..744dce63946e 100644
--- a/include/linux/mfd/stmfx.h
+++ b/include/linux/mfd/stmfx.h
@@ -5,7 +5,7 @@
  */
 
 #ifndef MFD_STMFX_H
-#define MFX_STMFX_H
+#define MFD_STMFX_H
 
 #include <linux/regmap.h>
 
@@ -109,6 +109,7 @@ struct stmfx {
 	struct device *dev;
 	struct regmap *map;
 	struct regulator *vdd;
+	int irq;
 	struct irq_domain *irq_domain;
 	struct mutex lock; /* IRQ bus lock */
 	u8 irq_src;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 5a27246db883..586171ba5bd7 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -727,6 +727,7 @@ struct mlx5_cmd_work_ent {
 	struct delayed_work	cb_timeout_work;
 	void		       *context;
 	int			idx;
+	struct completion	handling;
 	struct completion	done;
 	struct mlx5_cmd        *cmd;
 	struct work_struct	work;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 0eeac3466851..9310a7e1057b 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -750,7 +750,13 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits {
 	u8         swp_csum[0x1];
 	u8         swp_lso[0x1];
 	u8         cqe_checksum_full[0x1];
-	u8         reserved_at_24[0xc];
+	u8         tunnel_stateless_geneve_tx[0x1];
+	u8         tunnel_stateless_mpls_over_udp[0x1];
+	u8         tunnel_stateless_mpls_over_gre[0x1];
+	u8         tunnel_stateless_vxlan_gpe[0x1];
+	u8         tunnel_stateless_ipv4_over_vxlan[0x1];
+	u8         tunnel_stateless_ip_over_ip[0x1];
+	u8         reserved_at_2a[0x6];
 	u8         max_vxlan_udp_ports[0x8];
 	u8         reserved_at_38[0x6];
 	u8         max_geneve_opt_len[0x1];
@@ -3923,6 +3929,7 @@ struct mlx5_ifc_query_vport_state_out_bits {
 enum {
 	MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT  = 0x0,
 	MLX5_VPORT_STATE_OP_MOD_ESW_VPORT   = 0x1,
+	MLX5_VPORT_STATE_OP_MOD_UPLINK      = 0x2,
 };
 
 struct mlx5_ifc_arm_monitor_counter_in_bits {
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 14aee8b128a6..c4f0864be4df 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -677,7 +677,13 @@ static inline void *kvcalloc(size_t n, size_t size, gfp_t flags)
 }
 
 extern void kvfree(const void *addr);
+extern void kvfree_sensitive(const void *addr, size_t len);
 
+/*
+ * Mapcount of compound page as a whole, does not include mapped sub-pages.
+ *
+ * Must be called only for compound pages or any their tail sub-pages.
+ */
 static inline int compound_mapcount(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
@@ -697,10 +703,16 @@ static inline void page_mapcount_reset(struct page *page)
 
 int __page_mapcount(struct page *page);
 
+/*
+ * Mapcount of 0-order page; when compound sub-page, includes
+ * compound_mapcount().
+ *
+ * Result is undefined for pages which cannot be mapped into userspace.
+ * For example SLAB or special types of pages. See function page_has_type().
+ * They use this place in struct page differently.
+ */
 static inline int page_mapcount(struct page *page)
 {
-	VM_BUG_ON_PAGE(PageSlab(page), page);
-
 	if (unlikely(PageCompound(page)))
 		return __page_mapcount(page);
 	return atomic_read(&page->_mapcount) + 1;
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 56a8ad506072..4a4a64834d8e 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -332,6 +332,7 @@ struct mmc_host {
 				 MMC_CAP_UHS_SDR50 | MMC_CAP_UHS_SDR104 | \
 				 MMC_CAP_UHS_DDR50)
 #define MMC_CAP_SYNC_RUNTIME_PM	(1 << 21)	/* Synced runtime PM suspends. */
+#define MMC_CAP_NEED_RSP_BUSY	(1 << 22)	/* Commands with R1B can't use R1. */
 #define MMC_CAP_DRIVER_TYPE_A	(1 << 23)	/* Host supports Driver Type A */
 #define MMC_CAP_DRIVER_TYPE_C	(1 << 24)	/* Host supports Driver Type C */
 #define MMC_CAP_DRIVER_TYPE_D	(1 << 25)	/* Host supports Driver Type D */
diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h
index d1a5d5df02f5..08b25c02b5a1 100644
--- a/include/linux/mmc/sdio_ids.h
+++ b/include/linux/mmc/sdio_ids.h
@@ -71,6 +71,8 @@
 
 #define SDIO_VENDOR_ID_TI			0x0097
 #define SDIO_DEVICE_ID_TI_WL1271		0x4076
+#define SDIO_VENDOR_ID_TI_WL1251		0x104c
+#define SDIO_DEVICE_ID_TI_WL1251		0x9066
 
 #define SDIO_VENDOR_ID_STE			0x0020
 #define SDIO_DEVICE_ID_STE_CW1200		0x2280
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 70394cabaf4e..5f370f1525c4 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -699,6 +699,8 @@ typedef struct pglist_data {
 	/*
 	 * Must be held any time you expect node_start_pfn,
 	 * node_present_pages, node_spanned_pages or nr_zones to stay constant.
+	 * Also synchronizes pgdat->first_deferred_pfn during deferred page
+	 * init.
 	 *
 	 * pgdat_resize_lock() and pgdat_resize_unlock() are provided to
 	 * manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 770d9da3f300..5f6eb23644b3 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -299,7 +299,7 @@ struct pcmcia_device_id {
 #define INPUT_DEVICE_ID_LED_MAX		0x0f
 #define INPUT_DEVICE_ID_SND_MAX		0x07
 #define INPUT_DEVICE_ID_FF_MAX		0x7f
-#define INPUT_DEVICE_ID_SW_MAX		0x0f
+#define INPUT_DEVICE_ID_SW_MAX		0x10
 #define INPUT_DEVICE_ID_PROP_MAX	0x1f
 
 #define INPUT_DEVICE_ID_MATCH_BUS	1
@@ -638,6 +638,10 @@ struct mips_cdmm_device_id {
 /*
  * MODULE_DEVICE_TABLE expects this struct to be called x86cpu_device_id.
  * Although gcc seems to ignore this error, clang fails without this define.
+ *
+ * Note: The ordering of the struct is different from upstream because the
+ * static initializers in kernels < 5.7 still use C89 style while upstream
+ * has been converted to proper C99 initializers.
  */
 #define x86cpu_device_id x86_cpu_id
 struct x86_cpu_id {
@@ -646,6 +650,7 @@ struct x86_cpu_id {
 	__u16 model;
 	__u16 feature;	/* bit index */
 	kernel_ulong_t driver_data;
+	__u16 steppings;
 };
 
 #define X86_FEATURE_MATCH(x) \
@@ -654,6 +659,7 @@ struct x86_cpu_id {
 #define X86_VENDOR_ANY 0xffff
 #define X86_FAMILY_ANY 0
 #define X86_MODEL_ANY  0
+#define X86_STEPPING_ANY 0
 #define X86_FEATURE_ANY 0	/* Same as FPU, you can't test for that */
 
 /*
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index de025c0585ca..dea5837640ca 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -72,6 +72,8 @@ void netdev_set_default_ethtool_ops(struct net_device *dev,
 #define NET_RX_SUCCESS		0	/* keep 'em coming, baby */
 #define NET_RX_DROP		1	/* packet dropped */
 
+#define MAX_NEST_DEV 8
+
 /*
  * Transmit return codes: transmit return codes originate from three different
  * namespaces:
@@ -1636,6 +1638,8 @@ enum netdev_priv_flags {
  * 	@perm_addr:		Permanent hw address
  * 	@addr_assign_type:	Hw address assignment type
  * 	@addr_len:		Hardware address length
+ *	@upper_level:		Maximum depth level of upper devices.
+ *	@lower_level:		Maximum depth level of lower devices.
  *	@neigh_priv_len:	Used in neigh_alloc()
  * 	@dev_id:		Used to differentiate devices that share
  * 				the same link layer address
@@ -1867,6 +1871,8 @@ struct net_device {
 	unsigned char		perm_addr[MAX_ADDR_LEN];
 	unsigned char		addr_assign_type;
 	unsigned char		addr_len;
+	unsigned char		upper_level;
+	unsigned char		lower_level;
 	unsigned short		neigh_priv_len;
 	unsigned short          dev_id;
 	unsigned short          dev_port;
@@ -3035,7 +3041,7 @@ static inline int dev_recursion_level(void)
 	return this_cpu_read(softnet_data.xmit.recursion);
 }
 
-#define XMIT_RECURSION_LIMIT	10
+#define XMIT_RECURSION_LIMIT	8
 static inline bool dev_xmit_recursion(void)
 {
 	return unlikely(__this_cpu_read(softnet_data.xmit.recursion) >
@@ -3659,6 +3665,8 @@ int dev_set_alias(struct net_device *, const char *, size_t);
 int dev_get_alias(const struct net_device *, char *, size_t);
 int dev_change_net_namespace(struct net_device *, struct net *, const char *);
 int __dev_set_mtu(struct net_device *, int);
+int dev_validate_mtu(struct net_device *dev, int mtu,
+		     struct netlink_ext_ack *extack);
 int dev_set_mtu_ext(struct net_device *dev, int mtu,
 		    struct netlink_ext_ack *extack);
 int dev_set_mtu(struct net_device *, int);
@@ -4294,11 +4302,8 @@ void *netdev_lower_get_next(struct net_device *dev,
 	     ldev; \
 	     ldev = netdev_lower_get_next(dev, &(iter)))
 
-struct net_device *netdev_all_lower_get_next(struct net_device *dev,
+struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
 					     struct list_head **iter);
-struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev,
-						 struct list_head **iter);
-
 int netdev_walk_all_lower_dev(struct net_device *dev,
 			      int (*fn)(struct net_device *lower_dev,
 					void *data),
diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index f5e03809cdb2..a70ee7e323dc 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -121,6 +121,7 @@ struct ip_set_ext {
 	u32 timeout;
 	u8 packets_op;
 	u8 bytes_op;
+	bool target;
 };
 
 struct ip_set;
@@ -187,6 +188,14 @@ struct ip_set_type_variant {
 	/* Return true if "b" set is the same as "a"
 	 * according to the create set parameters */
 	bool (*same_set)(const struct ip_set *a, const struct ip_set *b);
+	/* Region-locking is used */
+	bool region_lock;
+};
+
+struct ip_set_region {
+	spinlock_t lock;	/* Region lock */
+	size_t ext_size;	/* Size of the dynamic extensions */
+	u32 elements;		/* Number of elements vs timeout */
 };
 
 /* The core set type structure */
@@ -445,20 +454,13 @@ ip6addrptr(const struct sk_buff *skb, bool src, struct in6_addr *addr)
 	       sizeof(*addr));
 }
 
-/* Calculate the bytes required to store the inclusive range of a-b */
-static inline int
-bitmap_bytes(u32 a, u32 b)
-{
-	return 4 * ((((b - a + 8) / 8) + 3) / 4);
-}
-
 #include <linux/netfilter/ipset/ip_set_timeout.h>
 #include <linux/netfilter/ipset/ip_set_comment.h>
 #include <linux/netfilter/ipset/ip_set_counter.h>
 #include <linux/netfilter/ipset/ip_set_skbinfo.h>
 
 #define IP_SET_INIT_KEXT(skb, opt, set)			\
-	{ .bytes = (skb)->len, .packets = 1,		\
+	{ .bytes = (skb)->len, .packets = 1, .target = true,\
 	  .timeout = ip_set_adt_opt_timeout(opt, set) }
 
 #define IP_SET_INIT_UEXT(set)				\
diff --git a/include/linux/netfilter/nf_conntrack_pptp.h b/include/linux/netfilter/nf_conntrack_pptp.h
index 833a5b2255ea..ade993809ebc 100644
--- a/include/linux/netfilter/nf_conntrack_pptp.h
+++ b/include/linux/netfilter/nf_conntrack_pptp.h
@@ -5,7 +5,7 @@
 
 #include <linux/netfilter/nf_conntrack_common.h>
 
-extern const char *const pptp_msg_name[];
+const char *pptp_msg_name(u_int16_t msg);
 
 /* state of the control session */
 enum pptp_ctrlsess_state {
diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
index cf09ab37b45b..851425c3178f 100644
--- a/include/linux/netfilter/nfnetlink.h
+++ b/include/linux/netfilter/nfnetlink.h
@@ -31,7 +31,7 @@ struct nfnetlink_subsystem {
 	const struct nfnl_callback *cb;	/* callback for individual types */
 	struct module *owner;
 	int (*commit)(struct net *net, struct sk_buff *skb);
-	int (*abort)(struct net *net, struct sk_buff *skb);
+	int (*abort)(struct net *net, struct sk_buff *skb, bool autoload);
 	void (*cleanup)(struct net *net);
 	bool (*valid_genid)(struct net *net, u32 genid);
 };
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index d363d5765cdf..cb66d2d53d6a 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -223,6 +223,7 @@ struct nfs4_copy_state {
 #define NFS_INO_INVALID_MTIME	BIT(10)		/* cached mtime is invalid */
 #define NFS_INO_INVALID_SIZE	BIT(11)		/* cached size is invalid */
 #define NFS_INO_INVALID_OTHER	BIT(12)		/* other attrs are invalid */
+#define NFS_INO_INVALID_BLOCKS	BIT(14)         /* cached blocks are invalid */
 
 #define NFS_INO_INVALID_ATTR	(NFS_INO_INVALID_CHANGE \
 		| NFS_INO_INVALID_CTIME \
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index f013c20b1046..06cd135a2958 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1307,11 +1307,13 @@ struct nfs41_impl_id {
 	struct nfstime4			date;
 };
 
+#define MAX_BIND_CONN_TO_SESSION_RETRIES 3
 struct nfs41_bind_conn_to_session_args {
 	struct nfs_client		*client;
 	struct nfs4_sessionid		sessionid;
 	u32				dir;
 	bool				use_conn_in_rdma_mode;
+	int				retries;
 };
 
 struct nfs41_bind_conn_to_session_res {
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index fd6549160f2c..38d458882319 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -309,7 +309,7 @@ static inline int TestClearPage##uname(struct page *page) { return 0; }
 
 __PAGEFLAG(Locked, locked, PF_NO_TAIL)
 PAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) __CLEARPAGEFLAG(Waiters, waiters, PF_ONLY_HEAD)
-PAGEFLAG(Error, error, PF_NO_COMPOUND) TESTCLEARFLAG(Error, error, PF_NO_COMPOUND)
+PAGEFLAG(Error, error, PF_NO_TAIL) TESTCLEARFLAG(Error, error, PF_NO_TAIL)
 PAGEFLAG(Referenced, referenced, PF_HEAD)
 	TESTCLEARFLAG(Referenced, referenced, PF_HEAD)
 	__SETPAGEFLAG(Referenced, referenced, PF_HEAD)
diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h
index f641badc2c61..0c12d69dde92 100644
--- a/include/linux/pci-epc.h
+++ b/include/linux/pci-epc.h
@@ -71,6 +71,7 @@ struct pci_epc_ops {
  * @bitmap: bitmap to manage the PCI address space
  * @pages: number of bits representing the address region
  * @page_size: size of each page
+ * @lock: mutex to protect bitmap
  */
 struct pci_epc_mem {
 	phys_addr_t	phys_base;
@@ -78,6 +79,8 @@ struct pci_epc_mem {
 	unsigned long	*bitmap;
 	size_t		page_size;
 	int		pages;
+	/* mutex to protect against concurrent access for memory allocation*/
+	struct mutex	lock;
 };
 
 /**
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 9feb59ac8550..645fc611d910 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -2288,9 +2288,11 @@ struct irq_domain *pci_host_bridge_acpi_msi_domain(struct pci_bus *bus);
 
 void
 pci_msi_register_fwnode_provider(struct fwnode_handle *(*fn)(struct device *));
+bool pci_pr3_present(struct pci_dev *pdev);
 #else
 static inline struct irq_domain *
 pci_host_bridge_acpi_msi_domain(struct pci_bus *bus) { return NULL; }
+static inline bool pci_pr3_present(struct pci_dev *pdev) { return false; }
 #endif
 
 #ifdef CONFIG_EEH
@@ -2300,7 +2302,7 @@ static inline struct eeh_dev *pci_dev_to_eeh_dev(struct pci_dev *pdev)
 }
 #endif
 
-void pci_add_dma_alias(struct pci_dev *dev, u8 devfn);
+void pci_add_dma_alias(struct pci_dev *dev, u8 devfn_from, unsigned nr_devfns);
 bool pci_devs_are_dma_aliases(struct pci_dev *dev1, struct pci_dev *dev2);
 int pci_for_each_dma_alias(struct pci_dev *pdev,
 			   int (*fn)(struct pci_dev *pdev,
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 862556761bbf..118495e7149e 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -148,6 +148,8 @@
 
 /* Vendors and devices.  Sort key: vendor first, device next. */
 
+#define PCI_VENDOR_ID_LOONGSON		0x0014
+
 #define PCI_VENDOR_ID_TTTECH		0x0357
 #define PCI_DEVICE_ID_TTTECH_MC322	0x000a
 
@@ -548,7 +550,9 @@
 #define PCI_DEVICE_ID_AMD_17H_DF_F3	0x1463
 #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F3 0x15eb
 #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F3 0x1493
+#define PCI_DEVICE_ID_AMD_17H_M60H_DF_F3 0x144b
 #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F3 0x1443
+#define PCI_DEVICE_ID_AMD_19H_DF_F3	0x1653
 #define PCI_DEVICE_ID_AMD_CNB17H_F3	0x1703
 #define PCI_DEVICE_ID_AMD_LANCE		0x2000
 #define PCI_DEVICE_ID_AMD_LANCE_HOME	0x2001
@@ -1829,6 +1833,12 @@
 #define PCI_VENDOR_ID_NVIDIA_SGS	0x12d2
 #define PCI_DEVICE_ID_NVIDIA_SGS_RIVA128 0x0018
 
+#define PCI_VENDOR_ID_PERICOM			0x12D8
+#define PCI_DEVICE_ID_PERICOM_PI7C9X7951	0x7951
+#define PCI_DEVICE_ID_PERICOM_PI7C9X7952	0x7952
+#define PCI_DEVICE_ID_PERICOM_PI7C9X7954	0x7954
+#define PCI_DEVICE_ID_PERICOM_PI7C9X7958	0x7958
+
 #define PCI_SUBVENDOR_ID_CHASE_PCIFAST		0x12E0
 #define PCI_SUBDEVICE_ID_CHASE_PCIFAST4		0x0031
 #define PCI_SUBDEVICE_ID_CHASE_PCIFAST8		0x0021
@@ -2574,6 +2584,8 @@
 
 #define PCI_VENDOR_ID_AMAZON		0x1d0f
 
+#define PCI_VENDOR_ID_ZHAOXIN		0x1d17
+
 #define PCI_VENDOR_ID_HYGON		0x1d94
 
 #define PCI_VENDOR_ID_HXT		0x1dbf
@@ -2998,6 +3010,7 @@
 #define PCI_DEVICE_ID_INTEL_84460GX	0x84ea
 #define PCI_DEVICE_ID_INTEL_IXP4XX	0x8500
 #define PCI_DEVICE_ID_INTEL_IXP2800	0x9004
+#define PCI_DEVICE_ID_INTEL_VMD_9A0B	0x9a0b
 #define PCI_DEVICE_ID_INTEL_S21152BB	0xb152
 
 #define PCI_VENDOR_ID_SCALEMP		0x8686
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index a6fabd865211..176bfbd52d97 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -175,8 +175,7 @@
  * Declaration/definition used for per-CPU variables that should be accessed
  * as decrypted when memory encryption is enabled in the guest.
  */
-#if defined(CONFIG_VIRTUALIZATION) && defined(CONFIG_AMD_MEM_ENCRYPT)
-
+#ifdef CONFIG_AMD_MEM_ENCRYPT
 #define DECLARE_PER_CPU_DECRYPTED(type, name)				\
 	DECLARE_PER_CPU_SECTION(type, name, "..decrypted")
 
diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h
index 4f052496cdfd..0a4f54dd4737 100644
--- a/include/linux/percpu_counter.h
+++ b/include/linux/percpu_counter.h
@@ -78,9 +78,9 @@ static inline s64 percpu_counter_read(struct percpu_counter *fbc)
  */
 static inline s64 percpu_counter_read_positive(struct percpu_counter *fbc)
 {
-	s64 ret = fbc->count;
+	/* Prevent reloads of fbc->count */
+	s64 ret = READ_ONCE(fbc->count);
 
-	barrier();		/* Prevent reloads of fbc->count */
 	if (ret >= 0)
 		return ret;
 	return 0;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 8e3c7d095944..9e13674fb566 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -336,6 +336,7 @@ struct phy_c45_device_ids {
  * is_gigabit_capable: Set to true if PHY supports 1000Mbps
  * has_fixups: Set to true if this phy has fixups/quirks.
  * suspended: Set to true if this phy has been suspended successfully.
+ * suspended_by_mdio_bus: Set to true if this phy was suspended by MDIO bus.
  * sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal.
  * loopback_enabled: Set true if this phy has been loopbacked successfully.
  * state: state of the PHY for management purposes
@@ -374,6 +375,7 @@ struct phy_device {
 	unsigned is_gigabit_capable:1;
 	unsigned has_fixups:1;
 	unsigned suspended:1;
+	unsigned suspended_by_mdio_bus:1;
 	unsigned sysfs_links:1;
 	unsigned loopback_enabled:1;
 
diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
index beb25f277889..6837544d6899 100644
--- a/include/linux/platform_device.h
+++ b/include/linux/platform_device.h
@@ -55,11 +55,14 @@ extern void __iomem *
 devm_platform_ioremap_resource(struct platform_device *pdev,
 			       unsigned int index);
 extern int platform_get_irq(struct platform_device *, unsigned int);
+extern int platform_get_irq_optional(struct platform_device *, unsigned int);
 extern int platform_irq_count(struct platform_device *);
 extern struct resource *platform_get_resource_byname(struct platform_device *,
 						     unsigned int,
 						     const char *);
 extern int platform_get_irq_byname(struct platform_device *, const char *);
+extern int platform_get_irq_byname_optional(struct platform_device *dev,
+					    const char *name);
 extern int platform_add_devices(struct platform_device **, int);
 
 struct platform_device_info {
diff --git a/include/linux/pnp.h b/include/linux/pnp.h
index 3b12fd28af78..fc4df3ccefc9 100644
--- a/include/linux/pnp.h
+++ b/include/linux/pnp.h
@@ -220,10 +220,8 @@ struct pnp_card {
 #define global_to_pnp_card(n) list_entry(n, struct pnp_card, global_list)
 #define protocol_to_pnp_card(n) list_entry(n, struct pnp_card, protocol_list)
 #define to_pnp_card(n) container_of(n, struct pnp_card, dev)
-#define pnp_for_each_card(card) \
-	for((card) = global_to_pnp_card(pnp_cards.next); \
-	(card) != global_to_pnp_card(&pnp_cards); \
-	(card) = global_to_pnp_card((card)->global_list.next))
+#define pnp_for_each_card(card)	\
+	list_for_each_entry(card, &pnp_cards, global_list)
 
 struct pnp_card_link {
 	struct pnp_card *card;
@@ -276,14 +274,9 @@ struct pnp_dev {
 #define card_to_pnp_dev(n) list_entry(n, struct pnp_dev, card_list)
 #define protocol_to_pnp_dev(n) list_entry(n, struct pnp_dev, protocol_list)
 #define	to_pnp_dev(n) container_of(n, struct pnp_dev, dev)
-#define pnp_for_each_dev(dev) \
-	for((dev) = global_to_pnp_dev(pnp_global.next); \
-	(dev) != global_to_pnp_dev(&pnp_global); \
-	(dev) = global_to_pnp_dev((dev)->global_list.next))
-#define card_for_each_dev(card,dev) \
-	for((dev) = card_to_pnp_dev((card)->devices.next); \
-	(dev) != card_to_pnp_dev(&(card)->devices); \
-	(dev) = card_to_pnp_dev((dev)->card_list.next))
+#define pnp_for_each_dev(dev) list_for_each_entry(dev, &pnp_global, global_list)
+#define card_for_each_dev(card, dev)	\
+	list_for_each_entry(dev, &(card)->devices, card_list)
 #define pnp_dev_name(dev) (dev)->name
 
 static inline void *pnp_get_drvdata(struct pnp_dev *pdev)
@@ -437,14 +430,10 @@ struct pnp_protocol {
 };
 
 #define to_pnp_protocol(n) list_entry(n, struct pnp_protocol, protocol_list)
-#define protocol_for_each_card(protocol,card) \
-	for((card) = protocol_to_pnp_card((protocol)->cards.next); \
-	(card) != protocol_to_pnp_card(&(protocol)->cards); \
-	(card) = protocol_to_pnp_card((card)->protocol_list.next))
-#define protocol_for_each_dev(protocol,dev) \
-	for((dev) = protocol_to_pnp_dev((protocol)->devices.next); \
-	(dev) != protocol_to_pnp_dev(&(protocol)->devices); \
-	(dev) = protocol_to_pnp_dev((dev)->protocol_list.next))
+#define protocol_for_each_card(protocol, card)	\
+	list_for_each_entry(card, &(protocol)->cards, protocol_list)
+#define protocol_for_each_dev(protocol, dev)	\
+	list_for_each_entry(dev, &(protocol)->devices, protocol_list)
 
 extern struct bus_type pnp_bus_type;
 
diff --git a/include/linux/power/smartreflex.h b/include/linux/power/smartreflex.h
index d0b37e937037..971c9264179e 100644
--- a/include/linux/power/smartreflex.h
+++ b/include/linux/power/smartreflex.h
@@ -293,6 +293,9 @@ struct omap_sr_data {
 	struct voltagedomain		*voltdm;
 };
 
+
+extern struct omap_sr_data omap_sr_pdata[OMAP_SR_NR];
+
 #ifdef CONFIG_POWER_AVS_OMAP
 
 /* Smartreflex module enable/disable interface */
diff --git a/include/linux/prandom.h b/include/linux/prandom.h
new file mode 100644
index 000000000000..aa16e6468f91
--- /dev/null
+++ b/include/linux/prandom.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * include/linux/prandom.h
+ *
+ * Include file for the fast pseudo-random 32-bit
+ * generation.
+ */
+#ifndef _LINUX_PRANDOM_H
+#define _LINUX_PRANDOM_H
+
+#include <linux/types.h>
+#include <linux/percpu.h>
+
+u32 prandom_u32(void);
+void prandom_bytes(void *buf, size_t nbytes);
+void prandom_seed(u32 seed);
+void prandom_reseed_late(void);
+
+struct rnd_state {
+	__u32 s1, s2, s3, s4;
+};
+
+DECLARE_PER_CPU(struct rnd_state, net_rand_state);
+
+u32 prandom_u32_state(struct rnd_state *state);
+void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes);
+void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state);
+
+#define prandom_init_once(pcpu_state)			\
+	DO_ONCE(prandom_seed_full_state, (pcpu_state))
+
+/**
+ * prandom_u32_max - returns a pseudo-random number in interval [0, ep_ro)
+ * @ep_ro: right open interval endpoint
+ *
+ * Returns a pseudo-random number that is in interval [0, ep_ro). Note
+ * that the result depends on PRNG being well distributed in [0, ~0U]
+ * u32 space. Here we use maximally equidistributed combined Tausworthe
+ * generator, that is, prandom_u32(). This is useful when requesting a
+ * random index of an array containing ep_ro elements, for example.
+ *
+ * Returns: pseudo-random number in interval [0, ep_ro)
+ */
+static inline u32 prandom_u32_max(u32 ep_ro)
+{
+	return (u32)(((u64) prandom_u32() * ep_ro) >> 32);
+}
+
+/*
+ * Handle minimum values for seeds
+ */
+static inline u32 __seed(u32 x, u32 m)
+{
+	return (x < m) ? x + m : x;
+}
+
+/**
+ * prandom_seed_state - set seed for prandom_u32_state().
+ * @state: pointer to state structure to receive the seed.
+ * @seed: arbitrary 64-bit value to use as a seed.
+ */
+static inline void prandom_seed_state(struct rnd_state *state, u64 seed)
+{
+	u32 i = (seed >> 32) ^ (seed << 10) ^ seed;
+
+	state->s1 = __seed(i,   2U);
+	state->s2 = __seed(i,   8U);
+	state->s3 = __seed(i,  16U);
+	state->s4 = __seed(i, 128U);
+}
+
+/* Pseudo random number generator from numerical recipes. */
+static inline u32 next_pseudo_random32(u32 seed)
+{
+	return seed * 1664525 + 1013904223;
+}
+
+#endif
diff --git a/include/linux/printk.h b/include/linux/printk.h
index cefd374c47b1..5252359a40f7 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -202,7 +202,6 @@ __printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...);
 void dump_stack_print_info(const char *log_lvl);
 void show_regs_print_info(const char *log_lvl);
 extern asmlinkage void dump_stack(void) __cold;
-extern void printk_safe_init(void);
 extern void printk_safe_flush(void);
 extern void printk_safe_flush_on_panic(void);
 #else
@@ -269,10 +268,6 @@ static inline void dump_stack(void)
 {
 }
 
-static inline void printk_safe_init(void)
-{
-}
-
 static inline void printk_safe_flush(void)
 {
 }
diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h
index 2dd0a9ed5b36..6d15040c642c 100644
--- a/include/linux/qed/qed_chain.h
+++ b/include/linux/qed/qed_chain.h
@@ -97,6 +97,11 @@ struct qed_chain_u32 {
 	u32 cons_idx;
 };
 
+struct addr_tbl_entry {
+	void *virt_addr;
+	dma_addr_t dma_map;
+};
+
 struct qed_chain {
 	/* fastpath portion of the chain - required for commands such
 	 * as produce / consume.
@@ -107,10 +112,11 @@ struct qed_chain {
 
 	/* Fastpath portions of the PBL [if exists] */
 	struct {
-		/* Table for keeping the virtual addresses of the chain pages,
-		 * respectively to the physical addresses in the pbl table.
+		/* Table for keeping the virtual and physical addresses of the
+		 * chain pages, respectively to the physical addresses
+		 * in the pbl table.
 		 */
-		void **pp_virt_addr_tbl;
+		struct addr_tbl_entry *pp_addr_tbl;
 
 		union {
 			struct qed_chain_pbl_u16 u16;
@@ -201,28 +207,34 @@ static inline u32 qed_chain_get_cons_idx_u32(struct qed_chain *p_chain)
 
 static inline u16 qed_chain_get_elem_left(struct qed_chain *p_chain)
 {
+	u16 elem_per_page = p_chain->elem_per_page;
+	u32 prod = p_chain->u.chain16.prod_idx;
+	u32 cons = p_chain->u.chain16.cons_idx;
 	u16 used;
 
-	used = (u16) (((u32)0x10000 +
-		       (u32)p_chain->u.chain16.prod_idx) -
-		      (u32)p_chain->u.chain16.cons_idx);
+	if (prod < cons)
+		prod += (u32)U16_MAX + 1;
+
+	used = (u16)(prod - cons);
 	if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR)
-		used -= p_chain->u.chain16.prod_idx / p_chain->elem_per_page -
-		    p_chain->u.chain16.cons_idx / p_chain->elem_per_page;
+		used -= prod / elem_per_page - cons / elem_per_page;
 
 	return (u16)(p_chain->capacity - used);
 }
 
 static inline u32 qed_chain_get_elem_left_u32(struct qed_chain *p_chain)
 {
+	u16 elem_per_page = p_chain->elem_per_page;
+	u64 prod = p_chain->u.chain32.prod_idx;
+	u64 cons = p_chain->u.chain32.cons_idx;
 	u32 used;
 
-	used = (u32) (((u64)0x100000000ULL +
-		       (u64)p_chain->u.chain32.prod_idx) -
-		      (u64)p_chain->u.chain32.cons_idx);
+	if (prod < cons)
+		prod += (u64)U32_MAX + 1;
+
+	used = (u32)(prod - cons);
 	if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR)
-		used -= p_chain->u.chain32.prod_idx / p_chain->elem_per_page -
-		    p_chain->u.chain32.cons_idx / p_chain->elem_per_page;
+		used -= (u32)(prod / elem_per_page - cons / elem_per_page);
 
 	return p_chain->capacity - used;
 }
@@ -287,7 +299,7 @@ qed_chain_advance_page(struct qed_chain *p_chain,
 				*(u32 *)page_to_inc = 0;
 			page_index = *(u32 *)page_to_inc;
 		}
-		*p_next_elem = p_chain->pbl.pp_virt_addr_tbl[page_index];
+		*p_next_elem = p_chain->pbl.pp_addr_tbl[page_index].virt_addr;
 	}
 }
 
@@ -537,7 +549,7 @@ static inline void qed_chain_init_params(struct qed_chain *p_chain,
 
 	p_chain->pbl_sp.p_phys_table = 0;
 	p_chain->pbl_sp.p_virt_table = NULL;
-	p_chain->pbl.pp_virt_addr_tbl = NULL;
+	p_chain->pbl.pp_addr_tbl = NULL;
 }
 
 /**
@@ -575,11 +587,11 @@ static inline void qed_chain_init_mem(struct qed_chain *p_chain,
 static inline void qed_chain_init_pbl_mem(struct qed_chain *p_chain,
 					  void *p_virt_pbl,
 					  dma_addr_t p_phys_pbl,
-					  void **pp_virt_addr_tbl)
+					  struct addr_tbl_entry *pp_addr_tbl)
 {
 	p_chain->pbl_sp.p_phys_table = p_phys_pbl;
 	p_chain->pbl_sp.p_virt_table = p_virt_pbl;
-	p_chain->pbl.pp_virt_addr_tbl = pp_virt_addr_tbl;
+	p_chain->pbl.pp_addr_tbl = pp_addr_tbl;
 }
 
 /**
@@ -644,7 +656,7 @@ static inline void *qed_chain_get_last_elem(struct qed_chain *p_chain)
 		break;
 	case QED_CHAIN_MODE_PBL:
 		last_page_idx = p_chain->page_cnt - 1;
-		p_virt_addr = p_chain->pbl.pp_virt_addr_tbl[last_page_idx];
+		p_virt_addr = p_chain->pbl.pp_addr_tbl[last_page_idx].virt_addr;
 		break;
 	}
 	/* p_virt_addr points at this stage to the last page of the chain */
@@ -716,7 +728,7 @@ static inline void qed_chain_pbl_zero_mem(struct qed_chain *p_chain)
 	page_cnt = qed_chain_get_page_cnt(p_chain);
 
 	for (i = 0; i < page_cnt; i++)
-		memset(p_chain->pbl.pp_virt_addr_tbl[i], 0,
+		memset(p_chain->pbl.pp_addr_tbl[i].virt_addr, 0,
 		       QED_CHAIN_PAGE_SIZE);
 }
 
diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h
index 0832c9b66852..0b6e7ad9cd2a 100644
--- a/include/linux/raid/pq.h
+++ b/include/linux/raid/pq.h
@@ -27,7 +27,6 @@ extern const char raid6_empty_zero_page[PAGE_SIZE];
 
 #include <errno.h>
 #include <inttypes.h>
-#include <limits.h>
 #include <stddef.h>
 #include <sys/mman.h>
 #include <sys/time.h>
diff --git a/include/linux/random.h b/include/linux/random.h
index 1f7dced2bba6..2f902463c408 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -107,61 +107,12 @@ declare_get_random_var_wait(long)
 
 unsigned long randomize_page(unsigned long start, unsigned long range);
 
-u32 prandom_u32(void);
-void prandom_bytes(void *buf, size_t nbytes);
-void prandom_seed(u32 seed);
-void prandom_reseed_late(void);
-
-struct rnd_state {
-	__u32 s1, s2, s3, s4;
-};
-
-u32 prandom_u32_state(struct rnd_state *state);
-void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes);
-void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state);
-
-#define prandom_init_once(pcpu_state)			\
-	DO_ONCE(prandom_seed_full_state, (pcpu_state))
-
-/**
- * prandom_u32_max - returns a pseudo-random number in interval [0, ep_ro)
- * @ep_ro: right open interval endpoint
- *
- * Returns a pseudo-random number that is in interval [0, ep_ro). Note
- * that the result depends on PRNG being well distributed in [0, ~0U]
- * u32 space. Here we use maximally equidistributed combined Tausworthe
- * generator, that is, prandom_u32(). This is useful when requesting a
- * random index of an array containing ep_ro elements, for example.
- *
- * Returns: pseudo-random number in interval [0, ep_ro)
- */
-static inline u32 prandom_u32_max(u32 ep_ro)
-{
-	return (u32)(((u64) prandom_u32() * ep_ro) >> 32);
-}
-
 /*
- * Handle minimum values for seeds
+ * This is designed to be standalone for just prandom
+ * users, but for now we include it from <linux/random.h>
+ * for legacy reasons.
  */
-static inline u32 __seed(u32 x, u32 m)
-{
-	return (x < m) ? x + m : x;
-}
-
-/**
- * prandom_seed_state - set seed for prandom_u32_state().
- * @state: pointer to state structure to receive the seed.
- * @seed: arbitrary 64-bit value to use as a seed.
- */
-static inline void prandom_seed_state(struct rnd_state *state, u64 seed)
-{
-	u32 i = (seed >> 32) ^ (seed << 10) ^ seed;
-
-	state->s1 = __seed(i,   2U);
-	state->s2 = __seed(i,   8U);
-	state->s3 = __seed(i,  16U);
-	state->s4 = __seed(i, 128U);
-}
+#include <linux/prandom.h>
 
 #ifdef CONFIG_ARCH_RANDOM
 # include <asm/archrandom.h>
@@ -192,10 +143,4 @@ static inline bool arch_has_random_seed(void)
 }
 #endif
 
-/* Pseudo random number generator from numerical recipes. */
-static inline u32 next_pseudo_random32(u32 seed)
-{
-	return seed * 1664525 + 1013904223;
-}
-
 #endif /* _LINUX_RANDOM_H */
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index e91ec9ddcd30..4158b7212936 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -41,6 +41,24 @@ static inline void INIT_LIST_HEAD_RCU(struct list_head *list)
 #define list_next_rcu(list)	(*((struct list_head __rcu **)(&(list)->next)))
 
 /*
+ * Check during list traversal that we are within an RCU reader
+ */
+
+#define check_arg_count_one(dummy)
+
+#ifdef CONFIG_PROVE_RCU_LIST
+#define __list_check_rcu(dummy, cond, extra...)				\
+	({								\
+	check_arg_count_one(extra);					\
+	RCU_LOCKDEP_WARN(!cond && !rcu_read_lock_any_held(),		\
+			 "RCU-list traversed in non-reader section!");	\
+	 })
+#else
+#define __list_check_rcu(dummy, cond, extra...)				\
+	({ check_arg_count_one(extra); })
+#endif
+
+/*
  * Insert a new entry between two known consecutive entries.
  *
  * This is only for internal list manipulation where we know
@@ -343,14 +361,16 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
  * @pos:	the type * to use as a loop cursor.
  * @head:	the head for your list.
  * @member:	the name of the list_head within the struct.
+ * @cond:	optional lockdep expression if called from non-RCU protection.
  *
  * This list-traversal primitive may safely run concurrently with
  * the _rcu list-mutation primitives such as list_add_rcu()
  * as long as the traversal is guarded by rcu_read_lock().
  */
-#define list_for_each_entry_rcu(pos, head, member) \
-	for (pos = list_entry_rcu((head)->next, typeof(*pos), member); \
-		&pos->member != (head); \
+#define list_for_each_entry_rcu(pos, head, member, cond...)		\
+	for (__list_check_rcu(dummy, ## cond, 0),			\
+	     pos = list_entry_rcu((head)->next, typeof(*pos), member);	\
+		&pos->member != (head);					\
 		pos = list_entry_rcu(pos->member.next, typeof(*pos), member))
 
 /**
@@ -616,13 +636,15 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n,
  * @pos:	the type * to use as a loop cursor.
  * @head:	the head for your list.
  * @member:	the name of the hlist_node within the struct.
+ * @cond:	optional lockdep expression if called from non-RCU protection.
  *
  * This list-traversal primitive may safely run concurrently with
  * the _rcu list-mutation primitives such as hlist_add_head_rcu()
  * as long as the traversal is guarded by rcu_read_lock().
  */
-#define hlist_for_each_entry_rcu(pos, head, member)			\
-	for (pos = hlist_entry_safe (rcu_dereference_raw(hlist_first_rcu(head)),\
+#define hlist_for_each_entry_rcu(pos, head, member, cond...)		\
+	for (__list_check_rcu(dummy, ## cond, 0),			\
+	     pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\
 			typeof(*(pos)), member);			\
 		pos;							\
 		pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\
@@ -642,10 +664,10 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n,
  * not do any RCU debugging or tracing.
  */
 #define hlist_for_each_entry_rcu_notrace(pos, head, member)			\
-	for (pos = hlist_entry_safe (rcu_dereference_raw_notrace(hlist_first_rcu(head)),\
+	for (pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_first_rcu(head)),\
 			typeof(*(pos)), member);			\
 		pos;							\
-		pos = hlist_entry_safe(rcu_dereference_raw_notrace(hlist_next_rcu(\
+		pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_next_rcu(\
 			&(pos)->member)), typeof(*(pos)), member))
 
 /**
diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h
index 61974c4c566b..90f2e2232c6d 100644
--- a/include/linux/rculist_nulls.h
+++ b/include/linux/rculist_nulls.h
@@ -34,7 +34,7 @@ static inline void hlist_nulls_del_init_rcu(struct hlist_nulls_node *n)
 {
 	if (!hlist_nulls_unhashed(n)) {
 		__hlist_nulls_del(n);
-		n->pprev = NULL;
+		WRITE_ONCE(n->pprev, NULL);
 	}
 }
 
@@ -66,7 +66,7 @@ static inline void hlist_nulls_del_init_rcu(struct hlist_nulls_node *n)
 static inline void hlist_nulls_del_rcu(struct hlist_nulls_node *n)
 {
 	__hlist_nulls_del(n);
-	n->pprev = LIST_POISON2;
+	WRITE_ONCE(n->pprev, LIST_POISON2);
 }
 
 /**
@@ -94,10 +94,10 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n,
 	struct hlist_nulls_node *first = h->first;
 
 	n->next = first;
-	n->pprev = &h->first;
+	WRITE_ONCE(n->pprev, &h->first);
 	rcu_assign_pointer(hlist_nulls_first_rcu(h), n);
 	if (!is_a_nulls(first))
-		first->pprev = &n->next;
+		WRITE_ONCE(first->pprev, &n->next);
 }
 
 /**
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 3508f4508a11..0ddf7543f45d 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -221,6 +221,7 @@ int debug_lockdep_rcu_enabled(void);
 int rcu_read_lock_held(void);
 int rcu_read_lock_bh_held(void);
 int rcu_read_lock_sched_held(void);
+int rcu_read_lock_any_held(void);
 
 #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
@@ -241,6 +242,12 @@ static inline int rcu_read_lock_sched_held(void)
 {
 	return !preemptible();
 }
+
+static inline int rcu_read_lock_any_held(void)
+{
+	return !preemptible();
+}
+
 #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
 #ifdef CONFIG_PROVE_RCU
@@ -367,7 +374,7 @@ static inline void rcu_preempt_sleep_check(void) { }
 #define rcu_assign_pointer(p, v)					      \
 ({									      \
 	uintptr_t _r_a_p__v = (uintptr_t)(v);				      \
-	rcu_check_sparse(p, __rcu);				      \
+	rcu_check_sparse(p, __rcu);					      \
 									      \
 	if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL)	      \
 		WRITE_ONCE((p), (typeof(p))(_r_a_p__v));		      \
@@ -377,6 +384,24 @@ static inline void rcu_preempt_sleep_check(void) { }
 })
 
 /**
+ * rcu_replace_pointer() - replace an RCU pointer, returning its old value
+ * @rcu_ptr: RCU pointer, whose old value is returned
+ * @ptr: regular pointer
+ * @c: the lockdep conditions under which the dereference will take place
+ *
+ * Perform a replacement, where @rcu_ptr is an RCU-annotated
+ * pointer and @c is the lockdep argument that is passed to the
+ * rcu_dereference_protected() call used to read that pointer.  The old
+ * value of @rcu_ptr is returned, and @rcu_ptr is set to @ptr.
+ */
+#define rcu_replace_pointer(rcu_ptr, ptr, c)				\
+({									\
+	typeof(ptr) __tmp = rcu_dereference_protected((rcu_ptr), (c));	\
+	rcu_assign_pointer((rcu_ptr), (ptr));				\
+	__tmp;								\
+})
+
+/**
  * rcu_swap_protected() - swap an RCU and a regular pointer
  * @rcu_ptr: RCU pointer
  * @ptr: regular pointer
@@ -477,7 +502,7 @@ static inline void rcu_preempt_sleep_check(void) { }
  * The no-tracing version of rcu_dereference_raw() must not call
  * rcu_read_lock_held().
  */
-#define rcu_dereference_raw_notrace(p) __rcu_dereference_check((p), 1, __rcu)
+#define rcu_dereference_raw_check(p) __rcu_dereference_check((p), 1, __rcu)
 
 /**
  * rcu_dereference_protected() - fetch RCU pointer when updates prevented
diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h
index 7cf8f797e13a..3ab1ddf151a2 100644
--- a/include/linux/regulator/ab8500.h
+++ b/include/linux/regulator/ab8500.h
@@ -37,14 +37,11 @@ enum ab8505_regulator_id {
 	AB8505_LDO_AUX6,
 	AB8505_LDO_INTCORE,
 	AB8505_LDO_ADC,
-	AB8505_LDO_USB,
 	AB8505_LDO_AUDIO,
 	AB8505_LDO_ANAMIC1,
 	AB8505_LDO_ANAMIC2,
 	AB8505_LDO_AUX8,
 	AB8505_LDO_ANA,
-	AB8505_SYSCLKREQ_2,
-	AB8505_SYSCLKREQ_4,
 	AB8505_NUM_REGULATORS,
 };
 
diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h
index 815983419375..7f65544025fc 100644
--- a/include/linux/regulator/consumer.h
+++ b/include/linux/regulator/consumer.h
@@ -281,6 +281,8 @@ void devm_regulator_unregister_notifier(struct regulator *regulator,
 void *regulator_get_drvdata(struct regulator *regulator);
 void regulator_set_drvdata(struct regulator *regulator, void *data);
 
+bool regulator_is_equal(struct regulator *reg1, struct regulator *reg2);
+
 #else
 
 /*
@@ -580,6 +582,11 @@ static inline int regulator_list_voltage(struct regulator *regulator, unsigned s
 	return -EINVAL;
 }
 
+static inline bool
+regulator_is_equal(struct regulator *reg1, struct regulator *reg2)
+{
+	return false;
+}
 #endif
 
 static inline int regulator_set_voltage_triplet(struct regulator *regulator,
diff --git a/include/linux/regulator/coupler.h b/include/linux/regulator/coupler.h
new file mode 100644
index 000000000000..0212d6255e4e
--- /dev/null
+++ b/include/linux/regulator/coupler.h
@@ -0,0 +1,97 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * coupler.h -- SoC Regulator support, coupler API.
+ *
+ * Regulator Coupler Interface.
+ */
+
+#ifndef __LINUX_REGULATOR_COUPLER_H_
+#define __LINUX_REGULATOR_COUPLER_H_
+
+#include <linux/kernel.h>
+#include <linux/suspend.h>
+
+struct regulator_coupler;
+struct regulator_dev;
+
+/**
+ * struct regulator_coupler - customized regulator's coupler
+ *
+ * Regulator's coupler allows to customize coupling algorithm.
+ *
+ * @list: couplers list entry
+ * @attach_regulator: Callback invoked on creation of a coupled regulator,
+ *                    couples are unresolved at this point. The callee should
+ *                    check that it could handle the regulator and return 0 on
+ *                    success, -errno on failure and 1 if given regulator is
+ *                    not suitable for this coupler (case of having multiple
+ *                    regulators in a system). Callback shall be implemented.
+ * @detach_regulator: Callback invoked on destruction of a coupled regulator.
+ *                    This callback is optional and could be NULL.
+ * @balance_voltage: Callback invoked when voltage of a coupled regulator is
+ *                   changing. Called with all of the coupled rdev's being held
+ *                   under "consumer lock". The callee should perform voltage
+ *                   balancing, changing voltage of the coupled regulators as
+ *                   needed. It's up to the coupler to verify the voltage
+ *                   before changing it in hardware, i.e. coupler should
+ *                   check consumer's min/max and etc. This callback is
+ *                   optional and could be NULL, in which case a generic
+ *                   voltage balancer will be used.
+ */
+struct regulator_coupler {
+	struct list_head list;
+
+	int (*attach_regulator)(struct regulator_coupler *coupler,
+				struct regulator_dev *rdev);
+	int (*detach_regulator)(struct regulator_coupler *coupler,
+				struct regulator_dev *rdev);
+	int (*balance_voltage)(struct regulator_coupler *coupler,
+			       struct regulator_dev *rdev,
+			       suspend_state_t state);
+};
+
+#ifdef CONFIG_REGULATOR
+int regulator_coupler_register(struct regulator_coupler *coupler);
+const char *rdev_get_name(struct regulator_dev *rdev);
+int regulator_check_consumers(struct regulator_dev *rdev,
+			      int *min_uV, int *max_uV,
+			      suspend_state_t state);
+int regulator_check_voltage(struct regulator_dev *rdev,
+			    int *min_uV, int *max_uV);
+int regulator_get_voltage_rdev(struct regulator_dev *rdev);
+int regulator_set_voltage_rdev(struct regulator_dev *rdev,
+			       int min_uV, int max_uV,
+			       suspend_state_t state);
+#else
+static inline int regulator_coupler_register(struct regulator_coupler *coupler)
+{
+	return 0;
+}
+static inline const char *rdev_get_name(struct regulator_dev *rdev)
+{
+	return NULL;
+}
+static inline int regulator_check_consumers(struct regulator_dev *rdev,
+					    int *min_uV, int *max_uV,
+					    suspend_state_t state)
+{
+	return -EINVAL;
+}
+static inline int regulator_check_voltage(struct regulator_dev *rdev,
+					  int *min_uV, int *max_uV)
+{
+	return -EINVAL;
+}
+static inline int regulator_get_voltage_rdev(struct regulator_dev *rdev)
+{
+	return -EINVAL;
+}
+static inline int regulator_set_voltage_rdev(struct regulator_dev *rdev,
+					     int min_uV, int max_uV,
+					     suspend_state_t state)
+{
+	return -EINVAL;
+}
+#endif
+
+#endif
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index d45ab52c91c9..64ef7514f62d 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -12,8 +12,6 @@
 #ifndef __LINUX_REGULATOR_DRIVER_H_
 #define __LINUX_REGULATOR_DRIVER_H_
 
-#define MAX_COUPLED		2
-
 #include <linux/device.h>
 #include <linux/notifier.h>
 #include <linux/regulator/consumer.h>
@@ -423,7 +421,8 @@ struct regulator_config {
  * incremented.
  */
 struct coupling_desc {
-	struct regulator_dev *coupled_rdevs[MAX_COUPLED];
+	struct regulator_dev **coupled_rdevs;
+	struct regulator_coupler *coupler;
 	int n_resolved;
 	int n_coupled;
 };
@@ -549,4 +548,5 @@ void regulator_unlock(struct regulator_dev *rdev);
  */
 int regulator_desc_list_voltage_linear_range(const struct regulator_desc *desc,
 					     unsigned int selector);
+
 #endif
diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h
index 5539efa76d26..a84cc8879c3e 100644
--- a/include/linux/regulator/machine.h
+++ b/include/linux/regulator/machine.h
@@ -153,7 +153,7 @@ struct regulation_constraints {
 	int system_load;
 
 	/* used for coupled regulators */
-	int max_spread;
+	u32 *max_spread;
 
 	/* used for changing voltage in steps */
 	int max_uV_step;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1157f6e245af..ef9265c1fd97 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -883,8 +883,8 @@ struct task_struct {
 	struct seccomp			seccomp;
 
 	/* Thread group tracking: */
-	u32				parent_exec_id;
-	u32				self_exec_id;
+	u64				parent_exec_id;
+	u64				self_exec_id;
 
 	/* Protection against (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed, mempolicy: */
 	spinlock_t			alloc_lock;
@@ -1857,11 +1857,11 @@ static inline void rseq_migrate(struct task_struct *t)
 
 /*
  * If parent process has a registered restartable sequences area, the
- * child inherits. Only applies when forking a process, not a thread.
+ * child inherits. Unregister rseq for a clone with CLONE_VM set.
  */
 static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
 {
-	if (clone_flags & CLONE_THREAD) {
+	if (clone_flags & CLONE_VM) {
 		t->rseq = NULL;
 		t->rseq_sig = 0;
 		t->rseq_event_mask = 0;
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 8557ec664213..b35921dfb68e 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -49,6 +49,8 @@ static inline void mmdrop(struct mm_struct *mm)
 		__mmdrop(mm);
 }
 
+void mmdrop(struct mm_struct *mm);
+
 /*
  * This has to be called after a get_task_mm()/mmget_not_zero()
  * followed by taking the mmap_sem for writing before modifying the
diff --git a/include/linux/sched/nohz.h b/include/linux/sched/nohz.h
index b36f4cf38111..ea8bc4d41faa 100644
--- a/include/linux/sched/nohz.h
+++ b/include/linux/sched/nohz.h
@@ -6,6 +6,8 @@
  * This is the interface between the scheduler and nohz/dynticks:
  */
 
+struct rq;
+
 #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
 extern void cpu_load_update_nohz_start(void);
 extern void cpu_load_update_nohz_stop(void);
@@ -23,9 +25,11 @@ static inline void nohz_balance_enter_idle(int cpu) { }
 
 #ifdef CONFIG_NO_HZ_COMMON
 void calc_load_nohz_start(void);
+void calc_load_nohz_remote(struct rq *rq);
 void calc_load_nohz_stop(void);
 #else
 static inline void calc_load_nohz_start(void) { }
+static inline void calc_load_nohz_remote(struct rq *rq) { }
 static inline void calc_load_nohz_stop(void) { }
 #endif /* CONFIG_NO_HZ_COMMON */
 
diff --git a/include/linux/selection.h b/include/linux/selection.h
index e2c1f96bf059..5b890ef5b59f 100644
--- a/include/linux/selection.h
+++ b/include/linux/selection.h
@@ -11,8 +11,8 @@
 #include <linux/tiocl.h>
 #include <linux/vt_buffer.h>
 
-extern struct vc_data *sel_cons;
 struct tty_struct;
+struct vc_data;
 
 extern void clear_selection(void);
 extern int set_selection_user(const struct tiocl_selection __user *sel,
@@ -24,6 +24,8 @@ extern int sel_loadlut(char __user *p);
 extern int mouse_reporting(void);
 extern void mouse_report(struct tty_struct * tty, int butt, int mrx, int mry);
 
+bool vc_is_sel(struct vc_data *vc);
+
 extern int console_blanked;
 
 extern const unsigned char color_table[];
diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h
index 86281ac7c305..860e0f843c12 100644
--- a/include/linux/set_memory.h
+++ b/include/linux/set_memory.h
@@ -26,7 +26,7 @@ static inline int set_direct_map_default_noflush(struct page *page)
 #endif
 
 #ifndef set_mce_nospec
-static inline int set_mce_nospec(unsigned long pfn)
+static inline int set_mce_nospec(unsigned long pfn, bool unmap)
 {
 	return 0;
 }
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 8b9c1d361db5..a3b1a7e2b017 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -639,8 +639,8 @@ typedef unsigned char *sk_buff_data_t;
  *	@offload_l3_fwd_mark: Packet was L3-forwarded in hardware
  *	@tc_skip_classify: do not classify packet. set by IFB device
  *	@tc_at_ingress: used within tc_classify to distinguish in/egress
- *	@tc_redirected: packet was redirected by a tc action
- *	@tc_from_ingress: if tc_redirected, tc_at_ingress at time of redirect
+ *	@redirected: packet was redirected by packet classifier
+ *	@from_ingress: packet was redirected from the ingress path
  *	@peeked: this packet has been seen already, so stats have been
  *		done for it, don't do them again
  *	@nf_trace: netfilter packet trace flag
@@ -821,8 +821,10 @@ struct sk_buff {
 #ifdef CONFIG_NET_CLS_ACT
 	__u8			tc_skip_classify:1;
 	__u8			tc_at_ingress:1;
-	__u8			tc_redirected:1;
-	__u8			tc_from_ingress:1;
+#endif
+#ifdef CONFIG_NET_REDIRECT
+	__u8			redirected:1;
+	__u8			from_ingress:1;
 #endif
 #ifdef CONFIG_TLS_DEVICE
 	__u8			decrypted:1;
@@ -4432,5 +4434,31 @@ static inline __wsum lco_csum(struct sk_buff *skb)
 	return csum_partial(l4_hdr, csum_start - l4_hdr, partial);
 }
 
+static inline bool skb_is_redirected(const struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_REDIRECT
+	return skb->redirected;
+#else
+	return false;
+#endif
+}
+
+static inline void skb_set_redirected(struct sk_buff *skb, bool from_ingress)
+{
+#ifdef CONFIG_NET_REDIRECT
+	skb->redirected = 1;
+	skb->from_ingress = from_ingress;
+	if (skb->from_ingress)
+		skb->tstamp = 0;
+#endif
+}
+
+static inline void skb_reset_redirect(struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_REDIRECT
+	skb->redirected = 0;
+#endif
+}
+
 #endif	/* __KERNEL__ */
 #endif	/* _LINUX_SKBUFF_H */
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 1edbb3a20748..59dc1976341e 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -187,6 +187,7 @@ static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src,
 	dst->sg.data[which] = src->sg.data[which];
 	dst->sg.data[which].length  = size;
 	dst->sg.size		   += size;
+	src->sg.size		   -= size;
 	src->sg.data[which].length -= size;
 	src->sg.data[which].offset += size;
 }
@@ -449,4 +450,12 @@ static inline void psock_progs_drop(struct sk_psock_progs *progs)
 	psock_set_prog(&progs->skb_verdict, NULL);
 }
 
+int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb);
+
+static inline bool sk_psock_strp_enabled(struct sk_psock *psock)
+{
+	if (!psock)
+		return false;
+	return psock->parser.enabled;
+}
 #endif /* _LINUX_SKMSG_H */
diff --git a/include/linux/soc/qcom/mdt_loader.h b/include/linux/soc/qcom/mdt_loader.h
index 944b06aefb0f..e600baec6825 100644
--- a/include/linux/soc/qcom/mdt_loader.h
+++ b/include/linux/soc/qcom/mdt_loader.h
@@ -21,4 +21,6 @@ int qcom_mdt_load_no_init(struct device *dev, const struct firmware *fw,
 			  const char *fw_name, int pas_id, void *mem_region,
 			  phys_addr_t mem_phys, size_t mem_size,
 			  phys_addr_t *reloc_base);
+void *qcom_mdt_read_metadata(const struct firmware *fw, size_t *data_len);
+
 #endif
diff --git a/include/linux/string.h b/include/linux/string.h
index 4deb11f7976b..375750448f42 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -250,6 +250,31 @@ void __read_overflow3(void) __compiletime_error("detected read beyond size of ob
 void __write_overflow(void) __compiletime_error("detected write beyond size of object passed as 1st parameter");
 
 #if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE)
+
+#ifdef CONFIG_KASAN
+extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr);
+extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp);
+extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy);
+extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove);
+extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset);
+extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat);
+extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy);
+extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen);
+extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat);
+extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy);
+#else
+#define __underlying_memchr	__builtin_memchr
+#define __underlying_memcmp	__builtin_memcmp
+#define __underlying_memcpy	__builtin_memcpy
+#define __underlying_memmove	__builtin_memmove
+#define __underlying_memset	__builtin_memset
+#define __underlying_strcat	__builtin_strcat
+#define __underlying_strcpy	__builtin_strcpy
+#define __underlying_strlen	__builtin_strlen
+#define __underlying_strncat	__builtin_strncat
+#define __underlying_strncpy	__builtin_strncpy
+#endif
+
 __FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size)
 {
 	size_t p_size = __builtin_object_size(p, 0);
@@ -257,14 +282,14 @@ __FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size)
 		__write_overflow();
 	if (p_size < size)
 		fortify_panic(__func__);
-	return __builtin_strncpy(p, q, size);
+	return __underlying_strncpy(p, q, size);
 }
 
 __FORTIFY_INLINE char *strcat(char *p, const char *q)
 {
 	size_t p_size = __builtin_object_size(p, 0);
 	if (p_size == (size_t)-1)
-		return __builtin_strcat(p, q);
+		return __underlying_strcat(p, q);
 	if (strlcat(p, q, p_size) >= p_size)
 		fortify_panic(__func__);
 	return p;
@@ -278,7 +303,7 @@ __FORTIFY_INLINE __kernel_size_t strlen(const char *p)
 	/* Work around gcc excess stack consumption issue */
 	if (p_size == (size_t)-1 ||
 	    (__builtin_constant_p(p[p_size - 1]) && p[p_size - 1] == '\0'))
-		return __builtin_strlen(p);
+		return __underlying_strlen(p);
 	ret = strnlen(p, p_size);
 	if (p_size <= ret)
 		fortify_panic(__func__);
@@ -311,7 +336,7 @@ __FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size)
 			__write_overflow();
 		if (len >= p_size)
 			fortify_panic(__func__);
-		__builtin_memcpy(p, q, len);
+		__underlying_memcpy(p, q, len);
 		p[len] = '\0';
 	}
 	return ret;
@@ -324,12 +349,12 @@ __FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count)
 	size_t p_size = __builtin_object_size(p, 0);
 	size_t q_size = __builtin_object_size(q, 0);
 	if (p_size == (size_t)-1 && q_size == (size_t)-1)
-		return __builtin_strncat(p, q, count);
+		return __underlying_strncat(p, q, count);
 	p_len = strlen(p);
 	copy_len = strnlen(q, count);
 	if (p_size < p_len + copy_len + 1)
 		fortify_panic(__func__);
-	__builtin_memcpy(p + p_len, q, copy_len);
+	__underlying_memcpy(p + p_len, q, copy_len);
 	p[p_len + copy_len] = '\0';
 	return p;
 }
@@ -341,7 +366,7 @@ __FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size)
 		__write_overflow();
 	if (p_size < size)
 		fortify_panic(__func__);
-	return __builtin_memset(p, c, size);
+	return __underlying_memset(p, c, size);
 }
 
 __FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size)
@@ -356,7 +381,7 @@ __FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size)
 	}
 	if (p_size < size || q_size < size)
 		fortify_panic(__func__);
-	return __builtin_memcpy(p, q, size);
+	return __underlying_memcpy(p, q, size);
 }
 
 __FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size)
@@ -371,7 +396,7 @@ __FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size)
 	}
 	if (p_size < size || q_size < size)
 		fortify_panic(__func__);
-	return __builtin_memmove(p, q, size);
+	return __underlying_memmove(p, q, size);
 }
 
 extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan);
@@ -397,7 +422,7 @@ __FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size)
 	}
 	if (p_size < size || q_size < size)
 		fortify_panic(__func__);
-	return __builtin_memcmp(p, q, size);
+	return __underlying_memcmp(p, q, size);
 }
 
 __FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size)
@@ -407,7 +432,7 @@ __FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size)
 		__read_overflow();
 	if (p_size < size)
 		fortify_panic(__func__);
-	return __builtin_memchr(p, c, size);
+	return __underlying_memchr(p, c, size);
 }
 
 void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv);
@@ -438,11 +463,22 @@ __FORTIFY_INLINE char *strcpy(char *p, const char *q)
 	size_t p_size = __builtin_object_size(p, 0);
 	size_t q_size = __builtin_object_size(q, 0);
 	if (p_size == (size_t)-1 && q_size == (size_t)-1)
-		return __builtin_strcpy(p, q);
+		return __underlying_strcpy(p, q);
 	memcpy(p, q, strlen(q) + 1);
 	return p;
 }
 
+/* Don't use these outside the FORITFY_SOURCE implementation */
+#undef __underlying_memchr
+#undef __underlying_memcmp
+#undef __underlying_memcpy
+#undef __underlying_memmove
+#undef __underlying_memset
+#undef __underlying_strcat
+#undef __underlying_strcpy
+#undef __underlying_strlen
+#undef __underlying_strncat
+#undef __underlying_strncpy
 #endif
 
 /**
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 6e8073140a5d..8d1873739afa 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -233,5 +233,10 @@ static inline int rpc_reply_expected(struct rpc_task *task)
 		(task->tk_msg.rpc_proc->p_decode != NULL);
 }
 
+static inline void rpc_task_close_connection(struct rpc_task *task)
+{
+	if (task->tk_xprt)
+		xprt_force_disconnect(task->tk_xprt);
+}
 #endif /* __KERNEL__ */
 #endif /* _LINUX_SUNRPC_CLNT_H */
diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h
index 5ac5db4d295f..7a65ab1fba0d 100644
--- a/include/linux/sunrpc/gss_api.h
+++ b/include/linux/sunrpc/gss_api.h
@@ -22,6 +22,7 @@
 struct gss_ctx {
 	struct gss_api_mech	*mech_type;
 	void			*internal_ctx_id;
+	unsigned int		slack, align;
 };
 
 #define GSS_C_NO_BUFFER		((struct xdr_netobj) 0)
@@ -49,7 +50,7 @@ int gss_import_sec_context(
 		size_t			bufsize,
 		struct gss_api_mech	*mech,
 		struct gss_ctx		**ctx_id,
-		time_t			*endtime,
+		time64_t		*endtime,
 		gfp_t			gfp_mask);
 u32 gss_get_mic(
 		struct gss_ctx		*ctx_id,
@@ -67,6 +68,7 @@ u32 gss_wrap(
 u32 gss_unwrap(
 		struct gss_ctx		*ctx_id,
 		int			offset,
+		int			len,
 		struct xdr_buf		*inbuf);
 u32 gss_delete_sec_context(
 		struct gss_ctx		**ctx_id);
@@ -83,6 +85,7 @@ struct pf_desc {
 	u32	service;
 	char	*name;
 	char	*auth_domain_name;
+	struct auth_domain *domain;
 	bool	datatouch;
 };
 
@@ -109,7 +112,7 @@ struct gss_api_ops {
 			const void		*input_token,
 			size_t			bufsize,
 			struct gss_ctx		*ctx_id,
-			time_t			*endtime,
+			time64_t		*endtime,
 			gfp_t			gfp_mask);
 	u32 (*gss_get_mic)(
 			struct gss_ctx		*ctx_id,
@@ -127,6 +130,7 @@ struct gss_api_ops {
 	u32 (*gss_unwrap)(
 			struct gss_ctx		*ctx_id,
 			int			offset,
+			int			len,
 			struct xdr_buf		*buf);
 	void (*gss_delete_sec_context)(
 			void			*internal_ctx_id);
diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h
index 02c0412e368c..e8f8ffe7448b 100644
--- a/include/linux/sunrpc/gss_krb5.h
+++ b/include/linux/sunrpc/gss_krb5.h
@@ -83,7 +83,7 @@ struct gss_krb5_enctype {
 	u32 (*encrypt_v2) (struct krb5_ctx *kctx, u32 offset,
 			   struct xdr_buf *buf,
 			   struct page **pages); /* v2 encryption function */
-	u32 (*decrypt_v2) (struct krb5_ctx *kctx, u32 offset,
+	u32 (*decrypt_v2) (struct krb5_ctx *kctx, u32 offset, u32 len,
 			   struct xdr_buf *buf, u32 *headskip,
 			   u32 *tailskip);	/* v2 decryption function */
 };
@@ -106,9 +106,9 @@ struct krb5_ctx {
 	struct crypto_sync_skcipher *initiator_enc_aux;
 	u8			Ksess[GSS_KRB5_MAX_KEYLEN]; /* session key */
 	u8			cksum[GSS_KRB5_MAX_KEYLEN];
-	s32			endtime;
 	atomic_t		seq_send;
 	atomic64_t		seq_send64;
+	time64_t		endtime;
 	struct xdr_netobj	mech_used;
 	u8			initiator_sign[GSS_KRB5_MAX_KEYLEN];
 	u8			acceptor_sign[GSS_KRB5_MAX_KEYLEN];
@@ -255,7 +255,7 @@ gss_wrap_kerberos(struct gss_ctx *ctx_id, int offset,
 		struct xdr_buf *outbuf, struct page **pages);
 
 u32
-gss_unwrap_kerberos(struct gss_ctx *ctx_id, int offset,
+gss_unwrap_kerberos(struct gss_ctx *ctx_id, int offset, int len,
 		struct xdr_buf *buf);
 
 
@@ -312,7 +312,7 @@ gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset,
 		     struct page **pages);
 
 u32
-gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset,
+gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, u32 len,
 		     struct xdr_buf *buf, u32 *plainoffset,
 		     u32 *plainlen);
 
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 1afe38eb33f7..82665ff360fd 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -517,6 +517,9 @@ void		   svc_wake_up(struct svc_serv *);
 void		   svc_reserve(struct svc_rqst *rqstp, int space);
 struct svc_pool *  svc_pool_for_cpu(struct svc_serv *serv, int cpu);
 char *		   svc_print_addr(struct svc_rqst *, char *, size_t);
+int		   svc_encode_read_payload(struct svc_rqst *rqstp,
+					   unsigned int offset,
+					   unsigned int length);
 unsigned int	   svc_fill_write_vector(struct svc_rqst *rqstp,
 					 struct page **pages,
 					 struct kvec *first, size_t total);
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 981f0d726ad4..9f588f923fe4 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -136,6 +136,8 @@ struct svc_rdma_recv_ctxt {
 	unsigned int		rc_page_count;
 	unsigned int		rc_hdr_count;
 	u32			rc_inv_rkey;
+	unsigned int		rc_read_payload_offset;
+	unsigned int		rc_read_payload_length;
 	struct page		*rc_pages[RPCSVC_MAXPAGES];
 };
 
@@ -161,6 +163,7 @@ extern bool svc_rdma_post_recvs(struct svcxprt_rdma *rdma);
 extern void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma,
 				   struct svc_rdma_recv_ctxt *ctxt);
 extern void svc_rdma_flush_recv_queues(struct svcxprt_rdma *rdma);
+extern void svc_rdma_release_rqst(struct svc_rqst *rqstp);
 extern int svc_rdma_recvfrom(struct svc_rqst *);
 
 /* svc_rdma_rw.c */
@@ -169,7 +172,9 @@ extern int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma,
 				    struct svc_rqst *rqstp,
 				    struct svc_rdma_recv_ctxt *head, __be32 *p);
 extern int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma,
-				     __be32 *wr_ch, struct xdr_buf *xdr);
+				     __be32 *wr_ch, struct xdr_buf *xdr,
+				     unsigned int offset,
+				     unsigned long length);
 extern int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma,
 				     __be32 *rp_ch, bool writelist,
 				     struct xdr_buf *xdr);
@@ -188,6 +193,8 @@ extern int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
 				  struct svc_rdma_send_ctxt *ctxt,
 				  struct xdr_buf *xdr, __be32 *wr_lst);
 extern int svc_rdma_sendto(struct svc_rqst *);
+extern int svc_rdma_read_payload(struct svc_rqst *rqstp, unsigned int offset,
+				 unsigned int length);
 
 /* svc_rdma_transport.c */
 extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *);
diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index ea6f46be9cb7..9e1e046de176 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -21,6 +21,8 @@ struct svc_xprt_ops {
 	int		(*xpo_has_wspace)(struct svc_xprt *);
 	int		(*xpo_recvfrom)(struct svc_rqst *);
 	int		(*xpo_sendto)(struct svc_rqst *);
+	int		(*xpo_read_payload)(struct svc_rqst *, unsigned int,
+					    unsigned int);
 	void		(*xpo_release_rqst)(struct svc_rqst *);
 	void		(*xpo_detach)(struct svc_xprt *);
 	void		(*xpo_free)(struct svc_xprt *);
diff --git a/include/linux/sunrpc/svcauth_gss.h b/include/linux/sunrpc/svcauth_gss.h
index a4528b26c8aa..d229d27ab19e 100644
--- a/include/linux/sunrpc/svcauth_gss.h
+++ b/include/linux/sunrpc/svcauth_gss.h
@@ -21,7 +21,8 @@ int gss_svc_init(void);
 void gss_svc_shutdown(void);
 int gss_svc_init_net(struct net *net);
 void gss_svc_shutdown_net(struct net *net);
-int svcauth_gss_register_pseudoflavor(u32 pseudoflavor, char * name);
+struct auth_domain *svcauth_gss_register_pseudoflavor(u32 pseudoflavor,
+						      char *name);
 u32 svcauth_gss_flavor(struct auth_domain *dom);
 
 #endif /* __KERNEL__ */
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 9ee3970ba59c..f47909e75cdb 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -179,7 +179,8 @@ xdr_adjust_iovec(struct kvec *iov, __be32 *p)
 extern void xdr_shift_buf(struct xdr_buf *, size_t);
 extern void xdr_buf_from_iov(struct kvec *, struct xdr_buf *);
 extern int xdr_buf_subsegment(struct xdr_buf *, struct xdr_buf *, unsigned int, unsigned int);
-extern int xdr_buf_read_netobj(struct xdr_buf *, struct xdr_netobj *, unsigned int);
+extern int xdr_buf_read_mic(struct xdr_buf *, struct xdr_netobj *, unsigned int);
+extern void xdr_buf_trim(struct xdr_buf *, unsigned int);
 extern int read_bytes_from_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int);
 extern int write_bytes_to_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int);
 
diff --git a/include/linux/swab.h b/include/linux/swab.h
index e466fd159c85..bcff5149861a 100644
--- a/include/linux/swab.h
+++ b/include/linux/swab.h
@@ -7,6 +7,7 @@
 # define swab16 __swab16
 # define swab32 __swab32
 # define swab64 __swab64
+# define swab __swab
 # define swahw32 __swahw32
 # define swahb32 __swahb32
 # define swab16p __swab16p
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 4d961668e5fc..8ca162c7c4c4 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -363,7 +363,8 @@ static inline void num_poisoned_pages_inc(void)
 }
 #endif
 
-#if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION)
+#if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION) || \
+    defined(CONFIG_DEVICE_PRIVATE)
 static inline int non_swap_entry(swp_entry_t entry)
 {
 	return swp_type(entry) >= MAX_SWAPFILES;
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 9a478a0cd3a2..908e1fa07586 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -221,6 +221,8 @@ struct tcp_sock {
 	} rack;
 	u16	advmss;		/* Advertised MSS			*/
 	u8	compressed_ack;
+	u8	tlp_retrans:1,	/* TLP is a retransmission */
+		unused_1:7;
 	u32	chrono_start;	/* Start time in jiffies of a TCP chrono */
 	u32	chrono_stat[3];	/* Time in jiffies for chrono_stat stats */
 	u8	chrono_type:2,	/* current chronograph type */
@@ -243,7 +245,7 @@ struct tcp_sock {
 		save_syn:1,	/* Save headers of SYN packet */
 		is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */
 		syn_smc:1;	/* SYN includes SMC */
-	u32	tlp_high_seq;	/* snd_nxt at the time of TLP retransmit. */
+	u32	tlp_high_seq;	/* snd_nxt at the time of TLP */
 
 	u64	tcp_wstamp_ns;	/* departure time for next sent data packet */
 	u64	tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */
@@ -395,7 +397,7 @@ struct tcp_sock {
 	/* fastopen_rsk points to request_sock that resulted in this big
 	 * socket. Used to retransmit SYNACKs etc.
 	 */
-	struct request_sock *fastopen_rsk;
+	struct request_sock __rcu *fastopen_rsk;
 	u32	*saved_syn;
 };
 
@@ -448,8 +450,8 @@ static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk)
 
 static inline bool tcp_passive_fastopen(const struct sock *sk)
 {
-	return (sk->sk_state == TCP_SYN_RECV &&
-		tcp_sk(sk)->fastopen_rsk != NULL);
+	return sk->sk_state == TCP_SYN_RECV &&
+	       rcu_access_pointer(tcp_sk(sk)->fastopen_rsk) != NULL;
 }
 
 static inline void fastopen_queue_tune(struct sock *sk, int backlog)
diff --git a/include/linux/tnum.h b/include/linux/tnum.h
index c7dc2b5902c0..06b9c20cc77e 100644
--- a/include/linux/tnum.h
+++ b/include/linux/tnum.h
@@ -26,7 +26,7 @@ struct tnum tnum_lshift(struct tnum a, u8 shift);
 /* Shift (rsh) a tnum right (by a fixed shift) */
 struct tnum tnum_rshift(struct tnum a, u8 shift);
 /* Shift (arsh) a tnum right (by a fixed min_shift) */
-struct tnum tnum_arshift(struct tnum a, u8 min_shift);
+struct tnum tnum_arshift(struct tnum a, u8 min_shift, u8 insn_bitness);
 /* Add two tnums, return @a + @b */
 struct tnum tnum_add(struct tnum a, struct tnum b);
 /* Subtract two tnums, return @a - @b */
diff --git a/include/linux/tpm.h b/include/linux/tpm.h
index 53c0ea9ec9df..77fdc988c610 100644
--- a/include/linux/tpm.h
+++ b/include/linux/tpm.h
@@ -93,6 +93,7 @@ struct tpm_space {
 	u8 *context_buf;
 	u32 session_tbl[3];
 	u8 *session_buf;
+	u32 buf_size;
 };
 
 struct tpm_bios_log {
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 8a62731673f7..84bc84f00e8f 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -539,6 +539,7 @@ extern int trace_event_get_offsets(struct trace_event_call *call);
 
 #define is_signed_type(type)	(((type)(-1)) < (type)1)
 
+int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set);
 int trace_set_clr_event(const char *system, const char *event, int set);
 
 /*
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 1fb11daa5c53..57ce5af258a3 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -362,7 +362,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 		static const char *___tp_str __tracepoint_string = str; \
 		___tp_str;						\
 	})
-#define __tracepoint_string	__attribute__((section("__tracepoint_str")))
+#define __tracepoint_string	__attribute__((section("__tracepoint_str"), used))
 #else
 /*
  * tracepoint_string() is used to save the string address for userspace
diff --git a/include/linux/tty.h b/include/linux/tty.h
index bfa4e2ee94a9..a99e9b8e4e31 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -66,7 +66,7 @@ struct tty_buffer {
 	int read;
 	int flags;
 	/* Data points here */
-	unsigned long data[0];
+	unsigned long data[];
 };
 
 /* Values for .flags field of tty_buffer */
@@ -225,6 +225,8 @@ struct tty_port_client_operations {
 	void (*write_wakeup)(struct tty_port *port);
 };
 
+extern const struct tty_port_client_operations tty_port_default_client_ops;
+
 struct tty_port {
 	struct tty_bufhead	buf;		/* Locked internally */
 	struct tty_struct	*tty;		/* Back pointer */
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index dac56e323671..2dd998f754e8 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -240,6 +240,17 @@ extern long probe_kernel_read(void *dst, const void *src, size_t size);
 extern long __probe_kernel_read(void *dst, const void *src, size_t size);
 
 /*
+ * probe_user_read(): safely attempt to read from a location in user space
+ * @dst: pointer to the buffer that shall take the data
+ * @src: address to read from
+ * @size: size of the data chunk
+ *
+ * Safely read from address @src to the buffer at @dst.  If a kernel fault
+ * happens, handle that and return -EFAULT.
+ */
+extern long probe_user_read(void *dst, const void __user *src, size_t size);
+
+/*
  * probe_kernel_write(): safely attempt to write to a location
  * @dst: address to write to
  * @src: pointer to the data that shall be written
@@ -251,7 +262,22 @@ extern long __probe_kernel_read(void *dst, const void *src, size_t size);
 extern long notrace probe_kernel_write(void *dst, const void *src, size_t size);
 extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size);
 
+/*
+ * probe_user_write(): safely attempt to write to a location in user space
+ * @dst: address to write to
+ * @src: pointer to the data that shall be written
+ * @size: size of the data chunk
+ *
+ * Safely write to address @dst from the buffer at @src.  If a kernel fault
+ * happens, handle that and return -EFAULT.
+ */
+extern long notrace probe_user_write(void __user *dst, const void *src, size_t size);
+extern long notrace __probe_user_write(void __user *dst, const void *src, size_t size);
+
 extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count);
+extern long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr,
+				     long count);
+extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count);
 
 /**
  * probe_kernel_address(): safely attempt to read from a location
diff --git a/include/linux/unaligned/generic.h b/include/linux/unaligned/generic.h
index 57d3114656e5..303289492859 100644
--- a/include/linux/unaligned/generic.h
+++ b/include/linux/unaligned/generic.h
@@ -2,6 +2,8 @@
 #ifndef _LINUX_UNALIGNED_GENERIC_H
 #define _LINUX_UNALIGNED_GENERIC_H
 
+#include <linux/types.h>
+
 /*
  * Cause a link-time error if we try an unaligned access other than
  * 1,2,4 or 8 bytes long
@@ -66,4 +68,48 @@ extern void __bad_unaligned_access_size(void);
 	}								\
 	(void)0; })
 
+static inline u32 __get_unaligned_be24(const u8 *p)
+{
+	return p[0] << 16 | p[1] << 8 | p[2];
+}
+
+static inline u32 get_unaligned_be24(const void *p)
+{
+	return __get_unaligned_be24(p);
+}
+
+static inline u32 __get_unaligned_le24(const u8 *p)
+{
+	return p[0] | p[1] << 8 | p[2] << 16;
+}
+
+static inline u32 get_unaligned_le24(const void *p)
+{
+	return __get_unaligned_le24(p);
+}
+
+static inline void __put_unaligned_be24(const u32 val, u8 *p)
+{
+	*p++ = val >> 16;
+	*p++ = val >> 8;
+	*p++ = val;
+}
+
+static inline void put_unaligned_be24(const u32 val, void *p)
+{
+	__put_unaligned_be24(val, p);
+}
+
+static inline void __put_unaligned_le24(const u32 val, u8 *p)
+{
+	*p++ = val;
+	*p++ = val >> 8;
+	*p++ = val >> 16;
+}
+
+static inline void put_unaligned_le24(const u32 val, void *p)
+{
+	__put_unaligned_le24(val, p);
+}
+
 #endif /* _LINUX_UNALIGNED_GENERIC_H */
diff --git a/include/linux/unicode.h b/include/linux/unicode.h
index aec2c6d800aa..990aa97d8049 100644
--- a/include/linux/unicode.h
+++ b/include/linux/unicode.h
@@ -17,6 +17,9 @@ int utf8_strncmp(const struct unicode_map *um,
 
 int utf8_strncasecmp(const struct unicode_map *um,
 		 const struct qstr *s1, const struct qstr *s2);
+int utf8_strncasecmp_folded(const struct unicode_map *um,
+			    const struct qstr *cf,
+			    const struct qstr *s1);
 
 int utf8_normalize(const struct unicode_map *um, const struct qstr *str,
 		   unsigned char *dest, size_t dlen);
diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h
index 8675e145ea8b..2040696d75b6 100644
--- a/include/linux/usb/composite.h
+++ b/include/linux/usb/composite.h
@@ -249,6 +249,9 @@ int usb_function_activate(struct usb_function *);
 
 int usb_interface_id(struct usb_configuration *, struct usb_function *);
 
+int config_ep_by_speed_and_alt(struct usb_gadget *g, struct usb_function *f,
+				struct usb_ep *_ep, u8 alt);
+
 int config_ep_by_speed(struct usb_gadget *g, struct usb_function *f,
 			struct usb_ep *_ep);
 
diff --git a/include/linux/usb/ehci_def.h b/include/linux/usb/ehci_def.h
index a15ce99dfc2d..78e006355557 100644
--- a/include/linux/usb/ehci_def.h
+++ b/include/linux/usb/ehci_def.h
@@ -151,7 +151,7 @@ struct ehci_regs {
 #define PORT_OWNER	(1<<13)		/* true: companion hc owns this port */
 #define PORT_POWER	(1<<12)		/* true: has power (see PPC) */
 #define PORT_USB11(x) (((x)&(3<<10)) == (1<<10))	/* USB 1.1 device */
-/* 11:10 for detecting lowspeed devices (reset vs release ownership) */
+#define PORT_LS_MASK	(3<<10)		/* Link status (SE0, K or J */
 /* 9 reserved */
 #define PORT_LPM	(1<<9)		/* LPM transaction */
 #define PORT_RESET	(1<<8)		/* reset port */
diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h
index 7595056b96c1..cbda5cfbcec1 100644
--- a/include/linux/usb/gadget.h
+++ b/include/linux/usb/gadget.h
@@ -369,6 +369,7 @@ struct usb_gadget_ops {
  * @connected: True if gadget is connected.
  * @lpm_capable: If the gadget max_speed is FULL or HIGH, this flag
  *	indicates that it supports LPM as per the LPM ECN & errata.
+ * @irq: the interrupt number for device controller.
  *
  * Gadgets have a mostly-portable "gadget driver" implementing device
  * functions, handling all usb configurations and interfaces.  Gadget
@@ -423,6 +424,7 @@ struct usb_gadget {
 	unsigned			deactivated:1;
 	unsigned			connected:1;
 	unsigned			lpm_capable:1;
+	int				irq;
 };
 #define work_to_gadget(w)	(container_of((w), struct usb_gadget, work))
 
diff --git a/include/linux/usb/irda.h b/include/linux/usb/irda.h
index 396d2b043e64..556a801efce3 100644
--- a/include/linux/usb/irda.h
+++ b/include/linux/usb/irda.h
@@ -119,11 +119,22 @@ struct usb_irda_cs_descriptor {
  * 6 - 115200 bps
  * 7 - 576000 bps
  * 8 - 1.152 Mbps
- * 9 - 5 mbps
+ * 9 - 4 Mbps
  * 10..15 - Reserved
  */
 #define USB_IRDA_STATUS_LINK_SPEED	0x0f
 
+#define USB_IRDA_LS_NO_CHANGE		0
+#define USB_IRDA_LS_2400		1
+#define USB_IRDA_LS_9600		2
+#define USB_IRDA_LS_19200		3
+#define USB_IRDA_LS_38400		4
+#define USB_IRDA_LS_57600		5
+#define USB_IRDA_LS_115200		6
+#define USB_IRDA_LS_576000		7
+#define USB_IRDA_LS_1152000		8
+#define USB_IRDA_LS_4000000		9
+
 /* The following is a 4-bit value used only for
  * outbound header:
  *
diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h
index a1be64c9940f..5e4c497f54d6 100644
--- a/include/linux/usb/quirks.h
+++ b/include/linux/usb/quirks.h
@@ -69,4 +69,7 @@
 /* Hub needs extra delay after resetting its port. */
 #define USB_QUIRK_HUB_SLOW_RESET		BIT(14)
 
+/* device has endpoints that should be ignored */
+#define USB_QUIRK_ENDPOINT_IGNORE		BIT(15)
+
 #endif /* __LINUX_USB_QUIRKS_H */
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 0d1fe9297ac6..e8a924eeea3d 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -3,6 +3,8 @@
 #define _LINUX_VIRTIO_NET_H
 
 #include <linux/if_vlan.h>
+#include <uapi/linux/tcp.h>
+#include <uapi/linux/udp.h>
 #include <uapi/linux/virtio_net.h>
 
 static inline int virtio_net_hdr_set_proto(struct sk_buff *skb,
@@ -28,17 +30,26 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 					bool little_endian)
 {
 	unsigned int gso_type = 0;
+	unsigned int thlen = 0;
+	unsigned int p_off = 0;
+	unsigned int ip_proto;
 
 	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
 		case VIRTIO_NET_HDR_GSO_TCPV4:
 			gso_type = SKB_GSO_TCPV4;
+			ip_proto = IPPROTO_TCP;
+			thlen = sizeof(struct tcphdr);
 			break;
 		case VIRTIO_NET_HDR_GSO_TCPV6:
 			gso_type = SKB_GSO_TCPV6;
+			ip_proto = IPPROTO_TCP;
+			thlen = sizeof(struct tcphdr);
 			break;
 		case VIRTIO_NET_HDR_GSO_UDP:
 			gso_type = SKB_GSO_UDP;
+			ip_proto = IPPROTO_UDP;
+			thlen = sizeof(struct udphdr);
 			break;
 		default:
 			return -EINVAL;
@@ -57,16 +68,23 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 
 		if (!skb_partial_csum_set(skb, start, off))
 			return -EINVAL;
+
+		p_off = skb_transport_offset(skb) + thlen;
+		if (p_off > skb_headlen(skb))
+			return -EINVAL;
 	} else {
 		/* gso packets without NEEDS_CSUM do not set transport_offset.
 		 * probe and drop if does not match one of the above types.
 		 */
 		if (gso_type && skb->network_header) {
+			struct flow_keys_basic keys;
+
 			if (!skb->protocol)
 				virtio_net_hdr_set_proto(skb, hdr);
 retry:
-			skb_probe_transport_header(skb);
-			if (!skb_transport_header_was_set(skb)) {
+			if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys,
+							      NULL, 0, 0, 0,
+							      0)) {
 				/* UFO does not specify ipv4 or 6: try both */
 				if (gso_type & SKB_GSO_UDP &&
 				    skb->protocol == htons(ETH_P_IP)) {
@@ -75,18 +93,33 @@ retry:
 				}
 				return -EINVAL;
 			}
+
+			p_off = keys.control.thoff + thlen;
+			if (p_off > skb_headlen(skb) ||
+			    keys.basic.ip_proto != ip_proto)
+				return -EINVAL;
+
+			skb_set_transport_header(skb, keys.control.thoff);
+		} else if (gso_type) {
+			p_off = thlen;
+			if (p_off > skb_headlen(skb))
+				return -EINVAL;
 		}
 	}
 
 	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size);
+		struct skb_shared_info *shinfo = skb_shinfo(skb);
 
-		skb_shinfo(skb)->gso_size = gso_size;
-		skb_shinfo(skb)->gso_type = gso_type;
+		/* Too small packets are not really GSO ones. */
+		if (skb->len - p_off > gso_size) {
+			shinfo->gso_size = gso_size;
+			shinfo->gso_type = gso_type;
 
-		/* Header must be checked, and gso_segs computed. */
-		skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
-		skb_shinfo(skb)->gso_segs = 0;
+			/* Header must be checked, and gso_segs computed. */
+			shinfo->gso_type |= SKB_GSO_DODGY;
+			shinfo->gso_segs = 0;
+		}
 	}
 
 	return 0;
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 51e131245379..dda1f04b766f 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -112,12 +112,13 @@ extern void vunmap(const void *addr);
 
 extern int remap_vmalloc_range_partial(struct vm_area_struct *vma,
 				       unsigned long uaddr, void *kaddr,
-				       unsigned long size);
+				       unsigned long pgoff, unsigned long size);
 
 extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
 							unsigned long pgoff);
-void vmalloc_sync_all(void);
- 
+void vmalloc_sync_mappings(void);
+void vmalloc_sync_unmappings(void);
+
 /*
  *	Lowlevel-APIs (not for driver use!)
  */
diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h
index 8dc77e40bc03..ded5c48598f3 100644
--- a/include/linux/vt_kern.h
+++ b/include/linux/vt_kern.h
@@ -135,7 +135,7 @@ extern int do_unbind_con_driver(const struct consw *csw, int first, int last,
 			     int deflt);
 int vty_init(const struct file_operations *console_fops);
 
-extern char vt_dont_switch;
+extern bool vt_dont_switch;
 extern int default_utf8;
 extern int global_cursor_default;
 
diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 5921599b6dc4..b27ba7a0b8d7 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -1613,6 +1613,7 @@ static inline void *xas_next_marked(struct xa_state *xas, unsigned long max,
 								xa_mark_t mark)
 {
 	struct xa_node *node = xas->xa_node;
+	void *entry;
 	unsigned int offset;
 
 	if (unlikely(xas_not_node(node) || node->shift))
@@ -1624,7 +1625,10 @@ static inline void *xas_next_marked(struct xa_state *xas, unsigned long max,
 		return NULL;
 	if (offset == XA_CHUNK_SIZE)
 		return xas_find_marked(xas, max, mark);
-	return xa_entry(xas->xa, node, offset);
+	entry = xa_entry(xas->xa, node, offset);
+	if (!entry)
+		return xas_find_marked(xas, max, mark);
+	return entry;
 }
 
 /*
diff --git a/include/linux/xattr.h b/include/linux/xattr.h
index 6dad031be3c2..3a71ad716da5 100644
--- a/include/linux/xattr.h
+++ b/include/linux/xattr.h
@@ -51,8 +51,10 @@ ssize_t vfs_getxattr(struct dentry *, const char *, void *, size_t);
 ssize_t vfs_listxattr(struct dentry *d, char *list, size_t size);
 int __vfs_setxattr(struct dentry *, struct inode *, const char *, const void *, size_t, int);
 int __vfs_setxattr_noperm(struct dentry *, const char *, const void *, size_t, int);
+int __vfs_setxattr_locked(struct dentry *, const char *, const void *, size_t, int, struct inode **);
 int vfs_setxattr(struct dentry *, const char *, const void *, size_t, int);
 int __vfs_removexattr(struct dentry *, const char *);
+int __vfs_removexattr_locked(struct dentry *, const char *, struct inode **);
 int vfs_removexattr(struct dentry *, const char *);
 
 ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size);
diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h
index 52875e3eee71..1409230ad3a4 100644
--- a/include/media/dvb-usb-ids.h
+++ b/include/media/dvb-usb-ids.h
@@ -388,6 +388,8 @@
 #define USB_PID_MYGICA_D689				0xd811
 #define USB_PID_MYGICA_T230				0xc688
 #define USB_PID_MYGICA_T230C				0xc689
+#define USB_PID_MYGICA_T230C2				0xc68a
+#define USB_PID_MYGICA_T230C_LITE			0xc699
 #define USB_PID_ELGATO_EYETV_DIVERSITY			0x0011
 #define USB_PID_ELGATO_EYETV_DTT			0x0021
 #define USB_PID_ELGATO_EYETV_DTT_2			0x003f
diff --git a/include/media/rc-map.h b/include/media/rc-map.h
index bebd3c4c6338..f9dce48409a5 100644
--- a/include/media/rc-map.h
+++ b/include/media/rc-map.h
@@ -280,6 +280,7 @@ struct rc_map *rc_map_get(const char *name);
 #define RC_MAP_VIDEOMATE_K100            "rc-videomate-k100"
 #define RC_MAP_VIDEOMATE_S350            "rc-videomate-s350"
 #define RC_MAP_VIDEOMATE_TV_PVR          "rc-videomate-tv-pvr"
+#define RC_MAP_KII_PRO                   "rc-videostrong-kii-pro"
 #define RC_MAP_WINFAST                   "rc-winfast"
 #define RC_MAP_WINFAST_USBII_DELUXE      "rc-winfast-usbii-deluxe"
 #define RC_MAP_SU3000                    "rc-su3000"
diff --git a/include/media/v4l2-device.h b/include/media/v4l2-device.h
index e0b8f2602670..a0e93f0ef62a 100644
--- a/include/media/v4l2-device.h
+++ b/include/media/v4l2-device.h
@@ -371,7 +371,7 @@ static inline bool v4l2_device_supports_requests(struct v4l2_device *v4l2_dev)
 		struct v4l2_subdev *__sd;				\
 									\
 		__v4l2_device_call_subdevs_p(v4l2_dev, __sd,		\
-			!(grpid) || __sd->grp_id == (grpid), o, f ,	\
+			(grpid) == 0 || __sd->grp_id == (grpid), o, f ,	\
 			##args);					\
 	} while (0)
 
@@ -403,7 +403,7 @@ static inline bool v4l2_device_supports_requests(struct v4l2_device *v4l2_dev)
 ({									\
 	struct v4l2_subdev *__sd;					\
 	__v4l2_device_call_subdevs_until_err_p(v4l2_dev, __sd,		\
-			!(grpid) || __sd->grp_id == (grpid), o, f ,	\
+			(grpid) == 0 || __sd->grp_id == (grpid), o, f ,	\
 			##args);					\
 })
 
@@ -431,8 +431,8 @@ static inline bool v4l2_device_supports_requests(struct v4l2_device *v4l2_dev)
 		struct v4l2_subdev *__sd;				\
 									\
 		__v4l2_device_call_subdevs_p(v4l2_dev, __sd,		\
-			!(grpmsk) || (__sd->grp_id & (grpmsk)), o, f ,	\
-			##args);					\
+			(grpmsk) == 0 || (__sd->grp_id & (grpmsk)), o,	\
+			f , ##args);					\
 	} while (0)
 
 /**
@@ -462,8 +462,8 @@ static inline bool v4l2_device_supports_requests(struct v4l2_device *v4l2_dev)
 ({									\
 	struct v4l2_subdev *__sd;					\
 	__v4l2_device_call_subdevs_until_err_p(v4l2_dev, __sd,		\
-			!(grpmsk) || (__sd->grp_id & (grpmsk)), o, f ,	\
-			##args);					\
+			(grpmsk) == 0 || (__sd->grp_id & (grpmsk)), o,	\
+			f , ##args);					\
 })
 
 
diff --git a/include/media/v4l2-rect.h b/include/media/v4l2-rect.h
index c86474dc7b55..8800a640c224 100644
--- a/include/media/v4l2-rect.h
+++ b/include/media/v4l2-rect.h
@@ -63,10 +63,10 @@ static inline void v4l2_rect_map_inside(struct v4l2_rect *r,
 		r->left = boundary->left;
 	if (r->top < boundary->top)
 		r->top = boundary->top;
-	if (r->left + r->width > boundary->width)
-		r->left = boundary->width - r->width;
-	if (r->top + r->height > boundary->height)
-		r->top = boundary->height - r->height;
+	if (r->left + r->width > boundary->left + boundary->width)
+		r->left = boundary->left + boundary->width - r->width;
+	if (r->top + r->height > boundary->top + boundary->height)
+		r->top = boundary->top + boundary->height - r->height;
 }
 
 /**
diff --git a/include/net/act_api.h b/include/net/act_api.h
index 3a1a72990fce..0ed71a918569 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -69,7 +69,8 @@ static inline void tcf_tm_dump(struct tcf_t *dtm, const struct tcf_t *stm)
 {
 	dtm->install = jiffies_to_clock_t(jiffies - stm->install);
 	dtm->lastuse = jiffies_to_clock_t(jiffies - stm->lastuse);
-	dtm->firstuse = jiffies_to_clock_t(jiffies - stm->firstuse);
+	dtm->firstuse = stm->firstuse ?
+		jiffies_to_clock_t(jiffies - stm->firstuse) : 0;
 	dtm->expires = jiffies_to_clock_t(stm->expires);
 }
 
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 3f62b347b04a..ab8b3eb53d4b 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -273,6 +273,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex,
 		      const struct in6_addr *addr);
 int ipv6_sock_ac_drop(struct sock *sk, int ifindex,
 		      const struct in6_addr *addr);
+void __ipv6_sock_ac_close(struct sock *sk);
 void ipv6_sock_ac_close(struct sock *sk);
 
 int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr);
diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h
index 1abae3c340a5..55b980b21f4b 100644
--- a/include/net/af_rxrpc.h
+++ b/include/net/af_rxrpc.h
@@ -16,6 +16,12 @@ struct sock;
 struct socket;
 struct rxrpc_call;
 
+enum rxrpc_interruptibility {
+	RXRPC_INTERRUPTIBLE,	/* Call is interruptible */
+	RXRPC_PREINTERRUPTIBLE,	/* Call can be cancelled whilst waiting for a slot */
+	RXRPC_UNINTERRUPTIBLE,	/* Call should not be interruptible at all */
+};
+
 /*
  * Debug ID counter for tracing.
  */
@@ -41,7 +47,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *,
 					   gfp_t,
 					   rxrpc_notify_rx_t,
 					   bool,
-					   bool,
+					   enum rxrpc_interruptibility,
 					   unsigned int);
 int rxrpc_kernel_send_data(struct socket *, struct rxrpc_call *,
 			   struct msghdr *, size_t,
@@ -53,14 +59,12 @@ bool rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *,
 void rxrpc_kernel_end_call(struct socket *, struct rxrpc_call *);
 void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *,
 			   struct sockaddr_rxrpc *);
-u64 rxrpc_kernel_get_rtt(struct socket *, struct rxrpc_call *);
+bool rxrpc_kernel_get_srtt(struct socket *, struct rxrpc_call *, u32 *);
 int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t,
 			       rxrpc_user_attach_call_t, unsigned long, gfp_t,
 			       unsigned int);
 void rxrpc_kernel_set_tx_length(struct socket *, struct rxrpc_call *, s64);
-bool rxrpc_kernel_check_life(const struct socket *, const struct rxrpc_call *,
-			     u32 *);
-void rxrpc_kernel_probe_life(struct socket *, struct rxrpc_call *);
+bool rxrpc_kernel_check_life(const struct socket *, const struct rxrpc_call *);
 u32 rxrpc_kernel_get_epoch(struct socket *, struct rxrpc_call *);
 bool rxrpc_kernel_get_reply_time(struct socket *, struct rxrpc_call *,
 				 ktime_t *);
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 8b13bd05befa..73bfed327f68 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3413,6 +3413,9 @@ struct cfg80211_update_owe_info {
  *
  * @start_radar_detection: Start radar detection in the driver.
  *
+ * @end_cac: End running CAC, probably because a related CAC
+ *	was finished on another phy.
+ *
  * @update_ft_ies: Provide updated Fast BSS Transition information to the
  *	driver. If the SME is in the driver/firmware, this information can be
  *	used in building Authentication and Reassociation Request frames.
@@ -3739,6 +3742,8 @@ struct cfg80211_ops {
 					 struct net_device *dev,
 					 struct cfg80211_chan_def *chandef,
 					 u32 cac_time_ms);
+	void	(*end_cac)(struct wiphy *wiphy,
+				struct net_device *dev);
 	int	(*update_ft_ies)(struct wiphy *wiphy, struct net_device *dev,
 				 struct cfg80211_update_ft_ies_params *ftie);
 	int	(*crit_proto_start)(struct wiphy *wiphy,
diff --git a/include/net/dst.h b/include/net/dst.h
index 4d61945d5d74..2fbb03797d14 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -401,7 +401,15 @@ static inline struct neighbour *dst_neigh_lookup(const struct dst_entry *dst, co
 static inline struct neighbour *dst_neigh_lookup_skb(const struct dst_entry *dst,
 						     struct sk_buff *skb)
 {
-	struct neighbour *n =  dst->ops->neigh_lookup(dst, skb, NULL);
+	struct neighbour *n = NULL;
+
+	/* The packets from tunnel devices (eg bareudp) may have only
+	 * metadata in the dst pointer of skb. Hence a pointer check of
+	 * neigh_lookup is needed.
+	 */
+	if (dst->ops->neigh_lookup)
+		n = dst->ops->neigh_lookup(dst, skb, NULL);
+
 	return IS_ERR(n) ? NULL : n;
 }
 
diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index b473df5b9512..10886c19cfc5 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -107,6 +107,7 @@ struct fib_rule_notifier_info {
 	[FRA_OIFNAME]	= { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \
 	[FRA_PRIORITY]	= { .type = NLA_U32 }, \
 	[FRA_FWMARK]	= { .type = NLA_U32 }, \
+	[FRA_TUN_ID]	= { .type = NLA_U64 }, \
 	[FRA_FWMASK]	= { .type = NLA_U32 }, \
 	[FRA_TABLE]     = { .type = NLA_U32 }, \
 	[FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, \
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 441577a78636..457ac35050cf 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -5,6 +5,7 @@
 #include <linux/types.h>
 #include <linux/in6.h>
 #include <linux/siphash.h>
+#include <linux/string.h>
 #include <uapi/linux/if_ether.h>
 
 /**
@@ -314,4 +315,12 @@ struct bpf_flow_dissector {
 	void			*data_end;
 };
 
+static inline void
+flow_dissector_init_keys(struct flow_dissector_key_control *key_control,
+			 struct flow_dissector_key_basic *key_basic)
+{
+	memset(key_control, 0, sizeof(*key_control));
+	memset(key_basic, 0, sizeof(*key_basic));
+}
+
 #endif
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 9292f1c588b7..2d9e67a69cbe 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -35,12 +35,6 @@ struct genl_info;
  *	do additional, common, filtering and return an error
  * @post_doit: called after an operation's doit callback, it may
  *	undo operations done by pre_doit, for example release locks
- * @mcast_bind: a socket bound to the given multicast group (which
- *	is given as the offset into the groups array)
- * @mcast_unbind: a socket was unbound from the given multicast group.
- *	Note that unbind() will not be called symmetrically if the
- *	generic netlink family is removed while there are still open
- *	sockets.
  * @attrbuf: buffer to store parsed attributes (private)
  * @mcgrps: multicast groups used by this family
  * @n_mcgrps: number of multicast groups
@@ -64,8 +58,6 @@ struct genl_family {
 	void			(*post_doit)(const struct genl_ops *ops,
 					     struct sk_buff *skb,
 					     struct genl_info *info);
-	int			(*mcast_bind)(struct net *net, int group);
-	void			(*mcast_unbind)(struct net *net, int group);
 	struct nlattr **	attrbuf;	/* private */
 	const struct genl_ops *	ops;
 	const struct genl_multicast_group *mcgrps;
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index c57d53e7e02c..1ba40380b4df 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -309,6 +309,10 @@ int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname,
 int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname,
 			       char __user *optval, unsigned int optlen);
 
+/* update the fast reuse flag when adding a socket */
+void inet_csk_update_fastreuse(struct inet_bind_bucket *tb,
+			       struct sock *sk);
+
 struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu);
 
 #define TCP_PINGPONG_THRESH	3
diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h
index c8e2bebd8d93..e1eaf1780288 100644
--- a/include/net/inet_ecn.h
+++ b/include/net/inet_ecn.h
@@ -4,6 +4,7 @@
 
 #include <linux/ip.h>
 #include <linux/skbuff.h>
+#include <linux/if_vlan.h>
 
 #include <net/inet_sock.h>
 #include <net/dsfield.h>
@@ -99,6 +100,20 @@ static inline int IP_ECN_set_ce(struct iphdr *iph)
 	return 1;
 }
 
+static inline int IP_ECN_set_ect1(struct iphdr *iph)
+{
+	u32 check = (__force u32)iph->check;
+
+	if ((iph->tos & INET_ECN_MASK) != INET_ECN_ECT_0)
+		return 0;
+
+	check += (__force u16)htons(0x100);
+
+	iph->check = (__force __sum16)(check + (check>=0xFFFF));
+	iph->tos ^= INET_ECN_MASK;
+	return 1;
+}
+
 static inline void IP_ECN_clear(struct iphdr *iph)
 {
 	iph->tos &= ~INET_ECN_MASK;
@@ -134,6 +149,22 @@ static inline int IP6_ECN_set_ce(struct sk_buff *skb, struct ipv6hdr *iph)
 	return 1;
 }
 
+static inline int IP6_ECN_set_ect1(struct sk_buff *skb, struct ipv6hdr *iph)
+{
+	__be32 from, to;
+
+	if ((ipv6_get_dsfield(iph) & INET_ECN_MASK) != INET_ECN_ECT_0)
+		return 0;
+
+	from = *(__be32 *)iph;
+	to = from ^ htonl(INET_ECN_MASK << 20);
+	*(__be32 *)iph = to;
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		skb->csum = csum_add(csum_sub(skb->csum, (__force __wsum)from),
+				     (__force __wsum)to);
+	return 1;
+}
+
 static inline void ipv6_copy_dscp(unsigned int dscp, struct ipv6hdr *inner)
 {
 	dscp &= ~INET_ECN_MASK;
@@ -142,7 +173,7 @@ static inline void ipv6_copy_dscp(unsigned int dscp, struct ipv6hdr *inner)
 
 static inline int INET_ECN_set_ce(struct sk_buff *skb)
 {
-	switch (skb->protocol) {
+	switch (skb_protocol(skb, true)) {
 	case cpu_to_be16(ETH_P_IP):
 		if (skb_network_header(skb) + sizeof(struct iphdr) <=
 		    skb_tail_pointer(skb))
@@ -159,6 +190,25 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb)
 	return 0;
 }
 
+static inline int INET_ECN_set_ect1(struct sk_buff *skb)
+{
+	switch (skb_protocol(skb, true)) {
+	case cpu_to_be16(ETH_P_IP):
+		if (skb_network_header(skb) + sizeof(struct iphdr) <=
+		    skb_tail_pointer(skb))
+			return IP_ECN_set_ect1(ip_hdr(skb));
+		break;
+
+	case cpu_to_be16(ETH_P_IPV6):
+		if (skb_network_header(skb) + sizeof(struct ipv6hdr) <=
+		    skb_tail_pointer(skb))
+			return IP6_ECN_set_ect1(skb, ipv6_hdr(skb));
+		break;
+	}
+
+	return 0;
+}
+
 /*
  * RFC 6040 4.2
  *  To decapsulate the inner header at the tunnel egress, a compliant
@@ -208,8 +258,12 @@ static inline int INET_ECN_decapsulate(struct sk_buff *skb,
 	int rc;
 
 	rc = __INET_ECN_decapsulate(outer, inner, &set_ce);
-	if (!rc && set_ce)
-		INET_ECN_set_ce(skb);
+	if (!rc) {
+		if (set_ce)
+			INET_ECN_set_ce(skb);
+		else if ((outer & INET_ECN_MASK) == INET_ECN_ECT_1)
+			INET_ECN_set_ect1(skb);
+	}
 
 	return rc;
 }
@@ -219,12 +273,16 @@ static inline int IP_ECN_decapsulate(const struct iphdr *oiph,
 {
 	__u8 inner;
 
-	if (skb->protocol == htons(ETH_P_IP))
+	switch (skb_protocol(skb, true)) {
+	case htons(ETH_P_IP):
 		inner = ip_hdr(skb)->tos;
-	else if (skb->protocol == htons(ETH_P_IPV6))
+		break;
+	case htons(ETH_P_IPV6):
 		inner = ipv6_get_dsfield(ipv6_hdr(skb));
-	else
+		break;
+	default:
 		return 0;
+	}
 
 	return INET_ECN_decapsulate(skb, oiph->tos, inner);
 }
@@ -234,12 +292,16 @@ static inline int IP6_ECN_decapsulate(const struct ipv6hdr *oipv6h,
 {
 	__u8 inner;
 
-	if (skb->protocol == htons(ETH_P_IP))
+	switch (skb_protocol(skb, true)) {
+	case htons(ETH_P_IP):
 		inner = ip_hdr(skb)->tos;
-	else if (skb->protocol == htons(ETH_P_IPV6))
+		break;
+	case htons(ETH_P_IPV6):
 		inner = ipv6_get_dsfield(ipv6_hdr(skb));
-	else
+		break;
+	default:
 		return 0;
+	}
 
 	return INET_ECN_decapsulate(skb, ipv6_get_dsfield(oipv6h), inner);
 }
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index d0019d3395cf..59802eb8d2cc 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -185,6 +185,12 @@ static inline spinlock_t *inet_ehash_lockp(
 
 int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo);
 
+static inline void inet_hashinfo2_free_mod(struct inet_hashinfo *h)
+{
+	kfree(h->lhash2);
+	h->lhash2 = NULL;
+}
+
 static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo)
 {
 	kvfree(hashinfo->ehash_locks);
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index ee7405e759ba..77c5a171703d 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -235,6 +235,7 @@ static inline bool ipv6_anycast_destination(const struct dst_entry *dst,
 
 	return rt->rt6i_flags & RTF_ANYCAST ||
 		(rt->rt6i_dst.plen < 127 &&
+		 !(rt->rt6i_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) &&
 		 ipv6_addr_equal(&rt->rt6i_dst.addr, daddr));
 }
 
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index bbeff32fb6cb..3cddf849d5b4 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -242,7 +242,6 @@ struct fib_dump_filter {
 	u32			table_id;
 	/* filter_set is an optimization that an entry is set */
 	bool			filter_set;
-	bool			dump_all_families;
 	unsigned char		protocol;
 	unsigned char		rt_type;
 	unsigned int		flags;
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index b71ad28fdc98..01e034774c5b 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1616,18 +1616,16 @@ static inline void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp)
 }
 #endif /* CONFIG_IP_VS_NFCT */
 
-/* Really using conntrack? */
-static inline bool ip_vs_conn_uses_conntrack(struct ip_vs_conn *cp,
-					     struct sk_buff *skb)
+/* Using old conntrack that can not be redirected to another real server? */
+static inline bool ip_vs_conn_uses_old_conntrack(struct ip_vs_conn *cp,
+						 struct sk_buff *skb)
 {
 #ifdef CONFIG_IP_VS_NFCT
 	enum ip_conntrack_info ctinfo;
 	struct nf_conn *ct;
 
-	if (!(cp->flags & IP_VS_CONN_F_NFCT))
-		return false;
 	ct = nf_ct_get(skb, &ctinfo);
-	if (ct)
+	if (ct && nf_ct_is_confirmed(ct))
 		return true;
 #endif
 	return false;
diff --git a/include/net/ipx.h b/include/net/ipx.h
index baf090390998..9d1342807b59 100644
--- a/include/net/ipx.h
+++ b/include/net/ipx.h
@@ -47,11 +47,6 @@ struct ipxhdr {
 /* From af_ipx.c */
 extern int sysctl_ipx_pprop_broadcasting;
 
-static __inline__ struct ipxhdr *ipx_hdr(struct sk_buff *skb)
-{
-	return (struct ipxhdr *)skb_transport_header(skb);
-}
-
 struct ipx_interface {
 	/* IPX address */
 	__be32			if_netnum;
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 456f2edf78dc..3a8e445257cd 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -5911,7 +5911,9 @@ enum rate_control_capabilities {
 struct rate_control_ops {
 	unsigned long capa;
 	const char *name;
-	void *(*alloc)(struct ieee80211_hw *hw, struct dentry *debugfsdir);
+	void *(*alloc)(struct ieee80211_hw *hw);
+	void (*add_debugfs)(struct ieee80211_hw *hw, void *priv,
+			    struct dentry *debugfsdir);
 	void (*free)(void *priv);
 
 	void *(*alloc_sta)(void *priv, struct ieee80211_sta *sta, gfp_t gfp);
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 5e679c8dae0b..8ec77bfdc1a4 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -467,7 +467,7 @@ static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb
 
 	do {
 		seq = read_seqbegin(&hh->hh_lock);
-		hh_len = hh->hh_len;
+		hh_len = READ_ONCE(hh->hh_len);
 		if (likely(hh_len <= HH_DATA_MOD)) {
 			hh_alen = HH_DATA_MOD;
 
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 3a78bc15423e..7a4f05f3c7f8 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -353,8 +353,13 @@ struct pernet_operations {
 	 * synchronize_rcu() related to these pernet_operations,
 	 * instead of separate synchronize_rcu() for every net.
 	 * Please, avoid synchronize_rcu() at all, where it's possible.
+	 *
+	 * Note that a combination of pre_exit() and exit() can
+	 * be used, since a synchronize_rcu() is guaranteed between
+	 * the calls.
 	 */
 	int (*init)(struct net *net);
+	void (*pre_exit)(struct net *net);
 	void (*exit)(struct net *net);
 	void (*exit_batch)(struct list_head *net_exit_list);
 	unsigned int *id;
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index d2bc733a2ef1..e79087419924 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -90,7 +90,7 @@ struct nf_conn {
 	struct hlist_node	nat_bysource;
 #endif
 	/* all members below initialized via memset */
-	u8 __nfct_init_offset[0];
+	struct { } __nfct_init_offset;
 
 	/* If we were expected by an expectation, this will be it */
 	struct nf_conn *master;
diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h
index 286fd960896f..a1a8d45adb42 100644
--- a/include/net/netns/nftables.h
+++ b/include/net/netns/nftables.h
@@ -7,6 +7,7 @@
 struct netns_nftables {
 	struct list_head	tables;
 	struct list_head	commit_list;
+	struct list_head	module_list;
 	struct mutex		commit_mutex;
 	unsigned int		base_seq;
 	u8			gencursor;
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 514e3c80ecc1..bc692c7c893d 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -241,31 +241,38 @@ __cls_set_class(unsigned long *clp, unsigned long cl)
 	return xchg(clp, cl);
 }
 
-static inline unsigned long
-cls_set_class(struct Qdisc *q, unsigned long *clp, unsigned long cl)
+static inline void
+__tcf_bind_filter(struct Qdisc *q, struct tcf_result *r, unsigned long base)
 {
-	unsigned long old_cl;
+	unsigned long cl;
 
-	sch_tree_lock(q);
-	old_cl = __cls_set_class(clp, cl);
-	sch_tree_unlock(q);
-	return old_cl;
+	cl = q->ops->cl_ops->bind_tcf(q, base, r->classid);
+	cl = __cls_set_class(&r->class, cl);
+	if (cl)
+		q->ops->cl_ops->unbind_tcf(q, cl);
 }
 
 static inline void
 tcf_bind_filter(struct tcf_proto *tp, struct tcf_result *r, unsigned long base)
 {
 	struct Qdisc *q = tp->chain->block->q;
-	unsigned long cl;
 
 	/* Check q as it is not set for shared blocks. In that case,
 	 * setting class is not supported.
 	 */
 	if (!q)
 		return;
-	cl = q->ops->cl_ops->bind_tcf(q, base, r->classid);
-	cl = cls_set_class(q, &r->class, cl);
-	if (cl)
+	sch_tree_lock(q);
+	__tcf_bind_filter(q, r, base);
+	sch_tree_unlock(q);
+}
+
+static inline void
+__tcf_unbind_filter(struct Qdisc *q, struct tcf_result *r)
+{
+	unsigned long cl;
+
+	if ((cl = __cls_set_class(&r->class, 0)) != 0)
 		q->ops->cl_ops->unbind_tcf(q, cl);
 }
 
@@ -273,12 +280,10 @@ static inline void
 tcf_unbind_filter(struct tcf_proto *tp, struct tcf_result *r)
 {
 	struct Qdisc *q = tp->chain->block->q;
-	unsigned long cl;
 
 	if (!q)
 		return;
-	if ((cl = __cls_set_class(&r->class, 0)) != 0)
-		q->ops->cl_ops->unbind_tcf(q, cl);
+	__tcf_unbind_filter(q, r);
 }
 
 struct tcf_exts {
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index aa99c73c3fbd..2abecd015f6d 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -128,17 +128,6 @@ static inline void qdisc_run(struct Qdisc *q)
 	}
 }
 
-static inline __be16 tc_skb_protocol(const struct sk_buff *skb)
-{
-	/* We need to take extra care in case the skb came via
-	 * vlan accelerated path. In that case, use skb->vlan_proto
-	 * as the original vlan header was already stripped.
-	 */
-	if (skb_vlan_tag_present(skb))
-		return skb->vlan_proto;
-	return skb->protocol;
-}
-
 /* Calculate maximal size of packet seen by hard_start_xmit
    routine of this device.
  */
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index ee9c9cb3014a..1430cc4a27a3 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -152,8 +152,8 @@ static inline bool qdisc_is_percpu_stats(const struct Qdisc *q)
 static inline bool qdisc_is_empty(const struct Qdisc *qdisc)
 {
 	if (qdisc_is_percpu_stats(qdisc))
-		return qdisc->empty;
-	return !qdisc->q.qlen;
+		return READ_ONCE(qdisc->empty);
+	return !READ_ONCE(qdisc->q.qlen);
 }
 
 static inline bool qdisc_run_begin(struct Qdisc *qdisc)
@@ -161,7 +161,7 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc)
 	if (qdisc->flags & TCQ_F_NOLOCK) {
 		if (!spin_trylock(&qdisc->seqlock))
 			return false;
-		qdisc->empty = false;
+		WRITE_ONCE(qdisc->empty, false);
 	} else if (qdisc_is_running(qdisc)) {
 		return false;
 	}
@@ -316,7 +316,8 @@ struct tcf_proto_ops {
 	int			(*reoffload)(struct tcf_proto *tp, bool add,
 					     tc_setup_cb_t *cb, void *cb_priv,
 					     struct netlink_ext_ack *extack);
-	void			(*bind_class)(void *, u32, unsigned long);
+	void			(*bind_class)(void *, u32, unsigned long,
+					      void *, unsigned long);
 	void *			(*tmplt_create)(struct net *net,
 						struct tcf_chain *chain,
 						struct nlattr **tca,
@@ -400,6 +401,7 @@ struct tcf_block {
 	struct mutex lock;
 	struct list_head chain_list;
 	u32 index; /* block index for shared blocks */
+	u32 classid; /* which class this block belongs to */
 	refcount_t refcnt;
 	struct net *net;
 	struct Qdisc *q;
@@ -697,22 +699,6 @@ void __qdisc_calculate_pkt_len(struct sk_buff *skb,
 			       const struct qdisc_size_table *stab);
 int skb_do_redirect(struct sk_buff *);
 
-static inline void skb_reset_tc(struct sk_buff *skb)
-{
-#ifdef CONFIG_NET_CLS_ACT
-	skb->tc_redirected = 0;
-#endif
-}
-
-static inline bool skb_is_tc_redirected(const struct sk_buff *skb)
-{
-#ifdef CONFIG_NET_CLS_ACT
-	return skb->tc_redirected;
-#else
-	return false;
-#endif
-}
-
 static inline bool skb_at_tc_ingress(const struct sk_buff *skb)
 {
 #ifdef CONFIG_NET_CLS_ACT
diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h
index 823afc42a3aa..06e1deeef464 100644
--- a/include/net/sctp/constants.h
+++ b/include/net/sctp/constants.h
@@ -341,11 +341,13 @@ enum {
 	 ipv4_is_anycast_6to4(a))
 
 /* Flags used for the bind address copy functions.  */
-#define SCTP_ADDR6_ALLOWED	0x00000001	/* IPv6 address is allowed by
+#define SCTP_ADDR4_ALLOWED	0x00000001	/* IPv4 address is allowed by
 						   local sock family */
-#define SCTP_ADDR4_PEERSUPP	0x00000002	/* IPv4 address is supported by
+#define SCTP_ADDR6_ALLOWED	0x00000002	/* IPv6 address is allowed by
+						   local sock family */
+#define SCTP_ADDR4_PEERSUPP	0x00000004	/* IPv4 address is supported by
 						   peer */
-#define SCTP_ADDR6_PEERSUPP	0x00000004	/* IPv6 address is supported by
+#define SCTP_ADDR6_PEERSUPP	0x00000008	/* IPv6 address is supported by
 						   peer */
 
 /* Reasons to retransmit. */
diff --git a/include/net/sock.h b/include/net/sock.h
index 47124aa5cdf9..86ec9c407746 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -849,6 +849,8 @@ static inline int sk_memalloc_socks(void)
 {
 	return static_branch_unlikely(&memalloc_socks_key);
 }
+
+void __receive_sock(struct file *file);
 #else
 
 static inline int sk_memalloc_socks(void)
@@ -856,6 +858,8 @@ static inline int sk_memalloc_socks(void)
 	return 0;
 }
 
+static inline void __receive_sock(struct file *file)
+{ }
 #endif
 
 static inline gfp_t sk_gfp_mask(const struct sock *sk, gfp_t gfp_mask)
@@ -883,12 +887,17 @@ static inline bool sk_acceptq_is_full(const struct sock *sk)
  */
 static inline int sk_stream_min_wspace(const struct sock *sk)
 {
-	return sk->sk_wmem_queued >> 1;
+	return READ_ONCE(sk->sk_wmem_queued) >> 1;
 }
 
 static inline int sk_stream_wspace(const struct sock *sk)
 {
-	return sk->sk_sndbuf - sk->sk_wmem_queued;
+	return READ_ONCE(sk->sk_sndbuf) - READ_ONCE(sk->sk_wmem_queued);
+}
+
+static inline void sk_wmem_queued_add(struct sock *sk, int val)
+{
+	WRITE_ONCE(sk->sk_wmem_queued, sk->sk_wmem_queued + val);
 }
 
 void sk_stream_write_space(struct sock *sk);
@@ -1212,7 +1221,7 @@ static inline void sk_refcnt_debug_release(const struct sock *sk)
 
 static inline bool __sk_stream_memory_free(const struct sock *sk, int wake)
 {
-	if (sk->sk_wmem_queued >= sk->sk_sndbuf)
+	if (READ_ONCE(sk->sk_wmem_queued) >= READ_ONCE(sk->sk_sndbuf))
 		return false;
 
 	return sk->sk_prot->stream_memory_free ?
@@ -1472,7 +1481,7 @@ DECLARE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key);
 static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
 {
 	sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
-	sk->sk_wmem_queued -= skb->truesize;
+	sk_wmem_queued_add(sk, -skb->truesize);
 	sk_mem_uncharge(sk, skb->truesize);
 	if (static_branch_unlikely(&tcp_tx_skb_cache_key) &&
 	    !sk->sk_tx_skb_cache && !skb_cloned(skb)) {
@@ -1798,7 +1807,6 @@ static inline int sk_rx_queue_get(const struct sock *sk)
 
 static inline void sk_set_socket(struct sock *sk, struct socket *sock)
 {
-	sk_tx_queue_clear(sk);
 	sk->sk_socket = sock;
 }
 
@@ -2019,7 +2027,7 @@ static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *fro
 	skb->len	     += copy;
 	skb->data_len	     += copy;
 	skb->truesize	     += copy;
-	sk->sk_wmem_queued   += copy;
+	sk_wmem_queued_add(sk, copy);
 	sk_mem_charge(sk, copy);
 	return 0;
 }
@@ -2225,10 +2233,14 @@ static inline void sk_wake_async(const struct sock *sk, int how, int band)
 
 static inline void sk_stream_moderate_sndbuf(struct sock *sk)
 {
-	if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK)) {
-		sk->sk_sndbuf = min(sk->sk_sndbuf, sk->sk_wmem_queued >> 1);
-		sk->sk_sndbuf = max_t(u32, sk->sk_sndbuf, SOCK_MIN_SNDBUF);
-	}
+	u32 val;
+
+	if (sk->sk_userlocks & SOCK_SNDBUF_LOCK)
+		return;
+
+	val = min(sk->sk_sndbuf, sk->sk_wmem_queued >> 1);
+
+	WRITE_ONCE(sk->sk_sndbuf, max_t(u32, val, SOCK_MIN_SNDBUF));
 }
 
 struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
@@ -2261,7 +2273,7 @@ bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag);
  */
 static inline bool sock_writeable(const struct sock *sk)
 {
-	return refcount_read(&sk->sk_wmem_alloc) < (sk->sk_sndbuf >> 1);
+	return refcount_read(&sk->sk_wmem_alloc) < (READ_ONCE(sk->sk_sndbuf) >> 1);
 }
 
 static inline gfp_t gfp_any(void)
@@ -2578,9 +2590,9 @@ static inline int sk_get_rmem0(const struct sock *sk, const struct proto *proto)
  */
 static inline void sk_pacing_shift_update(struct sock *sk, int val)
 {
-	if (!sk || !sk_fullsock(sk) || sk->sk_pacing_shift == val)
+	if (!sk || !sk_fullsock(sk) || READ_ONCE(sk->sk_pacing_shift) == val)
 		return;
-	sk->sk_pacing_shift = val;
+	WRITE_ONCE(sk->sk_pacing_shift, val);
 }
 
 /* if a socket is bound to a device, check that the given device
diff --git a/include/net/tc_act/tc_police.h b/include/net/tc_act/tc_police.h
index 8b9ef3664262..cfdc7cb82cad 100644
--- a/include/net/tc_act/tc_police.h
+++ b/include/net/tc_act/tc_police.h
@@ -54,7 +54,7 @@ static inline u64 tcf_police_rate_bytes_ps(const struct tc_action *act)
 	struct tcf_police *police = to_police(act);
 	struct tcf_police_params *params;
 
-	params = rcu_dereference_bh(police->params);
+	params = rcu_dereference_bh_rtnl(police->params);
 	return params->rate.rate_bytes_ps;
 }
 
@@ -63,7 +63,7 @@ static inline s64 tcf_police_tcfp_burst(const struct tc_action *act)
 	struct tcf_police *police = to_police(act);
 	struct tcf_police_params *params;
 
-	params = rcu_dereference_bh(police->params);
+	params = rcu_dereference_bh_rtnl(police->params);
 	return params->tcfp_burst;
 }
 
diff --git a/include/net/tc_act/tc_sample.h b/include/net/tc_act/tc_sample.h
index 0a559d4b6f0f..b4fce0fae645 100644
--- a/include/net/tc_act/tc_sample.h
+++ b/include/net/tc_act/tc_sample.h
@@ -44,7 +44,7 @@ static inline int tcf_sample_trunc_size(const struct tc_action *a)
 static inline struct psample_group *
 tcf_sample_psample_group(const struct tc_action *a)
 {
-	return rcu_dereference(to_sample(a)->psample_group);
+	return rcu_dereference_rtnl(to_sample(a)->psample_group);
 }
 
 #endif /* __NET_TC_SAMPLE_H */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index b6e69e6c81fd..a893ad19ac4f 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -49,7 +49,7 @@ extern struct inet_hashinfo tcp_hashinfo;
 extern struct percpu_counter tcp_orphan_count;
 void tcp_time_wait(struct sock *sk, int state, int timeo);
 
-#define MAX_TCP_HEADER	(128 + MAX_HEADER)
+#define MAX_TCP_HEADER	L1_CACHE_ALIGN(128 + MAX_HEADER)
 #define MAX_TCP_OPTION_SPACE 40
 #define TCP_MIN_SND_MSS		48
 #define TCP_MIN_GSO_SIZE	(TCP_MIN_SND_MSS - MAX_TCP_OPTION_SPACE)
@@ -1380,13 +1380,27 @@ static inline int tcp_win_from_space(const struct sock *sk, int space)
 /* Note: caller must be prepared to deal with negative returns */
 static inline int tcp_space(const struct sock *sk)
 {
-	return tcp_win_from_space(sk, sk->sk_rcvbuf - sk->sk_backlog.len -
+	return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) -
+				  READ_ONCE(sk->sk_backlog.len) -
 				  atomic_read(&sk->sk_rmem_alloc));
 }
 
 static inline int tcp_full_space(const struct sock *sk)
 {
-	return tcp_win_from_space(sk, sk->sk_rcvbuf);
+	return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf));
+}
+
+/* We provision sk_rcvbuf around 200% of sk_rcvlowat.
+ * If 87.5 % (7/8) of the space has been consumed, we want to override
+ * SO_RCVLOWAT constraint, since we are receiving skbs with too small
+ * len/truesize ratio.
+ */
+static inline bool tcp_rmem_pressure(const struct sock *sk)
+{
+	int rcvbuf = READ_ONCE(sk->sk_rcvbuf);
+	int threshold = rcvbuf - (rcvbuf >> 3);
+
+	return atomic_read(&sk->sk_rmem_alloc) > threshold;
 }
 
 extern void tcp_openreq_init_rwin(struct request_sock *req,
@@ -1884,7 +1898,8 @@ static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp)
 static inline bool tcp_stream_memory_free(const struct sock *sk, int wake)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
-	u32 notsent_bytes = tp->write_seq - tp->snd_nxt;
+	u32 notsent_bytes = READ_ONCE(tp->write_seq) -
+			    READ_ONCE(tp->snd_nxt);
 
 	return (notsent_bytes << wake) < tcp_notsent_lowat(tp);
 }
diff --git a/include/net/tls.h b/include/net/tls.h
index 773508c3479a..f458227161a9 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -156,6 +156,8 @@ struct tls_sw_context_tx {
 	struct tls_rec *open_rec;
 	struct list_head tx_list;
 	atomic_t encrypt_pending;
+	/* protect crypto_wait with encrypt_pending */
+	spinlock_t encrypt_compl_lock;
 	int async_notify;
 	int async_capable;
 
@@ -175,6 +177,8 @@ struct tls_sw_context_rx {
 	int async_capable;
 	bool decrypted;
 	atomic_t decrypt_pending;
+	/* protect crypto_wait with decrypt_pending*/
+	spinlock_t decrypt_compl_lock;
 	bool async_notify;
 };
 
@@ -543,6 +547,15 @@ static inline bool tls_sw_has_ctx_tx(const struct sock *sk)
 	return !!tls_sw_ctx_tx(ctx);
 }
 
+static inline bool tls_sw_has_ctx_rx(const struct sock *sk)
+{
+	struct tls_context *ctx = tls_get_ctx(sk);
+
+	if (!ctx)
+		return false;
+	return !!tls_sw_ctx_rx(ctx);
+}
+
 void tls_sw_write_space(struct sock *sk, struct tls_context *ctx);
 void tls_device_write_space(struct sock *sk, struct tls_context *ctx);
 
diff --git a/include/net/udp.h b/include/net/udp.h
index 79d141d2103b..f2c1178f6e12 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -476,6 +476,16 @@ static inline struct sk_buff *udp_rcv_segment(struct sock *sk,
 	if (!inet_get_convert_csum(sk))
 		features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
 
+	/* UDP segmentation expects packets of type CHECKSUM_PARTIAL or
+	 * CHECKSUM_NONE in __udp_gso_segment. UDP GRO indeed builds partial
+	 * packets in udp_gro_complete_segment. As does UDP GSO, verified by
+	 * udp_send_skb. But when those packets are looped in dev_loopback_xmit
+	 * their ip_summed is set to CHECKSUM_UNNECESSARY. Reset in this
+	 * specific case, where PARTIAL is both correct and required.
+	 */
+	if (skb->pkt_type == PACKET_LOOPBACK)
+		skb->ip_summed = CHECKSUM_PARTIAL;
+
 	/* the GSO CB lays after the UDP one, no need to save and restore any
 	 * CB fragment
 	 */
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index a2907873ed56..e410d02d0524 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -950,7 +950,7 @@ struct xfrm_dst {
 static inline struct dst_entry *xfrm_dst_path(const struct dst_entry *dst)
 {
 #ifdef CONFIG_XFRM
-	if (dst->xfrm) {
+	if (dst->xfrm || (dst->flags & DST_XFRM_QUEUE)) {
 		const struct xfrm_dst *xdst = (const struct xfrm_dst *) dst;
 
 		return xdst->path;
@@ -962,7 +962,7 @@ static inline struct dst_entry *xfrm_dst_path(const struct dst_entry *dst)
 static inline struct dst_entry *xfrm_dst_child(const struct dst_entry *dst)
 {
 #ifdef CONFIG_XFRM
-	if (dst->xfrm) {
+	if (dst->xfrm || (dst->flags & DST_XFRM_QUEUE)) {
 		struct xfrm_dst *xdst = (struct xfrm_dst *) dst;
 		return xdst->child;
 	}
@@ -1019,6 +1019,7 @@ struct xfrm_offload {
 #define	XFRM_GRO		32
 #define	XFRM_ESP_NO_TRAILER	64
 #define	XFRM_DEV_RESUME		128
+#define	XFRM_XMIT		256
 
 	__u32			status;
 #define CRYPTO_SUCCESS				1
@@ -1644,13 +1645,16 @@ int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk,
 		     void *);
 void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net);
 int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl);
-struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id,
-					  u8 type, int dir,
+struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net,
+					  const struct xfrm_mark *mark,
+					  u32 if_id, u8 type, int dir,
 					  struct xfrm_selector *sel,
 					  struct xfrm_sec_ctx *ctx, int delete,
 					  int *err);
-struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id, u8,
-				     int dir, u32 id, int delete, int *err);
+struct xfrm_policy *xfrm_policy_byid(struct net *net,
+				     const struct xfrm_mark *mark, u32 if_id,
+				     u8 type, int dir, u32 id, int delete,
+				     int *err);
 int xfrm_policy_flush(struct net *net, u8 type, bool task_valid);
 void xfrm_policy_hash_rebuild(struct net *net);
 u32 xfrm_get_acqseq(void);
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index d655e10791aa..4a76ec877603 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2220,7 +2220,6 @@ struct ib_port_cache {
 
 struct ib_cache {
 	rwlock_t                lock;
-	struct ib_event_handler event_handler;
 };
 
 struct ib_port_immutable {
@@ -2622,7 +2621,11 @@ struct ib_device {
 	struct rcu_head rcu_head;
 
 	struct list_head              event_handler_list;
-	spinlock_t                    event_handler_lock;
+	/* Protects event_handler_list */
+	struct rw_semaphore event_handler_rwsem;
+
+	/* Protects QP's event_handler calls and open_qp list */
+	spinlock_t event_handler_lock;
 
 	struct rw_semaphore	      client_data_rwsem;
 	struct xarray                 client_data;
@@ -2927,7 +2930,7 @@ bool ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state,
 
 void ib_register_event_handler(struct ib_event_handler *event_handler);
 void ib_unregister_event_handler(struct ib_event_handler *event_handler);
-void ib_dispatch_event(struct ib_event *event);
+void ib_dispatch_event(const struct ib_event *event);
 
 int ib_query_port(struct ib_device *device,
 		  u8 port_num, struct ib_port_attr *port_attr);
@@ -4259,6 +4262,9 @@ static inline int ib_check_mr_access(int flags)
 	    !(flags & IB_ACCESS_LOCAL_WRITE))
 		return -EINVAL;
 
+	if (flags & ~IB_ACCESS_SUPPORTED)
+		return -EINVAL;
+
 	return 0;
 }
 
diff --git a/include/rdma/uverbs_std_types.h b/include/rdma/uverbs_std_types.h
index 05eabfd5d0d3..9f382e7d4579 100644
--- a/include/rdma/uverbs_std_types.h
+++ b/include/rdma/uverbs_std_types.h
@@ -88,7 +88,7 @@ struct ib_uobject *__uobj_get_destroy(const struct uverbs_api_object *obj,
 
 static inline void uobj_put_destroy(struct ib_uobject *uobj)
 {
-	rdma_lookup_put_uobject(uobj, UVERBS_LOOKUP_WRITE);
+	rdma_lookup_put_uobject(uobj, UVERBS_LOOKUP_DESTROY);
 }
 
 static inline void uobj_put_read(struct ib_uobject *uobj)
diff --git a/include/sound/compress_driver.h b/include/sound/compress_driver.h
index bc88d6f964da..006f01922439 100644
--- a/include/sound/compress_driver.h
+++ b/include/sound/compress_driver.h
@@ -59,6 +59,7 @@ struct snd_compr_runtime {
  * @direction: stream direction, playback/recording
  * @metadata_set: metadata set flag, true when set
  * @next_track: has userspace signal next track transition, true when set
+ * @partial_drain: undergoing partial_drain for stream, true when set
  * @private_data: pointer to DSP private data
  */
 struct snd_compr_stream {
@@ -70,6 +71,7 @@ struct snd_compr_stream {
 	enum snd_compr_direction direction;
 	bool metadata_set;
 	bool next_track;
+	bool partial_drain;
 	void *private_data;
 };
 
@@ -173,7 +175,13 @@ static inline void snd_compr_drain_notify(struct snd_compr_stream *stream)
 	if (snd_BUG_ON(!stream))
 		return;
 
-	stream->runtime->state = SNDRV_PCM_STATE_SETUP;
+	/* for partial_drain case we are back to running state on success */
+	if (stream->partial_drain) {
+		stream->runtime->state = SNDRV_PCM_STATE_RUNNING;
+		stream->partial_drain = false; /* clear this flag as well */
+	} else {
+		stream->runtime->state = SNDRV_PCM_STATE_SETUP;
+	}
 
 	wake_up(&stream->runtime->sleep);
 }
diff --git a/include/sound/hda_regmap.h b/include/sound/hda_regmap.h
index 5141f8ffbb12..4c1b9bebbd60 100644
--- a/include/sound/hda_regmap.h
+++ b/include/sound/hda_regmap.h
@@ -24,6 +24,9 @@ int snd_hdac_regmap_write_raw(struct hdac_device *codec, unsigned int reg,
 			      unsigned int val);
 int snd_hdac_regmap_update_raw(struct hdac_device *codec, unsigned int reg,
 			       unsigned int mask, unsigned int val);
+int snd_hdac_regmap_update_raw_once(struct hdac_device *codec, unsigned int reg,
+				    unsigned int mask, unsigned int val);
+void snd_hdac_regmap_sync(struct hdac_device *codec);
 
 /**
  * snd_hdac_regmap_encode_verb - encode the verb to a pseudo register
diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h
index d0ed491dd7bf..a4ffeda303ef 100644
--- a/include/sound/hdaudio.h
+++ b/include/sound/hdaudio.h
@@ -86,6 +86,7 @@ struct hdac_device {
 
 	/* regmap */
 	struct regmap *regmap;
+	struct mutex regmap_lock;
 	struct snd_array vendor_verbs;
 	bool lazy_cache:1;	/* don't wake up for writes */
 	bool caps_overwriting:1; /* caps overwrite being in process */
diff --git a/include/sound/rawmidi.h b/include/sound/rawmidi.h
index 40ab20439fee..334842daa904 100644
--- a/include/sound/rawmidi.h
+++ b/include/sound/rawmidi.h
@@ -61,6 +61,7 @@ struct snd_rawmidi_runtime {
 	size_t avail_min;	/* min avail for wakeup */
 	size_t avail;		/* max used buffer for wakeup */
 	size_t xruns;		/* over/underruns counter */
+	int buffer_ref;		/* buffer reference count */
 	/* misc */
 	spinlock_t lock;
 	wait_queue_head_t sleep;
@@ -77,9 +78,9 @@ struct snd_rawmidi_substream {
 	struct list_head list;		/* list of all substream for given stream */
 	int stream;			/* direction */
 	int number;			/* substream number */
-	unsigned int opened: 1,		/* open flag */
-		     append: 1,		/* append flag (merge more streams) */
-		     active_sensing: 1; /* send active sensing when close */
+	bool opened;			/* open flag */
+	bool append;			/* append flag (merge more streams) */
+	bool active_sensing;		/* send active sensing when close */
 	int use_count;			/* use counter (for output) */
 	size_t bytes;
 	struct snd_rawmidi *rmidi;
diff --git a/include/sound/rt5670.h b/include/sound/rt5670.h
index f9024c7a1600..02e1d7778354 100644
--- a/include/sound/rt5670.h
+++ b/include/sound/rt5670.h
@@ -12,6 +12,7 @@ struct rt5670_platform_data {
 	int jd_mode;
 	bool in2_diff;
 	bool dev_gpio;
+	bool gpio1_is_ext_spk_en;
 
 	bool dmic_en;
 	unsigned int dmic1_data_pin;
diff --git a/include/sound/simple_card_utils.h b/include/sound/simple_card_utils.h
index d5cc3f992f15..67e55e44c08d 100644
--- a/include/sound/simple_card_utils.h
+++ b/include/sound/simple_card_utils.h
@@ -8,6 +8,7 @@
 #ifndef __SIMPLE_CARD_UTILS_H
 #define __SIMPLE_CARD_UTILS_H
 
+#include <linux/clk.h>
 #include <sound/soc.h>
 
 #define asoc_simple_init_hp(card, sjack, prefix) \
diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h
index a49d37140a64..591cd9e4692c 100644
--- a/include/target/iscsi/iscsi_target_core.h
+++ b/include/target/iscsi/iscsi_target_core.h
@@ -676,7 +676,7 @@ struct iscsi_session {
 	atomic_t		session_logout;
 	atomic_t		session_reinstatement;
 	atomic_t		session_stop_active;
-	atomic_t		sleep_on_sess_wait_comp;
+	atomic_t		session_close;
 	/* connection list */
 	struct list_head	sess_conn_list;
 	struct list_head	cr_active_list;
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 51b6f50eabee..1b752d8ea529 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -116,10 +116,4 @@ static inline bool target_dev_configured(struct se_device *se_dev)
 	return !!(se_dev->dev_flags & DF_CONFIGURED);
 }
 
-/* Only use get_unaligned_be24() if reading p - 1 is allowed. */
-static inline uint32_t get_unaligned_be24(const uint8_t *const p)
-{
-	return get_unaligned_be32(p - 1) & 0xffffffU;
-}
-
 #endif /* TARGET_CORE_BACKEND_H */
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index 51b1e0da2efc..988717c63253 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -202,7 +202,7 @@ enum afs_flock_operation {
 	EM(afs_call_trace_get,			"GET  ") \
 	EM(afs_call_trace_put,			"PUT  ") \
 	EM(afs_call_trace_wake,			"WAKE ") \
-	E_(afs_call_trace_work,			"WORK ")
+	E_(afs_call_trace_work,			"QUEUE")
 
 #define afs_fs_operations \
 	EM(afs_FS_FetchData,			"FS.FetchData") \
@@ -853,9 +853,9 @@ TRACE_EVENT(afs_call_state,
 
 TRACE_EVENT(afs_lookup,
 	    TP_PROTO(struct afs_vnode *dvnode, const struct qstr *name,
-		     struct afs_vnode *vnode),
+		     struct afs_fid *fid),
 
-	    TP_ARGS(dvnode, name, vnode),
+	    TP_ARGS(dvnode, name, fid),
 
 	    TP_STRUCT__entry(
 		    __field_struct(struct afs_fid,	dfid		)
@@ -866,13 +866,7 @@ TRACE_EVENT(afs_lookup,
 	    TP_fast_assign(
 		    int __len = min_t(int, name->len, 23);
 		    __entry->dfid = dvnode->fid;
-		    if (vnode) {
-			    __entry->fid = vnode->fid;
-		    } else {
-			    __entry->fid.vid = 0;
-			    __entry->fid.vnode = 0;
-			    __entry->fid.unique = 0;
-		    }
+		    __entry->fid = *fid;
 		    memcpy(__entry->name, name->name, __len);
 		    __entry->name[__len] = 0;
 			   ),
diff --git a/include/trace/events/preemptirq.h b/include/trace/events/preemptirq.h
index 95fba0471e5b..3f249e150c0c 100644
--- a/include/trace/events/preemptirq.h
+++ b/include/trace/events/preemptirq.h
@@ -18,13 +18,13 @@ DECLARE_EVENT_CLASS(preemptirq_template,
 	TP_ARGS(ip, parent_ip),
 
 	TP_STRUCT__entry(
-		__field(u32, caller_offs)
-		__field(u32, parent_offs)
+		__field(s32, caller_offs)
+		__field(s32, parent_offs)
 	),
 
 	TP_fast_assign(
-		__entry->caller_offs = (u32)(ip - (unsigned long)_stext);
-		__entry->parent_offs = (u32)(parent_ip - (unsigned long)_stext);
+		__entry->caller_offs = (s32)(ip - (unsigned long)_stext);
+		__entry->parent_offs = (s32)(parent_ip - (unsigned long)_stext);
 	),
 
 	TP_printk("caller=%pS parent=%pS",
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 02a3f78f7cd8..cea2d45e6aad 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -442,7 +442,7 @@ TRACE_EVENT_RCU(rcu_fqs,
  */
 TRACE_EVENT_RCU(rcu_dyntick,
 
-	TP_PROTO(const char *polarity, long oldnesting, long newnesting, atomic_t dynticks),
+	TP_PROTO(const char *polarity, long oldnesting, long newnesting, int dynticks),
 
 	TP_ARGS(polarity, oldnesting, newnesting, dynticks),
 
@@ -457,7 +457,7 @@ TRACE_EVENT_RCU(rcu_dyntick,
 		__entry->polarity = polarity;
 		__entry->oldnesting = oldnesting;
 		__entry->newnesting = newnesting;
-		__entry->dynticks = atomic_read(&dynticks);
+		__entry->dynticks = dynticks;
 	),
 
 	TP_printk("%s %lx %lx %#3x", __entry->polarity,
diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index df9851cb82b2..5954c3703216 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -1505,17 +1505,15 @@ DECLARE_EVENT_CLASS(svcrdma_sendcomp_event,
 
 TRACE_EVENT(svcrdma_post_send,
 	TP_PROTO(
-		const struct ib_send_wr *wr,
-		int status
+		const struct ib_send_wr *wr
 	),
 
-	TP_ARGS(wr, status),
+	TP_ARGS(wr),
 
 	TP_STRUCT__entry(
 		__field(const void *, cqe)
 		__field(unsigned int, num_sge)
 		__field(u32, inv_rkey)
-		__field(int, status)
 	),
 
 	TP_fast_assign(
@@ -1523,12 +1521,11 @@ TRACE_EVENT(svcrdma_post_send,
 		__entry->num_sge = wr->num_sge;
 		__entry->inv_rkey = (wr->opcode == IB_WR_SEND_WITH_INV) ?
 					wr->ex.invalidate_rkey : 0;
-		__entry->status = status;
 	),
 
-	TP_printk("cqe=%p num_sge=%u inv_rkey=0x%08x status=%d",
+	TP_printk("cqe=%p num_sge=%u inv_rkey=0x%08x",
 		__entry->cqe, __entry->num_sge,
-		__entry->inv_rkey, __entry->status
+		__entry->inv_rkey
 	)
 );
 
@@ -1593,26 +1590,23 @@ TRACE_EVENT(svcrdma_wc_receive,
 TRACE_EVENT(svcrdma_post_rw,
 	TP_PROTO(
 		const void *cqe,
-		int sqecount,
-		int status
+		int sqecount
 	),
 
-	TP_ARGS(cqe, sqecount, status),
+	TP_ARGS(cqe, sqecount),
 
 	TP_STRUCT__entry(
 		__field(const void *, cqe)
 		__field(int, sqecount)
-		__field(int, status)
 	),
 
 	TP_fast_assign(
 		__entry->cqe = cqe;
 		__entry->sqecount = sqecount;
-		__entry->status = status;
 	),
 
-	TP_printk("cqe=%p sqecount=%d status=%d",
-		__entry->cqe, __entry->sqecount, __entry->status
+	TP_printk("cqe=%p sqecount=%d",
+		__entry->cqe, __entry->sqecount
 	)
 );
 
@@ -1708,6 +1702,34 @@ DECLARE_EVENT_CLASS(svcrdma_sendqueue_event,
 DEFINE_SQ_EVENT(full);
 DEFINE_SQ_EVENT(retry);
 
+TRACE_EVENT(svcrdma_sq_post_err,
+	TP_PROTO(
+		const struct svcxprt_rdma *rdma,
+		int status
+	),
+
+	TP_ARGS(rdma, status),
+
+	TP_STRUCT__entry(
+		__field(int, avail)
+		__field(int, depth)
+		__field(int, status)
+		__string(addr, rdma->sc_xprt.xpt_remotebuf)
+	),
+
+	TP_fast_assign(
+		__entry->avail = atomic_read(&rdma->sc_sq_avail);
+		__entry->depth = rdma->sc_sq_depth;
+		__entry->status = status;
+		__assign_str(addr, rdma->sc_xprt.xpt_remotebuf);
+	),
+
+	TP_printk("addr=%s sc_sq_avail=%d/%d status=%d",
+		__get_str(addr), __entry->avail, __entry->depth,
+		__entry->status
+	)
+);
+
 #endif /* _TRACE_RPCRDMA_H */
 
 #include <trace/define_trace.h>
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index d19f8433d15f..5c5764f5e1d4 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -406,7 +406,7 @@ enum rxrpc_tx_point {
 	EM(rxrpc_cong_begin_retransmission,	" Retrans") \
 	EM(rxrpc_cong_cleared_nacks,		" Cleared") \
 	EM(rxrpc_cong_new_low_nack,		" NewLowN") \
-	EM(rxrpc_cong_no_change,		"") \
+	EM(rxrpc_cong_no_change,		" -") \
 	EM(rxrpc_cong_progress,			" Progres") \
 	EM(rxrpc_cong_retransmit_again,		" ReTxAgn") \
 	EM(rxrpc_cong_rtt_window_end,		" RttWinE") \
@@ -612,10 +612,10 @@ TRACE_EVENT(rxrpc_client,
 	    );
 
 TRACE_EVENT(rxrpc_call,
-	    TP_PROTO(struct rxrpc_call *call, enum rxrpc_call_trace op,
+	    TP_PROTO(unsigned int call_debug_id, enum rxrpc_call_trace op,
 		     int usage, const void *where, const void *aux),
 
-	    TP_ARGS(call, op, usage, where, aux),
+	    TP_ARGS(call_debug_id, op, usage, where, aux),
 
 	    TP_STRUCT__entry(
 		    __field(unsigned int,		call		)
@@ -626,7 +626,7 @@ TRACE_EVENT(rxrpc_call,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call->debug_id;
+		    __entry->call = call_debug_id;
 		    __entry->op = op;
 		    __entry->usage = usage;
 		    __entry->where = where;
@@ -1115,18 +1115,17 @@ TRACE_EVENT(rxrpc_rtt_tx,
 TRACE_EVENT(rxrpc_rtt_rx,
 	    TP_PROTO(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
 		     rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial,
-		     s64 rtt, u8 nr, s64 avg),
+		     u32 rtt, u32 rto),
 
-	    TP_ARGS(call, why, send_serial, resp_serial, rtt, nr, avg),
+	    TP_ARGS(call, why, send_serial, resp_serial, rtt, rto),
 
 	    TP_STRUCT__entry(
 		    __field(unsigned int,		call		)
 		    __field(enum rxrpc_rtt_rx_trace,	why		)
-		    __field(u8,				nr		)
 		    __field(rxrpc_serial_t,		send_serial	)
 		    __field(rxrpc_serial_t,		resp_serial	)
-		    __field(s64,			rtt		)
-		    __field(u64,			avg		)
+		    __field(u32,			rtt		)
+		    __field(u32,			rto		)
 			     ),
 
 	    TP_fast_assign(
@@ -1135,18 +1134,16 @@ TRACE_EVENT(rxrpc_rtt_rx,
 		    __entry->send_serial = send_serial;
 		    __entry->resp_serial = resp_serial;
 		    __entry->rtt = rtt;
-		    __entry->nr = nr;
-		    __entry->avg = avg;
+		    __entry->rto = rto;
 			   ),
 
-	    TP_printk("c=%08x %s sr=%08x rr=%08x rtt=%lld nr=%u avg=%lld",
+	    TP_printk("c=%08x %s sr=%08x rr=%08x rtt=%u rto=%u",
 		      __entry->call,
 		      __print_symbolic(__entry->why, rxrpc_rtt_rx_traces),
 		      __entry->send_serial,
 		      __entry->resp_serial,
 		      __entry->rtt,
-		      __entry->nr,
-		      __entry->avg)
+		      __entry->rto)
 	    );
 
 TRACE_EVENT(rxrpc_timer,
@@ -1547,6 +1544,41 @@ TRACE_EVENT(rxrpc_notify_socket,
 		      __entry->serial)
 	    );
 
+TRACE_EVENT(rxrpc_rx_discard_ack,
+	    TP_PROTO(unsigned int debug_id, rxrpc_serial_t serial,
+		     rxrpc_seq_t first_soft_ack, rxrpc_seq_t call_ackr_first,
+		     rxrpc_seq_t prev_pkt, rxrpc_seq_t call_ackr_prev),
+
+	    TP_ARGS(debug_id, serial, first_soft_ack, call_ackr_first,
+		    prev_pkt, call_ackr_prev),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,	debug_id	)
+		    __field(rxrpc_serial_t,	serial		)
+		    __field(rxrpc_seq_t,	first_soft_ack)
+		    __field(rxrpc_seq_t,	call_ackr_first)
+		    __field(rxrpc_seq_t,	prev_pkt)
+		    __field(rxrpc_seq_t,	call_ackr_prev)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->debug_id		= debug_id;
+		    __entry->serial		= serial;
+		    __entry->first_soft_ack	= first_soft_ack;
+		    __entry->call_ackr_first	= call_ackr_first;
+		    __entry->prev_pkt		= prev_pkt;
+		    __entry->call_ackr_prev	= call_ackr_prev;
+			   ),
+
+	    TP_printk("c=%08x r=%08x %08x<%08x %08x<%08x",
+		      __entry->debug_id,
+		      __entry->serial,
+		      __entry->first_soft_ack,
+		      __entry->call_ackr_first,
+		      __entry->prev_pkt,
+		      __entry->call_ackr_prev)
+	    );
+
 #endif /* _TRACE_RXRPC_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/sock.h b/include/trace/events/sock.h
index a0c4b8a30966..51fe9f6719eb 100644
--- a/include/trace/events/sock.h
+++ b/include/trace/events/sock.h
@@ -82,7 +82,7 @@ TRACE_EVENT(sock_rcvqueue_full,
 	TP_fast_assign(
 		__entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc);
 		__entry->truesize   = skb->truesize;
-		__entry->sk_rcvbuf  = sk->sk_rcvbuf;
+		__entry->sk_rcvbuf  = READ_ONCE(sk->sk_rcvbuf);
 	),
 
 	TP_printk("rmem_alloc=%d truesize=%u sk_rcvbuf=%d",
@@ -115,7 +115,7 @@ TRACE_EVENT(sock_exceed_buf_limit,
 		__entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc);
 		__entry->sysctl_wmem = sk_get_wmem0(sk, prot);
 		__entry->wmem_alloc = refcount_read(&sk->sk_wmem_alloc);
-		__entry->wmem_queued = sk->sk_wmem_queued;
+		__entry->wmem_queued = READ_ONCE(sk->sk_wmem_queued);
 		__entry->kind = kind;
 	),
 
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 79095434c1be..cb4f639714c5 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -67,8 +67,8 @@ DECLARE_EVENT_CLASS(writeback_page_template,
 
 	TP_fast_assign(
 		strscpy_pad(__entry->name,
-			    mapping ? dev_name(inode_to_bdi(mapping->host)->dev) : "(unknown)",
-			    32);
+			    bdi_dev_name(mapping ? inode_to_bdi(mapping->host) :
+					 NULL), 32);
 		__entry->ino = mapping ? mapping->host->i_ino : 0;
 		__entry->index = page->index;
 	),
@@ -111,8 +111,7 @@ DECLARE_EVENT_CLASS(writeback_dirty_inode_template,
 		struct backing_dev_info *bdi = inode_to_bdi(inode);
 
 		/* may be called for files on pseudo FSes w/ unregistered bdi */
-		strscpy_pad(__entry->name,
-			    bdi->dev ? dev_name(bdi->dev) : "(unknown)", 32);
+		strscpy_pad(__entry->name, bdi_dev_name(bdi), 32);
 		__entry->ino		= inode->i_ino;
 		__entry->state		= inode->i_state;
 		__entry->flags		= flags;
@@ -192,7 +191,7 @@ DECLARE_EVENT_CLASS(writeback_write_inode_template,
 
 	TP_fast_assign(
 		strscpy_pad(__entry->name,
-			    dev_name(inode_to_bdi(inode)->dev), 32);
+			    bdi_dev_name(inode_to_bdi(inode)), 32);
 		__entry->ino		= inode->i_ino;
 		__entry->sync_mode	= wbc->sync_mode;
 		__entry->cgroup_ino	= __trace_wbc_assign_cgroup(wbc);
@@ -235,9 +234,7 @@ DECLARE_EVENT_CLASS(writeback_work_class,
 		__field(unsigned int, cgroup_ino)
 	),
 	TP_fast_assign(
-		strscpy_pad(__entry->name,
-			    wb->bdi->dev ? dev_name(wb->bdi->dev) :
-			    "(unknown)", 32);
+		strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32);
 		__entry->nr_pages = work->nr_pages;
 		__entry->sb_dev = work->sb ? work->sb->s_dev : 0;
 		__entry->sync_mode = work->sync_mode;
@@ -290,7 +287,7 @@ DECLARE_EVENT_CLASS(writeback_class,
 		__field(unsigned int, cgroup_ino)
 	),
 	TP_fast_assign(
-		strscpy_pad(__entry->name, dev_name(wb->bdi->dev), 32);
+		strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32);
 		__entry->cgroup_ino = __trace_wb_assign_cgroup(wb);
 	),
 	TP_printk("bdi %s: cgroup_ino=%u",
@@ -312,7 +309,7 @@ TRACE_EVENT(writeback_bdi_register,
 		__array(char, name, 32)
 	),
 	TP_fast_assign(
-		strscpy_pad(__entry->name, dev_name(bdi->dev), 32);
+		strscpy_pad(__entry->name, bdi_dev_name(bdi), 32);
 	),
 	TP_printk("bdi %s",
 		__entry->name
@@ -337,7 +334,7 @@ DECLARE_EVENT_CLASS(wbc_class,
 	),
 
 	TP_fast_assign(
-		strscpy_pad(__entry->name, dev_name(bdi->dev), 32);
+		strscpy_pad(__entry->name, bdi_dev_name(bdi), 32);
 		__entry->nr_to_write	= wbc->nr_to_write;
 		__entry->pages_skipped	= wbc->pages_skipped;
 		__entry->sync_mode	= wbc->sync_mode;
@@ -388,7 +385,7 @@ TRACE_EVENT(writeback_queue_io,
 	),
 	TP_fast_assign(
 		unsigned long *older_than_this = work->older_than_this;
-		strscpy_pad(__entry->name, dev_name(wb->bdi->dev), 32);
+		strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32);
 		__entry->older	= older_than_this ?  *older_than_this : 0;
 		__entry->age	= older_than_this ?
 				  (jiffies - *older_than_this) * 1000 / HZ : -1;
@@ -474,7 +471,7 @@ TRACE_EVENT(bdi_dirty_ratelimit,
 	),
 
 	TP_fast_assign(
-		strscpy_pad(__entry->bdi, dev_name(wb->bdi->dev), 32);
+		strscpy_pad(__entry->bdi, bdi_dev_name(wb->bdi), 32);
 		__entry->write_bw	= KBps(wb->write_bandwidth);
 		__entry->avg_write_bw	= KBps(wb->avg_write_bandwidth);
 		__entry->dirty_rate	= KBps(dirty_rate);
@@ -539,7 +536,7 @@ TRACE_EVENT(balance_dirty_pages,
 
 	TP_fast_assign(
 		unsigned long freerun = (thresh + bg_thresh) / 2;
-		strscpy_pad(__entry->bdi, dev_name(wb->bdi->dev), 32);
+		strscpy_pad(__entry->bdi, bdi_dev_name(wb->bdi), 32);
 
 		__entry->limit		= global_wb_domain.dirty_limit;
 		__entry->setpoint	= (global_wb_domain.dirty_limit +
@@ -600,7 +597,7 @@ TRACE_EVENT(writeback_sb_inodes_requeue,
 
 	TP_fast_assign(
 		strscpy_pad(__entry->name,
-			    dev_name(inode_to_bdi(inode)->dev), 32);
+			    bdi_dev_name(inode_to_bdi(inode)), 32);
 		__entry->ino		= inode->i_ino;
 		__entry->state		= inode->i_state;
 		__entry->dirtied_when	= inode->dirtied_when;
@@ -674,7 +671,7 @@ DECLARE_EVENT_CLASS(writeback_single_inode_template,
 
 	TP_fast_assign(
 		strscpy_pad(__entry->name,
-			    dev_name(inode_to_bdi(inode)->dev), 32);
+			    bdi_dev_name(inode_to_bdi(inode)), 32);
 		__entry->ino		= inode->i_ino;
 		__entry->state		= inode->i_state;
 		__entry->dirtied_when	= inode->dirtied_when;
diff --git a/include/trace/events/xen.h b/include/trace/events/xen.h
index 9a0e8af21310..a5ccfa67bc5c 100644
--- a/include/trace/events/xen.h
+++ b/include/trace/events/xen.h
@@ -66,7 +66,11 @@ TRACE_EVENT(xen_mc_callback,
 	    TP_PROTO(xen_mc_callback_fn_t fn, void *data),
 	    TP_ARGS(fn, data),
 	    TP_STRUCT__entry(
-		    __field(xen_mc_callback_fn_t, fn)
+		    /*
+		     * Use field_struct to avoid is_signed_type()
+		     * comparison of a function pointer.
+		     */
+		    __field_struct(xen_mc_callback_fn_t, fn)
 		    __field(void *, data)
 		    ),
 	    TP_fast_assign(
diff --git a/include/uapi/linux/coresight-stm.h b/include/uapi/linux/coresight-stm.h
index aac550a52f80..8847dbf24151 100644
--- a/include/uapi/linux/coresight-stm.h
+++ b/include/uapi/linux/coresight-stm.h
@@ -2,8 +2,10 @@
 #ifndef __UAPI_CORESIGHT_STM_H_
 #define __UAPI_CORESIGHT_STM_H_
 
-#define STM_FLAG_TIMESTAMPED   BIT(3)
-#define STM_FLAG_GUARANTEED    BIT(7)
+#include <linux/const.h>
+
+#define STM_FLAG_TIMESTAMPED   _BITUL(3)
+#define STM_FLAG_GUARANTEED    _BITUL(7)
 
 /*
  * The CoreSight STM supports guaranteed and invariant timing
diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h
index 85387c76c24f..472cd5bc5567 100644
--- a/include/uapi/linux/input-event-codes.h
+++ b/include/uapi/linux/input-event-codes.h
@@ -808,7 +808,8 @@
 #define SW_LINEIN_INSERT	0x0d  /* set = inserted */
 #define SW_MUTE_DEVICE		0x0e  /* set = device disabled */
 #define SW_PEN_INSERTED		0x0f  /* set = pen inserted */
-#define SW_MAX			0x0f
+#define SW_MACHINE_COVER	0x10  /* set = cover closed */
+#define SW_MAX			0x10
 #define SW_CNT			(SW_MAX+1)
 
 /*
diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h
index f056b2a00d5c..9a61c28ed3ae 100644
--- a/include/uapi/linux/input.h
+++ b/include/uapi/linux/input.h
@@ -34,6 +34,7 @@ struct input_event {
 	__kernel_ulong_t __sec;
 #if defined(__sparc__) && defined(__arch64__)
 	unsigned int __usec;
+	unsigned int __pad;
 #else
 	__kernel_ulong_t __usec;
 #endif
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 2fe12b40d503..c32a985f9745 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -189,9 +189,11 @@ struct kvm_hyperv_exit {
 #define KVM_EXIT_HYPERV_SYNIC          1
 #define KVM_EXIT_HYPERV_HCALL          2
 	__u32 type;
+	__u32 pad1;
 	union {
 		struct {
 			__u32 msr;
+			__u32 pad2;
 			__u64 control;
 			__u64 evt_page;
 			__u64 msg_page;
diff --git a/include/uapi/linux/mmc/ioctl.h b/include/uapi/linux/mmc/ioctl.h
index 00c08120f3ba..27a39847d55c 100644
--- a/include/uapi/linux/mmc/ioctl.h
+++ b/include/uapi/linux/mmc/ioctl.h
@@ -3,6 +3,7 @@
 #define LINUX_MMC_IOCTL_H
 
 #include <linux/types.h>
+#include <linux/major.h>
 
 struct mmc_ioc_cmd {
 	/*
diff --git a/include/uapi/linux/netfilter/xt_sctp.h b/include/uapi/linux/netfilter/xt_sctp.h
index 4bc6d1a08781..b4d804a9fccb 100644
--- a/include/uapi/linux/netfilter/xt_sctp.h
+++ b/include/uapi/linux/netfilter/xt_sctp.h
@@ -41,19 +41,19 @@ struct xt_sctp_info {
 #define SCTP_CHUNKMAP_SET(chunkmap, type) 		\
 	do { 						\
 		(chunkmap)[type / bytes(__u32)] |= 	\
-			1 << (type % bytes(__u32));	\
+			1u << (type % bytes(__u32));	\
 	} while (0)
 
 #define SCTP_CHUNKMAP_CLEAR(chunkmap, type)		 	\
 	do {							\
 		(chunkmap)[type / bytes(__u32)] &= 		\
-			~(1 << (type % bytes(__u32)));	\
+			~(1u << (type % bytes(__u32)));	\
 	} while (0)
 
 #define SCTP_CHUNKMAP_IS_SET(chunkmap, type) 			\
 ({								\
 	((chunkmap)[type / bytes (__u32)] & 		\
-		(1 << (type % bytes (__u32)))) ? 1: 0;	\
+		(1u << (type % bytes (__u32)))) ? 1: 0;	\
 })
 
 #define SCTP_CHUNKMAP_RESET(chunkmap) \
diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h
index b0d15c73f6d7..1f2d8c81f0e0 100644
--- a/include/uapi/linux/raid/md_p.h
+++ b/include/uapi/linux/raid/md_p.h
@@ -329,6 +329,7 @@ struct mdp_superblock_1 {
 #define	MD_FEATURE_JOURNAL		512 /* support write cache */
 #define	MD_FEATURE_PPL			1024 /* support PPL */
 #define	MD_FEATURE_MULTIPLE_PPLS	2048 /* support for multiple PPLs */
+#define	MD_FEATURE_RAID0_LAYOUT		4096 /* layout is meaningful for RAID0 */
 #define	MD_FEATURE_ALL			(MD_FEATURE_BITMAP_OFFSET	\
 					|MD_FEATURE_RECOVERY_OFFSET	\
 					|MD_FEATURE_RESHAPE_ACTIVE	\
@@ -341,6 +342,7 @@ struct mdp_superblock_1 {
 					|MD_FEATURE_JOURNAL		\
 					|MD_FEATURE_PPL			\
 					|MD_FEATURE_MULTIPLE_PPLS	\
+					|MD_FEATURE_RAID0_LAYOUT	\
 					)
 
 struct r5l_payload_header {
diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h
index 90734aa5aa36..b5f901af79f0 100644
--- a/include/uapi/linux/seccomp.h
+++ b/include/uapi/linux/seccomp.h
@@ -93,5 +93,6 @@ struct seccomp_notif_resp {
 #define SECCOMP_IOCTL_NOTIF_RECV	SECCOMP_IOWR(0, struct seccomp_notif)
 #define SECCOMP_IOCTL_NOTIF_SEND	SECCOMP_IOWR(1,	\
 						struct seccomp_notif_resp)
-#define SECCOMP_IOCTL_NOTIF_ID_VALID	SECCOMP_IOR(2, __u64)
+#define SECCOMP_IOCTL_NOTIF_ID_VALID	SECCOMP_IOW(2, __u64)
+
 #endif /* _UAPI_LINUX_SECCOMP_H */
diff --git a/include/uapi/linux/serio.h b/include/uapi/linux/serio.h
index a0cac1d8670d..1937915be413 100644
--- a/include/uapi/linux/serio.h
+++ b/include/uapi/linux/serio.h
@@ -9,7 +9,7 @@
 #ifndef _UAPI_SERIO_H
 #define _UAPI_SERIO_H
 
-
+#include <linux/const.h>
 #include <linux/ioctl.h>
 
 #define SPIOCSTYPE	_IOW('q', 0x01, unsigned long)
@@ -18,10 +18,10 @@
 /*
  * bit masks for use in "interrupt" flags (3rd argument)
  */
-#define SERIO_TIMEOUT	BIT(0)
-#define SERIO_PARITY	BIT(1)
-#define SERIO_FRAME	BIT(2)
-#define SERIO_OOB_DATA	BIT(3)
+#define SERIO_TIMEOUT	_BITUL(0)
+#define SERIO_PARITY	_BITUL(1)
+#define SERIO_FRAME	_BITUL(2)
+#define SERIO_OOB_DATA	_BITUL(3)
 
 /*
  * Serio types
diff --git a/include/uapi/linux/swab.h b/include/uapi/linux/swab.h
index 23cd84868cc3..7272f85d6d6a 100644
--- a/include/uapi/linux/swab.h
+++ b/include/uapi/linux/swab.h
@@ -4,6 +4,7 @@
 
 #include <linux/types.h>
 #include <linux/compiler.h>
+#include <asm/bitsperlong.h>
 #include <asm/swab.h>
 
 /*
@@ -132,6 +133,15 @@ static inline __attribute_const__ __u32 __fswahb32(__u32 val)
 	__fswab64(x))
 #endif
 
+static __always_inline unsigned long __swab(const unsigned long y)
+{
+#if __BITS_PER_LONG == 64
+	return __swab64(y);
+#else /* __BITS_PER_LONG == 32 */
+	return __swab32(y);
+#endif
+}
+
 /**
  * __swahw32 - return a word-swapped 32-bit value
  * @x: value to wordswap
diff --git a/include/uapi/linux/usb/charger.h b/include/uapi/linux/usb/charger.h
index 5f72af35b3ed..ad22079125bf 100644
--- a/include/uapi/linux/usb/charger.h
+++ b/include/uapi/linux/usb/charger.h
@@ -14,18 +14,18 @@
  * ACA (Accessory Charger Adapters)
  */
 enum usb_charger_type {
-	UNKNOWN_TYPE,
-	SDP_TYPE,
-	DCP_TYPE,
-	CDP_TYPE,
-	ACA_TYPE,
+	UNKNOWN_TYPE = 0,
+	SDP_TYPE = 1,
+	DCP_TYPE = 2,
+	CDP_TYPE = 3,
+	ACA_TYPE = 4,
 };
 
 /* USB charger state */
 enum usb_charger_state {
-	USB_CHARGER_DEFAULT,
-	USB_CHARGER_PRESENT,
-	USB_CHARGER_ABSENT,
+	USB_CHARGER_DEFAULT = 0,
+	USB_CHARGER_PRESENT = 1,
+	USB_CHARGER_ABSENT = 2,
 };
 
 #endif /* _UAPI__LINUX_USB_CHARGER_H */
diff --git a/include/uapi/linux/vboxguest.h b/include/uapi/linux/vboxguest.h
index 612f0c7d3558..ded39da305d0 100644
--- a/include/uapi/linux/vboxguest.h
+++ b/include/uapi/linux/vboxguest.h
@@ -103,7 +103,7 @@ VMMDEV_ASSERT_SIZE(vbg_ioctl_driver_version_info, 24 + 20);
 
 
 /* IOCTL to perform a VMM Device request larger then 1KB. */
-#define VBG_IOCTL_VMMDEV_REQUEST_BIG	_IOC(_IOC_READ | _IOC_WRITE, 'V', 3, 0)
+#define VBG_IOCTL_VMMDEV_REQUEST_BIG	_IO('V', 3)
 
 
 /** VBG_IOCTL_HGCM_CONNECT data structure. */
@@ -198,7 +198,7 @@ struct vbg_ioctl_log {
 	} u;
 };
 
-#define VBG_IOCTL_LOG(s)		_IOC(_IOC_READ | _IOC_WRITE, 'V', 9, s)
+#define VBG_IOCTL_LOG(s)		_IO('V', 9)
 
 
 /** VBG_IOCTL_WAIT_FOR_EVENTS data structure. */
diff --git a/include/uapi/linux/wireless.h b/include/uapi/linux/wireless.h
index 86eca3208b6b..24f3371ad826 100644
--- a/include/uapi/linux/wireless.h
+++ b/include/uapi/linux/wireless.h
@@ -74,6 +74,12 @@
 #include <linux/socket.h>		/* for "struct sockaddr" et al	*/
 #include <linux/if.h>			/* for IFNAMSIZ and co... */
 
+#ifdef __KERNEL__
+#	include <linux/stddef.h>	/* for offsetof */
+#else
+#	include <stddef.h>		/* for offsetof */
+#endif
+
 /***************************** VERSION *****************************/
 /*
  * This constant is used to know the availability of the wireless
@@ -1090,8 +1096,7 @@ struct iw_event {
 /* iw_point events are special. First, the payload (extra data) come at
  * the end of the event, so they are bigger than IW_EV_POINT_LEN. Second,
  * we omit the pointer, so start at an offset. */
-#define IW_EV_POINT_OFF (((char *) &(((struct iw_point *) NULL)->length)) - \
-			  (char *) NULL)
+#define IW_EV_POINT_OFF offsetof(struct iw_point, length)
 #define IW_EV_POINT_LEN	(IW_EV_LCP_LEN + sizeof(struct iw_point) - \
 			 IW_EV_POINT_OFF)
 
diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h
index 5f3b9fec7b5f..ff7cfdc6cb44 100644
--- a/include/uapi/linux/xfrm.h
+++ b/include/uapi/linux/xfrm.h
@@ -304,7 +304,7 @@ enum xfrm_attr_type_t {
 	XFRMA_PROTO,		/* __u8 */
 	XFRMA_ADDRESS_FILTER,	/* struct xfrm_address_filter */
 	XFRMA_PAD,
-	XFRMA_OFFLOAD_DEV,	/* struct xfrm_state_offload */
+	XFRMA_OFFLOAD_DEV,	/* struct xfrm_user_offload */
 	XFRMA_SET_MARK,		/* __u32 */
 	XFRMA_SET_MARK_MASK,	/* __u32 */
 	XFRMA_IF_ID,		/* __u32 */
diff --git a/init/Kconfig b/init/Kconfig
index 7faf3bb07415..c77705e7dc7d 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -27,22 +27,6 @@ config CLANG_VERSION
 config CC_HAS_ASM_GOTO
 	def_bool $(success,$(srctree)/scripts/gcc-goto.sh $(CC))
 
-config CC_HAS_WARN_MAYBE_UNINITIALIZED
-	def_bool $(cc-option,-Wmaybe-uninitialized)
-	help
-	  GCC >= 4.7 supports this option.
-
-config CC_DISABLE_WARN_MAYBE_UNINITIALIZED
-	bool
-	depends on CC_HAS_WARN_MAYBE_UNINITIALIZED
-	default CC_IS_GCC && GCC_VERSION < 40900  # unreliable for GCC < 4.9
-	help
-	  GCC's -Wmaybe-uninitialized is not reliable by definition.
-	  Lots of false positive warnings are produced in some cases.
-
-	  If this option is enabled, -Wno-maybe-uninitialzed is passed
-	  to the compiler to suppress maybe-uninitialized warnings.
-
 config CONSTRUCTORS
 	bool
 	depends on !UML
@@ -1139,7 +1123,6 @@ config CC_OPTIMIZE_FOR_PERFORMANCE
 
 config CC_OPTIMIZE_FOR_SIZE
 	bool "Optimize for size"
-	imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED  # avoid false positives
 	help
 	  Enabling this option will pass "-Os" instead of "-O2" to
 	  your compiler resulting in a smaller kernel.
diff --git a/init/initramfs.c b/init/initramfs.c
index c47dad0884f7..5feee4f616d5 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -534,7 +534,7 @@ void __weak free_initrd_mem(unsigned long start, unsigned long end)
 }
 
 #ifdef CONFIG_KEXEC_CORE
-static bool kexec_free_initrd(void)
+static bool __init kexec_free_initrd(void)
 {
 	unsigned long crashk_start = (unsigned long)__va(crashk_res.start);
 	unsigned long crashk_end   = (unsigned long)__va(crashk_res.end);
diff --git a/init/main.c b/init/main.c
index f4dac4788bd2..d1ce0179d343 100644
--- a/init/main.c
+++ b/init/main.c
@@ -669,7 +669,6 @@ asmlinkage __visible void __init start_kernel(void)
 	boot_init_stack_canary();
 
 	time_init();
-	printk_safe_init();
 	perf_event_init();
 	profile_init();
 	call_function_init();
@@ -759,6 +758,8 @@ asmlinkage __visible void __init start_kernel(void)
 
 	/* Do the rest non-__init'ed, we're now alive */
 	arch_call_rest_init();
+
+	prevent_tail_call_optimization();
 }
 
 /* Call all constructor functions linked into the kernel. */
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 65c351564ad0..7815338ad32d 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -82,6 +82,7 @@ struct mqueue_inode_info {
 
 	struct sigevent notify;
 	struct pid *notify_owner;
+	u32 notify_self_exec_id;
 	struct user_namespace *notify_user_ns;
 	struct user_struct *user;	/* user who created, for accounting */
 	struct sock *notify_sock;
@@ -709,28 +710,44 @@ static void __do_notify(struct mqueue_inode_info *info)
 	 * synchronously. */
 	if (info->notify_owner &&
 	    info->attr.mq_curmsgs == 1) {
-		struct kernel_siginfo sig_i;
 		switch (info->notify.sigev_notify) {
 		case SIGEV_NONE:
 			break;
-		case SIGEV_SIGNAL:
-			/* sends signal */
+		case SIGEV_SIGNAL: {
+			struct kernel_siginfo sig_i;
+			struct task_struct *task;
+
+			/* do_mq_notify() accepts sigev_signo == 0, why?? */
+			if (!info->notify.sigev_signo)
+				break;
 
 			clear_siginfo(&sig_i);
 			sig_i.si_signo = info->notify.sigev_signo;
 			sig_i.si_errno = 0;
 			sig_i.si_code = SI_MESGQ;
 			sig_i.si_value = info->notify.sigev_value;
-			/* map current pid/uid into info->owner's namespaces */
 			rcu_read_lock();
+			/* map current pid/uid into info->owner's namespaces */
 			sig_i.si_pid = task_tgid_nr_ns(current,
 						ns_of_pid(info->notify_owner));
-			sig_i.si_uid = from_kuid_munged(info->notify_user_ns, current_uid());
+			sig_i.si_uid = from_kuid_munged(info->notify_user_ns,
+						current_uid());
+			/*
+			 * We can't use kill_pid_info(), this signal should
+			 * bypass check_kill_permission(). It is from kernel
+			 * but si_fromuser() can't know this.
+			 * We do check the self_exec_id, to avoid sending
+			 * signals to programs that don't expect them.
+			 */
+			task = pid_task(info->notify_owner, PIDTYPE_TGID);
+			if (task && task->self_exec_id ==
+						info->notify_self_exec_id) {
+				do_send_sig_info(info->notify.sigev_signo,
+						&sig_i, task, PIDTYPE_TGID);
+			}
 			rcu_read_unlock();
-
-			kill_pid_info(info->notify.sigev_signo,
-				      &sig_i, info->notify_owner);
 			break;
+		}
 		case SIGEV_THREAD:
 			set_cookie(info->notify_cookie, NOTIFY_WOKENUP);
 			netlink_sendskb(info->notify_sock, info->notify_cookie);
@@ -1320,6 +1337,7 @@ retry:
 			info->notify.sigev_signo = notification->sigev_signo;
 			info->notify.sigev_value = notification->sigev_value;
 			info->notify.sigev_notify = SIGEV_SIGNAL;
+			info->notify_self_exec_id = current->self_exec_id;
 			break;
 		}
 
diff --git a/ipc/msg.c b/ipc/msg.c
index 8dec945fa030..767587ab45a3 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -377,7 +377,7 @@ copy_msqid_from_user(struct msqid64_ds *out, void __user *buf, int version)
  * NOTE: no locks must be held, the rwsem is taken inside this function.
  */
 static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
-			struct msqid64_ds *msqid64)
+			struct ipc64_perm *perm, int msg_qbytes)
 {
 	struct kern_ipc_perm *ipcp;
 	struct msg_queue *msq;
@@ -387,7 +387,7 @@ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
 	rcu_read_lock();
 
 	ipcp = ipcctl_obtain_check(ns, &msg_ids(ns), msqid, cmd,
-				      &msqid64->msg_perm, msqid64->msg_qbytes);
+				      perm, msg_qbytes);
 	if (IS_ERR(ipcp)) {
 		err = PTR_ERR(ipcp);
 		goto out_unlock1;
@@ -409,18 +409,18 @@ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
 	{
 		DEFINE_WAKE_Q(wake_q);
 
-		if (msqid64->msg_qbytes > ns->msg_ctlmnb &&
+		if (msg_qbytes > ns->msg_ctlmnb &&
 		    !capable(CAP_SYS_RESOURCE)) {
 			err = -EPERM;
 			goto out_unlock1;
 		}
 
 		ipc_lock_object(&msq->q_perm);
-		err = ipc_update_perm(&msqid64->msg_perm, ipcp);
+		err = ipc_update_perm(perm, ipcp);
 		if (err)
 			goto out_unlock0;
 
-		msq->q_qbytes = msqid64->msg_qbytes;
+		msq->q_qbytes = msg_qbytes;
 
 		msq->q_ctime = ktime_get_real_seconds();
 		/*
@@ -601,9 +601,10 @@ static long ksys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf, int ver
 	case IPC_SET:
 		if (copy_msqid_from_user(&msqid64, buf, version))
 			return -EFAULT;
-		/* fallthru */
+		return msgctl_down(ns, msqid, cmd, &msqid64.msg_perm,
+				   msqid64.msg_qbytes);
 	case IPC_RMID:
-		return msgctl_down(ns, msqid, cmd, &msqid64);
+		return msgctl_down(ns, msqid, cmd, NULL, 0);
 	default:
 		return  -EINVAL;
 	}
@@ -735,9 +736,9 @@ static long compat_ksys_msgctl(int msqid, int cmd, void __user *uptr, int versio
 	case IPC_SET:
 		if (copy_compat_msqid_from_user(&msqid64, uptr, version))
 			return -EFAULT;
-		/* fallthru */
+		return msgctl_down(ns, msqid, cmd, &msqid64.msg_perm, msqid64.msg_qbytes);
 	case IPC_RMID:
-		return msgctl_down(ns, msqid, cmd, &msqid64);
+		return msgctl_down(ns, msqid, cmd, NULL, 0);
 	default:
 		return -EINVAL;
 	}
diff --git a/ipc/sem.c b/ipc/sem.c
index 7da4504bcc7c..e7113dab6304 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -2367,11 +2367,9 @@ void exit_sem(struct task_struct *tsk)
 		ipc_assert_locked_object(&sma->sem_perm);
 		list_del(&un->list_id);
 
-		/* we are the last process using this ulp, acquiring ulp->lock
-		 * isn't required. Besides that, we are also protected against
-		 * IPC_RMID as we hold sma->sem_perm lock now
-		 */
+		spin_lock(&ulp->lock);
 		list_del_rcu(&un->list_proc);
+		spin_unlock(&ulp->lock);
 
 		/* perform adjustments registered in un */
 		for (i = 0; i < sma->sem_nsems; i++) {
diff --git a/ipc/util.c b/ipc/util.c
index d126d156efc6..1821b6386d3b 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -764,21 +764,21 @@ static struct kern_ipc_perm *sysvipc_find_ipc(struct ipc_ids *ids, loff_t pos,
 			total++;
 	}
 
+	ipc = NULL;
 	if (total >= ids->in_use)
-		return NULL;
+		goto out;
 
 	for (; pos < ipc_mni; pos++) {
 		ipc = idr_find(&ids->ipcs_idr, pos);
 		if (ipc != NULL) {
-			*new_pos = pos + 1;
 			rcu_read_lock();
 			ipc_lock_object(ipc);
-			return ipc;
+			break;
 		}
 	}
-
-	/* Out of range - return NULL to terminate iteration */
-	return NULL;
+out:
+	*new_pos = pos + 1;
+	return ipc;
 }
 
 static void *sysvipc_proc_next(struct seq_file *s, void *it, loff_t *pos)
diff --git a/kernel/audit.c b/kernel/audit.c
index 486c968214d9..a664fe710289 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -879,7 +879,7 @@ main_queue:
 	return 0;
 }
 
-int audit_send_list(void *_dest)
+int audit_send_list_thread(void *_dest)
 {
 	struct audit_netlink_list *dest = _dest;
 	struct sk_buff *skb;
@@ -923,19 +923,30 @@ out_kfree_skb:
 	return NULL;
 }
 
+static void audit_free_reply(struct audit_reply *reply)
+{
+	if (!reply)
+		return;
+
+	if (reply->skb)
+		kfree_skb(reply->skb);
+	if (reply->net)
+		put_net(reply->net);
+	kfree(reply);
+}
+
 static int audit_send_reply_thread(void *arg)
 {
 	struct audit_reply *reply = (struct audit_reply *)arg;
-	struct sock *sk = audit_get_sk(reply->net);
 
 	audit_ctl_lock();
 	audit_ctl_unlock();
 
 	/* Ignore failure. It'll only happen if the sender goes away,
 	   because our timeout is set to infinite. */
-	netlink_unicast(sk, reply->skb, reply->portid, 0);
-	put_net(reply->net);
-	kfree(reply);
+	netlink_unicast(audit_get_sk(reply->net), reply->skb, reply->portid, 0);
+	reply->skb = NULL;
+	audit_free_reply(reply);
 	return 0;
 }
 
@@ -949,35 +960,32 @@ static int audit_send_reply_thread(void *arg)
  * @payload: payload data
  * @size: payload size
  *
- * Allocates an skb, builds the netlink message, and sends it to the port id.
- * No failure notifications.
+ * Allocates a skb, builds the netlink message, and sends it to the port id.
  */
 static void audit_send_reply(struct sk_buff *request_skb, int seq, int type, int done,
 			     int multi, const void *payload, int size)
 {
-	struct net *net = sock_net(NETLINK_CB(request_skb).sk);
-	struct sk_buff *skb;
 	struct task_struct *tsk;
-	struct audit_reply *reply = kmalloc(sizeof(struct audit_reply),
-					    GFP_KERNEL);
+	struct audit_reply *reply;
 
+	reply = kzalloc(sizeof(*reply), GFP_KERNEL);
 	if (!reply)
 		return;
 
-	skb = audit_make_reply(seq, type, done, multi, payload, size);
-	if (!skb)
-		goto out;
-
-	reply->net = get_net(net);
+	reply->skb = audit_make_reply(seq, type, done, multi, payload, size);
+	if (!reply->skb)
+		goto err;
+	reply->net = get_net(sock_net(NETLINK_CB(request_skb).sk));
 	reply->portid = NETLINK_CB(request_skb).portid;
-	reply->skb = skb;
 
 	tsk = kthread_run(audit_send_reply_thread, reply, "audit_send_reply");
-	if (!IS_ERR(tsk))
-		return;
-	kfree_skb(skb);
-out:
-	kfree(reply);
+	if (IS_ERR(tsk))
+		goto err;
+
+	return;
+
+err:
+	audit_free_reply(reply);
 }
 
 /*
@@ -1100,13 +1108,11 @@ static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature
 	audit_log_end(ab);
 }
 
-static int audit_set_feature(struct sk_buff *skb)
+static int audit_set_feature(struct audit_features *uaf)
 {
-	struct audit_features *uaf;
 	int i;
 
 	BUILD_BUG_ON(AUDIT_LAST_FEATURE + 1 > ARRAY_SIZE(audit_feature_names));
-	uaf = nlmsg_data(nlmsg_hdr(skb));
 
 	/* if there is ever a version 2 we should handle that here */
 
@@ -1174,6 +1180,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	u32			seq;
 	void			*data;
+	int			data_len;
 	int			err;
 	struct audit_buffer	*ab;
 	u16			msg_type = nlh->nlmsg_type;
@@ -1187,6 +1194,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	seq  = nlh->nlmsg_seq;
 	data = nlmsg_data(nlh);
+	data_len = nlmsg_len(nlh);
 
 	switch (msg_type) {
 	case AUDIT_GET: {
@@ -1210,7 +1218,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		struct audit_status	s;
 		memset(&s, 0, sizeof(s));
 		/* guard against past and future API changes */
-		memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh)));
+		memcpy(&s, data, min_t(size_t, sizeof(s), data_len));
 		if (s.mask & AUDIT_STATUS_ENABLED) {
 			err = audit_set_enabled(s.enabled);
 			if (err < 0)
@@ -1314,7 +1322,9 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 			return err;
 		break;
 	case AUDIT_SET_FEATURE:
-		err = audit_set_feature(skb);
+		if (data_len < sizeof(struct audit_features))
+			return -EINVAL;
+		err = audit_set_feature(data);
 		if (err)
 			return err;
 		break;
@@ -1323,9 +1333,14 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2:
 		if (!audit_enabled && msg_type != AUDIT_USER_AVC)
 			return 0;
+		/* exit early if there isn't at least one character to print */
+		if (data_len < 2)
+			return -EINVAL;
 
 		err = audit_filter(msg_type, AUDIT_FILTER_USER);
 		if (err == 1) { /* match or error */
+			char *str = data;
+
 			err = 0;
 			if (msg_type == AUDIT_USER_TTY) {
 				err = tty_audit_push();
@@ -1333,26 +1348,24 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 					break;
 			}
 			audit_log_user_recv_msg(&ab, msg_type);
-			if (msg_type != AUDIT_USER_TTY)
+			if (msg_type != AUDIT_USER_TTY) {
+				/* ensure NULL termination */
+				str[data_len - 1] = '\0';
 				audit_log_format(ab, " msg='%.*s'",
 						 AUDIT_MESSAGE_TEXT_MAX,
-						 (char *)data);
-			else {
-				int size;
-
+						 str);
+			} else {
 				audit_log_format(ab, " data=");
-				size = nlmsg_len(nlh);
-				if (size > 0 &&
-				    ((unsigned char *)data)[size - 1] == '\0')
-					size--;
-				audit_log_n_untrustedstring(ab, data, size);
+				if (data_len > 0 && str[data_len - 1] == '\0')
+					data_len--;
+				audit_log_n_untrustedstring(ab, str, data_len);
 			}
 			audit_log_end(ab);
 		}
 		break;
 	case AUDIT_ADD_RULE:
 	case AUDIT_DEL_RULE:
-		if (nlmsg_len(nlh) < sizeof(struct audit_rule_data))
+		if (data_len < sizeof(struct audit_rule_data))
 			return -EINVAL;
 		if (audit_enabled == AUDIT_LOCKED) {
 			audit_log_common_recv_msg(audit_context(), &ab,
@@ -1364,7 +1377,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 			audit_log_end(ab);
 			return -EPERM;
 		}
-		err = audit_rule_change(msg_type, seq, data, nlmsg_len(nlh));
+		err = audit_rule_change(msg_type, seq, data, data_len);
 		break;
 	case AUDIT_LIST_RULES:
 		err = audit_list_rules_send(skb, seq);
@@ -1379,7 +1392,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	case AUDIT_MAKE_EQUIV: {
 		void *bufp = data;
 		u32 sizes[2];
-		size_t msglen = nlmsg_len(nlh);
+		size_t msglen = data_len;
 		char *old, *new;
 
 		err = -EINVAL;
@@ -1455,7 +1468,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 		memset(&s, 0, sizeof(s));
 		/* guard against past and future API changes */
-		memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh)));
+		memcpy(&s, data, min_t(size_t, sizeof(s), data_len));
 		/* check if new data is valid */
 		if ((s.enabled != 0 && s.enabled != 1) ||
 		    (s.log_passwd != 0 && s.log_passwd != 1))
diff --git a/kernel/audit.h b/kernel/audit.h
index 6c076d4982da..c018dcab4b11 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -229,7 +229,7 @@ struct audit_netlink_list {
 	struct sk_buff_head q;
 };
 
-int audit_send_list(void *_dest);
+int audit_send_list_thread(void *_dest);
 
 extern int selinux_audit_rule_update(void);
 
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 9f8e190e3bea..d26db3c9a015 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -439,6 +439,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
 	bufp = data->buf;
 	for (i = 0; i < data->field_count; i++) {
 		struct audit_field *f = &entry->rule.fields[i];
+		u32 f_val;
 
 		err = -EINVAL;
 
@@ -447,12 +448,12 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
 			goto exit_free;
 
 		f->type = data->fields[i];
-		f->val = data->values[i];
+		f_val = data->values[i];
 
 		/* Support legacy tests for a valid loginuid */
-		if ((f->type == AUDIT_LOGINUID) && (f->val == AUDIT_UID_UNSET)) {
+		if ((f->type == AUDIT_LOGINUID) && (f_val == AUDIT_UID_UNSET)) {
 			f->type = AUDIT_LOGINUID_SET;
-			f->val = 0;
+			f_val = 0;
 			entry->rule.pflags |= AUDIT_LOGINUID_LEGACY;
 		}
 
@@ -468,7 +469,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
 		case AUDIT_SUID:
 		case AUDIT_FSUID:
 		case AUDIT_OBJ_UID:
-			f->uid = make_kuid(current_user_ns(), f->val);
+			f->uid = make_kuid(current_user_ns(), f_val);
 			if (!uid_valid(f->uid))
 				goto exit_free;
 			break;
@@ -477,11 +478,12 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
 		case AUDIT_SGID:
 		case AUDIT_FSGID:
 		case AUDIT_OBJ_GID:
-			f->gid = make_kgid(current_user_ns(), f->val);
+			f->gid = make_kgid(current_user_ns(), f_val);
 			if (!gid_valid(f->gid))
 				goto exit_free;
 			break;
 		case AUDIT_ARCH:
+			f->val = f_val;
 			entry->rule.arch_f = f;
 			break;
 		case AUDIT_SUBJ_USER:
@@ -494,11 +496,13 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
 		case AUDIT_OBJ_TYPE:
 		case AUDIT_OBJ_LEV_LOW:
 		case AUDIT_OBJ_LEV_HIGH:
-			str = audit_unpack_string(&bufp, &remain, f->val);
-			if (IS_ERR(str))
+			str = audit_unpack_string(&bufp, &remain, f_val);
+			if (IS_ERR(str)) {
+				err = PTR_ERR(str);
 				goto exit_free;
-			entry->rule.buflen += f->val;
-
+			}
+			entry->rule.buflen += f_val;
+			f->lsm_str = str;
 			err = security_audit_rule_init(f->type, f->op, str,
 						       (void **)&f->lsm_rule);
 			/* Keep currently invalid fields around in case they
@@ -507,68 +511,71 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
 				pr_warn("audit rule for LSM \'%s\' is invalid\n",
 					str);
 				err = 0;
-			}
-			if (err) {
-				kfree(str);
+			} else if (err)
 				goto exit_free;
-			} else
-				f->lsm_str = str;
 			break;
 		case AUDIT_WATCH:
-			str = audit_unpack_string(&bufp, &remain, f->val);
-			if (IS_ERR(str))
+			str = audit_unpack_string(&bufp, &remain, f_val);
+			if (IS_ERR(str)) {
+				err = PTR_ERR(str);
 				goto exit_free;
-			entry->rule.buflen += f->val;
-
-			err = audit_to_watch(&entry->rule, str, f->val, f->op);
+			}
+			err = audit_to_watch(&entry->rule, str, f_val, f->op);
 			if (err) {
 				kfree(str);
 				goto exit_free;
 			}
+			entry->rule.buflen += f_val;
 			break;
 		case AUDIT_DIR:
-			str = audit_unpack_string(&bufp, &remain, f->val);
-			if (IS_ERR(str))
+			str = audit_unpack_string(&bufp, &remain, f_val);
+			if (IS_ERR(str)) {
+				err = PTR_ERR(str);
 				goto exit_free;
-			entry->rule.buflen += f->val;
-
+			}
 			err = audit_make_tree(&entry->rule, str, f->op);
 			kfree(str);
 			if (err)
 				goto exit_free;
+			entry->rule.buflen += f_val;
 			break;
 		case AUDIT_INODE:
+			f->val = f_val;
 			err = audit_to_inode(&entry->rule, f);
 			if (err)
 				goto exit_free;
 			break;
 		case AUDIT_FILTERKEY:
-			if (entry->rule.filterkey || f->val > AUDIT_MAX_KEY_LEN)
+			if (entry->rule.filterkey || f_val > AUDIT_MAX_KEY_LEN)
 				goto exit_free;
-			str = audit_unpack_string(&bufp, &remain, f->val);
-			if (IS_ERR(str))
+			str = audit_unpack_string(&bufp, &remain, f_val);
+			if (IS_ERR(str)) {
+				err = PTR_ERR(str);
 				goto exit_free;
-			entry->rule.buflen += f->val;
+			}
+			entry->rule.buflen += f_val;
 			entry->rule.filterkey = str;
 			break;
 		case AUDIT_EXE:
-			if (entry->rule.exe || f->val > PATH_MAX)
+			if (entry->rule.exe || f_val > PATH_MAX)
 				goto exit_free;
-			str = audit_unpack_string(&bufp, &remain, f->val);
+			str = audit_unpack_string(&bufp, &remain, f_val);
 			if (IS_ERR(str)) {
 				err = PTR_ERR(str);
 				goto exit_free;
 			}
-			entry->rule.buflen += f->val;
-
-			audit_mark = audit_alloc_mark(&entry->rule, str, f->val);
+			audit_mark = audit_alloc_mark(&entry->rule, str, f_val);
 			if (IS_ERR(audit_mark)) {
 				kfree(str);
 				err = PTR_ERR(audit_mark);
 				goto exit_free;
 			}
+			entry->rule.buflen += f_val;
 			entry->rule.exe = audit_mark;
 			break;
+		default:
+			f->val = f_val;
+			break;
 		}
 	}
 
@@ -1137,11 +1144,8 @@ int audit_rule_change(int type, int seq, void *data, size_t datasz)
  */
 int audit_list_rules_send(struct sk_buff *request_skb, int seq)
 {
-	u32 portid = NETLINK_CB(request_skb).portid;
-	struct net *net = sock_net(NETLINK_CB(request_skb).sk);
 	struct task_struct *tsk;
 	struct audit_netlink_list *dest;
-	int err = 0;
 
 	/* We can't just spew out the rules here because we might fill
 	 * the available socket buffer space and deadlock waiting for
@@ -1149,25 +1153,26 @@ int audit_list_rules_send(struct sk_buff *request_skb, int seq)
 	 * happen if we're actually running in the context of auditctl
 	 * trying to _send_ the stuff */
 
-	dest = kmalloc(sizeof(struct audit_netlink_list), GFP_KERNEL);
+	dest = kmalloc(sizeof(*dest), GFP_KERNEL);
 	if (!dest)
 		return -ENOMEM;
-	dest->net = get_net(net);
-	dest->portid = portid;
+	dest->net = get_net(sock_net(NETLINK_CB(request_skb).sk));
+	dest->portid = NETLINK_CB(request_skb).portid;
 	skb_queue_head_init(&dest->q);
 
 	mutex_lock(&audit_filter_mutex);
 	audit_list_rules(seq, &dest->q);
 	mutex_unlock(&audit_filter_mutex);
 
-	tsk = kthread_run(audit_send_list, dest, "audit_send_list");
+	tsk = kthread_run(audit_send_list_thread, dest, "audit_send_list");
 	if (IS_ERR(tsk)) {
 		skb_queue_purge(&dest->q);
+		put_net(dest->net);
 		kfree(dest);
-		err = PTR_ERR(tsk);
+		return PTR_ERR(tsk);
 	}
 
-	return err;
+	return 0;
 }
 
 int audit_comparator(u32 left, u32 op, u32 right)
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 5fcc7a17eb5a..6d37931145d8 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -2309,7 +2309,7 @@ static int btf_enum_check_member(struct btf_verifier_env *env,
 
 	struct_size = struct_type->size;
 	bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off);
-	if (struct_size - bytes_offset < sizeof(int)) {
+	if (struct_size - bytes_offset < member_type->size) {
 		btf_verifier_log_member(env, struct_type, member,
 					"Member exceeds struct_size");
 		return -EINVAL;
@@ -3449,7 +3449,7 @@ int btf_get_info_by_fd(const struct btf *btf,
 		       union bpf_attr __user *uattr)
 {
 	struct bpf_btf_info __user *uinfo;
-	struct bpf_btf_info info = {};
+	struct bpf_btf_info info;
 	u32 info_copy, btf_copy;
 	void __user *ubtf;
 	u32 uinfo_len;
@@ -3458,6 +3458,7 @@ int btf_get_info_by_fd(const struct btf *btf,
 	uinfo_len = attr->info.info_len;
 
 	info_copy = min_t(u32, uinfo_len, sizeof(info));
+	memset(&info, 0, sizeof(info));
 	if (copy_from_user(&info, uinfo, info_copy))
 		return -EFAULT;
 
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 9c073a88374f..b6ad8cb50efc 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -239,8 +239,8 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
 {
 	struct list_head *progs = &cgrp->bpf.progs[type];
 	struct bpf_prog *old_prog = NULL;
-	struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE],
-		*old_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {NULL};
+	struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {};
+	struct bpf_cgroup_storage *old_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {};
 	enum bpf_cgroup_storage_type stype;
 	struct bpf_prog_list *pl;
 	bool pl_was_allocated;
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 8ebd0fa826f8..ae5de038f4a6 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -476,7 +476,7 @@ static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
 		return -EOVERFLOW;
 
 	/* Make sure CPU is a valid possible cpu */
-	if (!cpu_possible(key_cpu))
+	if (key_cpu >= nr_cpumask_bits || !cpu_possible(key_cpu))
 		return -ENODEV;
 
 	if (qsize == 0) {
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 583df5cb302d..09ba58465758 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -679,15 +679,20 @@ static void htab_elem_free_rcu(struct rcu_head *head)
 	preempt_enable();
 }
 
-static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
+static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l)
 {
 	struct bpf_map *map = &htab->map;
+	void *ptr;
 
 	if (map->ops->map_fd_put_ptr) {
-		void *ptr = fd_htab_map_get_ptr(map, l);
-
+		ptr = fd_htab_map_get_ptr(map, l);
 		map->ops->map_fd_put_ptr(ptr);
 	}
+}
+
+static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
+{
+	htab_put_fd_value(htab, l);
 
 	if (htab_is_prealloc(htab)) {
 		__pcpu_freelist_push(&htab->freelist, &l->fnode);
@@ -739,6 +744,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 			 */
 			pl_new = this_cpu_ptr(htab->extra_elems);
 			l_new = *pl_new;
+			htab_put_fd_value(htab, old_elem);
 			*pl_new = old_elem;
 		} else {
 			struct pcpu_freelist_node *l;
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index cc0d0cf114e3..482e259ffcfb 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -195,6 +195,7 @@ static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos)
 	void *key = map_iter(m)->key;
 	void *prev_key;
 
+	(*pos)++;
 	if (map_iter(m)->done)
 		return NULL;
 
@@ -207,8 +208,6 @@ static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos)
 		map_iter(m)->done = true;
 		return NULL;
 	}
-
-	++(*pos);
 	return key;
 }
 
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index ba635209ae9a..1853aa420f2f 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -321,7 +321,7 @@ int bpf_prog_offload_info_fill(struct bpf_prog_info *info,
 
 	ulen = info->jited_prog_len;
 	info->jited_prog_len = aux->offload->jited_len;
-	if (info->jited_prog_len & ulen) {
+	if (info->jited_prog_len && ulen) {
 		uinsns = u64_to_user_ptr(info->jited_prog_insns);
 		ulen = min_t(u32, info->jited_prog_len, ulen);
 		if (copy_to_user(uinsns, aux->offload->jited_image, ulen)) {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index f7a181f4d680..e1cc2d1f4003 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1102,7 +1102,8 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
-	if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
+	if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) ||
+	    !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
 		err = -EPERM;
 		goto err_put;
 	}
@@ -1130,8 +1131,10 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
 	if (err)
 		goto free_value;
 
-	if (copy_to_user(uvalue, value, value_size) != 0)
+	if (copy_to_user(uvalue, value, value_size) != 0) {
+		err = -EFAULT;
 		goto free_value;
+	}
 
 	err = 0;
 
@@ -2275,7 +2278,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 				   union bpf_attr __user *uattr)
 {
 	struct bpf_prog_info __user *uinfo = u64_to_user_ptr(attr->info.info);
-	struct bpf_prog_info info = {};
+	struct bpf_prog_info info;
 	u32 info_len = attr->info.info_len;
 	struct bpf_prog_stats stats;
 	char __user *uinsns;
@@ -2287,6 +2290,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 		return err;
 	info_len = min_t(u32, sizeof(info), info_len);
 
+	memset(&info, 0, sizeof(info));
 	if (copy_from_user(&info, uinfo, info_len))
 		return -EFAULT;
 
@@ -2550,7 +2554,7 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map,
 				  union bpf_attr __user *uattr)
 {
 	struct bpf_map_info __user *uinfo = u64_to_user_ptr(attr->info.info);
-	struct bpf_map_info info = {};
+	struct bpf_map_info info;
 	u32 info_len = attr->info.info_len;
 	int err;
 
@@ -2559,6 +2563,7 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map,
 		return err;
 	info_len = min_t(u32, sizeof(info), info_len);
 
+	memset(&info, 0, sizeof(info));
 	info.type = map->map_type;
 	info.id = map->id;
 	info.key_size = map->key_size;
@@ -2786,7 +2791,7 @@ out:
 
 SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
 {
-	union bpf_attr attr = {};
+	union bpf_attr attr;
 	int err;
 
 	if (sysctl_unprivileged_bpf_disabled && !capable(CAP_SYS_ADMIN))
@@ -2798,6 +2803,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	size = min_t(u32, size, sizeof(attr));
 
 	/* copy attributes from user space, may be less than sizeof(bpf_attr) */
+	memset(&attr, 0, sizeof(attr));
 	if (copy_from_user(&attr, uattr, size) != 0)
 		return -EFAULT;
 
diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c
index ca52b9642943..d4f335a9a899 100644
--- a/kernel/bpf/tnum.c
+++ b/kernel/bpf/tnum.c
@@ -44,14 +44,19 @@ struct tnum tnum_rshift(struct tnum a, u8 shift)
 	return TNUM(a.value >> shift, a.mask >> shift);
 }
 
-struct tnum tnum_arshift(struct tnum a, u8 min_shift)
+struct tnum tnum_arshift(struct tnum a, u8 min_shift, u8 insn_bitness)
 {
 	/* if a.value is negative, arithmetic shifting by minimum shift
 	 * will have larger negative offset compared to more shifting.
 	 * If a.value is nonnegative, arithmetic shifting by minimum shift
 	 * will have larger positive offset compare to more shifting.
 	 */
-	return TNUM((s64)a.value >> min_shift, (s64)a.mask >> min_shift);
+	if (insn_bitness == 32)
+		return TNUM((u32)(((s32)a.value) >> min_shift),
+			    (u32)(((s32)a.mask)  >> min_shift));
+	else
+		return TNUM((s64)a.value >> min_shift,
+			    (s64)a.mask  >> min_shift);
 }
 
 struct tnum tnum_add(struct tnum a, struct tnum b)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 438614c503c7..187ea0cfbcca 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -201,8 +201,7 @@ struct bpf_call_arg_meta {
 	bool pkt_access;
 	int regno;
 	int access_size;
-	s64 msize_smax_value;
-	u64 msize_umax_value;
+	u64 msize_max_value;
 	int ref_obj_id;
 	int func_id;
 };
@@ -918,17 +917,6 @@ static void __reg_bound_offset(struct bpf_reg_state *reg)
 						 reg->umax_value));
 }
 
-static void __reg_bound_offset32(struct bpf_reg_state *reg)
-{
-	u64 mask = 0xffffFFFF;
-	struct tnum range = tnum_range(reg->umin_value & mask,
-				       reg->umax_value & mask);
-	struct tnum lo32 = tnum_cast(reg->var_off, 4);
-	struct tnum hi32 = tnum_lshift(tnum_rshift(reg->var_off, 32), 32);
-
-	reg->var_off = tnum_or(hi32, tnum_intersect(lo32, range));
-}
-
 /* Reset the min/max bounds of a register */
 static void __mark_reg_unbounded(struct bpf_reg_state *reg)
 {
@@ -2668,8 +2656,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 		/* remember the mem_size which may be used later
 		 * to refine return values.
 		 */
-		meta->msize_smax_value = reg->smax_value;
-		meta->msize_umax_value = reg->umax_value;
+		meta->msize_max_value = reg->umax_value;
 
 		/* The register is SCALAR_VALUE; the access check
 		 * happens using its boundaries.
@@ -3152,21 +3139,44 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 	return 0;
 }
 
-static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type,
-				   int func_id,
-				   struct bpf_call_arg_meta *meta)
+static int do_refine_retval_range(struct bpf_verifier_env *env,
+				  struct bpf_reg_state *regs, int ret_type,
+				  int func_id, struct bpf_call_arg_meta *meta)
 {
 	struct bpf_reg_state *ret_reg = &regs[BPF_REG_0];
+	struct bpf_reg_state tmp_reg = *ret_reg;
+	bool ret;
 
 	if (ret_type != RET_INTEGER ||
 	    (func_id != BPF_FUNC_get_stack &&
 	     func_id != BPF_FUNC_probe_read_str))
-		return;
+		return 0;
+
+	/* Error case where ret is in interval [S32MIN, -1]. */
+	ret_reg->smin_value = S32_MIN;
+	ret_reg->smax_value = -1;
+
+	__reg_deduce_bounds(ret_reg);
+	__reg_bound_offset(ret_reg);
+	__update_reg_bounds(ret_reg);
+
+	ret = push_stack(env, env->insn_idx + 1, env->insn_idx, false);
+	if (!ret)
+		return -EFAULT;
+
+	*ret_reg = tmp_reg;
+
+	/* Success case where ret is in range [0, msize_max_value]. */
+	ret_reg->smin_value = 0;
+	ret_reg->smax_value = meta->msize_max_value;
+	ret_reg->umin_value = ret_reg->smin_value;
+	ret_reg->umax_value = ret_reg->smax_value;
 
-	ret_reg->smax_value = meta->msize_smax_value;
-	ret_reg->umax_value = meta->msize_umax_value;
 	__reg_deduce_bounds(ret_reg);
 	__reg_bound_offset(ret_reg);
+	__update_reg_bounds(ret_reg);
+
+	return 0;
 }
 
 static int
@@ -3395,7 +3405,9 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 		regs[BPF_REG_0].ref_obj_id = id;
 	}
 
-	do_refine_retval_range(regs, fn->ret_type, func_id, &meta);
+	err = do_refine_retval_range(env, regs, fn->ret_type, func_id, &meta);
+	if (err)
+		return err;
 
 	err = check_map_func_compatibility(env, meta.map_ptr, func_id);
 	if (err)
@@ -4095,9 +4107,16 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 		/* Upon reaching here, src_known is true and
 		 * umax_val is equal to umin_val.
 		 */
-		dst_reg->smin_value >>= umin_val;
-		dst_reg->smax_value >>= umin_val;
-		dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val);
+		if (insn_bitness == 32) {
+			dst_reg->smin_value = (u32)(((s32)dst_reg->smin_value) >> umin_val);
+			dst_reg->smax_value = (u32)(((s32)dst_reg->smax_value) >> umin_val);
+		} else {
+			dst_reg->smin_value >>= umin_val;
+			dst_reg->smax_value >>= umin_val;
+		}
+
+		dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val,
+						insn_bitness);
 
 		/* blow away the dst_reg umin_value/umax_value and rely on
 		 * dst_reg var_off to refine the result.
@@ -4591,6 +4610,70 @@ static bool cmp_val_with_extended_s64(s64 sval, struct bpf_reg_state *reg)
 		reg->smax_value <= 0 && reg->smin_value >= S32_MIN);
 }
 
+/* Constrain the possible values of @reg with unsigned upper bound @bound.
+ * If @is_exclusive, @bound is an exclusive limit, otherwise it is inclusive.
+ * If @is_jmp32, @bound is a 32-bit value that only constrains the low 32 bits
+ * of @reg.
+ */
+static void set_upper_bound(struct bpf_reg_state *reg, u64 bound, bool is_jmp32,
+			    bool is_exclusive)
+{
+	if (is_exclusive) {
+		/* There are no values for `reg` that make `reg<0` true. */
+		if (bound == 0)
+			return;
+		bound--;
+	}
+	if (is_jmp32) {
+		/* Constrain the register's value in the tnum representation.
+		 * For 64-bit comparisons this happens later in
+		 * __reg_bound_offset(), but for 32-bit comparisons, we can be
+		 * more precise than what can be derived from the updated
+		 * numeric bounds.
+		 */
+		struct tnum t = tnum_range(0, bound);
+
+		t.mask |= ~0xffffffffULL; /* upper half is unknown */
+		reg->var_off = tnum_intersect(reg->var_off, t);
+
+		/* Compute the 64-bit bound from the 32-bit bound. */
+		bound += gen_hi_max(reg->var_off);
+	}
+	reg->umax_value = min(reg->umax_value, bound);
+}
+
+/* Constrain the possible values of @reg with unsigned lower bound @bound.
+ * If @is_exclusive, @bound is an exclusive limit, otherwise it is inclusive.
+ * If @is_jmp32, @bound is a 32-bit value that only constrains the low 32 bits
+ * of @reg.
+ */
+static void set_lower_bound(struct bpf_reg_state *reg, u64 bound, bool is_jmp32,
+			    bool is_exclusive)
+{
+	if (is_exclusive) {
+		/* There are no values for `reg` that make `reg>MAX` true. */
+		if (bound == (is_jmp32 ? U32_MAX : U64_MAX))
+			return;
+		bound++;
+	}
+	if (is_jmp32) {
+		/* Constrain the register's value in the tnum representation.
+		 * For 64-bit comparisons this happens later in
+		 * __reg_bound_offset(), but for 32-bit comparisons, we can be
+		 * more precise than what can be derived from the updated
+		 * numeric bounds.
+		 */
+		struct tnum t = tnum_range(bound, U32_MAX);
+
+		t.mask |= ~0xffffffffULL; /* upper half is unknown */
+		reg->var_off = tnum_intersect(reg->var_off, t);
+
+		/* Compute the 64-bit bound from the 32-bit bound. */
+		bound += gen_hi_min(reg->var_off);
+	}
+	reg->umin_value = max(reg->umin_value, bound);
+}
+
 /* Adjusts the register min/max values in the case that the dst_reg is the
  * variable register that we are working on, and src_reg is a constant or we're
  * simply doing a BPF_K check.
@@ -4646,15 +4729,8 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg,
 	case BPF_JGE:
 	case BPF_JGT:
 	{
-		u64 false_umax = opcode == BPF_JGT ? val    : val - 1;
-		u64 true_umin = opcode == BPF_JGT ? val + 1 : val;
-
-		if (is_jmp32) {
-			false_umax += gen_hi_max(false_reg->var_off);
-			true_umin += gen_hi_min(true_reg->var_off);
-		}
-		false_reg->umax_value = min(false_reg->umax_value, false_umax);
-		true_reg->umin_value = max(true_reg->umin_value, true_umin);
+		set_upper_bound(false_reg, val, is_jmp32, opcode == BPF_JGE);
+		set_lower_bound(true_reg, val, is_jmp32, opcode == BPF_JGT);
 		break;
 	}
 	case BPF_JSGE:
@@ -4675,15 +4751,8 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg,
 	case BPF_JLE:
 	case BPF_JLT:
 	{
-		u64 false_umin = opcode == BPF_JLT ? val    : val + 1;
-		u64 true_umax = opcode == BPF_JLT ? val - 1 : val;
-
-		if (is_jmp32) {
-			false_umin += gen_hi_min(false_reg->var_off);
-			true_umax += gen_hi_max(true_reg->var_off);
-		}
-		false_reg->umin_value = max(false_reg->umin_value, false_umin);
-		true_reg->umax_value = min(true_reg->umax_value, true_umax);
+		set_lower_bound(false_reg, val, is_jmp32, opcode == BPF_JLE);
+		set_upper_bound(true_reg, val, is_jmp32, opcode == BPF_JLT);
 		break;
 	}
 	case BPF_JSLE:
@@ -4707,10 +4776,6 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg,
 	/* We might have learned some bits from the bounds. */
 	__reg_bound_offset(false_reg);
 	__reg_bound_offset(true_reg);
-	if (is_jmp32) {
-		__reg_bound_offset32(false_reg);
-		__reg_bound_offset32(true_reg);
-	}
 	/* Intersecting with the old var_off might have improved our bounds
 	 * slightly.  e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
 	 * then new var_off is (0; 0x7f...fc) which improves our umax.
@@ -4762,15 +4827,8 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
 	case BPF_JGE:
 	case BPF_JGT:
 	{
-		u64 false_umin = opcode == BPF_JGT ? val    : val + 1;
-		u64 true_umax = opcode == BPF_JGT ? val - 1 : val;
-
-		if (is_jmp32) {
-			false_umin += gen_hi_min(false_reg->var_off);
-			true_umax += gen_hi_max(true_reg->var_off);
-		}
-		false_reg->umin_value = max(false_reg->umin_value, false_umin);
-		true_reg->umax_value = min(true_reg->umax_value, true_umax);
+		set_lower_bound(false_reg, val, is_jmp32, opcode == BPF_JGE);
+		set_upper_bound(true_reg, val, is_jmp32, opcode == BPF_JGT);
 		break;
 	}
 	case BPF_JSGE:
@@ -4788,15 +4846,8 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
 	case BPF_JLE:
 	case BPF_JLT:
 	{
-		u64 false_umax = opcode == BPF_JLT ? val    : val - 1;
-		u64 true_umin = opcode == BPF_JLT ? val + 1 : val;
-
-		if (is_jmp32) {
-			false_umax += gen_hi_max(false_reg->var_off);
-			true_umin += gen_hi_min(true_reg->var_off);
-		}
-		false_reg->umax_value = min(false_reg->umax_value, false_umax);
-		true_reg->umin_value = max(true_reg->umin_value, true_umin);
+		set_upper_bound(false_reg, val, is_jmp32, opcode == BPF_JLE);
+		set_lower_bound(true_reg, val, is_jmp32, opcode == BPF_JLT);
 		break;
 	}
 	case BPF_JSLE:
@@ -4820,10 +4871,6 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
 	/* We might have learned some bits from the bounds. */
 	__reg_bound_offset(false_reg);
 	__reg_bound_offset(true_reg);
-	if (is_jmp32) {
-		__reg_bound_offset32(false_reg);
-		__reg_bound_offset32(true_reg);
-	}
 	/* Intersecting with the old var_off might have improved our bounds
 	 * slightly.  e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
 	 * then new var_off is (0; 0x7f...fc) which improves our umax.
@@ -5287,6 +5334,7 @@ static bool may_access_skb(enum bpf_prog_type type)
 static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
 {
 	struct bpf_reg_state *regs = cur_regs(env);
+	static const int ctx_reg = BPF_REG_6;
 	u8 mode = BPF_MODE(insn->code);
 	int i, err;
 
@@ -5320,7 +5368,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	}
 
 	/* check whether implicit source operand (register R6) is readable */
-	err = check_reg_arg(env, BPF_REG_6, SRC_OP);
+	err = check_reg_arg(env, ctx_reg, SRC_OP);
 	if (err)
 		return err;
 
@@ -5339,7 +5387,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
 		return -EINVAL;
 	}
 
-	if (regs[BPF_REG_6].type != PTR_TO_CTX) {
+	if (regs[ctx_reg].type != PTR_TO_CTX) {
 		verbose(env,
 			"at the time of BPF_LD_ABS|IND R6 != pointer to skb\n");
 		return -EINVAL;
@@ -5352,6 +5400,10 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			return err;
 	}
 
+	err = check_ctx_reg(env, &regs[ctx_reg], ctx_reg);
+	if (err < 0)
+		return err;
+
 	/* reset caller saved regs to unreadable */
 	for (i = 0; i < CALLER_SAVED_REGS; i++) {
 		mark_reg_not_init(env, regs, caller_saved[i]);
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 88006be40ea3..9dc41608b013 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -492,6 +492,7 @@ static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
 	 */
 	p++;
 	if (p >= end) {
+		(*pos)++;
 		return NULL;
 	} else {
 		*pos = *p;
@@ -802,7 +803,7 @@ void cgroup1_release_agent(struct work_struct *work)
 
 	pathbuf = kmalloc(PATH_MAX, GFP_KERNEL);
 	agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL);
-	if (!pathbuf || !agentbuf)
+	if (!pathbuf || !agentbuf || !strlen(agentbuf))
 		goto out;
 
 	spin_lock_irq(&css_set_lock);
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index acc899797fef..fb24e7424411 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -3068,8 +3068,6 @@ static int cgroup_apply_control_enable(struct cgroup *cgrp)
 		for_each_subsys(ss, ssid) {
 			struct cgroup_subsys_state *css = cgroup_css(dsct, ss);
 
-			WARN_ON_ONCE(css && percpu_ref_is_dying(&css->refcnt));
-
 			if (!(cgroup_ss_mask(dsct) & (1 << ss->id)))
 				continue;
 
@@ -3079,6 +3077,8 @@ static int cgroup_apply_control_enable(struct cgroup *cgrp)
 					return PTR_ERR(css);
 			}
 
+			WARN_ON_ONCE(percpu_ref_is_dying(&css->refcnt));
+
 			if (css_visible(css)) {
 				ret = css_populate_dir(css);
 				if (ret)
@@ -3114,11 +3114,11 @@ static void cgroup_apply_control_disable(struct cgroup *cgrp)
 		for_each_subsys(ss, ssid) {
 			struct cgroup_subsys_state *css = cgroup_css(dsct, ss);
 
-			WARN_ON_ONCE(css && percpu_ref_is_dying(&css->refcnt));
-
 			if (!css)
 				continue;
 
+			WARN_ON_ONCE(percpu_ref_is_dying(&css->refcnt));
+
 			if (css->parent &&
 			    !(cgroup_ss_mask(dsct) & (1 << ss->id))) {
 				kill_css(css);
@@ -3405,7 +3405,8 @@ static ssize_t cgroup_type_write(struct kernfs_open_file *of, char *buf,
 	if (strcmp(strstrip(buf), "threaded"))
 		return -EINVAL;
 
-	cgrp = cgroup_kn_lock_live(of->kn, false);
+	/* drain dying csses before we re-apply (threaded) subtree control */
+	cgrp = cgroup_kn_lock_live(of->kn, true);
 	if (!cgrp)
 		return -ENOENT;
 
@@ -4416,12 +4417,16 @@ static void css_task_iter_advance_css_set(struct css_task_iter *it)
 		}
 	} while (!css_set_populated(cset) && list_empty(&cset->dying_tasks));
 
-	if (!list_empty(&cset->tasks))
+	if (!list_empty(&cset->tasks)) {
 		it->task_pos = cset->tasks.next;
-	else if (!list_empty(&cset->mg_tasks))
+		it->cur_tasks_head = &cset->tasks;
+	} else if (!list_empty(&cset->mg_tasks)) {
 		it->task_pos = cset->mg_tasks.next;
-	else
+		it->cur_tasks_head = &cset->mg_tasks;
+	} else {
 		it->task_pos = cset->dying_tasks.next;
+		it->cur_tasks_head = &cset->dying_tasks;
+	}
 
 	it->tasks_head = &cset->tasks;
 	it->mg_tasks_head = &cset->mg_tasks;
@@ -4479,10 +4484,14 @@ repeat:
 		else
 			it->task_pos = it->task_pos->next;
 
-		if (it->task_pos == it->tasks_head)
+		if (it->task_pos == it->tasks_head) {
 			it->task_pos = it->mg_tasks_head->next;
-		if (it->task_pos == it->mg_tasks_head)
+			it->cur_tasks_head = it->mg_tasks_head;
+		}
+		if (it->task_pos == it->mg_tasks_head) {
 			it->task_pos = it->dying_tasks_head->next;
+			it->cur_tasks_head = it->dying_tasks_head;
+		}
 		if (it->task_pos == it->dying_tasks_head)
 			css_task_iter_advance_css_set(it);
 	} else {
@@ -4501,11 +4510,12 @@ repeat:
 			goto repeat;
 
 		/* and dying leaders w/o live member threads */
-		if (!atomic_read(&task->signal->live))
+		if (it->cur_tasks_head == it->dying_tasks_head &&
+		    !atomic_read(&task->signal->live))
 			goto repeat;
 	} else {
 		/* skip all dying ones */
-		if (task->flags & PF_EXITING)
+		if (it->cur_tasks_head == it->dying_tasks_head)
 			goto repeat;
 	}
 }
@@ -4614,6 +4624,9 @@ static void *cgroup_procs_next(struct seq_file *s, void *v, loff_t *pos)
 	struct kernfs_open_file *of = s->private;
 	struct css_task_iter *it = of->priv;
 
+	if (pos)
+		(*pos)++;
+
 	return css_task_iter_next(it);
 }
 
@@ -4629,7 +4642,7 @@ static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos,
 	 * from position 0, so we can simply keep iterating on !0 *pos.
 	 */
 	if (!it) {
-		if (WARN_ON_ONCE((*pos)++))
+		if (WARN_ON_ONCE((*pos)))
 			return ERR_PTR(-EINVAL);
 
 		it = kzalloc(sizeof(*it), GFP_KERNEL);
@@ -4637,10 +4650,11 @@ static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos,
 			return ERR_PTR(-ENOMEM);
 		of->priv = it;
 		css_task_iter_start(&cgrp->self, iter_flags, it);
-	} else if (!(*pos)++) {
+	} else if (!(*pos)) {
 		css_task_iter_end(it);
 		css_task_iter_start(&cgrp->self, iter_flags, it);
-	}
+	} else
+		return it->cur_task;
 
 	return cgroup_procs_next(s, NULL, NULL);
 }
@@ -6277,19 +6291,14 @@ void cgroup_sk_alloc_disable(void)
 
 void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
 {
-	if (cgroup_sk_alloc_disabled)
+	if (cgroup_sk_alloc_disabled) {
+		skcd->no_refcnt = 1;
 		return;
+	}
 
-	/* Socket clone path */
-	if (skcd->val) {
-		/*
-		 * We might be cloning a socket which is left in an empty
-		 * cgroup and the cgroup might have already been rmdir'd.
-		 * Don't use cgroup_get_live().
-		 */
-		cgroup_get(sock_cgroup_ptr(skcd));
+	/* Don't associate the sock with unrelated interrupted task's cgroup. */
+	if (in_interrupt())
 		return;
-	}
 
 	rcu_read_lock();
 
@@ -6307,8 +6316,24 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
 	rcu_read_unlock();
 }
 
+void cgroup_sk_clone(struct sock_cgroup_data *skcd)
+{
+	/* Socket clone path */
+	if (skcd->val) {
+		/*
+		 * We might be cloning a socket which is left in an empty
+		 * cgroup and the cgroup might have already been rmdir'd.
+		 * Don't use cgroup_get_live().
+		 */
+		cgroup_get(sock_cgroup_ptr(skcd));
+	}
+}
+
 void cgroup_sk_free(struct sock_cgroup_data *skcd)
 {
+	if (skcd->no_refcnt)
+		return;
+
 	cgroup_put(sock_cgroup_ptr(skcd));
 }
 
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index ca19b4c8acf5..4a942d4e9763 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -33,12 +33,9 @@ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu)
 		return;
 
 	/*
-	 * Paired with the one in cgroup_rstat_cpu_pop_upated().  Either we
-	 * see NULL updated_next or they see our updated stat.
-	 */
-	smp_mb();
-
-	/*
+	 * Speculative already-on-list test. This may race leading to
+	 * temporary inaccuracies, which is fine.
+	 *
 	 * Because @parent's updated_children is terminated with @parent
 	 * instead of NULL, we can tell whether @cgrp is on the list by
 	 * testing the next pointer for NULL.
@@ -134,13 +131,6 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
 		*nextp = rstatc->updated_next;
 		rstatc->updated_next = NULL;
 
-		/*
-		 * Paired with the one in cgroup_rstat_cpu_updated().
-		 * Either they see NULL updated_next or we see their
-		 * updated stat.
-		 */
-		smp_mb();
-
 		return pos;
 	}
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 44fe5c7cfc07..0e483a4aaf84 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -3,6 +3,7 @@
  *
  * This code is licenced under the GPL.
  */
+#include <linux/sched/mm.h>
 #include <linux/proc_fs.h>
 #include <linux/smp.h>
 #include <linux/init.h>
@@ -515,8 +516,7 @@ static int bringup_wait_for_ap(unsigned int cpu)
 	if (WARN_ON_ONCE((!cpu_online(cpu))))
 		return -ECANCELED;
 
-	/* Unpark the stopper thread and the hotplug thread of the target cpu */
-	stop_machine_unpark(cpu);
+	/* Unpark the hotplug thread of the target cpu */
 	kthread_unpark(st->thread);
 
 	/*
@@ -555,6 +555,21 @@ static int bringup_cpu(unsigned int cpu)
 	return bringup_wait_for_ap(cpu);
 }
 
+static int finish_cpu(unsigned int cpu)
+{
+	struct task_struct *idle = idle_thread_get(cpu);
+	struct mm_struct *mm = idle->active_mm;
+
+	/*
+	 * idle_task_exit() will have switched to &init_mm, now
+	 * clean up any remaining active_mm state.
+	 */
+	if (mm != &init_mm)
+		idle->active_mm = &init_mm;
+	mmdrop(mm);
+	return 0;
+}
+
 /*
  * Hotplug state machine related functions
  */
@@ -1079,8 +1094,8 @@ void notify_cpu_starting(unsigned int cpu)
 
 /*
  * Called from the idle task. Wake up the controlling task which brings the
- * stopper and the hotplug thread of the upcoming CPU up and then delegates
- * the rest of the online bringup to the hotplug thread.
+ * hotplug thread of the upcoming CPU up and then delegates the rest of the
+ * online bringup to the hotplug thread.
  */
 void cpuhp_online_idle(enum cpuhp_state state)
 {
@@ -1090,6 +1105,12 @@ void cpuhp_online_idle(enum cpuhp_state state)
 	if (state != CPUHP_AP_ONLINE_IDLE)
 		return;
 
+	/*
+	 * Unpart the stopper thread before we start the idle loop (and start
+	 * scheduling); this ensures the stopper task is always available.
+	 */
+	stop_machine_unpark(smp_processor_id());
+
 	st->state = CPUHP_AP_ONLINE_IDLE;
 	complete_ap_thread(st, true);
 }
@@ -1412,7 +1433,7 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 	[CPUHP_BRINGUP_CPU] = {
 		.name			= "cpu:bringup",
 		.startup.single		= bringup_cpu,
-		.teardown.single	= NULL,
+		.teardown.single	= finish_cpu,
 		.cant_stop		= true,
 	},
 	/* Final state before CPU kills itself */
@@ -1892,6 +1913,78 @@ void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
 }
 EXPORT_SYMBOL(__cpuhp_remove_state);
 
+#ifdef CONFIG_HOTPLUG_SMT
+static void cpuhp_offline_cpu_device(unsigned int cpu)
+{
+	struct device *dev = get_cpu_device(cpu);
+
+	dev->offline = true;
+	/* Tell user space about the state change */
+	kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
+}
+
+static void cpuhp_online_cpu_device(unsigned int cpu)
+{
+	struct device *dev = get_cpu_device(cpu);
+
+	dev->offline = false;
+	/* Tell user space about the state change */
+	kobject_uevent(&dev->kobj, KOBJ_ONLINE);
+}
+
+int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
+{
+	int cpu, ret = 0;
+
+	cpu_maps_update_begin();
+	for_each_online_cpu(cpu) {
+		if (topology_is_primary_thread(cpu))
+			continue;
+		ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
+		if (ret)
+			break;
+		/*
+		 * As this needs to hold the cpu maps lock it's impossible
+		 * to call device_offline() because that ends up calling
+		 * cpu_down() which takes cpu maps lock. cpu maps lock
+		 * needs to be held as this might race against in kernel
+		 * abusers of the hotplug machinery (thermal management).
+		 *
+		 * So nothing would update device:offline state. That would
+		 * leave the sysfs entry stale and prevent onlining after
+		 * smt control has been changed to 'off' again. This is
+		 * called under the sysfs hotplug lock, so it is properly
+		 * serialized against the regular offline usage.
+		 */
+		cpuhp_offline_cpu_device(cpu);
+	}
+	if (!ret)
+		cpu_smt_control = ctrlval;
+	cpu_maps_update_done();
+	return ret;
+}
+
+int cpuhp_smt_enable(void)
+{
+	int cpu, ret = 0;
+
+	cpu_maps_update_begin();
+	cpu_smt_control = CPU_SMT_ENABLED;
+	for_each_present_cpu(cpu) {
+		/* Skip online CPUs and CPUs on offline nodes */
+		if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
+			continue;
+		ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
+		if (ret)
+			break;
+		/* See comment in cpuhp_smt_disable() */
+		cpuhp_online_cpu_device(cpu);
+	}
+	cpu_maps_update_done();
+	return ret;
+}
+#endif
+
 #if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU)
 static ssize_t show_cpuhp_state(struct device *dev,
 				struct device_attribute *attr, char *buf)
@@ -2046,77 +2139,6 @@ static const struct attribute_group cpuhp_cpu_root_attr_group = {
 
 #ifdef CONFIG_HOTPLUG_SMT
 
-static void cpuhp_offline_cpu_device(unsigned int cpu)
-{
-	struct device *dev = get_cpu_device(cpu);
-
-	dev->offline = true;
-	/* Tell user space about the state change */
-	kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
-}
-
-static void cpuhp_online_cpu_device(unsigned int cpu)
-{
-	struct device *dev = get_cpu_device(cpu);
-
-	dev->offline = false;
-	/* Tell user space about the state change */
-	kobject_uevent(&dev->kobj, KOBJ_ONLINE);
-}
-
-int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
-{
-	int cpu, ret = 0;
-
-	cpu_maps_update_begin();
-	for_each_online_cpu(cpu) {
-		if (topology_is_primary_thread(cpu))
-			continue;
-		ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
-		if (ret)
-			break;
-		/*
-		 * As this needs to hold the cpu maps lock it's impossible
-		 * to call device_offline() because that ends up calling
-		 * cpu_down() which takes cpu maps lock. cpu maps lock
-		 * needs to be held as this might race against in kernel
-		 * abusers of the hotplug machinery (thermal management).
-		 *
-		 * So nothing would update device:offline state. That would
-		 * leave the sysfs entry stale and prevent onlining after
-		 * smt control has been changed to 'off' again. This is
-		 * called under the sysfs hotplug lock, so it is properly
-		 * serialized against the regular offline usage.
-		 */
-		cpuhp_offline_cpu_device(cpu);
-	}
-	if (!ret)
-		cpu_smt_control = ctrlval;
-	cpu_maps_update_done();
-	return ret;
-}
-
-int cpuhp_smt_enable(void)
-{
-	int cpu, ret = 0;
-
-	cpu_maps_update_begin();
-	cpu_smt_control = CPU_SMT_ENABLED;
-	for_each_present_cpu(cpu) {
-		/* Skip online CPUs and CPUs on offline nodes */
-		if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
-			continue;
-		ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
-		if (ret)
-			break;
-		/* See comment in cpuhp_smt_disable() */
-		cpuhp_online_cpu_device(cpu);
-	}
-	cpu_maps_update_done();
-	return ret;
-}
-
-
 static ssize_t
 __store_smt_control(struct device *dev, struct device_attribute *attr,
 		    const char *buf, size_t count)
diff --git a/kernel/cpu_pm.c b/kernel/cpu_pm.c
index cbca6879ab7d..44a259338e33 100644
--- a/kernel/cpu_pm.c
+++ b/kernel/cpu_pm.c
@@ -80,7 +80,7 @@ EXPORT_SYMBOL_GPL(cpu_pm_unregister_notifier);
  */
 int cpu_pm_enter(void)
 {
-	int nr_calls;
+	int nr_calls = 0;
 	int ret = 0;
 
 	ret = cpu_pm_notify(CPU_PM_ENTER, -1, &nr_calls);
@@ -131,7 +131,7 @@ EXPORT_SYMBOL_GPL(cpu_pm_exit);
  */
 int cpu_cluster_pm_enter(void)
 {
-	int nr_calls;
+	int nr_calls = 0;
 	int ret = 0;
 
 	ret = cpu_pm_notify(CPU_CLUSTER_PM_ENTER, -1, &nr_calls);
diff --git a/kernel/cred.c b/kernel/cred.c
index 153ae369e024..7cfd1db529d4 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -218,7 +218,7 @@ struct cred *cred_alloc_blank(void)
 	new->magic = CRED_MAGIC;
 #endif
 
-	if (security_cred_alloc_blank(new, GFP_KERNEL) < 0)
+	if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0)
 		goto error;
 
 	return new;
@@ -277,7 +277,7 @@ struct cred *prepare_creds(void)
 	new->security = NULL;
 #endif
 
-	if (security_prepare_creds(new, old, GFP_KERNEL) < 0)
+	if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
 		goto error;
 	validate_creds(new);
 	return new;
@@ -706,7 +706,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
 #ifdef CONFIG_SECURITY
 	new->security = NULL;
 #endif
-	if (security_prepare_creds(new, old, GFP_KERNEL) < 0)
+	if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
 		goto error;
 
 	put_cred(old);
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 5cc608de6883..18a6a8642495 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -501,6 +501,7 @@ static int kgdb_reenter_check(struct kgdb_state *ks)
 
 	if (exception_level > 1) {
 		dump_stack();
+		kgdb_io_module_registered = false;
 		panic("Recursive entry to debugger");
 	}
 
@@ -545,6 +546,7 @@ static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs,
 		arch_kgdb_ops.disable_hw_break(regs);
 
 acquirelock:
+	rcu_read_lock();
 	/*
 	 * Interrupts will be restored by the 'trap return' code, except when
 	 * single stepping.
@@ -601,6 +603,7 @@ return_normal:
 			atomic_dec(&slaves_in_kgdb);
 			dbg_touch_watchdogs();
 			local_irq_restore(flags);
+			rcu_read_unlock();
 			return 0;
 		}
 		cpu_relax();
@@ -619,6 +622,7 @@ return_normal:
 		raw_spin_unlock(&dbg_master_lock);
 		dbg_touch_watchdogs();
 		local_irq_restore(flags);
+		rcu_read_unlock();
 
 		goto acquirelock;
 	}
@@ -634,6 +638,8 @@ return_normal:
 	if (kgdb_skipexception(ks->ex_vector, ks->linux_regs))
 		goto kgdb_restore;
 
+	atomic_inc(&ignore_console_lock_warning);
+
 	/* Call the I/O driver's pre_exception routine */
 	if (dbg_io_ops->pre_exception)
 		dbg_io_ops->pre_exception();
@@ -706,6 +712,8 @@ cpu_master_loop:
 	if (dbg_io_ops->post_exception)
 		dbg_io_ops->post_exception();
 
+	atomic_dec(&ignore_console_lock_warning);
+
 	if (!kgdb_single_step) {
 		raw_spin_unlock(&dbg_slave_lock);
 		/* Wait till all the CPUs have quit from the debugger. */
@@ -738,6 +746,7 @@ kgdb_restore:
 	raw_spin_unlock(&dbg_master_lock);
 	dbg_touch_watchdogs();
 	local_irq_restore(flags);
+	rcu_read_unlock();
 
 	return kgdb_info[cpu].ret_state;
 }
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 9ecfa37c7fbf..bb5dec762b69 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -1103,12 +1103,12 @@ static int handle_ctrl_cmd(char *cmd)
 	case CTRL_P:
 		if (cmdptr != cmd_tail)
 			cmdptr = (cmdptr-1) % KDB_CMD_HISTORY_COUNT;
-		strncpy(cmd_cur, cmd_hist[cmdptr], CMD_BUFLEN);
+		strscpy(cmd_cur, cmd_hist[cmdptr], CMD_BUFLEN);
 		return 1;
 	case CTRL_N:
 		if (cmdptr != cmd_head)
 			cmdptr = (cmdptr+1) % KDB_CMD_HISTORY_COUNT;
-		strncpy(cmd_cur, cmd_hist[cmdptr], CMD_BUFLEN);
+		strscpy(cmd_cur, cmd_hist[cmdptr], CMD_BUFLEN);
 		return 1;
 	}
 	return 0;
@@ -1315,7 +1315,7 @@ do_full_getstr:
 		if (*cmdbuf != '\n') {
 			if (*cmdbuf < 32) {
 				if (cmdptr == cmd_head) {
-					strncpy(cmd_hist[cmd_head], cmd_cur,
+					strscpy(cmd_hist[cmd_head], cmd_cur,
 						CMD_BUFLEN);
 					*(cmd_hist[cmd_head] +
 					  strlen(cmd_hist[cmd_head])-1) = '\0';
@@ -1325,7 +1325,7 @@ do_full_getstr:
 				cmdbuf = cmd_cur;
 				goto do_full_getstr;
 			} else {
-				strncpy(cmd_hist[cmd_head], cmd_cur,
+				strscpy(cmd_hist[cmd_head], cmd_cur,
 					CMD_BUFLEN);
 			}
 
diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c
index 99b21efe2649..3fe6e0119ee6 100644
--- a/kernel/dma/coherent.c
+++ b/kernel/dma/coherent.c
@@ -146,7 +146,7 @@ static void *__dma_alloc_from_coherent(struct device *dev,
 
 	spin_lock_irqsave(&mem->spinlock, flags);
 
-	if (unlikely(size > (mem->size << PAGE_SHIFT)))
+	if (unlikely(size > ((dma_addr_t)mem->size << PAGE_SHIFT)))
 		goto err;
 
 	pageno = bitmap_find_free_region(mem->bitmap, mem->size, order);
@@ -156,8 +156,9 @@ static void *__dma_alloc_from_coherent(struct device *dev,
 	/*
 	 * Memory was found in the coherent area.
 	 */
-	*dma_handle = dma_get_device_base(dev, mem) + (pageno << PAGE_SHIFT);
-	ret = mem->virt_base + (pageno << PAGE_SHIFT);
+	*dma_handle = dma_get_device_base(dev, mem) +
+			((dma_addr_t)pageno << PAGE_SHIFT);
+	ret = mem->virt_base + ((dma_addr_t)pageno << PAGE_SHIFT);
 	spin_unlock_irqrestore(&mem->spinlock, flags);
 	memset(ret, 0, size);
 	return ret;
@@ -206,7 +207,7 @@ static int __dma_release_from_coherent(struct dma_coherent_mem *mem,
 				       int order, void *vaddr)
 {
 	if (mem && vaddr >= mem->virt_base && vaddr <
-		   (mem->virt_base + (mem->size << PAGE_SHIFT))) {
+		   (mem->virt_base + ((dma_addr_t)mem->size << PAGE_SHIFT))) {
 		int page = (vaddr - mem->virt_base) >> PAGE_SHIFT;
 		unsigned long flags;
 
@@ -250,10 +251,10 @@ static int __dma_mmap_from_coherent(struct dma_coherent_mem *mem,
 		struct vm_area_struct *vma, void *vaddr, size_t size, int *ret)
 {
 	if (mem && vaddr >= mem->virt_base && vaddr + size <=
-		   (mem->virt_base + (mem->size << PAGE_SHIFT))) {
+		   (mem->virt_base + ((dma_addr_t)mem->size << PAGE_SHIFT))) {
 		unsigned long off = vma->vm_pgoff;
 		int start = (vaddr - mem->virt_base) >> PAGE_SHIFT;
-		int user_count = vma_pages(vma);
+		unsigned long user_count = vma_pages(vma);
 		int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 
 		*ret = -ENXIO;
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 4ad74f5987ea..cb6425e52bf7 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -137,9 +137,12 @@ static const char *const maperr2str[] = {
 	[MAP_ERR_CHECKED] = "dma map error checked",
 };
 
-static const char *type2name[5] = { "single", "page",
-				    "scather-gather", "coherent",
-				    "resource" };
+static const char *type2name[] = {
+	[dma_debug_single] = "single",
+	[dma_debug_sg] = "scather-gather",
+	[dma_debug_coherent] = "coherent",
+	[dma_debug_resource] = "resource",
+};
 
 static const char *dir2name[4] = { "DMA_BIDIRECTIONAL", "DMA_TO_DEVICE",
 				   "DMA_FROM_DEVICE", "DMA_NONE" };
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 8552edfe81fb..bebc5ee62cbb 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -53,7 +53,8 @@ static inline dma_addr_t phys_to_dma_direct(struct device *dev,
 
 u64 dma_direct_get_required_mask(struct device *dev)
 {
-	u64 max_dma = phys_to_dma_direct(dev, (max_pfn - 1) << PAGE_SHIFT);
+	phys_addr_t phys = (phys_addr_t)(max_pfn - 1) << PAGE_SHIFT;
+	u64 max_dma = phys_to_dma_direct(dev, phys);
 
 	return (1ULL << (fls64(max_dma) - 1)) * 2 - 1;
 }
diff --git a/kernel/events/core.c b/kernel/events/core.c
index b077b6b3af97..0e6168c4cb7a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -93,11 +93,11 @@ static void remote_function(void *data)
  * @info:	the function call argument
  *
  * Calls the function @func when the task is currently running. This might
- * be on the current CPU, which just calls the function directly
+ * be on the current CPU, which just calls the function directly.  This will
+ * retry due to any failures in smp_call_function_single(), such as if the
+ * task_cpu() goes offline concurrently.
  *
- * returns: @func return value, or
- *	    -ESRCH  - when the process isn't running
- *	    -EAGAIN - when the process moved away
+ * returns @func return value or -ESRCH when the process isn't running
  */
 static int
 task_function_call(struct task_struct *p, remote_function_f func, void *info)
@@ -110,11 +110,16 @@ task_function_call(struct task_struct *p, remote_function_f func, void *info)
 	};
 	int ret;
 
-	do {
-		ret = smp_call_function_single(task_cpu(p), remote_function, &data, 1);
-		if (!ret)
-			ret = data.ret;
-	} while (ret == -EAGAIN);
+	for (;;) {
+		ret = smp_call_function_single(task_cpu(p), remote_function,
+					       &data, 1);
+		ret = !ret ? data.ret : -EAGAIN;
+
+		if (ret != -EAGAIN)
+			break;
+
+		cond_resched();
+	}
 
 	return ret;
 }
@@ -6444,9 +6449,12 @@ static u64 perf_virt_to_phys(u64 virt)
 		 * Try IRQ-safe __get_user_pages_fast first.
 		 * If failed, leave phys_addr as 0.
 		 */
-		if ((current->mm != NULL) &&
-		    (__get_user_pages_fast(virt, 1, 0, &p) == 1))
-			phys_addr = page_to_phys(p) + virt % PAGE_SIZE;
+		if (current->mm != NULL) {
+			pagefault_disable();
+			if (__get_user_pages_fast(virt, 1, 0, &p) == 1)
+				phys_addr = page_to_phys(p) + virt % PAGE_SIZE;
+			pagefault_enable();
+		}
 
 		if (p)
 			put_page(p);
@@ -6956,10 +6964,17 @@ static void perf_event_task_output(struct perf_event *event,
 		goto out;
 
 	task_event->event_id.pid = perf_event_pid(event, task);
-	task_event->event_id.ppid = perf_event_pid(event, current);
-
 	task_event->event_id.tid = perf_event_tid(event, task);
-	task_event->event_id.ptid = perf_event_tid(event, current);
+
+	if (task_event->event_id.header.type == PERF_RECORD_EXIT) {
+		task_event->event_id.ppid = perf_event_pid(event,
+							task->real_parent);
+		task_event->event_id.ptid = perf_event_pid(event,
+							task->real_parent);
+	} else {  /* PERF_RECORD_FORK */
+		task_event->event_id.ppid = perf_event_pid(event, current);
+		task_event->event_id.ptid = perf_event_tid(event, current);
+	}
 
 	task_event->event_id.time = perf_event_clock(event);
 
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 78f61bfc6b79..673044edd9ad 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -815,10 +815,6 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file,
 	if (ret)
 		goto out;
 
-	/* uprobe_write_opcode() assumes we don't cross page boundary */
-	BUG_ON((uprobe->offset & ~PAGE_MASK) +
-			UPROBE_SWBP_INSN_SIZE > PAGE_SIZE);
-
 	smp_wmb(); /* pairs with the smp_rmb() in handle_swbp() */
 	set_bit(UPROBE_COPY_INSN, &uprobe->flags);
 
@@ -1114,6 +1110,15 @@ static int __uprobe_register(struct inode *inode, loff_t offset,
 	if (offset > i_size_read(inode))
 		return -EINVAL;
 
+	/*
+	 * This ensures that copy_from_page(), copy_to_page() and
+	 * __update_ref_ctr() can't cross page boundary.
+	 */
+	if (!IS_ALIGNED(offset, UPROBE_SWBP_INSN_SIZE))
+		return -EINVAL;
+	if (!IS_ALIGNED(ref_ctr_offset, sizeof(short)))
+		return -EINVAL;
+
  retry:
 	uprobe = alloc_uprobe(inode, offset, ref_ctr_offset);
 	if (!uprobe)
@@ -1962,6 +1967,9 @@ static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr)
 	uprobe_opcode_t opcode;
 	int result;
 
+	if (WARN_ON_ONCE(!IS_ALIGNED(vaddr, UPROBE_SWBP_INSN_SIZE)))
+		return -EINVAL;
+
 	pagefault_disable();
 	result = __get_user(opcode, (uprobe_opcode_t __user *)vaddr);
 	pagefault_enable();
@@ -2145,7 +2153,7 @@ static void handle_swbp(struct pt_regs *regs)
 	if (!uprobe) {
 		if (is_swbp > 0) {
 			/* No matching uprobe; signal SIGTRAP. */
-			send_sig(SIGTRAP, current, 0);
+			force_sig(SIGTRAP, current);
 		} else {
 			/*
 			 * Either we raced with uprobe_unregister() or we can't
diff --git a/kernel/exit.c b/kernel/exit.c
index 235cf6825593..2dbaa5c86b73 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -579,10 +579,6 @@ static struct task_struct *find_child_reaper(struct task_struct *father,
 	}
 
 	write_unlock_irq(&tasklist_lock);
-	if (unlikely(pid_ns == &init_pid_ns)) {
-		panic("Attempted to kill init! exitcode=0x%08x\n",
-			father->signal->group_exit_code ?: father->exit_code);
-	}
 
 	list_for_each_entry_safe(p, n, dead, ptrace_entry) {
 		list_del_init(&p->ptrace_entry);
@@ -839,8 +835,12 @@ void __noreturn do_exit(long code)
 	struct task_struct *tsk = current;
 	int group_dead;
 
-	profile_task_exit(tsk);
-	kcov_task_exit(tsk);
+	/*
+	 * We can get here from a kernel oops, sometimes with preemption off.
+	 * Start by checking for critical errors.
+	 * Then fix up important state like USER_DS and preemption.
+	 * Then do everything else.
+	 */
 
 	WARN_ON(blk_needs_flush_plug(tsk));
 
@@ -858,6 +858,16 @@ void __noreturn do_exit(long code)
 	 */
 	set_fs(USER_DS);
 
+	if (unlikely(in_atomic())) {
+		pr_info("note: %s[%d] exited with preempt_count %d\n",
+			current->comm, task_pid_nr(current),
+			preempt_count());
+		preempt_count_set(PREEMPT_ENABLED);
+	}
+
+	profile_task_exit(tsk);
+	kcov_task_exit(tsk);
+
 	ptrace_event(PTRACE_EVENT_EXIT, code);
 
 	validate_creds_for_do_exit(tsk);
@@ -895,19 +905,20 @@ void __noreturn do_exit(long code)
 	raw_spin_lock_irq(&tsk->pi_lock);
 	raw_spin_unlock_irq(&tsk->pi_lock);
 
-	if (unlikely(in_atomic())) {
-		pr_info("note: %s[%d] exited with preempt_count %d\n",
-			current->comm, task_pid_nr(current),
-			preempt_count());
-		preempt_count_set(PREEMPT_ENABLED);
-	}
-
 	/* sync mm's RSS info before statistics gathering */
 	if (tsk->mm)
 		sync_mm_rss(tsk->mm);
 	acct_update_integrals(tsk);
 	group_dead = atomic_dec_and_test(&tsk->signal->live);
 	if (group_dead) {
+		/*
+		 * If the last thread of global init has exited, panic
+		 * immediately to get a useable coredump.
+		 */
+		if (unlikely(is_global_init(tsk)))
+			panic("Attempted to kill init! exitcode=0x%08x\n",
+				tsk->signal->group_exit_code ?: (int)code);
+
 #ifdef CONFIG_POSIX_TIMERS
 		hrtimer_cancel(&tsk->signal->real_timer);
 		exit_itimers(tsk->signal);
diff --git a/kernel/futex.c b/kernel/futex.c
index 0341a97155bd..5758f44c994a 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -379,9 +379,9 @@ static inline int hb_waiters_pending(struct futex_hash_bucket *hb)
  */
 static struct futex_hash_bucket *hash_futex(union futex_key *key)
 {
-	u32 hash = jhash2((u32*)&key->both.word,
-			  (sizeof(key->both.word)+sizeof(key->both.ptr))/4,
+	u32 hash = jhash2((u32 *)key, offsetof(typeof(*key), both.offset) / 4,
 			  key->both.offset);
+
 	return &futex_queues[hash & (futex_hashsize - 1)];
 }
 
@@ -423,7 +423,7 @@ static void get_futex_key_refs(union futex_key *key)
 
 	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
 	case FUT_OFF_INODE:
-		ihold(key->shared.inode); /* implies smp_mb(); (B) */
+		smp_mb();		/* explicit smp_mb(); (B) */
 		break;
 	case FUT_OFF_MMSHARED:
 		futex_get_mm(key); /* implies smp_mb(); (B) */
@@ -457,7 +457,6 @@ static void drop_futex_key_refs(union futex_key *key)
 
 	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
 	case FUT_OFF_INODE:
-		iput(key->shared.inode);
 		break;
 	case FUT_OFF_MMSHARED:
 		mmdrop(key->private.mm);
@@ -470,6 +469,46 @@ enum futex_access {
 	FUTEX_WRITE
 };
 
+/*
+ * Generate a machine wide unique identifier for this inode.
+ *
+ * This relies on u64 not wrapping in the life-time of the machine; which with
+ * 1ns resolution means almost 585 years.
+ *
+ * This further relies on the fact that a well formed program will not unmap
+ * the file while it has a (shared) futex waiting on it. This mapping will have
+ * a file reference which pins the mount and inode.
+ *
+ * If for some reason an inode gets evicted and read back in again, it will get
+ * a new sequence number and will _NOT_ match, even though it is the exact same
+ * file.
+ *
+ * It is important that match_futex() will never have a false-positive, esp.
+ * for PI futexes that can mess up the state. The above argues that false-negatives
+ * are only possible for malformed programs.
+ */
+static u64 get_inode_sequence_number(struct inode *inode)
+{
+	static atomic64_t i_seq;
+	u64 old;
+
+	/* Does the inode already have a sequence number? */
+	old = atomic64_read(&inode->i_sequence);
+	if (likely(old))
+		return old;
+
+	for (;;) {
+		u64 new = atomic64_add_return(1, &i_seq);
+		if (WARN_ON_ONCE(!new))
+			continue;
+
+		old = atomic64_cmpxchg_relaxed(&inode->i_sequence, 0, new);
+		if (old)
+			return old;
+		return new;
+	}
+}
+
 /**
  * get_futex_key() - Get parameters which are the keys for a futex
  * @uaddr:	virtual address of the futex
@@ -482,9 +521,15 @@ enum futex_access {
  *
  * The key words are stored in @key on success.
  *
- * For shared mappings, it's (page->index, file_inode(vma->vm_file),
- * offset_within_page).  For private mappings, it's (uaddr, current->mm).
- * We can usually work out the index without swapping in the page.
+ * For shared mappings (when @fshared), the key is:
+ *   ( inode->i_sequence, page->index, offset_within_page )
+ * [ also see get_inode_sequence_number() ]
+ *
+ * For private mappings (or when !@fshared), the key is:
+ *   ( current->mm, address, 0 )
+ *
+ * This allows (cross process, where applicable) identification of the futex
+ * without keeping the page pinned for the duration of the FUTEX_WAIT.
  *
  * lock_page() might sleep, the caller should not hold a spinlock.
  */
@@ -624,8 +669,6 @@ again:
 		key->private.mm = mm;
 		key->private.address = address;
 
-		get_futex_key_refs(key); /* implies smp_mb(); (B) */
-
 	} else {
 		struct inode *inode;
 
@@ -657,40 +700,14 @@ again:
 			goto again;
 		}
 
-		/*
-		 * Take a reference unless it is about to be freed. Previously
-		 * this reference was taken by ihold under the page lock
-		 * pinning the inode in place so i_lock was unnecessary. The
-		 * only way for this check to fail is if the inode was
-		 * truncated in parallel which is almost certainly an
-		 * application bug. In such a case, just retry.
-		 *
-		 * We are not calling into get_futex_key_refs() in file-backed
-		 * cases, therefore a successful atomic_inc return below will
-		 * guarantee that get_futex_key() will still imply smp_mb(); (B).
-		 */
-		if (!atomic_inc_not_zero(&inode->i_count)) {
-			rcu_read_unlock();
-			put_page(page);
-
-			goto again;
-		}
-
-		/* Should be impossible but lets be paranoid for now */
-		if (WARN_ON_ONCE(inode->i_mapping != mapping)) {
-			err = -EFAULT;
-			rcu_read_unlock();
-			iput(inode);
-
-			goto out;
-		}
-
 		key->both.offset |= FUT_OFF_INODE; /* inode-based key */
-		key->shared.inode = inode;
+		key->shared.i_seq = get_inode_sequence_number(inode);
 		key->shared.pgoff = basepage_index(tail);
 		rcu_read_unlock();
 	}
 
+	get_futex_key_refs(key); /* implies smp_mb(); (B) */
+
 out:
 	put_page(page);
 	return err;
diff --git a/kernel/gcov/fs.c b/kernel/gcov/fs.c
index 6e40ff6be083..291e0797125b 100644
--- a/kernel/gcov/fs.c
+++ b/kernel/gcov/fs.c
@@ -109,9 +109,9 @@ static void *gcov_seq_next(struct seq_file *seq, void *data, loff_t *pos)
 {
 	struct gcov_iterator *iter = data;
 
+	(*pos)++;
 	if (gcov_iter_next(iter))
 		return NULL;
-	(*pos)++;
 
 	return iter;
 }
diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c
index c1eccd4f6520..d44c8fd17609 100644
--- a/kernel/irq/debugfs.c
+++ b/kernel/irq/debugfs.c
@@ -114,6 +114,7 @@ static const struct irq_bit_descr irqdata_states[] = {
 	BIT_MASK_DESCR(IRQD_AFFINITY_MANAGED),
 	BIT_MASK_DESCR(IRQD_MANAGED_SHUTDOWN),
 	BIT_MASK_DESCR(IRQD_CAN_RESERVE),
+	BIT_MASK_DESCR(IRQD_MSI_NOMASK_QUIRK),
 
 	BIT_MASK_DESCR(IRQD_FORWARDED_TO_VCPU),
 
@@ -205,8 +206,15 @@ static ssize_t irq_debug_write(struct file *file, const char __user *user_buf,
 		chip_bus_lock(desc);
 		raw_spin_lock_irqsave(&desc->lock, flags);
 
-		if (irq_settings_is_level(desc) || desc->istate & IRQS_NMI) {
-			/* Can't do level nor NMIs, sorry */
+		/*
+		 * Don't allow injection when the interrupt is:
+		 *  - Level or NMI type
+		 *  - not activated
+		 *  - replaying already
+		 */
+		if (irq_settings_is_level(desc) ||
+		    !irqd_is_activated(&desc->irq_data) ||
+		    (desc->istate & (IRQS_NMI | IRQS_REPLAY))) {
 			err = -EINVAL;
 		} else {
 			desc->istate |= IRQS_PENDING;
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 3a948f41ab00..207bac6ad4c3 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -128,8 +128,6 @@ static inline void unregister_handler_proc(unsigned int irq,
 
 extern bool irq_can_set_affinity_usr(unsigned int irq);
 
-extern int irq_select_affinity_usr(unsigned int irq);
-
 extern void irq_set_thread_affinity(struct irq_desc *desc);
 
 extern int irq_do_set_affinity(struct irq_data *data,
@@ -424,6 +422,10 @@ static inline struct cpumask *irq_desc_get_pending_mask(struct irq_desc *desc)
 {
 	return desc->pending_mask;
 }
+static inline bool handle_enforce_irqctx(struct irq_data *data)
+{
+	return irqd_is_handle_enforce_irqctx(data);
+}
 bool irq_fixup_move_pending(struct irq_desc *desc, bool force_clear);
 #else /* CONFIG_GENERIC_PENDING_IRQ */
 static inline bool irq_can_move_pcntxt(struct irq_data *data)
@@ -450,6 +452,10 @@ static inline bool irq_fixup_move_pending(struct irq_desc *desc, bool fclear)
 {
 	return false;
 }
+static inline bool handle_enforce_irqctx(struct irq_data *data)
+{
+	return false;
+}
 #endif /* !CONFIG_GENERIC_PENDING_IRQ */
 
 #if !defined(CONFIG_IRQ_DOMAIN) || !defined(CONFIG_IRQ_DOMAIN_HIERARCHY)
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 9be995fc3c5a..6a27603fe1cf 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -638,9 +638,15 @@ void irq_init_desc(unsigned int irq)
 int generic_handle_irq(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_data *data;
 
 	if (!desc)
 		return -EINVAL;
+
+	data = irq_desc_get_irq_data(desc);
+	if (WARN_ON_ONCE(!in_irq() && handle_enforce_irqctx(data)))
+		return -EPERM;
+
 	generic_handle_irq_desc(desc);
 	return 0;
 }
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index a453e229f99c..ee549d1007a4 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -1291,6 +1291,11 @@ int irq_domain_alloc_irqs_hierarchy(struct irq_domain *domain,
 				    unsigned int irq_base,
 				    unsigned int nr_irqs, void *arg)
 {
+	if (!domain->ops->alloc) {
+		pr_debug("domain->ops->alloc() is NULL\n");
+		return -ENOSYS;
+	}
+
 	return domain->ops->alloc(domain, irq_base, nr_irqs, arg);
 }
 
@@ -1328,11 +1333,6 @@ int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base,
 			return -EINVAL;
 	}
 
-	if (!domain->ops->alloc) {
-		pr_debug("domain->ops->alloc() is NULL\n");
-		return -ENOSYS;
-	}
-
 	if (realloc && irq_base >= 0) {
 		virq = irq_base;
 	} else {
@@ -1457,6 +1457,7 @@ int irq_domain_push_irq(struct irq_domain *domain, int virq, void *arg)
 	if (rv) {
 		/* Restore the original irq_data. */
 		*root_irq_data = *child_irq_data;
+		kfree(child_irq_data);
 		goto error;
 	}
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index e8f7f179bf77..e557a375cd02 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -194,9 +194,9 @@ void irq_set_thread_affinity(struct irq_desc *desc)
 			set_bit(IRQTF_AFFINITY, &action->thread_flags);
 }
 
+#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
 static void irq_validate_effective_affinity(struct irq_data *data)
 {
-#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
 	const struct cpumask *m = irq_data_get_effective_affinity_mask(data);
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
 
@@ -204,9 +204,19 @@ static void irq_validate_effective_affinity(struct irq_data *data)
 		return;
 	pr_warn_once("irq_chip %s did not update eff. affinity mask of irq %u\n",
 		     chip->name, data->irq);
-#endif
 }
 
+static inline void irq_init_effective_affinity(struct irq_data *data,
+					       const struct cpumask *mask)
+{
+	cpumask_copy(irq_data_get_effective_affinity_mask(data), mask);
+}
+#else
+static inline void irq_validate_effective_affinity(struct irq_data *data) { }
+static inline void irq_init_effective_affinity(struct irq_data *data,
+					       const struct cpumask *mask) { }
+#endif
+
 int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
 			bool force)
 {
@@ -265,6 +275,30 @@ static int irq_try_set_affinity(struct irq_data *data,
 	return ret;
 }
 
+static bool irq_set_affinity_deactivated(struct irq_data *data,
+					 const struct cpumask *mask, bool force)
+{
+	struct irq_desc *desc = irq_data_to_desc(data);
+
+	/*
+	 * Handle irq chips which can handle affinity only in activated
+	 * state correctly
+	 *
+	 * If the interrupt is not yet activated, just store the affinity
+	 * mask and do not call the chip driver at all. On activation the
+	 * driver has to make sure anyway that the interrupt is in a
+	 * useable state so startup works.
+	 */
+	if (!IS_ENABLED(CONFIG_IRQ_DOMAIN_HIERARCHY) ||
+	    irqd_is_activated(data) || !irqd_affinity_on_activate(data))
+		return false;
+
+	cpumask_copy(desc->irq_common_data.affinity, mask);
+	irq_init_effective_affinity(data, mask);
+	irqd_set(data, IRQD_AFFINITY_SET);
+	return true;
+}
+
 int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
 			    bool force)
 {
@@ -275,6 +309,9 @@ int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
 	if (!chip || !chip->irq_set_affinity)
 		return -EINVAL;
 
+	if (irq_set_affinity_deactivated(data, mask, force))
+		return 0;
+
 	if (irq_can_move_pcntxt(data) && !irqd_is_setaffinity_pending(data)) {
 		ret = irq_try_set_affinity(data, mask, force);
 	} else {
@@ -284,7 +321,11 @@ int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
 
 	if (desc->affinity_notify) {
 		kref_get(&desc->affinity_notify->kref);
-		schedule_work(&desc->affinity_notify->work);
+		if (!schedule_work(&desc->affinity_notify->work)) {
+			/* Work was already scheduled, drop our extra ref */
+			kref_put(&desc->affinity_notify->kref,
+				 desc->affinity_notify->release);
+		}
 	}
 	irqd_set(data, IRQD_AFFINITY_SET);
 
@@ -384,7 +425,10 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 
 	if (old_notify) {
-		cancel_work_sync(&old_notify->work);
+		if (cancel_work_sync(&old_notify->work)) {
+			/* Pending work had a ref, put that one too */
+			kref_put(&old_notify->kref, old_notify->release);
+		}
 		kref_put(&old_notify->kref, old_notify->release);
 	}
 
@@ -442,23 +486,9 @@ int irq_setup_affinity(struct irq_desc *desc)
 {
 	return irq_select_affinity(irq_desc_get_irq(desc));
 }
-#endif
-
-/*
- * Called when a bogus affinity is set via /proc/irq
- */
-int irq_select_affinity_usr(unsigned int irq)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-	unsigned long flags;
-	int ret;
+#endif /* CONFIG_AUTO_IRQ_AFFINITY */
+#endif /* CONFIG_SMP */
 
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	ret = irq_setup_affinity(desc);
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	return ret;
-}
-#endif
 
 /**
  *	irq_set_vcpu_affinity - Set vcpu affinity for the interrupt
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index ad26fbcfbfc8..eb95f6106a1e 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -453,8 +453,11 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 			continue;
 
 		irq_data = irq_domain_get_irq_data(domain, desc->irq);
-		if (!can_reserve)
+		if (!can_reserve) {
 			irqd_clr_can_reserve(irq_data);
+			if (domain->flags & IRQ_DOMAIN_MSI_NOMASK_QUIRK)
+				irqd_set_msi_nomask_quirk(irq_data);
+		}
 		ret = irq_domain_activate_irq(irq_data, can_reserve);
 		if (ret)
 			goto cleanup;
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index da9addb8d655..e8c655b7a430 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -115,6 +115,28 @@ static int irq_affinity_list_proc_show(struct seq_file *m, void *v)
 	return show_irq_affinity(AFFINITY_LIST, m);
 }
 
+#ifndef CONFIG_AUTO_IRQ_AFFINITY
+static inline int irq_select_affinity_usr(unsigned int irq)
+{
+	/*
+	 * If the interrupt is started up already then this fails. The
+	 * interrupt is assigned to an online CPU already. There is no
+	 * point to move it around randomly. Tell user space that the
+	 * selected mask is bogus.
+	 *
+	 * If not then any change to the affinity is pointless because the
+	 * startup code invokes irq_setup_affinity() which will select
+	 * a online CPU anyway.
+	 */
+	return -EINVAL;
+}
+#else
+/* ALPHA magic affinity auto selector. Keep it for historical reasons. */
+static inline int irq_select_affinity_usr(unsigned int irq)
+{
+	return irq_select_affinity(irq);
+}
+#endif
 
 static ssize_t write_irq_affinity(int type, struct file *file,
 		const char __user *buffer, size_t count, loff_t *pos)
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index 98c04ca5fa43..5064b13b80d6 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -72,8 +72,9 @@ void check_irq_resend(struct irq_desc *desc)
 		desc->istate &= ~IRQS_PENDING;
 		desc->istate |= IRQS_REPLAY;
 
-		if (!desc->irq_data.chip->irq_retrigger ||
-		    !desc->irq_data.chip->irq_retrigger(&desc->irq_data)) {
+		if ((!desc->irq_data.chip->irq_retrigger ||
+		    !desc->irq_data.chip->irq_retrigger(&desc->irq_data)) &&
+		    !handle_enforce_irqctx(&desc->irq_data)) {
 #ifdef CONFIG_HARDIRQS_SW_RESEND
 			unsigned int irq = irq_desc_get_irq(desc);
 
diff --git a/kernel/irq/timings.c b/kernel/irq/timings.c
index 90c735da15d0..19d2fad379ee 100644
--- a/kernel/irq/timings.c
+++ b/kernel/irq/timings.c
@@ -267,6 +267,23 @@ void irq_timings_disable(void)
 #define PREDICTION_MAX		10 /* 2 ^ PREDICTION_MAX useconds */
 #define PREDICTION_BUFFER_SIZE	16 /* slots for EMAs, hardly more than 16 */
 
+/*
+ * Number of elements in the circular buffer: If it happens it was
+ * flushed before, then the number of elements could be smaller than
+ * IRQ_TIMINGS_SIZE, so the count is used, otherwise the array size is
+ * used as we wrapped. The index begins from zero when we did not
+ * wrap. That could be done in a nicer way with the proper circular
+ * array structure type but with the cost of extra computation in the
+ * interrupt handler hot path. We choose efficiency.
+ */
+#define for_each_irqts(i, irqts)					\
+	for (i = irqts->count < IRQ_TIMINGS_SIZE ?			\
+		     0 : irqts->count & IRQ_TIMINGS_MASK,		\
+		     irqts->count = min(IRQ_TIMINGS_SIZE,		\
+					irqts->count);			\
+	     irqts->count > 0; irqts->count--,				\
+		     i = (i + 1) & IRQ_TIMINGS_MASK)
+
 struct irqt_stat {
 	u64	last_ts;
 	u64	ema_time[PREDICTION_BUFFER_SIZE];
@@ -297,7 +314,16 @@ static u64 irq_timings_ema_new(u64 value, u64 ema_old)
 
 static int irq_timings_next_event_index(int *buffer, size_t len, int period_max)
 {
-	int i;
+	int period;
+
+	/*
+	 * Move the beginning pointer to the end minus the max period x 3.
+	 * We are at the point we can begin searching the pattern
+	 */
+	buffer = &buffer[len - (period_max * 3)];
+
+	/* Adjust the length to the maximum allowed period x 3 */
+	len = period_max * 3;
 
 	/*
 	 * The buffer contains the suite of intervals, in a ilog2
@@ -306,21 +332,45 @@ static int irq_timings_next_event_index(int *buffer, size_t len, int period_max)
 	 * period beginning at the end of the buffer. We do that for
 	 * each suffix.
 	 */
-	for (i = period_max; i >= PREDICTION_PERIOD_MIN ; i--) {
+	for (period = period_max; period >= PREDICTION_PERIOD_MIN; period--) {
 
-		int *begin = &buffer[len - (i * 3)];
-		int *ptr = begin;
+		/*
+		 * The first comparison always succeed because the
+		 * suffix is deduced from the first n-period bytes of
+		 * the buffer and we compare the initial suffix with
+		 * itself, so we can skip the first iteration.
+		 */
+		int idx = period;
+		size_t size = period;
 
 		/*
 		 * We look if the suite with period 'i' repeat
 		 * itself. If it is truncated at the end, as it
 		 * repeats we can use the period to find out the next
-		 * element.
+		 * element with the modulo.
 		 */
-		while (!memcmp(ptr, begin, i * sizeof(*ptr))) {
-			ptr += i;
-			if (ptr >= &buffer[len])
-				return begin[((i * 3) % i)];
+		while (!memcmp(buffer, &buffer[idx], size * sizeof(int))) {
+
+			/*
+			 * Move the index in a period basis
+			 */
+			idx += size;
+
+			/*
+			 * If this condition is reached, all previous
+			 * memcmp were successful, so the period is
+			 * found.
+			 */
+			if (idx == len)
+				return buffer[len % period];
+
+			/*
+			 * If the remaining elements to compare are
+			 * smaller than the period, readjust the size
+			 * of the comparison for the last iteration.
+			 */
+			if (len - idx < period)
+				size = len - idx;
 		}
 	}
 
@@ -493,11 +543,7 @@ u64 irq_timings_next_event(u64 now)
 	 * model while decrementing the counter because we consume the
 	 * data from our circular buffer.
 	 */
-
-	i = (irqts->count & IRQ_TIMINGS_MASK) - 1;
-	irqts->count = min(IRQ_TIMINGS_SIZE, irqts->count);
-
-	for (; irqts->count > 0; irqts->count--, i = (i + 1) & IRQ_TIMINGS_MASK) {
+	for_each_irqts(i, irqts) {
 		irq = irq_timing_decode(irqts->values[i], &ts);
 		s = idr_find(&irqt_stats, irq);
 		if (s)
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 136ce049c4ad..61f9d781f70a 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -645,19 +645,20 @@ static inline int kallsyms_for_perf(void)
  * Otherwise, require CAP_SYSLOG (assuming kptr_restrict isn't set to
  * block even that).
  */
-int kallsyms_show_value(void)
+bool kallsyms_show_value(const struct cred *cred)
 {
 	switch (kptr_restrict) {
 	case 0:
 		if (kallsyms_for_perf())
-			return 1;
+			return true;
 	/* fallthrough */
 	case 1:
-		if (has_capability_noaudit(current, CAP_SYSLOG))
-			return 1;
+		if (security_capable(cred, &init_user_ns, CAP_SYSLOG,
+				     CAP_OPT_NOAUDIT) == 0)
+			return true;
 	/* fallthrough */
 	default:
-		return 0;
+		return false;
 	}
 }
 
@@ -674,7 +675,11 @@ static int kallsyms_open(struct inode *inode, struct file *file)
 		return -ENOMEM;
 	reset_iter(iter, 0);
 
-	iter->show_value = kallsyms_show_value();
+	/*
+	 * Instead of checking this on every s_show() call, cache
+	 * the result here at open time.
+	 */
+	iter->show_value = kallsyms_show_value(file->f_cred);
 	return 0;
 }
 
diff --git a/kernel/kmod.c b/kernel/kmod.c
index bc6addd9152b..a2de58de6ab6 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -120,7 +120,7 @@ out:
  * invoke it.
  *
  * If module auto-loading support is disabled then this function
- * becomes a no-operation.
+ * simply returns -ENOENT.
  */
 int __request_module(bool wait, const char *fmt, ...)
 {
@@ -137,7 +137,7 @@ int __request_module(bool wait, const char *fmt, ...)
 	WARN_ON_ONCE(wait && current_is_async());
 
 	if (!modprobe_path[0])
-		return 0;
+		return -ENOENT;
 
 	va_start(args, fmt);
 	ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 1010bde1146b..a0dfc7d425f0 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -326,7 +326,8 @@ struct kprobe *get_kprobe(void *addr)
 	struct kprobe *p;
 
 	head = &kprobe_table[hash_ptr(addr, KPROBE_HASH_BITS)];
-	hlist_for_each_entry_rcu(p, head, hlist) {
+	hlist_for_each_entry_rcu(p, head, hlist,
+				 lockdep_is_held(&kprobe_mutex)) {
 		if (p->addr == addr)
 			return p;
 	}
@@ -510,6 +511,8 @@ static void do_unoptimize_kprobes(void)
 	arch_unoptimize_kprobes(&unoptimizing_list, &freeing_list);
 	/* Loop free_list for disarming */
 	list_for_each_entry_safe(op, tmp, &freeing_list, list) {
+		/* Switching from detour code to origin */
+		op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
 		/* Disarm probes if marked disabled */
 		if (kprobe_disabled(&op->kp))
 			arch_disarm_kprobe(&op->kp);
@@ -584,11 +587,12 @@ static void kprobe_optimizer(struct work_struct *work)
 	mutex_unlock(&module_mutex);
 	mutex_unlock(&text_mutex);
 	cpus_read_unlock();
-	mutex_unlock(&kprobe_mutex);
 
 	/* Step 5: Kick optimizer again if needed */
 	if (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list))
 		kick_kprobe_optimizer();
+
+	mutex_unlock(&kprobe_mutex);
 }
 
 /* Wait for completing optimization and unoptimization */
@@ -610,6 +614,18 @@ void wait_for_kprobe_optimizer(void)
 	mutex_unlock(&kprobe_mutex);
 }
 
+static bool optprobe_queued_unopt(struct optimized_kprobe *op)
+{
+	struct optimized_kprobe *_op;
+
+	list_for_each_entry(_op, &unoptimizing_list, list) {
+		if (op == _op)
+			return true;
+	}
+
+	return false;
+}
+
 /* Optimize kprobe if p is ready to be optimized */
 static void optimize_kprobe(struct kprobe *p)
 {
@@ -631,17 +647,21 @@ static void optimize_kprobe(struct kprobe *p)
 		return;
 
 	/* Check if it is already optimized. */
-	if (op->kp.flags & KPROBE_FLAG_OPTIMIZED)
+	if (op->kp.flags & KPROBE_FLAG_OPTIMIZED) {
+		if (optprobe_queued_unopt(op)) {
+			/* This is under unoptimizing. Just dequeue the probe */
+			list_del_init(&op->list);
+		}
 		return;
+	}
 	op->kp.flags |= KPROBE_FLAG_OPTIMIZED;
 
-	if (!list_empty(&op->list))
-		/* This is under unoptimizing. Just dequeue the probe */
-		list_del_init(&op->list);
-	else {
-		list_add(&op->list, &optimizing_list);
-		kick_kprobe_optimizer();
-	}
+	/* On unoptimizing/optimizing_list, op must have OPTIMIZED flag */
+	if (WARN_ON_ONCE(!list_empty(&op->list)))
+		return;
+
+	list_add(&op->list, &optimizing_list);
+	kick_kprobe_optimizer();
 }
 
 /* Short cut to direct unoptimizing */
@@ -649,6 +669,7 @@ static void force_unoptimize_kprobe(struct optimized_kprobe *op)
 {
 	lockdep_assert_cpus_held();
 	arch_unoptimize_kprobe(op);
+	op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
 	if (kprobe_disabled(&op->kp))
 		arch_disarm_kprobe(&op->kp);
 }
@@ -662,31 +683,33 @@ static void unoptimize_kprobe(struct kprobe *p, bool force)
 		return; /* This is not an optprobe nor optimized */
 
 	op = container_of(p, struct optimized_kprobe, kp);
-	if (!kprobe_optimized(p)) {
-		/* Unoptimized or unoptimizing case */
-		if (force && !list_empty(&op->list)) {
-			/*
-			 * Only if this is unoptimizing kprobe and forced,
-			 * forcibly unoptimize it. (No need to unoptimize
-			 * unoptimized kprobe again :)
-			 */
-			list_del_init(&op->list);
-			force_unoptimize_kprobe(op);
-		}
+	if (!kprobe_optimized(p))
 		return;
-	}
 
-	op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
 	if (!list_empty(&op->list)) {
-		/* Dequeue from the optimization queue */
-		list_del_init(&op->list);
+		if (optprobe_queued_unopt(op)) {
+			/* Queued in unoptimizing queue */
+			if (force) {
+				/*
+				 * Forcibly unoptimize the kprobe here, and queue it
+				 * in the freeing list for release afterwards.
+				 */
+				force_unoptimize_kprobe(op);
+				list_move(&op->list, &freeing_list);
+			}
+		} else {
+			/* Dequeue from the optimizing queue */
+			list_del_init(&op->list);
+			op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
+		}
 		return;
 	}
+
 	/* Optimized kprobe case */
-	if (force)
+	if (force) {
 		/* Forcibly update the code: this is a special case */
 		force_unoptimize_kprobe(op);
-	else {
+	} else {
 		list_add(&op->list, &unoptimizing_list);
 		kick_kprobe_optimizer();
 	}
@@ -1029,9 +1052,20 @@ static int disarm_kprobe_ftrace(struct kprobe *p)
 	return ret;
 }
 #else	/* !CONFIG_KPROBES_ON_FTRACE */
-#define prepare_kprobe(p)	arch_prepare_kprobe(p)
-#define arm_kprobe_ftrace(p)	(-ENODEV)
-#define disarm_kprobe_ftrace(p)	(-ENODEV)
+static inline int prepare_kprobe(struct kprobe *p)
+{
+	return arch_prepare_kprobe(p);
+}
+
+static inline int arm_kprobe_ftrace(struct kprobe *p)
+{
+	return -ENODEV;
+}
+
+static inline int disarm_kprobe_ftrace(struct kprobe *p)
+{
+	return -ENODEV;
+}
 #endif
 
 /* Arm a kprobe with text_mutex */
@@ -1191,6 +1225,26 @@ __releases(hlist_lock)
 }
 NOKPROBE_SYMBOL(kretprobe_table_unlock);
 
+struct kprobe kprobe_busy = {
+	.addr = (void *) get_kprobe,
+};
+
+void kprobe_busy_begin(void)
+{
+	struct kprobe_ctlblk *kcb;
+
+	preempt_disable();
+	__this_cpu_write(current_kprobe, &kprobe_busy);
+	kcb = get_kprobe_ctlblk();
+	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+}
+
+void kprobe_busy_end(void)
+{
+	__this_cpu_write(current_kprobe, NULL);
+	preempt_enable();
+}
+
 /*
  * This function is called from finish_task_switch when task tk becomes dead,
  * so that we can recycle any function-return probe instances associated
@@ -1208,6 +1262,8 @@ void kprobe_flush_task(struct task_struct *tk)
 		/* Early boot.  kretprobe_table_locks not yet initialized. */
 		return;
 
+	kprobe_busy_begin();
+
 	INIT_HLIST_HEAD(&empty_rp);
 	hash = hash_ptr(tk, KPROBE_HASH_BITS);
 	head = &kretprobe_inst_table[hash];
@@ -1221,6 +1277,8 @@ void kprobe_flush_task(struct task_struct *tk)
 		hlist_del(&ri->hlist);
 		kfree(ri);
 	}
+
+	kprobe_busy_end();
 }
 NOKPROBE_SYMBOL(kprobe_flush_task);
 
@@ -2033,6 +2091,13 @@ static void kill_kprobe(struct kprobe *p)
 	 * the original probed function (which will be freed soon) any more.
 	 */
 	arch_remove_kprobe(p);
+
+	/*
+	 * The module is going away. We should disarm the kprobe which
+	 * is using ftrace.
+	 */
+	if (kprobe_ftrace(p))
+		disarm_kprobe_ftrace(p);
 }
 
 /* Disable one kprobe */
@@ -2290,7 +2355,7 @@ static void report_probe(struct seq_file *pi, struct kprobe *p,
 	else
 		kprobe_type = "k";
 
-	if (!kallsyms_show_value())
+	if (!kallsyms_show_value(pi->file->f_cred))
 		addr = NULL;
 
 	if (sym)
@@ -2391,7 +2456,7 @@ static int kprobe_blacklist_seq_show(struct seq_file *m, void *v)
 	 * If /proc/kallsyms is not showing kernel address, we won't
 	 * show them here either.
 	 */
-	if (!kallsyms_show_value())
+	if (!kallsyms_show_value(m->file->f_cred))
 		seq_printf(m, "0x%px-0x%px\t%ps\n", NULL, NULL,
 			   (void *)ent->start_addr);
 	else
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 4fc8dc30cec0..98bdba3161d7 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -421,13 +421,6 @@ static int verbose(struct lock_class *class)
 	return 0;
 }
 
-/*
- * Stack-trace: tightly packed array of stack backtrace
- * addresses. Protected by the graph_lock.
- */
-unsigned long nr_stack_trace_entries;
-static unsigned long stack_trace[MAX_STACK_TRACE_ENTRIES];
-
 static void print_lockdep_off(const char *bug_msg)
 {
 	printk(KERN_DEBUG "%s\n", bug_msg);
@@ -437,6 +430,15 @@ static void print_lockdep_off(const char *bug_msg)
 #endif
 }
 
+unsigned long nr_stack_trace_entries;
+
+#ifdef CONFIG_PROVE_LOCKING
+/*
+ * Stack-trace: tightly packed array of stack backtrace
+ * addresses. Protected by the graph_lock.
+ */
+static unsigned long stack_trace[MAX_STACK_TRACE_ENTRIES];
+
 static int save_trace(struct lock_trace *trace)
 {
 	unsigned long *entries = stack_trace + nr_stack_trace_entries;
@@ -459,6 +461,7 @@ static int save_trace(struct lock_trace *trace)
 
 	return 1;
 }
+#endif
 
 unsigned int nr_hardirq_chains;
 unsigned int nr_softirq_chains;
@@ -472,6 +475,7 @@ unsigned int max_lockdep_depth;
 DEFINE_PER_CPU(struct lockdep_stats, lockdep_stats);
 #endif
 
+#ifdef CONFIG_PROVE_LOCKING
 /*
  * Locking printouts:
  */
@@ -489,6 +493,7 @@ static const char *usage_str[] =
 #undef LOCKDEP_STATE
 	[LOCK_USED] = "INITIAL USE",
 };
+#endif
 
 const char * __get_key_name(struct lockdep_subclass_key *key, char *str)
 {
@@ -1606,9 +1611,11 @@ unsigned long lockdep_count_forward_deps(struct lock_class *class)
 	this.class = class;
 
 	raw_local_irq_save(flags);
+	current->lockdep_recursion = 1;
 	arch_spin_lock(&lockdep_lock);
 	ret = __lockdep_count_forward_deps(&this);
 	arch_spin_unlock(&lockdep_lock);
+	current->lockdep_recursion = 0;
 	raw_local_irq_restore(flags);
 
 	return ret;
@@ -1633,9 +1640,11 @@ unsigned long lockdep_count_backward_deps(struct lock_class *class)
 	this.class = class;
 
 	raw_local_irq_save(flags);
+	current->lockdep_recursion = 1;
 	arch_spin_lock(&lockdep_lock);
 	ret = __lockdep_count_backward_deps(&this);
 	arch_spin_unlock(&lockdep_lock);
+	current->lockdep_recursion = 0;
 	raw_local_irq_restore(flags);
 
 	return ret;
@@ -2819,10 +2828,6 @@ static inline int validate_chain(struct task_struct *curr,
 {
 	return 1;
 }
-
-static void print_lock_trace(struct lock_trace *trace, unsigned int spaces)
-{
-}
 #endif
 
 /*
@@ -2876,12 +2881,10 @@ static void check_chain_key(struct task_struct *curr)
 #endif
 }
 
+#ifdef CONFIG_PROVE_LOCKING
 static int mark_lock(struct task_struct *curr, struct held_lock *this,
 		     enum lock_usage_bit new_bit);
 
-#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
-
-
 static void
 print_usage_bug_scenario(struct held_lock *lock)
 {
@@ -3369,8 +3372,12 @@ void trace_softirqs_off(unsigned long ip)
 		debug_atomic_inc(redundant_softirqs_off);
 }
 
-static int mark_irqflags(struct task_struct *curr, struct held_lock *hlock)
+static int
+mark_usage(struct task_struct *curr, struct held_lock *hlock, int check)
 {
+	if (!check)
+		goto lock_used;
+
 	/*
 	 * If non-trylock use in a hardirq or softirq context, then
 	 * mark the lock as used in these contexts:
@@ -3414,6 +3421,11 @@ static int mark_irqflags(struct task_struct *curr, struct held_lock *hlock)
 		}
 	}
 
+lock_used:
+	/* mark it as used: */
+	if (!mark_lock(curr, hlock, LOCK_USED))
+		return 0;
+
 	return 1;
 }
 
@@ -3445,35 +3457,6 @@ static int separate_irq_context(struct task_struct *curr,
 	return 0;
 }
 
-#else /* defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) */
-
-static inline
-int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
-		enum lock_usage_bit new_bit)
-{
-	WARN_ON(1); /* Impossible innit? when we don't have TRACE_IRQFLAG */
-	return 1;
-}
-
-static inline int mark_irqflags(struct task_struct *curr,
-		struct held_lock *hlock)
-{
-	return 1;
-}
-
-static inline unsigned int task_irq_context(struct task_struct *task)
-{
-	return 0;
-}
-
-static inline int separate_irq_context(struct task_struct *curr,
-		struct held_lock *hlock)
-{
-	return 0;
-}
-
-#endif /* defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) */
-
 /*
  * Mark a lock with a usage bit, and validate the state transition:
  */
@@ -3541,6 +3524,27 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 	return ret;
 }
 
+#else /* CONFIG_PROVE_LOCKING */
+
+static inline int
+mark_usage(struct task_struct *curr, struct held_lock *hlock, int check)
+{
+	return 1;
+}
+
+static inline unsigned int task_irq_context(struct task_struct *task)
+{
+	return 0;
+}
+
+static inline int separate_irq_context(struct task_struct *curr,
+		struct held_lock *hlock)
+{
+	return 0;
+}
+
+#endif /* CONFIG_PROVE_LOCKING */
+
 /*
  * Initialize a lock instance's lock-class mapping info:
  */
@@ -3744,11 +3748,8 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 #endif
 	hlock->pin_count = pin_count;
 
-	if (check && !mark_irqflags(curr, hlock))
-		return 0;
-
-	/* mark it as used: */
-	if (!mark_lock(curr, hlock, LOCK_USED))
+	/* Initialize the lock usage bit */
+	if (!mark_usage(curr, hlock, check))
 		return 0;
 
 	/*
@@ -4230,8 +4231,7 @@ static void __lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie cookie
  */
 static void check_flags(unsigned long flags)
 {
-#if defined(CONFIG_PROVE_LOCKING) && defined(CONFIG_DEBUG_LOCKDEP) && \
-    defined(CONFIG_TRACE_IRQFLAGS)
+#if defined(CONFIG_PROVE_LOCKING) && defined(CONFIG_DEBUG_LOCKDEP)
 	if (!debug_locks)
 		return;
 
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 80a463d31a8d..a9768d89e521 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -697,10 +697,10 @@ static void __torture_print_stats(char *page,
 		if (statp[i].n_lock_fail)
 			fail = true;
 		sum += statp[i].n_lock_acquired;
-		if (max < statp[i].n_lock_fail)
-			max = statp[i].n_lock_fail;
-		if (min > statp[i].n_lock_fail)
-			min = statp[i].n_lock_fail;
+		if (max < statp[i].n_lock_acquired)
+			max = statp[i].n_lock_acquired;
+		if (min > statp[i].n_lock_acquired)
+			min = statp[i].n_lock_acquired;
 	}
 	page += sprintf(page,
 			"%s:  Total: %lld  Max/Min: %ld/%ld %s  Fail: %d %s\n",
diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c
index 399669f7eba8..472dd462a40c 100644
--- a/kernel/locking/spinlock_debug.c
+++ b/kernel/locking/spinlock_debug.c
@@ -51,19 +51,19 @@ EXPORT_SYMBOL(__rwlock_init);
 
 static void spin_dump(raw_spinlock_t *lock, const char *msg)
 {
-	struct task_struct *owner = NULL;
+	struct task_struct *owner = READ_ONCE(lock->owner);
 
-	if (lock->owner && lock->owner != SPINLOCK_OWNER_INIT)
-		owner = lock->owner;
+	if (owner == SPINLOCK_OWNER_INIT)
+		owner = NULL;
 	printk(KERN_EMERG "BUG: spinlock %s on CPU#%d, %s/%d\n",
 		msg, raw_smp_processor_id(),
 		current->comm, task_pid_nr(current));
 	printk(KERN_EMERG " lock: %pS, .magic: %08x, .owner: %s/%d, "
 			".owner_cpu: %d\n",
-		lock, lock->magic,
+		lock, READ_ONCE(lock->magic),
 		owner ? owner->comm : "<none>",
 		owner ? task_pid_nr(owner) : -1,
-		lock->owner_cpu);
+		READ_ONCE(lock->owner_cpu));
 	dump_stack();
 }
 
@@ -80,16 +80,16 @@ static void spin_bug(raw_spinlock_t *lock, const char *msg)
 static inline void
 debug_spin_lock_before(raw_spinlock_t *lock)
 {
-	SPIN_BUG_ON(lock->magic != SPINLOCK_MAGIC, lock, "bad magic");
-	SPIN_BUG_ON(lock->owner == current, lock, "recursion");
-	SPIN_BUG_ON(lock->owner_cpu == raw_smp_processor_id(),
+	SPIN_BUG_ON(READ_ONCE(lock->magic) != SPINLOCK_MAGIC, lock, "bad magic");
+	SPIN_BUG_ON(READ_ONCE(lock->owner) == current, lock, "recursion");
+	SPIN_BUG_ON(READ_ONCE(lock->owner_cpu) == raw_smp_processor_id(),
 							lock, "cpu recursion");
 }
 
 static inline void debug_spin_lock_after(raw_spinlock_t *lock)
 {
-	lock->owner_cpu = raw_smp_processor_id();
-	lock->owner = current;
+	WRITE_ONCE(lock->owner_cpu, raw_smp_processor_id());
+	WRITE_ONCE(lock->owner, current);
 }
 
 static inline void debug_spin_unlock(raw_spinlock_t *lock)
@@ -99,8 +99,8 @@ static inline void debug_spin_unlock(raw_spinlock_t *lock)
 	SPIN_BUG_ON(lock->owner != current, lock, "wrong owner");
 	SPIN_BUG_ON(lock->owner_cpu != raw_smp_processor_id(),
 							lock, "wrong CPU");
-	lock->owner = SPINLOCK_OWNER_INIT;
-	lock->owner_cpu = -1;
+	WRITE_ONCE(lock->owner, SPINLOCK_OWNER_INIT);
+	WRITE_ONCE(lock->owner_cpu, -1);
 }
 
 /*
@@ -187,8 +187,8 @@ static inline void debug_write_lock_before(rwlock_t *lock)
 
 static inline void debug_write_lock_after(rwlock_t *lock)
 {
-	lock->owner_cpu = raw_smp_processor_id();
-	lock->owner = current;
+	WRITE_ONCE(lock->owner_cpu, raw_smp_processor_id());
+	WRITE_ONCE(lock->owner, current);
 }
 
 static inline void debug_write_unlock(rwlock_t *lock)
@@ -197,8 +197,8 @@ static inline void debug_write_unlock(rwlock_t *lock)
 	RWLOCK_BUG_ON(lock->owner != current, lock, "wrong owner");
 	RWLOCK_BUG_ON(lock->owner_cpu != raw_smp_processor_id(),
 							lock, "wrong CPU");
-	lock->owner = SPINLOCK_OWNER_INIT;
-	lock->owner_cpu = -1;
+	WRITE_ONCE(lock->owner, SPINLOCK_OWNER_INIT);
+	WRITE_ONCE(lock->owner_cpu, -1);
 }
 
 void do_raw_write_lock(rwlock_t *lock)
diff --git a/kernel/module.c b/kernel/module.c
index dcf2cc656e7c..9f35e1927807 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -208,7 +208,8 @@ static struct module *mod_find(unsigned long addr)
 {
 	struct module *mod;
 
-	list_for_each_entry_rcu(mod, &modules, list) {
+	list_for_each_entry_rcu(mod, &modules, list,
+				lockdep_is_held(&module_mutex)) {
 		if (within_module(addr, mod))
 			return mod;
 	}
@@ -442,7 +443,8 @@ bool each_symbol_section(bool (*fn)(const struct symsearch *arr,
 	if (each_symbol_in_section(arr, ARRAY_SIZE(arr), NULL, fn, data))
 		return true;
 
-	list_for_each_entry_rcu(mod, &modules, list) {
+	list_for_each_entry_rcu(mod, &modules, list,
+				lockdep_is_held(&module_mutex)) {
 		struct symsearch arr[] = {
 			{ mod->syms, mod->syms + mod->num_syms, mod->crcs,
 			  NOT_GPL_ONLY, false },
@@ -602,7 +604,8 @@ static struct module *find_module_all(const char *name, size_t len,
 
 	module_assert_mutex_or_preempt();
 
-	list_for_each_entry_rcu(mod, &modules, list) {
+	list_for_each_entry_rcu(mod, &modules, list,
+				lockdep_is_held(&module_mutex)) {
 		if (!even_unformed && mod->state == MODULE_STATE_UNFORMED)
 			continue;
 		if (strlen(mod->name) == len && !memcmp(mod->name, name, len))
@@ -1019,6 +1022,8 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
 	strlcpy(last_unloaded_module, mod->name, sizeof(last_unloaded_module));
 
 	free_module(mod);
+	/* someone could wait for the module in add_unformed_module() */
+	wake_up_all(&module_wq);
 	return 0;
 out:
 	mutex_unlock(&module_mutex);
@@ -1447,8 +1452,7 @@ static inline bool sect_empty(const Elf_Shdr *sect)
 }
 
 struct module_sect_attr {
-	struct module_attribute mattr;
-	char *name;
+	struct bin_attribute battr;
 	unsigned long address;
 };
 
@@ -1458,13 +1462,34 @@ struct module_sect_attrs {
 	struct module_sect_attr attrs[0];
 };
 
-static ssize_t module_sect_show(struct module_attribute *mattr,
-				struct module_kobject *mk, char *buf)
+#define MODULE_SECT_READ_SIZE (3 /* "0x", "\n" */ + (BITS_PER_LONG / 4))
+static ssize_t module_sect_read(struct file *file, struct kobject *kobj,
+				struct bin_attribute *battr,
+				char *buf, loff_t pos, size_t count)
 {
 	struct module_sect_attr *sattr =
-		container_of(mattr, struct module_sect_attr, mattr);
-	return sprintf(buf, "0x%px\n", kptr_restrict < 2 ?
-		       (void *)sattr->address : NULL);
+		container_of(battr, struct module_sect_attr, battr);
+	char bounce[MODULE_SECT_READ_SIZE + 1];
+	size_t wrote;
+
+	if (pos != 0)
+		return -EINVAL;
+
+	/*
+	 * Since we're a binary read handler, we must account for the
+	 * trailing NUL byte that sprintf will write: if "buf" is
+	 * too small to hold the NUL, or the NUL is exactly the last
+	 * byte, the read will look like it got truncated by one byte.
+	 * Since there is no way to ask sprintf nicely to not write
+	 * the NUL, we have to use a bounce buffer.
+	 */
+	wrote = scnprintf(bounce, sizeof(bounce), "0x%px\n",
+			 kallsyms_show_value(file->f_cred)
+				? (void *)sattr->address : NULL);
+	count = min(count, wrote);
+	memcpy(buf, bounce, count);
+
+	return count;
 }
 
 static void free_sect_attrs(struct module_sect_attrs *sect_attrs)
@@ -1472,7 +1497,7 @@ static void free_sect_attrs(struct module_sect_attrs *sect_attrs)
 	unsigned int section;
 
 	for (section = 0; section < sect_attrs->nsections; section++)
-		kfree(sect_attrs->attrs[section].name);
+		kfree(sect_attrs->attrs[section].battr.attr.name);
 	kfree(sect_attrs);
 }
 
@@ -1481,7 +1506,7 @@ static void add_sect_attrs(struct module *mod, const struct load_info *info)
 	unsigned int nloaded = 0, i, size[2];
 	struct module_sect_attrs *sect_attrs;
 	struct module_sect_attr *sattr;
-	struct attribute **gattr;
+	struct bin_attribute **gattr;
 
 	/* Count loaded sections and allocate structures */
 	for (i = 0; i < info->hdr->e_shnum; i++)
@@ -1489,35 +1514,34 @@ static void add_sect_attrs(struct module *mod, const struct load_info *info)
 			nloaded++;
 	size[0] = ALIGN(sizeof(*sect_attrs)
 			+ nloaded * sizeof(sect_attrs->attrs[0]),
-			sizeof(sect_attrs->grp.attrs[0]));
-	size[1] = (nloaded + 1) * sizeof(sect_attrs->grp.attrs[0]);
+			sizeof(sect_attrs->grp.bin_attrs[0]));
+	size[1] = (nloaded + 1) * sizeof(sect_attrs->grp.bin_attrs[0]);
 	sect_attrs = kzalloc(size[0] + size[1], GFP_KERNEL);
 	if (sect_attrs == NULL)
 		return;
 
 	/* Setup section attributes. */
 	sect_attrs->grp.name = "sections";
-	sect_attrs->grp.attrs = (void *)sect_attrs + size[0];
+	sect_attrs->grp.bin_attrs = (void *)sect_attrs + size[0];
 
 	sect_attrs->nsections = 0;
 	sattr = &sect_attrs->attrs[0];
-	gattr = &sect_attrs->grp.attrs[0];
+	gattr = &sect_attrs->grp.bin_attrs[0];
 	for (i = 0; i < info->hdr->e_shnum; i++) {
 		Elf_Shdr *sec = &info->sechdrs[i];
 		if (sect_empty(sec))
 			continue;
+		sysfs_bin_attr_init(&sattr->battr);
 		sattr->address = sec->sh_addr;
-		sattr->name = kstrdup(info->secstrings + sec->sh_name,
-					GFP_KERNEL);
-		if (sattr->name == NULL)
+		sattr->battr.attr.name =
+			kstrdup(info->secstrings + sec->sh_name, GFP_KERNEL);
+		if (sattr->battr.attr.name == NULL)
 			goto out;
 		sect_attrs->nsections++;
-		sysfs_attr_init(&sattr->mattr.attr);
-		sattr->mattr.show = module_sect_show;
-		sattr->mattr.store = NULL;
-		sattr->mattr.attr.name = sattr->name;
-		sattr->mattr.attr.mode = S_IRUSR;
-		*(gattr++) = &(sattr++)->mattr.attr;
+		sattr->battr.read = module_sect_read;
+		sattr->battr.size = MODULE_SECT_READ_SIZE;
+		sattr->battr.attr.mode = 0400;
+		*(gattr++) = &(sattr++)->battr;
 	}
 	*gattr = NULL;
 
@@ -1607,7 +1631,7 @@ static void add_notes_attrs(struct module *mod, const struct load_info *info)
 			continue;
 		if (info->sechdrs[i].sh_type == SHT_NOTE) {
 			sysfs_bin_attr_init(nattr);
-			nattr->attr.name = mod->sect_attrs->attrs[loaded].name;
+			nattr->attr.name = mod->sect_attrs->attrs[loaded].battr.attr.name;
 			nattr->attr.mode = S_IRUGO;
 			nattr->size = info->sechdrs[i].sh_size;
 			nattr->private = (void *) info->sechdrs[i].sh_addr;
@@ -1725,6 +1749,8 @@ static int module_add_modinfo_attrs(struct module *mod)
 error_out:
 	if (i > 0)
 		module_remove_modinfo_attrs(mod, --i);
+	else
+		kfree(mod->modinfo_attrs);
 	return error;
 }
 
@@ -2957,9 +2983,7 @@ static int setup_load_info(struct load_info *info, int flags)
 
 	/* Try to find a name early so we can log errors with a module name */
 	info->index.info = find_sec(info, ".modinfo");
-	if (!info->index.info)
-		info->name = "(missing .modinfo section)";
-	else
+	if (info->index.info)
 		info->name = get_modinfo(info, "name");
 
 	/* Find internal symbols and strings. */
@@ -2974,14 +2998,15 @@ static int setup_load_info(struct load_info *info, int flags)
 	}
 
 	if (info->index.sym == 0) {
-		pr_warn("%s: module has no symbols (stripped?)\n", info->name);
+		pr_warn("%s: module has no symbols (stripped?)\n",
+			info->name ?: "(missing .modinfo section or name field)");
 		return -ENOEXEC;
 	}
 
 	info->index.mod = find_sec(info, ".gnu.linkonce.this_module");
 	if (!info->index.mod) {
 		pr_warn("%s: No module found in object\n",
-			info->name ?: "(missing .modinfo name field)");
+			info->name ?: "(missing .modinfo section or name field)");
 		return -ENOEXEC;
 	}
 	/* This is temporary: point mod into copy of data. */
@@ -4285,7 +4310,7 @@ static int modules_open(struct inode *inode, struct file *file)
 
 	if (!err) {
 		struct seq_file *m = file->private_data;
-		m->private = kallsyms_show_value() ? NULL : (void *)8ul;
+		m->private = kallsyms_show_value(file->f_cred) ? NULL : (void *)8ul;
 	}
 
 	return err;
diff --git a/kernel/notifier.c b/kernel/notifier.c
index d9f5081d578d..157d7c29f720 100644
--- a/kernel/notifier.c
+++ b/kernel/notifier.c
@@ -554,7 +554,7 @@ NOKPROBE_SYMBOL(notify_die);
 
 int register_die_notifier(struct notifier_block *nb)
 {
-	vmalloc_sync_all();
+	vmalloc_sync_mappings();
 	return atomic_notifier_chain_register(&die_chain, nb);
 }
 EXPORT_SYMBOL_GPL(register_die_notifier);
diff --git a/kernel/padata.c b/kernel/padata.c
index 15a8ad63f4ff..4f39a5e7a853 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -35,6 +35,8 @@
 
 #define MAX_OBJ_NUM 1000
 
+static void padata_free_pd(struct parallel_data *pd);
+
 static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index)
 {
 	int cpu, target_cpu;
@@ -334,6 +336,7 @@ static void padata_serial_worker(struct work_struct *serial_work)
 	struct padata_serial_queue *squeue;
 	struct parallel_data *pd;
 	LIST_HEAD(local_list);
+	int cnt;
 
 	local_bh_disable();
 	squeue = container_of(serial_work, struct padata_serial_queue, work);
@@ -343,6 +346,8 @@ static void padata_serial_worker(struct work_struct *serial_work)
 	list_replace_init(&squeue->serial.list, &local_list);
 	spin_unlock(&squeue->serial.lock);
 
+	cnt = 0;
+
 	while (!list_empty(&local_list)) {
 		struct padata_priv *padata;
 
@@ -352,9 +357,12 @@ static void padata_serial_worker(struct work_struct *serial_work)
 		list_del_init(&padata->list);
 
 		padata->serial(padata);
-		atomic_dec(&pd->refcnt);
+		cnt++;
 	}
 	local_bh_enable();
+
+	if (atomic_sub_and_test(cnt, &pd->refcnt))
+		padata_free_pd(pd);
 }
 
 /**
@@ -501,7 +509,7 @@ static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst,
 	timer_setup(&pd->timer, padata_reorder_timer, 0);
 	atomic_set(&pd->seq_nr, -1);
 	atomic_set(&pd->reorder_objects, 0);
-	atomic_set(&pd->refcnt, 0);
+	atomic_set(&pd->refcnt, 1);
 	pd->pinst = pinst;
 	spin_lock_init(&pd->lock);
 
@@ -526,31 +534,6 @@ static void padata_free_pd(struct parallel_data *pd)
 	kfree(pd);
 }
 
-/* Flush all objects out of the padata queues. */
-static void padata_flush_queues(struct parallel_data *pd)
-{
-	int cpu;
-	struct padata_parallel_queue *pqueue;
-	struct padata_serial_queue *squeue;
-
-	for_each_cpu(cpu, pd->cpumask.pcpu) {
-		pqueue = per_cpu_ptr(pd->pqueue, cpu);
-		flush_work(&pqueue->work);
-	}
-
-	del_timer_sync(&pd->timer);
-
-	if (atomic_read(&pd->reorder_objects))
-		padata_reorder(pd);
-
-	for_each_cpu(cpu, pd->cpumask.cbcpu) {
-		squeue = per_cpu_ptr(pd->squeue, cpu);
-		flush_work(&squeue->work);
-	}
-
-	BUG_ON(atomic_read(&pd->refcnt) != 0);
-}
-
 static void __padata_start(struct padata_instance *pinst)
 {
 	pinst->flags |= PADATA_INIT;
@@ -564,10 +547,6 @@ static void __padata_stop(struct padata_instance *pinst)
 	pinst->flags &= ~PADATA_INIT;
 
 	synchronize_rcu();
-
-	get_online_cpus();
-	padata_flush_queues(pinst->pd);
-	put_online_cpus();
 }
 
 /* Replace the internal control structure with a new one. */
@@ -588,8 +567,8 @@ static void padata_replace(struct padata_instance *pinst,
 	if (!cpumask_equal(pd_old->cpumask.cbcpu, pd_new->cpumask.cbcpu))
 		notification_mask |= PADATA_CPU_SERIAL;
 
-	padata_flush_queues(pd_old);
-	padata_free_pd(pd_old);
+	if (atomic_dec_and_test(&pd_old->refcnt))
+		padata_free_pd(pd_old);
 
 	if (notification_mask)
 		blocking_notifier_call_chain(&pinst->cpumask_change_notifier,
@@ -692,8 +671,8 @@ int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type,
 	struct cpumask *serial_mask, *parallel_mask;
 	int err = -EINVAL;
 
-	mutex_lock(&pinst->lock);
 	get_online_cpus();
+	mutex_lock(&pinst->lock);
 
 	switch (cpumask_type) {
 	case PADATA_CPU_PARALLEL:
@@ -711,8 +690,8 @@ int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type,
 	err =  __padata_set_cpumasks(pinst, parallel_mask, serial_mask);
 
 out:
-	put_online_cpus();
 	mutex_unlock(&pinst->lock);
+	put_online_cpus();
 
 	return err;
 }
diff --git a/kernel/panic.c b/kernel/panic.c
index 3406a7a31449..d5be4272ab18 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -592,37 +592,25 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 	add_taint(taint, LOCKDEP_STILL_OK);
 }
 
-#ifdef WANT_WARN_ON_SLOWPATH
-void warn_slowpath_fmt(const char *file, int line, const char *fmt, ...)
+#ifndef __WARN_FLAGS
+void warn_slowpath_fmt(const char *file, int line, unsigned taint,
+		       const char *fmt, ...)
 {
 	struct warn_args args;
 
-	args.fmt = fmt;
-	va_start(args.args, fmt);
-	__warn(file, line, __builtin_return_address(0), TAINT_WARN, NULL,
-	       &args);
-	va_end(args.args);
-}
-EXPORT_SYMBOL(warn_slowpath_fmt);
-
-void warn_slowpath_fmt_taint(const char *file, int line,
-			     unsigned taint, const char *fmt, ...)
-{
-	struct warn_args args;
+	if (!fmt) {
+		pr_warn(CUT_HERE);
+		__warn(file, line, __builtin_return_address(0), taint,
+		       NULL, NULL);
+		return;
+	}
 
 	args.fmt = fmt;
 	va_start(args.args, fmt);
 	__warn(file, line, __builtin_return_address(0), taint, NULL, &args);
 	va_end(args.args);
 }
-EXPORT_SYMBOL(warn_slowpath_fmt_taint);
-
-void warn_slowpath_null(const char *file, int line)
-{
-	pr_warn(CUT_HERE);
-	__warn(file, line, __builtin_return_address(0), TAINT_WARN, NULL, NULL);
-}
-EXPORT_SYMBOL(warn_slowpath_null);
+EXPORT_SYMBOL(warn_slowpath_fmt);
 #else
 void __warn_printk(const char *fmt, ...)
 {
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index cd7434e6000d..9a67082bcbd8 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -897,6 +897,13 @@ static int software_resume(void)
 	error = freeze_processes();
 	if (error)
 		goto Close_Finish;
+
+	error = freeze_kernel_threads();
+	if (error) {
+		thaw_processes();
+		goto Close_Finish;
+	}
+
 	error = load_image_and_restore();
 	thaw_processes();
  Finish:
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 83105874f255..26b9168321e7 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -734,8 +734,15 @@ zone_found:
 	 * We have found the zone. Now walk the radix tree to find the leaf node
 	 * for our PFN.
 	 */
+
+	/*
+	 * If the zone we wish to scan is the the current zone and the
+	 * pfn falls into the current node then we do not need to walk
+	 * the tree.
+	 */
 	node = bm->cur.node;
-	if (((pfn - zone->start_pfn) & ~BM_BLOCK_MASK) == bm->cur.node_pfn)
+	if (zone == bm->cur.zone &&
+	    ((pfn - zone->start_pfn) & ~BM_BLOCK_MASK) == bm->cur.node_pfn)
 		goto node_found;
 
 	node      = zone->rtree;
diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h
index c8e6ab689d42..b2b0f526f249 100644
--- a/kernel/printk/internal.h
+++ b/kernel/printk/internal.h
@@ -23,6 +23,9 @@ __printf(1, 0) int vprintk_func(const char *fmt, va_list args);
 void __printk_safe_enter(void);
 void __printk_safe_exit(void);
 
+void printk_safe_init(void);
+bool printk_percpu_data_ready(void);
+
 #define printk_safe_enter_irqsave(flags)	\
 	do {					\
 		local_irq_save(flags);		\
@@ -64,4 +67,6 @@ __printf(1, 0) int vprintk_func(const char *fmt, va_list args) { return 0; }
 #define printk_safe_enter_irq() local_irq_disable()
 #define printk_safe_exit_irq() local_irq_enable()
 
+static inline void printk_safe_init(void) { }
+static inline bool printk_percpu_data_ready(void) { return false; }
 #endif /* CONFIG_PRINTK */
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 424abf802f02..89c6936dee11 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -450,6 +450,18 @@ static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN);
 static char *log_buf = __log_buf;
 static u32 log_buf_len = __LOG_BUF_LEN;
 
+/*
+ * We cannot access per-CPU data (e.g. per-CPU flush irq_work) before
+ * per_cpu_areas are initialised. This variable is set to true when
+ * it's safe to access per-CPU data.
+ */
+static bool __printk_percpu_data_ready __read_mostly;
+
+bool printk_percpu_data_ready(void)
+{
+	return __printk_percpu_data_ready;
+}
+
 /* Return log buffer address */
 char *log_buf_addr_get(void)
 {
@@ -1136,12 +1148,28 @@ static void __init log_buf_add_cpu(void)
 static inline void log_buf_add_cpu(void) {}
 #endif /* CONFIG_SMP */
 
+static void __init set_percpu_data_ready(void)
+{
+	printk_safe_init();
+	/* Make sure we set this flag only after printk_safe() init is done */
+	barrier();
+	__printk_percpu_data_ready = true;
+}
+
 void __init setup_log_buf(int early)
 {
 	unsigned long flags;
 	char *new_log_buf;
 	unsigned int free;
 
+	/*
+	 * Some archs call setup_log_buf() multiple times - first is very
+	 * early, e.g. from setup_arch(), and second - when percpu_areas
+	 * are initialised.
+	 */
+	if (!early)
+		set_percpu_data_ready();
+
 	if (log_buf != __log_buf)
 		return;
 
@@ -2760,8 +2788,6 @@ void register_console(struct console *newcon)
 		 * for us.
 		 */
 		logbuf_lock_irqsave(flags);
-		console_seq = syslog_seq;
-		console_idx = syslog_idx;
 		/*
 		 * We're about to replay the log buffer.  Only do this to the
 		 * just-registered console to avoid excessive message spam to
@@ -2773,6 +2799,8 @@ void register_console(struct console *newcon)
 		 */
 		exclusive_console = newcon;
 		exclusive_console_stop_seq = console_seq;
+		console_seq = syslog_seq;
+		console_idx = syslog_idx;
 		logbuf_unlock_irqrestore(flags);
 	}
 	console_unlock();
@@ -2956,6 +2984,9 @@ static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = {
 
 void wake_up_klogd(void)
 {
+	if (!printk_percpu_data_ready())
+		return;
+
 	preempt_disable();
 	if (waitqueue_active(&log_wait)) {
 		this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP);
@@ -2966,6 +2997,9 @@ void wake_up_klogd(void)
 
 void defer_console_output(void)
 {
+	if (!printk_percpu_data_ready())
+		return;
+
 	preempt_disable();
 	__this_cpu_or(printk_pending, PRINTK_PENDING_OUTPUT);
 	irq_work_queue(this_cpu_ptr(&wake_up_klogd_work));
diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c
index b4045e782743..d9a659a686f3 100644
--- a/kernel/printk/printk_safe.c
+++ b/kernel/printk/printk_safe.c
@@ -27,7 +27,6 @@
  * There are situations when we want to make sure that all buffers
  * were handled or when IRQs are blocked.
  */
-static int printk_safe_irq_ready __read_mostly;
 
 #define SAFE_LOG_BUF_LEN ((1 << CONFIG_PRINTK_SAFE_LOG_BUF_SHIFT) -	\
 				sizeof(atomic_t) -			\
@@ -51,7 +50,7 @@ static DEFINE_PER_CPU(struct printk_safe_seq_buf, nmi_print_seq);
 /* Get flushed in a more safe context. */
 static void queue_flush_work(struct printk_safe_seq_buf *s)
 {
-	if (printk_safe_irq_ready)
+	if (printk_percpu_data_ready())
 		irq_work_queue(&s->work);
 }
 
@@ -402,14 +401,6 @@ void __init printk_safe_init(void)
 #endif
 	}
 
-	/*
-	 * In the highly unlikely event that a NMI were to trigger at
-	 * this moment. Make sure IRQ work is set up before this
-	 * variable is set.
-	 */
-	barrier();
-	printk_safe_irq_ready = 1;
-
 	/* Flush pending messages that did not have scheduled IRQ works. */
 	printk_safe_flush();
 }
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 705887f63288..f7db0123a06b 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -259,12 +259,17 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state)
 	return ret;
 }
 
-static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode)
+static bool ptrace_has_cap(const struct cred *cred, struct user_namespace *ns,
+			   unsigned int mode)
 {
+	int ret;
+
 	if (mode & PTRACE_MODE_NOAUDIT)
-		return has_ns_capability_noaudit(current, ns, CAP_SYS_PTRACE);
+		ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NOAUDIT);
 	else
-		return has_ns_capability(current, ns, CAP_SYS_PTRACE);
+		ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NONE);
+
+	return ret == 0;
 }
 
 /* Returns 0 on success, -errno on denial. */
@@ -316,7 +321,7 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
 	    gid_eq(caller_gid, tcred->sgid) &&
 	    gid_eq(caller_gid, tcred->gid))
 		goto ok;
-	if (ptrace_has_cap(tcred->user_ns, mode))
+	if (ptrace_has_cap(cred, tcred->user_ns, mode))
 		goto ok;
 	rcu_read_unlock();
 	return -EPERM;
@@ -335,7 +340,7 @@ ok:
 	mm = task->mm;
 	if (mm &&
 	    ((get_dumpable(mm) != SUID_DUMP_USER) &&
-	     !ptrace_has_cap(mm->user_ns, mode)))
+	     !ptrace_has_cap(cred, mm->user_ns, mode)))
 	    return -EPERM;
 
 	return security_ptrace_access_check(task, mode);
diff --git a/kernel/rcu/Kconfig.debug b/kernel/rcu/Kconfig.debug
index 5ec3ea4028e2..4aa02eee8f6c 100644
--- a/kernel/rcu/Kconfig.debug
+++ b/kernel/rcu/Kconfig.debug
@@ -8,6 +8,17 @@ menu "RCU Debugging"
 config PROVE_RCU
 	def_bool PROVE_LOCKING
 
+config PROVE_RCU_LIST
+	bool "RCU list lockdep debugging"
+	depends on PROVE_RCU && RCU_EXPERT
+	default n
+	help
+	  Enable RCU lockdep checking for list usages. By default it is
+	  turned off since there are several list RCU users that still
+	  need to be converted to pass a lockdep expression. To prevent
+	  false-positive splats, we keep it default disabled but once all
+	  users are converted, we can remove this config option.
+
 config TORTURE_TEST
 	tristate
 	default n
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 9b761e546de8..58c178e2b394 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -530,7 +530,7 @@ static void srcu_gp_end(struct srcu_struct *ssp)
 	idx = rcu_seq_state(ssp->srcu_gp_seq);
 	WARN_ON_ONCE(idx != SRCU_STATE_SCAN2);
 	cbdelay = srcu_get_delay(ssp);
-	ssp->srcu_last_gp_end = ktime_get_mono_fast_ns();
+	WRITE_ONCE(ssp->srcu_last_gp_end, ktime_get_mono_fast_ns());
 	rcu_seq_end(&ssp->srcu_gp_seq);
 	gpseq = rcu_seq_current(&ssp->srcu_gp_seq);
 	if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, gpseq))
@@ -762,6 +762,7 @@ static bool srcu_might_be_idle(struct srcu_struct *ssp)
 	unsigned long flags;
 	struct srcu_data *sdp;
 	unsigned long t;
+	unsigned long tlast;
 
 	/* If the local srcu_data structure has callbacks, not idle.  */
 	local_irq_save(flags);
@@ -780,9 +781,9 @@ static bool srcu_might_be_idle(struct srcu_struct *ssp)
 
 	/* First, see if enough time has passed since the last GP. */
 	t = ktime_get_mono_fast_ns();
+	tlast = READ_ONCE(ssp->srcu_last_gp_end);
 	if (exp_holdoff == 0 ||
-	    time_in_range_open(t, ssp->srcu_last_gp_end,
-			       ssp->srcu_last_gp_end + exp_holdoff))
+	    time_in_range_open(t, tlast, tlast + exp_holdoff))
 		return false; /* Too soon after last GP. */
 
 	/* Next, check for probable idleness. */
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index affa7aae758f..58cdad75ddac 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -547,7 +547,7 @@ static void rcu_eqs_enter(bool user)
 	}
 
 	lockdep_assert_irqs_disabled();
-	trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, rdp->dynticks);
+	trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, atomic_read(&rdp->dynticks));
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
 	rdp = this_cpu_ptr(&rcu_data);
 	do_nocb_deferred_wakeup(rdp);
@@ -620,14 +620,15 @@ static __always_inline void rcu_nmi_exit_common(bool irq)
 	 * leave it in non-RCU-idle state.
 	 */
 	if (rdp->dynticks_nmi_nesting != 1) {
-		trace_rcu_dyntick(TPS("--="), rdp->dynticks_nmi_nesting, rdp->dynticks_nmi_nesting - 2, rdp->dynticks);
+		trace_rcu_dyntick(TPS("--="), rdp->dynticks_nmi_nesting, rdp->dynticks_nmi_nesting - 2,
+				  atomic_read(&rdp->dynticks));
 		WRITE_ONCE(rdp->dynticks_nmi_nesting, /* No store tearing. */
 			   rdp->dynticks_nmi_nesting - 2);
 		return;
 	}
 
 	/* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */
-	trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, rdp->dynticks);
+	trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, atomic_read(&rdp->dynticks));
 	WRITE_ONCE(rdp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */
 
 	if (irq)
@@ -714,7 +715,7 @@ static void rcu_eqs_exit(bool user)
 	rcu_dynticks_task_exit();
 	rcu_dynticks_eqs_exit();
 	rcu_cleanup_after_idle();
-	trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, rdp->dynticks);
+	trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, atomic_read(&rdp->dynticks));
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
 	WRITE_ONCE(rdp->dynticks_nesting, 1);
 	WARN_ON_ONCE(rdp->dynticks_nmi_nesting);
@@ -798,7 +799,7 @@ static __always_inline void rcu_nmi_enter_common(bool irq)
 	}
 	trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="),
 			  rdp->dynticks_nmi_nesting,
-			  rdp->dynticks_nmi_nesting + incby, rdp->dynticks);
+			  rdp->dynticks_nmi_nesting + incby, atomic_read(&rdp->dynticks));
 	WRITE_ONCE(rdp->dynticks_nmi_nesting, /* Prevent store tearing. */
 		   rdp->dynticks_nmi_nesting + incby);
 	barrier();
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 9c990df880d1..91357562f168 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -134,7 +134,7 @@ static void __maybe_unused sync_exp_reset_tree(void)
 	rcu_for_each_node_breadth_first(rnp) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		WARN_ON_ONCE(rnp->expmask);
-		rnp->expmask = rnp->expmaskinit;
+		WRITE_ONCE(rnp->expmask, rnp->expmaskinit);
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	}
 }
@@ -211,7 +211,7 @@ static void __rcu_report_exp_rnp(struct rcu_node *rnp,
 		rnp = rnp->parent;
 		raw_spin_lock_rcu_node(rnp); /* irqs already disabled */
 		WARN_ON_ONCE(!(rnp->expmask & mask));
-		rnp->expmask &= ~mask;
+		WRITE_ONCE(rnp->expmask, rnp->expmask & ~mask);
 	}
 }
 
@@ -241,7 +241,7 @@ static void rcu_report_exp_cpu_mult(struct rcu_node *rnp,
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		return;
 	}
-	rnp->expmask &= ~mask;
+	WRITE_ONCE(rnp->expmask, rnp->expmask & ~mask);
 	__rcu_report_exp_rnp(rnp, wake, flags); /* Releases rnp->lock. */
 }
 
@@ -373,12 +373,10 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 
 	/* IPI the remaining CPUs for expedited quiescent state. */
-	for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
+	for_each_leaf_node_cpu_mask(rnp, cpu, mask_ofl_ipi) {
 		unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
 		struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 
-		if (!(mask_ofl_ipi & mask))
-			continue;
 retry_ipi:
 		if (rcu_dynticks_in_eqs_since(rdp, rdp->exp_dynticks_snap)) {
 			mask_ofl_test |= mask;
@@ -487,7 +485,7 @@ static void synchronize_sched_expedited_wait(void)
 				struct rcu_data *rdp;
 
 				mask = leaf_node_cpu_bit(rnp, cpu);
-				if (!(rnp->expmask & mask))
+				if (!(READ_ONCE(rnp->expmask) & mask))
 					continue;
 				ndetected++;
 				rdp = per_cpu_ptr(&rcu_data, cpu);
@@ -499,7 +497,8 @@ static void synchronize_sched_expedited_wait(void)
 		}
 		pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n",
 			jiffies - jiffies_start, rcu_state.expedited_sequence,
-			rnp_root->expmask, ".T"[!!rnp_root->exp_tasks]);
+			READ_ONCE(rnp_root->expmask),
+			".T"[!!rnp_root->exp_tasks]);
 		if (ndetected) {
 			pr_err("blocking rcu_node structures:");
 			rcu_for_each_node_breadth_first(rnp) {
@@ -509,7 +508,7 @@ static void synchronize_sched_expedited_wait(void)
 					continue;
 				pr_cont(" l=%u:%d-%d:%#lx/%c",
 					rnp->level, rnp->grplo, rnp->grphi,
-					rnp->expmask,
+					READ_ONCE(rnp->expmask),
 					".T"[!!rnp->exp_tasks]);
 			}
 			pr_cont("\n");
@@ -517,7 +516,7 @@ static void synchronize_sched_expedited_wait(void)
 		rcu_for_each_leaf_node(rnp) {
 			for_each_leaf_node_possible_cpu(rnp, cpu) {
 				mask = leaf_node_cpu_bit(rnp, cpu);
-				if (!(rnp->expmask & mask))
+				if (!(READ_ONCE(rnp->expmask) & mask))
 					continue;
 				dump_cpu_task(cpu);
 			}
@@ -537,14 +536,13 @@ static void rcu_exp_wait_wake(unsigned long s)
 	struct rcu_node *rnp;
 
 	synchronize_sched_expedited_wait();
-	rcu_exp_gp_seq_end();
-	trace_rcu_exp_grace_period(rcu_state.name, s, TPS("end"));
 
-	/*
-	 * Switch over to wakeup mode, allowing the next GP, but -only- the
-	 * next GP, to proceed.
-	 */
+	// Switch over to wakeup mode, allowing the next GP to proceed.
+	// End the previous grace period only after acquiring the mutex
+	// to ensure that only one GP runs concurrently with wakeups.
 	mutex_lock(&rcu_state.exp_wake_mutex);
+	rcu_exp_gp_seq_end();
+	trace_rcu_exp_grace_period(rcu_state.name, s, TPS("end"));
 
 	rcu_for_each_node_breadth_first(rnp) {
 		if (ULONG_CMP_LT(READ_ONCE(rnp->exp_seq_rq), s)) {
@@ -555,7 +553,7 @@ static void rcu_exp_wait_wake(unsigned long s)
 			spin_unlock(&rnp->exp_lock);
 		}
 		smp_mb(); /* All above changes before wakeup. */
-		wake_up_all(&rnp->exp_wq[rcu_seq_ctr(rcu_state.expedited_sequence) & 0x3]);
+		wake_up_all(&rnp->exp_wq[rcu_seq_ctr(s) & 0x3]);
 	}
 	trace_rcu_exp_grace_period(rcu_state.name, s, TPS("endwake"));
 	mutex_unlock(&rcu_state.exp_wake_mutex);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 1102765f91fd..8df9df6e018c 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -240,7 +240,7 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 	 * blocked tasks.
 	 */
 	if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD)) {
-		rnp->gp_tasks = &t->rcu_node_entry;
+		WRITE_ONCE(rnp->gp_tasks, &t->rcu_node_entry);
 		WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq);
 	}
 	if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD))
@@ -371,7 +371,7 @@ EXPORT_SYMBOL_GPL(rcu_note_context_switch);
  */
 static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
 {
-	return rnp->gp_tasks != NULL;
+	return READ_ONCE(rnp->gp_tasks) != NULL;
 }
 
 /* Bias and limit values for ->rcu_read_lock_nesting. */
@@ -523,7 +523,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
 		trace_rcu_unlock_preempted_task(TPS("rcu_preempt"),
 						rnp->gp_seq, t->pid);
 		if (&t->rcu_node_entry == rnp->gp_tasks)
-			rnp->gp_tasks = np;
+			WRITE_ONCE(rnp->gp_tasks, np);
 		if (&t->rcu_node_entry == rnp->exp_tasks)
 			rnp->exp_tasks = np;
 		if (IS_ENABLED(CONFIG_RCU_BOOST)) {
@@ -661,7 +661,7 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
 		dump_blkd_tasks(rnp, 10);
 	if (rcu_preempt_has_tasks(rnp) &&
 	    (rnp->qsmaskinit || rnp->wait_blkd_tasks)) {
-		rnp->gp_tasks = rnp->blkd_tasks.next;
+		WRITE_ONCE(rnp->gp_tasks, rnp->blkd_tasks.next);
 		t = container_of(rnp->gp_tasks, struct task_struct,
 				 rcu_node_entry);
 		trace_rcu_unlock_preempted_task(TPS("rcu_preempt-GPS"),
@@ -755,7 +755,8 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
 		pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx\n",
 			__func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext);
 	pr_info("%s: ->gp_tasks %p ->boost_tasks %p ->exp_tasks %p\n",
-		__func__, rnp->gp_tasks, rnp->boost_tasks, rnp->exp_tasks);
+		__func__, READ_ONCE(rnp->gp_tasks), rnp->boost_tasks,
+		rnp->exp_tasks);
 	pr_info("%s: ->blkd_tasks", __func__);
 	i = 0;
 	list_for_each(lhp, &rnp->blkd_tasks) {
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index c3bf44ba42e5..eb5e63b6841f 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -61,9 +61,15 @@ module_param(rcu_normal_after_boot, int, 0);
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 /**
- * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section?
+ * rcu_read_lock_held_common() - might we be in RCU-sched read-side critical section?
+ * @ret:	Best guess answer if lockdep cannot be relied on
  *
- * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an
+ * Returns true if lockdep must be ignored, in which case *ret contains
+ * the best guess described below.  Otherwise returns false, in which
+ * case *ret tells the caller nothing and the caller should instead
+ * consult lockdep.
+ *
+ * If CONFIG_DEBUG_LOCK_ALLOC is selected, set *ret to nonzero iff in an
  * RCU-sched read-side critical section.  In absence of
  * CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side
  * critical section unless it can prove otherwise.  Note that disabling
@@ -75,35 +81,45 @@ module_param(rcu_normal_after_boot, int, 0);
  * Check debug_lockdep_rcu_enabled() to prevent false positives during boot
  * and while lockdep is disabled.
  *
- * Note that if the CPU is in the idle loop from an RCU point of
- * view (ie: that we are in the section between rcu_idle_enter() and
- * rcu_idle_exit()) then rcu_read_lock_held() returns false even if the CPU
- * did an rcu_read_lock().  The reason for this is that RCU ignores CPUs
- * that are in such a section, considering these as in extended quiescent
- * state, so such a CPU is effectively never in an RCU read-side critical
- * section regardless of what RCU primitives it invokes.  This state of
- * affairs is required --- we need to keep an RCU-free window in idle
- * where the CPU may possibly enter into low power mode. This way we can
- * notice an extended quiescent state to other CPUs that started a grace
- * period. Otherwise we would delay any grace period as long as we run in
- * the idle task.
+ * Note that if the CPU is in the idle loop from an RCU point of view (ie:
+ * that we are in the section between rcu_idle_enter() and rcu_idle_exit())
+ * then rcu_read_lock_held() sets *ret to false even if the CPU did an
+ * rcu_read_lock().  The reason for this is that RCU ignores CPUs that are
+ * in such a section, considering these as in extended quiescent state,
+ * so such a CPU is effectively never in an RCU read-side critical section
+ * regardless of what RCU primitives it invokes.  This state of affairs is
+ * required --- we need to keep an RCU-free window in idle where the CPU may
+ * possibly enter into low power mode. This way we can notice an extended
+ * quiescent state to other CPUs that started a grace period. Otherwise
+ * we would delay any grace period as long as we run in the idle task.
  *
- * Similarly, we avoid claiming an SRCU read lock held if the current
+ * Similarly, we avoid claiming an RCU read lock held if the current
  * CPU is offline.
  */
+static bool rcu_read_lock_held_common(bool *ret)
+{
+	if (!debug_lockdep_rcu_enabled()) {
+		*ret = 1;
+		return true;
+	}
+	if (!rcu_is_watching()) {
+		*ret = 0;
+		return true;
+	}
+	if (!rcu_lockdep_current_cpu_online()) {
+		*ret = 0;
+		return true;
+	}
+	return false;
+}
+
 int rcu_read_lock_sched_held(void)
 {
-	int lockdep_opinion = 0;
+	bool ret;
 
-	if (!debug_lockdep_rcu_enabled())
-		return 1;
-	if (!rcu_is_watching())
-		return 0;
-	if (!rcu_lockdep_current_cpu_online())
-		return 0;
-	if (debug_locks)
-		lockdep_opinion = lock_is_held(&rcu_sched_lock_map);
-	return lockdep_opinion || !preemptible();
+	if (rcu_read_lock_held_common(&ret))
+		return ret;
+	return lock_is_held(&rcu_sched_lock_map) || !preemptible();
 }
 EXPORT_SYMBOL(rcu_read_lock_sched_held);
 #endif
@@ -136,8 +152,7 @@ static atomic_t rcu_expedited_nesting = ATOMIC_INIT(1);
  */
 bool rcu_gp_is_expedited(void)
 {
-	return rcu_expedited || atomic_read(&rcu_expedited_nesting) ||
-	       rcu_scheduler_active == RCU_SCHEDULER_INIT;
+	return rcu_expedited || atomic_read(&rcu_expedited_nesting);
 }
 EXPORT_SYMBOL_GPL(rcu_gp_is_expedited);
 
@@ -261,12 +276,10 @@ NOKPROBE_SYMBOL(debug_lockdep_rcu_enabled);
  */
 int rcu_read_lock_held(void)
 {
-	if (!debug_lockdep_rcu_enabled())
-		return 1;
-	if (!rcu_is_watching())
-		return 0;
-	if (!rcu_lockdep_current_cpu_online())
-		return 0;
+	bool ret;
+
+	if (rcu_read_lock_held_common(&ret))
+		return ret;
 	return lock_is_held(&rcu_lock_map);
 }
 EXPORT_SYMBOL_GPL(rcu_read_lock_held);
@@ -288,16 +301,28 @@ EXPORT_SYMBOL_GPL(rcu_read_lock_held);
  */
 int rcu_read_lock_bh_held(void)
 {
-	if (!debug_lockdep_rcu_enabled())
-		return 1;
-	if (!rcu_is_watching())
-		return 0;
-	if (!rcu_lockdep_current_cpu_online())
-		return 0;
+	bool ret;
+
+	if (rcu_read_lock_held_common(&ret))
+		return ret;
 	return in_softirq() || irqs_disabled();
 }
 EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held);
 
+int rcu_read_lock_any_held(void)
+{
+	bool ret;
+
+	if (rcu_read_lock_held_common(&ret))
+		return ret;
+	if (lock_is_held(&rcu_lock_map) ||
+	    lock_is_held(&rcu_bh_lock_map) ||
+	    lock_is_held(&rcu_sched_lock_map))
+		return 1;
+	return !preemptible();
+}
+EXPORT_SYMBOL_GPL(rcu_read_lock_any_held);
+
 #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
 /**
diff --git a/kernel/relay.c b/kernel/relay.c
index ade14fb7ce2e..4b760ec16342 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -581,6 +581,11 @@ struct rchan *relay_open(const char *base_filename,
 		return NULL;
 
 	chan->buf = alloc_percpu(struct rchan_buf *);
+	if (!chan->buf) {
+		kfree(chan);
+		return NULL;
+	}
+
 	chan->version = RELAYFS_CHANNEL_VERSION;
 	chan->n_subbufs = n_subbufs;
 	chan->subbuf_size = subbuf_size;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c36452443381..dcc54d44fcde 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2338,6 +2338,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	 * Silence PROVE_RCU.
 	 */
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
+	rseq_migrate(p);
 	/*
 	 * We're setting the CPU for the first time, we don't migrate,
 	 * so use __set_task_cpu().
@@ -2402,6 +2403,7 @@ void wake_up_new_task(struct task_struct *p)
 	 * as we're not fully set-up yet.
 	 */
 	p->recent_used_cpu = task_cpu(p);
+	rseq_migrate(p);
 	__set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
 #endif
 	rq = __task_rq_lock(p, &rf);
@@ -3102,28 +3104,31 @@ static void sched_tick_remote(struct work_struct *work)
 	 * statistics and checks timeslices in a time-independent way, regardless
 	 * of when exactly it is running.
 	 */
-	if (idle_cpu(cpu) || !tick_nohz_tick_stopped_cpu(cpu))
+	if (!tick_nohz_tick_stopped_cpu(cpu))
 		goto out_requeue;
 
 	rq_lock_irq(rq, &rf);
 	curr = rq->curr;
-	if (is_idle_task(curr) || cpu_is_offline(cpu))
+	if (cpu_is_offline(cpu))
 		goto out_unlock;
 
 	update_rq_clock(rq);
-	delta = rq_clock_task(rq) - curr->se.exec_start;
 
-	/*
-	 * Make sure the next tick runs within a reasonable
-	 * amount of time.
-	 */
-	WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
+	if (!is_idle_task(curr)) {
+		/*
+		 * Make sure the next tick runs within a reasonable
+		 * amount of time.
+		 */
+		delta = rq_clock_task(rq) - curr->se.exec_start;
+		WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
+	}
 	curr->sched_class->task_tick(rq, curr, 0);
 
+	calc_load_nohz_remote(rq);
 out_unlock:
 	rq_unlock_irq(rq, &rf);
-
 out_requeue:
+
 	/*
 	 * Run the remote tick once per second (1Hz). This arbitrary
 	 * frequency is large enough to avoid overload but short enough
@@ -3857,7 +3862,8 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 	 */
 	if (dl_prio(prio)) {
 		if (!dl_prio(p->normal_prio) ||
-		    (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) {
+		    (pi_task && dl_prio(pi_task->prio) &&
+		     dl_entity_preempt(&pi_task->dl, &p->dl))) {
 			p->dl.dl_boosted = 1;
 			queue_flag |= ENQUEUE_REPLENISH;
 		} else
@@ -5563,13 +5569,14 @@ void idle_task_exit(void)
 	struct mm_struct *mm = current->active_mm;
 
 	BUG_ON(cpu_online(smp_processor_id()));
+	BUG_ON(current != this_rq()->idle);
 
 	if (mm != &init_mm) {
 		switch_mm(mm, &init_mm, current);
-		current->active_mm = &init_mm;
 		finish_arch_post_lock_switch();
 	}
-	mmdrop(mm);
+
+	/* finish_cpu(), as ran on the BP, will clean up the active_mm state */
 }
 
 /*
@@ -6430,8 +6437,15 @@ void sched_move_task(struct task_struct *tsk)
 
 	if (queued)
 		enqueue_task(rq, tsk, queue_flags);
-	if (running)
+	if (running) {
 		set_curr_task(rq, tsk);
+		/*
+		 * After changing group, the running task may have joined a
+		 * throttled one but it's still the running task. Trigger a
+		 * resched to make sure that task can still run.
+		 */
+		resched_curr(rq);
+	}
 
 	task_rq_unlock(rq, tsk, &rf);
 }
@@ -6566,6 +6580,8 @@ static DEFINE_MUTEX(cfs_constraints_mutex);
 
 const u64 max_cfs_quota_period = 1 * NSEC_PER_SEC; /* 1s */
 static const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */
+/* More than 203 days if BW_SHIFT equals 20. */
+static const u64 max_cfs_runtime = MAX_BW * NSEC_PER_USEC;
 
 static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime);
 
@@ -6594,6 +6610,12 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
 		return -EINVAL;
 
 	/*
+	 * Bound quota to defend quota against overflow during bandwidth shift.
+	 */
+	if (quota != RUNTIME_INF && quota > max_cfs_runtime)
+		return -EINVAL;
+
+	/*
 	 * Prevent race between setting of cfs_rq->runtime_enabled and
 	 * unthrottle_offline_cfs_rqs().
 	 */
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index fcdafdcb129c..3daa9b4cf6d9 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2679,6 +2679,7 @@ void __dl_clear_params(struct task_struct *p)
 	dl_se->dl_bw			= 0;
 	dl_se->dl_density		= 0;
 
+	dl_se->dl_boosted		= 0;
 	dl_se->dl_throttled		= 0;
 	dl_se->dl_yielded		= 0;
 	dl_se->dl_non_contending	= 0;
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 14c6a8716ba1..0650be5f5bc7 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -272,7 +272,7 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd)
 	set_table_entry(&table[7] , "busy_factor",	   &sd->busy_factor,	     sizeof(int) , 0644, proc_dointvec_minmax,   false);
 	set_table_entry(&table[8] , "imbalance_pct",	   &sd->imbalance_pct,	     sizeof(int) , 0644, proc_dointvec_minmax,   false);
 	set_table_entry(&table[9] , "cache_nice_tries",	   &sd->cache_nice_tries,    sizeof(int) , 0644, proc_dointvec_minmax,   false);
-	set_table_entry(&table[10], "flags",		   &sd->flags,		     sizeof(int) , 0644, proc_dointvec_minmax,   false);
+	set_table_entry(&table[10], "flags",		   &sd->flags,		     sizeof(int) , 0444, proc_dointvec_minmax,   false);
 	set_table_entry(&table[11], "max_newidle_lb_cost", &sd->max_newidle_lb_cost, sizeof(long), 0644, proc_doulongvec_minmax, false);
 	set_table_entry(&table[12], "name",		   sd->name,		CORENAME_MAX_SIZE, 0444, proc_dostring,		 false);
 	/* &table[13] is terminator */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 866dd0cbc920..50f4b19a5387 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2659,7 +2659,7 @@ static void task_tick_numa(struct rq *rq, struct task_struct *curr)
 	/*
 	 * We don't care about NUMA placement if we don't have memory.
 	 */
-	if (!curr->mm || (curr->flags & PF_EXITING) || work->next != work)
+	if ((curr->flags & (PF_EXITING | PF_KTHREAD)) || work->next != work)
 		return;
 
 	/*
@@ -3488,9 +3488,6 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 	cfs_rq->load_last_update_time_copy = sa->last_update_time;
 #endif
 
-	if (decayed)
-		cfs_rq_util_change(cfs_rq, 0);
-
 	return decayed;
 }
 
@@ -3596,8 +3593,12 @@ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 		attach_entity_load_avg(cfs_rq, se, SCHED_CPUFREQ_MIGRATION);
 		update_tg_load_avg(cfs_rq, 0);
 
-	} else if (decayed && (flags & UPDATE_TG))
-		update_tg_load_avg(cfs_rq, 0);
+	} else if (decayed) {
+		cfs_rq_util_change(cfs_rq, 0);
+
+		if (flags & UPDATE_TG)
+			update_tg_load_avg(cfs_rq, 0);
+	}
 }
 
 #ifndef CONFIG_64BIT
@@ -3805,7 +3806,11 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
 		return;
 	}
 
-	rq->misfit_task_load = task_h_load(p);
+	/*
+	 * Make sure that misfit_task_load will not be null even if
+	 * task_h_load() returns 0.
+	 */
+	rq->misfit_task_load = max_t(unsigned long, task_h_load(p), 1);
 }
 
 #else /* CONFIG_SMP */
@@ -3908,6 +3913,7 @@ static inline void check_schedstat_required(void)
 #endif
 }
 
+static inline bool cfs_bandwidth_used(void);
 
 /*
  * MIGRATION
@@ -3986,10 +3992,16 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 		__enqueue_entity(cfs_rq, se);
 	se->on_rq = 1;
 
-	if (cfs_rq->nr_running == 1) {
+	/*
+	 * When bandwidth control is enabled, cfs might have been removed
+	 * because of a parent been throttled but cfs->nr_running > 1. Try to
+	 * add it unconditionnally.
+	 */
+	if (cfs_rq->nr_running == 1 || cfs_bandwidth_used())
 		list_add_leaf_cfs_rq(cfs_rq);
+
+	if (cfs_rq->nr_running == 1)
 		check_enqueue_throttle(cfs_rq);
-	}
 }
 
 static void __clear_buddies_last(struct sched_entity *se)
@@ -4483,7 +4495,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	struct rq *rq = rq_of(cfs_rq);
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
 	struct sched_entity *se;
-	long task_delta, dequeue = 1;
+	long task_delta, idle_task_delta, dequeue = 1;
 	bool empty;
 
 	se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))];
@@ -4494,6 +4506,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	rcu_read_unlock();
 
 	task_delta = cfs_rq->h_nr_running;
+	idle_task_delta = cfs_rq->idle_h_nr_running;
 	for_each_sched_entity(se) {
 		struct cfs_rq *qcfs_rq = cfs_rq_of(se);
 		/* throttled entity or throttle-on-deactivate */
@@ -4503,6 +4516,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 		if (dequeue)
 			dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP);
 		qcfs_rq->h_nr_running -= task_delta;
+		qcfs_rq->idle_h_nr_running -= idle_task_delta;
 
 		if (qcfs_rq->load.weight)
 			dequeue = 0;
@@ -4541,8 +4555,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 	struct rq *rq = rq_of(cfs_rq);
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
 	struct sched_entity *se;
-	int enqueue = 1;
-	long task_delta;
+	long task_delta, idle_task_delta;
 
 	se = cfs_rq->tg->se[cpu_of(rq)];
 
@@ -4562,24 +4575,58 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 		return;
 
 	task_delta = cfs_rq->h_nr_running;
+	idle_task_delta = cfs_rq->idle_h_nr_running;
 	for_each_sched_entity(se) {
 		if (se->on_rq)
-			enqueue = 0;
+			break;
+		cfs_rq = cfs_rq_of(se);
+		enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP);
 
+		cfs_rq->h_nr_running += task_delta;
+		cfs_rq->idle_h_nr_running += idle_task_delta;
+
+		/* end evaluation on encountering a throttled cfs_rq */
+		if (cfs_rq_throttled(cfs_rq))
+			goto unthrottle_throttle;
+	}
+
+	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
-		if (enqueue)
-			enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP);
+
 		cfs_rq->h_nr_running += task_delta;
+		cfs_rq->idle_h_nr_running += idle_task_delta;
+
 
+		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(cfs_rq))
+			goto unthrottle_throttle;
+
+		/*
+		 * One parent has been throttled and cfs_rq removed from the
+		 * list. Add it back to not break the leaf list.
+		 */
+		if (throttled_hierarchy(cfs_rq))
+			list_add_leaf_cfs_rq(cfs_rq);
+	}
+
+	/* At this point se is NULL and we are at root level*/
+	add_nr_running(rq, task_delta);
+
+unthrottle_throttle:
+	/*
+	 * The cfs_rq_throttled() breaks in the above iteration can result in
+	 * incomplete leaf list maintenance, resulting in triggering the
+	 * assertion below.
+	 */
+	for_each_sched_entity(se) {
+		cfs_rq = cfs_rq_of(se);
+
+		if (list_add_leaf_cfs_rq(cfs_rq))
 			break;
 	}
 
 	assert_list_leaf_cfs_rq(rq);
 
-	if (!se)
-		add_nr_running(rq, task_delta);
-
 	/* Determine whether we need to wake up potentially idle CPU: */
 	if (rq->curr == rq->idle && rq->cfs.nr_running)
 		resched_curr(rq);
@@ -4904,6 +4951,8 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
 		if (!overrun)
 			break;
 
+		idle = do_sched_cfs_period_timer(cfs_b, overrun, flags);
+
 		if (++count > 3) {
 			u64 new, old = ktime_to_ns(cfs_b->period);
 
@@ -4933,8 +4982,6 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
 			/* reset count so we don't come right back in here */
 			count = 0;
 		}
-
-		idle = do_sched_cfs_period_timer(cfs_b, overrun, flags);
 	}
 	if (idle)
 		cfs_b->period_active = 0;
@@ -5172,6 +5219,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se;
+	int idle_h_nr_running = task_has_idle_policy(p);
 
 	/*
 	 * The code below (indirectly) updates schedutil which looks at
@@ -5195,30 +5243,38 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		cfs_rq = cfs_rq_of(se);
 		enqueue_entity(cfs_rq, se, flags);
 
-		/*
-		 * end evaluation on encountering a throttled cfs_rq
-		 *
-		 * note: in the case of encountering a throttled cfs_rq we will
-		 * post the final h_nr_running increment below.
-		 */
-		if (cfs_rq_throttled(cfs_rq))
-			break;
 		cfs_rq->h_nr_running++;
+		cfs_rq->idle_h_nr_running += idle_h_nr_running;
+
+		/* end evaluation on encountering a throttled cfs_rq */
+		if (cfs_rq_throttled(cfs_rq))
+			goto enqueue_throttle;
 
 		flags = ENQUEUE_WAKEUP;
 	}
 
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
+
+		update_load_avg(cfs_rq, se, UPDATE_TG);
+		update_cfs_group(se);
+
 		cfs_rq->h_nr_running++;
+		cfs_rq->idle_h_nr_running += idle_h_nr_running;
 
+		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(cfs_rq))
-			break;
+			goto enqueue_throttle;
 
-		update_load_avg(cfs_rq, se, UPDATE_TG);
-		update_cfs_group(se);
+               /*
+                * One parent has been throttled and cfs_rq removed from the
+                * list. Add it back to not break the leaf list.
+                */
+               if (throttled_hierarchy(cfs_rq))
+                       list_add_leaf_cfs_rq(cfs_rq);
 	}
 
+enqueue_throttle:
 	if (!se) {
 		add_nr_running(rq, 1);
 		/*
@@ -5272,20 +5328,18 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se;
 	int task_sleep = flags & DEQUEUE_SLEEP;
+	int idle_h_nr_running = task_has_idle_policy(p);
 
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
 		dequeue_entity(cfs_rq, se, flags);
 
-		/*
-		 * end evaluation on encountering a throttled cfs_rq
-		 *
-		 * note: in the case of encountering a throttled cfs_rq we will
-		 * post the final h_nr_running decrement below.
-		*/
-		if (cfs_rq_throttled(cfs_rq))
-			break;
 		cfs_rq->h_nr_running--;
+		cfs_rq->idle_h_nr_running -= idle_h_nr_running;
+
+		/* end evaluation on encountering a throttled cfs_rq */
+		if (cfs_rq_throttled(cfs_rq))
+			goto dequeue_throttle;
 
 		/* Don't dequeue parent if it has other entities besides us */
 		if (cfs_rq->load.weight) {
@@ -5304,15 +5358,20 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
+
+		update_load_avg(cfs_rq, se, UPDATE_TG);
+		update_cfs_group(se);
+
 		cfs_rq->h_nr_running--;
+		cfs_rq->idle_h_nr_running -= idle_h_nr_running;
 
+		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(cfs_rq))
-			break;
+			goto dequeue_throttle;
 
-		update_load_avg(cfs_rq, se, UPDATE_TG);
-		update_cfs_group(se);
 	}
 
+dequeue_throttle:
 	if (!se)
 		sub_nr_running(rq, 1);
 
@@ -6186,6 +6245,7 @@ static inline int select_idle_smt(struct task_struct *p, int target)
  */
 static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int target)
 {
+	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
 	struct sched_domain *this_sd;
 	u64 avg_cost, avg_idle;
 	u64 time, cost;
@@ -6216,11 +6276,11 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 
 	time = local_clock();
 
-	for_each_cpu_wrap(cpu, sched_domain_span(sd), target) {
+	cpumask_and(cpus, sched_domain_span(sd), &p->cpus_allowed);
+
+	for_each_cpu_wrap(cpu, cpus, target) {
 		if (!--nr)
 			return -1;
-		if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
-			continue;
 		if (available_idle_cpu(cpu))
 			break;
 	}
@@ -7602,7 +7662,15 @@ static int detach_tasks(struct lb_env *env)
 		if (!can_migrate_task(p, env))
 			goto next;
 
-		load = task_h_load(p);
+		/*
+		 * Depending of the number of CPUs and tasks and the
+		 * cgroup hierarchy, task_h_load() can return a null
+		 * value. Make sure that env->imbalance decreases
+		 * otherwise detach_tasks() will stop only after
+		 * detaching up to loop_max tasks.
+		 */
+		load = max_t(unsigned long, task_h_load(p), 1);
+
 
 		if (sched_feat(LB_MIN) && load < 16 && !env->sd->nr_balance_failed)
 			goto next;
@@ -7697,6 +7765,7 @@ static void attach_tasks(struct lb_env *env)
 	rq_unlock(env->dst_rq, &rf);
 }
 
+#ifdef CONFIG_NO_HZ_COMMON
 static inline bool cfs_rq_has_blocked(struct cfs_rq *cfs_rq)
 {
 	if (cfs_rq->avg.load_avg)
@@ -7724,6 +7793,41 @@ static inline bool others_have_blocked(struct rq *rq)
 	return false;
 }
 
+static inline void update_blocked_load_status(struct rq *rq, bool has_blocked)
+{
+	rq->last_blocked_load_update_tick = jiffies;
+
+	if (!has_blocked)
+		rq->has_blocked_load = 0;
+}
+#else
+static inline bool cfs_rq_has_blocked(struct cfs_rq *cfs_rq) { return false; }
+static inline bool others_have_blocked(struct rq *rq) { return false; }
+static inline void update_blocked_load_status(struct rq *rq, bool has_blocked) {}
+#endif
+
+static bool __update_blocked_others(struct rq *rq, bool *done)
+{
+	const struct sched_class *curr_class;
+	u64 now = rq_clock_pelt(rq);
+	bool decayed;
+
+	/*
+	 * update_load_avg() can call cpufreq_update_util(). Make sure that RT,
+	 * DL and IRQ signals have been updated before updating CFS.
+	 */
+	curr_class = rq->curr->sched_class;
+
+	decayed = update_rt_rq_load_avg(now, rq, curr_class == &rt_sched_class) |
+		  update_dl_rq_load_avg(now, rq, curr_class == &dl_sched_class) |
+		  update_irq_load_avg(rq, 0);
+
+	if (others_have_blocked(rq))
+		*done = false;
+
+	return decayed;
+}
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
 static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
@@ -7743,29 +7847,11 @@ static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
 	return true;
 }
 
-static void update_blocked_averages(int cpu)
+static bool __update_blocked_fair(struct rq *rq, bool *done)
 {
-	struct rq *rq = cpu_rq(cpu);
 	struct cfs_rq *cfs_rq, *pos;
-	const struct sched_class *curr_class;
-	struct rq_flags rf;
-	bool done = true;
-
-	rq_lock_irqsave(rq, &rf);
-	update_rq_clock(rq);
-
-	/*
-	 * update_cfs_rq_load_avg() can call cpufreq_update_util(). Make sure
-	 * that RT, DL and IRQ signals have been updated before updating CFS.
-	 */
-	curr_class = rq->curr->sched_class;
-	update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class);
-	update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class);
-	update_irq_load_avg(rq, 0);
-
-	/* Don't need periodic decay once load/util_avg are null */
-	if (others_have_blocked(rq))
-		done = false;
+	bool decayed = false;
+	int cpu = cpu_of(rq);
 
 	/*
 	 * Iterates the task_group tree in a bottom up fashion, see
@@ -7774,9 +7860,13 @@ static void update_blocked_averages(int cpu)
 	for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) {
 		struct sched_entity *se;
 
-		if (update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq))
+		if (update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq)) {
 			update_tg_load_avg(cfs_rq, 0);
 
+			if (cfs_rq == &rq->cfs)
+				decayed = true;
+		}
+
 		/* Propagate pending load changes to the parent, if any: */
 		se = cfs_rq->tg->se[cpu];
 		if (se && !skip_blocked_update(se))
@@ -7791,15 +7881,10 @@ static void update_blocked_averages(int cpu)
 
 		/* Don't need periodic decay once load/util_avg are null */
 		if (cfs_rq_has_blocked(cfs_rq))
-			done = false;
+			*done = false;
 	}
 
-#ifdef CONFIG_NO_HZ_COMMON
-	rq->last_blocked_load_update_tick = jiffies;
-	if (done)
-		rq->has_blocked_load = 0;
-#endif
-	rq_unlock_irqrestore(rq, &rf);
+	return decayed;
 }
 
 /*
@@ -7849,33 +7934,16 @@ static unsigned long task_h_load(struct task_struct *p)
 			cfs_rq_load_avg(cfs_rq) + 1);
 }
 #else
-static inline void update_blocked_averages(int cpu)
+static bool __update_blocked_fair(struct rq *rq, bool *done)
 {
-	struct rq *rq = cpu_rq(cpu);
 	struct cfs_rq *cfs_rq = &rq->cfs;
-	const struct sched_class *curr_class;
-	struct rq_flags rf;
-
-	rq_lock_irqsave(rq, &rf);
-	update_rq_clock(rq);
+	bool decayed;
 
-	/*
-	 * update_cfs_rq_load_avg() can call cpufreq_update_util(). Make sure
-	 * that RT, DL and IRQ signals have been updated before updating CFS.
-	 */
-	curr_class = rq->curr->sched_class;
-	update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class);
-	update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class);
-	update_irq_load_avg(rq, 0);
+	decayed = update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq);
+	if (cfs_rq_has_blocked(cfs_rq))
+		*done = false;
 
-	update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq);
-
-#ifdef CONFIG_NO_HZ_COMMON
-	rq->last_blocked_load_update_tick = jiffies;
-	if (!cfs_rq_has_blocked(cfs_rq) && !others_have_blocked(rq))
-		rq->has_blocked_load = 0;
-#endif
-	rq_unlock_irqrestore(rq, &rf);
+	return decayed;
 }
 
 static unsigned long task_h_load(struct task_struct *p)
@@ -7884,6 +7952,24 @@ static unsigned long task_h_load(struct task_struct *p)
 }
 #endif
 
+static void update_blocked_averages(int cpu)
+{
+	bool decayed = false, done = true;
+	struct rq *rq = cpu_rq(cpu);
+	struct rq_flags rf;
+
+	rq_lock_irqsave(rq, &rf);
+	update_rq_clock(rq);
+
+	decayed |= __update_blocked_others(rq, &done);
+	decayed |= __update_blocked_fair(rq, &done);
+
+	update_blocked_load_status(rq, !done);
+	if (decayed)
+		cpufreq_update_util(rq, 0);
+	rq_unlock_irqrestore(rq, &rf);
+}
+
 /********** Helpers for find_busiest_group ************************/
 
 /*
@@ -9587,7 +9673,12 @@ static void kick_ilb(unsigned int flags)
 {
 	int ilb_cpu;
 
-	nohz.next_balance++;
+	/*
+	 * Increase nohz.next_balance only when if full ilb is triggered but
+	 * not if we only update stats.
+	 */
+	if (flags & NOHZ_BALANCE_KICK)
+		nohz.next_balance = jiffies+1;
 
 	ilb_cpu = find_new_ilb();
 
@@ -9906,6 +9997,14 @@ static bool _nohz_idle_balance(struct rq *this_rq, unsigned int flags,
 		}
 	}
 
+	/*
+	 * next_balance will be updated only when there is a need.
+	 * When the CPU is attached to null domain for ex, it will not be
+	 * updated.
+	 */
+	if (likely(update_next_balance))
+		nohz.next_balance = next_balance;
+
 	/* Newly idle CPU doesn't need an update */
 	if (idle != CPU_NEWLY_IDLE) {
 		update_blocked_averages(this_cpu);
@@ -9926,14 +10025,6 @@ abort:
 	if (has_blocked_load)
 		WRITE_ONCE(nohz.has_blocked, 1);
 
-	/*
-	 * next_balance will be updated only when there is a need.
-	 * When the CPU is attached to null domain for ex, it will not be
-	 * updated.
-	 */
-	if (likely(update_next_balance))
-		nohz.next_balance = next_balance;
-
 	return ret;
 }
 
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index 28a516575c18..de22da666ac7 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -231,16 +231,11 @@ static inline int calc_load_read_idx(void)
 	return calc_load_idx & 1;
 }
 
-void calc_load_nohz_start(void)
+static void calc_load_nohz_fold(struct rq *rq)
 {
-	struct rq *this_rq = this_rq();
 	long delta;
 
-	/*
-	 * We're going into NO_HZ mode, if there's any pending delta, fold it
-	 * into the pending NO_HZ delta.
-	 */
-	delta = calc_load_fold_active(this_rq, 0);
+	delta = calc_load_fold_active(rq, 0);
 	if (delta) {
 		int idx = calc_load_write_idx();
 
@@ -248,6 +243,24 @@ void calc_load_nohz_start(void)
 	}
 }
 
+void calc_load_nohz_start(void)
+{
+	/*
+	 * We're going into NO_HZ mode, if there's any pending delta, fold it
+	 * into the pending NO_HZ delta.
+	 */
+	calc_load_nohz_fold(this_rq());
+}
+
+/*
+ * Keep track of the load for NOHZ_FULL, must be called between
+ * calc_load_nohz_{start,stop}().
+ */
+void calc_load_nohz_remote(struct rq *rq)
+{
+	calc_load_nohz_fold(rq);
+}
+
 void calc_load_nohz_stop(void)
 {
 	struct rq *this_rq = this_rq();
@@ -268,7 +281,7 @@ void calc_load_nohz_stop(void)
 		this_rq->calc_load_update += LOAD_FREQ;
 }
 
-static long calc_load_nohz_fold(void)
+static long calc_load_nohz_read(void)
 {
 	int idx = calc_load_read_idx();
 	long delta = 0;
@@ -323,7 +336,7 @@ static void calc_global_nohz(void)
 }
 #else /* !CONFIG_NO_HZ_COMMON */
 
-static inline long calc_load_nohz_fold(void) { return 0; }
+static inline long calc_load_nohz_read(void) { return 0; }
 static inline void calc_global_nohz(void) { }
 
 #endif /* CONFIG_NO_HZ_COMMON */
@@ -346,7 +359,7 @@ void calc_global_load(unsigned long ticks)
 	/*
 	 * Fold the 'old' NO_HZ-delta to include all NO_HZ CPUs.
 	 */
-	delta = calc_load_nohz_fold();
+	delta = calc_load_nohz_read();
 	if (delta)
 		atomic_long_add(delta, &calc_load_tasks);
 
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 517e3719027e..9154e745f097 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -185,7 +185,8 @@ static void group_init(struct psi_group *group)
 
 	for_each_possible_cpu(cpu)
 		seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq);
-	group->avg_next_update = sched_clock() + psi_period;
+	group->avg_last_update = sched_clock();
+	group->avg_next_update = group->avg_last_update + psi_period;
 	INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work);
 	mutex_init(&group->avgs_lock);
 	/* Init trigger-related members */
@@ -481,7 +482,7 @@ static u64 window_update(struct psi_window *win, u64 now, u64 value)
 		u32 remaining;
 
 		remaining = win->size - elapsed;
-		growth += div_u64(win->prev_growth * remaining, win->size);
+		growth += div64_u64(win->prev_growth * remaining, win->size);
 	}
 
 	return growth;
@@ -1198,6 +1199,9 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf,
 	if (static_branch_likely(&psi_disabled))
 		return -EOPNOTSUPP;
 
+	if (!nbytes)
+		return -EINVAL;
+
 	buf_size = min(nbytes, sizeof(buf));
 	if (copy_from_user(buf, user_buf, buf_size))
 		return -EFAULT;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 1e6b909dca36..c4108c93b2cf 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -9,6 +9,8 @@
 
 int sched_rr_timeslice = RR_TIMESLICE;
 int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE;
+/* More than 4 hours if BW_SHIFT equals 20. */
+static const u64 max_rt_runtime = MAX_BW;
 
 static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun);
 
@@ -2522,6 +2524,12 @@ static int tg_set_rt_bandwidth(struct task_group *tg,
 	if (rt_period == 0)
 		return -EINVAL;
 
+	/*
+	 * Bound quota to defend quota against overflow during bandwidth shift.
+	 */
+	if (rt_runtime != RUNTIME_INF && rt_runtime > max_rt_runtime)
+		return -EINVAL;
+
 	mutex_lock(&rt_constraints_mutex);
 	read_lock(&tasklist_lock);
 	err = __rt_schedulable(tg, rt_period, rt_runtime);
@@ -2643,7 +2651,9 @@ static int sched_rt_global_validate(void)
 		return -EINVAL;
 
 	if ((sysctl_sched_rt_runtime != RUNTIME_INF) &&
-		(sysctl_sched_rt_runtime > sysctl_sched_rt_period))
+		((sysctl_sched_rt_runtime > sysctl_sched_rt_period) ||
+		 ((u64)sysctl_sched_rt_runtime *
+			NSEC_PER_USEC > max_rt_runtime)))
 		return -EINVAL;
 
 	return 0;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 0c0ed23f315a..2efae7800633 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -124,7 +124,13 @@ static inline void cpu_load_update_active(struct rq *this_rq) { }
 #ifdef CONFIG_64BIT
 # define NICE_0_LOAD_SHIFT	(SCHED_FIXEDPOINT_SHIFT + SCHED_FIXEDPOINT_SHIFT)
 # define scale_load(w)		((w) << SCHED_FIXEDPOINT_SHIFT)
-# define scale_load_down(w)	((w) >> SCHED_FIXEDPOINT_SHIFT)
+# define scale_load_down(w) \
+({ \
+	unsigned long __w = (w); \
+	if (__w) \
+		__w = max(2UL, __w >> SCHED_FIXEDPOINT_SHIFT); \
+	__w; \
+})
 #else
 # define NICE_0_LOAD_SHIFT	(SCHED_FIXEDPOINT_SHIFT)
 # define scale_load(w)		(w)
@@ -487,7 +493,8 @@ struct cfs_rq {
 	struct load_weight	load;
 	unsigned long		runnable_weight;
 	unsigned int		nr_running;
-	unsigned int		h_nr_running;
+	unsigned int		h_nr_running;      /* SCHED_{NORMAL,BATCH,IDLE} */
+	unsigned int		idle_h_nr_running; /* SCHED_IDLE */
 
 	u64			exec_clock;
 	u64			min_vruntime;
@@ -1793,6 +1800,8 @@ extern void init_dl_rq_bw_ratio(struct dl_rq *dl_rq);
 #define BW_SHIFT		20
 #define BW_UNIT			(1 << BW_SHIFT)
 #define RATIO_SHIFT		8
+#define MAX_BW_BITS		(64 - BW_SHIFT)
+#define MAX_BW			((1ULL << MAX_BW_BITS) - 1)
 unsigned long to_ratio(u64 period, u64 runtime);
 
 extern void init_entity_runnable_average(struct sched_entity *se);
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index c429964ff9cf..6fb3e636fbe1 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1332,7 +1332,7 @@ sd_init(struct sched_domain_topology_level *tl,
 		sd_flags = (*tl->sd_flags)();
 	if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS,
 			"wrong sd_flags in topology description\n"))
-		sd_flags &= ~TOPOLOGY_SD_FLAGS;
+		sd_flags &= TOPOLOGY_SD_FLAGS;
 
 	/* Apply detected topology flags */
 	sd_flags |= dflags;
@@ -1872,6 +1872,42 @@ static struct sched_domain *build_sched_domain(struct sched_domain_topology_leve
 }
 
 /*
+ * Ensure topology masks are sane, i.e. there are no conflicts (overlaps) for
+ * any two given CPUs at this (non-NUMA) topology level.
+ */
+static bool topology_span_sane(struct sched_domain_topology_level *tl,
+			      const struct cpumask *cpu_map, int cpu)
+{
+	int i;
+
+	/* NUMA levels are allowed to overlap */
+	if (tl->flags & SDTL_OVERLAP)
+		return true;
+
+	/*
+	 * Non-NUMA levels cannot partially overlap - they must be either
+	 * completely equal or completely disjoint. Otherwise we can end up
+	 * breaking the sched_group lists - i.e. a later get_group() pass
+	 * breaks the linking done for an earlier span.
+	 */
+	for_each_cpu(i, cpu_map) {
+		if (i == cpu)
+			continue;
+		/*
+		 * We should 'and' all those masks with 'cpu_map' to exactly
+		 * match the topology we're about to build, but that can only
+		 * remove CPUs, which only lessens our ability to detect
+		 * overlaps
+		 */
+		if (!cpumask_equal(tl->mask(cpu), tl->mask(i)) &&
+		    cpumask_intersects(tl->mask(cpu), tl->mask(i)))
+			return false;
+	}
+
+	return true;
+}
+
+/*
  * Find the sched_domain_topology_level where all CPU capacities are visible
  * for all CPUs.
  */
@@ -1967,6 +2003,9 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 				has_asym = true;
 			}
 
+			if (WARN_ON(!topology_span_sane(tl, cpu_map, i)))
+				goto error;
+
 			sd = build_sched_domain(tl, cpu_map, attr, sd, dflags, i);
 
 			if (tl == sched_domain_topology)
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 811b4a86cdf6..e914d72b3290 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -42,6 +42,14 @@
 #include <linux/uaccess.h>
 #include <linux/anon_inodes.h>
 
+/*
+ * When SECCOMP_IOCTL_NOTIF_ID_VALID was first introduced, it had the
+ * wrong direction flag in the ioctl number. This is the broken one,
+ * which the kernel needs to keep supporting until all userspaces stop
+ * using the wrong command number.
+ */
+#define SECCOMP_IOCTL_NOTIF_ID_VALID_WRONG_DIR	SECCOMP_IOR(2, __u64)
+
 enum notify_state {
 	SECCOMP_NOTIFY_INIT,
 	SECCOMP_NOTIFY_SENT,
@@ -1161,6 +1169,7 @@ static long seccomp_notify_ioctl(struct file *file, unsigned int cmd,
 		return seccomp_notify_recv(filter, buf);
 	case SECCOMP_IOCTL_NOTIF_SEND:
 		return seccomp_notify_send(filter, buf);
+	case SECCOMP_IOCTL_NOTIF_ID_VALID_WRONG_DIR:
 	case SECCOMP_IOCTL_NOTIF_ID_VALID:
 		return seccomp_notify_id_valid(filter, buf);
 	default:
@@ -1198,6 +1207,7 @@ static const struct file_operations seccomp_notify_ops = {
 	.poll = seccomp_notify_poll,
 	.release = seccomp_notify_release,
 	.unlocked_ioctl = seccomp_notify_ioctl,
+	.compat_ioctl = seccomp_notify_ioctl,
 };
 
 static struct file *init_listener(struct seccomp_filter *filter)
diff --git a/kernel/signal.c b/kernel/signal.c
index adb0d3b460f5..00448edd0282 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -408,27 +408,32 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi
 {
 	struct sigqueue *q = NULL;
 	struct user_struct *user;
+	int sigpending;
 
 	/*
 	 * Protect access to @t credentials. This can go away when all
 	 * callers hold rcu read lock.
+	 *
+	 * NOTE! A pending signal will hold on to the user refcount,
+	 * and we get/put the refcount only when the sigpending count
+	 * changes from/to zero.
 	 */
 	rcu_read_lock();
-	user = get_uid(__task_cred(t)->user);
-	atomic_inc(&user->sigpending);
+	user = __task_cred(t)->user;
+	sigpending = atomic_inc_return(&user->sigpending);
+	if (sigpending == 1)
+		get_uid(user);
 	rcu_read_unlock();
 
-	if (override_rlimit ||
-	    atomic_read(&user->sigpending) <=
-			task_rlimit(t, RLIMIT_SIGPENDING)) {
+	if (override_rlimit || likely(sigpending <= task_rlimit(t, RLIMIT_SIGPENDING))) {
 		q = kmem_cache_alloc(sigqueue_cachep, flags);
 	} else {
 		print_dropped_signal(sig);
 	}
 
 	if (unlikely(q == NULL)) {
-		atomic_dec(&user->sigpending);
-		free_uid(user);
+		if (atomic_dec_and_test(&user->sigpending))
+			free_uid(user);
 	} else {
 		INIT_LIST_HEAD(&q->list);
 		q->flags = 0;
@@ -442,8 +447,8 @@ static void __sigqueue_free(struct sigqueue *q)
 {
 	if (q->flags & SIGQUEUE_PREALLOC)
 		return;
-	atomic_dec(&q->user->sigpending);
-	free_uid(q->user);
+	if (atomic_dec_and_test(&q->user->sigpending))
+		free_uid(q->user);
 	kmem_cache_free(sigqueue_cachep, q);
 }
 
@@ -1486,15 +1491,15 @@ int kill_pid_usb_asyncio(int sig, int errno, sigval_t addr,
 	unsigned long flags;
 	int ret = -EINVAL;
 
+	if (!valid_signal(sig))
+		return ret;
+
 	clear_siginfo(&info);
 	info.si_signo = sig;
 	info.si_errno = errno;
 	info.si_code = SI_ASYNCIO;
 	*((sigval_t *)&info.si_pid) = addr;
 
-	if (!valid_signal(sig))
-		return ret;
-
 	rcu_read_lock();
 	p = pid_task(pid, PIDTYPE_PID);
 	if (!p) {
@@ -1876,7 +1881,7 @@ bool do_notify_parent(struct task_struct *tsk, int sig)
 		 * This is only possible if parent == real_parent.
 		 * Check if it has changed security domain.
 		 */
-		if (tsk->parent_exec_id != tsk->parent->self_exec_id)
+		if (tsk->parent_exec_id != READ_ONCE(tsk->parent->self_exec_id))
 			sig = SIGCHLD;
 	}
 
@@ -1938,8 +1943,12 @@ bool do_notify_parent(struct task_struct *tsk, int sig)
 		if (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN)
 			sig = 0;
 	}
+	/*
+	 * Send with __send_signal as si_pid and si_uid are in the
+	 * parent's namespaces.
+	 */
 	if (valid_signal(sig) && sig)
-		__group_send_sig_info(sig, &info, tsk->parent);
+		__send_signal(sig, &info, tsk->parent, PIDTYPE_TGID, false);
 	__wake_up_parent(tsk, tsk->parent);
 	spin_unlock_irqrestore(&psig->siglock, flags);
 
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 13a0f2e6ebc2..e2ac0e37c4ae 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -554,25 +554,33 @@ static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
 static struct taskstats *taskstats_tgid_alloc(struct task_struct *tsk)
 {
 	struct signal_struct *sig = tsk->signal;
-	struct taskstats *stats;
+	struct taskstats *stats_new, *stats;
 
-	if (sig->stats || thread_group_empty(tsk))
-		goto ret;
+	/* Pairs with smp_store_release() below. */
+	stats = smp_load_acquire(&sig->stats);
+	if (stats || thread_group_empty(tsk))
+		return stats;
 
 	/* No problem if kmem_cache_zalloc() fails */
-	stats = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL);
+	stats_new = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL);
 
 	spin_lock_irq(&tsk->sighand->siglock);
-	if (!sig->stats) {
-		sig->stats = stats;
-		stats = NULL;
+	stats = sig->stats;
+	if (!stats) {
+		/*
+		 * Pairs with smp_store_release() above and order the
+		 * kmem_cache_zalloc().
+		 */
+		smp_store_release(&sig->stats, stats_new);
+		stats = stats_new;
+		stats_new = NULL;
 	}
 	spin_unlock_irq(&tsk->sighand->siglock);
 
-	if (stats)
-		kmem_cache_free(taskstats_cache, stats);
-ret:
-	return sig->stats;
+	if (stats_new)
+		kmem_cache_free(taskstats_cache, stats_new);
+
+	return stats;
 }
 
 /* Send pid data out on exit */
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index bfe0e0656f02..15f20dd30bd8 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -88,6 +88,8 @@ static int alarmtimer_rtc_add_device(struct device *dev,
 	unsigned long flags;
 	struct rtc_device *rtc = to_rtc_device(dev);
 	struct wakeup_source *__ws;
+	struct platform_device *pdev;
+	int ret = 0;
 
 	if (rtcdev)
 		return -EBUSY;
@@ -98,12 +100,14 @@ static int alarmtimer_rtc_add_device(struct device *dev,
 		return -1;
 
 	__ws = wakeup_source_register("alarmtimer");
+	pdev = platform_device_register_data(dev, "alarmtimer",
+					     PLATFORM_DEVID_AUTO, NULL, 0);
 
 	spin_lock_irqsave(&rtcdev_lock, flags);
-	if (!rtcdev) {
+	if (__ws && !IS_ERR(pdev) && !rtcdev) {
 		if (!try_module_get(rtc->owner)) {
-			spin_unlock_irqrestore(&rtcdev_lock, flags);
-			return -1;
+			ret = -1;
+			goto unlock;
 		}
 
 		rtcdev = rtc;
@@ -111,12 +115,17 @@ static int alarmtimer_rtc_add_device(struct device *dev,
 		get_device(dev);
 		ws = __ws;
 		__ws = NULL;
+		pdev = NULL;
+	} else {
+		ret = -1;
 	}
+unlock:
 	spin_unlock_irqrestore(&rtcdev_lock, flags);
 
+	platform_device_unregister(pdev);
 	wakeup_source_unregister(__ws);
 
-	return 0;
+	return ret;
 }
 
 static inline void alarmtimer_rtc_timer_init(void)
@@ -861,8 +870,7 @@ static struct platform_driver alarmtimer_driver = {
  */
 static int __init alarmtimer_init(void)
 {
-	struct platform_device *pdev;
-	int error = 0;
+	int error;
 	int i;
 
 	alarmtimer_rtc_timer_init();
@@ -885,15 +893,7 @@ static int __init alarmtimer_init(void)
 	if (error)
 		goto out_if;
 
-	pdev = platform_device_register_simple("alarmtimer", -1, NULL, 0);
-	if (IS_ERR(pdev)) {
-		error = PTR_ERR(pdev);
-		goto out_drv;
-	}
 	return 0;
-
-out_drv:
-	platform_driver_unregister(&alarmtimer_driver);
 out_if:
 	alarmtimer_rtc_interface_remove();
 	return error;
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 3bcc19ceb073..cf74160e79c7 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -293,8 +293,15 @@ static void clocksource_watchdog(struct timer_list *unused)
 	next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask);
 	if (next_cpu >= nr_cpu_ids)
 		next_cpu = cpumask_first(cpu_online_mask);
-	watchdog_timer.expires += WATCHDOG_INTERVAL;
-	add_timer_on(&watchdog_timer, next_cpu);
+
+	/*
+	 * Arm timer if not already pending: could race with concurrent
+	 * pair clocksource_stop_watchdog() clocksource_start_watchdog().
+	 */
+	if (!timer_pending(&watchdog_timer)) {
+		watchdog_timer.expires += WATCHDOG_INTERVAL;
+		add_timer_on(&watchdog_timer, next_cpu);
+	}
 out:
 	spin_unlock(&watchdog_lock);
 }
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index 142b07619918..3f16750ec7a3 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -205,7 +205,8 @@ sched_clock_register(u64 (*read)(void), int bits, unsigned long rate)
 
 	if (sched_clock_timer.function != NULL) {
 		/* update timeout for clock wrap */
-		hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
+		hrtimer_start(&sched_clock_timer, cd.wrap_kt,
+			      HRTIMER_MODE_REL_HARD);
 	}
 
 	r = rate;
@@ -249,9 +250,9 @@ void __init generic_sched_clock_init(void)
 	 * Start the timer to keep sched_clock() properly updated and
 	 * sets the initial epoch.
 	 */
-	hrtimer_init(&sched_clock_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer_init(&sched_clock_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 	sched_clock_timer.function = sched_clock_poll;
-	hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
+	hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL_HARD);
 }
 
 /*
@@ -288,7 +289,7 @@ void sched_clock_resume(void)
 	struct clock_read_data *rd = &cd.read_data[0];
 
 	rd->epoch_cyc = cd.actual_read_sched_clock();
-	hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
+	hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL_HARD);
 	rd->read_sched_clock = cd.actual_read_sched_clock;
 }
 
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index f4ee1a3428ae..e59a34f23aa2 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -58,8 +58,9 @@ static void tick_do_update_jiffies64(ktime_t now)
 
 	/*
 	 * Do a quick check without holding jiffies_lock:
+	 * The READ_ONCE() pairs with two updates done later in this function.
 	 */
-	delta = ktime_sub(now, last_jiffies_update);
+	delta = ktime_sub(now, READ_ONCE(last_jiffies_update));
 	if (delta < tick_period)
 		return;
 
@@ -70,8 +71,9 @@ static void tick_do_update_jiffies64(ktime_t now)
 	if (delta >= tick_period) {
 
 		delta = ktime_sub(delta, tick_period);
-		last_jiffies_update = ktime_add(last_jiffies_update,
-						tick_period);
+		/* Pairs with the lockless read in this function. */
+		WRITE_ONCE(last_jiffies_update,
+			   ktime_add(last_jiffies_update, tick_period));
 
 		/* Slow path for long timeouts */
 		if (unlikely(delta >= tick_period)) {
@@ -79,8 +81,10 @@ static void tick_do_update_jiffies64(ktime_t now)
 
 			ticks = ktime_divns(delta, incr);
 
-			last_jiffies_update = ktime_add_ns(last_jiffies_update,
-							   incr * ticks);
+			/* Pairs with the lockless read in this function. */
+			WRITE_ONCE(last_jiffies_update,
+				   ktime_add_ns(last_jiffies_update,
+						incr * ticks));
 		}
 		do_timer(++ticks);
 
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 44b726bab4bd..d911c8470149 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -819,7 +819,7 @@ ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs)
 
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
-	return base + nsecs;
+	return ktime_add_ns(base, nsecs);
 }
 EXPORT_SYMBOL_GPL(ktime_get_coarse_with_offset);
 
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 7d63b7347066..e70451eb2495 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -43,6 +43,7 @@
 #include <linux/sched/debug.h>
 #include <linux/slab.h>
 #include <linux/compat.h>
+#include <linux/random.h>
 
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
@@ -518,8 +519,8 @@ static int calc_wheel_index(unsigned long expires, unsigned long clk)
 		 * Force expire obscene large timeouts to expire at the
 		 * capacity limit of the wheel.
 		 */
-		if (expires >= WHEEL_TIMEOUT_CUTOFF)
-			expires = WHEEL_TIMEOUT_MAX;
+		if (delta >= WHEEL_TIMEOUT_CUTOFF)
+			expires = clk + WHEEL_TIMEOUT_MAX;
 
 		idx = calc_index(expires, LVL_DEPTH - 1);
 	}
@@ -581,7 +582,15 @@ trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer)
 	 * Set the next expiry time and kick the CPU so it can reevaluate the
 	 * wheel:
 	 */
-	base->next_expiry = timer->expires;
+	if (time_before(timer->expires, base->clk)) {
+		/*
+		 * Prevent from forward_timer_base() moving the base->clk
+		 * backward
+		 */
+		base->next_expiry = base->clk;
+	} else {
+		base->next_expiry = timer->expires;
+	}
 	wake_up_nohz_cpu(base->cpu);
 }
 
@@ -893,10 +902,13 @@ static inline void forward_timer_base(struct timer_base *base)
 	 * If the next expiry value is > jiffies, then we fast forward to
 	 * jiffies otherwise we forward to the next expiry value.
 	 */
-	if (time_after(base->next_expiry, jnow))
+	if (time_after(base->next_expiry, jnow)) {
 		base->clk = jnow;
-	else
+	} else {
+		if (WARN_ON_ONCE(time_before(base->next_expiry, base->clk)))
+			return;
 		base->clk = base->next_expiry;
+	}
 #endif
 }
 
@@ -1646,6 +1658,13 @@ void update_process_times(int user_tick)
 	scheduler_tick();
 	if (IS_ENABLED(CONFIG_POSIX_TIMERS))
 		run_posix_cpu_timers(p);
+
+	/* The current CPU might make use of net randoms without receiving IRQs
+	 * to renew them often enough. Let's update the net_rand_state from a
+	 * non-constant value that's not affine to the number of calls to make
+	 * sure it's updated when there's some activity (we don't care in idle).
+	 */
+	this_cpu_add(net_rand_state.s1, rol32(jiffies, 24) + user_tick);
 }
 
 /**
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 564e5fdb025f..9669aaf0cd76 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -371,7 +371,6 @@ config PROFILE_ANNOTATED_BRANCHES
 config PROFILE_ALL_BRANCHES
 	bool "Profile all if conditionals" if !FORTIFY_SOURCE
 	select TRACE_BRANCH_PROFILING
-	imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED  # avoid false positives
 	help
 	  This tracer profiles all branch conditions. Every if ()
 	  taken in the kernel is recorded whether it hit or miss.
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index e1c6d79fb4cc..8f18311f9be5 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -3,6 +3,9 @@
  * Copyright (C) 2006 Jens Axboe <axboe@kernel.dk>
  *
  */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/blkdev.h>
 #include <linux/blktrace_api.h>
@@ -336,6 +339,7 @@ static void put_probe_ref(void)
 
 static void blk_trace_cleanup(struct blk_trace *bt)
 {
+	synchronize_rcu();
 	blk_trace_free(bt);
 	put_probe_ref();
 }
@@ -344,7 +348,8 @@ static int __blk_trace_remove(struct request_queue *q)
 {
 	struct blk_trace *bt;
 
-	bt = xchg(&q->blk_trace, NULL);
+	bt = rcu_replace_pointer(q->blk_trace, NULL,
+				 lockdep_is_held(&q->blk_trace_mutex));
 	if (!bt)
 		return -EINVAL;
 
@@ -479,6 +484,8 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	struct dentry *dir = NULL;
 	int ret;
 
+	lockdep_assert_held(&q->blk_trace_mutex);
+
 	if (!buts->buf_size || !buts->buf_nr)
 		return -EINVAL;
 
@@ -494,6 +501,17 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	 */
 	strreplace(buts->name, '/', '_');
 
+	/*
+	 * bdev can be NULL, as with scsi-generic, this is a helpful as
+	 * we can be.
+	 */
+	if (rcu_dereference_protected(q->blk_trace,
+				      lockdep_is_held(&q->blk_trace_mutex))) {
+		pr_warn("Concurrent blktraces are not allowed on %s\n",
+			buts->name);
+		return -EBUSY;
+	}
+
 	bt = kzalloc(sizeof(*bt), GFP_KERNEL);
 	if (!bt)
 		return -ENOMEM;
@@ -507,13 +525,31 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	if (!bt->msg_data)
 		goto err;
 
-	ret = -ENOENT;
-
-	dir = debugfs_lookup(buts->name, blk_debugfs_root);
-	if (!dir)
+#ifdef CONFIG_BLK_DEBUG_FS
+	/*
+	 * When tracing whole make_request drivers (multiqueue) block devices,
+	 * reuse the existing debugfs directory created by the block layer on
+	 * init. For request-based block devices, all partitions block devices,
+	 * and scsi-generic block devices we create a temporary new debugfs
+	 * directory that will be removed once the trace ends.
+	 */
+	if (queue_is_mq(q) && bdev && bdev == bdev->bd_contains)
+		dir = q->debugfs_dir;
+	else
+#endif
 		bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root);
-	if (!dir)
+
+	/*
+	 * As blktrace relies on debugfs for its interface the debugfs directory
+	 * is required, contrary to the usual mantra of not checking for debugfs
+	 * files or directories.
+	 */
+	if (IS_ERR_OR_NULL(dir)) {
+		pr_warn("debugfs_dir not present for %s so skipping\n",
+			buts->name);
+		ret = -ENOENT;
 		goto err;
+	}
 
 	bt->dev = dev;
 	atomic_set(&bt->dropped, 0);
@@ -522,12 +558,8 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	ret = -EIO;
 	bt->dropped_file = debugfs_create_file("dropped", 0444, dir, bt,
 					       &blk_dropped_fops);
-	if (!bt->dropped_file)
-		goto err;
 
 	bt->msg_file = debugfs_create_file("msg", 0222, dir, bt, &blk_msg_fops);
-	if (!bt->msg_file)
-		goto err;
 
 	bt->rchan = relay_open("trace", dir, buts->buf_size,
 				buts->buf_nr, &blk_relay_callbacks, bt);
@@ -549,16 +581,11 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	bt->pid = buts->pid;
 	bt->trace_state = Blktrace_setup;
 
-	ret = -EBUSY;
-	if (cmpxchg(&q->blk_trace, NULL, bt))
-		goto err;
-
+	rcu_assign_pointer(q->blk_trace, bt);
 	get_probe_ref();
 
 	ret = 0;
 err:
-	if (dir && !bt->dir)
-		dput(dir);
 	if (ret)
 		blk_trace_free(bt);
 	return ret;
@@ -636,8 +663,10 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name,
 static int __blk_trace_startstop(struct request_queue *q, int start)
 {
 	int ret;
-	struct blk_trace *bt = q->blk_trace;
+	struct blk_trace *bt;
 
+	bt = rcu_dereference_protected(q->blk_trace,
+				       lockdep_is_held(&q->blk_trace_mutex));
 	if (bt == NULL)
 		return -EINVAL;
 
@@ -747,8 +776,8 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 void blk_trace_shutdown(struct request_queue *q)
 {
 	mutex_lock(&q->blk_trace_mutex);
-
-	if (q->blk_trace) {
+	if (rcu_dereference_protected(q->blk_trace,
+				      lockdep_is_held(&q->blk_trace_mutex))) {
 		__blk_trace_startstop(q, 0);
 		__blk_trace_remove(q);
 	}
@@ -760,8 +789,10 @@ void blk_trace_shutdown(struct request_queue *q)
 static union kernfs_node_id *
 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio)
 {
-	struct blk_trace *bt = q->blk_trace;
+	struct blk_trace *bt;
 
+	/* We don't use the 'bt' value here except as an optimization... */
+	bt = rcu_dereference_protected(q->blk_trace, 1);
 	if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP))
 		return NULL;
 
@@ -806,10 +837,14 @@ static void blk_add_trace_rq(struct request *rq, int error,
 			     unsigned int nr_bytes, u32 what,
 			     union kernfs_node_id *cgid)
 {
-	struct blk_trace *bt = rq->q->blk_trace;
+	struct blk_trace *bt;
 
-	if (likely(!bt))
+	rcu_read_lock();
+	bt = rcu_dereference(rq->q->blk_trace);
+	if (likely(!bt)) {
+		rcu_read_unlock();
 		return;
+	}
 
 	if (blk_rq_is_passthrough(rq))
 		what |= BLK_TC_ACT(BLK_TC_PC);
@@ -818,6 +853,7 @@ static void blk_add_trace_rq(struct request *rq, int error,
 
 	__blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq),
 			rq->cmd_flags, what, error, 0, NULL, cgid);
+	rcu_read_unlock();
 }
 
 static void blk_add_trace_rq_insert(void *ignore,
@@ -863,14 +899,19 @@ static void blk_add_trace_rq_complete(void *ignore, struct request *rq,
 static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
 			      u32 what, int error)
 {
-	struct blk_trace *bt = q->blk_trace;
+	struct blk_trace *bt;
 
-	if (likely(!bt))
+	rcu_read_lock();
+	bt = rcu_dereference(q->blk_trace);
+	if (likely(!bt)) {
+		rcu_read_unlock();
 		return;
+	}
 
 	__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
 			bio_op(bio), bio->bi_opf, what, error, 0, NULL,
 			blk_trace_bio_get_cgid(q, bio));
+	rcu_read_unlock();
 }
 
 static void blk_add_trace_bio_bounce(void *ignore,
@@ -915,11 +956,14 @@ static void blk_add_trace_getrq(void *ignore,
 	if (bio)
 		blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0);
 	else {
-		struct blk_trace *bt = q->blk_trace;
+		struct blk_trace *bt;
 
+		rcu_read_lock();
+		bt = rcu_dereference(q->blk_trace);
 		if (bt)
 			__blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_GETRQ, 0, 0,
 					NULL, NULL);
+		rcu_read_unlock();
 	}
 }
 
@@ -931,27 +975,35 @@ static void blk_add_trace_sleeprq(void *ignore,
 	if (bio)
 		blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0);
 	else {
-		struct blk_trace *bt = q->blk_trace;
+		struct blk_trace *bt;
 
+		rcu_read_lock();
+		bt = rcu_dereference(q->blk_trace);
 		if (bt)
 			__blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_SLEEPRQ,
 					0, 0, NULL, NULL);
+		rcu_read_unlock();
 	}
 }
 
 static void blk_add_trace_plug(void *ignore, struct request_queue *q)
 {
-	struct blk_trace *bt = q->blk_trace;
+	struct blk_trace *bt;
 
+	rcu_read_lock();
+	bt = rcu_dereference(q->blk_trace);
 	if (bt)
 		__blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, NULL);
+	rcu_read_unlock();
 }
 
 static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
 				    unsigned int depth, bool explicit)
 {
-	struct blk_trace *bt = q->blk_trace;
+	struct blk_trace *bt;
 
+	rcu_read_lock();
+	bt = rcu_dereference(q->blk_trace);
 	if (bt) {
 		__be64 rpdu = cpu_to_be64(depth);
 		u32 what;
@@ -963,22 +1015,28 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
 
 		__blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, NULL);
 	}
+	rcu_read_unlock();
 }
 
 static void blk_add_trace_split(void *ignore,
 				struct request_queue *q, struct bio *bio,
 				unsigned int pdu)
 {
-	struct blk_trace *bt = q->blk_trace;
+	struct blk_trace *bt;
 
+	rcu_read_lock();
+	bt = rcu_dereference(q->blk_trace);
 	if (bt) {
 		__be64 rpdu = cpu_to_be64(pdu);
 
 		__blk_add_trace(bt, bio->bi_iter.bi_sector,
 				bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf,
-				BLK_TA_SPLIT, bio->bi_status, sizeof(rpdu),
-				&rpdu, blk_trace_bio_get_cgid(q, bio));
+				BLK_TA_SPLIT,
+				blk_status_to_errno(bio->bi_status),
+				sizeof(rpdu), &rpdu,
+				blk_trace_bio_get_cgid(q, bio));
 	}
+	rcu_read_unlock();
 }
 
 /**
@@ -998,19 +1056,25 @@ static void blk_add_trace_bio_remap(void *ignore,
 				    struct request_queue *q, struct bio *bio,
 				    dev_t dev, sector_t from)
 {
-	struct blk_trace *bt = q->blk_trace;
+	struct blk_trace *bt;
 	struct blk_io_trace_remap r;
 
-	if (likely(!bt))
+	rcu_read_lock();
+	bt = rcu_dereference(q->blk_trace);
+	if (likely(!bt)) {
+		rcu_read_unlock();
 		return;
+	}
 
 	r.device_from = cpu_to_be32(dev);
 	r.device_to   = cpu_to_be32(bio_dev(bio));
 	r.sector_from = cpu_to_be64(from);
 
 	__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
-			bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_status,
+			bio_op(bio), bio->bi_opf, BLK_TA_REMAP,
+			blk_status_to_errno(bio->bi_status),
 			sizeof(r), &r, blk_trace_bio_get_cgid(q, bio));
+	rcu_read_unlock();
 }
 
 /**
@@ -1031,11 +1095,15 @@ static void blk_add_trace_rq_remap(void *ignore,
 				   struct request *rq, dev_t dev,
 				   sector_t from)
 {
-	struct blk_trace *bt = q->blk_trace;
+	struct blk_trace *bt;
 	struct blk_io_trace_remap r;
 
-	if (likely(!bt))
+	rcu_read_lock();
+	bt = rcu_dereference(q->blk_trace);
+	if (likely(!bt)) {
+		rcu_read_unlock();
 		return;
+	}
 
 	r.device_from = cpu_to_be32(dev);
 	r.device_to   = cpu_to_be32(disk_devt(rq->rq_disk));
@@ -1044,6 +1112,7 @@ static void blk_add_trace_rq_remap(void *ignore,
 	__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
 			rq_data_dir(rq), 0, BLK_TA_REMAP, 0,
 			sizeof(r), &r, blk_trace_request_get_cgid(q, rq));
+	rcu_read_unlock();
 }
 
 /**
@@ -1061,14 +1130,19 @@ void blk_add_driver_data(struct request_queue *q,
 			 struct request *rq,
 			 void *data, size_t len)
 {
-	struct blk_trace *bt = q->blk_trace;
+	struct blk_trace *bt;
 
-	if (likely(!bt))
+	rcu_read_lock();
+	bt = rcu_dereference(q->blk_trace);
+	if (likely(!bt)) {
+		rcu_read_unlock();
 		return;
+	}
 
 	__blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0,
 				BLK_TA_DRV_DATA, 0, len, data,
 				blk_trace_request_get_cgid(q, rq));
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(blk_add_driver_data);
 
@@ -1220,21 +1294,10 @@ static inline __u16 t_error(const struct trace_entry *ent)
 
 static __u64 get_pdu_int(const struct trace_entry *ent, bool has_cg)
 {
-	const __u64 *val = pdu_start(ent, has_cg);
+	const __be64 *val = pdu_start(ent, has_cg);
 	return be64_to_cpu(*val);
 }
 
-static void get_pdu_remap(const struct trace_entry *ent,
-			  struct blk_io_trace_remap *r, bool has_cg)
-{
-	const struct blk_io_trace_remap *__r = pdu_start(ent, has_cg);
-	__u64 sector_from = __r->sector_from;
-
-	r->device_from = be32_to_cpu(__r->device_from);
-	r->device_to   = be32_to_cpu(__r->device_to);
-	r->sector_from = be64_to_cpu(sector_from);
-}
-
 typedef void (blk_log_action_t) (struct trace_iterator *iter, const char *act,
 	bool has_cg);
 
@@ -1360,13 +1423,13 @@ static void blk_log_with_error(struct trace_seq *s,
 
 static void blk_log_remap(struct trace_seq *s, const struct trace_entry *ent, bool has_cg)
 {
-	struct blk_io_trace_remap r = { .device_from = 0, };
+	const struct blk_io_trace_remap *__r = pdu_start(ent, has_cg);
 
-	get_pdu_remap(ent, &r, has_cg);
 	trace_seq_printf(s, "%llu + %u <- (%d,%d) %llu\n",
 			 t_sector(ent), t_sec(ent),
-			 MAJOR(r.device_from), MINOR(r.device_from),
-			 (unsigned long long)r.sector_from);
+			 MAJOR(be32_to_cpu(__r->device_from)),
+			 MINOR(be32_to_cpu(__r->device_from)),
+			 be64_to_cpu(__r->sector_from));
 }
 
 static void blk_log_plug(struct trace_seq *s, const struct trace_entry *ent, bool has_cg)
@@ -1590,11 +1653,13 @@ static int blk_trace_remove_queue(struct request_queue *q)
 {
 	struct blk_trace *bt;
 
-	bt = xchg(&q->blk_trace, NULL);
+	bt = rcu_replace_pointer(q->blk_trace, NULL,
+				 lockdep_is_held(&q->blk_trace_mutex));
 	if (bt == NULL)
 		return -EINVAL;
 
 	put_probe_ref();
+	synchronize_rcu();
 	blk_trace_free(bt);
 	return 0;
 }
@@ -1621,10 +1686,7 @@ static int blk_trace_setup_queue(struct request_queue *q,
 
 	blk_trace_setup_lba(bt, bdev);
 
-	ret = -EBUSY;
-	if (cmpxchg(&q->blk_trace, NULL, bt))
-		goto free_bt;
-
+	rcu_assign_pointer(q->blk_trace, bt);
 	get_probe_ref();
 	return 0;
 
@@ -1756,6 +1818,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 	struct hd_struct *p = dev_to_part(dev);
 	struct request_queue *q;
 	struct block_device *bdev;
+	struct blk_trace *bt;
 	ssize_t ret = -ENXIO;
 
 	bdev = bdget(part_devt(p));
@@ -1768,21 +1831,23 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 
 	mutex_lock(&q->blk_trace_mutex);
 
+	bt = rcu_dereference_protected(q->blk_trace,
+				       lockdep_is_held(&q->blk_trace_mutex));
 	if (attr == &dev_attr_enable) {
-		ret = sprintf(buf, "%u\n", !!q->blk_trace);
+		ret = sprintf(buf, "%u\n", !!bt);
 		goto out_unlock_bdev;
 	}
 
-	if (q->blk_trace == NULL)
+	if (bt == NULL)
 		ret = sprintf(buf, "disabled\n");
 	else if (attr == &dev_attr_act_mask)
-		ret = blk_trace_mask2str(buf, q->blk_trace->act_mask);
+		ret = blk_trace_mask2str(buf, bt->act_mask);
 	else if (attr == &dev_attr_pid)
-		ret = sprintf(buf, "%u\n", q->blk_trace->pid);
+		ret = sprintf(buf, "%u\n", bt->pid);
 	else if (attr == &dev_attr_start_lba)
-		ret = sprintf(buf, "%llu\n", q->blk_trace->start_lba);
+		ret = sprintf(buf, "%llu\n", bt->start_lba);
 	else if (attr == &dev_attr_end_lba)
-		ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba);
+		ret = sprintf(buf, "%llu\n", bt->end_lba);
 
 out_unlock_bdev:
 	mutex_unlock(&q->blk_trace_mutex);
@@ -1799,6 +1864,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 	struct block_device *bdev;
 	struct request_queue *q;
 	struct hd_struct *p;
+	struct blk_trace *bt;
 	u64 value;
 	ssize_t ret = -EINVAL;
 
@@ -1829,8 +1895,10 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 
 	mutex_lock(&q->blk_trace_mutex);
 
+	bt = rcu_dereference_protected(q->blk_trace,
+				       lockdep_is_held(&q->blk_trace_mutex));
 	if (attr == &dev_attr_enable) {
-		if (!!value == !!q->blk_trace) {
+		if (!!value == !!bt) {
 			ret = 0;
 			goto out_unlock_bdev;
 		}
@@ -1842,18 +1910,21 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 	}
 
 	ret = 0;
-	if (q->blk_trace == NULL)
+	if (bt == NULL) {
 		ret = blk_trace_setup_queue(q, bdev);
+		bt = rcu_dereference_protected(q->blk_trace,
+				lockdep_is_held(&q->blk_trace_mutex));
+	}
 
 	if (ret == 0) {
 		if (attr == &dev_attr_act_mask)
-			q->blk_trace->act_mask = value;
+			bt->act_mask = value;
 		else if (attr == &dev_attr_pid)
-			q->blk_trace->pid = value;
+			bt->pid = value;
 		else if (attr == &dev_attr_start_lba)
-			q->blk_trace->start_lba = value;
+			bt->start_lba = value;
 		else if (attr == &dev_attr_end_lba)
-			q->blk_trace->end_lba = value;
+			bt->end_lba = value;
 	}
 
 out_unlock_bdev:
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index aaf66cd9daa6..a2c30e1eb7e4 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -155,7 +155,7 @@ static const struct bpf_func_proto bpf_probe_read_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
-BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src,
+BPF_CALL_3(bpf_probe_write_user, void __user *, unsafe_ptr, const void *, src,
 	   u32, size)
 {
 	/*
@@ -178,10 +178,8 @@ BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src,
 		return -EPERM;
 	if (unlikely(!nmi_uaccess_okay()))
 		return -EPERM;
-	if (!access_ok(unsafe_ptr, size))
-		return -EPERM;
 
-	return probe_kernel_write(unsafe_ptr, src, size);
+	return probe_user_write(unsafe_ptr, src, size);
 }
 
 static const struct bpf_func_proto bpf_probe_write_user_proto = {
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index baa54a76c6aa..98751023c05a 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -523,8 +523,7 @@ static int function_stat_show(struct seq_file *m, void *v)
 	}
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	avg = rec->time;
-	do_div(avg, rec->counter);
+	avg = div64_ul(rec->time, rec->counter);
 	if (tracing_thresh && (avg < tracing_thresh))
 		goto out;
 #endif
@@ -550,7 +549,8 @@ static int function_stat_show(struct seq_file *m, void *v)
 		 * Divide only 1000 for ns^2 -> us^2 conversion.
 		 * trace_print_graph_duration will divide 1000 again.
 		 */
-		do_div(stddev, rec->counter * (rec->counter - 1) * 1000);
+		stddev = div64_ul(stddev,
+				  rec->counter * (rec->counter - 1) * 1000);
 	}
 
 	trace_seq_init(&s);
@@ -5085,8 +5085,8 @@ static const struct file_operations ftrace_notrace_fops = {
 
 static DEFINE_MUTEX(graph_lock);
 
-struct ftrace_hash *ftrace_graph_hash = EMPTY_HASH;
-struct ftrace_hash *ftrace_graph_notrace_hash = EMPTY_HASH;
+struct ftrace_hash __rcu *ftrace_graph_hash = EMPTY_HASH;
+struct ftrace_hash __rcu *ftrace_graph_notrace_hash = EMPTY_HASH;
 
 enum graph_filter_type {
 	GRAPH_FILTER_NOTRACE	= 0,
@@ -5357,8 +5357,15 @@ ftrace_graph_release(struct inode *inode, struct file *file)
 
 		mutex_unlock(&graph_lock);
 
-		/* Wait till all users are no longer using the old hash */
-		synchronize_rcu();
+		/*
+		 * We need to do a hard force of sched synchronization.
+		 * This is because we use preempt_disable() to do RCU, but
+		 * the function tracers can be called where RCU is not watching
+		 * (like before user_exit()). We can not rely on the RCU
+		 * infrastructure to do the synchronization, thus we must do it
+		 * ourselves.
+		 */
+		schedule_on_each_cpu(ftrace_sync);
 
 		free_ftrace_hash(old_hash);
 	}
@@ -5671,8 +5678,11 @@ static int referenced_filters(struct dyn_ftrace *rec)
 	int cnt = 0;
 
 	for (ops = ftrace_ops_list; ops != &ftrace_list_end; ops = ops->next) {
-		if (ops_references_rec(ops, rec))
-		    cnt++;
+		if (ops_references_rec(ops, rec)) {
+			cnt++;
+			if (ops->flags & FTRACE_OPS_FL_SAVE_REGS)
+				rec->flags |= FTRACE_FL_REGS;
+		}
 	}
 
 	return cnt;
@@ -5849,8 +5859,8 @@ void ftrace_module_enable(struct module *mod)
 		if (ftrace_start_up)
 			cnt += referenced_filters(rec);
 
-		/* This clears FTRACE_FL_DISABLED */
-		rec->flags = cnt;
+		rec->flags &= ~FTRACE_FL_DISABLED;
+		rec->flags += cnt;
 
 		if (ftrace_start_up && cnt) {
 			int failed = __ftrace_replace_code(rec, 1);
@@ -6435,12 +6445,12 @@ void ftrace_pid_follow_fork(struct trace_array *tr, bool enable)
 	if (enable) {
 		register_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork,
 						  tr);
-		register_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit,
+		register_trace_sched_process_free(ftrace_pid_follow_sched_process_exit,
 						  tr);
 	} else {
 		unregister_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork,
 						    tr);
-		unregister_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit,
+		unregister_trace_sched_process_free(ftrace_pid_follow_sched_process_exit,
 						    tr);
 	}
 }
@@ -6513,9 +6523,10 @@ static void *fpid_next(struct seq_file *m, void *v, loff_t *pos)
 	struct trace_array *tr = m->private;
 	struct trace_pid_list *pid_list = rcu_dereference_sched(tr->function_pids);
 
-	if (v == FTRACE_NO_PIDS)
+	if (v == FTRACE_NO_PIDS) {
+		(*pos)++;
 		return NULL;
-
+	}
 	return trace_pid_next(pid_list, v, pos);
 }
 
diff --git a/kernel/trace/ftrace_internal.h b/kernel/trace/ftrace_internal.h
index 0515a2096f90..0456e0a3dab1 100644
--- a/kernel/trace/ftrace_internal.h
+++ b/kernel/trace/ftrace_internal.h
@@ -6,22 +6,22 @@
 
 /*
  * Traverse the ftrace_global_list, invoking all entries.  The reason that we
- * can use rcu_dereference_raw_notrace() is that elements removed from this list
+ * can use rcu_dereference_raw_check() is that elements removed from this list
  * are simply leaked, so there is no need to interact with a grace-period
- * mechanism.  The rcu_dereference_raw_notrace() calls are needed to handle
+ * mechanism.  The rcu_dereference_raw_check() calls are needed to handle
  * concurrent insertions into the ftrace_global_list.
  *
  * Silly Alpha and silly pointer-speculation compiler optimizations!
  */
 #define do_for_each_ftrace_op(op, list)			\
-	op = rcu_dereference_raw_notrace(list);			\
+	op = rcu_dereference_raw_check(list);			\
 	do
 
 /*
  * Optimized for just a single item in the list (as that is the normal case).
  */
 #define while_for_each_ftrace_op(op)				\
-	while (likely(op = rcu_dereference_raw_notrace((op)->next)) &&	\
+	while (likely(op = rcu_dereference_raw_check((op)->next)) &&	\
 	       unlikely((op) != &ftrace_list_end))
 
 extern struct ftrace_ops __rcu *ftrace_ops_list;
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 05b0b3139ebc..0e4af9941a23 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2366,7 +2366,7 @@ rb_update_event(struct ring_buffer_per_cpu *cpu_buffer,
 	if (unlikely(info->add_timestamp)) {
 		bool abs = ring_buffer_time_stamp_abs(cpu_buffer->buffer);
 
-		event = rb_add_time_stamp(event, info->delta, abs);
+		event = rb_add_time_stamp(event, abs ? info->delta : delta, abs);
 		length -= RB_LEN_TIME_EXTEND;
 		delta = 0;
 	}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 51a64fbd8bd0..c4c3daeba5c0 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1726,6 +1726,7 @@ static __init int init_trace_selftests(void)
 
 	pr_info("Running postponed tracer tests:\n");
 
+	tracing_selftest_running = true;
 	list_for_each_entry_safe(p, n, &postponed_selftests, list) {
 		/* This loop can take minutes when sanitizers are enabled, so
 		 * lets make sure we allow RCU processing.
@@ -1748,6 +1749,7 @@ static __init int init_trace_selftests(void)
 		list_del(&p->list);
 		kfree(p);
 	}
+	tracing_selftest_running = false;
 
  out:
 	mutex_unlock(&trace_types_lock);
@@ -2642,10 +2644,10 @@ static void ftrace_exports(struct ring_buffer_event *event)
 
 	preempt_disable_notrace();
 
-	export = rcu_dereference_raw_notrace(ftrace_exports_list);
+	export = rcu_dereference_raw_check(ftrace_exports_list);
 	while (export) {
 		trace_process_export(export, event);
-		export = rcu_dereference_raw_notrace(export->next);
+		export = rcu_dereference_raw_check(export->next);
 	}
 
 	preempt_enable_notrace();
@@ -4569,6 +4571,10 @@ int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set)
 
 int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
 {
+	if ((mask == TRACE_ITER_RECORD_TGID) ||
+	    (mask == TRACE_ITER_RECORD_CMD))
+		lockdep_assert_held(&event_mutex);
+
 	/* do nothing if flag is already set */
 	if (!!(tr->trace_flags & mask) == !!enabled)
 		return 0;
@@ -4636,6 +4642,7 @@ static int trace_set_options(struct trace_array *tr, char *option)
 
 	cmp += len;
 
+	mutex_lock(&event_mutex);
 	mutex_lock(&trace_types_lock);
 
 	ret = match_string(trace_options, -1, cmp);
@@ -4646,6 +4653,7 @@ static int trace_set_options(struct trace_array *tr, char *option)
 		ret = set_tracer_flag(tr, 1 << ret, !neg);
 
 	mutex_unlock(&trace_types_lock);
+	mutex_unlock(&event_mutex);
 
 	/*
 	 * If the first trailing whitespace is replaced with '\0' by strstrip,
@@ -7948,9 +7956,11 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt,
 	if (val != 0 && val != 1)
 		return -EINVAL;
 
+	mutex_lock(&event_mutex);
 	mutex_lock(&trace_types_lock);
 	ret = set_tracer_flag(tr, 1 << index, val);
 	mutex_unlock(&trace_types_lock);
+	mutex_unlock(&event_mutex);
 
 	if (ret < 0)
 		return ret;
@@ -8278,6 +8288,19 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
 	 */
 	allocate_snapshot = false;
 #endif
+
+	/*
+	 * Because of some magic with the way alloc_percpu() works on
+	 * x86_64, we need to synchronize the pgd of all the tables,
+	 * otherwise the trace events that happen in x86_64 page fault
+	 * handlers can't cope with accessing the chance that a
+	 * alloc_percpu()'d memory might be touched in the page fault trace
+	 * event. Oh, and we need to audit all other alloc_percpu() and vmalloc()
+	 * calls in tracing, because something might get triggered within a
+	 * page fault trace event!
+	 */
+	vmalloc_sync_mappings();
+
 	return 0;
 }
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 005f08629b8b..08088cafbb88 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -931,22 +931,31 @@ extern void __trace_graph_return(struct trace_array *tr,
 				 unsigned long flags, int pc);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-extern struct ftrace_hash *ftrace_graph_hash;
-extern struct ftrace_hash *ftrace_graph_notrace_hash;
+extern struct ftrace_hash __rcu *ftrace_graph_hash;
+extern struct ftrace_hash __rcu *ftrace_graph_notrace_hash;
 
 static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace)
 {
 	unsigned long addr = trace->func;
 	int ret = 0;
+	struct ftrace_hash *hash;
 
 	preempt_disable_notrace();
 
-	if (ftrace_hash_empty(ftrace_graph_hash)) {
+	/*
+	 * Have to open code "rcu_dereference_sched()" because the
+	 * function graph tracer can be called when RCU is not
+	 * "watching".
+	 * Protected with schedule_on_each_cpu(ftrace_sync)
+	 */
+	hash = rcu_dereference_protected(ftrace_graph_hash, !preemptible());
+
+	if (ftrace_hash_empty(hash)) {
 		ret = 1;
 		goto out;
 	}
 
-	if (ftrace_lookup_ip(ftrace_graph_hash, addr)) {
+	if (ftrace_lookup_ip(hash, addr)) {
 
 		/*
 		 * This needs to be cleared on the return functions
@@ -982,10 +991,20 @@ static inline void ftrace_graph_addr_finish(struct ftrace_graph_ret *trace)
 static inline int ftrace_graph_notrace_addr(unsigned long addr)
 {
 	int ret = 0;
+	struct ftrace_hash *notrace_hash;
 
 	preempt_disable_notrace();
 
-	if (ftrace_lookup_ip(ftrace_graph_notrace_hash, addr))
+	/*
+	 * Have to open code "rcu_dereference_sched()" because the
+	 * function graph tracer can be called when RCU is not
+	 * "watching".
+	 * Protected with schedule_on_each_cpu(ftrace_sync)
+	 */
+	notrace_hash = rcu_dereference_protected(ftrace_graph_notrace_hash,
+						 !preemptible());
+
+	if (ftrace_lookup_ip(notrace_hash, addr))
 		ret = 1;
 
 	preempt_enable_notrace();
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 0ce3db67f556..42d4afd2fc4f 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -327,7 +327,8 @@ void trace_event_enable_cmd_record(bool enable)
 	struct trace_event_file *file;
 	struct trace_array *tr;
 
-	mutex_lock(&event_mutex);
+	lockdep_assert_held(&event_mutex);
+
 	do_for_each_event_file(tr, file) {
 
 		if (!(file->flags & EVENT_FILE_FL_ENABLED))
@@ -341,7 +342,6 @@ void trace_event_enable_cmd_record(bool enable)
 			clear_bit(EVENT_FILE_FL_RECORDED_CMD_BIT, &file->flags);
 		}
 	} while_for_each_event_file();
-	mutex_unlock(&event_mutex);
 }
 
 void trace_event_enable_tgid_record(bool enable)
@@ -349,7 +349,8 @@ void trace_event_enable_tgid_record(bool enable)
 	struct trace_event_file *file;
 	struct trace_array *tr;
 
-	mutex_lock(&event_mutex);
+	lockdep_assert_held(&event_mutex);
+
 	do_for_each_event_file(tr, file) {
 		if (!(file->flags & EVENT_FILE_FL_ENABLED))
 			continue;
@@ -363,7 +364,6 @@ void trace_event_enable_tgid_record(bool enable)
 				  &file->flags);
 		}
 	} while_for_each_event_file();
-	mutex_unlock(&event_mutex);
 }
 
 static int __ftrace_event_enable_disable(struct trace_event_file *file,
@@ -534,12 +534,12 @@ void trace_event_follow_fork(struct trace_array *tr, bool enable)
 	if (enable) {
 		register_trace_prio_sched_process_fork(event_filter_pid_sched_process_fork,
 						       tr, INT_MIN);
-		register_trace_prio_sched_process_exit(event_filter_pid_sched_process_exit,
+		register_trace_prio_sched_process_free(event_filter_pid_sched_process_exit,
 						       tr, INT_MAX);
 	} else {
 		unregister_trace_sched_process_fork(event_filter_pid_sched_process_fork,
 						    tr);
-		unregister_trace_sched_process_exit(event_filter_pid_sched_process_exit,
+		unregister_trace_sched_process_free(event_filter_pid_sched_process_exit,
 						    tr);
 	}
 }
@@ -795,7 +795,7 @@ static int __ftrace_set_clr_event(struct trace_array *tr, const char *match,
 	return ret;
 }
 
-static int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set)
+int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set)
 {
 	char *event = NULL, *sub = NULL, *match;
 	int ret;
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index d5a4bda9ce7b..b878d0ec8181 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1659,7 +1659,7 @@ static int process_system_preds(struct trace_subsystem_dir *dir,
 	parse_error(pe, FILT_ERR_BAD_SUBSYS_FILTER, 0);
 	return -EINVAL;
  fail_mem:
-	kfree(filter);
+	__free_filter(filter);
 	/* If any call succeeded, we still need to sync */
 	if (!fail)
 		tracepoint_synchronize_unregister();
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 725b9b35f933..21caeb2052ef 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -111,6 +111,7 @@ struct hist_field {
 	struct ftrace_event_field	*field;
 	unsigned long			flags;
 	hist_field_fn_t			fn;
+	unsigned int			ref;
 	unsigned int			size;
 	unsigned int			offset;
 	unsigned int                    is_signed;
@@ -464,11 +465,12 @@ struct action_data {
 	 * When a histogram trigger is hit, the values of any
 	 * references to variables, including variables being passed
 	 * as parameters to synthetic events, are collected into a
-	 * var_ref_vals array.  This var_ref_idx is the index of the
-	 * first param in the array to be passed to the synthetic
-	 * event invocation.
+	 * var_ref_vals array.  This var_ref_idx array is an array of
+	 * indices into the var_ref_vals array, one for each synthetic
+	 * event param, and is passed to the synthetic event
+	 * invocation.
 	 */
-	unsigned int		var_ref_idx;
+	unsigned int		var_ref_idx[TRACING_MAP_VARS_MAX];
 	struct synth_event	*synth_event;
 	bool			use_trace_keyword;
 	char			*synth_event_name;
@@ -854,14 +856,14 @@ static struct trace_event_functions synth_event_funcs = {
 
 static notrace void trace_event_raw_event_synth(void *__data,
 						u64 *var_ref_vals,
-						unsigned int var_ref_idx)
+						unsigned int *var_ref_idx)
 {
 	struct trace_event_file *trace_file = __data;
 	struct synth_trace_event *entry;
 	struct trace_event_buffer fbuffer;
 	struct ring_buffer *buffer;
 	struct synth_event *event;
-	unsigned int i, n_u64;
+	unsigned int i, n_u64, val_idx;
 	int fields_size = 0;
 
 	event = trace_file->event_call->data;
@@ -884,14 +886,34 @@ static notrace void trace_event_raw_event_synth(void *__data,
 		goto out;
 
 	for (i = 0, n_u64 = 0; i < event->n_fields; i++) {
+		val_idx = var_ref_idx[i];
 		if (event->fields[i]->is_string) {
-			char *str_val = (char *)(long)var_ref_vals[var_ref_idx + i];
+			char *str_val = (char *)(long)var_ref_vals[val_idx];
 			char *str_field = (char *)&entry->fields[n_u64];
 
 			strscpy(str_field, str_val, STR_VAR_LEN_MAX);
 			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
 		} else {
-			entry->fields[n_u64] = var_ref_vals[var_ref_idx + i];
+			struct synth_field *field = event->fields[i];
+			u64 val = var_ref_vals[val_idx];
+
+			switch (field->size) {
+			case 1:
+				*(u8 *)&entry->fields[n_u64] = (u8)val;
+				break;
+
+			case 2:
+				*(u16 *)&entry->fields[n_u64] = (u16)val;
+				break;
+
+			case 4:
+				*(u32 *)&entry->fields[n_u64] = (u32)val;
+				break;
+
+			default:
+				entry->fields[n_u64] = val;
+				break;
+			}
 			n_u64++;
 		}
 	}
@@ -1073,10 +1095,10 @@ static struct tracepoint *alloc_synth_tracepoint(char *name)
 }
 
 typedef void (*synth_probe_func_t) (void *__data, u64 *var_ref_vals,
-				    unsigned int var_ref_idx);
+				    unsigned int *var_ref_idx);
 
 static inline void trace_synth(struct synth_event *event, u64 *var_ref_vals,
-			       unsigned int var_ref_idx)
+			       unsigned int *var_ref_idx)
 {
 	struct tracepoint *tp = event->tp;
 
@@ -1987,12 +2009,6 @@ static int parse_map_size(char *str)
 	unsigned long size, map_bits;
 	int ret;
 
-	strsep(&str, "=");
-	if (!str) {
-		ret = -EINVAL;
-		goto out;
-	}
-
 	ret = kstrtoul(str, 0, &size);
 	if (ret)
 		goto out;
@@ -2052,25 +2068,25 @@ static int parse_action(char *str, struct hist_trigger_attrs *attrs)
 static int parse_assignment(struct trace_array *tr,
 			    char *str, struct hist_trigger_attrs *attrs)
 {
-	int ret = 0;
+	int len, ret = 0;
 
-	if ((str_has_prefix(str, "key=")) ||
-	    (str_has_prefix(str, "keys="))) {
-		attrs->keys_str = kstrdup(str, GFP_KERNEL);
+	if ((len = str_has_prefix(str, "key=")) ||
+	    (len = str_has_prefix(str, "keys="))) {
+		attrs->keys_str = kstrdup(str + len, GFP_KERNEL);
 		if (!attrs->keys_str) {
 			ret = -ENOMEM;
 			goto out;
 		}
-	} else if ((str_has_prefix(str, "val=")) ||
-		   (str_has_prefix(str, "vals=")) ||
-		   (str_has_prefix(str, "values="))) {
-		attrs->vals_str = kstrdup(str, GFP_KERNEL);
+	} else if ((len = str_has_prefix(str, "val=")) ||
+		   (len = str_has_prefix(str, "vals=")) ||
+		   (len = str_has_prefix(str, "values="))) {
+		attrs->vals_str = kstrdup(str + len, GFP_KERNEL);
 		if (!attrs->vals_str) {
 			ret = -ENOMEM;
 			goto out;
 		}
-	} else if (str_has_prefix(str, "sort=")) {
-		attrs->sort_key_str = kstrdup(str, GFP_KERNEL);
+	} else if ((len = str_has_prefix(str, "sort="))) {
+		attrs->sort_key_str = kstrdup(str + len, GFP_KERNEL);
 		if (!attrs->sort_key_str) {
 			ret = -ENOMEM;
 			goto out;
@@ -2081,12 +2097,8 @@ static int parse_assignment(struct trace_array *tr,
 			ret = -ENOMEM;
 			goto out;
 		}
-	} else if (str_has_prefix(str, "clock=")) {
-		strsep(&str, "=");
-		if (!str) {
-			ret = -EINVAL;
-			goto out;
-		}
+	} else if ((len = str_has_prefix(str, "clock="))) {
+		str += len;
 
 		str = strstrip(str);
 		attrs->clock = kstrdup(str, GFP_KERNEL);
@@ -2094,8 +2106,8 @@ static int parse_assignment(struct trace_array *tr,
 			ret = -ENOMEM;
 			goto out;
 		}
-	} else if (str_has_prefix(str, "size=")) {
-		int map_bits = parse_map_size(str);
+	} else if ((len = str_has_prefix(str, "size="))) {
+		int map_bits = parse_map_size(str + len);
 
 		if (map_bits < 0) {
 			ret = map_bits;
@@ -2135,8 +2147,14 @@ parse_hist_trigger_attrs(struct trace_array *tr, char *trigger_str)
 
 	while (trigger_str) {
 		char *str = strsep(&trigger_str, ":");
+		char *rhs;
 
-		if (strchr(str, '=')) {
+		rhs = strchr(str, '=');
+		if (rhs) {
+			if (!strlen(++rhs)) {
+				ret = -EINVAL;
+				goto free;
+			}
 			ret = parse_assignment(tr, str, attrs);
 			if (ret)
 				goto free;
@@ -2380,12 +2398,23 @@ static int contains_operator(char *str)
 	return field_op;
 }
 
+static void get_hist_field(struct hist_field *hist_field)
+{
+	hist_field->ref++;
+}
+
 static void __destroy_hist_field(struct hist_field *hist_field)
 {
+	if (--hist_field->ref > 1)
+		return;
+
 	kfree(hist_field->var.name);
 	kfree(hist_field->name);
 	kfree(hist_field->type);
 
+	kfree(hist_field->system);
+	kfree(hist_field->event_name);
+
 	kfree(hist_field);
 }
 
@@ -2423,6 +2452,8 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
 	if (!hist_field)
 		return NULL;
 
+	hist_field->ref = 1;
+
 	hist_field->hist_data = hist_data;
 
 	if (flags & HIST_FIELD_FL_EXPR || flags & HIST_FIELD_FL_ALIAS)
@@ -2597,6 +2628,22 @@ static int init_var_ref(struct hist_field *ref_field,
 	goto out;
 }
 
+static int find_var_ref_idx(struct hist_trigger_data *hist_data,
+			    struct hist_field *var_field)
+{
+	struct hist_field *ref_field;
+	int i;
+
+	for (i = 0; i < hist_data->n_var_refs; i++) {
+		ref_field = hist_data->var_refs[i];
+		if (ref_field->var.idx == var_field->var.idx &&
+		    ref_field->var.hist_data == var_field->hist_data)
+			return i;
+	}
+
+	return -ENOENT;
+}
+
 /**
  * create_var_ref - Create a variable reference and attach it to trigger
  * @hist_data: The trigger that will be referencing the variable
@@ -2618,6 +2665,17 @@ static struct hist_field *create_var_ref(struct hist_trigger_data *hist_data,
 {
 	unsigned long flags = HIST_FIELD_FL_VAR_REF;
 	struct hist_field *ref_field;
+	int i;
+
+	/* Check if the variable already exists */
+	for (i = 0; i < hist_data->n_var_refs; i++) {
+		ref_field = hist_data->var_refs[i];
+		if (ref_field->var.idx == var_field->var.idx &&
+		    ref_field->var.hist_data == var_field->hist_data) {
+			get_hist_field(ref_field);
+			return ref_field;
+		}
+	}
 
 	ref_field = create_hist_field(var_field->hist_data, NULL, flags, NULL);
 	if (ref_field) {
@@ -3415,6 +3473,7 @@ static struct hist_field *create_var(struct hist_trigger_data *hist_data,
 		goto out;
 	}
 
+	var->ref = 1;
 	var->flags = HIST_FIELD_FL_VAR;
 	var->var.idx = idx;
 	var->var.hist_data = var->hist_data = hist_data;
@@ -4044,6 +4103,9 @@ static void destroy_field_vars(struct hist_trigger_data *hist_data)
 
 	for (i = 0; i < hist_data->n_field_vars; i++)
 		destroy_field_var(hist_data->field_vars[i]);
+
+	for (i = 0; i < hist_data->n_save_vars; i++)
+		destroy_field_var(hist_data->save_vars[i]);
 }
 
 static void save_field_var(struct hist_trigger_data *hist_data,
@@ -4155,11 +4217,11 @@ static int trace_action_create(struct hist_trigger_data *hist_data,
 	struct trace_array *tr = hist_data->event_file->tr;
 	char *event_name, *param, *system = NULL;
 	struct hist_field *hist_field, *var_ref;
-	unsigned int i, var_ref_idx;
+	unsigned int i;
 	unsigned int field_pos = 0;
 	struct synth_event *event;
 	char *synth_event_name;
-	int ret = 0;
+	int var_ref_idx, ret = 0;
 
 	lockdep_assert_held(&event_mutex);
 
@@ -4176,8 +4238,6 @@ static int trace_action_create(struct hist_trigger_data *hist_data,
 
 	event->ref++;
 
-	var_ref_idx = hist_data->n_var_refs;
-
 	for (i = 0; i < data->n_params; i++) {
 		char *p;
 
@@ -4226,6 +4286,14 @@ static int trace_action_create(struct hist_trigger_data *hist_data,
 				goto err;
 			}
 
+			var_ref_idx = find_var_ref_idx(hist_data, var_ref);
+			if (WARN_ON(var_ref_idx < 0)) {
+				ret = var_ref_idx;
+				goto err;
+			}
+
+			data->var_ref_idx[i] = var_ref_idx;
+
 			field_pos++;
 			kfree(p);
 			continue;
@@ -4244,7 +4312,6 @@ static int trace_action_create(struct hist_trigger_data *hist_data,
 	}
 
 	data->synth_event = event;
-	data->var_ref_idx = var_ref_idx;
  out:
 	return ret;
  err:
@@ -4463,10 +4530,6 @@ static int create_val_fields(struct hist_trigger_data *hist_data,
 	if (!fields_str)
 		goto out;
 
-	strsep(&fields_str, "=");
-	if (!fields_str)
-		goto out;
-
 	for (i = 0, j = 1; i < TRACING_MAP_VALS_MAX &&
 		     j < TRACING_MAP_VALS_MAX; i++) {
 		field_str = strsep(&fields_str, ",");
@@ -4561,10 +4624,6 @@ static int create_key_fields(struct hist_trigger_data *hist_data,
 	if (!fields_str)
 		goto out;
 
-	strsep(&fields_str, "=");
-	if (!fields_str)
-		goto out;
-
 	for (i = n_vals; i < n_vals + TRACING_MAP_KEYS_MAX; i++) {
 		field_str = strsep(&fields_str, ",");
 		if (!field_str)
@@ -4722,12 +4781,6 @@ static int create_sort_keys(struct hist_trigger_data *hist_data)
 	if (!fields_str)
 		goto out;
 
-	strsep(&fields_str, "=");
-	if (!fields_str) {
-		ret = -EINVAL;
-		goto out;
-	}
-
 	for (i = 0; i < TRACING_MAP_SORT_KEYS_MAX; i++) {
 		struct hist_field *hist_field;
 		char *field_str, *field_name;
@@ -4736,9 +4789,11 @@ static int create_sort_keys(struct hist_trigger_data *hist_data)
 		sort_key = &hist_data->sort_keys[i];
 
 		field_str = strsep(&fields_str, ",");
-		if (!field_str) {
-			if (i == 0)
-				ret = -EINVAL;
+		if (!field_str)
+			break;
+
+		if (!*field_str) {
+			ret = -EINVAL;
 			break;
 		}
 
@@ -4748,7 +4803,7 @@ static int create_sort_keys(struct hist_trigger_data *hist_data)
 		}
 
 		field_name = strsep(&field_str, ".");
-		if (!field_name) {
+		if (!field_name || !*field_name) {
 			ret = -EINVAL;
 			break;
 		}
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 2a2912cb4533..586ea94e0db1 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -115,9 +115,10 @@ static void *trigger_next(struct seq_file *m, void *t, loff_t *pos)
 {
 	struct trace_event_file *event_file = event_file_data(m->private);
 
-	if (t == SHOW_AVAILABLE_TRIGGERS)
+	if (t == SHOW_AVAILABLE_TRIGGERS) {
+		(*pos)++;
 		return NULL;
-
+	}
 	return seq_list_next(t, &event_file->triggers, pos);
 }
 
@@ -210,11 +211,17 @@ static int event_trigger_regex_open(struct inode *inode, struct file *file)
 
 static int trigger_process_regex(struct trace_event_file *file, char *buff)
 {
-	char *command, *next = buff;
+	char *command, *next;
 	struct event_command *p;
 	int ret = -EINVAL;
 
+	next = buff = skip_spaces(buff);
 	command = strsep(&next, ": \t");
+	if (next) {
+		next = skip_spaces(next);
+		if (!*next)
+			next = NULL;
+	}
 	command = (command[0] != '!') ? command : command + 1;
 
 	mutex_lock(&trigger_cmd_mutex);
@@ -617,8 +624,14 @@ event_trigger_callback(struct event_command *cmd_ops,
 	int ret;
 
 	/* separate the trigger from the filter (t:n [if filter]) */
-	if (param && isdigit(param[0]))
+	if (param && isdigit(param[0])) {
 		trigger = strsep(&param, " \t");
+		if (param) {
+			param = skip_spaces(param);
+			if (!*param)
+				param = NULL;
+		}
+	}
 
 	trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger);
 
@@ -1075,14 +1088,10 @@ register_snapshot_trigger(char *glob, struct event_trigger_ops *ops,
 			  struct event_trigger_data *data,
 			  struct trace_event_file *file)
 {
-	int ret = register_trigger(glob, ops, data, file);
-
-	if (ret > 0 && tracing_alloc_snapshot_instance(file->tr) != 0) {
-		unregister_trigger(glob, ops, data, file);
-		ret = 0;
-	}
+	if (tracing_alloc_snapshot_instance(file->tr) != 0)
+		return 0;
 
-	return ret;
+	return register_trigger(glob, ops, data, file);
 }
 
 static int
@@ -1359,6 +1368,11 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
 	trigger = strsep(&param, " \t");
 	if (!trigger)
 		return -EINVAL;
+	if (param) {
+		param = skip_spaces(param);
+		if (!*param)
+			param = NULL;
+	}
 
 	system = strsep(&trigger, ":");
 	if (!trigger)
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index 8030e24dbf14..568918fae8d4 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -270,6 +270,7 @@ static bool disable_migrate;
 static void move_to_next_cpu(void)
 {
 	struct cpumask *current_mask = &save_cpumask;
+	struct trace_array *tr = hwlat_trace;
 	int next_cpu;
 
 	if (disable_migrate)
@@ -283,7 +284,7 @@ static void move_to_next_cpu(void)
 		goto disable;
 
 	get_online_cpus();
-	cpumask_and(current_mask, cpu_online_mask, tracing_buffer_mask);
+	cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask);
 	next_cpu = cpumask_next(smp_processor_id(), current_mask);
 	put_online_cpus();
 
@@ -360,7 +361,7 @@ static int start_kthread(struct trace_array *tr)
 	/* Just pick the first CPU on first iteration */
 	current_mask = &save_cpumask;
 	get_online_cpus();
-	cpumask_and(current_mask, cpu_online_mask, tracing_buffer_mask);
+	cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask);
 	put_online_cpus();
 	next_cpu = cpumask_first(current_mask);
 
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index b8fbf1d11e10..4666bceb1383 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -408,7 +408,7 @@ static bool __within_notrace_func(unsigned long addr)
 
 static bool within_notrace_func(struct trace_kprobe *tk)
 {
-	unsigned long addr = addr = trace_kprobe_address(tk);
+	unsigned long addr = trace_kprobe_address(tk);
 	char symname[KSYM_NAME_LEN], *p;
 
 	if (!__within_notrace_func(addr))
@@ -788,6 +788,8 @@ static int trace_kprobe_show(struct seq_file *m, struct dyn_event *ev)
 	int i;
 
 	seq_putc(m, trace_kprobe_is_return(tk) ? 'r' : 'p');
+	if (trace_kprobe_is_return(tk) && tk->rp.maxactive)
+		seq_printf(m, "%d", tk->rp.maxactive);
 	seq_printf(m, ":%s/%s", tk->tp.call.class->system,
 			trace_event_name(&tk->tp.call));
 
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index e288168661e1..e304196d7c28 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -89,8 +89,10 @@ static void tracing_sched_unregister(void)
 
 static void tracing_start_sched_switch(int ops)
 {
-	bool sched_register = (!sched_cmdline_ref && !sched_tgid_ref);
+	bool sched_register;
+
 	mutex_lock(&sched_register_mutex);
+	sched_register = (!sched_cmdline_ref && !sched_tgid_ref);
 
 	switch (ops) {
 	case RECORD_CMDLINE:
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 743b2b520d34..7152062d6af6 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -631,7 +631,7 @@ static void start_wakeup_tracer(struct trace_array *tr)
 	if (ret) {
 		pr_info("wakeup trace: Couldn't activate tracepoint"
 			" probe to kernel_sched_migrate_task\n");
-		return;
+		goto fail_deprobe_sched_switch;
 	}
 
 	wakeup_reset(tr);
@@ -649,6 +649,8 @@ static void start_wakeup_tracer(struct trace_array *tr)
 		printk(KERN_ERR "failed to start wakeup tracer\n");
 
 	return;
+fail_deprobe_sched_switch:
+	unregister_trace_sched_switch(probe_wakeup_sched_switch, NULL);
 fail_deprobe_wake_new:
 	unregister_trace_sched_wakeup_new(probe_wakeup, NULL);
 fail_deprobe:
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 642a850af81a..5b4f50932478 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -184,6 +184,11 @@ static void check_stack(unsigned long ip, unsigned long *stack)
 	local_irq_restore(flags);
 }
 
+/* Some archs may not define MCOUNT_INSN_SIZE */
+#ifndef MCOUNT_INSN_SIZE
+# define MCOUNT_INSN_SIZE 0
+#endif
+
 static void
 stack_trace_call(unsigned long ip, unsigned long parent_ip,
 		 struct ftrace_ops *op, struct pt_regs *pt_regs)
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index 75bf1bcb4a8a..92b76f9e25ed 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -278,18 +278,22 @@ static int tracing_stat_init(void)
 
 	d_tracing = tracing_init_dentry();
 	if (IS_ERR(d_tracing))
-		return 0;
+		return -ENODEV;
 
 	stat_dir = tracefs_create_dir("trace_stat", d_tracing);
-	if (!stat_dir)
+	if (!stat_dir) {
 		pr_warn("Could not create tracefs 'trace_stat' entry\n");
+		return -ENOMEM;
+	}
 	return 0;
 }
 
 static int init_stat_file(struct stat_session *session)
 {
-	if (!stat_dir && tracing_stat_init())
-		return -ENODEV;
+	int ret;
+
+	if (!stat_dir && (ret = tracing_stat_init()))
+		return ret;
 
 	session->file = tracefs_create_file(session->ts->name, 0644,
 					    stat_dir,
@@ -302,7 +306,7 @@ static int init_stat_file(struct stat_session *session)
 int register_stat_tracer(struct tracer_stat *trace)
 {
 	struct stat_session *session, *node;
-	int ret;
+	int ret = -EINVAL;
 
 	if (!trace)
 		return -EINVAL;
@@ -313,17 +317,15 @@ int register_stat_tracer(struct tracer_stat *trace)
 	/* Already registered? */
 	mutex_lock(&all_stat_sessions_mutex);
 	list_for_each_entry(node, &all_stat_sessions, session_list) {
-		if (node->ts == trace) {
-			mutex_unlock(&all_stat_sessions_mutex);
-			return -EINVAL;
-		}
+		if (node->ts == trace)
+			goto out;
 	}
-	mutex_unlock(&all_stat_sessions_mutex);
 
+	ret = -ENOMEM;
 	/* Init the session */
 	session = kzalloc(sizeof(*session), GFP_KERNEL);
 	if (!session)
-		return -ENOMEM;
+		goto out;
 
 	session->ts = trace;
 	INIT_LIST_HEAD(&session->session_list);
@@ -332,15 +334,16 @@ int register_stat_tracer(struct tracer_stat *trace)
 	ret = init_stat_file(session);
 	if (ret) {
 		destroy_session(session);
-		return ret;
+		goto out;
 	}
 
+	ret = 0;
 	/* Register */
-	mutex_lock(&all_stat_sessions_mutex);
 	list_add_tail(&session->session_list, &all_stat_sessions);
+ out:
 	mutex_unlock(&all_stat_sessions_mutex);
 
-	return 0;
+	return ret;
 }
 
 void unregister_stat_tracer(struct tracer_stat *trace)
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 9a1c22310323..9e31bfc818ff 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -148,8 +148,8 @@ static int tracing_map_cmp_atomic64(void *val_a, void *val_b)
 #define DEFINE_TRACING_MAP_CMP_FN(type)					\
 static int tracing_map_cmp_##type(void *val_a, void *val_b)		\
 {									\
-	type a = *(type *)val_a;					\
-	type b = *(type *)val_b;					\
+	type a = (type)(*(u64 *)val_a);					\
+	type b = (type)(*(u64 *)val_b);					\
 									\
 	return (a > b) ? 1 : ((a < b) ? -1 : 0);			\
 }
diff --git a/kernel/umh.c b/kernel/umh.c
index 7f255b5a8845..3474d6aa55d8 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -475,6 +475,12 @@ static void umh_clean_and_save_pid(struct subprocess_info *info)
 {
 	struct umh_info *umh_info = info->data;
 
+	/* cleanup if umh_pipe_setup() was successful but exec failed */
+	if (info->pid && info->retval) {
+		fput(umh_info->pipe_to_umh);
+		fput(umh_info->pipe_from_umh);
+	}
+
 	argv_free(info->argv);
 	umh_info->pid = info->pid;
 }
@@ -544,6 +550,11 @@ EXPORT_SYMBOL_GPL(fork_usermode_blob);
  * Runs a user-space application.  The application is started
  * asynchronously if wait is not set, and runs as a child of system workqueues.
  * (ie. it runs with full root capabilities and optimized affinity).
+ *
+ * Note: successful return value does not guarantee the helper was called at
+ * all. You can't rely on sub_info->{init,cleanup} being called even for
+ * UMH_WAIT_* wait modes as STATIC_USERMODEHELPER_PATH="" turns all helpers
+ * into a successful no-op.
  */
 int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait)
 {
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 7f9e7b9306fe..c1853aea4c14 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -161,6 +161,8 @@ static void lockup_detector_update_enable(void)
 
 #ifdef CONFIG_SOFTLOCKUP_DETECTOR
 
+#define SOFTLOCKUP_RESET	ULONG_MAX
+
 /* Global variables, exported for sysctl */
 unsigned int __read_mostly softlockup_panic =
 			CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
@@ -274,7 +276,7 @@ notrace void touch_softlockup_watchdog_sched(void)
 	 * Preemption can be enabled.  It doesn't matter which CPU's timestamp
 	 * gets zeroed here, so use the raw_ operation.
 	 */
-	raw_cpu_write(watchdog_touch_ts, 0);
+	raw_cpu_write(watchdog_touch_ts, SOFTLOCKUP_RESET);
 }
 
 notrace void touch_softlockup_watchdog(void)
@@ -298,14 +300,14 @@ void touch_all_softlockup_watchdogs(void)
 	 * the softlockup check.
 	 */
 	for_each_cpu(cpu, &watchdog_allowed_mask)
-		per_cpu(watchdog_touch_ts, cpu) = 0;
+		per_cpu(watchdog_touch_ts, cpu) = SOFTLOCKUP_RESET;
 	wq_watchdog_touch(-1);
 }
 
 void touch_softlockup_watchdog_sync(void)
 {
 	__this_cpu_write(softlockup_touch_sync, true);
-	__this_cpu_write(watchdog_touch_ts, 0);
+	__this_cpu_write(watchdog_touch_ts, SOFTLOCKUP_RESET);
 }
 
 static int is_softlockup(unsigned long touch_ts)
@@ -383,7 +385,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	/* .. and repeat */
 	hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period));
 
-	if (touch_ts == 0) {
+	if (touch_ts == SOFTLOCKUP_RESET) {
 		if (unlikely(__this_cpu_read(softlockup_touch_sync))) {
 			/*
 			 * If the time stamp was touched atomically
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index aabfeeff1180..6bf536113bc1 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -425,7 +425,8 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq);
  * ignored.
  */
 #define for_each_pwq(pwq, wq)						\
-	list_for_each_entry_rcu((pwq), &(wq)->pwqs, pwqs_node)		\
+	list_for_each_entry_rcu((pwq), &(wq)->pwqs, pwqs_node,		\
+				lockdep_is_held(&wq->mutex))		\
 		if (({ assert_rcu_or_wq_mutex(wq); false; })) { }	\
 		else
 
@@ -1416,14 +1417,16 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 		return;
 	rcu_read_lock();
 retry:
-	if (req_cpu == WORK_CPU_UNBOUND)
-		cpu = wq_select_unbound_cpu(raw_smp_processor_id());
-
 	/* pwq which will be used unless @work is executing elsewhere */
-	if (!(wq->flags & WQ_UNBOUND))
-		pwq = per_cpu_ptr(wq->cpu_pwqs, cpu);
-	else
+	if (wq->flags & WQ_UNBOUND) {
+		if (req_cpu == WORK_CPU_UNBOUND)
+			cpu = wq_select_unbound_cpu(raw_smp_processor_id());
 		pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu));
+	} else {
+		if (req_cpu == WORK_CPU_UNBOUND)
+			cpu = raw_smp_processor_id();
+		pwq = per_cpu_ptr(wq->cpu_pwqs, cpu);
+	}
 
 	/*
 	 * If @work was previously on a different pool, it might still be
@@ -3493,7 +3496,6 @@ static void rcu_free_wq(struct rcu_head *rcu)
 	else
 		free_workqueue_attrs(wq->unbound_attrs);
 
-	kfree(wq->rescuer);
 	kfree(wq);
 }
 
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 120ec6f64bbc..33a11feb81de 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -223,6 +223,8 @@ config DEBUG_INFO_DWARF4
 config DEBUG_INFO_BTF
 	bool "Generate BTF typeinfo"
 	depends on DEBUG_INFO
+	depends on !DEBUG_INFO_SPLIT && !DEBUG_INFO_REDUCED
+	depends on !GCC_PLUGIN_RANDSTRUCT || COMPILE_TEST
 	help
 	  Generate deduplicated BTF type information from DWARF debug info.
 	  Turning this on expects presence of pahole tool, which will convert
diff --git a/lib/Makefile b/lib/Makefile
index 7c3c1ad21afc..87b3be3c336d 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -102,7 +102,7 @@ endif
 obj-$(CONFIG_DEBUG_INFO_REDUCED) += debug_info.o
 CFLAGS_debug_info.o += $(call cc-option, -femit-struct-debug-detailed=any)
 
-obj-y += math/
+obj-y += math/ crypto/
 
 obj-$(CONFIG_GENERIC_IOMAP) += iomap.o
 obj-$(CONFIG_GENERIC_PCI_IOMAP) += pci_iomap.o
diff --git a/lib/bug.c b/lib/bug.c
index 1077366f496b..8c98af0bf585 100644
--- a/lib/bug.c
+++ b/lib/bug.c
@@ -181,6 +181,15 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs)
 		}
 	}
 
+	/*
+	 * BUG() and WARN_ON() families don't print a custom debug message
+	 * before triggering the exception handler, so we must add the
+	 * "cut here" line now. WARN() issues its own "cut here" before the
+	 * extra debugging message it writes before triggering the handler.
+	 */
+	if ((bug->flags & BUGFLAG_NO_CUT_HERE) == 0)
+		printk(KERN_DEFAULT CUT_HERE);
+
 	if (warning) {
 		/* this is a WARN_ON rather than BUG/BUG_ON */
 		__warn(file, line, (void *)bugaddr, BUG_GET_TAINT(bug), regs,
@@ -188,8 +197,6 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs)
 		return BUG_TRAP_TYPE_WARN;
 	}
 
-	printk(KERN_DEFAULT CUT_HERE);
-
 	if (file)
 		pr_crit("kernel BUG at %s:%u!\n", file, line);
 	else
diff --git a/lib/crc-t10dif.c b/lib/crc-t10dif.c
index 8cc01a603416..c9acf1c12cfc 100644
--- a/lib/crc-t10dif.c
+++ b/lib/crc-t10dif.c
@@ -19,39 +19,46 @@
 static struct crypto_shash __rcu *crct10dif_tfm;
 static struct static_key crct10dif_fallback __read_mostly;
 static DEFINE_MUTEX(crc_t10dif_mutex);
+static struct work_struct crct10dif_rehash_work;
 
-static int crc_t10dif_rehash(struct notifier_block *self, unsigned long val, void *data)
+static int crc_t10dif_notify(struct notifier_block *self, unsigned long val, void *data)
 {
 	struct crypto_alg *alg = data;
-	struct crypto_shash *new, *old;
 
 	if (val != CRYPTO_MSG_ALG_LOADED ||
 	    static_key_false(&crct10dif_fallback) ||
 	    strncmp(alg->cra_name, CRC_T10DIF_STRING, strlen(CRC_T10DIF_STRING)))
 		return 0;
 
+	schedule_work(&crct10dif_rehash_work);
+	return 0;
+}
+
+static void crc_t10dif_rehash(struct work_struct *work)
+{
+	struct crypto_shash *new, *old;
+
 	mutex_lock(&crc_t10dif_mutex);
 	old = rcu_dereference_protected(crct10dif_tfm,
 					lockdep_is_held(&crc_t10dif_mutex));
 	if (!old) {
 		mutex_unlock(&crc_t10dif_mutex);
-		return 0;
+		return;
 	}
 	new = crypto_alloc_shash("crct10dif", 0, 0);
 	if (IS_ERR(new)) {
 		mutex_unlock(&crc_t10dif_mutex);
-		return 0;
+		return;
 	}
 	rcu_assign_pointer(crct10dif_tfm, new);
 	mutex_unlock(&crc_t10dif_mutex);
 
 	synchronize_rcu();
 	crypto_free_shash(old);
-	return 0;
 }
 
 static struct notifier_block crc_t10dif_nb = {
-	.notifier_call = crc_t10dif_rehash,
+	.notifier_call = crc_t10dif_notify,
 };
 
 __u16 crc_t10dif_update(__u16 crc, const unsigned char *buffer, size_t len)
@@ -86,19 +93,26 @@ EXPORT_SYMBOL(crc_t10dif);
 
 static int __init crc_t10dif_mod_init(void)
 {
+	struct crypto_shash *tfm;
+
+	INIT_WORK(&crct10dif_rehash_work, crc_t10dif_rehash);
 	crypto_register_notifier(&crc_t10dif_nb);
-	crct10dif_tfm = crypto_alloc_shash("crct10dif", 0, 0);
-	if (IS_ERR(crct10dif_tfm)) {
+	mutex_lock(&crc_t10dif_mutex);
+	tfm = crypto_alloc_shash("crct10dif", 0, 0);
+	if (IS_ERR(tfm)) {
 		static_key_slow_inc(&crct10dif_fallback);
-		crct10dif_tfm = NULL;
+		tfm = NULL;
 	}
+	RCU_INIT_POINTER(crct10dif_tfm, tfm);
+	mutex_unlock(&crc_t10dif_mutex);
 	return 0;
 }
 
 static void __exit crc_t10dif_mod_fini(void)
 {
 	crypto_unregister_notifier(&crc_t10dif_nb);
-	crypto_free_shash(crct10dif_tfm);
+	cancel_work_sync(&crct10dif_rehash_work);
+	crypto_free_shash(rcu_dereference_protected(crct10dif_tfm, 1));
 }
 
 module_init(crc_t10dif_mod_init);
@@ -106,11 +120,27 @@ module_exit(crc_t10dif_mod_fini);
 
 static int crc_t10dif_transform_show(char *buffer, const struct kernel_param *kp)
 {
+	struct crypto_shash *tfm;
+	const char *name;
+	int len;
+
 	if (static_key_false(&crct10dif_fallback))
 		return sprintf(buffer, "fallback\n");
 
-	return sprintf(buffer, "%s\n",
-		crypto_tfm_alg_driver_name(crypto_shash_tfm(crct10dif_tfm)));
+	rcu_read_lock();
+	tfm = rcu_dereference(crct10dif_tfm);
+	if (!tfm) {
+		len = sprintf(buffer, "init\n");
+		goto unlock;
+	}
+
+	name = crypto_tfm_alg_driver_name(crypto_shash_tfm(tfm));
+	len = sprintf(buffer, "%s\n", name);
+
+unlock:
+	rcu_read_unlock();
+
+	return len;
 }
 
 module_param_call(transform, NULL, crc_t10dif_transform_show, NULL, 0644);
diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile
new file mode 100644
index 000000000000..88195c34932d
--- /dev/null
+++ b/lib/crypto/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_CRYPTO_LIB_ARC4) += libarc4.o
+libarc4-y := arc4.o
diff --git a/lib/crypto/arc4.c b/lib/crypto/arc4.c
new file mode 100644
index 000000000000..c2020f19c652
--- /dev/null
+++ b/lib/crypto/arc4.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Cryptographic API
+ *
+ * ARC4 Cipher Algorithm
+ *
+ * Jon Oberheide <jon@oberheide.org>
+ */
+
+#include <crypto/arc4.h>
+#include <linux/module.h>
+
+int arc4_setkey(struct arc4_ctx *ctx, const u8 *in_key, unsigned int key_len)
+{
+	int i, j = 0, k = 0;
+
+	ctx->x = 1;
+	ctx->y = 0;
+
+	for (i = 0; i < 256; i++)
+		ctx->S[i] = i;
+
+	for (i = 0; i < 256; i++) {
+		u32 a = ctx->S[i];
+
+		j = (j + in_key[k] + a) & 0xff;
+		ctx->S[i] = ctx->S[j];
+		ctx->S[j] = a;
+		if (++k >= key_len)
+			k = 0;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(arc4_setkey);
+
+void arc4_crypt(struct arc4_ctx *ctx, u8 *out, const u8 *in, unsigned int len)
+{
+	u32 *const S = ctx->S;
+	u32 x, y, a, b;
+	u32 ty, ta, tb;
+
+	if (len == 0)
+		return;
+
+	x = ctx->x;
+	y = ctx->y;
+
+	a = S[x];
+	y = (y + a) & 0xff;
+	b = S[y];
+
+	do {
+		S[y] = a;
+		a = (a + b) & 0xff;
+		S[x] = b;
+		x = (x + 1) & 0xff;
+		ta = S[x];
+		ty = (y + ta) & 0xff;
+		tb = S[ty];
+		*out++ = *in++ ^ S[a];
+		if (--len == 0)
+			break;
+		y = ty;
+		a = ta;
+		b = tb;
+	} while (true);
+
+	ctx->x = x;
+	ctx->y = y;
+}
+EXPORT_SYMBOL(arc4_crypt);
+
+MODULE_LICENSE("GPL");
diff --git a/lib/devres.c b/lib/devres.c
index 6a0e9bd6524a..77c80ca9e485 100644
--- a/lib/devres.c
+++ b/lib/devres.c
@@ -9,6 +9,7 @@
 enum devm_ioremap_type {
 	DEVM_IOREMAP = 0,
 	DEVM_IOREMAP_NC,
+	DEVM_IOREMAP_UC,
 	DEVM_IOREMAP_WC,
 };
 
@@ -39,6 +40,9 @@ static void __iomem *__devm_ioremap(struct device *dev, resource_size_t offset,
 	case DEVM_IOREMAP_NC:
 		addr = ioremap_nocache(offset, size);
 		break;
+	case DEVM_IOREMAP_UC:
+		addr = ioremap_uc(offset, size);
+		break;
 	case DEVM_IOREMAP_WC:
 		addr = ioremap_wc(offset, size);
 		break;
@@ -69,6 +73,21 @@ void __iomem *devm_ioremap(struct device *dev, resource_size_t offset,
 EXPORT_SYMBOL(devm_ioremap);
 
 /**
+ * devm_ioremap_uc - Managed ioremap_uc()
+ * @dev: Generic device to remap IO address for
+ * @offset: Resource address to map
+ * @size: Size of map
+ *
+ * Managed ioremap_uc().  Map is automatically unmapped on driver detach.
+ */
+void __iomem *devm_ioremap_uc(struct device *dev, resource_size_t offset,
+			      resource_size_t size)
+{
+	return __devm_ioremap(dev, offset, size, DEVM_IOREMAP_UC);
+}
+EXPORT_SYMBOL_GPL(devm_ioremap_uc);
+
+/**
  * devm_ioremap_nocache - Managed ioremap_nocache()
  * @dev: Generic device to remap IO address for
  * @offset: Resource address to map
@@ -136,6 +155,7 @@ void __iomem *devm_ioremap_resource(struct device *dev,
 {
 	resource_size_t size;
 	void __iomem *dest_ptr;
+	char *pretty_name;
 
 	BUG_ON(!dev);
 
@@ -146,7 +166,15 @@ void __iomem *devm_ioremap_resource(struct device *dev,
 
 	size = resource_size(res);
 
-	if (!devm_request_mem_region(dev, res->start, size, dev_name(dev))) {
+	if (res->name)
+		pretty_name = devm_kasprintf(dev, GFP_KERNEL, "%s %s",
+					     dev_name(dev), res->name);
+	else
+		pretty_name = devm_kstrdup(dev, dev_name(dev), GFP_KERNEL);
+	if (!pretty_name)
+		return IOMEM_ERR_PTR(-ENOMEM);
+
+	if (!devm_request_mem_region(dev, res->start, size, pretty_name)) {
 		dev_err(dev, "can't request region for resource %pR\n", res);
 		return IOMEM_ERR_PTR(-EBUSY);
 	}
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index 8a16c2d498e9..af9aba06c59f 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -87,22 +87,22 @@ static struct { unsigned flag:8; char opt_char; } opt_array[] = {
 	{ _DPRINTK_FLAGS_NONE, '_' },
 };
 
+struct flagsbuf { char buf[ARRAY_SIZE(opt_array)+1]; };
+
 /* format a string into buf[] which describes the _ddebug's flags */
-static char *ddebug_describe_flags(struct _ddebug *dp, char *buf,
-				    size_t maxlen)
+static char *ddebug_describe_flags(unsigned int flags, struct flagsbuf *fb)
 {
-	char *p = buf;
+	char *p = fb->buf;
 	int i;
 
-	BUG_ON(maxlen < 6);
 	for (i = 0; i < ARRAY_SIZE(opt_array); ++i)
-		if (dp->flags & opt_array[i].flag)
+		if (flags & opt_array[i].flag)
 			*p++ = opt_array[i].opt_char;
-	if (p == buf)
+	if (p == fb->buf)
 		*p++ = '_';
 	*p = '\0';
 
-	return buf;
+	return fb->buf;
 }
 
 #define vpr_info(fmt, ...)					\
@@ -144,7 +144,7 @@ static int ddebug_change(const struct ddebug_query *query,
 	struct ddebug_table *dt;
 	unsigned int newflags;
 	unsigned int nfound = 0;
-	char flagbuf[10];
+	struct flagsbuf fbuf;
 
 	/* search for matching ddebugs */
 	mutex_lock(&ddebug_lock);
@@ -201,8 +201,7 @@ static int ddebug_change(const struct ddebug_query *query,
 			vpr_info("changed %s:%d [%s]%s =%s\n",
 				 trim_prefix(dp->filename), dp->lineno,
 				 dt->mod_name, dp->function,
-				 ddebug_describe_flags(dp, flagbuf,
-						       sizeof(flagbuf)));
+				 ddebug_describe_flags(dp->flags, &fbuf));
 		}
 	}
 	mutex_unlock(&ddebug_lock);
@@ -816,7 +815,7 @@ static int ddebug_proc_show(struct seq_file *m, void *p)
 {
 	struct ddebug_iter *iter = m->private;
 	struct _ddebug *dp = p;
-	char flagsbuf[10];
+	struct flagsbuf flags;
 
 	vpr_info("called m=%p p=%p\n", m, p);
 
@@ -829,7 +828,7 @@ static int ddebug_proc_show(struct seq_file *m, void *p)
 	seq_printf(m, "%s:%u [%s]%s =%s \"",
 		   trim_prefix(dp->filename), dp->lineno,
 		   iter->table->mod_name, dp->function,
-		   ddebug_describe_flags(dp, flagsbuf, sizeof(flagsbuf)));
+		   ddebug_describe_flags(dp->flags, &flags));
 	seq_escape(m, dp->format, "\t\r\n\"");
 	seq_puts(m, "\"\n");
 
diff --git a/lib/find_bit.c b/lib/find_bit.c
index 5c51eb45178a..4e68490fa703 100644
--- a/lib/find_bit.c
+++ b/lib/find_bit.c
@@ -149,18 +149,6 @@ EXPORT_SYMBOL(find_last_bit);
 
 #ifdef __BIG_ENDIAN
 
-/* include/linux/byteorder does not support "unsigned long" type */
-static inline unsigned long ext2_swab(const unsigned long y)
-{
-#if BITS_PER_LONG == 64
-	return (unsigned long) __swab64((u64) y);
-#elif BITS_PER_LONG == 32
-	return (unsigned long) __swab32((u32) y);
-#else
-#error BITS_PER_LONG not defined
-#endif
-}
-
 #if !defined(find_next_bit_le) || !defined(find_next_zero_bit_le)
 static inline unsigned long _find_next_bit_le(const unsigned long *addr1,
 		const unsigned long *addr2, unsigned long nbits,
@@ -177,7 +165,7 @@ static inline unsigned long _find_next_bit_le(const unsigned long *addr1,
 	tmp ^= invert;
 
 	/* Handle 1st word. */
-	tmp &= ext2_swab(BITMAP_FIRST_WORD_MASK(start));
+	tmp &= swab(BITMAP_FIRST_WORD_MASK(start));
 	start = round_down(start, BITS_PER_LONG);
 
 	while (!tmp) {
@@ -191,7 +179,7 @@ static inline unsigned long _find_next_bit_le(const unsigned long *addr1,
 		tmp ^= invert;
 	}
 
-	return min(start + __ffs(ext2_swab(tmp)), nbits);
+	return min(start + __ffs(swab(tmp)), nbits);
 }
 #endif
 
diff --git a/lib/lzo/lzo1x_compress.c b/lib/lzo/lzo1x_compress.c
index 717c940112f9..8ad5ba2b86e2 100644
--- a/lib/lzo/lzo1x_compress.c
+++ b/lib/lzo/lzo1x_compress.c
@@ -268,6 +268,19 @@ m_len_done:
 				*op++ = (M4_MARKER | ((m_off >> 11) & 8)
 						| (m_len - 2));
 			else {
+				if (unlikely(((m_off & 0x403f) == 0x403f)
+						&& (m_len >= 261)
+						&& (m_len <= 264))
+						&& likely(bitstream_version)) {
+					// Under lzo-rle, block copies
+					// for 261 <= length <= 264 and
+					// (distance & 0x80f3) == 0x80f3
+					// can result in ambiguous
+					// output. Adjust length
+					// to 260 to prevent ambiguity.
+					ip -= m_len - 260;
+					m_len = 260;
+				}
 				m_len -= M4_MAX_LEN;
 				*op++ = (M4_MARKER | ((m_off >> 11) & 8));
 				while (unlikely(m_len > 255)) {
diff --git a/lib/mpi/longlong.h b/lib/mpi/longlong.h
index 08c60d10747f..6c5229f98c9e 100644
--- a/lib/mpi/longlong.h
+++ b/lib/mpi/longlong.h
@@ -671,7 +671,7 @@ do {						\
 	**************  MIPS/64  **************
 	***************************************/
 #if (defined(__mips) && __mips >= 3) && W_TYPE_SIZE == 64
-#if defined(__mips_isa_rev) && __mips_isa_rev >= 6
+#if defined(__mips_isa_rev) && __mips_isa_rev >= 6 && defined(CONFIG_CC_IS_GCC)
 /*
  * GCC ends up emitting a __multi3 intrinsic call for MIPS64r6 with the plain C
  * code below, so we special case MIPS64r6 until the compiler can do better.
@@ -756,22 +756,22 @@ do {									\
 do { \
 	if (__builtin_constant_p(bh) && (bh) == 0) \
 		__asm__ ("{a%I4|add%I4c} %1,%3,%4\n\t{aze|addze} %0,%2" \
-		: "=r" ((USItype)(sh)), \
-		"=&r" ((USItype)(sl)) \
+		: "=r" (sh), \
+		"=&r" (sl) \
 		: "%r" ((USItype)(ah)), \
 		"%r" ((USItype)(al)), \
 		"rI" ((USItype)(bl))); \
 	else if (__builtin_constant_p(bh) && (bh) == ~(USItype) 0) \
 		__asm__ ("{a%I4|add%I4c} %1,%3,%4\n\t{ame|addme} %0,%2" \
-		: "=r" ((USItype)(sh)), \
-		"=&r" ((USItype)(sl)) \
+		: "=r" (sh), \
+		"=&r" (sl) \
 		: "%r" ((USItype)(ah)), \
 		"%r" ((USItype)(al)), \
 		"rI" ((USItype)(bl))); \
 	else \
 		__asm__ ("{a%I5|add%I5c} %1,%4,%5\n\t{ae|adde} %0,%2,%3" \
-		: "=r" ((USItype)(sh)), \
-		"=&r" ((USItype)(sl)) \
+		: "=r" (sh), \
+		"=&r" (sl) \
 		: "%r" ((USItype)(ah)), \
 		"r" ((USItype)(bh)), \
 		"%r" ((USItype)(al)), \
@@ -781,36 +781,36 @@ do { \
 do { \
 	if (__builtin_constant_p(ah) && (ah) == 0) \
 		__asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{sfze|subfze} %0,%2" \
-		: "=r" ((USItype)(sh)), \
-		"=&r" ((USItype)(sl)) \
+		: "=r" (sh), \
+		"=&r" (sl) \
 		: "r" ((USItype)(bh)), \
 		"rI" ((USItype)(al)), \
 		"r" ((USItype)(bl))); \
 	else if (__builtin_constant_p(ah) && (ah) == ~(USItype) 0) \
 		__asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{sfme|subfme} %0,%2" \
-		: "=r" ((USItype)(sh)), \
-		"=&r" ((USItype)(sl)) \
+		: "=r" (sh), \
+		"=&r" (sl) \
 		: "r" ((USItype)(bh)), \
 		"rI" ((USItype)(al)), \
 		"r" ((USItype)(bl))); \
 	else if (__builtin_constant_p(bh) && (bh) == 0) \
 		__asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{ame|addme} %0,%2" \
-		: "=r" ((USItype)(sh)), \
-		"=&r" ((USItype)(sl)) \
+		: "=r" (sh), \
+		"=&r" (sl) \
 		: "r" ((USItype)(ah)), \
 		"rI" ((USItype)(al)), \
 		"r" ((USItype)(bl))); \
 	else if (__builtin_constant_p(bh) && (bh) == ~(USItype) 0) \
 		__asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{aze|addze} %0,%2" \
-		: "=r" ((USItype)(sh)), \
-		"=&r" ((USItype)(sl)) \
+		: "=r" (sh), \
+		"=&r" (sl) \
 		: "r" ((USItype)(ah)), \
 		"rI" ((USItype)(al)), \
 		"r" ((USItype)(bl))); \
 	else \
 		__asm__ ("{sf%I4|subf%I4c} %1,%5,%4\n\t{sfe|subfe} %0,%3,%2" \
-		: "=r" ((USItype)(sh)), \
-		"=&r" ((USItype)(sl)) \
+		: "=r" (sh), \
+		"=&r" (sl) \
 		: "r" ((USItype)(ah)), \
 		"r" ((USItype)(bh)), \
 		"rI" ((USItype)(al)), \
@@ -821,7 +821,7 @@ do { \
 do { \
 	USItype __m0 = (m0), __m1 = (m1); \
 	__asm__ ("mulhwu %0,%1,%2" \
-	: "=r" ((USItype) ph) \
+	: "=r" (ph) \
 	: "%r" (__m0), \
 	"r" (__m1)); \
 	(pl) = __m0 * __m1; \
diff --git a/lib/raid6/test/Makefile b/lib/raid6/test/Makefile
index 3ab8720aa2f8..b9e6c3648be1 100644
--- a/lib/raid6/test/Makefile
+++ b/lib/raid6/test/Makefile
@@ -35,13 +35,13 @@ endif
 ifeq ($(IS_X86),yes)
         OBJS   += mmx.o sse1.o sse2.o avx2.o recov_ssse3.o recov_avx2.o avx512.o recov_avx512.o
         CFLAGS += $(shell echo "pshufb %xmm0, %xmm0" |		\
-                    gcc -c -x assembler - >&/dev/null &&	\
+                    gcc -c -x assembler - >/dev/null 2>&1 &&	\
                     rm ./-.o && echo -DCONFIG_AS_SSSE3=1)
         CFLAGS += $(shell echo "vpbroadcastb %xmm0, %ymm1" |	\
-                    gcc -c -x assembler - >&/dev/null &&	\
+                    gcc -c -x assembler - >/dev/null 2>&1 &&	\
                     rm ./-.o && echo -DCONFIG_AS_AVX2=1)
 	CFLAGS += $(shell echo "vpmovm2b %k1, %zmm5" |          \
-		    gcc -c -x assembler - >&/dev/null &&        \
+		    gcc -c -x assembler - >/dev/null 2>&1 &&	\
 		    rm ./-.o && echo -DCONFIG_AS_AVX512=1)
 else ifeq ($(HAS_NEON),yes)
         OBJS   += neon.o neon1.o neon2.o neon4.o neon8.o recov_neon.o recov_neon_inner.o
diff --git a/lib/random32.c b/lib/random32.c
index 763b920a6206..3d749abb9e80 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -48,7 +48,7 @@ static inline void prandom_state_selftest(void)
 }
 #endif
 
-static DEFINE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy;
+DEFINE_PER_CPU(struct rnd_state, net_rand_state);
 
 /**
  *	prandom_u32_state - seeded pseudo-random number generator.
diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index 54f57cd117c6..85ab49344a23 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -671,8 +671,8 @@ void sbitmap_add_wait_queue(struct sbitmap_queue *sbq,
 	if (!sbq_wait->sbq) {
 		sbq_wait->sbq = sbq;
 		atomic_inc(&sbq->ws_active);
+		add_wait_queue(&ws->wait, &sbq_wait->wait);
 	}
-	add_wait_queue(&ws->wait, &sbq_wait->wait);
 }
 EXPORT_SYMBOL_GPL(sbitmap_add_wait_queue);
 
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index eacb82468437..a79ef84f0fd6 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -303,7 +303,7 @@ int __sg_alloc_table(struct sg_table *table, unsigned int nents,
 			if (prv)
 				table->nents = ++table->orig_nents;
 
- 			return -ENOMEM;
+			return -ENOMEM;
 		}
 
 		sg_init_table(sg, alloc_size);
diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index 66cab785bea0..aae3577b0392 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -83,15 +83,19 @@ static bool init_stack_slab(void **prealloc)
 		return true;
 	if (stack_slabs[depot_index] == NULL) {
 		stack_slabs[depot_index] = *prealloc;
+		*prealloc = NULL;
 	} else {
-		stack_slabs[depot_index + 1] = *prealloc;
+		/* If this is the last depot slab, do not touch the next one. */
+		if (depot_index + 1 < STACK_ALLOC_MAX_SLABS) {
+			stack_slabs[depot_index + 1] = *prealloc;
+			*prealloc = NULL;
+		}
 		/*
 		 * This smp_store_release pairs with smp_load_acquire() from
 		 * |next_slab_inited| above and in depot_save_stack().
 		 */
 		smp_store_release(&next_slab_inited, 1);
 	}
-	*prealloc = NULL;
 	return true;
 }
 
diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c
index 023ba9f3b99f..10af8be1cace 100644
--- a/lib/strncpy_from_user.c
+++ b/lib/strncpy_from_user.c
@@ -29,13 +29,6 @@ static inline long do_strncpy_from_user(char *dst, const char __user *src,
 	const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
 	unsigned long res = 0;
 
-	/*
-	 * Truncate 'max' to the user-specified limit, so that
-	 * we only have one limit we need to check in the loop
-	 */
-	if (max > count)
-		max = count;
-
 	if (IS_UNALIGNED(src, dst))
 		goto byte_at_a_time;
 
@@ -113,6 +106,13 @@ long strncpy_from_user(char *dst, const char __user *src, long count)
 		unsigned long max = max_addr - src_addr;
 		long retval;
 
+		/*
+		 * Truncate 'max' to the user-specified limit, so that
+		 * we only have one limit we need to check in the loop
+		 */
+		if (max > count)
+			max = count;
+
 		kasan_check_write(dst, count);
 		check_object_size(dst, count, false);
 		if (user_access_begin(src, max)) {
diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c
index 7f2db3fe311f..069fc8e463d0 100644
--- a/lib/strnlen_user.c
+++ b/lib/strnlen_user.c
@@ -32,13 +32,6 @@ static inline long do_strnlen_user(const char __user *src, unsigned long count,
 	unsigned long c;
 
 	/*
-	 * Truncate 'max' to the user-specified limit, so that
-	 * we only have one limit we need to check in the loop
-	 */
-	if (max > count)
-		max = count;
-
-	/*
 	 * Do everything aligned. But that means that we
 	 * need to also expand the maximum..
 	 */
@@ -114,6 +107,13 @@ long strnlen_user(const char __user *str, long count)
 		unsigned long max = max_addr - src_addr;
 		long retval;
 
+		/*
+		 * Truncate 'max' to the user-specified limit, so that
+		 * we only have one limit we need to check in the loop
+		 */
+		if (max > count)
+			max = count;
+
 		if (user_access_begin(str, max)) {
 			retval = do_strnlen_user(str, count, max);
 			user_access_end();
diff --git a/lib/test_kasan.c b/lib/test_kasan.c
index e3c593c38eff..e67c7749272c 100644
--- a/lib/test_kasan.c
+++ b/lib/test_kasan.c
@@ -7,16 +7,17 @@
 
 #define pr_fmt(fmt) "kasan test: %s " fmt, __func__
 
+#include <linux/bitops.h>
 #include <linux/delay.h>
+#include <linux/kasan.h>
 #include <linux/kernel.h>
-#include <linux/mman.h>
 #include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/module.h>
 #include <linux/printk.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/uaccess.h>
-#include <linux/module.h>
-#include <linux/kasan.h>
 
 /*
  * Note: test functions are marked noinline so that their names appear in
@@ -153,6 +154,7 @@ static noinline void __init kmalloc_oob_krealloc_more(void)
 	if (!ptr1 || !ptr2) {
 		pr_err("Allocation failed\n");
 		kfree(ptr1);
+		kfree(ptr2);
 		return;
 	}
 
@@ -619,6 +621,79 @@ static noinline void __init kasan_strings(void)
 	strnlen(ptr, 1);
 }
 
+static noinline void __init kasan_bitops(void)
+{
+	/*
+	 * Allocate 1 more byte, which causes kzalloc to round up to 16-bytes;
+	 * this way we do not actually corrupt other memory.
+	 */
+	long *bits = kzalloc(sizeof(*bits) + 1, GFP_KERNEL);
+	if (!bits)
+		return;
+
+	/*
+	 * Below calls try to access bit within allocated memory; however, the
+	 * below accesses are still out-of-bounds, since bitops are defined to
+	 * operate on the whole long the bit is in.
+	 */
+	pr_info("out-of-bounds in set_bit\n");
+	set_bit(BITS_PER_LONG, bits);
+
+	pr_info("out-of-bounds in __set_bit\n");
+	__set_bit(BITS_PER_LONG, bits);
+
+	pr_info("out-of-bounds in clear_bit\n");
+	clear_bit(BITS_PER_LONG, bits);
+
+	pr_info("out-of-bounds in __clear_bit\n");
+	__clear_bit(BITS_PER_LONG, bits);
+
+	pr_info("out-of-bounds in clear_bit_unlock\n");
+	clear_bit_unlock(BITS_PER_LONG, bits);
+
+	pr_info("out-of-bounds in __clear_bit_unlock\n");
+	__clear_bit_unlock(BITS_PER_LONG, bits);
+
+	pr_info("out-of-bounds in change_bit\n");
+	change_bit(BITS_PER_LONG, bits);
+
+	pr_info("out-of-bounds in __change_bit\n");
+	__change_bit(BITS_PER_LONG, bits);
+
+	/*
+	 * Below calls try to access bit beyond allocated memory.
+	 */
+	pr_info("out-of-bounds in test_and_set_bit\n");
+	test_and_set_bit(BITS_PER_LONG + BITS_PER_BYTE, bits);
+
+	pr_info("out-of-bounds in __test_and_set_bit\n");
+	__test_and_set_bit(BITS_PER_LONG + BITS_PER_BYTE, bits);
+
+	pr_info("out-of-bounds in test_and_set_bit_lock\n");
+	test_and_set_bit_lock(BITS_PER_LONG + BITS_PER_BYTE, bits);
+
+	pr_info("out-of-bounds in test_and_clear_bit\n");
+	test_and_clear_bit(BITS_PER_LONG + BITS_PER_BYTE, bits);
+
+	pr_info("out-of-bounds in __test_and_clear_bit\n");
+	__test_and_clear_bit(BITS_PER_LONG + BITS_PER_BYTE, bits);
+
+	pr_info("out-of-bounds in test_and_change_bit\n");
+	test_and_change_bit(BITS_PER_LONG + BITS_PER_BYTE, bits);
+
+	pr_info("out-of-bounds in __test_and_change_bit\n");
+	__test_and_change_bit(BITS_PER_LONG + BITS_PER_BYTE, bits);
+
+	pr_info("out-of-bounds in test_bit\n");
+	(void)test_bit(BITS_PER_LONG + BITS_PER_BYTE, bits);
+
+#if defined(clear_bit_unlock_is_negative_byte)
+	pr_info("out-of-bounds in clear_bit_unlock_is_negative_byte\n");
+	clear_bit_unlock_is_negative_byte(BITS_PER_LONG + BITS_PER_BYTE, bits);
+#endif
+	kfree(bits);
+}
+
 static int __init kmalloc_tests_init(void)
 {
 	/*
@@ -660,6 +735,7 @@ static int __init kmalloc_tests_init(void)
 	kasan_memchr();
 	kasan_memcmp();
 	kasan_strings();
+	kasan_bitops();
 
 	kasan_restore_multi_shot(multishot);
 
diff --git a/lib/test_kmod.c b/lib/test_kmod.c
index 9cf77628fc91..87a0cc750ea2 100644
--- a/lib/test_kmod.c
+++ b/lib/test_kmod.c
@@ -745,7 +745,7 @@ static int trigger_config_run_type(struct kmod_test_device *test_dev,
 		break;
 	case TEST_KMOD_FS_TYPE:
 		kfree_const(config->test_fs);
-		config->test_driver = NULL;
+		config->test_fs = NULL;
 		copied = config_copy_test_fs(config, test_str,
 					     strlen(test_str));
 		break;
diff --git a/lib/test_objagg.c b/lib/test_objagg.c
index 72c1abfa154d..da137939a410 100644
--- a/lib/test_objagg.c
+++ b/lib/test_objagg.c
@@ -979,10 +979,10 @@ err_check_expect_stats2:
 err_world2_obj_get:
 	for (i--; i >= 0; i--)
 		world_obj_put(&world2, objagg, hints_case->key_ids[i]);
-	objagg_hints_put(hints);
-	objagg_destroy(objagg2);
 	i = hints_case->key_ids_count;
+	objagg_destroy(objagg2);
 err_check_expect_hints_stats:
+	objagg_hints_put(hints);
 err_hints_get:
 err_check_expect_stats:
 err_world_obj_get:
diff --git a/lib/test_printf.c b/lib/test_printf.c
index 944eb50f3862..a10a276e95c3 100644
--- a/lib/test_printf.c
+++ b/lib/test_printf.c
@@ -212,6 +212,7 @@ test_string(void)
 #define PTR_STR "ffff0123456789ab"
 #define PTR_VAL_NO_CRNG "(____ptrval____)"
 #define ZEROS "00000000"	/* hex 32 zero bits */
+#define ONES "ffffffff"		/* hex 32 one bits */
 
 static int __init
 plain_format(void)
@@ -243,6 +244,7 @@ plain_format(void)
 #define PTR_STR "456789ab"
 #define PTR_VAL_NO_CRNG "(ptrval)"
 #define ZEROS ""
+#define ONES ""
 
 static int __init
 plain_format(void)
@@ -328,14 +330,28 @@ test_hashed(const char *fmt, const void *p)
 	test(buf, fmt, p);
 }
 
+/*
+ * NULL pointers aren't hashed.
+ */
 static void __init
 null_pointer(void)
 {
-	test_hashed("%p", NULL);
+	test(ZEROS "00000000", "%p", NULL);
 	test(ZEROS "00000000", "%px", NULL);
 	test("(null)", "%pE", NULL);
 }
 
+/*
+ * Error pointers aren't hashed.
+ */
+static void __init
+error_pointer(void)
+{
+	test(ONES "fffffff5", "%p", ERR_PTR(-11));
+	test(ONES "fffffff5", "%px", ERR_PTR(-11));
+	test("(efault)", "%pE", ERR_PTR(-11));
+}
+
 #define PTR_INVALID ((void *)0x000000ab)
 
 static void __init
@@ -593,6 +609,7 @@ test_pointer(void)
 {
 	plain();
 	null_pointer();
+	error_pointer();
 	invalid_pointer();
 	symbol_ptr();
 	kernel_ptr();
diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index 7df4f7f395bf..d4f97925dbd8 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -2,6 +2,7 @@
 /*
  * test_xarray.c: Test the XArray API
  * Copyright (c) 2017-2018 Microsoft Corporation
+ * Copyright (c) 2019-2020 Oracle
  * Author: Matthew Wilcox <willy@infradead.org>
  */
 
@@ -11,6 +12,9 @@
 static unsigned int tests_run;
 static unsigned int tests_passed;
 
+static const unsigned int order_limit =
+		IS_ENABLED(CONFIG_XARRAY_MULTI) ? BITS_PER_LONG : 1;
+
 #ifndef XA_DEBUG
 # ifdef __KERNEL__
 void xa_dump(const struct xarray *xa) { }
@@ -902,28 +906,34 @@ static noinline void check_store_iter(struct xarray *xa)
 	XA_BUG_ON(xa, !xa_empty(xa));
 }
 
-static noinline void check_multi_find(struct xarray *xa)
+static noinline void check_multi_find_1(struct xarray *xa, unsigned order)
 {
 #ifdef CONFIG_XARRAY_MULTI
+	unsigned long multi = 3 << order;
+	unsigned long next = 4 << order;
 	unsigned long index;
 
-	xa_store_order(xa, 12, 2, xa_mk_value(12), GFP_KERNEL);
-	XA_BUG_ON(xa, xa_store_index(xa, 16, GFP_KERNEL) != NULL);
+	xa_store_order(xa, multi, order, xa_mk_value(multi), GFP_KERNEL);
+	XA_BUG_ON(xa, xa_store_index(xa, next, GFP_KERNEL) != NULL);
+	XA_BUG_ON(xa, xa_store_index(xa, next + 1, GFP_KERNEL) != NULL);
 
 	index = 0;
 	XA_BUG_ON(xa, xa_find(xa, &index, ULONG_MAX, XA_PRESENT) !=
-			xa_mk_value(12));
-	XA_BUG_ON(xa, index != 12);
-	index = 13;
+			xa_mk_value(multi));
+	XA_BUG_ON(xa, index != multi);
+	index = multi + 1;
 	XA_BUG_ON(xa, xa_find(xa, &index, ULONG_MAX, XA_PRESENT) !=
-			xa_mk_value(12));
-	XA_BUG_ON(xa, (index < 12) || (index >= 16));
+			xa_mk_value(multi));
+	XA_BUG_ON(xa, (index < multi) || (index >= next));
 	XA_BUG_ON(xa, xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT) !=
-			xa_mk_value(16));
-	XA_BUG_ON(xa, index != 16);
-
-	xa_erase_index(xa, 12);
-	xa_erase_index(xa, 16);
+			xa_mk_value(next));
+	XA_BUG_ON(xa, index != next);
+	XA_BUG_ON(xa, xa_find_after(xa, &index, next, XA_PRESENT) != NULL);
+	XA_BUG_ON(xa, index != next);
+
+	xa_erase_index(xa, multi);
+	xa_erase_index(xa, next);
+	xa_erase_index(xa, next + 1);
 	XA_BUG_ON(xa, !xa_empty(xa));
 #endif
 }
@@ -952,6 +962,20 @@ static noinline void check_multi_find_2(struct xarray *xa)
 	}
 }
 
+static noinline void check_multi_find_3(struct xarray *xa)
+{
+	unsigned int order;
+
+	for (order = 5; order < order_limit; order++) {
+		unsigned long index = 1UL << (order - 5);
+
+		XA_BUG_ON(xa, !xa_empty(xa));
+		xa_store_order(xa, 0, order - 4, xa_mk_index(0), GFP_KERNEL);
+		XA_BUG_ON(xa, xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT));
+		xa_erase_index(xa, 0);
+	}
+}
+
 static noinline void check_find_1(struct xarray *xa)
 {
 	unsigned long i, j, k;
@@ -1046,13 +1070,35 @@ static noinline void check_find_3(struct xarray *xa)
 	xa_destroy(xa);
 }
 
+static noinline void check_find_4(struct xarray *xa)
+{
+	unsigned long index = 0;
+	void *entry;
+
+	xa_store_index(xa, ULONG_MAX, GFP_KERNEL);
+
+	entry = xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT);
+	XA_BUG_ON(xa, entry != xa_mk_index(ULONG_MAX));
+
+	entry = xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT);
+	XA_BUG_ON(xa, entry);
+
+	xa_erase_index(xa, ULONG_MAX);
+}
+
 static noinline void check_find(struct xarray *xa)
 {
+	unsigned i;
+
 	check_find_1(xa);
 	check_find_2(xa);
 	check_find_3(xa);
-	check_multi_find(xa);
+	check_find_4(xa);
+
+	for (i = 2; i < 10; i++)
+		check_multi_find_1(xa, i);
 	check_multi_find_2(xa);
+	check_multi_find_3(xa);
 }
 
 /* See find_swap_entry() in mm/shmem.c */
@@ -1110,6 +1156,42 @@ static noinline void check_find_entry(struct xarray *xa)
 	XA_BUG_ON(xa, !xa_empty(xa));
 }
 
+static noinline void check_pause(struct xarray *xa)
+{
+	XA_STATE(xas, xa, 0);
+	void *entry;
+	unsigned int order;
+	unsigned long index = 1;
+	unsigned int count = 0;
+
+	for (order = 0; order < order_limit; order++) {
+		XA_BUG_ON(xa, xa_store_order(xa, index, order,
+					xa_mk_index(index), GFP_KERNEL));
+		index += 1UL << order;
+	}
+
+	rcu_read_lock();
+	xas_for_each(&xas, entry, ULONG_MAX) {
+		XA_BUG_ON(xa, entry != xa_mk_index(1UL << count));
+		count++;
+	}
+	rcu_read_unlock();
+	XA_BUG_ON(xa, count != order_limit);
+
+	count = 0;
+	xas_set(&xas, 0);
+	rcu_read_lock();
+	xas_for_each(&xas, entry, ULONG_MAX) {
+		XA_BUG_ON(xa, entry != xa_mk_index(1UL << count));
+		count++;
+		xas_pause(&xas);
+	}
+	rcu_read_unlock();
+	XA_BUG_ON(xa, count != order_limit);
+
+	xa_destroy(xa);
+}
+
 static noinline void check_move_tiny(struct xarray *xa)
 {
 	XA_STATE(xas, xa, 0);
@@ -1132,6 +1214,27 @@ static noinline void check_move_tiny(struct xarray *xa)
 	XA_BUG_ON(xa, !xa_empty(xa));
 }
 
+static noinline void check_move_max(struct xarray *xa)
+{
+	XA_STATE(xas, xa, 0);
+
+	xa_store_index(xa, ULONG_MAX, GFP_KERNEL);
+	rcu_read_lock();
+	XA_BUG_ON(xa, xas_find(&xas, ULONG_MAX) != xa_mk_index(ULONG_MAX));
+	XA_BUG_ON(xa, xas_find(&xas, ULONG_MAX) != NULL);
+	rcu_read_unlock();
+
+	xas_set(&xas, 0);
+	rcu_read_lock();
+	XA_BUG_ON(xa, xas_find(&xas, ULONG_MAX) != xa_mk_index(ULONG_MAX));
+	xas_pause(&xas);
+	XA_BUG_ON(xa, xas_find(&xas, ULONG_MAX) != NULL);
+	rcu_read_unlock();
+
+	xa_erase_index(xa, ULONG_MAX);
+	XA_BUG_ON(xa, !xa_empty(xa));
+}
+
 static noinline void check_move_small(struct xarray *xa, unsigned long idx)
 {
 	XA_STATE(xas, xa, 0);
@@ -1240,6 +1343,7 @@ static noinline void check_move(struct xarray *xa)
 	xa_destroy(xa);
 
 	check_move_tiny(xa);
+	check_move_max(xa);
 
 	for (i = 0; i < 16; i++)
 		check_move_small(xa, 1UL << i);
@@ -1596,6 +1700,7 @@ static int xarray_checks(void)
 	check_xa_alloc();
 	check_find(&array);
 	check_find_entry(&array);
+	check_pause(&array);
 	check_account(&array);
 	check_destroy(&array);
 	check_move(&array);
diff --git a/lib/ubsan.c b/lib/ubsan.c
index 0c4681118fcd..f007a406f89c 100644
--- a/lib/ubsan.c
+++ b/lib/ubsan.c
@@ -140,25 +140,21 @@ static void val_to_string(char *str, size_t size, struct type_descriptor *type,
 	}
 }
 
-static DEFINE_SPINLOCK(report_lock);
-
-static void ubsan_prologue(struct source_location *location,
-			unsigned long *flags)
+static void ubsan_prologue(struct source_location *location)
 {
 	current->in_ubsan++;
-	spin_lock_irqsave(&report_lock, *flags);
 
 	pr_err("========================================"
 		"========================================\n");
 	print_source_location("UBSAN: Undefined behaviour in", location);
 }
 
-static void ubsan_epilogue(unsigned long *flags)
+static void ubsan_epilogue(void)
 {
 	dump_stack();
 	pr_err("========================================"
 		"========================================\n");
-	spin_unlock_irqrestore(&report_lock, *flags);
+
 	current->in_ubsan--;
 }
 
@@ -167,14 +163,13 @@ static void handle_overflow(struct overflow_data *data, void *lhs,
 {
 
 	struct type_descriptor *type = data->type;
-	unsigned long flags;
 	char lhs_val_str[VALUE_LENGTH];
 	char rhs_val_str[VALUE_LENGTH];
 
 	if (suppress_report(&data->location))
 		return;
 
-	ubsan_prologue(&data->location, &flags);
+	ubsan_prologue(&data->location);
 
 	val_to_string(lhs_val_str, sizeof(lhs_val_str), type, lhs);
 	val_to_string(rhs_val_str, sizeof(rhs_val_str), type, rhs);
@@ -186,7 +181,7 @@ static void handle_overflow(struct overflow_data *data, void *lhs,
 		rhs_val_str,
 		type->type_name);
 
-	ubsan_epilogue(&flags);
+	ubsan_epilogue();
 }
 
 void __ubsan_handle_add_overflow(struct overflow_data *data,
@@ -214,20 +209,19 @@ EXPORT_SYMBOL(__ubsan_handle_mul_overflow);
 void __ubsan_handle_negate_overflow(struct overflow_data *data,
 				void *old_val)
 {
-	unsigned long flags;
 	char old_val_str[VALUE_LENGTH];
 
 	if (suppress_report(&data->location))
 		return;
 
-	ubsan_prologue(&data->location, &flags);
+	ubsan_prologue(&data->location);
 
 	val_to_string(old_val_str, sizeof(old_val_str), data->type, old_val);
 
 	pr_err("negation of %s cannot be represented in type %s:\n",
 		old_val_str, data->type->type_name);
 
-	ubsan_epilogue(&flags);
+	ubsan_epilogue();
 }
 EXPORT_SYMBOL(__ubsan_handle_negate_overflow);
 
@@ -235,13 +229,12 @@ EXPORT_SYMBOL(__ubsan_handle_negate_overflow);
 void __ubsan_handle_divrem_overflow(struct overflow_data *data,
 				void *lhs, void *rhs)
 {
-	unsigned long flags;
 	char rhs_val_str[VALUE_LENGTH];
 
 	if (suppress_report(&data->location))
 		return;
 
-	ubsan_prologue(&data->location, &flags);
+	ubsan_prologue(&data->location);
 
 	val_to_string(rhs_val_str, sizeof(rhs_val_str), data->type, rhs);
 
@@ -251,58 +244,52 @@ void __ubsan_handle_divrem_overflow(struct overflow_data *data,
 	else
 		pr_err("division by zero\n");
 
-	ubsan_epilogue(&flags);
+	ubsan_epilogue();
 }
 EXPORT_SYMBOL(__ubsan_handle_divrem_overflow);
 
 static void handle_null_ptr_deref(struct type_mismatch_data_common *data)
 {
-	unsigned long flags;
-
 	if (suppress_report(data->location))
 		return;
 
-	ubsan_prologue(data->location, &flags);
+	ubsan_prologue(data->location);
 
 	pr_err("%s null pointer of type %s\n",
 		type_check_kinds[data->type_check_kind],
 		data->type->type_name);
 
-	ubsan_epilogue(&flags);
+	ubsan_epilogue();
 }
 
 static void handle_misaligned_access(struct type_mismatch_data_common *data,
 				unsigned long ptr)
 {
-	unsigned long flags;
-
 	if (suppress_report(data->location))
 		return;
 
-	ubsan_prologue(data->location, &flags);
+	ubsan_prologue(data->location);
 
 	pr_err("%s misaligned address %p for type %s\n",
 		type_check_kinds[data->type_check_kind],
 		(void *)ptr, data->type->type_name);
 	pr_err("which requires %ld byte alignment\n", data->alignment);
 
-	ubsan_epilogue(&flags);
+	ubsan_epilogue();
 }
 
 static void handle_object_size_mismatch(struct type_mismatch_data_common *data,
 					unsigned long ptr)
 {
-	unsigned long flags;
-
 	if (suppress_report(data->location))
 		return;
 
-	ubsan_prologue(data->location, &flags);
+	ubsan_prologue(data->location);
 	pr_err("%s address %p with insufficient space\n",
 		type_check_kinds[data->type_check_kind],
 		(void *) ptr);
 	pr_err("for an object of type %s\n", data->type->type_name);
-	ubsan_epilogue(&flags);
+	ubsan_epilogue();
 }
 
 static void ubsan_type_mismatch_common(struct type_mismatch_data_common *data,
@@ -351,25 +338,23 @@ EXPORT_SYMBOL(__ubsan_handle_type_mismatch_v1);
 
 void __ubsan_handle_out_of_bounds(struct out_of_bounds_data *data, void *index)
 {
-	unsigned long flags;
 	char index_str[VALUE_LENGTH];
 
 	if (suppress_report(&data->location))
 		return;
 
-	ubsan_prologue(&data->location, &flags);
+	ubsan_prologue(&data->location);
 
 	val_to_string(index_str, sizeof(index_str), data->index_type, index);
 	pr_err("index %s is out of range for type %s\n", index_str,
 		data->array_type->type_name);
-	ubsan_epilogue(&flags);
+	ubsan_epilogue();
 }
 EXPORT_SYMBOL(__ubsan_handle_out_of_bounds);
 
 void __ubsan_handle_shift_out_of_bounds(struct shift_out_of_bounds_data *data,
 					void *lhs, void *rhs)
 {
-	unsigned long flags;
 	struct type_descriptor *rhs_type = data->rhs_type;
 	struct type_descriptor *lhs_type = data->lhs_type;
 	char rhs_str[VALUE_LENGTH];
@@ -379,7 +364,7 @@ void __ubsan_handle_shift_out_of_bounds(struct shift_out_of_bounds_data *data,
 	if (suppress_report(&data->location))
 		goto out;
 
-	ubsan_prologue(&data->location, &flags);
+	ubsan_prologue(&data->location);
 
 	val_to_string(rhs_str, sizeof(rhs_str), rhs_type, rhs);
 	val_to_string(lhs_str, sizeof(lhs_str), lhs_type, lhs);
@@ -402,7 +387,7 @@ void __ubsan_handle_shift_out_of_bounds(struct shift_out_of_bounds_data *data,
 			lhs_str, rhs_str,
 			lhs_type->type_name);
 
-	ubsan_epilogue(&flags);
+	ubsan_epilogue();
 out:
 	user_access_restore(ua_flags);
 }
@@ -411,11 +396,9 @@ EXPORT_SYMBOL(__ubsan_handle_shift_out_of_bounds);
 
 void __ubsan_handle_builtin_unreachable(struct unreachable_data *data)
 {
-	unsigned long flags;
-
-	ubsan_prologue(&data->location, &flags);
+	ubsan_prologue(&data->location);
 	pr_err("calling __builtin_unreachable()\n");
-	ubsan_epilogue(&flags);
+	ubsan_epilogue();
 	panic("can't return from __builtin_unreachable()");
 }
 EXPORT_SYMBOL(__ubsan_handle_builtin_unreachable);
@@ -423,19 +406,18 @@ EXPORT_SYMBOL(__ubsan_handle_builtin_unreachable);
 void __ubsan_handle_load_invalid_value(struct invalid_value_data *data,
 				void *val)
 {
-	unsigned long flags;
 	char val_str[VALUE_LENGTH];
 
 	if (suppress_report(&data->location))
 		return;
 
-	ubsan_prologue(&data->location, &flags);
+	ubsan_prologue(&data->location);
 
 	val_to_string(val_str, sizeof(val_str), data->type, val);
 
 	pr_err("load of value %s is not a valid value for type %s\n",
 		val_str, data->type->type_name);
 
-	ubsan_epilogue(&flags);
+	ubsan_epilogue();
 }
 EXPORT_SYMBOL(__ubsan_handle_load_invalid_value);
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 63937044c57d..672b1817e639 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -746,6 +746,13 @@ static char *ptr_to_id(char *buf, char *end, const void *ptr,
 	const char *str = sizeof(ptr) == 8 ? "(____ptrval____)" : "(ptrval)";
 	unsigned long hashval;
 
+	/*
+	 * Print the real pointer value for NULL and error pointers,
+	 * as they are not actual addresses.
+	 */
+	if (IS_ERR_OR_NULL(ptr))
+		return pointer_string(buf, end, ptr, spec);
+
 	/* When debugging early boot use non-cryptographically secure hash. */
 	if (unlikely(debug_boot_weak_hash)) {
 		hashval = hash_long((unsigned long)ptr, 32);
@@ -869,6 +876,15 @@ char *dentry_name(char *buf, char *end, const struct dentry *d, struct printf_sp
 	return widen_string(buf, n, end, spec);
 }
 
+static noinline_for_stack
+char *file_dentry_name(char *buf, char *end, const struct file *f,
+			struct printf_spec spec, const char *fmt)
+{
+	if (check_pointer(&buf, end, f, spec))
+		return buf;
+
+	return dentry_name(buf, end, f->f_path.dentry, spec, fmt);
+}
 #ifdef CONFIG_BLOCK
 static noinline_for_stack
 char *bdev_name(char *buf, char *end, struct block_device *bdev,
@@ -1799,7 +1815,7 @@ char *clock(char *buf, char *end, struct clk *clk, struct printf_spec spec,
 #ifdef CONFIG_COMMON_CLK
 		return string(buf, end, __clk_get_name(clk), spec);
 #else
-		return error_string(buf, end, "(%pC?)", spec);
+		return ptr_to_id(buf, end, clk, spec);
 #endif
 	}
 }
@@ -2166,9 +2182,7 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 	case 'C':
 		return clock(buf, end, ptr, spec, fmt);
 	case 'D':
-		return dentry_name(buf, end,
-				   ((const struct file *)ptr)->f_path.dentry,
-				   spec, fmt);
+		return file_dentry_name(buf, end, ptr, spec, fmt);
 #ifdef CONFIG_BLOCK
 	case 'g':
 		return bdev_name(buf, end, ptr, spec, fmt);
diff --git a/lib/xarray.c b/lib/xarray.c
index 1237c213f52b..08d71c7b7599 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0+
 /*
  * XArray implementation
- * Copyright (c) 2017 Microsoft Corporation
+ * Copyright (c) 2017-2018 Microsoft Corporation
+ * Copyright (c) 2018-2020 Oracle
  * Author: Matthew Wilcox <willy@infradead.org>
  */
 
@@ -967,17 +968,19 @@ void xas_pause(struct xa_state *xas)
 	if (xas_invalid(xas))
 		return;
 
+	xas->xa_node = XAS_RESTART;
 	if (node) {
-		unsigned int offset = xas->xa_offset;
+		unsigned long offset = xas->xa_offset;
 		while (++offset < XA_CHUNK_SIZE) {
 			if (!xa_is_sibling(xa_entry(xas->xa, node, offset)))
 				break;
 		}
 		xas->xa_index += (offset - xas->xa_offset) << node->shift;
+		if (xas->xa_index == 0)
+			xas->xa_node = XAS_BOUNDS;
 	} else {
 		xas->xa_index++;
 	}
-	xas->xa_node = XAS_RESTART;
 }
 EXPORT_SYMBOL_GPL(xas_pause);
 
@@ -1079,13 +1082,15 @@ void *xas_find(struct xa_state *xas, unsigned long max)
 {
 	void *entry;
 
-	if (xas_error(xas))
+	if (xas_error(xas) || xas->xa_node == XAS_BOUNDS)
 		return NULL;
+	if (xas->xa_index > max)
+		return set_bounds(xas);
 
 	if (!xas->xa_node) {
 		xas->xa_index = 1;
 		return set_bounds(xas);
-	} else if (xas_top(xas->xa_node)) {
+	} else if (xas->xa_node == XAS_RESTART) {
 		entry = xas_load(xas);
 		if (entry || xas_not_node(xas->xa_node))
 			return entry;
@@ -1150,6 +1155,8 @@ void *xas_find_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark)
 
 	if (xas_error(xas))
 		return NULL;
+	if (xas->xa_index > max)
+		goto max;
 
 	if (!xas->xa_node) {
 		xas->xa_index = 1;
@@ -1201,6 +1208,8 @@ void *xas_find_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark)
 		}
 
 		entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset);
+		if (!entry && !(xa_track_free(xas->xa) && mark == XA_FREE_MARK))
+			continue;
 		if (!xa_is_node(entry))
 			return entry;
 		xas->xa_node = xa_to_node(entry);
@@ -1824,6 +1833,18 @@ void *xa_find(struct xarray *xa, unsigned long *indexp,
 }
 EXPORT_SYMBOL(xa_find);
 
+static bool xas_sibling(struct xa_state *xas)
+{
+	struct xa_node *node = xas->xa_node;
+	unsigned long mask;
+
+	if (!node)
+		return false;
+	mask = (XA_CHUNK_SIZE << node->shift) - 1;
+	return (xas->xa_index & mask) >
+		((unsigned long)xas->xa_offset << node->shift);
+}
+
 /**
  * xa_find_after() - Search the XArray for a present entry.
  * @xa: XArray.
@@ -1847,21 +1868,20 @@ void *xa_find_after(struct xarray *xa, unsigned long *indexp,
 	XA_STATE(xas, xa, *indexp + 1);
 	void *entry;
 
+	if (xas.xa_index == 0)
+		return NULL;
+
 	rcu_read_lock();
 	for (;;) {
 		if ((__force unsigned int)filter < XA_MAX_MARKS)
 			entry = xas_find_marked(&xas, max, filter);
 		else
 			entry = xas_find(&xas, max);
-		if (xas.xa_node == XAS_BOUNDS)
+
+		if (xas_invalid(&xas))
 			break;
-		if (xas.xa_shift) {
-			if (xas.xa_index & ((1UL << xas.xa_shift) - 1))
-				continue;
-		} else {
-			if (xas.xa_offset < (xas.xa_index & XA_CHUNK_MASK))
-				continue;
-		}
+		if (xas_sibling(&xas))
+			continue;
 		if (!xas_retry(&xas, entry))
 			break;
 	}
diff --git a/lib/zlib_inflate/inffast.c b/lib/zlib_inflate/inffast.c
index 2c13ecc5bb2c..ed1f3df27260 100644
--- a/lib/zlib_inflate/inffast.c
+++ b/lib/zlib_inflate/inffast.c
@@ -10,17 +10,6 @@
 
 #ifndef ASMINF
 
-/* Allow machine dependent optimization for post-increment or pre-increment.
-   Based on testing to date,
-   Pre-increment preferred for:
-   - PowerPC G3 (Adler)
-   - MIPS R5000 (Randers-Pehrson)
-   Post-increment preferred for:
-   - none
-   No measurable difference:
-   - Pentium III (Anderson)
-   - M68060 (Nikl)
- */
 union uu {
 	unsigned short us;
 	unsigned char b[2];
@@ -38,16 +27,6 @@ get_unaligned16(const unsigned short *p)
 	return mm.us;
 }
 
-#ifdef POSTINC
-#  define OFF 0
-#  define PUP(a) *(a)++
-#  define UP_UNALIGNED(a) get_unaligned16((a)++)
-#else
-#  define OFF 1
-#  define PUP(a) *++(a)
-#  define UP_UNALIGNED(a) get_unaligned16(++(a))
-#endif
-
 /*
    Decode literal, length, and distance codes and write out the resulting
    literal and match bytes until either not enough input or output is
@@ -115,9 +94,9 @@ void inflate_fast(z_streamp strm, unsigned start)
 
     /* copy state to local variables */
     state = (struct inflate_state *)strm->state;
-    in = strm->next_in - OFF;
+    in = strm->next_in;
     last = in + (strm->avail_in - 5);
-    out = strm->next_out - OFF;
+    out = strm->next_out;
     beg = out - (start - strm->avail_out);
     end = out + (strm->avail_out - 257);
 #ifdef INFLATE_STRICT
@@ -138,9 +117,9 @@ void inflate_fast(z_streamp strm, unsigned start)
        input data or output space */
     do {
         if (bits < 15) {
-            hold += (unsigned long)(PUP(in)) << bits;
+            hold += (unsigned long)(*in++) << bits;
             bits += 8;
-            hold += (unsigned long)(PUP(in)) << bits;
+            hold += (unsigned long)(*in++) << bits;
             bits += 8;
         }
         this = lcode[hold & lmask];
@@ -150,14 +129,14 @@ void inflate_fast(z_streamp strm, unsigned start)
         bits -= op;
         op = (unsigned)(this.op);
         if (op == 0) {                          /* literal */
-            PUP(out) = (unsigned char)(this.val);
+            *out++ = (unsigned char)(this.val);
         }
         else if (op & 16) {                     /* length base */
             len = (unsigned)(this.val);
             op &= 15;                           /* number of extra bits */
             if (op) {
                 if (bits < op) {
-                    hold += (unsigned long)(PUP(in)) << bits;
+                    hold += (unsigned long)(*in++) << bits;
                     bits += 8;
                 }
                 len += (unsigned)hold & ((1U << op) - 1);
@@ -165,9 +144,9 @@ void inflate_fast(z_streamp strm, unsigned start)
                 bits -= op;
             }
             if (bits < 15) {
-                hold += (unsigned long)(PUP(in)) << bits;
+                hold += (unsigned long)(*in++) << bits;
                 bits += 8;
-                hold += (unsigned long)(PUP(in)) << bits;
+                hold += (unsigned long)(*in++) << bits;
                 bits += 8;
             }
             this = dcode[hold & dmask];
@@ -180,10 +159,10 @@ void inflate_fast(z_streamp strm, unsigned start)
                 dist = (unsigned)(this.val);
                 op &= 15;                       /* number of extra bits */
                 if (bits < op) {
-                    hold += (unsigned long)(PUP(in)) << bits;
+                    hold += (unsigned long)(*in++) << bits;
                     bits += 8;
                     if (bits < op) {
-                        hold += (unsigned long)(PUP(in)) << bits;
+                        hold += (unsigned long)(*in++) << bits;
                         bits += 8;
                     }
                 }
@@ -205,13 +184,13 @@ void inflate_fast(z_streamp strm, unsigned start)
                         state->mode = BAD;
                         break;
                     }
-                    from = window - OFF;
+                    from = window;
                     if (write == 0) {           /* very common case */
                         from += wsize - op;
                         if (op < len) {         /* some from window */
                             len -= op;
                             do {
-                                PUP(out) = PUP(from);
+                                *out++ = *from++;
                             } while (--op);
                             from = out - dist;  /* rest from output */
                         }
@@ -222,14 +201,14 @@ void inflate_fast(z_streamp strm, unsigned start)
                         if (op < len) {         /* some from end of window */
                             len -= op;
                             do {
-                                PUP(out) = PUP(from);
+                                *out++ = *from++;
                             } while (--op);
-                            from = window - OFF;
+                            from = window;
                             if (write < len) {  /* some from start of window */
                                 op = write;
                                 len -= op;
                                 do {
-                                    PUP(out) = PUP(from);
+                                    *out++ = *from++;
                                 } while (--op);
                                 from = out - dist;      /* rest from output */
                             }
@@ -240,21 +219,21 @@ void inflate_fast(z_streamp strm, unsigned start)
                         if (op < len) {         /* some from window */
                             len -= op;
                             do {
-                                PUP(out) = PUP(from);
+                                *out++ = *from++;
                             } while (--op);
                             from = out - dist;  /* rest from output */
                         }
                     }
                     while (len > 2) {
-                        PUP(out) = PUP(from);
-                        PUP(out) = PUP(from);
-                        PUP(out) = PUP(from);
+                        *out++ = *from++;
+                        *out++ = *from++;
+                        *out++ = *from++;
                         len -= 3;
                     }
                     if (len) {
-                        PUP(out) = PUP(from);
+                        *out++ = *from++;
                         if (len > 1)
-                            PUP(out) = PUP(from);
+                            *out++ = *from++;
                     }
                 }
                 else {
@@ -264,29 +243,29 @@ void inflate_fast(z_streamp strm, unsigned start)
                     from = out - dist;          /* copy direct from output */
 		    /* minimum length is three */
 		    /* Align out addr */
-		    if (!((long)(out - 1 + OFF) & 1)) {
-			PUP(out) = PUP(from);
+		    if (!((long)(out - 1) & 1)) {
+			*out++ = *from++;
 			len--;
 		    }
-		    sout = (unsigned short *)(out - OFF);
+		    sout = (unsigned short *)(out);
 		    if (dist > 2) {
 			unsigned short *sfrom;
 
-			sfrom = (unsigned short *)(from - OFF);
+			sfrom = (unsigned short *)(from);
 			loops = len >> 1;
 			do
 #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
-			    PUP(sout) = PUP(sfrom);
+			    *sout++ = *sfrom++;
 #else
-			    PUP(sout) = UP_UNALIGNED(sfrom);
+			    *sout++ = get_unaligned16(sfrom++);
 #endif
 			while (--loops);
-			out = (unsigned char *)sout + OFF;
-			from = (unsigned char *)sfrom + OFF;
+			out = (unsigned char *)sout;
+			from = (unsigned char *)sfrom;
 		    } else { /* dist == 1 or dist == 2 */
 			unsigned short pat16;
 
-			pat16 = *(sout-1+OFF);
+			pat16 = *(sout-1);
 			if (dist == 1) {
 				union uu mm;
 				/* copy one char pattern to both bytes */
@@ -296,12 +275,12 @@ void inflate_fast(z_streamp strm, unsigned start)
 			}
 			loops = len >> 1;
 			do
-			    PUP(sout) = pat16;
+			    *sout++ = pat16;
 			while (--loops);
-			out = (unsigned char *)sout + OFF;
+			out = (unsigned char *)sout;
 		    }
 		    if (len & 1)
-			PUP(out) = PUP(from);
+			*out++ = *from++;
                 }
             }
             else if ((op & 64) == 0) {          /* 2nd level distance code */
@@ -336,8 +315,8 @@ void inflate_fast(z_streamp strm, unsigned start)
     hold &= (1U << bits) - 1;
 
     /* update state and return */
-    strm->next_in = in + OFF;
-    strm->next_out = out + OFF;
+    strm->next_in = in;
+    strm->next_out = out;
     strm->avail_in = (unsigned)(in < last ? 5 + (last - in) : 5 - (in - last));
     strm->avail_out = (unsigned)(out < end ?
                                  257 + (end - out) : 257 - (out - end));
diff --git a/mm/Kconfig b/mm/Kconfig
index f0c76ba47695..fcde50b13640 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -765,4 +765,14 @@ config GUP_BENCHMARK
 config ARCH_HAS_PTE_SPECIAL
 	bool
 
+#
+# Some architectures require a special hugepage directory format that is
+# required to support multiple hugepage sizes. For example a4fe3ce76
+# "powerpc/mm: Allow more flexible layouts for hugepage pagetables"
+# introduced it on powerpc.  This allows for a more flexible hugepage
+# pagetable layouts.
+#
+config ARCH_HAS_HUGEPD
+	bool
+
 endmenu
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 909dae445ea7..18ddd26967b6 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -20,6 +20,7 @@ struct backing_dev_info noop_backing_dev_info = {
 EXPORT_SYMBOL_GPL(noop_backing_dev_info);
 
 static struct class *bdi_class;
+static const char *bdi_unknown_name = "(unknown)";
 
 /*
  * bdi_lock protects updates to bdi_list. bdi_list has RCU reader side
@@ -880,7 +881,8 @@ int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args)
 	if (bdi->dev)	/* The driver needs to use separate queues per device */
 		return 0;
 
-	dev = device_create_vargs(bdi_class, NULL, MKDEV(0, 0), bdi, fmt, args);
+	vsnprintf(bdi->dev_name, sizeof(bdi->dev_name), fmt, args);
+	dev = device_create(bdi_class, NULL, MKDEV(0, 0), bdi, bdi->dev_name);
 	if (IS_ERR(dev))
 		return PTR_ERR(dev);
 
@@ -976,6 +978,14 @@ void bdi_put(struct backing_dev_info *bdi)
 }
 EXPORT_SYMBOL(bdi_put);
 
+const char *bdi_dev_name(struct backing_dev_info *bdi)
+{
+	if (!bdi || !bdi->dev)
+		return bdi_unknown_name;
+	return bdi->dev_name;
+}
+EXPORT_SYMBOL_GPL(bdi_dev_name);
+
 static wait_queue_head_t congestion_wqh[2] = {
 		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]),
 		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
diff --git a/mm/compaction.c b/mm/compaction.c
index 5ab9c2b22693..4df0841bd7cd 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -2311,16 +2311,26 @@ static enum compact_result compact_zone_order(struct zone *zone, int order,
 		.page = NULL,
 	};
 
-	if (capture)
-		current->capture_control = &capc;
+	/*
+	 * Make sure the structs are really initialized before we expose the
+	 * capture control, in case we are interrupted and the interrupt handler
+	 * frees a page.
+	 */
+	barrier();
+	WRITE_ONCE(current->capture_control, &capc);
 
 	ret = compact_zone(&cc, &capc);
 
 	VM_BUG_ON(!list_empty(&cc.freepages));
 	VM_BUG_ON(!list_empty(&cc.migratepages));
 
-	*capture = capc.page;
-	current->capture_control = NULL;
+	/*
+	 * Make sure we hide capture control first before we read the captured
+	 * page pointer, otherwise an interrupt could free and capture a page
+	 * and we would leak it.
+	 */
+	WRITE_ONCE(current->capture_control, NULL);
+	*capture = READ_ONCE(capc.page);
 
 	return ret;
 }
@@ -2334,6 +2344,7 @@ int sysctl_extfrag_threshold = 500;
  * @alloc_flags: The allocation flags of the current allocation
  * @ac: The context of current allocation
  * @prio: Determines how hard direct compaction should try to succeed
+ * @capture: Pointer to free page created by compaction will be stored here
  *
  * This is the main entry point for direct page compaction.
  */
diff --git a/mm/filemap.c b/mm/filemap.c
index 39ba6d939cc3..7301431fb34e 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2350,27 +2350,6 @@ EXPORT_SYMBOL(generic_file_read_iter);
 
 #ifdef CONFIG_MMU
 #define MMAP_LOTSAMISS  (100)
-static struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf,
-					     struct file *fpin)
-{
-	int flags = vmf->flags;
-
-	if (fpin)
-		return fpin;
-
-	/*
-	 * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or
-	 * anything, so we only pin the file and drop the mmap_sem if only
-	 * FAULT_FLAG_ALLOW_RETRY is set.
-	 */
-	if ((flags & (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT)) ==
-	    FAULT_FLAG_ALLOW_RETRY) {
-		fpin = get_file(vmf->vma->vm_file);
-		up_read(&vmf->vma->vm_mm->mmap_sem);
-	}
-	return fpin;
-}
-
 /*
  * lock_page_maybe_drop_mmap - lock the page, possibly dropping the mmap_sem
  * @vmf - the vm_fault for this fault.
@@ -2480,7 +2459,7 @@ static struct file *do_async_mmap_readahead(struct vm_fault *vmf,
 	pgoff_t offset = vmf->pgoff;
 
 	/* If we don't want any read-ahead, don't bother */
-	if (vmf->vma->vm_flags & VM_RAND_READ)
+	if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages)
 		return fpin;
 	if (ra->mmap_miss > 0)
 		ra->mmap_miss--;
diff --git a/mm/gup.c b/mm/gup.c
index d2c14fc4b5d4..68177ec67de7 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1881,8 +1881,92 @@ static int __gup_device_huge_pud(pud_t pud, pud_t *pudp, unsigned long addr,
 }
 #endif
 
+#ifdef CONFIG_ARCH_HAS_HUGEPD
+static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
+				      unsigned long sz)
+{
+	unsigned long __boundary = (addr + sz) & ~(sz-1);
+	return (__boundary - 1 < end - 1) ? __boundary : end;
+}
+
+static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
+		       unsigned long end, unsigned int flags,
+		       struct page **pages, int *nr)
+{
+	unsigned long pte_end;
+	struct page *head, *page;
+	pte_t pte;
+	int refs;
+
+	pte_end = (addr + sz) & ~(sz-1);
+	if (pte_end < end)
+		end = pte_end;
+
+	pte = READ_ONCE(*ptep);
+
+	if (!pte_access_permitted(pte, flags & FOLL_WRITE))
+		return 0;
+
+	/* hugepages are never "special" */
+	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+
+	refs = 0;
+	head = pte_page(pte);
+
+	page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
+	do {
+		VM_BUG_ON(compound_head(page) != head);
+		pages[*nr] = page;
+		(*nr)++;
+		page++;
+		refs++;
+	} while (addr += PAGE_SIZE, addr != end);
+
+	if (!page_cache_add_speculative(head, refs)) {
+		*nr -= refs;
+		return 0;
+	}
+
+	if (unlikely(pte_val(pte) != pte_val(*ptep))) {
+		/* Could be optimized better */
+		*nr -= refs;
+		while (refs--)
+			put_page(head);
+		return 0;
+	}
+
+	return 1;
+}
+
+static int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
+		unsigned int pdshift, unsigned long end, unsigned int flags,
+		struct page **pages, int *nr)
+{
+	pte_t *ptep;
+	unsigned long sz = 1UL << hugepd_shift(hugepd);
+	unsigned long next;
+
+	ptep = hugepte_offset(hugepd, addr, pdshift);
+	do {
+		next = hugepte_addr_end(addr, end, sz);
+		if (!gup_hugepte(ptep, sz, addr, end, flags, pages, nr))
+			return 0;
+	} while (ptep++, addr = next, addr != end);
+
+	return 1;
+}
+#else
+static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
+		unsigned int pdshift, unsigned long end, unsigned int flags,
+		struct page **pages, int *nr)
+{
+	return 0;
+}
+#endif /* CONFIG_ARCH_HAS_HUGEPD */
+
 static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
-		unsigned long end, unsigned int flags, struct page **pages, int *nr)
+			unsigned long end, unsigned int flags,
+			struct page **pages, int *nr)
 {
 	struct page *head, *page;
 	int refs;
diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c
index 7dd602d7f8db..ad9d5b1c4473 100644
--- a/mm/gup_benchmark.c
+++ b/mm/gup_benchmark.c
@@ -26,6 +26,7 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
 	unsigned long i, nr_pages, addr, next;
 	int nr;
 	struct page **pages;
+	int ret = 0;
 
 	if (gup->size > ULONG_MAX)
 		return -EINVAL;
@@ -63,7 +64,9 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
 					    NULL);
 			break;
 		default:
-			return -1;
+			kvfree(pages);
+			ret = -EINVAL;
+			goto out;
 		}
 
 		if (nr <= 0)
@@ -85,7 +88,8 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
 	gup->put_delta_usec = ktime_us_delta(end_time, start_time);
 
 	kvfree(pages);
-	return 0;
+out:
+	return ret;
 }
 
 static long gup_benchmark_ioctl(struct file *filep, unsigned int cmd,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 83236e22a8a8..7cc039aa63ab 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -172,16 +172,13 @@ static ssize_t enabled_store(struct kobject *kobj,
 {
 	ssize_t ret = count;
 
-	if (!memcmp("always", buf,
-		    min(sizeof("always")-1, count))) {
+	if (sysfs_streq(buf, "always")) {
 		clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
 		set_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
-	} else if (!memcmp("madvise", buf,
-			   min(sizeof("madvise")-1, count))) {
+	} else if (sysfs_streq(buf, "madvise")) {
 		clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
 		set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
-	} else if (!memcmp("never", buf,
-			   min(sizeof("never")-1, count))) {
+	} else if (sysfs_streq(buf, "never")) {
 		clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
 		clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
 	} else
@@ -245,32 +242,27 @@ static ssize_t defrag_store(struct kobject *kobj,
 			    struct kobj_attribute *attr,
 			    const char *buf, size_t count)
 {
-	if (!memcmp("always", buf,
-		    min(sizeof("always")-1, count))) {
+	if (sysfs_streq(buf, "always")) {
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
 		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
-	} else if (!memcmp("defer+madvise", buf,
-		    min(sizeof("defer+madvise")-1, count))) {
+	} else if (sysfs_streq(buf, "defer+madvise")) {
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
 		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
-	} else if (!memcmp("defer", buf,
-		    min(sizeof("defer")-1, count))) {
+	} else if (sysfs_streq(buf, "defer")) {
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
 		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
-	} else if (!memcmp("madvise", buf,
-			   min(sizeof("madvise")-1, count))) {
+	} else if (sysfs_streq(buf, "madvise")) {
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
 		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
-	} else if (!memcmp("never", buf,
-			   min(sizeof("never")-1, count))) {
+	} else if (sysfs_streq(buf, "never")) {
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
@@ -508,13 +500,13 @@ void prep_transhuge_page(struct page *page)
 	set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR);
 }
 
-static unsigned long __thp_get_unmapped_area(struct file *filp, unsigned long len,
+static unsigned long __thp_get_unmapped_area(struct file *filp,
+		unsigned long addr, unsigned long len,
 		loff_t off, unsigned long flags, unsigned long size)
 {
-	unsigned long addr;
 	loff_t off_end = off + len;
 	loff_t off_align = round_up(off, size);
-	unsigned long len_pad;
+	unsigned long len_pad, ret;
 
 	if (off_end <= off_align || (off_end - off_align) < size)
 		return 0;
@@ -523,30 +515,40 @@ static unsigned long __thp_get_unmapped_area(struct file *filp, unsigned long le
 	if (len_pad < len || (off + len_pad) < off)
 		return 0;
 
-	addr = current->mm->get_unmapped_area(filp, 0, len_pad,
+	ret = current->mm->get_unmapped_area(filp, addr, len_pad,
 					      off >> PAGE_SHIFT, flags);
-	if (IS_ERR_VALUE(addr))
+
+	/*
+	 * The failure might be due to length padding. The caller will retry
+	 * without the padding.
+	 */
+	if (IS_ERR_VALUE(ret))
 		return 0;
 
-	addr += (off - addr) & (size - 1);
-	return addr;
+	/*
+	 * Do not try to align to THP boundary if allocation at the address
+	 * hint succeeds.
+	 */
+	if (ret == addr)
+		return addr;
+
+	ret += (off - ret) & (size - 1);
+	return ret;
 }
 
 unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr,
 		unsigned long len, unsigned long pgoff, unsigned long flags)
 {
+	unsigned long ret;
 	loff_t off = (loff_t)pgoff << PAGE_SHIFT;
 
-	if (addr)
-		goto out;
 	if (!IS_DAX(filp->f_mapping->host) || !IS_ENABLED(CONFIG_FS_DAX_PMD))
 		goto out;
 
-	addr = __thp_get_unmapped_area(filp, len, off, flags, PMD_SIZE);
-	if (addr)
-		return addr;
-
- out:
+	ret = __thp_get_unmapped_area(filp, addr, len, off, flags, PMD_SIZE);
+	if (ret)
+		return ret;
+out:
 	return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags);
 }
 EXPORT_SYMBOL_GPL(thp_get_unmapped_area);
@@ -2281,6 +2283,8 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 {
 	spinlock_t *ptl;
 	struct mmu_notifier_range range;
+	bool was_locked = false;
+	pmd_t _pmd;
 
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
 				address & HPAGE_PMD_MASK,
@@ -2293,11 +2297,32 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 	 * pmd against. Otherwise we can end up replacing wrong page.
 	 */
 	VM_BUG_ON(freeze && !page);
-	if (page && page != pmd_page(*pmd))
-	        goto out;
+	if (page) {
+		VM_WARN_ON_ONCE(!PageLocked(page));
+		was_locked = true;
+		if (page != pmd_page(*pmd))
+			goto out;
+	}
 
+repeat:
 	if (pmd_trans_huge(*pmd)) {
-		page = pmd_page(*pmd);
+		if (!page) {
+			page = pmd_page(*pmd);
+			if (unlikely(!trylock_page(page))) {
+				get_page(page);
+				_pmd = *pmd;
+				spin_unlock(ptl);
+				lock_page(page);
+				spin_lock(ptl);
+				if (unlikely(!pmd_same(*pmd, _pmd))) {
+					unlock_page(page);
+					put_page(page);
+					page = NULL;
+					goto repeat;
+				}
+				put_page(page);
+			}
+		}
 		if (PageMlocked(page))
 			clear_page_mlock(page);
 	} else if (!(pmd_devmap(*pmd) || is_pmd_migration_entry(*pmd)))
@@ -2305,6 +2330,8 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 	__split_huge_pmd_locked(vma, pmd, range.start, freeze);
 out:
 	spin_unlock(ptl);
+	if (!was_locked && page)
+		unlock_page(page);
 	/*
 	 * No need to double call mmu_notifier->invalidate_range() callback.
 	 * They are 3 cases to consider inside __split_huge_pmd_locked():
@@ -2664,7 +2691,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	unsigned long flags;
 	pgoff_t end;
 
-	VM_BUG_ON_PAGE(is_huge_zero_page(page), page);
+	VM_BUG_ON_PAGE(is_huge_zero_page(head), head);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
 
@@ -2953,8 +2980,7 @@ void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 		return;
 
 	flush_cache_range(vma, address, address + HPAGE_PMD_SIZE);
-	pmdval = *pvmw->pmd;
-	pmdp_invalidate(vma, address, pvmw->pmd);
+	pmdval = pmdp_invalidate(vma, address, pvmw->pmd);
 	if (pmd_dirty(pmdval))
 		set_page_dirty(page);
 	entry = make_migration_entry(page, pmd_write(pmdval));
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 4c842adf14e0..1eedc7003380 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -27,6 +27,7 @@
 #include <linux/swapops.h>
 #include <linux/jhash.h>
 #include <linux/numa.h>
+#include <linux/llist.h>
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
@@ -1255,7 +1256,7 @@ static inline void ClearPageHugeTemporary(struct page *page)
 	page[2].mapping = NULL;
 }
 
-void free_huge_page(struct page *page)
+static void __free_huge_page(struct page *page)
 {
 	/*
 	 * Can't pass hstate in here because it is called from the
@@ -1318,6 +1319,54 @@ void free_huge_page(struct page *page)
 	spin_unlock(&hugetlb_lock);
 }
 
+/*
+ * As free_huge_page() can be called from a non-task context, we have
+ * to defer the actual freeing in a workqueue to prevent potential
+ * hugetlb_lock deadlock.
+ *
+ * free_hpage_workfn() locklessly retrieves the linked list of pages to
+ * be freed and frees them one-by-one. As the page->mapping pointer is
+ * going to be cleared in __free_huge_page() anyway, it is reused as the
+ * llist_node structure of a lockless linked list of huge pages to be freed.
+ */
+static LLIST_HEAD(hpage_freelist);
+
+static void free_hpage_workfn(struct work_struct *work)
+{
+	struct llist_node *node;
+	struct page *page;
+
+	node = llist_del_all(&hpage_freelist);
+
+	while (node) {
+		page = container_of((struct address_space **)node,
+				     struct page, mapping);
+		node = node->next;
+		__free_huge_page(page);
+	}
+}
+static DECLARE_WORK(free_hpage_work, free_hpage_workfn);
+
+void free_huge_page(struct page *page)
+{
+	/*
+	 * Defer freeing if in non-task context to avoid hugetlb_lock deadlock.
+	 */
+	if (!in_task()) {
+		/*
+		 * Only call schedule_work() if hpage_freelist is previously
+		 * empty. Otherwise, schedule_work() had been called but the
+		 * workfn hasn't retrieved the list yet.
+		 */
+		if (llist_add((struct llist_node *)&page->mapping,
+			      &hpage_freelist))
+			schedule_work(&free_hpage_work);
+		return;
+	}
+
+	__free_huge_page(page);
+}
+
 static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 {
 	INIT_LIST_HEAD(&page->lru);
@@ -2964,6 +3013,22 @@ static unsigned int cpuset_mems_nr(unsigned int *array)
 }
 
 #ifdef CONFIG_SYSCTL
+static int proc_hugetlb_doulongvec_minmax(struct ctl_table *table, int write,
+					  void *buffer, size_t *length,
+					  loff_t *ppos, unsigned long *out)
+{
+	struct ctl_table dup_table;
+
+	/*
+	 * In order to avoid races with __do_proc_doulongvec_minmax(), we
+	 * can duplicate the @table and alter the duplicate of it.
+	 */
+	dup_table = *table;
+	dup_table.data = out;
+
+	return proc_doulongvec_minmax(&dup_table, write, buffer, length, ppos);
+}
+
 static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
 			 struct ctl_table *table, int write,
 			 void __user *buffer, size_t *length, loff_t *ppos)
@@ -2975,9 +3040,8 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
 	if (!hugepages_supported())
 		return -EOPNOTSUPP;
 
-	table->data = &tmp;
-	table->maxlen = sizeof(unsigned long);
-	ret = proc_doulongvec_minmax(table, write, buffer, length, ppos);
+	ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos,
+					     &tmp);
 	if (ret)
 		goto out;
 
@@ -3021,9 +3085,8 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write,
 	if (write && hstate_is_gigantic(h))
 		return -EINVAL;
 
-	table->data = &tmp;
-	table->maxlen = sizeof(unsigned long);
-	ret = proc_doulongvec_minmax(table, write, buffer, length, ppos);
+	ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos,
+					     &tmp);
 	if (ret)
 		goto out;
 
@@ -4879,8 +4942,8 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
+	pud_t *pud, pud_entry;
+	pmd_t *pmd, pmd_entry;
 
 	pgd = pgd_offset(mm, addr);
 	if (!pgd_present(*pgd))
@@ -4890,17 +4953,19 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 		return NULL;
 
 	pud = pud_offset(p4d, addr);
-	if (sz != PUD_SIZE && pud_none(*pud))
+	pud_entry = READ_ONCE(*pud);
+	if (sz != PUD_SIZE && pud_none(pud_entry))
 		return NULL;
 	/* hugepage or swap? */
-	if (pud_huge(*pud) || !pud_present(*pud))
+	if (pud_huge(pud_entry) || !pud_present(pud_entry))
 		return (pte_t *)pud;
 
 	pmd = pmd_offset(pud, addr);
-	if (sz != PMD_SIZE && pmd_none(*pmd))
+	pmd_entry = READ_ONCE(*pmd);
+	if (sz != PMD_SIZE && pmd_none(pmd_entry))
 		return NULL;
 	/* hugepage or swap? */
-	if (pmd_huge(*pmd) || !pmd_present(*pmd))
+	if (pmd_huge(pmd_entry) || !pmd_present(pmd_entry))
 		return (pte_t *)pmd;
 
 	return NULL;
diff --git a/mm/internal.h b/mm/internal.h
index e32390802fd3..5d91f9e90741 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -362,6 +362,27 @@ vma_address(struct page *page, struct vm_area_struct *vma)
 	return max(start, vma->vm_start);
 }
 
+static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf,
+						    struct file *fpin)
+{
+	int flags = vmf->flags;
+
+	if (fpin)
+		return fpin;
+
+	/*
+	 * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or
+	 * anything, so we only pin the file and drop the mmap_sem if only
+	 * FAULT_FLAG_ALLOW_RETRY is set.
+	 */
+	if ((flags & (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT)) ==
+	    FAULT_FLAG_ALLOW_RETRY) {
+		fpin = get_file(vmf->vma->vm_file);
+		up_read(&vmf->vma->vm_mm->mmap_sem);
+	}
+	return fpin;
+}
+
 #else /* !CONFIG_MMU */
 static inline void clear_page_mlock(struct page *page) { }
 static inline void mlock_vma_page(struct page *page) { }
diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile
index 08b43de2383b..f36ffc090f5f 100644
--- a/mm/kasan/Makefile
+++ b/mm/kasan/Makefile
@@ -14,10 +14,10 @@ CFLAGS_REMOVE_tags.o = $(CC_FLAGS_FTRACE)
 # Function splitter causes unnecessary splits in __asan_load1/__asan_store1
 # see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63533
 
-CFLAGS_common.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
-CFLAGS_generic.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
-CFLAGS_generic_report.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
-CFLAGS_tags.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
+CFLAGS_common.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) -DDISABLE_BRANCH_PROFILING
+CFLAGS_generic.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) -DDISABLE_BRANCH_PROFILING
+CFLAGS_generic_report.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) -DDISABLE_BRANCH_PROFILING
+CFLAGS_tags.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) -DDISABLE_BRANCH_PROFILING
 
 obj-$(CONFIG_KASAN) := common.o init.o report.o
 obj-$(CONFIG_KASAN_GENERIC) += generic.o generic_report.o quarantine.o
diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c
index 504c79363a34..4acdf7e1f965 100644
--- a/mm/kasan/generic.c
+++ b/mm/kasan/generic.c
@@ -15,7 +15,6 @@
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#define DISABLE_BRANCH_PROFILING
 
 #include <linux/export.h>
 #include <linux/interrupt.h>
diff --git a/mm/kasan/tags.c b/mm/kasan/tags.c
index 63fca3172659..0d83b7fc21fd 100644
--- a/mm/kasan/tags.c
+++ b/mm/kasan/tags.c
@@ -12,7 +12,6 @@
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#define DISABLE_BRANCH_PROFILING
 
 #include <linux/export.h>
 #include <linux/interrupt.h>
diff --git a/mm/ksm.c b/mm/ksm.c
index 4d5998ca31ae..d614a49ab82c 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -2130,8 +2130,16 @@ static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item)
 
 		down_read(&mm->mmap_sem);
 		vma = find_mergeable_vma(mm, rmap_item->address);
-		err = try_to_merge_one_page(vma, page,
-					    ZERO_PAGE(rmap_item->address));
+		if (vma) {
+			err = try_to_merge_one_page(vma, page,
+					ZERO_PAGE(rmap_item->address));
+		} else {
+			/*
+			 * If the vma is out of date, we do not need to
+			 * continue.
+			 */
+			err = 0;
+		}
 		up_read(&mm->mmap_sem);
 		/*
 		 * In case of failure, the page was not really empty, so we
diff --git a/mm/maccess.c b/mm/maccess.c
index 482d4d670f19..2d3c3d01064c 100644
--- a/mm/maccess.c
+++ b/mm/maccess.c
@@ -6,8 +6,32 @@
 #include <linux/mm.h>
 #include <linux/uaccess.h>
 
+static __always_inline long
+probe_read_common(void *dst, const void __user *src, size_t size)
+{
+	long ret;
+
+	pagefault_disable();
+	ret = __copy_from_user_inatomic(dst, src, size);
+	pagefault_enable();
+
+	return ret ? -EFAULT : 0;
+}
+
+static __always_inline long
+probe_write_common(void __user *dst, const void *src, size_t size)
+{
+	long ret;
+
+	pagefault_disable();
+	ret = __copy_to_user_inatomic(dst, src, size);
+	pagefault_enable();
+
+	return ret ? -EFAULT : 0;
+}
+
 /**
- * probe_kernel_read(): safely attempt to read from a location
+ * probe_kernel_read(): safely attempt to read from a kernel-space location
  * @dst: pointer to the buffer that shall take the data
  * @src: address to read from
  * @size: size of the data chunk
@@ -30,17 +54,41 @@ long __probe_kernel_read(void *dst, const void *src, size_t size)
 	mm_segment_t old_fs = get_fs();
 
 	set_fs(KERNEL_DS);
-	pagefault_disable();
-	ret = __copy_from_user_inatomic(dst,
-			(__force const void __user *)src, size);
-	pagefault_enable();
+	ret = probe_read_common(dst, (__force const void __user *)src, size);
 	set_fs(old_fs);
 
-	return ret ? -EFAULT : 0;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(probe_kernel_read);
 
 /**
+ * probe_user_read(): safely attempt to read from a user-space location
+ * @dst: pointer to the buffer that shall take the data
+ * @src: address to read from. This must be a user address.
+ * @size: size of the data chunk
+ *
+ * Safely read from user address @src to the buffer at @dst. If a kernel fault
+ * happens, handle that and return -EFAULT.
+ */
+
+long __weak probe_user_read(void *dst, const void __user *src, size_t size)
+    __attribute__((alias("__probe_user_read")));
+
+long __probe_user_read(void *dst, const void __user *src, size_t size)
+{
+	long ret = -EFAULT;
+	mm_segment_t old_fs = get_fs();
+
+	set_fs(USER_DS);
+	if (access_ok(src, size))
+		ret = probe_read_common(dst, src, size);
+	set_fs(old_fs);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(probe_user_read);
+
+/**
  * probe_kernel_write(): safely attempt to write to a location
  * @dst: address to write to
  * @src: pointer to the data that shall be written
@@ -49,6 +97,7 @@ EXPORT_SYMBOL_GPL(probe_kernel_read);
  * Safely write to address @dst from the buffer at @src.  If a kernel fault
  * happens, handle that and return -EFAULT.
  */
+
 long __weak probe_kernel_write(void *dst, const void *src, size_t size)
     __attribute__((alias("__probe_kernel_write")));
 
@@ -58,16 +107,41 @@ long __probe_kernel_write(void *dst, const void *src, size_t size)
 	mm_segment_t old_fs = get_fs();
 
 	set_fs(KERNEL_DS);
-	pagefault_disable();
-	ret = __copy_to_user_inatomic((__force void __user *)dst, src, size);
-	pagefault_enable();
+	ret = probe_write_common((__force void __user *)dst, src, size);
 	set_fs(old_fs);
 
-	return ret ? -EFAULT : 0;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(probe_kernel_write);
 
 /**
+ * probe_user_write(): safely attempt to write to a user-space location
+ * @dst: address to write to
+ * @src: pointer to the data that shall be written
+ * @size: size of the data chunk
+ *
+ * Safely write to address @dst from the buffer at @src.  If a kernel fault
+ * happens, handle that and return -EFAULT.
+ */
+
+long __weak probe_user_write(void __user *dst, const void *src, size_t size)
+    __attribute__((alias("__probe_user_write")));
+
+long __probe_user_write(void __user *dst, const void *src, size_t size)
+{
+	long ret = -EFAULT;
+	mm_segment_t old_fs = get_fs();
+
+	set_fs(USER_DS);
+	if (access_ok(dst, size))
+		ret = probe_write_common(dst, src, size);
+	set_fs(old_fs);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(probe_user_write);
+
+/**
  * strncpy_from_unsafe: - Copy a NUL terminated string from unsafe address.
  * @dst:   Destination address, in kernel space.  This buffer must be at
  *         least @count bytes long.
@@ -106,3 +180,76 @@ long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count)
 
 	return ret ? -EFAULT : src - unsafe_addr;
 }
+
+/**
+ * strncpy_from_unsafe_user: - Copy a NUL terminated string from unsafe user
+ *				address.
+ * @dst:   Destination address, in kernel space.  This buffer must be at
+ *         least @count bytes long.
+ * @unsafe_addr: Unsafe user address.
+ * @count: Maximum number of bytes to copy, including the trailing NUL.
+ *
+ * Copies a NUL-terminated string from unsafe user address to kernel buffer.
+ *
+ * On success, returns the length of the string INCLUDING the trailing NUL.
+ *
+ * If access fails, returns -EFAULT (some data may have been copied
+ * and the trailing NUL added).
+ *
+ * If @count is smaller than the length of the string, copies @count-1 bytes,
+ * sets the last byte of @dst buffer to NUL and returns @count.
+ */
+long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr,
+			      long count)
+{
+	mm_segment_t old_fs = get_fs();
+	long ret;
+
+	if (unlikely(count <= 0))
+		return 0;
+
+	set_fs(USER_DS);
+	pagefault_disable();
+	ret = strncpy_from_user(dst, unsafe_addr, count);
+	pagefault_enable();
+	set_fs(old_fs);
+
+	if (ret >= count) {
+		ret = count;
+		dst[ret - 1] = '\0';
+	} else if (ret > 0) {
+		ret++;
+	}
+
+	return ret;
+}
+
+/**
+ * strnlen_unsafe_user: - Get the size of a user string INCLUDING final NUL.
+ * @unsafe_addr: The string to measure.
+ * @count: Maximum count (including NUL)
+ *
+ * Get the size of a NUL-terminated string in user space without pagefault.
+ *
+ * Returns the size of the string INCLUDING the terminating NUL.
+ *
+ * If the string is too long, returns a number larger than @count. User
+ * has to check the return value against "> count".
+ * On exception (or invalid count), returns 0.
+ *
+ * Unlike strnlen_user, this can be used from IRQ handler etc. because
+ * it disables pagefaults.
+ */
+long strnlen_unsafe_user(const void __user *unsafe_addr, long count)
+{
+	mm_segment_t old_fs = get_fs();
+	int ret;
+
+	set_fs(USER_DS);
+	pagefault_disable();
+	ret = strnlen_user(unsafe_addr, count);
+	pagefault_enable();
+	set_fs(old_fs);
+
+	return ret;
+}
diff --git a/mm/madvise.c b/mm/madvise.c
index ae56d0ef337d..9c43c8515cef 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -308,9 +308,9 @@ static long madvise_willneed(struct vm_area_struct *vma,
 	 */
 	*prev = NULL;	/* tell sys_madvise we drop mmap_sem */
 	get_file(file);
-	up_read(&current->mm->mmap_sem);
 	offset = (loff_t)(start - vma->vm_start)
 			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
+	up_read(&current->mm->mmap_sem);
 	vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED);
 	fput(file);
 	down_read(&current->mm->mmap_sem);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d1debb6a5178..996f4cbe612f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -411,8 +411,10 @@ int memcg_expand_shrinker_maps(int new_id)
 		if (mem_cgroup_is_root(memcg))
 			continue;
 		ret = memcg_expand_one_shrinker_map(memcg, size, old_size);
-		if (ret)
+		if (ret) {
+			mem_cgroup_iter_break(NULL, memcg);
 			goto unlock;
+		}
 	}
 unlock:
 	if (!ret)
@@ -3888,7 +3890,7 @@ static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
 	struct mem_cgroup_thresholds *thresholds;
 	struct mem_cgroup_threshold_ary *new;
 	unsigned long usage;
-	int i, j, size;
+	int i, j, size, entries;
 
 	mutex_lock(&memcg->thresholds_lock);
 
@@ -3908,14 +3910,20 @@ static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
 	__mem_cgroup_threshold(memcg, type == _MEMSWAP);
 
 	/* Calculate new number of threshold */
-	size = 0;
+	size = entries = 0;
 	for (i = 0; i < thresholds->primary->size; i++) {
 		if (thresholds->primary->entries[i].eventfd != eventfd)
 			size++;
+		else
+			entries++;
 	}
 
 	new = thresholds->spare;
 
+	/* If no items related to eventfd have been cleared, nothing to do */
+	if (!entries)
+		goto unlock;
+
 	/* Set thresholds array to NULL if we don't have thresholds */
 	if (!size) {
 		kfree(new);
@@ -4622,12 +4630,6 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 {
 	int node;
 
-	/*
-	 * Flush percpu vmstats and vmevents to guarantee the value correctness
-	 * on parent's and all ancestor levels.
-	 */
-	memcg_flush_percpu_vmstats(memcg);
-	memcg_flush_percpu_vmevents(memcg);
 	for_each_node(node)
 		free_mem_cgroup_per_node_info(memcg, node);
 	free_percpu(memcg->vmstats_percpu);
@@ -4638,6 +4640,12 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 static void mem_cgroup_free(struct mem_cgroup *memcg)
 {
 	memcg_wb_domain_exit(memcg);
+	/*
+	 * Flush percpu vmstats and vmevents to guarantee the value correctness
+	 * on parent's and all ancestor levels.
+	 */
+	memcg_flush_percpu_vmstats(memcg);
+	memcg_flush_percpu_vmevents(memcg);
 	__mem_cgroup_free(memcg);
 }
 
@@ -4646,19 +4654,22 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 	struct mem_cgroup *memcg;
 	unsigned int size;
 	int node;
+	long error = -ENOMEM;
 
 	size = sizeof(struct mem_cgroup);
 	size += nr_node_ids * sizeof(struct mem_cgroup_per_node *);
 
 	memcg = kzalloc(size, GFP_KERNEL);
 	if (!memcg)
-		return NULL;
+		return ERR_PTR(error);
 
 	memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL,
 				 1, MEM_CGROUP_ID_MAX,
 				 GFP_KERNEL);
-	if (memcg->id.id < 0)
+	if (memcg->id.id < 0) {
+		error = memcg->id.id;
 		goto fail;
+	}
 
 	memcg->vmstats_local = alloc_percpu(struct memcg_vmstats_percpu);
 	if (!memcg->vmstats_local)
@@ -4695,7 +4706,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 fail:
 	mem_cgroup_id_remove(memcg);
 	__mem_cgroup_free(memcg);
-	return NULL;
+	return ERR_PTR(error);
 }
 
 static struct cgroup_subsys_state * __ref
@@ -4706,8 +4717,8 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	long error = -ENOMEM;
 
 	memcg = mem_cgroup_alloc();
-	if (!memcg)
-		return ERR_PTR(error);
+	if (IS_ERR(memcg))
+		return ERR_CAST(memcg);
 
 	memcg->high = PAGE_COUNTER_MAX;
 	memcg->soft_limit = PAGE_COUNTER_MAX;
@@ -4754,7 +4765,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 fail:
 	mem_cgroup_id_remove(memcg);
 	mem_cgroup_free(memcg);
-	return ERR_PTR(-ENOMEM);
+	return ERR_PTR(error);
 }
 
 static int mem_cgroup_css_online(struct cgroup_subsys_state *css)
@@ -5289,7 +5300,6 @@ static void __mem_cgroup_clear_mc(void)
 		if (!mem_cgroup_is_root(mc.to))
 			page_counter_uncharge(&mc.to->memory, mc.moved_swap);
 
-		mem_cgroup_id_get_many(mc.to, mc.moved_swap);
 		css_put_many(&mc.to->css, mc.moved_swap);
 
 		mc.moved_swap = 0;
@@ -5480,7 +5490,8 @@ put:			/* get_mctgt_type() gets the page */
 			ent = target.ent;
 			if (!mem_cgroup_move_swap_account(ent, mc.from, mc.to)) {
 				mc.precharge--;
-				/* we fixup refcnts and charges later. */
+				mem_cgroup_id_get_many(mc.to, 1);
+				/* we fixup other refcnts and charges later. */
 				mc.moved_swap++;
 			}
 			break;
@@ -6450,19 +6461,9 @@ void mem_cgroup_sk_alloc(struct sock *sk)
 	if (!mem_cgroup_sockets_enabled)
 		return;
 
-	/*
-	 * Socket cloning can throw us here with sk_memcg already
-	 * filled. It won't however, necessarily happen from
-	 * process context. So the test for root memcg given
-	 * the current task's memcg won't help us in this case.
-	 *
-	 * Respecting the original socket's memcg is a better
-	 * decision in this case.
-	 */
-	if (sk->sk_memcg) {
-		css_get(&sk->sk_memcg->css);
+	/* Do not associate the sock with unrelated interrupted task's memcg. */
+	if (in_interrupt())
 		return;
-	}
 
 	rcu_read_lock();
 	memcg = mem_cgroup_from_task(current);
diff --git a/mm/memory.c b/mm/memory.c
index b0efc69b2634..339f8ba20470 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2257,10 +2257,11 @@ static vm_fault_t do_page_mkwrite(struct vm_fault *vmf)
  *
  * The function expects the page to be locked and unlocks it.
  */
-static void fault_dirty_shared_page(struct vm_area_struct *vma,
-				    struct page *page)
+static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf)
 {
+	struct vm_area_struct *vma = vmf->vma;
 	struct address_space *mapping;
+	struct page *page = vmf->page;
 	bool dirtied;
 	bool page_mkwrite = vma->vm_ops && vma->vm_ops->page_mkwrite;
 
@@ -2275,16 +2276,30 @@ static void fault_dirty_shared_page(struct vm_area_struct *vma,
 	mapping = page_rmapping(page);
 	unlock_page(page);
 
+	if (!page_mkwrite)
+		file_update_time(vma->vm_file);
+
+	/*
+	 * Throttle page dirtying rate down to writeback speed.
+	 *
+	 * mapping may be NULL here because some device drivers do not
+	 * set page.mapping but still dirty their pages
+	 *
+	 * Drop the mmap_sem before waiting on IO, if we can. The file
+	 * is pinning the mapping, as per above.
+	 */
 	if ((dirtied || page_mkwrite) && mapping) {
-		/*
-		 * Some device drivers do not set page.mapping
-		 * but still dirty their pages
-		 */
+		struct file *fpin;
+
+		fpin = maybe_unlock_mmap_for_io(vmf, NULL);
 		balance_dirty_pages_ratelimited(mapping);
+		if (fpin) {
+			fput(fpin);
+			return VM_FAULT_RETRY;
+		}
 	}
 
-	if (!page_mkwrite)
-		file_update_time(vma->vm_file);
+	return 0;
 }
 
 /*
@@ -2527,6 +2542,7 @@ static vm_fault_t wp_page_shared(struct vm_fault *vmf)
 	__releases(vmf->ptl)
 {
 	struct vm_area_struct *vma = vmf->vma;
+	vm_fault_t ret = VM_FAULT_WRITE;
 
 	get_page(vmf->page);
 
@@ -2550,10 +2566,10 @@ static vm_fault_t wp_page_shared(struct vm_fault *vmf)
 		wp_page_reuse(vmf);
 		lock_page(vmf->page);
 	}
-	fault_dirty_shared_page(vma, vmf->page);
+	ret |= fault_dirty_shared_page(vmf);
 	put_page(vmf->page);
 
-	return VM_FAULT_WRITE;
+	return ret;
 }
 
 /*
@@ -3615,7 +3631,7 @@ static vm_fault_t do_shared_fault(struct vm_fault *vmf)
 		return ret;
 	}
 
-	fault_dirty_shared_page(vma, vmf->page);
+	ret |= fault_dirty_shared_page(vmf);
 	return ret;
 }
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index ec80a36b324e..b28d0616f002 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2792,6 +2792,9 @@ int mpol_parse_str(char *str, struct mempolicy **mpol)
 	char *flags = strchr(str, '=');
 	int err = 1, mode;
 
+	if (flags)
+		*flags++ = '\0';	/* terminate mode string */
+
 	if (nodelist) {
 		/* NUL-terminate mode or flags string */
 		*nodelist++ = '\0';
@@ -2802,9 +2805,6 @@ int mpol_parse_str(char *str, struct mempolicy **mpol)
 	} else
 		nodes_clear(nodes);
 
-	if (flags)
-		*flags++ = '\0';	/* terminate mode string */
-
 	mode = match_string(policy_modes, MPOL_MAX, str);
 	if (mode < 0)
 		goto out;
@@ -2812,7 +2812,9 @@ int mpol_parse_str(char *str, struct mempolicy **mpol)
 	switch (mode) {
 	case MPOL_PREFERRED:
 		/*
-		 * Insist on a nodelist of one node only
+		 * Insist on a nodelist of one node only, although later
+		 * we use first_node(nodes) to grab a single node, so here
+		 * nodelist (or nodes) cannot be empty.
 		 */
 		if (nodelist) {
 			char *rest = nodelist;
@@ -2820,6 +2822,8 @@ int mpol_parse_str(char *str, struct mempolicy **mpol)
 				rest++;
 			if (*rest)
 				goto out;
+			if (nodes_empty(nodes))
+				goto out;
 		}
 		break;
 	case MPOL_INTERLEAVE:
diff --git a/mm/migrate.c b/mm/migrate.c
index dbb3b5bee4ee..8631d8d3730c 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1522,9 +1522,11 @@ static int do_move_pages_to_node(struct mm_struct *mm,
 /*
  * Resolves the given address to a struct page, isolates it from the LRU and
  * puts it to the given pagelist.
- * Returns -errno if the page cannot be found/isolated or 0 when it has been
- * queued or the page doesn't need to be migrated because it is already on
- * the target node
+ * Returns:
+ *     errno - if the page cannot be found/isolated
+ *     0 - when it doesn't have to be migrated because it is already on the
+ *         target node
+ *     1 - when it has been queued
  */
 static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
 		int node, struct list_head *pagelist, bool migrate_all)
@@ -1563,7 +1565,7 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
 	if (PageHuge(page)) {
 		if (PageHead(page)) {
 			isolate_huge_page(page, pagelist);
-			err = 0;
+			err = 1;
 		}
 	} else {
 		struct page *head;
@@ -1573,7 +1575,7 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
 		if (err)
 			goto out_putpage;
 
-		err = 0;
+		err = 1;
 		list_add_tail(&head->lru, pagelist);
 		mod_node_page_state(page_pgdat(head),
 			NR_ISOLATED_ANON + page_is_file_cache(head),
@@ -1635,8 +1637,19 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
 			start = i;
 		} else if (node != current_node) {
 			err = do_move_pages_to_node(mm, &pagelist, current_node);
-			if (err)
+			if (err) {
+				/*
+				 * Positive err means the number of failed
+				 * pages to migrate.  Since we are going to
+				 * abort and return the number of non-migrated
+				 * pages, so need to incude the rest of the
+				 * nr_pages that have not been attempted as
+				 * well.
+				 */
+				if (err > 0)
+					err += nr_pages - i - 1;
 				goto out;
+			}
 			err = store_status(status, start, current_node, i - start);
 			if (err)
 				goto out;
@@ -1650,16 +1663,28 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
 		 */
 		err = add_page_for_migration(mm, addr, current_node,
 				&pagelist, flags & MPOL_MF_MOVE_ALL);
-		if (!err)
+
+		if (!err) {
+			/* The page is already on the target node */
+			err = store_status(status, i, current_node, 1);
+			if (err)
+				goto out_flush;
 			continue;
+		} else if (err > 0) {
+			/* The page is successfully queued for migration */
+			continue;
+		}
 
 		err = store_status(status, i, err, 1);
 		if (err)
 			goto out_flush;
 
 		err = do_move_pages_to_node(mm, &pagelist, current_node);
-		if (err)
+		if (err) {
+			if (err > 0)
+				err += nr_pages - i - 1;
 			goto out;
+		}
 		if (i > start) {
 			err = store_status(status, start, current_node, i - start);
 			if (err)
@@ -1673,9 +1698,16 @@ out_flush:
 
 	/* Make sure we do not overwrite the existing error */
 	err1 = do_move_pages_to_node(mm, &pagelist, current_node);
+	/*
+	 * Don't have to report non-attempted pages here since:
+	 *     - If the above loop is done gracefully all pages have been
+	 *       attempted.
+	 *     - If the above loop is aborted it means a fatal error
+	 *       happened, should return ret.
+	 */
 	if (!err1)
 		err1 = store_status(status, start, current_node, i - start);
-	if (!err)
+	if (err >= 0)
 		err = err1;
 out:
 	return err;
diff --git a/mm/mmap.c b/mm/mmap.c
index d8a903f61262..bc841e98bb92 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -90,12 +90,6 @@ static void unmap_region(struct mm_struct *mm,
  * MAP_PRIVATE	r: (no) no	r: (yes) yes	r: (no) yes	r: (no) yes
  *		w: (no) no	w: (no) no	w: (copy) copy	w: (no) no
  *		x: (no) no	x: (no) yes	x: (no) yes	x: (yes) yes
- *
- * On arm64, PROT_EXEC has the following behaviour for both MAP_SHARED and
- * MAP_PRIVATE:
- *								r: (no) no
- *								w: (no) no
- *								x: (yes) yes
  */
 pgprot_t protection_map[16] __ro_after_init = {
 	__P000, __P001, __P010, __P011, __P100, __P101, __P110, __P111,
@@ -2617,7 +2611,7 @@ static void unmap_region(struct mm_struct *mm,
  * Create a list of vma's touched by the unmap, removing them from the mm's
  * vma list as we go..
  */
-static void
+static bool
 detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct vm_area_struct *prev, unsigned long end)
 {
@@ -2642,6 +2636,17 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	/* Kill the cache */
 	vmacache_invalidate(mm);
+
+	/*
+	 * Do not downgrade mmap_lock if we are next to VM_GROWSDOWN or
+	 * VM_GROWSUP VMA. Such VMAs can change their size under
+	 * down_read(mmap_lock) and collide with the VMA we are about to unmap.
+	 */
+	if (vma && (vma->vm_flags & VM_GROWSDOWN))
+		return false;
+	if (prev && (prev->vm_flags & VM_GROWSUP))
+		return false;
+	return true;
 }
 
 /*
@@ -2822,7 +2827,8 @@ int __do_munmap(struct mm_struct *mm, unsigned long start, size_t len,
 	}
 
 	/* Detach vmas from rbtree */
-	detach_vmas_to_be_unmapped(mm, vma, prev, end);
+	if (!detach_vmas_to_be_unmapped(mm, vma, prev, end))
+		downgrade = false;
 
 	if (downgrade)
 		downgrade_write(&mm->mmap_sem);
@@ -3171,6 +3177,7 @@ void exit_mmap(struct mm_struct *mm)
 		if (vma->vm_flags & VM_ACCOUNT)
 			nr_accounted += vma_pages(vma);
 		vma = remove_vma(vma);
+		cond_resched();
 	}
 	vm_unacct_memory(nr_accounted);
 }
diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c
index 8c943a6e1696..a490ff445644 100644
--- a/mm/mmu_gather.c
+++ b/mm/mmu_gather.c
@@ -102,14 +102,14 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_
  */
 static inline void tlb_table_invalidate(struct mmu_gather *tlb)
 {
-#ifndef CONFIG_HAVE_RCU_TABLE_NO_INVALIDATE
-	/*
-	 * Invalidate page-table caches used by hardware walkers. Then we still
-	 * need to RCU-sched wait while freeing the pages because software
-	 * walkers can still be in-flight.
-	 */
-	tlb_flush_mmu_tlbonly(tlb);
-#endif
+	if (tlb_needs_table_invalidate()) {
+		/*
+		 * Invalidate page-table caches used by hardware walkers. Then
+		 * we still need to RCU-sched wait while freeing the pages
+		 * because software walkers can still be in-flight.
+		 */
+		tlb_flush_mmu_tlbonly(tlb);
+	}
 }
 
 static void tlb_remove_table_smp_sync(void *arg)
diff --git a/mm/mprotect.c b/mm/mprotect.c
index bf38dfbbb4b4..c5add7c033a0 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -161,6 +161,31 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 	return pages;
 }
 
+/*
+ * Used when setting automatic NUMA hinting protection where it is
+ * critical that a numa hinting PMD is not confused with a bad PMD.
+ */
+static inline int pmd_none_or_clear_bad_unless_trans_huge(pmd_t *pmd)
+{
+	pmd_t pmdval = pmd_read_atomic(pmd);
+
+	/* See pmd_none_or_trans_huge_or_clear_bad for info on barrier */
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	barrier();
+#endif
+
+	if (pmd_none(pmdval))
+		return 1;
+	if (pmd_trans_huge(pmdval))
+		return 0;
+	if (unlikely(pmd_bad(pmdval))) {
+		pmd_clear_bad(pmd);
+		return 1;
+	}
+
+	return 0;
+}
+
 static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		pud_t *pud, unsigned long addr, unsigned long end,
 		pgprot_t newprot, int dirty_accountable, int prot_numa)
@@ -178,8 +203,17 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		unsigned long this_pages;
 
 		next = pmd_addr_end(addr, end);
-		if (!is_swap_pmd(*pmd) && !pmd_trans_huge(*pmd) && !pmd_devmap(*pmd)
-				&& pmd_none_or_clear_bad(pmd))
+
+		/*
+		 * Automatic NUMA balancing walks the tables with mmap_sem
+		 * held for read. It's possible a parallel update to occur
+		 * between pmd_trans_huge() and a pmd_none_or_clear_bad()
+		 * check leading to a false positive and clearing.
+		 * Hence, it's necessary to atomically read the PMD value
+		 * for all the checks.
+		 */
+		if (!is_swap_pmd(*pmd) && !pmd_devmap(*pmd) &&
+		     pmd_none_or_clear_bad_unless_trans_huge(pmd))
 			goto next;
 
 		/* invoke the mmu notifier if the pmd is populated */
diff --git a/mm/mremap.c b/mm/mremap.c
index fc241d23cd97..8b6edb259495 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -266,7 +266,7 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 		new_pmd = alloc_new_pmd(vma->vm_mm, vma, new_addr);
 		if (!new_pmd)
 			break;
-		if (is_swap_pmd(*old_pmd) || pmd_trans_huge(*old_pmd)) {
+		if (is_swap_pmd(*old_pmd) || pmd_trans_huge(*old_pmd) || pmd_devmap(*old_pmd)) {
 			if (extent == HPAGE_PMD_SIZE) {
 				bool moved;
 				/* See comment in move_ptes() */
diff --git a/mm/nommu.c b/mm/nommu.c
index d7e4abcaca3e..690c26ac8b27 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -447,10 +447,14 @@ void vm_unmap_aliases(void)
 EXPORT_SYMBOL_GPL(vm_unmap_aliases);
 
 /*
- * Implement a stub for vmalloc_sync_all() if the architecture chose not to
- * have one.
+ * Implement a stub for vmalloc_sync_[un]mapping() if the architecture
+ * chose not to have one.
  */
-void __weak vmalloc_sync_all(void)
+void __weak vmalloc_sync_mappings(void)
+{
+}
+
+void __weak vmalloc_sync_unmappings(void)
 {
 }
 
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index bdbe8b6b1225..dde05d75c471 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -201,11 +201,11 @@ static void wb_min_max_ratio(struct bdi_writeback *wb,
 	if (this_bw < tot_bw) {
 		if (min) {
 			min *= this_bw;
-			do_div(min, tot_bw);
+			min = div64_ul(min, tot_bw);
 		}
 		if (max < 100) {
 			max *= this_bw;
-			do_div(max, tot_bw);
+			max = div64_ul(max, tot_bw);
 		}
 	}
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 30ca6634b3cd..10fa8891be62 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1507,6 +1507,7 @@ void set_zone_contiguous(struct zone *zone)
 		if (!__pageblock_pfn_to_page(block_start_pfn,
 					     block_end_pfn, zone))
 			return;
+		cond_resched();
 	}
 
 	/* We confirm that there is no hole */
@@ -1591,7 +1592,6 @@ static void __init deferred_free_pages(unsigned long pfn,
 		} else if (!(pfn & nr_pgmask)) {
 			deferred_free_range(pfn - nr_free, nr_free);
 			nr_free = 1;
-			touch_nmi_watchdog();
 		} else {
 			nr_free++;
 		}
@@ -1621,7 +1621,6 @@ static unsigned long  __init deferred_init_pages(struct zone *zone,
 			continue;
 		} else if (!page || !(pfn & nr_pgmask)) {
 			page = pfn_to_page(pfn);
-			touch_nmi_watchdog();
 		} else {
 			page++;
 		}
@@ -1744,6 +1743,13 @@ static int __init deferred_init_memmap(void *data)
 	BUG_ON(pgdat->first_deferred_pfn > pgdat_end_pfn(pgdat));
 	pgdat->first_deferred_pfn = ULONG_MAX;
 
+	/*
+	 * Once we unlock here, the zone cannot be grown anymore, thus if an
+	 * interrupt thread must allocate this early in boot, zone must be
+	 * pre-grown prior to start of deferred page initialization.
+	 */
+	pgdat_resize_unlock(pgdat, &flags);
+
 	/* Only the highest zone is deferred so find it */
 	for (zid = 0; zid < MAX_NR_ZONES; zid++) {
 		zone = pgdat->node_zones + zid;
@@ -1761,11 +1767,11 @@ static int __init deferred_init_memmap(void *data)
 	 * that we can avoid introducing any issues with the buddy
 	 * allocator.
 	 */
-	while (spfn < epfn)
+	while (spfn < epfn) {
 		nr_pages += deferred_init_maxorder(&i, zone, &spfn, &epfn);
+		cond_resched();
+	}
 zone_empty:
-	pgdat_resize_unlock(pgdat, &flags);
-
 	/* Sanity check that the next zone really is unpopulated */
 	WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone));
 
@@ -1808,17 +1814,6 @@ deferred_grow_zone(struct zone *zone, unsigned int order)
 	pgdat_resize_lock(pgdat, &flags);
 
 	/*
-	 * If deferred pages have been initialized while we were waiting for
-	 * the lock, return true, as the zone was grown.  The caller will retry
-	 * this zone.  We won't return to this function since the caller also
-	 * has this static branch.
-	 */
-	if (!static_branch_unlikely(&deferred_pages)) {
-		pgdat_resize_unlock(pgdat, &flags);
-		return true;
-	}
-
-	/*
 	 * If someone grew this zone while we were waiting for spinlock, return
 	 * true, as there might be enough pages already.
 	 */
@@ -1846,6 +1841,7 @@ deferred_grow_zone(struct zone *zone, unsigned int order)
 		first_deferred_pfn = spfn;
 
 		nr_pages += deferred_init_maxorder(&i, zone, &spfn, &epfn);
+		touch_nmi_watchdog();
 
 		/* We should only stop along section boundaries */
 		if ((first_deferred_pfn ^ spfn) < PAGES_PER_SECTION)
@@ -2289,6 +2285,14 @@ static inline void boost_watermark(struct zone *zone)
 
 	if (!watermark_boost_factor)
 		return;
+	/*
+	 * Don't bother in zones that are unlikely to produce results.
+	 * On small machines, including kdump capture kernels running
+	 * in a small area, boosting the watermark can cause an out of
+	 * memory situation immediately.
+	 */
+	if ((pageblock_nr_pages * 4) > zone_managed_pages(zone))
+		return;
 
 	max_boost = mult_frac(zone->_watermark[WMARK_HIGH],
 			watermark_boost_factor, 10000);
@@ -6848,7 +6852,8 @@ static u64 zero_pfn_range(unsigned long spfn, unsigned long epfn)
  * This function also addresses a similar issue where struct pages are left
  * uninitialized because the physical address range is not covered by
  * memblock.memory or memblock.reserved. That could happen when memblock
- * layout is manually configured via memmap=.
+ * layout is manually configured via memmap=, or when the highest physical
+ * address (max_pfn) does not end on a section boundary.
  */
 void __init zero_resv_unavail(void)
 {
@@ -6866,7 +6871,16 @@ void __init zero_resv_unavail(void)
 			pgcnt += zero_pfn_range(PFN_DOWN(next), PFN_UP(start));
 		next = end;
 	}
-	pgcnt += zero_pfn_range(PFN_DOWN(next), max_pfn);
+
+	/*
+	 * Early sections always have a fully populated memmap for the whole
+	 * section - see pfn_valid(). If the last section has holes at the
+	 * end and that section is marked "online", the memmap will be
+	 * considered initialized. Make sure that memmap has a well defined
+	 * state.
+	 */
+	pgcnt += zero_pfn_range(PFN_DOWN(next),
+				round_up(max_pfn, PAGES_PER_SECTION));
 
 	/*
 	 * Struct pages that do not have backing memory. This could be because
diff --git a/mm/page_counter.c b/mm/page_counter.c
index de31470655f6..147ff99187b8 100644
--- a/mm/page_counter.c
+++ b/mm/page_counter.c
@@ -77,7 +77,7 @@ void page_counter_charge(struct page_counter *counter, unsigned long nr_pages)
 		long new;
 
 		new = atomic_long_add_return(nr_pages, &c->usage);
-		propagate_protected_usage(counter, new);
+		propagate_protected_usage(c, new);
 		/*
 		 * This is indeed racy, but we can live with some
 		 * inaccuracy in the watermark.
@@ -121,7 +121,7 @@ bool page_counter_try_charge(struct page_counter *counter,
 		new = atomic_long_add_return(nr_pages, &c->usage);
 		if (new > c->max) {
 			atomic_long_sub(nr_pages, &c->usage);
-			propagate_protected_usage(counter, new);
+			propagate_protected_usage(c, new);
 			/*
 			 * This is racy, but we can live with some
 			 * inaccuracy in the failcnt.
@@ -130,7 +130,7 @@ bool page_counter_try_charge(struct page_counter *counter,
 			*fail = c;
 			goto failed;
 		}
-		propagate_protected_usage(counter, new);
+		propagate_protected_usage(c, new);
 		/*
 		 * Just like with failcnt, we can live with some
 		 * inaccuracy in the watermark.
diff --git a/mm/shmem.c b/mm/shmem.c
index 32c30ad3573d..2238a3df07a0 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2005,16 +2005,14 @@ static vm_fault_t shmem_fault(struct vm_fault *vmf)
 		    shmem_falloc->waitq &&
 		    vmf->pgoff >= shmem_falloc->start &&
 		    vmf->pgoff < shmem_falloc->next) {
+			struct file *fpin;
 			wait_queue_head_t *shmem_falloc_waitq;
 			DEFINE_WAIT_FUNC(shmem_fault_wait, synchronous_wake_function);
 
 			ret = VM_FAULT_NOPAGE;
-			if ((vmf->flags & FAULT_FLAG_ALLOW_RETRY) &&
-			   !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
-				/* It's polite to up mmap_sem if we can */
-				up_read(&vma->vm_mm->mmap_sem);
+			fpin = maybe_unlock_mmap_for_io(vmf, NULL);
+			if (fpin)
 				ret = VM_FAULT_RETRY;
-			}
 
 			shmem_falloc_waitq = shmem_falloc->waitq;
 			prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait,
@@ -2032,6 +2030,9 @@ static vm_fault_t shmem_fault(struct vm_fault *vmf)
 			spin_lock(&inode->i_lock);
 			finish_wait(shmem_falloc_waitq, &shmem_fault_wait);
 			spin_unlock(&inode->i_lock);
+
+			if (fpin)
+				fput(fpin);
 			return ret;
 		}
 		spin_unlock(&inode->i_lock);
@@ -2088,9 +2089,10 @@ unsigned long shmem_get_unmapped_area(struct file *file,
 	/*
 	 * Our priority is to support MAP_SHARED mapped hugely;
 	 * and support MAP_PRIVATE mapped hugely too, until it is COWed.
-	 * But if caller specified an address hint, respect that as before.
+	 * But if caller specified an address hint and we allocated area there
+	 * successfully, respect that as before.
 	 */
-	if (uaddr)
+	if (uaddr == addr)
 		return addr;
 
 	if (shmem_huge != SHMEM_HUGE_FORCE) {
@@ -2124,7 +2126,7 @@ unsigned long shmem_get_unmapped_area(struct file *file,
 	if (inflated_len < len)
 		return addr;
 
-	inflated_addr = get_area(NULL, 0, inflated_len, 0, flags);
+	inflated_addr = get_area(NULL, uaddr, inflated_len, 0, flags);
 	if (IS_ERR_VALUE(inflated_addr))
 		return addr;
 	if (inflated_addr & ~PAGE_MASK)
@@ -2164,7 +2166,11 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	int retval = -ENOMEM;
 
-	spin_lock_irq(&info->lock);
+	/*
+	 * What serializes the accesses to info->flags?
+	 * ipc_lock_object() when called from shmctl_do_lock(),
+	 * no serialization needed when called from shm_destroy().
+	 */
 	if (lock && !(info->flags & VM_LOCKED)) {
 		if (!user_shm_lock(inode->i_size, user))
 			goto out_nomem;
@@ -2179,7 +2185,6 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
 	retval = 0;
 
 out_nomem:
-	spin_unlock_irq(&info->lock);
 	return retval;
 }
 
@@ -2384,11 +2389,11 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 
 	lru_cache_add_anon(page);
 
-	spin_lock(&info->lock);
+	spin_lock_irq(&info->lock);
 	info->alloced++;
 	inode->i_blocks += BLOCKS_PER_PAGE;
 	shmem_recalc_inode(inode);
-	spin_unlock(&info->lock);
+	spin_unlock_irq(&info->lock);
 
 	inc_mm_counter(dst_mm, mm_counter_file(page));
 	page_add_file_rmap(page, false);
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 45f86ddc2637..70fb7eec7360 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -130,6 +130,7 @@ int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t nr,
 #ifdef CONFIG_MEMCG_KMEM
 
 LIST_HEAD(slab_root_caches);
+static DEFINE_SPINLOCK(memcg_kmem_wq_lock);
 
 void slab_init_memcg_params(struct kmem_cache *s)
 {
@@ -310,6 +311,14 @@ int slab_unmergeable(struct kmem_cache *s)
 	if (s->refcount < 0)
 		return 1;
 
+#ifdef CONFIG_MEMCG_KMEM
+	/*
+	 * Skip the dying kmem_cache.
+	 */
+	if (s->memcg_params.dying)
+		return 1;
+#endif
+
 	return 0;
 }
 
@@ -744,14 +753,22 @@ void slab_deactivate_memcg_cache_rcu_sched(struct kmem_cache *s,
 	    WARN_ON_ONCE(s->memcg_params.deact_fn))
 		return;
 
+	/*
+	 * memcg_kmem_wq_lock is used to synchronize memcg_params.dying
+	 * flag and make sure that no new kmem_cache deactivation tasks
+	 * are queued (see flush_memcg_workqueue() ).
+	 */
+	spin_lock_irq(&memcg_kmem_wq_lock);
 	if (s->memcg_params.root_cache->memcg_params.dying)
-		return;
+		goto unlock;
 
 	/* pin memcg so that @s doesn't get destroyed in the middle */
 	css_get(&s->memcg_params.memcg->css);
 
 	s->memcg_params.deact_fn = deact_fn;
 	call_rcu(&s->memcg_params.deact_rcu_head, kmemcg_deactivate_rcufn);
+unlock:
+	spin_unlock_irq(&memcg_kmem_wq_lock);
 }
 
 void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg)
@@ -859,12 +876,15 @@ static int shutdown_memcg_caches(struct kmem_cache *s)
 	return 0;
 }
 
-static void flush_memcg_workqueue(struct kmem_cache *s)
+static void memcg_set_kmem_cache_dying(struct kmem_cache *s)
 {
-	mutex_lock(&slab_mutex);
+	spin_lock_irq(&memcg_kmem_wq_lock);
 	s->memcg_params.dying = true;
-	mutex_unlock(&slab_mutex);
+	spin_unlock_irq(&memcg_kmem_wq_lock);
+}
 
+static void flush_memcg_workqueue(struct kmem_cache *s)
+{
 	/*
 	 * SLUB deactivates the kmem_caches through call_rcu. Make
 	 * sure all registered rcu callbacks have been invoked.
@@ -877,7 +897,8 @@ static void flush_memcg_workqueue(struct kmem_cache *s)
 	 * deactivates the memcg kmem_caches through workqueue. Make sure all
 	 * previous workitems on workqueue are processed.
 	 */
-	flush_workqueue(memcg_kmem_cache_wq);
+	if (likely(memcg_kmem_cache_wq))
+		flush_workqueue(memcg_kmem_cache_wq);
 
 	/*
 	 * If we're racing with children kmem_cache deactivation, it might
@@ -896,10 +917,6 @@ static inline int shutdown_memcg_caches(struct kmem_cache *s)
 {
 	return 0;
 }
-
-static inline void flush_memcg_workqueue(struct kmem_cache *s)
-{
-}
 #endif /* CONFIG_MEMCG_KMEM */
 
 void slab_kmem_cache_release(struct kmem_cache *s)
@@ -917,8 +934,6 @@ void kmem_cache_destroy(struct kmem_cache *s)
 	if (unlikely(!s))
 		return;
 
-	flush_memcg_workqueue(s);
-
 	get_online_cpus();
 	get_online_mems();
 
@@ -928,6 +943,22 @@ void kmem_cache_destroy(struct kmem_cache *s)
 	if (s->refcount)
 		goto out_unlock;
 
+#ifdef CONFIG_MEMCG_KMEM
+	memcg_set_kmem_cache_dying(s);
+
+	mutex_unlock(&slab_mutex);
+
+	put_online_mems();
+	put_online_cpus();
+
+	flush_memcg_workqueue(s);
+
+	get_online_cpus();
+	get_online_mems();
+
+	mutex_lock(&slab_mutex);
+#endif
+
 	err = shutdown_memcg_caches(s);
 	if (!err)
 		err = shutdown_cache(s);
@@ -1605,7 +1636,7 @@ void kzfree(const void *p)
 	if (unlikely(ZERO_OR_NULL_PTR(mem)))
 		return;
 	ks = ksize(mem);
-	memset(mem, 0, ks);
+	memzero_explicit(mem, ks);
 	kfree(mem);
 }
 EXPORT_SYMBOL(kzfree);
diff --git a/mm/slub.c b/mm/slub.c
index 5308227e65db..04a46eaea862 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -261,7 +261,7 @@ static inline void *freelist_ptr(const struct kmem_cache *s, void *ptr,
 	 * freepointer to be restored incorrectly.
 	 */
 	return (void *)((unsigned long)ptr ^ s->random ^
-			(unsigned long)kasan_reset_tag((void *)ptr_addr));
+			swab((unsigned long)kasan_reset_tag((void *)ptr_addr)));
 #else
 	return ptr;
 #endif
@@ -644,6 +644,20 @@ static void slab_fix(struct kmem_cache *s, char *fmt, ...)
 	va_end(args);
 }
 
+static bool freelist_corrupted(struct kmem_cache *s, struct page *page,
+			       void **freelist, void *nextfree)
+{
+	if ((s->flags & SLAB_CONSISTENCY_CHECKS) &&
+	    !check_valid_pointer(s, page, nextfree) && freelist) {
+		object_err(s, page, *freelist, "Freechain corrupt");
+		*freelist = NULL;
+		slab_fix(s, "Isolate corrupted freechain");
+		return true;
+	}
+
+	return false;
+}
+
 static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
 {
 	unsigned int off;	/* Offset of last byte */
@@ -1376,6 +1390,11 @@ static inline void inc_slabs_node(struct kmem_cache *s, int node,
 static inline void dec_slabs_node(struct kmem_cache *s, int node,
 							int objects) {}
 
+static bool freelist_corrupted(struct kmem_cache *s, struct page *page,
+			       void **freelist, void *nextfree)
+{
+	return false;
+}
 #endif /* CONFIG_SLUB_DEBUG */
 
 /*
@@ -1958,8 +1977,6 @@ static void *get_partial(struct kmem_cache *s, gfp_t flags, int node,
 
 	if (node == NUMA_NO_NODE)
 		searchnode = numa_mem_id();
-	else if (!node_present_pages(node))
-		searchnode = node_to_mem_node(node);
 
 	object = get_partial_node(s, get_node(s, searchnode), c, flags);
 	if (object || node != NUMA_NO_NODE)
@@ -2067,6 +2084,14 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page,
 		void *prior;
 		unsigned long counters;
 
+		/*
+		 * If 'nextfree' is invalid, it is possible that the object at
+		 * 'freelist' is already corrupted.  So isolate all objects
+		 * starting at 'freelist'.
+		 */
+		if (freelist_corrupted(s, page, &freelist, nextfree))
+			break;
+
 		do {
 			prior = page->freelist;
 			counters = page->counters;
@@ -2546,17 +2571,27 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 	struct page *page;
 
 	page = c->page;
-	if (!page)
+	if (!page) {
+		/*
+		 * if the node is not online or has no normal memory, just
+		 * ignore the node constraint
+		 */
+		if (unlikely(node != NUMA_NO_NODE &&
+			     !node_state(node, N_NORMAL_MEMORY)))
+			node = NUMA_NO_NODE;
 		goto new_slab;
+	}
 redo:
 
 	if (unlikely(!node_match(page, node))) {
-		int searchnode = node;
-
-		if (node != NUMA_NO_NODE && !node_present_pages(node))
-			searchnode = node_to_mem_node(node);
-
-		if (unlikely(!node_match(page, searchnode))) {
+		/*
+		 * same as above but node_match() being false already
+		 * implies node != NUMA_NO_NODE
+		 */
+		if (!node_state(node, N_NORMAL_MEMORY)) {
+			node = NUMA_NO_NODE;
+			goto redo;
+		} else {
 			stat(s, ALLOC_NODE_MISMATCH);
 			deactivate_slab(s, page, c->freelist, c);
 			goto new_slab;
@@ -2967,11 +3002,13 @@ redo:
 	barrier();
 
 	if (likely(page == c->page)) {
-		set_freepointer(s, tail_obj, c->freelist);
+		void **freelist = READ_ONCE(c->freelist);
+
+		set_freepointer(s, tail_obj, freelist);
 
 		if (unlikely(!this_cpu_cmpxchg_double(
 				s->cpu_slab->freelist, s->cpu_slab->tid,
-				c->freelist, tid,
+				freelist, tid,
 				head, next_tid(tid)))) {
 
 			note_cmpxchg_failure("slab_free", s, tid);
@@ -3145,6 +3182,15 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
 
 		if (unlikely(!object)) {
 			/*
+			 * We may have removed an object from c->freelist using
+			 * the fastpath in the previous iteration; in that case,
+			 * c->tid has not been bumped yet.
+			 * Since ___slab_alloc() may reenable interrupts while
+			 * allocating memory, we should bump c->tid now.
+			 */
+			c->tid = next_tid(c->tid);
+
+			/*
 			 * Invoking slow path likely have side-effect
 			 * of re-populating per CPU c->freelist
 			 */
@@ -5601,7 +5647,8 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
 		 */
 		if (buffer)
 			buf = buffer;
-		else if (root_cache->max_attr_size < ARRAY_SIZE(mbuf))
+		else if (root_cache->max_attr_size < ARRAY_SIZE(mbuf) &&
+			 !IS_ENABLED(CONFIG_SLUB_STATS))
 			buf = mbuf;
 		else {
 			buffer = (char *) get_zeroed_page(GFP_KERNEL);
@@ -5756,8 +5803,10 @@ static int sysfs_slab_add(struct kmem_cache *s)
 
 	s->kobj.kset = kset;
 	err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, "%s", name);
-	if (err)
+	if (err) {
+		kobject_put(&s->kobj);
 		goto out;
+	}
 
 	err = sysfs_create_group(&s->kobj, &slab_attr_group);
 	if (err)
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 61453f1faf72..3f2e8873ccfe 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -21,7 +21,7 @@
 #include <linux/vmalloc.h>
 #include <linux/swap_slots.h>
 #include <linux/huge_mm.h>
-
+#include "internal.h"
 #include <asm/pgtable.h>
 
 /*
@@ -417,7 +417,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		/* May fail (-ENOMEM) if XArray node allocation failed. */
 		__SetPageLocked(new_page);
 		__SetPageSwapBacked(new_page);
-		err = add_to_swap_cache(new_page, entry, gfp_mask & GFP_KERNEL);
+		err = add_to_swap_cache(new_page, entry, gfp_mask & GFP_RECLAIM_MASK);
 		if (likely(!err)) {
 			/* Initiate read into locked page */
 			SetPageWorkingset(new_page);
diff --git a/mm/util.c b/mm/util.c
index 9834c4ab7d8e..be52aa2c9733 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -461,6 +461,24 @@ void kvfree(const void *addr)
 }
 EXPORT_SYMBOL(kvfree);
 
+/**
+ * kvfree_sensitive - Free a data object containing sensitive information.
+ * @addr: address of the data object to be freed.
+ * @len: length of the data object.
+ *
+ * Use the special memzero_explicit() function to clear the content of a
+ * kvmalloc'ed object containing sensitive data to make sure that the
+ * compiler won't optimize out the data clearing.
+ */
+void kvfree_sensitive(const void *addr, size_t len)
+{
+	if (likely(!ZERO_OR_NULL_PTR(addr))) {
+		memzero_explicit((void *)addr, len);
+		kvfree(addr);
+	}
+}
+EXPORT_SYMBOL(kvfree_sensitive);
+
 static inline void *__page_rmapping(struct page *page)
 {
 	unsigned long mapping;
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 080d30408ce3..a47187f486ec 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -34,6 +34,7 @@
 #include <linux/llist.h>
 #include <linux/bitops.h>
 #include <linux/rbtree_augmented.h>
+#include <linux/overflow.h>
 
 #include <linux/uaccess.h>
 #include <asm/tlbflush.h>
@@ -1217,7 +1218,7 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end)
 	 * First make sure the mappings are removed from all page-tables
 	 * before they are freed.
 	 */
-	vmalloc_sync_all();
+	vmalloc_sync_unmappings();
 
 	/*
 	 * TODO: to calculate a flush range without looping.
@@ -2931,6 +2932,7 @@ finished:
  * @vma:		vma to cover
  * @uaddr:		target user address to start at
  * @kaddr:		virtual address of vmalloc kernel memory
+ * @pgoff:		offset from @kaddr to start at
  * @size:		size of map area
  *
  * Returns:	0 for success, -Exxx on failure
@@ -2943,9 +2945,15 @@ finished:
  * Similar to remap_pfn_range() (see mm/memory.c)
  */
 int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr,
-				void *kaddr, unsigned long size)
+				void *kaddr, unsigned long pgoff,
+				unsigned long size)
 {
 	struct vm_struct *area;
+	unsigned long off;
+	unsigned long end_index;
+
+	if (check_shl_overflow(pgoff, PAGE_SHIFT, &off))
+		return -EINVAL;
 
 	size = PAGE_ALIGN(size);
 
@@ -2959,8 +2967,10 @@ int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr,
 	if (!(area->flags & VM_USERMAP))
 		return -EINVAL;
 
-	if (kaddr + size > area->addr + get_vm_area_size(area))
+	if (check_add_overflow(size, off, &end_index) ||
+	    end_index > get_vm_area_size(area))
 		return -EINVAL;
+	kaddr += off;
 
 	do {
 		struct page *page = vmalloc_to_page(kaddr);
@@ -2999,22 +3009,25 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
 						unsigned long pgoff)
 {
 	return remap_vmalloc_range_partial(vma, vma->vm_start,
-					   addr + (pgoff << PAGE_SHIFT),
+					   addr, pgoff,
 					   vma->vm_end - vma->vm_start);
 }
 EXPORT_SYMBOL(remap_vmalloc_range);
 
 /*
- * Implement a stub for vmalloc_sync_all() if the architecture chose not to
- * have one.
+ * Implement stubs for vmalloc_sync_[un]mappings () if the architecture chose
+ * not to have one.
  *
  * The purpose of this function is to make sure the vmalloc area
  * mappings are identical in all page-tables in the system.
  */
-void __weak vmalloc_sync_all(void)
+void __weak vmalloc_sync_mappings(void)
 {
 }
 
+void __weak vmalloc_sync_unmappings(void)
+{
+}
 
 static int f(pte_t *pte, pgtable_t table, unsigned long addr, void *data)
 {
@@ -3242,9 +3255,19 @@ retry:
 			goto overflow;
 
 		/*
+		 * If required width exeeds current VA block, move
+		 * base downwards and then recheck.
+		 */
+		if (base + end > va->va_end) {
+			base = pvm_determine_end_from_reverse(&va, align) - end;
+			term_area = area;
+			continue;
+		}
+
+		/*
 		 * If this VA does not fit, move base downwards and recheck.
 		 */
-		if (base + start < va->va_start || base + end > va->va_end) {
+		if (base + start < va->va_start) {
 			va = node_to_va(rb_prev(&va->rb_node));
 			base = pvm_determine_end_from_reverse(&va, align) - end;
 			term_area = area;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 1b1b42de1ee8..fdd307634c08 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2379,10 +2379,13 @@ out:
 			/*
 			 * Scan types proportional to swappiness and
 			 * their relative recent reclaim efficiency.
-			 * Make sure we don't miss the last page
-			 * because of a round-off error.
+			 * Make sure we don't miss the last page on
+			 * the offlined memory cgroups because of a
+			 * round-off error.
 			 */
-			scan = DIV64_U64_ROUND_UP(scan * fraction[file],
+			scan = mem_cgroup_online(memcg) ?
+			       div64_u64(scan * fraction[file], denominator) :
+			       DIV64_U64_ROUND_UP(scan * fraction[file],
 						  denominator);
 			break;
 		case SCAN_FILE:
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 7d62ef2daf83..b85492d25ba2 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -2092,6 +2092,11 @@ static int zs_page_migrate(struct address_space *mapping, struct page *newpage,
 		zs_pool_dec_isolated(pool);
 	}
 
+	if (page_zone(newpage) != page_zone(page)) {
+		dec_zone_page_state(page, NR_ZSPAGES);
+		inc_zone_page_state(newpage, NR_ZSPAGES);
+	}
+
 	reset_page(page);
 	put_page(page);
 	page = newpage;
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index c46daf09a501..bb7ec1a3915d 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h
@@ -126,6 +126,7 @@ int vlan_check_real_dev(struct net_device *real_dev,
 void vlan_setup(struct net_device *dev);
 int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack);
 void unregister_vlan_dev(struct net_device *dev, struct list_head *head);
+void vlan_dev_uninit(struct net_device *dev);
 bool vlan_dev_inherit_address(struct net_device *dev,
 			      struct net_device *real_dev);
 
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index a0b2d8b9def7..2ab1107ef19f 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -617,7 +617,8 @@ static int vlan_dev_init(struct net_device *dev)
 	return 0;
 }
 
-static void vlan_dev_uninit(struct net_device *dev)
+/* Note: this function might be called multiple times for the same device. */
+void vlan_dev_uninit(struct net_device *dev)
 {
 	struct vlan_priority_tci_mapping *pm;
 	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index c482a6fe9393..0db85aeb119b 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -108,11 +108,13 @@ static int vlan_changelink(struct net_device *dev, struct nlattr *tb[],
 	struct ifla_vlan_flags *flags;
 	struct ifla_vlan_qos_mapping *m;
 	struct nlattr *attr;
-	int rem;
+	int rem, err;
 
 	if (data[IFLA_VLAN_FLAGS]) {
 		flags = nla_data(data[IFLA_VLAN_FLAGS]);
-		vlan_dev_change_flags(dev, flags->flags, flags->mask);
+		err = vlan_dev_change_flags(dev, flags->flags, flags->mask);
+		if (err)
+			return err;
 	}
 	if (data[IFLA_VLAN_INGRESS_QOS]) {
 		nla_for_each_nested(attr, data[IFLA_VLAN_INGRESS_QOS], rem) {
@@ -123,7 +125,9 @@ static int vlan_changelink(struct net_device *dev, struct nlattr *tb[],
 	if (data[IFLA_VLAN_EGRESS_QOS]) {
 		nla_for_each_nested(attr, data[IFLA_VLAN_EGRESS_QOS], rem) {
 			m = nla_data(attr);
-			vlan_dev_set_egress_priority(dev, m->from, m->to);
+			err = vlan_dev_set_egress_priority(dev, m->from, m->to);
+			if (err)
+				return err;
 		}
 	}
 	return 0;
@@ -179,10 +183,11 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev,
 		return -EINVAL;
 
 	err = vlan_changelink(dev, tb, data, extack);
-	if (err < 0)
-		return err;
-
-	return register_vlan_dev(dev, extack);
+	if (!err)
+		err = register_vlan_dev(dev, extack);
+	if (err)
+		vlan_dev_uninit(dev);
+	return err;
 }
 
 static inline size_t vlan_qos_map_size(unsigned int n)
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 13cd683a658a..12ecacf0c55f 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -362,6 +362,10 @@ static void p9_read_work(struct work_struct *work)
 		if (m->rreq->status == REQ_STATUS_SENT) {
 			list_del(&m->rreq->req_list);
 			p9_client_cb(m->client, m->rreq, REQ_STATUS_RCVD);
+		} else if (m->rreq->status == REQ_STATUS_FLSHD) {
+			/* Ignore replies associated with a cancelled request. */
+			p9_debug(P9_DEBUG_TRANS,
+				 "Ignore replies associated with a cancelled request\n");
 		} else {
 			spin_unlock(&m->client->lock);
 			p9_debug(P9_DEBUG_ERROR,
@@ -703,11 +707,20 @@ static int p9_fd_cancelled(struct p9_client *client, struct p9_req_t *req)
 {
 	p9_debug(P9_DEBUG_TRANS, "client %p req %p\n", client, req);
 
+	spin_lock(&client->lock);
+	/* Ignore cancelled request if message has been received
+	 * before lock.
+	 */
+	if (req->status == REQ_STATUS_RCVD) {
+		spin_unlock(&client->lock);
+		return 0;
+	}
+
 	/* we haven't received a response for oldreq,
 	 * remove it from the list.
 	 */
-	spin_lock(&client->lock);
 	list_del(&req->req_list);
+	req->status = REQ_STATUS_FLSHD;
 	spin_unlock(&client->lock);
 	p9_req_put(req);
 
@@ -803,20 +816,28 @@ static int p9_fd_open(struct p9_client *client, int rfd, int wfd)
 		return -ENOMEM;
 
 	ts->rd = fget(rfd);
+	if (!ts->rd)
+		goto out_free_ts;
+	if (!(ts->rd->f_mode & FMODE_READ))
+		goto out_put_rd;
 	ts->wr = fget(wfd);
-	if (!ts->rd || !ts->wr) {
-		if (ts->rd)
-			fput(ts->rd);
-		if (ts->wr)
-			fput(ts->wr);
-		kfree(ts);
-		return -EIO;
-	}
+	if (!ts->wr)
+		goto out_put_rd;
+	if (!(ts->wr->f_mode & FMODE_WRITE))
+		goto out_put_wr;
 
 	client->trans = ts;
 	client->status = Connected;
 
 	return 0;
+
+out_put_wr:
+	fput(ts->wr);
+out_put_rd:
+	fput(ts->rd);
+out_free_ts:
+	kfree(ts);
+	return -EIO;
 }
 
 static int p9_socket_open(struct p9_client *client, struct socket *csocket)
diff --git a/net/Kconfig b/net/Kconfig
index d122f53c6fa2..539f08416ccf 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -52,6 +52,9 @@ config NET_INGRESS
 config NET_EGRESS
 	bool
 
+config NET_REDIRECT
+	bool
+
 config SKB_EXTENSIONS
 	bool
 
diff --git a/net/appletalk/atalk_proc.c b/net/appletalk/atalk_proc.c
index 550c6ca007cc..9c1241292d1d 100644
--- a/net/appletalk/atalk_proc.c
+++ b/net/appletalk/atalk_proc.c
@@ -229,6 +229,8 @@ int __init atalk_proc_init(void)
 				     sizeof(struct aarp_iter_state), NULL))
 		goto out;
 
+	return 0;
+
 out:
 	remove_proc_subtree("atalk", init_net.proc_net);
 	return -ENOMEM;
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index bb222b882b67..2fdb1b573e8c 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -635,8 +635,10 @@ static int ax25_setsockopt(struct socket *sock, int level, int optname,
 		break;
 
 	case SO_BINDTODEVICE:
-		if (optlen > IFNAMSIZ)
-			optlen = IFNAMSIZ;
+		if (optlen > IFNAMSIZ - 1)
+			optlen = IFNAMSIZ - 1;
+
+		memset(devname, 0, sizeof(devname));
 
 		if (copy_from_user(devname, optval, optlen)) {
 			res = -EFAULT;
@@ -1185,7 +1187,10 @@ static int __must_check ax25_connect(struct socket *sock,
 	if (addr_len > sizeof(struct sockaddr_ax25) &&
 	    fsa->fsa_ax25.sax25_ndigis != 0) {
 		/* Valid number of digipeaters ? */
-		if (fsa->fsa_ax25.sax25_ndigis < 1 || fsa->fsa_ax25.sax25_ndigis > AX25_MAX_DIGIS) {
+		if (fsa->fsa_ax25.sax25_ndigis < 1 ||
+		    fsa->fsa_ax25.sax25_ndigis > AX25_MAX_DIGIS ||
+		    addr_len < sizeof(struct sockaddr_ax25) +
+		    sizeof(ax25_address) * fsa->fsa_ax25.sax25_ndigis) {
 			err = -EINVAL;
 			goto out_release;
 		}
@@ -1505,7 +1510,10 @@ static int ax25_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 			struct full_sockaddr_ax25 *fsa = (struct full_sockaddr_ax25 *)usax;
 
 			/* Valid number of digipeaters ? */
-			if (usax->sax25_ndigis < 1 || usax->sax25_ndigis > AX25_MAX_DIGIS) {
+			if (usax->sax25_ndigis < 1 ||
+			    usax->sax25_ndigis > AX25_MAX_DIGIS ||
+			    addr_len < sizeof(struct sockaddr_ax25) +
+			    sizeof(ax25_address) * usax->sax25_ndigis) {
 				err = -EINVAL;
 				goto out;
 			}
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index 5b0b20e6da95..d88a4de02237 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -789,6 +789,10 @@ static void batadv_iv_ogm_schedule_buff(struct batadv_hard_iface *hard_iface)
 
 	lockdep_assert_held(&hard_iface->bat_iv.ogm_buff_mutex);
 
+	/* interface already disabled by batadv_iv_ogm_iface_disable */
+	if (!*ogm_buff)
+		return;
+
 	/* the interface gets activated here to avoid race conditions between
 	 * the moment of activating the interface in
 	 * hardif_activate_interface() where the originator mac is set and
diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c
index 2614a9caee00..a39af0eefad3 100644
--- a/net/batman-adv/bat_v_elp.c
+++ b/net/batman-adv/bat_v_elp.c
@@ -120,20 +120,7 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh)
 	rtnl_lock();
 	ret = __ethtool_get_link_ksettings(hard_iface->net_dev, &link_settings);
 	rtnl_unlock();
-
-	/* Virtual interface drivers such as tun / tap interfaces, VLAN, etc
-	 * tend to initialize the interface throughput with some value for the
-	 * sake of having a throughput number to export via ethtool. This
-	 * exported throughput leaves batman-adv to conclude the interface
-	 * throughput is genuine (reflecting reality), thus no measurements
-	 * are necessary.
-	 *
-	 * Based on the observation that those interface types also tend to set
-	 * the link auto-negotiation to 'off', batman-adv shall check this
-	 * setting to differentiate between genuine link throughput information
-	 * and placeholders installed by virtual interfaces.
-	 */
-	if (ret == 0 && link_settings.base.autoneg == AUTONEG_ENABLE) {
+	if (ret == 0) {
 		/* link characteristics might change over time */
 		if (link_settings.base.duplex == DUPLEX_FULL)
 			hard_iface->bat_v.flags |= BATADV_FULL_DUPLEX;
diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c
index bc06e3cdfa84..47d7a4f267cd 100644
--- a/net/batman-adv/bat_v_ogm.c
+++ b/net/batman-adv/bat_v_ogm.c
@@ -703,7 +703,7 @@ static void batadv_v_ogm_process(const struct sk_buff *skb, int ogm_offset,
 
 	orig_node = batadv_v_ogm_orig_get(bat_priv, ogm_packet->orig);
 	if (!orig_node)
-		return;
+		goto out;
 
 	neigh_node = batadv_neigh_node_get_or_create(orig_node, if_incoming,
 						     ethhdr->h_source);
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index b0af3a11d406..ec7bf5a4a9fc 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -285,6 +285,7 @@ static u32 batadv_hash_dat(const void *data, u32 size)
 	u32 hash = 0;
 	const struct batadv_dat_entry *dat = data;
 	const unsigned char *key;
+	__be16 vid;
 	u32 i;
 
 	key = (const unsigned char *)&dat->ip;
@@ -294,7 +295,8 @@ static u32 batadv_hash_dat(const void *data, u32 size)
 		hash ^= (hash >> 6);
 	}
 
-	key = (const unsigned char *)&dat->vid;
+	vid = htons(dat->vid);
+	key = (__force const unsigned char *)&vid;
 	for (i = 0; i < sizeof(dat->vid); i++) {
 		hash += key[i];
 		hash += (hash << 10);
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index c5e7906045f3..b7f3d9ef83cf 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -1009,15 +1009,8 @@ static struct batadv_nc_path *batadv_nc_get_path(struct batadv_priv *bat_priv,
  */
 static u8 batadv_nc_random_weight_tq(u8 tq)
 {
-	u8 rand_val, rand_tq;
-
-	get_random_bytes(&rand_val, sizeof(rand_val));
-
 	/* randomize the estimated packet loss (max TQ - estimated TQ) */
-	rand_tq = rand_val * (BATADV_TQ_MAX_VALUE - tq);
-
-	/* normalize the randomized packet loss */
-	rand_tq /= BATADV_TQ_MAX_VALUE;
+	u8 rand_tq = prandom_u32_max(BATADV_TQ_MAX_VALUE + 1 - tq);
 
 	/* convert to (randomized) estimated tq again */
 	return BATADV_TQ_MAX_VALUE - rand_tq;
diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c
index 80fc3253c336..34e9948fbd45 100644
--- a/net/batman-adv/sysfs.c
+++ b/net/batman-adv/sysfs.c
@@ -1149,7 +1149,7 @@ static ssize_t batadv_store_throughput_override(struct kobject *kobj,
 	ret = batadv_parse_throughput(net_dev, buff, "throughput_override",
 				      &tp_override);
 	if (!ret)
-		return count;
+		goto out;
 
 	old_tp_override = atomic_read(&hard_iface->bat_v.throughput_override);
 	if (old_tp_override == tp_override)
@@ -1189,6 +1189,7 @@ static ssize_t batadv_show_throughput_override(struct kobject *kobj,
 
 	tp_override = atomic_read(&hard_iface->bat_v.throughput_override);
 
+	batadv_hardif_put(hard_iface);
 	return sprintf(buff, "%u.%u MBit\n", tp_override / 10,
 		       tp_override % 10);
 }
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index 9001bf331d56..120529290d99 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -50,6 +50,7 @@ static bool enable_6lowpan;
 /* We are listening incoming connections via this channel
  */
 static struct l2cap_chan *listen_chan;
+static DEFINE_MUTEX(set_lock);
 
 struct lowpan_peer {
 	struct list_head list;
@@ -1075,12 +1076,14 @@ static void do_enable_set(struct work_struct *work)
 
 	enable_6lowpan = set_enable->flag;
 
+	mutex_lock(&set_lock);
 	if (listen_chan) {
 		l2cap_chan_close(listen_chan, 0);
 		l2cap_chan_put(listen_chan);
 	}
 
 	listen_chan = bt_6lowpan_listen();
+	mutex_unlock(&set_lock);
 
 	kfree(set_enable);
 }
@@ -1132,11 +1135,13 @@ static ssize_t lowpan_control_write(struct file *fp,
 		if (ret == -EINVAL)
 			return ret;
 
+		mutex_lock(&set_lock);
 		if (listen_chan) {
 			l2cap_chan_close(listen_chan, 0);
 			l2cap_chan_put(listen_chan);
 			listen_chan = NULL;
 		}
+		mutex_unlock(&set_lock);
 
 		if (conn) {
 			struct lowpan_peer *peer;
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index f5c27065ad44..db735d0d931e 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -1173,8 +1173,10 @@ struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst,
 	if (!conn)
 		return ERR_PTR(-ENOMEM);
 
-	if (hci_explicit_conn_params_set(hdev, dst, dst_type) < 0)
+	if (hci_explicit_conn_params_set(hdev, dst, dst_type) < 0) {
+		hci_conn_del(conn);
 		return ERR_PTR(-EBUSY);
+	}
 
 	conn->state = BT_CONNECT;
 	set_bit(HCI_CONN_SCANNING, &conn->flags);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index d7a58a5a5d6b..90846751ce43 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1444,11 +1444,20 @@ static int hci_dev_do_open(struct hci_dev *hdev)
 
 	if (hci_dev_test_flag(hdev, HCI_SETUP) ||
 	    test_bit(HCI_QUIRK_NON_PERSISTENT_SETUP, &hdev->quirks)) {
+		bool invalid_bdaddr;
+
 		hci_sock_dev_event(hdev, HCI_DEV_SETUP);
 
 		if (hdev->setup)
 			ret = hdev->setup(hdev);
 
+		/* The transport driver can set the quirk to mark the
+		 * BD_ADDR invalid before creating the HCI device or in
+		 * its setup callback.
+		 */
+		invalid_bdaddr = test_bit(HCI_QUIRK_INVALID_BDADDR,
+					  &hdev->quirks);
+
 		if (ret)
 			goto setup_failed;
 
@@ -1457,20 +1466,33 @@ static int hci_dev_do_open(struct hci_dev *hdev)
 				hci_dev_get_bd_addr_from_property(hdev);
 
 			if (bacmp(&hdev->public_addr, BDADDR_ANY) &&
-			    hdev->set_bdaddr)
+			    hdev->set_bdaddr) {
 				ret = hdev->set_bdaddr(hdev,
 						       &hdev->public_addr);
+
+				/* If setting of the BD_ADDR from the device
+				 * property succeeds, then treat the address
+				 * as valid even if the invalid BD_ADDR
+				 * quirk indicates otherwise.
+				 */
+				if (!ret)
+					invalid_bdaddr = false;
+			}
 		}
 
 setup_failed:
 		/* The transport driver can set these quirks before
 		 * creating the HCI device or in its setup callback.
 		 *
+		 * For the invalid BD_ADDR quirk it is possible that
+		 * it becomes a valid address if the bootloader does
+		 * provide it (see above).
+		 *
 		 * In case any of them is set, the controller has to
 		 * start up as unconfigured.
 		 */
 		if (test_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks) ||
-		    test_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks))
+		    invalid_bdaddr)
 			hci_dev_set_flag(hdev, HCI_UNCONFIGURED);
 
 		/* For an unconfigured controller it is required to
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 9e4fcf406d9c..b323c65a4485 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1229,6 +1229,9 @@ static void store_pending_adv_report(struct hci_dev *hdev, bdaddr_t *bdaddr,
 {
 	struct discovery_state *d = &hdev->discovery;
 
+	if (len > HCI_MAX_AD_LENGTH)
+		return;
+
 	bacpy(&d->last_adv_addr, bdaddr);
 	d->last_adv_addr_type = bdaddr_type;
 	d->last_adv_rssi = rssi;
@@ -2396,7 +2399,7 @@ static void hci_inquiry_result_evt(struct hci_dev *hdev, struct sk_buff *skb)
 
 	BT_DBG("%s num_rsp %d", hdev->name, num_rsp);
 
-	if (!num_rsp)
+	if (!num_rsp || skb->len < num_rsp * sizeof(*info) + 1)
 		return;
 
 	if (hci_dev_test_flag(hdev, HCI_PERIODIC_INQ))
@@ -3992,6 +3995,9 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev,
 		struct inquiry_info_with_rssi_and_pscan_mode *info;
 		info = (void *) (skb->data + 1);
 
+		if (skb->len < num_rsp * sizeof(*info) + 1)
+			goto unlock;
+
 		for (; num_rsp; num_rsp--, info++) {
 			u32 flags;
 
@@ -4013,6 +4019,9 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev,
 	} else {
 		struct inquiry_info_with_rssi *info = (void *) (skb->data + 1);
 
+		if (skb->len < num_rsp * sizeof(*info) + 1)
+			goto unlock;
+
 		for (; num_rsp; num_rsp--, info++) {
 			u32 flags;
 
@@ -4033,6 +4042,7 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev,
 		}
 	}
 
+unlock:
 	hci_dev_unlock(hdev);
 }
 
@@ -4144,6 +4154,7 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev,
 	case 0x11:	/* Unsupported Feature or Parameter Value */
 	case 0x1c:	/* SCO interval rejected */
 	case 0x1a:	/* Unsupported Remote Feature */
+	case 0x1e:	/* Invalid LMP Parameters */
 	case 0x1f:	/* Unspecified error */
 	case 0x20:	/* Unsupported LMP Parameter value */
 		if (conn->out) {
@@ -4194,7 +4205,7 @@ static void hci_extended_inquiry_result_evt(struct hci_dev *hdev,
 
 	BT_DBG("%s num_rsp %d", hdev->name, num_rsp);
 
-	if (!num_rsp)
+	if (!num_rsp || skb->len < num_rsp * sizeof(*info) + 1)
 		return;
 
 	if (hci_dev_test_flag(hdev, HCI_PERIODIC_INQ))
@@ -5158,7 +5169,8 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev,
 
 static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr,
 			       u8 bdaddr_type, bdaddr_t *direct_addr,
-			       u8 direct_addr_type, s8 rssi, u8 *data, u8 len)
+			       u8 direct_addr_type, s8 rssi, u8 *data, u8 len,
+			       bool ext_adv)
 {
 	struct discovery_state *d = &hdev->discovery;
 	struct smp_irk *irk;
@@ -5180,6 +5192,11 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr,
 		return;
 	}
 
+	if (!ext_adv && len > HCI_MAX_AD_LENGTH) {
+		bt_dev_err_ratelimited(hdev, "legacy adv larger than 31 bytes");
+		return;
+	}
+
 	/* Find the end of the data in case the report contains padded zero
 	 * bytes at the end causing an invalid length value.
 	 *
@@ -5239,7 +5256,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr,
 	 */
 	conn = check_pending_le_conn(hdev, bdaddr, bdaddr_type, type,
 								direct_addr);
-	if (conn && type == LE_ADV_IND) {
+	if (!ext_adv && conn && type == LE_ADV_IND && len <= HCI_MAX_AD_LENGTH) {
 		/* Store report for later inclusion by
 		 * mgmt_device_connected
 		 */
@@ -5293,7 +5310,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr,
 	 * event or send an immediate device found event if the data
 	 * should not be stored for later.
 	 */
-	if (!has_pending_adv_report(hdev)) {
+	if (!ext_adv &&	!has_pending_adv_report(hdev)) {
 		/* If the report will trigger a SCAN_REQ store it for
 		 * later merging.
 		 */
@@ -5328,7 +5345,8 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr,
 		/* If the new report will trigger a SCAN_REQ store it for
 		 * later merging.
 		 */
-		if (type == LE_ADV_IND || type == LE_ADV_SCAN_IND) {
+		if (!ext_adv && (type == LE_ADV_IND ||
+				 type == LE_ADV_SCAN_IND)) {
 			store_pending_adv_report(hdev, bdaddr, bdaddr_type,
 						 rssi, flags, data, len);
 			return;
@@ -5368,7 +5386,7 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb)
 			rssi = ev->data[ev->length];
 			process_adv_report(hdev, ev->evt_type, &ev->bdaddr,
 					   ev->bdaddr_type, NULL, 0, rssi,
-					   ev->data, ev->length);
+					   ev->data, ev->length, false);
 		} else {
 			bt_dev_err(hdev, "Dropping invalid advertising data");
 		}
@@ -5442,7 +5460,8 @@ static void hci_le_ext_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		if (legacy_evt_type != LE_ADV_INVALID) {
 			process_adv_report(hdev, legacy_evt_type, &ev->bdaddr,
 					   ev->bdaddr_type, NULL, 0, ev->rssi,
-					   ev->data, ev->length);
+					   ev->data, ev->length,
+					   !(evt_type & LE_EXT_ADV_LEGACY_PDU));
 		}
 
 		ptr += sizeof(*ev) + ev->length;
@@ -5640,7 +5659,8 @@ static void hci_le_direct_adv_report_evt(struct hci_dev *hdev,
 
 		process_adv_report(hdev, ev->evt_type, &ev->bdaddr,
 				   ev->bdaddr_type, &ev->direct_addr,
-				   ev->direct_addr_type, ev->rssi, NULL, 0);
+				   ev->direct_addr_type, ev->rssi, NULL, 0,
+				   false);
 
 		ptr += sizeof(*ev);
 	}
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index d32077b28433..8159b344deef 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -831,6 +831,8 @@ static int hci_sock_release(struct socket *sock)
 	if (!sk)
 		return 0;
 
+	lock_sock(sk);
+
 	switch (hci_pi(sk)->channel) {
 	case HCI_CHANNEL_MONITOR:
 		atomic_dec(&monitor_promisc);
@@ -878,6 +880,7 @@ static int hci_sock_release(struct socket *sock)
 	skb_queue_purge(&sk->sk_receive_queue);
 	skb_queue_purge(&sk->sk_write_queue);
 
+	release_sock(sk);
 	sock_put(sk);
 	return 0;
 }
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 771e3e17bb6a..2c8ff1854beb 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -4928,10 +4928,8 @@ void __l2cap_physical_cfm(struct l2cap_chan *chan, int result)
 	BT_DBG("chan %p, result %d, local_amp_id %d, remote_amp_id %d",
 	       chan, result, local_amp_id, remote_amp_id);
 
-	if (chan->state == BT_DISCONN || chan->state == BT_CLOSED) {
-		l2cap_chan_unlock(chan);
+	if (chan->state == BT_DISCONN || chan->state == BT_CLOSED)
 		return;
-	}
 
 	if (chan->state != BT_CONNECTED) {
 		l2cap_do_create(chan, result, local_amp_id, remote_amp_id);
diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c
index 0c7d31c6c18c..a58584949a95 100644
--- a/net/bluetooth/rfcomm/tty.c
+++ b/net/bluetooth/rfcomm/tty.c
@@ -413,10 +413,8 @@ static int __rfcomm_create_dev(struct sock *sk, void __user *arg)
 		dlc = rfcomm_dlc_exists(&req.src, &req.dst, req.channel);
 		if (IS_ERR(dlc))
 			return PTR_ERR(dlc);
-		else if (dlc) {
-			rfcomm_dlc_put(dlc);
+		if (dlc)
 			return -EBUSY;
-		}
 		dlc = rfcomm_dlc_alloc(GFP_KERNEL);
 		if (!dlc)
 			return -ENOMEM;
diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c
index 37908561a64b..b18cdf03edb3 100644
--- a/net/bridge/br_arp_nd_proxy.c
+++ b/net/bridge/br_arp_nd_proxy.c
@@ -276,6 +276,10 @@ static void br_nd_send(struct net_bridge *br, struct net_bridge_port *p,
 	ns_olen = request->len - (skb_network_offset(request) +
 				  sizeof(struct ipv6hdr)) - sizeof(*ns);
 	for (i = 0; i < ns_olen - 1; i += (ns->opt[i + 1] << 3)) {
+		if (!ns->opt[i + 1]) {
+			kfree_skb(reply);
+			return;
+		}
 		if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) {
 			daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
 			break;
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index f8cac3702712..9e3e46bbb06e 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -991,7 +991,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
 		nsrcs_offset = len + offsetof(struct mld2_grec, grec_nsrcs);
 
 		if (skb_transport_offset(skb) + ipv6_transport_len(skb) <
-		    nsrcs_offset + sizeof(_nsrcs))
+		    nsrcs_offset + sizeof(__nsrcs))
 			return -EINVAL;
 
 		_nsrcs = skb_header_pointer(skb, nsrcs_offset,
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 9564a953bdf9..a36a3ba20460 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -207,8 +207,8 @@ struct net_bridge_port_group {
 	struct rcu_head			rcu;
 	struct timer_list		timer;
 	struct br_ip			addr;
+	unsigned char			eth_addr[ETH_ALEN] __aligned(2);
 	unsigned char			flags;
-	unsigned char			eth_addr[ETH_ALEN];
 };
 
 struct net_bridge_mdb_entry {
diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index b325b569e761..f48cf4cfb80f 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -31,6 +31,12 @@ static void nft_reject_br_push_etherhdr(struct sk_buff *oldskb,
 	ether_addr_copy(eth->h_dest, eth_hdr(oldskb)->h_source);
 	eth->h_proto = eth_hdr(oldskb)->h_proto;
 	skb_pull(nskb, ETH_HLEN);
+
+	if (skb_vlan_tag_present(oldskb)) {
+		u16 vid = skb_vlan_tag_get(oldskb);
+
+		__vlan_hwaccel_put_tag(nskb, oldskb->vlan_proto, vid);
+	}
 }
 
 static int nft_bridge_iphdr_validate(struct sk_buff *skb)
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index cd0b094468b6..f207eb7aabce 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -3241,12 +3241,16 @@ static struct ceph_msg_data *ceph_msg_data_add(struct ceph_msg *msg)
 
 static void ceph_msg_data_destroy(struct ceph_msg_data *data)
 {
-	if (data->type == CEPH_MSG_DATA_PAGELIST)
+	if (data->type == CEPH_MSG_DATA_PAGES && data->own_pages) {
+		int num_pages = calc_pages_for(data->alignment, data->length);
+		ceph_release_page_vector(data->pages, num_pages);
+	} else if (data->type == CEPH_MSG_DATA_PAGELIST) {
 		ceph_pagelist_release(data->pagelist);
+	}
 }
 
 void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages,
-		size_t length, size_t alignment)
+			     size_t length, size_t alignment, bool own_pages)
 {
 	struct ceph_msg_data *data;
 
@@ -3258,6 +3262,7 @@ void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages,
 	data->pages = pages;
 	data->length = length;
 	data->alignment = alignment & ~PAGE_MASK;
+	data->own_pages = own_pages;
 
 	msg->data_length += length;
 }
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 565ea889673c..bb85787f9237 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -453,6 +453,7 @@ static void target_copy(struct ceph_osd_request_target *dest,
 	dest->size = src->size;
 	dest->min_size = src->min_size;
 	dest->sort_bitwise = src->sort_bitwise;
+	dest->recovery_deletes = src->recovery_deletes;
 
 	dest->flags = src->flags;
 	dest->paused = src->paused;
@@ -953,7 +954,7 @@ static void ceph_osdc_msg_data_add(struct ceph_msg *msg,
 		BUG_ON(length > (u64) SIZE_MAX);
 		if (length)
 			ceph_msg_data_add_pages(msg, osd_data->pages,
-					length, osd_data->alignment);
+					length, osd_data->alignment, false);
 	} else if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGELIST) {
 		BUG_ON(!length);
 		ceph_msg_data_add_pagelist(msg, osd_data->pagelist);
@@ -3636,7 +3637,9 @@ static void handle_reply(struct ceph_osd *osd, struct ceph_msg *msg)
 		 * supported.
 		 */
 		req->r_t.target_oloc.pool = m.redirect.oloc.pool;
-		req->r_flags |= CEPH_OSD_FLAG_REDIRECTED;
+		req->r_flags |= CEPH_OSD_FLAG_REDIRECTED |
+				CEPH_OSD_FLAG_IGNORE_OVERLAY |
+				CEPH_OSD_FLAG_IGNORE_CACHE;
 		req->r_tid = 0;
 		__submit_request(req, false);
 		goto out_unlock_osdc;
@@ -4421,9 +4424,7 @@ static void handle_watch_notify(struct ceph_osd_client *osdc,
 							CEPH_MSG_DATA_PAGES);
 					*lreq->preply_pages = data->pages;
 					*lreq->preply_len = data->length;
-				} else {
-					ceph_release_page_vector(data->pages,
-					       calc_pages_for(0, data->length));
+					data->own_pages = false;
 				}
 			}
 			lreq->notify_finish_error = return_code;
@@ -5461,9 +5462,6 @@ out_unlock_osdc:
 	return m;
 }
 
-/*
- * TODO: switch to a msg-owned pagelist
- */
 static struct ceph_msg *alloc_msg_with_page_vector(struct ceph_msg_header *hdr)
 {
 	struct ceph_msg *m;
@@ -5477,7 +5475,6 @@ static struct ceph_msg *alloc_msg_with_page_vector(struct ceph_msg_header *hdr)
 
 	if (data_len) {
 		struct page **pages;
-		struct ceph_osd_data osd_data;
 
 		pages = ceph_alloc_page_vector(calc_pages_for(0, data_len),
 					       GFP_NOIO);
@@ -5486,9 +5483,7 @@ static struct ceph_msg *alloc_msg_with_page_vector(struct ceph_msg_header *hdr)
 			return NULL;
 		}
 
-		ceph_osd_data_pages_init(&osd_data, pages, data_len, 0, false,
-					 false);
-		ceph_osdc_msg_data_add(m, &osd_data);
+		ceph_msg_data_add_pages(m, pages, data_len, 0, true);
 	}
 
 	return m;
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 48a31dc9161c..f6a366eb8aa5 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -710,6 +710,15 @@ int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name)
 }
 EXPORT_SYMBOL(ceph_pg_poolid_by_name);
 
+u64 ceph_pg_pool_flags(struct ceph_osdmap *map, u64 id)
+{
+	struct ceph_pg_pool_info *pi;
+
+	pi = __lookup_pg_pool(&map->pg_pools, id);
+	return pi ? pi->flags : 0;
+}
+EXPORT_SYMBOL(ceph_pg_pool_flags);
+
 static void __remove_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *pi)
 {
 	rb_erase(&pi->node, root);
diff --git a/net/compat.c b/net/compat.c
index 3f9ce609397f..24906536870f 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -290,6 +290,7 @@ void scm_detach_fds_compat(struct msghdr *kmsg, struct scm_cookie *scm)
 			break;
 		}
 		/* Bump the usage count and install the file. */
+		__receive_sock(fp[i]);
 		fd_install(new_fd, get_file(fp[i]));
 	}
 
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index d1c4e1f3be2c..e013639b23c7 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -633,9 +633,10 @@ static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr)
 		return ERR_PTR(-ENOMEM);
 	bpf_map_init_from_attr(&smap->map, attr);
 
+	nbuckets = roundup_pow_of_two(num_possible_cpus());
 	/* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */
-	smap->bucket_log = max_t(u32, 1, ilog2(roundup_pow_of_two(num_possible_cpus())));
-	nbuckets = 1U << smap->bucket_log;
+	nbuckets = max_t(u32, 2, nbuckets);
+	smap->bucket_log = ilog2(nbuckets);
 	smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets,
 				 GFP_USER | __GFP_NOWARN);
 	if (!smap->buckets) {
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 5dc112ec7286..acb7d2b04a07 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -51,6 +51,7 @@
 #include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/uio.h>
+#include <linux/indirect_call_wrapper.h>
 
 #include <net/protocol.h>
 #include <linux/skbuff.h>
@@ -407,6 +408,11 @@ int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags)
 }
 EXPORT_SYMBOL(skb_kill_datagram);
 
+INDIRECT_CALLABLE_DECLARE(static size_t simple_copy_to_iter(const void *addr,
+						size_t bytes,
+						void *data __always_unused,
+						struct iov_iter *i));
+
 static int __skb_datagram_iter(const struct sk_buff *skb, int offset,
 			       struct iov_iter *to, int len, bool fault_short,
 			       size_t (*cb)(const void *, size_t, void *,
@@ -420,7 +426,8 @@ static int __skb_datagram_iter(const struct sk_buff *skb, int offset,
 	if (copy > 0) {
 		if (copy > len)
 			copy = len;
-		n = cb(skb->data + offset, copy, data, to);
+		n = INDIRECT_CALL_1(cb, simple_copy_to_iter,
+				    skb->data + offset, copy, data, to);
 		offset += n;
 		if (n != copy)
 			goto short_copy;
@@ -442,8 +449,9 @@ static int __skb_datagram_iter(const struct sk_buff *skb, int offset,
 
 			if (copy > len)
 				copy = len;
-			n = cb(vaddr + frag->page_offset +
-				offset - start, copy, data, to);
+			n = INDIRECT_CALL_1(cb, simple_copy_to_iter,
+					vaddr + frag->page_offset + offset - start,
+					copy, data, to);
 			kunmap(page);
 			offset += n;
 			if (n != copy)
@@ -640,7 +648,7 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb,
 		skb->len += copied;
 		skb->truesize += truesize;
 		if (sk && sk->sk_type == SOCK_STREAM) {
-			sk->sk_wmem_queued += truesize;
+			sk_wmem_queued_add(sk, truesize);
 			sk_mem_charge(sk, truesize);
 		} else {
 			refcount_add(truesize, &skb->sk->sk_wmem_alloc);
diff --git a/net/core/dev.c b/net/core/dev.c
index f9cd0705a392..cff7f1d91bf3 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -79,6 +79,7 @@
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
 #include <linux/mutex.h>
+#include <linux/rwsem.h>
 #include <linux/string.h>
 #include <linux/mm.h>
 #include <linux/socket.h>
@@ -194,7 +195,7 @@ static DEFINE_SPINLOCK(napi_hash_lock);
 static unsigned int napi_gen_id = NR_CPUS;
 static DEFINE_READ_MOSTLY_HASHTABLE(napi_hash, 8);
 
-static seqcount_t devnet_rename_seq;
+static DECLARE_RWSEM(devnet_rename_sem);
 
 static inline void dev_base_seq_inc(struct net *net)
 {
@@ -898,33 +899,28 @@ EXPORT_SYMBOL(dev_get_by_napi_id);
  *	@net: network namespace
  *	@name: a pointer to the buffer where the name will be stored.
  *	@ifindex: the ifindex of the interface to get the name from.
- *
- *	The use of raw_seqcount_begin() and cond_resched() before
- *	retrying is required as we want to give the writers a chance
- *	to complete when CONFIG_PREEMPT is not set.
  */
 int netdev_get_name(struct net *net, char *name, int ifindex)
 {
 	struct net_device *dev;
-	unsigned int seq;
+	int ret;
 
-retry:
-	seq = raw_seqcount_begin(&devnet_rename_seq);
+	down_read(&devnet_rename_sem);
 	rcu_read_lock();
+
 	dev = dev_get_by_index_rcu(net, ifindex);
 	if (!dev) {
-		rcu_read_unlock();
-		return -ENODEV;
+		ret = -ENODEV;
+		goto out;
 	}
 
 	strcpy(name, dev->name);
-	rcu_read_unlock();
-	if (read_seqcount_retry(&devnet_rename_seq, seq)) {
-		cond_resched();
-		goto retry;
-	}
 
-	return 0;
+	ret = 0;
+out:
+	rcu_read_unlock();
+	up_read(&devnet_rename_sem);
+	return ret;
 }
 
 /**
@@ -1197,10 +1193,10 @@ int dev_change_name(struct net_device *dev, const char *newname)
 	    likely(!(dev->priv_flags & IFF_LIVE_RENAME_OK)))
 		return -EBUSY;
 
-	write_seqcount_begin(&devnet_rename_seq);
+	down_write(&devnet_rename_sem);
 
 	if (strncmp(newname, dev->name, IFNAMSIZ) == 0) {
-		write_seqcount_end(&devnet_rename_seq);
+		up_write(&devnet_rename_sem);
 		return 0;
 	}
 
@@ -1208,7 +1204,7 @@ int dev_change_name(struct net_device *dev, const char *newname)
 
 	err = dev_get_valid_name(net, dev, newname);
 	if (err < 0) {
-		write_seqcount_end(&devnet_rename_seq);
+		up_write(&devnet_rename_sem);
 		return err;
 	}
 
@@ -1223,11 +1219,11 @@ rollback:
 	if (ret) {
 		memcpy(dev->name, oldname, IFNAMSIZ);
 		dev->name_assign_type = old_assign_type;
-		write_seqcount_end(&devnet_rename_seq);
+		up_write(&devnet_rename_sem);
 		return ret;
 	}
 
-	write_seqcount_end(&devnet_rename_seq);
+	up_write(&devnet_rename_sem);
 
 	netdev_adjacent_rename_links(dev, oldname);
 
@@ -1248,7 +1244,7 @@ rollback:
 		/* err >= 0 after dev_alloc_name() or stores the first errno */
 		if (err >= 0) {
 			err = ret;
-			write_seqcount_begin(&devnet_rename_seq);
+			down_write(&devnet_rename_sem);
 			memcpy(dev->name, oldname, IFNAMSIZ);
 			memcpy(oldname, newname, IFNAMSIZ);
 			dev->name_assign_type = old_assign_type;
@@ -2877,6 +2873,8 @@ static u16 skb_tx_hash(const struct net_device *dev,
 
 	if (skb_rx_queue_recorded(skb)) {
 		hash = skb_get_rx_queue(skb);
+		if (hash >= qoffset)
+			hash -= qoffset;
 		while (unlikely(hash >= qcount))
 			hash -= qcount;
 		return hash + qoffset;
@@ -3475,26 +3473,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 	qdisc_calculate_pkt_len(skb, q);
 
 	if (q->flags & TCQ_F_NOLOCK) {
-		if ((q->flags & TCQ_F_CAN_BYPASS) && q->empty &&
-		    qdisc_run_begin(q)) {
-			if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED,
-					      &q->state))) {
-				__qdisc_drop(skb, &to_free);
-				rc = NET_XMIT_DROP;
-				goto end_run;
-			}
-			qdisc_bstats_cpu_update(q, skb);
-
-			rc = NET_XMIT_SUCCESS;
-			if (sch_direct_xmit(skb, q, dev, txq, NULL, true))
-				__qdisc_run(q);
-
-end_run:
-			qdisc_run_end(q);
-		} else {
-			rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
-			qdisc_run(q);
-		}
+		rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
+		qdisc_run(q);
 
 		if (unlikely(to_free))
 			kfree_skb_list(to_free);
@@ -3942,10 +3922,12 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
 
 	local_bh_disable();
 
+	dev_xmit_recursion_inc();
 	HARD_TX_LOCK(dev, txq, smp_processor_id());
 	if (!netif_xmit_frozen_or_drv_stopped(txq))
 		ret = netdev_start_xmit(skb, dev, txq, false);
 	HARD_TX_UNLOCK(dev, txq);
+	dev_xmit_recursion_dec();
 
 	local_bh_enable();
 
@@ -3969,7 +3951,8 @@ EXPORT_SYMBOL(netdev_max_backlog);
 
 int netdev_tstamp_prequeue __read_mostly = 1;
 int netdev_budget __read_mostly = 300;
-unsigned int __read_mostly netdev_budget_usecs = 2000;
+/* Must be at least 2 jiffes to guarantee 1 jiffy timeout */
+unsigned int __read_mostly netdev_budget_usecs = 2 * USEC_PER_SEC / HZ;
 int weight_p __read_mostly = 64;           /* old backlog weight */
 int dev_weight_rx_bias __read_mostly = 1;  /* bias for backlog weight */
 int dev_weight_tx_bias __read_mostly = 1;  /* bias for output_queue quota */
@@ -4343,14 +4326,14 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 	/* Reinjected packets coming from act_mirred or similar should
 	 * not get XDP generic processing.
 	 */
-	if (skb_cloned(skb) || skb_is_tc_redirected(skb))
+	if (skb_is_redirected(skb))
 		return XDP_PASS;
 
 	/* XDP packets must be linear and must have sufficient headroom
 	 * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also
 	 * native XDP provides, thus we need to do it here as well.
 	 */
-	if (skb_is_nonlinear(skb) ||
+	if (skb_cloned(skb) || skb_is_nonlinear(skb) ||
 	    skb_headroom(skb) < XDP_PACKET_HEADROOM) {
 		int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb);
 		int troom = skb->tail + skb->data_len - skb->end;
@@ -4818,11 +4801,12 @@ static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev,
 	return 0;
 }
 
-static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc,
+static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc,
 				    struct packet_type **ppt_prev)
 {
 	struct packet_type *ptype, *pt_prev;
 	rx_handler_func_t *rx_handler;
+	struct sk_buff *skb = *pskb;
 	struct net_device *orig_dev;
 	bool deliver_exact = false;
 	int ret = NET_RX_DROP;
@@ -4853,8 +4837,10 @@ another_round:
 		ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), skb);
 		preempt_enable();
 
-		if (ret2 != XDP_PASS)
-			return NET_RX_DROP;
+		if (ret2 != XDP_PASS) {
+			ret = NET_RX_DROP;
+			goto out;
+		}
 		skb_reset_mac_len(skb);
 	}
 
@@ -4894,7 +4880,7 @@ skip_taps:
 			goto out;
 	}
 #endif
-	skb_reset_tc(skb);
+	skb_reset_redirect(skb);
 skip_classify:
 	if (pfmemalloc && !skb_pfmemalloc_protocol(skb))
 		goto drop;
@@ -5004,6 +4990,13 @@ drop:
 	}
 
 out:
+	/* The invariant here is that if *ppt_prev is not NULL
+	 * then skb should also be non-NULL.
+	 *
+	 * Apparently *ppt_prev assignment above holds this invariant due to
+	 * skb dereferencing near it.
+	 */
+	*pskb = skb;
 	return ret;
 }
 
@@ -5013,7 +5006,7 @@ static int __netif_receive_skb_one_core(struct sk_buff *skb, bool pfmemalloc)
 	struct packet_type *pt_prev = NULL;
 	int ret;
 
-	ret = __netif_receive_skb_core(skb, pfmemalloc, &pt_prev);
+	ret = __netif_receive_skb_core(&skb, pfmemalloc, &pt_prev);
 	if (pt_prev)
 		ret = INDIRECT_CALL_INET(pt_prev->func, ipv6_rcv, ip_rcv, skb,
 					 skb->dev, pt_prev, orig_dev);
@@ -5091,7 +5084,7 @@ static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemallo
 		struct packet_type *pt_prev = NULL;
 
 		skb_list_del_init(skb);
-		__netif_receive_skb_core(skb, pfmemalloc, &pt_prev);
+		__netif_receive_skb_core(&skb, pfmemalloc, &pt_prev);
 		if (!pt_prev)
 			continue;
 		if (pt_curr != pt_prev || od_curr != orig_dev) {
@@ -5326,7 +5319,7 @@ static void flush_backlog(struct work_struct *work)
 	skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) {
 		if (skb->dev->reg_state == NETREG_UNREGISTERING) {
 			__skb_unlink(skb, &sd->input_pkt_queue);
-			kfree_skb(skb);
+			dev_kfree_skb_irq(skb);
 			input_queue_head_incr(sd);
 		}
 	}
@@ -6616,6 +6609,21 @@ struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
 }
 EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu);
 
+static struct net_device *netdev_next_upper_dev(struct net_device *dev,
+						struct list_head **iter)
+{
+	struct netdev_adjacent *upper;
+
+	upper = list_entry((*iter)->next, struct netdev_adjacent, list);
+
+	if (&upper->list == &dev->adj_list.upper)
+		return NULL;
+
+	*iter = &upper->list;
+
+	return upper->dev;
+}
+
 static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev,
 						    struct list_head **iter)
 {
@@ -6633,28 +6641,93 @@ static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev,
 	return upper->dev;
 }
 
+static int netdev_walk_all_upper_dev(struct net_device *dev,
+				     int (*fn)(struct net_device *dev,
+					       void *data),
+				     void *data)
+{
+	struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+	struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+	int ret, cur = 0;
+
+	now = dev;
+	iter = &dev->adj_list.upper;
+
+	while (1) {
+		if (now != dev) {
+			ret = fn(now, data);
+			if (ret)
+				return ret;
+		}
+
+		next = NULL;
+		while (1) {
+			udev = netdev_next_upper_dev(now, &iter);
+			if (!udev)
+				break;
+
+			next = udev;
+			niter = &udev->adj_list.upper;
+			dev_stack[cur] = now;
+			iter_stack[cur++] = iter;
+			break;
+		}
+
+		if (!next) {
+			if (!cur)
+				return 0;
+			next = dev_stack[--cur];
+			niter = iter_stack[cur];
+		}
+
+		now = next;
+		iter = niter;
+	}
+
+	return 0;
+}
+
 int netdev_walk_all_upper_dev_rcu(struct net_device *dev,
 				  int (*fn)(struct net_device *dev,
 					    void *data),
 				  void *data)
 {
-	struct net_device *udev;
-	struct list_head *iter;
-	int ret;
+	struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+	struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+	int ret, cur = 0;
 
-	for (iter = &dev->adj_list.upper,
-	     udev = netdev_next_upper_dev_rcu(dev, &iter);
-	     udev;
-	     udev = netdev_next_upper_dev_rcu(dev, &iter)) {
-		/* first is the upper device itself */
-		ret = fn(udev, data);
-		if (ret)
-			return ret;
+	now = dev;
+	iter = &dev->adj_list.upper;
 
-		/* then look at all of its upper devices */
-		ret = netdev_walk_all_upper_dev_rcu(udev, fn, data);
-		if (ret)
-			return ret;
+	while (1) {
+		if (now != dev) {
+			ret = fn(now, data);
+			if (ret)
+				return ret;
+		}
+
+		next = NULL;
+		while (1) {
+			udev = netdev_next_upper_dev_rcu(now, &iter);
+			if (!udev)
+				break;
+
+			next = udev;
+			niter = &udev->adj_list.upper;
+			dev_stack[cur] = now;
+			iter_stack[cur++] = iter;
+			break;
+		}
+
+		if (!next) {
+			if (!cur)
+				return 0;
+			next = dev_stack[--cur];
+			niter = iter_stack[cur];
+		}
+
+		now = next;
+		iter = niter;
 	}
 
 	return 0;
@@ -6762,31 +6835,50 @@ int netdev_walk_all_lower_dev(struct net_device *dev,
 					void *data),
 			      void *data)
 {
-	struct net_device *ldev;
-	struct list_head *iter;
-	int ret;
+	struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+	struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+	int ret, cur = 0;
 
-	for (iter = &dev->adj_list.lower,
-	     ldev = netdev_next_lower_dev(dev, &iter);
-	     ldev;
-	     ldev = netdev_next_lower_dev(dev, &iter)) {
-		/* first is the lower device itself */
-		ret = fn(ldev, data);
-		if (ret)
-			return ret;
+	now = dev;
+	iter = &dev->adj_list.lower;
 
-		/* then look at all of its lower devices */
-		ret = netdev_walk_all_lower_dev(ldev, fn, data);
-		if (ret)
-			return ret;
+	while (1) {
+		if (now != dev) {
+			ret = fn(now, data);
+			if (ret)
+				return ret;
+		}
+
+		next = NULL;
+		while (1) {
+			ldev = netdev_next_lower_dev(now, &iter);
+			if (!ldev)
+				break;
+
+			next = ldev;
+			niter = &ldev->adj_list.lower;
+			dev_stack[cur] = now;
+			iter_stack[cur++] = iter;
+			break;
+		}
+
+		if (!next) {
+			if (!cur)
+				return 0;
+			next = dev_stack[--cur];
+			niter = iter_stack[cur];
+		}
+
+		now = next;
+		iter = niter;
 	}
 
 	return 0;
 }
 EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev);
 
-static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
-						    struct list_head **iter)
+struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
+					     struct list_head **iter)
 {
 	struct netdev_adjacent *lower;
 
@@ -6798,29 +6890,95 @@ static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
 
 	return lower->dev;
 }
+EXPORT_SYMBOL(netdev_next_lower_dev_rcu);
 
-int netdev_walk_all_lower_dev_rcu(struct net_device *dev,
-				  int (*fn)(struct net_device *dev,
-					    void *data),
-				  void *data)
+static u8 __netdev_upper_depth(struct net_device *dev)
+{
+	struct net_device *udev;
+	struct list_head *iter;
+	u8 max_depth = 0;
+
+	for (iter = &dev->adj_list.upper,
+	     udev = netdev_next_upper_dev(dev, &iter);
+	     udev;
+	     udev = netdev_next_upper_dev(dev, &iter)) {
+		if (max_depth < udev->upper_level)
+			max_depth = udev->upper_level;
+	}
+
+	return max_depth;
+}
+
+static u8 __netdev_lower_depth(struct net_device *dev)
 {
 	struct net_device *ldev;
 	struct list_head *iter;
-	int ret;
+	u8 max_depth = 0;
 
 	for (iter = &dev->adj_list.lower,
-	     ldev = netdev_next_lower_dev_rcu(dev, &iter);
+	     ldev = netdev_next_lower_dev(dev, &iter);
 	     ldev;
-	     ldev = netdev_next_lower_dev_rcu(dev, &iter)) {
-		/* first is the lower device itself */
-		ret = fn(ldev, data);
-		if (ret)
-			return ret;
+	     ldev = netdev_next_lower_dev(dev, &iter)) {
+		if (max_depth < ldev->lower_level)
+			max_depth = ldev->lower_level;
+	}
 
-		/* then look at all of its lower devices */
-		ret = netdev_walk_all_lower_dev_rcu(ldev, fn, data);
-		if (ret)
-			return ret;
+	return max_depth;
+}
+
+static int __netdev_update_upper_level(struct net_device *dev, void *data)
+{
+	dev->upper_level = __netdev_upper_depth(dev) + 1;
+	return 0;
+}
+
+static int __netdev_update_lower_level(struct net_device *dev, void *data)
+{
+	dev->lower_level = __netdev_lower_depth(dev) + 1;
+	return 0;
+}
+
+int netdev_walk_all_lower_dev_rcu(struct net_device *dev,
+				  int (*fn)(struct net_device *dev,
+					    void *data),
+				  void *data)
+{
+	struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+	struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+	int ret, cur = 0;
+
+	now = dev;
+	iter = &dev->adj_list.lower;
+
+	while (1) {
+		if (now != dev) {
+			ret = fn(now, data);
+			if (ret)
+				return ret;
+		}
+
+		next = NULL;
+		while (1) {
+			ldev = netdev_next_lower_dev_rcu(now, &iter);
+			if (!ldev)
+				break;
+
+			next = ldev;
+			niter = &ldev->adj_list.lower;
+			dev_stack[cur] = now;
+			iter_stack[cur++] = iter;
+			break;
+		}
+
+		if (!next) {
+			if (!cur)
+				return 0;
+			next = dev_stack[--cur];
+			niter = iter_stack[cur];
+		}
+
+		now = next;
+		iter = niter;
 	}
 
 	return 0;
@@ -7077,6 +7235,9 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 	if (netdev_has_upper_dev(upper_dev, dev))
 		return -EBUSY;
 
+	if ((dev->lower_level + upper_dev->upper_level) > MAX_NEST_DEV)
+		return -EMLINK;
+
 	if (!master) {
 		if (netdev_has_upper_dev(dev, upper_dev))
 			return -EEXIST;
@@ -7103,6 +7264,12 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 	if (ret)
 		goto rollback;
 
+	__netdev_update_upper_level(dev, NULL);
+	netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL);
+
+	__netdev_update_lower_level(upper_dev, NULL);
+	netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, NULL);
+
 	return 0;
 
 rollback:
@@ -7185,6 +7352,12 @@ void netdev_upper_dev_unlink(struct net_device *dev,
 
 	call_netdevice_notifiers_info(NETDEV_CHANGEUPPER,
 				      &changeupper_info.info);
+
+	__netdev_update_upper_level(dev, NULL);
+	netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL);
+
+	__netdev_update_lower_level(upper_dev, NULL);
+	netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, NULL);
 }
 EXPORT_SYMBOL(netdev_upper_dev_unlink);
 
@@ -7678,6 +7851,22 @@ int __dev_set_mtu(struct net_device *dev, int new_mtu)
 }
 EXPORT_SYMBOL(__dev_set_mtu);
 
+int dev_validate_mtu(struct net_device *dev, int new_mtu,
+		     struct netlink_ext_ack *extack)
+{
+	/* MTU must be positive, and in range */
+	if (new_mtu < 0 || new_mtu < dev->min_mtu) {
+		NL_SET_ERR_MSG(extack, "mtu less than device minimum");
+		return -EINVAL;
+	}
+
+	if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) {
+		NL_SET_ERR_MSG(extack, "mtu greater than device maximum");
+		return -EINVAL;
+	}
+	return 0;
+}
+
 /**
  *	dev_set_mtu_ext - Change maximum transfer unit
  *	@dev: device
@@ -7694,16 +7883,9 @@ int dev_set_mtu_ext(struct net_device *dev, int new_mtu,
 	if (new_mtu == dev->mtu)
 		return 0;
 
-	/* MTU must be positive, and in range */
-	if (new_mtu < 0 || new_mtu < dev->min_mtu) {
-		NL_SET_ERR_MSG(extack, "mtu less than device minimum");
-		return -EINVAL;
-	}
-
-	if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) {
-		NL_SET_ERR_MSG(extack, "mtu greater than device maximum");
-		return -EINVAL;
-	}
+	err = dev_validate_mtu(dev, new_mtu, extack);
+	if (err)
+		return err;
 
 	if (!netif_device_present(dev))
 		return -ENODEV;
@@ -8292,11 +8474,13 @@ static void netdev_sync_lower_features(struct net_device *upper,
 			netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n",
 				   &feature, lower->name);
 			lower->wanted_features &= ~feature;
-			netdev_update_features(lower);
+			__netdev_update_features(lower);
 
 			if (unlikely(lower->features & feature))
 				netdev_WARN(upper, "failed to disable %pNF on %s!\n",
 					    &feature, lower->name);
+			else
+				netdev_features_change(lower);
 		}
 	}
 }
@@ -8741,8 +8925,10 @@ int register_netdevice(struct net_device *dev)
 		goto err_uninit;
 
 	ret = netdev_register_kobject(dev);
-	if (ret)
+	if (ret) {
+		dev->reg_state = NETREG_UNREGISTERED;
 		goto err_uninit;
+	}
 	dev->reg_state = NETREG_REGISTERED;
 
 	__netdev_update_features(dev);
@@ -8776,6 +8962,13 @@ int register_netdevice(struct net_device *dev)
 		rcu_barrier();
 
 		dev->reg_state = NETREG_UNREGISTERED;
+		/* We should put the kobject that hold in
+		 * netdev_unregister_kobject(), otherwise
+		 * the net device cannot be freed when
+		 * driver calls free_netdev(), because the
+		 * kobject is being hold.
+		 */
+		kobject_put(&dev->dev.kobj);
 	}
 	/*
 	 *	Prevent userspace races by waiting until the network
@@ -9174,6 +9367,8 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 
 	dev->gso_max_size = GSO_MAX_SIZE;
 	dev->gso_max_segs = GSO_MAX_SEGS;
+	dev->upper_level = 1;
+	dev->lower_level = 1;
 
 	INIT_LIST_HEAD(&dev->napi_list);
 	INIT_LIST_HEAD(&dev->unreg_list);
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 132f4b757963..119d203b0723 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3068,34 +3068,41 @@ devlink_param_value_get_from_info(const struct devlink_param *param,
 				  struct genl_info *info,
 				  union devlink_param_value *value)
 {
+	struct nlattr *param_data;
 	int len;
 
-	if (param->type != DEVLINK_PARAM_TYPE_BOOL &&
-	    !info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA])
+	param_data = info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA];
+
+	if (param->type != DEVLINK_PARAM_TYPE_BOOL && !param_data)
 		return -EINVAL;
 
 	switch (param->type) {
 	case DEVLINK_PARAM_TYPE_U8:
-		value->vu8 = nla_get_u8(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]);
+		if (nla_len(param_data) != sizeof(u8))
+			return -EINVAL;
+		value->vu8 = nla_get_u8(param_data);
 		break;
 	case DEVLINK_PARAM_TYPE_U16:
-		value->vu16 = nla_get_u16(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]);
+		if (nla_len(param_data) != sizeof(u16))
+			return -EINVAL;
+		value->vu16 = nla_get_u16(param_data);
 		break;
 	case DEVLINK_PARAM_TYPE_U32:
-		value->vu32 = nla_get_u32(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]);
+		if (nla_len(param_data) != sizeof(u32))
+			return -EINVAL;
+		value->vu32 = nla_get_u32(param_data);
 		break;
 	case DEVLINK_PARAM_TYPE_STRING:
-		len = strnlen(nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]),
-			      nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]));
-		if (len == nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) ||
+		len = strnlen(nla_data(param_data), nla_len(param_data));
+		if (len == nla_len(param_data) ||
 		    len >= __DEVLINK_PARAM_MAX_STRING_VALUE)
 			return -EINVAL;
-		strcpy(value->vstr,
-		       nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]));
+		strcpy(value->vstr, nla_data(param_data));
 		break;
 	case DEVLINK_PARAM_TYPE_BOOL:
-		value->vbool = info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA] ?
-			       true : false;
+		if (param_data && nla_len(param_data))
+			return -EINVAL;
+		value->vbool = nla_get_flag(param_data);
 		break;
 	}
 	return 0;
@@ -3700,6 +3707,12 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
 		goto out_unlock;
 	}
 
+	/* return 0 if there is no further data to read */
+	if (start_offset >= region->size) {
+		err = 0;
+		goto out_unlock;
+	}
+
 	hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
 			  &devlink_nl_family, NLM_F_ACK | NLM_F_MULTI,
 			  DEVLINK_CMD_REGION_READ);
@@ -3731,6 +3744,11 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
 		end_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]);
 		end_offset += nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]);
 		dump = false;
+
+		if (start_offset == end_offset) {
+			err = 0;
+			goto nla_put_failure;
+		}
 	}
 
 	err = devlink_nl_region_read_snapshot_fill(skb, devlink,
@@ -4979,6 +4997,8 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 },
 	[DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING },
 	[DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32 },
+	[DEVLINK_ATTR_REGION_CHUNK_ADDR] = { .type = NLA_U64 },
+	[DEVLINK_ATTR_REGION_CHUNK_LEN] = { .type = NLA_U64 },
 	[DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING },
 	[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = { .type = NLA_U64 },
 	[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 },
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 4ea4347f5062..6a5cca21cab5 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -155,6 +155,7 @@ static void sched_send_work(struct timer_list *t)
 static void trace_drop_common(struct sk_buff *skb, void *location)
 {
 	struct net_dm_alert_msg *msg;
+	struct net_dm_drop_point *point;
 	struct nlmsghdr *nlh;
 	struct nlattr *nla;
 	int i;
@@ -173,11 +174,13 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
 	nlh = (struct nlmsghdr *)dskb->data;
 	nla = genlmsg_data(nlmsg_data(nlh));
 	msg = nla_data(nla);
+	point = msg->points;
 	for (i = 0; i < msg->entries; i++) {
-		if (!memcmp(&location, msg->points[i].pc, sizeof(void *))) {
-			msg->points[i].count++;
+		if (!memcmp(&location, &point->pc, sizeof(void *))) {
+			point->count++;
 			goto out;
 		}
+		point++;
 	}
 	if (msg->entries == dm_hit_limit)
 		goto out;
@@ -186,8 +189,8 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
 	 */
 	__nla_reserve_nohdr(dskb, sizeof(struct net_dm_drop_point));
 	nla->nla_len += NLA_ALIGN(sizeof(struct net_dm_drop_point));
-	memcpy(msg->points[msg->entries].pc, &location, sizeof(void *));
-	msg->points[msg->entries].count = 1;
+	memcpy(point->pc, &location, sizeof(void *));
+	point->count = 1;
 	msg->entries++;
 
 	if (!timer_pending(&data->send_timer)) {
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index dd220ce7ca7a..bb11fc87bbae 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -967,7 +967,7 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
 
 	frh = nlmsg_data(nlh);
 	frh->family = ops->family;
-	frh->table = rule->table;
+	frh->table = rule->table < 256 ? rule->table : RT_TABLE_COMPAT;
 	if (nla_put_u32(skb, FRA_TABLE, rule->table))
 		goto nla_put_failure;
 	if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen))
diff --git a/net/core/filter.c b/net/core/filter.c
index 82e0af0f221b..633b048792b2 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1765,25 +1765,27 @@ BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb,
 	   u32, offset, void *, to, u32, len, u32, start_header)
 {
 	u8 *end = skb_tail_pointer(skb);
-	u8 *net = skb_network_header(skb);
-	u8 *mac = skb_mac_header(skb);
-	u8 *ptr;
+	u8 *start, *ptr;
 
-	if (unlikely(offset > 0xffff || len > (end - mac)))
+	if (unlikely(offset > 0xffff))
 		goto err_clear;
 
 	switch (start_header) {
 	case BPF_HDR_START_MAC:
-		ptr = mac + offset;
+		if (unlikely(!skb_mac_header_was_set(skb)))
+			goto err_clear;
+		start = skb_mac_header(skb);
 		break;
 	case BPF_HDR_START_NET:
-		ptr = net + offset;
+		start = skb_network_header(skb);
 		break;
 	default:
 		goto err_clear;
 	}
 
-	if (likely(ptr >= mac && ptr + len <= end)) {
+	ptr = start + offset;
+
+	if (likely(ptr + len <= end)) {
 		memcpy(to, ptr, len);
 		return 0;
 	}
@@ -2054,6 +2056,7 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb)
 	}
 
 	skb->dev = dev;
+	skb->tstamp = 0;
 
 	dev_xmit_recursion_inc();
 	ret = dev_queue_xmit(skb);
@@ -2229,10 +2232,10 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start,
 	/* First find the starting scatterlist element */
 	i = msg->sg.start;
 	do {
+		offset += len;
 		len = sk_msg_elem(msg, i)->length;
 		if (start < offset + len)
 			break;
-		offset += len;
 		sk_msg_iter_var_next(i);
 	} while (i != msg->sg.end);
 
@@ -2344,7 +2347,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start,
 	   u32, len, u64, flags)
 {
 	struct scatterlist sge, nsge, nnsge, rsge = {0}, *psge;
-	u32 new, i = 0, l, space, copy = 0, offset = 0;
+	u32 new, i = 0, l = 0, space, copy = 0, offset = 0;
 	u8 *raw, *to, *from;
 	struct page *page;
 
@@ -2354,11 +2357,11 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start,
 	/* First find the starting scatterlist element */
 	i = msg->sg.start;
 	do {
+		offset += l;
 		l = sk_msg_elem(msg, i)->length;
 
 		if (start < offset + l)
 			break;
-		offset += l;
 		sk_msg_iter_var_next(i);
 	} while (i != msg->sg.end);
 
@@ -2413,6 +2416,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start,
 
 		sk_msg_iter_var_next(i);
 		sg_unmark_end(psge);
+		sg_unmark_end(&rsge);
 		sk_msg_iter_next(msg, end);
 	}
 
@@ -2504,7 +2508,7 @@ static void sk_msg_shift_right(struct sk_msg *msg, int i)
 BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start,
 	   u32, len, u64, flags)
 {
-	u32 i = 0, l, space, offset = 0;
+	u32 i = 0, l = 0, space, offset = 0;
 	u64 last = start + len;
 	int pop;
 
@@ -2514,11 +2518,11 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start,
 	/* First find the starting scatterlist element */
 	i = msg->sg.start;
 	do {
+		offset += l;
 		l = sk_msg_elem(msg, i)->length;
 
 		if (start < offset + l)
 			break;
-		offset += l;
 		sk_msg_iter_var_next(i);
 	} while (i != msg->sg.end);
 
@@ -2587,8 +2591,8 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start,
 			}
 			pop = 0;
 		} else if (pop >= sge->length - a) {
-			sge->length = a;
 			pop -= (sge->length - a);
+			sge->length = a;
 		}
 	}
 
@@ -2912,7 +2916,7 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb)
 
 static int bpf_skb_proto_xlat(struct sk_buff *skb, __be16 to_proto)
 {
-	__be16 from_proto = skb->protocol;
+	__be16 from_proto = skb_protocol(skb, true);
 
 	if (from_proto == htons(ETH_P_IP) &&
 	      to_proto == htons(ETH_P_IPV6))
@@ -2985,7 +2989,7 @@ static const struct bpf_func_proto bpf_skb_change_type_proto = {
 
 static u32 bpf_skb_net_base_len(const struct sk_buff *skb)
 {
-	switch (skb->protocol) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
 		return sizeof(struct iphdr);
 	case htons(ETH_P_IPV6):
@@ -3153,7 +3157,7 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
 	u32 len_cur, len_diff_abs = abs(len_diff);
 	u32 len_min = bpf_skb_net_base_len(skb);
 	u32 len_max = __bpf_skb_max_len(skb);
-	__be16 proto = skb->protocol;
+	__be16 proto = skb_protocol(skb, true);
 	bool shrink = len_diff < 0;
 	u32 off;
 	int ret;
@@ -3541,7 +3545,7 @@ static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
 		return err;
 	}
 	default:
-		break;
+		return -EBADRQC;
 	}
 	return 0;
 }
@@ -4244,12 +4248,14 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 		case SO_RCVBUF:
 			val = min_t(u32, val, sysctl_rmem_max);
 			sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
-			sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF);
+			WRITE_ONCE(sk->sk_rcvbuf,
+				   max_t(int, val * 2, SOCK_MIN_RCVBUF));
 			break;
 		case SO_SNDBUF:
 			val = min_t(u32, val, sysctl_wmem_max);
 			sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
-			sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF);
+			WRITE_ONCE(sk->sk_sndbuf,
+				   max_t(int, val * 2, SOCK_MIN_SNDBUF));
 			break;
 		case SO_MAX_PACING_RATE: /* 32bit version */
 			if (val != ~0U)
@@ -4916,7 +4922,7 @@ static int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len
 
 	switch (type) {
 	case BPF_LWT_ENCAP_SEG6_INLINE:
-		if (skb->protocol != htons(ETH_P_IPV6))
+		if (skb_protocol(skb, true) != htons(ETH_P_IPV6))
 			return -EBADMSG;
 
 		err = seg6_do_srh_inline(skb, srh);
@@ -5342,8 +5348,7 @@ __bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 	if (sk) {
 		sk = sk_to_full_sk(sk);
 		if (!sk_fullsock(sk)) {
-			if (!sock_flag(sk, SOCK_RCU_FREE))
-				sock_gen_put(sk);
+			sock_gen_put(sk);
 			return NULL;
 		}
 	}
@@ -5380,8 +5385,7 @@ bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 	if (sk) {
 		sk = sk_to_full_sk(sk);
 		if (!sk_fullsock(sk)) {
-			if (!sock_flag(sk, SOCK_RCU_FREE))
-				sock_gen_put(sk);
+			sock_gen_put(sk);
 			return NULL;
 		}
 	}
@@ -5448,7 +5452,8 @@ static const struct bpf_func_proto bpf_sk_lookup_udp_proto = {
 
 BPF_CALL_1(bpf_sk_release, struct sock *, sk)
 {
-	if (!sock_flag(sk, SOCK_RCU_FREE))
+	/* Only full sockets have sk->sk_flags. */
+	if (!sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE))
 		sock_gen_put(sk);
 	return 0;
 }
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 5e0f2ea25909..11c23403b3f3 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -125,12 +125,10 @@ int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr,
 	return 0;
 }
 
-int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
+static int flow_dissector_bpf_prog_detach(struct net *net)
 {
 	struct bpf_prog *attached;
-	struct net *net;
 
-	net = current->nsproxy->net_ns;
 	mutex_lock(&flow_dissector_mutex);
 	attached = rcu_dereference_protected(net->flow_dissector_prog,
 					     lockdep_is_held(&flow_dissector_mutex));
@@ -165,6 +163,24 @@ static __be16 skb_flow_get_be16(const struct sk_buff *skb, int poff,
 	return 0;
 }
 
+int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
+{
+	return flow_dissector_bpf_prog_detach(current->nsproxy->net_ns);
+}
+
+static void __net_exit flow_dissector_pernet_pre_exit(struct net *net)
+{
+	/* We're not racing with attach/detach because there are no
+	 * references to netns left when pre_exit gets called.
+	 */
+	if (rcu_access_pointer(net->flow_dissector_prog))
+		flow_dissector_bpf_prog_detach(net);
+}
+
+static struct pernet_operations flow_dissector_pernet_ops __net_initdata = {
+	.pre_exit = flow_dissector_pernet_pre_exit,
+};
+
 /**
  * __skb_flow_get_ports - extract the upper layer ports and return them
  * @skb: sk_buff to extract the ports from
@@ -1664,7 +1680,7 @@ static int __init init_default_flow_dissectors(void)
 	skb_flow_dissector_init(&flow_keys_basic_dissector,
 				flow_keys_basic_dissector_keys,
 				ARRAY_SIZE(flow_keys_basic_dissector_keys));
-	return 0;
-}
 
+	return register_pernet_subsys(&flow_dissector_pernet_ops);
+}
 core_initcall(init_default_flow_dissectors);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 134c51ce1cb7..6cdb1159f17b 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1192,7 +1192,7 @@ static void neigh_update_hhs(struct neighbour *neigh)
 
 	if (update) {
 		hh = &neigh->hh;
-		if (hh->hh_len) {
+		if (READ_ONCE(hh->hh_len)) {
 			write_seqlock_bh(&hh->hh_lock);
 			update(hh, neigh->dev, neigh->ha);
 			write_sequnlock_bh(&hh->hh_lock);
@@ -1471,7 +1471,7 @@ int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb)
 		struct net_device *dev = neigh->dev;
 		unsigned int seq;
 
-		if (dev->header_ops->cache && !neigh->hh.hh_len)
+		if (dev->header_ops->cache && !READ_ONCE(neigh->hh.hh_len))
 			neigh_hh_init(neigh);
 
 		do {
@@ -1952,6 +1952,9 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 				   NEIGH_UPDATE_F_OVERRIDE_ISROUTER);
 	}
 
+	if (protocol)
+		neigh->protocol = protocol;
+
 	if (ndm->ndm_flags & NTF_EXT_LEARNED)
 		flags |= NEIGH_UPDATE_F_EXT_LEARNED;
 
@@ -1965,9 +1968,6 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 		err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags,
 				     NETLINK_CB(skb).portid, extack);
 
-	if (protocol)
-		neigh->protocol = protocol;
-
 	neigh_release(neigh);
 
 out:
@@ -2047,8 +2047,8 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl,
 		goto nla_put_failure;
 	{
 		unsigned long now = jiffies;
-		unsigned int flush_delta = now - tbl->last_flush;
-		unsigned int rand_delta = now - tbl->last_rand;
+		long flush_delta = now - tbl->last_flush;
+		long rand_delta = now - tbl->last_rand;
 		struct neigh_hash_table *nht;
 		struct ndt_config ndc = {
 			.ndtc_key_len		= tbl->key_len,
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 865ba6ca16eb..229ecf256f4e 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1031,7 +1031,7 @@ static ssize_t tx_timeout_show(struct netdev_queue *queue, char *buf)
 	trans_timeout = queue->trans_timeout;
 	spin_unlock_irq(&queue->_xmit_lock);
 
-	return sprintf(buf, "%lu", trans_timeout);
+	return sprintf(buf, fmt_ulong, trans_timeout);
 }
 
 static unsigned int get_netdev_queue_index(struct netdev_queue *queue)
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 95fd26c01c40..e31ab1f9c91d 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -145,6 +145,17 @@ static void ops_free(const struct pernet_operations *ops, struct net *net)
 	}
 }
 
+static void ops_pre_exit_list(const struct pernet_operations *ops,
+			      struct list_head *net_exit_list)
+{
+	struct net *net;
+
+	if (ops->pre_exit) {
+		list_for_each_entry(net, net_exit_list, exit_list)
+			ops->pre_exit(net);
+	}
+}
+
 static void ops_exit_list(const struct pernet_operations *ops,
 			  struct list_head *net_exit_list)
 {
@@ -330,6 +341,12 @@ out_undo:
 	list_add(&net->exit_list, &net_exit_list);
 	saved_ops = ops;
 	list_for_each_entry_continue_reverse(ops, &pernet_list, list)
+		ops_pre_exit_list(ops, &net_exit_list);
+
+	synchronize_rcu();
+
+	ops = saved_ops;
+	list_for_each_entry_continue_reverse(ops, &pernet_list, list)
 		ops_exit_list(ops, &net_exit_list);
 
 	ops = saved_ops;
@@ -542,10 +559,15 @@ static void cleanup_net(struct work_struct *work)
 		list_add_tail(&net->exit_list, &net_exit_list);
 	}
 
+	/* Run all of the network namespace pre_exit methods */
+	list_for_each_entry_reverse(ops, &pernet_list, list)
+		ops_pre_exit_list(ops, &net_exit_list);
+
 	/*
 	 * Another CPU might be rcu-iterating the list, wait for it.
 	 * This needs to be before calling the exit() notifiers, so
 	 * the rcu_barrier() below isn't sufficient alone.
+	 * Also the pre_exit() and exit() methods need this barrier.
 	 */
 	synchronize_rcu();
 
@@ -1102,6 +1124,8 @@ static int __register_pernet_operations(struct list_head *list,
 out_undo:
 	/* If I have an error cleanup all namespaces I initialized */
 	list_del(&ops->list);
+	ops_pre_exit_list(ops, &net_exit_list);
+	synchronize_rcu();
 	ops_exit_list(ops, &net_exit_list);
 	ops_free_list(ops, &net_exit_list);
 	return error;
@@ -1116,6 +1140,8 @@ static void __unregister_pernet_operations(struct pernet_operations *ops)
 	/* See comment in __register_pernet_operations() */
 	for_each_net(net)
 		list_add_tail(&net->exit_list, &net_exit_list);
+	ops_pre_exit_list(ops, &net_exit_list);
+	synchronize_rcu();
 	ops_exit_list(ops, &net_exit_list);
 	ops_free_list(ops, &net_exit_list);
 }
@@ -1140,6 +1166,8 @@ static void __unregister_pernet_operations(struct pernet_operations *ops)
 	} else {
 		LIST_HEAD(net_exit_list);
 		list_add(&init_net.exit_list, &net_exit_list);
+		ops_pre_exit_list(ops, &net_exit_list);
+		synchronize_rcu();
 		ops_exit_list(ops, &net_exit_list);
 		ops_free_list(ops, &net_exit_list);
 	}
diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
index 0642f91c4038..41b24cd31562 100644
--- a/net/core/netclassid_cgroup.c
+++ b/net/core/netclassid_cgroup.c
@@ -53,30 +53,60 @@ static void cgrp_css_free(struct cgroup_subsys_state *css)
 	kfree(css_cls_state(css));
 }
 
+/*
+ * To avoid freezing of sockets creation for tasks with big number of threads
+ * and opened sockets lets release file_lock every 1000 iterated descriptors.
+ * New sockets will already have been created with new classid.
+ */
+
+struct update_classid_context {
+	u32 classid;
+	unsigned int batch;
+};
+
+#define UPDATE_CLASSID_BATCH 1000
+
 static int update_classid_sock(const void *v, struct file *file, unsigned n)
 {
 	int err;
+	struct update_classid_context *ctx = (void *)v;
 	struct socket *sock = sock_from_file(file, &err);
 
 	if (sock) {
 		spin_lock(&cgroup_sk_update_lock);
-		sock_cgroup_set_classid(&sock->sk->sk_cgrp_data,
-					(unsigned long)v);
+		sock_cgroup_set_classid(&sock->sk->sk_cgrp_data, ctx->classid);
 		spin_unlock(&cgroup_sk_update_lock);
 	}
+	if (--ctx->batch == 0) {
+		ctx->batch = UPDATE_CLASSID_BATCH;
+		return n + 1;
+	}
 	return 0;
 }
 
+static void update_classid_task(struct task_struct *p, u32 classid)
+{
+	struct update_classid_context ctx = {
+		.classid = classid,
+		.batch = UPDATE_CLASSID_BATCH
+	};
+	unsigned int fd = 0;
+
+	do {
+		task_lock(p);
+		fd = iterate_fd(p->files, fd, update_classid_sock, &ctx);
+		task_unlock(p);
+		cond_resched();
+	} while (fd);
+}
+
 static void cgrp_attach(struct cgroup_taskset *tset)
 {
 	struct cgroup_subsys_state *css;
 	struct task_struct *p;
 
 	cgroup_taskset_for_each(p, css, tset) {
-		task_lock(p);
-		iterate_fd(p->files, 0, update_classid_sock,
-			   (void *)(unsigned long)css_cls_state(css)->classid);
-		task_unlock(p);
+		update_classid_task(p, css_cls_state(css)->classid);
 	}
 }
 
@@ -97,13 +127,8 @@ static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft,
 	cs->classid = (u32)value;
 
 	css_task_iter_start(css, 0, &it);
-	while ((p = css_task_iter_next(&it))) {
-		task_lock(p);
-		iterate_fd(p->files, 0, update_classid_sock,
-			   (void *)(unsigned long)cs->classid);
-		task_unlock(p);
-		cond_resched();
-	}
+	while ((p = css_task_iter_next(&it)))
+		update_classid_task(p, cs->classid);
 	css_task_iter_end(&it);
 
 	return 0;
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 256b7954b720..8618242c677a 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -236,6 +236,8 @@ static void net_prio_attach(struct cgroup_taskset *tset)
 	struct task_struct *p;
 	struct cgroup_subsys_state *css;
 
+	cgroup_sk_alloc_disable();
+
 	cgroup_taskset_for_each(p, css, tset) {
 		void *v = (void *)(unsigned long)css->cgroup->id;
 
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index f975c5e2a369..52d27ac4023b 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3362,7 +3362,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev)
 			/* skb was 'freed' by stack, so clean few
 			 * bits and reuse it
 			 */
-			skb_reset_tc(skb);
+			skb_reset_redirect(skb);
 		} while (--burst > 0);
 		goto out; /* Skips xmit_mode M_START_XMIT */
 	} else if (pkt_dev->xmit_mode == M_QUEUE_XMIT) {
diff --git a/net/core/request_sock.c b/net/core/request_sock.c
index c9bb00008528..f35c2e998406 100644
--- a/net/core/request_sock.c
+++ b/net/core/request_sock.c
@@ -96,7 +96,7 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
 
 	fastopenq = &inet_csk(lsk)->icsk_accept_queue.fastopenq;
 
-	tcp_sk(sk)->fastopen_rsk = NULL;
+	RCU_INIT_POINTER(tcp_sk(sk)->fastopen_rsk, NULL);
 	spin_lock_bh(&fastopenq->lock);
 	fastopenq->qlen--;
 	tcp_rsk(req)->tfo_listener = false;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 48e8a826b32b..9a504779c4f5 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2949,8 +2949,17 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
 	dev->rtnl_link_ops = ops;
 	dev->rtnl_link_state = RTNL_LINK_INITIALIZING;
 
-	if (tb[IFLA_MTU])
-		dev->mtu = nla_get_u32(tb[IFLA_MTU]);
+	if (tb[IFLA_MTU]) {
+		u32 mtu = nla_get_u32(tb[IFLA_MTU]);
+		int err;
+
+		err = dev_validate_mtu(dev, mtu, extack);
+		if (err) {
+			free_netdev(dev);
+			return ERR_PTR(err);
+		}
+		dev->mtu = mtu;
+	}
 	if (tb[IFLA_ADDRESS]) {
 		memcpy(dev->dev_addr, nla_data(tb[IFLA_ADDRESS]),
 				nla_len(tb[IFLA_ADDRESS]));
@@ -3212,7 +3221,8 @@ replay:
 		 */
 		if (err < 0) {
 			/* If device is not registered at all, free it now */
-			if (dev->reg_state == NETREG_UNINITIALIZED)
+			if (dev->reg_state == NETREG_UNINITIALIZED ||
+			    dev->reg_state == NETREG_UNREGISTERED)
 				free_netdev(dev);
 			goto out;
 		}
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 74efd63f15e2..57f879316ab4 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4270,7 +4270,7 @@ static void skb_set_err_queue(struct sk_buff *skb)
 int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
 {
 	if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
-	    (unsigned int)sk->sk_rcvbuf)
+	    (unsigned int)READ_ONCE(sk->sk_rcvbuf))
 		return -ENOMEM;
 
 	skb_orphan(skb);
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index b79001a3f9a7..e16f985631ae 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -7,6 +7,7 @@
 
 #include <net/sock.h>
 #include <net/tcp.h>
+#include <net/tls.h>
 
 static bool sk_msg_try_coalesce_ok(struct sk_msg *msg, int elem_first_coalesce)
 {
@@ -687,13 +688,74 @@ static struct sk_psock *sk_psock_from_strp(struct strparser *strp)
 	return container_of(parser, struct sk_psock, parser);
 }
 
-static void sk_psock_verdict_apply(struct sk_psock *psock,
-				   struct sk_buff *skb, int verdict)
+static void sk_psock_skb_redirect(struct sk_buff *skb)
 {
 	struct sk_psock *psock_other;
 	struct sock *sk_other;
 	bool ingress;
 
+	sk_other = tcp_skb_bpf_redirect_fetch(skb);
+	if (unlikely(!sk_other)) {
+		kfree_skb(skb);
+		return;
+	}
+	psock_other = sk_psock(sk_other);
+	if (!psock_other || sock_flag(sk_other, SOCK_DEAD) ||
+	    !sk_psock_test_state(psock_other, SK_PSOCK_TX_ENABLED)) {
+		kfree_skb(skb);
+		return;
+	}
+
+	ingress = tcp_skb_bpf_ingress(skb);
+	if ((!ingress && sock_writeable(sk_other)) ||
+	    (ingress &&
+	     atomic_read(&sk_other->sk_rmem_alloc) <=
+	     sk_other->sk_rcvbuf)) {
+		if (!ingress)
+			skb_set_owner_w(skb, sk_other);
+		skb_queue_tail(&psock_other->ingress_skb, skb);
+		schedule_work(&psock_other->work);
+	} else {
+		kfree_skb(skb);
+	}
+}
+
+static void sk_psock_tls_verdict_apply(struct sk_buff *skb, int verdict)
+{
+	switch (verdict) {
+	case __SK_REDIRECT:
+		sk_psock_skb_redirect(skb);
+		break;
+	case __SK_PASS:
+	case __SK_DROP:
+	default:
+		break;
+	}
+}
+
+int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb)
+{
+	struct bpf_prog *prog;
+	int ret = __SK_PASS;
+
+	rcu_read_lock();
+	prog = READ_ONCE(psock->progs.skb_verdict);
+	if (likely(prog)) {
+		tcp_skb_bpf_redirect_clear(skb);
+		ret = sk_psock_bpf_run(psock, prog, skb);
+		ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
+	}
+	sk_psock_tls_verdict_apply(skb, ret);
+	rcu_read_unlock();
+	return ret;
+}
+EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read);
+
+static void sk_psock_verdict_apply(struct sk_psock *psock,
+				   struct sk_buff *skb, int verdict)
+{
+	struct sock *sk_other;
+
 	switch (verdict) {
 	case __SK_PASS:
 		sk_other = psock->sk;
@@ -712,25 +774,8 @@ static void sk_psock_verdict_apply(struct sk_psock *psock,
 		}
 		goto out_free;
 	case __SK_REDIRECT:
-		sk_other = tcp_skb_bpf_redirect_fetch(skb);
-		if (unlikely(!sk_other))
-			goto out_free;
-		psock_other = sk_psock(sk_other);
-		if (!psock_other || sock_flag(sk_other, SOCK_DEAD) ||
-		    !sk_psock_test_state(psock_other, SK_PSOCK_TX_ENABLED))
-			goto out_free;
-		ingress = tcp_skb_bpf_ingress(skb);
-		if ((!ingress && sock_writeable(sk_other)) ||
-		    (ingress &&
-		     atomic_read(&sk_other->sk_rmem_alloc) <=
-		     sk_other->sk_rcvbuf)) {
-			if (!ingress)
-				skb_set_owner_w(skb, sk_other);
-			skb_queue_tail(&psock_other->ingress_skb, skb);
-			schedule_work(&psock_other->work);
-			break;
-		}
-		/* fall-through */
+		sk_psock_skb_redirect(skb);
+		break;
 	case __SK_DROP:
 		/* fall-through */
 	default:
@@ -741,11 +786,18 @@ out_free:
 
 static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
 {
-	struct sk_psock *psock = sk_psock_from_strp(strp);
+	struct sk_psock *psock;
 	struct bpf_prog *prog;
 	int ret = __SK_DROP;
+	struct sock *sk;
 
 	rcu_read_lock();
+	sk = strp->sk;
+	psock = sk_psock(sk);
+	if (unlikely(!psock)) {
+		kfree_skb(skb);
+		goto out;
+	}
 	prog = READ_ONCE(psock->progs.skb_verdict);
 	if (likely(prog)) {
 		skb_orphan(skb);
@@ -753,8 +805,9 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
 		ret = sk_psock_bpf_run(psock, prog, skb);
 		ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
 	}
-	rcu_read_unlock();
 	sk_psock_verdict_apply(psock, skb, ret);
+out:
+	rcu_read_unlock();
 }
 
 static int sk_psock_strp_read_done(struct strparser *strp, int err)
@@ -784,9 +837,13 @@ static void sk_psock_strp_data_ready(struct sock *sk)
 	rcu_read_lock();
 	psock = sk_psock(sk);
 	if (likely(psock)) {
-		write_lock_bh(&sk->sk_callback_lock);
-		strp_data_ready(&psock->parser.strp);
-		write_unlock_bh(&sk->sk_callback_lock);
+		if (tls_sw_has_ctx_rx(sk)) {
+			psock->parser.saved_data_ready(sk);
+		} else {
+			write_lock_bh(&sk->sk_callback_lock);
+			strp_data_ready(&psock->parser.strp);
+			write_unlock_bh(&sk->sk_callback_lock);
+		}
 	}
 	rcu_read_unlock();
 }
@@ -794,15 +851,18 @@ static void sk_psock_strp_data_ready(struct sock *sk)
 static void sk_psock_write_space(struct sock *sk)
 {
 	struct sk_psock *psock;
-	void (*write_space)(struct sock *sk);
+	void (*write_space)(struct sock *sk) = NULL;
 
 	rcu_read_lock();
 	psock = sk_psock(sk);
-	if (likely(psock && sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)))
-		schedule_work(&psock->work);
-	write_space = psock->saved_write_space;
+	if (likely(psock)) {
+		if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
+			schedule_work(&psock->work);
+		write_space = psock->saved_write_space;
+	}
 	rcu_read_unlock();
-	write_space(sk);
+	if (write_space)
+		write_space(sk);
 }
 
 int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock)
diff --git a/net/core/sock.c b/net/core/sock.c
index 8cc3cc8f2761..fb83335a5abb 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -709,7 +709,7 @@ bool sk_mc_loop(struct sock *sk)
 		return inet6_sk(sk)->mc_loop;
 #endif
 	}
-	WARN_ON(1);
+	WARN_ON_ONCE(1);
 	return true;
 }
 EXPORT_SYMBOL(sk_mc_loop);
@@ -785,7 +785,8 @@ set_sndbuf:
 		 */
 		val = min_t(int, val, INT_MAX / 2);
 		sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
-		sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF);
+		WRITE_ONCE(sk->sk_sndbuf,
+			   max_t(int, val * 2, SOCK_MIN_SNDBUF));
 		/* Wake up sending tasks if we upped the value. */
 		sk->sk_write_space(sk);
 		break;
@@ -831,7 +832,8 @@ set_rcvbuf:
 		 * returning the value we actually used in getsockopt
 		 * is the most desirable behavior.
 		 */
-		sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF);
+		WRITE_ONCE(sk->sk_rcvbuf,
+			   max_t(int, val * 2, SOCK_MIN_RCVBUF));
 		break;
 
 	case SO_RCVBUFFORCE:
@@ -1673,6 +1675,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
 		cgroup_sk_alloc(&sk->sk_cgrp_data);
 		sock_update_classid(&sk->sk_cgrp_data);
 		sock_update_netprioidx(&sk->sk_cgrp_data);
+		sk_tx_queue_clear(sk);
 	}
 
 	return sk;
@@ -1826,8 +1829,11 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		atomic_set(&newsk->sk_zckey, 0);
 
 		sock_reset_flag(newsk, SOCK_DONE);
-		mem_cgroup_sk_alloc(newsk);
-		cgroup_sk_alloc(&newsk->sk_cgrp_data);
+
+		/* sk->sk_memcg will be populated at accept() time */
+		newsk->sk_memcg = NULL;
+
+		cgroup_sk_clone(&newsk->sk_cgrp_data);
 
 		rcu_read_lock();
 		filter = rcu_dereference(sk->sk_filter);
@@ -1883,6 +1889,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		 */
 		sk_refcnt_debug_inc(newsk);
 		sk_set_socket(newsk, NULL);
+		sk_tx_queue_clear(newsk);
 		RCU_INIT_POINTER(newsk->sk_wq, NULL);
 
 		if (newsk->sk_prot->sockets_allocated)
@@ -2081,8 +2088,10 @@ EXPORT_SYMBOL(sock_i_ino);
 struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
 			     gfp_t priority)
 {
-	if (force || refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) {
+	if (force ||
+	    refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf)) {
 		struct sk_buff *skb = alloc_skb(size, priority);
+
 		if (skb) {
 			skb_set_owner_w(skb, sk);
 			return skb;
@@ -2183,7 +2192,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo)
 			break;
 		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
-		if (refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf)
+		if (refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf))
 			break;
 		if (sk->sk_shutdown & SEND_SHUTDOWN)
 			break;
@@ -2218,7 +2227,7 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
 		if (sk->sk_shutdown & SEND_SHUTDOWN)
 			goto failure;
 
-		if (sk_wmem_alloc_get(sk) < sk->sk_sndbuf)
+		if (sk_wmem_alloc_get(sk) < READ_ONCE(sk->sk_sndbuf))
 			break;
 
 		sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
@@ -2720,6 +2729,27 @@ int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *
 }
 EXPORT_SYMBOL(sock_no_mmap);
 
+/*
+ * When a file is received (via SCM_RIGHTS, etc), we must bump the
+ * various sock-based usage counts.
+ */
+void __receive_sock(struct file *file)
+{
+	struct socket *sock;
+	int error;
+
+	/*
+	 * The resulting value of "error" is ignored here since we only
+	 * need to take action when the file is a socket and testing
+	 * "sock" for NULL is sufficient.
+	 */
+	sock = sock_from_file(file, &error);
+	if (sock) {
+		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
+		sock_update_classid(&sock->sk->sk_cgrp_data);
+	}
+}
+
 ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags)
 {
 	ssize_t res;
@@ -2799,7 +2829,7 @@ static void sock_def_write_space(struct sock *sk)
 	/* Do not wake up a writer until he can make "significant"
 	 * progress.  --DaveM
 	 */
-	if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) {
+	if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= READ_ONCE(sk->sk_sndbuf)) {
 		wq = rcu_dereference(sk->sk_wq);
 		if (skwq_has_sleeper(wq))
 			wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT |
@@ -2907,7 +2937,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 
 	sk->sk_max_pacing_rate = ~0UL;
 	sk->sk_pacing_rate = ~0UL;
-	sk->sk_pacing_shift = 10;
+	WRITE_ONCE(sk->sk_pacing_shift, 10);
 	sk->sk_incoming_cpu = -1;
 
 	sk_rx_queue_clear(sk);
@@ -3197,13 +3227,13 @@ void sk_get_meminfo(const struct sock *sk, u32 *mem)
 	memset(mem, 0, sizeof(*mem) * SK_MEMINFO_VARS);
 
 	mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk);
-	mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf;
+	mem[SK_MEMINFO_RCVBUF] = READ_ONCE(sk->sk_rcvbuf);
 	mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk);
-	mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf;
+	mem[SK_MEMINFO_SNDBUF] = READ_ONCE(sk->sk_sndbuf);
 	mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
-	mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued;
+	mem[SK_MEMINFO_WMEM_QUEUED] = READ_ONCE(sk->sk_wmem_queued);
 	mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
-	mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len;
+	mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len);
 	mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops);
 }
 
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 3b14de0e36d2..285976f79cba 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -238,20 +238,26 @@ static void sock_map_free(struct bpf_map *map)
 	struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
 	int i;
 
+	/* After the sync no updates or deletes will be in-flight so it
+	 * is safe to walk map and remove entries without risking a race
+	 * in EEXIST update case.
+	 */
 	synchronize_rcu();
-	rcu_read_lock();
-	raw_spin_lock_bh(&stab->lock);
 	for (i = 0; i < stab->map.max_entries; i++) {
 		struct sock **psk = &stab->sks[i];
 		struct sock *sk;
 
 		sk = xchg(psk, NULL);
-		if (sk)
+		if (sk) {
+			lock_sock(sk);
+			rcu_read_lock();
 			sock_map_unref(sk, psk);
+			release_sock(sk);
+			rcu_read_unlock();
+		}
 	}
-	raw_spin_unlock_bh(&stab->lock);
-	rcu_read_unlock();
 
+	/* wait for psock readers accessing its map link */
 	synchronize_rcu();
 
 	bpf_map_area_free(stab->sks);
@@ -418,14 +424,16 @@ static int sock_map_update_elem(struct bpf_map *map, void *key,
 		ret = -EINVAL;
 		goto out;
 	}
-	if (!sock_map_sk_is_suitable(sk) ||
-	    sk->sk_state != TCP_ESTABLISHED) {
+	if (!sock_map_sk_is_suitable(sk)) {
 		ret = -EOPNOTSUPP;
 		goto out;
 	}
 
 	sock_map_sk_acquire(sk);
-	ret = sock_map_update_common(map, idx, sk, flags);
+	if (sk->sk_state != TCP_ESTABLISHED)
+		ret = -EOPNOTSUPP;
+	else
+		ret = sock_map_update_common(map, idx, sk, flags);
 	sock_map_sk_release(sk);
 out:
 	fput(sock->file);
@@ -741,14 +749,16 @@ static int sock_hash_update_elem(struct bpf_map *map, void *key,
 		ret = -EINVAL;
 		goto out;
 	}
-	if (!sock_map_sk_is_suitable(sk) ||
-	    sk->sk_state != TCP_ESTABLISHED) {
+	if (!sock_map_sk_is_suitable(sk)) {
 		ret = -EOPNOTSUPP;
 		goto out;
 	}
 
 	sock_map_sk_acquire(sk);
-	ret = sock_hash_update_common(map, key, sk, flags);
+	if (sk->sk_state != TCP_ESTABLISHED)
+		ret = -EOPNOTSUPP;
+	else
+		ret = sock_hash_update_common(map, key, sk, flags);
 	sock_map_sk_release(sk);
 out:
 	fput(sock->file);
@@ -856,22 +866,49 @@ static void sock_hash_free(struct bpf_map *map)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
 	struct bpf_htab_bucket *bucket;
+	struct hlist_head unlink_list;
 	struct bpf_htab_elem *elem;
 	struct hlist_node *node;
 	int i;
 
+	/* After the sync no updates or deletes will be in-flight so it
+	 * is safe to walk map and remove entries without risking a race
+	 * in EEXIST update case.
+	 */
 	synchronize_rcu();
-	rcu_read_lock();
 	for (i = 0; i < htab->buckets_num; i++) {
 		bucket = sock_hash_select_bucket(htab, i);
+
+		/* We are racing with sock_hash_delete_from_link to
+		 * enter the spin-lock critical section. Every socket on
+		 * the list is still linked to sockhash. Since link
+		 * exists, psock exists and holds a ref to socket. That
+		 * lets us to grab a socket ref too.
+		 */
 		raw_spin_lock_bh(&bucket->lock);
-		hlist_for_each_entry_safe(elem, node, &bucket->head, node) {
-			hlist_del_rcu(&elem->node);
+		hlist_for_each_entry(elem, &bucket->head, node)
+			sock_hold(elem->sk);
+		hlist_move_list(&bucket->head, &unlink_list);
+		raw_spin_unlock_bh(&bucket->lock);
+
+		/* Process removed entries out of atomic context to
+		 * block for socket lock before deleting the psock's
+		 * link to sockhash.
+		 */
+		hlist_for_each_entry_safe(elem, node, &unlink_list, node) {
+			hlist_del(&elem->node);
+			rcu_read_lock();
+			lock_sock(elem->sk);
 			sock_map_unref(elem->sk, elem);
+			release_sock(elem->sk);
+			sock_put(elem->sk);
+			sock_hash_free_elem(htab, elem);
+			rcu_read_unlock();
 		}
-		raw_spin_unlock_bh(&bucket->lock);
 	}
-	rcu_read_unlock();
+
+	/* wait for psock readers accessing its map link */
+	synchronize_rcu();
 
 	bpf_map_area_free(htab->buckets);
 	kfree(htab);
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index 2f89777763ad..3f1fe0958ff6 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -112,6 +112,7 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse)
 	more_reuse->prog = reuse->prog;
 	more_reuse->reuseport_id = reuse->reuseport_id;
 	more_reuse->bind_inany = reuse->bind_inany;
+	more_reuse->has_conns = reuse->has_conns;
 
 	memcpy(more_reuse->socks, reuse->socks,
 	       reuse->num_socks * sizeof(struct sock *));
diff --git a/net/core/utils.c b/net/core/utils.c
index 6b6e51db9f3b..1f31a39236d5 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -438,6 +438,23 @@ void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb,
 }
 EXPORT_SYMBOL(inet_proto_csum_replace4);
 
+/**
+ * inet_proto_csum_replace16 - update layer 4 header checksum field
+ * @sum: Layer 4 header checksum field
+ * @skb: sk_buff for the packet
+ * @from: old IPv6 address
+ * @to: new IPv6 address
+ * @pseudohdr: True if layer 4 header checksum includes pseudoheader
+ *
+ * Update layer 4 header as per the update in IPv6 src/dst address.
+ *
+ * There is no need to update skb->csum in this function, because update in two
+ * fields a.) IPv6 src/dst address and b.) L4 header checksum cancels each other
+ * for skb->csum calculation. Whereas inet_proto_csum_replace4 function needs to
+ * update skb->csum, because update in 3 fields a.) IPv4 src/dst address,
+ * b.) IPv4 Header checksum and c.) L4 header checksum results in same diff as
+ * L4 Header checksum for skb->csum calculation.
+ */
 void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb,
 			       const __be32 *from, const __be32 *to,
 			       bool pseudohdr)
@@ -449,9 +466,6 @@ void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb,
 	if (skb->ip_summed != CHECKSUM_PARTIAL) {
 		*sum = csum_fold(csum_partial(diff, sizeof(diff),
 				 ~csum_unfold(*sum)));
-		if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr)
-			skb->csum = ~csum_partial(diff, sizeof(diff),
-						  ~skb->csum);
 	} else if (pseudohdr)
 		*sum = ~csum_fold(csum_partial(diff, sizeof(diff),
 				  csum_unfold(*sum)));
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 5bad08dc4316..cb61a9d281f6 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -1139,14 +1139,14 @@ static int __init dccp_init(void)
 	inet_hashinfo_init(&dccp_hashinfo);
 	rc = inet_hashinfo2_init_mod(&dccp_hashinfo);
 	if (rc)
-		goto out_fail;
+		goto out_free_percpu;
 	rc = -ENOBUFS;
 	dccp_hashinfo.bind_bucket_cachep =
 		kmem_cache_create("dccp_bind_bucket",
 				  sizeof(struct inet_bind_bucket), 0,
 				  SLAB_HWCACHE_ALIGN, NULL);
 	if (!dccp_hashinfo.bind_bucket_cachep)
-		goto out_free_percpu;
+		goto out_free_hashinfo2;
 
 	/*
 	 * Size and allocate the main established and bind bucket
@@ -1242,6 +1242,8 @@ out_free_dccp_ehash:
 	free_pages((unsigned long)dccp_hashinfo.ehash, ehash_order);
 out_free_bind_bucket_cachep:
 	kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep);
+out_free_hashinfo2:
+	inet_hashinfo2_free_mod(&dccp_hashinfo);
 out_free_percpu:
 	percpu_counter_destroy(&dccp_orphan_count);
 out_fail:
@@ -1265,6 +1267,7 @@ static void __exit dccp_fini(void)
 	kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep);
 	dccp_ackvec_exit();
 	dccp_sysctl_exit();
+	inet_hashinfo2_free_mod(&dccp_hashinfo);
 	percpu_counter_destroy(&dccp_orphan_count);
 }
 
diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c
index a65d553e730d..b13599277601 100644
--- a/net/dns_resolver/dns_key.c
+++ b/net/dns_resolver/dns_key.c
@@ -302,7 +302,7 @@ static void dns_resolver_describe(const struct key *key, struct seq_file *m)
  * - the key's semaphore is read-locked
  */
 static long dns_resolver_read(const struct key *key,
-			      char __user *buffer, size_t buflen)
+			      char *buffer, size_t buflen)
 {
 	int err = PTR_ERR(key->payload.data[dns_key_error]);
 
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index e720a9935e0a..1f2ef2922b96 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -426,7 +426,7 @@ static int dsa_tree_setup_switches(struct dsa_switch_tree *dst)
 
 			err = dsa_port_setup(dp);
 			if (err)
-				return err;
+				continue;
 		}
 	}
 
diff --git a/net/dsa/master.c b/net/dsa/master.c
index 4b52f8bac5e1..9f29a90cd66c 100644
--- a/net/dsa/master.c
+++ b/net/dsa/master.c
@@ -193,7 +193,8 @@ static void dsa_master_ndo_teardown(struct net_device *dev)
 {
 	struct dsa_port *cpu_dp = dev->dsa_ptr;
 
-	dev->netdev_ops = cpu_dp->orig_ndo_ops;
+	if (cpu_dp->orig_ndo_ops)
+		dev->netdev_ops = cpu_dp->orig_ndo_ops;
 	cpu_dp->orig_ndo_ops = NULL;
 }
 
diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
index 9c3114179690..9169b63a89e3 100644
--- a/net/dsa/tag_brcm.c
+++ b/net/dsa/tag_brcm.c
@@ -140,6 +140,8 @@ static struct sk_buff *brcm_tag_rcv_ll(struct sk_buff *skb,
 	/* Remove Broadcom tag and update checksum */
 	skb_pull_rcsum(skb, BRCM_TAG_LEN);
 
+	skb->offload_fwd_mark = 1;
+
 	return skb;
 }
 #endif
diff --git a/net/dsa/tag_gswip.c b/net/dsa/tag_gswip.c
index b678160bbd66..408d4af390a0 100644
--- a/net/dsa/tag_gswip.c
+++ b/net/dsa/tag_gswip.c
@@ -104,7 +104,7 @@ static struct sk_buff *gswip_tag_rcv(struct sk_buff *skb,
 }
 
 static const struct dsa_device_ops gswip_netdev_ops = {
-	.name = "gwsip",
+	.name = "gswip",
 	.proto	= DSA_TAG_PROTO_GSWIP,
 	.xmit = gswip_tag_xmit,
 	.rcv = gswip_tag_rcv,
diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c
index b5705cba8318..d6619edd53e5 100644
--- a/net/dsa/tag_mtk.c
+++ b/net/dsa/tag_mtk.c
@@ -15,6 +15,7 @@
 #define MTK_HDR_XMIT_TAGGED_TPID_8100	1
 #define MTK_HDR_RECV_SOURCE_PORT_MASK	GENMASK(2, 0)
 #define MTK_HDR_XMIT_DP_BIT_MASK	GENMASK(5, 0)
+#define MTK_HDR_XMIT_SA_DIS		BIT(6)
 
 static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
 				    struct net_device *dev)
@@ -22,6 +23,9 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
 	struct dsa_port *dp = dsa_slave_to_port(dev);
 	u8 *mtk_tag;
 	bool is_vlan_skb = true;
+	unsigned char *dest = eth_hdr(skb)->h_dest;
+	bool is_multicast_skb = is_multicast_ether_addr(dest) &&
+				!is_broadcast_ether_addr(dest);
 
 	/* Build the special tag after the MAC Source Address. If VLAN header
 	 * is present, it's required that VLAN header and special tag is
@@ -47,6 +51,10 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
 		     MTK_HDR_XMIT_UNTAGGED;
 	mtk_tag[1] = (1 << dp->index) & MTK_HDR_XMIT_DP_BIT_MASK;
 
+	/* Disable SA learning for multicast frames */
+	if (unlikely(is_multicast_skb))
+		mtk_tag[1] |= MTK_HDR_XMIT_SA_DIS;
+
 	/* Tag control information is kept for 802.1Q */
 	if (!is_vlan_skb) {
 		mtk_tag[2] = 0;
@@ -61,6 +69,9 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 {
 	int port;
 	__be16 *phdr, hdr;
+	unsigned char *dest = eth_hdr(skb)->h_dest;
+	bool is_multicast_skb = is_multicast_ether_addr(dest) &&
+				!is_broadcast_ether_addr(dest);
 
 	if (unlikely(!pskb_may_pull(skb, MTK_HDR_LEN)))
 		return NULL;
@@ -86,6 +97,10 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (!skb->dev)
 		return NULL;
 
+	/* Only unicast or broadcast frames are offloaded */
+	if (likely(!is_multicast_skb))
+		skb->offload_fwd_mark = 1;
+
 	return skb;
 }
 
diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index c95885215525..70db7c909f74 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -33,10 +33,7 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct dsa_port *dp = dsa_slave_to_port(dev);
 	u16 *phdr, hdr;
 
-	dev->stats.tx_packets++;
-	dev->stats.tx_bytes += skb->len;
-
-	if (skb_cow_head(skb, 0) < 0)
+	if (skb_cow_head(skb, QCA_HDR_LEN) < 0)
 		return NULL;
 
 	skb_push(skb, QCA_HDR_LEN);
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 20b0bcb7e9e3..c5a729118052 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -244,7 +244,12 @@ int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh, __be16
 	eth->h_proto = type;
 	memcpy(eth->h_source, dev->dev_addr, ETH_ALEN);
 	memcpy(eth->h_dest, neigh->ha, ETH_ALEN);
-	hh->hh_len = ETH_HLEN;
+
+	/* Pairs with READ_ONCE() in neigh_resolve_output(),
+	 * neigh_hh_output() and neigh_update_hhs().
+	 */
+	smp_store_release(&hh->hh_len, ETH_HLEN);
+
 	return 0;
 }
 EXPORT_SYMBOL(eth_header_cache);
diff --git a/net/hsr/hsr_debugfs.c b/net/hsr/hsr_debugfs.c
index 94447974a3c0..d5f709b940ff 100644
--- a/net/hsr/hsr_debugfs.c
+++ b/net/hsr/hsr_debugfs.c
@@ -20,6 +20,8 @@
 #include "hsr_main.h"
 #include "hsr_framereg.h"
 
+static struct dentry *hsr_debugfs_root_dir;
+
 static void print_mac_address(struct seq_file *sfp, unsigned char *mac)
 {
 	seq_printf(sfp, "%02x:%02x:%02x:%02x:%02x:%02x:",
@@ -63,8 +65,20 @@ hsr_node_table_open(struct inode *inode, struct file *filp)
 	return single_open(filp, hsr_node_table_show, inode->i_private);
 }
 
+void hsr_debugfs_rename(struct net_device *dev)
+{
+	struct hsr_priv *priv = netdev_priv(dev);
+	struct dentry *d;
+
+	d = debugfs_rename(hsr_debugfs_root_dir, priv->node_tbl_root,
+			   hsr_debugfs_root_dir, dev->name);
+	if (IS_ERR(d))
+		netdev_warn(dev, "failed to rename\n");
+	else
+		priv->node_tbl_root = d;
+}
+
 static const struct file_operations hsr_fops = {
-	.owner	= THIS_MODULE,
 	.open	= hsr_node_table_open,
 	.read	= seq_read,
 	.llseek = seq_lseek,
@@ -78,15 +92,14 @@ static const struct file_operations hsr_fops = {
  * When debugfs is configured this routine sets up the node_table file per
  * hsr device for dumping the node_table entries
  */
-int hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev)
+void hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev)
 {
-	int rc = -1;
 	struct dentry *de = NULL;
 
-	de = debugfs_create_dir(hsr_dev->name, NULL);
-	if (!de) {
-		pr_err("Cannot create hsr debugfs root\n");
-		return rc;
+	de = debugfs_create_dir(hsr_dev->name, hsr_debugfs_root_dir);
+	if (IS_ERR(de)) {
+		pr_err("Cannot create hsr debugfs directory\n");
+		return;
 	}
 
 	priv->node_tbl_root = de;
@@ -94,13 +107,13 @@ int hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev)
 	de = debugfs_create_file("node_table", S_IFREG | 0444,
 				 priv->node_tbl_root, priv,
 				 &hsr_fops);
-	if (!de) {
-		pr_err("Cannot create hsr node_table directory\n");
-		return rc;
+	if (IS_ERR(de)) {
+		pr_err("Cannot create hsr node_table file\n");
+		debugfs_remove(priv->node_tbl_root);
+		priv->node_tbl_root = NULL;
+		return;
 	}
 	priv->node_tbl_file = de;
-
-	return 0;
 }
 
 /* hsr_debugfs_term - Tear down debugfs intrastructure
@@ -117,3 +130,18 @@ hsr_debugfs_term(struct hsr_priv *priv)
 	debugfs_remove(priv->node_tbl_root);
 	priv->node_tbl_root = NULL;
 }
+
+void hsr_debugfs_create_root(void)
+{
+	hsr_debugfs_root_dir = debugfs_create_dir("hsr", NULL);
+	if (IS_ERR(hsr_debugfs_root_dir)) {
+		pr_err("Cannot create hsr debugfs root directory\n");
+		hsr_debugfs_root_dir = NULL;
+	}
+}
+
+void hsr_debugfs_remove_root(void)
+{
+	/* debugfs_remove() internally checks NULL and ERROR */
+	debugfs_remove(hsr_debugfs_root_dir);
+}
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index 8f30b3fa8593..acda3aa994c2 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -272,6 +272,8 @@ static void send_hsr_supervision_frame(struct hsr_port *master,
 			    skb->dev->dev_addr, skb->len) <= 0)
 		goto out;
 	skb_reset_mac_header(skb);
+	skb_reset_network_header(skb);
+	skb_reset_transport_header(skb);
 
 	if (hsr_ver > 0) {
 		hsr_tag = skb_put(skb, sizeof(struct hsr_tag));
@@ -367,7 +369,7 @@ static void hsr_dev_destroy(struct net_device *hsr_dev)
 	del_timer_sync(&hsr->prune_timer);
 	del_timer_sync(&hsr->announce_timer);
 
-	hsr_del_self_node(&hsr->self_node_db);
+	hsr_del_self_node(hsr);
 	hsr_del_nodes(&hsr->node_db);
 }
 
@@ -438,11 +440,12 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2],
 	INIT_LIST_HEAD(&hsr->ports);
 	INIT_LIST_HEAD(&hsr->node_db);
 	INIT_LIST_HEAD(&hsr->self_node_db);
+	spin_lock_init(&hsr->list_lock);
 
 	ether_addr_copy(hsr_dev->dev_addr, slave[0]->dev_addr);
 
 	/* Make sure we recognize frames from ourselves in hsr_rcv() */
-	res = hsr_create_self_node(&hsr->self_node_db, hsr_dev->dev_addr,
+	res = hsr_create_self_node(hsr, hsr_dev->dev_addr,
 				   slave[1]->dev_addr);
 	if (res < 0)
 		return res;
@@ -475,31 +478,32 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2],
 
 	res = hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER);
 	if (res)
-		goto err_add_port;
+		goto err_add_master;
 
 	res = register_netdevice(hsr_dev);
 	if (res)
-		goto fail;
+		goto err_unregister;
 
 	res = hsr_add_port(hsr, slave[0], HSR_PT_SLAVE_A);
 	if (res)
-		goto fail;
+		goto err_add_slaves;
+
 	res = hsr_add_port(hsr, slave[1], HSR_PT_SLAVE_B);
 	if (res)
-		goto fail;
+		goto err_add_slaves;
 
+	hsr_debugfs_init(hsr, hsr_dev);
 	mod_timer(&hsr->prune_timer, jiffies + msecs_to_jiffies(PRUNE_PERIOD));
-	res = hsr_debugfs_init(hsr, hsr_dev);
-	if (res)
-		goto fail;
 
 	return 0;
 
-fail:
+err_add_slaves:
+	unregister_netdevice(hsr_dev);
+err_unregister:
 	hsr_for_each_port(hsr, port)
 		hsr_del_port(port);
-err_add_port:
-	hsr_del_self_node(&hsr->self_node_db);
+err_add_master:
+	hsr_del_self_node(hsr);
 
 	return res;
 }
diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c
index 292be446007b..002f341f3564 100644
--- a/net/hsr/hsr_framereg.c
+++ b/net/hsr/hsr_framereg.c
@@ -75,10 +75,11 @@ static struct hsr_node *find_node_by_addr_A(struct list_head *node_db,
 /* Helper for device init; the self_node_db is used in hsr_rcv() to recognize
  * frames from self that's been looped over the HSR ring.
  */
-int hsr_create_self_node(struct list_head *self_node_db,
+int hsr_create_self_node(struct hsr_priv *hsr,
 			 unsigned char addr_a[ETH_ALEN],
 			 unsigned char addr_b[ETH_ALEN])
 {
+	struct list_head *self_node_db = &hsr->self_node_db;
 	struct hsr_node *node, *oldnode;
 
 	node = kmalloc(sizeof(*node), GFP_KERNEL);
@@ -88,33 +89,33 @@ int hsr_create_self_node(struct list_head *self_node_db,
 	ether_addr_copy(node->macaddress_A, addr_a);
 	ether_addr_copy(node->macaddress_B, addr_b);
 
-	rcu_read_lock();
+	spin_lock_bh(&hsr->list_lock);
 	oldnode = list_first_or_null_rcu(self_node_db,
 					 struct hsr_node, mac_list);
 	if (oldnode) {
 		list_replace_rcu(&oldnode->mac_list, &node->mac_list);
-		rcu_read_unlock();
-		synchronize_rcu();
-		kfree(oldnode);
+		spin_unlock_bh(&hsr->list_lock);
+		kfree_rcu(oldnode, rcu_head);
 	} else {
-		rcu_read_unlock();
 		list_add_tail_rcu(&node->mac_list, self_node_db);
+		spin_unlock_bh(&hsr->list_lock);
 	}
 
 	return 0;
 }
 
-void hsr_del_self_node(struct list_head *self_node_db)
+void hsr_del_self_node(struct hsr_priv *hsr)
 {
+	struct list_head *self_node_db = &hsr->self_node_db;
 	struct hsr_node *node;
 
-	rcu_read_lock();
+	spin_lock_bh(&hsr->list_lock);
 	node = list_first_or_null_rcu(self_node_db, struct hsr_node, mac_list);
-	rcu_read_unlock();
 	if (node) {
 		list_del_rcu(&node->mac_list);
-		kfree(node);
+		kfree_rcu(node, rcu_head);
 	}
+	spin_unlock_bh(&hsr->list_lock);
 }
 
 void hsr_del_nodes(struct list_head *node_db)
@@ -130,30 +131,43 @@ void hsr_del_nodes(struct list_head *node_db)
  * seq_out is used to initialize filtering of outgoing duplicate frames
  * originating from the newly added node.
  */
-struct hsr_node *hsr_add_node(struct list_head *node_db, unsigned char addr[],
-			      u16 seq_out)
+static struct hsr_node *hsr_add_node(struct hsr_priv *hsr,
+				     struct list_head *node_db,
+				     unsigned char addr[],
+				     u16 seq_out)
 {
-	struct hsr_node *node;
+	struct hsr_node *new_node, *node;
 	unsigned long now;
 	int i;
 
-	node = kzalloc(sizeof(*node), GFP_ATOMIC);
-	if (!node)
+	new_node = kzalloc(sizeof(*new_node), GFP_ATOMIC);
+	if (!new_node)
 		return NULL;
 
-	ether_addr_copy(node->macaddress_A, addr);
+	ether_addr_copy(new_node->macaddress_A, addr);
 
 	/* We are only interested in time diffs here, so use current jiffies
 	 * as initialization. (0 could trigger an spurious ring error warning).
 	 */
 	now = jiffies;
 	for (i = 0; i < HSR_PT_PORTS; i++)
-		node->time_in[i] = now;
+		new_node->time_in[i] = now;
 	for (i = 0; i < HSR_PT_PORTS; i++)
-		node->seq_out[i] = seq_out;
-
-	list_add_tail_rcu(&node->mac_list, node_db);
+		new_node->seq_out[i] = seq_out;
 
+	spin_lock_bh(&hsr->list_lock);
+	list_for_each_entry_rcu(node, node_db, mac_list) {
+		if (ether_addr_equal(node->macaddress_A, addr))
+			goto out;
+		if (ether_addr_equal(node->macaddress_B, addr))
+			goto out;
+	}
+	list_add_tail_rcu(&new_node->mac_list, node_db);
+	spin_unlock_bh(&hsr->list_lock);
+	return new_node;
+out:
+	spin_unlock_bh(&hsr->list_lock);
+	kfree(new_node);
 	return node;
 }
 
@@ -163,6 +177,7 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb,
 			      bool is_sup)
 {
 	struct list_head *node_db = &port->hsr->node_db;
+	struct hsr_priv *hsr = port->hsr;
 	struct hsr_node *node;
 	struct ethhdr *ethhdr;
 	u16 seq_out;
@@ -196,7 +211,7 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb,
 		seq_out = HSR_SEQNR_START;
 	}
 
-	return hsr_add_node(node_db, ethhdr->h_source, seq_out);
+	return hsr_add_node(hsr, node_db, ethhdr->h_source, seq_out);
 }
 
 /* Use the Supervision frame's info about an eventual macaddress_B for merging
@@ -206,10 +221,11 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb,
 void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr,
 			  struct hsr_port *port_rcv)
 {
-	struct ethhdr *ethhdr;
-	struct hsr_node *node_real;
+	struct hsr_priv *hsr = port_rcv->hsr;
 	struct hsr_sup_payload *hsr_sp;
+	struct hsr_node *node_real;
 	struct list_head *node_db;
+	struct ethhdr *ethhdr;
 	int i;
 
 	ethhdr = (struct ethhdr *)skb_mac_header(skb);
@@ -231,7 +247,7 @@ void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr,
 	node_real = find_node_by_addr_A(node_db, hsr_sp->macaddress_A);
 	if (!node_real)
 		/* No frame received from AddrA of this node yet */
-		node_real = hsr_add_node(node_db, hsr_sp->macaddress_A,
+		node_real = hsr_add_node(hsr, node_db, hsr_sp->macaddress_A,
 					 HSR_SEQNR_START - 1);
 	if (!node_real)
 		goto done; /* No mem */
@@ -252,7 +268,9 @@ void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr,
 	}
 	node_real->addr_B_port = port_rcv->type;
 
+	spin_lock_bh(&hsr->list_lock);
 	list_del_rcu(&node_curr->mac_list);
+	spin_unlock_bh(&hsr->list_lock);
 	kfree_rcu(node_curr, rcu_head);
 
 done:
@@ -368,12 +386,13 @@ void hsr_prune_nodes(struct timer_list *t)
 {
 	struct hsr_priv *hsr = from_timer(hsr, t, prune_timer);
 	struct hsr_node *node;
+	struct hsr_node *tmp;
 	struct hsr_port *port;
 	unsigned long timestamp;
 	unsigned long time_a, time_b;
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(node, &hsr->node_db, mac_list) {
+	spin_lock_bh(&hsr->list_lock);
+	list_for_each_entry_safe(node, tmp, &hsr->node_db, mac_list) {
 		/* Don't prune own node. Neither time_in[HSR_PT_SLAVE_A]
 		 * nor time_in[HSR_PT_SLAVE_B], will ever be updated for
 		 * the master port. Thus the master node will be repeatedly
@@ -421,7 +440,7 @@ void hsr_prune_nodes(struct timer_list *t)
 			kfree_rcu(node, rcu_head);
 		}
 	}
-	rcu_read_unlock();
+	spin_unlock_bh(&hsr->list_lock);
 
 	/* Restart timer */
 	mod_timer(&hsr->prune_timer,
@@ -463,12 +482,9 @@ int hsr_get_node_data(struct hsr_priv *hsr,
 	struct hsr_port *port;
 	unsigned long tdiff;
 
-	rcu_read_lock();
 	node = find_node_by_addr_A(&hsr->node_db, addr);
-	if (!node) {
-		rcu_read_unlock();
-		return -ENOENT;	/* No such entry */
-	}
+	if (!node)
+		return -ENOENT;
 
 	ether_addr_copy(addr_b, node->macaddress_B);
 
@@ -503,7 +519,5 @@ int hsr_get_node_data(struct hsr_priv *hsr,
 		*addr_b_ifindex = -1;
 	}
 
-	rcu_read_unlock();
-
 	return 0;
 }
diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h
index 89a3ce38151d..0f0fa12b4329 100644
--- a/net/hsr/hsr_framereg.h
+++ b/net/hsr/hsr_framereg.h
@@ -12,10 +12,8 @@
 
 struct hsr_node;
 
-void hsr_del_self_node(struct list_head *self_node_db);
+void hsr_del_self_node(struct hsr_priv *hsr);
 void hsr_del_nodes(struct list_head *node_db);
-struct hsr_node *hsr_add_node(struct list_head *node_db, unsigned char addr[],
-			      u16 seq_out);
 struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb,
 			      bool is_sup);
 void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr,
@@ -33,7 +31,7 @@ int hsr_register_frame_out(struct hsr_port *port, struct hsr_node *node,
 
 void hsr_prune_nodes(struct timer_list *t);
 
-int hsr_create_self_node(struct list_head *self_node_db,
+int hsr_create_self_node(struct hsr_priv *hsr,
 			 unsigned char addr_a[ETH_ALEN],
 			 unsigned char addr_b[ETH_ALEN]);
 
diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c
index b9988a662ee1..9e389accbfc7 100644
--- a/net/hsr/hsr_main.c
+++ b/net/hsr/hsr_main.c
@@ -45,6 +45,10 @@ static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event,
 	case NETDEV_CHANGE:	/* Link (carrier) state changes */
 		hsr_check_carrier_and_operstate(hsr);
 		break;
+	case NETDEV_CHANGENAME:
+		if (is_hsr_master(dev))
+			hsr_debugfs_rename(dev);
+		break;
 	case NETDEV_CHANGEADDR:
 		if (port->type == HSR_PT_MASTER) {
 			/* This should not happen since there's no
@@ -64,7 +68,7 @@ static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event,
 
 		/* Make sure we recognize frames from ourselves in hsr_rcv() */
 		port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B);
-		res = hsr_create_self_node(&hsr->self_node_db,
+		res = hsr_create_self_node(hsr,
 					   master->dev->dev_addr,
 					   port ?
 						port->dev->dev_addr :
@@ -123,6 +127,7 @@ static void __exit hsr_exit(void)
 {
 	unregister_netdevice_notifier(&hsr_nb);
 	hsr_netlink_exit();
+	hsr_debugfs_remove_root();
 }
 
 module_init(hsr_init);
diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h
index 96fac696a1e1..754d84b217f0 100644
--- a/net/hsr/hsr_main.h
+++ b/net/hsr/hsr_main.h
@@ -160,8 +160,9 @@ struct hsr_priv {
 	int announce_count;
 	u16 sequence_nr;
 	u16 sup_sequence_nr;	/* For HSRv1 separate seq_nr for supervision */
-	u8 prot_version;		/* Indicate if HSRv0 or HSRv1. */
-	spinlock_t seqnr_lock;			/* locking for sequence_nr */
+	u8 prot_version;	/* Indicate if HSRv0 or HSRv1. */
+	spinlock_t seqnr_lock;	/* locking for sequence_nr */
+	spinlock_t list_lock;	/* locking for node list */
 	unsigned char		sup_multicast_addr[ETH_ALEN];
 #ifdef	CONFIG_DEBUG_FS
 	struct dentry *node_tbl_root;
@@ -184,17 +185,24 @@ static inline u16 hsr_get_skb_sequence_nr(struct sk_buff *skb)
 }
 
 #if IS_ENABLED(CONFIG_DEBUG_FS)
-int hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev);
+void hsr_debugfs_rename(struct net_device *dev);
+void hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev);
 void hsr_debugfs_term(struct hsr_priv *priv);
+void hsr_debugfs_create_root(void);
+void hsr_debugfs_remove_root(void);
 #else
-static inline int hsr_debugfs_init(struct hsr_priv *priv,
-				   struct net_device *hsr_dev)
+static inline void hsr_debugfs_rename(struct net_device *dev)
 {
-	return 0;
 }
-
+static inline void hsr_debugfs_init(struct hsr_priv *priv,
+				    struct net_device *hsr_dev)
+{}
 static inline void hsr_debugfs_term(struct hsr_priv *priv)
 {}
+static inline void hsr_debugfs_create_root(void)
+{}
+static inline void hsr_debugfs_remove_root(void)
+{}
 #endif
 
 #endif /*  __HSR_PRIVATE_H */
diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c
index 8f8337f893ba..55c0b2e872a5 100644
--- a/net/hsr/hsr_netlink.c
+++ b/net/hsr/hsr_netlink.c
@@ -61,10 +61,16 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev,
 	else
 		multicast_spec = nla_get_u8(data[IFLA_HSR_MULTICAST_SPEC]);
 
-	if (!data[IFLA_HSR_VERSION])
+	if (!data[IFLA_HSR_VERSION]) {
 		hsr_version = 0;
-	else
+	} else {
 		hsr_version = nla_get_u8(data[IFLA_HSR_VERSION]);
+		if (hsr_version > 1) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Only versions 0..1 are supported");
+			return -EINVAL;
+		}
+	}
 
 	return hsr_dev_finalize(dev, link, multicast_spec, hsr_version);
 }
@@ -251,15 +257,16 @@ static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info)
 	if (!na)
 		goto invalid;
 
-	hsr_dev = __dev_get_by_index(genl_info_net(info),
-				     nla_get_u32(info->attrs[HSR_A_IFINDEX]));
+	rcu_read_lock();
+	hsr_dev = dev_get_by_index_rcu(genl_info_net(info),
+				       nla_get_u32(info->attrs[HSR_A_IFINDEX]));
 	if (!hsr_dev)
-		goto invalid;
+		goto rcu_unlock;
 	if (!is_hsr_master(hsr_dev))
-		goto invalid;
+		goto rcu_unlock;
 
 	/* Send reply */
-	skb_out = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	skb_out = genlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC);
 	if (!skb_out) {
 		res = -ENOMEM;
 		goto fail;
@@ -313,12 +320,10 @@ static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info)
 	res = nla_put_u16(skb_out, HSR_A_IF1_SEQ, hsr_node_if1_seq);
 	if (res < 0)
 		goto nla_put_failure;
-	rcu_read_lock();
 	port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A);
 	if (port)
 		res = nla_put_u32(skb_out, HSR_A_IF1_IFINDEX,
 				  port->dev->ifindex);
-	rcu_read_unlock();
 	if (res < 0)
 		goto nla_put_failure;
 
@@ -328,20 +333,22 @@ static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info)
 	res = nla_put_u16(skb_out, HSR_A_IF2_SEQ, hsr_node_if2_seq);
 	if (res < 0)
 		goto nla_put_failure;
-	rcu_read_lock();
 	port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B);
 	if (port)
 		res = nla_put_u32(skb_out, HSR_A_IF2_IFINDEX,
 				  port->dev->ifindex);
-	rcu_read_unlock();
 	if (res < 0)
 		goto nla_put_failure;
 
+	rcu_read_unlock();
+
 	genlmsg_end(skb_out, msg_head);
 	genlmsg_unicast(genl_info_net(info), skb_out, info->snd_portid);
 
 	return 0;
 
+rcu_unlock:
+	rcu_read_unlock();
 invalid:
 	netlink_ack(skb_in, nlmsg_hdr(skb_in), -EINVAL, NULL);
 	return 0;
@@ -351,6 +358,7 @@ nla_put_failure:
 	/* Fall through */
 
 fail:
+	rcu_read_unlock();
 	return res;
 }
 
@@ -358,16 +366,14 @@ fail:
  */
 static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info)
 {
-	/* For receiving */
-	struct nlattr *na;
+	unsigned char addr[ETH_ALEN];
 	struct net_device *hsr_dev;
-
-	/* For sending */
 	struct sk_buff *skb_out;
-	void *msg_head;
 	struct hsr_priv *hsr;
-	void *pos;
-	unsigned char addr[ETH_ALEN];
+	bool restart = false;
+	struct nlattr *na;
+	void *pos = NULL;
+	void *msg_head;
 	int res;
 
 	if (!info)
@@ -377,15 +383,17 @@ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info)
 	if (!na)
 		goto invalid;
 
-	hsr_dev = __dev_get_by_index(genl_info_net(info),
-				     nla_get_u32(info->attrs[HSR_A_IFINDEX]));
+	rcu_read_lock();
+	hsr_dev = dev_get_by_index_rcu(genl_info_net(info),
+				       nla_get_u32(info->attrs[HSR_A_IFINDEX]));
 	if (!hsr_dev)
-		goto invalid;
+		goto rcu_unlock;
 	if (!is_hsr_master(hsr_dev))
-		goto invalid;
+		goto rcu_unlock;
 
+restart:
 	/* Send reply */
-	skb_out = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	skb_out = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_ATOMIC);
 	if (!skb_out) {
 		res = -ENOMEM;
 		goto fail;
@@ -399,18 +407,26 @@ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info)
 		goto nla_put_failure;
 	}
 
-	res = nla_put_u32(skb_out, HSR_A_IFINDEX, hsr_dev->ifindex);
-	if (res < 0)
-		goto nla_put_failure;
+	if (!restart) {
+		res = nla_put_u32(skb_out, HSR_A_IFINDEX, hsr_dev->ifindex);
+		if (res < 0)
+			goto nla_put_failure;
+	}
 
 	hsr = netdev_priv(hsr_dev);
 
-	rcu_read_lock();
-	pos = hsr_get_next_node(hsr, NULL, addr);
+	if (!pos)
+		pos = hsr_get_next_node(hsr, NULL, addr);
 	while (pos) {
 		res = nla_put(skb_out, HSR_A_NODE_ADDR, ETH_ALEN, addr);
 		if (res < 0) {
-			rcu_read_unlock();
+			if (res == -EMSGSIZE) {
+				genlmsg_end(skb_out, msg_head);
+				genlmsg_unicast(genl_info_net(info), skb_out,
+						info->snd_portid);
+				restart = true;
+				goto restart;
+			}
 			goto nla_put_failure;
 		}
 		pos = hsr_get_next_node(hsr, pos, addr);
@@ -422,15 +438,18 @@ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info)
 
 	return 0;
 
+rcu_unlock:
+	rcu_read_unlock();
 invalid:
 	netlink_ack(skb_in, nlmsg_hdr(skb_in), -EINVAL, NULL);
 	return 0;
 
 nla_put_failure:
-	kfree_skb(skb_out);
+	nlmsg_free(skb_out);
 	/* Fall through */
 
 fail:
+	rcu_read_unlock();
 	return res;
 }
 
@@ -457,6 +476,7 @@ static struct genl_family hsr_genl_family __ro_after_init = {
 	.version = 1,
 	.maxattr = HSR_A_MAX,
 	.policy = hsr_genl_policy,
+	.netnsok = true,
 	.module = THIS_MODULE,
 	.ops = hsr_ops,
 	.n_ops = ARRAY_SIZE(hsr_ops),
@@ -476,6 +496,7 @@ int __init hsr_netlink_init(void)
 	if (rc)
 		goto fail_genl_register_family;
 
+	hsr_debugfs_create_root();
 	return 0;
 
 fail_genl_register_family:
diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c
index 88b6705ded83..279f2503d157 100644
--- a/net/hsr/hsr_slave.c
+++ b/net/hsr/hsr_slave.c
@@ -27,6 +27,8 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb)
 
 	rcu_read_lock(); /* hsr->node_db, hsr->ports */
 	port = hsr_port_get_rcu(skb->dev);
+	if (!port)
+		goto finish_pass;
 
 	if (hsr_addr_is_self(port->hsr, eth_hdr(skb)->h_source)) {
 		/* Directly kill frames sent by ourselves */
@@ -143,16 +145,16 @@ int hsr_add_port(struct hsr_priv *hsr, struct net_device *dev,
 	if (!port)
 		return -ENOMEM;
 
+	port->hsr = hsr;
+	port->dev = dev;
+	port->type = type;
+
 	if (type != HSR_PT_MASTER) {
 		res = hsr_portdev_setup(dev, port);
 		if (res)
 			goto fail_dev_setup;
 	}
 
-	port->hsr = hsr;
-	port->dev = dev;
-	port->type = type;
-
 	list_add_tail_rcu(&port->port_list, &hsr->ports);
 	synchronize_rcu();
 
diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c
index 2c7a38d76a3a..0672b2f01586 100644
--- a/net/ieee802154/nl_policy.c
+++ b/net/ieee802154/nl_policy.c
@@ -21,7 +21,13 @@ const struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = {
 	[IEEE802154_ATTR_HW_ADDR] = { .type = NLA_HW_ADDR, },
 	[IEEE802154_ATTR_PAN_ID] = { .type = NLA_U16, },
 	[IEEE802154_ATTR_CHANNEL] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_BCN_ORD] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_SF_ORD] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_PAN_COORD] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_BAT_EXT] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_COORD_REALIGN] = { .type = NLA_U8, },
 	[IEEE802154_ATTR_PAGE] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_DEV_TYPE] = { .type = NLA_U8, },
 	[IEEE802154_ATTR_COORD_SHORT_ADDR] = { .type = NLA_U16, },
 	[IEEE802154_ATTR_COORD_HW_ADDR] = { .type = NLA_HW_ADDR, },
 	[IEEE802154_ATTR_COORD_PAN_ID] = { .type = NLA_U16, },
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 974de4d20f25..955a7a3fcc42 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -303,6 +303,7 @@ config SYN_COOKIES
 
 config NET_IPVTI
 	tristate "Virtual (secure) IP: tunneling"
+	depends on IPV6 || IPV6=n
 	select INET_TUNNEL
 	select NET_IP_TUNNEL
 	select XFRM
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 376882215919..a23094b050f8 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1258,7 +1258,8 @@ static int cipso_v4_parsetag_rbm(const struct cipso_v4_doi *doi_def,
 			return ret_val;
 		}
 
-		secattr->flags |= NETLBL_SECATTR_MLS_CAT;
+		if (secattr->attr.mls.cat)
+			secattr->flags |= NETLBL_SECATTR_MLS_CAT;
 	}
 
 	return 0;
@@ -1439,7 +1440,8 @@ static int cipso_v4_parsetag_rng(const struct cipso_v4_doi *doi_def,
 			return ret_val;
 		}
 
-		secattr->flags |= NETLBL_SECATTR_MLS_CAT;
+		if (secattr->attr.mls.cat)
+			secattr->flags |= NETLBL_SECATTR_MLS_CAT;
 	}
 
 	return 0;
@@ -1724,6 +1726,7 @@ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway)
 {
 	unsigned char optbuf[sizeof(struct ip_options) + 40];
 	struct ip_options *opt = (struct ip_options *)optbuf;
+	int res;
 
 	if (ip_hdr(skb)->protocol == IPPROTO_ICMP || error != -EACCES)
 		return;
@@ -1735,7 +1738,11 @@ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway)
 
 	memset(opt, 0, sizeof(struct ip_options));
 	opt->optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr);
-	if (__ip_options_compile(dev_net(skb->dev), opt, skb, NULL))
+	rcu_read_lock();
+	res = __ip_options_compile(dev_net(skb->dev), opt, skb, NULL);
+	rcu_read_unlock();
+
+	if (res)
 		return;
 
 	if (gateway)
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index af0c3ea78c45..03c058aea500 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -275,6 +275,7 @@ static struct in_device *inetdev_init(struct net_device *dev)
 	err = devinet_sysctl_register(in_dev);
 	if (err) {
 		in_dev->dead = 1;
+		neigh_parms_release(&arp_tbl, in_dev->arp_parms);
 		in_dev_put(in_dev);
 		in_dev = NULL;
 		goto out;
@@ -593,12 +594,15 @@ struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix,
 	return NULL;
 }
 
-static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa)
+static int ip_mc_autojoin_config(struct net *net, bool join,
+				 const struct in_ifaddr *ifa)
 {
+#if defined(CONFIG_IP_MULTICAST)
 	struct ip_mreqn mreq = {
 		.imr_multiaddr.s_addr = ifa->ifa_address,
 		.imr_ifindex = ifa->ifa_dev->dev->ifindex,
 	};
+	struct sock *sk = net->ipv4.mc_autojoin_sk;
 	int ret;
 
 	ASSERT_RTNL();
@@ -611,6 +615,9 @@ static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa)
 	release_sock(sk);
 
 	return ret;
+#else
+	return -EOPNOTSUPP;
+#endif
 }
 
 static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -652,7 +659,7 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
 			continue;
 
 		if (ipv4_is_multicast(ifa->ifa_address))
-			ip_mc_config(net->ipv4.mc_autojoin_sk, false, ifa);
+			ip_mc_autojoin_config(net, false, ifa);
 		__inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).portid);
 		return 0;
 	}
@@ -914,8 +921,7 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
 		 */
 		set_ifa_lifetime(ifa, valid_lft, prefered_lft);
 		if (ifa->ifa_flags & IFA_F_MCAUTOJOIN) {
-			int ret = ip_mc_config(net->ipv4.mc_autojoin_sk,
-					       true, ifa);
+			int ret = ip_mc_autojoin_config(net, true, ifa);
 
 			if (ret < 0) {
 				inet_free_ifa(ifa);
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 2e5e377f50a1..80570e2504db 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -57,14 +57,14 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head,
 		if (!x)
 			goto out_reset;
 
+		skb->mark = xfrm_smark_get(skb->mark, x);
+
 		sp->xvec[sp->len++] = x;
 		sp->olen++;
 
 		xo = xfrm_offload(skb);
-		if (!xo) {
-			xfrm_state_put(x);
+		if (!xo)
 			goto out_reset;
-		}
 	}
 
 	xo->flags |= XFRM_GRO;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 48137d37695e..dc0dbf06f354 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -886,7 +886,6 @@ int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh,
 		return -EINVAL;
 	}
 
-	filter->dump_all_families = (rtm->rtm_family == AF_UNSPEC);
 	filter->flags    = rtm->rtm_flags;
 	filter->protocol = rtm->rtm_protocol;
 	filter->rt_type  = rtm->rtm_type;
@@ -957,14 +956,16 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 	if (filter.table_id) {
 		tb = fib_get_table(net, filter.table_id);
 		if (!tb) {
-			if (filter.dump_all_families)
+			if (rtnl_msg_family(cb->nlh) != PF_INET)
 				return skb->len;
 
 			NL_SET_ERR_MSG(cb->extack, "ipv4: FIB table does not exist");
 			return -ENOENT;
 		}
 
+		rcu_read_lock();
 		err = fib_table_dump(tb, skb, cb, &filter);
+		rcu_read_unlock();
 		return skb->len ? : err;
 	}
 
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index cf0d6666c8dd..332b9c481fa4 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1008,7 +1008,7 @@ static int fib_check_nh_v4_gw(struct net *net, struct fib_nh *nh, u32 table,
 		if (fl4.flowi4_scope < RT_SCOPE_LINK)
 			fl4.flowi4_scope = RT_SCOPE_LINK;
 
-		if (table)
+		if (table && table != RT_TABLE_MAIN)
 			tbl = fib_get_table(net, table);
 
 		if (tbl)
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 868c74771fa9..4c6f04b6afba 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1738,7 +1738,7 @@ struct fib_table *fib_trie_unmerge(struct fib_table *oldtb)
 	while ((l = leaf_walk_rcu(&tp, key)) != NULL) {
 		struct key_vector *local_l = NULL, *local_tp;
 
-		hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) {
+		hlist_for_each_entry(fa, &l->leaf, fa_list) {
 			struct fib_alias *new_fa;
 
 			if (local_tb->tb_id != fa->tb_id)
@@ -2067,6 +2067,12 @@ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb,
 	int count = cb->args[2];
 	t_key key = cb->args[3];
 
+	/* First time here, count and key are both always 0. Count > 0
+	 * and key == 0 means the dump has wrapped around and we are done.
+	 */
+	if (count && !key)
+		return skb->len;
+
 	while ((l = leaf_walk_rcu(&tp, key)) != NULL) {
 		int err;
 
@@ -2341,6 +2347,7 @@ static int fib_triestat_seq_show(struct seq_file *seq, void *v)
 		   " %zd bytes, size of tnode: %zd bytes.\n",
 		   LEAF_SIZE, TNODE_SIZE(0));
 
+	rcu_read_lock();
 	for (h = 0; h < FIB_TABLE_HASHSZ; h++) {
 		struct hlist_head *head = &net->ipv4.fib_table_hash[h];
 		struct fib_table *tb;
@@ -2360,7 +2367,9 @@ static int fib_triestat_seq_show(struct seq_file *seq, void *v)
 			trie_show_usage(seq, t->stats);
 #endif
 		}
+		cond_resched_rcu();
 	}
+	rcu_read_unlock();
 
 	return 0;
 }
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 30fa771d382a..dcc79ff54b41 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -662,8 +662,8 @@ static const struct nla_policy fou_nl_policy[FOU_ATTR_MAX + 1] = {
 	[FOU_ATTR_REMCSUM_NOPARTIAL]	= { .type = NLA_FLAG, },
 	[FOU_ATTR_LOCAL_V4]		= { .type = NLA_U32, },
 	[FOU_ATTR_PEER_V4]		= { .type = NLA_U32, },
-	[FOU_ATTR_LOCAL_V6]		= { .type = sizeof(struct in6_addr), },
-	[FOU_ATTR_PEER_V6]		= { .type = sizeof(struct in6_addr), },
+	[FOU_ATTR_LOCAL_V6]		= { .len = sizeof(struct in6_addr), },
+	[FOU_ATTR_PEER_V6]		= { .len = sizeof(struct in6_addr), },
 	[FOU_ATTR_PEER_PORT]		= { .type = NLA_U16, },
 	[FOU_ATTR_IFINDEX]		= { .type = NLA_S32, },
 };
diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 2d9fd83a408f..7fd73e4258bf 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -56,7 +56,9 @@ int gre_del_protocol(const struct gre_protocol *proto, u8 version)
 }
 EXPORT_SYMBOL_GPL(gre_del_protocol);
 
-/* Fills in tpi and returns header length to be pulled. */
+/* Fills in tpi and returns header length to be pulled.
+ * Note that caller must use pskb_may_pull() before pulling GRE header.
+ */
 int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 		     bool *csum_err, __be16 proto, int nhs)
 {
@@ -110,8 +112,14 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 	 * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
 	 */
 	if (greh->flags == 0 && tpi->proto == htons(ETH_P_WCCP)) {
+		u8 _val, *val;
+
+		val = skb_header_pointer(skb, nhs + hdr_len,
+					 sizeof(_val), &_val);
+		if (!val)
+			return -EINVAL;
 		tpi->proto = proto;
-		if ((*(u8 *)options & 0xF0) != 0x40)
+		if ((*val & 0xF0) != 0x40)
 			hdr_len += 4;
 	}
 	tpi->hdr_len = hdr_len;
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 4de7e962d3da..c840141876bc 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -15,12 +15,12 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 				       netdev_features_t features)
 {
 	int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb);
+	bool need_csum, need_recompute_csum, gso_partial;
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	u16 mac_offset = skb->mac_header;
 	__be16 protocol = skb->protocol;
 	u16 mac_len = skb->mac_len;
 	int gre_offset, outer_hlen;
-	bool need_csum, gso_partial;
 
 	if (!skb->encapsulation)
 		goto out;
@@ -41,6 +41,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 	skb->protocol = skb->inner_protocol;
 
 	need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_GRE_CSUM);
+	need_recompute_csum = skb->csum_not_inet;
 	skb->encap_hdr_csum = need_csum;
 
 	features &= skb->dev->hw_enc_features;
@@ -98,7 +99,15 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 		}
 
 		*(pcsum + 1) = 0;
-		*pcsum = gso_make_checksum(skb, 0);
+		if (need_recompute_csum && !skb_is_gso(skb)) {
+			__wsum csum;
+
+			csum = skb_checksum(skb, gre_offset,
+					    skb->len - gre_offset, 0);
+			*pcsum = csum_fold(csum);
+		} else {
+			*pcsum = gso_make_checksum(skb, 0);
+		}
 	} while ((skb = skb->next));
 out:
 	return segs;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 2a16c83a866c..92b31d251da8 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -24,17 +24,19 @@
 #include <net/addrconf.h>
 
 #if IS_ENABLED(CONFIG_IPV6)
-/* match_wildcard == true:  IPV6_ADDR_ANY equals to any IPv6 addresses if IPv6
- *                          only, and any IPv4 addresses if not IPv6 only
- * match_wildcard == false: addresses must be exactly the same, i.e.
- *                          IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY,
- *                          and 0.0.0.0 equals to 0.0.0.0 only
+/* match_sk*_wildcard == true:  IPV6_ADDR_ANY equals to any IPv6 addresses
+ *				if IPv6 only, and any IPv4 addresses
+ *				if not IPv6 only
+ * match_sk*_wildcard == false: addresses must be exactly the same, i.e.
+ *				IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY,
+ *				and 0.0.0.0 equals to 0.0.0.0 only
  */
 static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
 				 const struct in6_addr *sk2_rcv_saddr6,
 				 __be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
 				 bool sk1_ipv6only, bool sk2_ipv6only,
-				 bool match_wildcard)
+				 bool match_sk1_wildcard,
+				 bool match_sk2_wildcard)
 {
 	int addr_type = ipv6_addr_type(sk1_rcv_saddr6);
 	int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED;
@@ -44,8 +46,8 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
 		if (!sk2_ipv6only) {
 			if (sk1_rcv_saddr == sk2_rcv_saddr)
 				return true;
-			if (!sk1_rcv_saddr || !sk2_rcv_saddr)
-				return match_wildcard;
+			return (match_sk1_wildcard && !sk1_rcv_saddr) ||
+				(match_sk2_wildcard && !sk2_rcv_saddr);
 		}
 		return false;
 	}
@@ -53,11 +55,11 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
 	if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY)
 		return true;
 
-	if (addr_type2 == IPV6_ADDR_ANY && match_wildcard &&
+	if (addr_type2 == IPV6_ADDR_ANY && match_sk2_wildcard &&
 	    !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED))
 		return true;
 
-	if (addr_type == IPV6_ADDR_ANY && match_wildcard &&
+	if (addr_type == IPV6_ADDR_ANY && match_sk1_wildcard &&
 	    !(sk1_ipv6only && addr_type2 == IPV6_ADDR_MAPPED))
 		return true;
 
@@ -69,18 +71,19 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
 }
 #endif
 
-/* match_wildcard == true:  0.0.0.0 equals to any IPv4 addresses
- * match_wildcard == false: addresses must be exactly the same, i.e.
- *                          0.0.0.0 only equals to 0.0.0.0
+/* match_sk*_wildcard == true:  0.0.0.0 equals to any IPv4 addresses
+ * match_sk*_wildcard == false: addresses must be exactly the same, i.e.
+ *				0.0.0.0 only equals to 0.0.0.0
  */
 static bool ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
-				 bool sk2_ipv6only, bool match_wildcard)
+				 bool sk2_ipv6only, bool match_sk1_wildcard,
+				 bool match_sk2_wildcard)
 {
 	if (!sk2_ipv6only) {
 		if (sk1_rcv_saddr == sk2_rcv_saddr)
 			return true;
-		if (!sk1_rcv_saddr || !sk2_rcv_saddr)
-			return match_wildcard;
+		return (match_sk1_wildcard && !sk1_rcv_saddr) ||
+			(match_sk2_wildcard && !sk2_rcv_saddr);
 	}
 	return false;
 }
@@ -96,10 +99,12 @@ bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
 					    sk2->sk_rcv_saddr,
 					    ipv6_only_sock(sk),
 					    ipv6_only_sock(sk2),
+					    match_wildcard,
 					    match_wildcard);
 #endif
 	return ipv4_rcv_saddr_equal(sk->sk_rcv_saddr, sk2->sk_rcv_saddr,
-				    ipv6_only_sock(sk2), match_wildcard);
+				    ipv6_only_sock(sk2), match_wildcard,
+				    match_wildcard);
 }
 EXPORT_SYMBOL(inet_rcv_saddr_equal);
 
@@ -273,10 +278,61 @@ static inline int sk_reuseport_match(struct inet_bind_bucket *tb,
 					    tb->fast_rcv_saddr,
 					    sk->sk_rcv_saddr,
 					    tb->fast_ipv6_only,
-					    ipv6_only_sock(sk), true);
+					    ipv6_only_sock(sk), true, false);
 #endif
 	return ipv4_rcv_saddr_equal(tb->fast_rcv_saddr, sk->sk_rcv_saddr,
-				    ipv6_only_sock(sk), true);
+				    ipv6_only_sock(sk), true, false);
+}
+
+void inet_csk_update_fastreuse(struct inet_bind_bucket *tb,
+			       struct sock *sk)
+{
+	kuid_t uid = sock_i_uid(sk);
+	bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN;
+
+	if (hlist_empty(&tb->owners)) {
+		tb->fastreuse = reuse;
+		if (sk->sk_reuseport) {
+			tb->fastreuseport = FASTREUSEPORT_ANY;
+			tb->fastuid = uid;
+			tb->fast_rcv_saddr = sk->sk_rcv_saddr;
+			tb->fast_ipv6_only = ipv6_only_sock(sk);
+			tb->fast_sk_family = sk->sk_family;
+#if IS_ENABLED(CONFIG_IPV6)
+			tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
+#endif
+		} else {
+			tb->fastreuseport = 0;
+		}
+	} else {
+		if (!reuse)
+			tb->fastreuse = 0;
+		if (sk->sk_reuseport) {
+			/* We didn't match or we don't have fastreuseport set on
+			 * the tb, but we have sk_reuseport set on this socket
+			 * and we know that there are no bind conflicts with
+			 * this socket in this tb, so reset our tb's reuseport
+			 * settings so that any subsequent sockets that match
+			 * our current socket will be put on the fast path.
+			 *
+			 * If we reset we need to set FASTREUSEPORT_STRICT so we
+			 * do extra checking for all subsequent sk_reuseport
+			 * socks.
+			 */
+			if (!sk_reuseport_match(tb, sk)) {
+				tb->fastreuseport = FASTREUSEPORT_STRICT;
+				tb->fastuid = uid;
+				tb->fast_rcv_saddr = sk->sk_rcv_saddr;
+				tb->fast_ipv6_only = ipv6_only_sock(sk);
+				tb->fast_sk_family = sk->sk_family;
+#if IS_ENABLED(CONFIG_IPV6)
+				tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
+#endif
+			}
+		} else {
+			tb->fastreuseport = 0;
+		}
+	}
 }
 
 /* Obtain a reference to a local port for the given sock,
@@ -291,7 +347,6 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
 	struct inet_bind_hashbucket *head;
 	struct net *net = sock_net(sk);
 	struct inet_bind_bucket *tb = NULL;
-	kuid_t uid = sock_i_uid(sk);
 	int l3mdev;
 
 	l3mdev = inet_sk_bound_l3mdev(sk);
@@ -328,49 +383,8 @@ tb_found:
 			goto fail_unlock;
 	}
 success:
-	if (hlist_empty(&tb->owners)) {
-		tb->fastreuse = reuse;
-		if (sk->sk_reuseport) {
-			tb->fastreuseport = FASTREUSEPORT_ANY;
-			tb->fastuid = uid;
-			tb->fast_rcv_saddr = sk->sk_rcv_saddr;
-			tb->fast_ipv6_only = ipv6_only_sock(sk);
-			tb->fast_sk_family = sk->sk_family;
-#if IS_ENABLED(CONFIG_IPV6)
-			tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
-#endif
-		} else {
-			tb->fastreuseport = 0;
-		}
-	} else {
-		if (!reuse)
-			tb->fastreuse = 0;
-		if (sk->sk_reuseport) {
-			/* We didn't match or we don't have fastreuseport set on
-			 * the tb, but we have sk_reuseport set on this socket
-			 * and we know that there are no bind conflicts with
-			 * this socket in this tb, so reset our tb's reuseport
-			 * settings so that any subsequent sockets that match
-			 * our current socket will be put on the fast path.
-			 *
-			 * If we reset we need to set FASTREUSEPORT_STRICT so we
-			 * do extra checking for all subsequent sk_reuseport
-			 * socks.
-			 */
-			if (!sk_reuseport_match(tb, sk)) {
-				tb->fastreuseport = FASTREUSEPORT_STRICT;
-				tb->fastuid = uid;
-				tb->fast_rcv_saddr = sk->sk_rcv_saddr;
-				tb->fast_ipv6_only = ipv6_only_sock(sk);
-				tb->fast_sk_family = sk->sk_family;
-#if IS_ENABLED(CONFIG_IPV6)
-				tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
-#endif
-			}
-		} else {
-			tb->fastreuseport = 0;
-		}
-	}
+	inet_csk_update_fastreuse(tb, sk);
+
 	if (!inet_csk(sk)->icsk_bind_hash)
 		inet_bind_hash(sk, tb, port);
 	WARN_ON(inet_csk(sk)->icsk_bind_hash != tb);
@@ -482,8 +496,28 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
 		}
 		spin_unlock_bh(&queue->fastopenq.lock);
 	}
+
 out:
 	release_sock(sk);
+	if (newsk && mem_cgroup_sockets_enabled) {
+		int amt;
+
+		/* atomically get the memory usage, set and charge the
+		 * newsk->sk_memcg.
+		 */
+		lock_sock(newsk);
+
+		/* The socket has not been accepted yet, no need to look at
+		 * newsk->sk_wmem_queued.
+		 */
+		amt = sk_mem_pages(newsk->sk_forward_alloc +
+				   atomic_read(&newsk->sk_rmem_alloc));
+		mem_cgroup_sk_alloc(newsk);
+		if (newsk->sk_memcg && amt)
+			mem_cgroup_charge_skmem(newsk->sk_memcg, amt);
+
+		release_sock(newsk);
+	}
 	if (req)
 		reqsk_put(req);
 	return newsk;
@@ -907,7 +941,7 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req,
 	percpu_counter_inc(sk->sk_prot->orphan_count);
 
 	if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) {
-		BUG_ON(tcp_sk(child)->fastopen_rsk != req);
+		BUG_ON(rcu_access_pointer(tcp_sk(child)->fastopen_rsk) != req);
 		BUG_ON(sk != req->rsk_listener);
 
 		/* Paranoid, to prevent race condition if
@@ -916,7 +950,7 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req,
 		 * Also to satisfy an assertion in
 		 * tcp_v4_destroy_sock().
 		 */
-		tcp_sk(child)->fastopen_rsk = NULL;
+		RCU_INIT_POINTER(tcp_sk(child)->fastopen_rsk, NULL);
 	}
 	inet_csk_destroy_sock(child);
 }
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 96182ef71417..5b68bdaa8bff 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -100,13 +100,9 @@ static size_t inet_sk_attr_size(struct sock *sk,
 		aux = handler->idiag_get_aux_size(sk, net_admin);
 
 	return	  nla_total_size(sizeof(struct tcp_info))
-		+ nla_total_size(1) /* INET_DIAG_SHUTDOWN */
-		+ nla_total_size(1) /* INET_DIAG_TOS */
-		+ nla_total_size(1) /* INET_DIAG_TCLASS */
-		+ nla_total_size(4) /* INET_DIAG_MARK */
-		+ nla_total_size(4) /* INET_DIAG_CLASS_ID */
-		+ nla_total_size(sizeof(struct inet_diag_meminfo))
 		+ nla_total_size(sizeof(struct inet_diag_msg))
+		+ inet_diag_msg_attrs_size()
+		+ nla_total_size(sizeof(struct inet_diag_meminfo))
 		+ nla_total_size(SK_MEMINFO_VARS * sizeof(u32))
 		+ nla_total_size(TCP_CA_NAME_MAX)
 		+ nla_total_size(sizeof(struct tcpvegas_info))
@@ -147,6 +143,24 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 	if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, sk->sk_mark))
 		goto errout;
 
+	if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) ||
+	    ext & (1 << (INET_DIAG_TCLASS - 1))) {
+		u32 classid = 0;
+
+#ifdef CONFIG_SOCK_CGROUP_DATA
+		classid = sock_cgroup_classid(&sk->sk_cgrp_data);
+#endif
+		/* Fallback to socket priority if class id isn't set.
+		 * Classful qdiscs use it as direct reference to class.
+		 * For cgroup2 classid is always zero.
+		 */
+		if (!classid)
+			classid = sk->sk_priority;
+
+		if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid))
+			goto errout;
+	}
+
 	r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk));
 	r->idiag_inode = sock_i_ino(sk);
 
@@ -193,7 +207,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 	if (ext & (1 << (INET_DIAG_MEMINFO - 1))) {
 		struct inet_diag_meminfo minfo = {
 			.idiag_rmem = sk_rmem_alloc_get(sk),
-			.idiag_wmem = sk->sk_wmem_queued,
+			.idiag_wmem = READ_ONCE(sk->sk_wmem_queued),
 			.idiag_fmem = sk->sk_forward_alloc,
 			.idiag_tmem = sk_wmem_alloc_get(sk),
 		};
@@ -284,24 +298,6 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 			goto errout;
 	}
 
-	if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) ||
-	    ext & (1 << (INET_DIAG_TCLASS - 1))) {
-		u32 classid = 0;
-
-#ifdef CONFIG_SOCK_CGROUP_DATA
-		classid = sock_cgroup_classid(&sk->sk_cgrp_data);
-#endif
-		/* Fallback to socket priority if class id isn't set.
-		 * Classful qdiscs use it as direct reference to class.
-		 * For cgroup2 classid is always zero.
-		 */
-		if (!classid)
-			classid = sk->sk_priority;
-
-		if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid))
-			goto errout;
-	}
-
 out:
 	nlmsg_end(skb, nlh);
 	return 0;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 9a02663f1ef6..7a4e50f060ae 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -163,6 +163,7 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child)
 				return -ENOMEM;
 			}
 		}
+		inet_csk_update_fastreuse(tb, child);
 	}
 	inet_bind_hash(child, tb, port);
 	spin_unlock(&head->lock);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 10636fb6093e..85ba1453ba5c 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1149,6 +1149,24 @@ static int ipgre_netlink_parms(struct net_device *dev,
 	if (data[IFLA_GRE_FWMARK])
 		*fwmark = nla_get_u32(data[IFLA_GRE_FWMARK]);
 
+	return 0;
+}
+
+static int erspan_netlink_parms(struct net_device *dev,
+				struct nlattr *data[],
+				struct nlattr *tb[],
+				struct ip_tunnel_parm *parms,
+				__u32 *fwmark)
+{
+	struct ip_tunnel *t = netdev_priv(dev);
+	int err;
+
+	err = ipgre_netlink_parms(dev, data, tb, parms, fwmark);
+	if (err)
+		return err;
+	if (!data)
+		return 0;
+
 	if (data[IFLA_GRE_ERSPAN_VER]) {
 		t->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]);
 
@@ -1272,45 +1290,70 @@ static void ipgre_tap_setup(struct net_device *dev)
 	ip_tunnel_setup(dev, gre_tap_net_id);
 }
 
-static int ipgre_newlink(struct net *src_net, struct net_device *dev,
-			 struct nlattr *tb[], struct nlattr *data[],
-			 struct netlink_ext_ack *extack)
+static int
+ipgre_newlink_encap_setup(struct net_device *dev, struct nlattr *data[])
 {
-	struct ip_tunnel_parm p;
 	struct ip_tunnel_encap ipencap;
-	__u32 fwmark = 0;
-	int err;
 
 	if (ipgre_netlink_encap_parms(data, &ipencap)) {
 		struct ip_tunnel *t = netdev_priv(dev);
-		err = ip_tunnel_encap_setup(t, &ipencap);
+		int err = ip_tunnel_encap_setup(t, &ipencap);
 
 		if (err < 0)
 			return err;
 	}
 
+	return 0;
+}
+
+static int ipgre_newlink(struct net *src_net, struct net_device *dev,
+			 struct nlattr *tb[], struct nlattr *data[],
+			 struct netlink_ext_ack *extack)
+{
+	struct ip_tunnel_parm p;
+	__u32 fwmark = 0;
+	int err;
+
+	err = ipgre_newlink_encap_setup(dev, data);
+	if (err)
+		return err;
+
 	err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark);
 	if (err < 0)
 		return err;
 	return ip_tunnel_newlink(dev, tb, &p, fwmark);
 }
 
+static int erspan_newlink(struct net *src_net, struct net_device *dev,
+			  struct nlattr *tb[], struct nlattr *data[],
+			  struct netlink_ext_ack *extack)
+{
+	struct ip_tunnel_parm p;
+	__u32 fwmark = 0;
+	int err;
+
+	err = ipgre_newlink_encap_setup(dev, data);
+	if (err)
+		return err;
+
+	err = erspan_netlink_parms(dev, data, tb, &p, &fwmark);
+	if (err)
+		return err;
+	return ip_tunnel_newlink(dev, tb, &p, fwmark);
+}
+
 static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
 			    struct nlattr *data[],
 			    struct netlink_ext_ack *extack)
 {
 	struct ip_tunnel *t = netdev_priv(dev);
-	struct ip_tunnel_encap ipencap;
 	__u32 fwmark = t->fwmark;
 	struct ip_tunnel_parm p;
 	int err;
 
-	if (ipgre_netlink_encap_parms(data, &ipencap)) {
-		err = ip_tunnel_encap_setup(t, &ipencap);
-
-		if (err < 0)
-			return err;
-	}
+	err = ipgre_newlink_encap_setup(dev, data);
+	if (err)
+		return err;
 
 	err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark);
 	if (err < 0)
@@ -1323,8 +1366,34 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
 	t->parms.i_flags = p.i_flags;
 	t->parms.o_flags = p.o_flags;
 
-	if (strcmp(dev->rtnl_link_ops->kind, "erspan"))
-		ipgre_link_update(dev, !tb[IFLA_MTU]);
+	ipgre_link_update(dev, !tb[IFLA_MTU]);
+
+	return 0;
+}
+
+static int erspan_changelink(struct net_device *dev, struct nlattr *tb[],
+			     struct nlattr *data[],
+			     struct netlink_ext_ack *extack)
+{
+	struct ip_tunnel *t = netdev_priv(dev);
+	__u32 fwmark = t->fwmark;
+	struct ip_tunnel_parm p;
+	int err;
+
+	err = ipgre_newlink_encap_setup(dev, data);
+	if (err)
+		return err;
+
+	err = erspan_netlink_parms(dev, data, tb, &p, &fwmark);
+	if (err < 0)
+		return err;
+
+	err = ip_tunnel_changelink(dev, tb, &p, fwmark);
+	if (err < 0)
+		return err;
+
+	t->parms.i_flags = p.i_flags;
+	t->parms.o_flags = p.o_flags;
 
 	return 0;
 }
@@ -1515,8 +1584,8 @@ static struct rtnl_link_ops erspan_link_ops __read_mostly = {
 	.priv_size	= sizeof(struct ip_tunnel),
 	.setup		= erspan_setup,
 	.validate	= erspan_validate,
-	.newlink	= ipgre_newlink,
-	.changelink	= ipgre_changelink,
+	.newlink	= erspan_newlink,
+	.changelink	= erspan_changelink,
 	.dellink	= ip_tunnel_dellink,
 	.get_size	= ipgre_get_size,
 	.fill_info	= ipgre_fill_info,
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 0fe2a5d3e258..a0b4dc54f8a6 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -85,9 +85,10 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 				   __be32 remote, __be32 local,
 				   __be32 key)
 {
-	unsigned int hash;
 	struct ip_tunnel *t, *cand = NULL;
 	struct hlist_head *head;
+	struct net_device *ndev;
+	unsigned int hash;
 
 	hash = ip_tunnel_hash(key, remote);
 	head = &itn->tunnels[hash];
@@ -142,11 +143,8 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 			cand = t;
 	}
 
-	if (flags & TUNNEL_NO_KEY)
-		goto skip_key_lookup;
-
 	hlist_for_each_entry_rcu(t, head, hash_node) {
-		if (t->parms.i_key != key ||
+		if ((!(flags & TUNNEL_NO_KEY) && t->parms.i_key != key) ||
 		    t->parms.iph.saddr != 0 ||
 		    t->parms.iph.daddr != 0 ||
 		    !(t->dev->flags & IFF_UP))
@@ -158,7 +156,6 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 			cand = t;
 	}
 
-skip_key_lookup:
 	if (cand)
 		return cand;
 
@@ -166,8 +163,9 @@ skip_key_lookup:
 	if (t && t->dev->flags & IFF_UP)
 		return t;
 
-	if (itn->fb_tunnel_dev && itn->fb_tunnel_dev->flags & IFF_UP)
-		return netdev_priv(itn->fb_tunnel_dev);
+	ndev = READ_ONCE(itn->fb_tunnel_dev);
+	if (ndev && ndev->flags & IFF_UP)
+		return netdev_priv(ndev);
 
 	return NULL;
 }
@@ -1236,10 +1234,8 @@ int ip_tunnel_init(struct net_device *dev)
 	iph->version		= 4;
 	iph->ihl		= 5;
 
-	if (tunnel->collect_md) {
-		dev->features |= NETIF_F_NETNS_LOCAL;
+	if (tunnel->collect_md)
 		netif_keep_dst(dev);
-	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_init);
@@ -1251,9 +1247,9 @@ void ip_tunnel_uninit(struct net_device *dev)
 	struct ip_tunnel_net *itn;
 
 	itn = net_generic(net, tunnel->ip_tnl_net_id);
-	/* fb_tunnel_dev will be unregisted in net-exit call. */
-	if (itn->fb_tunnel_dev != dev)
-		ip_tunnel_del(itn, netdev_priv(dev));
+	ip_tunnel_del(itn, netdev_priv(dev));
+	if (itn->fb_tunnel_dev == dev)
+		WRITE_ONCE(itn->fb_tunnel_dev, NULL);
 
 	dst_cache_reset(&tunnel->dst_cache);
 }
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index fb9f6d60c27c..bd41354ed8c1 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -93,7 +93,28 @@ static int vti_rcv_proto(struct sk_buff *skb)
 
 static int vti_rcv_tunnel(struct sk_buff *skb)
 {
-	return vti_rcv(skb, ip_hdr(skb)->saddr, true);
+	struct ip_tunnel_net *itn = net_generic(dev_net(skb->dev), vti_net_id);
+	const struct iphdr *iph = ip_hdr(skb);
+	struct ip_tunnel *tunnel;
+
+	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
+				  iph->saddr, iph->daddr, 0);
+	if (tunnel) {
+		struct tnl_ptk_info tpi = {
+			.proto = htons(ETH_P_IP),
+		};
+
+		if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+			goto drop;
+		if (iptunnel_pull_header(skb, 0, tpi.proto, false))
+			goto drop;
+		return ip_tunnel_rcv(tunnel, skb, &tpi, NULL, false);
+	}
+
+	return -EINVAL;
+drop:
+	kfree_skb(skb);
+	return 0;
 }
 
 static int vti_rcv_cb(struct sk_buff *skb, int err)
@@ -187,8 +208,39 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
 	int mtu;
 
 	if (!dst) {
-		dev->stats.tx_carrier_errors++;
-		goto tx_error_icmp;
+		switch (skb->protocol) {
+		case htons(ETH_P_IP): {
+			struct rtable *rt;
+
+			fl->u.ip4.flowi4_oif = dev->ifindex;
+			fl->u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC;
+			rt = __ip_route_output_key(dev_net(dev), &fl->u.ip4);
+			if (IS_ERR(rt)) {
+				dev->stats.tx_carrier_errors++;
+				goto tx_error_icmp;
+			}
+			dst = &rt->dst;
+			skb_dst_set(skb, dst);
+			break;
+		}
+#if IS_ENABLED(CONFIG_IPV6)
+		case htons(ETH_P_IPV6):
+			fl->u.ip6.flowi6_oif = dev->ifindex;
+			fl->u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC;
+			dst = ip6_route_output(dev_net(dev), NULL, &fl->u.ip6);
+			if (dst->error) {
+				dst_release(dst);
+				dst = NULL;
+				dev->stats.tx_carrier_errors++;
+				goto tx_error_icmp;
+			}
+			skb_dst_set(skb, dst);
+			break;
+#endif
+		default:
+			dev->stats.tx_carrier_errors++;
+			goto tx_error_icmp;
+		}
 	}
 
 	dst_hold(dst);
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 2f01cf6fa0de..678575adaf3b 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -698,7 +698,7 @@ out:
 
 rtnl_link_failed:
 #if IS_ENABLED(CONFIG_MPLS)
-	xfrm4_tunnel_deregister(&mplsip_handler, AF_INET);
+	xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS);
 xfrm_tunnel_mplsip_failed:
 
 #endif
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index f2daddf1afac..0fa250635b0c 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2609,7 +2609,7 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
 
 		mrt = ipmr_get_table(sock_net(skb->sk), filter.table_id);
 		if (!mrt) {
-			if (filter.dump_all_families)
+			if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IPMR)
 				return skb->len;
 
 			NL_SET_ERR_MSG(cb->extack, "ipv4: MR table does not exist");
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 214154b47d56..f1f78a742b36 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -384,10 +384,11 @@ next:		;
 	return 1;
 }
 
-static inline int check_target(struct arpt_entry *e, const char *name)
+static int check_target(struct arpt_entry *e, struct net *net, const char *name)
 {
 	struct xt_entry_target *t = arpt_get_target(e);
 	struct xt_tgchk_param par = {
+		.net       = net,
 		.table     = name,
 		.entryinfo = e,
 		.target    = t->u.kernel.target,
@@ -399,8 +400,9 @@ static inline int check_target(struct arpt_entry *e, const char *name)
 	return xt_check_target(&par, t->u.target_size - sizeof(*t), 0, false);
 }
 
-static inline int
-find_check_entry(struct arpt_entry *e, const char *name, unsigned int size,
+static int
+find_check_entry(struct arpt_entry *e, struct net *net, const char *name,
+		 unsigned int size,
 		 struct xt_percpu_counter_alloc_state *alloc_state)
 {
 	struct xt_entry_target *t;
@@ -419,7 +421,7 @@ find_check_entry(struct arpt_entry *e, const char *name, unsigned int size,
 	}
 	t->u.kernel.target = target;
 
-	ret = check_target(e, name);
+	ret = check_target(e, net, name);
 	if (ret)
 		goto err;
 	return 0;
@@ -494,12 +496,13 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
 	return 0;
 }
 
-static inline void cleanup_entry(struct arpt_entry *e)
+static void cleanup_entry(struct arpt_entry *e, struct net *net)
 {
 	struct xt_tgdtor_param par;
 	struct xt_entry_target *t;
 
 	t = arpt_get_target(e);
+	par.net      = net;
 	par.target   = t->u.kernel.target;
 	par.targinfo = t->data;
 	par.family   = NFPROTO_ARP;
@@ -512,7 +515,9 @@ static inline void cleanup_entry(struct arpt_entry *e)
 /* Checks and translates the user-supplied table segment (held in
  * newinfo).
  */
-static int translate_table(struct xt_table_info *newinfo, void *entry0,
+static int translate_table(struct net *net,
+			   struct xt_table_info *newinfo,
+			   void *entry0,
 			   const struct arpt_replace *repl)
 {
 	struct xt_percpu_counter_alloc_state alloc_state = { 0 };
@@ -569,7 +574,7 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
 	/* Finally, each sanity check must pass */
 	i = 0;
 	xt_entry_foreach(iter, entry0, newinfo->size) {
-		ret = find_check_entry(iter, repl->name, repl->size,
+		ret = find_check_entry(iter, net, repl->name, repl->size,
 				       &alloc_state);
 		if (ret != 0)
 			break;
@@ -580,7 +585,7 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
 		xt_entry_foreach(iter, entry0, newinfo->size) {
 			if (i-- == 0)
 				break;
-			cleanup_entry(iter);
+			cleanup_entry(iter, net);
 		}
 		return ret;
 	}
@@ -923,7 +928,7 @@ static int __do_replace(struct net *net, const char *name,
 	/* Decrease module usage counts and free resource */
 	loc_cpu_old_entry = oldinfo->entries;
 	xt_entry_foreach(iter, loc_cpu_old_entry, oldinfo->size)
-		cleanup_entry(iter);
+		cleanup_entry(iter, net);
 
 	xt_free_table_info(oldinfo);
 	if (copy_to_user(counters_ptr, counters,
@@ -974,7 +979,7 @@ static int do_replace(struct net *net, const void __user *user,
 		goto free_newinfo;
 	}
 
-	ret = translate_table(newinfo, loc_cpu_entry, &tmp);
+	ret = translate_table(net, newinfo, loc_cpu_entry, &tmp);
 	if (ret != 0)
 		goto free_newinfo;
 
@@ -986,7 +991,7 @@ static int do_replace(struct net *net, const void __user *user,
 
  free_newinfo_untrans:
 	xt_entry_foreach(iter, loc_cpu_entry, newinfo->size)
-		cleanup_entry(iter);
+		cleanup_entry(iter, net);
  free_newinfo:
 	xt_free_table_info(newinfo);
 	return ret;
@@ -1149,7 +1154,8 @@ compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr,
 	}
 }
 
-static int translate_compat_table(struct xt_table_info **pinfo,
+static int translate_compat_table(struct net *net,
+				  struct xt_table_info **pinfo,
 				  void **pentry0,
 				  const struct compat_arpt_replace *compatr)
 {
@@ -1217,7 +1223,7 @@ static int translate_compat_table(struct xt_table_info **pinfo,
 	repl.num_counters = 0;
 	repl.counters = NULL;
 	repl.size = newinfo->size;
-	ret = translate_table(newinfo, entry1, &repl);
+	ret = translate_table(net, newinfo, entry1, &repl);
 	if (ret)
 		goto free_newinfo;
 
@@ -1270,7 +1276,7 @@ static int compat_do_replace(struct net *net, void __user *user,
 		goto free_newinfo;
 	}
 
-	ret = translate_compat_table(&newinfo, &loc_cpu_entry, &tmp);
+	ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp);
 	if (ret != 0)
 		goto free_newinfo;
 
@@ -1282,7 +1288,7 @@ static int compat_do_replace(struct net *net, void __user *user,
 
  free_newinfo_untrans:
 	xt_entry_foreach(iter, loc_cpu_entry, newinfo->size)
-		cleanup_entry(iter);
+		cleanup_entry(iter, net);
  free_newinfo:
 	xt_free_table_info(newinfo);
 	return ret;
@@ -1509,7 +1515,7 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len
 	return ret;
 }
 
-static void __arpt_unregister_table(struct xt_table *table)
+static void __arpt_unregister_table(struct net *net, struct xt_table *table)
 {
 	struct xt_table_info *private;
 	void *loc_cpu_entry;
@@ -1521,7 +1527,7 @@ static void __arpt_unregister_table(struct xt_table *table)
 	/* Decrease module usage counts and free resources */
 	loc_cpu_entry = private->entries;
 	xt_entry_foreach(iter, loc_cpu_entry, private->size)
-		cleanup_entry(iter);
+		cleanup_entry(iter, net);
 	if (private->number > private->initial_entries)
 		module_put(table_owner);
 	xt_free_table_info(private);
@@ -1546,7 +1552,7 @@ int arpt_register_table(struct net *net,
 	loc_cpu_entry = newinfo->entries;
 	memcpy(loc_cpu_entry, repl->entries, repl->size);
 
-	ret = translate_table(newinfo, loc_cpu_entry, repl);
+	ret = translate_table(net, newinfo, loc_cpu_entry, repl);
 	if (ret != 0)
 		goto out_free;
 
@@ -1561,7 +1567,7 @@ int arpt_register_table(struct net *net,
 
 	ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks));
 	if (ret != 0) {
-		__arpt_unregister_table(new_table);
+		__arpt_unregister_table(net, new_table);
 		*res = NULL;
 	}
 
@@ -1576,7 +1582,7 @@ void arpt_unregister_table(struct net *net, struct xt_table *table,
 			   const struct nf_hook_ops *ops)
 {
 	nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
-	__arpt_unregister_table(table);
+	__arpt_unregister_table(net, table);
 }
 
 /* The built-in targets: standard (NULL) and error. */
diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c
index b2aeb7bf5dac..2a1e10f4ae93 100644
--- a/net/ipv4/netfilter/nf_nat_pptp.c
+++ b/net/ipv4/netfilter/nf_nat_pptp.c
@@ -166,8 +166,7 @@ pptp_outbound_pkt(struct sk_buff *skb,
 		break;
 	default:
 		pr_debug("unknown outbound packet 0x%04x:%s\n", msg,
-			 msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] :
-					       pptp_msg_name[0]);
+			 pptp_msg_name(msg));
 		/* fall through */
 	case PPTP_SET_LINK_INFO:
 		/* only need to NAT in case PAC is behind NAT box */
@@ -268,9 +267,7 @@ pptp_inbound_pkt(struct sk_buff *skb,
 		pcid_off = offsetof(union pptp_ctrl_union, setlink.peersCallID);
 		break;
 	default:
-		pr_debug("unknown inbound packet %s\n",
-			 msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] :
-					       pptp_msg_name[0]);
+		pr_debug("unknown inbound packet %s\n", pptp_msg_name(msg));
 		/* fall through */
 	case PPTP_START_SESSION_REQUEST:
 	case PPTP_START_SESSION_REPLY:
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 9d24ef5c5d8f..ce723a526b73 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -786,6 +786,9 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 			   inet_sk_flowi_flags(sk), faddr, saddr, 0, 0,
 			   sk->sk_uid);
 
+	fl4.fl4_icmp_type = user_icmph.type;
+	fl4.fl4_icmp_code = user_icmph.code;
+
 	security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
 	rt = ip_route_output_flow(net, &fl4, sk);
 	if (IS_ERR(rt)) {
diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c
index e35736b99300..a93e7d1e1251 100644
--- a/net/ipv4/raw_diag.c
+++ b/net/ipv4/raw_diag.c
@@ -100,8 +100,9 @@ static int raw_diag_dump_one(struct sk_buff *in_skb,
 	if (IS_ERR(sk))
 		return PTR_ERR(sk);
 
-	rep = nlmsg_new(sizeof(struct inet_diag_msg) +
-			sizeof(struct inet_diag_meminfo) + 64,
+	rep = nlmsg_new(nla_total_size(sizeof(struct inet_diag_msg)) +
+			inet_diag_msg_attrs_size() +
+			nla_total_size(sizeof(struct inet_diag_meminfo)) + 64,
 			GFP_KERNEL);
 	if (!rep) {
 		sock_put(sk);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index edd352538d69..53615c5a8664 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -448,7 +448,7 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
 		n = ip_neigh_gw4(dev, pkey);
 	}
 
-	if (n && !refcount_inc_not_zero(&n->refcnt))
+	if (!IS_ERR(n) && !refcount_inc_not_zero(&n->refcnt))
 		n = NULL;
 
 	rcu_read_unlock_bh();
@@ -489,18 +489,16 @@ u32 ip_idents_reserve(u32 hash, int segs)
 	atomic_t *p_id = ip_idents + hash % IP_IDENTS_SZ;
 	u32 old = READ_ONCE(*p_tstamp);
 	u32 now = (u32)jiffies;
-	u32 new, delta = 0;
+	u32 delta = 0;
 
 	if (old != now && cmpxchg(p_tstamp, old, now) == old)
 		delta = prandom_u32_max(now - old);
 
-	/* Do not use atomic_add_return() as it makes UBSAN unhappy */
-	do {
-		old = (u32)atomic_read(p_id);
-		new = old + delta + segs;
-	} while (atomic_cmpxchg(p_id, old, new) != old);
-
-	return new - segs;
+	/* If UBSAN reports an error there, please make sure your compiler
+	 * supports -fno-strict-overflow before reporting it that was a bug
+	 * in UBSAN, and it has been fixed in GCC-8.
+	 */
+	return atomic_add_return(segs + delta, p_id) - segs;
 }
 EXPORT_SYMBOL(ip_idents_reserve);
 
@@ -913,7 +911,7 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 	/* Check for load limit; set rate_last to the latest sent
 	 * redirect.
 	 */
-	if (peer->rate_tokens == 0 ||
+	if (peer->n_redirects == 0 ||
 	    time_after(jiffies,
 		       (peer->rate_last +
 			(ip_rt_redirect_load << peer->n_redirects)))) {
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5abc277260b5..86ae03c1c54b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -450,8 +450,8 @@ void tcp_init_sock(struct sock *sk)
 
 	icsk->icsk_sync_mss = tcp_sync_mss;
 
-	sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1];
-	sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1];
+	WRITE_ONCE(sk->sk_sndbuf, sock_net(sk)->ipv4.sysctl_tcp_wmem[1]);
+	WRITE_ONCE(sk->sk_rcvbuf, sock_net(sk)->ipv4.sysctl_tcp_rmem[1]);
 
 	sk_sockets_allocated_inc(sk);
 	sk->sk_route_forced_caps = NETIF_F_GSO;
@@ -477,9 +477,17 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags)
 static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,
 					  int target, struct sock *sk)
 {
-	return (tp->rcv_nxt - tp->copied_seq >= target) ||
-		(sk->sk_prot->stream_memory_read ?
-		sk->sk_prot->stream_memory_read(sk) : false);
+	int avail = READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq);
+
+	if (avail > 0) {
+		if (avail >= target)
+			return true;
+		if (tcp_rmem_pressure(sk))
+			return true;
+	}
+	if (sk->sk_prot->stream_memory_read)
+		return sk->sk_prot->stream_memory_read(sk);
+	return false;
 }
 
 /*
@@ -543,10 +551,10 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 
 	/* Connected or passive Fast Open socket? */
 	if (state != TCP_SYN_SENT &&
-	    (state != TCP_SYN_RECV || tp->fastopen_rsk)) {
+	    (state != TCP_SYN_RECV || rcu_access_pointer(tp->fastopen_rsk))) {
 		int target = sock_rcvlowat(sk, 0, INT_MAX);
 
-		if (tp->urg_seq == tp->copied_seq &&
+		if (READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq) &&
 		    !sock_flag(sk, SOCK_URGINLINE) &&
 		    tp->urg_data)
 			target++;
@@ -607,7 +615,8 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 		unlock_sock_fast(sk, slow);
 		break;
 	case SIOCATMARK:
-		answ = tp->urg_data && tp->urg_seq == tp->copied_seq;
+		answ = tp->urg_data &&
+		       READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq);
 		break;
 	case SIOCOUTQ:
 		if (sk->sk_state == TCP_LISTEN)
@@ -616,7 +625,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 		if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
 			answ = 0;
 		else
-			answ = tp->write_seq - tp->snd_una;
+			answ = READ_ONCE(tp->write_seq) - tp->snd_una;
 		break;
 	case SIOCOUTQNSD:
 		if (sk->sk_state == TCP_LISTEN)
@@ -625,7 +634,8 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 		if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
 			answ = 0;
 		else
-			answ = tp->write_seq - tp->snd_nxt;
+			answ = READ_ONCE(tp->write_seq) -
+			       READ_ONCE(tp->snd_nxt);
 		break;
 	default:
 		return -ENOIOCTLCMD;
@@ -657,7 +667,7 @@ static void skb_entail(struct sock *sk, struct sk_buff *skb)
 	tcb->sacked  = 0;
 	__skb_header_release(skb);
 	tcp_add_write_queue_tail(sk, skb);
-	sk->sk_wmem_queued += skb->truesize;
+	sk_wmem_queued_add(sk, skb->truesize);
 	sk_mem_charge(sk, skb->truesize);
 	if (tp->nonagle & TCP_NAGLE_PUSH)
 		tp->nonagle &= ~TCP_NAGLE_PUSH;
@@ -1032,10 +1042,10 @@ new_segment:
 		skb->len += copy;
 		skb->data_len += copy;
 		skb->truesize += copy;
-		sk->sk_wmem_queued += copy;
+		sk_wmem_queued_add(sk, copy);
 		sk_mem_charge(sk, copy);
 		skb->ip_summed = CHECKSUM_PARTIAL;
-		tp->write_seq += copy;
+		WRITE_ONCE(tp->write_seq, tp->write_seq + copy);
 		TCP_SKB_CB(skb)->end_seq += copy;
 		tcp_skb_pcount_set(skb, 0);
 
@@ -1085,8 +1095,7 @@ do_error:
 		goto out;
 out_err:
 	/* make sure we wake any epoll edge trigger waiter */
-	if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 &&
-		     err == -EAGAIN)) {
+	if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) {
 		sk->sk_write_space(sk);
 		tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
 	}
@@ -1361,7 +1370,7 @@ new_segment:
 		if (!copied)
 			TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
 
-		tp->write_seq += copy;
+		WRITE_ONCE(tp->write_seq, tp->write_seq + copy);
 		TCP_SKB_CB(skb)->end_seq += copy;
 		tcp_skb_pcount_set(skb, 0);
 
@@ -1416,8 +1425,7 @@ out_err:
 	sock_zerocopy_put_abort(uarg, true);
 	err = sk_stream_error(sk, flags, err);
 	/* make sure we wake any epoll edge trigger waiter */
-	if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 &&
-		     err == -EAGAIN)) {
+	if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) {
 		sk->sk_write_space(sk);
 		tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
 	}
@@ -1667,9 +1675,9 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 		sk_eat_skb(sk, skb);
 		if (!desc->count)
 			break;
-		tp->copied_seq = seq;
+		WRITE_ONCE(tp->copied_seq, seq);
 	}
-	tp->copied_seq = seq;
+	WRITE_ONCE(tp->copied_seq, seq);
 
 	tcp_rcv_space_adjust(sk);
 
@@ -1708,7 +1716,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val)
 
 	val <<= 1;
 	if (val > sk->sk_rcvbuf) {
-		sk->sk_rcvbuf = val;
+		WRITE_ONCE(sk->sk_rcvbuf, val);
 		tcp_sk(sk)->window_clamp = tcp_win_from_space(sk, val);
 	}
 	return 0;
@@ -1756,10 +1764,11 @@ static int tcp_zerocopy_receive(struct sock *sk,
 
 	down_read(&current->mm->mmap_sem);
 
-	ret = -EINVAL;
 	vma = find_vma(current->mm, address);
-	if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops)
-		goto out;
+	if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops) {
+		up_read(&current->mm->mmap_sem);
+		return -EINVAL;
+	}
 	zc->length = min_t(unsigned long, zc->length, vma->vm_end - address);
 
 	tp = tcp_sk(sk);
@@ -1818,7 +1827,7 @@ static int tcp_zerocopy_receive(struct sock *sk,
 out:
 	up_read(&current->mm->mmap_sem);
 	if (length) {
-		tp->copied_seq = seq;
+		WRITE_ONCE(tp->copied_seq, seq);
 		tcp_rcv_space_adjust(sk);
 
 		/* Clean up data we have read: This will do ACK frames. */
@@ -1955,8 +1964,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 	struct sk_buff *skb, *last;
 	u32 urg_hole = 0;
 	struct scm_timestamping_internal tss;
-	bool has_tss = false;
-	bool has_cmsg;
+	int cmsg_flags;
 
 	if (unlikely(flags & MSG_ERRQUEUE))
 		return inet_recv_error(sk, msg, len, addr_len);
@@ -1971,7 +1979,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 	if (sk->sk_state == TCP_LISTEN)
 		goto out;
 
-	has_cmsg = tp->recvmsg_inq;
+	cmsg_flags = tp->recvmsg_inq ? 1 : 0;
 	timeo = sock_rcvtimeo(sk, nonblock);
 
 	/* Urgent data needs to be handled specially. */
@@ -2116,7 +2124,7 @@ found_ok_skb:
 			if (urg_offset < used) {
 				if (!urg_offset) {
 					if (!sock_flag(sk, SOCK_URGINLINE)) {
-						++*seq;
+						WRITE_ONCE(*seq, *seq + 1);
 						urg_hole++;
 						offset++;
 						used--;
@@ -2138,7 +2146,7 @@ found_ok_skb:
 			}
 		}
 
-		*seq += used;
+		WRITE_ONCE(*seq, *seq + used);
 		copied += used;
 		len -= used;
 
@@ -2149,14 +2157,15 @@ skip_copy:
 			tp->urg_data = 0;
 			tcp_fast_path_check(sk);
 		}
-		if (used + offset < skb->len)
-			continue;
 
 		if (TCP_SKB_CB(skb)->has_rxtstamp) {
 			tcp_update_recv_tstamps(skb, &tss);
-			has_tss = true;
-			has_cmsg = true;
+			cmsg_flags |= 2;
 		}
+
+		if (used + offset < skb->len)
+			continue;
+
 		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
 			goto found_fin_ok;
 		if (!(flags & MSG_PEEK))
@@ -2165,7 +2174,7 @@ skip_copy:
 
 found_fin_ok:
 		/* Process the FIN. */
-		++*seq;
+		WRITE_ONCE(*seq, *seq + 1);
 		if (!(flags & MSG_PEEK))
 			sk_eat_skb(sk, skb);
 		break;
@@ -2180,10 +2189,10 @@ found_fin_ok:
 
 	release_sock(sk);
 
-	if (has_cmsg) {
-		if (has_tss)
+	if (cmsg_flags) {
+		if (cmsg_flags & 2)
 			tcp_recv_timestamp(msg, sk, &tss);
-		if (tp->recvmsg_inq) {
+		if (cmsg_flags & 1) {
 			inq = tcp_inq_hint(sk);
 			put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq);
 		}
@@ -2486,7 +2495,10 @@ adjudge_to_death:
 	}
 
 	if (sk->sk_state == TCP_CLOSE) {
-		struct request_sock *req = tcp_sk(sk)->fastopen_rsk;
+		struct request_sock *req;
+
+		req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk,
+						lockdep_sock_is_held(sk));
 		/* We could get here with a non-NULL req if the socket is
 		 * aborted (e.g., closed with unread data) before 3WHS
 		 * finishes.
@@ -2559,6 +2571,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	int old_state = sk->sk_state;
+	u32 seq;
 
 	if (old_state != TCP_CLOSE)
 		tcp_set_state(sk, TCP_CLOSE);
@@ -2585,7 +2598,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 		__kfree_skb(sk->sk_rx_skb_cache);
 		sk->sk_rx_skb_cache = NULL;
 	}
-	tp->copied_seq = tp->rcv_nxt;
+	WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
 	tp->urg_data = 0;
 	tcp_write_queue_purge(sk);
 	tcp_fastopen_active_disable_ofo_check(sk);
@@ -2601,9 +2614,12 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->srtt_us = 0;
 	tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
 	tp->rcv_rtt_last_tsecr = 0;
-	tp->write_seq += tp->max_window + 2;
-	if (tp->write_seq == 0)
-		tp->write_seq = 1;
+
+	seq = tp->write_seq + tp->max_window + 2;
+	if (!seq)
+		seq = 1;
+	WRITE_ONCE(tp->write_seq, seq);
+
 	icsk->icsk_backoff = 0;
 	tp->snd_cwnd = 2;
 	icsk->icsk_probes_out = 0;
@@ -2612,10 +2628,15 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->snd_cwnd = TCP_INIT_CWND;
 	tp->snd_cwnd_cnt = 0;
 	tp->window_clamp = 0;
+	tp->delivered = 0;
 	tp->delivered_ce = 0;
+	if (icsk->icsk_ca_ops->release)
+		icsk->icsk_ca_ops->release(sk);
+	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 	tcp_set_ca_state(sk, TCP_CA_Open);
 	tp->is_sack_reneg = 0;
 	tcp_clear_retrans(tp);
+	tp->total_retrans = 0;
 	inet_csk_delack_init(sk);
 	/* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0
 	 * issue in __tcp_select_window()
@@ -2627,10 +2648,14 @@ int tcp_disconnect(struct sock *sk, int flags)
 	sk->sk_rx_dst = NULL;
 	tcp_saved_syn_free(tp);
 	tp->compressed_ack = 0;
+	tp->segs_in = 0;
+	tp->segs_out = 0;
 	tp->bytes_sent = 0;
 	tp->bytes_acked = 0;
 	tp->bytes_received = 0;
 	tp->bytes_retrans = 0;
+	tp->data_segs_in = 0;
+	tp->data_segs_out = 0;
 	tp->duplicate_sack[0].start_seq = 0;
 	tp->duplicate_sack[0].end_seq = 0;
 	tp->dsack_dups = 0;
@@ -2906,9 +2931,11 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		if (sk->sk_state != TCP_CLOSE)
 			err = -EPERM;
 		else if (tp->repair_queue == TCP_SEND_QUEUE)
-			tp->write_seq = val;
-		else if (tp->repair_queue == TCP_RECV_QUEUE)
-			tp->rcv_nxt = val;
+			WRITE_ONCE(tp->write_seq, val);
+		else if (tp->repair_queue == TCP_RECV_QUEUE) {
+			WRITE_ONCE(tp->rcv_nxt, val);
+			WRITE_ONCE(tp->copied_seq, val);
+		}
 		else
 			err = -EINVAL;
 		break;
@@ -3036,10 +3063,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 #ifdef CONFIG_TCP_MD5SIG
 	case TCP_MD5SIG:
 	case TCP_MD5SIG_EXT:
-		if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))
-			err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
-		else
-			err = -EINVAL;
+		err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
 		break;
 #endif
 	case TCP_USER_TIMEOUT:
@@ -3782,10 +3806,13 @@ EXPORT_SYMBOL(tcp_md5_hash_skb_data);
 
 int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key)
 {
+	u8 keylen = READ_ONCE(key->keylen); /* paired with WRITE_ONCE() in tcp_md5_do_add */
 	struct scatterlist sg;
 
-	sg_init_one(&sg, key->key, key->keylen);
-	ahash_request_set_crypt(hp->md5_req, &sg, NULL, key->keylen);
+	sg_init_one(&sg, key->key, keylen);
+	ahash_request_set_crypt(hp->md5_req, &sg, NULL, keylen);
+
+	/* tcp_md5_do_add() might change key->key under us */
 	return crypto_ahash_update(hp->md5_req);
 }
 EXPORT_SYMBOL(tcp_md5_hash_key);
@@ -3794,7 +3821,13 @@ EXPORT_SYMBOL(tcp_md5_hash_key);
 
 void tcp_done(struct sock *sk)
 {
-	struct request_sock *req = tcp_sk(sk)->fastopen_rsk;
+	struct request_sock *req;
+
+	/* We might be called with a new socket, after
+	 * inet_csk_prepare_forced_close() has been called
+	 * so we can not use lockdep_sock_is_held(sk)
+	 */
+	req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, 1);
 
 	if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV)
 		TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS);
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 00ade9c185ea..1c0d2815ec54 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -306,7 +306,8 @@ static u32 bbr_tso_segs_goal(struct sock *sk)
 	/* Sort of tcp_tso_autosize() but ignoring
 	 * driver provided sk_gso_max_size.
 	 */
-	bytes = min_t(unsigned long, sk->sk_pacing_rate >> sk->sk_pacing_shift,
+	bytes = min_t(unsigned long,
+		      sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift),
 		      GSO_MAX_SIZE - 1 - MAX_TCP_HEADER);
 	segs = max_t(u32, bytes / tp->mss_cache, bbr_min_tso_segs(sk));
 
@@ -776,8 +777,7 @@ static void bbr_update_bw(struct sock *sk, const struct rate_sample *rs)
 	 * bandwidth sample. Delivered is in packets and interval_us in uS and
 	 * ratio will be <<1 for most connections. So delivered is first scaled.
 	 */
-	bw = (u64)rs->delivered * BW_UNIT;
-	do_div(bw, rs->interval_us);
+	bw = div64_long((u64)rs->delivered * BW_UNIT, rs->interval_us);
 
 	/* If this sample is application-limited, it is likely to have a very
 	 * low delivered count that represents application behavior rather than
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index e38705165ac9..ad9f38202731 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -96,6 +96,9 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
 		} while (i != msg_rx->sg.end);
 
 		if (unlikely(peek)) {
+			if (msg_rx == list_last_entry(&psock->ingress_msg,
+						      struct sk_msg, list))
+				break;
 			msg_rx = list_next_entry(msg_rx, list);
 			continue;
 		}
@@ -123,12 +126,15 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 
 	if (unlikely(flags & MSG_ERRQUEUE))
 		return inet_recv_error(sk, msg, len, addr_len);
-	if (!skb_queue_empty(&sk->sk_receive_queue))
-		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 
 	psock = sk_psock_get(sk);
 	if (unlikely(!psock))
 		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+	if (!skb_queue_empty(&sk->sk_receive_queue) &&
+	    sk_psock_queue_empty(psock)) {
+		sk_psock_put(sk, psock);
+		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+	}
 	lock_sock(sk);
 msg_bytes_ready:
 	copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags);
@@ -139,7 +145,7 @@ msg_bytes_ready:
 		timeo = sock_rcvtimeo(sk, nonblock);
 		data = tcp_bpf_wait_data(sk, psock, flags, timeo, &err);
 		if (data) {
-			if (skb_queue_empty(&sk->sk_receive_queue))
+			if (!sk_psock_queue_empty(psock))
 				goto msg_bytes_ready;
 			release_sock(sk);
 			sk_psock_put(sk, psock);
@@ -200,7 +206,6 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock,
 
 	if (!ret) {
 		msg->sg.start = i;
-		msg->sg.size -= apply_bytes;
 		sk_psock_queue_msg(psock, tmp);
 		sk_psock_data_ready(sk, psock);
 	} else {
@@ -315,10 +320,7 @@ more_data:
 		 */
 		delta = msg->sg.size;
 		psock->eval = sk_psock_msg_verdict(sk, psock, msg);
-		if (msg->sg.size < delta)
-			delta -= msg->sg.size;
-		else
-			delta = 0;
+		delta -= msg->sg.size;
 	}
 
 	if (msg->cork_bytes &&
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index c445a81d144e..d7a1f2ef6c52 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -197,7 +197,7 @@ static void tcp_reinit_congestion_control(struct sock *sk,
 	icsk->icsk_ca_setsockopt = 1;
 	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 
-	if (sk->sk_state != TCP_CLOSE)
+	if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
 		tcp_init_congestion_control(sk);
 }
 
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 1b3d032a4df2..c7bf5b26bf0c 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -40,8 +40,8 @@
 
 /* Number of delay samples for detecting the increase of delay */
 #define HYSTART_MIN_SAMPLES	8
-#define HYSTART_DELAY_MIN	(4U<<3)
-#define HYSTART_DELAY_MAX	(16U<<3)
+#define HYSTART_DELAY_MIN	(4000U)	/* 4 ms */
+#define HYSTART_DELAY_MAX	(16000U)	/* 16 ms */
 #define HYSTART_DELAY_THRESH(x)	clamp(x, HYSTART_DELAY_MIN, HYSTART_DELAY_MAX)
 
 static int fast_convergence __read_mostly = 1;
@@ -53,7 +53,7 @@ static int tcp_friendliness __read_mostly = 1;
 static int hystart __read_mostly = 1;
 static int hystart_detect __read_mostly = HYSTART_ACK_TRAIN | HYSTART_DELAY;
 static int hystart_low_window __read_mostly = 16;
-static int hystart_ack_delta __read_mostly = 2;
+static int hystart_ack_delta_us __read_mostly = 2000;
 
 static u32 cube_rtt_scale __read_mostly;
 static u32 beta_scale __read_mostly;
@@ -77,8 +77,8 @@ MODULE_PARM_DESC(hystart_detect, "hybrid slow start detection mechanisms"
 		 " 1: packet-train 2: delay 3: both packet-train and delay");
 module_param(hystart_low_window, int, 0644);
 MODULE_PARM_DESC(hystart_low_window, "lower bound cwnd for hybrid slow start");
-module_param(hystart_ack_delta, int, 0644);
-MODULE_PARM_DESC(hystart_ack_delta, "spacing between ack's indicating train (msecs)");
+module_param(hystart_ack_delta_us, int, 0644);
+MODULE_PARM_DESC(hystart_ack_delta_us, "spacing between ack's indicating train (usecs)");
 
 /* BIC TCP Parameters */
 struct bictcp {
@@ -89,7 +89,7 @@ struct bictcp {
 	u32	bic_origin_point;/* origin point of bic function */
 	u32	bic_K;		/* time to origin point
 				   from the beginning of the current epoch */
-	u32	delay_min;	/* min delay (msec << 3) */
+	u32	delay_min;	/* min delay (usec) */
 	u32	epoch_start;	/* beginning of an epoch */
 	u32	ack_cnt;	/* number of acks */
 	u32	tcp_cwnd;	/* estimated tcp cwnd */
@@ -117,13 +117,9 @@ static inline void bictcp_reset(struct bictcp *ca)
 	ca->found = 0;
 }
 
-static inline u32 bictcp_clock(void)
+static inline u32 bictcp_clock_us(const struct sock *sk)
 {
-#if HZ < 1000
-	return ktime_to_ms(ktime_get_real());
-#else
-	return jiffies_to_msecs(jiffies);
-#endif
+	return tcp_sk(sk)->tcp_mstamp;
 }
 
 static inline void bictcp_hystart_reset(struct sock *sk)
@@ -131,9 +127,9 @@ static inline void bictcp_hystart_reset(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct bictcp *ca = inet_csk_ca(sk);
 
-	ca->round_start = ca->last_ack = bictcp_clock();
+	ca->round_start = ca->last_ack = bictcp_clock_us(sk);
 	ca->end_seq = tp->snd_nxt;
-	ca->curr_rtt = 0;
+	ca->curr_rtt = ~0U;
 	ca->sample_cnt = 0;
 }
 
@@ -276,7 +272,7 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd, u32 acked)
 	 */
 
 	t = (s32)(tcp_jiffies32 - ca->epoch_start);
-	t += msecs_to_jiffies(ca->delay_min >> 3);
+	t += usecs_to_jiffies(ca->delay_min);
 	/* change the unit from HZ to bictcp_HZ */
 	t <<= BICTCP_HZ;
 	do_div(t, HZ);
@@ -376,22 +372,54 @@ static void bictcp_state(struct sock *sk, u8 new_state)
 	}
 }
 
+/* Account for TSO/GRO delays.
+ * Otherwise short RTT flows could get too small ssthresh, since during
+ * slow start we begin with small TSO packets and ca->delay_min would
+ * not account for long aggregation delay when TSO packets get bigger.
+ * Ideally even with a very small RTT we would like to have at least one
+ * TSO packet being sent and received by GRO, and another one in qdisc layer.
+ * We apply another 100% factor because @rate is doubled at this point.
+ * We cap the cushion to 1ms.
+ */
+static u32 hystart_ack_delay(struct sock *sk)
+{
+	unsigned long rate;
+
+	rate = READ_ONCE(sk->sk_pacing_rate);
+	if (!rate)
+		return 0;
+	return min_t(u64, USEC_PER_MSEC,
+		     div64_ul((u64)GSO_MAX_SIZE * 4 * USEC_PER_SEC, rate));
+}
+
 static void hystart_update(struct sock *sk, u32 delay)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct bictcp *ca = inet_csk_ca(sk);
-
-	if (ca->found & hystart_detect)
-		return;
+	u32 threshold;
 
 	if (hystart_detect & HYSTART_ACK_TRAIN) {
-		u32 now = bictcp_clock();
+		u32 now = bictcp_clock_us(sk);
 
 		/* first detection parameter - ack-train detection */
-		if ((s32)(now - ca->last_ack) <= hystart_ack_delta) {
+		if ((s32)(now - ca->last_ack) <= hystart_ack_delta_us) {
 			ca->last_ack = now;
-			if ((s32)(now - ca->round_start) > ca->delay_min >> 4) {
-				ca->found |= HYSTART_ACK_TRAIN;
+
+			threshold = ca->delay_min + hystart_ack_delay(sk);
+
+			/* Hystart ack train triggers if we get ack past
+			 * ca->delay_min/2.
+			 * Pacing might have delayed packets up to RTT/2
+			 * during slow start.
+			 */
+			if (sk->sk_pacing_status == SK_PACING_NONE)
+				threshold >>= 1;
+
+			if ((s32)(now - ca->round_start) > threshold) {
+				ca->found = 1;
+				pr_debug("hystart_ack_train (%u > %u) delay_min %u (+ ack_delay %u) cwnd %u\n",
+					 now - ca->round_start, threshold,
+					 ca->delay_min, hystart_ack_delay(sk), tp->snd_cwnd);
 				NET_INC_STATS(sock_net(sk),
 					      LINUX_MIB_TCPHYSTARTTRAINDETECT);
 				NET_ADD_STATS(sock_net(sk),
@@ -404,15 +432,14 @@ static void hystart_update(struct sock *sk, u32 delay)
 
 	if (hystart_detect & HYSTART_DELAY) {
 		/* obtain the minimum delay of more than sampling packets */
+		if (ca->curr_rtt > delay)
+			ca->curr_rtt = delay;
 		if (ca->sample_cnt < HYSTART_MIN_SAMPLES) {
-			if (ca->curr_rtt == 0 || ca->curr_rtt > delay)
-				ca->curr_rtt = delay;
-
 			ca->sample_cnt++;
 		} else {
 			if (ca->curr_rtt > ca->delay_min +
 			    HYSTART_DELAY_THRESH(ca->delay_min >> 3)) {
-				ca->found |= HYSTART_DELAY;
+				ca->found = 1;
 				NET_INC_STATS(sock_net(sk),
 					      LINUX_MIB_TCPHYSTARTDELAYDETECT);
 				NET_ADD_STATS(sock_net(sk),
@@ -424,9 +451,6 @@ static void hystart_update(struct sock *sk, u32 delay)
 	}
 }
 
-/* Track delayed acknowledgment ratio using sliding window
- * ratio = (15*ratio + sample) / 16
- */
 static void bictcp_acked(struct sock *sk, const struct ack_sample *sample)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
@@ -441,7 +465,7 @@ static void bictcp_acked(struct sock *sk, const struct ack_sample *sample)
 	if (ca->epoch_start && (s32)(tcp_jiffies32 - ca->epoch_start) < HZ)
 		return;
 
-	delay = (sample->rtt_us << 3) / USEC_PER_MSEC;
+	delay = sample->rtt_us;
 	if (delay == 0)
 		delay = 1;
 
@@ -450,7 +474,7 @@ static void bictcp_acked(struct sock *sk, const struct ack_sample *sample)
 		ca->delay_min = delay;
 
 	/* hystart triggers when cwnd is larger than some threshold */
-	if (hystart && tcp_in_slow_start(tp) &&
+	if (!ca->found && tcp_in_slow_start(tp) && hystart &&
 	    tp->snd_cwnd >= hystart_low_window)
 		hystart_update(sk, delay);
 }
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index a3a386236d93..89b8de350b10 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -26,8 +26,9 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
 	} else if (sk->sk_type == SOCK_STREAM) {
 		const struct tcp_sock *tp = tcp_sk(sk);
 
-		r->idiag_rqueue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0);
-		r->idiag_wqueue = tp->write_seq - tp->snd_una;
+		r->idiag_rqueue = max_t(int, READ_ONCE(tp->rcv_nxt) -
+					     READ_ONCE(tp->copied_seq), 0);
+		r->idiag_wqueue = READ_ONCE(tp->write_seq) - tp->snd_una;
 	}
 	if (info)
 		tcp_get_info(sk, info);
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index f5a45e1e1182..35679b308615 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -236,7 +236,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
 	 */
 	tp = tcp_sk(child);
 
-	tp->fastopen_rsk = req;
+	rcu_assign_pointer(tp->fastopen_rsk, req);
 	tcp_rsk(req)->tfo_listener = true;
 
 	/* RFC1323: The window in SYN & SYN/ACK segments is never
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 6637b3484de6..755b44c7506a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -260,7 +260,8 @@ static void tcp_ecn_accept_cwr(struct sock *sk, const struct sk_buff *skb)
 		 * cwnd may be very low (even just 1 packet), so we should ACK
 		 * immediately.
 		 */
-		inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
+		if (TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq)
+			inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
 	}
 }
 
@@ -359,7 +360,8 @@ static void tcp_sndbuf_expand(struct sock *sk)
 	sndmem *= nr_segs * per_mss;
 
 	if (sk->sk_sndbuf < sndmem)
-		sk->sk_sndbuf = min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]);
+		WRITE_ONCE(sk->sk_sndbuf,
+			   min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]));
 }
 
 /* 2. Tuning advertised window (window_clamp, rcv_ssthresh)
@@ -483,8 +485,9 @@ static void tcp_clamp_window(struct sock *sk)
 	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
 	    !tcp_under_memory_pressure(sk) &&
 	    sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) {
-		sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc),
-				    net->ipv4.sysctl_tcp_rmem[2]);
+		WRITE_ONCE(sk->sk_rcvbuf,
+			   min(atomic_read(&sk->sk_rmem_alloc),
+			       net->ipv4.sysctl_tcp_rmem[2]));
 	}
 	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
 		tp->rcv_ssthresh = min(tp->window_clamp, 2U * tp->advmss);
@@ -648,7 +651,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
 		rcvbuf = min_t(u64, rcvwin * rcvmem,
 			       sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
 		if (rcvbuf > sk->sk_rcvbuf) {
-			sk->sk_rcvbuf = rcvbuf;
+			WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
 
 			/* Make the window clamp follow along.  */
 			tp->window_clamp = tcp_win_from_space(sk, rcvbuf);
@@ -909,9 +912,10 @@ static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq,
 /* This must be called before lost_out is incremented */
 static void tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb)
 {
-	if (!tp->retransmit_skb_hint ||
-	    before(TCP_SKB_CB(skb)->seq,
-		   TCP_SKB_CB(tp->retransmit_skb_hint)->seq))
+	if ((!tp->retransmit_skb_hint && tp->retrans_out >= tp->lost_out) ||
+	    (tp->retransmit_skb_hint &&
+	     before(TCP_SKB_CB(skb)->seq,
+		    TCP_SKB_CB(tp->retransmit_skb_hint)->seq)))
 		tp->retransmit_skb_hint = skb;
 }
 
@@ -1721,8 +1725,11 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
 		}
 
 		/* Ignore very old stuff early */
-		if (!after(sp[used_sacks].end_seq, prior_snd_una))
+		if (!after(sp[used_sacks].end_seq, prior_snd_una)) {
+			if (i == 0)
+				first_sack_index = -1;
 			continue;
+		}
 
 		used_sacks++;
 	}
@@ -2662,7 +2669,7 @@ static void tcp_process_loss(struct sock *sk, int flag, int num_dupack,
 	struct tcp_sock *tp = tcp_sk(sk);
 	bool recovered = !before(tp->snd_una, tp->high_seq);
 
-	if ((flag & FLAG_SND_UNA_ADVANCED || tp->fastopen_rsk) &&
+	if ((flag & FLAG_SND_UNA_ADVANCED || rcu_access_pointer(tp->fastopen_rsk)) &&
 	    tcp_try_undo_loss(sk, false))
 		return;
 
@@ -2933,6 +2940,8 @@ static bool tcp_ack_update_rtt(struct sock *sk, const int flag,
 		u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr;
 
 		if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) {
+			if (!delta)
+				delta = 1;
 			seq_rtt_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
 			ca_rtt_us = seq_rtt_us;
 		}
@@ -2986,7 +2995,7 @@ void tcp_rearm_rto(struct sock *sk)
 	/* If the retrans timer is currently being used by Fast Open
 	 * for SYN-ACK retrans purpose, stay put.
 	 */
-	if (tp->fastopen_rsk)
+	if (rcu_access_pointer(tp->fastopen_rsk))
 		return;
 
 	if (!tp->packets_out) {
@@ -3359,7 +3368,7 @@ static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq)
 
 	sock_owned_by_me((struct sock *)tp);
 	tp->bytes_received += delta;
-	tp->rcv_nxt = seq;
+	WRITE_ONCE(tp->rcv_nxt, seq);
 }
 
 /* Update our send window.
@@ -3494,10 +3503,8 @@ static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
 	}
 }
 
-/* This routine deals with acks during a TLP episode.
- * We mark the end of a TLP episode on receiving TLP dupack or when
- * ack is after tlp_high_seq.
- * Ref: loss detection algorithm in draft-dukkipati-tcpm-tcp-loss-probe.
+/* This routine deals with acks during a TLP episode and ends an episode by
+ * resetting tlp_high_seq. Ref: TLP algorithm in draft-ietf-tcpm-rack
  */
 static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
 {
@@ -3506,7 +3513,10 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
 	if (before(ack, tp->tlp_high_seq))
 		return;
 
-	if (flag & FLAG_DSACKING_ACK) {
+	if (!tp->tlp_retrans) {
+		/* TLP of new data has been acknowledged */
+		tp->tlp_high_seq = 0;
+	} else if (flag & FLAG_DSACKING_ACK) {
 		/* This DSACK means original and TLP probe arrived; no loss */
 		tp->tlp_high_seq = 0;
 	} else if (after(ack, tp->tlp_high_seq)) {
@@ -3672,6 +3682,15 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 		tcp_in_ack_event(sk, ack_ev_flags);
 	}
 
+	/* This is a deviation from RFC3168 since it states that:
+	 * "When the TCP data sender is ready to set the CWR bit after reducing
+	 * the congestion window, it SHOULD set the CWR bit only on the first
+	 * new data packet that it transmits."
+	 * We accept CWR on pure ACKs to be more robust
+	 * with widely-deployed TCP implementations that do this.
+	 */
+	tcp_ecn_accept_cwr(sk, skb);
+
 	/* We passed data and got it acked, remove any soft error
 	 * log. Something worked...
 	 */
@@ -4501,6 +4520,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 
 	if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP);
+		sk->sk_data_ready(sk);
 		tcp_drop(sk, skb);
 		return;
 	}
@@ -4533,7 +4553,11 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 	if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb,
 				 skb, &fragstolen)) {
 coalesce_done:
-		tcp_grow_window(sk, skb);
+		/* For non sack flows, do not grow window to force DUPACK
+		 * and trigger fast retransmit.
+		 */
+		if (tcp_is_sack(tp))
+			tcp_grow_window(sk, skb);
 		kfree_skb_partial(skb, fragstolen);
 		skb = NULL;
 		goto add_sack;
@@ -4617,7 +4641,11 @@ add_sack:
 		tcp_sack_new_ofo_skb(sk, seq, end_seq);
 end:
 	if (skb) {
-		tcp_grow_window(sk, skb);
+		/* For non sack flows, do not grow window to force DUPACK
+		 * and trigger fast retransmit.
+		 */
+		if (tcp_is_sack(tp))
+			tcp_grow_window(sk, skb);
 		skb_condense(skb);
 		skb_set_owner_r(skb, sk);
 	}
@@ -4697,7 +4725,8 @@ void tcp_data_ready(struct sock *sk)
 	const struct tcp_sock *tp = tcp_sk(sk);
 	int avail = tp->rcv_nxt - tp->copied_seq;
 
-	if (avail < sk->sk_rcvlowat && !sock_flag(sk, SOCK_DONE))
+	if (avail < sk->sk_rcvlowat && !tcp_rmem_pressure(sk) &&
+	    !sock_flag(sk, SOCK_DONE))
 		return;
 
 	sk->sk_data_ready(sk);
@@ -4716,8 +4745,6 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 	skb_dst_drop(skb);
 	__skb_pull(skb, tcp_hdr(skb)->doff * 4);
 
-	tcp_ecn_accept_cwr(sk, skb);
-
 	tp->rx_opt.dsack = 0;
 
 	/*  Queue data for delivery to the user.
@@ -4736,6 +4763,7 @@ queue_and_out:
 			sk_forced_mem_schedule(sk, skb->truesize);
 		else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) {
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP);
+			sk->sk_data_ready(sk);
 			goto drop;
 		}
 
@@ -5309,7 +5337,7 @@ static void tcp_check_urg(struct sock *sk, const struct tcphdr *th)
 	}
 
 	tp->urg_data = TCP_URG_NOTYET;
-	tp->urg_seq = ptr;
+	WRITE_ONCE(tp->urg_seq, ptr);
 
 	/* Disable header prediction. */
 	tp->pred_flags = 0;
@@ -5885,7 +5913,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		/* Ok.. it's good. Set up sequence numbers and
 		 * move to established.
 		 */
-		tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
+		WRITE_ONCE(tp->rcv_nxt, TCP_SKB_CB(skb)->seq + 1);
 		tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;
 
 		/* RFC1323: The window in SYN & SYN/ACK segments is
@@ -5914,7 +5942,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		/* Remember, tcp_poll() does not lock socket!
 		 * Change state from SYN-SENT only after copied_seq
 		 * is initialized. */
-		tp->copied_seq = tp->rcv_nxt;
+		WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
 
 		smc_check_reset_syn(tp);
 
@@ -5988,8 +6016,8 @@ discard:
 			tp->tcp_header_len = sizeof(struct tcphdr);
 		}
 
-		tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
-		tp->copied_seq = tp->rcv_nxt;
+		WRITE_ONCE(tp->rcv_nxt, TCP_SKB_CB(skb)->seq + 1);
+		WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
 		tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;
 
 		/* RFC1323: The window in SYN & SYN/ACK segments is
@@ -6040,7 +6068,13 @@ reset_and_undo:
 
 static void tcp_rcv_synrecv_state_fastopen(struct sock *sk)
 {
-	tcp_try_undo_loss(sk, false);
+	struct request_sock *req;
+
+	/* If we are still handling the SYNACK RTO, see if timestamp ECR allows
+	 * undo. If peer SACKs triggered fast recovery, we can't undo here.
+	 */
+	if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss)
+		tcp_try_undo_loss(sk, false);
 
 	/* Reset rtx states to prevent spurious retransmits_timed_out() */
 	tcp_sk(sk)->retrans_stamp = 0;
@@ -6049,7 +6083,9 @@ static void tcp_rcv_synrecv_state_fastopen(struct sock *sk)
 	/* Once we leave TCP_SYN_RECV or TCP_FIN_WAIT_1,
 	 * we no longer need req so release it.
 	 */
-	reqsk_fastopen_remove(sk, tcp_sk(sk)->fastopen_rsk, false);
+	req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk,
+					lockdep_sock_is_held(sk));
+	reqsk_fastopen_remove(sk, req, false);
 
 	/* Re-arm the timer because data may have been sent out.
 	 * This is similar to the regular data transmission case
@@ -6124,7 +6160,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 
 	tcp_mstamp_refresh(tp);
 	tp->rx_opt.saw_tstamp = 0;
-	req = tp->fastopen_rsk;
+	req = rcu_dereference_protected(tp->fastopen_rsk,
+					lockdep_sock_is_held(sk));
 	if (req) {
 		bool req_stolen;
 
@@ -6164,7 +6201,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 			tcp_try_undo_spurious_syn(sk);
 			tp->retrans_stamp = 0;
 			tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
-			tp->copied_seq = tp->rcv_nxt;
+			WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
 		}
 		smp_mb();
 		tcp_set_state(sk, TCP_ESTABLISHED);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index c0b1cdb8c001..ef4aa931d044 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -164,9 +164,11 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 		 * without appearing to create any others.
 		 */
 		if (likely(!tp->repair)) {
-			tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
-			if (tp->write_seq == 0)
-				tp->write_seq = 1;
+			u32 seq = tcptw->tw_snd_nxt + 65535 + 2;
+
+			if (!seq)
+				seq = 1;
+			WRITE_ONCE(tp->write_seq, seq);
 			tp->rx_opt.ts_recent	   = tcptw->tw_ts_recent;
 			tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
 		}
@@ -253,7 +255,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		tp->rx_opt.ts_recent	   = 0;
 		tp->rx_opt.ts_recent_stamp = 0;
 		if (likely(!tp->repair))
-			tp->write_seq	   = 0;
+			WRITE_ONCE(tp->write_seq, 0);
 	}
 
 	inet->inet_dport = usin->sin_port;
@@ -291,10 +293,11 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 	if (likely(!tp->repair)) {
 		if (!tp->write_seq)
-			tp->write_seq = secure_tcp_seq(inet->inet_saddr,
-						       inet->inet_daddr,
-						       inet->inet_sport,
-						       usin->sin_port);
+			WRITE_ONCE(tp->write_seq,
+				   secure_tcp_seq(inet->inet_saddr,
+						  inet->inet_daddr,
+						  inet->inet_sport,
+						  usin->sin_port));
 		tp->tsoffset = secure_tcp_ts_off(sock_net(sk),
 						 inet->inet_saddr,
 						 inet->inet_daddr);
@@ -478,7 +481,7 @@ int tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 	icsk = inet_csk(sk);
 	tp = tcp_sk(sk);
 	/* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */
-	fastopen = tp->fastopen_rsk;
+	fastopen = rcu_dereference(tp->fastopen_rsk);
 	snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una;
 	if (sk->sk_state != TCP_LISTEN &&
 	    !between(seq, snd_una, tp->snd_nxt)) {
@@ -1064,9 +1067,18 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 
 	key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen);
 	if (key) {
-		/* Pre-existing entry - just update that one. */
+		/* Pre-existing entry - just update that one.
+		 * Note that the key might be used concurrently.
+		 */
 		memcpy(key->key, newkey, newkeylen);
-		key->keylen = newkeylen;
+
+		/* Pairs with READ_ONCE() in tcp_md5_hash_key().
+		 * Also note that a reader could catch new key->keylen value
+		 * but old key->key[], this is the reason we use __GFP_ZERO
+		 * at sock_kmalloc() time below these lines.
+		 */
+		WRITE_ONCE(key->keylen, newkeylen);
+
 		return 0;
 	}
 
@@ -1082,7 +1094,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 		rcu_assign_pointer(tp->md5sig_info, md5sig);
 	}
 
-	key = sock_kmalloc(sk, sizeof(*key), gfp);
+	key = sock_kmalloc(sk, sizeof(*key), gfp | __GFP_ZERO);
 	if (!key)
 		return -ENOMEM;
 	if (!tcp_alloc_md5sig_pool()) {
@@ -2096,7 +2108,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
 	if (inet_csk(sk)->icsk_bind_hash)
 		inet_put_port(sk);
 
-	BUG_ON(tp->fastopen_rsk);
+	BUG_ON(rcu_access_pointer(tp->fastopen_rsk));
 
 	/* If socket is aborted during connect operation */
 	tcp_free_fastopen_req(tp);
@@ -2431,12 +2443,13 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
 		/* Because we don't lock the socket,
 		 * we might find a transient negative value.
 		 */
-		rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0);
+		rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) -
+				      READ_ONCE(tp->copied_seq), 0);
 
 	seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX "
 			"%08X %5u %8d %lu %d %pK %lu %lu %u %u %d",
 		i, src, srcp, dest, destp, state,
-		tp->write_seq - tp->snd_una,
+		READ_ONCE(tp->write_seq) - tp->snd_una,
 		rx_queue,
 		timer_active,
 		jiffies_delta_to_clock_t(timer_expires - jiffies),
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 7c35731816e2..bf7b3c8e338c 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -460,6 +460,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 	struct tcp_request_sock *treq = tcp_rsk(req);
 	struct inet_connection_sock *newicsk;
 	struct tcp_sock *oldtp, *newtp;
+	u32 seq;
 
 	if (!newsk)
 		return NULL;
@@ -473,12 +474,16 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 	/* Now setup tcp_sock */
 	newtp->pred_flags = 0;
 
-	newtp->rcv_wup = newtp->copied_seq =
-	newtp->rcv_nxt = treq->rcv_isn + 1;
+	seq = treq->rcv_isn + 1;
+	newtp->rcv_wup = seq;
+	WRITE_ONCE(newtp->copied_seq, seq);
+	WRITE_ONCE(newtp->rcv_nxt, seq);
 	newtp->segs_in = 1;
 
-	newtp->snd_sml = newtp->snd_una =
-	newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1;
+	seq = treq->snt_isn + 1;
+	newtp->snd_sml = newtp->snd_una = seq;
+	WRITE_ONCE(newtp->snd_nxt, seq);
+	newtp->snd_up = seq;
 
 	INIT_LIST_HEAD(&newtp->tsq_node);
 	INIT_LIST_HEAD(&newtp->tsorted_sent_queue);
@@ -493,7 +498,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 	newtp->total_retrans = req->num_retrans;
 
 	tcp_init_xmit_timers(newsk);
-	newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1;
+	WRITE_ONCE(newtp->write_seq, newtp->pushed_seq = treq->snt_isn + 1);
 
 	if (sock_flag(newsk, SOCK_KEEPOPEN))
 		inet_csk_reset_keepalive_timer(newsk,
@@ -539,7 +544,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 	newtp->rx_opt.mss_clamp = req->mss;
 	tcp_ecn_openreq_child(newtp, req);
 	newtp->fastopen_req = NULL;
-	newtp->fastopen_rsk = NULL;
+	RCU_INIT_POINTER(newtp->fastopen_rsk, NULL);
 
 	__TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS);
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 39eafd8041ad..807dc290fb7d 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -67,7 +67,7 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb)
 	struct tcp_sock *tp = tcp_sk(sk);
 	unsigned int prior_packets = tp->packets_out;
 
-	tp->snd_nxt = TCP_SKB_CB(skb)->end_seq;
+	WRITE_ONCE(tp->snd_nxt, TCP_SKB_CB(skb)->end_seq);
 
 	__skb_unlink(skb, &sk->sk_write_queue);
 	tcp_rbtree_insert(&sk->tcp_rtx_queue, skb);
@@ -662,7 +662,8 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 				       unsigned int mss, struct sk_buff *skb,
 				       struct tcp_out_options *opts,
 				       const struct tcp_md5sig_key *md5,
-				       struct tcp_fastopen_cookie *foc)
+				       struct tcp_fastopen_cookie *foc,
+				       enum tcp_synack_type synack_type)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	unsigned int remaining = MAX_TCP_OPTION_SPACE;
@@ -677,7 +678,8 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 		 * rather than TS in order to fit in better with old,
 		 * buggy kernels, but that was deemed to be unnecessary.
 		 */
-		ireq->tstamp_ok &= !ireq->sack_ok;
+		if (synack_type != TCP_SYNACK_COOKIE)
+			ireq->tstamp_ok &= !ireq->sack_ok;
 	}
 #endif
 
@@ -1187,10 +1189,10 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	/* Advance write_seq and place onto the write_queue. */
-	tp->write_seq = TCP_SKB_CB(skb)->end_seq;
+	WRITE_ONCE(tp->write_seq, TCP_SKB_CB(skb)->end_seq);
 	__skb_header_release(skb);
 	tcp_add_write_queue_tail(sk, skb);
-	sk->sk_wmem_queued += skb->truesize;
+	sk_wmem_queued_add(sk, skb->truesize);
 	sk_mem_charge(sk, skb->truesize);
 }
 
@@ -1324,7 +1326,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
 		return -ENOMEM; /* We'll just try again later. */
 	skb_copy_decrypted(buff, skb);
 
-	sk->sk_wmem_queued += buff->truesize;
+	sk_wmem_queued_add(sk, buff->truesize);
 	sk_mem_charge(sk, buff->truesize);
 	nlen = skb->len - len - nsize;
 	buff->truesize += nlen;
@@ -1434,7 +1436,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
 
 	if (delta_truesize) {
 		skb->truesize	   -= delta_truesize;
-		sk->sk_wmem_queued -= delta_truesize;
+		sk_wmem_queued_add(sk, -delta_truesize);
 		sk_mem_uncharge(sk, delta_truesize);
 		sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
 	}
@@ -1715,7 +1717,7 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
 	u32 bytes, segs;
 
 	bytes = min_t(unsigned long,
-		      sk->sk_pacing_rate >> sk->sk_pacing_shift,
+		      sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift),
 		      sk->sk_gso_max_size - 1 - MAX_TCP_HEADER);
 
 	/* Goal is to send at least one packet per ms,
@@ -1879,7 +1881,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
 		return -ENOMEM;
 	skb_copy_decrypted(buff, skb);
 
-	sk->sk_wmem_queued += buff->truesize;
+	sk_wmem_queued_add(sk, buff->truesize);
 	sk_mem_charge(sk, buff->truesize);
 	buff->truesize += nlen;
 	skb->truesize -= nlen;
@@ -2143,7 +2145,7 @@ static int tcp_mtu_probe(struct sock *sk)
 	nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false);
 	if (!nskb)
 		return -1;
-	sk->sk_wmem_queued += nskb->truesize;
+	sk_wmem_queued_add(sk, nskb->truesize);
 	sk_mem_charge(sk, nskb->truesize);
 
 	skb = tcp_send_head(sk);
@@ -2250,7 +2252,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
 
 	limit = max_t(unsigned long,
 		      2 * skb->truesize,
-		      sk->sk_pacing_rate >> sk->sk_pacing_shift);
+		      sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift));
 	if (sk->sk_pacing_status == SK_PACING_NONE)
 		limit = min_t(unsigned long, limit,
 			      sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes);
@@ -2469,7 +2471,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto)
 	/* Don't do any loss probe on a Fast Open connection before 3WHS
 	 * finishes.
 	 */
-	if (tp->fastopen_rsk)
+	if (rcu_access_pointer(tp->fastopen_rsk))
 		return false;
 
 	early_retrans = sock_net(sk)->ipv4.sysctl_tcp_early_retrans;
@@ -2533,6 +2535,11 @@ void tcp_send_loss_probe(struct sock *sk)
 	int pcount;
 	int mss = tcp_current_mss(sk);
 
+	/* At most one outstanding TLP */
+	if (tp->tlp_high_seq)
+		goto rearm_timer;
+
+	tp->tlp_retrans = 0;
 	skb = tcp_send_head(sk);
 	if (skb && tcp_snd_wnd_test(tp, skb, mss)) {
 		pcount = tp->packets_out;
@@ -2550,10 +2557,6 @@ void tcp_send_loss_probe(struct sock *sk)
 		return;
 	}
 
-	/* At most one outstanding TLP retransmission. */
-	if (tp->tlp_high_seq)
-		goto rearm_timer;
-
 	if (skb_still_in_host_queue(sk, skb))
 		goto rearm_timer;
 
@@ -2575,10 +2578,12 @@ void tcp_send_loss_probe(struct sock *sk)
 	if (__tcp_retransmit_skb(sk, skb, 1))
 		goto rearm_timer;
 
+	tp->tlp_retrans = 1;
+
+probe_sent:
 	/* Record snd_nxt for loss detection. */
 	tp->tlp_high_seq = tp->snd_nxt;
 
-probe_sent:
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSSPROBES);
 	/* Reset s.t. tcp_rearm_rto will restart timer from now */
 	inet_csk(sk)->icsk_pending = 0;
@@ -3129,7 +3134,7 @@ void tcp_send_fin(struct sock *sk)
 			 * if FIN had been sent. This is because retransmit path
 			 * does not change tp->snd_nxt.
 			 */
-			tp->snd_nxt++;
+			WRITE_ONCE(tp->snd_nxt, tp->snd_nxt + 1);
 			return;
 		}
 	} else {
@@ -3210,7 +3215,7 @@ int tcp_send_synack(struct sock *sk)
 			tcp_rtx_queue_unlink_and_free(skb, sk);
 			__skb_header_release(nskb);
 			tcp_rbtree_insert(&sk->tcp_rtx_queue, nskb);
-			sk->sk_wmem_queued += nskb->truesize;
+			sk_wmem_queued_add(sk, nskb->truesize);
 			sk_mem_charge(sk, nskb->truesize);
 			skb = nskb;
 		}
@@ -3291,7 +3296,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 #endif
 	skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4);
 	tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5,
-					     foc) + sizeof(*th);
+					     foc, synack_type) + sizeof(*th);
 
 	skb_push(skb, tcp_header_size);
 	skb_reset_transport_header(skb);
@@ -3411,14 +3416,14 @@ static void tcp_connect_init(struct sock *sk)
 	tp->snd_una = tp->write_seq;
 	tp->snd_sml = tp->write_seq;
 	tp->snd_up = tp->write_seq;
-	tp->snd_nxt = tp->write_seq;
+	WRITE_ONCE(tp->snd_nxt, tp->write_seq);
 
 	if (likely(!tp->repair))
 		tp->rcv_nxt = 0;
 	else
 		tp->rcv_tstamp = tcp_jiffies32;
 	tp->rcv_wup = tp->rcv_nxt;
-	tp->copied_seq = tp->rcv_nxt;
+	WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
 
 	inet_csk(sk)->icsk_rto = tcp_timeout_init(sk);
 	inet_csk(sk)->icsk_retransmits = 0;
@@ -3432,9 +3437,9 @@ static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb)
 
 	tcb->end_seq += skb->len;
 	__skb_header_release(skb);
-	sk->sk_wmem_queued += skb->truesize;
+	sk_wmem_queued_add(sk, skb->truesize);
 	sk_mem_charge(sk, skb->truesize);
-	tp->write_seq = tcb->end_seq;
+	WRITE_ONCE(tp->write_seq, tcb->end_seq);
 	tp->packets_out += tcp_skb_pcount(skb);
 }
 
@@ -3571,11 +3576,11 @@ int tcp_connect(struct sock *sk)
 	/* We change tp->snd_nxt after the tcp_transmit_skb() call
 	 * in order to make this packet get counted in tcpOutSegs.
 	 */
-	tp->snd_nxt = tp->write_seq;
+	WRITE_ONCE(tp->snd_nxt, tp->write_seq);
 	tp->pushed_seq = tp->write_seq;
 	buff = tcp_send_head(sk);
 	if (unlikely(buff)) {
-		tp->snd_nxt	= TCP_SKB_CB(buff)->seq;
+		WRITE_ONCE(tp->snd_nxt, TCP_SKB_CB(buff)->seq);
 		tp->pushed_seq	= TCP_SKB_CB(buff)->seq;
 	}
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS);
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 483323332d74..ace48d4e0801 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -386,15 +386,13 @@ abort:		tcp_write_err(sk);
  *	Timer for Fast Open socket to retransmit SYNACK. Note that the
  *	sk here is the child socket, not the parent (listener) socket.
  */
-static void tcp_fastopen_synack_timer(struct sock *sk)
+static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	int max_retries = icsk->icsk_syn_retries ? :
 	    sock_net(sk)->ipv4.sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct request_sock *req;
 
-	req = tcp_sk(sk)->fastopen_rsk;
 	req->rsk_ops->syn_ack_timeout(req);
 
 	if (req->num_timeout >= max_retries) {
@@ -435,11 +433,14 @@ void tcp_retransmit_timer(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct net *net = sock_net(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct request_sock *req;
 
-	if (tp->fastopen_rsk) {
+	req = rcu_dereference_protected(tp->fastopen_rsk,
+					lockdep_sock_is_held(sk));
+	if (req) {
 		WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV &&
 			     sk->sk_state != TCP_FIN_WAIT1);
-		tcp_fastopen_synack_timer(sk);
+		tcp_fastopen_synack_timer(sk, req);
 		/* Before we receive ACK to our SYN-ACK don't retransmit
 		 * anything else (e.g., data or FIN segments).
 		 */
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index e2acad68d9ff..1009a9e1b779 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -424,7 +424,7 @@ static struct sock *udp4_lib_lookup2(struct net *net,
 				     struct udp_hslot *hslot2,
 				     struct sk_buff *skb)
 {
-	struct sock *sk, *result;
+	struct sock *sk, *result, *reuseport_result;
 	int score, badness;
 	u32 hash = 0;
 
@@ -434,17 +434,20 @@ static struct sock *udp4_lib_lookup2(struct net *net,
 		score = compute_score(sk, net, saddr, sport,
 				      daddr, hnum, dif, sdif, exact_dif);
 		if (score > badness) {
+			reuseport_result = NULL;
+
 			if (sk->sk_reuseport &&
 			    sk->sk_state != TCP_ESTABLISHED) {
 				hash = udp_ehashfn(net, daddr, hnum,
 						   saddr, sport);
-				result = reuseport_select_sock(sk, hash, skb,
-							sizeof(struct udphdr));
-				if (result && !reuseport_has_conns(sk, false))
-					return result;
+				reuseport_result = reuseport_select_sock(sk, hash, skb,
+									 sizeof(struct udphdr));
+				if (reuseport_result && !reuseport_has_conns(sk, false))
+					return reuseport_result;
 			}
+
+			result = reuseport_result ? : sk;
 			badness = score;
-			result = sk;
 		}
 	}
 	return result;
@@ -1363,7 +1366,8 @@ static void udp_rmem_release(struct sock *sk, int size, int partial,
 	if (likely(partial)) {
 		up->forward_deficit += size;
 		size = up->forward_deficit;
-		if (size < (sk->sk_rcvbuf >> 2))
+		if (size < (sk->sk_rcvbuf >> 2) &&
+		    !skb_queue_empty(&up->reader_queue))
 			return;
 	} else {
 		size += up->forward_deficit;
@@ -1850,8 +1854,12 @@ int __udp_disconnect(struct sock *sk, int flags)
 	inet->inet_dport = 0;
 	sock_rps_reset_rxhash(sk);
 	sk->sk_bound_dev_if = 0;
-	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
+	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) {
 		inet_reset_saddr(sk);
+		if (sk->sk_prot->rehash &&
+		    (sk->sk_userlocks & SOCK_BINDPORT_LOCK))
+			sk->sk_prot->rehash(sk);
+	}
 
 	if (!(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) {
 		sk->sk_prot->unhash(sk);
@@ -2035,7 +2043,7 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
 	/*
 	 * 	UDP-Lite specific tests, ignored on UDP sockets
 	 */
-	if ((is_udplite & UDPLITE_RECV_CC)  &&  UDP_SKB_CB(skb)->partial_cov) {
+	if ((up->pcflag & UDPLITE_RECV_CC)  &&  UDP_SKB_CB(skb)->partial_cov) {
 
 		/*
 		 * MIB statistics other than incrementing the error count are
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index 910555a4d9fe..dccd2286bc28 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -64,8 +64,9 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb,
 		goto out;
 
 	err = -ENOMEM;
-	rep = nlmsg_new(sizeof(struct inet_diag_msg) +
-			sizeof(struct inet_diag_meminfo) + 64,
+	rep = nlmsg_new(nla_total_size(sizeof(struct inet_diag_msg)) +
+			inet_diag_msg_attrs_size() +
+			nla_total_size(sizeof(struct inet_diag_meminfo)) + 64,
 			GFP_KERNEL);
 	if (!rep)
 		goto out;
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index ecff3fce9807..ab343ae686d4 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -58,9 +58,7 @@ int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb)
 {
 	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 
-#ifdef CONFIG_NETFILTER
 	IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED;
-#endif
 
 	return xfrm_output(sk, skb);
 }
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 9f2c4bc260ef..a18e52f9776c 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1226,11 +1226,13 @@ check_cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long *expires)
 }
 
 static void
-cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, bool del_rt)
+cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires,
+		     bool del_rt, bool del_peer)
 {
 	struct fib6_info *f6i;
 
-	f6i = addrconf_get_prefix_route(&ifp->addr, ifp->prefix_len,
+	f6i = addrconf_get_prefix_route(del_peer ? &ifp->peer_addr : &ifp->addr,
+					ifp->prefix_len,
 					ifp->idev->dev, 0, RTF_DEFAULT, true);
 	if (f6i) {
 		if (del_rt)
@@ -1293,7 +1295,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 
 	if (action != CLEANUP_PREFIX_RT_NOP) {
 		cleanup_prefix_route(ifp, expires,
-			action == CLEANUP_PREFIX_RT_DEL);
+			action == CLEANUP_PREFIX_RT_DEL, false);
 	}
 
 	/* clean up prefsrc entries */
@@ -3292,6 +3294,10 @@ static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route)
 	if (netif_is_l3_master(idev->dev))
 		return;
 
+	/* no link local addresses on devices flagged as slaves */
+	if (idev->dev->flags & IFF_SLAVE)
+		return;
+
 	ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0);
 
 	switch (idev->cnf.addr_gen_mode) {
@@ -3343,6 +3349,10 @@ static void addrconf_dev_config(struct net_device *dev)
 	    (dev->type != ARPHRD_NONE) &&
 	    (dev->type != ARPHRD_RAWIP)) {
 		/* Alas, we support only Ethernet autoconfiguration. */
+		idev = __in6_dev_get(dev);
+		if (!IS_ERR_OR_NULL(idev) && dev->flags & IFF_UP &&
+		    dev->flags & IFF_MULTICAST)
+			ipv6_mc_up(idev);
 		return;
 	}
 
@@ -4584,12 +4594,14 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
 }
 
 static int modify_prefix_route(struct inet6_ifaddr *ifp,
-			       unsigned long expires, u32 flags)
+			       unsigned long expires, u32 flags,
+			       bool modify_peer)
 {
 	struct fib6_info *f6i;
 	u32 prio;
 
-	f6i = addrconf_get_prefix_route(&ifp->addr, ifp->prefix_len,
+	f6i = addrconf_get_prefix_route(modify_peer ? &ifp->peer_addr : &ifp->addr,
+					ifp->prefix_len,
 					ifp->idev->dev, 0, RTF_DEFAULT, true);
 	if (!f6i)
 		return -ENOENT;
@@ -4600,7 +4612,8 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp,
 		ip6_del_rt(dev_net(ifp->idev->dev), f6i);
 
 		/* add new one */
-		addrconf_prefix_route(&ifp->addr, ifp->prefix_len,
+		addrconf_prefix_route(modify_peer ? &ifp->peer_addr : &ifp->addr,
+				      ifp->prefix_len,
 				      ifp->rt_priority, ifp->idev->dev,
 				      expires, flags, GFP_KERNEL);
 	} else {
@@ -4622,6 +4635,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg)
 	unsigned long timeout;
 	bool was_managetempaddr;
 	bool had_prefixroute;
+	bool new_peer = false;
 
 	ASSERT_RTNL();
 
@@ -4653,6 +4667,13 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg)
 		cfg->preferred_lft = timeout;
 	}
 
+	if (cfg->peer_pfx &&
+	    memcmp(&ifp->peer_addr, cfg->peer_pfx, sizeof(struct in6_addr))) {
+		if (!ipv6_addr_any(&ifp->peer_addr))
+			cleanup_prefix_route(ifp, expires, true, true);
+		new_peer = true;
+	}
+
 	spin_lock_bh(&ifp->lock);
 	was_managetempaddr = ifp->flags & IFA_F_MANAGETEMPADDR;
 	had_prefixroute = ifp->flags & IFA_F_PERMANENT &&
@@ -4668,6 +4689,9 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg)
 	if (cfg->rt_priority && cfg->rt_priority != ifp->rt_priority)
 		ifp->rt_priority = cfg->rt_priority;
 
+	if (new_peer)
+		ifp->peer_addr = *cfg->peer_pfx;
+
 	spin_unlock_bh(&ifp->lock);
 	if (!(ifp->flags&IFA_F_TENTATIVE))
 		ipv6_ifa_notify(0, ifp);
@@ -4676,7 +4700,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg)
 		int rc = -ENOENT;
 
 		if (had_prefixroute)
-			rc = modify_prefix_route(ifp, expires, flags);
+			rc = modify_prefix_route(ifp, expires, flags, false);
 
 		/* prefix route could have been deleted; if so restore it */
 		if (rc == -ENOENT) {
@@ -4684,6 +4708,15 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg)
 					      ifp->rt_priority, ifp->idev->dev,
 					      expires, flags, GFP_KERNEL);
 		}
+
+		if (had_prefixroute && !ipv6_addr_any(&ifp->peer_addr))
+			rc = modify_prefix_route(ifp, expires, flags, true);
+
+		if (rc == -ENOENT && !ipv6_addr_any(&ifp->peer_addr)) {
+			addrconf_prefix_route(&ifp->peer_addr, ifp->prefix_len,
+					      ifp->rt_priority, ifp->idev->dev,
+					      expires, flags, GFP_KERNEL);
+		}
 	} else if (had_prefixroute) {
 		enum cleanup_prefix_rt_t action;
 		unsigned long rt_expires;
@@ -4694,7 +4727,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg)
 
 		if (action != CLEANUP_PREFIX_RT_NOP) {
 			cleanup_prefix_route(ifp, rt_expires,
-				action == CLEANUP_PREFIX_RT_DEL);
+				action == CLEANUP_PREFIX_RT_DEL, false);
 		}
 	}
 
@@ -5717,6 +5750,9 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla)
 	struct nlattr *tb[IFLA_INET6_MAX + 1];
 	int err;
 
+	if (!idev)
+		return -EAFNOSUPPORT;
+
 	if (nla_parse_nested_deprecated(tb, IFLA_INET6_MAX, nla, NULL, NULL) < 0)
 		BUG();
 
@@ -5979,9 +6015,9 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 		if (ifp->idev->cnf.forwarding)
 			addrconf_join_anycast(ifp);
 		if (!ipv6_addr_any(&ifp->peer_addr))
-			addrconf_prefix_route(&ifp->peer_addr, 128, 0,
-					      ifp->idev->dev, 0, 0,
-					      GFP_ATOMIC);
+			addrconf_prefix_route(&ifp->peer_addr, 128,
+					      ifp->rt_priority, ifp->idev->dev,
+					      0, 0, GFP_ATOMIC);
 		break;
 	case RTM_DELADDR:
 		if (ifp->idev->cnf.forwarding)
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index fed91ab7ec46..cf3a88a10ddd 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -183,7 +183,7 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	return 0;
 }
 
-void ipv6_sock_ac_close(struct sock *sk)
+void __ipv6_sock_ac_close(struct sock *sk)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct net_device *dev = NULL;
@@ -191,10 +191,7 @@ void ipv6_sock_ac_close(struct sock *sk)
 	struct net *net = sock_net(sk);
 	int	prev_index;
 
-	if (!np->ipv6_ac_list)
-		return;
-
-	rtnl_lock();
+	ASSERT_RTNL();
 	pac = np->ipv6_ac_list;
 	np->ipv6_ac_list = NULL;
 
@@ -211,6 +208,16 @@ void ipv6_sock_ac_close(struct sock *sk)
 		sock_kfree_s(sk, pac, sizeof(*pac));
 		pac = next;
 	}
+}
+
+void ipv6_sock_ac_close(struct sock *sk)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+
+	if (!np->ipv6_ac_list)
+		return;
+	rtnl_lock();
+	__ipv6_sock_ac_close(sk);
 	rtnl_unlock();
 }
 
diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c
index 221c81f85cbf..8d3f66c310db 100644
--- a/net/ipv6/calipso.c
+++ b/net/ipv6/calipso.c
@@ -1047,7 +1047,8 @@ static int calipso_opt_getattr(const unsigned char *calipso,
 			goto getattr_return;
 		}
 
-		secattr->flags |= NETLBL_SECATTR_MLS_CAT;
+		if (secattr->attr.mls.cat)
+			secattr->flags |= NETLBL_SECATTR_MLS_CAT;
 	}
 
 	secattr->type = NETLBL_NLTYPE_CALIPSO;
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index d0d8528b294a..454fd8ac06d3 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -79,14 +79,14 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head,
 		if (!x)
 			goto out_reset;
 
+		skb->mark = xfrm_smark_get(skb->mark, x);
+
 		sp->xvec[sp->len++] = x;
 		sp->olen++;
 
 		xo = xfrm_offload(skb);
-		if (!xo) {
-			xfrm_state_put(x);
+		if (!xo)
 			goto out_reset;
-		}
 	}
 
 	xo->flags |= XFRM_GRO;
@@ -121,9 +121,16 @@ static void esp6_gso_encap(struct xfrm_state *x, struct sk_buff *skb)
 	struct ip_esp_hdr *esph;
 	struct ipv6hdr *iph = ipv6_hdr(skb);
 	struct xfrm_offload *xo = xfrm_offload(skb);
-	int proto = iph->nexthdr;
+	u8 proto = iph->nexthdr;
 
 	skb_push(skb, -skb_network_offset(skb));
+
+	if (x->outer_mode.encap == XFRM_MODE_TRANSPORT) {
+		__be16 frag;
+
+		ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &proto, &frag);
+	}
+
 	esph = ip_esp_hdr(skb);
 	*skb_mac_header(skb) = IPPROTO_ESP;
 
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 455f1292e479..82a6c4c4a6e2 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -611,7 +611,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 	if (arg.filter.table_id) {
 		tb = fib6_get_table(net, arg.filter.table_id);
 		if (!tb) {
-			if (arg.filter.dump_all_families)
+			if (rtnl_msg_family(cb->nlh) != PF_INET6)
 				goto out;
 
 			NL_SET_ERR_MSG_MOD(cb->extack, "FIB table does not exist");
@@ -1004,8 +1004,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 					found++;
 					break;
 				}
-				if (rt_can_ecmp)
-					fallback_ins = fallback_ins ?: ins;
+				fallback_ins = fallback_ins ?: ins;
 				goto next_iter;
 			}
 
@@ -1048,7 +1047,9 @@ next_iter:
 	}
 
 	if (fallback_ins && !found) {
-		/* No ECMP-able route found, replace first non-ECMP one */
+		/* No matching route with same ecmp-able-ness found, replace
+		 * first matching route
+		 */
 		ins = fallback_ins;
 		iter = rcu_dereference_protected(*ins,
 				    lockdep_is_held(&rt->fib6_table->tb6_lock));
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 2d218973a219..8d48f7f9fdc6 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -127,6 +127,7 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev,
 			gre_proto == htons(ETH_P_ERSPAN2)) ?
 		       ARPHRD_ETHER : ARPHRD_IP6GRE;
 	int score, cand_score = 4;
+	struct net_device *ndev;
 
 	for_each_ip_tunnel_rcu(t, ign->tunnels_r_l[h0 ^ h1]) {
 		if (!ipv6_addr_equal(local, &t->parms.laddr) ||
@@ -238,9 +239,9 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev,
 	if (t && t->dev->flags & IFF_UP)
 		return t;
 
-	dev = ign->fb_tunnel_dev;
-	if (dev && dev->flags & IFF_UP)
-		return netdev_priv(dev);
+	ndev = READ_ONCE(ign->fb_tunnel_dev);
+	if (ndev && ndev->flags & IFF_UP)
+		return netdev_priv(ndev);
 
 	return NULL;
 }
@@ -413,6 +414,8 @@ static void ip6gre_tunnel_uninit(struct net_device *dev)
 
 	ip6gre_tunnel_unlink_md(ign, t);
 	ip6gre_tunnel_unlink(ign, t);
+	if (ign->fb_tunnel_dev == dev)
+		WRITE_ONCE(ign->fb_tunnel_dev, NULL);
 	dst_cache_reset(&t->dst_cache);
 	dev_put(dev);
 }
@@ -1466,7 +1469,6 @@ static int ip6gre_tunnel_init_common(struct net_device *dev)
 		dev->mtu -= 8;
 
 	if (tunnel->parms.collect_md) {
-		dev->features |= NETIF_F_NETNS_LOCAL;
 		netif_keep_dst(dev);
 	}
 	ip6gre_tnl_init_features(dev);
@@ -1558,17 +1560,18 @@ static void ip6gre_destroy_tunnels(struct net *net, struct list_head *head)
 static int __net_init ip6gre_init_net(struct net *net)
 {
 	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
+	struct net_device *ndev;
 	int err;
 
 	if (!net_has_fallback_tunnels(net))
 		return 0;
-	ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6gre0",
-					  NET_NAME_UNKNOWN,
-					  ip6gre_tunnel_setup);
-	if (!ign->fb_tunnel_dev) {
+	ndev = alloc_netdev(sizeof(struct ip6_tnl), "ip6gre0",
+			    NET_NAME_UNKNOWN, ip6gre_tunnel_setup);
+	if (!ndev) {
 		err = -ENOMEM;
 		goto err_alloc_dev;
 	}
+	ign->fb_tunnel_dev = ndev;
 	dev_net_set(ign->fb_tunnel_dev, net);
 	/* FB netdevice is special: we have one, and only one per netns.
 	 * Allowing to move it to another netns is clearly unsafe.
@@ -1588,7 +1591,7 @@ static int __net_init ip6gre_init_net(struct net *net)
 	return 0;
 
 err_reg_dev:
-	free_netdev(ign->fb_tunnel_dev);
+	free_netdev(ndev);
 err_alloc_dev:
 	return err;
 }
@@ -1894,7 +1897,6 @@ static void ip6gre_tap_setup(struct net_device *dev)
 	dev->needs_free_netdev = true;
 	dev->priv_destructor = ip6gre_dev_free;
 
-	dev->features |= NETIF_F_NETNS_LOCAL;
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 	netif_keep_dst(dev);
@@ -2196,7 +2198,6 @@ static void ip6erspan_tap_setup(struct net_device *dev)
 	dev->needs_free_netdev = true;
 	dev->priv_destructor = ip6gre_dev_free;
 
-	dev->features |= NETIF_F_NETNS_LOCAL;
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 	netif_keep_dst(dev);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 58a83f5d5135..a1134dcb75e1 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1877,10 +1877,8 @@ static int ip6_tnl_dev_init(struct net_device *dev)
 	if (err)
 		return err;
 	ip6_tnl_link_config(t);
-	if (t->parms.collect_md) {
-		dev->features |= NETIF_F_NETNS_LOCAL;
+	if (t->parms.collect_md)
 		netif_keep_dst(dev);
-	}
 	return 0;
 }
 
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 6f08b760c2a7..cc6180e08a4f 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -311,7 +311,7 @@ static int vti6_rcv(struct sk_buff *skb)
 
 		if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
 			rcu_read_unlock();
-			return 0;
+			goto discard;
 		}
 
 		ipv6h = ipv6_hdr(skb);
@@ -449,8 +449,35 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 	int err = -1;
 	int mtu;
 
-	if (!dst)
-		goto tx_err_link_failure;
+	if (!dst) {
+		switch (skb->protocol) {
+		case htons(ETH_P_IP): {
+			struct rtable *rt;
+
+			fl->u.ip4.flowi4_oif = dev->ifindex;
+			fl->u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC;
+			rt = __ip_route_output_key(dev_net(dev), &fl->u.ip4);
+			if (IS_ERR(rt))
+				goto tx_err_link_failure;
+			dst = &rt->dst;
+			skb_dst_set(skb, dst);
+			break;
+		}
+		case htons(ETH_P_IPV6):
+			fl->u.ip6.flowi6_oif = dev->ifindex;
+			fl->u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC;
+			dst = ip6_route_output(dev_net(dev), NULL, &fl->u.ip6);
+			if (dst->error) {
+				dst_release(dst);
+				dst = NULL;
+				goto tx_err_link_failure;
+			}
+			skb_dst_set(skb, dst);
+			break;
+		default:
+			goto tx_err_link_failure;
+		}
+	}
 
 	dst_hold(dst);
 	dst = xfrm_lookup(t->net, dst, fl, NULL, 0);
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index e80d36c5073d..da7ab5ac07fb 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -2498,7 +2498,7 @@ static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
 
 		mrt = ip6mr_get_table(sock_net(skb->sk), filter.table_id);
 		if (!mrt) {
-			if (filter.dump_all_families)
+			if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IP6MR)
 				return skb->len;
 
 			NL_SET_ERR_MSG_MOD(cb->extack, "MR table does not exist");
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 264c292e7dcc..0716282ea85d 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -183,8 +183,14 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 					retv = -EBUSY;
 					break;
 				}
-			} else if (sk->sk_protocol != IPPROTO_TCP)
+			} else if (sk->sk_protocol == IPPROTO_TCP) {
+				if (sk->sk_prot != &tcpv6_prot) {
+					retv = -EBUSY;
+					break;
+				}
+			} else {
 				break;
+			}
 
 			if (sk->sk_state != TCP_ESTABLISHED) {
 				retv = -ENOTCONN;
@@ -199,6 +205,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 
 			fl6_free_socklist(sk);
 			__ipv6_sock_mc_close(sk);
+			__ipv6_sock_ac_close(sk);
 
 			/*
 			 * Sock is moving from IPv6 to IPv4 (sk_prot), so
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index eaa4c2cc2fbb..c875c9b6edbe 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -2618,6 +2618,7 @@ void ipv6_mc_destroy_dev(struct inet6_dev *idev)
 		idev->mc_list = i->next;
 
 		write_unlock_bh(&idev->lock);
+		ip6_mc_clear_src(i);
 		ma_put(i);
 		write_lock_bh(&idev->lock);
 	}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 32ea5042dd50..a71b115e65fe 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2355,8 +2355,10 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 	const struct in6_addr *daddr, *saddr;
 	struct rt6_info *rt6 = (struct rt6_info *)dst;
 
-	if (dst_metric_locked(dst, RTAX_MTU))
-		return;
+	/* Note: do *NOT* check dst_metric_locked(dst, RTAX_MTU)
+	 * IPv6 pmtu discovery isn't optional, so 'mtu lock' cannot disable it.
+	 * [see also comment in rt6_mtu_change_route()]
+	 */
 
 	if (iph) {
 		daddr = &iph->daddr;
@@ -2987,7 +2989,7 @@ static bool fib6_is_reject(u32 flags, struct net_device *dev, int addr_type)
 	if ((flags & RTF_REJECT) ||
 	    (dev && (dev->flags & IFF_LOOPBACK) &&
 	     !(addr_type & IPV6_ADDR_LOOPBACK) &&
-	     !(flags & RTF_LOCAL)))
+	     !(flags & (RTF_ANYCAST | RTF_LOCAL))))
 		return true;
 
 	return false;
@@ -4559,6 +4561,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 		 */
 		cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL |
 						     NLM_F_REPLACE);
+		cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE;
 		nhn++;
 	}
 
diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index 9d4f75e0d33a..af1091451316 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -23,6 +23,7 @@
 #include <net/addrconf.h>
 #include <net/ip6_route.h>
 #include <net/dst_cache.h>
+#include <net/ip_tunnels.h>
 #ifdef CONFIG_IPV6_SEG6_HMAC
 #include <net/seg6_hmac.h>
 #endif
@@ -130,7 +131,8 @@ static bool decap_and_validate(struct sk_buff *skb, int proto)
 
 	skb_reset_network_header(skb);
 	skb_reset_transport_header(skb);
-	skb->encapsulation = 0;
+	if (iptunnel_pull_offloads(skb))
+		return false;
 
 	return true;
 }
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 86fbb8b85d5a..70b36dc26f62 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -215,7 +215,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	    !ipv6_addr_equal(&sk->sk_v6_daddr, &usin->sin6_addr)) {
 		tp->rx_opt.ts_recent = 0;
 		tp->rx_opt.ts_recent_stamp = 0;
-		tp->write_seq = 0;
+		WRITE_ONCE(tp->write_seq, 0);
 	}
 
 	sk->sk_v6_daddr = usin->sin6_addr;
@@ -311,10 +311,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 
 	if (likely(!tp->repair)) {
 		if (!tp->write_seq)
-			tp->write_seq = secure_tcpv6_seq(np->saddr.s6_addr32,
-							 sk->sk_v6_daddr.s6_addr32,
-							 inet->inet_sport,
-							 inet->inet_dport);
+			WRITE_ONCE(tp->write_seq,
+				   secure_tcpv6_seq(np->saddr.s6_addr32,
+						    sk->sk_v6_daddr.s6_addr32,
+						    inet->inet_sport,
+						    inet->inet_dport));
 		tp->tsoffset = secure_tcpv6_ts_off(sock_net(sk),
 						   np->saddr.s6_addr32,
 						   sk->sk_v6_daddr.s6_addr32);
@@ -406,7 +407,7 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 	tp = tcp_sk(sk);
 	/* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */
-	fastopen = tp->fastopen_rsk;
+	fastopen = rcu_dereference(tp->fastopen_rsk);
 	snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una;
 	if (sk->sk_state != TCP_LISTEN &&
 	    !between(seq, snd_una, tp->snd_nxt)) {
@@ -1852,7 +1853,8 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 		/* Because we don't lock the socket,
 		 * we might find a transient negative value.
 		 */
-		rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0);
+		rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) -
+				      READ_ONCE(tp->copied_seq), 0);
 
 	seq_printf(seq,
 		   "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
@@ -1863,7 +1865,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 		   dest->s6_addr32[0], dest->s6_addr32[1],
 		   dest->s6_addr32[2], dest->s6_addr32[3], destp,
 		   state,
-		   tp->write_seq - tp->snd_una,
+		   READ_ONCE(tp->write_seq) - tp->snd_una,
 		   rx_queue,
 		   timer_active,
 		   jiffies_delta_to_clock_t(timer_expires - jiffies),
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 9011a750f74f..e0ff2f60f53c 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -158,7 +158,7 @@ static struct sock *udp6_lib_lookup2(struct net *net,
 		int dif, int sdif, bool exact_dif,
 		struct udp_hslot *hslot2, struct sk_buff *skb)
 {
-	struct sock *sk, *result;
+	struct sock *sk, *result, *reuseport_result;
 	int score, badness;
 	u32 hash = 0;
 
@@ -168,17 +168,20 @@ static struct sock *udp6_lib_lookup2(struct net *net,
 		score = compute_score(sk, net, saddr, sport,
 				      daddr, hnum, dif, sdif, exact_dif);
 		if (score > badness) {
+			reuseport_result = NULL;
+
 			if (sk->sk_reuseport &&
 			    sk->sk_state != TCP_ESTABLISHED) {
 				hash = udp6_ehashfn(net, daddr, hnum,
 						    saddr, sport);
 
-				result = reuseport_select_sock(sk, hash, skb,
-							sizeof(struct udphdr));
-				if (result && !reuseport_has_conns(sk, false))
-					return result;
+				reuseport_result = reuseport_select_sock(sk, hash, skb,
+									 sizeof(struct udphdr));
+				if (reuseport_result && !reuseport_has_conns(sk, false))
+					return reuseport_result;
 			}
-			result = sk;
+
+			result = reuseport_result ? : sk;
 			badness = score;
 		}
 	}
@@ -655,7 +658,7 @@ static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
 	/*
 	 * UDP-Lite specific tests, ignored on UDP sockets (see net/ipv4/udp.c).
 	 */
-	if ((is_udplite & UDPLITE_RECV_CC)  &&  UDP_SKB_CB(skb)->partial_cov) {
+	if ((up->pcflag & UDPLITE_RECV_CC)  &&  UDP_SKB_CB(skb)->partial_cov) {
 
 		if (up->pcrlen == 0) {          /* full coverage was set  */
 			net_dbg_ratelimited("UDPLITE6: partial coverage %d while full coverage %d requested\n",
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index eecac1b7148e..cf2a0ce15c1c 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -111,9 +111,7 @@ int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb)
 {
 	memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
 
-#ifdef CONFIG_NETFILTER
 	IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED;
-#endif
 
 	return xfrm_output(sk, skb);
 }
diff --git a/net/key/af_key.c b/net/key/af_key.c
index fe5fc4bab7ee..d38988087ead 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -2402,7 +2402,7 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, const struct sa
 			return err;
 	}
 
-	xp = xfrm_policy_bysel_ctx(net, DUMMY_MARK, 0, XFRM_POLICY_TYPE_MAIN,
+	xp = xfrm_policy_bysel_ctx(net, &dummy_mark, 0, XFRM_POLICY_TYPE_MAIN,
 				   pol->sadb_x_policy_dir - 1, &sel, pol_ctx,
 				   1, &err);
 	security_xfrm_policy_free(pol_ctx);
@@ -2653,7 +2653,7 @@ static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, const struct sadb_
 		return -EINVAL;
 
 	delete = (hdr->sadb_msg_type == SADB_X_SPDDELETE2);
-	xp = xfrm_policy_byid(net, DUMMY_MARK, 0, XFRM_POLICY_TYPE_MAIN,
+	xp = xfrm_policy_byid(net, &dummy_mark, 0, XFRM_POLICY_TYPE_MAIN,
 			      dir, pol->sadb_x_policy_id, delete, &err);
 	if (xp == NULL)
 		return -ENOENT;
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 105e5a7092e7..4399c8466fe0 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -322,8 +322,13 @@ int l2tp_session_register(struct l2tp_session *session,
 
 		spin_lock_bh(&pn->l2tp_session_hlist_lock);
 
+		/* IP encap expects session IDs to be globally unique, while
+		 * UDP encap doesn't.
+		 */
 		hlist_for_each_entry(session_walk, g_head, global_hlist)
-			if (session_walk->session_id == session->session_id) {
+			if (session_walk->session_id == session->session_id &&
+			    (session_walk->tunnel->encap == L2TP_ENCAPTYPE_IP ||
+			     tunnel->encap == L2TP_ENCAPTYPE_IP)) {
 				err = -EEXIST;
 				goto err_tlock_pnlock;
 			}
@@ -1025,6 +1030,7 @@ static void l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb,
 
 	/* Queue the packet to IP for output */
 	skb->ignore_df = 1;
+	skb_dst_drop(skb);
 #if IS_ENABLED(CONFIG_IPV6)
 	if (l2tp_sk_is_v6(tunnel->sock))
 		error = inet6_csk_xmit(tunnel->sock, skb, NULL);
@@ -1096,10 +1102,6 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
 		goto out_unlock;
 	}
 
-	/* Get routing info from the tunnel socket */
-	skb_dst_drop(skb);
-	skb_dst_set(skb, sk_dst_check(sk, 0));
-
 	inet = inet_sk(sk);
 	fl = &inet->cork.fl;
 	switch (tunnel->encap) {
@@ -1455,6 +1457,9 @@ static int l2tp_validate_socket(const struct sock *sk, const struct net *net,
 	if (sk->sk_type != SOCK_DGRAM)
 		return -EPROTONOSUPPORT;
 
+	if (sk->sk_family != PF_INET && sk->sk_family != PF_INET6)
+		return -EPROTONOSUPPORT;
+
 	if ((encap == L2TP_ENCAPTYPE_UDP && sk->sk_protocol != IPPROTO_UDP) ||
 	    (encap == L2TP_ENCAPTYPE_IP && sk->sk_protocol != IPPROTO_L2TP))
 		return -EPROTONOSUPPORT;
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 622833317dcb..ec33c3768727 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -20,7 +20,6 @@
 #include <net/icmp.h>
 #include <net/udp.h>
 #include <net/inet_common.h>
-#include <net/inet_hashtables.h>
 #include <net/tcp_states.h>
 #include <net/protocol.h>
 #include <net/xfrm.h>
@@ -209,15 +208,31 @@ discard:
 	return 0;
 }
 
-static int l2tp_ip_open(struct sock *sk)
+static int l2tp_ip_hash(struct sock *sk)
 {
-	/* Prevent autobind. We don't have ports. */
-	inet_sk(sk)->inet_num = IPPROTO_L2TP;
+	if (sk_unhashed(sk)) {
+		write_lock_bh(&l2tp_ip_lock);
+		sk_add_node(sk, &l2tp_ip_table);
+		write_unlock_bh(&l2tp_ip_lock);
+	}
+	return 0;
+}
 
+static void l2tp_ip_unhash(struct sock *sk)
+{
+	if (sk_unhashed(sk))
+		return;
 	write_lock_bh(&l2tp_ip_lock);
-	sk_add_node(sk, &l2tp_ip_table);
+	sk_del_node_init(sk);
 	write_unlock_bh(&l2tp_ip_lock);
+}
+
+static int l2tp_ip_open(struct sock *sk)
+{
+	/* Prevent autobind. We don't have ports. */
+	inet_sk(sk)->inet_num = IPPROTO_L2TP;
 
+	l2tp_ip_hash(sk);
 	return 0;
 }
 
@@ -594,8 +609,8 @@ static struct proto l2tp_ip_prot = {
 	.sendmsg	   = l2tp_ip_sendmsg,
 	.recvmsg	   = l2tp_ip_recvmsg,
 	.backlog_rcv	   = l2tp_ip_backlog_recv,
-	.hash		   = inet_hash,
-	.unhash		   = inet_unhash,
+	.hash		   = l2tp_ip_hash,
+	.unhash		   = l2tp_ip_unhash,
 	.obj_size	   = sizeof(struct l2tp_ip_sock),
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_ip_setsockopt,
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index a504c6a418d3..e2d44e8b77d0 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -20,8 +20,6 @@
 #include <net/icmp.h>
 #include <net/udp.h>
 #include <net/inet_common.h>
-#include <net/inet_hashtables.h>
-#include <net/inet6_hashtables.h>
 #include <net/tcp_states.h>
 #include <net/protocol.h>
 #include <net/xfrm.h>
@@ -222,15 +220,31 @@ discard:
 	return 0;
 }
 
-static int l2tp_ip6_open(struct sock *sk)
+static int l2tp_ip6_hash(struct sock *sk)
 {
-	/* Prevent autobind. We don't have ports. */
-	inet_sk(sk)->inet_num = IPPROTO_L2TP;
+	if (sk_unhashed(sk)) {
+		write_lock_bh(&l2tp_ip6_lock);
+		sk_add_node(sk, &l2tp_ip6_table);
+		write_unlock_bh(&l2tp_ip6_lock);
+	}
+	return 0;
+}
 
+static void l2tp_ip6_unhash(struct sock *sk)
+{
+	if (sk_unhashed(sk))
+		return;
 	write_lock_bh(&l2tp_ip6_lock);
-	sk_add_node(sk, &l2tp_ip6_table);
+	sk_del_node_init(sk);
 	write_unlock_bh(&l2tp_ip6_lock);
+}
+
+static int l2tp_ip6_open(struct sock *sk)
+{
+	/* Prevent autobind. We don't have ports. */
+	inet_sk(sk)->inet_num = IPPROTO_L2TP;
 
+	l2tp_ip6_hash(sk);
 	return 0;
 }
 
@@ -728,8 +742,8 @@ static struct proto l2tp_ip6_prot = {
 	.sendmsg	   = l2tp_ip6_sendmsg,
 	.recvmsg	   = l2tp_ip6_recvmsg,
 	.backlog_rcv	   = l2tp_ip6_backlog_recv,
-	.hash		   = inet6_hash,
-	.unhash		   = inet_unhash,
+	.hash		   = l2tp_ip6_hash,
+	.unhash		   = l2tp_ip6_unhash,
 	.obj_size	   = sizeof(struct l2tp_ip6_sock),
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_ipv6_setsockopt,
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index f5a9bdc4980c..ebb381c3f1b9 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -920,51 +920,51 @@ static const struct genl_ops l2tp_nl_ops[] = {
 		.cmd = L2TP_CMD_TUNNEL_CREATE,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_tunnel_create,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_TUNNEL_DELETE,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_tunnel_delete,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_TUNNEL_MODIFY,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_tunnel_modify,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_TUNNEL_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_tunnel_get,
 		.dumpit = l2tp_nl_cmd_tunnel_dump,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_SESSION_CREATE,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_session_create,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_SESSION_DELETE,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_session_delete,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_SESSION_MODIFY,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_session_modify,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_SESSION_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_session_get,
 		.dumpit = l2tp_nl_cmd_session_dump,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 };
 
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 2017b7d780f5..e56b3ef0d5bc 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -269,6 +269,10 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr)
 
 	if (!sock_flag(sk, SOCK_ZAPPED))
 		goto out;
+	if (!addr->sllc_arphrd)
+		addr->sllc_arphrd = ARPHRD_ETHER;
+	if (addr->sllc_arphrd != ARPHRD_ETHER)
+		goto out;
 	rc = -ENODEV;
 	if (sk->sk_bound_dev_if) {
 		llc->dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if);
@@ -324,7 +328,9 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen)
 	if (unlikely(!sock_flag(sk, SOCK_ZAPPED) || addrlen != sizeof(*addr)))
 		goto out;
 	rc = -EAFNOSUPPORT;
-	if (unlikely(addr->sllc_family != AF_LLC))
+	if (!addr->sllc_arphrd)
+		addr->sllc_arphrd = ARPHRD_ETHER;
+	if (unlikely(addr->sllc_family != AF_LLC || addr->sllc_arphrd != ARPHRD_ETHER))
 		goto out;
 	dprintk("%s: binding %02X\n", __func__, addr->sllc_sap);
 	rc = -ENODEV;
@@ -332,8 +338,6 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen)
 	if (sk->sk_bound_dev_if) {
 		llc->dev = dev_get_by_index_rcu(&init_net, sk->sk_bound_dev_if);
 		if (llc->dev) {
-			if (!addr->sllc_arphrd)
-				addr->sllc_arphrd = llc->dev->type;
 			if (is_zero_ether_addr(addr->sllc_mac))
 				memcpy(addr->sllc_mac, llc->dev->dev_addr,
 				       IFHWADDRLEN);
diff --git a/net/llc/llc_station.c b/net/llc/llc_station.c
index 204a8351efff..c29170e767a8 100644
--- a/net/llc/llc_station.c
+++ b/net/llc/llc_station.c
@@ -32,7 +32,7 @@ static int llc_stat_ev_rx_null_dsap_xid_c(struct sk_buff *skb)
 	return LLC_PDU_IS_CMD(pdu) &&			/* command PDU */
 	       LLC_PDU_TYPE_IS_U(pdu) &&		/* U type PDU */
 	       LLC_U_PDU_CMD(pdu) == LLC_1_PDU_CMD_XID &&
-	       !pdu->dsap ? 0 : 1;			/* NULL DSAP value */
+	       !pdu->dsap;				/* NULL DSAP value */
 }
 
 static int llc_stat_ev_rx_null_dsap_test_c(struct sk_buff *skb)
@@ -42,7 +42,7 @@ static int llc_stat_ev_rx_null_dsap_test_c(struct sk_buff *skb)
 	return LLC_PDU_IS_CMD(pdu) &&			/* command PDU */
 	       LLC_PDU_TYPE_IS_U(pdu) &&		/* U type PDU */
 	       LLC_U_PDU_CMD(pdu) == LLC_1_PDU_CMD_TEST &&
-	       !pdu->dsap ? 0 : 1;			/* NULL DSAP */
+	       !pdu->dsap;				/* NULL DSAP */
 }
 
 static int llc_station_ac_send_xid_r(struct sk_buff *skb)
diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig
index 0227cce9685e..0c93b1b7a826 100644
--- a/net/mac80211/Kconfig
+++ b/net/mac80211/Kconfig
@@ -3,7 +3,7 @@ config MAC80211
 	tristate "Generic IEEE 802.11 Networking Stack (mac80211)"
 	depends on CFG80211
 	select CRYPTO
-	select CRYPTO_ARC4
+	select CRYPTO_LIB_ARC4
 	select CRYPTO_AES
 	select CRYPTO_CCM
 	select CRYPTO_GCM
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index c4ac767e5ac9..573b7de8a870 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <net/net_namespace.h>
 #include <linux/rcupdate.h>
+#include <linux/fips.h>
 #include <linux/if_ether.h>
 #include <net/cfg80211.h>
 #include "ieee80211_i.h"
@@ -402,9 +403,8 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev,
 	case WLAN_CIPHER_SUITE_WEP40:
 	case WLAN_CIPHER_SUITE_TKIP:
 	case WLAN_CIPHER_SUITE_WEP104:
-		if (IS_ERR(local->wep_tx_tfm))
+		if (WARN_ON_ONCE(fips_enabled))
 			return -EINVAL;
-		break;
 	case WLAN_CIPHER_SUITE_CCMP:
 	case WLAN_CIPHER_SUITE_CCMP_256:
 	case WLAN_CIPHER_SUITE_AES_CMAC:
@@ -2134,6 +2134,7 @@ static int ieee80211_leave_mesh(struct wiphy *wiphy, struct net_device *dev)
 	ieee80211_stop_mesh(sdata);
 	mutex_lock(&sdata->local->mtx);
 	ieee80211_vif_release_channel(sdata);
+	kfree(sdata->u.mesh.ie);
 	mutex_unlock(&sdata->local->mtx);
 
 	return 0;
@@ -2948,6 +2949,28 @@ static int ieee80211_start_radar_detection(struct wiphy *wiphy,
 	return err;
 }
 
+static void ieee80211_end_cac(struct wiphy *wiphy,
+			      struct net_device *dev)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	struct ieee80211_local *local = sdata->local;
+
+	mutex_lock(&local->mtx);
+	list_for_each_entry(sdata, &local->interfaces, list) {
+		/* it might be waiting for the local->mtx, but then
+		 * by the time it gets it, sdata->wdev.cac_started
+		 * will no longer be true
+		 */
+		cancel_delayed_work(&sdata->dfs_cac_timer_work);
+
+		if (sdata->wdev.cac_started) {
+			ieee80211_vif_release_channel(sdata);
+			sdata->wdev.cac_started = false;
+		}
+	}
+	mutex_unlock(&local->mtx);
+}
+
 static struct cfg80211_beacon_data *
 cfg80211_beacon_dup(struct cfg80211_beacon_data *beacon)
 {
@@ -4017,6 +4040,7 @@ const struct cfg80211_ops mac80211_config_ops = {
 #endif
 	.get_channel = ieee80211_cfg_get_channel,
 	.start_radar_detection = ieee80211_start_radar_detection,
+	.end_cac = ieee80211_end_cac,
 	.channel_switch = ieee80211_channel_switch,
 	.set_qos_map = ieee80211_set_qos_map,
 	.set_ap_chanwidth = ieee80211_set_ap_chanwidth,
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 6396d46a9a71..004e2e3adb88 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1255,8 +1255,8 @@ struct ieee80211_local {
 
 	struct rate_control_ref *rate_ctrl;
 
-	struct crypto_cipher *wep_tx_tfm;
-	struct crypto_cipher *wep_rx_tfm;
+	struct arc4_ctx wep_tx_ctx;
+	struct arc4_ctx wep_rx_ctx;
 	u32 wep_iv;
 
 	/* see iface.c */
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 157ff5f890d2..baa91b4aacd3 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -781,7 +781,7 @@ int ieee80211_key_link(struct ieee80211_key *key,
 
 	/* Non-pairwise keys must also not switch the cipher on rekey */
 	if (!pairwise) {
-		if (key && old_key && old_key->conf.cipher != key->conf.cipher)
+		if (old_key && old_key->conf.cipher != key->conf.cipher)
 			goto out;
 	}
 
diff --git a/net/mac80211/key.h b/net/mac80211/key.h
index be118c39433f..b8b9cd743bf4 100644
--- a/net/mac80211/key.h
+++ b/net/mac80211/key.h
@@ -11,6 +11,7 @@
 #include <linux/list.h>
 #include <linux/crypto.h>
 #include <linux/rcupdate.h>
+#include <crypto/arc4.h>
 #include <net/mac80211.h>
 
 #define NUM_DEFAULT_KEYS 4
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 55583b71ffaf..27045a9b4785 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -10,6 +10,7 @@
 
 #include <net/mac80211.h>
 #include <linux/module.h>
+#include <linux/fips.h>
 #include <linux/init.h>
 #include <linux/netdevice.h>
 #include <linux/types.h>
@@ -730,8 +731,7 @@ EXPORT_SYMBOL(ieee80211_alloc_hw_nm);
 
 static int ieee80211_init_cipher_suites(struct ieee80211_local *local)
 {
-	bool have_wep = !(IS_ERR(local->wep_tx_tfm) ||
-			  IS_ERR(local->wep_rx_tfm));
+	bool have_wep = !fips_enabled; /* FIPS does not permit the use of RC4 */
 	bool have_mfp = ieee80211_hw_check(&local->hw, MFP_CAPABLE);
 	int n_suites = 0, r = 0, w = 0;
 	u32 *suites;
@@ -1044,7 +1044,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 		local->hw.wiphy->signal_type = CFG80211_SIGNAL_TYPE_UNSPEC;
 		if (hw->max_signal <= 0) {
 			result = -EINVAL;
-			goto fail_wiphy_register;
+			goto fail_workqueue;
 		}
 	}
 
@@ -1112,7 +1112,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 
 	result = ieee80211_init_cipher_suites(local);
 	if (result < 0)
-		goto fail_wiphy_register;
+		goto fail_workqueue;
 
 	if (!local->ops->remain_on_channel)
 		local->hw.wiphy->max_remain_on_channel_duration = 5000;
@@ -1138,10 +1138,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 
 	local->hw.wiphy->max_num_csa_counters = IEEE80211_MAX_CSA_COUNTERS_NUM;
 
-	result = wiphy_register(local->hw.wiphy);
-	if (result < 0)
-		goto fail_wiphy_register;
-
 	/*
 	 * We use the number of queues for feature tests (QoS, HT) internally
 	 * so restrict them appropriately.
@@ -1164,8 +1160,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 	local->tx_headroom = max_t(unsigned int , local->hw.extra_tx_headroom,
 				   IEEE80211_TX_STATUS_HEADROOM);
 
-	debugfs_hw_add(local);
-
 	/*
 	 * if the driver doesn't specify a max listen interval we
 	 * use 5 which should be a safe default
@@ -1197,9 +1191,9 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 		goto fail_flows;
 
 	rtnl_lock();
-
 	result = ieee80211_init_rate_ctrl_alg(local,
 					      hw->rate_control_algorithm);
+	rtnl_unlock();
 	if (result < 0) {
 		wiphy_debug(local->hw.wiphy,
 			    "Failed to initialize rate control algorithm\n");
@@ -1253,6 +1247,15 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 		local->sband_allocated |= BIT(band);
 	}
 
+	result = wiphy_register(local->hw.wiphy);
+	if (result < 0)
+		goto fail_wiphy_register;
+
+	debugfs_hw_add(local);
+	rate_control_add_debugfs(local);
+
+	rtnl_lock();
+
 	/* add one default STA interface if supported */
 	if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_STATION) &&
 	    !ieee80211_hw_check(hw, NO_AUTO_VIF)) {
@@ -1292,18 +1295,17 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 #if defined(CONFIG_INET) || defined(CONFIG_IPV6)
  fail_ifa:
 #endif
+	wiphy_unregister(local->hw.wiphy);
+ fail_wiphy_register:
 	rtnl_lock();
 	rate_control_deinitialize(local);
 	ieee80211_remove_interfaces(local);
- fail_rate:
 	rtnl_unlock();
-	ieee80211_led_exit(local);
-	ieee80211_wep_free(local);
+ fail_rate:
  fail_flows:
+	ieee80211_led_exit(local);
 	destroy_workqueue(local->workqueue);
  fail_workqueue:
-	wiphy_unregister(local->hw.wiphy);
- fail_wiphy_register:
 	if (local->wiphy_ciphers_allocated)
 		kfree(local->hw.wiphy->cipher_suites);
 	kfree(local->int_scan_req);
@@ -1353,9 +1355,8 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw)
 	skb_queue_purge(&local->skb_queue_unreliable);
 	skb_queue_purge(&local->skb_queue_tdls_chsw);
 
-	destroy_workqueue(local->workqueue);
 	wiphy_unregister(local->hw.wiphy);
-	ieee80211_wep_free(local);
+	destroy_workqueue(local->workqueue);
 	ieee80211_led_exit(local);
 	kfree(local->int_scan_req);
 }
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 2e7fa743c892..13ec12d64428 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -1195,15 +1195,15 @@ static void ieee80211_mesh_rx_bcn_presp(struct ieee80211_sub_if_data *sdata,
 		    sdata->u.mesh.mshcfg.rssi_threshold < rx_status->signal)
 			mesh_neighbour_update(sdata, mgmt->sa, &elems,
 					      rx_status);
+
+		if (ifmsh->csa_role != IEEE80211_MESH_CSA_ROLE_INIT &&
+		    !sdata->vif.csa_active)
+			ieee80211_mesh_process_chnswitch(sdata, &elems, true);
 	}
 
 	if (ifmsh->sync_ops)
 		ifmsh->sync_ops->rx_bcn_presp(sdata,
 			stype, mgmt, &elems, rx_status);
-
-	if (ifmsh->csa_role != IEEE80211_MESH_CSA_ROLE_INIT &&
-	    !sdata->vif.csa_active)
-		ieee80211_mesh_process_chnswitch(sdata, &elems, true);
 }
 
 int ieee80211_mesh_finish_csa(struct ieee80211_sub_if_data *sdata)
@@ -1311,6 +1311,9 @@ static void mesh_rx_csa_frame(struct ieee80211_sub_if_data *sdata,
 	ieee802_11_parse_elems(pos, len - baselen, true, &elems,
 			       mgmt->bssid, NULL);
 
+	if (!mesh_matches_local(sdata, &elems))
+		return;
+
 	ifmsh->chsw_ttl = elems.mesh_chansw_params_ie->mesh_ttl;
 	if (!--ifmsh->chsw_ttl)
 		fwd_csa = false;
diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c
index 68af62306385..aa5150929996 100644
--- a/net/mac80211/mesh_hwmp.c
+++ b/net/mac80211/mesh_hwmp.c
@@ -328,6 +328,9 @@ u32 airtime_link_metric_get(struct ieee80211_local *local,
 	unsigned long fail_avg =
 		ewma_mesh_fail_avg_read(&sta->mesh->fail_avg);
 
+	if (sta->mesh->plink_state != NL80211_PLINK_ESTAB)
+		return MAX_METRIC;
+
 	/* Try to get rate based on HW/SW RC algorithm.
 	 * Rate is returned in units of Kbps, correct this
 	 * to comply with airtime calculation units
@@ -1100,7 +1103,14 @@ void mesh_path_start_discovery(struct ieee80211_sub_if_data *sdata)
 	mesh_path_sel_frame_tx(MPATH_PREQ, 0, sdata->vif.addr, ifmsh->sn,
 			       target_flags, mpath->dst, mpath->sn, da, 0,
 			       ttl, lifetime, 0, ifmsh->preq_id++, sdata);
+
+	spin_lock_bh(&mpath->state_lock);
+	if (mpath->flags & MESH_PATH_DELETED) {
+		spin_unlock_bh(&mpath->state_lock);
+		goto enddiscovery;
+	}
 	mod_timer(&mpath->timer, jiffies + mpath->discovery_timeout);
+	spin_unlock_bh(&mpath->state_lock);
 
 enddiscovery:
 	rcu_read_unlock();
@@ -1149,7 +1159,8 @@ int mesh_nexthop_resolve(struct ieee80211_sub_if_data *sdata,
 		}
 	}
 
-	if (!(mpath->flags & MESH_PATH_RESOLVING))
+	if (!(mpath->flags & MESH_PATH_RESOLVING) &&
+	    mesh_path_sel_is_hwmp(sdata))
 		mesh_queue_preq(mpath, PREQ_Q_F_START);
 
 	if (skb_queue_len(&mpath->frame_queue) >= MESH_FRAME_QUEUE_LEN)
diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c
index 117519bf33d6..aca608ae313f 100644
--- a/net/mac80211/mesh_pathtbl.c
+++ b/net/mac80211/mesh_pathtbl.c
@@ -521,6 +521,7 @@ static void mesh_path_free_rcu(struct mesh_table *tbl,
 	del_timer_sync(&mpath->timer);
 	atomic_dec(&sdata->u.mesh.mpaths);
 	atomic_dec(&tbl->entries);
+	mesh_path_flush_pending(mpath);
 	kfree_rcu(mpath, rcu);
 }
 
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index e75f1b4b3ce3..6377a5145106 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -8,10 +8,11 @@
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright (C) 2015 - 2017 Intel Deutschland GmbH
- * Copyright (C) 2018 - 2019 Intel Corporation
+ * Copyright (C) 2018 - 2020 Intel Corporation
  */
 
 #include <linux/delay.h>
+#include <linux/fips.h>
 #include <linux/if_ether.h>
 #include <linux/skbuff.h>
 #include <linux/if_arp.h>
@@ -1310,7 +1311,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 	if (!res) {
 		ch_switch.timestamp = timestamp;
 		ch_switch.device_timestamp = device_timestamp;
-		ch_switch.block_tx =  beacon ? csa_ie.mode : 0;
+		ch_switch.block_tx = csa_ie.mode;
 		ch_switch.chandef = csa_ie.chandef;
 		ch_switch.count = csa_ie.count;
 		ch_switch.delay = csa_ie.max_switch_time;
@@ -1403,7 +1404,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 
 	sdata->vif.csa_active = true;
 	sdata->csa_chandef = csa_ie.chandef;
-	sdata->csa_block_tx = ch_switch.block_tx;
+	sdata->csa_block_tx = csa_ie.mode;
 	ifmgd->csa_ignored_same_chan = false;
 
 	if (sdata->csa_block_tx)
@@ -1437,7 +1438,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 	 * reset when the disconnection worker runs.
 	 */
 	sdata->vif.csa_active = true;
-	sdata->csa_block_tx = ch_switch.block_tx;
+	sdata->csa_block_tx = csa_ie.mode;
 
 	ieee80211_queue_work(&local->hw, &ifmgd->csa_connection_drop_work);
 	mutex_unlock(&local->chanctx_mtx);
@@ -2458,7 +2459,7 @@ void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata,
 	if (!ieee80211_is_data(hdr->frame_control))
 	    return;
 
-	if (ieee80211_is_nullfunc(hdr->frame_control) &&
+	if (ieee80211_is_any_nullfunc(hdr->frame_control) &&
 	    sdata->u.mgd.probe_send_count > 0) {
 		if (ack)
 			ieee80211_sta_reset_conn_monitor(sdata);
@@ -2954,7 +2955,7 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata,
 	    (auth_transaction == 2 &&
 	     ifmgd->auth_data->expected_transaction == 2)) {
 		if (!ieee80211_mark_sta_auth(sdata, bssid))
-			goto out_err;
+			return; /* ignore frame -- wait for timeout */
 	} else if (ifmgd->auth_data->algorithm == WLAN_AUTH_SAE &&
 		   auth_transaction == 2) {
 		sdata_info(sdata, "SAE peer confirmed\n");
@@ -2962,10 +2963,6 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata,
 	}
 
 	cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len);
-	return;
- out_err:
-	mutex_unlock(&sdata->local->sta_mtx);
-	/* ignore frame -- wait for timeout */
 }
 
 #define case_WLAN(type) \
@@ -5056,7 +5053,7 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata,
 		auth_alg = WLAN_AUTH_OPEN;
 		break;
 	case NL80211_AUTHTYPE_SHARED_KEY:
-		if (IS_ERR(local->wep_tx_tfm))
+		if (fips_enabled)
 			return -EOPNOTSUPP;
 		auth_alg = WLAN_AUTH_SHARED_KEY;
 		break;
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index 47ee36677c2b..39954e77aaca 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -214,17 +214,16 @@ static ssize_t rcname_read(struct file *file, char __user *userbuf,
 				       ref->ops->name, len);
 }
 
-static const struct file_operations rcname_ops = {
+const struct file_operations rcname_ops = {
 	.read = rcname_read,
 	.open = simple_open,
 	.llseek = default_llseek,
 };
 #endif
 
-static struct rate_control_ref *rate_control_alloc(const char *name,
-					    struct ieee80211_local *local)
+static struct rate_control_ref *
+rate_control_alloc(const char *name, struct ieee80211_local *local)
 {
-	struct dentry *debugfsdir = NULL;
 	struct rate_control_ref *ref;
 
 	ref = kmalloc(sizeof(struct rate_control_ref), GFP_KERNEL);
@@ -234,13 +233,7 @@ static struct rate_control_ref *rate_control_alloc(const char *name,
 	if (!ref->ops)
 		goto free;
 
-#ifdef CONFIG_MAC80211_DEBUGFS
-	debugfsdir = debugfs_create_dir("rc", local->hw.wiphy->debugfsdir);
-	local->debugfs.rcdir = debugfsdir;
-	debugfs_create_file("name", 0400, debugfsdir, ref, &rcname_ops);
-#endif
-
-	ref->priv = ref->ops->alloc(&local->hw, debugfsdir);
+	ref->priv = ref->ops->alloc(&local->hw);
 	if (!ref->priv)
 		goto free;
 	return ref;
diff --git a/net/mac80211/rate.h b/net/mac80211/rate.h
index 5d5348bc41ec..db96d2da5c55 100644
--- a/net/mac80211/rate.h
+++ b/net/mac80211/rate.h
@@ -69,6 +69,29 @@ static inline void rate_control_remove_sta_debugfs(struct sta_info *sta)
 #endif
 }
 
+extern const struct file_operations rcname_ops;
+
+static inline void rate_control_add_debugfs(struct ieee80211_local *local)
+{
+#ifdef CONFIG_MAC80211_DEBUGFS
+	struct dentry *debugfsdir;
+
+	if (!local->rate_ctrl)
+		return;
+
+	if (!local->rate_ctrl->ops->add_debugfs)
+		return;
+
+	debugfsdir = debugfs_create_dir("rc", local->hw.wiphy->debugfsdir);
+	local->debugfs.rcdir = debugfsdir;
+	debugfs_create_file("name", 0400, debugfsdir,
+			    local->rate_ctrl, &rcname_ops);
+
+	local->rate_ctrl->ops->add_debugfs(&local->hw, local->rate_ctrl->priv,
+					   debugfsdir);
+#endif
+}
+
 void ieee80211_check_rate_mask(struct ieee80211_sub_if_data *sdata);
 
 /* Get a reference to the rate control algorithm. If `name' is NULL, get the
diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c
index 298a1acb3ce5..1c5e843dede2 100644
--- a/net/mac80211/rc80211_minstrel_ht.c
+++ b/net/mac80211/rc80211_minstrel_ht.c
@@ -1431,7 +1431,7 @@ minstrel_ht_init_cck_rates(struct minstrel_priv *mp)
 }
 
 static void *
-minstrel_ht_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir)
+minstrel_ht_alloc(struct ieee80211_hw *hw)
 {
 	struct minstrel_priv *mp;
 
@@ -1466,16 +1466,22 @@ minstrel_ht_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir)
 	mp->hw = hw;
 	mp->update_interval = 100;
 
+	minstrel_ht_init_cck_rates(mp);
+
+	return mp;
+}
+
 #ifdef CONFIG_MAC80211_DEBUGFS
+static void minstrel_ht_add_debugfs(struct ieee80211_hw *hw, void *priv,
+				    struct dentry *debugfsdir)
+{
+	struct minstrel_priv *mp = priv;
+
 	mp->fixed_rate_idx = (u32) -1;
 	debugfs_create_u32("fixed_rate_idx", S_IRUGO | S_IWUGO, debugfsdir,
 			   &mp->fixed_rate_idx);
-#endif
-
-	minstrel_ht_init_cck_rates(mp);
-
-	return mp;
 }
+#endif
 
 static void
 minstrel_ht_free(void *priv)
@@ -1514,6 +1520,7 @@ static const struct rate_control_ops mac80211_minstrel_ht = {
 	.alloc = minstrel_ht_alloc,
 	.free = minstrel_ht_free,
 #ifdef CONFIG_MAC80211_DEBUGFS
+	.add_debugfs = minstrel_ht_add_debugfs,
 	.add_sta_debugfs = minstrel_ht_add_sta_debugfs,
 #endif
 	.get_expected_throughput = minstrel_ht_get_expected_throughput,
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 768d14c9a716..5062532a4028 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1450,8 +1450,7 @@ ieee80211_rx_h_check_dup(struct ieee80211_rx_data *rx)
 		return RX_CONTINUE;
 
 	if (ieee80211_is_ctl(hdr->frame_control) ||
-	    ieee80211_is_nullfunc(hdr->frame_control) ||
-	    ieee80211_is_qos_nullfunc(hdr->frame_control) ||
+	    ieee80211_is_any_nullfunc(hdr->frame_control) ||
 	    is_multicast_ether_addr(hdr->addr1))
 		return RX_CONTINUE;
 
@@ -1838,8 +1837,7 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx)
 	 * Drop (qos-)data::nullfunc frames silently, since they
 	 * are used only to control station power saving mode.
 	 */
-	if (ieee80211_is_nullfunc(hdr->frame_control) ||
-	    ieee80211_is_qos_nullfunc(hdr->frame_control)) {
+	if (ieee80211_is_any_nullfunc(hdr->frame_control)) {
 		I802_DEBUG_INC(rx->local->rx_handlers_drop_nullfunc);
 
 		/*
@@ -2307,6 +2305,7 @@ static int ieee80211_802_1x_port_control(struct ieee80211_rx_data *rx)
 
 static int ieee80211_drop_unencrypted(struct ieee80211_rx_data *rx, __le16 fc)
 {
+	struct ieee80211_hdr *hdr = (void *)rx->skb->data;
 	struct sk_buff *skb = rx->skb;
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
 
@@ -2317,9 +2316,34 @@ static int ieee80211_drop_unencrypted(struct ieee80211_rx_data *rx, __le16 fc)
 	if (status->flag & RX_FLAG_DECRYPTED)
 		return 0;
 
+	/* check mesh EAPOL frames first */
+	if (unlikely(rx->sta && ieee80211_vif_is_mesh(&rx->sdata->vif) &&
+		     ieee80211_is_data(fc))) {
+		struct ieee80211s_hdr *mesh_hdr;
+		u16 hdr_len = ieee80211_hdrlen(fc);
+		u16 ethertype_offset;
+		__be16 ethertype;
+
+		if (!ether_addr_equal(hdr->addr1, rx->sdata->vif.addr))
+			goto drop_check;
+
+		/* make sure fixed part of mesh header is there, also checks skb len */
+		if (!pskb_may_pull(rx->skb, hdr_len + 6))
+			goto drop_check;
+
+		mesh_hdr = (struct ieee80211s_hdr *)(skb->data + hdr_len);
+		ethertype_offset = hdr_len + ieee80211_get_mesh_hdrlen(mesh_hdr) +
+				   sizeof(rfc1042_header);
+
+		if (skb_copy_bits(rx->skb, ethertype_offset, &ethertype, 2) == 0 &&
+		    ethertype == rx->sdata->control_port_protocol)
+			return 0;
+	}
+
+drop_check:
 	/* Drop unencrypted frames if key is set. */
 	if (unlikely(!ieee80211_has_protected(fc) &&
-		     !ieee80211_is_nullfunc(fc) &&
+		     !ieee80211_is_any_nullfunc(fc) &&
 		     ieee80211_is_data(fc) && rx->key))
 		return -EACCES;
 
@@ -4105,7 +4129,7 @@ void __ieee80211_check_fast_rx_iface(struct ieee80211_sub_if_data *sdata)
 
 	lockdep_assert_held(&local->sta_mtx);
 
-	list_for_each_entry_rcu(sta, &local->sta_list, list) {
+	list_for_each_entry(sta, &local->sta_list, list) {
 		if (sdata != sta->sdata &&
 		    (!sta->sdata->bss || sta->sdata->bss != sdata->bss))
 			continue;
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 044db4c698e9..2e217664f146 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -4,7 +4,7 @@
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright (C) 2015 - 2017 Intel Deutschland GmbH
- * Copyright (C) 2018 Intel Corporation
+ * Copyright (C) 2018-2020 Intel Corporation
  */
 
 #include <linux/module.h>
@@ -217,7 +217,8 @@ struct sta_info *sta_info_get_by_idx(struct ieee80211_sub_if_data *sdata,
 	struct sta_info *sta;
 	int i = 0;
 
-	list_for_each_entry_rcu(sta, &local->sta_list, list) {
+	list_for_each_entry_rcu(sta, &local->sta_list, list,
+				lockdep_is_held(&local->sta_mtx)) {
 		if (sdata != sta->sdata)
 			continue;
 		if (i < idx) {
@@ -991,6 +992,11 @@ static void __sta_info_destroy_part2(struct sta_info *sta)
 	might_sleep();
 	lockdep_assert_held(&local->sta_mtx);
 
+	if (sta->sta_state == IEEE80211_STA_AUTHORIZED) {
+		ret = sta_info_move_state(sta, IEEE80211_STA_ASSOC);
+		WARN_ON_ONCE(ret);
+	}
+
 	/* now keys can no longer be reached */
 	ieee80211_free_sta_keys(local, sta);
 
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 17ed4d915707..e541cee51208 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -484,8 +484,7 @@ static void ieee80211_report_ack_skb(struct ieee80211_local *local,
 		rcu_read_lock();
 		sdata = ieee80211_sdata_from_skb(local, skb);
 		if (sdata) {
-			if (ieee80211_is_nullfunc(hdr->frame_control) ||
-			    ieee80211_is_qos_nullfunc(hdr->frame_control))
+			if (ieee80211_is_any_nullfunc(hdr->frame_control))
 				cfg80211_probe_status(sdata->dev, hdr->addr1,
 						      cookie, acked,
 						      info->status.ack_signal,
@@ -870,7 +869,7 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw,
 			I802_DEBUG_INC(local->dot11FailedCount);
 	}
 
-	if ((ieee80211_is_nullfunc(fc) || ieee80211_is_qos_nullfunc(fc)) &&
+	if (ieee80211_is_any_nullfunc(fc) &&
 	    ieee80211_has_pm(fc) &&
 	    ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS) &&
 	    !(info->flags & IEEE80211_TX_CTL_INJECTED) &&
diff --git a/net/mac80211/tkip.c b/net/mac80211/tkip.c
index 7914b8e3ce8c..e7f57bb18f6e 100644
--- a/net/mac80211/tkip.c
+++ b/net/mac80211/tkip.c
@@ -219,7 +219,7 @@ EXPORT_SYMBOL(ieee80211_get_tkip_p2k);
  * @payload_len is the length of payload (_not_ including IV/ICV length).
  * @ta is the transmitter addresses.
  */
-int ieee80211_tkip_encrypt_data(struct crypto_cipher *tfm,
+int ieee80211_tkip_encrypt_data(struct arc4_ctx *ctx,
 				struct ieee80211_key *key,
 				struct sk_buff *skb,
 				u8 *payload, size_t payload_len)
@@ -228,7 +228,7 @@ int ieee80211_tkip_encrypt_data(struct crypto_cipher *tfm,
 
 	ieee80211_get_tkip_p2k(&key->conf, skb, rc4key);
 
-	return ieee80211_wep_encrypt_data(tfm, rc4key, 16,
+	return ieee80211_wep_encrypt_data(ctx, rc4key, 16,
 					  payload, payload_len);
 }
 
@@ -236,7 +236,7 @@ int ieee80211_tkip_encrypt_data(struct crypto_cipher *tfm,
  * beginning of the buffer containing IEEE 802.11 header payload, i.e.,
  * including IV, Ext. IV, real data, Michael MIC, ICV. @payload_len is the
  * length of payload, including IV, Ext. IV, MIC, ICV.  */
-int ieee80211_tkip_decrypt_data(struct crypto_cipher *tfm,
+int ieee80211_tkip_decrypt_data(struct arc4_ctx *ctx,
 				struct ieee80211_key *key,
 				u8 *payload, size_t payload_len, u8 *ta,
 				u8 *ra, int only_iv, int queue,
@@ -263,9 +263,21 @@ int ieee80211_tkip_decrypt_data(struct crypto_cipher *tfm,
 	if ((keyid >> 6) != key->conf.keyidx)
 		return TKIP_DECRYPT_INVALID_KEYIDX;
 
-	if (rx_ctx->ctx.state != TKIP_STATE_NOT_INIT &&
-	    (iv32 < rx_ctx->iv32 ||
-	     (iv32 == rx_ctx->iv32 && iv16 <= rx_ctx->iv16)))
+	/* Reject replays if the received TSC is smaller than or equal to the
+	 * last received value in a valid message, but with an exception for
+	 * the case where a new key has been set and no valid frame using that
+	 * key has yet received and the local RSC was initialized to 0. This
+	 * exception allows the very first frame sent by the transmitter to be
+	 * accepted even if that transmitter were to use TSC 0 (IEEE 802.11
+	 * described TSC to be initialized to 1 whenever a new key is taken into
+	 * use).
+	 */
+	if (iv32 < rx_ctx->iv32 ||
+	    (iv32 == rx_ctx->iv32 &&
+	     (iv16 < rx_ctx->iv16 ||
+	      (iv16 == rx_ctx->iv16 &&
+	       (rx_ctx->iv32 || rx_ctx->iv16 ||
+		rx_ctx->ctx.state != TKIP_STATE_NOT_INIT)))))
 		return TKIP_DECRYPT_REPLAY;
 
 	if (only_iv) {
@@ -294,7 +306,7 @@ int ieee80211_tkip_decrypt_data(struct crypto_cipher *tfm,
 
 	tkip_mixing_phase2(tk, &rx_ctx->ctx, iv16, rc4key);
 
-	res = ieee80211_wep_decrypt_data(tfm, rc4key, 16, pos, payload_len - 12);
+	res = ieee80211_wep_decrypt_data(ctx, rc4key, 16, pos, payload_len - 12);
  done:
 	if (res == TKIP_DECRYPT_OK) {
 		/*
diff --git a/net/mac80211/tkip.h b/net/mac80211/tkip.h
index 676a7babdf5d..9d2f8bd36cc7 100644
--- a/net/mac80211/tkip.h
+++ b/net/mac80211/tkip.h
@@ -10,7 +10,7 @@
 #include <linux/crypto.h>
 #include "key.h"
 
-int ieee80211_tkip_encrypt_data(struct crypto_cipher *tfm,
+int ieee80211_tkip_encrypt_data(struct arc4_ctx *ctx,
 				struct ieee80211_key *key,
 				struct sk_buff *skb,
 				u8 *payload, size_t payload_len);
@@ -21,7 +21,7 @@ enum {
 	TKIP_DECRYPT_INVALID_KEYIDX = -2,
 	TKIP_DECRYPT_REPLAY = -3,
 };
-int ieee80211_tkip_decrypt_data(struct crypto_cipher *tfm,
+int ieee80211_tkip_decrypt_data(struct arc4_ctx *ctx,
 				struct ieee80211_key *key,
 				u8 *payload, size_t payload_len, u8 *ta,
 				u8 *ra, int only_iv, int queue,
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index f13eb2f61ccf..86c0159c0a6f 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -5,7 +5,7 @@
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
- * Copyright (C) 2018 Intel Corporation
+ * Copyright (C) 2018, 2020 Intel Corporation
  *
  * Transmit and frame generation functions.
  */
@@ -296,7 +296,7 @@ ieee80211_tx_h_check_assoc(struct ieee80211_tx_data *tx)
 	if (unlikely(test_bit(SCAN_SW_SCANNING, &tx->local->scanning)) &&
 	    test_bit(SDATA_STATE_OFFCHANNEL, &tx->sdata->state) &&
 	    !ieee80211_is_probe_req(hdr->frame_control) &&
-	    !ieee80211_is_nullfunc(hdr->frame_control))
+	    !ieee80211_is_any_nullfunc(hdr->frame_control))
 		/*
 		 * When software scanning only nullfunc frames (to notify
 		 * the sleep state to the AP) and probe requests (for the
@@ -2262,6 +2262,15 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb,
 						    payload[7]);
 	}
 
+	/*
+	 * Initialize skb->priority for QoS frames. This is put in the TID field
+	 * of the frame before passing it to the driver.
+	 */
+	if (ieee80211_is_data_qos(hdr->frame_control)) {
+		u8 *p = ieee80211_get_qos_ctl(hdr);
+		skb->priority = *p & IEEE80211_QOS_CTL_TAG1D_MASK;
+	}
+
 	memset(info, 0, sizeof(*info));
 
 	info->flags = IEEE80211_TX_CTL_REQ_TX_STATUS |
@@ -3578,8 +3587,26 @@ begin:
 	tx.skb = skb;
 	tx.sdata = vif_to_sdata(info->control.vif);
 
-	if (txq->sta)
+	if (txq->sta) {
 		tx.sta = container_of(txq->sta, struct sta_info, sta);
+		/*
+		 * Drop unicast frames to unauthorised stations unless they are
+		 * EAPOL frames from the local station.
+		 */
+		if (unlikely(ieee80211_is_data(hdr->frame_control) &&
+			     !ieee80211_vif_is_mesh(&tx.sdata->vif) &&
+			     tx.sdata->vif.type != NL80211_IFTYPE_OCB &&
+			     !is_multicast_ether_addr(hdr->addr1) &&
+			     !test_sta_flag(tx.sta, WLAN_STA_AUTHORIZED) &&
+			     (!(info->control.flags &
+				IEEE80211_TX_CTRL_PORT_CTRL_PROTO) ||
+			      !ether_addr_equal(tx.sdata->vif.addr,
+						hdr->addr2)))) {
+			I802_DEBUG_INC(local->tx_handlers_drop_unauth_port);
+			ieee80211_free_txskb(&local->hw, skb);
+			goto begin;
+		}
+	}
 
 	/*
 	 * The key can be removed while the packet was queued, so need to call
@@ -5048,6 +5075,7 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev,
 	struct ieee80211_local *local = sdata->local;
 	struct sk_buff *skb;
 	struct ethhdr *ehdr;
+	u32 ctrl_flags = 0;
 	u32 flags;
 
 	/* Only accept CONTROL_PORT_PROTOCOL configured in CONNECT/ASSOCIATE
@@ -5057,6 +5085,9 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev,
 	    proto != cpu_to_be16(ETH_P_PREAUTH))
 		return -EINVAL;
 
+	if (proto == sdata->control_port_protocol)
+		ctrl_flags |= IEEE80211_TX_CTRL_PORT_CTRL_PROTO;
+
 	if (unencrypted)
 		flags = IEEE80211_TX_INTFL_DONT_ENCRYPT;
 	else
@@ -5082,7 +5113,7 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev,
 	skb_reset_mac_header(skb);
 
 	local_bh_disable();
-	__ieee80211_subif_start_xmit(skb, skb->dev, flags, 0);
+	__ieee80211_subif_start_xmit(skb, skb->dev, flags, ctrl_flags);
 	local_bh_enable();
 
 	return 0;
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 21212faec6d0..cf1952193712 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1063,16 +1063,22 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action,
 				elem_parse_failed = true;
 			break;
 		case WLAN_EID_VHT_OPERATION:
-			if (elen >= sizeof(struct ieee80211_vht_operation))
+			if (elen >= sizeof(struct ieee80211_vht_operation)) {
 				elems->vht_operation = (void *)pos;
-			else
-				elem_parse_failed = true;
+				if (calc_crc)
+					crc = crc32_be(crc, pos - 2, elen + 2);
+				break;
+			}
+			elem_parse_failed = true;
 			break;
 		case WLAN_EID_OPMODE_NOTIF:
-			if (elen > 0)
+			if (elen > 0) {
 				elems->opmode_notif = pos;
-			else
-				elem_parse_failed = true;
+				if (calc_crc)
+					crc = crc32_be(crc, pos - 2, elen + 2);
+				break;
+			}
+			elem_parse_failed = true;
 			break;
 		case WLAN_EID_MESH_ID:
 			elems->mesh_id = pos;
@@ -2930,10 +2936,22 @@ bool ieee80211_chandef_vht_oper(struct ieee80211_hw *hw,
 	int cf0, cf1;
 	int ccfs0, ccfs1, ccfs2;
 	int ccf0, ccf1;
+	u32 vht_cap;
+	bool support_80_80 = false;
+	bool support_160 = false;
 
 	if (!oper || !htop)
 		return false;
 
+	vht_cap = hw->wiphy->bands[chandef->chan->band]->vht_cap.cap;
+	support_160 = (vht_cap & (IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK |
+				  IEEE80211_VHT_CAP_EXT_NSS_BW_MASK));
+	support_80_80 = ((vht_cap &
+			 IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) ||
+			(vht_cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ &&
+			 vht_cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) ||
+			((vht_cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) >>
+				    IEEE80211_VHT_CAP_EXT_NSS_BW_SHIFT > 1));
 	ccfs0 = oper->center_freq_seg0_idx;
 	ccfs1 = oper->center_freq_seg1_idx;
 	ccfs2 = (le16_to_cpu(htop->operation_mode) &
@@ -2961,10 +2979,10 @@ bool ieee80211_chandef_vht_oper(struct ieee80211_hw *hw,
 			unsigned int diff;
 
 			diff = abs(ccf1 - ccf0);
-			if (diff == 8) {
+			if ((diff == 8) && support_160) {
 				new.width = NL80211_CHAN_WIDTH_160;
 				new.center_freq1 = cf1;
-			} else if (diff > 8) {
+			} else if ((diff > 8) && support_80_80) {
 				new.width = NL80211_CHAN_WIDTH_80P80;
 				new.center_freq2 = cf1;
 			}
diff --git a/net/mac80211/wep.c b/net/mac80211/wep.c
index 3d9e92867ef0..b75c2c54e665 100644
--- a/net/mac80211/wep.c
+++ b/net/mac80211/wep.c
@@ -27,30 +27,9 @@ int ieee80211_wep_init(struct ieee80211_local *local)
 	/* start WEP IV from a random value */
 	get_random_bytes(&local->wep_iv, IEEE80211_WEP_IV_LEN);
 
-	local->wep_tx_tfm = crypto_alloc_cipher("arc4", 0, 0);
-	if (IS_ERR(local->wep_tx_tfm)) {
-		local->wep_rx_tfm = ERR_PTR(-EINVAL);
-		return PTR_ERR(local->wep_tx_tfm);
-	}
-
-	local->wep_rx_tfm = crypto_alloc_cipher("arc4", 0, 0);
-	if (IS_ERR(local->wep_rx_tfm)) {
-		crypto_free_cipher(local->wep_tx_tfm);
-		local->wep_tx_tfm = ERR_PTR(-EINVAL);
-		return PTR_ERR(local->wep_rx_tfm);
-	}
-
 	return 0;
 }
 
-void ieee80211_wep_free(struct ieee80211_local *local)
-{
-	if (!IS_ERR(local->wep_tx_tfm))
-		crypto_free_cipher(local->wep_tx_tfm);
-	if (!IS_ERR(local->wep_rx_tfm))
-		crypto_free_cipher(local->wep_rx_tfm);
-}
-
 static inline bool ieee80211_wep_weak_iv(u32 iv, int keylen)
 {
 	/*
@@ -128,21 +107,17 @@ static void ieee80211_wep_remove_iv(struct ieee80211_local *local,
 /* Perform WEP encryption using given key. data buffer must have tailroom
  * for 4-byte ICV. data_len must not include this ICV. Note: this function
  * does _not_ add IV. data = RC4(data | CRC32(data)) */
-int ieee80211_wep_encrypt_data(struct crypto_cipher *tfm, u8 *rc4key,
+int ieee80211_wep_encrypt_data(struct arc4_ctx *ctx, u8 *rc4key,
 			       size_t klen, u8 *data, size_t data_len)
 {
 	__le32 icv;
-	int i;
-
-	if (IS_ERR(tfm))
-		return -1;
 
 	icv = cpu_to_le32(~crc32_le(~0, data, data_len));
 	put_unaligned(icv, (__le32 *)(data + data_len));
 
-	crypto_cipher_setkey(tfm, rc4key, klen);
-	for (i = 0; i < data_len + IEEE80211_WEP_ICV_LEN; i++)
-		crypto_cipher_encrypt_one(tfm, data + i, data + i);
+	arc4_setkey(ctx, rc4key, klen);
+	arc4_crypt(ctx, data, data, data_len + IEEE80211_WEP_ICV_LEN);
+	memzero_explicit(ctx, sizeof(*ctx));
 
 	return 0;
 }
@@ -181,7 +156,7 @@ int ieee80211_wep_encrypt(struct ieee80211_local *local,
 	/* Add room for ICV */
 	skb_put(skb, IEEE80211_WEP_ICV_LEN);
 
-	return ieee80211_wep_encrypt_data(local->wep_tx_tfm, rc4key, keylen + 3,
+	return ieee80211_wep_encrypt_data(&local->wep_tx_ctx, rc4key, keylen + 3,
 					  iv + IEEE80211_WEP_IV_LEN, len);
 }
 
@@ -189,18 +164,14 @@ int ieee80211_wep_encrypt(struct ieee80211_local *local,
 /* Perform WEP decryption using given key. data buffer includes encrypted
  * payload, including 4-byte ICV, but _not_ IV. data_len must not include ICV.
  * Return 0 on success and -1 on ICV mismatch. */
-int ieee80211_wep_decrypt_data(struct crypto_cipher *tfm, u8 *rc4key,
+int ieee80211_wep_decrypt_data(struct arc4_ctx *ctx, u8 *rc4key,
 			       size_t klen, u8 *data, size_t data_len)
 {
 	__le32 crc;
-	int i;
-
-	if (IS_ERR(tfm))
-		return -1;
 
-	crypto_cipher_setkey(tfm, rc4key, klen);
-	for (i = 0; i < data_len + IEEE80211_WEP_ICV_LEN; i++)
-		crypto_cipher_decrypt_one(tfm, data + i, data + i);
+	arc4_setkey(ctx, rc4key, klen);
+	arc4_crypt(ctx, data, data, data_len + IEEE80211_WEP_ICV_LEN);
+	memzero_explicit(ctx, sizeof(*ctx));
 
 	crc = cpu_to_le32(~crc32_le(~0, data, data_len));
 	if (memcmp(&crc, data + data_len, IEEE80211_WEP_ICV_LEN) != 0)
@@ -253,7 +224,7 @@ static int ieee80211_wep_decrypt(struct ieee80211_local *local,
 	/* Copy rest of the WEP key (the secret part) */
 	memcpy(rc4key + 3, key->conf.key, key->conf.keylen);
 
-	if (ieee80211_wep_decrypt_data(local->wep_rx_tfm, rc4key, klen,
+	if (ieee80211_wep_decrypt_data(&local->wep_rx_ctx, rc4key, klen,
 				       skb->data + hdrlen +
 				       IEEE80211_WEP_IV_LEN, len))
 		ret = -1;
diff --git a/net/mac80211/wep.h b/net/mac80211/wep.h
index 866a6798c9ef..997a034233c2 100644
--- a/net/mac80211/wep.h
+++ b/net/mac80211/wep.h
@@ -14,13 +14,12 @@
 #include "key.h"
 
 int ieee80211_wep_init(struct ieee80211_local *local);
-void ieee80211_wep_free(struct ieee80211_local *local);
-int ieee80211_wep_encrypt_data(struct crypto_cipher *tfm, u8 *rc4key,
+int ieee80211_wep_encrypt_data(struct arc4_ctx *ctx, u8 *rc4key,
 				size_t klen, u8 *data, size_t data_len);
 int ieee80211_wep_encrypt(struct ieee80211_local *local,
 			  struct sk_buff *skb,
 			  const u8 *key, int keylen, int keyidx);
-int ieee80211_wep_decrypt_data(struct crypto_cipher *tfm, u8 *rc4key,
+int ieee80211_wep_decrypt_data(struct arc4_ctx *ctx, u8 *rc4key,
 			       size_t klen, u8 *data, size_t data_len);
 
 ieee80211_rx_result
diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c
index a51c7909366e..ee72779729e5 100644
--- a/net/mac80211/wpa.c
+++ b/net/mac80211/wpa.c
@@ -239,7 +239,7 @@ static int tkip_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb)
 	/* Add room for ICV */
 	skb_put(skb, IEEE80211_TKIP_ICV_LEN);
 
-	return ieee80211_tkip_encrypt_data(tx->local->wep_tx_tfm,
+	return ieee80211_tkip_encrypt_data(&tx->local->wep_tx_ctx,
 					   key, skb, pos, len);
 }
 
@@ -290,7 +290,7 @@ ieee80211_crypto_tkip_decrypt(struct ieee80211_rx_data *rx)
 	if (status->flag & RX_FLAG_DECRYPTED)
 		hwaccel = 1;
 
-	res = ieee80211_tkip_decrypt_data(rx->local->wep_rx_tfm,
+	res = ieee80211_tkip_decrypt_data(&rx->local->wep_rx_ctx,
 					  key, skb->data + hdrlen,
 					  skb->len - hdrlen, rx->sta->sta.addr,
 					  hdr->addr1, hwaccel, rx->security_idx,
diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h
index 8acc4e173167..ecb3d67b41bf 100644
--- a/net/netfilter/ipset/ip_set_bitmap_gen.h
+++ b/net/netfilter/ipset/ip_set_bitmap_gen.h
@@ -61,9 +61,9 @@ mtype_destroy(struct ip_set *set)
 	if (SET_WITH_TIMEOUT(set))
 		del_timer_sync(&map->gc);
 
-	ip_set_free(map->members);
 	if (set->dsize && set->extensions & IPSET_EXT_DESTROY)
 		mtype_ext_cleanup(set);
+	ip_set_free(map->members);
 	ip_set_free(map);
 
 	set->data = NULL;
@@ -76,7 +76,7 @@ mtype_flush(struct ip_set *set)
 
 	if (set->extensions & IPSET_EXT_DESTROY)
 		mtype_ext_cleanup(set);
-	memset(map->members, 0, map->memsize);
+	bitmap_zero(map->members, map->elements);
 	set->elements = 0;
 	set->ext_size = 0;
 }
diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c
index e3884b0cca91..79d1a8e554dc 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ip.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ip.c
@@ -37,7 +37,7 @@ MODULE_ALIAS("ip_set_bitmap:ip");
 
 /* Type structure */
 struct bitmap_ip {
-	void *members;		/* the set members */
+	unsigned long *members;	/* the set members */
 	u32 first_ip;		/* host byte order, included in range */
 	u32 last_ip;		/* host byte order, included in range */
 	u32 elements;		/* number of max elements in the set */
@@ -220,7 +220,7 @@ init_map_ip(struct ip_set *set, struct bitmap_ip *map,
 	    u32 first_ip, u32 last_ip,
 	    u32 elements, u32 hosts, u8 netmask)
 {
-	map->members = ip_set_alloc(map->memsize);
+	map->members = bitmap_zalloc(elements, GFP_KERNEL | __GFP_NOWARN);
 	if (!map->members)
 		return false;
 	map->first_ip = first_ip;
@@ -310,11 +310,11 @@ bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
 	if (!map)
 		return -ENOMEM;
 
-	map->memsize = bitmap_bytes(0, elements - 1);
+	map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long);
 	set->variant = &bitmap_ip;
 	if (!init_map_ip(set, map, first_ip, last_ip,
 			 elements, hosts, netmask)) {
-		kfree(map);
+		ip_set_free(map);
 		return -ENOMEM;
 	}
 	if (tb[IPSET_ATTR_TIMEOUT]) {
diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
index cfe7b556775f..0aac330ef78b 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
@@ -43,7 +43,7 @@ enum {
 
 /* Type structure */
 struct bitmap_ipmac {
-	void *members;		/* the set members */
+	unsigned long *members;	/* the set members */
 	u32 first_ip;		/* host byte order, included in range */
 	u32 last_ip;		/* host byte order, included in range */
 	u32 elements;		/* number of max elements in the set */
@@ -300,7 +300,7 @@ static bool
 init_map_ipmac(struct ip_set *set, struct bitmap_ipmac *map,
 	       u32 first_ip, u32 last_ip, u32 elements)
 {
-	map->members = ip_set_alloc(map->memsize);
+	map->members = bitmap_zalloc(elements, GFP_KERNEL | __GFP_NOWARN);
 	if (!map->members)
 		return false;
 	map->first_ip = first_ip;
@@ -361,10 +361,10 @@ bitmap_ipmac_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
 	if (!map)
 		return -ENOMEM;
 
-	map->memsize = bitmap_bytes(0, elements - 1);
+	map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long);
 	set->variant = &bitmap_ipmac;
 	if (!init_map_ipmac(set, map, first_ip, last_ip, elements)) {
-		kfree(map);
+		ip_set_free(map);
 		return -ENOMEM;
 	}
 	if (tb[IPSET_ATTR_TIMEOUT]) {
diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c
index d8c140553379..044310ccf0a4 100644
--- a/net/netfilter/ipset/ip_set_bitmap_port.c
+++ b/net/netfilter/ipset/ip_set_bitmap_port.c
@@ -31,7 +31,7 @@ MODULE_ALIAS("ip_set_bitmap:port");
 
 /* Type structure */
 struct bitmap_port {
-	void *members;		/* the set members */
+	unsigned long *members;	/* the set members */
 	u16 first_port;		/* host byte order, included in range */
 	u16 last_port;		/* host byte order, included in range */
 	u32 elements;		/* number of max elements in the set */
@@ -205,7 +205,7 @@ static bool
 init_map_port(struct ip_set *set, struct bitmap_port *map,
 	      u16 first_port, u16 last_port)
 {
-	map->members = ip_set_alloc(map->memsize);
+	map->members = bitmap_zalloc(map->elements, GFP_KERNEL | __GFP_NOWARN);
 	if (!map->members)
 		return false;
 	map->first_port = first_port;
@@ -245,10 +245,10 @@ bitmap_port_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
 		return -ENOMEM;
 
 	map->elements = elements;
-	map->memsize = bitmap_bytes(0, map->elements);
+	map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long);
 	set->variant = &bitmap_port;
 	if (!init_map_port(set, map, first_port, last_port)) {
-		kfree(map);
+		ip_set_free(map);
 		return -ENOMEM;
 	}
 	if (tb[IPSET_ATTR_TIMEOUT]) {
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index e11e18d5b6fb..cb1930fd803d 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -382,6 +382,8 @@ ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], size_t len,
 	for (id = 0; id < IPSET_EXT_ID_MAX; id++) {
 		if (!add_extension(id, cadt_flags, tb))
 			continue;
+		if (align < ip_set_extensions[id].align)
+			align = ip_set_extensions[id].align;
 		len = ALIGN(len, ip_set_extensions[id].align);
 		set->offset[id] = len;
 		set->extensions |= ip_set_extensions[id].type;
@@ -557,6 +559,20 @@ ip_set_rcu_get(struct net *net, ip_set_id_t index)
 	return set;
 }
 
+static inline void
+ip_set_lock(struct ip_set *set)
+{
+	if (!set->variant->region_lock)
+		spin_lock_bh(&set->lock);
+}
+
+static inline void
+ip_set_unlock(struct ip_set *set)
+{
+	if (!set->variant->region_lock)
+		spin_unlock_bh(&set->lock);
+}
+
 int
 ip_set_test(ip_set_id_t index, const struct sk_buff *skb,
 	    const struct xt_action_param *par, struct ip_set_adt_opt *opt)
@@ -578,9 +594,9 @@ ip_set_test(ip_set_id_t index, const struct sk_buff *skb,
 	if (ret == -EAGAIN) {
 		/* Type requests element to be completed */
 		pr_debug("element must be completed, ADD is triggered\n");
-		spin_lock_bh(&set->lock);
+		ip_set_lock(set);
 		set->variant->kadt(set, skb, par, IPSET_ADD, opt);
-		spin_unlock_bh(&set->lock);
+		ip_set_unlock(set);
 		ret = 1;
 	} else {
 		/* --return-nomatch: invert matched element */
@@ -609,9 +625,9 @@ ip_set_add(ip_set_id_t index, const struct sk_buff *skb,
 	    !(opt->family == set->family || set->family == NFPROTO_UNSPEC))
 		return -IPSET_ERR_TYPE_MISMATCH;
 
-	spin_lock_bh(&set->lock);
+	ip_set_lock(set);
 	ret = set->variant->kadt(set, skb, par, IPSET_ADD, opt);
-	spin_unlock_bh(&set->lock);
+	ip_set_unlock(set);
 
 	return ret;
 }
@@ -631,9 +647,9 @@ ip_set_del(ip_set_id_t index, const struct sk_buff *skb,
 	    !(opt->family == set->family || set->family == NFPROTO_UNSPEC))
 		return -IPSET_ERR_TYPE_MISMATCH;
 
-	spin_lock_bh(&set->lock);
+	ip_set_lock(set);
 	ret = set->variant->kadt(set, skb, par, IPSET_DEL, opt);
-	spin_unlock_bh(&set->lock);
+	ip_set_unlock(set);
 
 	return ret;
 }
@@ -1098,9 +1114,9 @@ ip_set_flush_set(struct ip_set *set)
 {
 	pr_debug("set: %s\n",  set->name);
 
-	spin_lock_bh(&set->lock);
+	ip_set_lock(set);
 	set->variant->flush(set);
-	spin_unlock_bh(&set->lock);
+	ip_set_unlock(set);
 }
 
 static int ip_set_flush(struct net *net, struct sock *ctnl, struct sk_buff *skb,
@@ -1293,31 +1309,34 @@ ip_set_dump_policy[IPSET_ATTR_CMD_MAX + 1] = {
 };
 
 static int
-dump_init(struct netlink_callback *cb, struct ip_set_net *inst)
+ip_set_dump_start(struct netlink_callback *cb)
 {
 	struct nlmsghdr *nlh = nlmsg_hdr(cb->skb);
 	int min_len = nlmsg_total_size(sizeof(struct nfgenmsg));
 	struct nlattr *cda[IPSET_ATTR_CMD_MAX + 1];
 	struct nlattr *attr = (void *)nlh + min_len;
+	struct sk_buff *skb = cb->skb;
+	struct ip_set_net *inst = ip_set_pernet(sock_net(skb->sk));
 	u32 dump_type;
-	ip_set_id_t index;
 	int ret;
 
 	ret = nla_parse(cda, IPSET_ATTR_CMD_MAX, attr,
 			nlh->nlmsg_len - min_len,
 			ip_set_dump_policy, NULL);
 	if (ret)
-		return ret;
+		goto error;
 
 	cb->args[IPSET_CB_PROTO] = nla_get_u8(cda[IPSET_ATTR_PROTOCOL]);
 	if (cda[IPSET_ATTR_SETNAME]) {
+		ip_set_id_t index;
 		struct ip_set *set;
 
 		set = find_set_and_id(inst, nla_data(cda[IPSET_ATTR_SETNAME]),
 				      &index);
-		if (!set)
-			return -ENOENT;
-
+		if (!set) {
+			ret = -ENOENT;
+			goto error;
+		}
 		dump_type = DUMP_ONE;
 		cb->args[IPSET_CB_INDEX] = index;
 	} else {
@@ -1333,10 +1352,17 @@ dump_init(struct netlink_callback *cb, struct ip_set_net *inst)
 	cb->args[IPSET_CB_DUMP] = dump_type;
 
 	return 0;
+
+error:
+	/* We have to create and send the error message manually :-( */
+	if (nlh->nlmsg_flags & NLM_F_ACK) {
+		netlink_ack(cb->skb, nlh, ret, NULL);
+	}
+	return ret;
 }
 
 static int
-ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb)
+ip_set_dump_do(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	ip_set_id_t index = IPSET_INVALID_ID, max;
 	struct ip_set *set = NULL;
@@ -1347,18 +1373,8 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb)
 	bool is_destroyed;
 	int ret = 0;
 
-	if (!cb->args[IPSET_CB_DUMP]) {
-		ret = dump_init(cb, inst);
-		if (ret < 0) {
-			nlh = nlmsg_hdr(cb->skb);
-			/* We have to create and send the error message
-			 * manually :-(
-			 */
-			if (nlh->nlmsg_flags & NLM_F_ACK)
-				netlink_ack(cb->skb, nlh, ret, NULL);
-			return ret;
-		}
-	}
+	if (!cb->args[IPSET_CB_DUMP])
+		return -EINVAL;
 
 	if (cb->args[IPSET_CB_INDEX] >= inst->ip_set_max)
 		goto out;
@@ -1494,7 +1510,8 @@ static int ip_set_dump(struct net *net, struct sock *ctnl, struct sk_buff *skb,
 
 	{
 		struct netlink_dump_control c = {
-			.dump = ip_set_dump_start,
+			.start = ip_set_dump_start,
+			.dump = ip_set_dump_do,
 			.done = ip_set_dump_done,
 		};
 		return netlink_dump_start(ctnl, skb, nlh, &c);
@@ -1522,9 +1539,9 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set,
 	bool eexist = flags & IPSET_FLAG_EXIST, retried = false;
 
 	do {
-		spin_lock_bh(&set->lock);
+		ip_set_lock(set);
 		ret = set->variant->uadt(set, tb, adt, &lineno, flags, retried);
-		spin_unlock_bh(&set->lock);
+		ip_set_unlock(set);
 		retried = true;
 	} while (ret == -EAGAIN &&
 		 set->variant->resize &&
@@ -1691,6 +1708,7 @@ static int ip_set_utest(struct net *net, struct sock *ctnl, struct sk_buff *skb,
 	struct ip_set *set;
 	struct nlattr *tb[IPSET_ATTR_ADT_MAX + 1] = {};
 	int ret = 0;
+	u32 lineno;
 
 	if (unlikely(protocol_min_failed(attr) ||
 		     !attr[IPSET_ATTR_SETNAME] ||
@@ -1707,7 +1725,7 @@ static int ip_set_utest(struct net *net, struct sock *ctnl, struct sk_buff *skb,
 		return -IPSET_ERR_PROTOCOL;
 
 	rcu_read_lock_bh();
-	ret = set->variant->uadt(set, tb, IPSET_TEST, NULL, 0, 0);
+	ret = set->variant->uadt(set, tb, IPSET_TEST, &lineno, 0, 0);
 	rcu_read_unlock_bh();
 	/* Userspace can't trigger element to be re-added */
 	if (ret == -EAGAIN)
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 175f8fedcfaf..f970ff99f61b 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -8,13 +8,21 @@
 #include <linux/rcupdate.h>
 #include <linux/jhash.h>
 #include <linux/types.h>
+#include <linux/netfilter/nfnetlink.h>
 #include <linux/netfilter/ipset/ip_set_timeout.h>
 
-#define __ipset_dereference_protected(p, c)	rcu_dereference_protected(p, c)
-#define ipset_dereference_protected(p, set) \
-	__ipset_dereference_protected(p, lockdep_is_held(&(set)->lock))
-
-#define rcu_dereference_bh_nfnl(p)	rcu_dereference_bh_check(p, 1)
+#define __ipset_dereference(p)		\
+	rcu_dereference_protected(p, 1)
+#define ipset_dereference_nfnl(p)	\
+	rcu_dereference_protected(p,	\
+		lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET))
+#define ipset_dereference_set(p, set) 	\
+	rcu_dereference_protected(p,	\
+		lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET) || \
+		lockdep_is_held(&(set)->lock))
+#define ipset_dereference_bh_nfnl(p)	\
+	rcu_dereference_bh_check(p, 	\
+		lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET))
 
 /* Hashing which uses arrays to resolve clashing. The hash table is resized
  * (doubled) when searching becomes too long.
@@ -73,11 +81,35 @@ struct hbucket {
 		__aligned(__alignof__(u64));
 };
 
+/* Region size for locking == 2^HTABLE_REGION_BITS */
+#define HTABLE_REGION_BITS	10
+#define ahash_numof_locks(htable_bits)		\
+	((htable_bits) < HTABLE_REGION_BITS ? 1	\
+		: jhash_size((htable_bits) - HTABLE_REGION_BITS))
+#define ahash_sizeof_regions(htable_bits)		\
+	(ahash_numof_locks(htable_bits) * sizeof(struct ip_set_region))
+#define ahash_region(n, htable_bits)		\
+	((n) % ahash_numof_locks(htable_bits))
+#define ahash_bucket_start(h,  htable_bits)	\
+	((htable_bits) < HTABLE_REGION_BITS ? 0	\
+		: (h) * jhash_size(HTABLE_REGION_BITS))
+#define ahash_bucket_end(h,  htable_bits)	\
+	((htable_bits) < HTABLE_REGION_BITS ? jhash_size(htable_bits)	\
+		: ((h) + 1) * jhash_size(HTABLE_REGION_BITS))
+
+struct htable_gc {
+	struct delayed_work dwork;
+	struct ip_set *set;	/* Set the gc belongs to */
+	u32 region;		/* Last gc run position */
+};
+
 /* The hash table: the table size stored here in order to make resizing easy */
 struct htable {
 	atomic_t ref;		/* References for resizing */
-	atomic_t uref;		/* References for dumping */
+	atomic_t uref;		/* References for dumping and gc */
 	u8 htable_bits;		/* size of hash table == 2^htable_bits */
+	u32 maxelem;		/* Maxelem per region */
+	struct ip_set_region *hregion;	/* Region locks and ext sizes */
 	struct hbucket __rcu *bucket[0]; /* hashtable buckets */
 };
 
@@ -163,6 +195,10 @@ htable_bits(u32 hashsize)
 #define NLEN			0
 #endif /* IP_SET_HASH_WITH_NETS */
 
+#define SET_ELEM_EXPIRED(set, d)	\
+	(SET_WITH_TIMEOUT(set) &&	\
+	 ip_set_timeout_expired(ext_timeout(d, set)))
+
 #endif /* _IP_SET_HASH_GEN_H */
 
 #ifndef MTYPE
@@ -206,10 +242,12 @@ htable_bits(u32 hashsize)
 #undef mtype_test_cidrs
 #undef mtype_test
 #undef mtype_uref
-#undef mtype_expire
 #undef mtype_resize
+#undef mtype_ext_size
+#undef mtype_resize_ad
 #undef mtype_head
 #undef mtype_list
+#undef mtype_gc_do
 #undef mtype_gc
 #undef mtype_gc_init
 #undef mtype_variant
@@ -248,10 +286,12 @@ htable_bits(u32 hashsize)
 #define mtype_test_cidrs	IPSET_TOKEN(MTYPE, _test_cidrs)
 #define mtype_test		IPSET_TOKEN(MTYPE, _test)
 #define mtype_uref		IPSET_TOKEN(MTYPE, _uref)
-#define mtype_expire		IPSET_TOKEN(MTYPE, _expire)
 #define mtype_resize		IPSET_TOKEN(MTYPE, _resize)
+#define mtype_ext_size		IPSET_TOKEN(MTYPE, _ext_size)
+#define mtype_resize_ad		IPSET_TOKEN(MTYPE, _resize_ad)
 #define mtype_head		IPSET_TOKEN(MTYPE, _head)
 #define mtype_list		IPSET_TOKEN(MTYPE, _list)
+#define mtype_gc_do		IPSET_TOKEN(MTYPE, _gc_do)
 #define mtype_gc		IPSET_TOKEN(MTYPE, _gc)
 #define mtype_gc_init		IPSET_TOKEN(MTYPE, _gc_init)
 #define mtype_variant		IPSET_TOKEN(MTYPE, _variant)
@@ -276,8 +316,7 @@ htable_bits(u32 hashsize)
 /* The generic hash structure */
 struct htype {
 	struct htable __rcu *table; /* the hash table */
-	struct timer_list gc;	/* garbage collection when timeout enabled */
-	struct ip_set *set;	/* attached to this ip_set */
+	struct htable_gc gc;	/* gc workqueue */
 	u32 maxelem;		/* max elements in the hash */
 	u32 initval;		/* random jhash init value */
 #ifdef IP_SET_HASH_WITH_MARKMASK
@@ -289,21 +328,33 @@ struct htype {
 #ifdef IP_SET_HASH_WITH_NETMASK
 	u8 netmask;		/* netmask value for subnets to store */
 #endif
+	struct list_head ad;	/* Resize add|del backlist */
 	struct mtype_elem next; /* temporary storage for uadd */
 #ifdef IP_SET_HASH_WITH_NETS
 	struct net_prefixes nets[NLEN]; /* book-keeping of prefixes */
 #endif
 };
 
+/* ADD|DEL entries saved during resize */
+struct mtype_resize_ad {
+	struct list_head list;
+	enum ipset_adt ad;	/* ADD|DEL element */
+	struct mtype_elem d;	/* Element value */
+	struct ip_set_ext ext;	/* Extensions for ADD */
+	struct ip_set_ext mext;	/* Target extensions for ADD */
+	u32 flags;		/* Flags for ADD */
+};
+
 #ifdef IP_SET_HASH_WITH_NETS
 /* Network cidr size book keeping when the hash stores different
  * sized networks. cidr == real cidr + 1 to support /0.
  */
 static void
-mtype_add_cidr(struct htype *h, u8 cidr, u8 n)
+mtype_add_cidr(struct ip_set *set, struct htype *h, u8 cidr, u8 n)
 {
 	int i, j;
 
+	spin_lock_bh(&set->lock);
 	/* Add in increasing prefix order, so larger cidr first */
 	for (i = 0, j = -1; i < NLEN && h->nets[i].cidr[n]; i++) {
 		if (j != -1) {
@@ -312,7 +363,7 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 n)
 			j = i;
 		} else if (h->nets[i].cidr[n] == cidr) {
 			h->nets[CIDR_POS(cidr)].nets[n]++;
-			return;
+			goto unlock;
 		}
 	}
 	if (j != -1) {
@@ -321,24 +372,29 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 n)
 	}
 	h->nets[i].cidr[n] = cidr;
 	h->nets[CIDR_POS(cidr)].nets[n] = 1;
+unlock:
+	spin_unlock_bh(&set->lock);
 }
 
 static void
-mtype_del_cidr(struct htype *h, u8 cidr, u8 n)
+mtype_del_cidr(struct ip_set *set, struct htype *h, u8 cidr, u8 n)
 {
 	u8 i, j, net_end = NLEN - 1;
 
+	spin_lock_bh(&set->lock);
 	for (i = 0; i < NLEN; i++) {
 		if (h->nets[i].cidr[n] != cidr)
 			continue;
 		h->nets[CIDR_POS(cidr)].nets[n]--;
 		if (h->nets[CIDR_POS(cidr)].nets[n] > 0)
-			return;
+			goto unlock;
 		for (j = i; j < net_end && h->nets[j].cidr[n]; j++)
 			h->nets[j].cidr[n] = h->nets[j + 1].cidr[n];
 		h->nets[j].cidr[n] = 0;
-		return;
+		goto unlock;
 	}
+unlock:
+	spin_unlock_bh(&set->lock);
 }
 #endif
 
@@ -346,7 +402,7 @@ mtype_del_cidr(struct htype *h, u8 cidr, u8 n)
 static size_t
 mtype_ahash_memsize(const struct htype *h, const struct htable *t)
 {
-	return sizeof(*h) + sizeof(*t);
+	return sizeof(*h) + sizeof(*t) + ahash_sizeof_regions(t->htable_bits);
 }
 
 /* Get the ith element from the array block n */
@@ -370,24 +426,29 @@ mtype_flush(struct ip_set *set)
 	struct htype *h = set->data;
 	struct htable *t;
 	struct hbucket *n;
-	u32 i;
-
-	t = ipset_dereference_protected(h->table, set);
-	for (i = 0; i < jhash_size(t->htable_bits); i++) {
-		n = __ipset_dereference_protected(hbucket(t, i), 1);
-		if (!n)
-			continue;
-		if (set->extensions & IPSET_EXT_DESTROY)
-			mtype_ext_cleanup(set, n);
-		/* FIXME: use slab cache */
-		rcu_assign_pointer(hbucket(t, i), NULL);
-		kfree_rcu(n, rcu);
+	u32 r, i;
+
+	t = ipset_dereference_nfnl(h->table);
+	for (r = 0; r < ahash_numof_locks(t->htable_bits); r++) {
+		spin_lock_bh(&t->hregion[r].lock);
+		for (i = ahash_bucket_start(r, t->htable_bits);
+		     i < ahash_bucket_end(r, t->htable_bits); i++) {
+			n = __ipset_dereference(hbucket(t, i));
+			if (!n)
+				continue;
+			if (set->extensions & IPSET_EXT_DESTROY)
+				mtype_ext_cleanup(set, n);
+			/* FIXME: use slab cache */
+			rcu_assign_pointer(hbucket(t, i), NULL);
+			kfree_rcu(n, rcu);
+		}
+		t->hregion[r].ext_size = 0;
+		t->hregion[r].elements = 0;
+		spin_unlock_bh(&t->hregion[r].lock);
 	}
 #ifdef IP_SET_HASH_WITH_NETS
 	memset(h->nets, 0, sizeof(h->nets));
 #endif
-	set->elements = 0;
-	set->ext_size = 0;
 }
 
 /* Destroy the hashtable part of the set */
@@ -398,7 +459,7 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy)
 	u32 i;
 
 	for (i = 0; i < jhash_size(t->htable_bits); i++) {
-		n = __ipset_dereference_protected(hbucket(t, i), 1);
+		n = __ipset_dereference(hbucket(t, i));
 		if (!n)
 			continue;
 		if (set->extensions & IPSET_EXT_DESTROY && ext_destroy)
@@ -407,6 +468,7 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy)
 		kfree(n);
 	}
 
+	ip_set_free(t->hregion);
 	ip_set_free(t);
 }
 
@@ -415,28 +477,21 @@ static void
 mtype_destroy(struct ip_set *set)
 {
 	struct htype *h = set->data;
+	struct list_head *l, *lt;
 
 	if (SET_WITH_TIMEOUT(set))
-		del_timer_sync(&h->gc);
+		cancel_delayed_work_sync(&h->gc.dwork);
 
-	mtype_ahash_destroy(set,
-			    __ipset_dereference_protected(h->table, 1), true);
+	mtype_ahash_destroy(set, ipset_dereference_nfnl(h->table), true);
+	list_for_each_safe(l, lt, &h->ad) {
+		list_del(l);
+		kfree(l);
+	}
 	kfree(h);
 
 	set->data = NULL;
 }
 
-static void
-mtype_gc_init(struct ip_set *set, void (*gc)(struct timer_list *t))
-{
-	struct htype *h = set->data;
-
-	timer_setup(&h->gc, gc, 0);
-	mod_timer(&h->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ);
-	pr_debug("gc initialized, run in every %u\n",
-		 IPSET_GC_PERIOD(set->timeout));
-}
-
 static bool
 mtype_same_set(const struct ip_set *a, const struct ip_set *b)
 {
@@ -455,11 +510,9 @@ mtype_same_set(const struct ip_set *a, const struct ip_set *b)
 	       a->extensions == b->extensions;
 }
 
-/* Delete expired elements from the hashtable */
 static void
-mtype_expire(struct ip_set *set, struct htype *h)
+mtype_gc_do(struct ip_set *set, struct htype *h, struct htable *t, u32 r)
 {
-	struct htable *t;
 	struct hbucket *n, *tmp;
 	struct mtype_elem *data;
 	u32 i, j, d;
@@ -467,10 +520,12 @@ mtype_expire(struct ip_set *set, struct htype *h)
 #ifdef IP_SET_HASH_WITH_NETS
 	u8 k;
 #endif
+	u8 htable_bits = t->htable_bits;
 
-	t = ipset_dereference_protected(h->table, set);
-	for (i = 0; i < jhash_size(t->htable_bits); i++) {
-		n = __ipset_dereference_protected(hbucket(t, i), 1);
+	spin_lock_bh(&t->hregion[r].lock);
+	for (i = ahash_bucket_start(r, htable_bits);
+	     i < ahash_bucket_end(r, htable_bits); i++) {
+		n = __ipset_dereference(hbucket(t, i));
 		if (!n)
 			continue;
 		for (j = 0, d = 0; j < n->pos; j++) {
@@ -486,58 +541,100 @@ mtype_expire(struct ip_set *set, struct htype *h)
 			smp_mb__after_atomic();
 #ifdef IP_SET_HASH_WITH_NETS
 			for (k = 0; k < IPSET_NET_COUNT; k++)
-				mtype_del_cidr(h,
+				mtype_del_cidr(set, h,
 					NCIDR_PUT(DCIDR_GET(data->cidr, k)),
 					k);
 #endif
+			t->hregion[r].elements--;
 			ip_set_ext_destroy(set, data);
-			set->elements--;
 			d++;
 		}
 		if (d >= AHASH_INIT_SIZE) {
 			if (d >= n->size) {
+				t->hregion[r].ext_size -=
+					ext_size(n->size, dsize);
 				rcu_assign_pointer(hbucket(t, i), NULL);
 				kfree_rcu(n, rcu);
 				continue;
 			}
 			tmp = kzalloc(sizeof(*tmp) +
-				      (n->size - AHASH_INIT_SIZE) * dsize,
-				      GFP_ATOMIC);
+				(n->size - AHASH_INIT_SIZE) * dsize,
+				GFP_ATOMIC);
 			if (!tmp)
-				/* Still try to delete expired elements */
+				/* Still try to delete expired elements. */
 				continue;
 			tmp->size = n->size - AHASH_INIT_SIZE;
 			for (j = 0, d = 0; j < n->pos; j++) {
 				if (!test_bit(j, n->used))
 					continue;
 				data = ahash_data(n, j, dsize);
-				memcpy(tmp->value + d * dsize, data, dsize);
+				memcpy(tmp->value + d * dsize,
+				       data, dsize);
 				set_bit(d, tmp->used);
 				d++;
 			}
 			tmp->pos = d;
-			set->ext_size -= ext_size(AHASH_INIT_SIZE, dsize);
+			t->hregion[r].ext_size -=
+				ext_size(AHASH_INIT_SIZE, dsize);
 			rcu_assign_pointer(hbucket(t, i), tmp);
 			kfree_rcu(n, rcu);
 		}
 	}
+	spin_unlock_bh(&t->hregion[r].lock);
 }
 
 static void
-mtype_gc(struct timer_list *t)
+mtype_gc(struct work_struct *work)
 {
-	struct htype *h = from_timer(h, t, gc);
-	struct ip_set *set = h->set;
+	struct htable_gc *gc;
+	struct ip_set *set;
+	struct htype *h;
+	struct htable *t;
+	u32 r, numof_locks;
+	unsigned int next_run;
+
+	gc = container_of(work, struct htable_gc, dwork.work);
+	set = gc->set;
+	h = set->data;
 
-	pr_debug("called\n");
 	spin_lock_bh(&set->lock);
-	mtype_expire(set, h);
+	t = ipset_dereference_set(h->table, set);
+	atomic_inc(&t->uref);
+	numof_locks = ahash_numof_locks(t->htable_bits);
+	r = gc->region++;
+	if (r >= numof_locks) {
+		r = gc->region = 0;
+	}
+	next_run = (IPSET_GC_PERIOD(set->timeout) * HZ) / numof_locks;
+	if (next_run < HZ/10)
+		next_run = HZ/10;
 	spin_unlock_bh(&set->lock);
 
-	h->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ;
-	add_timer(&h->gc);
+	mtype_gc_do(set, h, t, r);
+
+	if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) {
+		pr_debug("Table destroy after resize by expire: %p\n", t);
+		mtype_ahash_destroy(set, t, false);
+	}
+
+	queue_delayed_work(system_power_efficient_wq, &gc->dwork, next_run);
+
+}
+
+static void
+mtype_gc_init(struct htable_gc *gc)
+{
+	INIT_DEFERRABLE_WORK(&gc->dwork, mtype_gc);
+	queue_delayed_work(system_power_efficient_wq, &gc->dwork, HZ);
 }
 
+static int
+mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
+	  struct ip_set_ext *mext, u32 flags);
+static int
+mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,
+	  struct ip_set_ext *mext, u32 flags);
+
 /* Resize a hash: create a new hash table with doubling the hashsize
  * and inserting the elements to it. Repeat until we succeed or
  * fail due to memory pressures.
@@ -548,7 +645,7 @@ mtype_resize(struct ip_set *set, bool retried)
 	struct htype *h = set->data;
 	struct htable *t, *orig;
 	u8 htable_bits;
-	size_t extsize, dsize = set->dsize;
+	size_t dsize = set->dsize;
 #ifdef IP_SET_HASH_WITH_NETS
 	u8 flags;
 	struct mtype_elem *tmp;
@@ -556,7 +653,9 @@ mtype_resize(struct ip_set *set, bool retried)
 	struct mtype_elem *data;
 	struct mtype_elem *d;
 	struct hbucket *n, *m;
-	u32 i, j, key;
+	struct list_head *l, *lt;
+	struct mtype_resize_ad *x;
+	u32 i, j, r, nr, key;
 	int ret;
 
 #ifdef IP_SET_HASH_WITH_NETS
@@ -564,10 +663,8 @@ mtype_resize(struct ip_set *set, bool retried)
 	if (!tmp)
 		return -ENOMEM;
 #endif
-	rcu_read_lock_bh();
-	orig = rcu_dereference_bh_nfnl(h->table);
+	orig = ipset_dereference_bh_nfnl(h->table);
 	htable_bits = orig->htable_bits;
-	rcu_read_unlock_bh();
 
 retry:
 	ret = 0;
@@ -584,88 +681,124 @@ retry:
 		ret = -ENOMEM;
 		goto out;
 	}
+	t->hregion = ip_set_alloc(ahash_sizeof_regions(htable_bits));
+	if (!t->hregion) {
+		ip_set_free(t);
+		ret = -ENOMEM;
+		goto out;
+	}
 	t->htable_bits = htable_bits;
+	t->maxelem = h->maxelem / ahash_numof_locks(htable_bits);
+	for (i = 0; i < ahash_numof_locks(htable_bits); i++)
+		spin_lock_init(&t->hregion[i].lock);
 
-	spin_lock_bh(&set->lock);
-	orig = __ipset_dereference_protected(h->table, 1);
-	/* There can't be another parallel resizing, but dumping is possible */
+	/* There can't be another parallel resizing,
+	 * but dumping, gc, kernel side add/del are possible
+	 */
+	orig = ipset_dereference_bh_nfnl(h->table);
 	atomic_set(&orig->ref, 1);
 	atomic_inc(&orig->uref);
-	extsize = 0;
 	pr_debug("attempt to resize set %s from %u to %u, t %p\n",
 		 set->name, orig->htable_bits, htable_bits, orig);
-	for (i = 0; i < jhash_size(orig->htable_bits); i++) {
-		n = __ipset_dereference_protected(hbucket(orig, i), 1);
-		if (!n)
-			continue;
-		for (j = 0; j < n->pos; j++) {
-			if (!test_bit(j, n->used))
+	for (r = 0; r < ahash_numof_locks(orig->htable_bits); r++) {
+		/* Expire may replace a hbucket with another one */
+		rcu_read_lock_bh();
+		for (i = ahash_bucket_start(r, orig->htable_bits);
+		     i < ahash_bucket_end(r, orig->htable_bits); i++) {
+			n = __ipset_dereference(hbucket(orig, i));
+			if (!n)
 				continue;
-			data = ahash_data(n, j, dsize);
+			for (j = 0; j < n->pos; j++) {
+				if (!test_bit(j, n->used))
+					continue;
+				data = ahash_data(n, j, dsize);
+				if (SET_ELEM_EXPIRED(set, data))
+					continue;
 #ifdef IP_SET_HASH_WITH_NETS
-			/* We have readers running parallel with us,
-			 * so the live data cannot be modified.
-			 */
-			flags = 0;
-			memcpy(tmp, data, dsize);
-			data = tmp;
-			mtype_data_reset_flags(data, &flags);
+				/* We have readers running parallel with us,
+				 * so the live data cannot be modified.
+				 */
+				flags = 0;
+				memcpy(tmp, data, dsize);
+				data = tmp;
+				mtype_data_reset_flags(data, &flags);
 #endif
-			key = HKEY(data, h->initval, htable_bits);
-			m = __ipset_dereference_protected(hbucket(t, key), 1);
-			if (!m) {
-				m = kzalloc(sizeof(*m) +
+				key = HKEY(data, h->initval, htable_bits);
+				m = __ipset_dereference(hbucket(t, key));
+				nr = ahash_region(key, htable_bits);
+				if (!m) {
+					m = kzalloc(sizeof(*m) +
 					    AHASH_INIT_SIZE * dsize,
 					    GFP_ATOMIC);
-				if (!m) {
-					ret = -ENOMEM;
-					goto cleanup;
-				}
-				m->size = AHASH_INIT_SIZE;
-				extsize += ext_size(AHASH_INIT_SIZE, dsize);
-				RCU_INIT_POINTER(hbucket(t, key), m);
-			} else if (m->pos >= m->size) {
-				struct hbucket *ht;
-
-				if (m->size >= AHASH_MAX(h)) {
-					ret = -EAGAIN;
-				} else {
-					ht = kzalloc(sizeof(*ht) +
+					if (!m) {
+						ret = -ENOMEM;
+						goto cleanup;
+					}
+					m->size = AHASH_INIT_SIZE;
+					t->hregion[nr].ext_size +=
+						ext_size(AHASH_INIT_SIZE,
+							 dsize);
+					RCU_INIT_POINTER(hbucket(t, key), m);
+				} else if (m->pos >= m->size) {
+					struct hbucket *ht;
+
+					if (m->size >= AHASH_MAX(h)) {
+						ret = -EAGAIN;
+					} else {
+						ht = kzalloc(sizeof(*ht) +
 						(m->size + AHASH_INIT_SIZE)
 						* dsize,
 						GFP_ATOMIC);
-					if (!ht)
-						ret = -ENOMEM;
+						if (!ht)
+							ret = -ENOMEM;
+					}
+					if (ret < 0)
+						goto cleanup;
+					memcpy(ht, m, sizeof(struct hbucket) +
+					       m->size * dsize);
+					ht->size = m->size + AHASH_INIT_SIZE;
+					t->hregion[nr].ext_size +=
+						ext_size(AHASH_INIT_SIZE,
+							 dsize);
+					kfree(m);
+					m = ht;
+					RCU_INIT_POINTER(hbucket(t, key), ht);
 				}
-				if (ret < 0)
-					goto cleanup;
-				memcpy(ht, m, sizeof(struct hbucket) +
-					      m->size * dsize);
-				ht->size = m->size + AHASH_INIT_SIZE;
-				extsize += ext_size(AHASH_INIT_SIZE, dsize);
-				kfree(m);
-				m = ht;
-				RCU_INIT_POINTER(hbucket(t, key), ht);
-			}
-			d = ahash_data(m, m->pos, dsize);
-			memcpy(d, data, dsize);
-			set_bit(m->pos++, m->used);
+				d = ahash_data(m, m->pos, dsize);
+				memcpy(d, data, dsize);
+				set_bit(m->pos++, m->used);
+				t->hregion[nr].elements++;
 #ifdef IP_SET_HASH_WITH_NETS
-			mtype_data_reset_flags(d, &flags);
+				mtype_data_reset_flags(d, &flags);
 #endif
+			}
 		}
+		rcu_read_unlock_bh();
 	}
-	rcu_assign_pointer(h->table, t);
-	set->ext_size = extsize;
 
-	spin_unlock_bh(&set->lock);
+	/* There can't be any other writer. */
+	rcu_assign_pointer(h->table, t);
 
 	/* Give time to other readers of the set */
 	synchronize_rcu();
 
 	pr_debug("set %s resized from %u (%p) to %u (%p)\n", set->name,
 		 orig->htable_bits, orig, t->htable_bits, t);
-	/* If there's nobody else dumping the table, destroy it */
+	/* Add/delete elements processed by the SET target during resize.
+	 * Kernel-side add cannot trigger a resize and userspace actions
+	 * are serialized by the mutex.
+	 */
+	list_for_each_safe(l, lt, &h->ad) {
+		x = list_entry(l, struct mtype_resize_ad, list);
+		if (x->ad == IPSET_ADD) {
+			mtype_add(set, &x->d, &x->ext, &x->mext, x->flags);
+		} else {
+			mtype_del(set, &x->d, NULL, NULL, 0);
+		}
+		list_del(l);
+		kfree(l);
+	}
+	/* If there's nobody else using the table, destroy it */
 	if (atomic_dec_and_test(&orig->uref)) {
 		pr_debug("Table destroy by resize %p\n", orig);
 		mtype_ahash_destroy(set, orig, false);
@@ -678,15 +811,44 @@ out:
 	return ret;
 
 cleanup:
+	rcu_read_unlock_bh();
 	atomic_set(&orig->ref, 0);
 	atomic_dec(&orig->uref);
-	spin_unlock_bh(&set->lock);
 	mtype_ahash_destroy(set, t, false);
 	if (ret == -EAGAIN)
 		goto retry;
 	goto out;
 }
 
+/* Get the current number of elements and ext_size in the set  */
+static void
+mtype_ext_size(struct ip_set *set, u32 *elements, size_t *ext_size)
+{
+	struct htype *h = set->data;
+	const struct htable *t;
+	u32 i, j, r;
+	struct hbucket *n;
+	struct mtype_elem *data;
+
+	t = rcu_dereference_bh(h->table);
+	for (r = 0; r < ahash_numof_locks(t->htable_bits); r++) {
+		for (i = ahash_bucket_start(r, t->htable_bits);
+		     i < ahash_bucket_end(r, t->htable_bits); i++) {
+			n = rcu_dereference_bh(hbucket(t, i));
+			if (!n)
+				continue;
+			for (j = 0; j < n->pos; j++) {
+				if (!test_bit(j, n->used))
+					continue;
+				data = ahash_data(n, j, set->dsize);
+				if (!SET_ELEM_EXPIRED(set, data))
+					(*elements)++;
+			}
+		}
+		*ext_size += t->hregion[r].ext_size;
+	}
+}
+
 /* Add an element to a hash and update the internal counters when succeeded,
  * otherwise report the proper error code.
  */
@@ -699,32 +861,49 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 	const struct mtype_elem *d = value;
 	struct mtype_elem *data;
 	struct hbucket *n, *old = ERR_PTR(-ENOENT);
-	int i, j = -1;
+	int i, j = -1, ret;
 	bool flag_exist = flags & IPSET_FLAG_EXIST;
 	bool deleted = false, forceadd = false, reuse = false;
-	u32 key, multi = 0;
+	u32 r, key, multi = 0, elements, maxelem;
 
-	if (set->elements >= h->maxelem) {
-		if (SET_WITH_TIMEOUT(set))
-			/* FIXME: when set is full, we slow down here */
-			mtype_expire(set, h);
-		if (set->elements >= h->maxelem && SET_WITH_FORCEADD(set))
+	rcu_read_lock_bh();
+	t = rcu_dereference_bh(h->table);
+	key = HKEY(value, h->initval, t->htable_bits);
+	r = ahash_region(key, t->htable_bits);
+	atomic_inc(&t->uref);
+	elements = t->hregion[r].elements;
+	maxelem = t->maxelem;
+	if (elements >= maxelem) {
+		u32 e;
+		if (SET_WITH_TIMEOUT(set)) {
+			rcu_read_unlock_bh();
+			mtype_gc_do(set, h, t, r);
+			rcu_read_lock_bh();
+		}
+		maxelem = h->maxelem;
+		elements = 0;
+		for (e = 0; e < ahash_numof_locks(t->htable_bits); e++)
+			elements += t->hregion[e].elements;
+		if (elements >= maxelem && SET_WITH_FORCEADD(set))
 			forceadd = true;
 	}
+	rcu_read_unlock_bh();
 
-	t = ipset_dereference_protected(h->table, set);
-	key = HKEY(value, h->initval, t->htable_bits);
-	n = __ipset_dereference_protected(hbucket(t, key), 1);
+	spin_lock_bh(&t->hregion[r].lock);
+	n = rcu_dereference_bh(hbucket(t, key));
 	if (!n) {
-		if (forceadd || set->elements >= h->maxelem)
+		if (forceadd || elements >= maxelem)
 			goto set_full;
 		old = NULL;
 		n = kzalloc(sizeof(*n) + AHASH_INIT_SIZE * set->dsize,
 			    GFP_ATOMIC);
-		if (!n)
-			return -ENOMEM;
+		if (!n) {
+			ret = -ENOMEM;
+			goto unlock;
+		}
 		n->size = AHASH_INIT_SIZE;
-		set->ext_size += ext_size(AHASH_INIT_SIZE, set->dsize);
+		t->hregion[r].ext_size +=
+			ext_size(AHASH_INIT_SIZE, set->dsize);
 		goto copy_elem;
 	}
 	for (i = 0; i < n->pos; i++) {
@@ -738,38 +917,37 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 		}
 		data = ahash_data(n, i, set->dsize);
 		if (mtype_data_equal(data, d, &multi)) {
-			if (flag_exist ||
-			    (SET_WITH_TIMEOUT(set) &&
-			     ip_set_timeout_expired(ext_timeout(data, set)))) {
+			if (flag_exist || SET_ELEM_EXPIRED(set, data)) {
 				/* Just the extensions could be overwritten */
 				j = i;
 				goto overwrite_extensions;
 			}
-			return -IPSET_ERR_EXIST;
+			ret = -IPSET_ERR_EXIST;
+			goto unlock;
 		}
 		/* Reuse first timed out entry */
-		if (SET_WITH_TIMEOUT(set) &&
-		    ip_set_timeout_expired(ext_timeout(data, set)) &&
-		    j == -1) {
+		if (SET_ELEM_EXPIRED(set, data) && j == -1) {
 			j = i;
 			reuse = true;
 		}
 	}
 	if (reuse || forceadd) {
+		if (j == -1)
+			j = 0;
 		data = ahash_data(n, j, set->dsize);
 		if (!deleted) {
 #ifdef IP_SET_HASH_WITH_NETS
 			for (i = 0; i < IPSET_NET_COUNT; i++)
-				mtype_del_cidr(h,
+				mtype_del_cidr(set, h,
 					NCIDR_PUT(DCIDR_GET(data->cidr, i)),
 					i);
 #endif
 			ip_set_ext_destroy(set, data);
-			set->elements--;
+			t->hregion[r].elements--;
 		}
 		goto copy_data;
 	}
-	if (set->elements >= h->maxelem)
+	if (elements >= maxelem)
 		goto set_full;
 	/* Create a new slot */
 	if (n->pos >= n->size) {
@@ -777,28 +955,32 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 		if (n->size >= AHASH_MAX(h)) {
 			/* Trigger rehashing */
 			mtype_data_next(&h->next, d);
-			return -EAGAIN;
+			ret = -EAGAIN;
+			goto resize;
 		}
 		old = n;
 		n = kzalloc(sizeof(*n) +
 			    (old->size + AHASH_INIT_SIZE) * set->dsize,
 			    GFP_ATOMIC);
-		if (!n)
-			return -ENOMEM;
+		if (!n) {
+			ret = -ENOMEM;
+			goto unlock;
+		}
 		memcpy(n, old, sizeof(struct hbucket) +
 		       old->size * set->dsize);
 		n->size = old->size + AHASH_INIT_SIZE;
-		set->ext_size += ext_size(AHASH_INIT_SIZE, set->dsize);
+		t->hregion[r].ext_size +=
+			ext_size(AHASH_INIT_SIZE, set->dsize);
 	}
 
 copy_elem:
 	j = n->pos++;
 	data = ahash_data(n, j, set->dsize);
 copy_data:
-	set->elements++;
+	t->hregion[r].elements++;
 #ifdef IP_SET_HASH_WITH_NETS
 	for (i = 0; i < IPSET_NET_COUNT; i++)
-		mtype_add_cidr(h, NCIDR_PUT(DCIDR_GET(d->cidr, i)), i);
+		mtype_add_cidr(set, h, NCIDR_PUT(DCIDR_GET(d->cidr, i)), i);
 #endif
 	memcpy(data, d, sizeof(struct mtype_elem));
 overwrite_extensions:
@@ -821,13 +1003,41 @@ overwrite_extensions:
 		if (old)
 			kfree_rcu(old, rcu);
 	}
+	ret = 0;
+resize:
+	spin_unlock_bh(&t->hregion[r].lock);
+	if (atomic_read(&t->ref) && ext->target) {
+		/* Resize is in process and kernel side add, save values */
+		struct mtype_resize_ad *x;
+
+		x = kzalloc(sizeof(struct mtype_resize_ad), GFP_ATOMIC);
+		if (!x)
+			/* Don't bother */
+			goto out;
+		x->ad = IPSET_ADD;
+		memcpy(&x->d, value, sizeof(struct mtype_elem));
+		memcpy(&x->ext, ext, sizeof(struct ip_set_ext));
+		memcpy(&x->mext, mext, sizeof(struct ip_set_ext));
+		x->flags = flags;
+		spin_lock_bh(&set->lock);
+		list_add_tail(&x->list, &h->ad);
+		spin_unlock_bh(&set->lock);
+	}
+	goto out;
 
-	return 0;
 set_full:
 	if (net_ratelimit())
 		pr_warn("Set %s is full, maxelem %u reached\n",
-			set->name, h->maxelem);
-	return -IPSET_ERR_HASH_FULL;
+			set->name, maxelem);
+	ret = -IPSET_ERR_HASH_FULL;
+unlock:
+	spin_unlock_bh(&t->hregion[r].lock);
+out:
+	if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) {
+		pr_debug("Table destroy after resize by add: %p\n", t);
+		mtype_ahash_destroy(set, t, false);
+	}
+	return ret;
 }
 
 /* Delete an element from the hash and free up space if possible.
@@ -841,13 +1051,23 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 	const struct mtype_elem *d = value;
 	struct mtype_elem *data;
 	struct hbucket *n;
-	int i, j, k, ret = -IPSET_ERR_EXIST;
+	struct mtype_resize_ad *x = NULL;
+	int i, j, k, r, ret = -IPSET_ERR_EXIST;
 	u32 key, multi = 0;
 	size_t dsize = set->dsize;
 
-	t = ipset_dereference_protected(h->table, set);
+	/* Userspace add and resize is excluded by the mutex.
+	 * Kernespace add does not trigger resize.
+	 */
+	rcu_read_lock_bh();
+	t = rcu_dereference_bh(h->table);
 	key = HKEY(value, h->initval, t->htable_bits);
-	n = __ipset_dereference_protected(hbucket(t, key), 1);
+	r = ahash_region(key, t->htable_bits);
+	atomic_inc(&t->uref);
+	rcu_read_unlock_bh();
+
+	spin_lock_bh(&t->hregion[r].lock);
+	n = rcu_dereference_bh(hbucket(t, key));
 	if (!n)
 		goto out;
 	for (i = 0, k = 0; i < n->pos; i++) {
@@ -858,8 +1078,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 		data = ahash_data(n, i, dsize);
 		if (!mtype_data_equal(data, d, &multi))
 			continue;
-		if (SET_WITH_TIMEOUT(set) &&
-		    ip_set_timeout_expired(ext_timeout(data, set)))
+		if (SET_ELEM_EXPIRED(set, data))
 			goto out;
 
 		ret = 0;
@@ -867,20 +1086,33 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 		smp_mb__after_atomic();
 		if (i + 1 == n->pos)
 			n->pos--;
-		set->elements--;
+		t->hregion[r].elements--;
 #ifdef IP_SET_HASH_WITH_NETS
 		for (j = 0; j < IPSET_NET_COUNT; j++)
-			mtype_del_cidr(h, NCIDR_PUT(DCIDR_GET(d->cidr, j)),
-				       j);
+			mtype_del_cidr(set, h,
+				       NCIDR_PUT(DCIDR_GET(d->cidr, j)), j);
 #endif
 		ip_set_ext_destroy(set, data);
 
+		if (atomic_read(&t->ref) && ext->target) {
+			/* Resize is in process and kernel side del,
+			 * save values
+			 */
+			x = kzalloc(sizeof(struct mtype_resize_ad),
+				    GFP_ATOMIC);
+			if (x) {
+				x->ad = IPSET_DEL;
+				memcpy(&x->d, value,
+				       sizeof(struct mtype_elem));
+				x->flags = flags;
+			}
+		}
 		for (; i < n->pos; i++) {
 			if (!test_bit(i, n->used))
 				k++;
 		}
 		if (n->pos == 0 && k == 0) {
-			set->ext_size -= ext_size(n->size, dsize);
+			t->hregion[r].ext_size -= ext_size(n->size, dsize);
 			rcu_assign_pointer(hbucket(t, key), NULL);
 			kfree_rcu(n, rcu);
 		} else if (k >= AHASH_INIT_SIZE) {
@@ -899,7 +1131,8 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 				k++;
 			}
 			tmp->pos = k;
-			set->ext_size -= ext_size(AHASH_INIT_SIZE, dsize);
+			t->hregion[r].ext_size -=
+				ext_size(AHASH_INIT_SIZE, dsize);
 			rcu_assign_pointer(hbucket(t, key), tmp);
 			kfree_rcu(n, rcu);
 		}
@@ -907,6 +1140,16 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 	}
 
 out:
+	spin_unlock_bh(&t->hregion[r].lock);
+	if (x) {
+		spin_lock_bh(&set->lock);
+		list_add(&x->list, &h->ad);
+		spin_unlock_bh(&set->lock);
+	}
+	if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) {
+		pr_debug("Table destroy after resize by del: %p\n", t);
+		mtype_ahash_destroy(set, t, false);
+	}
 	return ret;
 }
 
@@ -992,6 +1235,7 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 	int i, ret = 0;
 	u32 key, multi = 0;
 
+	rcu_read_lock_bh();
 	t = rcu_dereference_bh(h->table);
 #ifdef IP_SET_HASH_WITH_NETS
 	/* If we test an IP address and not a network address,
@@ -1023,6 +1267,7 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 			goto out;
 	}
 out:
+	rcu_read_unlock_bh();
 	return ret;
 }
 
@@ -1034,23 +1279,14 @@ mtype_head(struct ip_set *set, struct sk_buff *skb)
 	const struct htable *t;
 	struct nlattr *nested;
 	size_t memsize;
+	u32 elements = 0;
+	size_t ext_size = 0;
 	u8 htable_bits;
 
-	/* If any members have expired, set->elements will be wrong
-	 * mytype_expire function will update it with the right count.
-	 * we do not hold set->lock here, so grab it first.
-	 * set->elements can still be incorrect in the case of a huge set,
-	 * because elements might time out during the listing.
-	 */
-	if (SET_WITH_TIMEOUT(set)) {
-		spin_lock_bh(&set->lock);
-		mtype_expire(set, h);
-		spin_unlock_bh(&set->lock);
-	}
-
 	rcu_read_lock_bh();
-	t = rcu_dereference_bh_nfnl(h->table);
-	memsize = mtype_ahash_memsize(h, t) + set->ext_size;
+	t = rcu_dereference_bh(h->table);
+	mtype_ext_size(set, &elements, &ext_size);
+	memsize = mtype_ahash_memsize(h, t) + ext_size + set->ext_size;
 	htable_bits = t->htable_bits;
 	rcu_read_unlock_bh();
 
@@ -1072,7 +1308,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb)
 #endif
 	if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) ||
 	    nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) ||
-	    nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(set->elements)))
+	    nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(elements)))
 		goto nla_put_failure;
 	if (unlikely(ip_set_put_flags(skb, set)))
 		goto nla_put_failure;
@@ -1092,15 +1328,15 @@ mtype_uref(struct ip_set *set, struct netlink_callback *cb, bool start)
 
 	if (start) {
 		rcu_read_lock_bh();
-		t = rcu_dereference_bh_nfnl(h->table);
+		t = ipset_dereference_bh_nfnl(h->table);
 		atomic_inc(&t->uref);
 		cb->args[IPSET_CB_PRIVATE] = (unsigned long)t;
 		rcu_read_unlock_bh();
 	} else if (cb->args[IPSET_CB_PRIVATE]) {
 		t = (struct htable *)cb->args[IPSET_CB_PRIVATE];
 		if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) {
-			/* Resizing didn't destroy the hash table */
-			pr_debug("Table destroy by dump: %p\n", t);
+			pr_debug("Table destroy after resize "
+				 " by dump: %p\n", t);
 			mtype_ahash_destroy(set, t, false);
 		}
 		cb->args[IPSET_CB_PRIVATE] = 0;
@@ -1142,8 +1378,7 @@ mtype_list(const struct ip_set *set,
 			if (!test_bit(i, n->used))
 				continue;
 			e = ahash_data(n, i, set->dsize);
-			if (SET_WITH_TIMEOUT(set) &&
-			    ip_set_timeout_expired(ext_timeout(e, set)))
+			if (SET_ELEM_EXPIRED(set, e))
 				continue;
 			pr_debug("list hash %lu hbucket %p i %u, data %p\n",
 				 cb->args[IPSET_CB_ARG0], n, i, e);
@@ -1209,6 +1444,7 @@ static const struct ip_set_type_variant mtype_variant = {
 	.uref	= mtype_uref,
 	.resize	= mtype_resize,
 	.same_set = mtype_same_set,
+	.region_lock = true,
 };
 
 #ifdef IP_SET_EMIT_CREATE
@@ -1227,6 +1463,7 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set,
 	size_t hsize;
 	struct htype *h;
 	struct htable *t;
+	u32 i;
 
 	pr_debug("Create set %s with family %s\n",
 		 set->name, set->family == NFPROTO_IPV4 ? "inet" : "inet6");
@@ -1295,6 +1532,15 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set,
 		kfree(h);
 		return -ENOMEM;
 	}
+	t->hregion = ip_set_alloc(ahash_sizeof_regions(hbits));
+	if (!t->hregion) {
+		ip_set_free(t);
+		kfree(h);
+		return -ENOMEM;
+	}
+	h->gc.set = set;
+	for (i = 0; i < ahash_numof_locks(hbits); i++)
+		spin_lock_init(&t->hregion[i].lock);
 	h->maxelem = maxelem;
 #ifdef IP_SET_HASH_WITH_NETMASK
 	h->netmask = netmask;
@@ -1305,9 +1551,10 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set,
 	get_random_bytes(&h->initval, sizeof(h->initval));
 
 	t->htable_bits = hbits;
+	t->maxelem = h->maxelem / ahash_numof_locks(hbits);
 	RCU_INIT_POINTER(h->table, t);
 
-	h->set = set;
+	INIT_LIST_HEAD(&h->ad);
 	set->data = h;
 #ifndef IP_SET_PROTO_UNDEF
 	if (set->family == NFPROTO_IPV4) {
@@ -1330,12 +1577,10 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set,
 #ifndef IP_SET_PROTO_UNDEF
 		if (set->family == NFPROTO_IPV4)
 #endif
-			IPSET_TOKEN(HTYPE, 4_gc_init)(set,
-				IPSET_TOKEN(HTYPE, 4_gc));
+			IPSET_TOKEN(HTYPE, 4_gc_init)(&h->gc);
 #ifndef IP_SET_PROTO_UNDEF
 		else
-			IPSET_TOKEN(HTYPE, 6_gc_init)(set,
-				IPSET_TOKEN(HTYPE, 6_gc));
+			IPSET_TOKEN(HTYPE, 6_gc_init)(&h->gc);
 #endif
 	}
 	pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n",
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index 8ada318bf09d..eb9a8d97e65a 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -60,7 +60,7 @@ list_set_ktest(struct ip_set *set, const struct sk_buff *skb,
 	/* Don't lookup sub-counters at all */
 	opt->cmdflags &= ~IPSET_FLAG_MATCH_COUNTERS;
 	if (opt->cmdflags & IPSET_FLAG_SKIP_SUBCOUNTER_UPDATE)
-		opt->cmdflags &= ~IPSET_FLAG_SKIP_COUNTER_UPDATE;
+		opt->cmdflags |= IPSET_FLAG_SKIP_COUNTER_UPDATE;
 	list_for_each_entry_rcu(e, &map->members, list) {
 		ret = ip_set_test(e->id, skb, par, opt);
 		if (ret <= 0)
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index d5103a9eb302..c85752f8bd1a 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1955,14 +1955,14 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
 
 	conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
 	if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) {
-		bool uses_ct = false, resched = false;
+		bool old_ct = false, resched = false;
 
 		if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest &&
 		    unlikely(!atomic_read(&cp->dest->weight))) {
 			resched = true;
-			uses_ct = ip_vs_conn_uses_conntrack(cp, skb);
+			old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
 		} else if (is_new_conn_expected(cp, conn_reuse_mode)) {
-			uses_ct = ip_vs_conn_uses_conntrack(cp, skb);
+			old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
 			if (!atomic_read(&cp->n_control)) {
 				resched = true;
 			} else {
@@ -1970,15 +1970,17 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
 				 * that uses conntrack while it is still
 				 * referenced by controlled connection(s).
 				 */
-				resched = !uses_ct;
+				resched = !old_ct;
 			}
 		}
 
 		if (resched) {
+			if (!old_ct)
+				cp->flags &= ~IP_VS_CONN_F_NFCT;
 			if (!atomic_read(&cp->n_control))
 				ip_vs_conn_expire_now(cp);
 			__ip_vs_conn_put(cp);
-			if (uses_ct)
+			if (old_ct)
 				return NF_DROP;
 			cp = NULL;
 		}
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 8dc892a9dc91..0c1bc654245c 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1717,6 +1717,8 @@ static int sync_thread_backup(void *data)
 {
 	struct ip_vs_sync_thread_data *tinfo = data;
 	struct netns_ipvs *ipvs = tinfo->ipvs;
+	struct sock *sk = tinfo->sock->sk;
+	struct udp_sock *up = udp_sk(sk);
 	int len;
 
 	pr_info("sync thread started: state = BACKUP, mcast_ifn = %s, "
@@ -1724,12 +1726,14 @@ static int sync_thread_backup(void *data)
 		ipvs->bcfg.mcast_ifn, ipvs->bcfg.syncid, tinfo->id);
 
 	while (!kthread_should_stop()) {
-		wait_event_interruptible(*sk_sleep(tinfo->sock->sk),
-			 !skb_queue_empty(&tinfo->sock->sk->sk_receive_queue)
-			 || kthread_should_stop());
+		wait_event_interruptible(*sk_sleep(sk),
+					 !skb_queue_empty_lockless(&sk->sk_receive_queue) ||
+					 !skb_queue_empty_lockless(&up->reader_queue) ||
+					 kthread_should_stop());
 
 		/* do we have data now? */
-		while (!skb_queue_empty(&(tinfo->sock->sk->sk_receive_queue))) {
+		while (!skb_queue_empty_lockless(&sk->sk_receive_queue) ||
+		       !skb_queue_empty_lockless(&up->reader_queue)) {
 			len = ip_vs_receive(tinfo->sock, tinfo->buf,
 					ipvs->bcfg.sync_maxlen);
 			if (len <= 0) {
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index f05d0a0f3068..63618729d84d 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1381,9 +1381,9 @@ __nf_conntrack_alloc(struct net *net,
 	ct->status = 0;
 	ct->timeout = 0;
 	write_pnet(&ct->ct_net, net);
-	memset(&ct->__nfct_init_offset[0], 0,
+	memset(&ct->__nfct_init_offset, 0,
 	       offsetof(struct nf_conn, proto) -
-	       offsetof(struct nf_conn, __nfct_init_offset[0]));
+	       offsetof(struct nf_conn, __nfct_init_offset));
 
 	nf_ct_zone_add(ct, zone);
 
@@ -1881,22 +1881,18 @@ static void nf_conntrack_attach(struct sk_buff *nskb, const struct sk_buff *skb)
 	nf_conntrack_get(skb_nfct(nskb));
 }
 
-static int nf_conntrack_update(struct net *net, struct sk_buff *skb)
+static int __nf_conntrack_update(struct net *net, struct sk_buff *skb,
+				 struct nf_conn *ct,
+				 enum ip_conntrack_info ctinfo)
 {
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conntrack_tuple tuple;
-	enum ip_conntrack_info ctinfo;
 	struct nf_nat_hook *nat_hook;
 	unsigned int status;
-	struct nf_conn *ct;
 	int dataoff;
 	u16 l3num;
 	u8 l4num;
 
-	ct = nf_ct_get(skb, &ctinfo);
-	if (!ct || nf_ct_is_confirmed(ct))
-		return 0;
-
 	l3num = nf_ct_l3num(ct);
 
 	dataoff = get_l4proto(skb, skb_network_offset(skb), l3num, &l4num);
@@ -1953,6 +1949,78 @@ static int nf_conntrack_update(struct net *net, struct sk_buff *skb)
 	return 0;
 }
 
+/* This packet is coming from userspace via nf_queue, complete the packet
+ * processing after the helper invocation in nf_confirm().
+ */
+static int nf_confirm_cthelper(struct sk_buff *skb, struct nf_conn *ct,
+			       enum ip_conntrack_info ctinfo)
+{
+	const struct nf_conntrack_helper *helper;
+	const struct nf_conn_help *help;
+	int protoff;
+
+	help = nfct_help(ct);
+	if (!help)
+		return 0;
+
+	helper = rcu_dereference(help->helper);
+	if (!(helper->flags & NF_CT_HELPER_F_USERSPACE))
+		return 0;
+
+	switch (nf_ct_l3num(ct)) {
+	case NFPROTO_IPV4:
+		protoff = skb_network_offset(skb) + ip_hdrlen(skb);
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case NFPROTO_IPV6: {
+		__be16 frag_off;
+		u8 pnum;
+
+		pnum = ipv6_hdr(skb)->nexthdr;
+		protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum,
+					   &frag_off);
+		if (protoff < 0 || (frag_off & htons(~0x7)) != 0)
+			return 0;
+		break;
+	}
+#endif
+	default:
+		return 0;
+	}
+
+	if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) &&
+	    !nf_is_loopback_packet(skb)) {
+		if (!nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) {
+			NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop);
+			return -1;
+		}
+	}
+
+	/* We've seen it coming out the other side: confirm it */
+	return nf_conntrack_confirm(skb) == NF_DROP ? - 1 : 0;
+}
+
+static int nf_conntrack_update(struct net *net, struct sk_buff *skb)
+{
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct;
+	int err;
+
+	ct = nf_ct_get(skb, &ctinfo);
+	if (!ct)
+		return 0;
+
+	if (!nf_ct_is_confirmed(ct)) {
+		err = __nf_conntrack_update(net, skb, ct, ctinfo);
+		if (err < 0)
+			return err;
+
+		ct = nf_ct_get(skb, &ctinfo);
+	}
+
+	return nf_confirm_cthelper(skb, ct, ctinfo);
+}
+
 static bool nf_conntrack_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple,
 				       const struct sk_buff *skb)
 {
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 1b77444d5b52..47eb42649639 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -3599,6 +3599,9 @@ static void __net_exit ctnetlink_net_exit_batch(struct list_head *net_exit_list)
 
 	list_for_each_entry(net, net_exit_list, exit_list)
 		ctnetlink_net_exit(net);
+
+	/* wait for other cpus until they are done with ctnl_notifiers */
+	synchronize_rcu();
 }
 
 static struct pernet_operations ctnetlink_net_ops = {
diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c
index b22042ad0fca..584c606e7fe0 100644
--- a/net/netfilter/nf_conntrack_pptp.c
+++ b/net/netfilter/nf_conntrack_pptp.c
@@ -72,24 +72,32 @@ EXPORT_SYMBOL_GPL(nf_nat_pptp_hook_expectfn);
 
 #if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG)
 /* PptpControlMessageType names */
-const char *const pptp_msg_name[] = {
-	"UNKNOWN_MESSAGE",
-	"START_SESSION_REQUEST",
-	"START_SESSION_REPLY",
-	"STOP_SESSION_REQUEST",
-	"STOP_SESSION_REPLY",
-	"ECHO_REQUEST",
-	"ECHO_REPLY",
-	"OUT_CALL_REQUEST",
-	"OUT_CALL_REPLY",
-	"IN_CALL_REQUEST",
-	"IN_CALL_REPLY",
-	"IN_CALL_CONNECT",
-	"CALL_CLEAR_REQUEST",
-	"CALL_DISCONNECT_NOTIFY",
-	"WAN_ERROR_NOTIFY",
-	"SET_LINK_INFO"
+static const char *const pptp_msg_name_array[PPTP_MSG_MAX + 1] = {
+	[0]				= "UNKNOWN_MESSAGE",
+	[PPTP_START_SESSION_REQUEST]	= "START_SESSION_REQUEST",
+	[PPTP_START_SESSION_REPLY]	= "START_SESSION_REPLY",
+	[PPTP_STOP_SESSION_REQUEST]	= "STOP_SESSION_REQUEST",
+	[PPTP_STOP_SESSION_REPLY]	= "STOP_SESSION_REPLY",
+	[PPTP_ECHO_REQUEST]		= "ECHO_REQUEST",
+	[PPTP_ECHO_REPLY]		= "ECHO_REPLY",
+	[PPTP_OUT_CALL_REQUEST]		= "OUT_CALL_REQUEST",
+	[PPTP_OUT_CALL_REPLY]		= "OUT_CALL_REPLY",
+	[PPTP_IN_CALL_REQUEST]		= "IN_CALL_REQUEST",
+	[PPTP_IN_CALL_REPLY]		= "IN_CALL_REPLY",
+	[PPTP_IN_CALL_CONNECT]		= "IN_CALL_CONNECT",
+	[PPTP_CALL_CLEAR_REQUEST]	= "CALL_CLEAR_REQUEST",
+	[PPTP_CALL_DISCONNECT_NOTIFY]	= "CALL_DISCONNECT_NOTIFY",
+	[PPTP_WAN_ERROR_NOTIFY]		= "WAN_ERROR_NOTIFY",
+	[PPTP_SET_LINK_INFO]		= "SET_LINK_INFO"
 };
+
+const char *pptp_msg_name(u_int16_t msg)
+{
+	if (msg > PPTP_MSG_MAX)
+		return pptp_msg_name_array[0];
+
+	return pptp_msg_name_array[msg];
+}
 EXPORT_SYMBOL(pptp_msg_name);
 #endif
 
@@ -276,7 +284,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff,
 	typeof(nf_nat_pptp_hook_inbound) nf_nat_pptp_inbound;
 
 	msg = ntohs(ctlh->messageType);
-	pr_debug("inbound control message %s\n", pptp_msg_name[msg]);
+	pr_debug("inbound control message %s\n", pptp_msg_name(msg));
 
 	switch (msg) {
 	case PPTP_START_SESSION_REPLY:
@@ -311,7 +319,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff,
 		pcid = pptpReq->ocack.peersCallID;
 		if (info->pns_call_id != pcid)
 			goto invalid;
-		pr_debug("%s, CID=%X, PCID=%X\n", pptp_msg_name[msg],
+		pr_debug("%s, CID=%X, PCID=%X\n", pptp_msg_name(msg),
 			 ntohs(cid), ntohs(pcid));
 
 		if (pptpReq->ocack.resultCode == PPTP_OUTCALL_CONNECT) {
@@ -328,7 +336,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff,
 			goto invalid;
 
 		cid = pptpReq->icreq.callID;
-		pr_debug("%s, CID=%X\n", pptp_msg_name[msg], ntohs(cid));
+		pr_debug("%s, CID=%X\n", pptp_msg_name(msg), ntohs(cid));
 		info->cstate = PPTP_CALL_IN_REQ;
 		info->pac_call_id = cid;
 		break;
@@ -347,7 +355,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff,
 		if (info->pns_call_id != pcid)
 			goto invalid;
 
-		pr_debug("%s, PCID=%X\n", pptp_msg_name[msg], ntohs(pcid));
+		pr_debug("%s, PCID=%X\n", pptp_msg_name(msg), ntohs(pcid));
 		info->cstate = PPTP_CALL_IN_CONF;
 
 		/* we expect a GRE connection from PAC to PNS */
@@ -357,7 +365,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff,
 	case PPTP_CALL_DISCONNECT_NOTIFY:
 		/* server confirms disconnect */
 		cid = pptpReq->disc.callID;
-		pr_debug("%s, CID=%X\n", pptp_msg_name[msg], ntohs(cid));
+		pr_debug("%s, CID=%X\n", pptp_msg_name(msg), ntohs(cid));
 		info->cstate = PPTP_CALL_NONE;
 
 		/* untrack this call id, unexpect GRE packets */
@@ -384,7 +392,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff,
 invalid:
 	pr_debug("invalid %s: type=%d cid=%u pcid=%u "
 		 "cstate=%d sstate=%d pns_cid=%u pac_cid=%u\n",
-		 msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] : pptp_msg_name[0],
+		 pptp_msg_name(msg),
 		 msg, ntohs(cid), ntohs(pcid),  info->cstate, info->sstate,
 		 ntohs(info->pns_call_id), ntohs(info->pac_call_id));
 	return NF_ACCEPT;
@@ -404,7 +412,7 @@ pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff,
 	typeof(nf_nat_pptp_hook_outbound) nf_nat_pptp_outbound;
 
 	msg = ntohs(ctlh->messageType);
-	pr_debug("outbound control message %s\n", pptp_msg_name[msg]);
+	pr_debug("outbound control message %s\n", pptp_msg_name(msg));
 
 	switch (msg) {
 	case PPTP_START_SESSION_REQUEST:
@@ -426,7 +434,7 @@ pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff,
 		info->cstate = PPTP_CALL_OUT_REQ;
 		/* track PNS call id */
 		cid = pptpReq->ocreq.callID;
-		pr_debug("%s, CID=%X\n", pptp_msg_name[msg], ntohs(cid));
+		pr_debug("%s, CID=%X\n", pptp_msg_name(msg), ntohs(cid));
 		info->pns_call_id = cid;
 		break;
 
@@ -440,7 +448,7 @@ pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff,
 		pcid = pptpReq->icack.peersCallID;
 		if (info->pac_call_id != pcid)
 			goto invalid;
-		pr_debug("%s, CID=%X PCID=%X\n", pptp_msg_name[msg],
+		pr_debug("%s, CID=%X PCID=%X\n", pptp_msg_name(msg),
 			 ntohs(cid), ntohs(pcid));
 
 		if (pptpReq->icack.resultCode == PPTP_INCALL_ACCEPT) {
@@ -480,7 +488,7 @@ pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff,
 invalid:
 	pr_debug("invalid %s: type=%d cid=%u pcid=%u "
 		 "cstate=%d sstate=%d pns_cid=%u pac_cid=%u\n",
-		 msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] : pptp_msg_name[0],
+		 pptp_msg_name(msg),
 		 msg, ntohs(cid), ntohs(pcid),  info->cstate, info->sstate,
 		 ntohs(info->pns_call_id), ntohs(info->pac_call_id));
 	return NF_ACCEPT;
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index b6b14db3955b..b3f4a334f9d7 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -677,6 +677,9 @@ static int dccp_timeout_nlattr_to_obj(struct nlattr *tb[],
 	unsigned int *timeouts = data;
 	int i;
 
+	if (!timeouts)
+		 timeouts = dn->dccp_timeout;
+
 	/* set default DCCP timeouts. */
 	for (i=0; i<CT_DCCP_MAX; i++)
 		timeouts[i] = dn->dccp_timeout[i];
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index 522c08c23600..8ddcd5100638 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -114,7 +114,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = {
 	{
 /*	ORIGINAL	*/
 /*                  sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */
-/* init         */ {sCW, sCW, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA},
+/* init         */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA},
 /* init_ack     */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},
 /* abort        */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL},
 /* shutdown     */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL, sSS},
@@ -130,7 +130,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = {
 /*	REPLY	*/
 /*                  sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */
 /* init         */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* INIT in sCL Big TODO */
-/* init_ack     */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},
+/* init_ack     */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},
 /* abort        */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV, sCL},
 /* shutdown     */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV, sSR},
 /* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV, sHA},
@@ -316,7 +316,7 @@ sctp_new(struct nf_conn *ct, const struct sk_buff *skb,
 			ct->proto.sctp.vtag[IP_CT_DIR_REPLY] = sh->vtag;
 		}
 
-		ct->proto.sctp.state = new_state;
+		ct->proto.sctp.state = SCTP_CONNTRACK_NONE;
 	}
 
 	return true;
@@ -594,6 +594,9 @@ static int sctp_timeout_nlattr_to_obj(struct nlattr *tb[],
 	struct nf_sctp_net *sn = nf_sctp_pernet(net);
 	int i;
 
+	if (!timeouts)
+		timeouts = sn->timeouts;
+
 	/* set default SCTP timeouts. */
 	for (i=0; i<SCTP_CONNTRACK_MAX; i++)
 		timeouts[i] = sn->timeouts[i];
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 0006503d2da9..199e00cc6ec3 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -411,7 +411,7 @@ static void *ct_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 		*pos = cpu + 1;
 		return per_cpu_ptr(net->ct.stat, cpu);
 	}
-
+	(*pos)++;
 	return NULL;
 }
 
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index b9e7dd6e60ce..e92aa6b7eb80 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -189,6 +189,7 @@ static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev,
 	if (!pskb_may_pull(skb, thoff + sizeof(*ports)))
 		return -1;
 
+	iph = ip_hdr(skb);
 	ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
 
 	tuple->src_v4.s_addr	= iph->saddr;
@@ -449,6 +450,7 @@ static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev,
 	if (!pskb_may_pull(skb, thoff + sizeof(*ports)))
 		return -1;
 
+	ip6h = ipv6_hdr(skb);
 	ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
 
 	tuple->src_v6		= ip6h->saddr;
diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c
index 83a24cc5753b..28d3313db8f9 100644
--- a/net/netfilter/nf_nat_proto.c
+++ b/net/netfilter/nf_nat_proto.c
@@ -68,15 +68,13 @@ static bool udp_manip_pkt(struct sk_buff *skb,
 			  enum nf_nat_manip_type maniptype)
 {
 	struct udphdr *hdr;
-	bool do_csum;
 
 	if (!skb_make_writable(skb, hdroff + sizeof(*hdr)))
 		return false;
 
 	hdr = (struct udphdr *)(skb->data + hdroff);
-	do_csum = hdr->check || skb->ip_summed == CHECKSUM_PARTIAL;
+	__udp_manip_pkt(skb, iphdroff, hdr, tuple, maniptype, !!hdr->check);
 
-	__udp_manip_pkt(skb, iphdroff, hdr, tuple, maniptype, do_csum);
 	return true;
 }
 
@@ -233,6 +231,19 @@ icmp_manip_pkt(struct sk_buff *skb,
 		return false;
 
 	hdr = (struct icmphdr *)(skb->data + hdroff);
+	switch (hdr->type) {
+	case ICMP_ECHO:
+	case ICMP_ECHOREPLY:
+	case ICMP_TIMESTAMP:
+	case ICMP_TIMESTAMPREPLY:
+	case ICMP_INFO_REQUEST:
+	case ICMP_INFO_REPLY:
+	case ICMP_ADDRESS:
+	case ICMP_ADDRESSREPLY:
+		break;
+	default:
+		return true;
+	}
 	inet_proto_csum_replace2(&hdr->checksum, skb,
 				 hdr->un.echo.id, tuple->src.u.icmp.id, false);
 	hdr->un.echo.id = tuple->src.u.icmp.id;
@@ -1022,8 +1033,8 @@ int nf_nat_inet_register_fn(struct net *net, const struct nf_hook_ops *ops)
 	ret = nf_nat_register_fn(net, NFPROTO_IPV4, ops, nf_nat_ipv4_ops,
 				 ARRAY_SIZE(nf_nat_ipv4_ops));
 	if (ret)
-		nf_nat_ipv6_unregister_fn(net, ops);
-
+		nf_nat_unregister_fn(net, NFPROTO_IPV6, ops,
+					ARRAY_SIZE(nf_nat_ipv6_ops));
 	return ret;
 }
 EXPORT_SYMBOL_GPL(nf_nat_inet_register_fn);
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 2c440015ff0c..3d8aca9ac06d 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -190,7 +190,7 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state,
 		goto err;
 	}
 
-	if (!skb_dst_force(skb) && state->hook != NF_INET_PRE_ROUTING) {
+	if (skb_dst(skb) && !skb_dst_force(skb)) {
 		status = -ENETDOWN;
 		goto err;
 	}
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index 8ce74ed985c0..969efcc725cb 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -270,7 +270,7 @@ static void *synproxy_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 		*pos = cpu + 1;
 		return per_cpu_ptr(snet->stats, cpu);
 	}
-
+	(*pos)++;
 	return NULL;
 }
 
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 4d8714d78192..dd8d4bb1145c 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -21,6 +21,8 @@
 #include <net/net_namespace.h>
 #include <net/sock.h>
 
+#define NFT_MODULE_AUTOLOAD_LIMIT (MODULE_NAME_LEN - sizeof("nft-expr-255-"))
+
 static LIST_HEAD(nf_tables_expressions);
 static LIST_HEAD(nf_tables_objects);
 static LIST_HEAD(nf_tables_flowtables);
@@ -485,46 +487,70 @@ static inline u64 nf_tables_alloc_handle(struct nft_table *table)
 static const struct nft_chain_type *chain_type[NFPROTO_NUMPROTO][NFT_CHAIN_T_MAX];
 
 static const struct nft_chain_type *
+__nft_chain_type_get(u8 family, enum nft_chain_types type)
+{
+	if (family >= NFPROTO_NUMPROTO ||
+	    type >= NFT_CHAIN_T_MAX)
+		return NULL;
+
+	return chain_type[family][type];
+}
+
+static const struct nft_chain_type *
 __nf_tables_chain_type_lookup(const struct nlattr *nla, u8 family)
 {
+	const struct nft_chain_type *type;
 	int i;
 
 	for (i = 0; i < NFT_CHAIN_T_MAX; i++) {
-		if (chain_type[family][i] != NULL &&
-		    !nla_strcmp(nla, chain_type[family][i]->name))
-			return chain_type[family][i];
+		type = __nft_chain_type_get(family, i);
+		if (!type)
+			continue;
+		if (!nla_strcmp(nla, type->name))
+			return type;
 	}
 	return NULL;
 }
 
-/*
- * Loading a module requires dropping mutex that guards the
- * transaction.
- * We first need to abort any pending transactions as once
- * mutex is unlocked a different client could start a new
- * transaction.  It must not see any 'future generation'
- * changes * as these changes will never happen.
- */
-#ifdef CONFIG_MODULES
-static int __nf_tables_abort(struct net *net);
+struct nft_module_request {
+	struct list_head	list;
+	char			module[MODULE_NAME_LEN];
+	bool			done;
+};
 
-static void nft_request_module(struct net *net, const char *fmt, ...)
+#ifdef CONFIG_MODULES
+static int nft_request_module(struct net *net, const char *fmt, ...)
 {
 	char module_name[MODULE_NAME_LEN];
+	struct nft_module_request *req;
 	va_list args;
 	int ret;
 
-	__nf_tables_abort(net);
-
 	va_start(args, fmt);
 	ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args);
 	va_end(args);
-	if (WARN(ret >= MODULE_NAME_LEN, "truncated: '%s' (len %d)", module_name, ret))
-		return;
+	if (ret >= MODULE_NAME_LEN)
+		return 0;
 
-	mutex_unlock(&net->nft.commit_mutex);
-	request_module("%s", module_name);
-	mutex_lock(&net->nft.commit_mutex);
+	list_for_each_entry(req, &net->nft.module_list, list) {
+		if (!strcmp(req->module, module_name)) {
+			if (req->done)
+				return 0;
+
+			/* A request to load this module already exists. */
+			return -EAGAIN;
+		}
+	}
+
+	req = kmalloc(sizeof(*req), GFP_KERNEL);
+	if (!req)
+		return -ENOMEM;
+
+	req->done = false;
+	strlcpy(req->module, module_name, MODULE_NAME_LEN);
+	list_add_tail(&req->list, &net->nft.module_list);
+
+	return -EAGAIN;
 }
 #endif
 
@@ -548,10 +574,9 @@ nf_tables_chain_type_lookup(struct net *net, const struct nlattr *nla,
 	lockdep_nfnl_nft_mutex_not_held();
 #ifdef CONFIG_MODULES
 	if (autoload) {
-		nft_request_module(net, "nft-chain-%u-%.*s", family,
-				   nla_len(nla), (const char *)nla_data(nla));
-		type = __nf_tables_chain_type_lookup(nla, family);
-		if (type != NULL)
+		if (nft_request_module(net, "nft-chain-%u-%.*s", family,
+				       nla_len(nla),
+				       (const char *)nla_data(nla)) == -EAGAIN)
 			return ERR_PTR(-EAGAIN);
 	}
 #endif
@@ -976,12 +1001,18 @@ static int nft_flush_table(struct nft_ctx *ctx)
 	}
 
 	list_for_each_entry_safe(flowtable, nft, &ctx->table->flowtables, list) {
+		if (!nft_is_active_next(ctx->net, flowtable))
+			continue;
+
 		err = nft_delflowtable(ctx, flowtable);
 		if (err < 0)
 			goto out;
 	}
 
 	list_for_each_entry_safe(obj, ne, &ctx->table->objects, list) {
+		if (!nft_is_active_next(ctx->net, obj))
+			continue;
+
 		err = nft_delobj(ctx, obj);
 		if (err < 0)
 			goto out;
@@ -1084,11 +1115,8 @@ static void nf_tables_table_destroy(struct nft_ctx *ctx)
 
 void nft_register_chain_type(const struct nft_chain_type *ctype)
 {
-	if (WARN_ON(ctype->family >= NFPROTO_NUMPROTO))
-		return;
-
 	nfnl_lock(NFNL_SUBSYS_NFTABLES);
-	if (WARN_ON(chain_type[ctype->family][ctype->type] != NULL)) {
+	if (WARN_ON(__nft_chain_type_get(ctype->family, ctype->type))) {
 		nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 		return;
 	}
@@ -1172,7 +1200,8 @@ static const struct nla_policy nft_chain_policy[NFTA_CHAIN_MAX + 1] = {
 				    .len = NFT_CHAIN_MAXNAMELEN - 1 },
 	[NFTA_CHAIN_HOOK]	= { .type = NLA_NESTED },
 	[NFTA_CHAIN_POLICY]	= { .type = NLA_U32 },
-	[NFTA_CHAIN_TYPE]	= { .type = NLA_STRING },
+	[NFTA_CHAIN_TYPE]	= { .type = NLA_STRING,
+				    .len = NFT_MODULE_AUTOLOAD_LIMIT },
 	[NFTA_CHAIN_COUNTERS]	= { .type = NLA_NESTED },
 };
 
@@ -1545,7 +1574,10 @@ static int nft_chain_parse_hook(struct net *net,
 	hook->num = ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM]));
 	hook->priority = ntohl(nla_get_be32(ha[NFTA_HOOK_PRIORITY]));
 
-	type = chain_type[family][NFT_CHAIN_T_DEFAULT];
+	type = __nft_chain_type_get(family, NFT_CHAIN_T_DEFAULT);
+	if (!type)
+		return -EOPNOTSUPP;
+
 	if (nla[NFTA_CHAIN_TYPE]) {
 		type = nf_tables_chain_type_lookup(net, nla[NFTA_CHAIN_TYPE],
 						   family, autoload);
@@ -2031,6 +2063,18 @@ static const struct nft_expr_type *__nft_expr_type_get(u8 family,
 	return NULL;
 }
 
+#ifdef CONFIG_MODULES
+static int nft_expr_type_request_module(struct net *net, u8 family,
+					struct nlattr *nla)
+{
+	if (nft_request_module(net, "nft-expr-%u-%.*s", family,
+			       nla_len(nla), (char *)nla_data(nla)) == -EAGAIN)
+		return -EAGAIN;
+
+	return 0;
+}
+#endif
+
 static const struct nft_expr_type *nft_expr_type_get(struct net *net,
 						     u8 family,
 						     struct nlattr *nla)
@@ -2047,14 +2091,12 @@ static const struct nft_expr_type *nft_expr_type_get(struct net *net,
 	lockdep_nfnl_nft_mutex_not_held();
 #ifdef CONFIG_MODULES
 	if (type == NULL) {
-		nft_request_module(net, "nft-expr-%u-%.*s", family,
-				   nla_len(nla), (char *)nla_data(nla));
-		if (__nft_expr_type_get(family, nla))
+		if (nft_expr_type_request_module(net, family, nla) == -EAGAIN)
 			return ERR_PTR(-EAGAIN);
 
-		nft_request_module(net, "nft-expr-%.*s",
-				   nla_len(nla), (char *)nla_data(nla));
-		if (__nft_expr_type_get(family, nla))
+		if (nft_request_module(net, "nft-expr-%.*s",
+				       nla_len(nla),
+				       (char *)nla_data(nla)) == -EAGAIN)
 			return ERR_PTR(-EAGAIN);
 	}
 #endif
@@ -2062,7 +2104,8 @@ static const struct nft_expr_type *nft_expr_type_get(struct net *net,
 }
 
 static const struct nla_policy nft_expr_policy[NFTA_EXPR_MAX + 1] = {
-	[NFTA_EXPR_NAME]	= { .type = NLA_STRING },
+	[NFTA_EXPR_NAME]	= { .type = NLA_STRING,
+				    .len = NFT_MODULE_AUTOLOAD_LIMIT },
 	[NFTA_EXPR_DATA]	= { .type = NLA_NESTED },
 };
 
@@ -2142,6 +2185,13 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx,
 				       (const struct nlattr * const *)info->tb);
 		if (IS_ERR(ops)) {
 			err = PTR_ERR(ops);
+#ifdef CONFIG_MODULES
+			if (err == -EAGAIN)
+				if (nft_expr_type_request_module(ctx->net,
+								 ctx->family,
+								 tb[NFTA_EXPR_NAME]) != -EAGAIN)
+					err = -ENOENT;
+#endif
 			goto err1;
 		}
 	} else
@@ -2967,8 +3017,7 @@ nft_select_set_ops(const struct nft_ctx *ctx,
 	lockdep_nfnl_nft_mutex_not_held();
 #ifdef CONFIG_MODULES
 	if (list_empty(&nf_tables_set_types)) {
-		nft_request_module(ctx->net, "nft-set");
-		if (!list_empty(&nf_tables_set_types))
+		if (nft_request_module(ctx->net, "nft-set") == -EAGAIN)
 			return ERR_PTR(-EAGAIN);
 	}
 #endif
@@ -3519,7 +3568,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
 			      NFT_SET_INTERVAL | NFT_SET_TIMEOUT |
 			      NFT_SET_MAP | NFT_SET_EVAL |
 			      NFT_SET_OBJECT))
-			return -EINVAL;
+			return -EOPNOTSUPP;
 		/* Only one of these operations is supported */
 		if ((flags & (NFT_SET_MAP | NFT_SET_OBJECT)) ==
 			     (NFT_SET_MAP | NFT_SET_OBJECT))
@@ -3557,7 +3606,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
 		objtype = ntohl(nla_get_be32(nla[NFTA_SET_OBJ_TYPE]));
 		if (objtype == NFT_OBJECT_UNSPEC ||
 		    objtype > NFT_OBJECT_MAX)
-			return -EINVAL;
+			return -EOPNOTSUPP;
 	} else if (flags & NFT_SET_OBJECT)
 		return -EINVAL;
 	else
@@ -3888,7 +3937,8 @@ static const struct nla_policy nft_set_elem_policy[NFTA_SET_ELEM_MAX + 1] = {
 	[NFTA_SET_ELEM_USERDATA]	= { .type = NLA_BINARY,
 					    .len = NFT_USERDATA_MAXLEN },
 	[NFTA_SET_ELEM_EXPR]		= { .type = NLA_NESTED },
-	[NFTA_SET_ELEM_OBJREF]		= { .type = NLA_STRING },
+	[NFTA_SET_ELEM_OBJREF]		= { .type = NLA_STRING,
+					    .len = NFT_OBJ_MAXNAMELEN - 1 },
 };
 
 static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX + 1] = {
@@ -4209,8 +4259,10 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 		return err;
 
 	err = -EINVAL;
-	if (desc.type != NFT_DATA_VALUE || desc.len != set->klen)
+	if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) {
+		nft_data_release(&elem.key.val, desc.type);
 		return err;
+	}
 
 	priv = set->ops->get(ctx->net, set, &elem, flags);
 	if (IS_ERR(priv))
@@ -4443,14 +4495,20 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 		if (nla[NFTA_SET_ELEM_DATA] == NULL &&
 		    !(flags & NFT_SET_ELEM_INTERVAL_END))
 			return -EINVAL;
-		if (nla[NFTA_SET_ELEM_DATA] != NULL &&
-		    flags & NFT_SET_ELEM_INTERVAL_END)
-			return -EINVAL;
 	} else {
 		if (nla[NFTA_SET_ELEM_DATA] != NULL)
 			return -EINVAL;
 	}
 
+	if ((flags & NFT_SET_ELEM_INTERVAL_END) &&
+	     (nla[NFTA_SET_ELEM_DATA] ||
+	      nla[NFTA_SET_ELEM_OBJREF] ||
+	      nla[NFTA_SET_ELEM_TIMEOUT] ||
+	      nla[NFTA_SET_ELEM_EXPIRATION] ||
+	      nla[NFTA_SET_ELEM_USERDATA] ||
+	      nla[NFTA_SET_ELEM_EXPR]))
+		return -EINVAL;
+
 	timeout = 0;
 	if (nla[NFTA_SET_ELEM_TIMEOUT] != NULL) {
 		if (!(set->flags & NFT_SET_TIMEOUT))
@@ -5071,8 +5129,7 @@ nft_obj_type_get(struct net *net, u32 objtype)
 	lockdep_nfnl_nft_mutex_not_held();
 #ifdef CONFIG_MODULES
 	if (type == NULL) {
-		nft_request_module(net, "nft-obj-%u", objtype);
-		if (__nft_obj_type_get(objtype))
+		if (nft_request_module(net, "nft-obj-%u", objtype) == -EAGAIN)
 			return ERR_PTR(-EAGAIN);
 	}
 #endif
@@ -5634,8 +5691,7 @@ nft_flowtable_type_get(struct net *net, u8 family)
 	lockdep_nfnl_nft_mutex_not_held();
 #ifdef CONFIG_MODULES
 	if (type == NULL) {
-		nft_request_module(net, "nf-flowtable-%u", family);
-		if (__nft_flowtable_type_get(family))
+		if (nft_request_module(net, "nf-flowtable-%u", family) == -EAGAIN)
 			return ERR_PTR(-EAGAIN);
 	}
 #endif
@@ -6567,6 +6623,18 @@ static void nft_chain_del(struct nft_chain *chain)
 	list_del_rcu(&chain->list);
 }
 
+static void nf_tables_module_autoload_cleanup(struct net *net)
+{
+	struct nft_module_request *req, *next;
+
+	WARN_ON_ONCE(!list_empty(&net->nft.commit_list));
+	list_for_each_entry_safe(req, next, &net->nft.module_list, list) {
+		WARN_ON_ONCE(!req->done);
+		list_del(&req->list);
+		kfree(req);
+	}
+}
+
 static void nf_tables_commit_release(struct net *net)
 {
 	struct nft_trans *trans;
@@ -6579,6 +6647,7 @@ static void nf_tables_commit_release(struct net *net)
 	 * to prevent expensive synchronize_rcu() in commit phase.
 	 */
 	if (list_empty(&net->nft.commit_list)) {
+		nf_tables_module_autoload_cleanup(net);
 		mutex_unlock(&net->nft.commit_mutex);
 		return;
 	}
@@ -6593,6 +6662,7 @@ static void nf_tables_commit_release(struct net *net)
 	list_splice_tail_init(&net->nft.commit_list, &nf_tables_destroy_list);
 	spin_unlock(&nf_tables_destroy_list_lock);
 
+	nf_tables_module_autoload_cleanup(net);
 	mutex_unlock(&net->nft.commit_mutex);
 
 	schedule_work(&trans_destroy_work);
@@ -6771,6 +6841,21 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 	return 0;
 }
 
+static void nf_tables_module_autoload(struct net *net)
+{
+	struct nft_module_request *req, *next;
+	LIST_HEAD(module_list);
+
+	list_splice_init(&net->nft.module_list, &module_list);
+	mutex_unlock(&net->nft.commit_mutex);
+	list_for_each_entry_safe(req, next, &module_list, list) {
+		request_module("%s", req->module);
+		req->done = true;
+	}
+	mutex_lock(&net->nft.commit_mutex);
+	list_splice(&module_list, &net->nft.module_list);
+}
+
 static void nf_tables_abort_release(struct nft_trans *trans)
 {
 	switch (trans->msg_type) {
@@ -6800,7 +6885,7 @@ static void nf_tables_abort_release(struct nft_trans *trans)
 	kfree(trans);
 }
 
-static int __nf_tables_abort(struct net *net)
+static int __nf_tables_abort(struct net *net, bool autoload)
 {
 	struct nft_trans *trans, *next;
 	struct nft_trans_elem *te;
@@ -6917,6 +7002,11 @@ static int __nf_tables_abort(struct net *net)
 		nf_tables_abort_release(trans);
 	}
 
+	if (autoload)
+		nf_tables_module_autoload(net);
+	else
+		nf_tables_module_autoload_cleanup(net);
+
 	return 0;
 }
 
@@ -6925,9 +7015,9 @@ static void nf_tables_cleanup(struct net *net)
 	nft_validate_state_update(net, NFT_VALIDATE_SKIP);
 }
 
-static int nf_tables_abort(struct net *net, struct sk_buff *skb)
+static int nf_tables_abort(struct net *net, struct sk_buff *skb, bool autoload)
 {
-	int ret = __nf_tables_abort(net);
+	int ret = __nf_tables_abort(net, autoload);
 
 	mutex_unlock(&net->nft.commit_mutex);
 
@@ -7522,6 +7612,7 @@ static int __net_init nf_tables_init_net(struct net *net)
 {
 	INIT_LIST_HEAD(&net->nft.tables);
 	INIT_LIST_HEAD(&net->nft.commit_list);
+	INIT_LIST_HEAD(&net->nft.module_list);
 	mutex_init(&net->nft.commit_mutex);
 	net->nft.base_seq = 1;
 	net->nft.validate_state = NFT_VALIDATE_SKIP;
@@ -7533,10 +7624,11 @@ static void __net_exit nf_tables_exit_net(struct net *net)
 {
 	mutex_lock(&net->nft.commit_mutex);
 	if (!list_empty(&net->nft.commit_list))
-		__nf_tables_abort(net);
+		__nf_tables_abort(net, false);
 	__nft_release_tables(net);
 	mutex_unlock(&net->nft.commit_mutex);
 	WARN_ON_ONCE(!list_empty(&net->nft.tables));
+	WARN_ON_ONCE(!list_empty(&net->nft.module_list));
 }
 
 static struct pernet_operations nf_tables_net_ops = {
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 4abbb452cf6c..99127e2d95a8 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -476,7 +476,7 @@ ack:
 	}
 done:
 	if (status & NFNL_BATCH_REPLAY) {
-		ss->abort(net, oskb);
+		ss->abort(net, oskb, true);
 		nfnl_err_reset(&err_list);
 		kfree_skb(skb);
 		module_put(ss->owner);
@@ -487,11 +487,11 @@ done:
 			status |= NFNL_BATCH_REPLAY;
 			goto done;
 		} else if (err) {
-			ss->abort(net, oskb);
+			ss->abort(net, oskb, false);
 			netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL);
 		}
 	} else {
-		ss->abort(net, oskb);
+		ss->abort(net, oskb, false);
 	}
 	if (ss->cleanup)
 		ss->cleanup(net);
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index 7525063c25f5..81406b93f126 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -103,7 +103,7 @@ nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct)
 	if (help->helper->data_len == 0)
 		return -EINVAL;
 
-	nla_memcpy(help->data, nla_data(attr), sizeof(help->data));
+	nla_memcpy(help->data, attr, sizeof(help->data));
 	return 0;
 }
 
@@ -240,6 +240,7 @@ nfnl_cthelper_create(const struct nlattr * const tb[],
 		ret = -ENOMEM;
 		goto err2;
 	}
+	helper->data_len = size;
 
 	helper->flags |= NF_CT_HELPER_F_USERSPACE;
 	memcpy(&helper->tuple, tuple, sizeof(struct nf_conntrack_tuple));
@@ -742,6 +743,8 @@ static const struct nla_policy nfnl_cthelper_policy[NFCTH_MAX+1] = {
 	[NFCTH_NAME] = { .type = NLA_NUL_STRING,
 			 .len = NF_CT_HELPER_NAME_LEN-1 },
 	[NFCTH_QUEUE_NUM] = { .type = NLA_U32, },
+	[NFCTH_PRIV_DATA_LEN] = { .type = NLA_U32, },
+	[NFCTH_STATUS] = { .type = NLA_U32, },
 };
 
 static const struct nfnl_callback nfnl_cthelper_cb[NFNL_MSG_CTHELPER_MAX] = {
diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c
index f42326b40d6f..2e7ced752ef1 100644
--- a/net/netfilter/nfnetlink_osf.c
+++ b/net/netfilter/nfnetlink_osf.c
@@ -166,12 +166,12 @@ static bool nf_osf_match_one(const struct sk_buff *skb,
 static const struct tcphdr *nf_osf_hdr_ctx_init(struct nf_osf_hdr_ctx *ctx,
 						const struct sk_buff *skb,
 						const struct iphdr *ip,
-						unsigned char *opts)
+						unsigned char *opts,
+						struct tcphdr *_tcph)
 {
 	const struct tcphdr *tcp;
-	struct tcphdr _tcph;
 
-	tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), &_tcph);
+	tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), _tcph);
 	if (!tcp)
 		return NULL;
 
@@ -206,10 +206,11 @@ nf_osf_match(const struct sk_buff *skb, u_int8_t family,
 	int fmatch = FMATCH_WRONG;
 	struct nf_osf_hdr_ctx ctx;
 	const struct tcphdr *tcp;
+	struct tcphdr _tcph;
 
 	memset(&ctx, 0, sizeof(ctx));
 
-	tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts);
+	tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts, &_tcph);
 	if (!tcp)
 		return false;
 
@@ -266,10 +267,11 @@ bool nf_osf_find(const struct sk_buff *skb,
 	const struct nf_osf_finger *kf;
 	struct nf_osf_hdr_ctx ctx;
 	const struct tcphdr *tcp;
+	struct tcphdr _tcph;
 
 	memset(&ctx, 0, sizeof(ctx));
 
-	tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts);
+	tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts, &_tcph);
 	if (!tcp)
 		return false;
 
diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c
index b310b637b550..143b13b28a59 100644
--- a/net/netfilter/nft_bitwise.c
+++ b/net/netfilter/nft_bitwise.c
@@ -79,7 +79,7 @@ static int nft_bitwise_init(const struct nft_ctx *ctx,
 			    tb[NFTA_BITWISE_MASK]);
 	if (err < 0)
 		return err;
-	if (d1.len != priv->len) {
+	if (d1.type != NFT_DATA_VALUE || d1.len != priv->len) {
 		err = -EINVAL;
 		goto err1;
 	}
@@ -88,7 +88,7 @@ static int nft_bitwise_init(const struct nft_ctx *ctx,
 			    tb[NFTA_BITWISE_XOR]);
 	if (err < 0)
 		goto err1;
-	if (d2.len != priv->len) {
+	if (d2.type != NFT_DATA_VALUE || d2.len != priv->len) {
 		err = -EINVAL;
 		goto err2;
 	}
diff --git a/net/netfilter/nft_chain_nat.c b/net/netfilter/nft_chain_nat.c
index ff9ac8ae0031..eac4a901233f 100644
--- a/net/netfilter/nft_chain_nat.c
+++ b/net/netfilter/nft_chain_nat.c
@@ -89,6 +89,7 @@ static const struct nft_chain_type nft_chain_nat_inet = {
 	.name		= "nat",
 	.type		= NFT_CHAIN_T_NAT,
 	.family		= NFPROTO_INET,
+	.owner		= THIS_MODULE,
 	.hook_mask	= (1 << NF_INET_PRE_ROUTING) |
 			  (1 << NF_INET_LOCAL_IN) |
 			  (1 << NF_INET_LOCAL_OUT) |
diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c
index 411c0cf741e3..abd7be110f80 100644
--- a/net/netfilter/nft_cmp.c
+++ b/net/netfilter/nft_cmp.c
@@ -79,6 +79,12 @@ static int nft_cmp_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	if (err < 0)
 		return err;
 
+	if (desc.type != NFT_DATA_VALUE) {
+		err = -EINVAL;
+		nft_data_release(&priv->data, desc.type);
+		return err;
+	}
+
 	priv->sreg = nft_parse_register(tb[NFTA_CMP_SREG]);
 	err = nft_validate_register_load(priv->sreg, desc.len);
 	if (err < 0)
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index 01705ad74a9a..da21b771a259 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -179,9 +179,6 @@ static int nft_flow_offload_init(const struct nft_ctx *ctx,
 static void nft_flow_offload_destroy(const struct nft_ctx *ctx,
 				     const struct nft_expr *expr)
 {
-	struct nft_flow_offload *priv = nft_expr_priv(expr);
-
-	priv->flowtable->use--;
 	nf_ct_netns_put(ctx->net, ctx->family);
 }
 
diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c
index 61b7f93ac681..42afcd2bc6f8 100644
--- a/net/netfilter/nft_fwd_netdev.c
+++ b/net/netfilter/nft_fwd_netdev.c
@@ -27,6 +27,9 @@ static void nft_fwd_netdev_eval(const struct nft_expr *expr,
 	struct nft_fwd_netdev *priv = nft_expr_priv(expr);
 	int oif = regs->data[priv->sreg_dev];
 
+	/* This is used by ifb only. */
+	skb_set_redirected(pkt->skb, true);
+
 	nf_fwd_netdev_egress(pkt, oif);
 	regs->verdict.code = NF_STOLEN;
 }
@@ -179,6 +182,13 @@ nla_put_failure:
 	return -1;
 }
 
+static int nft_fwd_validate(const struct nft_ctx *ctx,
+			    const struct nft_expr *expr,
+			    const struct nft_data **data)
+{
+	return nft_chain_validate_hooks(ctx->chain, (1 << NF_NETDEV_INGRESS));
+}
+
 static struct nft_expr_type nft_fwd_netdev_type;
 static const struct nft_expr_ops nft_fwd_neigh_netdev_ops = {
 	.type		= &nft_fwd_netdev_type,
@@ -186,6 +196,7 @@ static const struct nft_expr_ops nft_fwd_neigh_netdev_ops = {
 	.eval		= nft_fwd_neigh_eval,
 	.init		= nft_fwd_neigh_init,
 	.dump		= nft_fwd_neigh_dump,
+	.validate	= nft_fwd_validate,
 };
 
 static const struct nft_expr_ops nft_fwd_netdev_ops = {
@@ -194,6 +205,7 @@ static const struct nft_expr_ops nft_fwd_netdev_ops = {
 	.eval		= nft_fwd_netdev_eval,
 	.init		= nft_fwd_netdev_init,
 	.dump		= nft_fwd_netdev_dump,
+	.validate	= nft_fwd_validate,
 };
 
 static const struct nft_expr_ops *
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index a54329b8634a..b34231cd82ac 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -544,6 +544,10 @@ nft_meta_select_ops(const struct nft_ctx *ctx,
 	if (tb[NFTA_META_DREG] && tb[NFTA_META_SREG])
 		return ERR_PTR(-EINVAL);
 
+#if defined(CONFIG_NF_TABLES_BRIDGE) && IS_MODULE(CONFIG_NFT_BRIDGE_META)
+	if (ctx->family == NFPROTO_BRIDGE)
+		return ERR_PTR(-EAGAIN);
+#endif
 	if (tb[NFTA_META_DREG])
 		return &nft_meta_get_ops;
 
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index c3c93e95b46e..243e8107f456 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -129,7 +129,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 		priv->type = NF_NAT_MANIP_DST;
 		break;
 	default:
-		return -EINVAL;
+		return -EOPNOTSUPP;
 	}
 
 	if (tb[NFTA_NAT_FAMILY] == NULL)
@@ -196,7 +196,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	if (tb[NFTA_NAT_FLAGS]) {
 		priv->flags = ntohl(nla_get_be32(tb[NFTA_NAT_FLAGS]));
 		if (priv->flags & ~NF_NAT_RANGE_MASK)
-			return -EINVAL;
+			return -EOPNOTSUPP;
 	}
 
 	return nf_ct_netns_get(ctx->net, family);
diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c
index f54d6ae15bb1..b42247aa48a9 100644
--- a/net/netfilter/nft_osf.c
+++ b/net/netfilter/nft_osf.c
@@ -61,6 +61,9 @@ static int nft_osf_init(const struct nft_ctx *ctx,
 	int err;
 	u8 ttl;
 
+	if (!tb[NFTA_OSF_DREG])
+		return -EINVAL;
+
 	if (tb[NFTA_OSF_TTL]) {
 		ttl = nla_get_u8(tb[NFTA_OSF_TTL]);
 		if (ttl > 2)
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 680bd9f38a81..f2ab0066e7a7 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -118,6 +118,7 @@ static const struct nla_policy nft_payload_policy[NFTA_PAYLOAD_MAX + 1] = {
 	[NFTA_PAYLOAD_LEN]		= { .type = NLA_U32 },
 	[NFTA_PAYLOAD_CSUM_TYPE]	= { .type = NLA_U32 },
 	[NFTA_PAYLOAD_CSUM_OFFSET]	= { .type = NLA_U32 },
+	[NFTA_PAYLOAD_CSUM_FLAGS]	= { .type = NLA_U32 },
 };
 
 static int nft_payload_init(const struct nft_ctx *ctx,
diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c
index 4701fa8a45e7..89efcc5a533d 100644
--- a/net/netfilter/nft_range.c
+++ b/net/netfilter/nft_range.c
@@ -66,11 +66,21 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr
 	if (err < 0)
 		return err;
 
+	if (desc_from.type != NFT_DATA_VALUE) {
+		err = -EINVAL;
+		goto err1;
+	}
+
 	err = nft_data_init(NULL, &priv->data_to, sizeof(priv->data_to),
 			    &desc_to, tb[NFTA_RANGE_TO_DATA]);
 	if (err < 0)
 		goto err1;
 
+	if (desc_to.type != NFT_DATA_VALUE) {
+		err = -EINVAL;
+		goto err2;
+	}
+
 	if (desc_from.len != desc_to.len) {
 		err = -EINVAL;
 		goto err2;
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 419d58ef802b..34ae80ea96ae 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -33,6 +33,11 @@ static bool nft_rbtree_interval_end(const struct nft_rbtree_elem *rbe)
 	       (*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END);
 }
 
+static bool nft_rbtree_interval_start(const struct nft_rbtree_elem *rbe)
+{
+	return !nft_rbtree_interval_end(rbe);
+}
+
 static bool nft_rbtree_equal(const struct nft_set *set, const void *this,
 			     const struct nft_rbtree_elem *interval)
 {
@@ -64,7 +69,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set
 			if (interval &&
 			    nft_rbtree_equal(set, this, interval) &&
 			    nft_rbtree_interval_end(rbe) &&
-			    !nft_rbtree_interval_end(interval))
+			    nft_rbtree_interval_start(interval))
 				continue;
 			interval = rbe;
 		} else if (d > 0)
@@ -74,8 +79,17 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set
 				parent = rcu_dereference_raw(parent->rb_left);
 				continue;
 			}
-			if (nft_rbtree_interval_end(rbe))
-				goto out;
+
+			if (nft_set_elem_expired(&rbe->ext))
+				return false;
+
+			if (nft_rbtree_interval_end(rbe)) {
+				if (nft_set_is_anonymous(set))
+					return false;
+				parent = rcu_dereference_raw(parent->rb_left);
+				interval = NULL;
+				continue;
+			}
 
 			*ext = &rbe->ext;
 			return true;
@@ -84,11 +98,12 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set
 
 	if (set->flags & NFT_SET_INTERVAL && interval != NULL &&
 	    nft_set_elem_active(&interval->ext, genmask) &&
-	    !nft_rbtree_interval_end(interval)) {
+	    !nft_set_elem_expired(&interval->ext) &&
+	    nft_rbtree_interval_start(interval)) {
 		*ext = &interval->ext;
 		return true;
 	}
-out:
+
 	return false;
 }
 
@@ -139,8 +154,13 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set,
 			if (flags & NFT_SET_ELEM_INTERVAL_END)
 				interval = rbe;
 		} else {
-			if (!nft_set_elem_active(&rbe->ext, genmask))
+			if (!nft_set_elem_active(&rbe->ext, genmask)) {
 				parent = rcu_dereference_raw(parent->rb_left);
+				continue;
+			}
+
+			if (nft_set_elem_expired(&rbe->ext))
+				return false;
 
 			if (!nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) ||
 			    (*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END) ==
@@ -148,12 +168,17 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set,
 				*elem = rbe;
 				return true;
 			}
-			return false;
+
+			if (nft_rbtree_interval_end(rbe))
+				interval = NULL;
+
+			parent = rcu_dereference_raw(parent->rb_left);
 		}
 	}
 
 	if (set->flags & NFT_SET_INTERVAL && interval != NULL &&
 	    nft_set_elem_active(&interval->ext, genmask) &&
+	    !nft_set_elem_expired(&interval->ext) &&
 	    ((!nft_rbtree_interval_end(interval) &&
 	      !(flags & NFT_SET_ELEM_INTERVAL_END)) ||
 	     (nft_rbtree_interval_end(interval) &&
@@ -213,9 +238,9 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 			p = &parent->rb_right;
 		else {
 			if (nft_rbtree_interval_end(rbe) &&
-			    !nft_rbtree_interval_end(new)) {
+			    nft_rbtree_interval_start(new)) {
 				p = &parent->rb_left;
-			} else if (!nft_rbtree_interval_end(rbe) &&
+			} else if (nft_rbtree_interval_start(rbe) &&
 				   nft_rbtree_interval_end(new)) {
 				p = &parent->rb_right;
 			} else if (nft_set_elem_active(&rbe->ext, genmask)) {
@@ -306,10 +331,10 @@ static void *nft_rbtree_deactivate(const struct net *net,
 			parent = parent->rb_right;
 		else {
 			if (nft_rbtree_interval_end(rbe) &&
-			    !nft_rbtree_interval_end(this)) {
+			    nft_rbtree_interval_start(this)) {
 				parent = parent->rb_left;
 				continue;
-			} else if (!nft_rbtree_interval_end(rbe) &&
+			} else if (nft_rbtree_interval_start(rbe) &&
 				   nft_rbtree_interval_end(this)) {
 				parent = parent->rb_right;
 				continue;
@@ -339,6 +364,8 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
 
 		if (iter->count < iter->skip)
 			goto cont;
+		if (nft_set_elem_expired(&rbe->ext))
+			goto cont;
 		if (!nft_set_elem_active(&rbe->ext, iter->genmask))
 			goto cont;
 
diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c
index f92a82c73880..95980154ef02 100644
--- a/net/netfilter/nft_tproxy.c
+++ b/net/netfilter/nft_tproxy.c
@@ -50,7 +50,7 @@ static void nft_tproxy_eval_v4(const struct nft_expr *expr,
 	taddr = nf_tproxy_laddr4(skb, taddr, iph->daddr);
 
 	if (priv->sreg_port)
-		tport = regs->data[priv->sreg_port];
+		tport = nft_reg_load16(&regs->data[priv->sreg_port]);
 	if (!tport)
 		tport = hp->dest;
 
@@ -117,7 +117,7 @@ static void nft_tproxy_eval_v6(const struct nft_expr *expr,
 	taddr = *nf_tproxy_laddr6(skb, &taddr, &iph->daddr);
 
 	if (priv->sreg_port)
-		tport = regs->data[priv->sreg_port];
+		tport = nft_reg_load16(&regs->data[priv->sreg_port]);
 	if (!tport)
 		tport = hp->dest;
 
diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c
index 3d4c2ae605a8..1effd4878619 100644
--- a/net/netfilter/nft_tunnel.c
+++ b/net/netfilter/nft_tunnel.c
@@ -76,7 +76,7 @@ static int nft_tunnel_get_init(const struct nft_ctx *ctx,
 	struct nft_tunnel *priv = nft_expr_priv(expr);
 	u32 len;
 
-	if (!tb[NFTA_TUNNEL_KEY] &&
+	if (!tb[NFTA_TUNNEL_KEY] ||
 	    !tb[NFTA_TUNNEL_DREG])
 		return -EINVAL;
 
@@ -248,8 +248,9 @@ static int nft_tunnel_obj_vxlan_init(const struct nlattr *attr,
 }
 
 static const struct nla_policy nft_tunnel_opts_erspan_policy[NFTA_TUNNEL_KEY_ERSPAN_MAX + 1] = {
+	[NFTA_TUNNEL_KEY_ERSPAN_VERSION]	= { .type = NLA_U32 },
 	[NFTA_TUNNEL_KEY_ERSPAN_V1_INDEX]	= { .type = NLA_U32 },
-	[NFTA_TUNNEL_KEY_ERSPAN_V2_DIR]	= { .type = NLA_U8 },
+	[NFTA_TUNNEL_KEY_ERSPAN_V2_DIR]		= { .type = NLA_U8 },
 	[NFTA_TUNNEL_KEY_ERSPAN_V2_HWID]	= { .type = NLA_U8 },
 };
 
@@ -266,6 +267,9 @@ static int nft_tunnel_obj_erspan_init(const struct nlattr *attr,
 	if (err < 0)
 		return err;
 
+	if (!tb[NFTA_TUNNEL_KEY_ERSPAN_VERSION])
+		 return -EINVAL;
+
 	version = ntohl(nla_get_be32(tb[NFTA_TUNNEL_KEY_ERSPAN_VERSION]));
 	switch (version) {
 	case ERSPAN_VERSION:
@@ -335,6 +339,8 @@ static const struct nla_policy nft_tunnel_key_policy[NFTA_TUNNEL_KEY_MAX + 1] =
 	[NFTA_TUNNEL_KEY_FLAGS]	= { .type = NLA_U32, },
 	[NFTA_TUNNEL_KEY_TOS]	= { .type = NLA_U8, },
 	[NFTA_TUNNEL_KEY_TTL]	= { .type = NLA_U8, },
+	[NFTA_TUNNEL_KEY_SPORT]	= { .type = NLA_U16, },
+	[NFTA_TUNNEL_KEY_DPORT]	= { .type = NLA_U16, },
 	[NFTA_TUNNEL_KEY_OPTS]	= { .type = NLA_NESTED, },
 };
 
@@ -501,8 +507,8 @@ static int nft_tunnel_opts_dump(struct sk_buff *skb,
 static int nft_tunnel_ports_dump(struct sk_buff *skb,
 				 struct ip_tunnel_info *info)
 {
-	if (nla_put_be16(skb, NFTA_TUNNEL_KEY_SPORT, htons(info->key.tp_src)) < 0 ||
-	    nla_put_be16(skb, NFTA_TUNNEL_KEY_DPORT, htons(info->key.tp_dst)) < 0)
+	if (nla_put_be16(skb, NFTA_TUNNEL_KEY_SPORT, info->key.tp_src) < 0 ||
+	    nla_put_be16(skb, NFTA_TUNNEL_KEY_DPORT, info->key.tp_dst) < 0)
 		return -1;
 
 	return 0;
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index ce70c2576bb2..44f971f31992 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -1551,6 +1551,9 @@ static void *xt_mttg_seq_next(struct seq_file *seq, void *v, loff_t *ppos,
 	uint8_t nfproto = (unsigned long)PDE_DATA(file_inode(seq->file));
 	struct nf_mttg_trav *trav = seq->private;
 
+	if (ppos != NULL)
+		++(*ppos);
+
 	switch (trav->class) {
 	case MTTG_TRAV_INIT:
 		trav->class = MTTG_TRAV_NFP_UNSPEC;
@@ -1576,9 +1579,6 @@ static void *xt_mttg_seq_next(struct seq_file *seq, void *v, loff_t *ppos,
 	default:
 		return NULL;
 	}
-
-	if (ppos != NULL)
-		++*ppos;
 	return trav;
 }
 
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index 2d2691dd51e0..6be05be8ed47 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -36,6 +36,7 @@
 #include <linux/netfilter_ipv6/ip6_tables.h>
 #include <linux/netfilter/xt_hashlimit.h>
 #include <linux/mutex.h>
+#include <linux/refcount.h>
 #include <linux/kernel.h>
 
 MODULE_LICENSE("GPL");
@@ -109,7 +110,7 @@ struct dsthash_ent {
 
 struct xt_hashlimit_htable {
 	struct hlist_node node;		/* global list of all htables */
-	int use;
+	refcount_t use;
 	u_int8_t family;
 	bool rnd_initialized;
 
@@ -310,7 +311,7 @@ static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg,
 	for (i = 0; i < hinfo->cfg.size; i++)
 		INIT_HLIST_HEAD(&hinfo->hash[i]);
 
-	hinfo->use = 1;
+	refcount_set(&hinfo->use, 1);
 	hinfo->count = 0;
 	hinfo->family = family;
 	hinfo->rnd_initialized = false;
@@ -352,21 +353,7 @@ static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg,
 	return 0;
 }
 
-static bool select_all(const struct xt_hashlimit_htable *ht,
-		       const struct dsthash_ent *he)
-{
-	return true;
-}
-
-static bool select_gc(const struct xt_hashlimit_htable *ht,
-		      const struct dsthash_ent *he)
-{
-	return time_after_eq(jiffies, he->expires);
-}
-
-static void htable_selective_cleanup(struct xt_hashlimit_htable *ht,
-			bool (*select)(const struct xt_hashlimit_htable *ht,
-				      const struct dsthash_ent *he))
+static void htable_selective_cleanup(struct xt_hashlimit_htable *ht, bool select_all)
 {
 	unsigned int i;
 
@@ -376,7 +363,7 @@ static void htable_selective_cleanup(struct xt_hashlimit_htable *ht,
 
 		spin_lock_bh(&ht->lock);
 		hlist_for_each_entry_safe(dh, n, &ht->hash[i], node) {
-			if ((*select)(ht, dh))
+			if (time_after_eq(jiffies, dh->expires) || select_all)
 				dsthash_free(ht, dh);
 		}
 		spin_unlock_bh(&ht->lock);
@@ -390,7 +377,7 @@ static void htable_gc(struct work_struct *work)
 
 	ht = container_of(work, struct xt_hashlimit_htable, gc_work.work);
 
-	htable_selective_cleanup(ht, select_gc);
+	htable_selective_cleanup(ht, false);
 
 	queue_delayed_work(system_power_efficient_wq,
 			   &ht->gc_work, msecs_to_jiffies(ht->cfg.gc_interval));
@@ -410,15 +397,6 @@ static void htable_remove_proc_entry(struct xt_hashlimit_htable *hinfo)
 		remove_proc_entry(hinfo->name, parent);
 }
 
-static void htable_destroy(struct xt_hashlimit_htable *hinfo)
-{
-	cancel_delayed_work_sync(&hinfo->gc_work);
-	htable_remove_proc_entry(hinfo);
-	htable_selective_cleanup(hinfo, select_all);
-	kfree(hinfo->name);
-	vfree(hinfo);
-}
-
 static struct xt_hashlimit_htable *htable_find_get(struct net *net,
 						   const char *name,
 						   u_int8_t family)
@@ -429,7 +407,7 @@ static struct xt_hashlimit_htable *htable_find_get(struct net *net,
 	hlist_for_each_entry(hinfo, &hashlimit_net->htables, node) {
 		if (!strcmp(name, hinfo->name) &&
 		    hinfo->family == family) {
-			hinfo->use++;
+			refcount_inc(&hinfo->use);
 			return hinfo;
 		}
 	}
@@ -438,12 +416,16 @@ static struct xt_hashlimit_htable *htable_find_get(struct net *net,
 
 static void htable_put(struct xt_hashlimit_htable *hinfo)
 {
-	mutex_lock(&hashlimit_mutex);
-	if (--hinfo->use == 0) {
+	if (refcount_dec_and_mutex_lock(&hinfo->use, &hashlimit_mutex)) {
 		hlist_del(&hinfo->node);
-		htable_destroy(hinfo);
+		htable_remove_proc_entry(hinfo);
+		mutex_unlock(&hashlimit_mutex);
+
+		cancel_delayed_work_sync(&hinfo->gc_work);
+		htable_selective_cleanup(hinfo, true);
+		kfree(hinfo->name);
+		vfree(hinfo);
 	}
-	mutex_unlock(&hashlimit_mutex);
 }
 
 /* The algorithm used is the Simple Token Bucket Filter (TBF)
@@ -846,6 +828,8 @@ hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	return hashlimit_mt_common(skb, par, hinfo, &info->cfg, 3);
 }
 
+#define HASHLIMIT_MAX_SIZE 1048576
+
 static int hashlimit_mt_check_common(const struct xt_mtchk_param *par,
 				     struct xt_hashlimit_htable **hinfo,
 				     struct hashlimit_cfg3 *cfg,
@@ -856,6 +840,14 @@ static int hashlimit_mt_check_common(const struct xt_mtchk_param *par,
 
 	if (cfg->gc_interval == 0 || cfg->expire == 0)
 		return -EINVAL;
+	if (cfg->size > HASHLIMIT_MAX_SIZE) {
+		cfg->size = HASHLIMIT_MAX_SIZE;
+		pr_info_ratelimited("size too large, truncated to %u\n", cfg->size);
+	}
+	if (cfg->max > HASHLIMIT_MAX_SIZE) {
+		cfg->max = HASHLIMIT_MAX_SIZE;
+		pr_info_ratelimited("max too large, truncated to %u\n", cfg->max);
+	}
 	if (par->family == NFPROTO_IPV4) {
 		if (cfg->srcmask > 32 || cfg->dstmask > 32)
 			return -EINVAL;
diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c
index 781e0b482189..6c2582a19766 100644
--- a/net/netfilter/xt_recent.c
+++ b/net/netfilter/xt_recent.c
@@ -492,12 +492,12 @@ static void *recent_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	const struct recent_entry *e = v;
 	const struct list_head *head = e->list.next;
 
+	(*pos)++;
 	while (head == &t->iphash[st->bucket]) {
 		if (++st->bucket >= ip_list_hash_size)
 			return NULL;
 		head = t->iphash[st->bucket].next;
 	}
-	(*pos)++;
 	return list_entry(head, struct recent_entry, list);
 }
 
diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c
index 2b0ef55cf89e..52389a25d76d 100644
--- a/net/netlabel/netlabel_kapi.c
+++ b/net/netlabel/netlabel_kapi.c
@@ -734,6 +734,12 @@ int netlbl_catmap_getlong(struct netlbl_lsm_catmap *catmap,
 	if ((off & (BITS_PER_LONG - 1)) != 0)
 		return -EINVAL;
 
+	/* a null catmap is equivalent to an empty one */
+	if (!catmap) {
+		*offset = (u32)-1;
+		return 0;
+	}
+
 	if (off < catmap->startbit) {
 		off = catmap->startbit;
 		*offset = off;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index e9ddfd782d16..b7db1f99fc70 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1019,7 +1019,8 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 	if (nlk->netlink_bind && groups) {
 		int group;
 
-		for (group = 0; group < nlk->ngroups; group++) {
+		/* nl_groups is a u32, so cap the maximum groups we can bind */
+		for (group = 0; group < BITS_PER_TYPE(u32); group++) {
 			if (!test_bit(group, &groups))
 				continue;
 			err = nlk->netlink_bind(net, group + 1);
@@ -1038,7 +1039,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 			netlink_insert(sk, nladdr->nl_pid) :
 			netlink_autobind(sock);
 		if (err) {
-			netlink_undo_bind(nlk->ngroups, groups, sk);
+			netlink_undo_bind(BITS_PER_TYPE(u32), groups, sk);
 			goto unlock;
 		}
 	}
@@ -2438,7 +2439,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
 							       in_skb->len))
 				WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_OFFS,
 						    (u8 *)extack->bad_attr -
-						    in_skb->data));
+						    (u8 *)nlh));
 		} else {
 			if (extack->cookie_len)
 				WARN_ON(nla_put(skb, NLMSGERR_ATTR_COOKIE,
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index efccd1ac9a66..102b8d6b5612 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -989,60 +989,11 @@ static struct genl_family genl_ctrl __ro_after_init = {
 	.netnsok = true,
 };
 
-static int genl_bind(struct net *net, int group)
-{
-	struct genl_family *f;
-	int err = -ENOENT;
-	unsigned int id;
-
-	down_read(&cb_lock);
-
-	idr_for_each_entry(&genl_fam_idr, f, id) {
-		if (group >= f->mcgrp_offset &&
-		    group < f->mcgrp_offset + f->n_mcgrps) {
-			int fam_grp = group - f->mcgrp_offset;
-
-			if (!f->netnsok && net != &init_net)
-				err = -ENOENT;
-			else if (f->mcast_bind)
-				err = f->mcast_bind(net, fam_grp);
-			else
-				err = 0;
-			break;
-		}
-	}
-	up_read(&cb_lock);
-
-	return err;
-}
-
-static void genl_unbind(struct net *net, int group)
-{
-	struct genl_family *f;
-	unsigned int id;
-
-	down_read(&cb_lock);
-
-	idr_for_each_entry(&genl_fam_idr, f, id) {
-		if (group >= f->mcgrp_offset &&
-		    group < f->mcgrp_offset + f->n_mcgrps) {
-			int fam_grp = group - f->mcgrp_offset;
-
-			if (f->mcast_unbind)
-				f->mcast_unbind(net, fam_grp);
-			break;
-		}
-	}
-	up_read(&cb_lock);
-}
-
 static int __net_init genl_pernet_init(struct net *net)
 {
 	struct netlink_kernel_cfg cfg = {
 		.input		= genl_rcv,
 		.flags		= NL_CFG_F_NONROOT_RECV,
-		.bind		= genl_bind,
-		.unbind		= genl_unbind,
 	};
 
 	/* we'll bump the group number right afterwards */
diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c
index d41335bad1f8..89cd9de21594 100644
--- a/net/netrom/nr_route.c
+++ b/net/netrom/nr_route.c
@@ -208,6 +208,7 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic,
 		/* refcount initialized at 1 */
 		spin_unlock_bh(&nr_node_list_lock);
 
+		nr_neigh_put(nr_neigh);
 		return 0;
 	}
 	nr_node_lock(nr_node);
diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c
index 6f1b096e601c..43811b5219b5 100644
--- a/net/nfc/hci/core.c
+++ b/net/nfc/hci/core.c
@@ -181,13 +181,20 @@ exit:
 void nfc_hci_cmd_received(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd,
 			  struct sk_buff *skb)
 {
-	u8 gate = hdev->pipes[pipe].gate;
 	u8 status = NFC_HCI_ANY_OK;
 	struct hci_create_pipe_resp *create_info;
 	struct hci_delete_pipe_noti *delete_info;
 	struct hci_all_pipe_cleared_noti *cleared_info;
+	u8 gate;
 
-	pr_debug("from gate %x pipe %x cmd %x\n", gate, pipe, cmd);
+	pr_debug("from pipe %x cmd %x\n", pipe, cmd);
+
+	if (pipe >= NFC_HCI_MAX_PIPES) {
+		status = NFC_HCI_ANY_E_NOK;
+		goto exit;
+	}
+
+	gate = hdev->pipes[pipe].gate;
 
 	switch (cmd) {
 	case NFC_HCI_ADM_NOTIFY_PIPE_CREATED:
@@ -375,8 +382,14 @@ void nfc_hci_event_received(struct nfc_hci_dev *hdev, u8 pipe, u8 event,
 			    struct sk_buff *skb)
 {
 	int r = 0;
-	u8 gate = hdev->pipes[pipe].gate;
+	u8 gate;
+
+	if (pipe >= NFC_HCI_MAX_PIPES) {
+		pr_err("Discarded event %x to invalid pipe %x\n", event, pipe);
+		goto exit;
+	}
 
+	gate = hdev->pipes[pipe].gate;
 	if (gate == NFC_HCI_INVALID_GATE) {
 		pr_err("Discarded event %x to unopened pipe %x\n", event, pipe);
 		goto exit;
diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index afde0d763039..1b261375722e 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -32,6 +32,7 @@ static const struct nla_policy nfc_genl_policy[NFC_ATTR_MAX + 1] = {
 	[NFC_ATTR_DEVICE_NAME] = { .type = NLA_STRING,
 				.len = NFC_DEVICE_NAME_MAXSIZE },
 	[NFC_ATTR_PROTOCOLS] = { .type = NLA_U32 },
+	[NFC_ATTR_TARGET_INDEX] = { .type = NLA_U32 },
 	[NFC_ATTR_COMM_MODE] = { .type = NLA_U8 },
 	[NFC_ATTR_RF_MODE] = { .type = NLA_U8 },
 	[NFC_ATTR_DEVICE_POWERED] = { .type = NLA_U8 },
@@ -43,7 +44,10 @@ static const struct nla_policy nfc_genl_policy[NFC_ATTR_MAX + 1] = {
 	[NFC_ATTR_LLC_SDP] = { .type = NLA_NESTED },
 	[NFC_ATTR_FIRMWARE_NAME] = { .type = NLA_STRING,
 				     .len = NFC_FIRMWARE_NAME_MAXSIZE },
+	[NFC_ATTR_SE_INDEX] = { .type = NLA_U32 },
 	[NFC_ATTR_SE_APDU] = { .type = NLA_BINARY },
+	[NFC_ATTR_VENDOR_ID] = { .type = NLA_U32 },
+	[NFC_ATTR_VENDOR_SUBCMD] = { .type = NLA_U32 },
 	[NFC_ATTR_VENDOR_DATA] = { .type = NLA_BINARY },
 
 };
diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c
index ba5ffd3badd3..b5c867fe3232 100644
--- a/net/nfc/rawsock.c
+++ b/net/nfc/rawsock.c
@@ -332,10 +332,13 @@ static int rawsock_create(struct net *net, struct socket *sock,
 	if ((sock->type != SOCK_SEQPACKET) && (sock->type != SOCK_RAW))
 		return -ESOCKTNOSUPPORT;
 
-	if (sock->type == SOCK_RAW)
+	if (sock->type == SOCK_RAW) {
+		if (!capable(CAP_NET_RAW))
+			return -EPERM;
 		sock->ops = &rawsock_raw_ops;
-	else
+	} else {
 		sock->ops = &rawsock_ops;
+	}
 
 	sk = sk_alloc(net, PF_NFC, GFP_ATOMIC, nfc_proto->proto, kern);
 	if (!sk)
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index bd131469e4ca..7c541eb9ec5f 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -1206,9 +1206,10 @@ static int execute_check_pkt_len(struct datapath *dp, struct sk_buff *skb,
 				 struct sw_flow_key *key,
 				 const struct nlattr *attr, bool last)
 {
+	struct ovs_skb_cb *ovs_cb = OVS_CB(skb);
 	const struct nlattr *actions, *cpl_arg;
+	int len, max_len, rem = nla_len(attr);
 	const struct check_pkt_len_arg *arg;
-	int rem = nla_len(attr);
 	bool clone_flow_key;
 
 	/* The first netlink attribute in 'attr' is always
@@ -1217,7 +1218,11 @@ static int execute_check_pkt_len(struct datapath *dp, struct sk_buff *skb,
 	cpl_arg = nla_data(attr);
 	arg = nla_data(cpl_arg);
 
-	if (skb->len <= arg->pkt_len) {
+	len = ovs_cb->mru ? ovs_cb->mru + skb->mac_len : skb->len;
+	max_len = arg->pkt_len;
+
+	if ((skb_is_gso(skb) && skb_gso_validate_mac_len(skb, max_len)) ||
+	    len <= max_len) {
 		/* Second netlink attribute in 'attr' is always
 		 * 'OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL'.
 		 */
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index f38466b7050d..8d66222a65df 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -276,10 +276,6 @@ void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key)
 	ovs_ct_update_key(skb, NULL, key, false, false);
 }
 
-#define IN6_ADDR_INITIALIZER(ADDR) \
-	{ (ADDR).s6_addr32[0], (ADDR).s6_addr32[1], \
-	  (ADDR).s6_addr32[2], (ADDR).s6_addr32[3] }
-
 int ovs_ct_put_key(const struct sw_flow_key *swkey,
 		   const struct sw_flow_key *output, struct sk_buff *skb)
 {
@@ -301,24 +297,30 @@ int ovs_ct_put_key(const struct sw_flow_key *swkey,
 
 	if (swkey->ct_orig_proto) {
 		if (swkey->eth.type == htons(ETH_P_IP)) {
-			struct ovs_key_ct_tuple_ipv4 orig = {
-				output->ipv4.ct_orig.src,
-				output->ipv4.ct_orig.dst,
-				output->ct.orig_tp.src,
-				output->ct.orig_tp.dst,
-				output->ct_orig_proto,
-			};
+			struct ovs_key_ct_tuple_ipv4 orig;
+
+			memset(&orig, 0, sizeof(orig));
+			orig.ipv4_src = output->ipv4.ct_orig.src;
+			orig.ipv4_dst = output->ipv4.ct_orig.dst;
+			orig.src_port = output->ct.orig_tp.src;
+			orig.dst_port = output->ct.orig_tp.dst;
+			orig.ipv4_proto = output->ct_orig_proto;
+
 			if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4,
 				    sizeof(orig), &orig))
 				return -EMSGSIZE;
 		} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
-			struct ovs_key_ct_tuple_ipv6 orig = {
-				IN6_ADDR_INITIALIZER(output->ipv6.ct_orig.src),
-				IN6_ADDR_INITIALIZER(output->ipv6.ct_orig.dst),
-				output->ct.orig_tp.src,
-				output->ct.orig_tp.dst,
-				output->ct_orig_proto,
-			};
+			struct ovs_key_ct_tuple_ipv6 orig;
+
+			memset(&orig, 0, sizeof(orig));
+			memcpy(orig.ipv6_src, output->ipv6.ct_orig.src.s6_addr32,
+			       sizeof(orig.ipv6_src));
+			memcpy(orig.ipv6_dst, output->ipv6.ct_orig.dst.s6_addr32,
+			       sizeof(orig.ipv6_dst));
+			orig.src_port = output->ct.orig_tp.src;
+			orig.dst_port = output->ct.orig_tp.dst;
+			orig.ipv6_proto = output->ct_orig_proto;
+
 			if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6,
 				    sizeof(orig), &orig))
 				return -EMSGSIZE;
@@ -1585,7 +1587,7 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
 		case OVS_CT_ATTR_TIMEOUT:
 			memcpy(info->timeout, nla_data(a), nla_len(a));
 			if (!memchr(info->timeout, '\0', nla_len(a))) {
-				OVS_NLERR(log, "Invalid conntrack helper");
+				OVS_NLERR(log, "Invalid conntrack timeout");
 				return -EINVAL;
 			}
 			break;
@@ -1885,7 +1887,8 @@ static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net)
 		struct hlist_head *head = &info->limits[i];
 		struct ovs_ct_limit *ct_limit;
 
-		hlist_for_each_entry_rcu(ct_limit, head, hlist_node)
+		hlist_for_each_entry_rcu(ct_limit, head, hlist_node,
+					 lockdep_ovsl_is_held())
 			kfree_rcu(ct_limit, rcu);
 	}
 	kfree(ovs_net->ct_limit_info->limits);
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 72f091f5c1b7..fc46a08b068e 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -2381,8 +2381,10 @@ static void __net_exit ovs_exit_net(struct net *dnet)
 	struct net *net;
 	LIST_HEAD(head);
 
-	ovs_ct_exit(dnet);
 	ovs_lock();
+
+	ovs_ct_exit(dnet);
+
 	list_for_each_entry_safe(dp, dp_next, &ovs_net->dps, list_node)
 		__dp_destroy(dp);
 
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 01c71a8f0c71..b2e4c4b192e6 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -384,7 +384,7 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status)
 	smp_wmb();
 }
 
-static int __packet_get_status(struct packet_sock *po, void *frame)
+static int __packet_get_status(const struct packet_sock *po, void *frame)
 {
 	union tpacket_uhdr h;
 
@@ -460,10 +460,10 @@ static __u32 __packet_set_timestamp(struct packet_sock *po, void *frame,
 	return ts_status;
 }
 
-static void *packet_lookup_frame(struct packet_sock *po,
-		struct packet_ring_buffer *rb,
-		unsigned int position,
-		int status)
+static void *packet_lookup_frame(const struct packet_sock *po,
+				 const struct packet_ring_buffer *rb,
+				 unsigned int position,
+				 int status)
 {
 	unsigned int pg_vec_pos, frame_offset;
 	union tpacket_uhdr h;
@@ -759,7 +759,7 @@ static void prb_close_block(struct tpacket_kbdq_core *pkc1,
 	struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1;
 	struct sock *sk = &po->sk;
 
-	if (po->stats.stats3.tp_drops)
+	if (atomic_read(&po->tp_drops))
 		status |= TP_STATUS_LOSING;
 
 	last_pkt = (struct tpacket3_hdr *)pkc1->prev;
@@ -1084,10 +1084,10 @@ static void *packet_current_rx_frame(struct packet_sock *po,
 	}
 }
 
-static void *prb_lookup_block(struct packet_sock *po,
-				     struct packet_ring_buffer *rb,
-				     unsigned int idx,
-				     int status)
+static void *prb_lookup_block(const struct packet_sock *po,
+			      const struct packet_ring_buffer *rb,
+			      unsigned int idx,
+			      int status)
 {
 	struct tpacket_kbdq_core *pkc  = GET_PBDQC_FROM_RB(rb);
 	struct tpacket_block_desc *pbd = GET_PBLOCK_DESC(pkc, idx);
@@ -1200,12 +1200,12 @@ static void packet_free_pending(struct packet_sock *po)
 #define ROOM_LOW	0x1
 #define ROOM_NORMAL	0x2
 
-static bool __tpacket_has_room(struct packet_sock *po, int pow_off)
+static bool __tpacket_has_room(const struct packet_sock *po, int pow_off)
 {
 	int idx, len;
 
-	len = po->rx_ring.frame_max + 1;
-	idx = po->rx_ring.head;
+	len = READ_ONCE(po->rx_ring.frame_max) + 1;
+	idx = READ_ONCE(po->rx_ring.head);
 	if (pow_off)
 		idx += len >> pow_off;
 	if (idx >= len)
@@ -1213,12 +1213,12 @@ static bool __tpacket_has_room(struct packet_sock *po, int pow_off)
 	return packet_lookup_frame(po, &po->rx_ring, idx, TP_STATUS_KERNEL);
 }
 
-static bool __tpacket_v3_has_room(struct packet_sock *po, int pow_off)
+static bool __tpacket_v3_has_room(const struct packet_sock *po, int pow_off)
 {
 	int idx, len;
 
-	len = po->rx_ring.prb_bdqc.knum_blocks;
-	idx = po->rx_ring.prb_bdqc.kactive_blk_num;
+	len = READ_ONCE(po->rx_ring.prb_bdqc.knum_blocks);
+	idx = READ_ONCE(po->rx_ring.prb_bdqc.kactive_blk_num);
 	if (pow_off)
 		idx += len >> pow_off;
 	if (idx >= len)
@@ -1226,15 +1226,18 @@ static bool __tpacket_v3_has_room(struct packet_sock *po, int pow_off)
 	return prb_lookup_block(po, &po->rx_ring, idx, TP_STATUS_KERNEL);
 }
 
-static int __packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb)
+static int __packet_rcv_has_room(const struct packet_sock *po,
+				 const struct sk_buff *skb)
 {
-	struct sock *sk = &po->sk;
+	const struct sock *sk = &po->sk;
 	int ret = ROOM_NONE;
 
 	if (po->prot_hook.func != tpacket_rcv) {
-		int avail = sk->sk_rcvbuf - atomic_read(&sk->sk_rmem_alloc)
-					  - (skb ? skb->truesize : 0);
-		if (avail > (sk->sk_rcvbuf >> ROOM_POW_OFF))
+		int rcvbuf = READ_ONCE(sk->sk_rcvbuf);
+		int avail = rcvbuf - atomic_read(&sk->sk_rmem_alloc)
+				   - (skb ? skb->truesize : 0);
+
+		if (avail > (rcvbuf >> ROOM_POW_OFF))
 			return ROOM_NORMAL;
 		else if (avail > 0)
 			return ROOM_LOW;
@@ -1259,19 +1262,24 @@ static int __packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb)
 
 static int packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb)
 {
-	int ret;
-	bool has_room;
+	int pressure, ret;
 
-	spin_lock_bh(&po->sk.sk_receive_queue.lock);
 	ret = __packet_rcv_has_room(po, skb);
-	has_room = ret == ROOM_NORMAL;
-	if (po->pressure == has_room)
-		po->pressure = !has_room;
-	spin_unlock_bh(&po->sk.sk_receive_queue.lock);
+	pressure = ret != ROOM_NORMAL;
+
+	if (READ_ONCE(po->pressure) != pressure)
+		WRITE_ONCE(po->pressure, pressure);
 
 	return ret;
 }
 
+static void packet_rcv_try_clear_pressure(struct packet_sock *po)
+{
+	if (READ_ONCE(po->pressure) &&
+	    __packet_rcv_has_room(po, NULL) == ROOM_NORMAL)
+		WRITE_ONCE(po->pressure,  0);
+}
+
 static void packet_sock_destruct(struct sock *sk)
 {
 	skb_queue_purge(&sk->sk_error_queue);
@@ -1289,15 +1297,21 @@ static void packet_sock_destruct(struct sock *sk)
 
 static bool fanout_flow_is_huge(struct packet_sock *po, struct sk_buff *skb)
 {
-	u32 rxhash;
+	u32 *history = po->rollover->history;
+	u32 victim, rxhash;
 	int i, count = 0;
 
 	rxhash = skb_get_hash(skb);
 	for (i = 0; i < ROLLOVER_HLEN; i++)
-		if (po->rollover->history[i] == rxhash)
+		if (READ_ONCE(history[i]) == rxhash)
 			count++;
 
-	po->rollover->history[prandom_u32() % ROLLOVER_HLEN] = rxhash;
+	victim = prandom_u32() % ROLLOVER_HLEN;
+
+	/* Avoid dirtying the cache line if possible */
+	if (READ_ONCE(history[victim]) != rxhash)
+		WRITE_ONCE(history[victim], rxhash);
+
 	return count > (ROLLOVER_HLEN >> 1);
 }
 
@@ -1352,7 +1366,7 @@ static unsigned int fanout_demux_rollover(struct packet_fanout *f,
 	i = j = min_t(int, po->rollover->sock, num - 1);
 	do {
 		po_next = pkt_sk(f->arr[i]);
-		if (po_next != po_skip && !po_next->pressure &&
+		if (po_next != po_skip && !READ_ONCE(po_next->pressure) &&
 		    packet_rcv_has_room(po_next, skb) == ROOM_NORMAL) {
 			if (i != j)
 				po->rollover->sock = i;
@@ -2127,10 +2141,8 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev,
 
 drop_n_acct:
 	is_drop_n_account = true;
-	spin_lock(&sk->sk_receive_queue.lock);
-	po->stats.stats1.tp_drops++;
+	atomic_inc(&po->tp_drops);
 	atomic_inc(&sk->sk_drops);
-	spin_unlock(&sk->sk_receive_queue.lock);
 
 drop_n_restore:
 	if (skb_head != skb->data && skb_shared(skb)) {
@@ -2156,11 +2168,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	int skb_len = skb->len;
 	unsigned int snaplen, res;
 	unsigned long status = TP_STATUS_USER;
-	unsigned short macoff, netoff, hdrlen;
+	unsigned short macoff, hdrlen;
+	unsigned int netoff;
 	struct sk_buff *copy_skb = NULL;
 	struct timespec ts;
 	__u32 ts_status;
 	bool is_drop_n_account = false;
+	unsigned int slot_id = 0;
 	bool do_vnet = false;
 
 	/* struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT.
@@ -2194,6 +2208,12 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (!res)
 		goto drop_n_restore;
 
+	/* If we are flooded, just give up */
+	if (__packet_rcv_has_room(po, skb) == ROOM_NONE) {
+		atomic_inc(&po->tp_drops);
+		goto drop_n_restore;
+	}
+
 	if (skb->ip_summed == CHECKSUM_PARTIAL)
 		status |= TP_STATUS_CSUMNOTREADY;
 	else if (skb->pkt_type != PACKET_OUTGOING &&
@@ -2218,6 +2238,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		}
 		macoff = netoff - maclen;
 	}
+	if (netoff > USHRT_MAX) {
+		atomic_inc(&po->tp_drops);
+		goto drop_n_restore;
+	}
 	if (po->tp_version <= TPACKET_V2) {
 		if (macoff + snaplen > po->rx_ring.frame_size) {
 			if (po->copy_thresh &&
@@ -2256,6 +2280,20 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 					TP_STATUS_KERNEL, (macoff+snaplen));
 	if (!h.raw)
 		goto drop_n_account;
+
+	if (po->tp_version <= TPACKET_V2) {
+		slot_id = po->rx_ring.head;
+		if (test_bit(slot_id, po->rx_ring.rx_owner_map))
+			goto drop_n_account;
+		__set_bit(slot_id, po->rx_ring.rx_owner_map);
+	}
+
+	if (do_vnet &&
+	    virtio_net_hdr_from_skb(skb, h.raw + macoff -
+				    sizeof(struct virtio_net_hdr),
+				    vio_le(), true, 0))
+		goto drop_n_account;
+
 	if (po->tp_version <= TPACKET_V2) {
 		packet_increment_rx_head(po, &po->rx_ring);
 	/*
@@ -2264,16 +2302,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	 * Anyways, moving it for V1/V2 only as V3 doesn't need this
 	 * at packet level.
 	 */
-		if (po->stats.stats1.tp_drops)
+		if (atomic_read(&po->tp_drops))
 			status |= TP_STATUS_LOSING;
 	}
 
-	if (do_vnet &&
-	    virtio_net_hdr_from_skb(skb, h.raw + macoff -
-				    sizeof(struct virtio_net_hdr),
-				    vio_le(), true, 0))
-		goto drop_n_account;
-
 	po->stats.stats1.tp_packets++;
 	if (copy_skb) {
 		status |= TP_STATUS_COPY;
@@ -2361,7 +2393,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 #endif
 
 	if (po->tp_version <= TPACKET_V2) {
+		spin_lock(&sk->sk_receive_queue.lock);
 		__packet_set_status(po, h.raw, status);
+		__clear_bit(slot_id, po->rx_ring.rx_owner_map);
+		spin_unlock(&sk->sk_receive_queue.lock);
 		sk->sk_data_ready(sk);
 	} else {
 		prb_clear_blk_fill_status(&po->rx_ring);
@@ -2380,9 +2415,9 @@ drop:
 	return 0;
 
 drop_n_account:
-	is_drop_n_account = true;
-	po->stats.stats1.tp_drops++;
 	spin_unlock(&sk->sk_receive_queue.lock);
+	atomic_inc(&po->tp_drops);
+	is_drop_n_account = true;
 
 	sk->sk_data_ready(sk);
 	kfree_skb(copy_skb);
@@ -3326,8 +3361,7 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	if (skb == NULL)
 		goto out;
 
-	if (pkt_sk(sk)->pressure)
-		packet_rcv_has_room(pkt_sk(sk), NULL);
+	packet_rcv_try_clear_pressure(pkt_sk(sk));
 
 	if (pkt_sk(sk)->has_vnet_hdr) {
 		err = packet_rcv_vnet(msg, skb, &len);
@@ -3899,6 +3933,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 	void *data = &val;
 	union tpacket_stats_u st;
 	struct tpacket_rollover_stats rstats;
+	int drops;
 
 	if (level != SOL_PACKET)
 		return -ENOPROTOOPT;
@@ -3915,14 +3950,17 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 		memcpy(&st, &po->stats, sizeof(st));
 		memset(&po->stats, 0, sizeof(po->stats));
 		spin_unlock_bh(&sk->sk_receive_queue.lock);
+		drops = atomic_xchg(&po->tp_drops, 0);
 
 		if (po->tp_version == TPACKET_V3) {
 			lv = sizeof(struct tpacket_stats_v3);
-			st.stats3.tp_packets += st.stats3.tp_drops;
+			st.stats3.tp_drops = drops;
+			st.stats3.tp_packets += drops;
 			data = &st.stats3;
 		} else {
 			lv = sizeof(struct tpacket_stats);
-			st.stats1.tp_packets += st.stats1.tp_drops;
+			st.stats1.tp_drops = drops;
+			st.stats1.tp_packets += drops;
 			data = &st.stats1;
 		}
 
@@ -4141,8 +4179,7 @@ static __poll_t packet_poll(struct file *file, struct socket *sock,
 			TP_STATUS_KERNEL))
 			mask |= EPOLLIN | EPOLLRDNORM;
 	}
-	if (po->pressure && __packet_rcv_has_room(po, NULL) == ROOM_NORMAL)
-		po->pressure = 0;
+	packet_rcv_try_clear_pressure(po);
 	spin_unlock_bh(&sk->sk_receive_queue.lock);
 	spin_lock_bh(&sk->sk_write_queue.lock);
 	if (po->tx_ring.pg_vec) {
@@ -4256,6 +4293,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 {
 	struct pgv *pg_vec = NULL;
 	struct packet_sock *po = pkt_sk(sk);
+	unsigned long *rx_owner_map = NULL;
 	int was_running, order = 0;
 	struct packet_ring_buffer *rb;
 	struct sk_buff_head *rb_queue;
@@ -4341,6 +4379,12 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 			}
 			break;
 		default:
+			if (!tx_ring) {
+				rx_owner_map = bitmap_alloc(req->tp_frame_nr,
+					GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO);
+				if (!rx_owner_map)
+					goto out_free_pg_vec;
+			}
 			break;
 		}
 	}
@@ -4370,6 +4414,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		err = 0;
 		spin_lock_bh(&rb_queue->lock);
 		swap(rb->pg_vec, pg_vec);
+		if (po->tp_version <= TPACKET_V2)
+			swap(rb->rx_owner_map, rx_owner_map);
 		rb->frame_max = (req->tp_frame_nr - 1);
 		rb->head = 0;
 		rb->frame_size = req->tp_frame_size;
@@ -4401,6 +4447,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 	}
 
 out_free_pg_vec:
+	bitmap_free(rx_owner_map);
 	if (pg_vec)
 		free_pg_vec(pg_vec, order, req->tp_block_nr);
 out:
diff --git a/net/packet/internal.h b/net/packet/internal.h
index c70a2794456f..907f4cd2a718 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -70,7 +70,10 @@ struct packet_ring_buffer {
 
 	unsigned int __percpu	*pending_refcnt;
 
-	struct tpacket_kbdq_core	prb_bdqc;
+	union {
+		unsigned long			*rx_owner_map;
+		struct tpacket_kbdq_core	prb_bdqc;
+	};
 };
 
 extern struct mutex fanout_mutex;
@@ -132,6 +135,7 @@ struct packet_sock {
 	struct net_device __rcu	*cached_dev;
 	int			(*xmit)(struct sk_buff *skb);
 	struct packet_type	prot_hook ____cacheline_aligned_in_smp;
+	atomic_t		tp_drops ____cacheline_aligned_in_smp;
 };
 
 static struct packet_sock *pkt_sk(struct sock *sk)
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 88f98f27ad88..1ce1e710d025 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -196,7 +196,7 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb,
 	hdr->size = cpu_to_le32(len);
 	hdr->confirm_rx = 0;
 
-	skb_put_padto(skb, ALIGN(len, 4));
+	skb_put_padto(skb, ALIGN(len, 4) + sizeof(*hdr));
 
 	mutex_lock(&node->ep_lock);
 	if (node->ep)
@@ -259,7 +259,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len)
 	unsigned int ver;
 	size_t hdrlen;
 
-	if (len & 3)
+	if (len == 0 || len & 3)
 		return -EINVAL;
 
 	skb = netdev_alloc_skb(NULL, len);
@@ -273,6 +273,8 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len)
 
 	switch (ver) {
 	case QRTR_PROTO_VER_1:
+		if (len < sizeof(*v1))
+			goto err;
 		v1 = data;
 		hdrlen = sizeof(*v1);
 
@@ -286,6 +288,8 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len)
 		size = le32_to_cpu(v1->size);
 		break;
 	case QRTR_PROTO_VER_2:
+		if (len < sizeof(*v2))
+			goto err;
 		v2 = data;
 		hdrlen = sizeof(*v2) + v2->optlen;
 
@@ -711,7 +715,7 @@ static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb,
 	}
 	mutex_unlock(&qrtr_node_lock);
 
-	qrtr_local_enqueue(node, skb, type, from, to);
+	qrtr_local_enqueue(NULL, skb, type, from, to);
 
 	return 0;
 }
@@ -763,20 +767,21 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 
 	node = NULL;
 	if (addr->sq_node == QRTR_NODE_BCAST) {
-		enqueue_fn = qrtr_bcast_enqueue;
-		if (addr->sq_port != QRTR_PORT_CTRL) {
+		if (addr->sq_port != QRTR_PORT_CTRL &&
+		    qrtr_local_nid != QRTR_NODE_BCAST) {
 			release_sock(sk);
 			return -ENOTCONN;
 		}
+		enqueue_fn = qrtr_bcast_enqueue;
 	} else if (addr->sq_node == ipc->us.sq_node) {
 		enqueue_fn = qrtr_local_enqueue;
 	} else {
-		enqueue_fn = qrtr_node_enqueue;
 		node = qrtr_node_lookup(addr->sq_node);
 		if (!node) {
 			release_sock(sk);
 			return -ECONNRESET;
 		}
+		enqueue_fn = qrtr_node_enqueue;
 	}
 
 	plen = (len + 3) & ~3;
@@ -999,6 +1004,7 @@ static int qrtr_release(struct socket *sock)
 		sk->sk_state_change(sk);
 
 	sock_set_flag(sk, SOCK_DEAD);
+	sock_orphan(sk);
 	sock->sk = NULL;
 
 	if (!sock_flag(sk, SOCK_ZAPPED))
diff --git a/net/rds/message.c b/net/rds/message.c
index 50f13f1d4ae0..2d43e13d6dd5 100644
--- a/net/rds/message.c
+++ b/net/rds/message.c
@@ -308,26 +308,20 @@ out:
 /*
  * RDS ops use this to grab SG entries from the rm's sg pool.
  */
-struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents,
-					  int *ret)
+struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents)
 {
 	struct scatterlist *sg_first = (struct scatterlist *) &rm[1];
 	struct scatterlist *sg_ret;
 
-	if (WARN_ON(!ret))
-		return NULL;
-
 	if (nents <= 0) {
 		pr_warn("rds: alloc sgs failed! nents <= 0\n");
-		*ret = -EINVAL;
-		return NULL;
+		return ERR_PTR(-EINVAL);
 	}
 
 	if (rm->m_used_sgs + nents > rm->m_total_sgs) {
 		pr_warn("rds: alloc sgs failed! total %d used %d nents %d\n",
 			rm->m_total_sgs, rm->m_used_sgs, nents);
-		*ret = -ENOMEM;
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 
 	sg_ret = &sg_first[rm->m_used_sgs];
@@ -343,7 +337,6 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in
 	unsigned int i;
 	int num_sgs = DIV_ROUND_UP(total_len, PAGE_SIZE);
 	int extra_bytes = num_sgs * sizeof(struct scatterlist);
-	int ret;
 
 	rm = rds_message_alloc(extra_bytes, GFP_NOWAIT);
 	if (!rm)
@@ -352,10 +345,10 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in
 	set_bit(RDS_MSG_PAGEVEC, &rm->m_flags);
 	rm->m_inc.i_hdr.h_len = cpu_to_be32(total_len);
 	rm->data.op_nents = DIV_ROUND_UP(total_len, PAGE_SIZE);
-	rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs, &ret);
-	if (!rm->data.op_sg) {
+	rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs);
+	if (IS_ERR(rm->data.op_sg)) {
 		rds_message_put(rm);
-		return ERR_PTR(ret);
+		return ERR_CAST(rm->data.op_sg);
 	}
 
 	for (i = 0; i < rm->data.op_nents; ++i) {
diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index b340ed4fc43a..ca64d1c3231c 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -624,9 +624,11 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm,
 	op->op_active = 1;
 	op->op_recverr = rs->rs_recverr;
 	WARN_ON(!nr_pages);
-	op->op_sg = rds_message_alloc_sgs(rm, nr_pages, &ret);
-	if (!op->op_sg)
+	op->op_sg = rds_message_alloc_sgs(rm, nr_pages);
+	if (IS_ERR(op->op_sg)) {
+		ret = PTR_ERR(op->op_sg);
 		goto out_pages;
+	}
 
 	if (op->op_notify || op->op_recverr) {
 		/* We allocate an uninitialized notifier here, because
@@ -838,9 +840,11 @@ int rds_cmsg_atomic(struct rds_sock *rs, struct rds_message *rm,
 	rm->atomic.op_silent = !!(args->flags & RDS_RDMA_SILENT);
 	rm->atomic.op_active = 1;
 	rm->atomic.op_recverr = rs->rs_recverr;
-	rm->atomic.op_sg = rds_message_alloc_sgs(rm, 1, &ret);
-	if (!rm->atomic.op_sg)
+	rm->atomic.op_sg = rds_message_alloc_sgs(rm, 1);
+	if (IS_ERR(rm->atomic.op_sg)) {
+		ret = PTR_ERR(rm->atomic.op_sg);
 		goto err;
+	}
 
 	/* verify 8 byte-aligned */
 	if (args->local_addr & 0x7) {
diff --git a/net/rds/rds.h b/net/rds/rds.h
index 0d8f67cadd74..952fc5e68d75 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -845,8 +845,7 @@ rds_conn_connecting(struct rds_connection *conn)
 
 /* message.c */
 struct rds_message *rds_message_alloc(unsigned int nents, gfp_t gfp);
-struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents,
-					  int *ret);
+struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents);
 int rds_message_copy_from_user(struct rds_message *rm, struct iov_iter *from,
 			       bool zcopy);
 struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned int total_len);
diff --git a/net/rds/recv.c b/net/rds/recv.c
index a42ba7fa06d5..dd15f93d2ef1 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -450,12 +450,13 @@ static int rds_still_queued(struct rds_sock *rs, struct rds_incoming *inc,
 int rds_notify_queue_get(struct rds_sock *rs, struct msghdr *msghdr)
 {
 	struct rds_notifier *notifier;
-	struct rds_rdma_notify cmsg = { 0 }; /* fill holes with zero */
+	struct rds_rdma_notify cmsg;
 	unsigned int count = 0, max_messages = ~0U;
 	unsigned long flags;
 	LIST_HEAD(copy);
 	int err = 0;
 
+	memset(&cmsg, 0, sizeof(cmsg));	/* fill holes with zero */
 
 	/* put_cmsg copies to user space and thus may sleep. We can't do this
 	 * with rs_lock held, so first grab as many notifications as we can stuff
diff --git a/net/rds/send.c b/net/rds/send.c
index 166dd578c1cc..c46b5fb0da89 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1264,9 +1264,11 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 
 	/* Attach data to the rm */
 	if (payload_len) {
-		rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs, &ret);
-		if (!rm->data.op_sg)
+		rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs);
+		if (IS_ERR(rm->data.op_sg)) {
+			ret = PTR_ERR(rm->data.op_sg);
 			goto out;
+		}
 		ret = rds_message_copy_from_user(rm, &msg->msg_iter, zcopy);
 		if (ret)
 			goto out;
diff --git a/net/rfkill/core.c b/net/rfkill/core.c
index f9b08a6d8dbe..d1a955c79219 100644
--- a/net/rfkill/core.c
+++ b/net/rfkill/core.c
@@ -1002,10 +1002,13 @@ static void rfkill_sync_work(struct work_struct *work)
 int __must_check rfkill_register(struct rfkill *rfkill)
 {
 	static unsigned long rfkill_no;
-	struct device *dev = &rfkill->dev;
+	struct device *dev;
 	int error;
 
-	BUG_ON(!rfkill);
+	if (!rfkill)
+		return -EINVAL;
+
+	dev = &rfkill->dev;
 
 	mutex_lock(&rfkill_global_mutex);
 
diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile
index 6ffb7e9887ce..ddd0f95713a9 100644
--- a/net/rxrpc/Makefile
+++ b/net/rxrpc/Makefile
@@ -25,6 +25,7 @@ rxrpc-y := \
 	peer_event.o \
 	peer_object.o \
 	recvmsg.o \
+	rtt.o \
 	security.o \
 	sendmsg.o \
 	skbuff.o \
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 8c9bd3ae9edf..102c5715106f 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -194,6 +194,7 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len)
 service_in_use:
 	write_unlock(&local->services_lock);
 	rxrpc_unuse_local(local);
+	rxrpc_put_local(local);
 	ret = -EADDRINUSE;
 error_unlock:
 	release_sock(&rx->sk);
@@ -284,7 +285,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
 					   gfp_t gfp,
 					   rxrpc_notify_rx_t notify_rx,
 					   bool upgrade,
-					   bool intr,
+					   enum rxrpc_interruptibility interruptibility,
 					   unsigned int debug_id)
 {
 	struct rxrpc_conn_parameters cp;
@@ -309,7 +310,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
 	memset(&p, 0, sizeof(p));
 	p.user_call_ID = user_call_ID;
 	p.tx_total_len = tx_total_len;
-	p.intr = intr;
+	p.interruptibility = interruptibility;
 
 	memset(&cp, 0, sizeof(cp));
 	cp.local		= rx->local;
@@ -370,45 +371,18 @@ EXPORT_SYMBOL(rxrpc_kernel_end_call);
  * rxrpc_kernel_check_life - Check to see whether a call is still alive
  * @sock: The socket the call is on
  * @call: The call to check
- * @_life: Where to store the life value
  *
- * Allow a kernel service to find out whether a call is still alive - ie. we're
- * getting ACKs from the server.  Passes back in *_life a number representing
- * the life state which can be compared to that returned by a previous call and
- * return true if the call is still alive.
- *
- * If the life state stalls, rxrpc_kernel_probe_life() should be called and
- * then 2RTT waited.
+ * Allow a kernel service to find out whether a call is still alive -
+ * ie. whether it has completed.
  */
 bool rxrpc_kernel_check_life(const struct socket *sock,
-			     const struct rxrpc_call *call,
-			     u32 *_life)
+			     const struct rxrpc_call *call)
 {
-	*_life = call->acks_latest;
 	return call->state != RXRPC_CALL_COMPLETE;
 }
 EXPORT_SYMBOL(rxrpc_kernel_check_life);
 
 /**
- * rxrpc_kernel_probe_life - Poke the peer to see if it's still alive
- * @sock: The socket the call is on
- * @call: The call to check
- *
- * In conjunction with rxrpc_kernel_check_life(), allow a kernel service to
- * find out whether a call is still alive by pinging it.  This should cause the
- * life state to be bumped in about 2*RTT.
- *
- * The must be called in TASK_RUNNING state on pain of might_sleep() objecting.
- */
-void rxrpc_kernel_probe_life(struct socket *sock, struct rxrpc_call *call)
-{
-	rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false,
-			  rxrpc_propose_ack_ping_for_check_life);
-	rxrpc_send_ack_packet(call, true, NULL);
-}
-EXPORT_SYMBOL(rxrpc_kernel_probe_life);
-
-/**
  * rxrpc_kernel_get_epoch - Retrieve the epoch value from a call.
  * @sock: The socket the call is on
  * @call: The call to query
@@ -902,6 +876,7 @@ static int rxrpc_release_sock(struct sock *sk)
 	rxrpc_queue_work(&rxnet->client_conn_reaper);
 
 	rxrpc_unuse_local(rx->local);
+	rxrpc_put_local(rx->local);
 	rx->local = NULL;
 	key_put(rx->key);
 	rx->key = NULL;
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 9796c45d2f6a..872f54c41a1d 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -7,6 +7,7 @@
 
 #include <linux/atomic.h>
 #include <linux/seqlock.h>
+#include <linux/win_minmax.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 #include <net/sock.h>
@@ -203,6 +204,7 @@ struct rxrpc_skb_priv {
 struct rxrpc_security {
 	const char		*name;		/* name of this service */
 	u8			security_index;	/* security type provided */
+	u32			no_key_abort;	/* Abort code indicating no key */
 
 	/* Initialise a security service */
 	int (*init)(void);
@@ -301,11 +303,14 @@ struct rxrpc_peer {
 #define RXRPC_RTT_CACHE_SIZE 32
 	spinlock_t		rtt_input_lock;	/* RTT lock for input routine */
 	ktime_t			rtt_last_req;	/* Time of last RTT request */
-	u64			rtt;		/* Current RTT estimate (in nS) */
-	u64			rtt_sum;	/* Sum of cache contents */
-	u64			rtt_cache[RXRPC_RTT_CACHE_SIZE]; /* Determined RTT cache */
-	u8			rtt_cursor;	/* next entry at which to insert */
-	u8			rtt_usage;	/* amount of cache actually used */
+	unsigned int		rtt_count;	/* Number of samples we've got */
+
+	u32			srtt_us;	/* smoothed round trip time << 3 in usecs */
+	u32			mdev_us;	/* medium deviation			*/
+	u32			mdev_max_us;	/* maximal mdev for the last rtt period	*/
+	u32			rttvar_us;	/* smoothed mdev_max			*/
+	u32			rto_j;		/* Retransmission timeout in jiffies */
+	u8			backoff;	/* Backoff timeout */
 
 	u8			cong_cwnd;	/* Congestion window size */
 };
@@ -479,7 +484,7 @@ enum rxrpc_call_flag {
 	RXRPC_CALL_BEGAN_RX_TIMER,	/* We began the expect_rx_by timer */
 	RXRPC_CALL_RX_HEARD,		/* The peer responded at least once to this call */
 	RXRPC_CALL_RX_UNDERRUN,		/* Got data underrun */
-	RXRPC_CALL_IS_INTR,		/* The call is interruptible */
+	RXRPC_CALL_DISCONNECTED,	/* The call has been disconnected */
 };
 
 /*
@@ -585,6 +590,7 @@ struct rxrpc_call {
 	atomic_t		usage;
 	u16			service_id;	/* service ID */
 	u8			security_ix;	/* Security type */
+	enum rxrpc_interruptibility interruptibility; /* At what point call may be interrupted */
 	u32			call_id;	/* call ID on connection  */
 	u32			cid;		/* connection ID plus channel index */
 	int			debug_id;	/* debug ID for printks */
@@ -650,7 +656,6 @@ struct rxrpc_call {
 
 	/* receive-phase ACK management */
 	u8			ackr_reason;	/* reason to ACK */
-	u16			ackr_skew;	/* skew on packet being ACK'd */
 	rxrpc_serial_t		ackr_serial;	/* serial of packet being ACK'd */
 	rxrpc_serial_t		ackr_first_seq;	/* first sequence number received */
 	rxrpc_seq_t		ackr_prev_seq;	/* previous sequence number received */
@@ -663,7 +668,6 @@ struct rxrpc_call {
 
 	/* transmission-phase ACK management */
 	ktime_t			acks_latest_ts;	/* Timestamp of latest ACK received */
-	rxrpc_serial_t		acks_latest;	/* serial number of latest ACK received */
 	rxrpc_seq_t		acks_lowest_nak; /* Lowest NACK in the buffer (or ==tx_hard_ack) */
 	rxrpc_seq_t		acks_lost_top;	/* tx_top at the time lost-ack ping sent */
 	rxrpc_serial_t		acks_lost_ping;	/* Serial number of probe ACK */
@@ -709,7 +713,7 @@ struct rxrpc_call_params {
 		u32		normal;		/* Max time since last call packet (msec) */
 	} timeouts;
 	u8			nr_timeouts;	/* Number of timeouts specified */
-	bool			intr;		/* The call is interruptible */
+	enum rxrpc_interruptibility interruptibility; /* How is interruptible is the call? */
 };
 
 struct rxrpc_send_params {
@@ -744,7 +748,7 @@ int rxrpc_reject_call(struct rxrpc_sock *);
 /*
  * call_event.c
  */
-void rxrpc_propose_ACK(struct rxrpc_call *, u8, u16, u32, bool, bool,
+void rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, bool, bool,
 		       enum rxrpc_propose_ack_trace);
 void rxrpc_process_call(struct work_struct *);
 
@@ -966,8 +970,9 @@ static inline void rxrpc_reduce_conn_timer(struct rxrpc_connection *conn,
 struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *,
 						     struct sk_buff *);
 struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *, gfp_t);
-void rxrpc_new_incoming_connection(struct rxrpc_sock *,
-				   struct rxrpc_connection *, struct sk_buff *);
+void rxrpc_new_incoming_connection(struct rxrpc_sock *, struct rxrpc_connection *,
+				   const struct rxrpc_security *, struct key *,
+				   struct sk_buff *);
 void rxrpc_unpublish_service_conn(struct rxrpc_connection *);
 
 /*
@@ -1008,6 +1013,16 @@ void rxrpc_unuse_local(struct rxrpc_local *);
 void rxrpc_queue_local(struct rxrpc_local *);
 void rxrpc_destroy_all_locals(struct rxrpc_net *);
 
+static inline bool __rxrpc_unuse_local(struct rxrpc_local *local)
+{
+	return atomic_dec_return(&local->active_users) == 0;
+}
+
+static inline bool __rxrpc_use_local(struct rxrpc_local *local)
+{
+	return atomic_fetch_add_unless(&local->active_users, 1, 0) != 0;
+}
+
 /*
  * misc.c
  */
@@ -1018,7 +1033,6 @@ extern unsigned long rxrpc_idle_ack_delay;
 extern unsigned int rxrpc_rx_window_size;
 extern unsigned int rxrpc_rx_mtu;
 extern unsigned int rxrpc_rx_jumbo_max;
-extern unsigned long rxrpc_resend_timeout;
 
 extern const s8 rxrpc_ack_priority[];
 
@@ -1046,8 +1060,6 @@ void rxrpc_send_keepalive(struct rxrpc_peer *);
  * peer_event.c
  */
 void rxrpc_error_report(struct sock *);
-void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace,
-			rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t);
 void rxrpc_peer_keepalive_worker(struct work_struct *);
 
 /*
@@ -1080,6 +1092,14 @@ void rxrpc_notify_socket(struct rxrpc_call *);
 int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int);
 
 /*
+ * rtt.c
+ */
+void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace,
+			rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t);
+unsigned long rxrpc_get_rto_backoff(struct rxrpc_peer *, bool);
+void rxrpc_peer_init_rtt(struct rxrpc_peer *);
+
+/*
  * rxkad.c
  */
 #ifdef CONFIG_RXKAD
@@ -1092,7 +1112,9 @@ extern const struct rxrpc_security rxkad;
 int __init rxrpc_init_security(void);
 void rxrpc_exit_security(void);
 int rxrpc_init_client_conn_security(struct rxrpc_connection *);
-int rxrpc_init_server_conn_security(struct rxrpc_connection *);
+bool rxrpc_look_up_server_security(struct rxrpc_local *, struct rxrpc_sock *,
+				   const struct rxrpc_security **, struct key **,
+				   struct sk_buff *);
 
 /*
  * sendmsg.c
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index 00c095d74145..7d8574f6b2da 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -97,7 +97,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx,
 	call->flags |= (1 << RXRPC_CALL_IS_SERVICE);
 	call->state = RXRPC_CALL_SERVER_PREALLOC;
 
-	trace_rxrpc_call(call, rxrpc_call_new_service,
+	trace_rxrpc_call(call->debug_id, rxrpc_call_new_service,
 			 atomic_read(&call->usage),
 			 here, (const void *)user_call_ID);
 
@@ -240,6 +240,22 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx)
 }
 
 /*
+ * Ping the other end to fill our RTT cache and to retrieve the rwind
+ * and MTU parameters.
+ */
+static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb)
+{
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	ktime_t now = skb->tstamp;
+
+	if (call->peer->rtt_count < 3 ||
+	    ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), now))
+		rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial,
+				  true, true,
+				  rxrpc_propose_ack_ping_for_params);
+}
+
+/*
  * Allocate a new incoming call from the prealloc pool, along with a connection
  * and a peer as necessary.
  */
@@ -247,6 +263,8 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
 						    struct rxrpc_local *local,
 						    struct rxrpc_peer *peer,
 						    struct rxrpc_connection *conn,
+						    const struct rxrpc_security *sec,
+						    struct key *key,
 						    struct sk_buff *skb)
 {
 	struct rxrpc_backlog *b = rx->backlog;
@@ -294,7 +312,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
 		conn->params.local = rxrpc_get_local(local);
 		conn->params.peer = peer;
 		rxrpc_see_connection(conn);
-		rxrpc_new_incoming_connection(rx, conn, skb);
+		rxrpc_new_incoming_connection(rx, conn, sec, key, skb);
 	} else {
 		rxrpc_get_connection(conn);
 	}
@@ -332,9 +350,11 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local,
 					   struct sk_buff *skb)
 {
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	const struct rxrpc_security *sec = NULL;
 	struct rxrpc_connection *conn;
 	struct rxrpc_peer *peer = NULL;
-	struct rxrpc_call *call;
+	struct rxrpc_call *call = NULL;
+	struct key *key = NULL;
 
 	_enter("");
 
@@ -345,9 +365,7 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local,
 				  sp->hdr.seq, RX_INVALID_OPERATION, ESHUTDOWN);
 		skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
 		skb->priority = RX_INVALID_OPERATION;
-		_leave(" = NULL [close]");
-		call = NULL;
-		goto out;
+		goto no_call;
 	}
 
 	/* The peer, connection and call may all have sprung into existence due
@@ -357,29 +375,19 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local,
 	 */
 	conn = rxrpc_find_connection_rcu(local, skb, &peer);
 
-	call = rxrpc_alloc_incoming_call(rx, local, peer, conn, skb);
+	if (!conn && !rxrpc_look_up_server_security(local, rx, &sec, &key, skb))
+		goto no_call;
+
+	call = rxrpc_alloc_incoming_call(rx, local, peer, conn, sec, key, skb);
+	key_put(key);
 	if (!call) {
 		skb->mark = RXRPC_SKB_MARK_REJECT_BUSY;
-		_leave(" = NULL [busy]");
-		call = NULL;
-		goto out;
+		goto no_call;
 	}
 
 	trace_rxrpc_receive(call, rxrpc_receive_incoming,
 			    sp->hdr.serial, sp->hdr.seq);
 
-	/* Lock the call to prevent rxrpc_kernel_send/recv_data() and
-	 * sendmsg()/recvmsg() inconveniently stealing the mutex once the
-	 * notification is generated.
-	 *
-	 * The BUG should never happen because the kernel should be well
-	 * behaved enough not to access the call before the first notification
-	 * event and userspace is prevented from doing so until the state is
-	 * appropriate.
-	 */
-	if (!mutex_trylock(&call->user_mutex))
-		BUG();
-
 	/* Make the call live. */
 	rxrpc_incoming_call(rx, call, skb);
 	conn = call->conn;
@@ -420,6 +428,9 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local,
 		BUG();
 	}
 	spin_unlock(&conn->state_lock);
+	spin_unlock(&rx->incoming_lock);
+
+	rxrpc_send_ping(call, skb);
 
 	if (call->state == RXRPC_CALL_SERVER_ACCEPTING)
 		rxrpc_notify_socket(call);
@@ -432,9 +443,12 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local,
 	rxrpc_put_call(call, rxrpc_call_put);
 
 	_leave(" = %p{%d}", call, call->debug_id);
-out:
-	spin_unlock(&rx->incoming_lock);
 	return call;
+
+no_call:
+	spin_unlock(&rx->incoming_lock);
+	_leave(" = NULL [%u]", skb->mark);
+	return NULL;
 }
 
 /*
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index bc2adeb3acb9..97ddf2f72a56 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -43,8 +43,7 @@ static void rxrpc_propose_ping(struct rxrpc_call *call,
  * propose an ACK be sent
  */
 static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
-				u16 skew, u32 serial, bool immediate,
-				bool background,
+				u32 serial, bool immediate, bool background,
 				enum rxrpc_propose_ack_trace why)
 {
 	enum rxrpc_propose_ack_outcome outcome = rxrpc_propose_ack_use;
@@ -69,14 +68,12 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
 		if (RXRPC_ACK_UPDATEABLE & (1 << ack_reason)) {
 			outcome = rxrpc_propose_ack_update;
 			call->ackr_serial = serial;
-			call->ackr_skew = skew;
 		}
 		if (!immediate)
 			goto trace;
 	} else if (prior > rxrpc_ack_priority[call->ackr_reason]) {
 		call->ackr_reason = ack_reason;
 		call->ackr_serial = serial;
-		call->ackr_skew = skew;
 	} else {
 		outcome = rxrpc_propose_ack_subsume;
 	}
@@ -114,8 +111,8 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
 	} else {
 		unsigned long now = jiffies, ack_at;
 
-		if (call->peer->rtt_usage > 0)
-			ack_at = nsecs_to_jiffies(call->peer->rtt);
+		if (call->peer->srtt_us != 0)
+			ack_at = usecs_to_jiffies(call->peer->srtt_us >> 3);
 		else
 			ack_at = expiry;
 
@@ -137,11 +134,11 @@ trace:
  * propose an ACK be sent, locking the call structure
  */
 void rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
-		       u16 skew, u32 serial, bool immediate, bool background,
+		       u32 serial, bool immediate, bool background,
 		       enum rxrpc_propose_ack_trace why)
 {
 	spin_lock_bh(&call->lock);
-	__rxrpc_propose_ACK(call, ack_reason, skew, serial,
+	__rxrpc_propose_ACK(call, ack_reason, serial,
 			    immediate, background, why);
 	spin_unlock_bh(&call->lock);
 }
@@ -160,24 +157,18 @@ static void rxrpc_congestion_timeout(struct rxrpc_call *call)
 static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
 {
 	struct sk_buff *skb;
-	unsigned long resend_at;
+	unsigned long resend_at, rto_j;
 	rxrpc_seq_t cursor, seq, top;
-	ktime_t now, max_age, oldest, ack_ts, timeout, min_timeo;
+	ktime_t now, max_age, oldest, ack_ts;
 	int ix;
 	u8 annotation, anno_type, retrans = 0, unacked = 0;
 
 	_enter("{%d,%d}", call->tx_hard_ack, call->tx_top);
 
-	if (call->peer->rtt_usage > 1)
-		timeout = ns_to_ktime(call->peer->rtt * 3 / 2);
-	else
-		timeout = ms_to_ktime(rxrpc_resend_timeout);
-	min_timeo = ns_to_ktime((1000000000 / HZ) * 4);
-	if (ktime_before(timeout, min_timeo))
-		timeout = min_timeo;
+	rto_j = call->peer->rto_j;
 
 	now = ktime_get_real();
-	max_age = ktime_sub(now, timeout);
+	max_age = ktime_sub(now, jiffies_to_usecs(rto_j));
 
 	spin_lock_bh(&call->lock);
 
@@ -222,7 +213,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
 	}
 
 	resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest)));
-	resend_at += jiffies + rxrpc_resend_timeout;
+	resend_at += jiffies + rto_j;
 	WRITE_ONCE(call->resend_at, resend_at);
 
 	if (unacked)
@@ -237,9 +228,9 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
 					rxrpc_timer_set_for_resend);
 		spin_unlock_bh(&call->lock);
 		ack_ts = ktime_sub(now, call->acks_latest_ts);
-		if (ktime_to_ns(ack_ts) < call->peer->rtt)
+		if (ktime_to_us(ack_ts) < (call->peer->srtt_us >> 3))
 			goto out;
-		rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false,
+		rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false,
 				  rxrpc_propose_ack_ping_for_lost_ack);
 		rxrpc_send_ack_packet(call, true, NULL);
 		goto out;
@@ -257,7 +248,18 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
 		if (anno_type != RXRPC_TX_ANNO_RETRANS)
 			continue;
 
+		/* We need to reset the retransmission state, but we need to do
+		 * so before we drop the lock as a new ACK/NAK may come in and
+		 * confuse things
+		 */
+		annotation &= ~RXRPC_TX_ANNO_MASK;
+		annotation |= RXRPC_TX_ANNO_UNACK | RXRPC_TX_ANNO_RESENT;
+		call->rxtx_annotations[ix] = annotation;
+
 		skb = call->rxtx_buffer[ix];
+		if (!skb)
+			continue;
+
 		rxrpc_get_skb(skb, rxrpc_skb_tx_got);
 		spin_unlock_bh(&call->lock);
 
@@ -271,24 +273,6 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
 
 		rxrpc_free_skb(skb, rxrpc_skb_tx_freed);
 		spin_lock_bh(&call->lock);
-
-		/* We need to clear the retransmit state, but there are two
-		 * things we need to be aware of: A new ACK/NAK might have been
-		 * received and the packet might have been hard-ACK'd (in which
-		 * case it will no longer be in the buffer).
-		 */
-		if (after(seq, call->tx_hard_ack)) {
-			annotation = call->rxtx_annotations[ix];
-			anno_type = annotation & RXRPC_TX_ANNO_MASK;
-			if (anno_type == RXRPC_TX_ANNO_RETRANS ||
-			    anno_type == RXRPC_TX_ANNO_NAK) {
-				annotation &= ~RXRPC_TX_ANNO_MASK;
-				annotation |= RXRPC_TX_ANNO_UNACK;
-			}
-			annotation |= RXRPC_TX_ANNO_RESENT;
-			call->rxtx_annotations[ix] = annotation;
-		}
-
 		if (after(call->tx_hard_ack, seq))
 			seq = call->tx_hard_ack;
 	}
@@ -372,7 +356,7 @@ recheck_state:
 	if (time_after_eq(now, t)) {
 		trace_rxrpc_timer(call, rxrpc_timer_exp_keepalive, now);
 		cmpxchg(&call->keepalive_at, t, now + MAX_JIFFY_OFFSET);
-		rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, true,
+		rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, true,
 				  rxrpc_propose_ack_ping_for_keepalive);
 		set_bit(RXRPC_CALL_EV_PING, &call->events);
 	}
@@ -407,7 +391,7 @@ recheck_state:
 	send_ack = NULL;
 	if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) {
 		call->acks_lost_top = call->tx_top;
-		rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false,
+		rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false,
 				  rxrpc_propose_ack_ping_for_lost_ack);
 		send_ack = &call->acks_lost_ping;
 	}
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 217b12be9e08..d7f5db7b74fb 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -237,10 +237,10 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 		return call;
 	}
 
-	if (p->intr)
-		__set_bit(RXRPC_CALL_IS_INTR, &call->flags);
+	call->interruptibility = p->interruptibility;
 	call->tx_total_len = p->tx_total_len;
-	trace_rxrpc_call(call, rxrpc_call_new_client, atomic_read(&call->usage),
+	trace_rxrpc_call(call->debug_id, rxrpc_call_new_client,
+			 atomic_read(&call->usage),
 			 here, (const void *)p->user_call_ID);
 
 	/* We need to protect a partially set up call against the user as we
@@ -288,10 +288,10 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 	 */
 	ret = rxrpc_connect_call(rx, call, cp, srx, gfp);
 	if (ret < 0)
-		goto error;
+		goto error_attached_to_socket;
 
-	trace_rxrpc_call(call, rxrpc_call_connected, atomic_read(&call->usage),
-			 here, NULL);
+	trace_rxrpc_call(call->debug_id, rxrpc_call_connected,
+			 atomic_read(&call->usage), here, NULL);
 
 	rxrpc_start_call_timer(call);
 
@@ -308,18 +308,29 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 error_dup_user_ID:
 	write_unlock(&rx->call_lock);
 	release_sock(&rx->sk);
-	ret = -EEXIST;
-
-error:
 	__rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
-				    RX_CALL_DEAD, ret);
-	trace_rxrpc_call(call, rxrpc_call_error, atomic_read(&call->usage),
-			 here, ERR_PTR(ret));
+				    RX_CALL_DEAD, -EEXIST);
+	trace_rxrpc_call(call->debug_id, rxrpc_call_error,
+			 atomic_read(&call->usage), here, ERR_PTR(-EEXIST));
 	rxrpc_release_call(rx, call);
 	mutex_unlock(&call->user_mutex);
 	rxrpc_put_call(call, rxrpc_call_put);
-	_leave(" = %d", ret);
-	return ERR_PTR(ret);
+	_leave(" = -EEXIST");
+	return ERR_PTR(-EEXIST);
+
+	/* We got an error, but the call is attached to the socket and is in
+	 * need of release.  However, we might now race with recvmsg() when
+	 * completing the call queues it.  Return 0 from sys_sendmsg() and
+	 * leave the error to recvmsg() to deal with.
+	 */
+error_attached_to_socket:
+	trace_rxrpc_call(call->debug_id, rxrpc_call_error,
+			 atomic_read(&call->usage), here, ERR_PTR(ret));
+	set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
+	__rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
+				    RX_CALL_DEAD, ret);
+	_leave(" = c=%08x [err]", call->debug_id);
+	return call;
 }
 
 /*
@@ -376,7 +387,8 @@ bool rxrpc_queue_call(struct rxrpc_call *call)
 	if (n == 0)
 		return false;
 	if (rxrpc_queue_work(&call->processor))
-		trace_rxrpc_call(call, rxrpc_call_queued, n + 1, here, NULL);
+		trace_rxrpc_call(call->debug_id, rxrpc_call_queued, n + 1,
+				 here, NULL);
 	else
 		rxrpc_put_call(call, rxrpc_call_put_noqueue);
 	return true;
@@ -391,7 +403,8 @@ bool __rxrpc_queue_call(struct rxrpc_call *call)
 	int n = atomic_read(&call->usage);
 	ASSERTCMP(n, >=, 1);
 	if (rxrpc_queue_work(&call->processor))
-		trace_rxrpc_call(call, rxrpc_call_queued_ref, n, here, NULL);
+		trace_rxrpc_call(call->debug_id, rxrpc_call_queued_ref, n,
+				 here, NULL);
 	else
 		rxrpc_put_call(call, rxrpc_call_put_noqueue);
 	return true;
@@ -406,7 +419,8 @@ void rxrpc_see_call(struct rxrpc_call *call)
 	if (call) {
 		int n = atomic_read(&call->usage);
 
-		trace_rxrpc_call(call, rxrpc_call_seen, n, here, NULL);
+		trace_rxrpc_call(call->debug_id, rxrpc_call_seen, n,
+				 here, NULL);
 	}
 }
 
@@ -418,7 +432,7 @@ void rxrpc_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op)
 	const void *here = __builtin_return_address(0);
 	int n = atomic_inc_return(&call->usage);
 
-	trace_rxrpc_call(call, op, n, here, NULL);
+	trace_rxrpc_call(call->debug_id, op, n, here, NULL);
 }
 
 /*
@@ -433,7 +447,8 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call)
 
 	_enter("{%d,%d}", call->debug_id, atomic_read(&call->usage));
 
-	trace_rxrpc_call(call, rxrpc_call_release, atomic_read(&call->usage),
+	trace_rxrpc_call(call->debug_id, rxrpc_call_release,
+			 atomic_read(&call->usage),
 			 here, (const void *)call->flags);
 
 	ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
@@ -476,7 +491,7 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call)
 
 	_debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, conn);
 
-	if (conn)
+	if (conn && !test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
 		rxrpc_disconnect_call(call);
 
 	for (i = 0; i < RXRPC_RXTX_BUFF_SIZE; i++) {
@@ -526,12 +541,13 @@ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace op)
 {
 	struct rxrpc_net *rxnet = call->rxnet;
 	const void *here = __builtin_return_address(0);
+	unsigned int debug_id = call->debug_id;
 	int n;
 
 	ASSERT(call != NULL);
 
 	n = atomic_dec_return(&call->usage);
-	trace_rxrpc_call(call, op, n, here, NULL);
+	trace_rxrpc_call(debug_id, op, n, here, NULL);
 	ASSERTCMP(n, >=, 0);
 	if (n == 0) {
 		_debug("call %d dead", call->debug_id);
@@ -548,13 +564,14 @@ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace op)
 }
 
 /*
- * Final call destruction under RCU.
+ * Final call destruction - but must be done in process context.
  */
-static void rxrpc_rcu_destroy_call(struct rcu_head *rcu)
+static void rxrpc_destroy_call(struct work_struct *work)
 {
-	struct rxrpc_call *call = container_of(rcu, struct rxrpc_call, rcu);
+	struct rxrpc_call *call = container_of(work, struct rxrpc_call, processor);
 	struct rxrpc_net *rxnet = call->rxnet;
 
+	rxrpc_put_connection(call->conn);
 	rxrpc_put_peer(call->peer);
 	kfree(call->rxtx_buffer);
 	kfree(call->rxtx_annotations);
@@ -564,6 +581,22 @@ static void rxrpc_rcu_destroy_call(struct rcu_head *rcu)
 }
 
 /*
+ * Final call destruction under RCU.
+ */
+static void rxrpc_rcu_destroy_call(struct rcu_head *rcu)
+{
+	struct rxrpc_call *call = container_of(rcu, struct rxrpc_call, rcu);
+
+	if (in_softirq()) {
+		INIT_WORK(&call->processor, rxrpc_destroy_call);
+		if (!rxrpc_queue_work(&call->processor))
+			BUG();
+	} else {
+		rxrpc_destroy_call(&call->processor);
+	}
+}
+
+/*
  * clean up a call
  */
 void rxrpc_cleanup_call(struct rxrpc_call *call)
@@ -578,7 +611,6 @@ void rxrpc_cleanup_call(struct rxrpc_call *call)
 
 	ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
 	ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags));
-	ASSERTCMP(call->conn, ==, NULL);
 
 	/* Clean up the Rx/Tx buffer */
 	for (i = 0; i < RXRPC_RXTX_BUFF_SIZE; i++)
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index aea82f909c60..90a51c0ee46d 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -651,13 +651,20 @@ static int rxrpc_wait_for_channel(struct rxrpc_call *call, gfp_t gfp)
 
 		add_wait_queue_exclusive(&call->waitq, &myself);
 		for (;;) {
-			if (test_bit(RXRPC_CALL_IS_INTR, &call->flags))
+			switch (call->interruptibility) {
+			case RXRPC_INTERRUPTIBLE:
+			case RXRPC_PREINTERRUPTIBLE:
 				set_current_state(TASK_INTERRUPTIBLE);
-			else
+				break;
+			case RXRPC_UNINTERRUPTIBLE:
+			default:
 				set_current_state(TASK_UNINTERRUPTIBLE);
+				break;
+			}
 			if (call->call_id)
 				break;
-			if (test_bit(RXRPC_CALL_IS_INTR, &call->flags) &&
+			if ((call->interruptibility == RXRPC_INTERRUPTIBLE ||
+			     call->interruptibility == RXRPC_PREINTERRUPTIBLE) &&
 			    signal_pending(current)) {
 				ret = -ERESTARTSYS;
 				break;
@@ -781,6 +788,7 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call)
 	u32 cid;
 
 	spin_lock(&conn->channel_lock);
+	set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
 
 	cid = call->cid;
 	if (cid) {
@@ -788,7 +796,6 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call)
 		chan = &conn->channels[channel];
 	}
 	trace_rxrpc_client(conn, channel, rxrpc_client_chan_disconnect);
-	call->conn = NULL;
 
 	/* Calls that have never actually been assigned a channel can simply be
 	 * discarded.  If the conn didn't get used either, it will follow
@@ -904,7 +911,6 @@ out:
 	spin_unlock(&rxnet->client_conn_cache_lock);
 out_2:
 	spin_unlock(&conn->channel_lock);
-	rxrpc_put_connection(conn);
 	_leave("");
 	return;
 
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index df6624c140be..488cb118fa3f 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -376,21 +376,7 @@ static void rxrpc_secure_connection(struct rxrpc_connection *conn)
 	_enter("{%d}", conn->debug_id);
 
 	ASSERT(conn->security_ix != 0);
-
-	if (!conn->params.key) {
-		_debug("set up security");
-		ret = rxrpc_init_server_conn_security(conn);
-		switch (ret) {
-		case 0:
-			break;
-		case -ENOENT:
-			abort_code = RX_CALL_DEAD;
-			goto abort;
-		default:
-			abort_code = RXKADNOAUTH;
-			goto abort;
-		}
-	}
+	ASSERT(conn->server_key);
 
 	if (conn->security->issue_challenge(conn) < 0) {
 		abort_code = RX_CALL_DEAD;
@@ -452,16 +438,12 @@ again:
 /*
  * connection-level event processor
  */
-void rxrpc_process_connection(struct work_struct *work)
+static void rxrpc_do_process_connection(struct rxrpc_connection *conn)
 {
-	struct rxrpc_connection *conn =
-		container_of(work, struct rxrpc_connection, processor);
 	struct sk_buff *skb;
 	u32 abort_code = RX_PROTOCOL_ERROR;
 	int ret;
 
-	rxrpc_see_connection(conn);
-
 	if (test_and_clear_bit(RXRPC_CONN_EV_CHALLENGE, &conn->events))
 		rxrpc_secure_connection(conn);
 
@@ -489,18 +471,32 @@ void rxrpc_process_connection(struct work_struct *work)
 		}
 	}
 
-out:
-	rxrpc_put_connection(conn);
-	_leave("");
 	return;
 
 requeue_and_leave:
 	skb_queue_head(&conn->rx_queue, skb);
-	goto out;
+	return;
 
 protocol_error:
 	if (rxrpc_abort_connection(conn, ret, abort_code) < 0)
 		goto requeue_and_leave;
 	rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
-	goto out;
+	return;
+}
+
+void rxrpc_process_connection(struct work_struct *work)
+{
+	struct rxrpc_connection *conn =
+		container_of(work, struct rxrpc_connection, processor);
+
+	rxrpc_see_connection(conn);
+
+	if (__rxrpc_use_local(conn->params.local)) {
+		rxrpc_do_process_connection(conn);
+		rxrpc_unuse_local(conn->params.local);
+	}
+
+	rxrpc_put_connection(conn);
+	_leave("");
+	return;
 }
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 434ef392212b..d76868acfa1a 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -212,9 +212,11 @@ void rxrpc_disconnect_call(struct rxrpc_call *call)
 
 	call->peer->cong_cwnd = call->cong_cwnd;
 
-	spin_lock_bh(&conn->params.peer->lock);
-	hlist_del_rcu(&call->error_link);
-	spin_unlock_bh(&conn->params.peer->lock);
+	if (!hlist_unhashed(&call->error_link)) {
+		spin_lock_bh(&call->peer->lock);
+		hlist_del_rcu(&call->error_link);
+		spin_unlock_bh(&call->peer->lock);
+	}
 
 	if (rxrpc_is_client_call(call))
 		return rxrpc_disconnect_client_call(call);
@@ -223,9 +225,8 @@ void rxrpc_disconnect_call(struct rxrpc_call *call)
 	__rxrpc_disconnect_call(conn, call);
 	spin_unlock(&conn->channel_lock);
 
-	call->conn = NULL;
+	set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
 	conn->idle_timestamp = jiffies;
-	rxrpc_put_connection(conn);
 }
 
 /*
diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c
index b30e13f6d95f..cd9440576f2d 100644
--- a/net/rxrpc/conn_service.c
+++ b/net/rxrpc/conn_service.c
@@ -148,6 +148,8 @@ struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxn
  */
 void rxrpc_new_incoming_connection(struct rxrpc_sock *rx,
 				   struct rxrpc_connection *conn,
+				   const struct rxrpc_security *sec,
+				   struct key *key,
 				   struct sk_buff *skb)
 {
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
@@ -160,6 +162,8 @@ void rxrpc_new_incoming_connection(struct rxrpc_sock *rx,
 	conn->service_id	= sp->hdr.serviceId;
 	conn->security_ix	= sp->hdr.securityIndex;
 	conn->out_clientflag	= 0;
+	conn->security		= sec;
+	conn->server_key	= key_get(key);
 	if (conn->security_ix)
 		conn->state	= RXRPC_CONN_SERVICE_UNSECURED;
 	else
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index ee95d1cd1cdf..5df738d527c9 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -91,11 +91,11 @@ static void rxrpc_congestion_management(struct rxrpc_call *call,
 		/* We analyse the number of packets that get ACK'd per RTT
 		 * period and increase the window if we managed to fill it.
 		 */
-		if (call->peer->rtt_usage == 0)
+		if (call->peer->rtt_count == 0)
 			goto out;
 		if (ktime_before(skb->tstamp,
-				 ktime_add_ns(call->cong_tstamp,
-					      call->peer->rtt)))
+				 ktime_add_us(call->cong_tstamp,
+					      call->peer->srtt_us >> 3)))
 			goto out_no_clear_ca;
 		change = rxrpc_cong_rtt_window_end;
 		call->cong_tstamp = skb->tstamp;
@@ -193,23 +193,6 @@ send_extra_data:
 }
 
 /*
- * Ping the other end to fill our RTT cache and to retrieve the rwind
- * and MTU parameters.
- */
-static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb,
-			    int skew)
-{
-	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
-	ktime_t now = skb->tstamp;
-
-	if (call->peer->rtt_usage < 3 ||
-	    ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), now))
-		rxrpc_propose_ACK(call, RXRPC_ACK_PING, skew, sp->hdr.serial,
-				  true, true,
-				  rxrpc_propose_ack_ping_for_params);
-}
-
-/*
  * Apply a hard ACK by advancing the Tx window.
  */
 static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
@@ -419,8 +402,7 @@ static void rxrpc_input_dup_data(struct rxrpc_call *call, rxrpc_seq_t seq,
 /*
  * Process a DATA packet, adding the packet to the Rx ring.
  */
-static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb,
-			     u16 skew)
+static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
 {
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	enum rxrpc_call_state state;
@@ -600,18 +582,16 @@ skip:
 
 ack:
 	if (ack)
-		rxrpc_propose_ACK(call, ack, skew, ack_serial,
+		rxrpc_propose_ACK(call, ack, ack_serial,
 				  immediate_ack, true,
 				  rxrpc_propose_ack_input_data);
 	else
-		rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, skew, serial,
+		rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial,
 				  false, true,
 				  rxrpc_propose_ack_input_data);
 
-	if (sp->hdr.seq == READ_ONCE(call->rx_hard_ack) + 1) {
-		trace_rxrpc_notify_socket(call->debug_id, serial);
-		rxrpc_notify_socket(call);
-	}
+	trace_rxrpc_notify_socket(call->debug_id, serial);
+	rxrpc_notify_socket(call);
 
 unlock:
 	spin_unlock(&call->input_lock);
@@ -733,13 +713,12 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
 	       ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU),
 	       rwind, ntohl(ackinfo->jumbo_max));
 
+	if (rwind > RXRPC_RXTX_BUFF_SIZE - 1)
+		rwind = RXRPC_RXTX_BUFF_SIZE - 1;
 	if (call->tx_winsize != rwind) {
-		if (rwind > RXRPC_RXTX_BUFF_SIZE - 1)
-			rwind = RXRPC_RXTX_BUFF_SIZE - 1;
 		if (rwind > call->tx_winsize)
 			wake = true;
-		trace_rxrpc_rx_rwind_change(call, sp->hdr.serial,
-					    ntohl(ackinfo->rwind), wake);
+		trace_rxrpc_rx_rwind_change(call, sp->hdr.serial, rwind, wake);
 		call->tx_winsize = rwind;
 	}
 
@@ -813,6 +792,30 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks,
 }
 
 /*
+ * Return true if the ACK is valid - ie. it doesn't appear to have regressed
+ * with respect to the ack state conveyed by preceding ACKs.
+ */
+static bool rxrpc_is_ack_valid(struct rxrpc_call *call,
+			       rxrpc_seq_t first_pkt, rxrpc_seq_t prev_pkt)
+{
+	rxrpc_seq_t base = READ_ONCE(call->ackr_first_seq);
+
+	if (after(first_pkt, base))
+		return true; /* The window advanced */
+
+	if (before(first_pkt, base))
+		return false; /* firstPacket regressed */
+
+	if (after_eq(prev_pkt, call->ackr_prev_seq))
+		return true; /* previousPacket hasn't regressed. */
+
+	/* Some rx implementations put a serial number in previousPacket. */
+	if (after_eq(prev_pkt, base + call->tx_winsize))
+		return false;
+	return true;
+}
+
+/*
  * Process an ACK packet.
  *
  * ack.firstPacket is the sequence number of the first soft-ACK'd/NAK'd packet
@@ -822,8 +825,7 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks,
  * soft-ACK means that the packet may be discarded and retransmission
  * requested.  A phase is complete when all packets are hard-ACK'd.
  */
-static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
-			    u16 skew)
+static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 {
 	struct rxrpc_ack_summary summary = { 0 };
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
@@ -867,18 +869,21 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
 	if (buf.ack.reason == RXRPC_ACK_PING) {
 		_proto("Rx ACK %%%u PING Request", sp->hdr.serial);
 		rxrpc_propose_ACK(call, RXRPC_ACK_PING_RESPONSE,
-				  skew, sp->hdr.serial, true, true,
+				  sp->hdr.serial, true, true,
 				  rxrpc_propose_ack_respond_to_ping);
 	} else if (sp->hdr.flags & RXRPC_REQUEST_ACK) {
 		rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED,
-				  skew, sp->hdr.serial, true, true,
+				  sp->hdr.serial, true, true,
 				  rxrpc_propose_ack_respond_to_ack);
 	}
 
 	/* Discard any out-of-order or duplicate ACKs (outside lock). */
-	if (before(first_soft_ack, call->ackr_first_seq) ||
-	    before(prev_pkt, call->ackr_prev_seq))
+	if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) {
+		trace_rxrpc_rx_discard_ack(call->debug_id, sp->hdr.serial,
+					   first_soft_ack, call->ackr_first_seq,
+					   prev_pkt, call->ackr_prev_seq);
 		return;
+	}
 
 	buf.info.rxMTU = 0;
 	ioffset = offset + nr_acks + 3;
@@ -889,11 +894,13 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
 	spin_lock(&call->input_lock);
 
 	/* Discard any out-of-order or duplicate ACKs (inside lock). */
-	if (before(first_soft_ack, call->ackr_first_seq) ||
-	    before(prev_pkt, call->ackr_prev_seq))
+	if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) {
+		trace_rxrpc_rx_discard_ack(call->debug_id, sp->hdr.serial,
+					   first_soft_ack, call->ackr_first_seq,
+					   prev_pkt, call->ackr_prev_seq);
 		goto out;
+	}
 	call->acks_latest_ts = skb->tstamp;
-	call->acks_latest = sp->hdr.serial;
 
 	call->ackr_first_seq = first_soft_ack;
 	call->ackr_prev_seq = prev_pkt;
@@ -948,7 +955,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
 	    RXRPC_TX_ANNO_LAST &&
 	    summary.nr_acks == call->tx_top - hard_ack &&
 	    rxrpc_is_client_call(call))
-		rxrpc_propose_ACK(call, RXRPC_ACK_PING, skew, sp->hdr.serial,
+		rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial,
 				  false, true,
 				  rxrpc_propose_ack_ping_for_lost_reply);
 
@@ -1004,7 +1011,7 @@ static void rxrpc_input_abort(struct rxrpc_call *call, struct sk_buff *skb)
  * Process an incoming call packet.
  */
 static void rxrpc_input_call_packet(struct rxrpc_call *call,
-				    struct sk_buff *skb, u16 skew)
+				    struct sk_buff *skb)
 {
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	unsigned long timo;
@@ -1023,11 +1030,11 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call,
 
 	switch (sp->hdr.type) {
 	case RXRPC_PACKET_TYPE_DATA:
-		rxrpc_input_data(call, skb, skew);
+		rxrpc_input_data(call, skb);
 		break;
 
 	case RXRPC_PACKET_TYPE_ACK:
-		rxrpc_input_ack(call, skb, skew);
+		rxrpc_input_ack(call, skb);
 		break;
 
 	case RXRPC_PACKET_TYPE_BUSY:
@@ -1181,7 +1188,6 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb)
 	struct rxrpc_peer *peer = NULL;
 	struct rxrpc_sock *rx = NULL;
 	unsigned int channel;
-	int skew = 0;
 
 	_enter("%p", udp_sk);
 
@@ -1309,15 +1315,8 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb)
 			goto out;
 		}
 
-		/* Note the serial number skew here */
-		skew = (int)sp->hdr.serial - (int)conn->hi_serial;
-		if (skew >= 0) {
-			if (skew > 0)
-				conn->hi_serial = sp->hdr.serial;
-		} else {
-			skew = -skew;
-			skew = min(skew, 65535);
-		}
+		if ((int)sp->hdr.serial - (int)conn->hi_serial > 0)
+			conn->hi_serial = sp->hdr.serial;
 
 		/* Call-bound packets are routed by connection channel. */
 		channel = sp->hdr.cid & RXRPC_CHANNELMASK;
@@ -1380,11 +1379,9 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb)
 		call = rxrpc_new_incoming_call(local, rx, skb);
 		if (!call)
 			goto reject_packet;
-		rxrpc_send_ping(call, skb, skew);
-		mutex_unlock(&call->user_mutex);
 	}
 
-	rxrpc_input_call_packet(call, skb, skew);
+	rxrpc_input_call_packet(call, skb);
 	goto discard;
 
 discard:
diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c
index 83e3357a65a6..7369d023b8b0 100644
--- a/net/rxrpc/key.c
+++ b/net/rxrpc/key.c
@@ -31,7 +31,7 @@ static void rxrpc_free_preparse_s(struct key_preparsed_payload *);
 static void rxrpc_destroy(struct key *);
 static void rxrpc_destroy_s(struct key *);
 static void rxrpc_describe(const struct key *, struct seq_file *);
-static long rxrpc_read(const struct key *, char __user *, size_t);
+static long rxrpc_read(const struct key *, char *, size_t);
 
 /*
  * rxrpc defined keys take an arbitrary string as the description and an
@@ -1040,12 +1040,12 @@ EXPORT_SYMBOL(rxrpc_get_null_key);
  * - this returns the result in XDR form
  */
 static long rxrpc_read(const struct key *key,
-		       char __user *buffer, size_t buflen)
+		       char *buffer, size_t buflen)
 {
 	const struct rxrpc_key_token *token;
 	const struct krb5_principal *princ;
 	size_t size;
-	__be32 __user *xdr, *oldxdr;
+	__be32 *xdr, *oldxdr;
 	u32 cnlen, toksize, ntoks, tok, zero;
 	u16 toksizes[AFSTOKEN_MAX];
 	int loop;
@@ -1122,30 +1122,25 @@ static long rxrpc_read(const struct key *key,
 	if (!buffer || buflen < size)
 		return size;
 
-	xdr = (__be32 __user *) buffer;
+	xdr = (__be32 *)buffer;
 	zero = 0;
 #define ENCODE(x)				\
 	do {					\
-		__be32 y = htonl(x);		\
-		if (put_user(y, xdr++) < 0)	\
-			goto fault;		\
+		*xdr++ = htonl(x);		\
 	} while(0)
 #define ENCODE_DATA(l, s)						\
 	do {								\
 		u32 _l = (l);						\
 		ENCODE(l);						\
-		if (copy_to_user(xdr, (s), _l) != 0)			\
-			goto fault;					\
-		if (_l & 3 &&						\
-		    copy_to_user((u8 __user *)xdr + _l, &zero, 4 - (_l & 3)) != 0) \
-			goto fault;					\
+		memcpy(xdr, (s), _l);					\
+		if (_l & 3)						\
+			memcpy((u8 *)xdr + _l, &zero, 4 - (_l & 3));	\
 		xdr += (_l + 3) >> 2;					\
 	} while(0)
 #define ENCODE64(x)					\
 	do {						\
 		__be64 y = cpu_to_be64(x);		\
-		if (copy_to_user(xdr, &y, 8) != 0)	\
-			goto fault;			\
+		memcpy(xdr, &y, 8);			\
 		xdr += 8 >> 2;				\
 	} while(0)
 #define ENCODE_STR(s)				\
@@ -1236,8 +1231,4 @@ static long rxrpc_read(const struct key *key,
 	ASSERTCMP((char __user *) xdr - buffer, ==, size);
 	_leave(" = %zu", size);
 	return size;
-
-fault:
-	_leave(" = -EFAULT");
-	return -EFAULT;
 }
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 72a6e12a9304..ce65db43f36b 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -165,15 +165,6 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
 			goto error;
 		}
 
-		/* we want to set the don't fragment bit */
-		opt = IPV6_PMTUDISC_DO;
-		ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER,
-					(char *) &opt, sizeof(opt));
-		if (ret < 0) {
-			_debug("setsockopt failed");
-			goto error;
-		}
-
 		/* Fall through and set IPv4 options too otherwise we don't get
 		 * errors from IPv4 packets sent through the IPv6 socket.
 		 */
@@ -364,11 +355,14 @@ void rxrpc_queue_local(struct rxrpc_local *local)
 void rxrpc_put_local(struct rxrpc_local *local)
 {
 	const void *here = __builtin_return_address(0);
+	unsigned int debug_id;
 	int n;
 
 	if (local) {
+		debug_id = local->debug_id;
+
 		n = atomic_dec_return(&local->usage);
-		trace_rxrpc_local(local->debug_id, rxrpc_local_put, n, here);
+		trace_rxrpc_local(debug_id, rxrpc_local_put, n, here);
 
 		if (n == 0)
 			call_rcu(&local->rcu, rxrpc_local_rcu);
@@ -380,14 +374,11 @@ void rxrpc_put_local(struct rxrpc_local *local)
  */
 struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *local)
 {
-	unsigned int au;
-
 	local = rxrpc_get_local_maybe(local);
 	if (!local)
 		return NULL;
 
-	au = atomic_fetch_add_unless(&local->active_users, 1, 0);
-	if (au == 0) {
+	if (!__rxrpc_use_local(local)) {
 		rxrpc_put_local(local);
 		return NULL;
 	}
@@ -401,14 +392,11 @@ struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *local)
  */
 void rxrpc_unuse_local(struct rxrpc_local *local)
 {
-	unsigned int au;
-
 	if (local) {
-		au = atomic_dec_return(&local->active_users);
-		if (au == 0)
+		if (__rxrpc_unuse_local(local)) {
+			rxrpc_get_local(local);
 			rxrpc_queue_local(local);
-		else
-			rxrpc_put_local(local);
+		}
 	}
 }
 
@@ -462,7 +450,7 @@ static void rxrpc_local_processor(struct work_struct *work)
 
 	do {
 		again = false;
-		if (atomic_read(&local->active_users) == 0) {
+		if (!__rxrpc_use_local(local)) {
 			rxrpc_local_destroyer(local);
 			break;
 		}
@@ -476,6 +464,8 @@ static void rxrpc_local_processor(struct work_struct *work)
 			rxrpc_process_local_events(local);
 			again = true;
 		}
+
+		__rxrpc_unuse_local(local);
 	} while (again);
 
 	rxrpc_put_local(local);
diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c
index 214405f75346..d4144fd86f84 100644
--- a/net/rxrpc/misc.c
+++ b/net/rxrpc/misc.c
@@ -63,11 +63,6 @@ unsigned int rxrpc_rx_mtu = 5692;
  */
 unsigned int rxrpc_rx_jumbo_max = 4;
 
-/*
- * Time till packet resend (in milliseconds).
- */
-unsigned long rxrpc_resend_timeout = 4 * HZ;
-
 const s8 rxrpc_ack_priority[] = {
 	[0]				= 0,
 	[RXRPC_ACK_DELAY]		= 1,
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index a0b6abfbd277..905484a50357 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -87,7 +87,7 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn,
 	*_top = top;
 
 	pkt->ack.bufferSpace	= htons(8);
-	pkt->ack.maxSkew	= htons(call->ackr_skew);
+	pkt->ack.maxSkew	= htons(0);
 	pkt->ack.firstPacket	= htonl(hard_ack + 1);
 	pkt->ack.previousPacket	= htonl(call->ackr_prev_seq);
 	pkt->ack.serial		= htonl(serial);
@@ -129,7 +129,7 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn,
 int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 			  rxrpc_serial_t *_serial)
 {
-	struct rxrpc_connection *conn = NULL;
+	struct rxrpc_connection *conn;
 	struct rxrpc_ack_buffer *pkt;
 	struct msghdr msg;
 	struct kvec iov[2];
@@ -139,18 +139,14 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 	int ret;
 	u8 reason;
 
-	spin_lock_bh(&call->lock);
-	if (call->conn)
-		conn = rxrpc_get_connection_maybe(call->conn);
-	spin_unlock_bh(&call->lock);
-	if (!conn)
+	if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
 		return -ECONNRESET;
 
 	pkt = kzalloc(sizeof(*pkt), GFP_KERNEL);
-	if (!pkt) {
-		rxrpc_put_connection(conn);
+	if (!pkt)
 		return -ENOMEM;
-	}
+
+	conn = call->conn;
 
 	msg.msg_name	= &call->peer->srx.transport;
 	msg.msg_namelen	= call->peer->srx.transport_len;
@@ -228,7 +224,6 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 			if (ping)
 				clear_bit(RXRPC_CALL_PINGING, &call->flags);
 			rxrpc_propose_ACK(call, pkt->ack.reason,
-					  ntohs(pkt->ack.maxSkew),
 					  ntohl(pkt->ack.serial),
 					  false, true,
 					  rxrpc_propose_ack_retry_tx);
@@ -245,7 +240,6 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 	}
 
 out:
-	rxrpc_put_connection(conn);
 	kfree(pkt);
 	return ret;
 }
@@ -255,7 +249,7 @@ out:
  */
 int rxrpc_send_abort_packet(struct rxrpc_call *call)
 {
-	struct rxrpc_connection *conn = NULL;
+	struct rxrpc_connection *conn;
 	struct rxrpc_abort_buffer pkt;
 	struct msghdr msg;
 	struct kvec iov[1];
@@ -272,13 +266,11 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call)
 	    test_bit(RXRPC_CALL_TX_LAST, &call->flags))
 		return 0;
 
-	spin_lock_bh(&call->lock);
-	if (call->conn)
-		conn = rxrpc_get_connection_maybe(call->conn);
-	spin_unlock_bh(&call->lock);
-	if (!conn)
+	if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
 		return -ECONNRESET;
 
+	conn = call->conn;
+
 	msg.msg_name	= &call->peer->srx.transport;
 	msg.msg_namelen	= call->peer->srx.transport_len;
 	msg.msg_control	= NULL;
@@ -313,8 +305,6 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call)
 		trace_rxrpc_tx_packet(call->debug_id, &pkt.whdr,
 				      rxrpc_tx_point_call_abort);
 	rxrpc_tx_backoff(call, ret);
-
-	rxrpc_put_connection(conn);
 	return ret;
 }
 
@@ -379,7 +369,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 	    (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events) ||
 	     retrans ||
 	     call->cong_mode == RXRPC_CALL_SLOW_START ||
-	     (call->peer->rtt_usage < 3 && sp->hdr.seq & 1) ||
+	     (call->peer->rtt_count < 3 && sp->hdr.seq & 1) ||
 	     ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000),
 			  ktime_get_real())))
 		whdr.flags |= RXRPC_REQUEST_ACK;
@@ -433,13 +423,10 @@ done:
 		if (whdr.flags & RXRPC_REQUEST_ACK) {
 			call->peer->rtt_last_req = skb->tstamp;
 			trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_data, serial);
-			if (call->peer->rtt_usage > 1) {
+			if (call->peer->rtt_count > 1) {
 				unsigned long nowj = jiffies, ack_lost_at;
 
-				ack_lost_at = nsecs_to_jiffies(2 * call->peer->rtt);
-				if (ack_lost_at < 1)
-					ack_lost_at = 1;
-
+				ack_lost_at = rxrpc_get_rto_backoff(call->peer, retrans);
 				ack_lost_at += nowj;
 				WRITE_ONCE(call->ack_lost_at, ack_lost_at);
 				rxrpc_reduce_call_timer(call, ack_lost_at, nowj,
@@ -484,41 +471,21 @@ send_fragmentable:
 	skb->tstamp = ktime_get_real();
 
 	switch (conn->params.local->srx.transport.family) {
+	case AF_INET6:
 	case AF_INET:
 		opt = IP_PMTUDISC_DONT;
-		ret = kernel_setsockopt(conn->params.local->socket,
-					SOL_IP, IP_MTU_DISCOVER,
-					(char *)&opt, sizeof(opt));
-		if (ret == 0) {
-			ret = kernel_sendmsg(conn->params.local->socket, &msg,
-					     iov, 2, len);
-			conn->params.peer->last_tx_at = ktime_get_seconds();
-
-			opt = IP_PMTUDISC_DO;
-			kernel_setsockopt(conn->params.local->socket, SOL_IP,
-					  IP_MTU_DISCOVER,
-					  (char *)&opt, sizeof(opt));
-		}
-		break;
-
-#ifdef CONFIG_AF_RXRPC_IPV6
-	case AF_INET6:
-		opt = IPV6_PMTUDISC_DONT;
-		ret = kernel_setsockopt(conn->params.local->socket,
-					SOL_IPV6, IPV6_MTU_DISCOVER,
-					(char *)&opt, sizeof(opt));
-		if (ret == 0) {
-			ret = kernel_sendmsg(conn->params.local->socket, &msg,
-					     iov, 2, len);
-			conn->params.peer->last_tx_at = ktime_get_seconds();
-
-			opt = IPV6_PMTUDISC_DO;
-			kernel_setsockopt(conn->params.local->socket,
-					  SOL_IPV6, IPV6_MTU_DISCOVER,
-					  (char *)&opt, sizeof(opt));
-		}
+		kernel_setsockopt(conn->params.local->socket,
+				  SOL_IP, IP_MTU_DISCOVER,
+				  (char *)&opt, sizeof(opt));
+		ret = kernel_sendmsg(conn->params.local->socket, &msg,
+				     iov, 2, len);
+		conn->params.peer->last_tx_at = ktime_get_seconds();
+
+		opt = IP_PMTUDISC_DO;
+		kernel_setsockopt(conn->params.local->socket,
+				  SOL_IP, IP_MTU_DISCOVER,
+				  (char *)&opt, sizeof(opt));
 		break;
-#endif
 	}
 
 	if (ret < 0)
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index e92e0526e0dc..02ffe730163b 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -296,52 +296,6 @@ static void rxrpc_distribute_error(struct rxrpc_peer *peer, int error,
 }
 
 /*
- * Add RTT information to cache.  This is called in softirq mode and has
- * exclusive access to the peer RTT data.
- */
-void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
-			rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial,
-			ktime_t send_time, ktime_t resp_time)
-{
-	struct rxrpc_peer *peer = call->peer;
-	s64 rtt;
-	u64 sum = peer->rtt_sum, avg;
-	u8 cursor = peer->rtt_cursor, usage = peer->rtt_usage;
-
-	rtt = ktime_to_ns(ktime_sub(resp_time, send_time));
-	if (rtt < 0)
-		return;
-
-	spin_lock(&peer->rtt_input_lock);
-
-	/* Replace the oldest datum in the RTT buffer */
-	sum -= peer->rtt_cache[cursor];
-	sum += rtt;
-	peer->rtt_cache[cursor] = rtt;
-	peer->rtt_cursor = (cursor + 1) & (RXRPC_RTT_CACHE_SIZE - 1);
-	peer->rtt_sum = sum;
-	if (usage < RXRPC_RTT_CACHE_SIZE) {
-		usage++;
-		peer->rtt_usage = usage;
-	}
-
-	spin_unlock(&peer->rtt_input_lock);
-
-	/* Now recalculate the average */
-	if (usage == RXRPC_RTT_CACHE_SIZE) {
-		avg = sum / RXRPC_RTT_CACHE_SIZE;
-	} else {
-		avg = sum;
-		do_div(avg, usage);
-	}
-
-	/* Don't need to update this under lock */
-	peer->rtt = avg;
-	trace_rxrpc_rtt_rx(call, why, send_serial, resp_serial, rtt,
-			   usage, avg);
-}
-
-/*
  * Perform keep-alive pings.
  */
 static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet,
@@ -364,27 +318,31 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet,
 		if (!rxrpc_get_peer_maybe(peer))
 			continue;
 
-		spin_unlock_bh(&rxnet->peer_hash_lock);
+		if (__rxrpc_use_local(peer->local)) {
+			spin_unlock_bh(&rxnet->peer_hash_lock);
 
-		keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME;
-		slot = keepalive_at - base;
-		_debug("%02x peer %u t=%d {%pISp}",
-		       cursor, peer->debug_id, slot, &peer->srx.transport);
+			keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME;
+			slot = keepalive_at - base;
+			_debug("%02x peer %u t=%d {%pISp}",
+			       cursor, peer->debug_id, slot, &peer->srx.transport);
 
-		if (keepalive_at <= base ||
-		    keepalive_at > base + RXRPC_KEEPALIVE_TIME) {
-			rxrpc_send_keepalive(peer);
-			slot = RXRPC_KEEPALIVE_TIME;
-		}
+			if (keepalive_at <= base ||
+			    keepalive_at > base + RXRPC_KEEPALIVE_TIME) {
+				rxrpc_send_keepalive(peer);
+				slot = RXRPC_KEEPALIVE_TIME;
+			}
 
-		/* A transmission to this peer occurred since last we examined
-		 * it so put it into the appropriate future bucket.
-		 */
-		slot += cursor;
-		slot &= mask;
-		spin_lock_bh(&rxnet->peer_hash_lock);
-		list_add_tail(&peer->keepalive_link,
-			      &rxnet->peer_keepalive[slot & mask]);
+			/* A transmission to this peer occurred since last we
+			 * examined it so put it into the appropriate future
+			 * bucket.
+			 */
+			slot += cursor;
+			slot &= mask;
+			spin_lock_bh(&rxnet->peer_hash_lock);
+			list_add_tail(&peer->keepalive_link,
+				      &rxnet->peer_keepalive[slot & mask]);
+			rxrpc_unuse_local(peer->local);
+		}
 		rxrpc_put_peer_locked(peer);
 	}
 
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 64830d8c1fdb..e011594adcd1 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -224,6 +224,8 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp)
 		spin_lock_init(&peer->rtt_input_lock);
 		peer->debug_id = atomic_inc_return(&rxrpc_debug_id);
 
+		rxrpc_peer_init_rtt(peer);
+
 		if (RXRPC_TX_SMSS > 2190)
 			peer->cong_cwnd = 2;
 		else if (RXRPC_TX_SMSS > 1095)
@@ -495,14 +497,24 @@ void rxrpc_kernel_get_peer(struct socket *sock, struct rxrpc_call *call,
 EXPORT_SYMBOL(rxrpc_kernel_get_peer);
 
 /**
- * rxrpc_kernel_get_rtt - Get a call's peer RTT
+ * rxrpc_kernel_get_srtt - Get a call's peer smoothed RTT
  * @sock: The socket on which the call is in progress.
  * @call: The call to query
+ * @_srtt: Where to store the SRTT value.
  *
- * Get the call's peer RTT.
+ * Get the call's peer smoothed RTT in uS.
  */
-u64 rxrpc_kernel_get_rtt(struct socket *sock, struct rxrpc_call *call)
+bool rxrpc_kernel_get_srtt(struct socket *sock, struct rxrpc_call *call,
+			   u32 *_srtt)
 {
-	return call->peer->rtt;
+	struct rxrpc_peer *peer = call->peer;
+
+	if (peer->rtt_count == 0) {
+		*_srtt = 1000000; /* 1S */
+		return false;
+	}
+
+	*_srtt = call->peer->srtt_us >> 3;
+	return true;
 }
-EXPORT_SYMBOL(rxrpc_kernel_get_rtt);
+EXPORT_SYMBOL(rxrpc_kernel_get_srtt);
diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c
index b9d053e42821..543afd9bd664 100644
--- a/net/rxrpc/proc.c
+++ b/net/rxrpc/proc.c
@@ -68,7 +68,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v)
 			 "Proto Local                                          "
 			 " Remote                                         "
 			 " SvID ConnID   CallID   End Use State    Abort   "
-			 " UserID           TxSeq    TW RxSeq    RW RxSerial RxTimo\n");
+			 " DebugId  TxSeq    TW RxSeq    RW RxSerial RxTimo\n");
 		return 0;
 	}
 
@@ -100,7 +100,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v)
 	rx_hard_ack = READ_ONCE(call->rx_hard_ack);
 	seq_printf(seq,
 		   "UDP   %-47.47s %-47.47s %4x %08x %08x %s %3u"
-		   " %-8.8s %08x %lx %08x %02x %08x %02x %08x %06lx\n",
+		   " %-8.8s %08x %08x %08x %02x %08x %02x %08x %06lx\n",
 		   lbuff,
 		   rbuff,
 		   call->service_id,
@@ -110,7 +110,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v)
 		   atomic_read(&call->usage),
 		   rxrpc_call_states[call->state],
 		   call->abort_code,
-		   call->user_call_ID,
+		   call->debug_id,
 		   tx_hard_ack, READ_ONCE(call->tx_top) - tx_hard_ack,
 		   rx_hard_ack, READ_ONCE(call->rx_top) - rx_hard_ack,
 		   call->rx_serial,
@@ -222,7 +222,7 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v)
 		seq_puts(seq,
 			 "Proto Local                                          "
 			 " Remote                                         "
-			 " Use CW  MTU   LastUse          RTT Rc\n"
+			 " Use  CW   MTU LastUse      RTT      RTO\n"
 			 );
 		return 0;
 	}
@@ -236,15 +236,15 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v)
 	now = ktime_get_seconds();
 	seq_printf(seq,
 		   "UDP   %-47.47s %-47.47s %3u"
-		   " %3u %5u %6llus %12llu %2u\n",
+		   " %3u %5u %6llus %8u %8u\n",
 		   lbuff,
 		   rbuff,
 		   atomic_read(&peer->usage),
 		   peer->cong_cwnd,
 		   peer->mtu,
 		   now - peer->last_tx_at,
-		   peer->rtt,
-		   peer->rtt_cursor);
+		   peer->srtt_us >> 3,
+		   jiffies_to_usecs(peer->rto_j));
 
 	return 0;
 }
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 5abf46cf9e6c..ba5d9c2885b0 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -141,7 +141,7 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial)
 	ASSERTCMP(call->rx_hard_ack, ==, call->rx_top);
 
 	if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) {
-		rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, 0, serial, false, true,
+		rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, serial, false, true,
 				  rxrpc_propose_ack_terminal_ack);
 		//rxrpc_send_ack_packet(call, false, NULL);
 	}
@@ -159,7 +159,7 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial)
 		call->state = RXRPC_CALL_SERVER_ACK_REQUEST;
 		call->expect_req_by = jiffies + MAX_JIFFY_OFFSET;
 		write_unlock_bh(&call->state_lock);
-		rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, 0, serial, false, true,
+		rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, false, true,
 				  rxrpc_propose_ack_processing_op);
 		break;
 	default:
@@ -212,7 +212,7 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call)
 		if (after_eq(hard_ack, call->ackr_consumed + 2) ||
 		    after_eq(top, call->ackr_seen + 2) ||
 		    (hard_ack == top && after(hard_ack, call->ackr_consumed)))
-			rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, 0, serial,
+			rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial,
 					  true, true,
 					  rxrpc_propose_ack_rotate_rx);
 		if (call->ackr_reason && call->ackr_reason != RXRPC_ACK_DELAY)
@@ -449,7 +449,7 @@ try_again:
 	    list_empty(&rx->recvmsg_q) &&
 	    rx->sk.sk_state != RXRPC_SERVER_LISTENING) {
 		release_sock(&rx->sk);
-		return -ENODATA;
+		return -EAGAIN;
 	}
 
 	if (list_empty(&rx->recvmsg_q)) {
@@ -526,7 +526,7 @@ try_again:
 			goto error_unlock_call;
 	}
 
-	if (msg->msg_name) {
+	if (msg->msg_name && call->peer) {
 		struct sockaddr_rxrpc *srx = msg->msg_name;
 		size_t len = sizeof(call->peer->srx);
 
diff --git a/net/rxrpc/rtt.c b/net/rxrpc/rtt.c
new file mode 100644
index 000000000000..928d8b34a3ee
--- /dev/null
+++ b/net/rxrpc/rtt.c
@@ -0,0 +1,195 @@
+// SPDX-License-Identifier: GPL-2.0
+/* RTT/RTO calculation.
+ *
+ * Adapted from TCP for AF_RXRPC by David Howells (dhowells@redhat.com)
+ *
+ * https://tools.ietf.org/html/rfc6298
+ * https://tools.ietf.org/html/rfc1122#section-4.2.3.1
+ * http://ccr.sigcomm.org/archive/1995/jan95/ccr-9501-partridge87.pdf
+ */
+
+#include <linux/net.h>
+#include "ar-internal.h"
+
+#define RXRPC_RTO_MAX	((unsigned)(120 * HZ))
+#define RXRPC_TIMEOUT_INIT ((unsigned)(1*HZ))	/* RFC6298 2.1 initial RTO value	*/
+#define rxrpc_jiffies32 ((u32)jiffies)		/* As rxrpc_jiffies32 */
+#define rxrpc_min_rtt_wlen 300			/* As sysctl_tcp_min_rtt_wlen */
+
+static u32 rxrpc_rto_min_us(struct rxrpc_peer *peer)
+{
+	return 200;
+}
+
+static u32 __rxrpc_set_rto(const struct rxrpc_peer *peer)
+{
+	return _usecs_to_jiffies((peer->srtt_us >> 3) + peer->rttvar_us);
+}
+
+static u32 rxrpc_bound_rto(u32 rto)
+{
+	return min(rto, RXRPC_RTO_MAX);
+}
+
+/*
+ * Called to compute a smoothed rtt estimate. The data fed to this
+ * routine either comes from timestamps, or from segments that were
+ * known _not_ to have been retransmitted [see Karn/Partridge
+ * Proceedings SIGCOMM 87]. The algorithm is from the SIGCOMM 88
+ * piece by Van Jacobson.
+ * NOTE: the next three routines used to be one big routine.
+ * To save cycles in the RFC 1323 implementation it was better to break
+ * it up into three procedures. -- erics
+ */
+static void rxrpc_rtt_estimator(struct rxrpc_peer *peer, long sample_rtt_us)
+{
+	long m = sample_rtt_us; /* RTT */
+	u32 srtt = peer->srtt_us;
+
+	/*	The following amusing code comes from Jacobson's
+	 *	article in SIGCOMM '88.  Note that rtt and mdev
+	 *	are scaled versions of rtt and mean deviation.
+	 *	This is designed to be as fast as possible
+	 *	m stands for "measurement".
+	 *
+	 *	On a 1990 paper the rto value is changed to:
+	 *	RTO = rtt + 4 * mdev
+	 *
+	 * Funny. This algorithm seems to be very broken.
+	 * These formulae increase RTO, when it should be decreased, increase
+	 * too slowly, when it should be increased quickly, decrease too quickly
+	 * etc. I guess in BSD RTO takes ONE value, so that it is absolutely
+	 * does not matter how to _calculate_ it. Seems, it was trap
+	 * that VJ failed to avoid. 8)
+	 */
+	if (srtt != 0) {
+		m -= (srtt >> 3);	/* m is now error in rtt est */
+		srtt += m;		/* rtt = 7/8 rtt + 1/8 new */
+		if (m < 0) {
+			m = -m;		/* m is now abs(error) */
+			m -= (peer->mdev_us >> 2);   /* similar update on mdev */
+			/* This is similar to one of Eifel findings.
+			 * Eifel blocks mdev updates when rtt decreases.
+			 * This solution is a bit different: we use finer gain
+			 * for mdev in this case (alpha*beta).
+			 * Like Eifel it also prevents growth of rto,
+			 * but also it limits too fast rto decreases,
+			 * happening in pure Eifel.
+			 */
+			if (m > 0)
+				m >>= 3;
+		} else {
+			m -= (peer->mdev_us >> 2);   /* similar update on mdev */
+		}
+
+		peer->mdev_us += m;		/* mdev = 3/4 mdev + 1/4 new */
+		if (peer->mdev_us > peer->mdev_max_us) {
+			peer->mdev_max_us = peer->mdev_us;
+			if (peer->mdev_max_us > peer->rttvar_us)
+				peer->rttvar_us = peer->mdev_max_us;
+		}
+	} else {
+		/* no previous measure. */
+		srtt = m << 3;		/* take the measured time to be rtt */
+		peer->mdev_us = m << 1;	/* make sure rto = 3*rtt */
+		peer->rttvar_us = max(peer->mdev_us, rxrpc_rto_min_us(peer));
+		peer->mdev_max_us = peer->rttvar_us;
+	}
+
+	peer->srtt_us = max(1U, srtt);
+}
+
+/*
+ * Calculate rto without backoff.  This is the second half of Van Jacobson's
+ * routine referred to above.
+ */
+static void rxrpc_set_rto(struct rxrpc_peer *peer)
+{
+	u32 rto;
+
+	/* 1. If rtt variance happened to be less 50msec, it is hallucination.
+	 *    It cannot be less due to utterly erratic ACK generation made
+	 *    at least by solaris and freebsd. "Erratic ACKs" has _nothing_
+	 *    to do with delayed acks, because at cwnd>2 true delack timeout
+	 *    is invisible. Actually, Linux-2.4 also generates erratic
+	 *    ACKs in some circumstances.
+	 */
+	rto = __rxrpc_set_rto(peer);
+
+	/* 2. Fixups made earlier cannot be right.
+	 *    If we do not estimate RTO correctly without them,
+	 *    all the algo is pure shit and should be replaced
+	 *    with correct one. It is exactly, which we pretend to do.
+	 */
+
+	/* NOTE: clamping at RXRPC_RTO_MIN is not required, current algo
+	 * guarantees that rto is higher.
+	 */
+	peer->rto_j = rxrpc_bound_rto(rto);
+}
+
+static void rxrpc_ack_update_rtt(struct rxrpc_peer *peer, long rtt_us)
+{
+	if (rtt_us < 0)
+		return;
+
+	//rxrpc_update_rtt_min(peer, rtt_us);
+	rxrpc_rtt_estimator(peer, rtt_us);
+	rxrpc_set_rto(peer);
+
+	/* RFC6298: only reset backoff on valid RTT measurement. */
+	peer->backoff = 0;
+}
+
+/*
+ * Add RTT information to cache.  This is called in softirq mode and has
+ * exclusive access to the peer RTT data.
+ */
+void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
+			rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial,
+			ktime_t send_time, ktime_t resp_time)
+{
+	struct rxrpc_peer *peer = call->peer;
+	s64 rtt_us;
+
+	rtt_us = ktime_to_us(ktime_sub(resp_time, send_time));
+	if (rtt_us < 0)
+		return;
+
+	spin_lock(&peer->rtt_input_lock);
+	rxrpc_ack_update_rtt(peer, rtt_us);
+	if (peer->rtt_count < 3)
+		peer->rtt_count++;
+	spin_unlock(&peer->rtt_input_lock);
+
+	trace_rxrpc_rtt_rx(call, why, send_serial, resp_serial,
+			   peer->srtt_us >> 3, peer->rto_j);
+}
+
+/*
+ * Get the retransmission timeout to set in jiffies, backing it off each time
+ * we retransmit.
+ */
+unsigned long rxrpc_get_rto_backoff(struct rxrpc_peer *peer, bool retrans)
+{
+	u64 timo_j;
+	u8 backoff = READ_ONCE(peer->backoff);
+
+	timo_j = peer->rto_j;
+	timo_j <<= backoff;
+	if (retrans && timo_j * 2 <= RXRPC_RTO_MAX)
+		WRITE_ONCE(peer->backoff, backoff + 1);
+
+	if (timo_j < 1)
+		timo_j = 1;
+
+	return timo_j;
+}
+
+void rxrpc_peer_init_rtt(struct rxrpc_peer *peer)
+{
+	peer->rto_j	= RXRPC_TIMEOUT_INIT;
+	peer->mdev_us	= jiffies_to_usecs(RXRPC_TIMEOUT_INIT);
+	peer->backoff	= 0;
+	//minmax_reset(&peer->rtt_min, rxrpc_jiffies32, ~0U);
+}
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index ae8cd8926456..49e0b0fde24c 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -618,9 +618,9 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn)
 	u32 serial;
 	int ret;
 
-	_enter("{%d,%x}", conn->debug_id, key_serial(conn->params.key));
+	_enter("{%d,%x}", conn->debug_id, key_serial(conn->server_key));
 
-	ret = key_validate(conn->params.key);
+	ret = key_validate(conn->server_key);
 	if (ret < 0)
 		return ret;
 
@@ -1114,7 +1114,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
 	ret = rxkad_decrypt_ticket(conn, skb, ticket, ticket_len, &session_key,
 				   &expiry, _abort_code);
 	if (ret < 0)
-		goto temporary_error_free_resp;
+		goto temporary_error_free_ticket;
 
 	/* use the session key from inside the ticket to decrypt the
 	 * response */
@@ -1196,7 +1196,6 @@ protocol_error:
 
 temporary_error_free_ticket:
 	kfree(ticket);
-temporary_error_free_resp:
 	kfree(response);
 temporary_error:
 	/* Ignore the response packet if we got a temporary error such as
@@ -1243,6 +1242,7 @@ static void rxkad_exit(void)
 const struct rxrpc_security rxkad = {
 	.name				= "rxkad",
 	.security_index			= RXRPC_SECURITY_RXKAD,
+	.no_key_abort			= RXKADUNKNOWNKEY,
 	.init				= rxkad_init,
 	.exit				= rxkad_exit,
 	.init_connection_security	= rxkad_init_connection_security,
diff --git a/net/rxrpc/security.c b/net/rxrpc/security.c
index 2e78f0cc7ef1..fe79f514f47a 100644
--- a/net/rxrpc/security.c
+++ b/net/rxrpc/security.c
@@ -101,62 +101,58 @@ int rxrpc_init_client_conn_security(struct rxrpc_connection *conn)
 }
 
 /*
- * initialise the security on a server connection
+ * Find the security key for a server connection.
  */
-int rxrpc_init_server_conn_security(struct rxrpc_connection *conn)
+bool rxrpc_look_up_server_security(struct rxrpc_local *local, struct rxrpc_sock *rx,
+				   const struct rxrpc_security **_sec,
+				   struct key **_key,
+				   struct sk_buff *skb)
 {
 	const struct rxrpc_security *sec;
-	struct rxrpc_local *local = conn->params.local;
-	struct rxrpc_sock *rx;
-	struct key *key;
-	key_ref_t kref;
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	key_ref_t kref = NULL;
 	char kdesc[5 + 1 + 3 + 1];
 
 	_enter("");
 
-	sprintf(kdesc, "%u:%u", conn->service_id, conn->security_ix);
+	sprintf(kdesc, "%u:%u", sp->hdr.serviceId, sp->hdr.securityIndex);
 
-	sec = rxrpc_security_lookup(conn->security_ix);
+	sec = rxrpc_security_lookup(sp->hdr.securityIndex);
 	if (!sec) {
-		_leave(" = -ENOKEY [lookup]");
-		return -ENOKEY;
+		trace_rxrpc_abort(0, "SVS",
+				  sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
+				  RX_INVALID_OPERATION, EKEYREJECTED);
+		skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
+		skb->priority = RX_INVALID_OPERATION;
+		return false;
 	}
 
-	/* find the service */
-	read_lock(&local->services_lock);
-	rx = rcu_dereference_protected(local->service,
-				       lockdep_is_held(&local->services_lock));
-	if (rx && (rx->srx.srx_service == conn->service_id ||
-		   rx->second_service == conn->service_id))
-		goto found_service;
+	if (sp->hdr.securityIndex == RXRPC_SECURITY_NONE)
+		goto out;
 
-	/* the service appears to have died */
-	read_unlock(&local->services_lock);
-	_leave(" = -ENOENT");
-	return -ENOENT;
-
-found_service:
 	if (!rx->securities) {
-		read_unlock(&local->services_lock);
-		_leave(" = -ENOKEY");
-		return -ENOKEY;
+		trace_rxrpc_abort(0, "SVR",
+				  sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
+				  RX_INVALID_OPERATION, EKEYREJECTED);
+		skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
+		skb->priority = RX_INVALID_OPERATION;
+		return false;
 	}
 
 	/* look through the service's keyring */
 	kref = keyring_search(make_key_ref(rx->securities, 1UL),
 			      &key_type_rxrpc_s, kdesc);
 	if (IS_ERR(kref)) {
-		read_unlock(&local->services_lock);
-		_leave(" = %ld [search]", PTR_ERR(kref));
-		return PTR_ERR(kref);
+		trace_rxrpc_abort(0, "SVK",
+				  sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
+				  sec->no_key_abort, EKEYREJECTED);
+		skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
+		skb->priority = sec->no_key_abort;
+		return false;
 	}
 
-	key = key_ref_to_ptr(kref);
-	read_unlock(&local->services_lock);
-
-	conn->server_key = key;
-	conn->security = sec;
-
-	_leave(" = 0");
-	return 0;
+out:
+	*_sec = sec;
+	*_key = key_ref_to_ptr(kref);
+	return true;
 }
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index f0bdac412a36..732c7ae56afd 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -18,6 +18,21 @@
 #include "ar-internal.h"
 
 /*
+ * Return true if there's sufficient Tx queue space.
+ */
+static bool rxrpc_check_tx_space(struct rxrpc_call *call, rxrpc_seq_t *_tx_win)
+{
+	unsigned int win_size =
+		min_t(unsigned int, call->tx_winsize,
+		      call->cong_cwnd + call->cong_extra);
+	rxrpc_seq_t tx_win = READ_ONCE(call->tx_hard_ack);
+
+	if (_tx_win)
+		*_tx_win = tx_win;
+	return call->tx_top - tx_win < win_size;
+}
+
+/*
  * Wait for space to appear in the Tx queue or a signal to occur.
  */
 static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx,
@@ -26,9 +41,7 @@ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx,
 {
 	for (;;) {
 		set_current_state(TASK_INTERRUPTIBLE);
-		if (call->tx_top - call->tx_hard_ack <
-		    min_t(unsigned int, call->tx_winsize,
-			  call->cong_cwnd + call->cong_extra))
+		if (rxrpc_check_tx_space(call, NULL))
 			return 0;
 
 		if (call->state >= RXRPC_CALL_COMPLETE)
@@ -49,40 +62,36 @@ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx,
  * Wait for space to appear in the Tx queue uninterruptibly, but with
  * a timeout of 2*RTT if no progress was made and a signal occurred.
  */
-static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx,
+static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx,
 					    struct rxrpc_call *call)
 {
 	rxrpc_seq_t tx_start, tx_win;
-	signed long rtt2, timeout;
-	u64 rtt;
+	signed long rtt, timeout;
 
-	rtt = READ_ONCE(call->peer->rtt);
-	rtt2 = nsecs_to_jiffies64(rtt) * 2;
-	if (rtt2 < 1)
-		rtt2 = 1;
+	rtt = READ_ONCE(call->peer->srtt_us) >> 3;
+	rtt = usecs_to_jiffies(rtt) * 2;
+	if (rtt < 2)
+		rtt = 2;
 
-	timeout = rtt2;
+	timeout = rtt;
 	tx_start = READ_ONCE(call->tx_hard_ack);
 
 	for (;;) {
 		set_current_state(TASK_UNINTERRUPTIBLE);
 
 		tx_win = READ_ONCE(call->tx_hard_ack);
-		if (call->tx_top - tx_win <
-		    min_t(unsigned int, call->tx_winsize,
-			  call->cong_cwnd + call->cong_extra))
+		if (rxrpc_check_tx_space(call, &tx_win))
 			return 0;
 
 		if (call->state >= RXRPC_CALL_COMPLETE)
 			return call->error;
 
-		if (test_bit(RXRPC_CALL_IS_INTR, &call->flags) &&
-		    timeout == 0 &&
+		if (timeout == 0 &&
 		    tx_win == tx_start && signal_pending(current))
 			return -EINTR;
 
 		if (tx_win != tx_start) {
-			timeout = rtt2;
+			timeout = rtt;
 			tx_start = tx_win;
 		}
 
@@ -92,6 +101,26 @@ static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx,
 }
 
 /*
+ * Wait for space to appear in the Tx queue uninterruptibly.
+ */
+static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx,
+					    struct rxrpc_call *call,
+					    long *timeo)
+{
+	for (;;) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		if (rxrpc_check_tx_space(call, NULL))
+			return 0;
+
+		if (call->state >= RXRPC_CALL_COMPLETE)
+			return call->error;
+
+		trace_rxrpc_transmit(call, rxrpc_transmit_wait);
+		*timeo = schedule_timeout(*timeo);
+	}
+}
+
+/*
  * wait for space to appear in the transmit/ACK window
  * - caller holds the socket locked
  */
@@ -108,10 +137,19 @@ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx,
 
 	add_wait_queue(&call->waitq, &myself);
 
-	if (waitall)
-		ret = rxrpc_wait_for_tx_window_nonintr(rx, call);
-	else
-		ret = rxrpc_wait_for_tx_window_intr(rx, call, timeo);
+	switch (call->interruptibility) {
+	case RXRPC_INTERRUPTIBLE:
+		if (waitall)
+			ret = rxrpc_wait_for_tx_window_waitall(rx, call);
+		else
+			ret = rxrpc_wait_for_tx_window_intr(rx, call, timeo);
+		break;
+	case RXRPC_PREINTERRUPTIBLE:
+	case RXRPC_UNINTERRUPTIBLE:
+	default:
+		ret = rxrpc_wait_for_tx_window_nonintr(rx, call, timeo);
+		break;
+	}
 
 	remove_wait_queue(&call->waitq, &myself);
 	set_current_state(TASK_RUNNING);
@@ -232,16 +270,9 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,
 		_debug("need instant resend %d", ret);
 		rxrpc_instant_resend(call, ix);
 	} else {
-		unsigned long now = jiffies, resend_at;
+		unsigned long now = jiffies;
+		unsigned long resend_at = now + call->peer->rto_j;
 
-		if (call->peer->rtt_usage > 1)
-			resend_at = nsecs_to_jiffies(call->peer->rtt * 3 / 2);
-		else
-			resend_at = rxrpc_resend_timeout;
-		if (resend_at < 1)
-			resend_at = 1;
-
-		resend_at += now;
 		WRITE_ONCE(call->resend_at, resend_at);
 		rxrpc_reduce_call_timer(call, resend_at, now,
 					rxrpc_timer_set_for_send);
@@ -275,7 +306,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 	/* this should be in poll */
 	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
-	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
+	if (sk->sk_shutdown & SEND_SHUTDOWN)
 		return -EPIPE;
 
 	more = msg->msg_flags & MSG_MORE;
@@ -302,9 +333,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 
 			_debug("alloc");
 
-			if (call->tx_top - call->tx_hard_ack >=
-			    min_t(unsigned int, call->tx_winsize,
-				  call->cong_cwnd + call->cong_extra)) {
+			if (!rxrpc_check_tx_space(call, NULL)) {
 				ret = -EAGAIN;
 				if (msg->msg_flags & MSG_DONTWAIT)
 					goto maybe_error;
@@ -618,7 +647,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 		.call.tx_total_len	= -1,
 		.call.user_call_ID	= 0,
 		.call.nr_timeouts	= 0,
-		.call.intr		= true,
+		.call.interruptibility	= RXRPC_INTERRUPTIBLE,
 		.abort_code		= 0,
 		.command		= RXRPC_CMD_SEND_DATA,
 		.exclusive		= false,
@@ -653,6 +682,9 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 		if (IS_ERR(call))
 			return PTR_ERR(call);
 		/* ... and we have the call lock. */
+		ret = 0;
+		if (READ_ONCE(call->state) == RXRPC_CALL_COMPLETE)
+			goto out_put_unlock;
 	} else {
 		switch (READ_ONCE(call->state)) {
 		case RXRPC_CALL_UNINITIALISED:
diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c
index 1e3fa67d91aa..265a38bc5ce1 100644
--- a/net/rxrpc/sysctl.c
+++ b/net/rxrpc/sysctl.c
@@ -72,15 +72,6 @@ static struct ctl_table rxrpc_sysctl_table[] = {
 		.extra1		= (void *)&one_jiffy,
 		.extra2		= (void *)&max_jiffies,
 	},
-	{
-		.procname	= "resend_timeout",
-		.data		= &rxrpc_resend_timeout,
-		.maxlen		= sizeof(unsigned long),
-		.mode		= 0644,
-		.proc_handler	= proc_doulongvec_ms_jiffies_minmax,
-		.extra1		= (void *)&one_jiffy,
-		.extra2		= (void *)&max_jiffies,
-	},
 
 	/* Non-time values */
 	{
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 2b43cacf82af..1a8f2f85ea1a 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -43,17 +43,20 @@ static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a,
 	tcf_lastuse_update(&ca->tcf_tm);
 	bstats_update(&ca->tcf_bstats, skb);
 
-	if (skb->protocol == htons(ETH_P_IP)) {
+	switch (skb_protocol(skb, true)) {
+	case htons(ETH_P_IP):
 		if (skb->len < sizeof(struct iphdr))
 			goto out;
 
 		proto = NFPROTO_IPV4;
-	} else if (skb->protocol == htons(ETH_P_IPV6)) {
+		break;
+	case htons(ETH_P_IPV6):
 		if (skb->len < sizeof(struct ipv6hdr))
 			goto out;
 
 		proto = NFPROTO_IPV6;
-	} else {
+		break;
+	default:
 		goto out;
 	}
 
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index d3cfad88dc3a..428b1ae00123 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -587,7 +587,7 @@ static int tcf_csum_act(struct sk_buff *skb, const struct tc_action *a,
 		goto drop;
 
 	update_flags = params->update_flags;
-	protocol = tc_skb_protocol(skb);
+	protocol = skb_protocol(skb, false);
 again:
 	switch (protocol) {
 	case cpu_to_be16(ETH_P_IP):
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 3a31e241c647..a0cfb4793c93 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -536,6 +536,9 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	}
 
 	ife = to_ife(*a);
+	if (ret == ACT_P_CREATED)
+		INIT_LIST_HEAD(&ife->metalist);
+
 	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
 	if (err < 0)
 		goto release_idr;
@@ -565,10 +568,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 		p->eth_type = ife_type;
 	}
 
-
-	if (ret == ACT_P_CREATED)
-		INIT_LIST_HEAD(&ife->metalist);
-
 	if (tb[TCA_IFE_METALST]) {
 		err = nla_parse_nested_deprecated(tb2, IFE_META_MAX,
 						  tb[TCA_IFE_METALST], NULL,
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 394db3cb55c2..a82400f219f3 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -272,10 +272,8 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a,
 
 	/* mirror is always swallowed */
 	if (is_redirect) {
-		skb2->tc_redirected = 1;
-		skb2->tc_from_ingress = skb2->tc_at_ingress;
-		if (skb2->tc_from_ingress)
-			skb2->tstamp = 0;
+		skb_set_redirected(skb2, skb2->tc_at_ingress);
+
 		/* let's the caller reinsert the packet, if possible */
 		if (use_reinsert) {
 			res->ingress = want_ingress;
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 6a8d3337c577..f98b2791ecec 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -41,7 +41,7 @@ static int tcf_skbedit_act(struct sk_buff *skb, const struct tc_action *a,
 	if (params->flags & SKBEDIT_F_INHERITDSFIELD) {
 		int wlen = skb_network_offset(skb);
 
-		switch (tc_skb_protocol(skb)) {
+		switch (skb_protocol(skb, true)) {
 		case htons(ETH_P_IP):
 			wlen += sizeof(struct iphdr);
 			if (!pskb_may_pull(skb, wlen))
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 545d283b157f..2b94d6f02dbb 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1727,7 +1727,7 @@ int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 reclassify:
 #endif
 	for (; tp; tp = rcu_dereference_bh(tp->next)) {
-		__be16 protocol = tc_skb_protocol(skb);
+		__be16 protocol = skb_protocol(skb, false);
 		int err;
 
 		if (tp->protocol != protocol &&
@@ -2149,6 +2149,7 @@ replay:
 		err = PTR_ERR(block);
 		goto errout;
 	}
+	block->classid = parent;
 
 	chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
 	if (chain_index > TC_ACT_EXT_VAL_MASK) {
@@ -2199,9 +2200,8 @@ replay:
 							       &chain_info));
 
 		mutex_unlock(&chain->filter_chain_lock);
-		tp_new = tcf_proto_create(nla_data(tca[TCA_KIND]),
-					  protocol, prio, chain, rtnl_held,
-					  extack);
+		tp_new = tcf_proto_create(name, protocol, prio, chain,
+					  rtnl_held, extack);
 		if (IS_ERR(tp_new)) {
 			err = PTR_ERR(tp_new);
 			goto errout_tp;
@@ -2692,12 +2692,10 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 			return skb->len;
 
 		parent = tcm->tcm_parent;
-		if (!parent) {
+		if (!parent)
 			q = dev->qdisc;
-			parent = q->handle;
-		} else {
+		else
 			q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent));
-		}
 		if (!q)
 			goto out;
 		cops = q->ops->cl_ops;
@@ -2713,6 +2711,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 		block = cops->tcf_block(q, cl, NULL);
 		if (!block)
 			goto out;
+		parent = block->classid;
 		if (tcf_block_shared(block))
 			q = NULL;
 	}
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index 4aafbe3d435c..f256a7c69093 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -263,12 +263,17 @@ skip:
 	}
 }
 
-static void basic_bind_class(void *fh, u32 classid, unsigned long cl)
+static void basic_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+			     unsigned long base)
 {
 	struct basic_filter *f = fh;
 
-	if (f && f->res.classid == classid)
-		f->res.class = cl;
+	if (f && f->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &f->res, base);
+		else
+			__tcf_unbind_filter(q, &f->res);
+	}
 }
 
 static int basic_dump(struct net *net, struct tcf_proto *tp, void *fh,
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 691f71830134..64d8a219bf3c 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -625,12 +625,17 @@ nla_put_failure:
 	return -1;
 }
 
-static void cls_bpf_bind_class(void *fh, u32 classid, unsigned long cl)
+static void cls_bpf_bind_class(void *fh, u32 classid, unsigned long cl,
+			       void *q, unsigned long base)
 {
 	struct cls_bpf_prog *prog = fh;
 
-	if (prog && prog->res.classid == classid)
-		prog->res.class = cl;
+	if (prog && prog->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &prog->res, base);
+		else
+			__tcf_unbind_filter(q, &prog->res);
+	}
 }
 
 static void cls_bpf_walk(struct tcf_proto *tp, struct tcf_walker *arg,
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 80ae7b9fa90a..ab53a93b2f2b 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -80,7 +80,7 @@ static u32 flow_get_dst(const struct sk_buff *skb, const struct flow_keys *flow)
 	if (dst)
 		return ntohl(dst);
 
-	return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb);
+	return addr_fold(skb_dst(skb)) ^ (__force u16)skb_protocol(skb, true);
 }
 
 static u32 flow_get_proto(const struct sk_buff *skb,
@@ -104,7 +104,7 @@ static u32 flow_get_proto_dst(const struct sk_buff *skb,
 	if (flow->ports.ports)
 		return ntohs(flow->ports.dst);
 
-	return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb);
+	return addr_fold(skb_dst(skb)) ^ (__force u16)skb_protocol(skb, true);
 }
 
 static u32 flow_get_iif(const struct sk_buff *skb)
@@ -151,7 +151,7 @@ static u32 flow_get_nfct(const struct sk_buff *skb)
 static u32 flow_get_nfct_src(const struct sk_buff *skb,
 			     const struct flow_keys *flow)
 {
-	switch (tc_skb_protocol(skb)) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
 		return ntohl(CTTUPLE(skb, src.u3.ip));
 	case htons(ETH_P_IPV6):
@@ -164,7 +164,7 @@ fallback:
 static u32 flow_get_nfct_dst(const struct sk_buff *skb,
 			     const struct flow_keys *flow)
 {
-	switch (tc_skb_protocol(skb)) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
 		return ntohl(CTTUPLE(skb, dst.u3.ip));
 	case htons(ETH_P_IPV6):
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index eedd5786c084..5e112f9e6078 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -282,13 +282,14 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 	struct fl_flow_key skb_mkey;
 
 	list_for_each_entry_rcu(mask, &head->masks, list) {
+		flow_dissector_init_keys(&skb_key.control, &skb_key.basic);
 		fl_clear_masked_range(&skb_key, mask);
 
 		skb_key.indev_ifindex = skb->skb_iif;
 		/* skb_flow_dissect() does not set n_proto in case an unknown
 		 * protocol, so do it rather here.
 		 */
-		skb_key.basic.n_proto = skb->protocol;
+		skb_key.basic.n_proto = skb_protocol(skb, false);
 		skb_flow_dissect_tunnel_info(skb, &mask->dissector, &skb_key);
 		skb_flow_dissect(skb, &mask->dissector, &skb_key, 0);
 
@@ -704,6 +705,7 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
 	[TCA_FLOWER_KEY_ENC_IP_TTL_MASK] = { .type = NLA_U8 },
 	[TCA_FLOWER_KEY_ENC_OPTS]	= { .type = NLA_NESTED },
 	[TCA_FLOWER_KEY_ENC_OPTS_MASK]	= { .type = NLA_NESTED },
+	[TCA_FLOWER_FLAGS]		= { .type = NLA_U32 },
 };
 
 static const struct nla_policy
@@ -2402,12 +2404,17 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static void fl_bind_class(void *fh, u32 classid, unsigned long cl)
+static void fl_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+			  unsigned long base)
 {
 	struct cls_fl_filter *f = fh;
 
-	if (f && f->res.classid == classid)
-		f->res.class = cl;
+	if (f && f->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &f->res, base);
+		else
+			__tcf_unbind_filter(q, &f->res);
+	}
 }
 
 static struct tcf_proto_ops cls_fl_ops __read_mostly = {
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index 4dab833f66cb..b6c36d60ffae 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -432,12 +432,17 @@ nla_put_failure:
 	return -1;
 }
 
-static void fw_bind_class(void *fh, u32 classid, unsigned long cl)
+static void fw_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+			  unsigned long base)
 {
 	struct fw_filter *f = fh;
 
-	if (f && f->res.classid == classid)
-		f->res.class = cl;
+	if (f && f->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &f->res, base);
+		else
+			__tcf_unbind_filter(q, &f->res);
+	}
 }
 
 static struct tcf_proto_ops cls_fw_ops __read_mostly = {
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 38c0a9f0f296..2a72a061c41b 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -157,6 +157,7 @@ static void *mall_get(struct tcf_proto *tp, u32 handle)
 static const struct nla_policy mall_policy[TCA_MATCHALL_MAX + 1] = {
 	[TCA_MATCHALL_UNSPEC]		= { .type = NLA_UNSPEC },
 	[TCA_MATCHALL_CLASSID]		= { .type = NLA_U32 },
+	[TCA_MATCHALL_FLAGS]		= { .type = NLA_U32 },
 };
 
 static int mall_set_parms(struct net *net, struct tcf_proto *tp,
@@ -391,12 +392,17 @@ nla_put_failure:
 	return -1;
 }
 
-static void mall_bind_class(void *fh, u32 classid, unsigned long cl)
+static void mall_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+			    unsigned long base)
 {
 	struct cls_mall_head *head = fh;
 
-	if (head && head->res.classid == classid)
-		head->res.class = cl;
+	if (head && head->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &head->res, base);
+		else
+			__tcf_unbind_filter(q, &head->res);
+	}
 }
 
 static struct tcf_proto_ops cls_mall_ops __read_mostly = {
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 2d9e0b4484ea..5efa3e7ace15 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -534,8 +534,8 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
 			fp = &b->ht[h];
 			for (pfp = rtnl_dereference(*fp); pfp;
 			     fp = &pfp->next, pfp = rtnl_dereference(*fp)) {
-				if (pfp == f) {
-					*fp = f->next;
+				if (pfp == fold) {
+					rcu_assign_pointer(*fp, fold->next);
 					break;
 				}
 			}
@@ -641,12 +641,17 @@ nla_put_failure:
 	return -1;
 }
 
-static void route4_bind_class(void *fh, u32 classid, unsigned long cl)
+static void route4_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+			      unsigned long base)
 {
 	struct route4_filter *f = fh;
 
-	if (f && f->res.classid == classid)
-		f->res.class = cl;
+	if (f && f->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &f->res, base);
+		else
+			__tcf_unbind_filter(q, &f->res);
+	}
 }
 
 static struct tcf_proto_ops cls_route4_ops __read_mostly = {
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index 2f3c03b25d5d..d36949d9382c 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -463,10 +463,8 @@ static u32 gen_tunnel(struct rsvp_head *data)
 
 static const struct nla_policy rsvp_policy[TCA_RSVP_MAX + 1] = {
 	[TCA_RSVP_CLASSID]	= { .type = NLA_U32 },
-	[TCA_RSVP_DST]		= { .type = NLA_BINARY,
-				    .len = RSVP_DST_LEN * sizeof(u32) },
-	[TCA_RSVP_SRC]		= { .type = NLA_BINARY,
-				    .len = RSVP_DST_LEN * sizeof(u32) },
+	[TCA_RSVP_DST]		= { .len = RSVP_DST_LEN * sizeof(u32) },
+	[TCA_RSVP_SRC]		= { .len = RSVP_DST_LEN * sizeof(u32) },
 	[TCA_RSVP_PINFO]	= { .len = sizeof(struct tc_rsvp_pinfo) },
 };
 
@@ -738,12 +736,17 @@ nla_put_failure:
 	return -1;
 }
 
-static void rsvp_bind_class(void *fh, u32 classid, unsigned long cl)
+static void rsvp_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+			    unsigned long base)
 {
 	struct rsvp_filter *f = fh;
 
-	if (f && f->res.classid == classid)
-		f->res.class = cl;
+	if (f && f->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &f->res, base);
+		else
+			__tcf_unbind_filter(q, &f->res);
+	}
 }
 
 static struct tcf_proto_ops RSVP_OPS __read_mostly = {
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index e573e5a5c794..61e95029c18f 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -11,6 +11,7 @@
 #include <linux/skbuff.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
+#include <linux/refcount.h>
 #include <net/act_api.h>
 #include <net/netlink.h>
 #include <net/pkt_cls.h>
@@ -26,9 +27,12 @@
 #define DEFAULT_HASH_SIZE	64	/* optimized for diffserv */
 
 
+struct tcindex_data;
+
 struct tcindex_filter_result {
 	struct tcf_exts		exts;
 	struct tcf_result	res;
+	struct tcindex_data	*p;
 	struct rcu_work		rwork;
 };
 
@@ -49,6 +53,7 @@ struct tcindex_data {
 	u32 hash;		/* hash table size; 0 if undefined */
 	u32 alloc_hash;		/* allocated size */
 	u32 fall_through;	/* 0: only classify if explicit match */
+	refcount_t refcnt;	/* a temporary refcnt for perfect hash */
 	struct rcu_work rwork;
 };
 
@@ -57,6 +62,20 @@ static inline int tcindex_filter_is_set(struct tcindex_filter_result *r)
 	return tcf_exts_has_actions(&r->exts) || r->res.classid;
 }
 
+static void tcindex_data_get(struct tcindex_data *p)
+{
+	refcount_inc(&p->refcnt);
+}
+
+static void tcindex_data_put(struct tcindex_data *p)
+{
+	if (refcount_dec_and_test(&p->refcnt)) {
+		kfree(p->perfect);
+		kfree(p->h);
+		kfree(p);
+	}
+}
+
 static struct tcindex_filter_result *tcindex_lookup(struct tcindex_data *p,
 						    u16 key)
 {
@@ -132,6 +151,7 @@ static int tcindex_init(struct tcf_proto *tp)
 	p->mask = 0xffff;
 	p->hash = DEFAULT_HASH_SIZE;
 	p->fall_through = 1;
+	refcount_set(&p->refcnt, 1); /* Paired with tcindex_destroy_work() */
 
 	rcu_assign_pointer(tp->root, p);
 	return 0;
@@ -141,6 +161,7 @@ static void __tcindex_destroy_rexts(struct tcindex_filter_result *r)
 {
 	tcf_exts_destroy(&r->exts);
 	tcf_exts_put_net(&r->exts);
+	tcindex_data_put(r->p);
 }
 
 static void tcindex_destroy_rexts_work(struct work_struct *work)
@@ -212,6 +233,8 @@ found:
 		else
 			__tcindex_destroy_fexts(f);
 	} else {
+		tcindex_data_get(p);
+
 		if (tcf_exts_get_net(&r->exts))
 			tcf_queue_work(&r->rwork, tcindex_destroy_rexts_work);
 		else
@@ -228,9 +251,7 @@ static void tcindex_destroy_work(struct work_struct *work)
 					      struct tcindex_data,
 					      rwork);
 
-	kfree(p->perfect);
-	kfree(p->h);
-	kfree(p);
+	tcindex_data_put(p);
 }
 
 static inline int
@@ -248,9 +269,11 @@ static const struct nla_policy tcindex_policy[TCA_TCINDEX_MAX + 1] = {
 };
 
 static int tcindex_filter_result_init(struct tcindex_filter_result *r,
+				      struct tcindex_data *p,
 				      struct net *net)
 {
 	memset(r, 0, sizeof(*r));
+	r->p = p;
 	return tcf_exts_init(&r->exts, net, TCA_TCINDEX_ACT,
 			     TCA_TCINDEX_POLICE);
 }
@@ -261,8 +284,10 @@ static void tcindex_partial_destroy_work(struct work_struct *work)
 					      struct tcindex_data,
 					      rwork);
 
+	rtnl_lock();
 	kfree(p->perfect);
 	kfree(p);
+	rtnl_unlock();
 }
 
 static void tcindex_free_perfect_hash(struct tcindex_data *cp)
@@ -288,6 +313,7 @@ static int tcindex_alloc_perfect_hash(struct net *net, struct tcindex_data *cp)
 				    TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
 		if (err < 0)
 			goto errout;
+		cp->perfect[i].p = cp;
 	}
 
 	return 0;
@@ -332,33 +358,45 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	cp->alloc_hash = p->alloc_hash;
 	cp->fall_through = p->fall_through;
 	cp->tp = tp;
+	refcount_set(&cp->refcnt, 1); /* Paired with tcindex_destroy_work() */
+
+	if (tb[TCA_TCINDEX_HASH])
+		cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]);
+
+	if (tb[TCA_TCINDEX_MASK])
+		cp->mask = nla_get_u16(tb[TCA_TCINDEX_MASK]);
+
+	if (tb[TCA_TCINDEX_SHIFT])
+		cp->shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]);
+
+	if (!cp->hash) {
+		/* Hash not specified, use perfect hash if the upper limit
+		 * of the hashing index is below the threshold.
+		 */
+		if ((cp->mask >> cp->shift) < PERFECT_HASH_THRESHOLD)
+			cp->hash = (cp->mask >> cp->shift) + 1;
+		else
+			cp->hash = DEFAULT_HASH_SIZE;
+	}
 
 	if (p->perfect) {
 		int i;
 
 		if (tcindex_alloc_perfect_hash(net, cp) < 0)
 			goto errout;
-		for (i = 0; i < cp->hash; i++)
+		cp->alloc_hash = cp->hash;
+		for (i = 0; i < min(cp->hash, p->hash); i++)
 			cp->perfect[i].res = p->perfect[i].res;
 		balloc = 1;
 	}
 	cp->h = p->h;
 
-	err = tcindex_filter_result_init(&new_filter_result, net);
+	err = tcindex_filter_result_init(&new_filter_result, cp, net);
 	if (err < 0)
-		goto errout1;
+		goto errout_alloc;
 	if (old_r)
 		cr = r->res;
 
-	if (tb[TCA_TCINDEX_HASH])
-		cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]);
-
-	if (tb[TCA_TCINDEX_MASK])
-		cp->mask = nla_get_u16(tb[TCA_TCINDEX_MASK]);
-
-	if (tb[TCA_TCINDEX_SHIFT])
-		cp->shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]);
-
 	err = -EBUSY;
 
 	/* Hash already allocated, make sure that we still meet the
@@ -376,16 +414,6 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	if (tb[TCA_TCINDEX_FALL_THROUGH])
 		cp->fall_through = nla_get_u32(tb[TCA_TCINDEX_FALL_THROUGH]);
 
-	if (!cp->hash) {
-		/* Hash not specified, use perfect hash if the upper limit
-		 * of the hashing index is below the threshold.
-		 */
-		if ((cp->mask >> cp->shift) < PERFECT_HASH_THRESHOLD)
-			cp->hash = (cp->mask >> cp->shift) + 1;
-		else
-			cp->hash = DEFAULT_HASH_SIZE;
-	}
-
 	if (!cp->perfect && !cp->h)
 		cp->alloc_hash = cp->hash;
 
@@ -431,7 +459,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 			goto errout_alloc;
 		f->key = handle;
 		f->next = NULL;
-		err = tcindex_filter_result_init(&f->result, net);
+		err = tcindex_filter_result_init(&f->result, cp, net);
 		if (err < 0) {
 			kfree(f);
 			goto errout_alloc;
@@ -444,7 +472,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	}
 
 	if (old_r && old_r != r) {
-		err = tcindex_filter_result_init(old_r, net);
+		err = tcindex_filter_result_init(old_r, cp, net);
 		if (err < 0) {
 			kfree(f);
 			goto errout_alloc;
@@ -484,7 +512,6 @@ errout_alloc:
 		tcindex_free_perfect_hash(cp);
 	else if (balloc == 2)
 		kfree(cp->h);
-errout1:
 	tcf_exts_destroy(&new_filter_result.exts);
 errout:
 	kfree(cp);
@@ -569,6 +596,14 @@ static void tcindex_destroy(struct tcf_proto *tp, bool rtnl_held,
 		for (i = 0; i < p->hash; i++) {
 			struct tcindex_filter_result *r = p->perfect + i;
 
+			/* tcf_queue_work() does not guarantee the ordering we
+			 * want, so we have to take this refcnt temporarily to
+			 * ensure 'p' is freed after all tcindex_filter_result
+			 * here. Imperfect hash does not need this, because it
+			 * uses linked lists rather than an array.
+			 */
+			tcindex_data_get(p);
+
 			tcf_unbind_filter(tp, &r->res);
 			if (tcf_exts_get_net(&r->exts))
 				tcf_queue_work(&r->rwork,
@@ -654,12 +689,17 @@ nla_put_failure:
 	return -1;
 }
 
-static void tcindex_bind_class(void *fh, u32 classid, unsigned long cl)
+static void tcindex_bind_class(void *fh, u32 classid, unsigned long cl,
+			       void *q, unsigned long base)
 {
 	struct tcindex_filter_result *r = fh;
 
-	if (r && r->res.classid == classid)
-		r->res.class = cl;
+	if (r && r->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &r->res, base);
+		else
+			__tcf_unbind_filter(q, &r->res);
+	}
 }
 
 static struct tcf_proto_ops cls_tcindex_ops __read_mostly = {
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index c7727de5e073..0443ac3ecf1e 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -1271,12 +1271,17 @@ static int u32_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
 	return 0;
 }
 
-static void u32_bind_class(void *fh, u32 classid, unsigned long cl)
+static void u32_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+			   unsigned long base)
 {
 	struct tc_u_knode *n = fh;
 
-	if (n && n->res.classid == classid)
-		n->res.class = cl;
+	if (n && n->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &n->res, base);
+		else
+			__tcf_unbind_filter(q, &n->res);
+	}
 }
 
 static int u32_dump(struct net *net, struct tcf_proto *tp, void *fh,
diff --git a/net/sched/em_ipset.c b/net/sched/em_ipset.c
index df00566d327d..c95cf86fb431 100644
--- a/net/sched/em_ipset.c
+++ b/net/sched/em_ipset.c
@@ -59,7 +59,7 @@ static int em_ipset_match(struct sk_buff *skb, struct tcf_ematch *em,
 	};
 	int ret, network_offset;
 
-	switch (tc_skb_protocol(skb)) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
 		state.pf = NFPROTO_IPV4;
 		if (!pskb_network_may_pull(skb, sizeof(struct iphdr)))
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index 82bd14e7ac93..8de4968177bd 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -195,7 +195,7 @@ META_COLLECTOR(int_priority)
 META_COLLECTOR(int_protocol)
 {
 	/* Let userspace take care of the byte ordering */
-	dst->value = tc_skb_protocol(skb);
+	dst->value = skb_protocol(skb, false);
 }
 
 META_COLLECTOR(int_pkttype)
@@ -446,7 +446,7 @@ META_COLLECTOR(int_sk_wmem_queued)
 		*err = -1;
 		return;
 	}
-	dst->value = sk->sk_wmem_queued;
+	dst->value = READ_ONCE(sk->sk_wmem_queued);
 }
 
 META_COLLECTOR(int_sk_fwd_alloc)
diff --git a/net/sched/ematch.c b/net/sched/ematch.c
index 8f2ad706784d..dd3b8c11a2e0 100644
--- a/net/sched/ematch.c
+++ b/net/sched/ematch.c
@@ -238,6 +238,9 @@ static int tcf_em_validate(struct tcf_proto *tp,
 			goto errout;
 
 		if (em->ops->change) {
+			err = -EINVAL;
+			if (em_hdr->flags & TCF_EM_SIMPLE)
+				goto errout;
 			err = em->ops->change(net, data, data_len, em);
 			if (err < 0)
 				goto errout;
@@ -263,12 +266,12 @@ static int tcf_em_validate(struct tcf_proto *tp,
 				}
 				em->data = (unsigned long) v;
 			}
+			em->datalen = data_len;
 		}
 	}
 
 	em->matchid = em_hdr->matchid;
 	em->flags = em_hdr->flags;
-	em->datalen = data_len;
 	em->net = net;
 
 	err = 0;
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 1047825d9f48..50794125bf02 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1891,8 +1891,9 @@ static int tclass_del_notify(struct net *net,
 
 struct tcf_bind_args {
 	struct tcf_walker w;
-	u32 classid;
+	unsigned long base;
 	unsigned long cl;
+	u32 classid;
 };
 
 static int tcf_node_bind(struct tcf_proto *tp, void *n, struct tcf_walker *arg)
@@ -1903,28 +1904,30 @@ static int tcf_node_bind(struct tcf_proto *tp, void *n, struct tcf_walker *arg)
 		struct Qdisc *q = tcf_block_q(tp->chain->block);
 
 		sch_tree_lock(q);
-		tp->ops->bind_class(n, a->classid, a->cl);
+		tp->ops->bind_class(n, a->classid, a->cl, q, a->base);
 		sch_tree_unlock(q);
 	}
 	return 0;
 }
 
-static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid,
-			   unsigned long new_cl)
+struct tc_bind_class_args {
+	struct qdisc_walker w;
+	unsigned long new_cl;
+	u32 portid;
+	u32 clid;
+};
+
+static int tc_bind_class_walker(struct Qdisc *q, unsigned long cl,
+				struct qdisc_walker *w)
 {
+	struct tc_bind_class_args *a = (struct tc_bind_class_args *)w;
 	const struct Qdisc_class_ops *cops = q->ops->cl_ops;
 	struct tcf_block *block;
 	struct tcf_chain *chain;
-	unsigned long cl;
 
-	cl = cops->find(q, portid);
-	if (!cl)
-		return;
-	if (!cops->tcf_block)
-		return;
 	block = cops->tcf_block(q, cl, NULL);
 	if (!block)
-		return;
+		return 0;
 	for (chain = tcf_get_next_chain(block, NULL);
 	     chain;
 	     chain = tcf_get_next_chain(block, chain)) {
@@ -1935,11 +1938,29 @@ static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid,
 			struct tcf_bind_args arg = {};
 
 			arg.w.fn = tcf_node_bind;
-			arg.classid = clid;
-			arg.cl = new_cl;
+			arg.classid = a->clid;
+			arg.base = cl;
+			arg.cl = a->new_cl;
 			tp->ops->walk(tp, &arg.w, true);
 		}
 	}
+
+	return 0;
+}
+
+static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid,
+			   unsigned long new_cl)
+{
+	const struct Qdisc_class_ops *cops = q->ops->cl_ops;
+	struct tc_bind_class_args args = {};
+
+	if (!cops->tcf_block)
+		return;
+	args.portid = portid;
+	args.clid = clid;
+	args.new_cl = new_cl;
+	args.w.fn = tc_bind_class_walker;
+	q->ops->cl_ops->walk(q, &args.w);
 }
 
 #else
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index f4f9b8cdbffb..6385995dc700 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -553,16 +553,16 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt,
 	if (!p->link.q)
 		p->link.q = &noop_qdisc;
 	pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q);
+	p->link.vcc = NULL;
+	p->link.sock = NULL;
+	p->link.common.classid = sch->handle;
+	p->link.ref = 1;
 
 	err = tcf_block_get(&p->link.block, &p->link.filter_list, sch,
 			    extack);
 	if (err)
 		return err;
 
-	p->link.vcc = NULL;
-	p->link.sock = NULL;
-	p->link.common.classid = sch->handle;
-	p->link.ref = 1;
 	tasklet_init(&p->task, sch_atm_dequeue, (unsigned long)sch);
 	return 0;
 }
diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 53a80bc6b13a..896c0562cb42 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -592,7 +592,7 @@ static void cake_update_flowkeys(struct flow_keys *keys,
 	struct nf_conntrack_tuple tuple = {};
 	bool rev = !skb->_nfct;
 
-	if (tc_skb_protocol(skb) != htons(ETH_P_IP))
+	if (skb_protocol(skb, true) != htons(ETH_P_IP))
 		return;
 
 	if (!nf_ct_get_tuple_skb(&tuple, skb))
@@ -1515,32 +1515,51 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free)
 	return idx + (tin << 16);
 }
 
-static u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash)
+static u8 cake_handle_diffserv(struct sk_buff *skb, bool wash)
 {
-	int wlen = skb_network_offset(skb);
+	const int offset = skb_network_offset(skb);
+	u16 *buf, buf_;
 	u8 dscp;
 
-	switch (tc_skb_protocol(skb)) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
-		wlen += sizeof(struct iphdr);
-		if (!pskb_may_pull(skb, wlen) ||
-		    skb_try_make_writable(skb, wlen))
+		buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_);
+		if (unlikely(!buf))
 			return 0;
 
-		dscp = ipv4_get_dsfield(ip_hdr(skb)) >> 2;
-		if (wash && dscp)
+		/* ToS is in the second byte of iphdr */
+		dscp = ipv4_get_dsfield((struct iphdr *)buf) >> 2;
+
+		if (wash && dscp) {
+			const int wlen = offset + sizeof(struct iphdr);
+
+			if (!pskb_may_pull(skb, wlen) ||
+			    skb_try_make_writable(skb, wlen))
+				return 0;
+
 			ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0);
+		}
+
 		return dscp;
 
 	case htons(ETH_P_IPV6):
-		wlen += sizeof(struct ipv6hdr);
-		if (!pskb_may_pull(skb, wlen) ||
-		    skb_try_make_writable(skb, wlen))
+		buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_);
+		if (unlikely(!buf))
 			return 0;
 
-		dscp = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2;
-		if (wash && dscp)
+		/* Traffic class is in the first and second bytes of ipv6hdr */
+		dscp = ipv6_get_dsfield((struct ipv6hdr *)buf) >> 2;
+
+		if (wash && dscp) {
+			const int wlen = offset + sizeof(struct ipv6hdr);
+
+			if (!pskb_may_pull(skb, wlen) ||
+			    skb_try_make_writable(skb, wlen))
+				return 0;
+
 			ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0);
+		}
+
 		return dscp;
 
 	case htons(ETH_P_ARP):
@@ -1557,14 +1576,17 @@ static struct cake_tin_data *cake_select_tin(struct Qdisc *sch,
 {
 	struct cake_sched_data *q = qdisc_priv(sch);
 	u32 tin, mark;
+	bool wash;
 	u8 dscp;
 
 	/* Tin selection: Default to diffserv-based selection, allow overriding
-	 * using firewall marks or skb->priority.
+	 * using firewall marks or skb->priority. Call DSCP parsing early if
+	 * wash is enabled, otherwise defer to below to skip unneeded parsing.
 	 */
-	dscp = cake_handle_diffserv(skb,
-				    q->rate_flags & CAKE_FLAG_WASH);
 	mark = (skb->mark & q->fwmark_mask) >> q->fwmark_shft;
+	wash = !!(q->rate_flags & CAKE_FLAG_WASH);
+	if (wash)
+		dscp = cake_handle_diffserv(skb, wash);
 
 	if (q->tin_mode == CAKE_DIFFSERV_BESTEFFORT)
 		tin = 0;
@@ -1578,6 +1600,8 @@ static struct cake_tin_data *cake_select_tin(struct Qdisc *sch,
 		tin = q->tin_order[TC_H_MIN(skb->priority) - 1];
 
 	else {
+		if (!wash)
+			dscp = cake_handle_diffserv(skb, wash);
 		tin = q->tin_index[dscp];
 
 		if (unlikely(tin >= q->tin_cnt))
@@ -1769,7 +1793,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 						      q->avg_window_begin));
 			u64 b = q->avg_window_bytes * (u64)NSEC_PER_SEC;
 
-			do_div(b, window_interval);
+			b = div64_u64(b, window_interval);
 			q->avg_peak_bandwidth =
 				cake_ewma(q->avg_peak_bandwidth, b,
 					  b > q->avg_peak_bandwidth ? 2 : 8);
@@ -2184,6 +2208,7 @@ static const struct nla_policy cake_policy[TCA_CAKE_MAX + 1] = {
 	[TCA_CAKE_MPU]		 = { .type = NLA_U32 },
 	[TCA_CAKE_INGRESS]	 = { .type = NLA_U32 },
 	[TCA_CAKE_ACK_FILTER]	 = { .type = NLA_U32 },
+	[TCA_CAKE_SPLIT_GSO]	 = { .type = NLA_U32 },
 	[TCA_CAKE_FWMARK]	 = { .type = NLA_U32 },
 };
 
@@ -2678,7 +2703,7 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt,
 	qdisc_watchdog_init(&q->watchdog, sch);
 
 	if (opt) {
-		int err = cake_change(sch, opt, extack);
+		err = cake_change(sch, opt, extack);
 
 		if (err)
 			return err;
@@ -2995,7 +3020,7 @@ static int cake_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 			PUT_STAT_S32(BLUE_TIMER_US,
 				     ktime_to_us(
 					     ktime_sub(now,
-						     flow->cvars.blue_timer)));
+						       flow->cvars.blue_timer)));
 		}
 		if (flow->cvars.dropping) {
 			PUT_STAT_S32(DROP_NEXT_US,
diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index 284ab2dcf47f..35a860764dfa 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -181,6 +181,11 @@ static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch)
 	s64 credits;
 	int len;
 
+	/* The previous packet is still being sent */
+	if (now < q->last) {
+		qdisc_watchdog_schedule_ns(&q->watchdog, q->last);
+		return NULL;
+	}
 	if (q->credits < 0) {
 		credits = timediff_to_credits(now - q->last, q->idleslope);
 
@@ -212,7 +217,12 @@ static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch)
 	credits += q->credits;
 
 	q->credits = max_t(s64, credits, q->locredit);
-	q->last = now;
+	/* Estimate of the transmission of the last byte of the packet in ns */
+	if (unlikely(atomic64_read(&q->port_rate) == 0))
+		q->last = now;
+	else
+		q->last = now + div64_s64(len * NSEC_PER_SEC,
+					  atomic64_read(&q->port_rate));
 
 	return skb;
 }
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index dba70377bbd9..4021f726b58f 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -323,7 +323,8 @@ static void choke_reset(struct Qdisc *sch)
 
 	sch->q.qlen = 0;
 	sch->qstats.backlog = 0;
-	memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *));
+	if (q->tab)
+		memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *));
 	q->head = q->tail = 0;
 	red_restart(&q->vars);
 }
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 05605b30bef3..2b88710994d7 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -210,7 +210,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	if (p->set_tc_index) {
 		int wlen = skb_network_offset(skb);
 
-		switch (tc_skb_protocol(skb)) {
+		switch (skb_protocol(skb, true)) {
 		case htons(ETH_P_IP):
 			wlen += sizeof(struct iphdr);
 			if (!pskb_may_pull(skb, wlen) ||
@@ -303,7 +303,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
 	index = skb->tc_index & (p->indices - 1);
 	pr_debug("index %d->%d\n", skb->tc_index, index);
 
-	switch (tc_skb_protocol(skb)) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
 		ipv4_change_dsfield(ip_hdr(skb), p->mv[index].mask,
 				    p->mv[index].value);
@@ -320,7 +320,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
 		 */
 		if (p->mv[index].mask != 0xff || p->mv[index].value)
 			pr_warn("%s: unsupported protocol %d\n",
-				__func__, ntohs(tc_skb_protocol(skb)));
+				__func__, ntohs(skb_protocol(skb, true)));
 		break;
 	}
 
diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c
index b244881d2b9a..e7e20a05fc13 100644
--- a/net/sched/sch_etf.c
+++ b/net/sched/sch_etf.c
@@ -77,7 +77,7 @@ static bool is_packet_valid(struct Qdisc *sch, struct sk_buff *nskb)
 	struct sock *sk = nskb->sk;
 	ktime_t now;
 
-	if (!sk)
+	if (!sk || !sk_fullsock(sk))
 		return false;
 
 	if (!sock_flag(sk, SOCK_TXTIME))
@@ -131,8 +131,9 @@ static void report_sock_error(struct sk_buff *skb, u32 err, u8 code)
 	struct sock_exterr_skb *serr;
 	struct sk_buff *clone;
 	ktime_t txtime = skb->tstamp;
+	struct sock *sk = skb->sk;
 
-	if (!skb->sk || !(skb->sk->sk_txtime_report_errors))
+	if (!sk || !sk_fullsock(sk) || !(sk->sk_txtime_report_errors))
 		return;
 
 	clone = skb_clone(skb, GFP_ATOMIC);
@@ -148,7 +149,7 @@ static void report_sock_error(struct sk_buff *skb, u32 err, u8 code)
 	serr->ee.ee_data = (txtime >> 32); /* high part of tstamp */
 	serr->ee.ee_info = txtime; /* low part of tstamp */
 
-	if (sock_queue_err_skb(skb->sk, clone))
+	if (sock_queue_err_skb(sk, clone))
 		kfree_skb(clone);
 }
 
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 78ecdf146882..f757ea90aba6 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -745,6 +745,7 @@ static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = {
 	[TCA_FQ_FLOW_MAX_RATE]		= { .type = NLA_U32 },
 	[TCA_FQ_BUCKETS_LOG]		= { .type = NLA_U32 },
 	[TCA_FQ_FLOW_REFILL_DELAY]	= { .type = NLA_U32 },
+	[TCA_FQ_ORPHAN_MASK]		= { .type = NLA_U32 },
 	[TCA_FQ_LOW_RATE_THRESHOLD]	= { .type = NLA_U32 },
 	[TCA_FQ_CE_THRESHOLD]		= { .type = NLA_U32 },
 };
@@ -787,10 +788,12 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt,
 	if (tb[TCA_FQ_QUANTUM]) {
 		u32 quantum = nla_get_u32(tb[TCA_FQ_QUANTUM]);
 
-		if (quantum > 0)
+		if (quantum > 0 && quantum <= (1 << 20)) {
 			q->quantum = quantum;
-		else
+		} else {
+			NL_SET_ERR_MSG_MOD(extack, "invalid quantum");
 			err = -EINVAL;
+		}
 	}
 
 	if (tb[TCA_FQ_INITIAL_QUANTUM])
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index d59fbcc745d1..23dabff624cb 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -425,7 +425,7 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt,
 		q->quantum = max(256U, nla_get_u32(tb[TCA_FQ_CODEL_QUANTUM]));
 
 	if (tb[TCA_FQ_CODEL_DROP_BATCH_SIZE])
-		q->drop_batch_size = min(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE]));
+		q->drop_batch_size = max(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE]));
 
 	if (tb[TCA_FQ_CODEL_MEMORY_LIMIT])
 		q->memory_limit = min(1U << 31, nla_get_u32(tb[TCA_FQ_CODEL_MEMORY_LIMIT]));
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 17bd8f539bc7..71c836757952 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -469,6 +469,7 @@ void __netdev_watchdog_up(struct net_device *dev)
 			dev_hold(dev);
 	}
 }
+EXPORT_SYMBOL_GPL(__netdev_watchdog_up);
 
 static void dev_watchdog_up(struct net_device *dev)
 {
@@ -657,7 +658,7 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc)
 	if (likely(skb)) {
 		qdisc_update_stats_at_dequeue(qdisc, skb);
 	} else {
-		qdisc->empty = true;
+		WRITE_ONCE(qdisc->empty, true);
 	}
 
 	return skb;
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 18b884cfdfe8..647941702f9f 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -292,8 +292,14 @@ static int prio_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	struct tc_prio_qopt_offload graft_offload;
 	unsigned long band = arg - 1;
 
-	if (new == NULL)
-		new = &noop_qdisc;
+	if (!new) {
+		new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
+					TC_H_MAKE(sch->handle, arg), extack);
+		if (!new)
+			new = &noop_qdisc;
+		else
+			qdisc_hash_add(new, true);
+	}
 
 	*old = qdisc_replace(sch, new, &q->queues[band]);
 
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index c787d4d46017..5a6def5e4e6d 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -637,6 +637,15 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt)
 	if (ctl->divisor &&
 	    (!is_power_of_2(ctl->divisor) || ctl->divisor > 65536))
 		return -EINVAL;
+
+	/* slot->allot is a short, make sure quantum is not too big. */
+	if (ctl->quantum) {
+		unsigned int scaled = SFQ_ALLOT_SIZE(ctl->quantum);
+
+		if (scaled <= 0 || scaled > SHRT_MAX)
+			return -EINVAL;
+	}
+
 	if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max,
 					ctl_v1->Wlog))
 		return -EINVAL;
diff --git a/net/sched/sch_skbprio.c b/net/sched/sch_skbprio.c
index 0fb10abf7579..7a5e4c454715 100644
--- a/net/sched/sch_skbprio.c
+++ b/net/sched/sch_skbprio.c
@@ -169,6 +169,9 @@ static int skbprio_change(struct Qdisc *sch, struct nlattr *opt,
 {
 	struct tc_skbprio_qopt *ctl = nla_data(opt);
 
+	if (opt->nla_len != nla_attr_size(sizeof(*ctl)))
+		return -EINVAL;
+
 	sch->limit = ctl->limit;
 	return 0;
 }
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 49c5379696d8..bc18daa3ba51 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -234,8 +234,10 @@ static struct sk_buff *taprio_dequeue(struct Qdisc *sch)
 		prio = skb->priority;
 		tc = netdev_get_prio_tc_map(dev, prio);
 
-		if (!(gate_mask & BIT(tc)))
+		if (!(gate_mask & BIT(tc))) {
+			skb = NULL;
 			continue;
+		}
 
 		len = qdisc_pkt_len(skb);
 		guard = ktime_add_ns(q->get_time(),
@@ -245,13 +247,17 @@ static struct sk_buff *taprio_dequeue(struct Qdisc *sch)
 		 * guard band ...
 		 */
 		if (gate_mask != TAPRIO_ALL_GATES_OPEN &&
-		    ktime_after(guard, entry->close_time))
+		    ktime_after(guard, entry->close_time)) {
+			skb = NULL;
 			continue;
+		}
 
 		/* ... and no budget. */
 		if (gate_mask != TAPRIO_ALL_GATES_OPEN &&
-		    atomic_sub_return(len, &entry->budget) < 0)
+		    atomic_sub_return(len, &entry->budget) < 0) {
+			skb = NULL;
 			continue;
+		}
 
 		skb = child->ops->dequeue(child);
 		if (unlikely(!skb))
@@ -901,7 +907,7 @@ static void taprio_destroy(struct Qdisc *sch)
 	}
 	q->qdiscs = NULL;
 
-	netdev_set_num_tc(dev, 0);
+	netdev_reset_tc(dev);
 
 	if (q->oper_sched)
 		call_rcu(&q->oper_sched->rcu, taprio_free_sched_cb);
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index 689ef6f3ded8..2f1f0a378408 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -239,7 +239,7 @@ __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res,
 		char haddr[MAX_ADDR_LEN];
 
 		neigh_ha_snapshot(haddr, n, dev);
-		err = dev_hard_header(skb, dev, ntohs(tc_skb_protocol(skb)),
+		err = dev_hard_header(skb, dev, ntohs(skb_protocol(skb, false)),
 				      haddr, NULL, skb->len);
 
 		if (err < 0)
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index bce6221bd083..50bbdd385eaa 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1580,12 +1580,15 @@ void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len)
 int sctp_assoc_set_bind_addr_from_ep(struct sctp_association *asoc,
 				     enum sctp_scope scope, gfp_t gfp)
 {
+	struct sock *sk = asoc->base.sk;
 	int flags;
 
 	/* Use scoping rules to determine the subset of addresses from
 	 * the endpoint.
 	 */
-	flags = (PF_INET6 == asoc->base.sk->sk_family) ? SCTP_ADDR6_ALLOWED : 0;
+	flags = (PF_INET6 == sk->sk_family) ? SCTP_ADDR6_ALLOWED : 0;
+	if (!inet_v6_ipv6only(sk))
+		flags |= SCTP_ADDR4_ALLOWED;
 	if (asoc->peer.ipv4_address)
 		flags |= SCTP_ADDR4_PEERSUPP;
 	if (asoc->peer.ipv6_address)
diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c
index f54333cbbe0f..e86a05d3878d 100644
--- a/net/sctp/bind_addr.c
+++ b/net/sctp/bind_addr.c
@@ -466,6 +466,7 @@ static int sctp_copy_one_addr(struct net *net, struct sctp_bind_addr *dest,
 		 * well as the remote peer.
 		 */
 		if ((((AF_INET == addr->sa.sa_family) &&
+		      (flags & SCTP_ADDR4_ALLOWED) &&
 		      (flags & SCTP_ADDR4_PEERSUPP))) ||
 		    (((AF_INET6 == addr->sa.sa_family) &&
 		      (flags & SCTP_ADDR6_ALLOWED) &&
diff --git a/net/sctp/diag.c b/net/sctp/diag.c
index fc9a4c6629ce..ba9f64fdfd23 100644
--- a/net/sctp/diag.c
+++ b/net/sctp/diag.c
@@ -175,7 +175,7 @@ static int inet_sctp_diag_fill(struct sock *sk, struct sctp_association *asoc,
 		mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
 		mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued;
 		mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
-		mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len;
+		mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len);
 		mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops);
 
 		if (nla_put(skb, INET_DIAG_SKMEMINFO, sizeof(mem), &mem) < 0)
@@ -237,15 +237,11 @@ static size_t inet_assoc_attr_size(struct sctp_association *asoc)
 		addrcnt++;
 
 	return	  nla_total_size(sizeof(struct sctp_info))
-		+ nla_total_size(1) /* INET_DIAG_SHUTDOWN */
-		+ nla_total_size(1) /* INET_DIAG_TOS */
-		+ nla_total_size(1) /* INET_DIAG_TCLASS */
-		+ nla_total_size(4) /* INET_DIAG_MARK */
-		+ nla_total_size(4) /* INET_DIAG_CLASS_ID */
 		+ nla_total_size(addrlen * asoc->peer.transport_count)
 		+ nla_total_size(addrlen * addrcnt)
-		+ nla_total_size(sizeof(struct inet_diag_meminfo))
 		+ nla_total_size(sizeof(struct inet_diag_msg))
+		+ inet_diag_msg_attrs_size()
+		+ nla_total_size(sizeof(struct inet_diag_meminfo))
 		+ 64;
 }
 
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 9cc55a3e6d48..579908a2d2d7 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -228,7 +228,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 {
 	struct sctp_association *asoc = t->asoc;
 	struct dst_entry *dst = NULL;
-	struct flowi6 *fl6 = &fl->u.ip6;
+	struct flowi _fl;
+	struct flowi6 *fl6 = &_fl.u.ip6;
 	struct sctp_bind_addr *bp;
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sctp_sockaddr_entry *laddr;
@@ -238,7 +239,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	enum sctp_scope scope;
 	__u8 matchlen = 0;
 
-	memset(fl6, 0, sizeof(struct flowi6));
+	memset(&_fl, 0, sizeof(_fl));
 	fl6->daddr = daddr->v6.sin6_addr;
 	fl6->fl6_dport = daddr->v6.sin6_port;
 	fl6->flowi6_proto = IPPROTO_SCTP;
@@ -276,8 +277,11 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	rcu_read_unlock();
 
 	dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p);
-	if (!asoc || saddr)
+	if (!asoc || saddr) {
+		t->dst = dst;
+		memcpy(fl, &_fl, sizeof(_fl));
 		goto out;
+	}
 
 	bp = &asoc->base.bind_addr;
 	scope = sctp_scope(daddr);
@@ -300,6 +304,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 			if ((laddr->a.sa.sa_family == AF_INET6) &&
 			    (sctp_v6_cmp_addr(&dst_saddr, &laddr->a))) {
 				rcu_read_unlock();
+				t->dst = dst;
+				memcpy(fl, &_fl, sizeof(_fl));
 				goto out;
 			}
 		}
@@ -338,6 +344,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 			if (!IS_ERR_OR_NULL(dst))
 				dst_release(dst);
 			dst = bdst;
+			t->dst = dst;
+			memcpy(fl, &_fl, sizeof(_fl));
 			break;
 		}
 
@@ -351,6 +359,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 			dst_release(dst);
 		dst = bdst;
 		matchlen = bmatchlen;
+		t->dst = dst;
+		memcpy(fl, &_fl, sizeof(_fl));
 	}
 	rcu_read_unlock();
 
@@ -359,14 +369,12 @@ out:
 		struct rt6_info *rt;
 
 		rt = (struct rt6_info *)dst;
-		t->dst = dst;
 		t->dst_cookie = rt6_get_cookie(rt);
 		pr_debug("rt6_dst:%pI6/%d rt6_src:%pI6\n",
 			 &rt->rt6i_dst.addr, rt->rt6i_dst.plen,
-			 &fl6->saddr);
+			 &fl->u.ip6.saddr);
 	} else {
 		t->dst = NULL;
-
 		pr_debug("no route\n");
 	}
 }
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 015c81ac6fe5..5968dbe8ca80 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -148,7 +148,8 @@ int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *bp,
 		 * sock as well as the remote peer.
 		 */
 		if (addr->a.sa.sa_family == AF_INET &&
-		    !(copy_flags & SCTP_ADDR4_PEERSUPP))
+		    (!(copy_flags & SCTP_ADDR4_ALLOWED) ||
+		     !(copy_flags & SCTP_ADDR4_PEERSUPP)))
 			continue;
 		if (addr->a.sa.sa_family == AF_INET6 &&
 		    (!(copy_flags & SCTP_ADDR6_ALLOWED) ||
@@ -409,7 +410,8 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 {
 	struct sctp_association *asoc = t->asoc;
 	struct rtable *rt;
-	struct flowi4 *fl4 = &fl->u.ip4;
+	struct flowi _fl;
+	struct flowi4 *fl4 = &_fl.u.ip4;
 	struct sctp_bind_addr *bp;
 	struct sctp_sockaddr_entry *laddr;
 	struct dst_entry *dst = NULL;
@@ -419,7 +421,7 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 
 	if (t->dscp & SCTP_DSCP_SET_MASK)
 		tos = t->dscp & SCTP_DSCP_VAL_MASK;
-	memset(fl4, 0x0, sizeof(struct flowi4));
+	memset(&_fl, 0x0, sizeof(_fl));
 	fl4->daddr  = daddr->v4.sin_addr.s_addr;
 	fl4->fl4_dport = daddr->v4.sin_port;
 	fl4->flowi4_proto = IPPROTO_SCTP;
@@ -438,8 +440,11 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		 &fl4->saddr);
 
 	rt = ip_route_output_key(sock_net(sk), fl4);
-	if (!IS_ERR(rt))
+	if (!IS_ERR(rt)) {
 		dst = &rt->dst;
+		t->dst = dst;
+		memcpy(fl, &_fl, sizeof(_fl));
+	}
 
 	/* If there is no association or if a source address is passed, no
 	 * more validation is required.
@@ -502,27 +507,33 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		odev = __ip_dev_find(sock_net(sk), laddr->a.v4.sin_addr.s_addr,
 				     false);
 		if (!odev || odev->ifindex != fl4->flowi4_oif) {
-			if (!dst)
+			if (!dst) {
 				dst = &rt->dst;
-			else
+				t->dst = dst;
+				memcpy(fl, &_fl, sizeof(_fl));
+			} else {
 				dst_release(&rt->dst);
+			}
 			continue;
 		}
 
 		dst_release(dst);
 		dst = &rt->dst;
+		t->dst = dst;
+		memcpy(fl, &_fl, sizeof(_fl));
 		break;
 	}
 
 out_unlock:
 	rcu_read_unlock();
 out:
-	t->dst = dst;
-	if (dst)
+	if (dst) {
 		pr_debug("rt_dst:%pI4, rt_src:%pI4\n",
-			 &fl4->daddr, &fl4->saddr);
-	else
+			 &fl->u.ip4.daddr, &fl->u.ip4.saddr);
+	} else {
+		t->dst = NULL;
 		pr_debug("no route\n");
+	}
 }
 
 /* For v4, the source address is cached in the route entry(dst). So no need
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 9b0e5b0d701a..8f179abec5ed 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -856,7 +856,11 @@ struct sctp_chunk *sctp_make_shutdown(const struct sctp_association *asoc,
 	struct sctp_chunk *retval;
 	__u32 ctsn;
 
-	ctsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map);
+	if (chunk && chunk->asoc)
+		ctsn = sctp_tsnmap_get_ctsn(&chunk->asoc->peer.tsn_map);
+	else
+		ctsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map);
+
 	shut.cum_tsn_ack = htonl(ctsn);
 
 	retval = sctp_make_control(asoc, SCTP_CID_SHUTDOWN, 0,
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index e52b2128e43b..6927b658dad3 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -1358,8 +1358,10 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type,
 			/* Generate an INIT ACK chunk.  */
 			new_obj = sctp_make_init_ack(asoc, chunk, GFP_ATOMIC,
 						     0);
-			if (!new_obj)
-				goto nomem;
+			if (!new_obj) {
+				error = -ENOMEM;
+				break;
+			}
 
 			sctp_add_cmd_sf(commands, SCTP_CMD_REPLY,
 					SCTP_CHUNK(new_obj));
@@ -1381,7 +1383,8 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type,
 			if (!new_obj) {
 				if (cmd->obj.chunk)
 					sctp_chunk_free(cmd->obj.chunk);
-				goto nomem;
+				error = -ENOMEM;
+				break;
 			}
 			sctp_add_cmd_sf(commands, SCTP_CMD_REPLY,
 					SCTP_CHUNK(new_obj));
@@ -1428,8 +1431,10 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type,
 
 			/* Generate a SHUTDOWN chunk.  */
 			new_obj = sctp_make_shutdown(asoc, chunk);
-			if (!new_obj)
-				goto nomem;
+			if (!new_obj) {
+				error = -ENOMEM;
+				break;
+			}
 			sctp_add_cmd_sf(commands, SCTP_CMD_REPLY,
 					SCTP_CHUNK(new_obj));
 			break;
@@ -1517,9 +1522,17 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type,
 			timeout = asoc->timeouts[cmd->obj.to];
 			BUG_ON(!timeout);
 
-			timer->expires = jiffies + timeout;
-			sctp_association_hold(asoc);
-			add_timer(timer);
+			/*
+			 * SCTP has a hard time with timer starts.  Because we process
+			 * timer starts as side effects, it can be hard to tell if we
+			 * have already started a timer or not, which leads to BUG
+			 * halts when we call add_timer. So here, instead of just starting
+			 * a timer, if the timer is already started, and just mod
+			 * the timer with the shorter of the two expiration times
+			 */
+			if (!timer_pending(timer))
+				sctp_association_hold(asoc);
+			timer_reduce(timer, jiffies + timeout);
 			break;
 
 		case SCTP_CMD_TIMER_RESTART:
@@ -1765,11 +1778,17 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type,
 			break;
 		}
 
-		if (error)
+		if (error) {
+			cmd = sctp_next_cmd(commands);
+			while (cmd) {
+				if (cmd->verb == SCTP_CMD_REPLY)
+					sctp_chunk_free(cmd->obj.chunk);
+				cmd = sctp_next_cmd(commands);
+			}
 			break;
+		}
 	}
 
-out:
 	/* If this is in response to a received chunk, wait until
 	 * we are done with the packet to open the queue so that we don't
 	 * send multiple packets in response to a single request.
@@ -1784,7 +1803,4 @@ out:
 		sp->data_ready_signalled = 0;
 
 	return error;
-nomem:
-	error = -ENOMEM;
-	goto out;
 }
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 9eeea0d8e4cf..6b2886dc3120 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -170,6 +170,16 @@ static inline bool sctp_chunk_length_valid(struct sctp_chunk *chunk,
 	return true;
 }
 
+/* Check for format error in an ABORT chunk */
+static inline bool sctp_err_chunk_valid(struct sctp_chunk *chunk)
+{
+	struct sctp_errhdr *err;
+
+	sctp_walk_errors(err, chunk->chunk_hdr);
+
+	return (void *)err == (void *)chunk->chunk_end;
+}
+
 /**********************************************************
  * These are the state functions for handling chunk events.
  **********************************************************/
@@ -1846,16 +1856,17 @@ static enum sctp_disposition sctp_sf_do_dupcook_a(
 	/* Update the content of current association. */
 	sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc));
 	sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev));
-	if (sctp_state(asoc, SHUTDOWN_PENDING) &&
+	if ((sctp_state(asoc, SHUTDOWN_PENDING) ||
+	     sctp_state(asoc, SHUTDOWN_SENT)) &&
 	    (sctp_sstate(asoc->base.sk, CLOSING) ||
 	     sock_flag(asoc->base.sk, SOCK_DEAD))) {
-		/* if were currently in SHUTDOWN_PENDING, but the socket
-		 * has been closed by user, don't transition to ESTABLISHED.
-		 * Instead trigger SHUTDOWN bundled with COOKIE_ACK.
+		/* If the socket has been closed by user, don't
+		 * transition to ESTABLISHED. Instead trigger SHUTDOWN
+		 * bundled with COOKIE_ACK.
 		 */
 		sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl));
 		return sctp_sf_do_9_2_start_shutdown(net, ep, asoc,
-						     SCTP_ST_CHUNK(0), NULL,
+						     SCTP_ST_CHUNK(0), repl,
 						     commands);
 	} else {
 		sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
@@ -2255,6 +2266,9 @@ enum sctp_disposition sctp_sf_shutdown_pending_abort(
 		    sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
 		return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
 
+	if (!sctp_err_chunk_valid(chunk))
+		return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
 	return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands);
 }
 
@@ -2298,6 +2312,9 @@ enum sctp_disposition sctp_sf_shutdown_sent_abort(
 		    sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
 		return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
 
+	if (!sctp_err_chunk_valid(chunk))
+		return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
 	/* Stop the T2-shutdown timer. */
 	sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
 			SCTP_TO(SCTP_EVENT_TIMEOUT_T2_SHUTDOWN));
@@ -2565,6 +2582,9 @@ enum sctp_disposition sctp_sf_do_9_1_abort(
 		    sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
 		return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
 
+	if (!sctp_err_chunk_valid(chunk))
+		return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
 	return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands);
 }
 
@@ -2582,16 +2602,8 @@ static enum sctp_disposition __sctp_sf_do_9_1_abort(
 
 	/* See if we have an error cause code in the chunk.  */
 	len = ntohs(chunk->chunk_hdr->length);
-	if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr)) {
-		struct sctp_errhdr *err;
-
-		sctp_walk_errors(err, chunk->chunk_hdr);
-		if ((void *)err != (void *)chunk->chunk_end)
-			return sctp_sf_pdiscard(net, ep, asoc, type, arg,
-						commands);
-
+	if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr))
 		error = ((struct sctp_errhdr *)chunk->skb->data)->cause;
-	}
 
 	sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNRESET));
 	/* ASSOC_FAILED will DELETE_TCB. */
@@ -5457,7 +5469,7 @@ enum sctp_disposition sctp_sf_do_9_2_start_shutdown(
 	 * in the Cumulative TSN Ack field the last sequential TSN it
 	 * has received from the peer.
 	 */
-	reply = sctp_make_shutdown(asoc, NULL);
+	reply = sctp_make_shutdown(asoc, arg);
 	if (!reply)
 		goto nomem;
 
@@ -6055,7 +6067,7 @@ enum sctp_disposition sctp_sf_autoclose_timer_expire(
 	disposition = SCTP_DISPOSITION_CONSUME;
 	if (sctp_outq_is_empty(&asoc->outqueue)) {
 		disposition = sctp_sf_do_9_2_start_shutdown(net, ep, asoc, type,
-							    arg, commands);
+							    NULL, commands);
 	}
 
 	return disposition;
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 2d3e096ae751..ed0682f33c8b 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -147,29 +147,44 @@ static void sctp_clear_owner_w(struct sctp_chunk *chunk)
 	skb_orphan(chunk->skb);
 }
 
+#define traverse_and_process()	\
+do {				\
+	msg = chunk->msg;	\
+	if (msg == prev_msg)	\
+		continue;	\
+	list_for_each_entry(c, &msg->chunks, frag_list) {	\
+		if ((clear && asoc->base.sk == c->skb->sk) ||	\
+		    (!clear && asoc->base.sk != c->skb->sk))	\
+			cb(c);	\
+	}			\
+	prev_msg = msg;		\
+} while (0)
+
 static void sctp_for_each_tx_datachunk(struct sctp_association *asoc,
+				       bool clear,
 				       void (*cb)(struct sctp_chunk *))
 
 {
+	struct sctp_datamsg *msg, *prev_msg = NULL;
 	struct sctp_outq *q = &asoc->outqueue;
+	struct sctp_chunk *chunk, *c;
 	struct sctp_transport *t;
-	struct sctp_chunk *chunk;
 
 	list_for_each_entry(t, &asoc->peer.transport_addr_list, transports)
 		list_for_each_entry(chunk, &t->transmitted, transmitted_list)
-			cb(chunk);
+			traverse_and_process();
 
 	list_for_each_entry(chunk, &q->retransmit, transmitted_list)
-		cb(chunk);
+		traverse_and_process();
 
 	list_for_each_entry(chunk, &q->sacked, transmitted_list)
-		cb(chunk);
+		traverse_and_process();
 
 	list_for_each_entry(chunk, &q->abandoned, transmitted_list)
-		cb(chunk);
+		traverse_and_process();
 
 	list_for_each_entry(chunk, &q->out_chunk_list, list)
-		cb(chunk);
+		traverse_and_process();
 }
 
 static void sctp_for_each_rx_skb(struct sctp_association *asoc, struct sock *sk,
@@ -9316,9 +9331,9 @@ static int sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 	 * paths won't try to lock it and then oldsk.
 	 */
 	lock_sock_nested(newsk, SINGLE_DEPTH_NESTING);
-	sctp_for_each_tx_datachunk(assoc, sctp_clear_owner_w);
+	sctp_for_each_tx_datachunk(assoc, true, sctp_clear_owner_w);
 	sctp_assoc_migrate(assoc, newsk);
-	sctp_for_each_tx_datachunk(assoc, sctp_set_owner_w);
+	sctp_for_each_tx_datachunk(assoc, false, sctp_set_owner_w);
 
 	/* If the association on the newsk is already closed before accept()
 	 * is called, set RCV_SHUTDOWN flag.
diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index c1a100d2fed3..e13cbd5c0193 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -22,17 +22,11 @@
 #include <net/sctp/sm.h>
 #include <net/sctp/stream_sched.h>
 
-/* Migrates chunks from stream queues to new stream queues if needed,
- * but not across associations. Also, removes those chunks to streams
- * higher than the new max.
- */
-static void sctp_stream_outq_migrate(struct sctp_stream *stream,
-				     struct sctp_stream *new, __u16 outcnt)
+static void sctp_stream_shrink_out(struct sctp_stream *stream, __u16 outcnt)
 {
 	struct sctp_association *asoc;
 	struct sctp_chunk *ch, *temp;
 	struct sctp_outq *outq;
-	int i;
 
 	asoc = container_of(stream, struct sctp_association, stream);
 	outq = &asoc->outqueue;
@@ -56,6 +50,19 @@ static void sctp_stream_outq_migrate(struct sctp_stream *stream,
 
 		sctp_chunk_free(ch);
 	}
+}
+
+/* Migrates chunks from stream queues to new stream queues if needed,
+ * but not across associations. Also, removes those chunks to streams
+ * higher than the new max.
+ */
+static void sctp_stream_outq_migrate(struct sctp_stream *stream,
+				     struct sctp_stream *new, __u16 outcnt)
+{
+	int i;
+
+	if (stream->outcnt > outcnt)
+		sctp_stream_shrink_out(stream, outcnt);
 
 	if (new) {
 		/* Here we actually move the old ext stuff into the new
@@ -1038,11 +1045,13 @@ struct sctp_chunk *sctp_process_strreset_resp(
 		nums = ntohs(addstrm->number_of_streams);
 		number = stream->outcnt - nums;
 
-		if (result == SCTP_STRRESET_PERFORMED)
+		if (result == SCTP_STRRESET_PERFORMED) {
 			for (i = number; i < stream->outcnt; i++)
 				SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN;
-		else
+		} else {
+			sctp_stream_shrink_out(stream, number);
 			stream->outcnt = number;
+		}
 
 		*evp = sctp_ulpevent_make_stream_change_event(asoc, flags,
 			0, nums, GFP_ATOMIC);
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index fe955fae2995..1070e6edeca2 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -125,8 +125,10 @@ EXPORT_SYMBOL_GPL(smc_proto6);
 
 static void smc_restore_fallback_changes(struct smc_sock *smc)
 {
-	smc->clcsock->file->private_data = smc->sk.sk_socket;
-	smc->clcsock->file = NULL;
+	if (smc->clcsock->file) { /* non-accepted sockets have no file yet */
+		smc->clcsock->file->private_data = smc->sk.sk_socket;
+		smc->clcsock->file = NULL;
+	}
 }
 
 static int smc_release(struct socket *sock)
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 745afd82f281..bd0aed55ca20 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -369,7 +369,9 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info)
 	dclc.hdr.length = htons(sizeof(struct smc_clc_msg_decline));
 	dclc.hdr.version = SMC_CLC_V1;
 	dclc.hdr.flag = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ? 1 : 0;
-	memcpy(dclc.id_for_peer, local_systemid, sizeof(local_systemid));
+	if (smc->conn.lgr && !smc->conn.lgr->is_smcd)
+		memcpy(dclc.id_for_peer, local_systemid,
+		       sizeof(local_systemid));
 	dclc.peer_diagnosis = htonl(peer_diag_info);
 	memcpy(dclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
 
diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
index f38727ecf8b2..e1f64f4ba236 100644
--- a/net/smc/smc_diag.c
+++ b/net/smc/smc_diag.c
@@ -39,16 +39,15 @@ static void smc_diag_msg_common_fill(struct smc_diag_msg *r, struct sock *sk)
 {
 	struct smc_sock *smc = smc_sk(sk);
 
+	memset(r, 0, sizeof(*r));
 	r->diag_family = sk->sk_family;
+	sock_diag_save_cookie(sk, r->id.idiag_cookie);
 	if (!smc->clcsock)
 		return;
 	r->id.idiag_sport = htons(smc->clcsock->sk->sk_num);
 	r->id.idiag_dport = smc->clcsock->sk->sk_dport;
 	r->id.idiag_if = smc->clcsock->sk->sk_bound_dev_if;
-	sock_diag_save_cookie(sk, r->id.idiag_cookie);
 	if (sk->sk_protocol == SMCPROTO_SMC) {
-		memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
-		memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
 		r->id.idiag_src[0] = smc->clcsock->sk->sk_rcv_saddr;
 		r->id.idiag_dst[0] = smc->clcsock->sk->sk_daddr;
 #if IS_ENABLED(CONFIG_IPV6)
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index d14ca4af6f94..d74a71dff5b8 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -560,12 +560,15 @@ static void smc_ib_remove_dev(struct ib_device *ibdev, void *client_data)
 	struct smc_ib_device *smcibdev;
 
 	smcibdev = ib_get_client_data(ibdev, &smc_ib_client);
+	if (!smcibdev || smcibdev->ibdev != ibdev)
+		return;
 	ib_set_client_data(ibdev, &smc_ib_client, NULL);
 	spin_lock(&smc_ib_devices.lock);
 	list_del_init(&smcibdev->list); /* remove from smc_ib_devices */
 	spin_unlock(&smc_ib_devices.lock);
 	smc_ib_cleanup_per_ibdev(smcibdev);
 	ib_unregister_event_handler(&smcibdev->event_handler);
+	cancel_work_sync(&smcibdev->port_event_work);
 	kfree(smcibdev);
 }
 
diff --git a/net/socket.c b/net/socket.c
index 38eec1583f6d..81ee3118dfa1 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -496,7 +496,7 @@ static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed)
 	if (f.file) {
 		sock = sock_from_file(f.file, err);
 		if (likely(sock)) {
-			*fput_needed = f.flags;
+			*fput_needed = f.flags & FDPUT_FPUT;
 			return sock;
 		}
 		fdput(f);
@@ -960,7 +960,7 @@ static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to)
 			     .msg_iocb = iocb};
 	ssize_t res;
 
-	if (file->f_flags & O_NONBLOCK)
+	if (file->f_flags & O_NONBLOCK || (iocb->ki_flags & IOCB_NOWAIT))
 		msg.msg_flags = MSG_DONTWAIT;
 
 	if (iocb->ki_pos != 0)
@@ -985,7 +985,7 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (iocb->ki_pos != 0)
 		return -ESPIPE;
 
-	if (file->f_flags & O_NONBLOCK)
+	if (file->f_flags & O_NONBLOCK || (iocb->ki_flags & IOCB_NOWAIT))
 		msg.msg_flags = MSG_DONTWAIT;
 
 	if (sock->type == SOCK_SEQPACKET)
@@ -3412,6 +3412,7 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 	case SIOCSARP:
 	case SIOCGARP:
 	case SIOCDARP:
+	case SIOCOUTQNSD:
 	case SIOCATMARK:
 		return sock_do_ioctl(net, sock, cmd, arg);
 	}
diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c
index d024af4be85e..105d17af4abc 100644
--- a/net/sunrpc/addr.c
+++ b/net/sunrpc/addr.c
@@ -82,11 +82,11 @@ static size_t rpc_ntop6(const struct sockaddr *sap,
 
 	rc = snprintf(scopebuf, sizeof(scopebuf), "%c%u",
 			IPV6_SCOPE_DELIMITER, sin6->sin6_scope_id);
-	if (unlikely((size_t)rc > sizeof(scopebuf)))
+	if (unlikely((size_t)rc >= sizeof(scopebuf)))
 		return 0;
 
 	len += rc;
-	if (unlikely(len > buflen))
+	if (unlikely(len >= buflen))
 		return 0;
 
 	strcat(buf, scopebuf);
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 4ce42c62458e..5fc6c028f89c 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -20,6 +20,7 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/auth.h>
 #include <linux/sunrpc/auth_gss.h>
+#include <linux/sunrpc/gss_krb5.h>
 #include <linux/sunrpc/svcauth_gss.h>
 #include <linux/sunrpc/gss_err.h>
 #include <linux/workqueue.h>
@@ -1050,7 +1051,7 @@ gss_create_new(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt)
 		goto err_put_mech;
 	auth = &gss_auth->rpc_auth;
 	auth->au_cslack = GSS_CRED_SLACK >> 2;
-	auth->au_rslack = GSS_VERF_SLACK >> 2;
+	auth->au_rslack = GSS_KRB5_MAX_SLACK_NEEDED >> 2;
 	auth->au_verfsize = GSS_VERF_SLACK >> 2;
 	auth->au_ralign = GSS_VERF_SLACK >> 2;
 	auth->au_flags = 0;
@@ -1934,35 +1935,69 @@ gss_unwrap_resp_auth(struct rpc_cred *cred)
 	return 0;
 }
 
+/*
+ * RFC 2203, Section 5.3.2.2
+ *
+ *	struct rpc_gss_integ_data {
+ *		opaque databody_integ<>;
+ *		opaque checksum<>;
+ *	};
+ *
+ *	struct rpc_gss_data_t {
+ *		unsigned int seq_num;
+ *		proc_req_arg_t arg;
+ *	};
+ */
 static int
 gss_unwrap_resp_integ(struct rpc_task *task, struct rpc_cred *cred,
 		      struct gss_cl_ctx *ctx, struct rpc_rqst *rqstp,
 		      struct xdr_stream *xdr)
 {
-	struct xdr_buf integ_buf, *rcv_buf = &rqstp->rq_rcv_buf;
-	u32 data_offset, mic_offset, integ_len, maj_stat;
+	struct xdr_buf gss_data, *rcv_buf = &rqstp->rq_rcv_buf;
 	struct rpc_auth *auth = cred->cr_auth;
+	u32 len, offset, seqno, maj_stat;
 	struct xdr_netobj mic;
-	__be32 *p;
+	int ret;
 
-	p = xdr_inline_decode(xdr, 2 * sizeof(*p));
-	if (unlikely(!p))
+	ret = -EIO;
+	mic.data = NULL;
+
+	/* opaque databody_integ<>; */
+	if (xdr_stream_decode_u32(xdr, &len))
 		goto unwrap_failed;
-	integ_len = be32_to_cpup(p++);
-	if (integ_len & 3)
+	if (len & 3)
 		goto unwrap_failed;
-	data_offset = (u8 *)(p) - (u8 *)rcv_buf->head[0].iov_base;
-	mic_offset = integ_len + data_offset;
-	if (mic_offset > rcv_buf->len)
+	offset = rcv_buf->len - xdr_stream_remaining(xdr);
+	if (xdr_stream_decode_u32(xdr, &seqno))
 		goto unwrap_failed;
-	if (be32_to_cpup(p) != rqstp->rq_seqno)
+	if (seqno != rqstp->rq_seqno)
 		goto bad_seqno;
+	if (xdr_buf_subsegment(rcv_buf, &gss_data, offset, len))
+		goto unwrap_failed;
 
-	if (xdr_buf_subsegment(rcv_buf, &integ_buf, data_offset, integ_len))
+	/*
+	 * The xdr_stream now points to the beginning of the
+	 * upper layer payload, to be passed below to
+	 * rpcauth_unwrap_resp_decode(). The checksum, which
+	 * follows the upper layer payload in @rcv_buf, is
+	 * located and parsed without updating the xdr_stream.
+	 */
+
+	/* opaque checksum<>; */
+	offset += len;
+	if (xdr_decode_word(rcv_buf, offset, &len))
+		goto unwrap_failed;
+	offset += sizeof(__be32);
+	if (offset + len > rcv_buf->len)
 		goto unwrap_failed;
-	if (xdr_buf_read_netobj(rcv_buf, &mic, mic_offset))
+	mic.len = len;
+	mic.data = kmalloc(len, GFP_NOFS);
+	if (!mic.data)
 		goto unwrap_failed;
-	maj_stat = gss_verify_mic(ctx->gc_gss_ctx, &integ_buf, &mic);
+	if (read_bytes_from_xdr_buf(rcv_buf, offset, mic.data, mic.len))
+		goto unwrap_failed;
+
+	maj_stat = gss_verify_mic(ctx->gc_gss_ctx, &gss_data, &mic);
 	if (maj_stat == GSS_S_CONTEXT_EXPIRED)
 		clear_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags);
 	if (maj_stat != GSS_S_COMPLETE)
@@ -1970,16 +2005,21 @@ gss_unwrap_resp_integ(struct rpc_task *task, struct rpc_cred *cred,
 
 	auth->au_rslack = auth->au_verfsize + 2 + 1 + XDR_QUADLEN(mic.len);
 	auth->au_ralign = auth->au_verfsize + 2;
-	return 0;
+	ret = 0;
+
+out:
+	kfree(mic.data);
+	return ret;
+
 unwrap_failed:
 	trace_rpcgss_unwrap_failed(task);
-	return -EIO;
+	goto out;
 bad_seqno:
-	trace_rpcgss_bad_seqno(task, rqstp->rq_seqno, be32_to_cpup(p));
-	return -EIO;
+	trace_rpcgss_bad_seqno(task, rqstp->rq_seqno, seqno);
+	goto out;
 bad_mic:
 	trace_rpcgss_verify_mic(task, maj_stat);
-	return -EIO;
+	goto out;
 }
 
 static int
@@ -1990,7 +2030,6 @@ gss_unwrap_resp_priv(struct rpc_task *task, struct rpc_cred *cred,
 	struct xdr_buf *rcv_buf = &rqstp->rq_rcv_buf;
 	struct kvec *head = rqstp->rq_rcv_buf.head;
 	struct rpc_auth *auth = cred->cr_auth;
-	unsigned int savedlen = rcv_buf->len;
 	u32 offset, opaque_len, maj_stat;
 	__be32 *p;
 
@@ -2001,9 +2040,9 @@ gss_unwrap_resp_priv(struct rpc_task *task, struct rpc_cred *cred,
 	offset = (u8 *)(p) - (u8 *)head->iov_base;
 	if (offset + opaque_len > rcv_buf->len)
 		goto unwrap_failed;
-	rcv_buf->len = offset + opaque_len;
 
-	maj_stat = gss_unwrap(ctx->gc_gss_ctx, offset, rcv_buf);
+	maj_stat = gss_unwrap(ctx->gc_gss_ctx, offset,
+			      offset + opaque_len, rcv_buf);
 	if (maj_stat == GSS_S_CONTEXT_EXPIRED)
 		clear_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags);
 	if (maj_stat != GSS_S_COMPLETE)
@@ -2017,10 +2056,9 @@ gss_unwrap_resp_priv(struct rpc_task *task, struct rpc_cred *cred,
 	 */
 	xdr_init_decode(xdr, rcv_buf, p, rqstp);
 
-	auth->au_rslack = auth->au_verfsize + 2 +
-			  XDR_QUADLEN(savedlen - rcv_buf->len);
-	auth->au_ralign = auth->au_verfsize + 2 +
-			  XDR_QUADLEN(savedlen - rcv_buf->len);
+	auth->au_rslack = auth->au_verfsize + 2 + ctx->gc_gss_ctx->slack;
+	auth->au_ralign = auth->au_verfsize + 2 + ctx->gc_gss_ctx->align;
+
 	return 0;
 unwrap_failed:
 	trace_rpcgss_unwrap_failed(task);
diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c
index 6f2d30d7b766..e7180da1fc6a 100644
--- a/net/sunrpc/auth_gss/gss_krb5_crypto.c
+++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c
@@ -851,8 +851,8 @@ out_err:
 }
 
 u32
-gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf,
-		     u32 *headskip, u32 *tailskip)
+gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, u32 len,
+		     struct xdr_buf *buf, u32 *headskip, u32 *tailskip)
 {
 	struct xdr_buf subbuf;
 	u32 ret = 0;
@@ -881,7 +881,7 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf,
 
 	/* create a segment skipping the header and leaving out the checksum */
 	xdr_buf_subsegment(buf, &subbuf, offset + GSS_KRB5_TOK_HDR_LEN,
-				    (buf->len - offset - GSS_KRB5_TOK_HDR_LEN -
+				    (len - offset - GSS_KRB5_TOK_HDR_LEN -
 				     kctx->gk5e->cksumlength));
 
 	nblocks = (subbuf.len + blocksize - 1) / blocksize;
@@ -926,7 +926,7 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf,
 		goto out_err;
 
 	/* Get the packet's hmac value */
-	ret = read_bytes_from_xdr_buf(buf, buf->len - kctx->gk5e->cksumlength,
+	ret = read_bytes_from_xdr_buf(buf, len - kctx->gk5e->cksumlength,
 				      pkt_hmac, kctx->gk5e->cksumlength);
 	if (ret)
 		goto out_err;
diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c
index 6e5d6d240215..75b3c2e9e8f8 100644
--- a/net/sunrpc/auth_gss/gss_krb5_mech.c
+++ b/net/sunrpc/auth_gss/gss_krb5_mech.c
@@ -253,6 +253,7 @@ gss_import_v1_context(const void *p, const void *end, struct krb5_ctx *ctx)
 {
 	u32 seq_send;
 	int tmp;
+	u32 time32;
 
 	p = simple_get_bytes(p, end, &ctx->initiate, sizeof(ctx->initiate));
 	if (IS_ERR(p))
@@ -290,9 +291,11 @@ gss_import_v1_context(const void *p, const void *end, struct krb5_ctx *ctx)
 		p = ERR_PTR(-ENOSYS);
 		goto out_err;
 	}
-	p = simple_get_bytes(p, end, &ctx->endtime, sizeof(ctx->endtime));
+	p = simple_get_bytes(p, end, &time32, sizeof(time32));
 	if (IS_ERR(p))
 		goto out_err;
+	/* unsigned 32-bit time overflows in year 2106 */
+	ctx->endtime = (time64_t)time32;
 	p = simple_get_bytes(p, end, &seq_send, sizeof(seq_send));
 	if (IS_ERR(p))
 		goto out_err;
@@ -587,15 +590,18 @@ gss_import_v2_context(const void *p, const void *end, struct krb5_ctx *ctx,
 {
 	u64 seq_send64;
 	int keylen;
+	u32 time32;
 
 	p = simple_get_bytes(p, end, &ctx->flags, sizeof(ctx->flags));
 	if (IS_ERR(p))
 		goto out_err;
 	ctx->initiate = ctx->flags & KRB5_CTX_FLAG_INITIATOR;
 
-	p = simple_get_bytes(p, end, &ctx->endtime, sizeof(ctx->endtime));
+	p = simple_get_bytes(p, end, &time32, sizeof(time32));
 	if (IS_ERR(p))
 		goto out_err;
+	/* unsigned 32-bit time overflows in year 2106 */
+	ctx->endtime = (time64_t)time32;
 	p = simple_get_bytes(p, end, &seq_send64, sizeof(seq_send64));
 	if (IS_ERR(p))
 		goto out_err;
@@ -659,7 +665,7 @@ out_err:
 static int
 gss_import_sec_context_kerberos(const void *p, size_t len,
 				struct gss_ctx *ctx_id,
-				time_t *endtime,
+				time64_t *endtime,
 				gfp_t gfp_mask)
 {
 	const void *end = (const void *)((const char *)p + len);
diff --git a/net/sunrpc/auth_gss/gss_krb5_seal.c b/net/sunrpc/auth_gss/gss_krb5_seal.c
index 48fe4a591b54..f1d280accf43 100644
--- a/net/sunrpc/auth_gss/gss_krb5_seal.c
+++ b/net/sunrpc/auth_gss/gss_krb5_seal.c
@@ -131,14 +131,14 @@ gss_get_mic_v1(struct krb5_ctx *ctx, struct xdr_buf *text,
 	struct xdr_netobj	md5cksum = {.len = sizeof(cksumdata),
 					    .data = cksumdata};
 	void			*ptr;
-	s32			now;
+	time64_t		now;
 	u32			seq_send;
 	u8			*cksumkey;
 
 	dprintk("RPC:       %s\n", __func__);
 	BUG_ON(ctx == NULL);
 
-	now = get_seconds();
+	now = ktime_get_real_seconds();
 
 	ptr = setup_token(ctx, token);
 
@@ -170,7 +170,7 @@ gss_get_mic_v2(struct krb5_ctx *ctx, struct xdr_buf *text,
 	struct xdr_netobj cksumobj = { .len = sizeof(cksumdata),
 				       .data = cksumdata};
 	void *krb5_hdr;
-	s32 now;
+	time64_t now;
 	u8 *cksumkey;
 	unsigned int cksum_usage;
 	__be64 seq_send_be64;
@@ -198,7 +198,7 @@ gss_get_mic_v2(struct krb5_ctx *ctx, struct xdr_buf *text,
 
 	memcpy(krb5_hdr + GSS_KRB5_TOK_HDR_LEN, cksumobj.data, cksumobj.len);
 
-	now = get_seconds();
+	now = ktime_get_real_seconds();
 
 	return (ctx->endtime < now) ? GSS_S_CONTEXT_EXPIRED : GSS_S_COMPLETE;
 }
diff --git a/net/sunrpc/auth_gss/gss_krb5_unseal.c b/net/sunrpc/auth_gss/gss_krb5_unseal.c
index ef2b25b86d2f..aaab91cf24c8 100644
--- a/net/sunrpc/auth_gss/gss_krb5_unseal.c
+++ b/net/sunrpc/auth_gss/gss_krb5_unseal.c
@@ -124,7 +124,7 @@ gss_verify_mic_v1(struct krb5_ctx *ctx,
 
 	/* it got through unscathed.  Make sure the context is unexpired */
 
-	now = get_seconds();
+	now = ktime_get_real_seconds();
 
 	if (now > ctx->endtime)
 		return GSS_S_CONTEXT_EXPIRED;
@@ -149,7 +149,7 @@ gss_verify_mic_v2(struct krb5_ctx *ctx,
 	char cksumdata[GSS_KRB5_MAX_CKSUM_LEN];
 	struct xdr_netobj cksumobj = {.len = sizeof(cksumdata),
 				      .data = cksumdata};
-	s32 now;
+	time64_t now;
 	u8 *ptr = read_token->data;
 	u8 *cksumkey;
 	u8 flags;
@@ -194,7 +194,7 @@ gss_verify_mic_v2(struct krb5_ctx *ctx,
 		return GSS_S_BAD_SIG;
 
 	/* it got through unscathed.  Make sure the context is unexpired */
-	now = get_seconds();
+	now = ktime_get_real_seconds();
 	if (now > ctx->endtime)
 		return GSS_S_CONTEXT_EXPIRED;
 
diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c
index 14a0aff0cd84..90b8329fef82 100644
--- a/net/sunrpc/auth_gss/gss_krb5_wrap.c
+++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c
@@ -163,7 +163,7 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset,
 					    .data = cksumdata};
 	int			blocksize = 0, plainlen;
 	unsigned char		*ptr, *msg_start;
-	s32			now;
+	time64_t		now;
 	int			headlen;
 	struct page		**tmp_pages;
 	u32			seq_send;
@@ -172,7 +172,7 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset,
 
 	dprintk("RPC:       %s\n", __func__);
 
-	now = get_seconds();
+	now = ktime_get_real_seconds();
 
 	blocksize = crypto_sync_skcipher_blocksize(kctx->enc);
 	gss_krb5_add_padding(buf, offset, blocksize);
@@ -261,14 +261,16 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset,
 }
 
 static u32
-gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf)
+gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, int len,
+		       struct xdr_buf *buf, unsigned int *slack,
+		       unsigned int *align)
 {
 	int			signalg;
 	int			sealalg;
 	char			cksumdata[GSS_KRB5_MAX_CKSUM_LEN];
 	struct xdr_netobj	md5cksum = {.len = sizeof(cksumdata),
 					    .data = cksumdata};
-	s32			now;
+	time64_t		now;
 	int			direction;
 	s32			seqnum;
 	unsigned char		*ptr;
@@ -279,12 +281,13 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf)
 	u32			conflen = kctx->gk5e->conflen;
 	int			crypt_offset;
 	u8			*cksumkey;
+	unsigned int		saved_len = buf->len;
 
 	dprintk("RPC:       gss_unwrap_kerberos\n");
 
 	ptr = (u8 *)buf->head[0].iov_base + offset;
 	if (g_verify_token_header(&kctx->mech_used, &bodysize, &ptr,
-					buf->len - offset))
+					len - offset))
 		return GSS_S_DEFECTIVE_TOKEN;
 
 	if ((ptr[0] != ((KG_TOK_WRAP_MSG >> 8) & 0xff)) ||
@@ -324,6 +327,7 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf)
 	    (!kctx->initiate && direction != 0))
 		return GSS_S_BAD_SIG;
 
+	buf->len = len;
 	if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) {
 		struct crypto_sync_skcipher *cipher;
 		int err;
@@ -359,7 +363,7 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf)
 
 	/* it got through unscathed.  Make sure the context is unexpired */
 
-	now = get_seconds();
+	now = ktime_get_real_seconds();
 
 	if (now > kctx->endtime)
 		return GSS_S_CONTEXT_EXPIRED;
@@ -376,11 +380,15 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf)
 	data_len = (buf->head[0].iov_base + buf->head[0].iov_len) - data_start;
 	memmove(orig_start, data_start, data_len);
 	buf->head[0].iov_len -= (data_start - orig_start);
-	buf->len -= (data_start - orig_start);
+	buf->len = len - (data_start - orig_start);
 
 	if (gss_krb5_remove_padding(buf, blocksize))
 		return GSS_S_DEFECTIVE_TOKEN;
 
+	/* slack must include room for krb5 padding */
+	*slack = XDR_QUADLEN(saved_len - buf->len);
+	/* The GSS blob always precedes the RPC message payload */
+	*align = *slack;
 	return GSS_S_COMPLETE;
 }
 
@@ -439,7 +447,7 @@ gss_wrap_kerberos_v2(struct krb5_ctx *kctx, u32 offset,
 		     struct xdr_buf *buf, struct page **pages)
 {
 	u8		*ptr, *plainhdr;
-	s32		now;
+	time64_t	now;
 	u8		flags = 0x00;
 	__be16		*be16ptr;
 	__be64		*be64ptr;
@@ -481,14 +489,16 @@ gss_wrap_kerberos_v2(struct krb5_ctx *kctx, u32 offset,
 	if (err)
 		return err;
 
-	now = get_seconds();
+	now = ktime_get_real_seconds();
 	return (kctx->endtime < now) ? GSS_S_CONTEXT_EXPIRED : GSS_S_COMPLETE;
 }
 
 static u32
-gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf)
+gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, int len,
+		       struct xdr_buf *buf, unsigned int *slack,
+		       unsigned int *align)
 {
-	s32		now;
+	time64_t	now;
 	u8		*ptr;
 	u8		flags = 0x00;
 	u16		ec, rrc;
@@ -532,7 +542,7 @@ gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf)
 	if (rrc != 0)
 		rotate_left(offset + 16, buf, rrc);
 
-	err = (*kctx->gk5e->decrypt_v2)(kctx, offset, buf,
+	err = (*kctx->gk5e->decrypt_v2)(kctx, offset, len, buf,
 					&headskip, &tailskip);
 	if (err)
 		return GSS_S_FAILURE;
@@ -542,7 +552,7 @@ gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf)
 	 * it against the original
 	 */
 	err = read_bytes_from_xdr_buf(buf,
-				buf->len - GSS_KRB5_TOK_HDR_LEN - tailskip,
+				len - GSS_KRB5_TOK_HDR_LEN - tailskip,
 				decrypted_hdr, GSS_KRB5_TOK_HDR_LEN);
 	if (err) {
 		dprintk("%s: error %u getting decrypted_hdr\n", __func__, err);
@@ -557,7 +567,7 @@ gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf)
 	/* do sequencing checks */
 
 	/* it got through unscathed.  Make sure the context is unexpired */
-	now = get_seconds();
+	now = ktime_get_real_seconds();
 	if (now > kctx->endtime)
 		return GSS_S_CONTEXT_EXPIRED;
 
@@ -568,18 +578,19 @@ gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf)
 	 * Note that buf->head[0].iov_len may indicate the available
 	 * head buffer space rather than that actually occupied.
 	 */
-	movelen = min_t(unsigned int, buf->head[0].iov_len, buf->len);
+	movelen = min_t(unsigned int, buf->head[0].iov_len, len);
 	movelen -= offset + GSS_KRB5_TOK_HDR_LEN + headskip;
-	if (offset + GSS_KRB5_TOK_HDR_LEN + headskip + movelen >
-	    buf->head[0].iov_len)
-		return GSS_S_FAILURE;
+	BUG_ON(offset + GSS_KRB5_TOK_HDR_LEN + headskip + movelen >
+							buf->head[0].iov_len);
 	memmove(ptr, ptr + GSS_KRB5_TOK_HDR_LEN + headskip, movelen);
 	buf->head[0].iov_len -= GSS_KRB5_TOK_HDR_LEN + headskip;
-	buf->len -= GSS_KRB5_TOK_HDR_LEN + headskip;
+	buf->len = len - (GSS_KRB5_TOK_HDR_LEN + headskip);
 
 	/* Trim off the trailing "extra count" and checksum blob */
-	buf->len -= ec + GSS_KRB5_TOK_HDR_LEN + tailskip;
+	xdr_buf_trim(buf, ec + GSS_KRB5_TOK_HDR_LEN + tailskip);
 
+	*align = XDR_QUADLEN(GSS_KRB5_TOK_HDR_LEN + headskip);
+	*slack = *align + XDR_QUADLEN(ec + GSS_KRB5_TOK_HDR_LEN + tailskip);
 	return GSS_S_COMPLETE;
 }
 
@@ -603,7 +614,8 @@ gss_wrap_kerberos(struct gss_ctx *gctx, int offset,
 }
 
 u32
-gss_unwrap_kerberos(struct gss_ctx *gctx, int offset, struct xdr_buf *buf)
+gss_unwrap_kerberos(struct gss_ctx *gctx, int offset,
+		    int len, struct xdr_buf *buf)
 {
 	struct krb5_ctx	*kctx = gctx->internal_ctx_id;
 
@@ -613,9 +625,11 @@ gss_unwrap_kerberos(struct gss_ctx *gctx, int offset, struct xdr_buf *buf)
 	case ENCTYPE_DES_CBC_RAW:
 	case ENCTYPE_DES3_CBC_RAW:
 	case ENCTYPE_ARCFOUR_HMAC:
-		return gss_unwrap_kerberos_v1(kctx, offset, buf);
+		return gss_unwrap_kerberos_v1(kctx, offset, len, buf,
+					      &gctx->slack, &gctx->align);
 	case ENCTYPE_AES128_CTS_HMAC_SHA1_96:
 	case ENCTYPE_AES256_CTS_HMAC_SHA1_96:
-		return gss_unwrap_kerberos_v2(kctx, offset, buf);
+		return gss_unwrap_kerberos_v2(kctx, offset, len, buf,
+					      &gctx->slack, &gctx->align);
 	}
 }
diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c
index 82060099a429..95cebc912f63 100644
--- a/net/sunrpc/auth_gss/gss_mech_switch.c
+++ b/net/sunrpc/auth_gss/gss_mech_switch.c
@@ -36,6 +36,8 @@ gss_mech_free(struct gss_api_mech *gm)
 
 	for (i = 0; i < gm->gm_pf_num; i++) {
 		pf = &gm->gm_pfs[i];
+		if (pf->domain)
+			auth_domain_put(pf->domain);
 		kfree(pf->auth_domain_name);
 		pf->auth_domain_name = NULL;
 	}
@@ -58,6 +60,7 @@ make_auth_domain_name(char *name)
 static int
 gss_mech_svc_setup(struct gss_api_mech *gm)
 {
+	struct auth_domain *dom;
 	struct pf_desc *pf;
 	int i, status;
 
@@ -67,10 +70,13 @@ gss_mech_svc_setup(struct gss_api_mech *gm)
 		status = -ENOMEM;
 		if (pf->auth_domain_name == NULL)
 			goto out;
-		status = svcauth_gss_register_pseudoflavor(pf->pseudoflavor,
-							pf->auth_domain_name);
-		if (status)
+		dom = svcauth_gss_register_pseudoflavor(
+			pf->pseudoflavor, pf->auth_domain_name);
+		if (IS_ERR(dom)) {
+			status = PTR_ERR(dom);
 			goto out;
+		}
+		pf->domain = dom;
 	}
 	return 0;
 out:
@@ -374,7 +380,7 @@ int
 gss_import_sec_context(const void *input_token, size_t bufsize,
 		       struct gss_api_mech	*mech,
 		       struct gss_ctx		**ctx_id,
-		       time_t			*endtime,
+		       time64_t			*endtime,
 		       gfp_t gfp_mask)
 {
 	if (!(*ctx_id = kzalloc(sizeof(**ctx_id), gfp_mask)))
@@ -438,10 +444,11 @@ gss_wrap(struct gss_ctx	*ctx_id,
 u32
 gss_unwrap(struct gss_ctx	*ctx_id,
 	   int			offset,
+	   int			len,
 	   struct xdr_buf	*buf)
 {
 	return ctx_id->mech_type->gm_ops
-		->gss_unwrap(ctx_id, offset, buf);
+		->gss_unwrap(ctx_id, offset, len, buf);
 }
 
 
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 8be2f209982b..0bd2df7f2503 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -433,7 +433,7 @@ static int rsc_parse(struct cache_detail *cd,
 	int id;
 	int len, rv;
 	struct rsc rsci, *rscp = NULL;
-	time_t expiry;
+	time64_t expiry;
 	int status = -EINVAL;
 	struct gss_api_mech *gm = NULL;
 
@@ -800,7 +800,7 @@ u32 svcauth_gss_flavor(struct auth_domain *dom)
 
 EXPORT_SYMBOL_GPL(svcauth_gss_flavor);
 
-int
+struct auth_domain *
 svcauth_gss_register_pseudoflavor(u32 pseudoflavor, char * name)
 {
 	struct gss_domain	*new;
@@ -817,21 +817,23 @@ svcauth_gss_register_pseudoflavor(u32 pseudoflavor, char * name)
 	new->h.flavour = &svcauthops_gss;
 	new->pseudoflavor = pseudoflavor;
 
-	stat = 0;
 	test = auth_domain_lookup(name, &new->h);
-	if (test != &new->h) { /* Duplicate registration */
+	if (test != &new->h) {
+		pr_warn("svc: duplicate registration of gss pseudo flavour %s.\n",
+			name);
+		stat = -EADDRINUSE;
 		auth_domain_put(test);
-		kfree(new->h.name);
-		goto out_free_dom;
+		goto out_free_name;
 	}
-	return 0;
+	return test;
 
+out_free_name:
+	kfree(new->h.name);
 out_free_dom:
 	kfree(new);
 out:
-	return stat;
+	return ERR_PTR(stat);
 }
-
 EXPORT_SYMBOL_GPL(svcauth_gss_register_pseudoflavor);
 
 static inline int
@@ -897,7 +899,7 @@ unwrap_integ_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct g
 	if (svc_getnl(&buf->head[0]) != seq)
 		goto out;
 	/* trim off the mic and padding at the end before returning */
-	buf->len -= 4 + round_up_to_quad(mic.len);
+	xdr_buf_trim(buf, round_up_to_quad(mic.len) + 4);
 	stat = 0;
 out:
 	kfree(mic.data);
@@ -925,7 +927,7 @@ static int
 unwrap_priv_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gss_ctx *ctx)
 {
 	u32 priv_len, maj_stat;
-	int pad, saved_len, remaining_len, offset;
+	int pad, remaining_len, offset;
 
 	clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
 
@@ -945,13 +947,8 @@ unwrap_priv_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gs
 	buf->len -= pad;
 	fix_priv_head(buf, pad);
 
-	/* Maybe it would be better to give gss_unwrap a length parameter: */
-	saved_len = buf->len;
-	buf->len = priv_len;
-	maj_stat = gss_unwrap(ctx, 0, buf);
+	maj_stat = gss_unwrap(ctx, 0, priv_len, buf);
 	pad = priv_len - buf->len;
-	buf->len = saved_len;
-	buf->len -= pad;
 	/* The upper layers assume the buffer is aligned on 4-byte boundaries.
 	 * In the krb5p case, at least, the data ends up offset, so we need to
 	 * move it around. */
@@ -1075,24 +1072,32 @@ gss_read_verf(struct rpc_gss_wire_cred *gc,
 	return 0;
 }
 
-/* Ok this is really heavily depending on a set of semantics in
- * how rqstp is set up by svc_recv and pages laid down by the
- * server when reading a request. We are basically guaranteed that
- * the token lays all down linearly across a set of pages, starting
- * at iov_base in rq_arg.head[0] which happens to be the first of a
- * set of pages stored in rq_pages[].
- * rq_arg.head[0].iov_base will provide us the page_base to pass
- * to the upcall.
- */
-static inline int
-gss_read_proxy_verf(struct svc_rqst *rqstp,
-		    struct rpc_gss_wire_cred *gc, __be32 *authp,
-		    struct xdr_netobj *in_handle,
-		    struct gssp_in_token *in_token)
+static void gss_free_in_token_pages(struct gssp_in_token *in_token)
 {
-	struct kvec *argv = &rqstp->rq_arg.head[0];
 	u32 inlen;
-	int res;
+	int i;
+
+	i = 0;
+	inlen = in_token->page_len;
+	while (inlen) {
+		if (in_token->pages[i])
+			put_page(in_token->pages[i]);
+		inlen -= inlen > PAGE_SIZE ? PAGE_SIZE : inlen;
+	}
+
+	kfree(in_token->pages);
+	in_token->pages = NULL;
+}
+
+static int gss_read_proxy_verf(struct svc_rqst *rqstp,
+			       struct rpc_gss_wire_cred *gc, __be32 *authp,
+			       struct xdr_netobj *in_handle,
+			       struct gssp_in_token *in_token)
+{
+	struct kvec *argv = &rqstp->rq_arg.head[0];
+	unsigned int page_base, length;
+	int pages, i, res;
+	size_t inlen;
 
 	res = gss_read_common_verf(gc, argv, authp, in_handle);
 	if (res)
@@ -1102,10 +1107,36 @@ gss_read_proxy_verf(struct svc_rqst *rqstp,
 	if (inlen > (argv->iov_len + rqstp->rq_arg.page_len))
 		return SVC_DENIED;
 
-	in_token->pages = rqstp->rq_pages;
-	in_token->page_base = (ulong)argv->iov_base & ~PAGE_MASK;
+	pages = DIV_ROUND_UP(inlen, PAGE_SIZE);
+	in_token->pages = kcalloc(pages, sizeof(struct page *), GFP_KERNEL);
+	if (!in_token->pages)
+		return SVC_DENIED;
+	in_token->page_base = 0;
 	in_token->page_len = inlen;
+	for (i = 0; i < pages; i++) {
+		in_token->pages[i] = alloc_page(GFP_KERNEL);
+		if (!in_token->pages[i]) {
+			gss_free_in_token_pages(in_token);
+			return SVC_DENIED;
+		}
+	}
 
+	length = min_t(unsigned int, inlen, argv->iov_len);
+	memcpy(page_address(in_token->pages[0]), argv->iov_base, length);
+	inlen -= length;
+
+	i = 1;
+	page_base = rqstp->rq_arg.page_base;
+	while (inlen) {
+		length = min_t(unsigned int, inlen, PAGE_SIZE);
+		memcpy(page_address(in_token->pages[i]),
+		       page_address(rqstp->rq_arg.pages[i]) + page_base,
+		       length);
+
+		inlen -= length;
+		page_base = 0;
+		i++;
+	}
 	return 0;
 }
 
@@ -1184,7 +1215,7 @@ static int gss_proxy_save_rsc(struct cache_detail *cd,
 	static atomic64_t ctxhctr;
 	long long ctxh;
 	struct gss_api_mech *gm = NULL;
-	time_t expiry;
+	time64_t expiry;
 	int status = -EINVAL;
 
 	memset(&rsci, 0, sizeof(rsci));
@@ -1211,6 +1242,7 @@ static int gss_proxy_save_rsc(struct cache_detail *cd,
 		dprintk("RPC:       No creds found!\n");
 		goto out;
 	} else {
+		struct timespec64 boot;
 
 		/* steal creds */
 		rsci.cred = ud->creds;
@@ -1231,6 +1263,9 @@ static int gss_proxy_save_rsc(struct cache_detail *cd,
 						&expiry, GFP_KERNEL);
 		if (status)
 			goto out;
+
+		getboottime64(&boot);
+		expiry -= boot.tv_sec;
 	}
 
 	rsci.h.expiry_time = expiry;
@@ -1280,8 +1315,11 @@ static int svcauth_gss_proxy_init(struct svc_rqst *rqstp,
 		break;
 	case GSS_S_COMPLETE:
 		status = gss_proxy_save_rsc(sn->rsc_cache, &ud, &handle);
-		if (status)
+		if (status) {
+			pr_info("%s: gss_proxy_save_rsc failed (%d)\n",
+				__func__, status);
 			goto out;
+		}
 		cli_handle.data = (u8 *)&handle;
 		cli_handle.len = sizeof(handle);
 		break;
@@ -1292,15 +1330,20 @@ static int svcauth_gss_proxy_init(struct svc_rqst *rqstp,
 
 	/* Got an answer to the upcall; use it: */
 	if (gss_write_init_verf(sn->rsc_cache, rqstp,
-				&cli_handle, &ud.major_status))
+				&cli_handle, &ud.major_status)) {
+		pr_info("%s: gss_write_init_verf failed\n", __func__);
 		goto out;
+	}
 	if (gss_write_resv(resv, PAGE_SIZE,
 			   &cli_handle, &ud.out_token,
-			   ud.major_status, ud.minor_status))
+			   ud.major_status, ud.minor_status)) {
+		pr_info("%s: gss_write_resv failed\n", __func__);
 		goto out;
+	}
 
 	ret = SVC_COMPLETE;
 out:
+	gss_free_in_token_pages(&ud.in_token);
 	gssp_free_upcall_data(&ud);
 	return ret;
 }
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 66fbb9d2fba7..1270d26990fb 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -53,9 +53,6 @@ static void cache_init(struct cache_head *h, struct cache_detail *detail)
 	h->last_refresh = now;
 }
 
-static inline int cache_is_valid(struct cache_head *h);
-static void cache_fresh_locked(struct cache_head *head, time_t expiry,
-				struct cache_detail *detail);
 static void cache_fresh_unlocked(struct cache_head *head,
 				struct cache_detail *detail);
 
@@ -105,9 +102,6 @@ static struct cache_head *sunrpc_cache_add_entry(struct cache_detail *detail,
 			if (cache_is_expired(detail, tmp)) {
 				hlist_del_init_rcu(&tmp->cache_list);
 				detail->entries --;
-				if (cache_is_valid(tmp) == -EAGAIN)
-					set_bit(CACHE_NEGATIVE, &tmp->flags);
-				cache_fresh_locked(tmp, 0, detail);
 				freeme = tmp;
 				break;
 			}
@@ -1888,7 +1882,9 @@ void sunrpc_cache_unhash(struct cache_detail *cd, struct cache_head *h)
 	if (!hlist_unhashed(&h->cache_list)){
 		hlist_del_init_rcu(&h->cache_list);
 		cd->entries--;
+		set_bit(CACHE_CLEANED, &h->flags);
 		spin_unlock(&cd->hash_lock);
+		cache_fresh_unlocked(h, cd);
 		cache_put(h, cd);
 	} else
 		spin_unlock(&cd->hash_lock);
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index d504d3a895d1..62bd29c849c1 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -2341,6 +2341,11 @@ rpc_check_timeout(struct rpc_task *task)
 {
 	struct rpc_clnt	*clnt = task->tk_client;
 
+	if (RPC_SIGNALLED(task)) {
+		rpc_call_rpcerror(task, -ERESTARTSYS);
+		return;
+	}
+
 	if (xprt_adjust_timeout(task->tk_rqstp) == 0)
 		return;
 
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index 126d31472a99..be04bafcdb7f 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -1312,6 +1312,7 @@ rpc_gssd_dummy_populate(struct dentry *root, struct rpc_pipe *pipe_data)
 	q.len = strlen(gssd_dummy_clnt_dir[0].name);
 	clnt_dentry = d_hash_and_lookup(gssd_dentry, &q);
 	if (!clnt_dentry) {
+		__rpc_depopulate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1);
 		pipe_dentry = ERR_PTR(-ENOENT);
 		goto out;
 	}
diff --git a/net/sunrpc/sunrpc.h b/net/sunrpc/sunrpc.h
index c9bacb3c930f..82035fa65b8f 100644
--- a/net/sunrpc/sunrpc.h
+++ b/net/sunrpc/sunrpc.h
@@ -56,4 +56,5 @@ int svc_send_common(struct socket *sock, struct xdr_buf *xdr,
 
 int rpc_clients_notifier_register(void);
 void rpc_clients_notifier_unregister(void);
+void auth_domain_cleanup(void);
 #endif /* _NET_SUNRPC_SUNRPC_H */
diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c
index f9edaa9174a4..236fadc4a439 100644
--- a/net/sunrpc/sunrpc_syms.c
+++ b/net/sunrpc/sunrpc_syms.c
@@ -23,6 +23,7 @@
 #include <linux/sunrpc/rpc_pipe_fs.h>
 #include <linux/sunrpc/xprtsock.h>
 
+#include "sunrpc.h"
 #include "netns.h"
 
 unsigned int sunrpc_net_id;
@@ -131,6 +132,7 @@ cleanup_sunrpc(void)
 	unregister_rpc_pipefs();
 	rpc_destroy_mempool();
 	unregister_pernet_subsys(&sunrpc_net_ops);
+	auth_domain_cleanup();
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	rpc_unregister_sysctl();
 #endif
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index e15cb704453e..f843d27452c9 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1635,6 +1635,22 @@ u32 svc_max_payload(const struct svc_rqst *rqstp)
 EXPORT_SYMBOL_GPL(svc_max_payload);
 
 /**
+ * svc_encode_read_payload - mark a range of bytes as a READ payload
+ * @rqstp: svc_rqst to operate on
+ * @offset: payload's byte offset in rqstp->rq_res
+ * @length: size of payload, in bytes
+ *
+ * Returns zero on success, or a negative errno if a permanent
+ * error occurred.
+ */
+int svc_encode_read_payload(struct svc_rqst *rqstp, unsigned int offset,
+			    unsigned int length)
+{
+	return rqstp->rq_xprt->xpt_ops->xpo_read_payload(rqstp, offset, length);
+}
+EXPORT_SYMBOL_GPL(svc_encode_read_payload);
+
+/**
  * svc_fill_write_vector - Construct data argument for VFS write call
  * @rqstp: svc_rqst to operate on
  * @pages: list of pages containing data payload
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 869ce7737997..26384a36237e 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -897,9 +897,6 @@ int svc_send(struct svc_rqst *rqstp)
 	if (!xprt)
 		goto out;
 
-	/* release the receive skb before sending the reply */
-	xprt->xpt_ops->xpo_release_rqst(rqstp);
-
 	/* calculate over-all length */
 	xb = &rqstp->rq_res;
 	xb->len = xb->head[0].iov_len +
@@ -1028,6 +1025,8 @@ static void svc_delete_xprt(struct svc_xprt *xprt)
 
 	dprintk("svc: svc_delete_xprt(%p)\n", xprt);
 	xprt->xpt_ops->xpo_detach(xprt);
+	if (xprt->xpt_bc_xprt)
+		xprt->xpt_bc_xprt->ops->close(xprt->xpt_bc_xprt);
 
 	spin_lock_bh(&serv->sv_lock);
 	list_del_init(&xprt->xpt_list);
diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c
index 550b214cb001..998b196b6176 100644
--- a/net/sunrpc/svcauth.c
+++ b/net/sunrpc/svcauth.c
@@ -19,6 +19,10 @@
 #include <linux/err.h>
 #include <linux/hash.h>
 
+#include <trace/events/sunrpc.h>
+
+#include "sunrpc.h"
+
 #define RPCDBG_FACILITY	RPCDBG_AUTH
 
 
@@ -203,3 +207,26 @@ struct auth_domain *auth_domain_find(char *name)
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(auth_domain_find);
+
+/**
+ * auth_domain_cleanup - check that the auth_domain table is empty
+ *
+ * On module unload the auth_domain_table must be empty.  To make it
+ * easier to catch bugs which don't clean up domains properly, we
+ * warn if anything remains in the table at cleanup time.
+ *
+ * Note that we cannot proactively remove the domains at this stage.
+ * The ->release() function might be in a module that has already been
+ * unloaded.
+ */
+
+void auth_domain_cleanup(void)
+{
+	int h;
+	struct auth_domain *hp;
+
+	for (h = 0; h < DN_HASHMAX; h++)
+		hlist_for_each_entry(hp, &auth_domain_table[h], hash)
+			pr_warn("svc: domain %s still present at module unload.\n",
+				hp->name);
+}
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 2934dd711715..d52abde51f1b 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -279,6 +279,12 @@ out:
 	return len;
 }
 
+static int svc_sock_read_payload(struct svc_rqst *rqstp, unsigned int offset,
+				 unsigned int length)
+{
+	return 0;
+}
+
 /*
  * Report socket names for nfsdfs
  */
@@ -605,6 +611,8 @@ svc_udp_sendto(struct svc_rqst *rqstp)
 {
 	int		error;
 
+	svc_release_udp_skb(rqstp);
+
 	error = svc_sendto(rqstp, &rqstp->rq_res);
 	if (error == -ECONNREFUSED)
 		/* ICMP error on earlier request. */
@@ -653,6 +661,7 @@ static const struct svc_xprt_ops svc_udp_ops = {
 	.xpo_create = svc_udp_create,
 	.xpo_recvfrom = svc_udp_recvfrom,
 	.xpo_sendto = svc_udp_sendto,
+	.xpo_read_payload = svc_sock_read_payload,
 	.xpo_release_rqst = svc_release_udp_skb,
 	.xpo_detach = svc_sock_detach,
 	.xpo_free = svc_sock_free,
@@ -1137,6 +1146,8 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp)
 	int sent;
 	__be32 reclen;
 
+	svc_release_skb(rqstp);
+
 	/* Set up the first element of the reply kvec.
 	 * Any other kvecs that may be in use have been taken
 	 * care of by the server implementation itself.
@@ -1171,6 +1182,7 @@ static const struct svc_xprt_ops svc_tcp_ops = {
 	.xpo_create = svc_tcp_create,
 	.xpo_recvfrom = svc_tcp_recvfrom,
 	.xpo_sendto = svc_tcp_sendto,
+	.xpo_read_payload = svc_sock_read_payload,
 	.xpo_release_rqst = svc_release_skb,
 	.xpo_detach = svc_tcp_sock_detach,
 	.xpo_free = svc_sock_free,
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index db116fc8ff44..683f058b9061 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -1118,6 +1118,7 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf,
 		base = 0;
 	} else {
 		base -= buf->head[0].iov_len;
+		subbuf->head[0].iov_base = buf->head[0].iov_base;
 		subbuf->head[0].iov_len = 0;
 	}
 
@@ -1130,6 +1131,8 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf,
 		base = 0;
 	} else {
 		base -= buf->page_len;
+		subbuf->pages = buf->pages;
+		subbuf->page_base = 0;
 		subbuf->page_len = 0;
 	}
 
@@ -1141,6 +1144,7 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf,
 		base = 0;
 	} else {
 		base -= buf->tail[0].iov_len;
+		subbuf->tail[0].iov_base = buf->tail[0].iov_base;
 		subbuf->tail[0].iov_len = 0;
 	}
 
@@ -1150,6 +1154,47 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf,
 }
 EXPORT_SYMBOL_GPL(xdr_buf_subsegment);
 
+/**
+ * xdr_buf_trim - lop at most "len" bytes off the end of "buf"
+ * @buf: buf to be trimmed
+ * @len: number of bytes to reduce "buf" by
+ *
+ * Trim an xdr_buf by the given number of bytes by fixing up the lengths. Note
+ * that it's possible that we'll trim less than that amount if the xdr_buf is
+ * too small, or if (for instance) it's all in the head and the parser has
+ * already read too far into it.
+ */
+void xdr_buf_trim(struct xdr_buf *buf, unsigned int len)
+{
+	size_t cur;
+	unsigned int trim = len;
+
+	if (buf->tail[0].iov_len) {
+		cur = min_t(size_t, buf->tail[0].iov_len, trim);
+		buf->tail[0].iov_len -= cur;
+		trim -= cur;
+		if (!trim)
+			goto fix_len;
+	}
+
+	if (buf->page_len) {
+		cur = min_t(unsigned int, buf->page_len, trim);
+		buf->page_len -= cur;
+		trim -= cur;
+		if (!trim)
+			goto fix_len;
+	}
+
+	if (buf->head[0].iov_len) {
+		cur = min_t(size_t, buf->head[0].iov_len, trim);
+		buf->head[0].iov_len -= cur;
+		trim -= cur;
+	}
+fix_len:
+	buf->len -= (len - trim);
+}
+EXPORT_SYMBOL_GPL(xdr_buf_trim);
+
 static void __read_bytes_from_xdr_buf(struct xdr_buf *subbuf, void *obj, unsigned int len)
 {
 	unsigned int this_len;
@@ -1235,52 +1280,60 @@ xdr_encode_word(struct xdr_buf *buf, unsigned int base, u32 obj)
 }
 EXPORT_SYMBOL_GPL(xdr_encode_word);
 
-/* If the netobj starting offset bytes from the start of xdr_buf is contained
- * entirely in the head, pages, or tail, set object to point to it; otherwise
- * shift the buffer until it is contained entirely within the pages or tail.
+/**
+ * xdr_buf_read_mic() - obtain the address of the GSS mic from xdr buf
+ * @buf: pointer to buffer containing a mic
+ * @mic: on success, returns the address of the mic
+ * @offset: the offset in buf where mic may be found
+ *
+ * This function may modify the xdr buf if the mic is found to be straddling
+ * a boundary between head, pages, and tail.  On success the mic can be read
+ * from the address returned.  There is no need to free the mic.
+ *
+ * Return: Success returns 0, otherwise an integer error.
  */
-int xdr_buf_read_netobj(struct xdr_buf *buf, struct xdr_netobj *obj, unsigned int offset)
+int xdr_buf_read_mic(struct xdr_buf *buf, struct xdr_netobj *mic, unsigned int offset)
 {
 	struct xdr_buf subbuf;
 	unsigned int boundary;
 
-	if (xdr_decode_word(buf, offset, &obj->len))
+	if (xdr_decode_word(buf, offset, &mic->len))
 		return -EFAULT;
 	offset += 4;
 
-	/* Is the obj partially in the head? */
+	/* Is the mic partially in the head? */
 	boundary = buf->head[0].iov_len;
-	if (offset < boundary && (offset + obj->len) > boundary)
+	if (offset < boundary && (offset + mic->len) > boundary)
 		xdr_shift_buf(buf, boundary - offset);
 
-	/* Is the obj partially in the pages? */
+	/* Is the mic partially in the pages? */
 	boundary += buf->page_len;
-	if (offset < boundary && (offset + obj->len) > boundary)
+	if (offset < boundary && (offset + mic->len) > boundary)
 		xdr_shrink_pagelen(buf, boundary - offset);
 
-	if (xdr_buf_subsegment(buf, &subbuf, offset, obj->len))
+	if (xdr_buf_subsegment(buf, &subbuf, offset, mic->len))
 		return -EFAULT;
 
-	/* Is the obj contained entirely in the head? */
-	obj->data = subbuf.head[0].iov_base;
-	if (subbuf.head[0].iov_len == obj->len)
+	/* Is the mic contained entirely in the head? */
+	mic->data = subbuf.head[0].iov_base;
+	if (subbuf.head[0].iov_len == mic->len)
 		return 0;
-	/* ..or is the obj contained entirely in the tail? */
-	obj->data = subbuf.tail[0].iov_base;
-	if (subbuf.tail[0].iov_len == obj->len)
+	/* ..or is the mic contained entirely in the tail? */
+	mic->data = subbuf.tail[0].iov_base;
+	if (subbuf.tail[0].iov_len == mic->len)
 		return 0;
 
-	/* Find a contiguous area in @buf to hold all of @obj */
-	if (obj->len > buf->buflen - buf->len)
+	/* Find a contiguous area in @buf to hold all of @mic */
+	if (mic->len > buf->buflen - buf->len)
 		return -ENOMEM;
 	if (buf->tail[0].iov_len != 0)
-		obj->data = buf->tail[0].iov_base + buf->tail[0].iov_len;
+		mic->data = buf->tail[0].iov_base + buf->tail[0].iov_len;
 	else
-		obj->data = buf->head[0].iov_base + buf->head[0].iov_len;
-	__read_bytes_from_xdr_buf(&subbuf, obj->data, obj->len);
+		mic->data = buf->head[0].iov_base + buf->head[0].iov_len;
+	__read_bytes_from_xdr_buf(&subbuf, mic->data, mic->len);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(xdr_buf_read_netobj);
+EXPORT_SYMBOL_GPL(xdr_buf_read_mic);
 
 /* Returns 0 on success, or else a negative error code. */
 static int
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index 794ba4ca0994..7b1694c0a77e 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -381,8 +381,8 @@ struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt,
 	struct rpcrdma_frwr *frwr;
 	struct rpcrdma_mr *mr;
 	struct ib_mr *ibmr;
+	int i, n, dma_nents;
 	struct ib_reg_wr *reg_wr;
-	int i, n;
 	u8 key;
 
 	mr = NULL;
@@ -417,15 +417,16 @@ struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt,
 			break;
 	}
 	mr->mr_dir = rpcrdma_data_dir(writing);
+	mr->mr_nents = i;
 
-	mr->mr_nents =
-		ib_dma_map_sg(ia->ri_id->device, mr->mr_sg, i, mr->mr_dir);
-	if (!mr->mr_nents)
+	dma_nents = ib_dma_map_sg(ia->ri_id->device, mr->mr_sg, mr->mr_nents,
+				  mr->mr_dir);
+	if (!dma_nents)
 		goto out_dmamap_err;
 
 	ibmr = frwr->fr_mr;
-	n = ib_map_mr_sg(ibmr, mr->mr_sg, mr->mr_nents, NULL, PAGE_SIZE);
-	if (unlikely(n != mr->mr_nents))
+	n = ib_map_mr_sg(ibmr, mr->mr_sg, dma_nents, NULL, PAGE_SIZE);
+	if (n != dma_nents)
 		goto out_mapmr_err;
 
 	ibmr->iova &= 0x00000000ffffffff;
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 85115a2e2639..77a911d14015 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -71,7 +71,7 @@ static unsigned int rpcrdma_max_call_header_size(unsigned int maxsegs)
 	size = RPCRDMA_HDRLEN_MIN;
 
 	/* Maximum Read list size */
-	size = maxsegs * rpcrdma_readchunk_maxsz * sizeof(__be32);
+	size += maxsegs * rpcrdma_readchunk_maxsz * sizeof(__be32);
 
 	/* Minimal Read chunk size */
 	size += sizeof(__be32);	/* segment count */
@@ -96,7 +96,7 @@ static unsigned int rpcrdma_max_reply_header_size(unsigned int maxsegs)
 	size = RPCRDMA_HDRLEN_MIN;
 
 	/* Maximum Write list size */
-	size = sizeof(__be32);		/* segment count */
+	size += sizeof(__be32);		/* segment count */
 	size += maxsegs * rpcrdma_segment_maxsz * sizeof(__be32);
 	size += sizeof(__be32);	/* list discriminator */
 
@@ -1219,8 +1219,7 @@ rpcrdma_decode_error(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep,
 			be32_to_cpup(p), be32_to_cpu(rep->rr_xid));
 	}
 
-	r_xprt->rx_stats.bad_reply_count++;
-	return -EREMOTEIO;
+	return -EIO;
 }
 
 /* Perform XID lookup, reconstruction of the RPC reply, and
@@ -1259,13 +1258,11 @@ out:
 	spin_unlock(&xprt->queue_lock);
 	return;
 
-/* If the incoming reply terminated a pending RPC, the next
- * RPC call will post a replacement receive buffer as it is
- * being marshaled.
- */
 out_badheader:
 	trace_xprtrdma_reply_hdr(rep);
 	r_xprt->rx_stats.bad_reply_count++;
+	rqst->rq_task->tk_status = status;
+	status = 0;
 	goto out;
 }
 
@@ -1365,6 +1362,7 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep)
 		xprt->cwnd = credits << RPC_CWNDSHIFT;
 		spin_unlock_bh(&xprt->transport_lock);
 	}
+	rpcrdma_post_recvs(r_xprt, false);
 
 	req = rpcr_to_rdmar(rqst);
 	if (req->rl_reply) {
diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index bed57d8b5c19..6436b65f11fb 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -195,6 +195,7 @@ rpcrdma_bc_send_request(struct svcxprt_rdma *rdma, struct rpc_rqst *rqst)
 	pr_info("%s: %*ph\n", __func__, 64, rqst->rq_buffer);
 #endif
 
+	rqst->rq_xtime = ktime_get();
 	rc = svc_rdma_bc_sendto(rdma, rqst, ctxt);
 	if (rc) {
 		svc_rdma_send_ctxt_put(rdma, ctxt);
@@ -241,6 +242,8 @@ static void
 xprt_rdma_bc_close(struct rpc_xprt *xprt)
 {
 	dprintk("svcrdma: %s: xprt %p\n", __func__, xprt);
+
+	xprt_disconnect_done(xprt);
 	xprt->cwnd = RPC_CWNDSHIFT;
 }
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 65e2fb9aac65..6566620912d6 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -193,6 +193,7 @@ svc_rdma_recv_ctxt_get(struct svcxprt_rdma *rdma)
 
 out:
 	ctxt->rc_page_count = 0;
+	ctxt->rc_read_payload_length = 0;
 	return ctxt;
 
 out_empty:
@@ -226,6 +227,26 @@ void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma,
 		svc_rdma_recv_ctxt_destroy(rdma, ctxt);
 }
 
+/**
+ * svc_rdma_release_rqst - Release transport-specific per-rqst resources
+ * @rqstp: svc_rqst being released
+ *
+ * Ensure that the recv_ctxt is released whether or not a Reply
+ * was sent. For example, the client could close the connection,
+ * or svc_process could drop an RPC, before the Reply is sent.
+ */
+void svc_rdma_release_rqst(struct svc_rqst *rqstp)
+{
+	struct svc_rdma_recv_ctxt *ctxt = rqstp->rq_xprt_ctxt;
+	struct svc_xprt *xprt = rqstp->rq_xprt;
+	struct svcxprt_rdma *rdma =
+		container_of(xprt, struct svcxprt_rdma, sc_xprt);
+
+	rqstp->rq_xprt_ctxt = NULL;
+	if (ctxt)
+		svc_rdma_recv_ctxt_put(rdma, ctxt);
+}
+
 static int __svc_rdma_post_recv(struct svcxprt_rdma *rdma,
 				struct svc_rdma_recv_ctxt *ctxt)
 {
@@ -760,6 +781,8 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 	__be32 *p;
 	int ret;
 
+	rqstp->rq_xprt_ctxt = NULL;
+
 	spin_lock(&rdma_xprt->sc_rq_dto_lock);
 	ctxt = svc_rdma_next_recv_ctxt(&rdma_xprt->sc_read_complete_q);
 	if (ctxt) {
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index 2121c9b4d275..04ec2a83af69 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -322,8 +322,6 @@ static int svc_rdma_post_chunk_ctxt(struct svc_rdma_chunk_ctxt *cc)
 		if (atomic_sub_return(cc->cc_sqecount,
 				      &rdma->sc_sq_avail) > 0) {
 			ret = ib_post_send(rdma->sc_qp, first_wr, &bad_wr);
-			trace_svcrdma_post_rw(&cc->cc_cqe,
-					      cc->cc_sqecount, ret);
 			if (ret)
 				break;
 			return 0;
@@ -336,6 +334,7 @@ static int svc_rdma_post_chunk_ctxt(struct svc_rdma_chunk_ctxt *cc)
 		trace_svcrdma_sq_retry(rdma);
 	} while (1);
 
+	trace_svcrdma_sq_post_err(rdma, ret);
 	set_bit(XPT_CLOSE, &xprt->xpt_flags);
 
 	/* If even one was posted, there will be a completion. */
@@ -481,18 +480,19 @@ static int svc_rdma_send_xdr_kvec(struct svc_rdma_write_info *info,
 				     vec->iov_len);
 }
 
-/* Send an xdr_buf's page list by itself. A Write chunk is
- * just the page list. a Reply chunk is the head, page list,
- * and tail. This function is shared between the two types
- * of chunk.
+/* Send an xdr_buf's page list by itself. A Write chunk is just
+ * the page list. A Reply chunk is @xdr's head, page list, and
+ * tail. This function is shared between the two types of chunk.
  */
 static int svc_rdma_send_xdr_pagelist(struct svc_rdma_write_info *info,
-				      struct xdr_buf *xdr)
+				      struct xdr_buf *xdr,
+				      unsigned int offset,
+				      unsigned long length)
 {
 	info->wi_xdr = xdr;
-	info->wi_next_off = 0;
+	info->wi_next_off = offset - xdr->head[0].iov_len;
 	return svc_rdma_build_writes(info, svc_rdma_pagelist_to_sg,
-				     xdr->page_len);
+				     length);
 }
 
 /**
@@ -500,6 +500,8 @@ static int svc_rdma_send_xdr_pagelist(struct svc_rdma_write_info *info,
  * @rdma: controlling RDMA transport
  * @wr_ch: Write chunk provided by client
  * @xdr: xdr_buf containing the data payload
+ * @offset: payload's byte offset in @xdr
+ * @length: size of payload, in bytes
  *
  * Returns a non-negative number of bytes the chunk consumed, or
  *	%-E2BIG if the payload was larger than the Write chunk,
@@ -509,19 +511,20 @@ static int svc_rdma_send_xdr_pagelist(struct svc_rdma_write_info *info,
  *	%-EIO if rdma_rw initialization failed (DMA mapping, etc).
  */
 int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma, __be32 *wr_ch,
-			      struct xdr_buf *xdr)
+			      struct xdr_buf *xdr,
+			      unsigned int offset, unsigned long length)
 {
 	struct svc_rdma_write_info *info;
 	int ret;
 
-	if (!xdr->page_len)
+	if (!length)
 		return 0;
 
 	info = svc_rdma_write_info_alloc(rdma, wr_ch);
 	if (!info)
 		return -ENOMEM;
 
-	ret = svc_rdma_send_xdr_pagelist(info, xdr);
+	ret = svc_rdma_send_xdr_pagelist(info, xdr, offset, length);
 	if (ret < 0)
 		goto out_err;
 
@@ -530,7 +533,7 @@ int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma, __be32 *wr_ch,
 		goto out_err;
 
 	trace_svcrdma_encode_write(xdr->page_len);
-	return xdr->page_len;
+	return length;
 
 out_err:
 	svc_rdma_write_info_free(info);
@@ -570,7 +573,9 @@ int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma, __be32 *rp_ch,
 	 * client did not provide Write chunks.
 	 */
 	if (!writelist && xdr->page_len) {
-		ret = svc_rdma_send_xdr_pagelist(info, xdr);
+		ret = svc_rdma_send_xdr_pagelist(info, xdr,
+						 xdr->head[0].iov_len,
+						 xdr->page_len);
 		if (ret < 0)
 			goto out_err;
 		consumed += xdr->page_len;
@@ -671,7 +676,6 @@ static int svc_rdma_build_read_chunk(struct svc_rqst *rqstp,
 				     struct svc_rdma_read_info *info,
 				     __be32 *p)
 {
-	unsigned int i;
 	int ret;
 
 	ret = -EINVAL;
@@ -694,12 +698,6 @@ static int svc_rdma_build_read_chunk(struct svc_rqst *rqstp,
 		info->ri_chunklen += rs_length;
 	}
 
-	/* Pages under I/O have been copied to head->rc_pages.
-	 * Prevent their premature release by svc_xprt_release() .
-	 */
-	for (i = 0; i < info->ri_readctxt->rc_page_count; i++)
-		rqstp->rq_pages[i] = NULL;
-
 	return ret;
 }
 
@@ -794,6 +792,26 @@ out:
 	return ret;
 }
 
+/* Pages under I/O have been copied to head->rc_pages. Ensure they
+ * are not released by svc_xprt_release() until the I/O is complete.
+ *
+ * This has to be done after all Read WRs are constructed to properly
+ * handle a page that is part of I/O on behalf of two different RDMA
+ * segments.
+ *
+ * Do this only if I/O has been posted. Otherwise, we do indeed want
+ * svc_xprt_release() to clean things up properly.
+ */
+static void svc_rdma_save_io_pages(struct svc_rqst *rqstp,
+				   const unsigned int start,
+				   const unsigned int num_pages)
+{
+	unsigned int i;
+
+	for (i = start; i < num_pages + start; i++)
+		rqstp->rq_pages[i] = NULL;
+}
+
 /**
  * svc_rdma_recv_read_chunk - Pull a Read chunk from the client
  * @rdma: controlling RDMA transport
@@ -847,6 +865,7 @@ int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma, struct svc_rqst *rqstp,
 	ret = svc_rdma_post_chunk_ctxt(&info->ri_cc);
 	if (ret < 0)
 		goto out_err;
+	svc_rdma_save_io_pages(rqstp, 0, head->rc_page_count);
 	return 0;
 
 out_err:
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 6fdba72f89f4..217106c66a13 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -306,15 +306,17 @@ int svc_rdma_send(struct svcxprt_rdma *rdma, struct ib_send_wr *wr)
 		}
 
 		svc_xprt_get(&rdma->sc_xprt);
+		trace_svcrdma_post_send(wr);
 		ret = ib_post_send(rdma->sc_qp, wr, NULL);
-		trace_svcrdma_post_send(wr, ret);
-		if (ret) {
-			set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags);
-			svc_xprt_put(&rdma->sc_xprt);
-			wake_up(&rdma->sc_send_wait);
-		}
-		break;
+		if (ret)
+			break;
+		return 0;
 	}
+
+	trace_svcrdma_sq_post_err(rdma, ret);
+	set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags);
+	svc_xprt_put(&rdma->sc_xprt);
+	wake_up(&rdma->sc_send_wait);
 	return ret;
 }
 
@@ -854,7 +856,18 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
 
 	if (wr_lst) {
 		/* XXX: Presume the client sent only one Write chunk */
-		ret = svc_rdma_send_write_chunk(rdma, wr_lst, xdr);
+		unsigned long offset;
+		unsigned int length;
+
+		if (rctxt->rc_read_payload_length) {
+			offset = rctxt->rc_read_payload_offset;
+			length = rctxt->rc_read_payload_length;
+		} else {
+			offset = xdr->head[0].iov_len;
+			length = xdr->page_len;
+		}
+		ret = svc_rdma_send_write_chunk(rdma, wr_lst, xdr, offset,
+						length);
 		if (ret < 0)
 			goto err2;
 		svc_rdma_xdr_encode_write_list(rdma_resp, wr_lst, ret);
@@ -871,12 +884,7 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
 				      wr_lst, rp_ch);
 	if (ret < 0)
 		goto err1;
-	ret = 0;
-
-out:
-	rqstp->rq_xprt_ctxt = NULL;
-	svc_rdma_recv_ctxt_put(rdma, rctxt);
-	return ret;
+	return 0;
 
  err2:
 	if (ret != -E2BIG && ret != -EINVAL)
@@ -885,14 +893,39 @@ out:
 	ret = svc_rdma_send_error_msg(rdma, sctxt, rqstp);
 	if (ret < 0)
 		goto err1;
-	ret = 0;
-	goto out;
+	return 0;
 
  err1:
 	svc_rdma_send_ctxt_put(rdma, sctxt);
  err0:
 	trace_svcrdma_send_failed(rqstp, ret);
 	set_bit(XPT_CLOSE, &xprt->xpt_flags);
-	ret = -ENOTCONN;
-	goto out;
+	return -ENOTCONN;
+}
+
+/**
+ * svc_rdma_read_payload - special processing for a READ payload
+ * @rqstp: svc_rqst to operate on
+ * @offset: payload's byte offset in @xdr
+ * @length: size of payload, in bytes
+ *
+ * Returns zero on success.
+ *
+ * For the moment, just record the xdr_buf location of the READ
+ * payload. svc_rdma_sendto will use that location later when
+ * we actually send the payload.
+ */
+int svc_rdma_read_payload(struct svc_rqst *rqstp, unsigned int offset,
+			  unsigned int length)
+{
+	struct svc_rdma_recv_ctxt *rctxt = rqstp->rq_xprt_ctxt;
+
+	/* XXX: Just one READ payload slot for now, since our
+	 * transport implementation currently supports only one
+	 * Write chunk.
+	 */
+	rctxt->rc_read_payload_offset = offset;
+	rctxt->rc_read_payload_length = length;
+
+	return 0;
 }
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 0004535c0188..acb7c558e4fd 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -71,7 +71,6 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
 					struct sockaddr *sa, int salen,
 					int flags);
 static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt);
-static void svc_rdma_release_rqst(struct svc_rqst *);
 static void svc_rdma_detach(struct svc_xprt *xprt);
 static void svc_rdma_free(struct svc_xprt *xprt);
 static int svc_rdma_has_wspace(struct svc_xprt *xprt);
@@ -82,6 +81,7 @@ static const struct svc_xprt_ops svc_rdma_ops = {
 	.xpo_create = svc_rdma_create,
 	.xpo_recvfrom = svc_rdma_recvfrom,
 	.xpo_sendto = svc_rdma_sendto,
+	.xpo_read_payload = svc_rdma_read_payload,
 	.xpo_release_rqst = svc_rdma_release_rqst,
 	.xpo_detach = svc_rdma_detach,
 	.xpo_free = svc_rdma_free,
@@ -559,10 +559,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 	return NULL;
 }
 
-static void svc_rdma_release_rqst(struct svc_rqst *rqstp)
-{
-}
-
 /*
  * When connected, an svc_xprt has at least two references:
  *
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 3f67c395845d..638285d6602d 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -81,7 +81,6 @@ rpcrdma_regbuf_alloc(size_t size, enum dma_data_direction direction,
 		     gfp_t flags);
 static void rpcrdma_regbuf_dma_unmap(struct rpcrdma_regbuf *rb);
 static void rpcrdma_regbuf_free(struct rpcrdma_regbuf *rb);
-static void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp);
 
 /* Wait for outstanding transport work to finish. ib_drain_qp
  * handles the drains in the wrong order for us, so open code
@@ -169,7 +168,6 @@ rpcrdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc)
 				   rdmab_addr(rep->rr_rdmabuf),
 				   wc->byte_len, DMA_FROM_DEVICE);
 
-	rpcrdma_post_recvs(r_xprt, false);
 	rpcrdma_reply_handler(rep);
 	return;
 
@@ -246,6 +244,7 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event)
 			ia->ri_id->device->name,
 			rpcrdma_addrstr(r_xprt), rpcrdma_portstr(r_xprt));
 #endif
+		init_completion(&ia->ri_remove_done);
 		set_bit(RPCRDMA_IAF_REMOVING, &ia->ri_flags);
 		ep->rep_connected = -ENODEV;
 		xprt_force_disconnect(xprt);
@@ -300,7 +299,6 @@ rpcrdma_create_id(struct rpcrdma_xprt *xprt, struct rpcrdma_ia *ia)
 	trace_xprtrdma_conn_start(xprt);
 
 	init_completion(&ia->ri_done);
-	init_completion(&ia->ri_remove_done);
 
 	id = rdma_create_id(xprt->rx_xprt.xprt_net, rpcrdma_cm_event_handler,
 			    xprt, RDMA_PS_TCP, IB_QPT_RC);
@@ -611,6 +609,7 @@ static int rpcrdma_ep_recreate_xprt(struct rpcrdma_xprt *r_xprt,
 				    struct ib_qp_init_attr *qp_init_attr)
 {
 	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+	struct rpcrdma_ep *ep = &r_xprt->rx_ep;
 	int rc, err;
 
 	trace_xprtrdma_reinsert(r_xprt);
@@ -625,6 +624,7 @@ static int rpcrdma_ep_recreate_xprt(struct rpcrdma_xprt *r_xprt,
 		pr_err("rpcrdma: rpcrdma_ep_create returned %d\n", err);
 		goto out2;
 	}
+	memcpy(qp_init_attr, &ep->rep_attr, sizeof(*qp_init_attr));
 
 	rc = -ENETUNREACH;
 	err = rdma_create_qp(ia->ri_id, ia->ri_pd, qp_init_attr);
@@ -1502,8 +1502,13 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia,
 	return 0;
 }
 
-static void
-rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp)
+/**
+ * rpcrdma_post_recvs - Refill the Receive Queue
+ * @r_xprt: controlling transport instance
+ * @temp: mark Receive buffers to be deleted after use
+ *
+ */
+void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp)
 {
 	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
 	struct rpcrdma_ep *ep = &r_xprt->rx_ep;
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index d1e0749bcbc4..6554f89ebaa1 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -496,6 +496,7 @@ void rpcrdma_ep_disconnect(struct rpcrdma_ep *, struct rpcrdma_ia *);
 
 int rpcrdma_ep_post(struct rpcrdma_ia *, struct rpcrdma_ep *,
 				struct rpcrdma_req *);
+void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp);
 
 /*
  * Buffer calls - xprtrdma/verbs.c
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 85166c552542..676bc9c30477 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2611,6 +2611,8 @@ static int bc_sendto(struct rpc_rqst *req)
 		.iov_len	= sizeof(marker),
 	};
 
+	req->rq_xtime = ktime_get();
+
 	len = kernel_sendmsg(transport->sock, &msg, &iov, 1, iov.iov_len);
 	if (len != iov.iov_len)
 		return -EAGAIN;
@@ -2636,7 +2638,6 @@ static int bc_send_request(struct rpc_rqst *req)
 	struct svc_xprt	*xprt;
 	int len;
 
-	dprintk("sending request with xid: %08x\n", ntohl(req->rq_xid));
 	/*
 	 * Get the server socket associated with this callback xprt
 	 */
@@ -2665,6 +2666,7 @@ static int bc_send_request(struct rpc_rqst *req)
 
 static void bc_close(struct rpc_xprt *xprt)
 {
+	xprt_disconnect_done(xprt);
 }
 
 /*
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index 6c997d4a6218..f04a105d8768 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -305,17 +305,17 @@ static int tipc_rcast_xmit(struct net *net, struct sk_buff_head *pkts,
  * @skb: socket buffer to copy
  * @method: send method to be used
  * @dests: destination nodes for message.
- * @cong_link_cnt: returns number of encountered congested destination links
  * Returns 0 if success, otherwise errno
  */
 static int tipc_mcast_send_sync(struct net *net, struct sk_buff *skb,
 				struct tipc_mc_method *method,
-				struct tipc_nlist *dests,
-				u16 *cong_link_cnt)
+				struct tipc_nlist *dests)
 {
 	struct tipc_msg *hdr, *_hdr;
 	struct sk_buff_head tmpq;
 	struct sk_buff *_skb;
+	u16 cong_link_cnt;
+	int rc = 0;
 
 	/* Is a cluster supporting with new capabilities ? */
 	if (!(tipc_net(net)->capabilities & TIPC_MCAST_RBCTL))
@@ -343,18 +343,19 @@ static int tipc_mcast_send_sync(struct net *net, struct sk_buff *skb,
 	_hdr = buf_msg(_skb);
 	msg_set_size(_hdr, MCAST_H_SIZE);
 	msg_set_is_rcast(_hdr, !msg_is_rcast(hdr));
+	msg_set_errcode(_hdr, TIPC_ERR_NO_PORT);
 
 	skb_queue_head_init(&tmpq);
 	__skb_queue_tail(&tmpq, _skb);
 	if (method->rcast)
-		tipc_bcast_xmit(net, &tmpq, cong_link_cnt);
+		rc = tipc_bcast_xmit(net, &tmpq, &cong_link_cnt);
 	else
-		tipc_rcast_xmit(net, &tmpq, dests, cong_link_cnt);
+		rc = tipc_rcast_xmit(net, &tmpq, dests, &cong_link_cnt);
 
 	/* This queue should normally be empty by now */
 	__skb_queue_purge(&tmpq);
 
-	return 0;
+	return rc;
 }
 
 /* tipc_mcast_xmit - deliver message to indicated destination nodes
@@ -396,9 +397,14 @@ int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts,
 		msg_set_is_rcast(hdr, method->rcast);
 
 		/* Switch method ? */
-		if (rcast != method->rcast)
-			tipc_mcast_send_sync(net, skb, method,
-					     dests, cong_link_cnt);
+		if (rcast != method->rcast) {
+			rc = tipc_mcast_send_sync(net, skb, method, dests);
+			if (unlikely(rc)) {
+				pr_err("Unable to send SYN: method %d, rc %d\n",
+				       rcast, rc);
+				goto exit;
+			}
+		}
 
 		if (method->rcast)
 			rc = tipc_rcast_xmit(net, pkts, dests, cong_link_cnt);
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 2bed6589f41e..17ed11af2a13 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -138,10 +138,7 @@ static int bearer_name_validate(const char *name,
 	u32 if_len;
 
 	/* copy bearer name & ensure length is OK */
-	name_copy[TIPC_MAX_BEARER_NAME - 1] = 0;
-	/* need above in case non-Posix strncpy() doesn't pad with nulls */
-	strncpy(name_copy, name, TIPC_MAX_BEARER_NAME);
-	if (name_copy[TIPC_MAX_BEARER_NAME - 1] != 0)
+	if (strscpy(name_copy, name, TIPC_MAX_BEARER_NAME) < 0)
 		return 0;
 
 	/* ensure all component parts of bearer name are present */
diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c
index 6a6eae88442f..58708b4c7719 100644
--- a/net/tipc/monitor.c
+++ b/net/tipc/monitor.c
@@ -665,6 +665,21 @@ void tipc_mon_delete(struct net *net, int bearer_id)
 	kfree(mon);
 }
 
+void tipc_mon_reinit_self(struct net *net)
+{
+	struct tipc_monitor *mon;
+	int bearer_id;
+
+	for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) {
+		mon = tipc_monitor(net, bearer_id);
+		if (!mon)
+			continue;
+		write_lock_bh(&mon->lock);
+		mon->self->addr = tipc_own_addr(net);
+		write_unlock_bh(&mon->lock);
+	}
+}
+
 int tipc_nl_monitor_set_threshold(struct net *net, u32 cluster_size)
 {
 	struct tipc_net *tn = tipc_net(net);
diff --git a/net/tipc/monitor.h b/net/tipc/monitor.h
index 2a21b93e0d04..ed63d2e650b0 100644
--- a/net/tipc/monitor.h
+++ b/net/tipc/monitor.h
@@ -77,6 +77,7 @@ int __tipc_nl_add_monitor(struct net *net, struct tipc_nl_msg *msg,
 			  u32 bearer_id);
 int tipc_nl_add_monitor_peer(struct net *net, struct tipc_nl_msg *msg,
 			     u32 bearer_id, u32 *prev_node);
+void tipc_mon_reinit_self(struct net *net);
 
 extern const int tipc_max_domain_size;
 #endif
diff --git a/net/tipc/net.c b/net/tipc/net.c
index 85707c185360..2de3cec9929d 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -42,6 +42,7 @@
 #include "node.h"
 #include "bcast.h"
 #include "netlink.h"
+#include "monitor.h"
 
 /*
  * The TIPC locking policy is designed to ensure a very fine locking
@@ -136,6 +137,7 @@ static void tipc_net_finalize(struct net *net, u32 addr)
 	tipc_set_node_addr(net, addr);
 	tipc_named_reinit(net);
 	tipc_sk_reinit(net);
+	tipc_mon_reinit_self(net);
 	tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr,
 			     TIPC_CLUSTER_SCOPE, 0, addr);
 }
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 99bd166bccec..e9bbf4a00881 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -111,6 +111,7 @@ const struct nla_policy tipc_nl_prop_policy[TIPC_NLA_PROP_MAX + 1] = {
 	[TIPC_NLA_PROP_PRIO]		= { .type = NLA_U32 },
 	[TIPC_NLA_PROP_TOL]		= { .type = NLA_U32 },
 	[TIPC_NLA_PROP_WIN]		= { .type = NLA_U32 },
+	[TIPC_NLA_PROP_MTU]		= { .type = NLA_U32 },
 	[TIPC_NLA_PROP_BROADCAST]	= { .type = NLA_U32 },
 	[TIPC_NLA_PROP_BROADCAST_RATIO]	= { .type = NLA_U32 }
 };
@@ -261,7 +262,7 @@ struct genl_family tipc_genl_family __ro_after_init = {
 	.version	= TIPC_GENL_V2_VERSION,
 	.hdrsize	= 0,
 	.maxattr	= TIPC_NLA_MAX,
-	.policy = tipc_nl_policy,
+	.policy		= tipc_nl_policy,
 	.netnsok	= true,
 	.module		= THIS_MODULE,
 	.ops		= tipc_genl_v2_ops,
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 90ecca988d12..648d15045855 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -504,7 +504,7 @@ static void __tipc_shutdown(struct socket *sock, int error)
 	struct sock *sk = sock->sk;
 	struct tipc_sock *tsk = tipc_sk(sk);
 	struct net *net = sock_net(sk);
-	long timeout = CONN_TIMEOUT_DEFAULT;
+	long timeout = msecs_to_jiffies(CONN_TIMEOUT_DEFAULT);
 	u32 dnode = tsk_peer_node(tsk);
 	struct sk_buff *skb;
 
@@ -1306,8 +1306,8 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
 	struct tipc_msg *hdr = &tsk->phdr;
 	struct tipc_name_seq *seq;
 	struct sk_buff_head pkts;
-	u32 dport, dnode = 0;
-	u32 type, inst;
+	u32 dport = 0, dnode = 0;
+	u32 type = 0, inst = 0;
 	int mtu, rc;
 
 	if (unlikely(dlen > TIPC_MAX_USER_MSG_SIZE))
@@ -1360,23 +1360,11 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
 		type = dest->addr.name.name.type;
 		inst = dest->addr.name.name.instance;
 		dnode = dest->addr.name.domain;
-		msg_set_type(hdr, TIPC_NAMED_MSG);
-		msg_set_hdr_sz(hdr, NAMED_H_SIZE);
-		msg_set_nametype(hdr, type);
-		msg_set_nameinst(hdr, inst);
-		msg_set_lookup_scope(hdr, tipc_node2scope(dnode));
 		dport = tipc_nametbl_translate(net, type, inst, &dnode);
-		msg_set_destnode(hdr, dnode);
-		msg_set_destport(hdr, dport);
 		if (unlikely(!dport && !dnode))
 			return -EHOSTUNREACH;
 	} else if (dest->addrtype == TIPC_ADDR_ID) {
 		dnode = dest->addr.id.node;
-		msg_set_type(hdr, TIPC_DIRECT_MSG);
-		msg_set_lookup_scope(hdr, 0);
-		msg_set_destnode(hdr, dnode);
-		msg_set_destport(hdr, dest->addr.id.ref);
-		msg_set_hdr_sz(hdr, BASIC_H_SIZE);
 	} else {
 		return -EINVAL;
 	}
@@ -1387,13 +1375,31 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
 	if (unlikely(rc))
 		return rc;
 
+	if (dest->addrtype == TIPC_ADDR_NAME) {
+		msg_set_type(hdr, TIPC_NAMED_MSG);
+		msg_set_hdr_sz(hdr, NAMED_H_SIZE);
+		msg_set_nametype(hdr, type);
+		msg_set_nameinst(hdr, inst);
+		msg_set_lookup_scope(hdr, tipc_node2scope(dnode));
+		msg_set_destnode(hdr, dnode);
+		msg_set_destport(hdr, dport);
+	} else { /* TIPC_ADDR_ID */
+		msg_set_type(hdr, TIPC_DIRECT_MSG);
+		msg_set_lookup_scope(hdr, 0);
+		msg_set_destnode(hdr, dnode);
+		msg_set_destport(hdr, dest->addr.id.ref);
+		msg_set_hdr_sz(hdr, BASIC_H_SIZE);
+	}
+
 	skb_queue_head_init(&pkts);
 	mtu = tipc_node_get_mtu(net, dnode, tsk->portid);
 	rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts);
 	if (unlikely(rc != dlen))
 		return rc;
-	if (unlikely(syn && !tipc_msg_skb_clone(&pkts, &sk->sk_write_queue)))
+	if (unlikely(syn && !tipc_msg_skb_clone(&pkts, &sk->sk_write_queue))) {
+		__skb_queue_purge(&pkts);
 		return -ENOMEM;
+	}
 
 	trace_tipc_sk_sendmsg(sk, skb_peek(&pkts), TIPC_DUMP_SK_SNDQ, " ");
 	rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid);
@@ -2681,6 +2687,7 @@ static void tipc_sk_timeout(struct timer_list *t)
 	if (sock_owned_by_user(sk)) {
 		sk_reset_timer(sk, &sk->sk_timer, jiffies + HZ / 20);
 		bh_unlock_sock(sk);
+		sock_put(sk);
 		return;
 	}
 
@@ -3790,7 +3797,7 @@ int tipc_sk_dump(struct sock *sk, u16 dqueues, char *buf)
 	i += scnprintf(buf + i, sz - i, " %d", sk->sk_sndbuf);
 	i += scnprintf(buf + i, sz - i, " | %d", sk_rmem_alloc_get(sk));
 	i += scnprintf(buf + i, sz - i, " %d", sk->sk_rcvbuf);
-	i += scnprintf(buf + i, sz - i, " | %d\n", sk->sk_backlog.len);
+	i += scnprintf(buf + i, sz - i, " | %d\n", READ_ONCE(sk->sk_backlog.len));
 
 	if (dqueues & TIPC_DUMP_SK_SNDQ) {
 		i += scnprintf(buf + i, sz - i, "sk_write_queue: ");
diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c
index f345662890a6..c58b5782a3a6 100644
--- a/net/tipc/topsrv.c
+++ b/net/tipc/topsrv.c
@@ -401,10 +401,11 @@ static int tipc_conn_rcv_from_sock(struct tipc_conn *con)
 		read_lock_bh(&sk->sk_callback_lock);
 		ret = tipc_conn_rcv_sub(srv, con, &s);
 		read_unlock_bh(&sk->sk_callback_lock);
+		if (!ret)
+			return 0;
 	}
-	if (ret < 0)
-		tipc_conn_close(con);
 
+	tipc_conn_close(con);
 	return ret;
 }
 
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 08994beaa2fc..3b0c363e7f83 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -477,7 +477,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page,
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct iov_iter	msg_iter;
-	char *kaddr = kmap(page);
+	char *kaddr;
 	struct kvec iov;
 	int rc;
 
@@ -492,6 +492,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page,
 		goto out;
 	}
 
+	kaddr = kmap(page);
 	iov.iov_base = kaddr + offset;
 	iov.iov_len = size;
 	iov_iter_kvec(&msg_iter, WRITE, &iov, 1, size);
@@ -509,7 +510,7 @@ struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context,
 				       u32 seq, u64 *p_record_sn)
 {
 	u64 record_sn = context->hint_record_sn;
-	struct tls_record_info *info;
+	struct tls_record_info *info, *last;
 
 	info = context->retransmit_hint;
 	if (!info ||
@@ -519,6 +520,24 @@ struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context,
 		 */
 		info = list_first_entry(&context->records_list,
 					struct tls_record_info, list);
+		/* send the start_marker record if seq number is before the
+		 * tls offload start marker sequence number. This record is
+		 * required to handle TCP packets which are before TLS offload
+		 * started.
+		 *  And if it's not start marker, look if this seq number
+		 * belongs to the list.
+		 */
+		if (likely(!tls_record_is_start_marker(info))) {
+			/* we have the first record, get the last record to see
+			 * if this seq number belongs to the list.
+			 */
+			last = list_last_entry(&context->records_list,
+					       struct tls_record_info, list);
+
+			if (!between(seq, tls_record_start_seq(info),
+				     last->end_seq))
+				return NULL;
+		}
 		record_sn = context->unacked_record_sn;
 	}
 
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 98483c75f095..eff098d15e56 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -203,10 +203,12 @@ static void tls_decrypt_done(struct crypto_async_request *req, int err)
 
 	kfree(aead_req);
 
+	spin_lock_bh(&ctx->decrypt_compl_lock);
 	pending = atomic_dec_return(&ctx->decrypt_pending);
 
-	if (!pending && READ_ONCE(ctx->async_notify))
+	if (!pending && ctx->async_notify)
 		complete(&ctx->async_wait.completion);
+	spin_unlock_bh(&ctx->decrypt_compl_lock);
 }
 
 static int tls_do_decryption(struct sock *sk,
@@ -464,10 +466,12 @@ static void tls_encrypt_done(struct crypto_async_request *req, int err)
 			ready = true;
 	}
 
+	spin_lock_bh(&ctx->encrypt_compl_lock);
 	pending = atomic_dec_return(&ctx->encrypt_pending);
 
-	if (!pending && READ_ONCE(ctx->async_notify))
+	if (!pending && ctx->async_notify)
 		complete(&ctx->async_wait.completion);
+	spin_unlock_bh(&ctx->encrypt_compl_lock);
 
 	if (!ready)
 		return;
@@ -677,12 +681,32 @@ static int tls_push_record(struct sock *sk, int flags,
 
 	split_point = msg_pl->apply_bytes;
 	split = split_point && split_point < msg_pl->sg.size;
+	if (unlikely((!split &&
+		      msg_pl->sg.size +
+		      prot->overhead_size > msg_en->sg.size) ||
+		     (split &&
+		      split_point +
+		      prot->overhead_size > msg_en->sg.size))) {
+		split = true;
+		split_point = msg_en->sg.size;
+	}
 	if (split) {
 		rc = tls_split_open_record(sk, rec, &tmp, msg_pl, msg_en,
 					   split_point, prot->overhead_size,
 					   &orig_end);
 		if (rc < 0)
 			return rc;
+		/* This can happen if above tls_split_open_record allocates
+		 * a single large encryption buffer instead of two smaller
+		 * ones. In this case adjust pointers and continue without
+		 * split.
+		 */
+		if (!msg_pl->sg.size) {
+			tls_merge_open_record(sk, rec, tmp, orig_end);
+			msg_pl = &rec->msg_plaintext;
+			msg_en = &rec->msg_encrypted;
+			split = false;
+		}
 		sk_msg_trim(sk, msg_en, msg_pl->sg.size +
 			    prot->overhead_size);
 	}
@@ -704,6 +728,12 @@ static int tls_push_record(struct sock *sk, int flags,
 		sg_mark_end(sk_msg_elem(msg_pl, i));
 	}
 
+	if (msg_pl->sg.end < msg_pl->sg.start) {
+		sg_chain(&msg_pl->sg.data[msg_pl->sg.start],
+			 MAX_SKB_FRAGS - msg_pl->sg.start + 1,
+			 msg_pl->sg.data);
+	}
+
 	i = msg_pl->sg.start;
 	sg_chain(rec->sg_aead_in, 2, &msg_pl->sg.data[i]);
 
@@ -751,7 +781,7 @@ static int tls_push_record(struct sock *sk, int flags,
 
 static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk,
 			       bool full_record, u8 record_type,
-			       size_t *copied, int flags)
+			       ssize_t *copied, int flags)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
@@ -767,10 +797,13 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk,
 	psock = sk_psock_get(sk);
 	if (!psock || !policy) {
 		err = tls_push_record(sk, flags, record_type);
-		if (err) {
+		if (err && sk->sk_err == EBADMSG) {
 			*copied -= sk_msg_free(sk, msg);
 			tls_free_open_rec(sk);
+			err = -sk->sk_err;
 		}
+		if (psock)
+			sk_psock_put(sk, psock);
 		return err;
 	}
 more_data:
@@ -778,10 +811,7 @@ more_data:
 	if (psock->eval == __SK_NONE) {
 		delta = msg->sg.size;
 		psock->eval = sk_psock_msg_verdict(sk, psock, msg);
-		if (delta < msg->sg.size)
-			delta -= msg->sg.size;
-		else
-			delta = 0;
+		delta -= msg->sg.size;
 	}
 	if (msg->cork_bytes && msg->cork_bytes > msg->sg.size &&
 	    !enospc && !full_record) {
@@ -796,9 +826,10 @@ more_data:
 	switch (psock->eval) {
 	case __SK_PASS:
 		err = tls_push_record(sk, flags, record_type);
-		if (err < 0) {
+		if (err && sk->sk_err == EBADMSG) {
 			*copied -= sk_msg_free(sk, msg);
 			tls_free_open_rec(sk);
+			err = -sk->sk_err;
 			goto out_err;
 		}
 		break;
@@ -888,7 +919,8 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	unsigned char record_type = TLS_RECORD_TYPE_DATA;
 	bool is_kvec = iov_iter_is_kvec(&msg->msg_iter);
 	bool eor = !(msg->msg_flags & MSG_MORE);
-	size_t try_to_copy, copied = 0;
+	size_t try_to_copy;
+	ssize_t copied = 0;
 	struct sk_msg *msg_pl, *msg_en;
 	struct tls_rec *rec;
 	int required_size;
@@ -898,6 +930,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	int num_zc = 0;
 	int orig_size;
 	int ret = 0;
+	int pending;
 
 	if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL))
 		return -EOPNOTSUPP;
@@ -1064,13 +1097,19 @@ trim_sgl:
 		goto send_end;
 	} else if (num_zc) {
 		/* Wait for pending encryptions to get completed */
-		smp_store_mb(ctx->async_notify, true);
+		spin_lock_bh(&ctx->encrypt_compl_lock);
+		ctx->async_notify = true;
 
-		if (atomic_read(&ctx->encrypt_pending))
+		pending = atomic_read(&ctx->encrypt_pending);
+		spin_unlock_bh(&ctx->encrypt_compl_lock);
+		if (pending)
 			crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
 		else
 			reinit_completion(&ctx->async_wait.completion);
 
+		/* There can be no concurrent accesses, since we have no
+		 * pending encrypt operations
+		 */
 		WRITE_ONCE(ctx->async_notify, false);
 
 		if (ctx->async_wait.err) {
@@ -1090,7 +1129,7 @@ send_end:
 
 	release_sock(sk);
 	mutex_unlock(&tls_ctx->tx_lock);
-	return copied ? copied : ret;
+	return copied > 0 ? copied : ret;
 }
 
 static int tls_sw_do_sendpage(struct sock *sk, struct page *page,
@@ -1104,7 +1143,7 @@ static int tls_sw_do_sendpage(struct sock *sk, struct page *page,
 	struct sk_msg *msg_pl;
 	struct tls_rec *rec;
 	int num_async = 0;
-	size_t copied = 0;
+	ssize_t copied = 0;
 	bool full_record;
 	int record_room;
 	int ret = 0;
@@ -1206,7 +1245,7 @@ wait_for_memory:
 	}
 sendpage_end:
 	ret = sk_stream_error(sk, flags, ret);
-	return copied ? copied : ret;
+	return copied > 0 ? copied : ret;
 }
 
 int tls_sw_sendpage_locked(struct sock *sk, struct page *page,
@@ -1698,7 +1737,9 @@ int tls_sw_recvmsg(struct sock *sk,
 	long timeo;
 	bool is_kvec = iov_iter_is_kvec(&msg->msg_iter);
 	bool is_peek = flags & MSG_PEEK;
+	bool bpf_strp_enabled;
 	int num_async = 0;
+	int pending;
 
 	flags |= nonblock;
 
@@ -1707,6 +1748,7 @@ int tls_sw_recvmsg(struct sock *sk,
 
 	psock = sk_psock_get(sk);
 	lock_sock(sk);
+	bpf_strp_enabled = sk_psock_strp_enabled(psock);
 
 	/* Process pending decrypted records. It must be non-zero-copy */
 	err = process_rx_list(ctx, msg, &control, &cmsg, 0, len, false,
@@ -1760,11 +1802,12 @@ int tls_sw_recvmsg(struct sock *sk,
 
 		if (to_decrypt <= len && !is_kvec && !is_peek &&
 		    ctx->control == TLS_RECORD_TYPE_DATA &&
-		    prot->version != TLS_1_3_VERSION)
+		    prot->version != TLS_1_3_VERSION &&
+		    !bpf_strp_enabled)
 			zc = true;
 
 		/* Do not use async mode if record is non-data */
-		if (ctx->control == TLS_RECORD_TYPE_DATA)
+		if (ctx->control == TLS_RECORD_TYPE_DATA && !bpf_strp_enabled)
 			async_capable = ctx->async_capable;
 		else
 			async_capable = false;
@@ -1814,6 +1857,19 @@ int tls_sw_recvmsg(struct sock *sk,
 			goto pick_next_record;
 
 		if (!zc) {
+			if (bpf_strp_enabled) {
+				err = sk_psock_tls_strp_read(psock, skb);
+				if (err != __SK_PASS) {
+					rxm->offset = rxm->offset + rxm->full_len;
+					rxm->full_len = 0;
+					if (err == __SK_DROP)
+						consume_skb(skb);
+					ctx->recv_pkt = NULL;
+					__strp_unpause(&ctx->strp);
+					continue;
+				}
+			}
+
 			if (rxm->full_len > len) {
 				retain_skb = true;
 				chunk = len;
@@ -1861,8 +1917,11 @@ pick_next_record:
 recv_end:
 	if (num_async) {
 		/* Wait for all previously submitted records to be decrypted */
-		smp_store_mb(ctx->async_notify, true);
-		if (atomic_read(&ctx->decrypt_pending)) {
+		spin_lock_bh(&ctx->decrypt_compl_lock);
+		ctx->async_notify = true;
+		pending = atomic_read(&ctx->decrypt_pending);
+		spin_unlock_bh(&ctx->decrypt_compl_lock);
+		if (pending) {
 			err = crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
 			if (err) {
 				/* one of async decrypt failed */
@@ -1874,6 +1933,10 @@ recv_end:
 		} else {
 			reinit_completion(&ctx->async_wait.completion);
 		}
+
+		/* There can be no concurrent accesses, since we have no
+		 * pending decrypt operations
+		 */
 		WRITE_ONCE(ctx->async_notify, false);
 
 		/* Drain records from the rx_list & copy if required */
@@ -2054,8 +2117,9 @@ static void tls_data_ready(struct sock *sk)
 	strp_data_ready(&ctx->strp);
 
 	psock = sk_psock_get(sk);
-	if (psock && !list_empty(&psock->ingress_msg)) {
-		ctx->saved_data_ready(sk);
+	if (psock) {
+		if (!list_empty(&psock->ingress_msg))
+			ctx->saved_data_ready(sk);
 		sk_psock_put(sk, psock);
 	}
 }
@@ -2218,6 +2282,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 
 	if (tx) {
 		crypto_init_wait(&sw_ctx_tx->async_wait);
+		spin_lock_init(&sw_ctx_tx->encrypt_compl_lock);
 		crypto_info = &ctx->crypto_send.info;
 		cctx = &ctx->tx;
 		aead = &sw_ctx_tx->aead_send;
@@ -2226,6 +2291,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 		sw_ctx_tx->tx_work.sk = sk;
 	} else {
 		crypto_init_wait(&sw_ctx_rx->async_wait);
+		spin_lock_init(&sw_ctx_rx->decrypt_compl_lock);
 		crypto_info = &ctx->crypto_recv.info;
 		cctx = &ctx->rx;
 		skb_queue_head_init(&sw_ctx_rx->rx_list);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 0d8da809bea2..b3369d678f1a 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -646,6 +646,9 @@ static __poll_t unix_poll(struct file *, struct socket *, poll_table *);
 static __poll_t unix_dgram_poll(struct file *, struct socket *,
 				    poll_table *);
 static int unix_ioctl(struct socket *, unsigned int, unsigned long);
+#ifdef CONFIG_COMPAT
+static int unix_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
+#endif
 static int unix_shutdown(struct socket *, int);
 static int unix_stream_sendmsg(struct socket *, struct msghdr *, size_t);
 static int unix_stream_recvmsg(struct socket *, struct msghdr *, size_t, int);
@@ -687,6 +690,9 @@ static const struct proto_ops unix_stream_ops = {
 	.getname =	unix_getname,
 	.poll =		unix_poll,
 	.ioctl =	unix_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl =	unix_compat_ioctl,
+#endif
 	.listen =	unix_listen,
 	.shutdown =	unix_shutdown,
 	.setsockopt =	sock_no_setsockopt,
@@ -710,6 +716,9 @@ static const struct proto_ops unix_dgram_ops = {
 	.getname =	unix_getname,
 	.poll =		unix_dgram_poll,
 	.ioctl =	unix_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl =	unix_compat_ioctl,
+#endif
 	.listen =	sock_no_listen,
 	.shutdown =	unix_shutdown,
 	.setsockopt =	sock_no_setsockopt,
@@ -732,6 +741,9 @@ static const struct proto_ops unix_seqpacket_ops = {
 	.getname =	unix_getname,
 	.poll =		unix_dgram_poll,
 	.ioctl =	unix_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl =	unix_compat_ioctl,
+#endif
 	.listen =	unix_listen,
 	.shutdown =	unix_shutdown,
 	.setsockopt =	sock_no_setsockopt,
@@ -2582,6 +2594,13 @@ static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 	return err;
 }
 
+#ifdef CONFIG_COMPAT
+static int unix_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
+{
+	return unix_ioctl(sock, cmd, (unsigned long)compat_ptr(arg));
+}
+#endif
+
 static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wait)
 {
 	struct sock *sk = sock->sk;
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 582a3e4dfce2..7bd6c8199ca6 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1275,7 +1275,7 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, int flags,
 	/* Wait for children sockets to appear; these are the new sockets
 	 * created upon connection establishment.
 	 */
-	timeout = sock_sndtimeo(listener, flags & O_NONBLOCK);
+	timeout = sock_rcvtimeo(listener, flags & O_NONBLOCK);
 	prepare_to_wait(sk_sleep(listener), &wait, TASK_INTERRUPTIBLE);
 
 	while ((connected = vsock_dequeue_accept(listener)) == NULL &&
diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
index 920f14705346..420e1cfa028f 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -135,28 +135,15 @@ struct hvsock {
  ****************************************************************************
  * The only valid Service GUIDs, from the perspectives of both the host and *
  * Linux VM, that can be connected by the other end, must conform to this   *
- * format: <port>-facb-11e6-bd58-64006a7986d3, and the "port" must be in    *
- * this range [0, 0x7FFFFFFF].                                              *
+ * format: <port>-facb-11e6-bd58-64006a7986d3.                              *
  ****************************************************************************
  *
  * When we write apps on the host to connect(), the GUID ServiceID is used.
  * When we write apps in Linux VM to connect(), we only need to specify the
  * port and the driver will form the GUID and use that to request the host.
  *
- * From the perspective of Linux VM:
- * 1. the local ephemeral port (i.e. the local auto-bound port when we call
- * connect() without explicit bind()) is generated by __vsock_bind_stream(),
- * and the range is [1024, 0xFFFFFFFF).
- * 2. the remote ephemeral port (i.e. the auto-generated remote port for
- * a connect request initiated by the host's connect()) is generated by
- * hvs_remote_addr_init() and the range is [0x80000000, 0xFFFFFFFF).
  */
 
-#define MAX_LISTEN_PORT			((u32)0x7FFFFFFF)
-#define MAX_VM_LISTEN_PORT		MAX_LISTEN_PORT
-#define MAX_HOST_LISTEN_PORT		MAX_LISTEN_PORT
-#define MIN_HOST_EPHEMERAL_PORT		(MAX_HOST_LISTEN_PORT + 1)
-
 /* 00000000-facb-11e6-bd58-64006a7986d3 */
 static const uuid_le srv_id_template =
 	UUID_LE(0x00000000, 0xfacb, 0x11e6, 0xbd, 0x58,
@@ -179,33 +166,6 @@ static void hvs_addr_init(struct sockaddr_vm *addr, const uuid_le *svr_id)
 	vsock_addr_init(addr, VMADDR_CID_ANY, port);
 }
 
-static void hvs_remote_addr_init(struct sockaddr_vm *remote,
-				 struct sockaddr_vm *local)
-{
-	static u32 host_ephemeral_port = MIN_HOST_EPHEMERAL_PORT;
-	struct sock *sk;
-
-	vsock_addr_init(remote, VMADDR_CID_ANY, VMADDR_PORT_ANY);
-
-	while (1) {
-		/* Wrap around ? */
-		if (host_ephemeral_port < MIN_HOST_EPHEMERAL_PORT ||
-		    host_ephemeral_port == VMADDR_PORT_ANY)
-			host_ephemeral_port = MIN_HOST_EPHEMERAL_PORT;
-
-		remote->svm_port = host_ephemeral_port++;
-
-		sk = vsock_find_connected_socket(remote, local);
-		if (!sk) {
-			/* Found an available ephemeral port */
-			return;
-		}
-
-		/* Release refcnt got in vsock_find_connected_socket */
-		sock_put(sk);
-	}
-}
-
 static void hvs_set_channel_pending_send_size(struct vmbus_channel *chan)
 {
 	set_channel_pending_send_size(chan,
@@ -332,12 +292,7 @@ static void hvs_open_connection(struct vmbus_channel *chan)
 	if_type = &chan->offermsg.offer.if_type;
 	if_instance = &chan->offermsg.offer.if_instance;
 	conn_from_host = chan->offermsg.offer.u.pipe.user_def[0];
-
-	/* The host or the VM should only listen on a port in
-	 * [0, MAX_LISTEN_PORT]
-	 */
-	if (!is_valid_srv_id(if_type) ||
-	    get_port_by_srv_id(if_type) > MAX_LISTEN_PORT)
+	if (!is_valid_srv_id(if_type))
 		return;
 
 	hvs_addr_init(&addr, conn_from_host ? if_type : if_instance);
@@ -400,8 +355,11 @@ static void hvs_open_connection(struct vmbus_channel *chan)
 		sk->sk_ack_backlog++;
 
 		hvs_addr_init(&vnew->local_addr, if_type);
-		hvs_remote_addr_init(&vnew->remote_addr, &vnew->local_addr);
 
+		/* Remote peer is always the host */
+		vsock_addr_init(&vnew->remote_addr,
+				VMADDR_CID_HOST, VMADDR_PORT_ANY);
+		vnew->remote_addr.svm_port = get_port_by_srv_id(if_instance);
 		hvs_new->vm_srv_id = *if_type;
 		hvs_new->host_srv_id = *if_instance;
 
@@ -706,16 +664,6 @@ static bool hvs_stream_is_active(struct vsock_sock *vsk)
 
 static bool hvs_stream_allow(u32 cid, u32 port)
 {
-	/* The host's port range [MIN_HOST_EPHEMERAL_PORT, 0xFFFFFFFF) is
-	 * reserved as ephemeral ports, which are used as the host's ports
-	 * when the host initiates connections.
-	 *
-	 * Perform this check in the guest so an immediate error is produced
-	 * instead of a timeout.
-	 */
-	if (port > MAX_HOST_LISTEN_PORT)
-		return false;
-
 	if (cid == VMADDR_CID_HOST)
 		return true;
 
diff --git a/net/wireless/core.c b/net/wireless/core.c
index ed24a0b071c3..fa6353b9ca1e 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -1093,6 +1093,7 @@ static void __cfg80211_unregister_wdev(struct wireless_dev *wdev, bool sync)
 
 #ifdef CONFIG_CFG80211_WEXT
 	kzfree(wdev->wext.keys);
+	wdev->wext.keys = NULL;
 #endif
 	/* only initialized if we have a netdev */
 	if (wdev->netdev)
diff --git a/net/wireless/ethtool.c b/net/wireless/ethtool.c
index a9c0f368db5d..24e18405cdb4 100644
--- a/net/wireless/ethtool.c
+++ b/net/wireless/ethtool.c
@@ -7,9 +7,13 @@
 void cfg80211_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	struct device *pdev = wiphy_dev(wdev->wiphy);
 
-	strlcpy(info->driver, wiphy_dev(wdev->wiphy)->driver->name,
-		sizeof(info->driver));
+	if (pdev->driver)
+		strlcpy(info->driver, pdev->driver->name,
+			sizeof(info->driver));
+	else
+		strlcpy(info->driver, "N/A", sizeof(info->driver));
 
 	strlcpy(info->version, init_utsname()->release, sizeof(info->version));
 
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 30cddf8878ce..f4f2d3e23a54 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -421,6 +421,7 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT] = { .type = NLA_FLAG },
 	[NL80211_ATTR_CONTROL_PORT_OVER_NL80211] = { .type = NLA_FLAG },
 	[NL80211_ATTR_PRIVACY] = { .type = NLA_FLAG },
+	[NL80211_ATTR_STATUS_CODE] = { .type = NLA_U16 },
 	[NL80211_ATTR_CIPHER_SUITE_GROUP] = { .type = NLA_U32 },
 	[NL80211_ATTR_WPA_VERSIONS] = { .type = NLA_U32 },
 	[NL80211_ATTR_PID] = { .type = NLA_U32 },
@@ -452,6 +453,8 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_WOWLAN_TRIGGERS] = { .type = NLA_NESTED },
 	[NL80211_ATTR_STA_PLINK_STATE] =
 		NLA_POLICY_MAX(NLA_U8, NUM_NL80211_PLINK_STATES - 1),
+	[NL80211_ATTR_MEASUREMENT_DURATION] = { .type = NLA_U16 },
+	[NL80211_ATTR_MEASUREMENT_DURATION_MANDATORY] = { .type = NLA_FLAG },
 	[NL80211_ATTR_MESH_PEER_AID] =
 		NLA_POLICY_RANGE(NLA_U16, 1, IEEE80211_MAX_AID),
 	[NL80211_ATTR_SCHED_SCAN_INTERVAL] = { .type = NLA_U32 },
@@ -513,6 +516,8 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_MDID] = { .type = NLA_U16 },
 	[NL80211_ATTR_IE_RIC] = { .type = NLA_BINARY,
 				  .len = IEEE80211_MAX_DATA_LEN },
+	[NL80211_ATTR_CRIT_PROT_ID] = { .type = NLA_U16 },
+	[NL80211_ATTR_MAX_CRIT_PROT_DURATION] = { .type = NLA_U16 },
 	[NL80211_ATTR_PEER_AID] =
 		NLA_POLICY_RANGE(NLA_U16, 1, IEEE80211_MAX_AID),
 	[NL80211_ATTR_CH_SWITCH_COUNT] = { .type = NLA_U32 },
@@ -543,6 +548,7 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 		NLA_POLICY_MAX(NLA_U8, IEEE80211_NUM_UPS - 1),
 	[NL80211_ATTR_ADMITTED_TIME] = { .type = NLA_U16 },
 	[NL80211_ATTR_SMPS_MODE] = { .type = NLA_U8 },
+	[NL80211_ATTR_OPER_CLASS] = { .type = NLA_U8 },
 	[NL80211_ATTR_MAC_MASK] = {
 		.type = NLA_EXACT_LEN_WARN,
 		.len = ETH_ALEN
@@ -596,10 +602,8 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_HE_CAPABILITY] = { .type = NLA_BINARY,
 					 .len = NL80211_HE_MAX_CAPABILITY_LEN },
 
-	[NL80211_ATTR_FTM_RESPONDER] = {
-		.type = NLA_NESTED,
-		.validation_data = nl80211_ftm_responder_policy,
-	},
+	[NL80211_ATTR_FTM_RESPONDER] =
+		NLA_POLICY_NESTED(nl80211_ftm_responder_policy),
 	[NL80211_ATTR_TIMEOUT] = NLA_POLICY_MIN(NLA_U32, 1),
 	[NL80211_ATTR_PEER_MEASUREMENTS] =
 		NLA_POLICY_NESTED(nl80211_pmsr_attr_policy),
@@ -10669,6 +10673,7 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev,
 		if (err)
 			return err;
 
+		cfg80211_sinfo_release_content(&sinfo);
 		if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_BEACON_SIGNAL_AVG))
 			wdev->cqm_config->last_rssi_event_value =
 				(s8) sinfo.rx_beacon_signal_avg;
@@ -12755,13 +12760,13 @@ static int nl80211_vendor_cmd(struct sk_buff *skb, struct genl_info *info)
 				if (!wdev_running(wdev))
 					return -ENETDOWN;
 			}
-
-			if (!vcmd->doit)
-				return -EOPNOTSUPP;
 		} else {
 			wdev = NULL;
 		}
 
+		if (!vcmd->doit)
+			return -EOPNOTSUPP;
+
 		if (info->attrs[NL80211_ATTR_VENDOR_DATA]) {
 			data = nla_data(info->attrs[NL80211_ATTR_VENDOR_DATA]);
 			len = nla_len(info->attrs[NL80211_ATTR_VENDOR_DATA]);
@@ -13572,6 +13577,8 @@ static int nl80211_probe_mesh_link(struct sk_buff *skb, struct genl_info *info)
 	if (err)
 		return err;
 
+	cfg80211_sinfo_release_content(&sinfo);
+
 	return rdev_probe_mesh_link(rdev, dev, dest, buf, len);
 }
 
@@ -16167,7 +16174,7 @@ void cfg80211_sta_opmode_change_notify(struct net_device *dev, const u8 *mac,
 		goto nla_put_failure;
 
 	if ((sta_opmode->changed & STA_OPMODE_MAX_BW_CHANGED) &&
-	    nla_put_u8(msg, NL80211_ATTR_CHANNEL_WIDTH, sta_opmode->bw))
+	    nla_put_u32(msg, NL80211_ATTR_CHANNEL_WIDTH, sta_opmode->bw))
 		goto nla_put_failure;
 
 	if ((sta_opmode->changed & STA_OPMODE_N_SS_CHANGED) &&
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index e853a4fe6f97..e0d34f796d0b 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -538,6 +538,10 @@ static inline int
 rdev_set_wiphy_params(struct cfg80211_registered_device *rdev, u32 changed)
 {
 	int ret;
+
+	if (!rdev->ops->set_wiphy_params)
+		return -EOPNOTSUPP;
+
 	trace_rdev_set_wiphy_params(&rdev->wiphy, changed);
 	ret = rdev->ops->set_wiphy_params(&rdev->wiphy, changed);
 	trace_rdev_return_int(&rdev->wiphy, ret);
@@ -1167,6 +1171,16 @@ rdev_start_radar_detection(struct cfg80211_registered_device *rdev,
 	return ret;
 }
 
+static inline void
+rdev_end_cac(struct cfg80211_registered_device *rdev,
+	     struct net_device *dev)
+{
+	trace_rdev_end_cac(&rdev->wiphy, dev);
+	if (rdev->ops->end_cac)
+		rdev->ops->end_cac(&rdev->wiphy, dev);
+	trace_rdev_return_void(&rdev->wiphy);
+}
+
 static inline int
 rdev_set_mcast_rate(struct cfg80211_registered_device *rdev,
 		    struct net_device *dev,
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 36eba5804efe..017340a4b818 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -2261,21 +2261,22 @@ static void update_all_wiphy_regulatory(enum nl80211_reg_initiator initiator)
 
 static void handle_channel_custom(struct wiphy *wiphy,
 				  struct ieee80211_channel *chan,
-				  const struct ieee80211_regdomain *regd)
+				  const struct ieee80211_regdomain *regd,
+				  u32 min_bw)
 {
 	u32 bw_flags = 0;
 	const struct ieee80211_reg_rule *reg_rule = NULL;
 	const struct ieee80211_power_rule *power_rule = NULL;
 	u32 bw;
 
-	for (bw = MHZ_TO_KHZ(20); bw >= MHZ_TO_KHZ(5); bw = bw / 2) {
+	for (bw = MHZ_TO_KHZ(20); bw >= min_bw; bw = bw / 2) {
 		reg_rule = freq_reg_info_regd(MHZ_TO_KHZ(chan->center_freq),
 					      regd, bw);
 		if (!IS_ERR(reg_rule))
 			break;
 	}
 
-	if (IS_ERR(reg_rule)) {
+	if (IS_ERR_OR_NULL(reg_rule)) {
 		pr_debug("Disabling freq %d MHz as custom regd has no rule that fits it\n",
 			 chan->center_freq);
 		if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) {
@@ -2324,8 +2325,14 @@ static void handle_band_custom(struct wiphy *wiphy,
 	if (!sband)
 		return;
 
+	/*
+	 * We currently assume that you always want at least 20 MHz,
+	 * otherwise channel 12 might get enabled if this rule is
+	 * compatible to US, which permits 2402 - 2472 MHz.
+	 */
 	for (i = 0; i < sband->n_channels; i++)
-		handle_channel_custom(wiphy, &sband->channels[i], regd);
+		handle_channel_custom(wiphy, &sband->channels[i], regd,
+				      MHZ_TO_KHZ(20));
 }
 
 /* Used by drivers prior to wiphy registration */
@@ -3867,6 +3874,25 @@ bool regulatory_pre_cac_allowed(struct wiphy *wiphy)
 	return pre_cac_allowed;
 }
 
+static void cfg80211_check_and_end_cac(struct cfg80211_registered_device *rdev)
+{
+	struct wireless_dev *wdev;
+	/* If we finished CAC or received radar, we should end any
+	 * CAC running on the same channels.
+	 * the check !cfg80211_chandef_dfs_usable contain 2 options:
+	 * either all channels are available - those the CAC_FINISHED
+	 * event has effected another wdev state, or there is a channel
+	 * in unavailable state in wdev chandef - those the RADAR_DETECTED
+	 * event has effected another wdev state.
+	 * In both cases we should end the CAC on the wdev.
+	 */
+	list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) {
+		if (wdev->cac_started &&
+		    !cfg80211_chandef_dfs_usable(&rdev->wiphy, &wdev->chandef))
+			rdev_end_cac(rdev, wdev->netdev);
+	}
+}
+
 void regulatory_propagate_dfs_state(struct wiphy *wiphy,
 				    struct cfg80211_chan_def *chandef,
 				    enum nl80211_dfs_state dfs_state,
@@ -3893,8 +3919,10 @@ void regulatory_propagate_dfs_state(struct wiphy *wiphy,
 		cfg80211_set_dfs_state(&rdev->wiphy, chandef, dfs_state);
 
 		if (event == NL80211_RADAR_DETECTED ||
-		    event == NL80211_RADAR_CAC_FINISHED)
+		    event == NL80211_RADAR_CAC_FINISHED) {
 			cfg80211_sched_dfs_chan_update(rdev);
+			cfg80211_check_and_end_cac(rdev);
+		}
 
 		nl80211_radar_notify(rdev, chandef, event, NULL, GFP_KERNEL);
 	}
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index 7d34cb884840..9d96da127e09 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -1283,14 +1283,14 @@ void cfg80211_autodisconnect_wk(struct work_struct *work)
 	if (wdev->conn_owner_nlportid) {
 		switch (wdev->iftype) {
 		case NL80211_IFTYPE_ADHOC:
-			cfg80211_leave_ibss(rdev, wdev->netdev, false);
+			__cfg80211_leave_ibss(rdev, wdev->netdev, false);
 			break;
 		case NL80211_IFTYPE_AP:
 		case NL80211_IFTYPE_P2P_GO:
-			cfg80211_stop_ap(rdev, wdev->netdev, false);
+			__cfg80211_stop_ap(rdev, wdev->netdev, false);
 			break;
 		case NL80211_IFTYPE_MESH_POINT:
-			cfg80211_leave_mesh(rdev, wdev->netdev);
+			__cfg80211_leave_mesh(rdev, wdev->netdev);
 			break;
 		case NL80211_IFTYPE_STATION:
 		case NL80211_IFTYPE_P2P_CLIENT:
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 2abfff925aac..08b0ee8bb590 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -646,6 +646,11 @@ DEFINE_EVENT(wiphy_netdev_evt, rdev_flush_pmksa,
 	TP_ARGS(wiphy, netdev)
 );
 
+DEFINE_EVENT(wiphy_netdev_evt, rdev_end_cac,
+	     TP_PROTO(struct wiphy *wiphy, struct net_device *netdev),
+	     TP_ARGS(wiphy, netdev)
+);
+
 DECLARE_EVENT_CLASS(station_add_change,
 	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u8 *mac,
 		 struct station_parameters *params),
diff --git a/net/wireless/util.c b/net/wireless/util.c
index f68818dbac1a..95fc3bbaa07c 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -555,7 +555,7 @@ __frame_add_frag(struct sk_buff *skb, struct page *page,
 	struct skb_shared_info *sh = skb_shinfo(skb);
 	int page_offset;
 
-	page_ref_inc(page);
+	get_page(page);
 	page_offset = ptr - page_address(page);
 	skb_add_rx_frag(skb, sh->nr_frags, page, page_offset, len, size);
 }
diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c
index 5e677dac2a0c..69102fda9ebd 100644
--- a/net/wireless/wext-core.c
+++ b/net/wireless/wext-core.c
@@ -657,7 +657,8 @@ struct iw_statistics *get_wireless_stats(struct net_device *dev)
 	return NULL;
 }
 
-static int iw_handler_get_iwstats(struct net_device *		dev,
+/* noinline to avoid a bogus warning with -O3 */
+static noinline int iw_handler_get_iwstats(struct net_device *	dev,
 				  struct iw_request_info *	info,
 				  union iwreq_data *		wrqu,
 				  char *			extra)
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 6aee9f5e8e71..256f3e97d1f3 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -760,6 +760,10 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr,
 	if (sk->sk_state == TCP_ESTABLISHED)
 		goto out;
 
+	rc = -EALREADY;	/* Do nothing if call is already in progress */
+	if (sk->sk_state == TCP_SYN_SENT)
+		goto out;
+
 	sk->sk_state   = TCP_CLOSE;
 	sock->state = SS_UNCONNECTED;
 
@@ -806,7 +810,7 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr,
 	/* Now the loop */
 	rc = -EINPROGRESS;
 	if (sk->sk_state != TCP_ESTABLISHED && (flags & O_NONBLOCK))
-		goto out_put_neigh;
+		goto out;
 
 	rc = x25_wait_for_connection_establishment(sk);
 	if (rc)
diff --git a/net/x25/x25_dev.c b/net/x25/x25_dev.c
index 5c111bc3c8ea..48b0f02592fe 100644
--- a/net/x25/x25_dev.c
+++ b/net/x25/x25_dev.c
@@ -115,8 +115,10 @@ int x25_lapb_receive_frame(struct sk_buff *skb, struct net_device *dev,
 		goto drop;
 	}
 
-	if (!pskb_may_pull(skb, 1))
+	if (!pskb_may_pull(skb, 1)) {
+		x25_neigh_put(nb);
 		return 0;
+	}
 
 	switch (skb->data[0]) {
 
diff --git a/net/x25/x25_subr.c b/net/x25/x25_subr.c
index 8aa415a38814..0285aaa1e93c 100644
--- a/net/x25/x25_subr.c
+++ b/net/x25/x25_subr.c
@@ -357,6 +357,12 @@ void x25_disconnect(struct sock *sk, int reason, unsigned char cause,
 		sk->sk_state_change(sk);
 		sock_set_flag(sk, SOCK_DEAD);
 	}
+	if (x25->neighbour) {
+		read_lock_bh(&x25_list_lock);
+		x25_neigh_put(x25->neighbour);
+		x25->neighbour = NULL;
+		read_unlock_bh(&x25_list_lock);
+	}
 }
 
 /*
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 6ad8031c0a54..7459fc756da8 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -309,9 +309,9 @@ static int xdp_umem_account_pages(struct xdp_umem *umem)
 static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 {
 	u32 chunk_size = mr->chunk_size, headroom = mr->headroom;
+	u64 npgs, addr = mr->addr, size = mr->len;
 	unsigned int chunks, chunks_per_page;
-	u64 addr = mr->addr, size = mr->len;
-	int size_chk, err, i;
+	int err, i;
 
 	if (chunk_size < XDP_UMEM_MIN_CHUNK_SIZE || chunk_size > PAGE_SIZE) {
 		/* Strictly speaking we could support this, if:
@@ -336,6 +336,10 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	if ((addr + size) < addr)
 		return -EINVAL;
 
+	npgs = div_u64(size, PAGE_SIZE);
+	if (npgs > U32_MAX)
+		return -EINVAL;
+
 	chunks = (unsigned int)div_u64(size, chunk_size);
 	if (chunks == 0)
 		return -EINVAL;
@@ -346,8 +350,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 
 	headroom = ALIGN(headroom, 64);
 
-	size_chk = chunk_size - headroom - XDP_PACKET_HEADROOM;
-	if (size_chk < 0)
+	if (headroom >= chunk_size - XDP_PACKET_HEADROOM)
 		return -EINVAL;
 
 	umem->address = (unsigned long)addr;
@@ -355,7 +358,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	umem->size = size;
 	umem->headroom = headroom;
 	umem->chunk_size_nohr = chunk_size - headroom;
-	umem->npgs = size / PAGE_SIZE;
+	umem->npgs = (u32)npgs;
 	umem->pgs = NULL;
 	umem->user = NULL;
 	INIT_LIST_HEAD(&umem->xsk_list);
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 5e0637db92ea..ce6ff65b5095 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -256,10 +256,8 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
 
 		len = desc.len;
 		skb = sock_alloc_send_skb(sk, len, 1, &err);
-		if (unlikely(!skb)) {
-			err = -EAGAIN;
+		if (unlikely(!skb))
 			goto out;
-		}
 
 		skb_put(skb, len);
 		addr = desc.addr;
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index ff654306d836..9d76ba7e1cc7 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -25,12 +25,10 @@ static void __xfrm_transport_prep(struct xfrm_state *x, struct sk_buff *skb,
 	struct xfrm_offload *xo = xfrm_offload(skb);
 
 	skb_reset_mac_len(skb);
-	pskb_pull(skb, skb->mac_len + hsize + x->props.header_len);
-
-	if (xo->flags & XFRM_GSO_SEGMENT) {
-		skb_reset_transport_header(skb);
+	if (xo->flags & XFRM_GSO_SEGMENT)
 		skb->transport_header -= x->props.header_len;
-	}
+
+	pskb_pull(skb, skb_transport_offset(skb) + x->props.header_len);
 }
 
 static void __xfrm_mode_tunnel_prep(struct xfrm_state *x, struct sk_buff *skb,
@@ -84,7 +82,7 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur
 	struct xfrm_offload *xo = xfrm_offload(skb);
 	struct sec_path *sp;
 
-	if (!xo)
+	if (!xo || (xo->flags & XFRM_XMIT))
 		return skb;
 
 	if (!(features & NETIF_F_HW_ESP))
@@ -105,6 +103,8 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur
 		return skb;
 	}
 
+	xo->flags |= XFRM_XMIT;
+
 	if (skb_is_gso(skb)) {
 		struct net_device *dev = skb->dev;
 
@@ -391,6 +391,7 @@ static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void
 		return xfrm_dev_feat_change(dev);
 
 	case NETDEV_DOWN:
+	case NETDEV_UNREGISTER:
 		return xfrm_dev_down(dev);
 	}
 	return NOTIFY_DONE;
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 526fff80b84d..805b336369fa 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -642,7 +642,7 @@ resume:
 		dev_put(skb->dev);
 
 		spin_lock(&x->lock);
-		if (nexthdr <= 0) {
+		if (nexthdr < 0) {
 			if (nexthdr == -EBADMSG) {
 				xfrm_audit_state_icvfail(x, skb,
 							 x->type->proto);
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index ad3a2555c517..71508b35725d 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -324,9 +324,6 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 	int err = -1;
 	int mtu;
 
-	if (!dst)
-		goto tx_err_link_failure;
-
 	dst_hold(dst);
 	dst = xfrm_lookup_with_ifid(xi->net, dst, fl, NULL, 0, xi->p.if_id);
 	if (IS_ERR(dst)) {
@@ -353,7 +350,7 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 
 	mtu = dst_mtu(dst);
 	if (!skb->ignore_df && skb->len > mtu) {
-		skb_dst_update_pmtu(skb, mtu);
+		skb_dst_update_pmtu_no_confirm(skb, mtu);
 
 		if (skb->protocol == htons(ETH_P_IPV6)) {
 			if (mtu < IPV6_MIN_MTU)
@@ -399,6 +396,7 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct xfrm_if *xi = netdev_priv(dev);
 	struct net_device_stats *stats = &xi->dev->stats;
+	struct dst_entry *dst = skb_dst(skb);
 	struct flowi fl;
 	int ret;
 
@@ -408,10 +406,33 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev)
 	case htons(ETH_P_IPV6):
 		xfrm_decode_session(skb, &fl, AF_INET6);
 		memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+		if (!dst) {
+			fl.u.ip6.flowi6_oif = dev->ifindex;
+			fl.u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC;
+			dst = ip6_route_output(dev_net(dev), NULL, &fl.u.ip6);
+			if (dst->error) {
+				dst_release(dst);
+				stats->tx_carrier_errors++;
+				goto tx_err;
+			}
+			skb_dst_set(skb, dst);
+		}
 		break;
 	case htons(ETH_P_IP):
 		xfrm_decode_session(skb, &fl, AF_INET);
 		memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+		if (!dst) {
+			struct rtable *rt;
+
+			fl.u.ip4.flowi4_oif = dev->ifindex;
+			fl.u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC;
+			rt = __ip_route_output_key(dev_net(dev), &fl.u.ip4);
+			if (IS_ERR(rt)) {
+				stats->tx_carrier_errors++;
+				goto tx_err;
+			}
+			skb_dst_set(skb, &rt->dst);
+		}
 		break;
 	default:
 		goto tx_err;
@@ -619,12 +640,9 @@ static void xfrmi_dev_setup(struct net_device *dev)
 {
 	dev->netdev_ops 	= &xfrmi_netdev_ops;
 	dev->type		= ARPHRD_NONE;
-	dev->hard_header_len 	= ETH_HLEN;
-	dev->min_header_len	= ETH_HLEN;
 	dev->mtu		= ETH_DATA_LEN;
 	dev->min_mtu		= ETH_MIN_MTU;
-	dev->max_mtu		= ETH_DATA_LEN;
-	dev->addr_len		= ETH_ALEN;
+	dev->max_mtu		= IP_MAX_MTU;
 	dev->flags 		= IFF_NOARP;
 	dev->needs_free_netdev	= true;
 	dev->priv_destructor	= xfrmi_dev_free;
@@ -807,9 +825,30 @@ static void __net_exit xfrmi_exit_net(struct net *net)
 	rtnl_unlock();
 }
 
+static void __net_exit xfrmi_exit_batch_net(struct list_head *net_exit_list)
+{
+	struct net *net;
+	LIST_HEAD(list);
+
+	rtnl_lock();
+	list_for_each_entry(net, net_exit_list, exit_list) {
+		struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
+		struct xfrm_if __rcu **xip;
+		struct xfrm_if *xi;
+
+		for (xip = &xfrmn->xfrmi[0];
+		     (xi = rtnl_dereference(*xip)) != NULL;
+		     xip = &xi->next)
+			unregister_netdevice_queue(xi->dev, &list);
+	}
+	unregister_netdevice_many(&list);
+	rtnl_unlock();
+}
+
 static struct pernet_operations xfrmi_net_ops = {
 	.init = xfrmi_init_net,
 	.exit = xfrmi_exit_net,
+	.exit_batch = xfrmi_exit_batch_net,
 	.id   = &xfrmi_net_id,
 	.size = sizeof(struct xfrmi_net),
 };
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 9499b35feb92..2e7288e4da7b 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -586,18 +586,20 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb)
 		xfrm_state_hold(x);
 
 		if (skb_is_gso(skb)) {
-			skb_shinfo(skb)->gso_type |= SKB_GSO_ESP;
+			if (skb->inner_protocol)
+				return xfrm_output_gso(net, sk, skb);
 
-			return xfrm_output2(net, sk, skb);
+			skb_shinfo(skb)->gso_type |= SKB_GSO_ESP;
+			goto out;
 		}
 
 		if (x->xso.dev && x->xso.dev->features & NETIF_F_HW_ESP_TX_CSUM)
 			goto out;
+	} else {
+		if (skb_is_gso(skb))
+			return xfrm_output_gso(net, sk, skb);
 	}
 
-	if (skb_is_gso(skb))
-		return xfrm_output_gso(net, sk, skb);
-
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		err = skb_checksum_help(skb);
 		if (err) {
@@ -643,7 +645,8 @@ void xfrm_local_error(struct sk_buff *skb, int mtu)
 
 	if (skb->protocol == htons(ETH_P_IP))
 		proto = AF_INET;
-	else if (skb->protocol == htons(ETH_P_IPV6))
+	else if (skb->protocol == htons(ETH_P_IPV6) &&
+		 skb->sk->sk_family == AF_INET6)
 		proto = AF_INET6;
 	else
 		return;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 7c2fa80b20bd..c7106f43db45 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -431,7 +431,9 @@ EXPORT_SYMBOL(xfrm_policy_destroy);
 
 static void xfrm_policy_kill(struct xfrm_policy *policy)
 {
+	write_lock_bh(&policy->lock);
 	policy->walk.dead = 1;
+	write_unlock_bh(&policy->lock);
 
 	atomic_inc(&policy->genid);
 
@@ -1431,19 +1433,10 @@ static void xfrm_policy_requeue(struct xfrm_policy *old,
 	spin_unlock_bh(&pq->hold_queue.lock);
 }
 
-static bool xfrm_policy_mark_match(struct xfrm_policy *policy,
-				   struct xfrm_policy *pol)
+static inline bool xfrm_policy_mark_match(const struct xfrm_mark *mark,
+					  struct xfrm_policy *pol)
 {
-	u32 mark = policy->mark.v & policy->mark.m;
-
-	if (policy->mark.v == pol->mark.v && policy->mark.m == pol->mark.m)
-		return true;
-
-	if ((mark & pol->mark.m) == pol->mark.v &&
-	    policy->priority == pol->priority)
-		return true;
-
-	return false;
+	return mark->v == pol->mark.v && mark->m == pol->mark.m;
 }
 
 static u32 xfrm_pol_bin_key(const void *data, u32 len, u32 seed)
@@ -1506,7 +1499,7 @@ static void xfrm_policy_insert_inexact_list(struct hlist_head *chain,
 		if (pol->type == policy->type &&
 		    pol->if_id == policy->if_id &&
 		    !selector_cmp(&pol->selector, &policy->selector) &&
-		    xfrm_policy_mark_match(policy, pol) &&
+		    xfrm_policy_mark_match(&policy->mark, pol) &&
 		    xfrm_sec_ctx_match(pol->security, policy->security) &&
 		    !WARN_ON(delpol)) {
 			delpol = pol;
@@ -1541,7 +1534,7 @@ static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain,
 		if (pol->type == policy->type &&
 		    pol->if_id == policy->if_id &&
 		    !selector_cmp(&pol->selector, &policy->selector) &&
-		    xfrm_policy_mark_match(policy, pol) &&
+		    xfrm_policy_mark_match(&policy->mark, pol) &&
 		    xfrm_sec_ctx_match(pol->security, policy->security) &&
 		    !WARN_ON(delpol)) {
 			if (excl)
@@ -1613,9 +1606,8 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 EXPORT_SYMBOL(xfrm_policy_insert);
 
 static struct xfrm_policy *
-__xfrm_policy_bysel_ctx(struct hlist_head *chain, u32 mark, u32 if_id,
-			u8 type, int dir,
-			struct xfrm_selector *sel,
+__xfrm_policy_bysel_ctx(struct hlist_head *chain, const struct xfrm_mark *mark,
+			u32 if_id, u8 type, int dir, struct xfrm_selector *sel,
 			struct xfrm_sec_ctx *ctx)
 {
 	struct xfrm_policy *pol;
@@ -1626,7 +1618,7 @@ __xfrm_policy_bysel_ctx(struct hlist_head *chain, u32 mark, u32 if_id,
 	hlist_for_each_entry(pol, chain, bydst) {
 		if (pol->type == type &&
 		    pol->if_id == if_id &&
-		    (mark & pol->mark.m) == pol->mark.v &&
+		    xfrm_policy_mark_match(mark, pol) &&
 		    !selector_cmp(sel, &pol->selector) &&
 		    xfrm_sec_ctx_match(ctx, pol->security))
 			return pol;
@@ -1635,11 +1627,10 @@ __xfrm_policy_bysel_ctx(struct hlist_head *chain, u32 mark, u32 if_id,
 	return NULL;
 }
 
-struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id,
-					  u8 type, int dir,
-					  struct xfrm_selector *sel,
-					  struct xfrm_sec_ctx *ctx, int delete,
-					  int *err)
+struct xfrm_policy *
+xfrm_policy_bysel_ctx(struct net *net, const struct xfrm_mark *mark, u32 if_id,
+		      u8 type, int dir, struct xfrm_selector *sel,
+		      struct xfrm_sec_ctx *ctx, int delete, int *err)
 {
 	struct xfrm_pol_inexact_bin *bin = NULL;
 	struct xfrm_policy *pol, *ret = NULL;
@@ -1706,9 +1697,9 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id,
 }
 EXPORT_SYMBOL(xfrm_policy_bysel_ctx);
 
-struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id,
-				     u8 type, int dir, u32 id, int delete,
-				     int *err)
+struct xfrm_policy *
+xfrm_policy_byid(struct net *net, const struct xfrm_mark *mark, u32 if_id,
+		 u8 type, int dir, u32 id, int delete, int *err)
 {
 	struct xfrm_policy *pol, *ret;
 	struct hlist_head *chain;
@@ -1723,8 +1714,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id,
 	ret = NULL;
 	hlist_for_each_entry(pol, chain, byidx) {
 		if (pol->type == type && pol->index == id &&
-		    pol->if_id == if_id &&
-		    (mark & pol->mark.m) == pol->mark.v) {
+		    pol->if_id == if_id && xfrm_policy_mark_match(mark, pol)) {
 			xfrm_pol_hold(pol);
 			if (delete) {
 				*err = security_xfrm_policy_delete(
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index b88ba45ff1ac..fbb7d9d06478 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -110,7 +110,8 @@ static inline int verify_sec_ctx_len(struct nlattr **attrs)
 		return 0;
 
 	uctx = nla_data(rt);
-	if (uctx->len != (sizeof(struct xfrm_user_sec_ctx) + uctx->ctx_len))
+	if (uctx->len > nla_len(rt) ||
+	    uctx->len != (sizeof(struct xfrm_user_sec_ctx) + uctx->ctx_len))
 		return -EINVAL;
 
 	return 0;
@@ -1862,7 +1863,6 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct km_event c;
 	int delete;
 	struct xfrm_mark m;
-	u32 mark = xfrm_mark_get(attrs, &m);
 	u32 if_id = 0;
 
 	p = nlmsg_data(nlh);
@@ -1879,8 +1879,11 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (attrs[XFRMA_IF_ID])
 		if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
 
+	xfrm_mark_get(attrs, &m);
+
 	if (p->index)
-		xp = xfrm_policy_byid(net, mark, if_id, type, p->dir, p->index, delete, &err);
+		xp = xfrm_policy_byid(net, &m, if_id, type, p->dir,
+				      p->index, delete, &err);
 	else {
 		struct nlattr *rt = attrs[XFRMA_SEC_CTX];
 		struct xfrm_sec_ctx *ctx;
@@ -1897,8 +1900,8 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
 			if (err)
 				return err;
 		}
-		xp = xfrm_policy_bysel_ctx(net, mark, if_id, type, p->dir, &p->sel,
-					   ctx, delete, &err);
+		xp = xfrm_policy_bysel_ctx(net, &m, if_id, type, p->dir,
+					   &p->sel, ctx, delete, &err);
 		security_xfrm_policy_free(ctx);
 	}
 	if (xp == NULL)
@@ -2165,7 +2168,6 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh,
 	u8 type = XFRM_POLICY_TYPE_MAIN;
 	int err = -ENOENT;
 	struct xfrm_mark m;
-	u32 mark = xfrm_mark_get(attrs, &m);
 	u32 if_id = 0;
 
 	err = copy_from_user_policy_type(&type, attrs);
@@ -2179,8 +2181,11 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (attrs[XFRMA_IF_ID])
 		if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
 
+	xfrm_mark_get(attrs, &m);
+
 	if (p->index)
-		xp = xfrm_policy_byid(net, mark, if_id, type, p->dir, p->index, 0, &err);
+		xp = xfrm_policy_byid(net, &m, if_id, type, p->dir, p->index,
+				      0, &err);
 	else {
 		struct nlattr *rt = attrs[XFRMA_SEC_CTX];
 		struct xfrm_sec_ctx *ctx;
@@ -2197,7 +2202,7 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh,
 			if (err)
 				return err;
 		}
-		xp = xfrm_policy_bysel_ctx(net, mark, if_id, type, p->dir,
+		xp = xfrm_policy_bysel_ctx(net, &m, if_id, type, p->dir,
 					   &p->sel, ctx, 0, &err);
 		security_xfrm_policy_free(ctx);
 	}
@@ -2275,6 +2280,9 @@ static int xfrm_add_acquire(struct sk_buff *skb, struct nlmsghdr *nlh,
 	err = verify_newpolicy_info(&ua->policy);
 	if (err)
 		goto free_state;
+	err = verify_sec_ctx_len(attrs);
+	if (err)
+		goto free_state;
 
 	/*   build an XP */
 	xp = xfrm_policy_construct(net, &ua->policy, attrs, &err);
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 095562695dcb..84ff0a116fe6 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -217,6 +217,7 @@ BTF_LLVM_PROBE := $(shell echo "int main() { return 0; }" | \
 			  readelf -S ./llvm_btf_verify.o | grep BTF; \
 			  /bin/rm -f ./llvm_btf_verify.o)
 
+BPF_EXTRA_CFLAGS += -fno-stack-protector
 ifneq ($(BTF_LLVM_PROBE),)
 	EXTRA_CFLAGS += -g
 else
@@ -233,7 +234,7 @@ all:
 
 clean:
 	$(MAKE) -C ../../ M=$(CURDIR) clean
-	@rm -f *~
+	@find $(CURDIR) -type f -name '*~' -delete
 
 $(LIBBPF): FORCE
 # Fix up variables inherited from Kbuild that tools/ build system won't like
diff --git a/samples/bpf/fds_example.c b/samples/bpf/fds_example.c
index e51eb060244e..2e89eb2c2688 100644
--- a/samples/bpf/fds_example.c
+++ b/samples/bpf/fds_example.c
@@ -30,6 +30,8 @@
 #define BPF_M_MAP	1
 #define BPF_M_PROG	2
 
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
 static void usage(void)
 {
 	printf("Usage: fds_example [...]\n");
@@ -57,7 +59,6 @@ static int bpf_prog_create(const char *object)
 		BPF_EXIT_INSN(),
 	};
 	size_t insns_cnt = sizeof(insns) / sizeof(struct bpf_insn);
-	char bpf_log_buf[BPF_LOG_BUF_SIZE];
 	struct bpf_object *obj;
 	int prog_fd;
 
diff --git a/samples/bpf/lwt_len_hist_user.c b/samples/bpf/lwt_len_hist_user.c
index 587b68b1f8dd..430a4b7e353e 100644
--- a/samples/bpf/lwt_len_hist_user.c
+++ b/samples/bpf/lwt_len_hist_user.c
@@ -15,8 +15,6 @@
 #define MAX_INDEX 64
 #define MAX_STARS 38
 
-char bpf_log_buf[BPF_LOG_BUF_SIZE];
-
 static void stars(char *str, long val, long max, int width)
 {
 	int i;
diff --git a/samples/bpf/syscall_tp_kern.c b/samples/bpf/syscall_tp_kern.c
index 1d78819ffef1..630ce8c4d5a2 100644
--- a/samples/bpf/syscall_tp_kern.c
+++ b/samples/bpf/syscall_tp_kern.c
@@ -47,13 +47,27 @@ static __always_inline void count(void *map)
 SEC("tracepoint/syscalls/sys_enter_open")
 int trace_enter_open(struct syscalls_enter_open_args *ctx)
 {
-	count((void *)&enter_open_map);
+	count(&enter_open_map);
+	return 0;
+}
+
+SEC("tracepoint/syscalls/sys_enter_openat")
+int trace_enter_open_at(struct syscalls_enter_open_args *ctx)
+{
+	count(&enter_open_map);
 	return 0;
 }
 
 SEC("tracepoint/syscalls/sys_exit_open")
 int trace_enter_exit(struct syscalls_exit_open_args *ctx)
 {
-	count((void *)&exit_open_map);
+	count(&exit_open_map);
+	return 0;
+}
+
+SEC("tracepoint/syscalls/sys_exit_openat")
+int trace_enter_exit_at(struct syscalls_exit_open_args *ctx)
+{
+	count(&exit_open_map);
 	return 0;
 }
diff --git a/samples/bpf/trace_event_user.c b/samples/bpf/trace_event_user.c
index 16a16eadd509..749a50f2f9f3 100644
--- a/samples/bpf/trace_event_user.c
+++ b/samples/bpf/trace_event_user.c
@@ -37,9 +37,9 @@ static void print_ksym(__u64 addr)
 	}
 
 	printf("%s;", sym->name);
-	if (!strcmp(sym->name, "sys_read"))
+	if (!strstr(sym->name, "sys_read"))
 		sys_read_seen = true;
-	else if (!strcmp(sym->name, "sys_write"))
+	else if (!strstr(sym->name, "sys_write"))
 		sys_write_seen = true;
 }
 
diff --git a/samples/bpf/xdp_monitor_user.c b/samples/bpf/xdp_monitor_user.c
index dd558cbb2309..ef53b93db573 100644
--- a/samples/bpf/xdp_monitor_user.c
+++ b/samples/bpf/xdp_monitor_user.c
@@ -509,11 +509,8 @@ static void *alloc_rec_per_cpu(int record_size)
 {
 	unsigned int nr_cpus = bpf_num_possible_cpus();
 	void *array;
-	size_t size;
 
-	size = record_size * nr_cpus;
-	array = malloc(size);
-	memset(array, 0, size);
+	array = calloc(nr_cpus, record_size);
 	if (!array) {
 		fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus);
 		exit(EXIT_FAIL_MEM);
@@ -528,8 +525,7 @@ static struct stats_record *alloc_stats_record(void)
 	int i;
 
 	/* Alloc main stats_record structure */
-	rec = malloc(sizeof(*rec));
-	memset(rec, 0, sizeof(*rec));
+	rec = calloc(1, sizeof(*rec));
 	if (!rec) {
 		fprintf(stderr, "Mem alloc error\n");
 		exit(EXIT_FAIL_MEM);
diff --git a/samples/bpf/xdp_redirect_cpu_kern.c b/samples/bpf/xdp_redirect_cpu_kern.c
index a306d1c75622..f6a2b9aa04b2 100644
--- a/samples/bpf/xdp_redirect_cpu_kern.c
+++ b/samples/bpf/xdp_redirect_cpu_kern.c
@@ -15,7 +15,7 @@
 #include "bpf_helpers.h"
 #include "hash_func01.h"
 
-#define MAX_CPUS 64 /* WARNING - sync with _user.c */
+#define MAX_CPUS NR_CPUS
 
 /* Special map type that can XDP_REDIRECT frames to another CPU */
 struct bpf_map_def SEC("maps") cpu_map = {
diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c
index 575deaca429f..daa903569a0f 100644
--- a/samples/bpf/xdp_redirect_cpu_user.c
+++ b/samples/bpf/xdp_redirect_cpu_user.c
@@ -13,15 +13,18 @@ static const char *__doc__ =
 #include <unistd.h>
 #include <locale.h>
 #include <sys/resource.h>
+#include <sys/sysinfo.h>
 #include <getopt.h>
 #include <net/if.h>
 #include <time.h>
+#include <linux/limits.h>
+
+#define __must_check
+#include <linux/err.h>
 
 #include <arpa/inet.h>
 #include <linux/if_link.h>
 
-#define MAX_CPUS 64 /* WARNING - sync with _kern.c */
-
 /* How many xdp_progs are defined in _kern.c */
 #define MAX_PROG 6
 
@@ -36,6 +39,7 @@ static char *ifname;
 static __u32 prog_id;
 
 static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
+static int n_cpus;
 static int cpu_map_fd;
 static int rx_cnt_map_fd;
 static int redirect_err_cnt_map_fd;
@@ -46,6 +50,10 @@ static int cpus_count_map_fd;
 static int cpus_iterator_map_fd;
 static int exception_cnt_map_fd;
 
+#define NUM_TP 5
+struct bpf_link *tp_links[NUM_TP] = { 0 };
+static int tp_cnt = 0;
+
 /* Exit return codes */
 #define EXIT_OK		0
 #define EXIT_FAIL		1
@@ -88,6 +96,10 @@ static void int_exit(int sig)
 			printf("program on interface changed, not removing\n");
 		}
 	}
+	/* Detach tracepoints */
+	while (tp_cnt)
+		bpf_link__destroy(tp_links[--tp_cnt]);
+
 	exit(EXIT_OK);
 }
 
@@ -158,7 +170,7 @@ struct stats_record {
 	struct record redir_err;
 	struct record kthread;
 	struct record exception;
-	struct record enq[MAX_CPUS];
+	struct record enq[];
 };
 
 static bool map_collect_percpu(int fd, __u32 key, struct record *rec)
@@ -198,11 +210,8 @@ static struct datarec *alloc_record_per_cpu(void)
 {
 	unsigned int nr_cpus = bpf_num_possible_cpus();
 	struct datarec *array;
-	size_t size;
 
-	size = sizeof(struct datarec) * nr_cpus;
-	array = malloc(size);
-	memset(array, 0, size);
+	array = calloc(nr_cpus, sizeof(struct datarec));
 	if (!array) {
 		fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus);
 		exit(EXIT_FAIL_MEM);
@@ -213,19 +222,20 @@ static struct datarec *alloc_record_per_cpu(void)
 static struct stats_record *alloc_stats_record(void)
 {
 	struct stats_record *rec;
-	int i;
+	int i, size;
 
-	rec = malloc(sizeof(*rec));
-	memset(rec, 0, sizeof(*rec));
+	size = sizeof(*rec) + n_cpus * sizeof(struct record);
+	rec = malloc(size);
 	if (!rec) {
 		fprintf(stderr, "Mem alloc error\n");
 		exit(EXIT_FAIL_MEM);
 	}
+	memset(rec, 0, size);
 	rec->rx_cnt.cpu    = alloc_record_per_cpu();
 	rec->redir_err.cpu = alloc_record_per_cpu();
 	rec->kthread.cpu   = alloc_record_per_cpu();
 	rec->exception.cpu = alloc_record_per_cpu();
-	for (i = 0; i < MAX_CPUS; i++)
+	for (i = 0; i < n_cpus; i++)
 		rec->enq[i].cpu = alloc_record_per_cpu();
 
 	return rec;
@@ -235,7 +245,7 @@ static void free_stats_record(struct stats_record *r)
 {
 	int i;
 
-	for (i = 0; i < MAX_CPUS; i++)
+	for (i = 0; i < n_cpus; i++)
 		free(r->enq[i].cpu);
 	free(r->exception.cpu);
 	free(r->kthread.cpu);
@@ -338,7 +348,7 @@ static void stats_print(struct stats_record *stats_rec,
 	}
 
 	/* cpumap enqueue stats */
-	for (to_cpu = 0; to_cpu < MAX_CPUS; to_cpu++) {
+	for (to_cpu = 0; to_cpu < n_cpus; to_cpu++) {
 		char *fmt = "%-15s %3d:%-3d %'-14.0f %'-11.0f %'-10.2f %s\n";
 		char *fm2 = "%-15s %3s:%-3d %'-14.0f %'-11.0f %'-10.2f %s\n";
 		char *errstr = "";
@@ -463,7 +473,7 @@ static void stats_collect(struct stats_record *rec)
 	map_collect_percpu(fd, 1, &rec->redir_err);
 
 	fd = cpumap_enqueue_cnt_map_fd;
-	for (i = 0; i < MAX_CPUS; i++)
+	for (i = 0; i < n_cpus; i++)
 		map_collect_percpu(fd, i, &rec->enq[i]);
 
 	fd = cpumap_kthread_cnt_map_fd;
@@ -537,10 +547,10 @@ static int create_cpu_entry(__u32 cpu, __u32 queue_size,
  */
 static void mark_cpus_unavailable(void)
 {
-	__u32 invalid_cpu = MAX_CPUS;
+	__u32 invalid_cpu = n_cpus;
 	int ret, i;
 
-	for (i = 0; i < MAX_CPUS; i++) {
+	for (i = 0; i < n_cpus; i++) {
 		ret = bpf_map_update_elem(cpus_available_map_fd, &i,
 					  &invalid_cpu, 0);
 		if (ret) {
@@ -588,23 +598,61 @@ static void stats_poll(int interval, bool use_separators, char *prog_name,
 	free_stats_record(prev);
 }
 
+static struct bpf_link * attach_tp(struct bpf_object *obj,
+				   const char *tp_category,
+				   const char* tp_name)
+{
+	struct bpf_program *prog;
+	struct bpf_link *link;
+	char sec_name[PATH_MAX];
+	int len;
+
+	len = snprintf(sec_name, PATH_MAX, "tracepoint/%s/%s",
+		       tp_category, tp_name);
+	if (len < 0)
+		exit(EXIT_FAIL);
+
+	prog = bpf_object__find_program_by_title(obj, sec_name);
+	if (!prog) {
+		fprintf(stderr, "ERR: finding progsec: %s\n", sec_name);
+		exit(EXIT_FAIL_BPF);
+	}
+
+	link = bpf_program__attach_tracepoint(prog, tp_category, tp_name);
+	if (IS_ERR(link))
+		exit(EXIT_FAIL_BPF);
+
+	return link;
+}
+
+static void init_tracepoints(struct bpf_object *obj) {
+	tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_redirect_err");
+	tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_redirect_map_err");
+	tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_exception");
+	tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_cpumap_enqueue");
+	tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_cpumap_kthread");
+}
+
 static int init_map_fds(struct bpf_object *obj)
 {
-	cpu_map_fd = bpf_object__find_map_fd_by_name(obj, "cpu_map");
-	rx_cnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rx_cnt");
+	/* Maps updated by tracepoints */
 	redirect_err_cnt_map_fd =
 		bpf_object__find_map_fd_by_name(obj, "redirect_err_cnt");
+	exception_cnt_map_fd =
+		bpf_object__find_map_fd_by_name(obj, "exception_cnt");
 	cpumap_enqueue_cnt_map_fd =
 		bpf_object__find_map_fd_by_name(obj, "cpumap_enqueue_cnt");
 	cpumap_kthread_cnt_map_fd =
 		bpf_object__find_map_fd_by_name(obj, "cpumap_kthread_cnt");
+
+	/* Maps used by XDP */
+	rx_cnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rx_cnt");
+	cpu_map_fd = bpf_object__find_map_fd_by_name(obj, "cpu_map");
 	cpus_available_map_fd =
 		bpf_object__find_map_fd_by_name(obj, "cpus_available");
 	cpus_count_map_fd = bpf_object__find_map_fd_by_name(obj, "cpus_count");
 	cpus_iterator_map_fd =
 		bpf_object__find_map_fd_by_name(obj, "cpus_iterator");
-	exception_cnt_map_fd =
-		bpf_object__find_map_fd_by_name(obj, "exception_cnt");
 
 	if (cpu_map_fd < 0 || rx_cnt_map_fd < 0 ||
 	    redirect_err_cnt_map_fd < 0 || cpumap_enqueue_cnt_map_fd < 0 ||
@@ -638,6 +686,8 @@ int main(int argc, char **argv)
 	int prog_fd;
 	__u32 qsize;
 
+	n_cpus = get_nprocs_conf();
+
 	/* Notice: choosing he queue size is very important with the
 	 * ixgbe driver, because it's driver page recycling trick is
 	 * dependend on pages being returned quickly.  The number of
@@ -662,6 +712,7 @@ int main(int argc, char **argv)
 			strerror(errno));
 		return EXIT_FAIL;
 	}
+	init_tracepoints(obj);
 	if (init_map_fds(obj) < 0) {
 		fprintf(stderr, "bpf_object__find_map_fd_by_name failed\n");
 		return EXIT_FAIL;
@@ -706,7 +757,7 @@ int main(int argc, char **argv)
 		case 'c':
 			/* Add multiple CPUs */
 			add_cpu = strtoul(optarg, NULL, 0);
-			if (add_cpu >= MAX_CPUS) {
+			if (add_cpu >= n_cpus) {
 				fprintf(stderr,
 				"--cpu nr too large for cpumap err(%d):%s\n",
 					errno, strerror(errno));
diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c
index 1210f3b170f0..1ea81d7acada 100644
--- a/samples/bpf/xdp_rxq_info_user.c
+++ b/samples/bpf/xdp_rxq_info_user.c
@@ -198,11 +198,8 @@ static struct datarec *alloc_record_per_cpu(void)
 {
 	unsigned int nr_cpus = bpf_num_possible_cpus();
 	struct datarec *array;
-	size_t size;
 
-	size = sizeof(struct datarec) * nr_cpus;
-	array = malloc(size);
-	memset(array, 0, size);
+	array = calloc(nr_cpus, sizeof(struct datarec));
 	if (!array) {
 		fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus);
 		exit(EXIT_FAIL_MEM);
@@ -214,11 +211,8 @@ static struct record *alloc_record_per_rxq(void)
 {
 	unsigned int nr_rxqs = bpf_map__def(rx_queue_index_map)->max_entries;
 	struct record *array;
-	size_t size;
 
-	size = sizeof(struct record) * nr_rxqs;
-	array = malloc(size);
-	memset(array, 0, size);
+	array = calloc(nr_rxqs, sizeof(struct record));
 	if (!array) {
 		fprintf(stderr, "Mem alloc error (nr_rxqs:%u)\n", nr_rxqs);
 		exit(EXIT_FAIL_MEM);
@@ -232,8 +226,7 @@ static struct stats_record *alloc_stats_record(void)
 	struct stats_record *rec;
 	int i;
 
-	rec = malloc(sizeof(*rec));
-	memset(rec, 0, sizeof(*rec));
+	rec = calloc(1, sizeof(struct stats_record));
 	if (!rec) {
 		fprintf(stderr, "Mem alloc error\n");
 		exit(EXIT_FAIL_MEM);
@@ -489,9 +482,9 @@ int main(int argc, char **argv)
 	if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd))
 		return EXIT_FAIL;
 
-	map = bpf_map__next(NULL, obj);
-	stats_global_map = bpf_map__next(map, obj);
-	rx_queue_index_map = bpf_map__next(stats_global_map, obj);
+	map =  bpf_object__find_map_by_name(obj, "config_map");
+	stats_global_map = bpf_object__find_map_by_name(obj, "stats_global_map");
+	rx_queue_index_map = bpf_object__find_map_by_name(obj, "rx_queue_index_map");
 	if (!map || !stats_global_map || !rx_queue_index_map) {
 		printf("finding a map in obj file failed\n");
 		return EXIT_FAIL;
diff --git a/samples/seccomp/user-trap.c b/samples/seccomp/user-trap.c
index 6d0125ca8af7..20291ec6489f 100644
--- a/samples/seccomp/user-trap.c
+++ b/samples/seccomp/user-trap.c
@@ -298,14 +298,14 @@ int main(void)
 		req = malloc(sizes.seccomp_notif);
 		if (!req)
 			goto out_close;
-		memset(req, 0, sizeof(*req));
 
 		resp = malloc(sizes.seccomp_notif_resp);
 		if (!resp)
 			goto out_req;
-		memset(resp, 0, sizeof(*resp));
+		memset(resp, 0, sizes.seccomp_notif_resp);
 
 		while (1) {
+			memset(req, 0, sizes.seccomp_notif);
 			if (ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, req)) {
 				perror("ioctl recv");
 				goto out_resp;
diff --git a/samples/trace_printk/trace-printk.c b/samples/trace_printk/trace-printk.c
index 7affc3b50b61..cfc159580263 100644
--- a/samples/trace_printk/trace-printk.c
+++ b/samples/trace_printk/trace-printk.c
@@ -36,6 +36,7 @@ static int __init trace_printk_init(void)
 
 	/* Kick off printing in irq context */
 	irq_work_queue(&irqwork);
+	irq_work_sync(&irqwork);
 
 	trace_printk("This is a %s that will use trace_bprintk()\n",
 		     "static string");
diff --git a/samples/vfio-mdev/mdpy.c b/samples/vfio-mdev/mdpy.c
index cc86bf6566e4..9894693f3be1 100644
--- a/samples/vfio-mdev/mdpy.c
+++ b/samples/vfio-mdev/mdpy.c
@@ -418,7 +418,7 @@ static int mdpy_mmap(struct mdev_device *mdev, struct vm_area_struct *vma)
 		return -EINVAL;
 
 	return remap_vmalloc_range_partial(vma, vma->vm_start,
-					   mdev_state->memblk,
+					   mdev_state->memblk, 0,
 					   vma->vm_end - vma->vm_start);
 }
 
diff --git a/samples/vfs/test-statx.c b/samples/vfs/test-statx.c
index a3d68159fb51..507f09c38b49 100644
--- a/samples/vfs/test-statx.c
+++ b/samples/vfs/test-statx.c
@@ -23,6 +23,8 @@
 #include <linux/fcntl.h>
 #define statx foo
 #define statx_timestamp foo_timestamp
+struct statx;
+struct statx_timestamp;
 #include <sys/stat.h>
 #undef statx
 #undef statx_timestamp
diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index f641bb0aa63f..2ea6bcefc43d 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -55,14 +55,13 @@ kecho := $($(quiet)kecho)
 # - stdin is piped in from the first prerequisite ($<) so one has
 #   to specify a valid file as first prerequisite (often the kbuild file)
 define filechk
-	$(Q)set -e;				\
-	mkdir -p $(dir $@);			\
-	{ $(filechk_$(1)); } > $@.tmp;		\
-	if [ -r $@ ] && cmp -s $@ $@.tmp; then	\
-		rm -f $@.tmp;			\
-	else					\
-		$(kecho) '  UPD     $@';	\
-		mv -f $@.tmp $@;		\
+	$(Q)set -e;						\
+	mkdir -p $(dir $@);					\
+	trap "rm -f $(dot-target).tmp" EXIT;			\
+	{ $(filechk_$(1)); } > $(dot-target).tmp;		\
+	if [ ! -r $@ ] || ! cmp -s $@ $(dot-target).tmp; then	\
+		$(kecho) '  UPD     $@';			\
+		mv -f $(dot-target).tmp $@;			\
 	fi
 endef
 
@@ -83,20 +82,21 @@ cc-cross-prefix = $(firstword $(foreach c, $(filter-out -%, $(1)), \
 			$(if $(shell command -v $(c)gcc 2>/dev/null), $(c))))
 
 # output directory for tests below
-TMPOUT := $(if $(KBUILD_EXTMOD),$(firstword $(KBUILD_EXTMOD))/)
+TMPOUT = $(if $(KBUILD_EXTMOD),$(firstword $(KBUILD_EXTMOD))/).tmp_$$$$
 
 # try-run
 # Usage: option = $(call try-run, $(CC)...-o "$$TMP",option-ok,otherwise)
 # Exit code chooses option. "$$TMP" serves as a temporary file and is
 # automatically cleaned up.
 try-run = $(shell set -e;		\
-	TMP="$(TMPOUT).$$$$.tmp";	\
-	TMPO="$(TMPOUT).$$$$.o";	\
+	TMP=$(TMPOUT)/tmp;		\
+	TMPO=$(TMPOUT)/tmp.o;		\
+	mkdir -p $(TMPOUT);		\
+	trap "rm -rf $(TMPOUT)" EXIT;	\
 	if ($(1)) >/dev/null 2>&1;	\
 	then echo "$(2)";		\
 	else echo "$(3)";		\
-	fi;				\
-	rm -f "$$TMP" "$$TMPO")
+	fi)
 
 # as-option
 # Usage: cflags-y += $(call as-option,-Wa$(comma)-isa=foo,)
diff --git a/scripts/Kconfig.include b/scripts/Kconfig.include
index 4bbf4fc163a2..e9551628ca6c 100644
--- a/scripts/Kconfig.include
+++ b/scripts/Kconfig.include
@@ -25,7 +25,7 @@ failure = $(if-success,$(1),n,y)
 
 # $(cc-option,<flag>)
 # Return y if the compiler supports <flag>, n otherwise
-cc-option = $(success,$(CC) -Werror $(CLANG_FLAGS) $(1) -E -x c /dev/null -o /dev/null)
+cc-option = $(success,$(CC) -Werror $(CLANG_FLAGS) $(1) -S -x c /dev/null -o /dev/null)
 
 # $(ld-option,<flag>)
 # Return y if the linker supports <flag>, n otherwise
@@ -37,3 +37,10 @@ $(error-if,$(failure,command -v $(LD)),linker '$(LD)' not found)
 
 # gcc version including patch level
 gcc-version := $(shell,$(srctree)/scripts/gcc-version.sh $(CC))
+
+# machine bit flags
+#  $(m32-flag): -m32 if the compiler supports it, or an empty string otherwise.
+#  $(m64-flag): -m64 if the compiler supports it, or an empty string otherwise.
+cc-option-bit = $(if-success,$(CC) -Werror $(1) -E -x c /dev/null -o /dev/null,$(1))
+m32-flag := $(cc-option-bit,-m32)
+m64-flag := $(cc-option-bit,-m64)
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index f1f38c8cdc74..0ca3a6464d15 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -300,13 +300,13 @@ DT_TMP_SCHEMA := $(objtree)/$(DT_BINDING_DIR)/processed-schema.yaml
 quiet_cmd_dtb_check =	CHECK   $@
       cmd_dtb_check =	$(DT_CHECKER) -u $(srctree)/$(DT_BINDING_DIR) -p $(DT_TMP_SCHEMA) $@ ;
 
-define rule_dtc_dt_yaml
+define rule_dtc
 	$(call cmd_and_fixdep,dtc,yaml)
 	$(call cmd,dtb_check)
 endef
 
 $(obj)/%.dt.yaml: $(src)/%.dts $(DTC) $(DT_TMP_SCHEMA) FORCE
-	$(call if_changed_rule,dtc_dt_yaml)
+	$(call if_changed_rule,dtc,yaml)
 
 dtc-tmp = $(subst $(comma),_,$(dot-target).dts.tmp)
 
diff --git a/scripts/config b/scripts/config
index e0e39826dae9..eee5b7f3a092 100755
--- a/scripts/config
+++ b/scripts/config
@@ -7,6 +7,9 @@ myname=${0##*/}
 # If no prefix forced, use the default CONFIG_
 CONFIG_="${CONFIG_-CONFIG_}"
 
+# We use an uncommon delimiter for sed substitutions
+SED_DELIM=$(echo -en "\001")
+
 usage() {
 	cat >&2 <<EOL
 Manipulate options in a .config file from the command line.
@@ -83,7 +86,7 @@ txt_subst() {
 	local infile="$3"
 	local tmpfile="$infile.swp"
 
-	sed -e "s:$before:$after:" "$infile" >"$tmpfile"
+	sed -e "s$SED_DELIM$before$SED_DELIM$after$SED_DELIM" "$infile" >"$tmpfile"
 	# replace original file with the edited one
 	mv "$tmpfile" "$infile"
 }
diff --git a/scripts/decode_stacktrace.sh b/scripts/decode_stacktrace.sh
index 6c2c05a75b54..ad262ec7487d 100755
--- a/scripts/decode_stacktrace.sh
+++ b/scripts/decode_stacktrace.sh
@@ -84,8 +84,8 @@ parse_symbol() {
 		return
 	fi
 
-	# Strip out the base of the path
-	code=${code#$basepath/}
+	# Strip out the base of the path on each line
+	code=$(while read -r line; do echo "${line#$basepath/}"; done <<< "$code")
 
 	# In the case of inlines, move everything to same line
 	code=${code//$'\n'/' '}
diff --git a/scripts/decodecode b/scripts/decodecode
index ba8b8d5834e6..fbdb325cdf4f 100755
--- a/scripts/decodecode
+++ b/scripts/decodecode
@@ -126,7 +126,7 @@ faultlinenum=$(( $(wc -l $T.oo  | cut -d" " -f1) - \
 faultline=`cat $T.dis | head -1 | cut -d":" -f2-`
 faultline=`echo "$faultline" | sed -e 's/\[/\\\[/g; s/\]/\\\]/g'`
 
-cat $T.oo | sed -e "${faultlinenum}s/^\(.*:\)\(.*\)/\1\*\2\t\t<-- trapping instruction/"
+cat $T.oo | sed -e "${faultlinenum}s/^\([^:]*:\)\(.*\)/\1\*\2\t\t<-- trapping instruction/"
 echo
 cat $T.aa
 cleanup
diff --git a/scripts/dtc/dtc-lexer.l b/scripts/dtc/dtc-lexer.l
index 06c040902444..d1b3810156c7 100644
--- a/scripts/dtc/dtc-lexer.l
+++ b/scripts/dtc/dtc-lexer.l
@@ -38,7 +38,6 @@ LINECOMMENT	"//".*\n
 #include "srcpos.h"
 #include "dtc-parser.tab.h"
 
-YYLTYPE yylloc;
 extern bool treesource_error;
 
 /* CAUTION: this will stop working if we ever use yyless() or yyunput() */
diff --git a/scripts/find-unused-docs.sh b/scripts/find-unused-docs.sh
index 3f46f8977dc4..ee6a50e33aba 100755
--- a/scripts/find-unused-docs.sh
+++ b/scripts/find-unused-docs.sh
@@ -54,7 +54,7 @@ for file in `find $1 -name '*.c'`; do
 	if [[ ${FILES_INCLUDED[$file]+_} ]]; then
 	continue;
 	fi
-	str=$(scripts/kernel-doc -text -export "$file" 2>/dev/null)
+	str=$(scripts/kernel-doc -export "$file" 2>/dev/null)
 	if [[ -n "$str" ]]; then
 	echo "$file"
 	fi
diff --git a/scripts/gcc-plugins/Kconfig b/scripts/gcc-plugins/Kconfig
index e9c677a53c74..c2551f7256e2 100644
--- a/scripts/gcc-plugins/Kconfig
+++ b/scripts/gcc-plugins/Kconfig
@@ -14,8 +14,8 @@ config HAVE_GCC_PLUGINS
 	  An arch should select this symbol if it supports building with
 	  GCC plugins.
 
-config GCC_PLUGINS
-	bool
+menuconfig GCC_PLUGINS
+	bool "GCC plugins"
 	depends on HAVE_GCC_PLUGINS
 	depends on PLUGIN_HOSTCC != ""
 	default y
@@ -25,8 +25,7 @@ config GCC_PLUGINS
 
 	  See Documentation/gcc-plugins.txt for details.
 
-menu "GCC plugins"
-	depends on GCC_PLUGINS
+if GCC_PLUGINS
 
 config GCC_PLUGIN_CYC_COMPLEXITY
 	bool "Compute the cyclomatic complexity of a function" if EXPERT
@@ -113,4 +112,4 @@ config GCC_PLUGIN_ARM_SSP_PER_TASK
 	bool
 	depends on GCC_PLUGINS && ARM
 
-endmenu
+endif
diff --git a/scripts/gcc-plugins/Makefile b/scripts/gcc-plugins/Makefile
index aa0d0ec6936d..9e95862f2788 100644
--- a/scripts/gcc-plugins/Makefile
+++ b/scripts/gcc-plugins/Makefile
@@ -11,6 +11,7 @@ else
   HOST_EXTRACXXFLAGS += -I$(GCC_PLUGINS_DIR)/include -I$(src) -std=gnu++98 -fno-rtti
   HOST_EXTRACXXFLAGS += -fno-exceptions -fasynchronous-unwind-tables -ggdb
   HOST_EXTRACXXFLAGS += -Wno-narrowing -Wno-unused-variable
+  HOST_EXTRACXXFLAGS += -Wno-format-diag
   export HOST_EXTRACXXFLAGS
 endif
 
diff --git a/scripts/gcc-plugins/gcc-common.h b/scripts/gcc-plugins/gcc-common.h
index 17f06079a712..9ad76b7f3f10 100644
--- a/scripts/gcc-plugins/gcc-common.h
+++ b/scripts/gcc-plugins/gcc-common.h
@@ -35,7 +35,9 @@
 #include "ggc.h"
 #include "timevar.h"
 
+#if BUILDING_GCC_VERSION < 10000
 #include "params.h"
+#endif
 
 #if BUILDING_GCC_VERSION <= 4009
 #include "pointer-set.h"
@@ -847,6 +849,7 @@ static inline gimple gimple_build_assign_with_ops(enum tree_code subcode, tree l
 	return gimple_build_assign(lhs, subcode, op1, op2 PASS_MEM_STAT);
 }
 
+#if BUILDING_GCC_VERSION < 10000
 template <>
 template <>
 inline bool is_a_helper<const ggoto *>::test(const_gimple gs)
@@ -860,6 +863,7 @@ inline bool is_a_helper<const greturn *>::test(const_gimple gs)
 {
 	return gs->code == GIMPLE_RETURN;
 }
+#endif
 
 static inline gasm *as_a_gasm(gimple stmt)
 {
diff --git a/scripts/gdb/linux/rbtree.py b/scripts/gdb/linux/rbtree.py
index 39db889b874c..c4b991607917 100644
--- a/scripts/gdb/linux/rbtree.py
+++ b/scripts/gdb/linux/rbtree.py
@@ -12,7 +12,7 @@ rb_node_type = utils.CachedType("struct rb_node")
 
 def rb_first(root):
     if root.type == rb_root_type.get_type():
-        node = node.address.cast(rb_root_type.get_type().pointer())
+        node = root.address.cast(rb_root_type.get_type().pointer())
     elif root.type != rb_root_type.get_type().pointer():
         raise gdb.GdbError("Must be struct rb_root not {}".format(root.type))
 
@@ -28,7 +28,7 @@ def rb_first(root):
 
 def rb_last(root):
     if root.type == rb_root_type.get_type():
-        node = node.address.cast(rb_root_type.get_type().pointer())
+        node = root.address.cast(rb_root_type.get_type().pointer())
     elif root.type != rb_root_type.get_type().pointer():
         raise gdb.GdbError("Must be struct rb_root not {}".format(root.type))
 
diff --git a/scripts/gdb/linux/symbols.py b/scripts/gdb/linux/symbols.py
index 3c2950430289..aa06240ad38b 100644
--- a/scripts/gdb/linux/symbols.py
+++ b/scripts/gdb/linux/symbols.py
@@ -96,7 +96,7 @@ lx-symbols command."""
             return ""
         attrs = sect_attrs['attrs']
         section_name_to_address = {
-            attrs[n]['name'].string(): attrs[n]['address']
+            attrs[n]['battr']['attr']['name'].string(): attrs[n]['address']
             for n in range(int(sect_attrs['nsections']))}
         args = []
         for section_name in [".data", ".data..read_mostly", ".rodata", ".bss",
diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index 27964917cbfd..3ac33d315e1c 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -1372,7 +1372,7 @@ bool conf_set_all_new_symbols(enum conf_def_mode mode)
 
 		sym_calc_value(csym);
 		if (mode == def_random)
-			has_changed = randomize_choice_values(csym);
+			has_changed |= randomize_choice_values(csym);
 		else {
 			set_all_choice_values(csym);
 			has_changed = true;
diff --git a/scripts/kconfig/expr.c b/scripts/kconfig/expr.c
index 77ffff3a053c..9f1de58e9f0c 100644
--- a/scripts/kconfig/expr.c
+++ b/scripts/kconfig/expr.c
@@ -254,6 +254,13 @@ static int expr_eq(struct expr *e1, struct expr *e2)
 {
 	int res, old_count;
 
+	/*
+	 * A NULL expr is taken to be yes, but there's also a different way to
+	 * represent yes. expr_is_yes() checks for either representation.
+	 */
+	if (!e1 || !e2)
+		return expr_is_yes(e1) && expr_is_yes(e2);
+
 	if (e1->type != e2->type)
 		return 0;
 	switch (e1->type) {
diff --git a/scripts/kconfig/qconf.cc b/scripts/kconfig/qconf.cc
index ce7fc87a49a7..1ce172967b16 100644
--- a/scripts/kconfig/qconf.cc
+++ b/scripts/kconfig/qconf.cc
@@ -627,7 +627,7 @@ void ConfigList::updateMenuList(ConfigItem *parent, struct menu* menu)
 			last = item;
 			continue;
 		}
-	hide:
+hide:
 		if (item && item->menu == child) {
 			last = parent->firstChild();
 			if (last == item)
@@ -692,7 +692,7 @@ void ConfigList::updateMenuList(ConfigList *parent, struct menu* menu)
 			last = item;
 			continue;
 		}
-	hide:
+hide:
 		if (item && item->menu == child) {
 			last = (ConfigItem*)parent->topLevelItem(0);
 			if (last == item)
@@ -1225,10 +1225,11 @@ QMenu* ConfigInfoView::createStandardContextMenu(const QPoint & pos)
 {
 	QMenu* popup = Parent::createStandardContextMenu(pos);
 	QAction* action = new QAction("Show Debug Info", popup);
-	  action->setCheckable(true);
-	  connect(action, SIGNAL(toggled(bool)), SLOT(setShowDebug(bool)));
-	  connect(this, SIGNAL(showDebugChanged(bool)), action, SLOT(setOn(bool)));
-	  action->setChecked(showDebug());
+
+	action->setCheckable(true);
+	connect(action, SIGNAL(toggled(bool)), SLOT(setShowDebug(bool)));
+	connect(this, SIGNAL(showDebugChanged(bool)), action, SLOT(setOn(bool)));
+	action->setChecked(showDebug());
 	popup->addSeparator();
 	popup->addAction(action);
 	return popup;
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index a7124f895b24..307574be4e22 100755..100644
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -97,13 +97,13 @@ gen_btf()
 	local pahole_ver;
 
 	if ! [ -x "$(command -v ${PAHOLE})" ]; then
-		info "BTF" "${1}: pahole (${PAHOLE}) is not available"
+		echo >&2 "BTF: ${1}: pahole (${PAHOLE}) is not available"
 		return 0
 	fi
 
 	pahole_ver=$(${PAHOLE} --version | sed -E 's/v([0-9]+)\.([0-9]+)/\1\2/')
 	if [ "${pahole_ver}" -lt "113" ]; then
-		info "BTF" "${1}: pahole version $(${PAHOLE} --version) is too old, need at least v1.13"
+		echo >&2 "BTF: ${1}: pahole version $(${PAHOLE} --version) is too old, need at least v1.13"
 		return 0
 	fi
 
diff --git a/scripts/mksysmap b/scripts/mksysmap
index a35acc0d0b82..9aa23d15862a 100755
--- a/scripts/mksysmap
+++ b/scripts/mksysmap
@@ -41,4 +41,4 @@
 # so we just ignore them to let readprofile continue to work.
 # (At least sparc64 has __crc_ in the middle).
 
-$NM -n $1 | grep -v '\( [aNUw] \)\|\(__crc_\)\|\( \$[adt]\)\|\( .L\)' > $2
+$NM -n $1 | grep -v '\( [aNUw] \)\|\(__crc_\)\|\( \$[adt]\)\|\( \.L\)' > $2
diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian
index 8351584cb24e..de4d89c5306f 100755
--- a/scripts/package/mkdebian
+++ b/scripts/package/mkdebian
@@ -136,7 +136,7 @@ mkdir -p debian/source/
 echo "1.0" > debian/source/format
 
 echo $debarch > debian/arch
-extra_build_depends=", $(if_enabled_echo CONFIG_UNWINDER_ORC libelf-dev)"
+extra_build_depends=", $(if_enabled_echo CONFIG_UNWINDER_ORC libelf-dev:native)"
 extra_build_depends="$extra_build_depends, $(if_enabled_echo CONFIG_SYSTEM_TRUSTED_KEYRING libssl-dev:native)"
 
 # Generate a simple changelog template
@@ -174,7 +174,7 @@ Source: $sourcename
 Section: kernel
 Priority: optional
 Maintainer: $maintainer
-Build-Depends: bc, kmod, cpio, bison, flex | flex:native $extra_build_depends
+Build-Depends: bc, rsync, kmod, cpio, bison, flex | flex:native $extra_build_depends
 Homepage: http://www.kernel.org/
 
 Package: $packagename
diff --git a/scripts/parse-maintainers.pl b/scripts/parse-maintainers.pl
index 255cef1b098d..255cef1b098d 100644..100755
--- a/scripts/parse-maintainers.pl
+++ b/scripts/parse-maintainers.pl
diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c
index 8387a9bc064a..5f58c8e7cb59 100644
--- a/scripts/recordmcount.c
+++ b/scripts/recordmcount.c
@@ -39,6 +39,12 @@
 #define R_AARCH64_ABS64	257
 #endif
 
+#define R_ARM_PC24		1
+#define R_ARM_THM_CALL		10
+#define R_ARM_CALL		28
+
+#define R_AARCH64_CALL26	283
+
 static int fd_map;	/* File descriptor for file being modified. */
 static int mmap_failed; /* Boolean flag. */
 static char gpfx;	/* prefix for global symbol name (sometimes '_') */
@@ -414,6 +420,23 @@ is_mcounted_section_name(char const *const txtname)
 #define RECORD_MCOUNT_64
 #include "recordmcount.h"
 
+static int arm_is_fake_mcount(Elf32_Rel const *rp)
+{
+	switch (ELF32_R_TYPE(w(rp->r_info))) {
+	case R_ARM_THM_CALL:
+	case R_ARM_CALL:
+	case R_ARM_PC24:
+		return 0;
+	}
+
+	return 1;
+}
+
+static int arm64_is_fake_mcount(Elf64_Rel const *rp)
+{
+	return ELF64_R_TYPE(w(rp->r_info)) != R_AARCH64_CALL26;
+}
+
 /* 64-bit EM_MIPS has weird ELF64_Rela.r_info.
  * http://techpubs.sgi.com/library/manuals/4000/007-4658-001/pdf/007-4658-001.pdf
  * We interpret Table 29 Relocation Operation (Elf64_Rel, Elf64_Rela) [p.40]
@@ -515,12 +538,14 @@ do_file(char const *const fname)
 			 altmcount = "__gnu_mcount_nc";
 			 make_nop = make_nop_arm;
 			 rel_type_nop = R_ARM_NONE;
+			 is_fake_mcount32 = arm_is_fake_mcount;
 			 break;
 	case EM_AARCH64:
 			reltype = R_AARCH64_ABS64;
 			make_nop = make_nop_arm64;
 			rel_type_nop = R_AARCH64_NONE;
 			ideal_nop = ideal_nop4_arm64;
+			is_fake_mcount64 = arm64_is_fake_mcount;
 			gpfx = '_';
 			break;
 	case EM_IA_64:	 reltype = R_IA64_IMM64;   gpfx = '_'; break;
diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index 66d0b4245ef6..6b9da8d074cc 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -414,7 +414,7 @@ static ssize_t policy_update(u32 mask, const char __user *buf, size_t size,
 	 */
 	error = aa_may_manage_policy(label, ns, mask);
 	if (error)
-		return error;
+		goto end_section;
 
 	data = aa_simple_write_to_buffer(buf, size, size, pos);
 	error = PTR_ERR(data);
@@ -422,6 +422,7 @@ static ssize_t policy_update(u32 mask, const char __user *buf, size_t size,
 		error = aa_replace_profiles(ns, label, mask, data);
 		aa_put_loaddata(data);
 	}
+end_section:
 	end_current_label_crit_section(label);
 
 	return error;
@@ -583,7 +584,7 @@ static __poll_t ns_revision_poll(struct file *file, poll_table *pt)
 
 void __aa_bump_ns_revision(struct aa_ns *ns)
 {
-	ns->revision++;
+	WRITE_ONCE(ns->revision, ns->revision + 1);
 	wake_up_interruptible(&ns->wait);
 }
 
diff --git a/security/apparmor/audit.c b/security/apparmor/audit.c
index 5a98661a8b46..597732503815 100644
--- a/security/apparmor/audit.c
+++ b/security/apparmor/audit.c
@@ -197,8 +197,9 @@ int aa_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule)
 	rule->label = aa_label_parse(&root_ns->unconfined->label, rulestr,
 				     GFP_KERNEL, true, false);
 	if (IS_ERR(rule->label)) {
+		int err = PTR_ERR(rule->label);
 		aa_audit_rule_free(rule);
-		return PTR_ERR(rule->label);
+		return err;
 	}
 
 	*vrule = rule;
diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c
index 9e0492795267..1a33f490e667 100644
--- a/security/apparmor/domain.c
+++ b/security/apparmor/domain.c
@@ -317,6 +317,7 @@ static int aa_xattrs_match(const struct linux_binprm *bprm,
 
 	if (!bprm || !profile->xattr_count)
 		return 0;
+	might_sleep();
 
 	/* transition from exec match to xattr set */
 	state = aa_dfa_null_transition(profile->xmatch, state);
@@ -361,10 +362,11 @@ out:
 }
 
 /**
- * __attach_match_ - find an attachment match
+ * find_attach - do attachment search for unconfined processes
  * @bprm - binprm structure of transitioning task
- * @name - to match against  (NOT NULL)
+ * @ns: the current namespace  (NOT NULL)
  * @head - profile list to walk  (NOT NULL)
+ * @name - to match against  (NOT NULL)
  * @info - info message if there was an error (NOT NULL)
  *
  * Do a linear search on the profiles in the list.  There is a matching
@@ -374,12 +376,11 @@ out:
  *
  * Requires: @head not be shared or have appropriate locks held
  *
- * Returns: profile or NULL if no match found
+ * Returns: label or NULL if no match found
  */
-static struct aa_profile *__attach_match(const struct linux_binprm *bprm,
-					 const char *name,
-					 struct list_head *head,
-					 const char **info)
+static struct aa_label *find_attach(const struct linux_binprm *bprm,
+				    struct aa_ns *ns, struct list_head *head,
+				    const char *name, const char **info)
 {
 	int candidate_len = 0, candidate_xattrs = 0;
 	bool conflict = false;
@@ -388,6 +389,8 @@ static struct aa_profile *__attach_match(const struct linux_binprm *bprm,
 	AA_BUG(!name);
 	AA_BUG(!head);
 
+	rcu_read_lock();
+restart:
 	list_for_each_entry_rcu(profile, head, base.list) {
 		if (profile->label.flags & FLAG_NULL &&
 		    &profile->label == ns_unconfined(profile->ns))
@@ -413,16 +416,32 @@ static struct aa_profile *__attach_match(const struct linux_binprm *bprm,
 			perm = dfa_user_allow(profile->xmatch, state);
 			/* any accepting state means a valid match. */
 			if (perm & MAY_EXEC) {
-				int ret;
+				int ret = 0;
 
 				if (count < candidate_len)
 					continue;
 
-				ret = aa_xattrs_match(bprm, profile, state);
-				/* Fail matching if the xattrs don't match */
-				if (ret < 0)
-					continue;
-
+				if (bprm && profile->xattr_count) {
+					long rev = READ_ONCE(ns->revision);
+
+					if (!aa_get_profile_not0(profile))
+						goto restart;
+					rcu_read_unlock();
+					ret = aa_xattrs_match(bprm, profile,
+							      state);
+					rcu_read_lock();
+					aa_put_profile(profile);
+					if (rev !=
+					    READ_ONCE(ns->revision))
+						/* policy changed */
+						goto restart;
+					/*
+					 * Fail matching if the xattrs don't
+					 * match
+					 */
+					if (ret < 0)
+						continue;
+				}
 				/*
 				 * TODO: allow for more flexible best match
 				 *
@@ -445,43 +464,28 @@ static struct aa_profile *__attach_match(const struct linux_binprm *bprm,
 				candidate_xattrs = ret;
 				conflict = false;
 			}
-		} else if (!strcmp(profile->base.name, name))
+		} else if (!strcmp(profile->base.name, name)) {
 			/*
 			 * old exact non-re match, without conditionals such
 			 * as xattrs. no more searching required
 			 */
-			return profile;
+			candidate = profile;
+			goto out;
+		}
 	}
 
-	if (conflict) {
-		*info = "conflicting profile attachments";
+	if (!candidate || conflict) {
+		if (conflict)
+			*info = "conflicting profile attachments";
+		rcu_read_unlock();
 		return NULL;
 	}
 
-	return candidate;
-}
-
-/**
- * find_attach - do attachment search for unconfined processes
- * @bprm - binprm structure of transitioning task
- * @ns: the current namespace  (NOT NULL)
- * @list: list to search  (NOT NULL)
- * @name: the executable name to match against  (NOT NULL)
- * @info: info message if there was an error
- *
- * Returns: label or NULL if no match found
- */
-static struct aa_label *find_attach(const struct linux_binprm *bprm,
-				    struct aa_ns *ns, struct list_head *list,
-				    const char *name, const char **info)
-{
-	struct aa_profile *profile;
-
-	rcu_read_lock();
-	profile = aa_get_profile(__attach_match(bprm, name, list, info));
+out:
+	candidate = aa_get_newest_profile(candidate);
 	rcu_read_unlock();
 
-	return profile ? &profile->label : NULL;
+	return &candidate->label;
 }
 
 static const char *next_name(int xtype, const char *name)
@@ -931,7 +935,8 @@ int apparmor_bprm_set_creds(struct linux_binprm *bprm)
 	 * aways results in a further reduction of permissions.
 	 */
 	if ((bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS) &&
-	    !unconfined(label) && !aa_label_is_subset(new, ctx->nnp)) {
+	    !unconfined(label) &&
+	    !aa_label_is_unconfined_subset(new, ctx->nnp)) {
 		error = -EPERM;
 		info = "no new privs";
 		goto audit;
@@ -1209,7 +1214,7 @@ int aa_change_hat(const char *hats[], int count, u64 token, int flags)
 		 * reduce restrictions.
 		 */
 		if (task_no_new_privs(current) && !unconfined(label) &&
-		    !aa_label_is_subset(new, ctx->nnp)) {
+		    !aa_label_is_unconfined_subset(new, ctx->nnp)) {
 			/* not an apparmor denial per se, so don't log it */
 			AA_DEBUG("no_new_privs - change_hat denied");
 			error = -EPERM;
@@ -1230,7 +1235,7 @@ int aa_change_hat(const char *hats[], int count, u64 token, int flags)
 		 * reduce restrictions.
 		 */
 		if (task_no_new_privs(current) && !unconfined(label) &&
-		    !aa_label_is_subset(previous, ctx->nnp)) {
+		    !aa_label_is_unconfined_subset(previous, ctx->nnp)) {
 			/* not an apparmor denial per se, so don't log it */
 			AA_DEBUG("no_new_privs - change_hat denied");
 			error = -EPERM;
@@ -1330,6 +1335,7 @@ int aa_change_profile(const char *fqname, int flags)
 		ctx->nnp = aa_get_label(label);
 
 	if (!fqname || !*fqname) {
+		aa_put_label(label);
 		AA_DEBUG("no profile name");
 		return -EINVAL;
 	}
@@ -1348,8 +1354,6 @@ int aa_change_profile(const char *fqname, int flags)
 			op = OP_CHANGE_PROFILE;
 	}
 
-	label = aa_get_current_label();
-
 	if (*fqname == '&') {
 		stack = true;
 		/* don't have label_parse() do stacking */
@@ -1426,7 +1430,7 @@ check:
 		 * reduce restrictions.
 		 */
 		if (task_no_new_privs(current) && !unconfined(label) &&
-		    !aa_label_is_subset(new, ctx->nnp)) {
+		    !aa_label_is_unconfined_subset(new, ctx->nnp)) {
 			/* not an apparmor denial per se, so don't log it */
 			AA_DEBUG("no_new_privs - change_hat denied");
 			error = -EPERM;
diff --git a/security/apparmor/include/label.h b/security/apparmor/include/label.h
index 47942c4ba7ca..255764ab06e2 100644
--- a/security/apparmor/include/label.h
+++ b/security/apparmor/include/label.h
@@ -281,6 +281,7 @@ bool aa_label_init(struct aa_label *label, int size, gfp_t gfp);
 struct aa_label *aa_label_alloc(int size, struct aa_proxy *proxy, gfp_t gfp);
 
 bool aa_label_is_subset(struct aa_label *set, struct aa_label *sub);
+bool aa_label_is_unconfined_subset(struct aa_label *set, struct aa_label *sub);
 struct aa_profile *__aa_label_next_not_in_set(struct label_it *I,
 					     struct aa_label *set,
 					     struct aa_label *sub);
diff --git a/security/apparmor/label.c b/security/apparmor/label.c
index bd9b8f6f4c04..01a1ddacd21b 100644
--- a/security/apparmor/label.c
+++ b/security/apparmor/label.c
@@ -550,6 +550,39 @@ bool aa_label_is_subset(struct aa_label *set, struct aa_label *sub)
 	return __aa_label_next_not_in_set(&i, set, sub) == NULL;
 }
 
+/**
+ * aa_label_is_unconfined_subset - test if @sub is a subset of @set
+ * @set: label to test against
+ * @sub: label to test if is subset of @set
+ *
+ * This checks for subset but taking into account unconfined. IF
+ * @sub contains an unconfined profile that does not have a matching
+ * unconfined in @set then this will not cause the test to fail.
+ * Conversely we don't care about an unconfined in @set that is not in
+ * @sub
+ *
+ * Returns: true if @sub is special_subset of @set
+ *     else false
+ */
+bool aa_label_is_unconfined_subset(struct aa_label *set, struct aa_label *sub)
+{
+	struct label_it i = { };
+	struct aa_profile *p;
+
+	AA_BUG(!set);
+	AA_BUG(!sub);
+
+	if (sub == set)
+		return true;
+
+	do {
+		p = __aa_label_next_not_in_set(&i, set, sub);
+		if (p && !profile_unconfined(p))
+			break;
+	} while (p);
+
+	return p == NULL;
+}
 
 
 /**
@@ -1531,13 +1564,13 @@ static const char *label_modename(struct aa_ns *ns, struct aa_label *label,
 
 	label_for_each(i, label, profile) {
 		if (aa_ns_visible(ns, profile->ns, flags & FLAG_VIEW_SUBNS)) {
-			if (profile->mode == APPARMOR_UNCONFINED)
+			count++;
+			if (profile == profile->ns->unconfined)
 				/* special case unconfined so stacks with
 				 * unconfined don't report as mixed. ie.
 				 * profile_foo//&:ns1:unconfined (mixed)
 				 */
 				continue;
-			count++;
 			if (mode == -1)
 				mode = profile->mode;
 			else if (mode != profile->mode)
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index ec3a928af829..e31965dc6dd1 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -791,7 +791,12 @@ static void apparmor_sk_clone_security(const struct sock *sk,
 	struct aa_sk_ctx *ctx = SK_CTX(sk);
 	struct aa_sk_ctx *new = SK_CTX(newsk);
 
+	if (new->label)
+		aa_put_label(new->label);
 	new->label = aa_get_label(ctx->label);
+
+	if (new->peer)
+		aa_put_label(new->peer);
 	new->peer = aa_get_label(ctx->peer);
 }
 
diff --git a/security/apparmor/match.c b/security/apparmor/match.c
index 6ccd3734a841..43669403f755 100644
--- a/security/apparmor/match.c
+++ b/security/apparmor/match.c
@@ -97,6 +97,9 @@ static struct table_header *unpack_table(char *blob, size_t bsize)
 	      th.td_flags == YYTD_DATA8))
 		goto out;
 
+	/* if we have a table it must have some entries */
+	if (th.td_lolen == 0)
+		goto out;
 	tsize = table_size(th.td_lolen, th.td_flags);
 	if (bsize < tsize)
 		goto out;
@@ -198,6 +201,8 @@ static int verify_dfa(struct aa_dfa *dfa)
 
 	state_count = dfa->tables[YYTD_ID_BASE]->td_lolen;
 	trans_count = dfa->tables[YYTD_ID_NXT]->td_lolen;
+	if (state_count == 0)
+		goto out;
 	for (i = 0; i < state_count; i++) {
 		if (!(BASE_TABLE(dfa)[i] & MATCH_FLAG_DIFF_ENCODE) &&
 		    (DEFAULT_TABLE(dfa)[i] >= state_count))
diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c
index ade333074c8e..06355717ee84 100644
--- a/security/apparmor/policy.c
+++ b/security/apparmor/policy.c
@@ -1124,8 +1124,8 @@ ssize_t aa_remove_profiles(struct aa_ns *policy_ns, struct aa_label *subj,
 	if (!name) {
 		/* remove namespace - can only happen if fqname[0] == ':' */
 		mutex_lock_nested(&ns->parent->lock, ns->level);
-		__aa_remove_ns(ns);
 		__aa_bump_ns_revision(ns);
+		__aa_remove_ns(ns);
 		mutex_unlock(&ns->parent->lock);
 	} else {
 		/* remove profile */
@@ -1137,9 +1137,9 @@ ssize_t aa_remove_profiles(struct aa_ns *policy_ns, struct aa_label *subj,
 			goto fail_ns_lock;
 		}
 		name = profile->base.hname;
+		__aa_bump_ns_revision(ns);
 		__remove_profile(profile);
 		__aa_labelset_update_subtree(ns);
-		__aa_bump_ns_revision(ns);
 		mutex_unlock(&ns->lock);
 	}
 
diff --git a/security/commoncap.c b/security/commoncap.c
index c0b9664ee49e..06a7f6abe321 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -812,6 +812,7 @@ int cap_bprm_set_creds(struct linux_binprm *bprm)
 	int ret;
 	kuid_t root_uid;
 
+	new->cap_ambient = old->cap_ambient;
 	if (WARN_ON(!cap_ambient_invariant_ok(old)))
 		return -EPERM;
 
diff --git a/security/integrity/evm/evm_crypto.c b/security/integrity/evm/evm_crypto.c
index d485f6fc908e..ee6bd945f3d6 100644
--- a/security/integrity/evm/evm_crypto.c
+++ b/security/integrity/evm/evm_crypto.c
@@ -75,7 +75,7 @@ static struct shash_desc *init_desc(char type, uint8_t hash_algo)
 {
 	long rc;
 	const char *algo;
-	struct crypto_shash **tfm;
+	struct crypto_shash **tfm, *tmp_tfm;
 	struct shash_desc *desc;
 
 	if (type == EVM_XATTR_HMAC) {
@@ -93,31 +93,31 @@ static struct shash_desc *init_desc(char type, uint8_t hash_algo)
 		algo = hash_algo_name[hash_algo];
 	}
 
-	if (*tfm == NULL) {
-		mutex_lock(&mutex);
-		if (*tfm)
-			goto out;
-		*tfm = crypto_alloc_shash(algo, 0, CRYPTO_NOLOAD);
-		if (IS_ERR(*tfm)) {
-			rc = PTR_ERR(*tfm);
-			pr_err("Can not allocate %s (reason: %ld)\n", algo, rc);
-			*tfm = NULL;
+	if (*tfm)
+		goto alloc;
+	mutex_lock(&mutex);
+	if (*tfm)
+		goto unlock;
+
+	tmp_tfm = crypto_alloc_shash(algo, 0, CRYPTO_NOLOAD);
+	if (IS_ERR(tmp_tfm)) {
+		pr_err("Can not allocate %s (reason: %ld)\n", algo,
+		       PTR_ERR(tmp_tfm));
+		mutex_unlock(&mutex);
+		return ERR_CAST(tmp_tfm);
+	}
+	if (type == EVM_XATTR_HMAC) {
+		rc = crypto_shash_setkey(tmp_tfm, evmkey, evmkey_len);
+		if (rc) {
+			crypto_free_shash(tmp_tfm);
 			mutex_unlock(&mutex);
 			return ERR_PTR(rc);
 		}
-		if (type == EVM_XATTR_HMAC) {
-			rc = crypto_shash_setkey(*tfm, evmkey, evmkey_len);
-			if (rc) {
-				crypto_free_shash(*tfm);
-				*tfm = NULL;
-				mutex_unlock(&mutex);
-				return ERR_PTR(rc);
-			}
-		}
-out:
-		mutex_unlock(&mutex);
 	}
-
+	*tfm = tmp_tfm;
+unlock:
+	mutex_unlock(&mutex);
+alloc:
 	desc = kmalloc(sizeof(*desc) + crypto_shash_descsize(*tfm),
 			GFP_KERNEL);
 	if (!desc)
@@ -209,7 +209,7 @@ static int evm_calc_hmac_or_hash(struct dentry *dentry,
 	data->hdr.length = crypto_shash_digestsize(desc->tfm);
 
 	error = -ENODATA;
-	list_for_each_entry_rcu(xattr, &evm_config_xattrnames, list) {
+	list_for_each_entry_lockless(xattr, &evm_config_xattrnames, list) {
 		bool is_ima = false;
 
 		if (strcmp(xattr->name, XATTR_NAME_IMA) == 0)
@@ -243,7 +243,7 @@ static int evm_calc_hmac_or_hash(struct dentry *dentry,
 
 	/* Portable EVM signatures must include an IMA hash */
 	if (type == EVM_XATTR_PORTABLE_DIGSIG && !ima_present)
-		return -EPERM;
+		error = -EPERM;
 out:
 	kfree(xattr_value);
 	kfree(desc);
diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c
index 5bbd8b4dc29a..f7f4ceb62580 100644
--- a/security/integrity/evm/evm_main.c
+++ b/security/integrity/evm/evm_main.c
@@ -99,7 +99,7 @@ static int evm_find_protected_xattrs(struct dentry *dentry)
 	if (!(inode->i_opflags & IOP_XATTR))
 		return -EOPNOTSUPP;
 
-	list_for_each_entry_rcu(xattr, &evm_config_xattrnames, list) {
+	list_for_each_entry_lockless(xattr, &evm_config_xattrnames, list) {
 		error = __vfs_getxattr(dentry, inode, xattr->name, NULL, 0);
 		if (error < 0) {
 			if (error == -ENODATA)
@@ -230,7 +230,7 @@ static int evm_protected_xattr(const char *req_xattr_name)
 	struct xattr_list *xattr;
 
 	namelen = strlen(req_xattr_name);
-	list_for_each_entry_rcu(xattr, &evm_config_xattrnames, list) {
+	list_for_each_entry_lockless(xattr, &evm_config_xattrnames, list) {
 		if ((strlen(xattr->name) == namelen)
 		    && (strncmp(req_xattr_name, xattr->name, namelen) == 0)) {
 			found = 1;
diff --git a/security/integrity/evm/evm_secfs.c b/security/integrity/evm/evm_secfs.c
index c11c1f7b3ddd..0f37ef27268d 100644
--- a/security/integrity/evm/evm_secfs.c
+++ b/security/integrity/evm/evm_secfs.c
@@ -234,7 +234,14 @@ static ssize_t evm_write_xattrs(struct file *file, const char __user *buf,
 		goto out;
 	}
 
-	/* Guard against races in evm_read_xattrs */
+	/*
+	 * xattr_list_mutex guards against races in evm_read_xattrs().
+	 * Entries are only added to the evm_config_xattrnames list
+	 * and never deleted. Therefore, the list is traversed
+	 * using list_for_each_entry_lockless() without holding
+	 * the mutex in evm_calc_hmac_or_hash(), evm_find_protected_xattrs()
+	 * and evm_protected_xattr().
+	 */
 	mutex_lock(&xattr_list_mutex);
 	list_for_each_entry(tmp, &evm_config_xattrnames, list) {
 		if (strcmp(xattr->name, tmp->name) == 0) {
diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig
index 2692c7358c2c..3ae199689d17 100644
--- a/security/integrity/ima/Kconfig
+++ b/security/integrity/ima/Kconfig
@@ -226,7 +226,7 @@ config IMA_APPRAISE_REQUIRE_POLICY_SIGS
 
 config IMA_APPRAISE_BOOTPARAM
 	bool "ima_appraise boot parameter"
-	depends on IMA_APPRAISE && !IMA_ARCH_POLICY
+	depends on IMA_APPRAISE
 	default y
 	help
 	  This option enables the different "ima_appraise=" modes
diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index ca10917b5f89..3a056bc08f44 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -36,7 +36,7 @@ enum tpm_pcrs { TPM_PCR0 = 0, TPM_PCR8 = 8 };
 #define IMA_DIGEST_SIZE		SHA1_DIGEST_SIZE
 #define IMA_EVENT_NAME_LEN_MAX	255
 
-#define IMA_HASH_BITS 9
+#define IMA_HASH_BITS 10
 #define IMA_MEASURE_HTABLE_SIZE (1 << IMA_HASH_BITS)
 
 #define IMA_TEMPLATE_FIELD_ID_MAX_LEN	16
@@ -52,6 +52,7 @@ extern int ima_policy_flag;
 extern int ima_hash_algo;
 extern int ima_appraise;
 extern struct tpm_chip *ima_tpm_chip;
+extern const char boot_aggregate_name[];
 
 /* IMA event related data */
 struct ima_event_data {
@@ -135,7 +136,7 @@ int ima_calc_buffer_hash(const void *buf, loff_t len,
 int ima_calc_field_array_hash(struct ima_field_data *field_data,
 			      struct ima_template_desc *desc, int num_fields,
 			      struct ima_digest_data *hash);
-int __init ima_calc_boot_aggregate(struct ima_digest_data *hash);
+int ima_calc_boot_aggregate(struct ima_digest_data *hash);
 void ima_add_violation(struct file *file, const unsigned char *filename,
 		       struct integrity_iint_cache *iint,
 		       const char *op, const char *cause);
@@ -163,9 +164,10 @@ struct ima_h_table {
 };
 extern struct ima_h_table ima_htable;
 
-static inline unsigned long ima_hash_key(u8 *digest)
+static inline unsigned int ima_hash_key(u8 *digest)
 {
-	return hash_long(*digest, IMA_HASH_BITS);
+	/* there is no point in taking a hash of part of a digest */
+	return (digest[0] | digest[1] << 8) % IMA_MEASURE_HTABLE_SIZE;
 }
 
 #define __ima_hooks(hook)		\
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index f0cd67cab6aa..9e2a3993a922 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -18,6 +18,12 @@
 static int __init default_appraise_setup(char *str)
 {
 #ifdef CONFIG_IMA_APPRAISE_BOOTPARAM
+	if (arch_ima_get_secureboot()) {
+		pr_info("Secure boot enabled: ignoring ima_appraise=%s boot parameter option",
+			str);
+		return 1;
+	}
+
 	if (strncmp(str, "off", 3) == 0)
 		ima_appraise = 0;
 	else if (strncmp(str, "log", 3) == 0)
diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c
index 73044fc6a952..d5ad7b2539c7 100644
--- a/security/integrity/ima/ima_crypto.c
+++ b/security/integrity/ima/ima_crypto.c
@@ -411,7 +411,7 @@ int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash)
 	loff_t i_size;
 	int rc;
 	struct file *f = file;
-	bool new_file_instance = false, modified_flags = false;
+	bool new_file_instance = false, modified_mode = false;
 
 	/*
 	 * For consistency, fail file's opened with the O_DIRECT flag on
@@ -431,13 +431,13 @@ int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash)
 		f = dentry_open(&file->f_path, flags, file->f_cred);
 		if (IS_ERR(f)) {
 			/*
-			 * Cannot open the file again, lets modify f_flags
+			 * Cannot open the file again, lets modify f_mode
 			 * of original and continue
 			 */
 			pr_info_ratelimited("Unable to reopen file for reading.\n");
 			f = file;
-			f->f_flags |= FMODE_READ;
-			modified_flags = true;
+			f->f_mode |= FMODE_READ;
+			modified_mode = true;
 		} else {
 			new_file_instance = true;
 		}
@@ -455,8 +455,8 @@ int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash)
 out:
 	if (new_file_instance)
 		fput(f);
-	else if (modified_flags)
-		f->f_flags &= ~FMODE_READ;
+	else if (modified_mode)
+		f->f_mode &= ~FMODE_READ;
 	return rc;
 }
 
@@ -645,7 +645,7 @@ int ima_calc_buffer_hash(const void *buf, loff_t len,
 	return calc_buffer_shash(buf, len, hash);
 }
 
-static void __init ima_pcrread(u32 idx, struct tpm_digest *d)
+static void ima_pcrread(u32 idx, struct tpm_digest *d)
 {
 	if (!ima_tpm_chip)
 		return;
@@ -655,18 +655,29 @@ static void __init ima_pcrread(u32 idx, struct tpm_digest *d)
 }
 
 /*
- * Calculate the boot aggregate hash
+ * The boot_aggregate is a cumulative hash over TPM registers 0 - 7.  With
+ * TPM 1.2 the boot_aggregate was based on reading the SHA1 PCRs, but with
+ * TPM 2.0 hash agility, TPM chips could support multiple TPM PCR banks,
+ * allowing firmware to configure and enable different banks.
+ *
+ * Knowing which TPM bank is read to calculate the boot_aggregate digest
+ * needs to be conveyed to a verifier.  For this reason, use the same
+ * hash algorithm for reading the TPM PCRs as for calculating the boot
+ * aggregate digest as stored in the measurement list.
  */
-static int __init ima_calc_boot_aggregate_tfm(char *digest,
-					      struct crypto_shash *tfm)
+static int ima_calc_boot_aggregate_tfm(char *digest, u16 alg_id,
+				       struct crypto_shash *tfm)
 {
-	struct tpm_digest d = { .alg_id = TPM_ALG_SHA1, .digest = {0} };
+	struct tpm_digest d = { .alg_id = alg_id, .digest = {0} };
 	int rc;
 	u32 i;
 	SHASH_DESC_ON_STACK(shash, tfm);
 
 	shash->tfm = tfm;
 
+	pr_devel("calculating the boot-aggregate based on TPM bank: %04x\n",
+		 d.alg_id);
+
 	rc = crypto_shash_init(shash);
 	if (rc != 0)
 		return rc;
@@ -675,24 +686,48 @@ static int __init ima_calc_boot_aggregate_tfm(char *digest,
 	for (i = TPM_PCR0; i < TPM_PCR8; i++) {
 		ima_pcrread(i, &d);
 		/* now accumulate with current aggregate */
-		rc = crypto_shash_update(shash, d.digest, TPM_DIGEST_SIZE);
+		rc = crypto_shash_update(shash, d.digest,
+					 crypto_shash_digestsize(tfm));
 	}
 	if (!rc)
 		crypto_shash_final(shash, digest);
 	return rc;
 }
 
-int __init ima_calc_boot_aggregate(struct ima_digest_data *hash)
+int ima_calc_boot_aggregate(struct ima_digest_data *hash)
 {
 	struct crypto_shash *tfm;
-	int rc;
+	u16 crypto_id, alg_id;
+	int rc, i, bank_idx = -1;
+
+	for (i = 0; i < ima_tpm_chip->nr_allocated_banks; i++) {
+		crypto_id = ima_tpm_chip->allocated_banks[i].crypto_id;
+		if (crypto_id == hash->algo) {
+			bank_idx = i;
+			break;
+		}
+
+		if (crypto_id == HASH_ALGO_SHA256)
+			bank_idx = i;
+
+		if (bank_idx == -1 && crypto_id == HASH_ALGO_SHA1)
+			bank_idx = i;
+	}
+
+	if (bank_idx == -1) {
+		pr_err("No suitable TPM algorithm for boot aggregate\n");
+		return 0;
+	}
+
+	hash->algo = ima_tpm_chip->allocated_banks[bank_idx].crypto_id;
 
 	tfm = ima_alloc_tfm(hash->algo);
 	if (IS_ERR(tfm))
 		return PTR_ERR(tfm);
 
 	hash->length = crypto_shash_digestsize(tfm);
-	rc = ima_calc_boot_aggregate_tfm(hash->digest, tfm);
+	alg_id = ima_tpm_chip->allocated_banks[bank_idx].alg_id;
+	rc = ima_calc_boot_aggregate_tfm(hash->digest, alg_id, tfm);
 
 	ima_free_tfm(tfm);
 
diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
index 2000e8df0301..68571c40d61f 100644
--- a/security/integrity/ima/ima_fs.c
+++ b/security/integrity/ima/ima_fs.c
@@ -340,8 +340,7 @@ static ssize_t ima_write_policy(struct file *file, const char __user *buf,
 		integrity_audit_msg(AUDIT_INTEGRITY_STATUS, NULL, NULL,
 				    "policy_update", "signed policy required",
 				    1, 0);
-		if (ima_appraise & IMA_APPRAISE_ENFORCE)
-			result = -EACCES;
+		result = -EACCES;
 	} else {
 		result = ima_parse_add_rule(data);
 	}
diff --git a/security/integrity/ima/ima_init.c b/security/integrity/ima/ima_init.c
index 1e47c1026471..b2e52457e699 100644
--- a/security/integrity/ima/ima_init.c
+++ b/security/integrity/ima/ima_init.c
@@ -21,13 +21,13 @@
 #include "ima.h"
 
 /* name for boot aggregate entry */
-static const char boot_aggregate_name[] = "boot_aggregate";
+const char boot_aggregate_name[] = "boot_aggregate";
 struct tpm_chip *ima_tpm_chip;
 
 /* Add the boot aggregate to the IMA measurement list and extend
  * the PCR register.
  *
- * Calculate the boot aggregate, a SHA1 over tpm registers 0-7,
+ * Calculate the boot aggregate, a hash over tpm registers 0-7,
  * assuming a TPM chip exists, and zeroes if the TPM chip does not
  * exist.  Add the boot aggregate measurement to the measurement
  * list and extend the PCR register.
@@ -51,15 +51,27 @@ static int __init ima_add_boot_aggregate(void)
 	int violation = 0;
 	struct {
 		struct ima_digest_data hdr;
-		char digest[TPM_DIGEST_SIZE];
+		char digest[TPM_MAX_DIGEST_SIZE];
 	} hash;
 
 	memset(iint, 0, sizeof(*iint));
 	memset(&hash, 0, sizeof(hash));
 	iint->ima_hash = &hash.hdr;
-	iint->ima_hash->algo = HASH_ALGO_SHA1;
-	iint->ima_hash->length = SHA1_DIGEST_SIZE;
-
+	iint->ima_hash->algo = ima_hash_algo;
+	iint->ima_hash->length = hash_digest_size[ima_hash_algo];
+
+	/*
+	 * With TPM 2.0 hash agility, TPM chips could support multiple TPM
+	 * PCR banks, allowing firmware to configure and enable different
+	 * banks.  The SHA1 bank is not necessarily enabled.
+	 *
+	 * Use the same hash algorithm for reading the TPM PCRs as for
+	 * calculating the boot aggregate digest.  Preference is given to
+	 * the configured IMA default hash algorithm.  Otherwise, use the
+	 * TCG required banks - SHA256 for TPM 2.0, SHA1 for TPM 1.2.
+	 * Ultimately select SHA1 also for TPM 2.0 if the SHA256 PCR bank
+	 * is not found.
+	 */
 	if (ima_tpm_chip) {
 		result = ima_calc_boot_aggregate(&hash.hdr);
 		if (result < 0) {
diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c
index 7b53f2ca58e2..781d8a408513 100644
--- a/security/integrity/ima/ima_policy.c
+++ b/security/integrity/ima/ima_policy.c
@@ -200,7 +200,7 @@ struct ima_rule_entry *arch_policy_entry __ro_after_init;
 static LIST_HEAD(ima_default_rules);
 static LIST_HEAD(ima_policy_rules);
 static LIST_HEAD(ima_temp_rules);
-static struct list_head *ima_rules;
+static struct list_head *ima_rules = &ima_default_rules;
 
 static int ima_policy __initdata;
 
@@ -495,9 +495,12 @@ static void add_rules(struct ima_rule_entry *entries, int count,
 			list_add_tail(&entry->list, &ima_policy_rules);
 		}
 		if (entries[i].action == APPRAISE) {
-			temp_ima_appraise |= ima_appraise_flag(entries[i].func);
-			if (entries[i].func == POLICY_CHECK)
-				temp_ima_appraise |= IMA_APPRAISE_POLICY;
+			if (entries != build_appraise_rules)
+				temp_ima_appraise |=
+					ima_appraise_flag(entries[i].func);
+			else
+				build_ima_appraise |=
+					ima_appraise_flag(entries[i].func);
 		}
 	}
 }
@@ -616,7 +619,6 @@ void __init ima_init_policy(void)
 			  ARRAY_SIZE(default_appraise_rules),
 			  IMA_DEFAULT_POLICY);
 
-	ima_rules = &ima_default_rules;
 	ima_update_policy_flag();
 }
 
diff --git a/security/integrity/ima/ima_template_lib.c b/security/integrity/ima/ima_template_lib.c
index 9fe0ef7f91e2..d3e5a49b2df4 100644
--- a/security/integrity/ima/ima_template_lib.c
+++ b/security/integrity/ima/ima_template_lib.c
@@ -281,6 +281,24 @@ int ima_eventdigest_init(struct ima_event_data *event_data,
 		goto out;
 	}
 
+	if ((const char *)event_data->filename == boot_aggregate_name) {
+		if (ima_tpm_chip) {
+			hash.hdr.algo = HASH_ALGO_SHA1;
+			result = ima_calc_boot_aggregate(&hash.hdr);
+
+			/* algo can change depending on available PCR banks */
+			if (!result && hash.hdr.algo != HASH_ALGO_SHA1)
+				result = -EINVAL;
+
+			if (result < 0)
+				memset(&hash, 0, sizeof(hash));
+		}
+
+		cur_digest = hash.hdr.digest;
+		cur_digestsize = hash_digest_size[HASH_ALGO_SHA1];
+		goto out;
+	}
+
 	if (!event_data->file)	/* missing info to re-calculate the digest */
 		return -EINVAL;
 
diff --git a/security/integrity/platform_certs/load_uefi.c b/security/integrity/platform_certs/load_uefi.c
index 81b19c52832b..020fc7a11ef0 100644
--- a/security/integrity/platform_certs/load_uefi.c
+++ b/security/integrity/platform_certs/load_uefi.c
@@ -39,16 +39,18 @@ static __init bool uefi_check_ignore_db(void)
  * Get a certificate list blob from the named EFI variable.
  */
 static __init void *get_cert_list(efi_char16_t *name, efi_guid_t *guid,
-				  unsigned long *size)
+				  unsigned long *size, efi_status_t *status)
 {
-	efi_status_t status;
 	unsigned long lsize = 4;
 	unsigned long tmpdb[4];
 	void *db;
 
-	status = efi.get_variable(name, guid, NULL, &lsize, &tmpdb);
-	if (status != EFI_BUFFER_TOO_SMALL) {
-		pr_err("Couldn't get size: 0x%lx\n", status);
+	*status = efi.get_variable(name, guid, NULL, &lsize, &tmpdb);
+	if (*status == EFI_NOT_FOUND)
+		return NULL;
+
+	if (*status != EFI_BUFFER_TOO_SMALL) {
+		pr_err("Couldn't get size: 0x%lx\n", *status);
 		return NULL;
 	}
 
@@ -56,10 +58,10 @@ static __init void *get_cert_list(efi_char16_t *name, efi_guid_t *guid,
 	if (!db)
 		return NULL;
 
-	status = efi.get_variable(name, guid, NULL, &lsize, db);
-	if (status != EFI_SUCCESS) {
+	*status = efi.get_variable(name, guid, NULL, &lsize, db);
+	if (*status != EFI_SUCCESS) {
 		kfree(db);
-		pr_err("Error reading db var: 0x%lx\n", status);
+		pr_err("Error reading db var: 0x%lx\n", *status);
 		return NULL;
 	}
 
@@ -144,6 +146,7 @@ static int __init load_uefi_certs(void)
 	efi_guid_t mok_var = EFI_SHIM_LOCK_GUID;
 	void *db = NULL, *dbx = NULL, *mok = NULL;
 	unsigned long dbsize = 0, dbxsize = 0, moksize = 0;
+	efi_status_t status;
 	int rc = 0;
 
 	if (!efi.get_variable)
@@ -153,9 +156,12 @@ static int __init load_uefi_certs(void)
 	 * an error if we can't get them.
 	 */
 	if (!uefi_check_ignore_db()) {
-		db = get_cert_list(L"db", &secure_var, &dbsize);
+		db = get_cert_list(L"db", &secure_var, &dbsize, &status);
 		if (!db) {
-			pr_err("MODSIGN: Couldn't get UEFI db list\n");
+			if (status == EFI_NOT_FOUND)
+				pr_debug("MODSIGN: db variable wasn't found\n");
+			else
+				pr_err("MODSIGN: Couldn't get UEFI db list\n");
 		} else {
 			rc = parse_efi_signature_list("UEFI:db",
 					db, dbsize, get_handler_for_db);
@@ -166,9 +172,12 @@ static int __init load_uefi_certs(void)
 		}
 	}
 
-	mok = get_cert_list(L"MokListRT", &mok_var, &moksize);
+	mok = get_cert_list(L"MokListRT", &mok_var, &moksize, &status);
 	if (!mok) {
-		pr_info("Couldn't get UEFI MokListRT\n");
+		if (status == EFI_NOT_FOUND)
+			pr_debug("MokListRT variable wasn't found\n");
+		else
+			pr_info("Couldn't get UEFI MokListRT\n");
 	} else {
 		rc = parse_efi_signature_list("UEFI:MokListRT",
 					      mok, moksize, get_handler_for_db);
@@ -177,9 +186,12 @@ static int __init load_uefi_certs(void)
 		kfree(mok);
 	}
 
-	dbx = get_cert_list(L"dbx", &secure_var, &dbxsize);
+	dbx = get_cert_list(L"dbx", &secure_var, &dbxsize, &status);
 	if (!dbx) {
-		pr_info("Couldn't get UEFI dbx list\n");
+		if (status == EFI_NOT_FOUND)
+			pr_debug("dbx variable wasn't found\n");
+		else
+			pr_info("Couldn't get UEFI dbx list\n");
 	} else {
 		rc = parse_efi_signature_list("UEFI:dbx",
 					      dbx, dbxsize,
diff --git a/security/keys/big_key.c b/security/keys/big_key.c
index 001abe530a0d..82008f900930 100644
--- a/security/keys/big_key.c
+++ b/security/keys/big_key.c
@@ -352,7 +352,7 @@ void big_key_describe(const struct key *key, struct seq_file *m)
  * read the key data
  * - the key's semaphore is read-locked
  */
-long big_key_read(const struct key *key, char __user *buffer, size_t buflen)
+long big_key_read(const struct key *key, char *buffer, size_t buflen)
 {
 	size_t datalen = (size_t)key->payload.data[big_key_len];
 	long ret;
@@ -391,9 +391,8 @@ long big_key_read(const struct key *key, char __user *buffer, size_t buflen)
 
 		ret = datalen;
 
-		/* copy decrypted data to user */
-		if (copy_to_user(buffer, buf->virt, datalen) != 0)
-			ret = -EFAULT;
+		/* copy out decrypted data */
+		memcpy(buffer, buf->virt, datalen);
 
 err_fput:
 		fput(file);
@@ -401,9 +400,7 @@ error:
 		big_key_free_buffer(buf);
 	} else {
 		ret = datalen;
-		if (copy_to_user(buffer, key->payload.data[big_key_data],
-				 datalen) != 0)
-			ret = -EFAULT;
+		memcpy(buffer, key->payload.data[big_key_data], datalen);
 	}
 
 	return ret;
diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
index 60720f58cbe0..f6797ba44bf7 100644
--- a/security/keys/encrypted-keys/encrypted.c
+++ b/security/keys/encrypted-keys/encrypted.c
@@ -902,14 +902,14 @@ out:
 }
 
 /*
- * encrypted_read - format and copy the encrypted data to userspace
+ * encrypted_read - format and copy out the encrypted data
  *
  * The resulting datablob format is:
  * <master-key name> <decrypted data length> <encrypted iv> <encrypted data>
  *
  * On success, return to userspace the encrypted key datablob size.
  */
-static long encrypted_read(const struct key *key, char __user *buffer,
+static long encrypted_read(const struct key *key, char *buffer,
 			   size_t buflen)
 {
 	struct encrypted_key_payload *epayload;
@@ -957,8 +957,7 @@ static long encrypted_read(const struct key *key, char __user *buffer,
 	key_put(mkey);
 	memzero_explicit(derived_key, sizeof(derived_key));
 
-	if (copy_to_user(buffer, ascii_buf, asciiblob_len) != 0)
-		ret = -EFAULT;
+	memcpy(buffer, ascii_buf, asciiblob_len);
 	kzfree(ascii_buf);
 
 	return asciiblob_len;
diff --git a/security/keys/internal.h b/security/keys/internal.h
index d59bc25a9249..f300df1ece02 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -16,6 +16,8 @@
 #include <linux/keyctl.h>
 #include <linux/refcount.h>
 #include <linux/compat.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
 
 struct iovec;
 
@@ -337,5 +339,4 @@ static inline void key_check(const struct key *key)
 #define key_check(key) do {} while(0)
 
 #endif
-
 #endif /* _INTERNAL_H */
diff --git a/security/keys/key.c b/security/keys/key.c
index 9a6108aefae9..32df6a06abc3 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -379,7 +379,7 @@ int key_payload_reserve(struct key *key, size_t datalen)
 		spin_lock(&key->user->lock);
 
 		if (delta > 0 &&
-		    (key->user->qnbytes + delta >= maxbytes ||
+		    (key->user->qnbytes + delta > maxbytes ||
 		     key->user->qnbytes + delta < key->user->qnbytes)) {
 			ret = -EDQUOT;
 		}
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index 5aa605ef8d9d..304e51e1ef24 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -128,10 +128,7 @@ SYSCALL_DEFINE5(add_key, const char __user *, _type,
 
 	key_ref_put(keyring_ref);
  error3:
-	if (payload) {
-		memzero_explicit(payload, plen);
-		kvfree(payload);
-	}
+	kvfree_sensitive(payload, plen);
  error2:
 	kfree(description);
  error:
@@ -325,7 +322,7 @@ long keyctl_update_key(key_serial_t id,
 	payload = NULL;
 	if (plen) {
 		ret = -ENOMEM;
-		payload = kmalloc(plen, GFP_KERNEL);
+		payload = kvmalloc(plen, GFP_KERNEL);
 		if (!payload)
 			goto error;
 
@@ -346,7 +343,7 @@ long keyctl_update_key(key_serial_t id,
 
 	key_ref_put(key_ref);
 error2:
-	kzfree(payload);
+	kvfree_sensitive(payload, plen);
 error:
 	return ret;
 }
@@ -738,6 +735,21 @@ error:
 }
 
 /*
+ * Call the read method
+ */
+static long __keyctl_read_key(struct key *key, char *buffer, size_t buflen)
+{
+	long ret;
+
+	down_read(&key->sem);
+	ret = key_validate(key);
+	if (ret == 0)
+		ret = key->type->read(key, buffer, buflen);
+	up_read(&key->sem);
+	return ret;
+}
+
+/*
  * Read a key's payload.
  *
  * The key must either grant the caller Read permission, or it must grant the
@@ -752,26 +764,28 @@ long keyctl_read_key(key_serial_t keyid, char __user *buffer, size_t buflen)
 	struct key *key;
 	key_ref_t key_ref;
 	long ret;
+	char *key_data = NULL;
+	size_t key_data_len;
 
 	/* find the key first */
 	key_ref = lookup_user_key(keyid, 0, 0);
 	if (IS_ERR(key_ref)) {
 		ret = -ENOKEY;
-		goto error;
+		goto out;
 	}
 
 	key = key_ref_to_ptr(key_ref);
 
 	ret = key_read_state(key);
 	if (ret < 0)
-		goto error2; /* Negatively instantiated */
+		goto key_put_out; /* Negatively instantiated */
 
 	/* see if we can read it directly */
 	ret = key_permission(key_ref, KEY_NEED_READ);
 	if (ret == 0)
 		goto can_read_key;
 	if (ret != -EACCES)
-		goto error2;
+		goto key_put_out;
 
 	/* we can't; see if it's searchable from this process's keyrings
 	 * - we automatically take account of the fact that it may be
@@ -779,26 +793,78 @@ long keyctl_read_key(key_serial_t keyid, char __user *buffer, size_t buflen)
 	 */
 	if (!is_key_possessed(key_ref)) {
 		ret = -EACCES;
-		goto error2;
+		goto key_put_out;
 	}
 
 	/* the key is probably readable - now try to read it */
 can_read_key:
-	ret = -EOPNOTSUPP;
-	if (key->type->read) {
-		/* Read the data with the semaphore held (since we might sleep)
-		 * to protect against the key being updated or revoked.
+	if (!key->type->read) {
+		ret = -EOPNOTSUPP;
+		goto key_put_out;
+	}
+
+	if (!buffer || !buflen) {
+		/* Get the key length from the read method */
+		ret = __keyctl_read_key(key, NULL, 0);
+		goto key_put_out;
+	}
+
+	/*
+	 * Read the data with the semaphore held (since we might sleep)
+	 * to protect against the key being updated or revoked.
+	 *
+	 * Allocating a temporary buffer to hold the keys before
+	 * transferring them to user buffer to avoid potential
+	 * deadlock involving page fault and mmap_sem.
+	 *
+	 * key_data_len = (buflen <= PAGE_SIZE)
+	 *		? buflen : actual length of key data
+	 *
+	 * This prevents allocating arbitrary large buffer which can
+	 * be much larger than the actual key length. In the latter case,
+	 * at least 2 passes of this loop is required.
+	 */
+	key_data_len = (buflen <= PAGE_SIZE) ? buflen : 0;
+	for (;;) {
+		if (key_data_len) {
+			key_data = kvmalloc(key_data_len, GFP_KERNEL);
+			if (!key_data) {
+				ret = -ENOMEM;
+				goto key_put_out;
+			}
+		}
+
+		ret = __keyctl_read_key(key, key_data, key_data_len);
+
+		/*
+		 * Read methods will just return the required length without
+		 * any copying if the provided length isn't large enough.
 		 */
-		down_read(&key->sem);
-		ret = key_validate(key);
-		if (ret == 0)
-			ret = key->type->read(key, buffer, buflen);
-		up_read(&key->sem);
+		if (ret <= 0 || ret > buflen)
+			break;
+
+		/*
+		 * The key may change (unlikely) in between 2 consecutive
+		 * __keyctl_read_key() calls. In this case, we reallocate
+		 * a larger buffer and redo the key read when
+		 * key_data_len < ret <= buflen.
+		 */
+		if (ret > key_data_len) {
+			if (unlikely(key_data))
+				kvfree_sensitive(key_data, key_data_len);
+			key_data_len = ret;
+			continue;	/* Allocate buffer */
+		}
+
+		if (copy_to_user(buffer, key_data, ret))
+			ret = -EFAULT;
+		break;
 	}
+	kvfree_sensitive(key_data, key_data_len);
 
-error2:
+key_put_out:
 	key_put(key);
-error:
+out:
 	return ret;
 }
 
@@ -877,8 +943,8 @@ long keyctl_chown_key(key_serial_t id, uid_t user, gid_t group)
 				key_quota_root_maxbytes : key_quota_maxbytes;
 
 			spin_lock(&newowner->lock);
-			if (newowner->qnkeys + 1 >= maxkeys ||
-			    newowner->qnbytes + key->quotalen >= maxbytes ||
+			if (newowner->qnkeys + 1 > maxkeys ||
+			    newowner->qnbytes + key->quotalen > maxbytes ||
 			    newowner->qnbytes + key->quotalen <
 			    newowner->qnbytes)
 				goto quota_overrun;
@@ -1096,10 +1162,7 @@ long keyctl_instantiate_key_common(key_serial_t id,
 		keyctl_change_reqkey_auth(NULL);
 
 error2:
-	if (payload) {
-		memzero_explicit(payload, plen);
-		kvfree(payload);
-	}
+	kvfree_sensitive(payload, plen);
 error:
 	return ret;
 }
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index e311cc5df358..f00a21a5381c 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -429,7 +429,6 @@ static int keyring_read_iterator(const void *object, void *data)
 {
 	struct keyring_read_iterator_context *ctx = data;
 	const struct key *key = keyring_ptr_to_key(object);
-	int ret;
 
 	kenter("{%s,%d},,{%zu/%zu}",
 	       key->type->name, key->serial, ctx->count, ctx->buflen);
@@ -437,10 +436,7 @@ static int keyring_read_iterator(const void *object, void *data)
 	if (ctx->count >= ctx->buflen)
 		return 1;
 
-	ret = put_user(key->serial, ctx->buffer);
-	if (ret < 0)
-		return ret;
-	ctx->buffer++;
+	*ctx->buffer++ = key->serial;
 	ctx->count += sizeof(key->serial);
 	return 0;
 }
diff --git a/security/keys/proc.c b/security/keys/proc.c
index 4e3266a2529e..bc892a93e527 100644
--- a/security/keys/proc.c
+++ b/security/keys/proc.c
@@ -139,6 +139,8 @@ static void *proc_keys_next(struct seq_file *p, void *v, loff_t *_pos)
 	n = key_serial_next(p, v);
 	if (n)
 		*_pos = key_node_serial(n);
+	else
+		(*_pos)++;
 	return n;
 }
 
diff --git a/security/keys/request_key_auth.c b/security/keys/request_key_auth.c
index 8491becb5727..edf0c14624c5 100644
--- a/security/keys/request_key_auth.c
+++ b/security/keys/request_key_auth.c
@@ -22,7 +22,7 @@ static int request_key_auth_instantiate(struct key *,
 static void request_key_auth_describe(const struct key *, struct seq_file *);
 static void request_key_auth_revoke(struct key *);
 static void request_key_auth_destroy(struct key *);
-static long request_key_auth_read(const struct key *, char __user *, size_t);
+static long request_key_auth_read(const struct key *, char *, size_t);
 
 /*
  * The request-key authorisation key type definition.
@@ -80,7 +80,7 @@ static void request_key_auth_describe(const struct key *key,
  * - the key's semaphore is read-locked
  */
 static long request_key_auth_read(const struct key *key,
-				  char __user *buffer, size_t buflen)
+				  char *buffer, size_t buflen)
 {
 	struct request_key_auth *rka = get_request_key_auth(key);
 	size_t datalen;
@@ -97,8 +97,7 @@ static long request_key_auth_read(const struct key *key,
 		if (buflen > datalen)
 			buflen = datalen;
 
-		if (copy_to_user(buffer, rka->callout_info, buflen) != 0)
-			ret = -EFAULT;
+		memcpy(buffer, rka->callout_info, buflen);
 	}
 
 	return ret;
diff --git a/security/keys/trusted.c b/security/keys/trusted.c
index 1fbd77816610..36afc29aecc3 100644
--- a/security/keys/trusted.c
+++ b/security/keys/trusted.c
@@ -1144,11 +1144,10 @@ out:
  * trusted_read - copy the sealed blob data to userspace in hex.
  * On success, return to userspace the trusted key datablob size.
  */
-static long trusted_read(const struct key *key, char __user *buffer,
+static long trusted_read(const struct key *key, char *buffer,
 			 size_t buflen)
 {
 	const struct trusted_key_payload *p;
-	char *ascii_buf;
 	char *bufp;
 	int i;
 
@@ -1157,18 +1156,9 @@ static long trusted_read(const struct key *key, char __user *buffer,
 		return -EINVAL;
 
 	if (buffer && buflen >= 2 * p->blob_len) {
-		ascii_buf = kmalloc_array(2, p->blob_len, GFP_KERNEL);
-		if (!ascii_buf)
-			return -ENOMEM;
-
-		bufp = ascii_buf;
+		bufp = buffer;
 		for (i = 0; i < p->blob_len; i++)
 			bufp = hex_byte_pack(bufp, p->blob[i]);
-		if (copy_to_user(buffer, ascii_buf, 2 * p->blob_len) != 0) {
-			kzfree(ascii_buf);
-			return -EFAULT;
-		}
-		kzfree(ascii_buf);
 	}
 	return 2 * p->blob_len;
 }
diff --git a/security/keys/user_defined.c b/security/keys/user_defined.c
index 6f12de4ce549..07d4287e9084 100644
--- a/security/keys/user_defined.c
+++ b/security/keys/user_defined.c
@@ -168,7 +168,7 @@ EXPORT_SYMBOL_GPL(user_describe);
  * read the key data
  * - the key's semaphore is read-locked
  */
-long user_read(const struct key *key, char __user *buffer, size_t buflen)
+long user_read(const struct key *key, char *buffer, size_t buflen)
 {
 	const struct user_key_payload *upayload;
 	long ret;
@@ -181,8 +181,7 @@ long user_read(const struct key *key, char __user *buffer, size_t buflen)
 		if (buflen > upayload->datalen)
 			buflen = upayload->datalen;
 
-		if (copy_to_user(buffer, upayload->data, buflen) != 0)
-			ret = -EFAULT;
+		memcpy(buffer, upayload->data, buflen);
 	}
 
 	return ret;
diff --git a/security/selinux/avc.c b/security/selinux/avc.c
index ecd3829996aa..d18cb32a242a 100644
--- a/security/selinux/avc.c
+++ b/security/selinux/avc.c
@@ -424,7 +424,7 @@ static inline int avc_xperms_audit(struct selinux_state *state,
 	if (likely(!audited))
 		return 0;
 	return slow_avc_audit(state, ssid, tsid, tclass, requested,
-			audited, denied, result, ad, 0);
+			audited, denied, result, ad);
 }
 
 static void avc_node_free(struct rcu_head *rhead)
@@ -617,40 +617,37 @@ static struct avc_node *avc_insert(struct selinux_avc *avc,
 	struct avc_node *pos, *node = NULL;
 	int hvalue;
 	unsigned long flag;
+	spinlock_t *lock;
+	struct hlist_head *head;
 
 	if (avc_latest_notif_update(avc, avd->seqno, 1))
-		goto out;
+		return NULL;
 
 	node = avc_alloc_node(avc);
-	if (node) {
-		struct hlist_head *head;
-		spinlock_t *lock;
-		int rc = 0;
-
-		hvalue = avc_hash(ssid, tsid, tclass);
-		avc_node_populate(node, ssid, tsid, tclass, avd);
-		rc = avc_xperms_populate(node, xp_node);
-		if (rc) {
-			kmem_cache_free(avc_node_cachep, node);
-			return NULL;
-		}
-		head = &avc->avc_cache.slots[hvalue];
-		lock = &avc->avc_cache.slots_lock[hvalue];
+	if (!node)
+		return NULL;
 
-		spin_lock_irqsave(lock, flag);
-		hlist_for_each_entry(pos, head, list) {
-			if (pos->ae.ssid == ssid &&
-			    pos->ae.tsid == tsid &&
-			    pos->ae.tclass == tclass) {
-				avc_node_replace(avc, node, pos);
-				goto found;
-			}
+	avc_node_populate(node, ssid, tsid, tclass, avd);
+	if (avc_xperms_populate(node, xp_node)) {
+		avc_node_kill(avc, node);
+		return NULL;
+	}
+
+	hvalue = avc_hash(ssid, tsid, tclass);
+	head = &avc->avc_cache.slots[hvalue];
+	lock = &avc->avc_cache.slots_lock[hvalue];
+	spin_lock_irqsave(lock, flag);
+	hlist_for_each_entry(pos, head, list) {
+		if (pos->ae.ssid == ssid &&
+			pos->ae.tsid == tsid &&
+			pos->ae.tclass == tclass) {
+			avc_node_replace(avc, node, pos);
+			goto found;
 		}
-		hlist_add_head_rcu(&node->list, head);
-found:
-		spin_unlock_irqrestore(lock, flag);
 	}
-out:
+	hlist_add_head_rcu(&node->list, head);
+found:
+	spin_unlock_irqrestore(lock, flag);
 	return node;
 }
 
@@ -758,8 +755,7 @@ static void avc_audit_post_callback(struct audit_buffer *ab, void *a)
 noinline int slow_avc_audit(struct selinux_state *state,
 			    u32 ssid, u32 tsid, u16 tclass,
 			    u32 requested, u32 audited, u32 denied, int result,
-			    struct common_audit_data *a,
-			    unsigned int flags)
+			    struct common_audit_data *a)
 {
 	struct common_audit_data stack_data;
 	struct selinux_audit_data sad;
@@ -772,17 +768,6 @@ noinline int slow_avc_audit(struct selinux_state *state,
 		a->type = LSM_AUDIT_DATA_NONE;
 	}
 
-	/*
-	 * When in a RCU walk do the audit on the RCU retry.  This is because
-	 * the collection of the dname in an inode audit message is not RCU
-	 * safe.  Note this may drop some audits when the situation changes
-	 * during retry. However this is logically just as if the operation
-	 * happened a little later.
-	 */
-	if ((a->type == LSM_AUDIT_DATA_INODE) &&
-	    (flags & MAY_NOT_BLOCK))
-		return -ECHILD;
-
 	sad.tclass = tclass;
 	sad.requested = requested;
 	sad.ssid = ssid;
@@ -855,15 +840,14 @@ static int avc_update_node(struct selinux_avc *avc,
 	/*
 	 * If we are in a non-blocking code path, e.g. VFS RCU walk,
 	 * then we must not add permissions to a cache entry
-	 * because we cannot safely audit the denial.  Otherwise,
+	 * because we will not audit the denial.  Otherwise,
 	 * during the subsequent blocking retry (e.g. VFS ref walk), we
 	 * will find the permissions already granted in the cache entry
 	 * and won't audit anything at all, leading to silent denials in
 	 * permissive mode that only appear when in enforcing mode.
 	 *
-	 * See the corresponding handling in slow_avc_audit(), and the
-	 * logic in selinux_inode_permission for the MAY_NOT_BLOCK flag,
-	 * which is transliterated into AVC_NONBLOCKING.
+	 * See the corresponding handling of MAY_NOT_BLOCK in avc_audit()
+	 * and selinux_inode_permission().
 	 */
 	if (flags & AVC_NONBLOCKING)
 		return 0;
@@ -907,7 +891,7 @@ static int avc_update_node(struct selinux_avc *avc,
 	if (orig->ae.xp_node) {
 		rc = avc_xperms_populate(node, orig->ae.xp_node);
 		if (rc) {
-			kmem_cache_free(avc_node_cachep, node);
+			avc_node_kill(avc, node);
 			goto out_unlock;
 		}
 	}
@@ -1205,6 +1189,25 @@ int avc_has_perm(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass,
 	return rc;
 }
 
+int avc_has_perm_flags(struct selinux_state *state,
+		       u32 ssid, u32 tsid, u16 tclass, u32 requested,
+		       struct common_audit_data *auditdata,
+		       int flags)
+{
+	struct av_decision avd;
+	int rc, rc2;
+
+	rc = avc_has_perm_noaudit(state, ssid, tsid, tclass, requested,
+				  (flags & MAY_NOT_BLOCK) ? AVC_NONBLOCKING : 0,
+				  &avd);
+
+	rc2 = avc_audit(state, ssid, tsid, tclass, requested, &avd, rc,
+			auditdata, flags);
+	if (rc2)
+		return rc2;
+	return rc;
+}
+
 u32 avc_policy_seqno(struct selinux_state *state)
 {
 	return state->avc->avc_cache.latest_notif;
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index c106167423a1..3cdc5a22004a 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -2764,6 +2764,14 @@ static int selinux_mount(const char *dev_name,
 		return path_has_perm(cred, path, FILE__MOUNTON);
 }
 
+static int selinux_move_mount(const struct path *from_path,
+			      const struct path *to_path)
+{
+	const struct cred *cred = current_cred();
+
+	return path_has_perm(cred, to_path, FILE__MOUNTON);
+}
+
 static int selinux_umount(struct vfsmount *mnt, int flags)
 {
 	const struct cred *cred = current_cred();
@@ -3006,14 +3014,14 @@ static int selinux_inode_follow_link(struct dentry *dentry, struct inode *inode,
 	if (IS_ERR(isec))
 		return PTR_ERR(isec);
 
-	return avc_has_perm(&selinux_state,
-			    sid, isec->sid, isec->sclass, FILE__READ, &ad);
+	return avc_has_perm_flags(&selinux_state,
+				  sid, isec->sid, isec->sclass, FILE__READ, &ad,
+				  rcu ? MAY_NOT_BLOCK : 0);
 }
 
 static noinline int audit_inode_permission(struct inode *inode,
 					   u32 perms, u32 audited, u32 denied,
-					   int result,
-					   unsigned flags)
+					   int result)
 {
 	struct common_audit_data ad;
 	struct inode_security_struct *isec = selinux_inode(inode);
@@ -3024,7 +3032,7 @@ static noinline int audit_inode_permission(struct inode *inode,
 
 	rc = slow_avc_audit(&selinux_state,
 			    current_sid(), isec->sid, isec->sclass, perms,
-			    audited, denied, result, &ad, flags);
+			    audited, denied, result, &ad);
 	if (rc)
 		return rc;
 	return 0;
@@ -3071,7 +3079,11 @@ static int selinux_inode_permission(struct inode *inode, int mask)
 	if (likely(!audited))
 		return rc;
 
-	rc2 = audit_inode_permission(inode, perms, audited, denied, rc, flags);
+	/* fall back to ref-walk if we have to generate audit */
+	if (flags & MAY_NOT_BLOCK)
+		return -ECHILD;
+
+	rc2 = audit_inode_permission(inode, perms, audited, denied, rc);
 	if (rc2)
 		return rc2;
 	return rc;
@@ -5461,44 +5473,6 @@ static int selinux_tun_dev_open(void *security)
 	return 0;
 }
 
-static int selinux_nlmsg_perm(struct sock *sk, struct sk_buff *skb)
-{
-	int err = 0;
-	u32 perm;
-	struct nlmsghdr *nlh;
-	struct sk_security_struct *sksec = sk->sk_security;
-
-	if (skb->len < NLMSG_HDRLEN) {
-		err = -EINVAL;
-		goto out;
-	}
-	nlh = nlmsg_hdr(skb);
-
-	err = selinux_nlmsg_lookup(sksec->sclass, nlh->nlmsg_type, &perm);
-	if (err) {
-		if (err == -EINVAL) {
-			pr_warn_ratelimited("SELinux: unrecognized netlink"
-			       " message: protocol=%hu nlmsg_type=%hu sclass=%s"
-			       " pig=%d comm=%s\n",
-			       sk->sk_protocol, nlh->nlmsg_type,
-			       secclass_map[sksec->sclass - 1].name,
-			       task_pid_nr(current), current->comm);
-			if (!enforcing_enabled(&selinux_state) ||
-			    security_get_allow_unknown(&selinux_state))
-				err = 0;
-		}
-
-		/* Ignore */
-		if (err == -ENOENT)
-			err = 0;
-		goto out;
-	}
-
-	err = sock_has_perm(sk, perm);
-out:
-	return err;
-}
-
 #ifdef CONFIG_NETFILTER
 
 static unsigned int selinux_ip_forward(struct sk_buff *skb,
@@ -5827,7 +5801,60 @@ static unsigned int selinux_ipv6_postroute(void *priv,
 
 static int selinux_netlink_send(struct sock *sk, struct sk_buff *skb)
 {
-	return selinux_nlmsg_perm(sk, skb);
+	int rc = 0;
+	unsigned int msg_len;
+	unsigned int data_len = skb->len;
+	unsigned char *data = skb->data;
+	struct nlmsghdr *nlh;
+	struct sk_security_struct *sksec = sk->sk_security;
+	u16 sclass = sksec->sclass;
+	u32 perm;
+
+	while (data_len >= nlmsg_total_size(0)) {
+		nlh = (struct nlmsghdr *)data;
+
+		/* NOTE: the nlmsg_len field isn't reliably set by some netlink
+		 *       users which means we can't reject skb's with bogus
+		 *       length fields; our solution is to follow what
+		 *       netlink_rcv_skb() does and simply skip processing at
+		 *       messages with length fields that are clearly junk
+		 */
+		if (nlh->nlmsg_len < NLMSG_HDRLEN || nlh->nlmsg_len > data_len)
+			return 0;
+
+		rc = selinux_nlmsg_lookup(sclass, nlh->nlmsg_type, &perm);
+		if (rc == 0) {
+			rc = sock_has_perm(sk, perm);
+			if (rc)
+				return rc;
+		} else if (rc == -EINVAL) {
+			/* -EINVAL is a missing msg/perm mapping */
+			pr_warn_ratelimited("SELinux: unrecognized netlink"
+				" message: protocol=%hu nlmsg_type=%hu sclass=%s"
+				" pid=%d comm=%s\n",
+				sk->sk_protocol, nlh->nlmsg_type,
+				secclass_map[sclass - 1].name,
+				task_pid_nr(current), current->comm);
+			if (enforcing_enabled(&selinux_state) &&
+			    !security_get_allow_unknown(&selinux_state))
+				return rc;
+			rc = 0;
+		} else if (rc == -ENOENT) {
+			/* -ENOENT is a missing socket/class mapping, ignore */
+			rc = 0;
+		} else {
+			return rc;
+		}
+
+		/* move to the next message after applying netlink padding */
+		msg_len = NLMSG_ALIGN(nlh->nlmsg_len);
+		if (msg_len >= data_len)
+			return 0;
+		data_len -= msg_len;
+		data += msg_len;
+	}
+
+	return rc;
 }
 
 static void ipc_init_security(struct ipc_security_struct *isec, u16 sclass)
@@ -6788,6 +6815,8 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = {
 	LSM_HOOK_INIT(sb_clone_mnt_opts, selinux_sb_clone_mnt_opts),
 	LSM_HOOK_INIT(sb_add_mnt_opt, selinux_add_mnt_opt),
 
+	LSM_HOOK_INIT(move_mount, selinux_move_mount),
+
 	LSM_HOOK_INIT(dentry_init_security, selinux_dentry_init_security),
 	LSM_HOOK_INIT(dentry_create_files_as, selinux_dentry_create_files_as),
 
diff --git a/security/selinux/include/avc.h b/security/selinux/include/avc.h
index 7be0e1e90e8b..cf4cc3ef959b 100644
--- a/security/selinux/include/avc.h
+++ b/security/selinux/include/avc.h
@@ -100,8 +100,7 @@ static inline u32 avc_audit_required(u32 requested,
 int slow_avc_audit(struct selinux_state *state,
 		   u32 ssid, u32 tsid, u16 tclass,
 		   u32 requested, u32 audited, u32 denied, int result,
-		   struct common_audit_data *a,
-		   unsigned flags);
+		   struct common_audit_data *a);
 
 /**
  * avc_audit - Audit the granting or denial of permissions.
@@ -135,9 +134,12 @@ static inline int avc_audit(struct selinux_state *state,
 	audited = avc_audit_required(requested, avd, result, 0, &denied);
 	if (likely(!audited))
 		return 0;
+	/* fall back to ref-walk if we have to generate audit */
+	if (flags & MAY_NOT_BLOCK)
+		return -ECHILD;
 	return slow_avc_audit(state, ssid, tsid, tclass,
 			      requested, audited, denied, result,
-			      a, flags);
+			      a);
 }
 
 #define AVC_STRICT 1 /* Ignore permissive mode. */
@@ -153,6 +155,11 @@ int avc_has_perm(struct selinux_state *state,
 		 u32 ssid, u32 tsid,
 		 u16 tclass, u32 requested,
 		 struct common_audit_data *auditdata);
+int avc_has_perm_flags(struct selinux_state *state,
+		       u32 ssid, u32 tsid,
+		       u16 tclass, u32 requested,
+		       struct common_audit_data *auditdata,
+		       int flags);
 
 int avc_has_extended_perms(struct selinux_state *state,
 			   u32 ssid, u32 tsid, u16 tclass, u32 requested,
diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c
index f8efaa9f647c..23abad429668 100644
--- a/security/selinux/ss/policydb.c
+++ b/security/selinux/ss/policydb.c
@@ -2494,6 +2494,7 @@ int policydb_read(struct policydb *p, void *fp)
 	if (rc)
 		goto bad;
 
+	rc = -ENOMEM;
 	p->type_attr_map_array = kvcalloc(p->p_types.nprim,
 					  sizeof(*p->type_attr_map_array),
 					  GFP_KERNEL);
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index 3585ef8c4836..e3cfbb182243 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -2845,8 +2845,12 @@ err:
 	if (*names) {
 		for (i = 0; i < *len; i++)
 			kfree((*names)[i]);
+		kfree(*names);
 	}
 	kfree(*values);
+	*len = 0;
+	*names = NULL;
+	*values = NULL;
 	goto out;
 }
 
diff --git a/security/smack/smack.h b/security/smack/smack.h
index 62529f382942..335d2411abe4 100644
--- a/security/smack/smack.h
+++ b/security/smack/smack.h
@@ -148,7 +148,6 @@ struct smk_net4addr {
 	struct smack_known	*smk_label;	/* label */
 };
 
-#if IS_ENABLED(CONFIG_IPV6)
 /*
  * An entry in the table identifying IPv6 hosts.
  */
@@ -159,9 +158,7 @@ struct smk_net6addr {
 	int			smk_masks;	/* mask size */
 	struct smack_known	*smk_label;	/* label */
 };
-#endif /* CONFIG_IPV6 */
 
-#ifdef SMACK_IPV6_PORT_LABELING
 /*
  * An entry in the table identifying ports.
  */
@@ -174,7 +171,6 @@ struct smk_port_label {
 	short			smk_sock_type;	/* Socket type */
 	short			smk_can_reuse;
 };
-#endif /* SMACK_IPV6_PORT_LABELING */
 
 struct smack_known_list_elem {
 	struct list_head	list;
@@ -335,9 +331,7 @@ extern struct smack_known smack_known_web;
 extern struct mutex	smack_known_lock;
 extern struct list_head smack_known_list;
 extern struct list_head smk_net4addr_list;
-#if IS_ENABLED(CONFIG_IPV6)
 extern struct list_head smk_net6addr_list;
-#endif /* CONFIG_IPV6 */
 
 extern struct mutex     smack_onlycap_lock;
 extern struct list_head smack_onlycap_list;
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 36b6b9d4cbaf..f3781622a04d 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -51,10 +51,8 @@
 #define SMK_RECEIVING	1
 #define SMK_SENDING	2
 
-#ifdef SMACK_IPV6_PORT_LABELING
-DEFINE_MUTEX(smack_ipv6_lock);
+static DEFINE_MUTEX(smack_ipv6_lock);
 static LIST_HEAD(smk_ipv6_port_list);
-#endif
 static struct kmem_cache *smack_inode_cache;
 struct kmem_cache *smack_rule_cache;
 int smack_enabled;
@@ -2330,7 +2328,6 @@ static struct smack_known *smack_ipv4host_label(struct sockaddr_in *sip)
 	return NULL;
 }
 
-#if IS_ENABLED(CONFIG_IPV6)
 /*
  * smk_ipv6_localhost - Check for local ipv6 host address
  * @sip: the address
@@ -2398,7 +2395,6 @@ static struct smack_known *smack_ipv6host_label(struct sockaddr_in6 *sip)
 
 	return NULL;
 }
-#endif /* CONFIG_IPV6 */
 
 /**
  * smack_netlabel - Set the secattr on a socket
@@ -2487,7 +2483,6 @@ static int smack_netlabel_send(struct sock *sk, struct sockaddr_in *sap)
 	return smack_netlabel(sk, sk_lbl);
 }
 
-#if IS_ENABLED(CONFIG_IPV6)
 /**
  * smk_ipv6_check - check Smack access
  * @subject: subject Smack label
@@ -2520,7 +2515,6 @@ static int smk_ipv6_check(struct smack_known *subject,
 	rc = smk_bu_note("IPv6 check", subject, object, MAY_WRITE, rc);
 	return rc;
 }
-#endif /* CONFIG_IPV6 */
 
 #ifdef SMACK_IPV6_PORT_LABELING
 /**
@@ -2609,6 +2603,7 @@ static void smk_ipv6_port_label(struct socket *sock, struct sockaddr *address)
 	mutex_unlock(&smack_ipv6_lock);
 	return;
 }
+#endif
 
 /**
  * smk_ipv6_port_check - check Smack port access
@@ -2670,7 +2665,6 @@ static int smk_ipv6_port_check(struct sock *sk, struct sockaddr_in6 *address,
 
 	return smk_ipv6_check(skp, object, address, act);
 }
-#endif /* SMACK_IPV6_PORT_LABELING */
 
 /**
  * smack_inode_setsecurity - set smack xattrs
@@ -2835,42 +2829,36 @@ static int smack_socket_connect(struct socket *sock, struct sockaddr *sap,
 				int addrlen)
 {
 	int rc = 0;
-#if IS_ENABLED(CONFIG_IPV6)
-	struct sockaddr_in6 *sip = (struct sockaddr_in6 *)sap;
-#endif
-#ifdef SMACK_IPV6_SECMARK_LABELING
-	struct smack_known *rsp;
-	struct socket_smack *ssp;
-#endif
 
 	if (sock->sk == NULL)
 		return 0;
+	if (sock->sk->sk_family != PF_INET &&
+	    (!IS_ENABLED(CONFIG_IPV6) || sock->sk->sk_family != PF_INET6))
+		return 0;
+	if (addrlen < offsetofend(struct sockaddr, sa_family))
+		return 0;
+	if (IS_ENABLED(CONFIG_IPV6) && sap->sa_family == AF_INET6) {
+		struct sockaddr_in6 *sip = (struct sockaddr_in6 *)sap;
+		struct smack_known *rsp = NULL;
 
-#ifdef SMACK_IPV6_SECMARK_LABELING
-	ssp = sock->sk->sk_security;
-#endif
+		if (addrlen < SIN6_LEN_RFC2133)
+			return 0;
+		if (__is_defined(SMACK_IPV6_SECMARK_LABELING))
+			rsp = smack_ipv6host_label(sip);
+		if (rsp != NULL) {
+			struct socket_smack *ssp = sock->sk->sk_security;
 
-	switch (sock->sk->sk_family) {
-	case PF_INET:
-		if (addrlen < sizeof(struct sockaddr_in) ||
-		    sap->sa_family != AF_INET)
-			return -EINVAL;
-		rc = smack_netlabel_send(sock->sk, (struct sockaddr_in *)sap);
-		break;
-	case PF_INET6:
-		if (addrlen < SIN6_LEN_RFC2133 || sap->sa_family != AF_INET6)
-			return -EINVAL;
-#ifdef SMACK_IPV6_SECMARK_LABELING
-		rsp = smack_ipv6host_label(sip);
-		if (rsp != NULL)
 			rc = smk_ipv6_check(ssp->smk_out, rsp, sip,
-						SMK_CONNECTING);
-#endif
-#ifdef SMACK_IPV6_PORT_LABELING
-		rc = smk_ipv6_port_check(sock->sk, sip, SMK_CONNECTING);
-#endif
-		break;
+					    SMK_CONNECTING);
+		}
+		if (__is_defined(SMACK_IPV6_PORT_LABELING))
+			rc = smk_ipv6_port_check(sock->sk, sip, SMK_CONNECTING);
+
+		return rc;
 	}
+	if (sap->sa_family != AF_INET || addrlen < sizeof(struct sockaddr_in))
+		return 0;
+	rc = smack_netlabel_send(sock->sk, (struct sockaddr_in *)sap);
 	return rc;
 }
 
diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c
index ef0d8712d318..8c000344b7ec 100644
--- a/security/smack/smackfs.c
+++ b/security/smack/smackfs.c
@@ -877,11 +877,21 @@ static ssize_t smk_set_cipso(struct file *file, const char __user *buf,
 	else
 		rule += strlen(skp->smk_known) + 1;
 
+	if (rule > data + count) {
+		rc = -EOVERFLOW;
+		goto out;
+	}
+
 	ret = sscanf(rule, "%d", &maplevel);
-	if (ret != 1 || maplevel > SMACK_CIPSO_MAXLEVEL)
+	if (ret != 1 || maplevel < 0 || maplevel > SMACK_CIPSO_MAXLEVEL)
 		goto out;
 
 	rule += SMK_DIGITLEN;
+	if (rule > data + count) {
+		rc = -EOVERFLOW;
+		goto out;
+	}
+
 	ret = sscanf(rule, "%d", &catlen);
 	if (ret != 1 || catlen > SMACK_CIPSO_MAXCATNUM)
 		goto out;
@@ -894,6 +904,10 @@ static ssize_t smk_set_cipso(struct file *file, const char __user *buf,
 
 	for (i = 0; i < catlen; i++) {
 		rule += SMK_DIGITLEN;
+		if (rule > data + count) {
+			rc = -EOVERFLOW;
+			goto out;
+		}
 		ret = sscanf(rule, "%u", &cat);
 		if (ret != 1 || cat > SMACK_CIPSO_MAXCATNUM)
 			goto out;
@@ -2709,7 +2723,6 @@ static int smk_open_relabel_self(struct inode *inode, struct file *file)
 static ssize_t smk_write_relabel_self(struct file *file, const char __user *buf,
 				size_t count, loff_t *ppos)
 {
-	struct task_smack *tsp = smack_cred(current_cred());
 	char *data;
 	int rc;
 	LIST_HEAD(list_tmp);
@@ -2734,11 +2747,21 @@ static ssize_t smk_write_relabel_self(struct file *file, const char __user *buf,
 	kfree(data);
 
 	if (!rc || (rc == -EINVAL && list_empty(&list_tmp))) {
+		struct cred *new;
+		struct task_smack *tsp;
+
+		new = prepare_creds();
+		if (!new) {
+			rc = -ENOMEM;
+			goto out;
+		}
+		tsp = smack_cred(new);
 		smk_destroy_label_list(&tsp->smk_relabel);
 		list_splice(&list_tmp, &tsp->smk_relabel);
+		commit_creds(new);
 		return count;
 	}
-
+out:
 	smk_destroy_label_list(&list_tmp);
 	return rc;
 }
diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c
index dd3d5942e669..adedd4dfb2be 100644
--- a/security/tomoyo/common.c
+++ b/security/tomoyo/common.c
@@ -2320,9 +2320,9 @@ static const char * const tomoyo_memory_headers[TOMOYO_MAX_MEMORY_STAT] = {
 	[TOMOYO_MEMORY_QUERY]  = "query message:",
 };
 
-/* Timestamp counter for last updated. */
-static unsigned int tomoyo_stat_updated[TOMOYO_MAX_POLICY_STAT];
 /* Counter for number of updates. */
+static atomic_t tomoyo_stat_updated[TOMOYO_MAX_POLICY_STAT];
+/* Timestamp counter for last updated. */
 static time64_t tomoyo_stat_modified[TOMOYO_MAX_POLICY_STAT];
 
 /**
@@ -2334,10 +2334,7 @@ static time64_t tomoyo_stat_modified[TOMOYO_MAX_POLICY_STAT];
  */
 void tomoyo_update_stat(const u8 index)
 {
-	/*
-	 * I don't use atomic operations because race condition is not fatal.
-	 */
-	tomoyo_stat_updated[index]++;
+	atomic_inc(&tomoyo_stat_updated[index]);
 	tomoyo_stat_modified[index] = ktime_get_real_seconds();
 }
 
@@ -2358,7 +2355,7 @@ static void tomoyo_read_stat(struct tomoyo_io_buffer *head)
 	for (i = 0; i < TOMOYO_MAX_POLICY_STAT; i++) {
 		tomoyo_io_printf(head, "Policy %-30s %10u",
 				 tomoyo_policy_headers[i],
-				 tomoyo_stat_updated[i]);
+				 atomic_read(&tomoyo_stat_updated[i]));
 		if (tomoyo_stat_modified[i]) {
 			struct tomoyo_time stamp;
 
diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c
index f34ce564d92c..1afa06b80f06 100644
--- a/sound/core/compress_offload.c
+++ b/sound/core/compress_offload.c
@@ -722,6 +722,9 @@ static int snd_compr_stop(struct snd_compr_stream *stream)
 
 	retval = stream->ops->trigger(stream, SNDRV_PCM_TRIGGER_STOP);
 	if (!retval) {
+		/* clear flags and stop any drain wait */
+		stream->partial_drain = false;
+		stream->metadata_set = false;
 		snd_compr_drain_notify(stream);
 		stream->runtime->total_bytes_available = 0;
 		stream->runtime->total_bytes_transferred = 0;
@@ -879,6 +882,7 @@ static int snd_compr_partial_drain(struct snd_compr_stream *stream)
 	if (stream->next_track == false)
 		return -EPERM;
 
+	stream->partial_drain = true;
 	retval = stream->ops->trigger(stream, SND_COMPR_TRIGGER_PARTIAL_DRAIN);
 	if (retval) {
 		pr_debug("Partial drain returned failure\n");
diff --git a/sound/core/control.c b/sound/core/control.c
index 5be5b9b931bf..ea99bd961a7a 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -1434,8 +1434,9 @@ static int call_tlv_handler(struct snd_ctl_file *file, int op_flag,
 	if (kctl->tlv.c == NULL)
 		return -ENXIO;
 
-	/* When locked, this is unavailable. */
-	if (vd->owner != NULL && vd->owner != file)
+	/* Write and command operations are not allowed for locked element. */
+	if (op_flag != SNDRV_CTL_TLV_OP_READ &&
+	    vd->owner != NULL && vd->owner != file)
 		return -EPERM;
 
 	return kctl->tlv.c(kctl, op_flag, size, buf);
diff --git a/sound/core/hwdep.c b/sound/core/hwdep.c
index 00cb5aed10a9..28bec15b0959 100644
--- a/sound/core/hwdep.c
+++ b/sound/core/hwdep.c
@@ -216,12 +216,12 @@ static int snd_hwdep_dsp_load(struct snd_hwdep *hw,
 	if (info.index >= 32)
 		return -EINVAL;
 	/* check whether the dsp was already loaded */
-	if (hw->dsp_loaded & (1 << info.index))
+	if (hw->dsp_loaded & (1u << info.index))
 		return -EBUSY;
 	err = hw->ops.dsp_load(hw, &info);
 	if (err < 0)
 		return err;
-	hw->dsp_loaded |= (1 << info.index);
+	hw->dsp_loaded |= (1u << info.index);
 	return 0;
 }
 
diff --git a/sound/core/info.c b/sound/core/info.c
index e051a029ccfb..f18f4ef6661e 100644
--- a/sound/core/info.c
+++ b/sound/core/info.c
@@ -608,7 +608,9 @@ int snd_info_get_line(struct snd_info_buffer *buffer, char *line, int len)
 {
 	int c = -1;
 
-	if (snd_BUG_ON(!buffer || !buffer->buffer))
+	if (snd_BUG_ON(!buffer))
+		return 1;
+	if (!buffer->buffer)
 		return 1;
 	if (len <= 0 || buffer->stop || buffer->error)
 		return 1;
diff --git a/sound/core/oss/pcm_plugin.c b/sound/core/oss/pcm_plugin.c
index 31cb2acf8afc..da400da1fafe 100644
--- a/sound/core/oss/pcm_plugin.c
+++ b/sound/core/oss/pcm_plugin.c
@@ -111,7 +111,7 @@ int snd_pcm_plug_alloc(struct snd_pcm_substream *plug, snd_pcm_uframes_t frames)
 		while (plugin->next) {
 			if (plugin->dst_frames)
 				frames = plugin->dst_frames(plugin, frames);
-			if (snd_BUG_ON((snd_pcm_sframes_t)frames <= 0))
+			if ((snd_pcm_sframes_t)frames <= 0)
 				return -ENXIO;
 			plugin = plugin->next;
 			err = snd_pcm_plugin_alloc(plugin, frames);
@@ -123,7 +123,7 @@ int snd_pcm_plug_alloc(struct snd_pcm_substream *plug, snd_pcm_uframes_t frames)
 		while (plugin->prev) {
 			if (plugin->src_frames)
 				frames = plugin->src_frames(plugin, frames);
-			if (snd_BUG_ON((snd_pcm_sframes_t)frames <= 0))
+			if ((snd_pcm_sframes_t)frames <= 0)
 				return -ENXIO;
 			plugin = plugin->prev;
 			err = snd_pcm_plugin_alloc(plugin, frames);
@@ -196,7 +196,9 @@ int snd_pcm_plugin_free(struct snd_pcm_plugin *plugin)
 	return 0;
 }
 
-snd_pcm_sframes_t snd_pcm_plug_client_size(struct snd_pcm_substream *plug, snd_pcm_uframes_t drv_frames)
+static snd_pcm_sframes_t plug_client_size(struct snd_pcm_substream *plug,
+					  snd_pcm_uframes_t drv_frames,
+					  bool check_size)
 {
 	struct snd_pcm_plugin *plugin, *plugin_prev, *plugin_next;
 	int stream;
@@ -212,12 +214,18 @@ snd_pcm_sframes_t snd_pcm_plug_client_size(struct snd_pcm_substream *plug, snd_p
 			plugin_prev = plugin->prev;
 			if (plugin->src_frames)
 				drv_frames = plugin->src_frames(plugin, drv_frames);
+			if (check_size && plugin->buf_frames &&
+			    drv_frames > plugin->buf_frames)
+				drv_frames = plugin->buf_frames;
 			plugin = plugin_prev;
 		}
 	} else if (stream == SNDRV_PCM_STREAM_CAPTURE) {
 		plugin = snd_pcm_plug_first(plug);
 		while (plugin && drv_frames > 0) {
 			plugin_next = plugin->next;
+			if (check_size && plugin->buf_frames &&
+			    drv_frames > plugin->buf_frames)
+				drv_frames = plugin->buf_frames;
 			if (plugin->dst_frames)
 				drv_frames = plugin->dst_frames(plugin, drv_frames);
 			plugin = plugin_next;
@@ -227,7 +235,9 @@ snd_pcm_sframes_t snd_pcm_plug_client_size(struct snd_pcm_substream *plug, snd_p
 	return drv_frames;
 }
 
-snd_pcm_sframes_t snd_pcm_plug_slave_size(struct snd_pcm_substream *plug, snd_pcm_uframes_t clt_frames)
+static snd_pcm_sframes_t plug_slave_size(struct snd_pcm_substream *plug,
+					 snd_pcm_uframes_t clt_frames,
+					 bool check_size)
 {
 	struct snd_pcm_plugin *plugin, *plugin_prev, *plugin_next;
 	snd_pcm_sframes_t frames;
@@ -243,6 +253,9 @@ snd_pcm_sframes_t snd_pcm_plug_slave_size(struct snd_pcm_substream *plug, snd_pc
 		plugin = snd_pcm_plug_first(plug);
 		while (plugin && frames > 0) {
 			plugin_next = plugin->next;
+			if (check_size && plugin->buf_frames &&
+			    frames > plugin->buf_frames)
+				frames = plugin->buf_frames;
 			if (plugin->dst_frames) {
 				frames = plugin->dst_frames(plugin, frames);
 				if (frames < 0)
@@ -259,6 +272,9 @@ snd_pcm_sframes_t snd_pcm_plug_slave_size(struct snd_pcm_substream *plug, snd_pc
 				if (frames < 0)
 					return frames;
 			}
+			if (check_size && plugin->buf_frames &&
+			    frames > plugin->buf_frames)
+				frames = plugin->buf_frames;
 			plugin = plugin_prev;
 		}
 	} else
@@ -266,6 +282,18 @@ snd_pcm_sframes_t snd_pcm_plug_slave_size(struct snd_pcm_substream *plug, snd_pc
 	return frames;
 }
 
+snd_pcm_sframes_t snd_pcm_plug_client_size(struct snd_pcm_substream *plug,
+					   snd_pcm_uframes_t drv_frames)
+{
+	return plug_client_size(plug, drv_frames, false);
+}
+
+snd_pcm_sframes_t snd_pcm_plug_slave_size(struct snd_pcm_substream *plug,
+					  snd_pcm_uframes_t clt_frames)
+{
+	return plug_slave_size(plug, clt_frames, false);
+}
+
 static int snd_pcm_plug_formats(const struct snd_mask *mask,
 				snd_pcm_format_t format)
 {
@@ -622,7 +650,7 @@ snd_pcm_sframes_t snd_pcm_plug_write_transfer(struct snd_pcm_substream *plug, st
 		src_channels = dst_channels;
 		plugin = next;
 	}
-	return snd_pcm_plug_client_size(plug, frames);
+	return plug_client_size(plug, frames, true);
 }
 
 snd_pcm_sframes_t snd_pcm_plug_read_transfer(struct snd_pcm_substream *plug, struct snd_pcm_plugin_channel *dst_channels_final, snd_pcm_uframes_t size)
@@ -632,7 +660,7 @@ snd_pcm_sframes_t snd_pcm_plug_read_transfer(struct snd_pcm_substream *plug, str
 	snd_pcm_sframes_t frames = size;
 	int err;
 
-	frames = snd_pcm_plug_slave_size(plug, frames);
+	frames = plug_slave_size(plug, frames, true);
 	if (frames < 0)
 		return frames;
 
diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c
index 2236b5e0c1f2..1662573a4030 100644
--- a/sound/core/pcm_lib.c
+++ b/sound/core/pcm_lib.c
@@ -423,6 +423,7 @@ static int snd_pcm_update_hw_ptr0(struct snd_pcm_substream *substream,
 
  no_delta_check:
 	if (runtime->status->hw_ptr == new_hw_ptr) {
+		runtime->hw_ptr_jiffies = curr_jiffies;
 		update_audio_tstamp(substream, &curr_tstamp, &audio_tstamp);
 		return 0;
 	}
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 38541322ccec..f37cb1ebd728 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -136,6 +136,16 @@ void snd_pcm_stream_lock_irq(struct snd_pcm_substream *substream)
 }
 EXPORT_SYMBOL_GPL(snd_pcm_stream_lock_irq);
 
+static void snd_pcm_stream_lock_nested(struct snd_pcm_substream *substream)
+{
+	struct snd_pcm_group *group = &substream->self_group;
+
+	if (substream->pcm->nonatomic)
+		mutex_lock_nested(&group->mutex, SINGLE_DEPTH_NESTING);
+	else
+		spin_lock_nested(&group->lock, SINGLE_DEPTH_NESTING);
+}
+
 /**
  * snd_pcm_stream_unlock_irq - Unlock the PCM stream
  * @substream: PCM substream
@@ -1994,6 +2004,12 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd)
 	}
 	pcm_file = f.file->private_data;
 	substream1 = pcm_file->substream;
+
+	if (substream == substream1) {
+		res = -EINVAL;
+		goto _badf;
+	}
+
 	group = kzalloc(sizeof(*group), GFP_KERNEL);
 	if (!group) {
 		res = -ENOMEM;
@@ -2022,7 +2038,7 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd)
 	snd_pcm_stream_unlock_irq(substream);
 
 	snd_pcm_group_lock_irq(target_group, nonatomic);
-	snd_pcm_stream_lock(substream1);
+	snd_pcm_stream_lock_nested(substream1);
 	snd_pcm_group_assign(substream1, target_group);
 	refcount_inc(&target_group->refs);
 	snd_pcm_stream_unlock(substream1);
@@ -2038,7 +2054,7 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd)
 
 static void relink_to_local(struct snd_pcm_substream *substream)
 {
-	snd_pcm_stream_lock(substream);
+	snd_pcm_stream_lock_nested(substream);
 	snd_pcm_group_assign(substream, &substream->self_group);
 	snd_pcm_stream_unlock(substream);
 }
@@ -3408,7 +3424,8 @@ int snd_pcm_lib_default_mmap(struct snd_pcm_substream *substream,
 #endif /* CONFIG_GENERIC_ALLOCATOR */
 #ifndef CONFIG_X86 /* for avoiding warnings arch/x86/mm/pat.c */
 	if (IS_ENABLED(CONFIG_HAS_DMA) && !substream->ops->page &&
-	    substream->dma_buffer.dev.type == SNDRV_DMA_TYPE_DEV)
+	    (substream->dma_buffer.dev.type == SNDRV_DMA_TYPE_DEV ||
+	     substream->dma_buffer.dev.type == SNDRV_DMA_TYPE_DEV_UC))
 		return dma_mmap_coherent(substream->dma_buffer.dev.dev,
 					 area,
 					 substream->runtime->dma_area,
diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c
index 8a12a7538d63..94db4683cfaf 100644
--- a/sound/core/rawmidi.c
+++ b/sound/core/rawmidi.c
@@ -97,6 +97,17 @@ static void snd_rawmidi_input_event_work(struct work_struct *work)
 		runtime->event(runtime->substream);
 }
 
+/* buffer refcount management: call with runtime->lock held */
+static inline void snd_rawmidi_buffer_ref(struct snd_rawmidi_runtime *runtime)
+{
+	runtime->buffer_ref++;
+}
+
+static inline void snd_rawmidi_buffer_unref(struct snd_rawmidi_runtime *runtime)
+{
+	runtime->buffer_ref--;
+}
+
 static int snd_rawmidi_runtime_create(struct snd_rawmidi_substream *substream)
 {
 	struct snd_rawmidi_runtime *runtime;
@@ -646,6 +657,11 @@ static int resize_runtime_buffer(struct snd_rawmidi_runtime *runtime,
 		if (!newbuf)
 			return -ENOMEM;
 		spin_lock_irq(&runtime->lock);
+		if (runtime->buffer_ref) {
+			spin_unlock_irq(&runtime->lock);
+			kvfree(newbuf);
+			return -EBUSY;
+		}
 		oldbuf = runtime->buffer;
 		runtime->buffer = newbuf;
 		runtime->buffer_size = params->buffer_size;
@@ -945,8 +961,10 @@ static long snd_rawmidi_kernel_read1(struct snd_rawmidi_substream *substream,
 	long result = 0, count1;
 	struct snd_rawmidi_runtime *runtime = substream->runtime;
 	unsigned long appl_ptr;
+	int err = 0;
 
 	spin_lock_irqsave(&runtime->lock, flags);
+	snd_rawmidi_buffer_ref(runtime);
 	while (count > 0 && runtime->avail) {
 		count1 = runtime->buffer_size - runtime->appl_ptr;
 		if (count1 > count)
@@ -965,16 +983,19 @@ static long snd_rawmidi_kernel_read1(struct snd_rawmidi_substream *substream,
 		if (userbuf) {
 			spin_unlock_irqrestore(&runtime->lock, flags);
 			if (copy_to_user(userbuf + result,
-					 runtime->buffer + appl_ptr, count1)) {
-				return result > 0 ? result : -EFAULT;
-			}
+					 runtime->buffer + appl_ptr, count1))
+				err = -EFAULT;
 			spin_lock_irqsave(&runtime->lock, flags);
+			if (err)
+				goto out;
 		}
 		result += count1;
 		count -= count1;
 	}
+ out:
+	snd_rawmidi_buffer_unref(runtime);
 	spin_unlock_irqrestore(&runtime->lock, flags);
-	return result;
+	return result > 0 ? result : err;
 }
 
 long snd_rawmidi_kernel_read(struct snd_rawmidi_substream *substream,
@@ -1268,6 +1289,7 @@ static long snd_rawmidi_kernel_write1(struct snd_rawmidi_substream *substream,
 			return -EAGAIN;
 		}
 	}
+	snd_rawmidi_buffer_ref(runtime);
 	while (count > 0 && runtime->avail > 0) {
 		count1 = runtime->buffer_size - runtime->appl_ptr;
 		if (count1 > count)
@@ -1299,6 +1321,7 @@ static long snd_rawmidi_kernel_write1(struct snd_rawmidi_substream *substream,
 	}
       __end:
 	count1 = runtime->avail < runtime->buffer_size;
+	snd_rawmidi_buffer_unref(runtime);
 	spin_unlock_irqrestore(&runtime->lock, flags);
 	if (count1)
 		snd_rawmidi_output_trigger(substream, 1);
diff --git a/sound/core/seq/oss/seq_oss.c b/sound/core/seq/oss/seq_oss.c
index 17f913657304..c8b9c0b315d8 100644
--- a/sound/core/seq/oss/seq_oss.c
+++ b/sound/core/seq/oss/seq_oss.c
@@ -168,10 +168,16 @@ static long
 odev_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	struct seq_oss_devinfo *dp;
+	long rc;
+
 	dp = file->private_data;
 	if (snd_BUG_ON(!dp))
 		return -ENXIO;
-	return snd_seq_oss_ioctl(dp, cmd, arg);
+
+	mutex_lock(&register_mutex);
+	rc = snd_seq_oss_ioctl(dp, cmd, arg);
+	mutex_unlock(&register_mutex);
+	return rc;
 }
 
 #ifdef CONFIG_COMPAT
diff --git a/sound/core/seq/oss/seq_oss_midi.c b/sound/core/seq/oss/seq_oss_midi.c
index a88c235b2ea3..2ddfe2226651 100644
--- a/sound/core/seq/oss/seq_oss_midi.c
+++ b/sound/core/seq/oss/seq_oss_midi.c
@@ -602,6 +602,7 @@ send_midi_event(struct seq_oss_devinfo *dp, struct snd_seq_event *ev, struct seq
 		len = snd_seq_oss_timer_start(dp->timer);
 	if (ev->type == SNDRV_SEQ_EVENT_SYSEX) {
 		snd_seq_oss_readq_sysex(dp->readq, mdev->seq_device, ev);
+		snd_midi_event_reset_decode(mdev->coder);
 	} else {
 		len = snd_midi_event_decode(mdev->coder, msg, sizeof(msg), ev);
 		if (len > 0)
diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
index 6d9592f0ae1d..cc93157fa950 100644
--- a/sound/core/seq/seq_clientmgr.c
+++ b/sound/core/seq/seq_clientmgr.c
@@ -580,7 +580,7 @@ static int update_timestamp_of_queue(struct snd_seq_event *event,
 	event->queue = queue;
 	event->flags &= ~SNDRV_SEQ_TIME_STAMP_MASK;
 	if (real_time) {
-		event->time.time = snd_seq_timer_get_cur_time(q->timer);
+		event->time.time = snd_seq_timer_get_cur_time(q->timer, true);
 		event->flags |= SNDRV_SEQ_TIME_STAMP_REAL;
 	} else {
 		event->time.tick = snd_seq_timer_get_cur_tick(q->timer);
@@ -1659,7 +1659,7 @@ static int snd_seq_ioctl_get_queue_status(struct snd_seq_client *client,
 	tmr = queue->timer;
 	status->events = queue->tickq->cells + queue->timeq->cells;
 
-	status->time = snd_seq_timer_get_cur_time(tmr);
+	status->time = snd_seq_timer_get_cur_time(tmr, true);
 	status->tick = snd_seq_timer_get_cur_tick(tmr);
 
 	status->running = tmr->running;
diff --git a/sound/core/seq/seq_queue.c b/sound/core/seq/seq_queue.c
index caf68bf42f13..71a6ea62c3be 100644
--- a/sound/core/seq/seq_queue.c
+++ b/sound/core/seq/seq_queue.c
@@ -238,6 +238,8 @@ void snd_seq_check_queue(struct snd_seq_queue *q, int atomic, int hop)
 {
 	unsigned long flags;
 	struct snd_seq_event_cell *cell;
+	snd_seq_tick_time_t cur_tick;
+	snd_seq_real_time_t cur_time;
 
 	if (q == NULL)
 		return;
@@ -254,17 +256,18 @@ void snd_seq_check_queue(struct snd_seq_queue *q, int atomic, int hop)
 
       __again:
 	/* Process tick queue... */
+	cur_tick = snd_seq_timer_get_cur_tick(q->timer);
 	for (;;) {
-		cell = snd_seq_prioq_cell_out(q->tickq,
-					      &q->timer->tick.cur_tick);
+		cell = snd_seq_prioq_cell_out(q->tickq, &cur_tick);
 		if (!cell)
 			break;
 		snd_seq_dispatch_event(cell, atomic, hop);
 	}
 
 	/* Process time queue... */
+	cur_time = snd_seq_timer_get_cur_time(q->timer, false);
 	for (;;) {
-		cell = snd_seq_prioq_cell_out(q->timeq, &q->timer->cur_time);
+		cell = snd_seq_prioq_cell_out(q->timeq, &cur_time);
 		if (!cell)
 			break;
 		snd_seq_dispatch_event(cell, atomic, hop);
@@ -392,6 +395,7 @@ int snd_seq_queue_check_access(int queueid, int client)
 int snd_seq_queue_set_owner(int queueid, int client, int locked)
 {
 	struct snd_seq_queue *q = queueptr(queueid);
+	unsigned long flags;
 
 	if (q == NULL)
 		return -EINVAL;
@@ -401,8 +405,10 @@ int snd_seq_queue_set_owner(int queueid, int client, int locked)
 		return -EPERM;
 	}
 
+	spin_lock_irqsave(&q->owner_lock, flags);
 	q->locked = locked ? 1 : 0;
 	q->owner = client;
+	spin_unlock_irqrestore(&q->owner_lock, flags);
 	queue_access_unlock(q);
 	queuefree(q);
 
@@ -539,15 +545,17 @@ void snd_seq_queue_client_termination(int client)
 	unsigned long flags;
 	int i;
 	struct snd_seq_queue *q;
+	bool matched;
 
 	for (i = 0; i < SNDRV_SEQ_MAX_QUEUES; i++) {
 		if ((q = queueptr(i)) == NULL)
 			continue;
 		spin_lock_irqsave(&q->owner_lock, flags);
-		if (q->owner == client)
+		matched = (q->owner == client);
+		if (matched)
 			q->klocked = 1;
 		spin_unlock_irqrestore(&q->owner_lock, flags);
-		if (q->owner == client) {
+		if (matched) {
 			if (q->timer->running)
 				snd_seq_timer_stop(q->timer);
 			snd_seq_timer_reset(q->timer);
@@ -739,6 +747,8 @@ void snd_seq_info_queues_read(struct snd_info_entry *entry,
 	int i, bpm;
 	struct snd_seq_queue *q;
 	struct snd_seq_timer *tmr;
+	bool locked;
+	int owner;
 
 	for (i = 0; i < SNDRV_SEQ_MAX_QUEUES; i++) {
 		if ((q = queueptr(i)) == NULL)
@@ -750,9 +760,14 @@ void snd_seq_info_queues_read(struct snd_info_entry *entry,
 		else
 			bpm = 0;
 
+		spin_lock_irq(&q->owner_lock);
+		locked = q->locked;
+		owner = q->owner;
+		spin_unlock_irq(&q->owner_lock);
+
 		snd_iprintf(buffer, "queue %d: [%s]\n", q->queue, q->name);
-		snd_iprintf(buffer, "owned by client    : %d\n", q->owner);
-		snd_iprintf(buffer, "lock status        : %s\n", q->locked ? "Locked" : "Free");
+		snd_iprintf(buffer, "owned by client    : %d\n", owner);
+		snd_iprintf(buffer, "lock status        : %s\n", locked ? "Locked" : "Free");
 		snd_iprintf(buffer, "queued time events : %d\n", snd_seq_prioq_avail(q->timeq));
 		snd_iprintf(buffer, "queued tick events : %d\n", snd_seq_prioq_avail(q->tickq));
 		snd_iprintf(buffer, "timer state        : %s\n", tmr->running ? "Running" : "Stopped");
diff --git a/sound/core/seq/seq_timer.c b/sound/core/seq/seq_timer.c
index 161f3170bd7e..0b43fc5fe349 100644
--- a/sound/core/seq/seq_timer.c
+++ b/sound/core/seq/seq_timer.c
@@ -422,14 +422,15 @@ int snd_seq_timer_continue(struct snd_seq_timer *tmr)
 }
 
 /* return current 'real' time. use timeofday() to get better granularity. */
-snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr)
+snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr,
+					       bool adjust_ktime)
 {
 	snd_seq_real_time_t cur_time;
 	unsigned long flags;
 
 	spin_lock_irqsave(&tmr->lock, flags);
 	cur_time = tmr->cur_time;
-	if (tmr->running) { 
+	if (adjust_ktime && tmr->running) {
 		struct timespec64 tm;
 
 		ktime_get_ts64(&tm);
@@ -446,7 +447,13 @@ snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr)
  high PPQ values) */
 snd_seq_tick_time_t snd_seq_timer_get_cur_tick(struct snd_seq_timer *tmr)
 {
-	return tmr->tick.cur_tick;
+	snd_seq_tick_time_t cur_tick;
+	unsigned long flags;
+
+	spin_lock_irqsave(&tmr->lock, flags);
+	cur_tick = tmr->tick.cur_tick;
+	spin_unlock_irqrestore(&tmr->lock, flags);
+	return cur_tick;
 }
 
 
@@ -465,15 +472,19 @@ void snd_seq_info_timer_read(struct snd_info_entry *entry,
 		q = queueptr(idx);
 		if (q == NULL)
 			continue;
-		if ((tmr = q->timer) == NULL ||
-		    (ti = tmr->timeri) == NULL) {
-			queuefree(q);
-			continue;
-		}
+		mutex_lock(&q->timer_mutex);
+		tmr = q->timer;
+		if (!tmr)
+			goto unlock;
+		ti = tmr->timeri;
+		if (!ti)
+			goto unlock;
 		snd_iprintf(buffer, "Timer for queue %i : %s\n", q->queue, ti->timer->name);
 		resolution = snd_timer_resolution(ti) * tmr->ticks;
 		snd_iprintf(buffer, "  Period time : %lu.%09lu\n", resolution / 1000000000, resolution % 1000000000);
 		snd_iprintf(buffer, "  Skew : %u / %u\n", tmr->skew, tmr->skew_base);
+unlock:
+		mutex_unlock(&q->timer_mutex);
 		queuefree(q);
  	}
 }
diff --git a/sound/core/seq/seq_timer.h b/sound/core/seq/seq_timer.h
index 66c3e344eae3..4bec57df8158 100644
--- a/sound/core/seq/seq_timer.h
+++ b/sound/core/seq/seq_timer.h
@@ -120,7 +120,8 @@ int snd_seq_timer_set_tempo_ppq(struct snd_seq_timer *tmr, int tempo, int ppq);
 int snd_seq_timer_set_position_tick(struct snd_seq_timer *tmr, snd_seq_tick_time_t position);
 int snd_seq_timer_set_position_time(struct snd_seq_timer *tmr, snd_seq_real_time_t position);
 int snd_seq_timer_set_skew(struct snd_seq_timer *tmr, unsigned int skew, unsigned int base);
-snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr);
+snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr,
+					       bool adjust_ktime);
 snd_seq_tick_time_t snd_seq_timer_get_cur_tick(struct snd_seq_timer *tmr);
 
 extern int seq_default_timer_class;
diff --git a/sound/core/seq/seq_virmidi.c b/sound/core/seq/seq_virmidi.c
index 626d87c1539b..77d7037d1476 100644
--- a/sound/core/seq/seq_virmidi.c
+++ b/sound/core/seq/seq_virmidi.c
@@ -81,6 +81,7 @@ static int snd_virmidi_dev_receive_event(struct snd_virmidi_dev *rdev,
 			if ((ev->flags & SNDRV_SEQ_EVENT_LENGTH_MASK) != SNDRV_SEQ_EVENT_LENGTH_VARIABLE)
 				continue;
 			snd_seq_dump_var_event(ev, (snd_seq_dump_func_t)snd_rawmidi_receive, vmidi->substream);
+			snd_midi_event_reset_decode(vmidi->parser);
 		} else {
 			len = snd_midi_event_decode(vmidi->parser, msg, sizeof(msg), ev);
 			if (len > 0)
diff --git a/sound/drivers/dummy.c b/sound/drivers/dummy.c
index aee7c04d49e5..b61ba0321a72 100644
--- a/sound/drivers/dummy.c
+++ b/sound/drivers/dummy.c
@@ -915,7 +915,7 @@ static void print_formats(struct snd_dummy *dummy,
 {
 	int i;
 
-	for (i = 0; i < SNDRV_PCM_FORMAT_LAST; i++) {
+	for (i = 0; i <= SNDRV_PCM_FORMAT_LAST; i++) {
 		if (dummy->pcm_hw.formats & (1ULL << i))
 			snd_iprintf(buffer, " %s", snd_pcm_format_name(i));
 	}
diff --git a/sound/drivers/opl3/opl3_synth.c b/sound/drivers/opl3/opl3_synth.c
index e69a4ef0d6bd..08c10ac9d6c8 100644
--- a/sound/drivers/opl3/opl3_synth.c
+++ b/sound/drivers/opl3/opl3_synth.c
@@ -91,6 +91,8 @@ int snd_opl3_ioctl(struct snd_hwdep * hw, struct file *file,
 		{
 			struct snd_dm_fm_info info;
 
+			memset(&info, 0, sizeof(info));
+
 			info.fm_mode = opl3->fm_mode;
 			info.rhythm = opl3->rhythm;
 			if (copy_to_user(argp, &info, sizeof(struct snd_dm_fm_info)))
diff --git a/sound/firewire/dice/dice-extension.c b/sound/firewire/dice/dice-extension.c
index a63fcbc875ad..02f4a8318e38 100644
--- a/sound/firewire/dice/dice-extension.c
+++ b/sound/firewire/dice/dice-extension.c
@@ -159,8 +159,11 @@ int snd_dice_detect_extension_formats(struct snd_dice *dice)
 		int j;
 
 		for (j = i + 1; j < 9; ++j) {
-			if (pointers[i * 2] == pointers[j * 2])
+			if (pointers[i * 2] == pointers[j * 2]) {
+				// Fallback to limited functionality.
+				err = -ENXIO;
 				goto end;
+			}
 		}
 	}
 
diff --git a/sound/firewire/motu/motu-proc.c b/sound/firewire/motu/motu-proc.c
index ea46fb4c1b5a..126a7bd187bb 100644
--- a/sound/firewire/motu/motu-proc.c
+++ b/sound/firewire/motu/motu-proc.c
@@ -16,7 +16,7 @@ static const char *const clock_names[] = {
 	[SND_MOTU_CLOCK_SOURCE_SPDIF_ON_OPT] = "S/PDIF on optical interface",
 	[SND_MOTU_CLOCK_SOURCE_SPDIF_ON_OPT_A] = "S/PDIF on optical interface A",
 	[SND_MOTU_CLOCK_SOURCE_SPDIF_ON_OPT_B] = "S/PDIF on optical interface B",
-	[SND_MOTU_CLOCK_SOURCE_SPDIF_ON_COAX] = "S/PCIF on coaxial interface",
+	[SND_MOTU_CLOCK_SOURCE_SPDIF_ON_COAX] = "S/PDIF on coaxial interface",
 	[SND_MOTU_CLOCK_SOURCE_AESEBU_ON_XLR] = "AESEBU on XLR interface",
 	[SND_MOTU_CLOCK_SOURCE_WORD_ON_BNC] = "Word clock on BNC interface",
 };
diff --git a/sound/firewire/tascam/amdtp-tascam.c b/sound/firewire/tascam/amdtp-tascam.c
index d9d20ef22f5b..9d7263aed2b4 100644
--- a/sound/firewire/tascam/amdtp-tascam.c
+++ b/sound/firewire/tascam/amdtp-tascam.c
@@ -147,14 +147,15 @@ static void read_status_messages(struct amdtp_stream *s,
 			if ((before ^ after) & mask) {
 				struct snd_firewire_tascam_change *entry =
 						&tscm->queue[tscm->push_pos];
+				unsigned long flag;
 
-				spin_lock_irq(&tscm->lock);
+				spin_lock_irqsave(&tscm->lock, flag);
 				entry->index = index;
 				entry->before = before;
 				entry->after = after;
 				if (++tscm->push_pos >= SND_TSCM_QUEUE_COUNT)
 					tscm->push_pos = 0;
-				spin_unlock_irq(&tscm->lock);
+				spin_unlock_irqrestore(&tscm->lock, flag);
 
 				wake_up(&tscm->hwdep_wait);
 			}
diff --git a/sound/hda/ext/hdac_ext_controller.c b/sound/hda/ext/hdac_ext_controller.c
index 211ca85acd8c..a70f6f86903d 100644
--- a/sound/hda/ext/hdac_ext_controller.c
+++ b/sound/hda/ext/hdac_ext_controller.c
@@ -254,6 +254,7 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_link_power_down_all);
 int snd_hdac_ext_bus_link_get(struct hdac_bus *bus,
 				struct hdac_ext_link *link)
 {
+	unsigned long codec_mask;
 	int ret = 0;
 
 	mutex_lock(&bus->lock);
@@ -275,9 +276,11 @@ int snd_hdac_ext_bus_link_get(struct hdac_bus *bus,
 		 *  HDA spec section 4.3 - Codec Discovery
 		 */
 		udelay(521);
-		bus->codec_mask = snd_hdac_chip_readw(bus, STATESTS);
-		dev_dbg(bus->dev, "codec_mask = 0x%lx\n", bus->codec_mask);
-		snd_hdac_chip_writew(bus, STATESTS, bus->codec_mask);
+		codec_mask = snd_hdac_chip_readw(bus, STATESTS);
+		dev_dbg(bus->dev, "codec_mask = 0x%lx\n", codec_mask);
+		snd_hdac_chip_writew(bus, STATESTS, codec_mask);
+		if (!bus->codec_mask)
+			bus->codec_mask = codec_mask;
 	}
 
 	mutex_unlock(&bus->lock);
diff --git a/sound/hda/hdac_device.c b/sound/hda/hdac_device.c
index 3842f9d34b7c..c2386b292153 100644
--- a/sound/hda/hdac_device.c
+++ b/sound/hda/hdac_device.c
@@ -57,6 +57,7 @@ int snd_hdac_device_init(struct hdac_device *codec, struct hdac_bus *bus,
 	codec->addr = addr;
 	codec->type = HDA_DEV_CORE;
 	mutex_init(&codec->widget_lock);
+	mutex_init(&codec->regmap_lock);
 	pm_runtime_set_active(&codec->dev);
 	pm_runtime_get_noresume(&codec->dev);
 	atomic_set(&codec->in_pm, 0);
diff --git a/sound/hda/hdac_regmap.c b/sound/hda/hdac_regmap.c
index f399a1552e73..f064178f7cdc 100644
--- a/sound/hda/hdac_regmap.c
+++ b/sound/hda/hdac_regmap.c
@@ -362,6 +362,7 @@ static const struct regmap_config hda_regmap_cfg = {
 	.reg_write = hda_reg_write,
 	.use_single_read = true,
 	.use_single_write = true,
+	.disable_locking = true,
 };
 
 /**
@@ -424,12 +425,29 @@ EXPORT_SYMBOL_GPL(snd_hdac_regmap_add_vendor_verb);
 static int reg_raw_write(struct hdac_device *codec, unsigned int reg,
 			 unsigned int val)
 {
+	int err;
+
+	mutex_lock(&codec->regmap_lock);
 	if (!codec->regmap)
-		return hda_reg_write(codec, reg, val);
+		err = hda_reg_write(codec, reg, val);
 	else
-		return regmap_write(codec->regmap, reg, val);
+		err = regmap_write(codec->regmap, reg, val);
+	mutex_unlock(&codec->regmap_lock);
+	return err;
 }
 
+/* a helper macro to call @func_call; retry with power-up if failed */
+#define CALL_RAW_FUNC(codec, func_call)				\
+	({							\
+		int _err = func_call;				\
+		if (_err == -EAGAIN) {				\
+			_err = snd_hdac_power_up_pm(codec);	\
+			if (_err >= 0)				\
+				_err = func_call;		\
+			snd_hdac_power_down_pm(codec);		\
+		}						\
+		_err;})
+
 /**
  * snd_hdac_regmap_write_raw - write a pseudo register with power mgmt
  * @codec: the codec object
@@ -441,42 +459,29 @@ static int reg_raw_write(struct hdac_device *codec, unsigned int reg,
 int snd_hdac_regmap_write_raw(struct hdac_device *codec, unsigned int reg,
 			      unsigned int val)
 {
-	int err;
-
-	err = reg_raw_write(codec, reg, val);
-	if (err == -EAGAIN) {
-		err = snd_hdac_power_up_pm(codec);
-		if (err >= 0)
-			err = reg_raw_write(codec, reg, val);
-		snd_hdac_power_down_pm(codec);
-	}
-	return err;
+	return CALL_RAW_FUNC(codec, reg_raw_write(codec, reg, val));
 }
 EXPORT_SYMBOL_GPL(snd_hdac_regmap_write_raw);
 
 static int reg_raw_read(struct hdac_device *codec, unsigned int reg,
 			unsigned int *val, bool uncached)
 {
+	int err;
+
+	mutex_lock(&codec->regmap_lock);
 	if (uncached || !codec->regmap)
-		return hda_reg_read(codec, reg, val);
+		err = hda_reg_read(codec, reg, val);
 	else
-		return regmap_read(codec->regmap, reg, val);
+		err = regmap_read(codec->regmap, reg, val);
+	mutex_unlock(&codec->regmap_lock);
+	return err;
 }
 
 static int __snd_hdac_regmap_read_raw(struct hdac_device *codec,
 				      unsigned int reg, unsigned int *val,
 				      bool uncached)
 {
-	int err;
-
-	err = reg_raw_read(codec, reg, val, uncached);
-	if (err == -EAGAIN) {
-		err = snd_hdac_power_up_pm(codec);
-		if (err >= 0)
-			err = reg_raw_read(codec, reg, val, uncached);
-		snd_hdac_power_down_pm(codec);
-	}
-	return err;
+	return CALL_RAW_FUNC(codec, reg_raw_read(codec, reg, val, uncached));
 }
 
 /**
@@ -503,6 +508,35 @@ int snd_hdac_regmap_read_raw_uncached(struct hdac_device *codec,
 	return __snd_hdac_regmap_read_raw(codec, reg, val, true);
 }
 
+static int reg_raw_update(struct hdac_device *codec, unsigned int reg,
+			  unsigned int mask, unsigned int val)
+{
+	unsigned int orig;
+	bool change;
+	int err;
+
+	mutex_lock(&codec->regmap_lock);
+	if (codec->regmap) {
+		err = regmap_update_bits_check(codec->regmap, reg, mask, val,
+					       &change);
+		if (!err)
+			err = change ? 1 : 0;
+	} else {
+		err = hda_reg_read(codec, reg, &orig);
+		if (!err) {
+			val &= mask;
+			val |= orig & ~mask;
+			if (val != orig) {
+				err = hda_reg_write(codec, reg, val);
+				if (!err)
+					err = 1;
+			}
+		}
+	}
+	mutex_unlock(&codec->regmap_lock);
+	return err;
+}
+
 /**
  * snd_hdac_regmap_update_raw - update a pseudo register with power mgmt
  * @codec: the codec object
@@ -515,19 +549,57 @@ int snd_hdac_regmap_read_raw_uncached(struct hdac_device *codec,
 int snd_hdac_regmap_update_raw(struct hdac_device *codec, unsigned int reg,
 			       unsigned int mask, unsigned int val)
 {
+	return CALL_RAW_FUNC(codec, reg_raw_update(codec, reg, mask, val));
+}
+EXPORT_SYMBOL_GPL(snd_hdac_regmap_update_raw);
+
+static int reg_raw_update_once(struct hdac_device *codec, unsigned int reg,
+			       unsigned int mask, unsigned int val)
+{
 	unsigned int orig;
 	int err;
 
-	val &= mask;
-	err = snd_hdac_regmap_read_raw(codec, reg, &orig);
-	if (err < 0)
-		return err;
-	val |= orig & ~mask;
-	if (val == orig)
-		return 0;
-	err = snd_hdac_regmap_write_raw(codec, reg, val);
+	if (!codec->regmap)
+		return reg_raw_update(codec, reg, mask, val);
+
+	mutex_lock(&codec->regmap_lock);
+	regcache_cache_only(codec->regmap, true);
+	err = regmap_read(codec->regmap, reg, &orig);
+	regcache_cache_only(codec->regmap, false);
 	if (err < 0)
-		return err;
-	return 1;
+		err = regmap_update_bits(codec->regmap, reg, mask, val);
+	mutex_unlock(&codec->regmap_lock);
+	return err;
 }
-EXPORT_SYMBOL_GPL(snd_hdac_regmap_update_raw);
+
+/**
+ * snd_hdac_regmap_update_raw_once - initialize the register value only once
+ * @codec: the codec object
+ * @reg: pseudo register
+ * @mask: bit mask to update
+ * @val: value to update
+ *
+ * Performs the update of the register bits only once when the register
+ * hasn't been initialized yet.  Used in HD-audio legacy driver.
+ * Returns zero if successful or a negative error code
+ */
+int snd_hdac_regmap_update_raw_once(struct hdac_device *codec, unsigned int reg,
+				    unsigned int mask, unsigned int val)
+{
+	return CALL_RAW_FUNC(codec, reg_raw_update_once(codec, reg, mask, val));
+}
+EXPORT_SYMBOL_GPL(snd_hdac_regmap_update_raw_once);
+
+/**
+ * snd_hdac_regmap_sync - sync out the cached values for PM resume
+ * @codec: the codec object
+ */
+void snd_hdac_regmap_sync(struct hdac_device *codec)
+{
+	if (codec->regmap) {
+		mutex_lock(&codec->regmap_lock);
+		regcache_sync(codec->regmap);
+		mutex_unlock(&codec->regmap_lock);
+	}
+}
+EXPORT_SYMBOL_GPL(snd_hdac_regmap_sync);
diff --git a/sound/hda/hdmi_chmap.c b/sound/hda/hdmi_chmap.c
index 886cb7811bd6..2efee794cac6 100644
--- a/sound/hda/hdmi_chmap.c
+++ b/sound/hda/hdmi_chmap.c
@@ -250,7 +250,7 @@ void snd_hdac_print_channel_allocation(int spk_alloc, char *buf, int buflen)
 
 	for (i = 0, j = 0; i < ARRAY_SIZE(cea_speaker_allocation_names); i++) {
 		if (spk_alloc & (1 << i))
-			j += snprintf(buf + j, buflen - j,  " %s",
+			j += scnprintf(buf + j, buflen - j,  " %s",
 					cea_speaker_allocation_names[i]);
 	}
 	buf[j] = '\0';	/* necessary when j == 0 */
diff --git a/sound/isa/cs423x/cs4236.c b/sound/isa/cs423x/cs4236.c
index 78dd213589b4..fa3c39cff5f8 100644
--- a/sound/isa/cs423x/cs4236.c
+++ b/sound/isa/cs423x/cs4236.c
@@ -278,7 +278,8 @@ static int snd_cs423x_pnp_init_mpu(int dev, struct pnp_dev *pdev)
 	} else {
 		mpu_port[dev] = pnp_port_start(pdev, 0);
 		if (mpu_irq[dev] >= 0 &&
-		    pnp_irq_valid(pdev, 0) && pnp_irq(pdev, 0) >= 0) {
+		    pnp_irq_valid(pdev, 0) &&
+		    pnp_irq(pdev, 0) != (resource_size_t)-1) {
 			mpu_irq[dev] = pnp_irq(pdev, 0);
 		} else {
 			mpu_irq[dev] = -1;	/* disable interrupt */
diff --git a/sound/isa/es1688/es1688.c b/sound/isa/es1688/es1688.c
index 9be89377171b..b4e9b0de3b42 100644
--- a/sound/isa/es1688/es1688.c
+++ b/sound/isa/es1688/es1688.c
@@ -267,8 +267,10 @@ static int snd_es968_pnp_detect(struct pnp_card_link *pcard,
 		return error;
 	}
 	error = snd_es1688_probe(card, dev);
-	if (error < 0)
+	if (error < 0) {
+		snd_card_free(card);
 		return error;
+	}
 	pnp_set_card_drvdata(pcard, card);
 	snd_es968_pnp_is_probed = 1;
 	return 0;
diff --git a/sound/isa/opti9xx/miro.c b/sound/isa/opti9xx/miro.c
index 0458934de1c7..9ca5c83de8a7 100644
--- a/sound/isa/opti9xx/miro.c
+++ b/sound/isa/opti9xx/miro.c
@@ -867,10 +867,13 @@ static void snd_miro_write(struct snd_miro *chip, unsigned char reg,
 	spin_unlock_irqrestore(&chip->lock, flags);
 }
 
+static inline void snd_miro_write_mask(struct snd_miro *chip,
+		unsigned char reg, unsigned char value, unsigned char mask)
+{
+	unsigned char oldval = snd_miro_read(chip, reg);
 
-#define snd_miro_write_mask(chip, reg, value, mask)	\
-	snd_miro_write(chip, reg,			\
-		(snd_miro_read(chip, reg) & ~(mask)) | ((value) & (mask)))
+	snd_miro_write(chip, reg, (oldval & ~mask) | (value & mask));
+}
 
 /*
  *  Proc Interface
diff --git a/sound/isa/opti9xx/opti92x-ad1848.c b/sound/isa/opti9xx/opti92x-ad1848.c
index fb36bb5d55df..fb87eedc8121 100644
--- a/sound/isa/opti9xx/opti92x-ad1848.c
+++ b/sound/isa/opti9xx/opti92x-ad1848.c
@@ -317,10 +317,13 @@ static void snd_opti9xx_write(struct snd_opti9xx *chip, unsigned char reg,
 }
 
 
-#define snd_opti9xx_write_mask(chip, reg, value, mask)	\
-	snd_opti9xx_write(chip, reg,			\
-		(snd_opti9xx_read(chip, reg) & ~(mask)) | ((value) & (mask)))
+static inline void snd_opti9xx_write_mask(struct snd_opti9xx *chip,
+		unsigned char reg, unsigned char value, unsigned char mask)
+{
+	unsigned char oldval = snd_opti9xx_read(chip, reg);
 
+	snd_opti9xx_write(chip, reg, (oldval & ~mask) | (value & mask));
+}
 
 static int snd_opti9xx_configure(struct snd_opti9xx *chip,
 					   long port,
diff --git a/sound/isa/wavefront/wavefront_synth.c b/sound/isa/wavefront/wavefront_synth.c
index aec1c46e6697..1dfb2b8e6fd6 100644
--- a/sound/isa/wavefront/wavefront_synth.c
+++ b/sound/isa/wavefront/wavefront_synth.c
@@ -1172,7 +1172,10 @@ wavefront_send_alias (snd_wavefront_t *dev, wavefront_patch_info *header)
 				      "alias for %d\n",
 				      header->number,
 				      header->hdr.a.OriginalSample);
-    
+
+	if (header->number >= WF_MAX_SAMPLE)
+		return -EINVAL;
+
 	munge_int32 (header->number, &alias_hdr[0], 2);
 	munge_int32 (header->hdr.a.OriginalSample, &alias_hdr[2], 2);
 	munge_int32 (*((unsigned int *)&header->hdr.a.sampleStartOffset),
@@ -1203,6 +1206,9 @@ wavefront_send_multisample (snd_wavefront_t *dev, wavefront_patch_info *header)
 	int num_samples;
 	unsigned char *msample_hdr;
 
+	if (header->number >= WF_MAX_SAMPLE)
+		return -EINVAL;
+
 	msample_hdr = kmalloc(WF_MSAMPLE_BYTES, GFP_KERNEL);
 	if (! msample_hdr)
 		return -ENOMEM;
diff --git a/sound/pci/echoaudio/echoaudio.c b/sound/pci/echoaudio/echoaudio.c
index b612a536a5a1..0e15d497946a 100644
--- a/sound/pci/echoaudio/echoaudio.c
+++ b/sound/pci/echoaudio/echoaudio.c
@@ -2199,7 +2199,6 @@ static int snd_echo_resume(struct device *dev)
 	if (err < 0) {
 		kfree(commpage_bak);
 		dev_err(dev, "resume init_hw err=%d\n", err);
-		snd_echo_free(chip);
 		return err;
 	}
 
@@ -2226,7 +2225,6 @@ static int snd_echo_resume(struct device *dev)
 	if (request_irq(pci->irq, snd_echo_interrupt, IRQF_SHARED,
 			KBUILD_MODNAME, chip)) {
 		dev_err(chip->card->dev, "cannot grab irq\n");
-		snd_echo_free(chip);
 		return -EBUSY;
 	}
 	chip->irq = pci->irq;
diff --git a/sound/pci/hda/hda_auto_parser.c b/sound/pci/hda/hda_auto_parser.c
index 18e6546b4467..6465839aa459 100644
--- a/sound/pci/hda/hda_auto_parser.c
+++ b/sound/pci/hda/hda_auto_parser.c
@@ -72,6 +72,12 @@ static int compare_input_type(const void *ap, const void *bp)
 	if (a->type != b->type)
 		return (int)(a->type - b->type);
 
+	/* If has both hs_mic and hp_mic, pick the hs_mic ahead of hp_mic. */
+	if (a->is_headset_mic && b->is_headphone_mic)
+		return -1; /* don't swap */
+	else if (a->is_headphone_mic && b->is_headset_mic)
+		return 1; /* swap */
+
 	/* In case one has boost and the other one has not,
 	   pick the one with boost first. */
 	return (int)(b->has_boost_on_pin - a->has_boost_on_pin);
diff --git a/sound/pci/hda/hda_beep.c b/sound/pci/hda/hda_beep.c
index b7d9160ed868..c6e1e03a5e4d 100644
--- a/sound/pci/hda/hda_beep.c
+++ b/sound/pci/hda/hda_beep.c
@@ -290,8 +290,12 @@ int snd_hda_mixer_amp_switch_get_beep(struct snd_kcontrol *kcontrol,
 {
 	struct hda_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct hda_beep *beep = codec->beep;
+	int chs = get_amp_channels(kcontrol);
+
 	if (beep && (!beep->enabled || !ctl_has_mute(kcontrol))) {
-		ucontrol->value.integer.value[0] =
+		if (chs & 1)
+			ucontrol->value.integer.value[0] = beep->enabled;
+		if (chs & 2)
 			ucontrol->value.integer.value[1] = beep->enabled;
 		return 0;
 	}
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index c2a6554c9877..0922a8bb32d0 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -1267,6 +1267,18 @@ int snd_hda_override_amp_caps(struct hda_codec *codec, hda_nid_t nid, int dir,
 }
 EXPORT_SYMBOL_GPL(snd_hda_override_amp_caps);
 
+static unsigned int encode_amp(struct hda_codec *codec, hda_nid_t nid,
+			       int ch, int dir, int idx)
+{
+	unsigned int cmd = snd_hdac_regmap_encode_amp(nid, ch, dir, idx);
+
+	/* enable fake mute if no h/w mute but min=mute */
+	if ((query_amp_caps(codec, nid, dir) &
+	     (AC_AMPCAP_MUTE | AC_AMPCAP_MIN_MUTE)) == AC_AMPCAP_MIN_MUTE)
+		cmd |= AC_AMP_FAKE_MUTE;
+	return cmd;
+}
+
 /**
  * snd_hda_codec_amp_update - update the AMP mono value
  * @codec: HD-audio codec
@@ -1282,12 +1294,8 @@ EXPORT_SYMBOL_GPL(snd_hda_override_amp_caps);
 int snd_hda_codec_amp_update(struct hda_codec *codec, hda_nid_t nid,
 			     int ch, int dir, int idx, int mask, int val)
 {
-	unsigned int cmd = snd_hdac_regmap_encode_amp(nid, ch, dir, idx);
+	unsigned int cmd = encode_amp(codec, nid, ch, dir, idx);
 
-	/* enable fake mute if no h/w mute but min=mute */
-	if ((query_amp_caps(codec, nid, dir) &
-	     (AC_AMPCAP_MUTE | AC_AMPCAP_MIN_MUTE)) == AC_AMPCAP_MIN_MUTE)
-		cmd |= AC_AMP_FAKE_MUTE;
 	return snd_hdac_regmap_update_raw(&codec->core, cmd, mask, val);
 }
 EXPORT_SYMBOL_GPL(snd_hda_codec_amp_update);
@@ -1335,16 +1343,11 @@ EXPORT_SYMBOL_GPL(snd_hda_codec_amp_stereo);
 int snd_hda_codec_amp_init(struct hda_codec *codec, hda_nid_t nid, int ch,
 			   int dir, int idx, int mask, int val)
 {
-	int orig;
+	unsigned int cmd = encode_amp(codec, nid, ch, dir, idx);
 
 	if (!codec->core.regmap)
 		return -EINVAL;
-	regcache_cache_only(codec->core.regmap, true);
-	orig = snd_hda_codec_amp_read(codec, nid, ch, dir, idx);
-	regcache_cache_only(codec->core.regmap, false);
-	if (orig >= 0)
-		return 0;
-	return snd_hda_codec_amp_update(codec, nid, ch, dir, idx, mask, val);
+	return snd_hdac_regmap_update_raw_once(&codec->core, cmd, mask, val);
 }
 EXPORT_SYMBOL_GPL(snd_hda_codec_amp_init);
 
@@ -2905,8 +2908,7 @@ static void hda_call_codec_resume(struct hda_codec *codec)
 	else {
 		if (codec->patch_ops.init)
 			codec->patch_ops.init(codec);
-		if (codec->core.regmap)
-			regcache_sync(codec->core.regmap);
+		snd_hda_regmap_sync(codec);
 	}
 
 	if (codec->jackpoll_interval)
@@ -2922,6 +2924,10 @@ static int hda_codec_runtime_suspend(struct device *dev)
 	struct hda_codec *codec = dev_to_hda_codec(dev);
 	unsigned int state;
 
+	/* Nothing to do if card registration fails and the component driver never probes */
+	if (!codec->card)
+		return 0;
+
 	cancel_delayed_work_sync(&codec->jackpoll_work);
 	state = hda_call_codec_suspend(codec);
 	if (codec->link_down_at_suspend ||
@@ -2936,6 +2942,10 @@ static int hda_codec_runtime_resume(struct device *dev)
 {
 	struct hda_codec *codec = dev_to_hda_codec(dev);
 
+	/* Nothing to do if card registration fails and the component driver never probes */
+	if (!codec->card)
+		return 0;
+
 	codec_display_power(codec, true);
 	snd_hdac_codec_link_up(&codec->core);
 	hda_call_codec_resume(codec);
@@ -4019,7 +4029,7 @@ void snd_print_pcm_bits(int pcm, char *buf, int buflen)
 
 	for (i = 0, j = 0; i < ARRAY_SIZE(bits); i++)
 		if (pcm & (AC_SUPPCM_BITS_8 << i))
-			j += snprintf(buf + j, buflen - j,  " %d", bits[i]);
+			j += scnprintf(buf + j, buflen - j,  " %d", bits[i]);
 
 	buf[j] = '\0'; /* necessary when j == 0 */
 }
diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c
index 1158bcf55148..a25a68ab9abb 100644
--- a/sound/pci/hda/hda_controller.c
+++ b/sound/pci/hda/hda_controller.c
@@ -875,7 +875,7 @@ static int azx_rirb_get_response(struct hdac_bus *bus, unsigned int addr,
 		return -EAGAIN; /* give a chance to retry */
 	}
 
-	dev_WARN(chip->card->dev,
+	dev_err(chip->card->dev,
 		"azx_get_response timeout, switching to single_cmd mode: last cmd=0x%08x\n",
 		bus->last_cmd[addr]);
 	chip->single_cmd = 1;
diff --git a/sound/pci/hda/hda_eld.c b/sound/pci/hda/hda_eld.c
index d081fb2880a0..82cf1da2ff12 100644
--- a/sound/pci/hda/hda_eld.c
+++ b/sound/pci/hda/hda_eld.c
@@ -360,7 +360,7 @@ static void hdmi_print_pcm_rates(int pcm, char *buf, int buflen)
 
 	for (i = 0, j = 0; i < ARRAY_SIZE(alsa_rates); i++)
 		if (pcm & (1 << i))
-			j += snprintf(buf + j, buflen - j,  " %d",
+			j += scnprintf(buf + j, buflen - j,  " %d",
 				alsa_rates[i]);
 
 	buf[j] = '\0'; /* necessary when j == 0 */
diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index 10d502328b76..6815f9dc8545 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -4401,7 +4401,7 @@ EXPORT_SYMBOL_GPL(snd_hda_gen_fix_pin_power);
  */
 
 /* check each pin in the given array; returns true if any of them is plugged */
-static bool detect_jacks(struct hda_codec *codec, int num_pins, hda_nid_t *pins)
+static bool detect_jacks(struct hda_codec *codec, int num_pins, const hda_nid_t *pins)
 {
 	int i;
 	bool present = false;
@@ -4420,7 +4420,7 @@ static bool detect_jacks(struct hda_codec *codec, int num_pins, hda_nid_t *pins)
 }
 
 /* standard HP/line-out auto-mute helper */
-static void do_automute(struct hda_codec *codec, int num_pins, hda_nid_t *pins,
+static void do_automute(struct hda_codec *codec, int num_pins, const hda_nid_t *pins,
 			int *paths, bool mute)
 {
 	struct hda_gen_spec *spec = codec->spec;
@@ -6027,7 +6027,7 @@ int snd_hda_gen_init(struct hda_codec *codec)
 	/* call init functions of standard auto-mute helpers */
 	update_automute_all(codec);
 
-	regcache_sync(codec->core.regmap);
+	snd_hda_regmap_sync(codec);
 
 	if (spec->vmaster_mute.sw_kctl && spec->vmaster_mute.hook)
 		snd_hda_sync_vmaster_hook(&spec->vmaster_mute);
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 15aecf433367..011f8e958743 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -277,12 +277,13 @@ enum {
 
 /* quirks for old Intel chipsets */
 #define AZX_DCAPS_INTEL_ICH \
-	(AZX_DCAPS_OLD_SSYNC | AZX_DCAPS_NO_ALIGN_BUFSIZE)
+	(AZX_DCAPS_OLD_SSYNC | AZX_DCAPS_NO_ALIGN_BUFSIZE |\
+	 AZX_DCAPS_SYNC_WRITE)
 
 /* quirks for Intel PCH */
 #define AZX_DCAPS_INTEL_PCH_BASE \
 	(AZX_DCAPS_NO_ALIGN_BUFSIZE | AZX_DCAPS_COUNT_LPIB_DELAY |\
-	 AZX_DCAPS_SNOOP_TYPE(SCH))
+	 AZX_DCAPS_SNOOP_TYPE(SCH) | AZX_DCAPS_SYNC_WRITE)
 
 /* PCH up to IVB; no runtime PM; bind with i915 gfx */
 #define AZX_DCAPS_INTEL_PCH_NOPM \
@@ -297,13 +298,13 @@ enum {
 #define AZX_DCAPS_INTEL_HASWELL \
 	(/*AZX_DCAPS_ALIGN_BUFSIZE |*/ AZX_DCAPS_COUNT_LPIB_DELAY |\
 	 AZX_DCAPS_PM_RUNTIME | AZX_DCAPS_I915_COMPONENT |\
-	 AZX_DCAPS_SNOOP_TYPE(SCH))
+	 AZX_DCAPS_SNOOP_TYPE(SCH) | AZX_DCAPS_SYNC_WRITE)
 
 /* Broadwell HDMI can't use position buffer reliably, force to use LPIB */
 #define AZX_DCAPS_INTEL_BROADWELL \
 	(/*AZX_DCAPS_ALIGN_BUFSIZE |*/ AZX_DCAPS_POSFIX_LPIB |\
 	 AZX_DCAPS_PM_RUNTIME | AZX_DCAPS_I915_COMPONENT |\
-	 AZX_DCAPS_SNOOP_TYPE(SCH))
+	 AZX_DCAPS_SNOOP_TYPE(SCH) | AZX_DCAPS_SYNC_WRITE)
 
 #define AZX_DCAPS_INTEL_BAYTRAIL \
 	(AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_I915_COMPONENT)
@@ -1067,6 +1068,8 @@ static int azx_freeze_noirq(struct device *dev)
 	struct azx *chip = card->private_data;
 	struct pci_dev *pci = to_pci_dev(dev);
 
+	if (!azx_is_pm_ready(card))
+		return 0;
 	if (chip->driver_type == AZX_DRIVER_SKL)
 		pci_set_power_state(pci, PCI_D3hot);
 
@@ -1079,6 +1082,8 @@ static int azx_thaw_noirq(struct device *dev)
 	struct azx *chip = card->private_data;
 	struct pci_dev *pci = to_pci_dev(dev);
 
+	if (!azx_is_pm_ready(card))
+		return 0;
 	if (chip->driver_type == AZX_DRIVER_SKL)
 		pci_set_power_state(pci, PCI_D0);
 
@@ -1195,10 +1200,8 @@ static void azx_vs_set_state(struct pci_dev *pci,
 		if (!disabled) {
 			dev_info(chip->card->dev,
 				 "Start delayed initialization\n");
-			if (azx_probe_continue(chip) < 0) {
+			if (azx_probe_continue(chip) < 0)
 				dev_err(chip->card->dev, "initialization error\n");
-				hda->init_failed = true;
-			}
 		}
 	} else {
 		dev_info(chip->card->dev, "%s via vga_switcheroo\n",
@@ -1326,12 +1329,15 @@ static int register_vga_switcheroo(struct azx *chip)
 /*
  * destructor
  */
-static int azx_free(struct azx *chip)
+static void azx_free(struct azx *chip)
 {
 	struct pci_dev *pci = chip->pci;
 	struct hda_intel *hda = container_of(chip, struct hda_intel, chip);
 	struct hdac_bus *bus = azx_bus(chip);
 
+	if (hda->freed)
+		return;
+
 	if (azx_has_pm_runtime(chip) && chip->running)
 		pm_runtime_get_noresume(&pci->dev);
 	chip->running = 0;
@@ -1375,9 +1381,8 @@ static int azx_free(struct azx *chip)
 
 	if (chip->driver_caps & AZX_DCAPS_I915_COMPONENT)
 		snd_hdac_i915_exit(bus);
-	kfree(hda);
 
-	return 0;
+	hda->freed = 1;
 }
 
 static int azx_dev_disconnect(struct snd_device *device)
@@ -1393,7 +1398,8 @@ static int azx_dev_disconnect(struct snd_device *device)
 
 static int azx_dev_free(struct snd_device *device)
 {
-	return azx_free(device->device_data);
+	azx_free(device->device_data);
+	return 0;
 }
 
 #ifdef SUPPORT_VGA_SWITCHEROO
@@ -1708,7 +1714,7 @@ static int azx_create(struct snd_card *card, struct pci_dev *pci,
 	if (err < 0)
 		return err;
 
-	hda = kzalloc(sizeof(*hda), GFP_KERNEL);
+	hda = devm_kzalloc(&pci->dev, sizeof(*hda), GFP_KERNEL);
 	if (!hda) {
 		pci_disable_device(pci);
 		return -ENOMEM;
@@ -1753,7 +1759,6 @@ static int azx_create(struct snd_card *card, struct pci_dev *pci,
 
 	err = azx_bus_init(chip, model[dev], &pci_hda_io_ops);
 	if (err < 0) {
-		kfree(hda);
 		pci_disable_device(pci);
 		return err;
 	}
@@ -1945,7 +1950,7 @@ static int azx_first_init(struct azx *chip)
 	/* codec detection */
 	if (!azx_bus(chip)->codec_mask) {
 		dev_err(card->dev, "no codecs found!\n");
-		return -ENODEV;
+		/* keep running the rest for the runtime PM */
 	}
 
 	if (azx_acquire_irq(chip, 0) < 0)
@@ -1967,24 +1972,15 @@ static void azx_firmware_cb(const struct firmware *fw, void *context)
 {
 	struct snd_card *card = context;
 	struct azx *chip = card->private_data;
-	struct pci_dev *pci = chip->pci;
 
-	if (!fw) {
-		dev_err(card->dev, "Cannot load firmware, aborting\n");
-		goto error;
-	}
-
-	chip->fw = fw;
+	if (fw)
+		chip->fw = fw;
+	else
+		dev_err(card->dev, "Cannot load firmware, continue without patching\n");
 	if (!chip->disabled) {
 		/* continue probing */
-		if (azx_probe_continue(chip))
-			goto error;
+		azx_probe_continue(chip);
 	}
-	return; /* OK */
-
- error:
-	snd_card_free(card);
-	pci_set_drvdata(pci, NULL);
 }
 #endif
 
@@ -2079,6 +2075,17 @@ static const struct hdac_io_ops pci_hda_io_ops = {
 	.dma_free_pages = dma_free_pages,
 };
 
+/* Blacklist for skipping the whole probe:
+ * some HD-audio PCI entries are exposed without any codecs, and such devices
+ * should be ignored from the beginning.
+ */
+static const struct pci_device_id driver_blacklist[] = {
+	{ PCI_DEVICE_SUB(0x1022, 0x1487, 0x1043, 0x874f) }, /* ASUS ROG Zenith II / Strix */
+	{ PCI_DEVICE_SUB(0x1022, 0x1487, 0x1462, 0xcb59) }, /* MSI TRX40 Creator */
+	{ PCI_DEVICE_SUB(0x1022, 0x1487, 0x1462, 0xcb60) }, /* MSI TRX40 */
+	{}
+};
+
 static const struct hda_controller_ops pci_hda_ops = {
 	.disable_msi_reset_irq = disable_msi_reset_irq,
 	.pcm_mmap_prepare = pcm_mmap_prepare,
@@ -2095,6 +2102,11 @@ static int azx_probe(struct pci_dev *pci,
 	bool schedule_probe;
 	int err;
 
+	if (pci_match_id(driver_blacklist, pci)) {
+		dev_info(&pci->dev, "Skipping the blacklisted device\n");
+		return -ENODEV;
+	}
+
 	if (dev >= SNDRV_CARDS)
 		return -ENODEV;
 	if (!enable[dev]) {
@@ -2181,6 +2193,8 @@ static struct snd_pci_quirk power_save_blacklist[] = {
 	/* https://bugzilla.redhat.com/show_bug.cgi?id=1581607 */
 	SND_PCI_QUIRK(0x1558, 0x3501, "Clevo W35xSS_370SS", 0),
 	/* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */
+	SND_PCI_QUIRK(0x1558, 0x6504, "Clevo W65_67SB", 0),
+	/* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */
 	SND_PCI_QUIRK(0x1028, 0x0497, "Dell Precision T3600", 0),
 	/* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */
 	/* Note the P55A-UD3 and Z87-D3HP share the subsys id for the HDA dev */
@@ -2281,9 +2295,11 @@ static int azx_probe_continue(struct azx *chip)
 #endif
 
 	/* create codec instances */
-	err = azx_probe_codecs(chip, azx_max_codecs[chip->driver_type]);
-	if (err < 0)
-		goto out_free;
+	if (bus->codec_mask) {
+		err = azx_probe_codecs(chip, azx_max_codecs[chip->driver_type]);
+		if (err < 0)
+			goto out_free;
+	}
 
 #ifdef CONFIG_SND_HDA_PATCH_LOADER
 	if (chip->fw) {
@@ -2297,7 +2313,7 @@ static int azx_probe_continue(struct azx *chip)
 #endif
 	}
 #endif
-	if ((probe_only[dev] & 1) == 0) {
+	if (bus->codec_mask && !(probe_only[dev] & 1)) {
 		err = azx_codec_configure(chip);
 		if (err < 0)
 			goto out_free;
@@ -2314,17 +2330,22 @@ static int azx_probe_continue(struct azx *chip)
 
 	set_default_power_save(chip);
 
-	if (azx_has_pm_runtime(chip))
+	if (azx_has_pm_runtime(chip)) {
+		pm_runtime_use_autosuspend(&pci->dev);
 		pm_runtime_put_autosuspend(&pci->dev);
+	}
 
 out_free:
-	if (err < 0 || !hda->need_i915_power)
+	if (err < 0) {
+		azx_free(chip);
+		return err;
+	}
+
+	if (!hda->need_i915_power)
 		display_power(chip, false);
-	if (err < 0)
-		hda->init_failed = 1;
 	complete_all(&hda->probe_wait);
 	to_hda_bus(bus)->bus_probing = 0;
-	return err;
+	return 0;
 }
 
 static void azx_remove(struct pci_dev *pci)
@@ -2437,12 +2458,22 @@ static const struct pci_device_id azx_ids[] = {
 	/* Icelake */
 	{ PCI_DEVICE(0x8086, 0x34c8),
 	  .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
+	/* Icelake-H */
+	{ PCI_DEVICE(0x8086, 0x3dc8),
+	  .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
 	/* Jasperlake */
 	{ PCI_DEVICE(0x8086, 0x38c8),
 	  .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
+	{ PCI_DEVICE(0x8086, 0x4dc8),
+	  .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
+	/* Tigerlake-H */
+	{ PCI_DEVICE(0x8086, 0x43c8),
+	  .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
 	/* Tigerlake */
 	{ PCI_DEVICE(0x8086, 0xa0c8),
 	  .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
+	{ PCI_DEVICE(0x8086, 0x4b58),
+	  .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
 	/* Broxton-P(Apollolake) */
 	{ PCI_DEVICE(0x8086, 0x5a98),
 	  .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_BROXTON },
diff --git a/sound/pci/hda/hda_intel.h b/sound/pci/hda/hda_intel.h
index 1468865e0342..9302c9e67950 100644
--- a/sound/pci/hda/hda_intel.h
+++ b/sound/pci/hda/hda_intel.h
@@ -28,6 +28,7 @@ struct hda_intel {
 	unsigned int need_eld_notify_link:1;
 	unsigned int vga_switcheroo_registered:1;
 	unsigned int init_failed:1; /* delayed init failed */
+	unsigned int freed:1; /* resources already released */
 
 	bool need_i915_power:1; /* the hda controller needs i915 power */
 };
diff --git a/sound/pci/hda/hda_local.h b/sound/pci/hda/hda_local.h
index 349a8312d06a..d249fe4098bc 100644
--- a/sound/pci/hda/hda_local.h
+++ b/sound/pci/hda/hda_local.h
@@ -138,6 +138,8 @@ int snd_hda_codec_reset(struct hda_codec *codec);
 void snd_hda_codec_register(struct hda_codec *codec);
 void snd_hda_codec_cleanup_for_unbind(struct hda_codec *codec);
 
+#define snd_hda_regmap_sync(codec)	snd_hdac_regmap_sync(&(codec)->core)
+
 enum {
 	HDA_VMUTE_OFF,
 	HDA_VMUTE_ON,
diff --git a/sound/pci/hda/hda_sysfs.c b/sound/pci/hda/hda_sysfs.c
index fcc34417cbce..6dbe99131bc4 100644
--- a/sound/pci/hda/hda_sysfs.c
+++ b/sound/pci/hda/hda_sysfs.c
@@ -222,7 +222,7 @@ static ssize_t init_verbs_show(struct device *dev,
 	int i, len = 0;
 	mutex_lock(&codec->user_mutex);
 	snd_array_for_each(&codec->init_verbs, i, v) {
-		len += snprintf(buf + len, PAGE_SIZE - len,
+		len += scnprintf(buf + len, PAGE_SIZE - len,
 				"0x%02x 0x%03x 0x%04x\n",
 				v->nid, v->verb, v->param);
 	}
@@ -272,7 +272,7 @@ static ssize_t hints_show(struct device *dev,
 	int i, len = 0;
 	mutex_lock(&codec->user_mutex);
 	snd_array_for_each(&codec->hints, i, hint) {
-		len += snprintf(buf + len, PAGE_SIZE - len,
+		len += scnprintf(buf + len, PAGE_SIZE - len,
 				"%s = %s\n", hint->key, hint->val);
 	}
 	mutex_unlock(&codec->user_mutex);
diff --git a/sound/pci/hda/patch_analog.c b/sound/pci/hda/patch_analog.c
index bc9dd8e6fd86..c64895f99299 100644
--- a/sound/pci/hda/patch_analog.c
+++ b/sound/pci/hda/patch_analog.c
@@ -389,7 +389,7 @@ static int patch_ad1986a(struct hda_codec *codec)
 {
 	int err;
 	struct ad198x_spec *spec;
-	static hda_nid_t preferred_pairs[] = {
+	static const hda_nid_t preferred_pairs[] = {
 		0x1a, 0x03,
 		0x1b, 0x03,
 		0x1c, 0x04,
@@ -519,9 +519,9 @@ static int ad1983_add_spdif_mux_ctl(struct hda_codec *codec)
 
 static int patch_ad1983(struct hda_codec *codec)
 {
+	static const hda_nid_t conn_0c[] = { 0x08 };
+	static const hda_nid_t conn_0d[] = { 0x09 };
 	struct ad198x_spec *spec;
-	static hda_nid_t conn_0c[] = { 0x08 };
-	static hda_nid_t conn_0d[] = { 0x09 };
 	int err;
 
 	err = alloc_ad_spec(codec);
diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 43e4c837e829..08bf3c2888a0 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -1180,7 +1180,9 @@ static const struct snd_pci_quirk ca0132_quirks[] = {
 	SND_PCI_QUIRK(0x1458, 0xA016, "Recon3Di", QUIRK_R3DI),
 	SND_PCI_QUIRK(0x1458, 0xA026, "Gigabyte G1.Sniper Z97", QUIRK_R3DI),
 	SND_PCI_QUIRK(0x1458, 0xA036, "Gigabyte GA-Z170X-Gaming 7", QUIRK_R3DI),
+	SND_PCI_QUIRK(0x3842, 0x1038, "EVGA X99 Classified", QUIRK_R3DI),
 	SND_PCI_QUIRK(0x1102, 0x0013, "Recon3D", QUIRK_R3D),
+	SND_PCI_QUIRK(0x1102, 0x0018, "Recon3D", QUIRK_R3D),
 	SND_PCI_QUIRK(0x1102, 0x0051, "Sound Blaster AE-5", QUIRK_AE5),
 	{}
 };
@@ -4669,7 +4671,7 @@ static int ca0132_alt_select_in(struct hda_codec *codec)
 			tmp = FLOAT_ONE;
 			break;
 		case QUIRK_AE5:
-			ca0113_mmio_command_set(codec, 0x48, 0x28, 0x00);
+			ca0113_mmio_command_set(codec, 0x30, 0x28, 0x00);
 			tmp = FLOAT_THREE;
 			break;
 		default:
@@ -4715,7 +4717,7 @@ static int ca0132_alt_select_in(struct hda_codec *codec)
 			r3di_gpio_mic_set(codec, R3DI_REAR_MIC);
 			break;
 		case QUIRK_AE5:
-			ca0113_mmio_command_set(codec, 0x48, 0x28, 0x00);
+			ca0113_mmio_command_set(codec, 0x30, 0x28, 0x00);
 			break;
 		default:
 			break;
@@ -4754,7 +4756,7 @@ static int ca0132_alt_select_in(struct hda_codec *codec)
 			tmp = FLOAT_ONE;
 			break;
 		case QUIRK_AE5:
-			ca0113_mmio_command_set(codec, 0x48, 0x28, 0x3f);
+			ca0113_mmio_command_set(codec, 0x30, 0x28, 0x3f);
 			tmp = FLOAT_THREE;
 			break;
 		default:
@@ -5746,6 +5748,11 @@ static int ca0132_switch_get(struct snd_kcontrol *kcontrol,
 		return 0;
 	}
 
+	if (nid == ZXR_HEADPHONE_GAIN) {
+		*valp = spec->zxr_gain_set;
+		return 0;
+	}
+
 	return 0;
 }
 
@@ -7802,23 +7809,23 @@ static void sbz_region2_exit(struct hda_codec *codec)
 
 static void sbz_set_pin_ctl_default(struct hda_codec *codec)
 {
-	hda_nid_t pins[5] = {0x0B, 0x0C, 0x0E, 0x12, 0x13};
+	static const hda_nid_t pins[] = {0x0B, 0x0C, 0x0E, 0x12, 0x13};
 	unsigned int i;
 
 	snd_hda_codec_write(codec, 0x11, 0,
 			AC_VERB_SET_PIN_WIDGET_CONTROL, 0x40);
 
-	for (i = 0; i < 5; i++)
+	for (i = 0; i < ARRAY_SIZE(pins); i++)
 		snd_hda_codec_write(codec, pins[i], 0,
 				AC_VERB_SET_PIN_WIDGET_CONTROL, 0x00);
 }
 
 static void ca0132_clear_unsolicited(struct hda_codec *codec)
 {
-	hda_nid_t pins[7] = {0x0B, 0x0E, 0x0F, 0x10, 0x11, 0x12, 0x13};
+	static const hda_nid_t pins[] = {0x0B, 0x0E, 0x0F, 0x10, 0x11, 0x12, 0x13};
 	unsigned int i;
 
-	for (i = 0; i < 7; i++) {
+	for (i = 0; i < ARRAY_SIZE(pins); i++) {
 		snd_hda_codec_write(codec, pins[i], 0,
 				AC_VERB_SET_UNSOLICITED_ENABLE, 0x00);
 	}
@@ -7842,10 +7849,10 @@ static void sbz_gpio_shutdown_commands(struct hda_codec *codec, int dir,
 
 static void zxr_dbpro_power_state_shutdown(struct hda_codec *codec)
 {
-	hda_nid_t pins[7] = {0x05, 0x0c, 0x09, 0x0e, 0x08, 0x11, 0x01};
+	static const hda_nid_t pins[] = {0x05, 0x0c, 0x09, 0x0e, 0x08, 0x11, 0x01};
 	unsigned int i;
 
-	for (i = 0; i < 7; i++)
+	for (i = 0; i < ARRAY_SIZE(pins); i++)
 		snd_hda_codec_write(codec, pins[i], 0,
 				AC_VERB_SET_POWER_STATE, 0x03);
 }
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index 90aa0f400a57..396b5503038a 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -116,7 +116,7 @@ static void cx_auto_parse_eapd(struct hda_codec *codec)
 }
 
 static void cx_auto_turn_eapd(struct hda_codec *codec, int num_pins,
-			      hda_nid_t *pins, bool on)
+			      const hda_nid_t *pins, bool on)
 {
 	int i;
 	for (i = 0; i < num_pins; i++) {
@@ -922,6 +922,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = {
 	SND_PCI_QUIRK(0x17aa, 0x215f, "Lenovo T510", CXT_PINCFG_LENOVO_TP410),
 	SND_PCI_QUIRK(0x17aa, 0x21ce, "Lenovo T420", CXT_PINCFG_LENOVO_TP410),
 	SND_PCI_QUIRK(0x17aa, 0x21cf, "Lenovo T520", CXT_PINCFG_LENOVO_TP410),
+	SND_PCI_QUIRK(0x17aa, 0x21d2, "Lenovo T420s", CXT_PINCFG_LENOVO_TP410),
 	SND_PCI_QUIRK(0x17aa, 0x21da, "Lenovo X220", CXT_PINCFG_LENOVO_TP410),
 	SND_PCI_QUIRK(0x17aa, 0x21db, "Lenovo X220-tablet", CXT_PINCFG_LENOVO_TP410),
 	SND_PCI_QUIRK(0x17aa, 0x38af, "Lenovo IdeaPad Z560", CXT_FIXUP_MUTE_LED_EAPD),
@@ -959,10 +960,10 @@ static const struct hda_model_fixup cxt5066_fixup_models[] = {
 static void add_cx5051_fake_mutes(struct hda_codec *codec)
 {
 	struct conexant_spec *spec = codec->spec;
-	static hda_nid_t out_nids[] = {
+	static const hda_nid_t out_nids[] = {
 		0x10, 0x11, 0
 	};
-	hda_nid_t *p;
+	const hda_nid_t *p;
 
 	for (p = out_nids; *p; p++)
 		snd_hda_override_amp_caps(codec, *p, HDA_OUTPUT,
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 52af1abed4cc..499e671bc2cc 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -1801,33 +1801,43 @@ static int hdmi_add_cvt(struct hda_codec *codec, hda_nid_t cvt_nid)
 
 static int hdmi_parse_codec(struct hda_codec *codec)
 {
-	hda_nid_t nid;
+	hda_nid_t start_nid;
+	unsigned int caps;
 	int i, nodes;
 
-	nodes = snd_hda_get_sub_nodes(codec, codec->core.afg, &nid);
-	if (!nid || nodes < 0) {
+	nodes = snd_hda_get_sub_nodes(codec, codec->core.afg, &start_nid);
+	if (!start_nid || nodes < 0) {
 		codec_warn(codec, "HDMI: failed to get afg sub nodes\n");
 		return -EINVAL;
 	}
 
-	for (i = 0; i < nodes; i++, nid++) {
-		unsigned int caps;
-		unsigned int type;
+	/*
+	 * hdmi_add_pin() assumes total amount of converters to
+	 * be known, so first discover all converters
+	 */
+	for (i = 0; i < nodes; i++) {
+		hda_nid_t nid = start_nid + i;
 
 		caps = get_wcaps(codec, nid);
-		type = get_wcaps_type(caps);
 
 		if (!(caps & AC_WCAP_DIGITAL))
 			continue;
 
-		switch (type) {
-		case AC_WID_AUD_OUT:
+		if (get_wcaps_type(caps) == AC_WID_AUD_OUT)
 			hdmi_add_cvt(codec, nid);
-			break;
-		case AC_WID_PIN:
+	}
+
+	/* discover audio pins */
+	for (i = 0; i < nodes; i++) {
+		hda_nid_t nid = start_nid + i;
+
+		caps = get_wcaps(codec, nid);
+
+		if (!(caps & AC_WCAP_DIGITAL))
+			continue;
+
+		if (get_wcaps_type(caps) == AC_WID_PIN)
 			hdmi_add_pin(codec, nid);
-			break;
-		}
 	}
 
 	return 0;
@@ -1845,8 +1855,10 @@ static bool check_non_pcm_per_cvt(struct hda_codec *codec, hda_nid_t cvt_nid)
 	/* Add sanity check to pass klockwork check.
 	 * This should never happen.
 	 */
-	if (WARN_ON(spdif == NULL))
+	if (WARN_ON(spdif == NULL)) {
+		mutex_unlock(&codec->spdif_mutex);
 		return true;
+	}
 	non_pcm = !!(spdif->status & IEC958_AES0_NONAUDIO);
 	mutex_unlock(&codec->spdif_mutex);
 	return non_pcm;
@@ -2216,7 +2228,9 @@ static int generic_hdmi_build_controls(struct hda_codec *codec)
 
 	for (pin_idx = 0; pin_idx < spec->num_pins; pin_idx++) {
 		struct hdmi_spec_per_pin *per_pin = get_pin(spec, pin_idx);
+		struct hdmi_eld *pin_eld = &per_pin->sink_eld;
 
+		pin_eld->eld_valid = false;
 		hdmi_present_sense(per_pin, 0);
 	}
 
@@ -2331,7 +2345,7 @@ static int generic_hdmi_resume(struct hda_codec *codec)
 	int pin_idx;
 
 	codec->patch_ops.init(codec);
-	regcache_sync(codec->core.regmap);
+	snd_hda_regmap_sync(codec);
 
 	for (pin_idx = 0; pin_idx < spec->num_pins; pin_idx++) {
 		struct hdmi_spec_per_pin *per_pin = get_pin(spec, pin_idx);
@@ -2641,9 +2655,12 @@ static int alloc_intel_hdmi(struct hda_codec *codec)
 /* parse and post-process for Intel codecs */
 static int parse_intel_hdmi(struct hda_codec *codec)
 {
-	int err;
+	int err, retries = 3;
+
+	do {
+		err = hdmi_parse_codec(codec);
+	} while (err < 0 && retries--);
 
-	err = hdmi_parse_codec(codec);
 	if (err < 0) {
 		generic_spec_free(codec);
 		return err;
@@ -3952,6 +3969,11 @@ HDA_CODEC_ENTRY(0x10de0095, "GPU 95 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de0097, "GPU 97 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de0098, "GPU 98 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de0099, "GPU 99 HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de009a, "GPU 9a HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de009d, "GPU 9d HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de009e, "GPU 9e HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de009f, "GPU 9f HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00a0, "GPU a0 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de8001, "MCP73 HDMI",	patch_nvhdmi_2ch),
 HDA_CODEC_ENTRY(0x10de8067, "MCP67/68 HDMI",	patch_nvhdmi_2ch),
 HDA_CODEC_ENTRY(0x11069f80, "VX900 HDMI/DP",	patch_via_hdmi),
@@ -3975,6 +3997,7 @@ HDA_CODEC_ENTRY(0x8086280c, "Cannonlake HDMI",	patch_i915_glk_hdmi),
 HDA_CODEC_ENTRY(0x8086280d, "Geminilake HDMI",	patch_i915_glk_hdmi),
 HDA_CODEC_ENTRY(0x8086280f, "Icelake HDMI",	patch_i915_icl_hdmi),
 HDA_CODEC_ENTRY(0x80862812, "Tigerlake HDMI",	patch_i915_tgl_hdmi),
+HDA_CODEC_ENTRY(0x8086281a, "Jasperlake HDMI",	patch_i915_icl_hdmi),
 HDA_CODEC_ENTRY(0x80862880, "CedarTrail HDMI",	patch_generic_hdmi),
 HDA_CODEC_ENTRY(0x80862882, "Valleyview2 HDMI",	patch_i915_byt_hdmi),
 HDA_CODEC_ENTRY(0x80862883, "Braswell HDMI",	patch_i915_byt_hdmi),
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 4b23e374d367..d496ad64a880 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -81,11 +81,20 @@ struct alc_spec {
 
 	/* mute LED for HP laptops, see alc269_fixup_mic_mute_hook() */
 	int mute_led_polarity;
+	int micmute_led_polarity;
 	hda_nid_t mute_led_nid;
 	hda_nid_t cap_mute_led_nid;
 
 	unsigned int gpio_mute_led_mask;
 	unsigned int gpio_mic_led_mask;
+	unsigned int mute_led_coef_idx;
+	unsigned int mute_led_coefbit_mask;
+	unsigned int mute_led_coefbit_on;
+	unsigned int mute_led_coefbit_off;
+	unsigned int mic_led_coef_idx;
+	unsigned int mic_led_coefbit_mask;
+	unsigned int mic_led_coefbit_on;
+	unsigned int mic_led_coefbit_off;
 
 	hda_nid_t headset_mic_pin;
 	hda_nid_t headphone_mic_pin;
@@ -107,6 +116,7 @@ struct alc_spec {
 	unsigned int done_hp_init:1;
 	unsigned int no_shutup_pins:1;
 	unsigned int ultra_low_power:1;
+	unsigned int has_hs_key:1;
 
 	/* for PLL fix */
 	hda_nid_t pll_nid;
@@ -367,11 +377,15 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
 	case 0x10ec0215:
 	case 0x10ec0233:
 	case 0x10ec0235:
+	case 0x10ec0236:
+	case 0x10ec0245:
 	case 0x10ec0255:
+	case 0x10ec0256:
 	case 0x10ec0257:
 	case 0x10ec0282:
 	case 0x10ec0283:
 	case 0x10ec0286:
+	case 0x10ec0287:
 	case 0x10ec0288:
 	case 0x10ec0285:
 	case 0x10ec0298:
@@ -379,11 +393,6 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
 	case 0x10ec0300:
 		alc_update_coef_idx(codec, 0x10, 1<<9, 0);
 		break;
-	case 0x10ec0236:
-	case 0x10ec0256:
-		alc_write_coef_idx(codec, 0x36, 0x5757);
-		alc_update_coef_idx(codec, 0x10, 1<<9, 0);
-		break;
 	case 0x10ec0275:
 		alc_update_coef_idx(codec, 0xe, 0, 1<<0);
 		break;
@@ -412,6 +421,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
 	case 0x10ec0672:
 		alc_update_coef_idx(codec, 0xd, 0, 1<<14); /* EAPD Ctrl */
 		break;
+	case 0x10ec0222:
 	case 0x10ec0623:
 		alc_update_coef_idx(codec, 0x19, 1<<13, 0);
 		break;
@@ -430,6 +440,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
 		break;
 	case 0x10ec0899:
 	case 0x10ec0900:
+	case 0x10ec0b00:
 	case 0x10ec1168:
 	case 0x10ec1220:
 		alc_update_coef_idx(codec, 0x7, 1<<1, 0);
@@ -464,10 +475,10 @@ static void set_eapd(struct hda_codec *codec, hda_nid_t nid, int on)
 static void alc_auto_setup_eapd(struct hda_codec *codec, bool on)
 {
 	/* We currently only handle front, HP */
-	static hda_nid_t pins[] = {
+	static const hda_nid_t pins[] = {
 		0x0f, 0x10, 0x14, 0x15, 0x17, 0
 	};
-	hda_nid_t *p;
+	const hda_nid_t *p;
 	for (p = pins; *p; p++)
 		set_eapd(codec, *p, on);
 }
@@ -501,6 +512,7 @@ static void alc_shutup_pins(struct hda_codec *codec)
 	struct alc_spec *spec = codec->spec;
 
 	switch (codec->core.vendor_id) {
+	case 0x10ec0283:
 	case 0x10ec0286:
 	case 0x10ec0288:
 	case 0x10ec0298:
@@ -788,9 +800,11 @@ static void alc_ssid_check(struct hda_codec *codec, const hda_nid_t *ports)
 {
 	if (!alc_subsystem_id(codec, ports)) {
 		struct alc_spec *spec = codec->spec;
-		codec_dbg(codec,
-			  "realtek: Enable default setup for auto mode as fallback\n");
-		spec->init_amp = ALC_INIT_DEFAULT;
+		if (spec->init_amp == ALC_INIT_UNDEFINED) {
+			codec_dbg(codec,
+				  "realtek: Enable default setup for auto mode as fallback\n");
+			spec->init_amp = ALC_INIT_DEFAULT;
+		}
 	}
 }
 
@@ -904,7 +918,7 @@ static int alc_resume(struct hda_codec *codec)
 	if (!spec->no_depop_delay)
 		msleep(150); /* to avoid pop noise */
 	codec->patch_ops.init(codec);
-	regcache_sync(codec->core.regmap);
+	snd_hda_regmap_sync(codec);
 	hda_call_check_power_status(codec, 0x01);
 	return 0;
 }
@@ -946,7 +960,7 @@ struct alc_codec_rename_pci_table {
 	const char *name;
 };
 
-static struct alc_codec_rename_table rename_tbl[] = {
+static const struct alc_codec_rename_table rename_tbl[] = {
 	{ 0x10ec0221, 0xf00f, 0x1003, "ALC231" },
 	{ 0x10ec0269, 0xfff0, 0x3010, "ALC277" },
 	{ 0x10ec0269, 0xf0f0, 0x2010, "ALC259" },
@@ -967,7 +981,7 @@ static struct alc_codec_rename_table rename_tbl[] = {
 	{ } /* terminator */
 };
 
-static struct alc_codec_rename_pci_table rename_pci_tbl[] = {
+static const struct alc_codec_rename_pci_table rename_pci_tbl[] = {
 	{ 0x10ec0280, 0x1028, 0, "ALC3220" },
 	{ 0x10ec0282, 0x1028, 0, "ALC3221" },
 	{ 0x10ec0283, 0x1028, 0, "ALC3223" },
@@ -1935,19 +1949,19 @@ static void alc889_fixup_dac_route(struct hda_codec *codec,
 {
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
 		/* fake the connections during parsing the tree */
-		hda_nid_t conn1[2] = { 0x0c, 0x0d };
-		hda_nid_t conn2[2] = { 0x0e, 0x0f };
-		snd_hda_override_conn_list(codec, 0x14, 2, conn1);
-		snd_hda_override_conn_list(codec, 0x15, 2, conn1);
-		snd_hda_override_conn_list(codec, 0x18, 2, conn2);
-		snd_hda_override_conn_list(codec, 0x1a, 2, conn2);
+		static const hda_nid_t conn1[] = { 0x0c, 0x0d };
+		static const hda_nid_t conn2[] = { 0x0e, 0x0f };
+		snd_hda_override_conn_list(codec, 0x14, ARRAY_SIZE(conn1), conn1);
+		snd_hda_override_conn_list(codec, 0x15, ARRAY_SIZE(conn1), conn1);
+		snd_hda_override_conn_list(codec, 0x18, ARRAY_SIZE(conn2), conn2);
+		snd_hda_override_conn_list(codec, 0x1a, ARRAY_SIZE(conn2), conn2);
 	} else if (action == HDA_FIXUP_ACT_PROBE) {
 		/* restore the connections */
-		hda_nid_t conn[5] = { 0x0c, 0x0d, 0x0e, 0x0f, 0x26 };
-		snd_hda_override_conn_list(codec, 0x14, 5, conn);
-		snd_hda_override_conn_list(codec, 0x15, 5, conn);
-		snd_hda_override_conn_list(codec, 0x18, 5, conn);
-		snd_hda_override_conn_list(codec, 0x1a, 5, conn);
+		static const hda_nid_t conn[] = { 0x0c, 0x0d, 0x0e, 0x0f, 0x26 };
+		snd_hda_override_conn_list(codec, 0x14, ARRAY_SIZE(conn), conn);
+		snd_hda_override_conn_list(codec, 0x15, ARRAY_SIZE(conn), conn);
+		snd_hda_override_conn_list(codec, 0x18, ARRAY_SIZE(conn), conn);
+		snd_hda_override_conn_list(codec, 0x1a, ARRAY_SIZE(conn), conn);
 	}
 }
 
@@ -1955,8 +1969,8 @@ static void alc889_fixup_dac_route(struct hda_codec *codec,
 static void alc889_fixup_mbp_vref(struct hda_codec *codec,
 				  const struct hda_fixup *fix, int action)
 {
+	static const hda_nid_t nids[] = { 0x14, 0x15, 0x19 };
 	struct alc_spec *spec = codec->spec;
-	static hda_nid_t nids[3] = { 0x14, 0x15, 0x19 };
 	int i;
 
 	if (action != HDA_FIXUP_ACT_INIT)
@@ -1992,7 +2006,7 @@ static void alc889_fixup_mac_pins(struct hda_codec *codec,
 static void alc889_fixup_imac91_vref(struct hda_codec *codec,
 				     const struct hda_fixup *fix, int action)
 {
-	static hda_nid_t nids[2] = { 0x18, 0x1a };
+	static const hda_nid_t nids[] = { 0x18, 0x1a };
 
 	if (action == HDA_FIXUP_ACT_INIT)
 		alc889_fixup_mac_pins(codec, nids, ARRAY_SIZE(nids));
@@ -2002,7 +2016,7 @@ static void alc889_fixup_imac91_vref(struct hda_codec *codec,
 static void alc889_fixup_mba11_vref(struct hda_codec *codec,
 				    const struct hda_fixup *fix, int action)
 {
-	static hda_nid_t nids[1] = { 0x18 };
+	static const hda_nid_t nids[] = { 0x18 };
 
 	if (action == HDA_FIXUP_ACT_INIT)
 		alc889_fixup_mac_pins(codec, nids, ARRAY_SIZE(nids));
@@ -2012,7 +2026,7 @@ static void alc889_fixup_mba11_vref(struct hda_codec *codec,
 static void alc889_fixup_mba21_vref(struct hda_codec *codec,
 				    const struct hda_fixup *fix, int action)
 {
-	static hda_nid_t nids[2] = { 0x18, 0x19 };
+	static const hda_nid_t nids[] = { 0x18, 0x19 };
 
 	if (action == HDA_FIXUP_ACT_INIT)
 		alc889_fixup_mac_pins(codec, nids, ARRAY_SIZE(nids));
@@ -2094,7 +2108,7 @@ static void alc1220_fixup_clevo_p950(struct hda_codec *codec,
 				     const struct hda_fixup *fix,
 				     int action)
 {
-	hda_nid_t conn1[1] = { 0x0c };
+	static const hda_nid_t conn1[] = { 0x0c };
 
 	if (action != HDA_FIXUP_ACT_PRE_PROBE)
 		return;
@@ -2103,8 +2117,8 @@ static void alc1220_fixup_clevo_p950(struct hda_codec *codec,
 	/* We therefore want to make sure 0x14 (front headphone) and
 	 * 0x1b (speakers) use the stereo DAC 0x02
 	 */
-	snd_hda_override_conn_list(codec, 0x14, 1, conn1);
-	snd_hda_override_conn_list(codec, 0x1b, 1, conn1);
+	snd_hda_override_conn_list(codec, 0x14, ARRAY_SIZE(conn1), conn1);
+	snd_hda_override_conn_list(codec, 0x1b, ARRAY_SIZE(conn1), conn1);
 }
 
 static void alc_fixup_headset_mode_no_hp_mic(struct hda_codec *codec,
@@ -2444,6 +2458,13 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1071, 0x8258, "Evesham Voyaeger", ALC882_FIXUP_EAPD),
 	SND_PCI_QUIRK(0x1458, 0xa002, "Gigabyte EP45-DS3/Z87X-UD3H", ALC889_FIXUP_FRONT_HP_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1458, 0xa0b8, "Gigabyte AZ370-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS),
+	SND_PCI_QUIRK(0x1458, 0xa0cd, "Gigabyte X570 Aorus Master", ALC1220_FIXUP_CLEVO_P950),
+	SND_PCI_QUIRK(0x1458, 0xa0ce, "Gigabyte X570 Aorus Xtreme", ALC1220_FIXUP_CLEVO_P950),
+	SND_PCI_QUIRK(0x1462, 0x11f7, "MSI-GE63", ALC1220_FIXUP_CLEVO_P950),
+	SND_PCI_QUIRK(0x1462, 0x1228, "MSI-GP63", ALC1220_FIXUP_CLEVO_P950),
+	SND_PCI_QUIRK(0x1462, 0x1275, "MSI-GL63", ALC1220_FIXUP_CLEVO_P950),
+	SND_PCI_QUIRK(0x1462, 0x1276, "MSI-GL73", ALC1220_FIXUP_CLEVO_P950),
+	SND_PCI_QUIRK(0x1462, 0x1293, "MSI-GP65", ALC1220_FIXUP_CLEVO_P950),
 	SND_PCI_QUIRK(0x1462, 0x7350, "MSI-7350", ALC889_FIXUP_CD),
 	SND_PCI_QUIRK(0x1462, 0xda57, "MSI Z270-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS),
 	SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3),
@@ -2455,6 +2476,9 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1558, 0x97e1, "Clevo P970[ER][CDFN]", ALC1220_FIXUP_CLEVO_P950),
 	SND_PCI_QUIRK(0x1558, 0x65d1, "Clevo PB51[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
 	SND_PCI_QUIRK(0x1558, 0x67d1, "Clevo PB71[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
+	SND_PCI_QUIRK(0x1558, 0x50d3, "Clevo PC50[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
+	SND_PCI_QUIRK(0x1558, 0x70d1, "Clevo PC70[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
+	SND_PCI_QUIRK(0x1558, 0x7714, "Clevo X170", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
 	SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD),
 	SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD),
 	SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Y530", ALC882_FIXUP_LENOVO_Y530),
@@ -2525,6 +2549,7 @@ static int patch_alc882(struct hda_codec *codec)
 	case 0x10ec0882:
 	case 0x10ec0885:
 	case 0x10ec0900:
+	case 0x10ec0b00:
 	case 0x10ec1220:
 		break;
 	default:
@@ -2973,6 +2998,107 @@ static int alc269_parse_auto_config(struct hda_codec *codec)
 	return alc_parse_auto_config(codec, alc269_ignore, ssids);
 }
 
+static const struct hda_jack_keymap alc_headset_btn_keymap[] = {
+	{ SND_JACK_BTN_0, KEY_PLAYPAUSE },
+	{ SND_JACK_BTN_1, KEY_VOICECOMMAND },
+	{ SND_JACK_BTN_2, KEY_VOLUMEUP },
+	{ SND_JACK_BTN_3, KEY_VOLUMEDOWN },
+	{}
+};
+
+static void alc_headset_btn_callback(struct hda_codec *codec,
+				     struct hda_jack_callback *jack)
+{
+	int report = 0;
+
+	if (jack->unsol_res & (7 << 13))
+		report |= SND_JACK_BTN_0;
+
+	if (jack->unsol_res  & (1 << 16 | 3 << 8))
+		report |= SND_JACK_BTN_1;
+
+	/* Volume up key */
+	if (jack->unsol_res & (7 << 23))
+		report |= SND_JACK_BTN_2;
+
+	/* Volume down key */
+	if (jack->unsol_res & (7 << 10))
+		report |= SND_JACK_BTN_3;
+
+	jack->jack->button_state = report;
+}
+
+static void alc_disable_headset_jack_key(struct hda_codec *codec)
+{
+	struct alc_spec *spec = codec->spec;
+
+	if (!spec->has_hs_key)
+		return;
+
+	switch (codec->core.vendor_id) {
+	case 0x10ec0215:
+	case 0x10ec0225:
+	case 0x10ec0285:
+	case 0x10ec0295:
+	case 0x10ec0289:
+	case 0x10ec0299:
+		alc_write_coef_idx(codec, 0x48, 0x0);
+		alc_update_coef_idx(codec, 0x49, 0x0045, 0x0);
+		alc_update_coef_idx(codec, 0x44, 0x0045 << 8, 0x0);
+		break;
+	case 0x10ec0236:
+	case 0x10ec0256:
+		alc_write_coef_idx(codec, 0x48, 0x0);
+		alc_update_coef_idx(codec, 0x49, 0x0045, 0x0);
+		break;
+	}
+}
+
+static void alc_enable_headset_jack_key(struct hda_codec *codec)
+{
+	struct alc_spec *spec = codec->spec;
+
+	if (!spec->has_hs_key)
+		return;
+
+	switch (codec->core.vendor_id) {
+	case 0x10ec0215:
+	case 0x10ec0225:
+	case 0x10ec0285:
+	case 0x10ec0295:
+	case 0x10ec0289:
+	case 0x10ec0299:
+		alc_write_coef_idx(codec, 0x48, 0xd011);
+		alc_update_coef_idx(codec, 0x49, 0x007f, 0x0045);
+		alc_update_coef_idx(codec, 0x44, 0x007f << 8, 0x0045 << 8);
+		break;
+	case 0x10ec0236:
+	case 0x10ec0256:
+		alc_write_coef_idx(codec, 0x48, 0xd011);
+		alc_update_coef_idx(codec, 0x49, 0x007f, 0x0045);
+		break;
+	}
+}
+
+static void alc_fixup_headset_jack(struct hda_codec *codec,
+				    const struct hda_fixup *fix, int action)
+{
+	struct alc_spec *spec = codec->spec;
+
+	switch (action) {
+	case HDA_FIXUP_ACT_PRE_PROBE:
+		spec->has_hs_key = 1;
+		snd_hda_jack_detect_enable_callback(codec, 0x55,
+						    alc_headset_btn_callback);
+		snd_hda_jack_add_kctl(codec, 0x55, "Headset Jack", false,
+				      SND_JACK_HEADSET, alc_headset_btn_keymap);
+		break;
+	case HDA_FIXUP_ACT_INIT:
+		alc_enable_headset_jack_key(codec);
+		break;
+	}
+}
+
 static void alc269vb_toggle_power_output(struct hda_codec *codec, int power_up)
 {
 	alc_update_coef_idx(codec, 0x04, 1 << 11, power_up ? (1 << 11) : 0);
@@ -2991,7 +3117,7 @@ static void alc269_shutup(struct hda_codec *codec)
 	alc_shutup_pins(codec);
 }
 
-static struct coef_fw alc282_coefs[] = {
+static const struct coef_fw alc282_coefs[] = {
 	WRITE_COEF(0x03, 0x0002), /* Power Down Control */
 	UPDATE_COEF(0x05, 0xff3f, 0x0700), /* FIFO and filter clock */
 	WRITE_COEF(0x07, 0x0200), /* DMIC control */
@@ -3103,7 +3229,7 @@ static void alc282_shutup(struct hda_codec *codec)
 	alc_write_coef_idx(codec, 0x78, coef78);
 }
 
-static struct coef_fw alc283_coefs[] = {
+static const struct coef_fw alc283_coefs[] = {
 	WRITE_COEF(0x03, 0x0002), /* Power Down Control */
 	UPDATE_COEF(0x05, 0xff3f, 0x0700), /* FIFO and filter clock */
 	WRITE_COEF(0x07, 0x0200), /* DMIC control */
@@ -3260,7 +3386,13 @@ static void alc256_init(struct hda_codec *codec)
 	alc_update_coefex_idx(codec, 0x57, 0x04, 0x0007, 0x4); /* Hight power */
 	alc_update_coefex_idx(codec, 0x53, 0x02, 0x8000, 1 << 15); /* Clear bit */
 	alc_update_coefex_idx(codec, 0x53, 0x02, 0x8000, 0 << 15);
-	alc_update_coef_idx(codec, 0x36, 1 << 13, 1 << 5); /* Switch pcbeep path to Line in path*/
+	/*
+	 * Expose headphone mic (or possibly Line In on some machines) instead
+	 * of PC Beep on 1Ah, and disable 1Ah loopback for all outputs. See
+	 * Documentation/sound/hd-audio/realtek-pc-beep.rst for details of
+	 * this register.
+	 */
+	alc_write_coef_idx(codec, 0x36, 0x5757);
 }
 
 static void alc256_shutup(struct hda_codec *codec)
@@ -3363,6 +3495,8 @@ static void alc225_shutup(struct hda_codec *codec)
 
 	if (!hp_pin)
 		hp_pin = 0x21;
+
+	alc_disable_headset_jack_key(codec);
 	/* 3k pull low control for Headset jack. */
 	alc_update_coef_idx(codec, 0x4a, 0, 3 << 10);
 
@@ -3402,6 +3536,9 @@ static void alc225_shutup(struct hda_codec *codec)
 		alc_update_coef_idx(codec, 0x4a, 3<<4, 2<<4);
 		msleep(30);
 	}
+
+	alc_update_coef_idx(codec, 0x4a, 3 << 10, 0);
+	alc_enable_headset_jack_key(codec);
 }
 
 static void alc_default_init(struct hda_codec *codec)
@@ -3596,8 +3733,8 @@ static void alc5505_dsp_init(struct hda_codec *codec)
 }
 
 #ifdef HALT_REALTEK_ALC5505
-#define alc5505_dsp_suspend(codec)	/* NOP */
-#define alc5505_dsp_resume(codec)	/* NOP */
+#define alc5505_dsp_suspend(codec)	do { } while (0) /* NOP */
+#define alc5505_dsp_resume(codec)	do { } while (0) /* NOP */
 #else
 #define alc5505_dsp_suspend(codec)	alc5505_dsp_halt(codec)
 #define alc5505_dsp_resume(codec)	alc5505_dsp_back_from_halt(codec)
@@ -3633,7 +3770,7 @@ static int alc269_resume(struct hda_codec *codec)
 		msleep(200);
 	}
 
-	regcache_sync(codec->core.regmap);
+	snd_hda_regmap_sync(codec);
 	hda_call_check_power_status(codec, 0x01);
 
 	/* on some machine, the BIOS will clear the codec gpio data when enter
@@ -3944,11 +4081,9 @@ static void alc269_fixup_hp_mute_led_mic3(struct hda_codec *codec,
 
 /* update LED status via GPIO */
 static void alc_update_gpio_led(struct hda_codec *codec, unsigned int mask,
-				bool enabled)
+				int polarity, bool enabled)
 {
-	struct alc_spec *spec = codec->spec;
-
-	if (spec->mute_led_polarity)
+	if (polarity)
 		enabled = !enabled;
 	alc_update_gpio_data(codec, mask, !enabled); /* muted -> LED on */
 }
@@ -3959,7 +4094,8 @@ static void alc_fixup_gpio_mute_hook(void *private_data, int enabled)
 	struct hda_codec *codec = private_data;
 	struct alc_spec *spec = codec->spec;
 
-	alc_update_gpio_led(codec, spec->gpio_mute_led_mask, enabled);
+	alc_update_gpio_led(codec, spec->gpio_mute_led_mask,
+			    spec->mute_led_polarity, enabled);
 }
 
 /* turn on/off mic-mute LED via GPIO per capture hook */
@@ -3968,6 +4104,7 @@ static void alc_gpio_micmute_update(struct hda_codec *codec)
 	struct alc_spec *spec = codec->spec;
 
 	alc_update_gpio_led(codec, spec->gpio_mic_led_mask,
+			    spec->micmute_led_polarity,
 			    spec->gen.micmute_led.led_value);
 }
 
@@ -3999,6 +4136,12 @@ static void alc269_fixup_hp_gpio_led(struct hda_codec *codec,
 	alc_fixup_hp_gpio_led(codec, action, 0x08, 0x10);
 }
 
+static void alc285_fixup_hp_gpio_led(struct hda_codec *codec,
+				const struct hda_fixup *fix, int action)
+{
+	alc_fixup_hp_gpio_led(codec, action, 0x04, 0x00);
+}
+
 static void alc286_fixup_hp_gpio_led(struct hda_codec *codec,
 				const struct hda_fixup *fix, int action)
 {
@@ -4053,6 +4196,111 @@ static void alc280_fixup_hp_gpio4(struct hda_codec *codec,
 	}
 }
 
+/* update mute-LED according to the speaker mute state via COEF bit */
+static void alc_fixup_mute_led_coefbit_hook(void *private_data, int enabled)
+{
+	struct hda_codec *codec = private_data;
+	struct alc_spec *spec = codec->spec;
+
+	if (spec->mute_led_polarity)
+		enabled = !enabled;
+
+	/* temporarily power up/down for setting COEF bit */
+	enabled ? alc_update_coef_idx(codec, spec->mute_led_coef_idx,
+		spec->mute_led_coefbit_mask, spec->mute_led_coefbit_off) :
+		  alc_update_coef_idx(codec, spec->mute_led_coef_idx,
+		spec->mute_led_coefbit_mask, spec->mute_led_coefbit_on);
+}
+
+static void alc285_fixup_hp_mute_led_coefbit(struct hda_codec *codec,
+					  const struct hda_fixup *fix,
+					  int action)
+{
+	struct alc_spec *spec = codec->spec;
+
+	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		spec->mute_led_polarity = 0;
+		spec->mute_led_coef_idx = 0x0b;
+		spec->mute_led_coefbit_mask = 1<<3;
+		spec->mute_led_coefbit_on = 1<<3;
+		spec->mute_led_coefbit_off = 0;
+		spec->gen.vmaster_mute.hook = alc_fixup_mute_led_coefbit_hook;
+		spec->gen.vmaster_mute_enum = 1;
+	}
+}
+
+static void alc236_fixup_hp_mute_led_coefbit(struct hda_codec *codec,
+					  const struct hda_fixup *fix,
+					  int action)
+{
+	struct alc_spec *spec = codec->spec;
+
+	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		spec->mute_led_polarity = 0;
+		spec->mute_led_coef_idx = 0x34;
+		spec->mute_led_coefbit_mask = 1<<5;
+		spec->mute_led_coefbit_on = 0;
+		spec->mute_led_coefbit_off = 1<<5;
+		spec->gen.vmaster_mute.hook = alc_fixup_mute_led_coefbit_hook;
+		spec->gen.vmaster_mute_enum = 1;
+	}
+}
+
+/* turn on/off mic-mute LED per capture hook by coef bit */
+static void alc_hp_cap_micmute_update(struct hda_codec *codec)
+{
+	struct alc_spec *spec = codec->spec;
+
+	if (spec->gen.micmute_led.led_value)
+		alc_update_coef_idx(codec, spec->mic_led_coef_idx,
+			spec->mic_led_coefbit_mask, spec->mic_led_coefbit_on);
+	else
+		alc_update_coef_idx(codec, spec->mic_led_coef_idx,
+			spec->mic_led_coefbit_mask, spec->mic_led_coefbit_off);
+}
+
+static void alc285_fixup_hp_coef_micmute_led(struct hda_codec *codec,
+				const struct hda_fixup *fix, int action)
+{
+	struct alc_spec *spec = codec->spec;
+
+	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		spec->mic_led_coef_idx = 0x19;
+		spec->mic_led_coefbit_mask = 1<<13;
+		spec->mic_led_coefbit_on = 1<<13;
+		spec->mic_led_coefbit_off = 0;
+		snd_hda_gen_add_micmute_led(codec, alc_hp_cap_micmute_update);
+	}
+}
+
+static void alc236_fixup_hp_coef_micmute_led(struct hda_codec *codec,
+				const struct hda_fixup *fix, int action)
+{
+	struct alc_spec *spec = codec->spec;
+
+	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		spec->mic_led_coef_idx = 0x35;
+		spec->mic_led_coefbit_mask = 3<<2;
+		spec->mic_led_coefbit_on = 2<<2;
+		spec->mic_led_coefbit_off = 1<<2;
+		snd_hda_gen_add_micmute_led(codec, alc_hp_cap_micmute_update);
+	}
+}
+
+static void alc285_fixup_hp_mute_led(struct hda_codec *codec,
+				const struct hda_fixup *fix, int action)
+{
+	alc285_fixup_hp_mute_led_coefbit(codec, fix, action);
+	alc285_fixup_hp_coef_micmute_led(codec, fix, action);
+}
+
+static void alc236_fixup_hp_mute_led(struct hda_codec *codec,
+				const struct hda_fixup *fix, int action)
+{
+	alc236_fixup_hp_mute_led_coefbit(codec, fix, action);
+	alc236_fixup_hp_coef_micmute_led(codec, fix, action);
+}
+
 #if IS_REACHABLE(CONFIG_INPUT)
 static void gpio2_mic_hotkey_event(struct hda_codec *codec,
 				   struct hda_jack_callback *event)
@@ -4142,6 +4390,7 @@ static void alc233_fixup_lenovo_line2_mic_hotkey(struct hda_codec *codec,
 {
 	struct alc_spec *spec = codec->spec;
 
+	spec->micmute_led_polarity = 1;
 	alc_fixup_hp_gpio_led(codec, action, 0, 0x04);
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
 		spec->init_amp = ALC_INIT_DEFAULT;
@@ -4179,7 +4428,7 @@ static void alc269_fixup_hp_line1_mic1_led(struct hda_codec *codec,
 	}
 }
 
-static struct coef_fw alc225_pre_hsmode[] = {
+static const struct coef_fw alc225_pre_hsmode[] = {
 	UPDATE_COEF(0x4a, 1<<8, 0),
 	UPDATE_COEFEX(0x57, 0x05, 1<<14, 0),
 	UPDATE_COEF(0x63, 3<<14, 3<<14),
@@ -4192,7 +4441,7 @@ static struct coef_fw alc225_pre_hsmode[] = {
 
 static void alc_headset_mode_unplugged(struct hda_codec *codec)
 {
-	static struct coef_fw coef0255[] = {
+	static const struct coef_fw coef0255[] = {
 		WRITE_COEF(0x1b, 0x0c0b), /* LDO and MISC control */
 		WRITE_COEF(0x45, 0xd089), /* UAJ function set to menual mode */
 		UPDATE_COEFEX(0x57, 0x05, 1<<14, 0), /* Direct Drive HP Amp control(Set to verb control)*/
@@ -4200,7 +4449,7 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec)
 		WRITE_COEFEX(0x57, 0x03, 0x8aa6), /* Direct Drive HP Amp control */
 		{}
 	};
-	static struct coef_fw coef0256[] = {
+	static const struct coef_fw coef0256[] = {
 		WRITE_COEF(0x1b, 0x0c4b), /* LDO and MISC control */
 		WRITE_COEF(0x45, 0xd089), /* UAJ function set to menual mode */
 		WRITE_COEF(0x06, 0x6104), /* Set MIC2 Vref gate with HP */
@@ -4208,7 +4457,7 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec)
 		UPDATE_COEFEX(0x57, 0x05, 1<<14, 0), /* Direct Drive HP Amp control(Set to verb control)*/
 		{}
 	};
-	static struct coef_fw coef0233[] = {
+	static const struct coef_fw coef0233[] = {
 		WRITE_COEF(0x1b, 0x0c0b),
 		WRITE_COEF(0x45, 0xc429),
 		UPDATE_COEF(0x35, 0x4000, 0),
@@ -4218,7 +4467,7 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec)
 		WRITE_COEF(0x32, 0x42a3),
 		{}
 	};
-	static struct coef_fw coef0288[] = {
+	static const struct coef_fw coef0288[] = {
 		UPDATE_COEF(0x4f, 0xfcc0, 0xc400),
 		UPDATE_COEF(0x50, 0x2000, 0x2000),
 		UPDATE_COEF(0x56, 0x0006, 0x0006),
@@ -4226,18 +4475,18 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec)
 		UPDATE_COEF(0x67, 0x2000, 0),
 		{}
 	};
-	static struct coef_fw coef0298[] = {
+	static const struct coef_fw coef0298[] = {
 		UPDATE_COEF(0x19, 0x1300, 0x0300),
 		{}
 	};
-	static struct coef_fw coef0292[] = {
+	static const struct coef_fw coef0292[] = {
 		WRITE_COEF(0x76, 0x000e),
 		WRITE_COEF(0x6c, 0x2400),
 		WRITE_COEF(0x18, 0x7308),
 		WRITE_COEF(0x6b, 0xc429),
 		{}
 	};
-	static struct coef_fw coef0293[] = {
+	static const struct coef_fw coef0293[] = {
 		UPDATE_COEF(0x10, 7<<8, 6<<8), /* SET Line1 JD to 0 */
 		UPDATE_COEFEX(0x57, 0x05, 1<<15|1<<13, 0x0), /* SET charge pump by verb */
 		UPDATE_COEFEX(0x57, 0x03, 1<<10, 1<<10), /* SET EN_OSW to 1 */
@@ -4246,16 +4495,16 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec)
 		UPDATE_COEF(0x4a, 0x000f, 0x000e), /* Combo Jack auto detect */
 		{}
 	};
-	static struct coef_fw coef0668[] = {
+	static const struct coef_fw coef0668[] = {
 		WRITE_COEF(0x15, 0x0d40),
 		WRITE_COEF(0xb7, 0x802b),
 		{}
 	};
-	static struct coef_fw coef0225[] = {
+	static const struct coef_fw coef0225[] = {
 		UPDATE_COEF(0x63, 3<<14, 0),
 		{}
 	};
-	static struct coef_fw coef0274[] = {
+	static const struct coef_fw coef0274[] = {
 		UPDATE_COEF(0x4a, 0x0100, 0),
 		UPDATE_COEFEX(0x57, 0x05, 0x4000, 0),
 		UPDATE_COEF(0x6b, 0xf000, 0x5000),
@@ -4320,25 +4569,25 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec)
 static void alc_headset_mode_mic_in(struct hda_codec *codec, hda_nid_t hp_pin,
 				    hda_nid_t mic_pin)
 {
-	static struct coef_fw coef0255[] = {
+	static const struct coef_fw coef0255[] = {
 		WRITE_COEFEX(0x57, 0x03, 0x8aa6),
 		WRITE_COEF(0x06, 0x6100), /* Set MIC2 Vref gate to normal */
 		{}
 	};
-	static struct coef_fw coef0256[] = {
+	static const struct coef_fw coef0256[] = {
 		UPDATE_COEFEX(0x57, 0x05, 1<<14, 1<<14), /* Direct Drive HP Amp control(Set to verb control)*/
 		WRITE_COEFEX(0x57, 0x03, 0x09a3),
 		WRITE_COEF(0x06, 0x6100), /* Set MIC2 Vref gate to normal */
 		{}
 	};
-	static struct coef_fw coef0233[] = {
+	static const struct coef_fw coef0233[] = {
 		UPDATE_COEF(0x35, 0, 1<<14),
 		WRITE_COEF(0x06, 0x2100),
 		WRITE_COEF(0x1a, 0x0021),
 		WRITE_COEF(0x26, 0x008c),
 		{}
 	};
-	static struct coef_fw coef0288[] = {
+	static const struct coef_fw coef0288[] = {
 		UPDATE_COEF(0x4f, 0x00c0, 0),
 		UPDATE_COEF(0x50, 0x2000, 0),
 		UPDATE_COEF(0x56, 0x0006, 0),
@@ -4347,30 +4596,30 @@ static void alc_headset_mode_mic_in(struct hda_codec *codec, hda_nid_t hp_pin,
 		UPDATE_COEF(0x67, 0x2000, 0x2000),
 		{}
 	};
-	static struct coef_fw coef0292[] = {
+	static const struct coef_fw coef0292[] = {
 		WRITE_COEF(0x19, 0xa208),
 		WRITE_COEF(0x2e, 0xacf0),
 		{}
 	};
-	static struct coef_fw coef0293[] = {
+	static const struct coef_fw coef0293[] = {
 		UPDATE_COEFEX(0x57, 0x05, 0, 1<<15|1<<13), /* SET charge pump by verb */
 		UPDATE_COEFEX(0x57, 0x03, 1<<10, 0), /* SET EN_OSW to 0 */
 		UPDATE_COEF(0x1a, 1<<3, 0), /* Combo JD gating without LINE1-VREFO */
 		{}
 	};
-	static struct coef_fw coef0688[] = {
+	static const struct coef_fw coef0688[] = {
 		WRITE_COEF(0xb7, 0x802b),
 		WRITE_COEF(0xb5, 0x1040),
 		UPDATE_COEF(0xc3, 0, 1<<12),
 		{}
 	};
-	static struct coef_fw coef0225[] = {
+	static const struct coef_fw coef0225[] = {
 		UPDATE_COEFEX(0x57, 0x05, 1<<14, 1<<14),
 		UPDATE_COEF(0x4a, 3<<4, 2<<4),
 		UPDATE_COEF(0x63, 3<<14, 0),
 		{}
 	};
-	static struct coef_fw coef0274[] = {
+	static const struct coef_fw coef0274[] = {
 		UPDATE_COEFEX(0x57, 0x05, 0x4000, 0x4000),
 		UPDATE_COEF(0x4a, 0x0010, 0),
 		UPDATE_COEF(0x6b, 0xf000, 0),
@@ -4456,7 +4705,7 @@ static void alc_headset_mode_mic_in(struct hda_codec *codec, hda_nid_t hp_pin,
 
 static void alc_headset_mode_default(struct hda_codec *codec)
 {
-	static struct coef_fw coef0225[] = {
+	static const struct coef_fw coef0225[] = {
 		UPDATE_COEF(0x45, 0x3f<<10, 0x30<<10),
 		UPDATE_COEF(0x45, 0x3f<<10, 0x31<<10),
 		UPDATE_COEF(0x49, 3<<8, 0<<8),
@@ -4465,14 +4714,14 @@ static void alc_headset_mode_default(struct hda_codec *codec)
 		UPDATE_COEF(0x67, 0xf000, 0x3000),
 		{}
 	};
-	static struct coef_fw coef0255[] = {
+	static const struct coef_fw coef0255[] = {
 		WRITE_COEF(0x45, 0xc089),
 		WRITE_COEF(0x45, 0xc489),
 		WRITE_COEFEX(0x57, 0x03, 0x8ea6),
 		WRITE_COEF(0x49, 0x0049),
 		{}
 	};
-	static struct coef_fw coef0256[] = {
+	static const struct coef_fw coef0256[] = {
 		WRITE_COEF(0x45, 0xc489),
 		WRITE_COEFEX(0x57, 0x03, 0x0da3),
 		WRITE_COEF(0x49, 0x0049),
@@ -4480,12 +4729,12 @@ static void alc_headset_mode_default(struct hda_codec *codec)
 		WRITE_COEF(0x06, 0x6100),
 		{}
 	};
-	static struct coef_fw coef0233[] = {
+	static const struct coef_fw coef0233[] = {
 		WRITE_COEF(0x06, 0x2100),
 		WRITE_COEF(0x32, 0x4ea3),
 		{}
 	};
-	static struct coef_fw coef0288[] = {
+	static const struct coef_fw coef0288[] = {
 		UPDATE_COEF(0x4f, 0xfcc0, 0xc400), /* Set to TRS type */
 		UPDATE_COEF(0x50, 0x2000, 0x2000),
 		UPDATE_COEF(0x56, 0x0006, 0x0006),
@@ -4493,26 +4742,26 @@ static void alc_headset_mode_default(struct hda_codec *codec)
 		UPDATE_COEF(0x67, 0x2000, 0),
 		{}
 	};
-	static struct coef_fw coef0292[] = {
+	static const struct coef_fw coef0292[] = {
 		WRITE_COEF(0x76, 0x000e),
 		WRITE_COEF(0x6c, 0x2400),
 		WRITE_COEF(0x6b, 0xc429),
 		WRITE_COEF(0x18, 0x7308),
 		{}
 	};
-	static struct coef_fw coef0293[] = {
+	static const struct coef_fw coef0293[] = {
 		UPDATE_COEF(0x4a, 0x000f, 0x000e), /* Combo Jack auto detect */
 		WRITE_COEF(0x45, 0xC429), /* Set to TRS type */
 		UPDATE_COEF(0x1a, 1<<3, 0), /* Combo JD gating without LINE1-VREFO */
 		{}
 	};
-	static struct coef_fw coef0688[] = {
+	static const struct coef_fw coef0688[] = {
 		WRITE_COEF(0x11, 0x0041),
 		WRITE_COEF(0x15, 0x0d40),
 		WRITE_COEF(0xb7, 0x802b),
 		{}
 	};
-	static struct coef_fw coef0274[] = {
+	static const struct coef_fw coef0274[] = {
 		WRITE_COEF(0x45, 0x4289),
 		UPDATE_COEF(0x4a, 0x0010, 0x0010),
 		UPDATE_COEF(0x6b, 0x0f00, 0),
@@ -4575,53 +4824,53 @@ static void alc_headset_mode_ctia(struct hda_codec *codec)
 {
 	int val;
 
-	static struct coef_fw coef0255[] = {
+	static const struct coef_fw coef0255[] = {
 		WRITE_COEF(0x45, 0xd489), /* Set to CTIA type */
 		WRITE_COEF(0x1b, 0x0c2b),
 		WRITE_COEFEX(0x57, 0x03, 0x8ea6),
 		{}
 	};
-	static struct coef_fw coef0256[] = {
+	static const struct coef_fw coef0256[] = {
 		WRITE_COEF(0x45, 0xd489), /* Set to CTIA type */
 		WRITE_COEF(0x1b, 0x0e6b),
 		{}
 	};
-	static struct coef_fw coef0233[] = {
+	static const struct coef_fw coef0233[] = {
 		WRITE_COEF(0x45, 0xd429),
 		WRITE_COEF(0x1b, 0x0c2b),
 		WRITE_COEF(0x32, 0x4ea3),
 		{}
 	};
-	static struct coef_fw coef0288[] = {
+	static const struct coef_fw coef0288[] = {
 		UPDATE_COEF(0x50, 0x2000, 0x2000),
 		UPDATE_COEF(0x56, 0x0006, 0x0006),
 		UPDATE_COEF(0x66, 0x0008, 0),
 		UPDATE_COEF(0x67, 0x2000, 0),
 		{}
 	};
-	static struct coef_fw coef0292[] = {
+	static const struct coef_fw coef0292[] = {
 		WRITE_COEF(0x6b, 0xd429),
 		WRITE_COEF(0x76, 0x0008),
 		WRITE_COEF(0x18, 0x7388),
 		{}
 	};
-	static struct coef_fw coef0293[] = {
+	static const struct coef_fw coef0293[] = {
 		WRITE_COEF(0x45, 0xd429), /* Set to ctia type */
 		UPDATE_COEF(0x10, 7<<8, 7<<8), /* SET Line1 JD to 1 */
 		{}
 	};
-	static struct coef_fw coef0688[] = {
+	static const struct coef_fw coef0688[] = {
 		WRITE_COEF(0x11, 0x0001),
 		WRITE_COEF(0x15, 0x0d60),
 		WRITE_COEF(0xc3, 0x0000),
 		{}
 	};
-	static struct coef_fw coef0225_1[] = {
+	static const struct coef_fw coef0225_1[] = {
 		UPDATE_COEF(0x45, 0x3f<<10, 0x35<<10),
 		UPDATE_COEF(0x63, 3<<14, 2<<14),
 		{}
 	};
-	static struct coef_fw coef0225_2[] = {
+	static const struct coef_fw coef0225_2[] = {
 		UPDATE_COEF(0x45, 0x3f<<10, 0x35<<10),
 		UPDATE_COEF(0x63, 3<<14, 1<<14),
 		{}
@@ -4693,48 +4942,48 @@ static void alc_headset_mode_ctia(struct hda_codec *codec)
 /* Nokia type */
 static void alc_headset_mode_omtp(struct hda_codec *codec)
 {
-	static struct coef_fw coef0255[] = {
+	static const struct coef_fw coef0255[] = {
 		WRITE_COEF(0x45, 0xe489), /* Set to OMTP Type */
 		WRITE_COEF(0x1b, 0x0c2b),
 		WRITE_COEFEX(0x57, 0x03, 0x8ea6),
 		{}
 	};
-	static struct coef_fw coef0256[] = {
+	static const struct coef_fw coef0256[] = {
 		WRITE_COEF(0x45, 0xe489), /* Set to OMTP Type */
 		WRITE_COEF(0x1b, 0x0e6b),
 		{}
 	};
-	static struct coef_fw coef0233[] = {
+	static const struct coef_fw coef0233[] = {
 		WRITE_COEF(0x45, 0xe429),
 		WRITE_COEF(0x1b, 0x0c2b),
 		WRITE_COEF(0x32, 0x4ea3),
 		{}
 	};
-	static struct coef_fw coef0288[] = {
+	static const struct coef_fw coef0288[] = {
 		UPDATE_COEF(0x50, 0x2000, 0x2000),
 		UPDATE_COEF(0x56, 0x0006, 0x0006),
 		UPDATE_COEF(0x66, 0x0008, 0),
 		UPDATE_COEF(0x67, 0x2000, 0),
 		{}
 	};
-	static struct coef_fw coef0292[] = {
+	static const struct coef_fw coef0292[] = {
 		WRITE_COEF(0x6b, 0xe429),
 		WRITE_COEF(0x76, 0x0008),
 		WRITE_COEF(0x18, 0x7388),
 		{}
 	};
-	static struct coef_fw coef0293[] = {
+	static const struct coef_fw coef0293[] = {
 		WRITE_COEF(0x45, 0xe429), /* Set to omtp type */
 		UPDATE_COEF(0x10, 7<<8, 7<<8), /* SET Line1 JD to 1 */
 		{}
 	};
-	static struct coef_fw coef0688[] = {
+	static const struct coef_fw coef0688[] = {
 		WRITE_COEF(0x11, 0x0001),
 		WRITE_COEF(0x15, 0x0d50),
 		WRITE_COEF(0xc3, 0x0000),
 		{}
 	};
-	static struct coef_fw coef0225[] = {
+	static const struct coef_fw coef0225[] = {
 		UPDATE_COEF(0x45, 0x3f<<10, 0x39<<10),
 		UPDATE_COEF(0x63, 3<<14, 2<<14),
 		{}
@@ -4794,17 +5043,17 @@ static void alc_determine_headset_type(struct hda_codec *codec)
 	int val;
 	bool is_ctia = false;
 	struct alc_spec *spec = codec->spec;
-	static struct coef_fw coef0255[] = {
+	static const struct coef_fw coef0255[] = {
 		WRITE_COEF(0x45, 0xd089), /* combo jack auto switch control(Check type)*/
 		WRITE_COEF(0x49, 0x0149), /* combo jack auto switch control(Vref
  conteol) */
 		{}
 	};
-	static struct coef_fw coef0288[] = {
+	static const struct coef_fw coef0288[] = {
 		UPDATE_COEF(0x4f, 0xfcc0, 0xd400), /* Check Type */
 		{}
 	};
-	static struct coef_fw coef0298[] = {
+	static const struct coef_fw coef0298[] = {
 		UPDATE_COEF(0x50, 0x2000, 0x2000),
 		UPDATE_COEF(0x56, 0x0006, 0x0006),
 		UPDATE_COEF(0x66, 0x0008, 0),
@@ -4812,19 +5061,19 @@ static void alc_determine_headset_type(struct hda_codec *codec)
 		UPDATE_COEF(0x19, 0x1300, 0x1300),
 		{}
 	};
-	static struct coef_fw coef0293[] = {
+	static const struct coef_fw coef0293[] = {
 		UPDATE_COEF(0x4a, 0x000f, 0x0008), /* Combo Jack auto detect */
 		WRITE_COEF(0x45, 0xD429), /* Set to ctia type */
 		{}
 	};
-	static struct coef_fw coef0688[] = {
+	static const struct coef_fw coef0688[] = {
 		WRITE_COEF(0x11, 0x0001),
 		WRITE_COEF(0xb7, 0x802b),
 		WRITE_COEF(0x15, 0x0d60),
 		WRITE_COEF(0xc3, 0x0c00),
 		{}
 	};
-	static struct coef_fw coef0274[] = {
+	static const struct coef_fw coef0274[] = {
 		UPDATE_COEF(0x4a, 0x0010, 0),
 		UPDATE_COEF(0x4a, 0x8000, 0),
 		WRITE_COEF(0x45, 0xd289),
@@ -5111,7 +5360,7 @@ static void alc_fixup_headset_mode_no_hp_mic(struct hda_codec *codec,
 static void alc255_set_default_jack_type(struct hda_codec *codec)
 {
 	/* Set to iphone type */
-	static struct coef_fw alc255fw[] = {
+	static const struct coef_fw alc255fw[] = {
 		WRITE_COEF(0x1b, 0x880b),
 		WRITE_COEF(0x45, 0xd089),
 		WRITE_COEF(0x1b, 0x080b),
@@ -5119,7 +5368,7 @@ static void alc255_set_default_jack_type(struct hda_codec *codec)
 		WRITE_COEF(0x1b, 0x0c0b),
 		{}
 	};
-	static struct coef_fw alc256fw[] = {
+	static const struct coef_fw alc256fw[] = {
 		WRITE_COEF(0x1b, 0x884b),
 		WRITE_COEF(0x45, 0xd089),
 		WRITE_COEF(0x1b, 0x084b),
@@ -5238,18 +5487,9 @@ static void alc_fixup_tpt470_dock(struct hda_codec *codec,
 		{ 0x19, 0x21a11010 }, /* dock mic */
 		{ }
 	};
-	/* Assure the speaker pin to be coupled with DAC NID 0x03; otherwise
-	 * the speaker output becomes too low by some reason on Thinkpads with
-	 * ALC298 codec
-	 */
-	static hda_nid_t preferred_pairs[] = {
-		0x14, 0x03, 0x17, 0x02, 0x21, 0x02,
-		0
-	};
 	struct alc_spec *spec = codec->spec;
 
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
-		spec->gen.preferred_dacs = preferred_pairs;
 		spec->parse_flags = HDA_PINCFG_NO_HP_FIXUP;
 		snd_hda_apply_pincfgs(codec, pincfgs);
 	} else if (action == HDA_FIXUP_ACT_INIT) {
@@ -5262,6 +5502,23 @@ static void alc_fixup_tpt470_dock(struct hda_codec *codec,
 	}
 }
 
+static void alc_fixup_tpt470_dacs(struct hda_codec *codec,
+				  const struct hda_fixup *fix, int action)
+{
+	/* Assure the speaker pin to be coupled with DAC NID 0x03; otherwise
+	 * the speaker output becomes too low by some reason on Thinkpads with
+	 * ALC298 codec
+	 */
+	static const hda_nid_t preferred_pairs[] = {
+		0x14, 0x03, 0x17, 0x02, 0x21, 0x02,
+		0
+	};
+	struct alc_spec *spec = codec->spec;
+
+	if (action == HDA_FIXUP_ACT_PRE_PROBE)
+		spec->gen.preferred_dacs = preferred_pairs;
+}
+
 static void alc_shutup_dell_xps13(struct hda_codec *codec)
 {
 	struct alc_spec *spec = codec->spec;
@@ -5503,9 +5760,9 @@ static void alc290_fixup_mono_speakers(struct hda_codec *codec,
 		/* DAC node 0x03 is giving mono output. We therefore want to
 		   make sure 0x14 (front speaker) and 0x15 (headphones) use the
 		   stereo DAC, while leaving 0x17 (bass speaker) for node 0x03. */
-		hda_nid_t conn1[2] = { 0x0c };
-		snd_hda_override_conn_list(codec, 0x14, 1, conn1);
-		snd_hda_override_conn_list(codec, 0x15, 1, conn1);
+		static const hda_nid_t conn1[] = { 0x0c };
+		snd_hda_override_conn_list(codec, 0x14, ARRAY_SIZE(conn1), conn1);
+		snd_hda_override_conn_list(codec, 0x15, ARRAY_SIZE(conn1), conn1);
 	}
 }
 
@@ -5520,8 +5777,8 @@ static void alc298_fixup_speaker_volume(struct hda_codec *codec,
 		   Pin Complex), since Node 0x02 has Amp-out caps, we can adjust
 		   speaker's volume now. */
 
-		hda_nid_t conn1[1] = { 0x0c };
-		snd_hda_override_conn_list(codec, 0x17, 1, conn1);
+		static const hda_nid_t conn1[] = { 0x0c };
+		snd_hda_override_conn_list(codec, 0x17, ARRAY_SIZE(conn1), conn1);
 	}
 }
 
@@ -5530,8 +5787,18 @@ static void alc295_fixup_disable_dac3(struct hda_codec *codec,
 				      const struct hda_fixup *fix, int action)
 {
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
-		hda_nid_t conn[2] = { 0x02, 0x03 };
-		snd_hda_override_conn_list(codec, 0x17, 2, conn);
+		static const hda_nid_t conn[] = { 0x02, 0x03 };
+		snd_hda_override_conn_list(codec, 0x17, ARRAY_SIZE(conn), conn);
+	}
+}
+
+/* force NID 0x17 (Bass Speaker) to DAC1 to share it with the main speaker */
+static void alc285_fixup_speaker2_to_dac1(struct hda_codec *codec,
+					  const struct hda_fixup *fix, int action)
+{
+	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		static const hda_nid_t conn[] = { 0x02 };
+		snd_hda_override_conn_list(codec, 0x17, ARRAY_SIZE(conn), conn);
 	}
 }
 
@@ -5543,7 +5810,8 @@ static void alc280_hp_gpio4_automute_hook(struct hda_codec *codec,
 
 	snd_hda_gen_hp_automute(codec, jack);
 	/* mute_led_polarity is set to 0, so we pass inverted value here */
-	alc_update_gpio_led(codec, 0x10, !spec->gen.hp_jack_present);
+	alc_update_gpio_led(codec, 0x10, spec->mute_led_polarity,
+			    !spec->gen.hp_jack_present);
 }
 
 /* Manage GPIOs for HP EliteBook Folio 9480m.
@@ -5580,6 +5848,39 @@ static void alc275_fixup_gpio4_off(struct hda_codec *codec,
 	}
 }
 
+/* Quirk for Thinkpad X1 7th and 8th Gen
+ * The following fixed routing needed
+ * DAC1 (NID 0x02) -> Speaker (NID 0x14); some eq applied secretly
+ * DAC2 (NID 0x03) -> Bass (NID 0x17) & Headphone (NID 0x21); sharing a DAC
+ * DAC3 (NID 0x06) -> Unused, due to the lack of volume amp
+ */
+static void alc285_fixup_thinkpad_x1_gen7(struct hda_codec *codec,
+					  const struct hda_fixup *fix, int action)
+{
+	static const hda_nid_t conn[] = { 0x02, 0x03 }; /* exclude 0x06 */
+	static const hda_nid_t preferred_pairs[] = {
+		0x14, 0x02, 0x17, 0x03, 0x21, 0x03, 0
+	};
+	struct alc_spec *spec = codec->spec;
+
+	switch (action) {
+	case HDA_FIXUP_ACT_PRE_PROBE:
+		snd_hda_override_conn_list(codec, 0x17, ARRAY_SIZE(conn), conn);
+		spec->gen.preferred_dacs = preferred_pairs;
+		break;
+	case HDA_FIXUP_ACT_BUILD:
+		/* The generic parser creates somewhat unintuitive volume ctls
+		 * with the fixed routing above, and the shared DAC2 may be
+		 * confusing for PA.
+		 * Rename those to unique names so that PA doesn't touch them
+		 * and use only Master volume.
+		 */
+		rename_ctl(codec, "Front Playback Volume", "DAC1 Playback Volume");
+		rename_ctl(codec, "Bass Speaker Playback Volume", "DAC2 Playback Volume");
+		break;
+	}
+}
+
 static void alc233_alc662_fixup_lenovo_dual_codecs(struct hda_codec *codec,
 					 const struct hda_fixup *fix,
 					 int action)
@@ -5604,12 +5905,21 @@ static void alc233_alc662_fixup_lenovo_dual_codecs(struct hda_codec *codec,
 	}
 }
 
+static void alc225_fixup_s3_pop_noise(struct hda_codec *codec,
+				      const struct hda_fixup *fix, int action)
+{
+	if (action != HDA_FIXUP_ACT_PRE_PROBE)
+		return;
+
+	codec->power_save_node = 1;
+}
+
 /* Forcibly assign NID 0x03 to HP/LO while NID 0x02 to SPK for EQ */
 static void alc274_fixup_bind_dacs(struct hda_codec *codec,
 				    const struct hda_fixup *fix, int action)
 {
 	struct alc_spec *spec = codec->spec;
-	static hda_nid_t preferred_pairs[] = {
+	static const hda_nid_t preferred_pairs[] = {
 		0x21, 0x03, 0x1b, 0x03, 0x16, 0x02,
 		0
 	};
@@ -5632,66 +5942,6 @@ static void alc285_fixup_invalidate_dacs(struct hda_codec *codec,
 	snd_hda_override_wcaps(codec, 0x03, 0);
 }
 
-static const struct hda_jack_keymap alc_headset_btn_keymap[] = {
-	{ SND_JACK_BTN_0, KEY_PLAYPAUSE },
-	{ SND_JACK_BTN_1, KEY_VOICECOMMAND },
-	{ SND_JACK_BTN_2, KEY_VOLUMEUP },
-	{ SND_JACK_BTN_3, KEY_VOLUMEDOWN },
-	{}
-};
-
-static void alc_headset_btn_callback(struct hda_codec *codec,
-				     struct hda_jack_callback *jack)
-{
-	int report = 0;
-
-	if (jack->unsol_res & (7 << 13))
-		report |= SND_JACK_BTN_0;
-
-	if (jack->unsol_res  & (1 << 16 | 3 << 8))
-		report |= SND_JACK_BTN_1;
-
-	/* Volume up key */
-	if (jack->unsol_res & (7 << 23))
-		report |= SND_JACK_BTN_2;
-
-	/* Volume down key */
-	if (jack->unsol_res & (7 << 10))
-		report |= SND_JACK_BTN_3;
-
-	jack->jack->button_state = report;
-}
-
-static void alc_fixup_headset_jack(struct hda_codec *codec,
-				    const struct hda_fixup *fix, int action)
-{
-
-	switch (action) {
-	case HDA_FIXUP_ACT_PRE_PROBE:
-		snd_hda_jack_detect_enable_callback(codec, 0x55,
-						    alc_headset_btn_callback);
-		snd_hda_jack_add_kctl(codec, 0x55, "Headset Jack", false,
-				      SND_JACK_HEADSET, alc_headset_btn_keymap);
-		break;
-	case HDA_FIXUP_ACT_INIT:
-		switch (codec->core.vendor_id) {
-		case 0x10ec0225:
-		case 0x10ec0295:
-		case 0x10ec0299:
-			alc_write_coef_idx(codec, 0x48, 0xd011);
-			alc_update_coef_idx(codec, 0x49, 0x007f, 0x0045);
-			alc_update_coef_idx(codec, 0x44, 0x007f << 8, 0x0045 << 8);
-			break;
-		case 0x10ec0236:
-		case 0x10ec0256:
-			alc_write_coef_idx(codec, 0x48, 0xd011);
-			alc_update_coef_idx(codec, 0x49, 0x007f, 0x0045);
-			break;
-		}
-		break;
-	}
-}
-
 static void alc295_fixup_chromebook(struct hda_codec *codec,
 				    const struct hda_fixup *fix, int action)
 {
@@ -5723,6 +5973,16 @@ static void alc_fixup_disable_mic_vref(struct hda_codec *codec,
 		snd_hda_codec_set_pin_target(codec, 0x19, PIN_VREFHIZ);
 }
 
+static void  alc285_fixup_hp_gpio_amp_init(struct hda_codec *codec,
+			      const struct hda_fixup *fix, int action)
+{
+	if (action != HDA_FIXUP_ACT_INIT)
+		return;
+
+	msleep(100);
+	alc_write_coef_idx(codec, 0x65, 0x0);
+}
+
 /* for hda_fixup_thinkpad_acpi() */
 #include "thinkpad_helper.c"
 
@@ -5768,6 +6028,7 @@ enum {
 	ALC269_FIXUP_HP_LINE1_MIC1_LED,
 	ALC269_FIXUP_INV_DMIC,
 	ALC269_FIXUP_LENOVO_DOCK,
+	ALC269_FIXUP_LENOVO_DOCK_LIMIT_BOOST,
 	ALC269_FIXUP_NO_SHUTUP,
 	ALC286_FIXUP_SONY_MIC_NO_PRESENCE,
 	ALC269_FIXUP_PINCFG_NO_HP_TO_LINEOUT,
@@ -5828,13 +6089,13 @@ enum {
 	ALC298_FIXUP_DELL1_MIC_NO_PRESENCE,
 	ALC298_FIXUP_DELL_AIO_MIC_NO_PRESENCE,
 	ALC275_FIXUP_DELL_XPS,
-	ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE,
 	ALC293_FIXUP_LENOVO_SPK_NOISE,
 	ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY,
 	ALC255_FIXUP_DELL_SPK_NOISE,
 	ALC225_FIXUP_DISABLE_MIC_VREF,
 	ALC225_FIXUP_DELL1_MIC_NO_PRESENCE,
 	ALC295_FIXUP_DISABLE_DAC3,
+	ALC285_FIXUP_SPEAKER2_TO_DAC1,
 	ALC280_FIXUP_HP_HEADSET_MIC,
 	ALC221_FIXUP_HP_FRONT_MIC,
 	ALC292_FIXUP_TPT460,
@@ -5851,9 +6112,11 @@ enum {
 	ALC233_FIXUP_ACER_HEADSET_MIC,
 	ALC294_FIXUP_LENOVO_MIC_LOCATION,
 	ALC225_FIXUP_DELL_WYSE_MIC_NO_PRESENCE,
+	ALC225_FIXUP_S3_POP_NOISE,
 	ALC700_FIXUP_INTEL_REFERENCE,
 	ALC274_FIXUP_DELL_BIND_DACS,
 	ALC274_FIXUP_DELL_AIO_LINEOUT_VERB,
+	ALC298_FIXUP_TPT470_DOCK_FIX,
 	ALC298_FIXUP_TPT470_DOCK,
 	ALC255_FIXUP_DUMMY_LINEOUT_VERB,
 	ALC255_FIXUP_DELL_HEADSET_MIC,
@@ -5879,9 +6142,32 @@ enum {
 	ALC256_FIXUP_ASUS_HEADSET_MIC,
 	ALC256_FIXUP_ASUS_MIC_NO_PRESENCE,
 	ALC299_FIXUP_PREDATOR_SPK,
-	ALC294_FIXUP_ASUS_INTSPK_HEADSET_MIC,
 	ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE,
-	ALC294_FIXUP_ASUS_INTSPK_GPIO,
+	ALC289_FIXUP_DELL_SPK2,
+	ALC289_FIXUP_DUAL_SPK,
+	ALC294_FIXUP_SPK2_TO_DAC1,
+	ALC294_FIXUP_ASUS_DUAL_SPK,
+	ALC285_FIXUP_THINKPAD_X1_GEN7,
+	ALC285_FIXUP_THINKPAD_HEADSET_JACK,
+	ALC294_FIXUP_ASUS_HPE,
+	ALC294_FIXUP_ASUS_COEF_1B,
+	ALC285_FIXUP_HP_GPIO_LED,
+	ALC285_FIXUP_HP_MUTE_LED,
+	ALC236_FIXUP_HP_MUTE_LED,
+	ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET,
+	ALC295_FIXUP_ASUS_MIC_NO_PRESENCE,
+	ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS,
+	ALC269VC_FIXUP_ACER_HEADSET_MIC,
+	ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE,
+	ALC289_FIXUP_ASUS_GA401,
+	ALC289_FIXUP_ASUS_GA502,
+	ALC256_FIXUP_ACER_MIC_NO_PRESENCE,
+	ALC285_FIXUP_HP_GPIO_AMP_INIT,
+	ALC269_FIXUP_CZC_B20,
+	ALC269_FIXUP_CZC_TMI,
+	ALC269_FIXUP_CZC_L101,
+	ALC269_FIXUP_LEMOTE_A1802,
+	ALC269_FIXUP_LEMOTE_A190X,
 };
 
 static const struct hda_fixup alc269_fixups[] = {
@@ -6079,6 +6365,12 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC269_FIXUP_PINCFG_NO_HP_TO_LINEOUT
 	},
+	[ALC269_FIXUP_LENOVO_DOCK_LIMIT_BOOST] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc269_fixup_limit_int_mic_boost,
+		.chained = true,
+		.chain_id = ALC269_FIXUP_LENOVO_DOCK,
+	},
 	[ALC269_FIXUP_PINCFG_NO_HP_TO_LINEOUT] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc269_fixup_pincfg_no_hp_to_lineout,
@@ -6547,17 +6839,6 @@ static const struct hda_fixup alc269_fixups[] = {
 			{}
 		}
 	},
-	[ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE] = {
-		.type = HDA_FIXUP_VERBS,
-		.v.verbs = (const struct hda_verb[]) {
-			/* Disable pass-through path for FRONT 14h */
-			{0x20, AC_VERB_SET_COEF_INDEX, 0x36},
-			{0x20, AC_VERB_SET_PROC_COEF, 0x1737},
-			{}
-		},
-		.chained = true,
-		.chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE
-	},
 	[ALC293_FIXUP_LENOVO_SPK_NOISE] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_disable_aamix,
@@ -6620,6 +6901,12 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc295_fixup_disable_dac3,
 	},
+	[ALC285_FIXUP_SPEAKER2_TO_DAC1] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc285_fixup_speaker2_to_dac1,
+		.chained = true,
+		.chain_id = ALC269_FIXUP_THINKPAD_ACPI
+	},
 	[ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
@@ -6720,6 +7007,12 @@ static const struct hda_fixup alc269_fixups[] = {
 			{ }
 		},
 		.chained = true,
+		.chain_id = ALC225_FIXUP_S3_POP_NOISE
+	},
+	[ALC225_FIXUP_S3_POP_NOISE] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc225_fixup_s3_pop_noise,
+		.chained = true,
 		.chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC
 	},
 	[ALC700_FIXUP_INTEL_REFERENCE] = {
@@ -6752,12 +7045,18 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC274_FIXUP_DELL_BIND_DACS
 	},
-	[ALC298_FIXUP_TPT470_DOCK] = {
+	[ALC298_FIXUP_TPT470_DOCK_FIX] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_tpt470_dock,
 		.chained = true,
 		.chain_id = ALC293_FIXUP_LENOVO_SPK_NOISE
 	},
+	[ALC298_FIXUP_TPT470_DOCK] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_tpt470_dacs,
+		.chained = true,
+		.chain_id = ALC298_FIXUP_TPT470_DOCK_FIX
+	},
 	[ALC255_FIXUP_DUMMY_LINEOUT_VERB] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
@@ -6818,7 +7117,7 @@ static const struct hda_fixup alc269_fixups[] = {
 			{ }
 		},
 		.chained = true,
-		.chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC
+		.chain_id = ALC269_FIXUP_HEADSET_MIC
 	},
 	[ALC294_FIXUP_ASUS_HEADSET_MIC] = {
 		.type = HDA_FIXUP_PINS,
@@ -6827,7 +7126,7 @@ static const struct hda_fixup alc269_fixups[] = {
 			{ }
 		},
 		.chained = true,
-		.chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC
+		.chain_id = ALC269_FIXUP_HEADSET_MIC
 	},
 	[ALC294_FIXUP_ASUS_SPK] = {
 		.type = HDA_FIXUP_VERBS,
@@ -6835,6 +7134,8 @@ static const struct hda_fixup alc269_fixups[] = {
 			/* Set EAPD high */
 			{ 0x20, AC_VERB_SET_COEF_INDEX, 0x40 },
 			{ 0x20, AC_VERB_SET_PROC_COEF, 0x8800 },
+			{ 0x20, AC_VERB_SET_COEF_INDEX, 0x0f },
+			{ 0x20, AC_VERB_SET_PROC_COEF, 0x7774 },
 			{ }
 		},
 		.chained = true,
@@ -6937,32 +7238,246 @@ static const struct hda_fixup alc269_fixups[] = {
 			{ }
 		}
 	},
-	[ALC294_FIXUP_ASUS_INTSPK_HEADSET_MIC] = {
+	[ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
-			{ 0x14, 0x411111f0 }, /* disable confusing internal speaker */
-			{ 0x19, 0x04a11150 }, /* use as headset mic, without its own jack detect */
+			{ 0x19, 0x04a11040 },
+			{ 0x21, 0x04211020 },
 			{ }
 		},
 		.chained = true,
-		.chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC
+		.chain_id = ALC256_FIXUP_ASUS_HEADSET_MODE
 	},
-	[ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE] = {
+	[ALC289_FIXUP_DELL_SPK2] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
-			{ 0x19, 0x04a11040 },
-			{ 0x21, 0x04211020 },
+			{ 0x17, 0x90170130 }, /* bass spk */
 			{ }
 		},
 		.chained = true,
-		.chain_id = ALC256_FIXUP_ASUS_HEADSET_MODE
+		.chain_id = ALC269_FIXUP_DELL4_MIC_NO_PRESENCE
 	},
-	[ALC294_FIXUP_ASUS_INTSPK_GPIO] = {
+	[ALC289_FIXUP_DUAL_SPK] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc285_fixup_speaker2_to_dac1,
+		.chained = true,
+		.chain_id = ALC289_FIXUP_DELL_SPK2
+	},
+	[ALC294_FIXUP_SPK2_TO_DAC1] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc285_fixup_speaker2_to_dac1,
+		.chained = true,
+		.chain_id = ALC294_FIXUP_ASUS_HEADSET_MIC
+	},
+	[ALC294_FIXUP_ASUS_DUAL_SPK] = {
 		.type = HDA_FIXUP_FUNC,
 		/* The GPIO must be pulled to initialize the AMP */
 		.v.func = alc_fixup_gpio4,
 		.chained = true,
-		.chain_id = ALC294_FIXUP_ASUS_INTSPK_HEADSET_MIC
+		.chain_id = ALC294_FIXUP_SPK2_TO_DAC1
+	},
+	[ALC285_FIXUP_THINKPAD_X1_GEN7] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc285_fixup_thinkpad_x1_gen7,
+		.chained = true,
+		.chain_id = ALC269_FIXUP_THINKPAD_ACPI
+	},
+	[ALC285_FIXUP_THINKPAD_HEADSET_JACK] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_headset_jack,
+		.chained = true,
+		.chain_id = ALC285_FIXUP_THINKPAD_X1_GEN7
+	},
+	[ALC294_FIXUP_ASUS_HPE] = {
+		.type = HDA_FIXUP_VERBS,
+		.v.verbs = (const struct hda_verb[]) {
+			/* Set EAPD high */
+			{ 0x20, AC_VERB_SET_COEF_INDEX, 0x0f },
+			{ 0x20, AC_VERB_SET_PROC_COEF, 0x7774 },
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC294_FIXUP_ASUS_HEADSET_MIC
+	},
+	[ALC294_FIXUP_ASUS_COEF_1B] = {
+		.type = HDA_FIXUP_VERBS,
+		.v.verbs = (const struct hda_verb[]) {
+			/* Set bit 10 to correct noisy output after reboot from
+			 * Windows 10 (due to pop noise reduction?)
+			 */
+			{ 0x20, AC_VERB_SET_COEF_INDEX, 0x1b },
+			{ 0x20, AC_VERB_SET_PROC_COEF, 0x4e4b },
+			{ }
+		},
+	},
+	[ALC285_FIXUP_HP_GPIO_LED] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc285_fixup_hp_gpio_led,
+	},
+	[ALC285_FIXUP_HP_MUTE_LED] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc285_fixup_hp_mute_led,
+	},
+	[ALC236_FIXUP_HP_MUTE_LED] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc236_fixup_hp_mute_led,
+	},
+	[ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET] = {
+		.type = HDA_FIXUP_VERBS,
+		.v.verbs = (const struct hda_verb[]) {
+			{ 0x1a, AC_VERB_SET_PIN_WIDGET_CONTROL, 0xc5 },
+			{ }
+		},
+	},
+	[ALC295_FIXUP_ASUS_MIC_NO_PRESENCE] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x19, 0x01a1913c }, /* use as headset mic, without its own jack detect */
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC269_FIXUP_HEADSET_MODE
+	},
+	[ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x14, 0x90100120 }, /* use as internal speaker */
+			{ 0x18, 0x02a111f0 }, /* use as headset mic, without its own jack detect */
+			{ 0x1a, 0x01011020 }, /* use as line out */
+			{ },
+		},
+		.chained = true,
+		.chain_id = ALC269_FIXUP_HEADSET_MIC
+	},
+	[ALC269VC_FIXUP_ACER_HEADSET_MIC] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x18, 0x02a11030 }, /* use as headset mic */
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC269_FIXUP_HEADSET_MIC
+	},
+	[ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x18, 0x01a11130 }, /* use as headset mic, without its own jack detect */
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC269_FIXUP_HEADSET_MIC
+	},
+	[ALC289_FIXUP_ASUS_GA401] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x19, 0x03a11020 }, /* headset mic with jack detect */
+			{ }
+		},
+	},
+	[ALC289_FIXUP_ASUS_GA502] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x19, 0x03a11020 }, /* headset mic with jack detect */
+			{ }
+		},
+	},
+	[ALC256_FIXUP_ACER_MIC_NO_PRESENCE] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x19, 0x02a11120 }, /* use as headset mic, without its own jack detect */
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC256_FIXUP_ASUS_HEADSET_MODE
+	},
+	[ALC285_FIXUP_HP_GPIO_AMP_INIT] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc285_fixup_hp_gpio_amp_init,
+		.chained = true,
+		.chain_id = ALC285_FIXUP_HP_GPIO_LED
+	},
+	[ALC269_FIXUP_CZC_B20] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x12, 0x411111f0 },
+			{ 0x14, 0x90170110 }, /* speaker */
+			{ 0x15, 0x032f1020 }, /* HP out */
+			{ 0x17, 0x411111f0 },
+			{ 0x18, 0x03ab1040 }, /* mic */
+			{ 0x19, 0xb7a7013f },
+			{ 0x1a, 0x0181305f },
+			{ 0x1b, 0x411111f0 },
+			{ 0x1d, 0x411111f0 },
+			{ 0x1e, 0x411111f0 },
+			{ }
+		},
+		.chain_id = ALC269_FIXUP_DMIC,
+	},
+	[ALC269_FIXUP_CZC_TMI] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x12, 0x4000c000 },
+			{ 0x14, 0x90170110 }, /* speaker */
+			{ 0x15, 0x0421401f }, /* HP out */
+			{ 0x17, 0x411111f0 },
+			{ 0x18, 0x04a19020 }, /* mic */
+			{ 0x19, 0x411111f0 },
+			{ 0x1a, 0x411111f0 },
+			{ 0x1b, 0x411111f0 },
+			{ 0x1d, 0x40448505 },
+			{ 0x1e, 0x411111f0 },
+			{ 0x20, 0x8000ffff },
+			{ }
+		},
+		.chain_id = ALC269_FIXUP_DMIC,
+	},
+	[ALC269_FIXUP_CZC_L101] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x12, 0x40000000 },
+			{ 0x14, 0x01014010 }, /* speaker */
+			{ 0x15, 0x411111f0 }, /* HP out */
+			{ 0x16, 0x411111f0 },
+			{ 0x18, 0x01a19020 }, /* mic */
+			{ 0x19, 0x02a19021 },
+			{ 0x1a, 0x0181302f },
+			{ 0x1b, 0x0221401f },
+			{ 0x1c, 0x411111f0 },
+			{ 0x1d, 0x4044c601 },
+			{ 0x1e, 0x411111f0 },
+			{ }
+		},
+		.chain_id = ALC269_FIXUP_DMIC,
+	},
+	[ALC269_FIXUP_LEMOTE_A1802] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x12, 0x40000000 },
+			{ 0x14, 0x90170110 }, /* speaker */
+			{ 0x17, 0x411111f0 },
+			{ 0x18, 0x03a19040 }, /* mic1 */
+			{ 0x19, 0x90a70130 }, /* mic2 */
+			{ 0x1a, 0x411111f0 },
+			{ 0x1b, 0x411111f0 },
+			{ 0x1d, 0x40489d2d },
+			{ 0x1e, 0x411111f0 },
+			{ 0x20, 0x0003ffff },
+			{ 0x21, 0x03214020 },
+			{ }
+		},
+		.chain_id = ALC269_FIXUP_DMIC,
+	},
+	[ALC269_FIXUP_LEMOTE_A190X] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x14, 0x99130110 }, /* speaker */
+			{ 0x15, 0x0121401f }, /* HP out */
+			{ 0x18, 0x01a19c20 }, /* rear  mic */
+			{ 0x19, 0x99a3092f }, /* front mic */
+			{ 0x1b, 0x0201401f }, /* front lineout */
+			{ }
+		},
+		.chain_id = ALC269_FIXUP_DMIC,
 	},
 };
 
@@ -6979,16 +7494,20 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0x0775, "Acer Aspire E1-572", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572),
 	SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS),
 	SND_PCI_QUIRK(0x1025, 0x102b, "Acer Aspire C24-860", ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1025, 0x1065, "Acer Aspire C20-820", ALC269VC_FIXUP_ACER_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x106d, "Acer Cloudbook 14", ALC283_FIXUP_CHROME_BOOK),
 	SND_PCI_QUIRK(0x1025, 0x1099, "Acer Aspire E5-523G", ALC255_FIXUP_ACER_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1025, 0x110e, "Acer Aspire ES1-432", ALC255_FIXUP_ACER_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1025, 0x1246, "Acer Predator Helios 500", ALC299_FIXUP_PREDATOR_SPK),
+	SND_PCI_QUIRK(0x1025, 0x1247, "Acer vCopperbox", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS),
+	SND_PCI_QUIRK(0x1025, 0x1248, "Acer Veriton N4660G", ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1025, 0x128f, "Acer Veriton Z6860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x1290, "Acer Veriton Z4860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x1291, "Acer Veriton Z4660G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x1308, "Acer Aspire Z24-890", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x132a, "Acer TravelMate B114-21", ALC233_FIXUP_ACER_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x1330, "Acer TravelMate X514-51T", ALC255_FIXUP_ACER_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1025, 0x1430, "Acer TravelMate B311R-31", ALC256_FIXUP_ACER_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z),
 	SND_PCI_QUIRK(0x1028, 0x054b, "Dell XPS one 2710", ALC275_FIXUP_DELL_XPS),
 	SND_PCI_QUIRK(0x1028, 0x05bd, "Dell Latitude E6440", ALC292_FIXUP_DELL_E7X),
@@ -7017,17 +7536,14 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x06de, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK),
 	SND_PCI_QUIRK(0x1028, 0x06df, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK),
 	SND_PCI_QUIRK(0x1028, 0x06e0, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK),
-	SND_PCI_QUIRK(0x1028, 0x0704, "Dell XPS 13 9350", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
 	SND_PCI_QUIRK(0x1028, 0x0706, "Dell Inspiron 7559", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER),
 	SND_PCI_QUIRK(0x1028, 0x0725, "Dell Inspiron 3162", ALC255_FIXUP_DELL_SPK_NOISE),
 	SND_PCI_QUIRK(0x1028, 0x0738, "Dell Precision 5820", ALC269_FIXUP_NO_SHUTUP),
-	SND_PCI_QUIRK(0x1028, 0x075b, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
 	SND_PCI_QUIRK(0x1028, 0x075c, "Dell XPS 27 7760", ALC298_FIXUP_SPK_VOLUME),
 	SND_PCI_QUIRK(0x1028, 0x075d, "Dell AIO", ALC298_FIXUP_SPK_VOLUME),
 	SND_PCI_QUIRK(0x1028, 0x07b0, "Dell Precision 7520", ALC295_FIXUP_DISABLE_DAC3),
 	SND_PCI_QUIRK(0x1028, 0x0798, "Dell Inspiron 17 7000 Gaming", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER),
 	SND_PCI_QUIRK(0x1028, 0x080c, "Dell WYSE", ALC225_FIXUP_DELL_WYSE_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x082a, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
 	SND_PCI_QUIRK(0x1028, 0x084b, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB),
 	SND_PCI_QUIRK(0x1028, 0x084e, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB),
 	SND_PCI_QUIRK(0x1028, 0x0871, "Dell Precision 3630", ALC255_FIXUP_DELL_HEADSET_MIC),
@@ -7036,6 +7552,10 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x08ad, "Dell WYSE AIO", ALC225_FIXUP_DELL_WYSE_AIO_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x08ae, "Dell WYSE NB", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0935, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB),
+	SND_PCI_QUIRK(0x1028, 0x097e, "Dell Precision", ALC289_FIXUP_DUAL_SPK),
+	SND_PCI_QUIRK(0x1028, 0x097d, "Dell Precision", ALC289_FIXUP_DUAL_SPK),
+	SND_PCI_QUIRK(0x1028, 0x098d, "Dell Precision", ALC233_FIXUP_ASUS_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1028, 0x09bf, "Dell Precision", ALC233_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2),
@@ -7107,6 +7627,11 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x83b9, "HP Spectre x360", ALC269_FIXUP_HP_MUTE_LED_MIC3),
 	SND_PCI_QUIRK(0x103c, 0x8497, "HP Envy x360", ALC269_FIXUP_HP_MUTE_LED_MIC3),
 	SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3),
+	SND_PCI_QUIRK(0x103c, 0x869d, "HP", ALC236_FIXUP_HP_MUTE_LED),
+	SND_PCI_QUIRK(0x103c, 0x8729, "HP", ALC285_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8736, "HP", ALC285_FIXUP_HP_GPIO_AMP_INIT),
+	SND_PCI_QUIRK(0x103c, 0x877a, "HP", ALC285_FIXUP_HP_MUTE_LED),
+	SND_PCI_QUIRK(0x103c, 0x877d, "HP", ALC236_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
 	SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
@@ -7123,14 +7648,21 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK),
 	SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A),
 	SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC),
-	SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_INTSPK_GPIO),
+	SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_DUAL_SPK),
 	SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x18f1, "Asus FX505DT", ALC256_FIXUP_ASUS_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x194e, "ASUS UX563FD", ALC294_FIXUP_ASUS_HPE),
+	SND_PCI_QUIRK(0x1043, 0x19ce, "ASUS B9450FA", ALC294_FIXUP_ASUS_HPE),
+	SND_PCI_QUIRK(0x1043, 0x19e1, "ASUS UX581LV", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW),
 	SND_PCI_QUIRK(0x1043, 0x1a30, "ASUS X705UD", ALC256_FIXUP_ASUS_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1b11, "ASUS UX431DA", ALC294_FIXUP_ASUS_COEF_1B),
 	SND_PCI_QUIRK(0x1043, 0x1b13, "Asus U41SV", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502),
+	SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2),
 	SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x1043, 0x834a, "ASUS S101", ALC269_FIXUP_STEREO_DMIC),
@@ -7150,9 +7682,13 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x10cf, 0x1629, "Lifebook U7x7", ALC255_FIXUP_LIFEBOOK_U7x7_HEADSET_MIC),
 	SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC),
 	SND_PCI_QUIRK(0x10ec, 0x10f2, "Intel Reference board", ALC700_FIXUP_INTEL_REFERENCE),
+	SND_PCI_QUIRK(0x10ec, 0x1230, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK),
 	SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE),
 	SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC),
+	SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
+	SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
 	SND_PCI_QUIRK(0x144d, 0xc740, "Samsung Ativ book 8 (NP870Z5G)", ALC269_FIXUP_ATIV_BOOK_8),
+	SND_PCI_QUIRK(0x144d, 0xc812, "Samsung Notebook Pen S (NT950SBE-X58)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
 	SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1462, 0xb171, "Cubi N 8GL (MS-B171)", ALC283_FIXUP_HEADSET_MIC),
@@ -7162,12 +7698,13 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1558, 0x8560, "System76 Gazelle (gaze14)", ALC269_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1558, 0x8561, "System76 Gazelle (gaze14)", ALC269_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC233_FIXUP_LENOVO_MULTI_CODECS),
+	SND_PCI_QUIRK(0x17aa, 0x1048, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE),
 	SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE),
 	SND_PCI_QUIRK(0x17aa, 0x21b8, "Thinkpad Edge 14", ALC269_FIXUP_SKU_IGNORE),
 	SND_PCI_QUIRK(0x17aa, 0x21ca, "Thinkpad L412", ALC269_FIXUP_SKU_IGNORE),
 	SND_PCI_QUIRK(0x17aa, 0x21e9, "Thinkpad Edge 15", ALC269_FIXUP_SKU_IGNORE),
-	SND_PCI_QUIRK(0x17aa, 0x21f6, "Thinkpad T530", ALC269_FIXUP_LENOVO_DOCK),
+	SND_PCI_QUIRK(0x17aa, 0x21f6, "Thinkpad T530", ALC269_FIXUP_LENOVO_DOCK_LIMIT_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x21fa, "Thinkpad X230", ALC269_FIXUP_LENOVO_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x21f3, "Thinkpad T430", ALC269_FIXUP_LENOVO_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x21fb, "Thinkpad T430s", ALC269_FIXUP_LENOVO_DOCK),
@@ -7195,6 +7732,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x224c, "Thinkpad", ALC298_FIXUP_TPT470_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x224d, "Thinkpad", ALC298_FIXUP_TPT470_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x225d, "Thinkpad T480", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+	SND_PCI_QUIRK(0x17aa, 0x2292, "Thinkpad X1 Carbon 7th", ALC285_FIXUP_THINKPAD_HEADSET_JACK),
+	SND_PCI_QUIRK(0x17aa, 0x22be, "Thinkpad X1 Carbon 8th", ALC285_FIXUP_THINKPAD_HEADSET_JACK),
 	SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
 	SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
 	SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
@@ -7229,9 +7768,14 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K),
 	SND_PCI_QUIRK(0x17aa, 0x9e54, "LENOVO NB", ALC269_FIXUP_LENOVO_EAPD),
 	SND_PCI_QUIRK(0x19e5, 0x3204, "Huawei MACH-WX9", ALC256_FIXUP_HUAWEI_MACH_WX9_PINS),
+	SND_PCI_QUIRK(0x1b35, 0x1235, "CZC B20", ALC269_FIXUP_CZC_B20),
+	SND_PCI_QUIRK(0x1b35, 0x1236, "CZC TMI", ALC269_FIXUP_CZC_TMI),
+	SND_PCI_QUIRK(0x1b35, 0x1237, "CZC L101", ALC269_FIXUP_CZC_L101),
 	SND_PCI_QUIRK(0x1b7d, 0xa831, "Ordissimo EVE2 ", ALC269VB_FIXUP_ORDISSIMO_EVE2), /* Also known as Malata PC-B1303 */
 	SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x10ec, 0x118c, "Medion EE4254 MD62100", ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1c06, 0x2013, "Lemote A1802", ALC269_FIXUP_LEMOTE_A1802),
+	SND_PCI_QUIRK(0x1c06, 0x2015, "Lemote A190X", ALC269_FIXUP_LEMOTE_A190X),
 
 #if 0
 	/* Below is a quirk table taken from the old code.
@@ -7303,6 +7847,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{.id = ALC269_FIXUP_HEADSET_MODE, .name = "headset-mode"},
 	{.id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC, .name = "headset-mode-no-hp-mic"},
 	{.id = ALC269_FIXUP_LENOVO_DOCK, .name = "lenovo-dock"},
+	{.id = ALC269_FIXUP_LENOVO_DOCK_LIMIT_BOOST, .name = "lenovo-dock-limit-boost"},
 	{.id = ALC269_FIXUP_HP_GPIO_LED, .name = "hp-gpio-led"},
 	{.id = ALC269_FIXUP_HP_DOCK_GPIO_MIC1_LED, .name = "hp-dock-gpio-mic1-led"},
 	{.id = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, .name = "dell-headset-multi"},
@@ -7314,6 +7859,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{.id = ALC292_FIXUP_TPT440_DOCK, .name = "tpt440-dock"},
 	{.id = ALC292_FIXUP_TPT440, .name = "tpt440"},
 	{.id = ALC292_FIXUP_TPT460, .name = "tpt460"},
+	{.id = ALC298_FIXUP_TPT470_DOCK_FIX, .name = "tpt470-dock-fix"},
 	{.id = ALC298_FIXUP_TPT470_DOCK, .name = "tpt470-dock"},
 	{.id = ALC233_FIXUP_LENOVO_MULTI_CODECS, .name = "dual-codecs"},
 	{.id = ALC700_FIXUP_INTEL_REFERENCE, .name = "alc700-ref"},
@@ -7373,12 +7919,12 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{.id = ALC298_FIXUP_DELL1_MIC_NO_PRESENCE, .name = "alc298-dell1"},
 	{.id = ALC298_FIXUP_DELL_AIO_MIC_NO_PRESENCE, .name = "alc298-dell-aio"},
 	{.id = ALC275_FIXUP_DELL_XPS, .name = "alc275-dell-xps"},
-	{.id = ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE, .name = "alc256-dell-xps13"},
 	{.id = ALC293_FIXUP_LENOVO_SPK_NOISE, .name = "lenovo-spk-noise"},
 	{.id = ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY, .name = "lenovo-hotkey"},
 	{.id = ALC255_FIXUP_DELL_SPK_NOISE, .name = "dell-spk-noise"},
 	{.id = ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, .name = "alc225-dell1"},
 	{.id = ALC295_FIXUP_DISABLE_DAC3, .name = "alc295-disable-dac3"},
+	{.id = ALC285_FIXUP_SPEAKER2_TO_DAC1, .name = "alc285-speaker2-to-dac1"},
 	{.id = ALC280_FIXUP_HP_HEADSET_MIC, .name = "alc280-hp-headset"},
 	{.id = ALC221_FIXUP_HP_FRONT_MIC, .name = "alc221-hp-mic"},
 	{.id = ALC298_FIXUP_SPK_VOLUME, .name = "alc298-spk-volume"},
@@ -7786,6 +8332,18 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x12, 0x90a60130},
 		{0x17, 0x90170110},
 		{0x21, 0x03211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1043, "ASUS", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE,
+		{0x12, 0x90a60120},
+		{0x17, 0x90170110},
+		{0x21, 0x04211030}),
+	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1043, "ASUS", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE,
+		{0x12, 0x90a60130},
+		{0x17, 0x90170110},
+		{0x21, 0x03211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1043, "ASUS", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE,
+		{0x12, 0x90a60130},
+		{0x17, 0x90170110},
+		{0x21, 0x03211020}),
 	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE,
 		{0x14, 0x90170110},
 		{0x21, 0x04211020}),
@@ -7821,6 +8379,12 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		ALC225_STANDARD_PINS,
 		{0x12, 0xb7a60130},
 		{0x17, 0x90170110}),
+	SND_HDA_PIN_QUIRK(0x10ec0623, 0x17aa, "Lenovo", ALC283_FIXUP_HEADSET_MIC,
+		{0x14, 0x01014010},
+		{0x17, 0x90170120},
+		{0x18, 0x02a11030},
+		{0x19, 0x02a1103f},
+		{0x21, 0x0221101f}),
 	{}
 };
 
@@ -7966,7 +8530,9 @@ static int patch_alc269(struct hda_codec *codec)
 		spec->gen.mixer_nid = 0;
 		break;
 	case 0x10ec0215:
+	case 0x10ec0245:
 	case 0x10ec0285:
+	case 0x10ec0287:
 	case 0x10ec0289:
 		spec->codec_variant = ALC269_TYPE_ALC215;
 		spec->shutup = alc225_shutup;
@@ -8392,7 +8958,30 @@ static void alc662_fixup_usi_headset_mic(struct hda_codec *codec,
 	}
 }
 
-static struct coef_fw alc668_coefs[] = {
+static void alc671_fixup_hp_headset_mic2(struct hda_codec *codec,
+					     const struct hda_fixup *fix, int action)
+{
+	struct alc_spec *spec = codec->spec;
+
+	static const struct hda_pintbl pincfgs[] = {
+		{ 0x19, 0x02a11040 }, /* use as headset mic, with its own jack detect */
+		{ 0x1b, 0x0181304f },
+		{ }
+	};
+
+	switch (action) {
+	case HDA_FIXUP_ACT_PRE_PROBE:
+		spec->gen.mixer_nid = 0;
+		spec->parse_flags |= HDA_PINCFG_HEADSET_MIC;
+		snd_hda_apply_pincfgs(codec, pincfgs);
+		break;
+	case HDA_FIXUP_ACT_INIT:
+		alc_write_coef_idx(codec, 0x19, 0xa054);
+		break;
+	}
+}
+
+static const struct coef_fw alc668_coefs[] = {
 	WRITE_COEF(0x01, 0xbebe), WRITE_COEF(0x02, 0xaaaa), WRITE_COEF(0x03,    0x0),
 	WRITE_COEF(0x04, 0x0180), WRITE_COEF(0x06,    0x0), WRITE_COEF(0x07, 0x0f80),
 	WRITE_COEF(0x08, 0x0031), WRITE_COEF(0x0a, 0x0060), WRITE_COEF(0x0b,    0x0),
@@ -8426,6 +9015,7 @@ enum {
 	ALC662_FIXUP_LED_GPIO1,
 	ALC662_FIXUP_IDEAPAD,
 	ALC272_FIXUP_MARIO,
+	ALC662_FIXUP_CZC_ET26,
 	ALC662_FIXUP_CZC_P10T,
 	ALC662_FIXUP_SKU_IGNORE,
 	ALC662_FIXUP_HP_RP5800,
@@ -8463,6 +9053,9 @@ enum {
 	ALC662_FIXUP_USI_FUNC,
 	ALC662_FIXUP_USI_HEADSET_MODE,
 	ALC662_FIXUP_LENOVO_MULTI_CODECS,
+	ALC671_FIXUP_HP_HEADSET_MIC2,
+	ALC662_FIXUP_ACER_X2660G_HEADSET_MODE,
+	ALC662_FIXUP_ACER_NITRO_HEADSET_MODE,
 };
 
 static const struct hda_fixup alc662_fixups[] = {
@@ -8490,6 +9083,25 @@ static const struct hda_fixup alc662_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc272_fixup_mario,
 	},
+	[ALC662_FIXUP_CZC_ET26] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{0x12, 0x403cc000},
+			{0x14, 0x90170110}, /* speaker */
+			{0x15, 0x411111f0},
+			{0x16, 0x411111f0},
+			{0x18, 0x01a19030}, /* mic */
+			{0x19, 0x90a7013f}, /* int-mic */
+			{0x1a, 0x01014020},
+			{0x1b, 0x0121401f},
+			{0x1c, 0x411111f0},
+			{0x1d, 0x411111f0},
+			{0x1e, 0x40478e35},
+			{}
+		},
+		.chained = true,
+		.chain_id = ALC662_FIXUP_SKU_IGNORE
+	},
 	[ALC662_FIXUP_CZC_P10T] = {
 		.type = HDA_FIXUP_VERBS,
 		.v.verbs = (const struct hda_verb[]) {
@@ -8789,6 +9401,29 @@ static const struct hda_fixup alc662_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc233_alc662_fixup_lenovo_dual_codecs,
 	},
+	[ALC671_FIXUP_HP_HEADSET_MIC2] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc671_fixup_hp_headset_mic2,
+	},
+	[ALC662_FIXUP_ACER_X2660G_HEADSET_MODE] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x1a, 0x02a1113c }, /* use as headset mic, without its own jack detect */
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC662_FIXUP_USI_FUNC
+	},
+	[ALC662_FIXUP_ACER_NITRO_HEADSET_MODE] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x1a, 0x01a11140 }, /* use as headset mic, without its own jack detect */
+			{ 0x1b, 0x0221144f },
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC662_FIXUP_USI_FUNC
+	},
 };
 
 static const struct snd_pci_quirk alc662_fixup_tbl[] = {
@@ -8800,6 +9435,8 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0x0349, "eMachines eM250", ALC662_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x1025, 0x034a, "Gateway LT27", ALC662_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x1025, 0x038b, "Acer Aspire 8943G", ALC662_FIXUP_ASPIRE),
+	SND_PCI_QUIRK(0x1025, 0x123c, "Acer Nitro N50-600", ALC662_FIXUP_ACER_NITRO_HEADSET_MODE),
+	SND_PCI_QUIRK(0x1025, 0x124e, "Acer 2660G", ALC662_FIXUP_ACER_X2660G_HEADSET_MODE),
 	SND_PCI_QUIRK(0x1028, 0x05d8, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x05db, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x05fe, "Dell XPS 15", ALC668_FIXUP_DELL_XPS13),
@@ -8833,6 +9470,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1849, 0x5892, "ASRock B150M", ALC892_FIXUP_ASROCK_MOBO),
 	SND_PCI_QUIRK(0x19da, 0xa130, "Zotac Z68", ALC662_FIXUP_ZOTAC_Z68),
 	SND_PCI_QUIRK(0x1b0a, 0x01b8, "ACER Veriton", ALC662_FIXUP_ACER_VERITON),
+	SND_PCI_QUIRK(0x1b35, 0x1234, "CZC ET26", ALC662_FIXUP_CZC_ET26),
 	SND_PCI_QUIRK(0x1b35, 0x2206, "CZC P10T", ALC662_FIXUP_CZC_P10T),
 
 #if 0
@@ -8969,6 +9607,23 @@ static const struct snd_hda_pin_quirk alc662_pin_fixup_tbl[] = {
 		{0x12, 0x90a60130},
 		{0x14, 0x90170110},
 		{0x15, 0x0321101f}),
+	SND_HDA_PIN_QUIRK(0x10ec0671, 0x103c, "HP cPC", ALC671_FIXUP_HP_HEADSET_MIC2,
+		{0x14, 0x01014010},
+		{0x17, 0x90170150},
+		{0x19, 0x02a11060},
+		{0x1b, 0x01813030},
+		{0x21, 0x02211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0671, 0x103c, "HP cPC", ALC671_FIXUP_HP_HEADSET_MIC2,
+		{0x14, 0x01014010},
+		{0x18, 0x01a19040},
+		{0x1b, 0x01813030},
+		{0x21, 0x02211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0671, 0x103c, "HP cPC", ALC671_FIXUP_HP_HEADSET_MIC2,
+		{0x14, 0x01014020},
+		{0x17, 0x90170110},
+		{0x18, 0x01a19050},
+		{0x1b, 0x01813040},
+		{0x21, 0x02211030}),
 	{}
 };
 
@@ -9094,6 +9749,7 @@ static const struct hda_device_id snd_hda_id_realtek[] = {
 	HDA_CODEC_ENTRY(0x10ec0234, "ALC234", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0235, "ALC233", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0236, "ALC236", patch_alc269),
+	HDA_CODEC_ENTRY(0x10ec0245, "ALC245", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0255, "ALC255", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0256, "ALC256", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0257, "ALC257", patch_alc269),
@@ -9113,6 +9769,7 @@ static const struct hda_device_id snd_hda_id_realtek[] = {
 	HDA_CODEC_ENTRY(0x10ec0284, "ALC284", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0285, "ALC285", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0286, "ALC286", patch_alc269),
+	HDA_CODEC_ENTRY(0x10ec0287, "ALC287", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0288, "ALC288", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0289, "ALC289", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0290, "ALC290", patch_alc269),
@@ -9156,6 +9813,7 @@ static const struct hda_device_id snd_hda_id_realtek[] = {
 	HDA_CODEC_ENTRY(0x10ec0892, "ALC892", patch_alc662),
 	HDA_CODEC_ENTRY(0x10ec0899, "ALC898", patch_alc882),
 	HDA_CODEC_ENTRY(0x10ec0900, "ALC1150", patch_alc882),
+	HDA_CODEC_ENTRY(0x10ec0b00, "ALCS1200A", patch_alc882),
 	HDA_CODEC_ENTRY(0x10ec1168, "ALC1220", patch_alc882),
 	HDA_CODEC_ENTRY(0x10ec1220, "ALC1220", patch_alc882),
 	{} /* terminator */
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 0d9b62768241..e02f58e0d650 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -795,7 +795,7 @@ static int find_mute_led_cfg(struct hda_codec *codec, int default_polarity)
 static bool has_builtin_speaker(struct hda_codec *codec)
 {
 	struct sigmatel_spec *spec = codec->spec;
-	hda_nid_t *nid_pin;
+	const hda_nid_t *nid_pin;
 	int nids, i;
 
 	if (spec->gen.autocfg.line_out_type == AUTO_PIN_SPEAKER_OUT) {
@@ -2191,7 +2191,7 @@ static void hp_envy_ts_fixup_dac_bind(struct hda_codec *codec,
 					    int action)
 {
 	struct sigmatel_spec *spec = codec->spec;
-	static hda_nid_t preferred_pairs[] = {
+	static const hda_nid_t preferred_pairs[] = {
 		0xd, 0x13,
 		0
 	};
diff --git a/sound/pci/hda/patch_via.c b/sound/pci/hda/patch_via.c
index 29dcdb8b36db..7ef8f3105cdb 100644
--- a/sound/pci/hda/patch_via.c
+++ b/sound/pci/hda/patch_via.c
@@ -396,7 +396,7 @@ static int via_resume(struct hda_codec *codec)
 	/* some delay here to make jack detection working (bko#98921) */
 	msleep(10);
 	codec->patch_ops.init(codec);
-	regcache_sync(codec->core.regmap);
+	snd_hda_regmap_sync(codec);
 	return 0;
 }
 #endif
@@ -1038,8 +1038,8 @@ static const struct snd_pci_quirk vt2002p_fixups[] = {
  */
 static void fix_vt1802_connections(struct hda_codec *codec)
 {
-	static hda_nid_t conn_24[] = { 0x14, 0x1c };
-	static hda_nid_t conn_33[] = { 0x1c };
+	static const hda_nid_t conn_24[] = { 0x14, 0x1c };
+	static const hda_nid_t conn_33[] = { 0x1c };
 
 	snd_hda_override_conn_list(codec, 0x24, ARRAY_SIZE(conn_24), conn_24);
 	snd_hda_override_conn_list(codec, 0x33, ARRAY_SIZE(conn_33), conn_33);
diff --git a/sound/pci/ice1712/ice1712.c b/sound/pci/ice1712/ice1712.c
index 4b0dea7f7669..2654eebd5663 100644
--- a/sound/pci/ice1712/ice1712.c
+++ b/sound/pci/ice1712/ice1712.c
@@ -2360,7 +2360,8 @@ static int snd_ice1712_chip_init(struct snd_ice1712 *ice)
 	pci_write_config_byte(ice->pci, 0x61, ice->eeprom.data[ICE_EEP1_ACLINK]);
 	pci_write_config_byte(ice->pci, 0x62, ice->eeprom.data[ICE_EEP1_I2SID]);
 	pci_write_config_byte(ice->pci, 0x63, ice->eeprom.data[ICE_EEP1_SPDIF]);
-	if (ice->eeprom.subvendor != ICE1712_SUBDEVICE_STDSP24) {
+	if (ice->eeprom.subvendor != ICE1712_SUBDEVICE_STDSP24 &&
+	    ice->eeprom.subvendor != ICE1712_SUBDEVICE_STAUDIO_ADCIII) {
 		ice->gpio.write_mask = ice->eeprom.gpiomask;
 		ice->gpio.direction = ice->eeprom.gpiodir;
 		snd_ice1712_write(ice, ICE1712_IREG_GPIO_WRITE_MASK,
diff --git a/sound/pci/ice1712/ice1724.c b/sound/pci/ice1712/ice1724.c
index e62c11816683..f360b33a1042 100644
--- a/sound/pci/ice1712/ice1724.c
+++ b/sound/pci/ice1712/ice1724.c
@@ -647,6 +647,7 @@ static int snd_vt1724_set_pro_rate(struct snd_ice1712 *ice, unsigned int rate,
 	unsigned long flags;
 	unsigned char mclk_change;
 	unsigned int i, old_rate;
+	bool call_set_rate = false;
 
 	if (rate > ice->hw_rates->list[ice->hw_rates->count - 1])
 		return -EINVAL;
@@ -670,7 +671,7 @@ static int snd_vt1724_set_pro_rate(struct snd_ice1712 *ice, unsigned int rate,
 		 * setting clock rate for internal clock mode */
 		old_rate = ice->get_rate(ice);
 		if (force || (old_rate != rate))
-			ice->set_rate(ice, rate);
+			call_set_rate = true;
 		else if (rate == ice->cur_rate) {
 			spin_unlock_irqrestore(&ice->reg_lock, flags);
 			return 0;
@@ -678,12 +679,14 @@ static int snd_vt1724_set_pro_rate(struct snd_ice1712 *ice, unsigned int rate,
 	}
 
 	ice->cur_rate = rate;
+	spin_unlock_irqrestore(&ice->reg_lock, flags);
+
+	if (call_set_rate)
+		ice->set_rate(ice, rate);
 
 	/* setting master clock */
 	mclk_change = ice->set_mclk(ice, rate);
 
-	spin_unlock_irqrestore(&ice->reg_lock, flags);
-
 	if (mclk_change && ice->gpio.i2s_mclk_changed)
 		ice->gpio.i2s_mclk_changed(ice);
 	if (ice->gpio.set_pro_rate)
diff --git a/sound/pci/ice1712/prodigy_hifi.c b/sound/pci/ice1712/prodigy_hifi.c
index 9d71e9d5c9a0..3cf41c11a405 100644
--- a/sound/pci/ice1712/prodigy_hifi.c
+++ b/sound/pci/ice1712/prodigy_hifi.c
@@ -536,7 +536,7 @@ static int wm_adc_mux_enum_get(struct snd_kcontrol *kcontrol,
 	struct snd_ice1712 *ice = snd_kcontrol_chip(kcontrol);
 
 	mutex_lock(&ice->gpio_mutex);
-	ucontrol->value.integer.value[0] = wm_get(ice, WM_ADC_MUX) & 0x1f;
+	ucontrol->value.enumerated.item[0] = wm_get(ice, WM_ADC_MUX) & 0x1f;
 	mutex_unlock(&ice->gpio_mutex);
 	return 0;
 }
@@ -550,7 +550,7 @@ static int wm_adc_mux_enum_put(struct snd_kcontrol *kcontrol,
 
 	mutex_lock(&ice->gpio_mutex);
 	oval = wm_get(ice, WM_ADC_MUX);
-	nval = (oval & 0xe0) | ucontrol->value.integer.value[0];
+	nval = (oval & 0xe0) | ucontrol->value.enumerated.item[0];
 	if (nval != oval) {
 		wm_put(ice, WM_ADC_MUX, nval);
 		change = 1;
diff --git a/sound/sh/aica.c b/sound/sh/aica.c
index 52e9cfb4f819..8421b2f9c9f3 100644
--- a/sound/sh/aica.c
+++ b/sound/sh/aica.c
@@ -101,10 +101,10 @@ static void spu_memset(u32 toi, u32 what, int length)
 }
 
 /* spu_memload - write to SPU address space */
-static void spu_memload(u32 toi, void *from, int length)
+static void spu_memload(u32 toi, const void *from, int length)
 {
 	unsigned long flags;
-	u32 *froml = from;
+	const u32 *froml = from;
 	u32 __iomem *to = (u32 __iomem *) (SPU_MEMORY_BASE + toi);
 	int i;
 	u32 val;
diff --git a/sound/sh/sh_dac_audio.c b/sound/sh/sh_dac_audio.c
index ed877a138965..7c46494466ff 100644
--- a/sound/sh/sh_dac_audio.c
+++ b/sound/sh/sh_dac_audio.c
@@ -175,7 +175,6 @@ static int snd_sh_dac_pcm_copy(struct snd_pcm_substream *substream,
 {
 	/* channel is not used (interleaved data) */
 	struct snd_sh_dac *chip = snd_pcm_substream_chip(substream);
-	struct snd_pcm_runtime *runtime = substream->runtime;
 
 	if (copy_from_user_toio(chip->data_buffer + pos, src, count))
 		return -EFAULT;
@@ -195,7 +194,6 @@ static int snd_sh_dac_pcm_copy_kernel(struct snd_pcm_substream *substream,
 {
 	/* channel is not used (interleaved data) */
 	struct snd_sh_dac *chip = snd_pcm_substream_chip(substream);
-	struct snd_pcm_runtime *runtime = substream->runtime;
 
 	memcpy_toio(chip->data_buffer + pos, src, count);
 	chip->buffer_end = chip->data_buffer + pos + count;
@@ -214,7 +212,6 @@ static int snd_sh_dac_pcm_silence(struct snd_pcm_substream *substream,
 {
 	/* channel is not used (interleaved data) */
 	struct snd_sh_dac *chip = snd_pcm_substream_chip(substream);
-	struct snd_pcm_runtime *runtime = substream->runtime;
 
 	memset_io(chip->data_buffer + pos, 0, count);
 	chip->buffer_end = chip->data_buffer + pos + count;
diff --git a/sound/soc/atmel/Kconfig b/sound/soc/atmel/Kconfig
index 06c1d5ce642c..71f2d42188c4 100644
--- a/sound/soc/atmel/Kconfig
+++ b/sound/soc/atmel/Kconfig
@@ -10,27 +10,35 @@ config SND_ATMEL_SOC
 if SND_ATMEL_SOC
 
 config SND_ATMEL_SOC_PDC
-	tristate
+	bool
 	depends on HAS_DMA
-	default m if SND_ATMEL_SOC_SSC_PDC=m && SND_ATMEL_SOC_SSC=m
-	default y if SND_ATMEL_SOC_SSC_PDC=y || (SND_ATMEL_SOC_SSC_PDC=m && SND_ATMEL_SOC_SSC=y)
-
-config SND_ATMEL_SOC_SSC_PDC
-	tristate
 
 config SND_ATMEL_SOC_DMA
-	tristate
+	bool
 	select SND_SOC_GENERIC_DMAENGINE_PCM
-	default m if SND_ATMEL_SOC_SSC_DMA=m && SND_ATMEL_SOC_SSC=m
-	default y if SND_ATMEL_SOC_SSC_DMA=y || (SND_ATMEL_SOC_SSC_DMA=m && SND_ATMEL_SOC_SSC=y)
-
-config SND_ATMEL_SOC_SSC_DMA
-	tristate
 
 config SND_ATMEL_SOC_SSC
 	tristate
-	default y if SND_ATMEL_SOC_SSC_DMA=y || SND_ATMEL_SOC_SSC_PDC=y
-	default m if SND_ATMEL_SOC_SSC_DMA=m || SND_ATMEL_SOC_SSC_PDC=m
+	select SND_ATMEL_SOC_DMA
+	select SND_ATMEL_SOC_PDC
+
+config SND_ATMEL_SOC_SSC_PDC
+	tristate "SoC PCM DAI support for AT91 SSC controller using PDC"
+	depends on ATMEL_SSC
+	select SND_ATMEL_SOC_PDC
+	select SND_ATMEL_SOC_SSC
+	help
+	  Say Y or M if you want to add support for Atmel SSC interface
+	  in PDC mode configured using audio-graph-card in device-tree.
+
+config SND_ATMEL_SOC_SSC_DMA
+	tristate "SoC PCM DAI support for AT91 SSC controller using DMA"
+	depends on ATMEL_SSC
+	select SND_ATMEL_SOC_DMA
+	select SND_ATMEL_SOC_SSC
+	help
+	  Say Y or M if you want to add support for Atmel SSC interface
+	  in DMA mode configured using audio-graph-card in device-tree.
 
 config SND_AT91_SOC_SAM9G20_WM8731
 	tristate "SoC Audio support for WM8731-based At91sam9g20 evaluation board"
diff --git a/sound/soc/atmel/Makefile b/sound/soc/atmel/Makefile
index 1f6890ed3738..c7d2989791be 100644
--- a/sound/soc/atmel/Makefile
+++ b/sound/soc/atmel/Makefile
@@ -6,8 +6,14 @@ snd-soc-atmel_ssc_dai-objs := atmel_ssc_dai.o
 snd-soc-atmel-i2s-objs := atmel-i2s.o
 snd-soc-mchp-i2s-mcc-objs := mchp-i2s-mcc.o
 
-obj-$(CONFIG_SND_ATMEL_SOC_PDC) += snd-soc-atmel-pcm-pdc.o
-obj-$(CONFIG_SND_ATMEL_SOC_DMA) += snd-soc-atmel-pcm-dma.o
+# pdc and dma need to both be built-in if any user of
+# ssc is built-in.
+ifdef CONFIG_SND_ATMEL_SOC_PDC
+obj-$(CONFIG_SND_ATMEL_SOC_SSC) += snd-soc-atmel-pcm-pdc.o
+endif
+ifdef CONFIG_SND_ATMEL_SOC_DMA
+obj-$(CONFIG_SND_ATMEL_SOC_SSC) += snd-soc-atmel-pcm-dma.o
+endif
 obj-$(CONFIG_SND_ATMEL_SOC_SSC) += snd-soc-atmel_ssc_dai.o
 obj-$(CONFIG_SND_ATMEL_SOC_I2S) += snd-soc-atmel-i2s.o
 obj-$(CONFIG_SND_MCHP_SOC_I2S_MCC) += snd-soc-mchp-i2s-mcc.o
diff --git a/sound/soc/codecs/hdac_hda.c b/sound/soc/codecs/hdac_hda.c
index 4570f662fb48..d78f4d856aaf 100644
--- a/sound/soc/codecs/hdac_hda.c
+++ b/sound/soc/codecs/hdac_hda.c
@@ -498,7 +498,9 @@ static int hdac_hda_dev_remove(struct hdac_device *hdev)
 	struct hdac_hda_priv *hda_pvt;
 
 	hda_pvt = dev_get_drvdata(&hdev->dev);
-	cancel_delayed_work_sync(&hda_pvt->codec.jackpoll_work);
+	if (hda_pvt && hda_pvt->codec.registered)
+		cancel_delayed_work_sync(&hda_pvt->codec.jackpoll_work);
+
 	return 0;
 }
 
diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index c9f9820968bb..0b05ec05748f 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -148,14 +148,14 @@ static struct hdac_hdmi_pcm *
 hdac_hdmi_get_pcm_from_cvt(struct hdac_hdmi_priv *hdmi,
 			   struct hdac_hdmi_cvt *cvt)
 {
-	struct hdac_hdmi_pcm *pcm = NULL;
+	struct hdac_hdmi_pcm *pcm;
 
 	list_for_each_entry(pcm, &hdmi->pcm_list, head) {
 		if (pcm->cvt == cvt)
-			break;
+			return pcm;
 	}
 
-	return pcm;
+	return NULL;
 }
 
 static void hdac_hdmi_jack_report(struct hdac_hdmi_pcm *pcm,
diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c
index f6bf4cfbea23..45da2b51543e 100644
--- a/sound/soc/codecs/max98090.c
+++ b/sound/soc/codecs/max98090.c
@@ -2103,10 +2103,8 @@ static void max98090_pll_det_disable_work(struct work_struct *work)
 			    M98090_IULK_MASK, 0);
 }
 
-static void max98090_pll_work(struct work_struct *work)
+static void max98090_pll_work(struct max98090_priv *max98090)
 {
-	struct max98090_priv *max98090 =
-		container_of(work, struct max98090_priv, pll_work);
 	struct snd_soc_component *component = max98090->component;
 
 	if (!snd_soc_component_is_active(component))
@@ -2259,7 +2257,7 @@ static irqreturn_t max98090_interrupt(int irq, void *data)
 
 	if (active & M98090_ULK_MASK) {
 		dev_dbg(component->dev, "M98090_ULK_MASK\n");
-		schedule_work(&max98090->pll_work);
+		max98090_pll_work(max98090);
 	}
 
 	if (active & M98090_JDET_MASK) {
@@ -2422,7 +2420,6 @@ static int max98090_probe(struct snd_soc_component *component)
 			  max98090_pll_det_enable_work);
 	INIT_WORK(&max98090->pll_det_disable_work,
 		  max98090_pll_det_disable_work);
-	INIT_WORK(&max98090->pll_work, max98090_pll_work);
 
 	/* Enable jack detection */
 	snd_soc_component_write(component, M98090_REG_JACK_DETECT,
@@ -2475,7 +2472,6 @@ static void max98090_remove(struct snd_soc_component *component)
 	cancel_delayed_work_sync(&max98090->jack_work);
 	cancel_delayed_work_sync(&max98090->pll_det_enable_work);
 	cancel_work_sync(&max98090->pll_det_disable_work);
-	cancel_work_sync(&max98090->pll_work);
 	max98090->component = NULL;
 }
 
diff --git a/sound/soc/codecs/max98090.h b/sound/soc/codecs/max98090.h
index 57965cd678b4..a197114b0dad 100644
--- a/sound/soc/codecs/max98090.h
+++ b/sound/soc/codecs/max98090.h
@@ -1530,7 +1530,6 @@ struct max98090_priv {
 	struct delayed_work jack_work;
 	struct delayed_work pll_det_enable_work;
 	struct work_struct pll_det_disable_work;
-	struct work_struct pll_work;
 	struct snd_soc_jack *jack;
 	unsigned int dai_fmt;
 	int tdm_slots;
diff --git a/sound/soc/codecs/max98373.c b/sound/soc/codecs/max98373.c
index 528695cd6a1c..569f7ca227e6 100644
--- a/sound/soc/codecs/max98373.c
+++ b/sound/soc/codecs/max98373.c
@@ -843,8 +843,8 @@ static int max98373_resume(struct device *dev)
 {
 	struct max98373_priv *max98373 = dev_get_drvdata(dev);
 
-	max98373_reset(max98373, dev);
 	regcache_cache_only(max98373->regmap, false);
+	max98373_reset(max98373, dev);
 	regcache_sync(max98373->regmap);
 	return 0;
 }
diff --git a/sound/soc/codecs/max9867.c b/sound/soc/codecs/max9867.c
index 8600c5439e1e..2e4aa23b5a60 100644
--- a/sound/soc/codecs/max9867.c
+++ b/sound/soc/codecs/max9867.c
@@ -46,13 +46,13 @@ static const SNDRV_CTL_TLVD_DECLARE_DB_RANGE(max9867_micboost_tlv,
 
 static const struct snd_kcontrol_new max9867_snd_controls[] = {
 	SOC_DOUBLE_R_TLV("Master Playback Volume", MAX9867_LEFTVOL,
-			MAX9867_RIGHTVOL, 0, 41, 1, max9867_master_tlv),
+			MAX9867_RIGHTVOL, 0, 40, 1, max9867_master_tlv),
 	SOC_DOUBLE_R_TLV("Line Capture Volume", MAX9867_LEFTLINELVL,
 			MAX9867_RIGHTLINELVL, 0, 15, 1, max9867_line_tlv),
 	SOC_DOUBLE_R_TLV("Mic Capture Volume", MAX9867_LEFTMICGAIN,
 			MAX9867_RIGHTMICGAIN, 0, 20, 1, max9867_mic_tlv),
 	SOC_DOUBLE_R_TLV("Mic Boost Capture Volume", MAX9867_LEFTMICGAIN,
-			MAX9867_RIGHTMICGAIN, 5, 4, 0, max9867_micboost_tlv),
+			MAX9867_RIGHTMICGAIN, 5, 3, 0, max9867_micboost_tlv),
 	SOC_SINGLE("Digital Sidetone Volume", MAX9867_SIDETONE, 0, 31, 1),
 	SOC_SINGLE_TLV("Digital Playback Volume", MAX9867_DACLEVEL, 0, 15, 1,
 			max9867_dac_tlv),
diff --git a/sound/soc/codecs/msm8916-wcd-analog.c b/sound/soc/codecs/msm8916-wcd-analog.c
index aa9a8ac987dc..c820d5a386f6 100644
--- a/sound/soc/codecs/msm8916-wcd-analog.c
+++ b/sound/soc/codecs/msm8916-wcd-analog.c
@@ -391,9 +391,6 @@ static int pm8916_wcd_analog_enable_micbias_int(struct snd_soc_component
 
 	switch (event) {
 	case SND_SOC_DAPM_PRE_PMU:
-		snd_soc_component_update_bits(component, CDC_A_MICB_1_INT_RBIAS,
-				    MICB_1_INT_TX2_INT_RBIAS_EN_MASK,
-				    MICB_1_INT_TX2_INT_RBIAS_EN_ENABLE);
 		snd_soc_component_update_bits(component, reg, MICB_1_EN_PULL_DOWN_EN_MASK, 0);
 		snd_soc_component_update_bits(component, CDC_A_MICB_1_EN,
 				    MICB_1_EN_OPA_STG2_TAIL_CURR_MASK,
@@ -443,6 +440,14 @@ static int pm8916_wcd_analog_enable_micbias_int1(struct
 	struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
 	struct pm8916_wcd_analog_priv *wcd = snd_soc_component_get_drvdata(component);
 
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		snd_soc_component_update_bits(component, CDC_A_MICB_1_INT_RBIAS,
+				    MICB_1_INT_TX1_INT_RBIAS_EN_MASK,
+				    MICB_1_INT_TX1_INT_RBIAS_EN_ENABLE);
+		break;
+	}
+
 	return pm8916_wcd_analog_enable_micbias_int(component, event, w->reg,
 						     wcd->micbias1_cap_mode);
 }
@@ -553,6 +558,11 @@ static int pm8916_wcd_analog_enable_micbias_int2(struct
 	struct pm8916_wcd_analog_priv *wcd = snd_soc_component_get_drvdata(component);
 
 	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		snd_soc_component_update_bits(component, CDC_A_MICB_1_INT_RBIAS,
+				    MICB_1_INT_TX2_INT_RBIAS_EN_MASK,
+				    MICB_1_INT_TX2_INT_RBIAS_EN_ENABLE);
+		break;
 	case SND_SOC_DAPM_POST_PMU:
 		pm8916_mbhc_configure_bias(wcd, true);
 		break;
@@ -888,10 +898,10 @@ static const struct snd_soc_dapm_widget pm8916_wcd_analog_dapm_widgets[] = {
 
 	SND_SOC_DAPM_SUPPLY("MIC BIAS External1", CDC_A_MICB_1_EN, 7, 0,
 			    pm8916_wcd_analog_enable_micbias_ext1,
-			    SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD),
+			    SND_SOC_DAPM_POST_PMU),
 	SND_SOC_DAPM_SUPPLY("MIC BIAS External2", CDC_A_MICB_2_EN, 7, 0,
 			    pm8916_wcd_analog_enable_micbias_ext2,
-			    SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_POST_PMD),
+			    SND_SOC_DAPM_POST_PMU),
 
 	SND_SOC_DAPM_ADC_E("ADC1", NULL, CDC_A_TX_1_EN, 7, 0,
 			   pm8916_wcd_analog_enable_adc,
diff --git a/sound/soc/codecs/msm8916-wcd-digital.c b/sound/soc/codecs/msm8916-wcd-digital.c
index ab7e26827cf8..1d56370fae69 100644
--- a/sound/soc/codecs/msm8916-wcd-digital.c
+++ b/sound/soc/codecs/msm8916-wcd-digital.c
@@ -356,6 +356,12 @@ static int msm8916_wcd_digital_enable_interpolator(
 		snd_soc_component_write(component, rx_gain_reg[w->shift],
 			      snd_soc_component_read32(component, rx_gain_reg[w->shift]));
 		break;
+	case SND_SOC_DAPM_POST_PMD:
+		snd_soc_component_update_bits(component, LPASS_CDC_CLK_RX_RESET_CTL,
+					      1 << w->shift, 1 << w->shift);
+		snd_soc_component_update_bits(component, LPASS_CDC_CLK_RX_RESET_CTL,
+					      1 << w->shift, 0x0);
+		break;
 	}
 	return 0;
 }
diff --git a/sound/soc/codecs/pcm512x.c b/sound/soc/codecs/pcm512x.c
index 861210f6bf4f..4cbef9affffd 100644
--- a/sound/soc/codecs/pcm512x.c
+++ b/sound/soc/codecs/pcm512x.c
@@ -1564,13 +1564,15 @@ int pcm512x_probe(struct device *dev, struct regmap *regmap)
 	}
 
 	pcm512x->sclk = devm_clk_get(dev, NULL);
-	if (PTR_ERR(pcm512x->sclk) == -EPROBE_DEFER)
-		return -EPROBE_DEFER;
+	if (PTR_ERR(pcm512x->sclk) == -EPROBE_DEFER) {
+		ret = -EPROBE_DEFER;
+		goto err;
+	}
 	if (!IS_ERR(pcm512x->sclk)) {
 		ret = clk_prepare_enable(pcm512x->sclk);
 		if (ret != 0) {
 			dev_err(dev, "Failed to enable SCLK: %d\n", ret);
-			return ret;
+			goto err;
 		}
 	}
 
diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c
index adbae1f36a8a..747ca248bf10 100644
--- a/sound/soc/codecs/rt5640.c
+++ b/sound/soc/codecs/rt5640.c
@@ -2432,6 +2432,13 @@ static void rt5640_disable_jack_detect(struct snd_soc_component *component)
 {
 	struct rt5640_priv *rt5640 = snd_soc_component_get_drvdata(component);
 
+	/*
+	 * soc_remove_component() force-disables jack and thus rt5640->jack
+	 * could be NULL at the time of driver's module unloading.
+	 */
+	if (!rt5640->jack)
+		return;
+
 	disable_irq(rt5640->irq);
 	rt5640_cancel_work(rt5640);
 
diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index 19662ee330d6..c83f7f5da96b 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -3625,6 +3625,12 @@ static const struct rt5645_platform_data asus_t100ha_platform_data = {
 	.inv_jd1_1 = true,
 };
 
+static const struct rt5645_platform_data asus_t101ha_platform_data = {
+	.dmic1_data_pin = RT5645_DMIC_DATA_IN2N,
+	.dmic2_data_pin = RT5645_DMIC2_DISABLE,
+	.jd_mode = 3,
+};
+
 static const struct rt5645_platform_data lenovo_ideapad_miix_310_pdata = {
 	.jd_mode = 3,
 	.in2_diff = true,
@@ -3703,6 +3709,14 @@ static const struct dmi_system_id dmi_platform_data[] = {
 		.driver_data = (void *)&asus_t100ha_platform_data,
 	},
 	{
+		.ident = "ASUS T101HA",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "T101HA"),
+		},
+		.driver_data = (void *)&asus_t101ha_platform_data,
+	},
+	{
 		.ident = "MINIX Z83-4",
 		.matches = {
 			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "MINIX"),
diff --git a/sound/soc/codecs/rt5670.c b/sound/soc/codecs/rt5670.c
index 70fee6849ab0..f21181734170 100644
--- a/sound/soc/codecs/rt5670.c
+++ b/sound/soc/codecs/rt5670.c
@@ -31,18 +31,19 @@
 #include "rt5670.h"
 #include "rt5670-dsp.h"
 
-#define RT5670_DEV_GPIO     BIT(0)
-#define RT5670_IN2_DIFF     BIT(1)
-#define RT5670_DMIC_EN      BIT(2)
-#define RT5670_DMIC1_IN2P   BIT(3)
-#define RT5670_DMIC1_GPIO6  BIT(4)
-#define RT5670_DMIC1_GPIO7  BIT(5)
-#define RT5670_DMIC2_INR    BIT(6)
-#define RT5670_DMIC2_GPIO8  BIT(7)
-#define RT5670_DMIC3_GPIO5  BIT(8)
-#define RT5670_JD_MODE1     BIT(9)
-#define RT5670_JD_MODE2     BIT(10)
-#define RT5670_JD_MODE3     BIT(11)
+#define RT5670_DEV_GPIO			BIT(0)
+#define RT5670_IN2_DIFF			BIT(1)
+#define RT5670_DMIC_EN			BIT(2)
+#define RT5670_DMIC1_IN2P		BIT(3)
+#define RT5670_DMIC1_GPIO6		BIT(4)
+#define RT5670_DMIC1_GPIO7		BIT(5)
+#define RT5670_DMIC2_INR		BIT(6)
+#define RT5670_DMIC2_GPIO8		BIT(7)
+#define RT5670_DMIC3_GPIO5		BIT(8)
+#define RT5670_JD_MODE1			BIT(9)
+#define RT5670_JD_MODE2			BIT(10)
+#define RT5670_JD_MODE3			BIT(11)
+#define RT5670_GPIO1_IS_EXT_SPK_EN	BIT(12)
 
 static unsigned long rt5670_quirk;
 static unsigned int quirk_override;
@@ -1447,6 +1448,33 @@ static int rt5670_hp_event(struct snd_soc_dapm_widget *w,
 	return 0;
 }
 
+static int rt5670_spk_event(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
+	struct rt5670_priv *rt5670 = snd_soc_component_get_drvdata(component);
+
+	if (!rt5670->pdata.gpio1_is_ext_spk_en)
+		return 0;
+
+	switch (event) {
+	case SND_SOC_DAPM_POST_PMU:
+		regmap_update_bits(rt5670->regmap, RT5670_GPIO_CTRL2,
+				   RT5670_GP1_OUT_MASK, RT5670_GP1_OUT_HI);
+		break;
+
+	case SND_SOC_DAPM_PRE_PMD:
+		regmap_update_bits(rt5670->regmap, RT5670_GPIO_CTRL2,
+				   RT5670_GP1_OUT_MASK, RT5670_GP1_OUT_LO);
+		break;
+
+	default:
+		return 0;
+	}
+
+	return 0;
+}
+
 static int rt5670_bst1_event(struct snd_soc_dapm_widget *w,
 	struct snd_kcontrol *kcontrol, int event)
 {
@@ -1860,7 +1888,9 @@ static const struct snd_soc_dapm_widget rt5670_specific_dapm_widgets[] = {
 };
 
 static const struct snd_soc_dapm_widget rt5672_specific_dapm_widgets[] = {
-	SND_SOC_DAPM_PGA("SPO Amp", SND_SOC_NOPM, 0, 0, NULL, 0),
+	SND_SOC_DAPM_PGA_E("SPO Amp", SND_SOC_NOPM, 0, 0, NULL, 0,
+			   rt5670_spk_event, SND_SOC_DAPM_PRE_PMD |
+			   SND_SOC_DAPM_POST_PMU),
 	SND_SOC_DAPM_OUTPUT("SPOLP"),
 	SND_SOC_DAPM_OUTPUT("SPOLN"),
 	SND_SOC_DAPM_OUTPUT("SPORP"),
@@ -2857,14 +2887,14 @@ static const struct dmi_system_id dmi_platform_intel_quirks[] = {
 	},
 	{
 		.callback = rt5670_quirk_cb,
-		.ident = "Lenovo Thinkpad Tablet 10",
+		.ident = "Lenovo Miix 2 10",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
 			DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo Miix 2 10"),
 		},
 		.driver_data = (unsigned long *)(RT5670_DMIC_EN |
 						 RT5670_DMIC1_IN2P |
-						 RT5670_DEV_GPIO |
+						 RT5670_GPIO1_IS_EXT_SPK_EN |
 						 RT5670_JD_MODE2),
 	},
 	{
@@ -2924,6 +2954,10 @@ static int rt5670_i2c_probe(struct i2c_client *i2c,
 		rt5670->pdata.dev_gpio = true;
 		dev_info(&i2c->dev, "quirk dev_gpio\n");
 	}
+	if (rt5670_quirk & RT5670_GPIO1_IS_EXT_SPK_EN) {
+		rt5670->pdata.gpio1_is_ext_spk_en = true;
+		dev_info(&i2c->dev, "quirk GPIO1 is external speaker enable\n");
+	}
 	if (rt5670_quirk & RT5670_IN2_DIFF) {
 		rt5670->pdata.in2_diff = true;
 		dev_info(&i2c->dev, "quirk IN2_DIFF\n");
@@ -3023,6 +3057,13 @@ static int rt5670_i2c_probe(struct i2c_client *i2c,
 				   RT5670_GP1_PF_MASK, RT5670_GP1_PF_OUT);
 	}
 
+	if (rt5670->pdata.gpio1_is_ext_spk_en) {
+		regmap_update_bits(rt5670->regmap, RT5670_GPIO_CTRL1,
+				   RT5670_GP1_PIN_MASK, RT5670_GP1_PIN_GPIO1);
+		regmap_update_bits(rt5670->regmap, RT5670_GPIO_CTRL2,
+				   RT5670_GP1_PF_MASK, RT5670_GP1_PF_OUT);
+	}
+
 	if (rt5670->pdata.jd_mode) {
 		regmap_update_bits(rt5670->regmap, RT5670_GLB_CLK,
 				   RT5670_SCLK_SRC_MASK, RT5670_SCLK_SRC_RCCLK);
diff --git a/sound/soc/codecs/rt5670.h b/sound/soc/codecs/rt5670.h
index a8c3e44770b8..de0203369b7c 100644
--- a/sound/soc/codecs/rt5670.h
+++ b/sound/soc/codecs/rt5670.h
@@ -757,7 +757,7 @@
 #define RT5670_PWR_VREF2_BIT			4
 #define RT5670_PWR_FV2				(0x1 << 3)
 #define RT5670_PWR_FV2_BIT			3
-#define RT5670_LDO_SEL_MASK			(0x3)
+#define RT5670_LDO_SEL_MASK			(0x7)
 #define RT5670_LDO_SEL_SFT			0
 
 /* Power Management for Analog 2 (0x64) */
diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c
index 1199e91b569e..a0cce7452b45 100644
--- a/sound/soc/codecs/rt5682.c
+++ b/sound/soc/codecs/rt5682.c
@@ -72,6 +72,7 @@ struct rt5682_priv {
 static const struct reg_sequence patch_list[] = {
 	{RT5682_HP_IMP_SENS_CTRL_19, 0x1000},
 	{RT5682_DAC_ADC_DIG_VOL1, 0xa020},
+	{RT5682_I2C_CTRL, 0x000f},
 };
 
 static const struct reg_default rt5682_reg[] = {
@@ -2481,6 +2482,7 @@ static void rt5682_calibrate(struct rt5682_priv *rt5682)
 	mutex_lock(&rt5682->calibrate_mutex);
 
 	rt5682_reset(rt5682->regmap);
+	regmap_write(rt5682->regmap, RT5682_I2C_CTRL, 0x000f);
 	regmap_write(rt5682->regmap, RT5682_PWR_ANLG_1, 0xa2af);
 	usleep_range(15000, 20000);
 	regmap_write(rt5682->regmap, RT5682_PWR_ANLG_1, 0xf2af);
diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c
index 8e5e48f6a24b..c58ad2a13e4e 100644
--- a/sound/soc/codecs/sgtl5000.c
+++ b/sound/soc/codecs/sgtl5000.c
@@ -1343,7 +1343,8 @@ static int sgtl5000_set_power_regs(struct snd_soc_component *component)
 		 * if vddio == vdda the source of charge pump should be
 		 * assigned manually to VDDIO
 		 */
-		if (vddio == vdda) {
+		if (regulator_is_equal(sgtl5000->supplies[VDDA].consumer,
+				       sgtl5000->supplies[VDDIO].consumer)) {
 			lreg_ctrl |= SGTL5000_VDDC_ASSN_OVRD;
 			lreg_ctrl |= SGTL5000_VDDC_MAN_ASSN_VDDIO <<
 				    SGTL5000_VDDC_MAN_ASSN_SHIFT;
@@ -1643,6 +1644,40 @@ static int sgtl5000_i2c_probe(struct i2c_client *client,
 		dev_err(&client->dev,
 			"Error %d initializing CHIP_CLK_CTRL\n", ret);
 
+	/* Mute everything to avoid pop from the following power-up */
+	ret = regmap_write(sgtl5000->regmap, SGTL5000_CHIP_ANA_CTRL,
+			   SGTL5000_CHIP_ANA_CTRL_DEFAULT);
+	if (ret) {
+		dev_err(&client->dev,
+			"Error %d muting outputs via CHIP_ANA_CTRL\n", ret);
+		goto disable_clk;
+	}
+
+	/*
+	 * If VAG is powered-on (e.g. from previous boot), it would be disabled
+	 * by the write to ANA_POWER in later steps of the probe code. This
+	 * may create a loud pop even with all outputs muted. The proper way
+	 * to circumvent this is disabling the bit first and waiting the proper
+	 * cool-down time.
+	 */
+	ret = regmap_read(sgtl5000->regmap, SGTL5000_CHIP_ANA_POWER, &value);
+	if (ret) {
+		dev_err(&client->dev, "Failed to read ANA_POWER: %d\n", ret);
+		goto disable_clk;
+	}
+	if (value & SGTL5000_VAG_POWERUP) {
+		ret = regmap_update_bits(sgtl5000->regmap,
+					 SGTL5000_CHIP_ANA_POWER,
+					 SGTL5000_VAG_POWERUP,
+					 0);
+		if (ret) {
+			dev_err(&client->dev, "Error %d disabling VAG\n", ret);
+			goto disable_clk;
+		}
+
+		msleep(SGTL5000_VAG_POWERDOWN_DELAY);
+	}
+
 	/* Follow section 2.2.1.1 of AN3663 */
 	ana_pwr = SGTL5000_ANA_POWER_DEFAULT;
 	if (sgtl5000->num_supplies <= VDDD) {
diff --git a/sound/soc/codecs/sgtl5000.h b/sound/soc/codecs/sgtl5000.h
index 18cae08bbd3a..066517e352a7 100644
--- a/sound/soc/codecs/sgtl5000.h
+++ b/sound/soc/codecs/sgtl5000.h
@@ -233,6 +233,7 @@
 /*
  * SGTL5000_CHIP_ANA_CTRL
  */
+#define SGTL5000_CHIP_ANA_CTRL_DEFAULT		0x0133
 #define SGTL5000_LINE_OUT_MUTE			0x0100
 #define SGTL5000_HP_SEL_MASK			0x0040
 #define SGTL5000_HP_SEL_SHIFT			6
diff --git a/sound/soc/codecs/tas571x.c b/sound/soc/codecs/tas571x.c
index 20798fa2988a..be4fd16bcad7 100644
--- a/sound/soc/codecs/tas571x.c
+++ b/sound/soc/codecs/tas571x.c
@@ -820,8 +820,10 @@ static int tas571x_i2c_probe(struct i2c_client *client,
 
 	priv->regmap = devm_regmap_init(dev, NULL, client,
 					priv->chip->regmap_config);
-	if (IS_ERR(priv->regmap))
-		return PTR_ERR(priv->regmap);
+	if (IS_ERR(priv->regmap)) {
+		ret = PTR_ERR(priv->regmap);
+		goto disable_regs;
+	}
 
 	priv->pdn_gpio = devm_gpiod_get_optional(dev, "pdn", GPIOD_OUT_LOW);
 	if (IS_ERR(priv->pdn_gpio)) {
@@ -845,7 +847,7 @@ static int tas571x_i2c_probe(struct i2c_client *client,
 
 	ret = regmap_write(priv->regmap, TAS571X_OSC_TRIM_REG, 0);
 	if (ret)
-		return ret;
+		goto disable_regs;
 
 	usleep_range(50000, 60000);
 
@@ -861,12 +863,20 @@ static int tas571x_i2c_probe(struct i2c_client *client,
 		 */
 		ret = regmap_update_bits(priv->regmap, TAS571X_MVOL_REG, 1, 0);
 		if (ret)
-			return ret;
+			goto disable_regs;
 	}
 
-	return devm_snd_soc_register_component(&client->dev,
+	ret = devm_snd_soc_register_component(&client->dev,
 				      &priv->component_driver,
 				      &tas571x_dai, 1);
+	if (ret)
+		goto disable_regs;
+
+	return ret;
+
+disable_regs:
+	regulator_bulk_disable(priv->chip->num_supply_names, priv->supplies);
+	return ret;
 }
 
 static int tas571x_i2c_remove(struct i2c_client *client)
diff --git a/sound/soc/codecs/wm8960.c b/sound/soc/codecs/wm8960.c
index 55112c1bba5e..6cf0f6612bda 100644
--- a/sound/soc/codecs/wm8960.c
+++ b/sound/soc/codecs/wm8960.c
@@ -860,8 +860,7 @@ static int wm8960_hw_params(struct snd_pcm_substream *substream,
 
 	wm8960->is_stream_in_use[tx] = true;
 
-	if (snd_soc_component_get_bias_level(component) == SND_SOC_BIAS_ON &&
-	    !wm8960->is_stream_in_use[!tx])
+	if (!wm8960->is_stream_in_use[!tx])
 		return wm8960_configure_clocking(component);
 
 	return 0;
diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c
index 3e5c69fbc33a..d9d59f45833f 100644
--- a/sound/soc/codecs/wm8962.c
+++ b/sound/soc/codecs/wm8962.c
@@ -2788,7 +2788,7 @@ static int fll_factors(struct _fll_div *fll_div, unsigned int Fref,
 
 	if (target % Fref == 0) {
 		fll_div->theta = 0;
-		fll_div->lambda = 0;
+		fll_div->lambda = 1;
 	} else {
 		gcd_fll = gcd(target, fratio * Fref);
 
@@ -2858,7 +2858,7 @@ static int wm8962_set_fll(struct snd_soc_component *component, int fll_id, int s
 		return -EINVAL;
 	}
 
-	if (fll_div.theta || fll_div.lambda)
+	if (fll_div.theta)
 		fll1 |= WM8962_FLL_FRAC;
 
 	/* Stop the FLL while we reconfigure */
diff --git a/sound/soc/fsl/fsl_asrc_dma.c b/sound/soc/fsl/fsl_asrc_dma.c
index 01052a0808b0..5aee6b8366d2 100644
--- a/sound/soc/fsl/fsl_asrc_dma.c
+++ b/sound/soc/fsl/fsl_asrc_dma.c
@@ -241,6 +241,7 @@ static int fsl_asrc_dma_hw_params(struct snd_pcm_substream *substream,
 	ret = dmaengine_slave_config(pair->dma_chan[dir], &config_be);
 	if (ret) {
 		dev_err(dev, "failed to config DMA channel for Back-End\n");
+		dma_release_channel(pair->dma_chan[dir]);
 		return ret;
 	}
 
diff --git a/sound/soc/fsl/fsl_audmix.c b/sound/soc/fsl/fsl_audmix.c
index 3f69ce98bc4b..fe54b32b1eb0 100644
--- a/sound/soc/fsl/fsl_audmix.c
+++ b/sound/soc/fsl/fsl_audmix.c
@@ -507,15 +507,20 @@ static int fsl_audmix_probe(struct platform_device *pdev)
 					      ARRAY_SIZE(fsl_audmix_dai));
 	if (ret) {
 		dev_err(dev, "failed to register ASoC DAI\n");
-		return ret;
+		goto err_disable_pm;
 	}
 
 	priv->pdev = platform_device_register_data(dev, mdrv, 0, NULL, 0);
 	if (IS_ERR(priv->pdev)) {
 		ret = PTR_ERR(priv->pdev);
 		dev_err(dev, "failed to register platform %s: %d\n", mdrv, ret);
+		goto err_disable_pm;
 	}
 
+	return 0;
+
+err_disable_pm:
+	pm_runtime_disable(dev);
 	return ret;
 }
 
@@ -523,6 +528,8 @@ static int fsl_audmix_remove(struct platform_device *pdev)
 {
 	struct fsl_audmix *priv = dev_get_drvdata(&pdev->dev);
 
+	pm_runtime_disable(&pdev->dev);
+
 	if (priv->pdev)
 		platform_device_unregister(priv->pdev);
 
diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c
index 8593269156bd..5e8078ba0a5d 100644
--- a/sound/soc/fsl/fsl_sai.c
+++ b/sound/soc/fsl/fsl_sai.c
@@ -907,12 +907,24 @@ static int fsl_sai_probe(struct platform_device *pdev)
 	ret = devm_snd_soc_register_component(&pdev->dev, &fsl_component,
 			&fsl_sai_dai, 1);
 	if (ret)
-		return ret;
+		goto err_pm_disable;
 
-	if (sai->sai_on_imx)
-		return imx_pcm_dma_init(pdev, IMX_SAI_DMABUF_SIZE);
-	else
-		return devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0);
+	if (sai->sai_on_imx) {
+		ret = imx_pcm_dma_init(pdev, IMX_SAI_DMABUF_SIZE);
+		if (ret)
+			goto err_pm_disable;
+	} else {
+		ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0);
+		if (ret)
+			goto err_pm_disable;
+	}
+
+	return ret;
+
+err_pm_disable:
+	pm_runtime_disable(&pdev->dev);
+
+	return ret;
 }
 
 static int fsl_sai_remove(struct platform_device *pdev)
diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c
index d83be26d6446..0e2bdad373d6 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -678,8 +678,9 @@ static int fsl_ssi_set_bclk(struct snd_pcm_substream *substream,
 	struct regmap *regs = ssi->regs;
 	u32 pm = 999, div2, psr, stccr, mask, afreq, factor, i;
 	unsigned long clkrate, baudrate, tmprate;
-	unsigned int slots = params_channels(hw_params);
-	unsigned int slot_width = 32;
+	unsigned int channels = params_channels(hw_params);
+	unsigned int slot_width = params_width(hw_params);
+	unsigned int slots = 2;
 	u64 sub, savesub = 100000;
 	unsigned int freq;
 	bool baudclk_is_used;
@@ -688,10 +689,14 @@ static int fsl_ssi_set_bclk(struct snd_pcm_substream *substream,
 	/* Override slots and slot_width if being specifically set... */
 	if (ssi->slots)
 		slots = ssi->slots;
-	/* ...but keep 32 bits if slots is 2 -- I2S Master mode */
-	if (ssi->slot_width && slots != 2)
+	if (ssi->slot_width)
 		slot_width = ssi->slot_width;
 
+	/* ...but force 32 bits for stereo audio using I2S Master Mode */
+	if (channels == 2 &&
+	    (ssi->i2s_net & SSI_SCR_I2S_MODE_MASK) == SSI_SCR_I2S_MODE_MASTER)
+		slot_width = 32;
+
 	/* Generate bit clock based on the slot number and slot width */
 	freq = slots * slot_width * params_rate(hw_params);
 
diff --git a/sound/soc/fsl/imx-audmix.c b/sound/soc/fsl/imx-audmix.c
index 9aaf3e5b45b9..a0f5c4a37ceb 100644
--- a/sound/soc/fsl/imx-audmix.c
+++ b/sound/soc/fsl/imx-audmix.c
@@ -300,14 +300,14 @@ static int imx_audmix_probe(struct platform_device *pdev)
 	priv->card.num_configs = priv->num_dai_conf;
 	priv->card.dapm_routes = priv->dapm_routes;
 	priv->card.num_dapm_routes = priv->num_dapm_routes;
-	priv->card.dev = pdev->dev.parent;
+	priv->card.dev = &pdev->dev;
 	priv->card.owner = THIS_MODULE;
 	priv->card.name = "imx-audmix";
 
 	platform_set_drvdata(pdev, &priv->card);
 	snd_soc_card_set_drvdata(&priv->card, priv);
 
-	ret = devm_snd_soc_register_card(pdev->dev.parent, &priv->card);
+	ret = devm_snd_soc_register_card(&pdev->dev, &priv->card);
 	if (ret) {
 		dev_err(&pdev->dev, "snd_soc_register_card failed\n");
 		return ret;
diff --git a/sound/soc/img/img-i2s-in.c b/sound/soc/img/img-i2s-in.c
index fdd2c73fd2fa..869fe0068cbd 100644
--- a/sound/soc/img/img-i2s-in.c
+++ b/sound/soc/img/img-i2s-in.c
@@ -482,6 +482,7 @@ static int img_i2s_in_probe(struct platform_device *pdev)
 	if (IS_ERR(rst)) {
 		if (PTR_ERR(rst) == -EPROBE_DEFER) {
 			ret = -EPROBE_DEFER;
+			pm_runtime_put(&pdev->dev);
 			goto err_suspend;
 		}
 
diff --git a/sound/soc/intel/Kconfig b/sound/soc/intel/Kconfig
index 1f868da106b7..48f2b91b3bed 100644
--- a/sound/soc/intel/Kconfig
+++ b/sound/soc/intel/Kconfig
@@ -59,6 +59,9 @@ config SND_SOC_INTEL_HASWELL
 	  If you have a Intel Haswell or Broadwell platform connected to
 	  an I2S codec, then enable this option by saying Y or m. This is
 	  typically used for Chromebooks. This is a recommended option.
+	  This option is mutually exclusive with the SOF support on
+	  Broadwell. If you want to enable SOF on Broadwell, you need to
+	  deselect this option first.
 
 config SND_SOC_INTEL_BAYTRAIL
 	tristate "Baytrail (legacy) Platforms"
diff --git a/sound/soc/intel/atom/sst-atom-controls.c b/sound/soc/intel/atom/sst-atom-controls.c
index baef461a99f1..df8f7994d3b7 100644
--- a/sound/soc/intel/atom/sst-atom-controls.c
+++ b/sound/soc/intel/atom/sst-atom-controls.c
@@ -966,7 +966,9 @@ static int sst_set_be_modules(struct snd_soc_dapm_widget *w,
 	dev_dbg(c->dev, "Enter: widget=%s\n", w->name);
 
 	if (SND_SOC_DAPM_EVENT_ON(event)) {
+		mutex_lock(&drv->lock);
 		ret = sst_send_slot_map(drv);
+		mutex_unlock(&drv->lock);
 		if (ret)
 			return ret;
 		ret = sst_send_pipe_module_params(w, k);
@@ -1333,7 +1335,7 @@ int sst_send_pipe_gains(struct snd_soc_dai *dai, int stream, int mute)
 				dai->capture_widget->name);
 		w = dai->capture_widget;
 		snd_soc_dapm_widget_for_each_source_path(w, p) {
-			if (p->connected && !p->connected(w, p->sink))
+			if (p->connected && !p->connected(w, p->source))
 				continue;
 
 			if (p->connect &&  p->source->power &&
diff --git a/sound/soc/intel/atom/sst/sst_pci.c b/sound/soc/intel/atom/sst/sst_pci.c
index d952719bc098..5862fe968083 100644
--- a/sound/soc/intel/atom/sst/sst_pci.c
+++ b/sound/soc/intel/atom/sst/sst_pci.c
@@ -99,7 +99,7 @@ static int sst_platform_get_resources(struct intel_sst_drv *ctx)
 	dev_dbg(ctx->dev, "DRAM Ptr %p\n", ctx->dram);
 do_release_regions:
 	pci_release_regions(pci);
-	return 0;
+	return ret;
 }
 
 /*
diff --git a/sound/soc/intel/boards/bxt_rt298.c b/sound/soc/intel/boards/bxt_rt298.c
index 771df36fbbaf..82d4fdacfcf7 100644
--- a/sound/soc/intel/boards/bxt_rt298.c
+++ b/sound/soc/intel/boards/bxt_rt298.c
@@ -537,6 +537,7 @@ static int bxt_card_late_probe(struct snd_soc_card *card)
 /* broxton audio machine driver for SPT + RT298S */
 static struct snd_soc_card broxton_rt298 = {
 	.name = "broxton-rt298",
+	.owner = THIS_MODULE,
 	.dai_link = broxton_rt298_dais,
 	.num_links = ARRAY_SIZE(broxton_rt298_dais),
 	.controls = broxton_controls,
@@ -552,6 +553,7 @@ static struct snd_soc_card broxton_rt298 = {
 
 static struct snd_soc_card geminilake_rt298 = {
 	.name = "geminilake-rt298",
+	.owner = THIS_MODULE,
 	.dai_link = broxton_rt298_dais,
 	.num_links = ARRAY_SIZE(broxton_rt298_dais),
 	.controls = broxton_controls,
diff --git a/sound/soc/intel/boards/bytcht_es8316.c b/sound/soc/intel/boards/bytcht_es8316.c
index c360ebc3ccc7..1d2fe84bd3d7 100644
--- a/sound/soc/intel/boards/bytcht_es8316.c
+++ b/sound/soc/intel/boards/bytcht_es8316.c
@@ -441,7 +441,8 @@ static const struct dmi_system_id byt_cht_es8316_quirk_table[] = {
 			DMI_MATCH(DMI_SYS_VENDOR, "IRBIS"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "NB41"),
 		},
-		.driver_data = (void *)(BYT_CHT_ES8316_INTMIC_IN2_MAP
+		.driver_data = (void *)(BYT_CHT_ES8316_SSP0
+					| BYT_CHT_ES8316_INTMIC_IN2_MAP
 					| BYT_CHT_ES8316_JD_INVERTED),
 	},
 	{	/* Teclast X98 Plus II */
@@ -546,8 +547,10 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev)
 
 	if (cnt) {
 		ret = device_add_properties(codec_dev, props);
-		if (ret)
+		if (ret) {
+			put_device(codec_dev);
 			return ret;
+		}
 	}
 
 	devm_acpi_dev_add_driver_gpios(codec_dev, byt_cht_es8316_gpios);
diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index 7f94f9328f9c..be73a54c1bf3 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -591,6 +591,17 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
 					BYT_RT5640_SSP0_AIF1 |
 					BYT_RT5640_MCLK_EN),
 	},
+	{
+		/* MPMAN MPWIN895CL */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "MPMAN"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "MPWIN8900CL"),
+		},
+		.driver_data = (void *)(BYTCR_INPUT_DEFAULTS |
+					BYT_RT5640_MONO_SPEAKER |
+					BYT_RT5640_SSP0_AIF1 |
+					BYT_RT5640_MCLK_EN),
+	},
 	{	/* MSI S100 tablet */
 		.matches = {
 			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Micro-Star International Co., Ltd."),
@@ -707,13 +718,17 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
 					BYT_RT5640_MCLK_EN),
 	},
 	{
+		/* Teclast X89 */
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "TECLAST"),
 			DMI_MATCH(DMI_BOARD_NAME, "tPAD"),
 		},
 		.driver_data = (void *)(BYT_RT5640_IN3_MAP |
-					BYT_RT5640_MCLK_EN |
-					BYT_RT5640_SSP0_AIF1),
+					BYT_RT5640_JD_SRC_JD1_IN4P |
+					BYT_RT5640_OVCD_TH_2000UA |
+					BYT_RT5640_OVCD_SF_1P0 |
+					BYT_RT5640_SSP0_AIF1 |
+					BYT_RT5640_MCLK_EN),
 	},
 	{	/* Toshiba Satellite Click Mini L9W-B */
 		.matches = {
@@ -727,6 +742,30 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
 					BYT_RT5640_SSP0_AIF1 |
 					BYT_RT5640_MCLK_EN),
 	},
+	{	/* Toshiba Encore WT8-A */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "TOSHIBA WT8-A"),
+		},
+		.driver_data = (void *)(BYT_RT5640_DMIC1_MAP |
+					BYT_RT5640_JD_SRC_JD2_IN4N |
+					BYT_RT5640_OVCD_TH_2000UA |
+					BYT_RT5640_OVCD_SF_0P75 |
+					BYT_RT5640_JD_NOT_INV |
+					BYT_RT5640_MCLK_EN),
+	},
+	{	/* Toshiba Encore WT10-A */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "TOSHIBA WT10-A-103"),
+		},
+		.driver_data = (void *)(BYT_RT5640_DMIC1_MAP |
+					BYT_RT5640_JD_SRC_JD1_IN4P |
+					BYT_RT5640_OVCD_TH_2000UA |
+					BYT_RT5640_OVCD_SF_0P75 |
+					BYT_RT5640_SSP0_AIF2 |
+					BYT_RT5640_MCLK_EN),
+	},
 	{	/* Catch-all for generic Insyde tablets, must be last */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Insyde"),
diff --git a/sound/soc/intel/boards/cht_bsw_rt5645.c b/sound/soc/intel/boards/cht_bsw_rt5645.c
index 2c07ec8b42ae..c406528e4c9c 100644
--- a/sound/soc/intel/boards/cht_bsw_rt5645.c
+++ b/sound/soc/intel/boards/cht_bsw_rt5645.c
@@ -48,6 +48,7 @@ struct cht_mc_private {
 #define CHT_RT5645_SSP2_AIF2     BIT(16) /* default is using AIF1  */
 #define CHT_RT5645_SSP0_AIF1     BIT(17)
 #define CHT_RT5645_SSP0_AIF2     BIT(18)
+#define CHT_RT5645_PMC_PLT_CLK_0 BIT(19)
 
 static unsigned long cht_rt5645_quirk = 0;
 
@@ -59,6 +60,8 @@ static void log_quirks(struct device *dev)
 		dev_info(dev, "quirk SSP0_AIF1 enabled");
 	if (cht_rt5645_quirk & CHT_RT5645_SSP0_AIF2)
 		dev_info(dev, "quirk SSP0_AIF2 enabled");
+	if (cht_rt5645_quirk & CHT_RT5645_PMC_PLT_CLK_0)
+		dev_info(dev, "quirk PMC_PLT_CLK_0 enabled");
 }
 
 static int platform_clock_control(struct snd_soc_dapm_widget *w,
@@ -226,16 +229,22 @@ static int cht_aif1_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-/* uncomment when we have a real quirk
 static int cht_rt5645_quirk_cb(const struct dmi_system_id *id)
 {
 	cht_rt5645_quirk = (unsigned long)id->driver_data;
 	return 1;
 }
-*/
 
 static const struct dmi_system_id cht_rt5645_quirk_table[] = {
 	{
+		/* Strago family Chromebooks */
+		.callback = cht_rt5645_quirk_cb,
+		.matches = {
+			DMI_MATCH(DMI_PRODUCT_FAMILY, "Intel_Strago"),
+		},
+		.driver_data = (void *)CHT_RT5645_PMC_PLT_CLK_0,
+	},
+	{
 	},
 };
 
@@ -530,6 +539,7 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
 	int dai_index = 0;
 	int ret_val = 0;
 	int i;
+	const char *mclk_name;
 
 	drv = devm_kzalloc(&pdev->dev, sizeof(*drv), GFP_KERNEL);
 	if (!drv)
@@ -665,11 +675,15 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
 	if (ret_val)
 		return ret_val;
 
-	drv->mclk = devm_clk_get(&pdev->dev, "pmc_plt_clk_3");
+	if (cht_rt5645_quirk & CHT_RT5645_PMC_PLT_CLK_0)
+		mclk_name = "pmc_plt_clk_0";
+	else
+		mclk_name = "pmc_plt_clk_3";
+
+	drv->mclk = devm_clk_get(&pdev->dev, mclk_name);
 	if (IS_ERR(drv->mclk)) {
-		dev_err(&pdev->dev,
-			"Failed to get MCLK from pmc_plt_clk_3: %ld\n",
-			PTR_ERR(drv->mclk));
+		dev_err(&pdev->dev, "Failed to get MCLK from %s: %ld\n",
+			mclk_name, PTR_ERR(drv->mclk));
 		return PTR_ERR(drv->mclk);
 	}
 
diff --git a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c
index cfcc89f0fed0..0090baae1b2d 100644
--- a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c
+++ b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c
@@ -624,7 +624,7 @@ static int kabylake_card_late_probe(struct snd_soc_card *card)
  * kabylake audio machine driver for  MAX98927 + RT5514 + RT5663
  */
 static struct snd_soc_card kabylake_audio_card = {
-	.name = "kbl_r5514_5663_max",
+	.name = "kbl-r5514-5663-max",
 	.owner = THIS_MODULE,
 	.dai_link = kabylake_dais,
 	.num_links = ARRAY_SIZE(kabylake_dais),
diff --git a/sound/soc/intel/boards/skl_hda_dsp_generic.c b/sound/soc/intel/boards/skl_hda_dsp_generic.c
index fc52d3a32354..5d5b8ca1002f 100644
--- a/sound/soc/intel/boards/skl_hda_dsp_generic.c
+++ b/sound/soc/intel/boards/skl_hda_dsp_generic.c
@@ -86,7 +86,7 @@ skl_hda_add_dai_link(struct snd_soc_card *card, struct snd_soc_dai_link *link)
 }
 
 static struct snd_soc_card hda_soc_card = {
-	.name = "skl_hda_card",
+	.name = "hda-dsp",
 	.owner = THIS_MODULE,
 	.dai_link = skl_hda_be_dai_links,
 	.dapm_widgets = skl_hda_widgets,
diff --git a/sound/soc/intel/boards/sof_rt5682.c b/sound/soc/intel/boards/sof_rt5682.c
index ba65e59dddab..5a6e593b0962 100644
--- a/sound/soc/intel/boards/sof_rt5682.c
+++ b/sound/soc/intel/boards/sof_rt5682.c
@@ -292,7 +292,7 @@ static int speaker_codec_init(struct snd_soc_pcm_runtime *rtd)
 
 /* sof audio machine driver for rt5682 codec */
 static struct snd_soc_card sof_audio_card_rt5682 = {
-	.name = "sof_rt5682",
+	.name = "rt5682", /* the sof- prefix is added by the core */
 	.owner = THIS_MODULE,
 	.controls = sof_controls,
 	.num_controls = ARRAY_SIZE(sof_controls),
@@ -498,6 +498,14 @@ static int sof_audio_probe(struct platform_device *pdev)
 	if (!ctx)
 		return -ENOMEM;
 
+	mach = (&pdev->dev)->platform_data;
+
+	/* A speaker amp might not be present when the quirk claims one is.
+	 * Detect this via whether the machine driver match includes quirk_data.
+	 */
+	if ((sof_rt5682_quirk & SOF_SPEAKER_AMP_PRESENT) && !mach->quirk_data)
+		sof_rt5682_quirk &= ~SOF_SPEAKER_AMP_PRESENT;
+
 	if (x86_match_cpu(legacy_cpi_ids)) {
 		is_legacy_cpu = 1;
 		dmic_num = 0;
@@ -533,7 +541,6 @@ static int sof_audio_probe(struct platform_device *pdev)
 	INIT_LIST_HEAD(&ctx->hdmi_pcm_list);
 
 	sof_audio_card_rt5682.dev = &pdev->dev;
-	mach = (&pdev->dev)->platform_data;
 
 	/* set platform name for each dailink */
 	ret = snd_soc_fixup_dai_links_platform_name(&sof_audio_card_rt5682,
diff --git a/sound/soc/intel/skylake/skl-debug.c b/sound/soc/intel/skylake/skl-debug.c
index bffc6a9619fc..48970349b01c 100644
--- a/sound/soc/intel/skylake/skl-debug.c
+++ b/sound/soc/intel/skylake/skl-debug.c
@@ -34,8 +34,8 @@ static ssize_t skl_print_pins(struct skl_module_pin *m_pin, char *buf,
 	int i;
 	ssize_t ret = 0;
 
-	for (i = 0; i < max_pin; i++)
-		ret += snprintf(buf + size, MOD_BUF - size,
+	for (i = 0; i < max_pin; i++) {
+		ret += scnprintf(buf + size, MOD_BUF - size,
 				"%s %d\n\tModule %d\n\tInstance %d\n\t"
 				"In-used %s\n\tType %s\n"
 				"\tState %d\n\tIndex %d\n",
@@ -45,13 +45,15 @@ static ssize_t skl_print_pins(struct skl_module_pin *m_pin, char *buf,
 				m_pin[i].in_use ? "Used" : "Unused",
 				m_pin[i].is_dynamic ? "Dynamic" : "Static",
 				m_pin[i].pin_state, i);
+		size += ret;
+	}
 	return ret;
 }
 
 static ssize_t skl_print_fmt(struct skl_module_fmt *fmt, char *buf,
 					ssize_t size, bool direction)
 {
-	return snprintf(buf + size, MOD_BUF - size,
+	return scnprintf(buf + size, MOD_BUF - size,
 			"%s\n\tCh %d\n\tFreq %d\n\tBit depth %d\n\t"
 			"Valid bit depth %d\n\tCh config %#x\n\tInterleaving %d\n\t"
 			"Sample Type %d\n\tCh Map %#x\n",
@@ -73,16 +75,16 @@ static ssize_t module_read(struct file *file, char __user *user_buf,
 	if (!buf)
 		return -ENOMEM;
 
-	ret = snprintf(buf, MOD_BUF, "Module:\n\tUUID %pUL\n\tModule id %d\n"
+	ret = scnprintf(buf, MOD_BUF, "Module:\n\tUUID %pUL\n\tModule id %d\n"
 			"\tInstance id %d\n\tPvt_id %d\n", mconfig->guid,
 			mconfig->id.module_id, mconfig->id.instance_id,
 			mconfig->id.pvt_id);
 
-	ret += snprintf(buf + ret, MOD_BUF - ret,
+	ret += scnprintf(buf + ret, MOD_BUF - ret,
 			"Resources:\n\tMCPS %#x\n\tIBS %#x\n\tOBS %#x\t\n",
 			mconfig->mcps, mconfig->ibs, mconfig->obs);
 
-	ret += snprintf(buf + ret, MOD_BUF - ret,
+	ret += scnprintf(buf + ret, MOD_BUF - ret,
 			"Module data:\n\tCore %d\n\tIn queue %d\n\t"
 			"Out queue %d\n\tType %s\n",
 			mconfig->core_id, mconfig->max_in_queue,
@@ -92,38 +94,38 @@ static ssize_t module_read(struct file *file, char __user *user_buf,
 	ret += skl_print_fmt(mconfig->in_fmt, buf, ret, true);
 	ret += skl_print_fmt(mconfig->out_fmt, buf, ret, false);
 
-	ret += snprintf(buf + ret, MOD_BUF - ret,
+	ret += scnprintf(buf + ret, MOD_BUF - ret,
 			"Fixup:\n\tParams %#x\n\tConverter %#x\n",
 			mconfig->params_fixup, mconfig->converter);
 
-	ret += snprintf(buf + ret, MOD_BUF - ret,
+	ret += scnprintf(buf + ret, MOD_BUF - ret,
 			"Module Gateway:\n\tType %#x\n\tVbus %#x\n\tHW conn %#x\n\tSlot %#x\n",
 			mconfig->dev_type, mconfig->vbus_id,
 			mconfig->hw_conn_type, mconfig->time_slot);
 
-	ret += snprintf(buf + ret, MOD_BUF - ret,
+	ret += scnprintf(buf + ret, MOD_BUF - ret,
 			"Pipeline:\n\tID %d\n\tPriority %d\n\tConn Type %d\n\t"
 			"Pages %#x\n", mconfig->pipe->ppl_id,
 			mconfig->pipe->pipe_priority, mconfig->pipe->conn_type,
 			mconfig->pipe->memory_pages);
 
-	ret += snprintf(buf + ret, MOD_BUF - ret,
+	ret += scnprintf(buf + ret, MOD_BUF - ret,
 			"\tParams:\n\t\tHost DMA %d\n\t\tLink DMA %d\n",
 			mconfig->pipe->p_params->host_dma_id,
 			mconfig->pipe->p_params->link_dma_id);
 
-	ret += snprintf(buf + ret, MOD_BUF - ret,
+	ret += scnprintf(buf + ret, MOD_BUF - ret,
 			"\tPCM params:\n\t\tCh %d\n\t\tFreq %d\n\t\tFormat %d\n",
 			mconfig->pipe->p_params->ch,
 			mconfig->pipe->p_params->s_freq,
 			mconfig->pipe->p_params->s_fmt);
 
-	ret += snprintf(buf + ret, MOD_BUF - ret,
+	ret += scnprintf(buf + ret, MOD_BUF - ret,
 			"\tLink %#x\n\tStream %#x\n",
 			mconfig->pipe->p_params->linktype,
 			mconfig->pipe->p_params->stream);
 
-	ret += snprintf(buf + ret, MOD_BUF - ret,
+	ret += scnprintf(buf + ret, MOD_BUF - ret,
 			"\tState %d\n\tPassthru %s\n",
 			mconfig->pipe->state,
 			mconfig->pipe->passthru ? "true" : "false");
@@ -133,7 +135,7 @@ static ssize_t module_read(struct file *file, char __user *user_buf,
 	ret += skl_print_pins(mconfig->m_out_pin, buf,
 			mconfig->max_out_queue, ret, false);
 
-	ret += snprintf(buf + ret, MOD_BUF - ret,
+	ret += scnprintf(buf + ret, MOD_BUF - ret,
 			"Other:\n\tDomain %d\n\tHomogeneous Input %s\n\t"
 			"Homogeneous Output %s\n\tIn Queue Mask %d\n\t"
 			"Out Queue Mask %d\n\tDMA ID %d\n\tMem Pages %d\n\t"
@@ -191,7 +193,7 @@ static ssize_t fw_softreg_read(struct file *file, char __user *user_buf,
 		__ioread32_copy(d->fw_read_buff, fw_reg_addr, w0_stat_sz >> 2);
 
 	for (offset = 0; offset < FW_REG_SIZE; offset += 16) {
-		ret += snprintf(tmp + ret, FW_REG_BUF - ret, "%#.4x: ", offset);
+		ret += scnprintf(tmp + ret, FW_REG_BUF - ret, "%#.4x: ", offset);
 		hex_dump_to_buffer(d->fw_read_buff + offset, 16, 16, 4,
 				   tmp + ret, FW_REG_BUF - ret, 0);
 		ret += strlen(tmp + ret);
diff --git a/sound/soc/jz4740/jz4740-i2s.c b/sound/soc/jz4740/jz4740-i2s.c
index 13408de34055..0bbd86390be5 100644
--- a/sound/soc/jz4740/jz4740-i2s.c
+++ b/sound/soc/jz4740/jz4740-i2s.c
@@ -83,7 +83,7 @@
 #define JZ_AIC_I2S_STATUS_BUSY BIT(2)
 
 #define JZ_AIC_CLK_DIV_MASK 0xf
-#define I2SDIV_DV_SHIFT 8
+#define I2SDIV_DV_SHIFT 0
 #define I2SDIV_DV_MASK (0xf << I2SDIV_DV_SHIFT)
 #define I2SDIV_IDV_SHIFT 8
 #define I2SDIV_IDV_MASK (0xf << I2SDIV_IDV_SHIFT)
diff --git a/sound/soc/meson/axg-fifo.c b/sound/soc/meson/axg-fifo.c
index 01c1c7db2510..db4f2363b822 100644
--- a/sound/soc/meson/axg-fifo.c
+++ b/sound/soc/meson/axg-fifo.c
@@ -226,7 +226,7 @@ static int axg_fifo_pcm_open(struct snd_pcm_substream *ss)
 	/* Enable pclk to access registers and clock the fifo ip */
 	ret = clk_prepare_enable(fifo->pclk);
 	if (ret)
-		return ret;
+		goto free_irq;
 
 	/* Setup status2 so it reports the memory pointer */
 	regmap_update_bits(fifo->map, FIFO_CTRL1,
@@ -246,8 +246,14 @@ static int axg_fifo_pcm_open(struct snd_pcm_substream *ss)
 	/* Take memory arbitror out of reset */
 	ret = reset_control_deassert(fifo->arb);
 	if (ret)
-		clk_disable_unprepare(fifo->pclk);
+		goto free_clk;
+
+	return 0;
 
+free_clk:
+	clk_disable_unprepare(fifo->pclk);
+free_irq:
+	free_irq(fifo->irq, ss);
 	return ret;
 }
 
diff --git a/sound/soc/meson/axg-tdm-formatter.c b/sound/soc/meson/axg-tdm-formatter.c
index 0c6cce5c5773..9bcaf4b8b57e 100644
--- a/sound/soc/meson/axg-tdm-formatter.c
+++ b/sound/soc/meson/axg-tdm-formatter.c
@@ -68,7 +68,7 @@ EXPORT_SYMBOL_GPL(axg_tdm_formatter_set_channel_masks);
 static int axg_tdm_formatter_enable(struct axg_tdm_formatter *formatter)
 {
 	struct axg_tdm_stream *ts = formatter->stream;
-	bool invert = formatter->drv->quirks->invert_sclk;
+	bool invert;
 	int ret;
 
 	/* Do nothing if the formatter is already enabled */
@@ -76,11 +76,12 @@ static int axg_tdm_formatter_enable(struct axg_tdm_formatter *formatter)
 		return 0;
 
 	/*
-	 * If sclk is inverted, invert it back and provide the inversion
-	 * required by the formatter
+	 * If sclk is inverted, it means the bit should latched on the
+	 * rising edge which is what our HW expects. If not, we need to
+	 * invert it before the formatter.
 	 */
-	invert ^= axg_tdm_sclk_invert(ts->iface->fmt);
-	ret = clk_set_phase(formatter->sclk, invert ? 180 : 0);
+	invert = axg_tdm_sclk_invert(ts->iface->fmt);
+	ret = clk_set_phase(formatter->sclk, invert ? 0 : 180);
 	if (ret)
 		return ret;
 
diff --git a/sound/soc/meson/axg-tdm-formatter.h b/sound/soc/meson/axg-tdm-formatter.h
index 9ef98e955cb2..a1f0dcc0ff13 100644
--- a/sound/soc/meson/axg-tdm-formatter.h
+++ b/sound/soc/meson/axg-tdm-formatter.h
@@ -16,7 +16,6 @@ struct snd_kcontrol;
 
 struct axg_tdm_formatter_hw {
 	unsigned int skew_offset;
-	bool invert_sclk;
 };
 
 struct axg_tdm_formatter_ops {
diff --git a/sound/soc/meson/axg-tdm-interface.c b/sound/soc/meson/axg-tdm-interface.c
index 585ce030b79b..702595715f94 100644
--- a/sound/soc/meson/axg-tdm-interface.c
+++ b/sound/soc/meson/axg-tdm-interface.c
@@ -119,18 +119,25 @@ static int axg_tdm_iface_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 {
 	struct axg_tdm_iface *iface = snd_soc_dai_get_drvdata(dai);
 
-	/* These modes are not supported */
-	if (fmt & (SND_SOC_DAIFMT_CBS_CFM | SND_SOC_DAIFMT_CBM_CFS)) {
+	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+	case SND_SOC_DAIFMT_CBS_CFS:
+		if (!iface->mclk) {
+			dev_err(dai->dev, "cpu clock master: mclk missing\n");
+			return -ENODEV;
+		}
+		break;
+
+	case SND_SOC_DAIFMT_CBM_CFM:
+		break;
+
+	case SND_SOC_DAIFMT_CBS_CFM:
+	case SND_SOC_DAIFMT_CBM_CFS:
 		dev_err(dai->dev, "only CBS_CFS and CBM_CFM are supported\n");
+		/* Fall-through */
+	default:
 		return -EINVAL;
 	}
 
-	/* If the TDM interface is the clock master, it requires mclk */
-	if (!iface->mclk && (fmt & SND_SOC_DAIFMT_CBS_CFS)) {
-		dev_err(dai->dev, "cpu clock master: mclk missing\n");
-		return -ENODEV;
-	}
-
 	iface->fmt = fmt;
 	return 0;
 }
@@ -319,7 +326,8 @@ static int axg_tdm_iface_hw_params(struct snd_pcm_substream *substream,
 	if (ret)
 		return ret;
 
-	if (iface->fmt & SND_SOC_DAIFMT_CBS_CFS) {
+	if ((iface->fmt & SND_SOC_DAIFMT_MASTER_MASK) ==
+	    SND_SOC_DAIFMT_CBS_CFS) {
 		ret = axg_tdm_iface_set_sclk(dai, params);
 		if (ret)
 			return ret;
diff --git a/sound/soc/meson/axg-tdmin.c b/sound/soc/meson/axg-tdmin.c
index a790f925a4ef..396a8201001b 100644
--- a/sound/soc/meson/axg-tdmin.c
+++ b/sound/soc/meson/axg-tdmin.c
@@ -208,15 +208,29 @@ static const struct axg_tdm_formatter_driver axg_tdmin_drv = {
 	.regmap_cfg	= &axg_tdmin_regmap_cfg,
 	.ops		= &axg_tdmin_ops,
 	.quirks		= &(const struct axg_tdm_formatter_hw) {
-		.invert_sclk	= false,
 		.skew_offset	= 2,
 	},
 };
 
+static const struct axg_tdm_formatter_driver g12a_tdmin_drv = {
+	.component_drv	= &axg_tdmin_component_drv,
+	.regmap_cfg	= &axg_tdmin_regmap_cfg,
+	.ops		= &axg_tdmin_ops,
+	.quirks		= &(const struct axg_tdm_formatter_hw) {
+		.skew_offset	= 3,
+	},
+};
+
 static const struct of_device_id axg_tdmin_of_match[] = {
 	{
 		.compatible = "amlogic,axg-tdmin",
 		.data = &axg_tdmin_drv,
+	}, {
+		.compatible = "amlogic,g12a-tdmin",
+		.data = &g12a_tdmin_drv,
+	}, {
+		.compatible = "amlogic,sm1-tdmin",
+		.data = &g12a_tdmin_drv,
 	}, {}
 };
 MODULE_DEVICE_TABLE(of, axg_tdmin_of_match);
diff --git a/sound/soc/meson/axg-tdmout.c b/sound/soc/meson/axg-tdmout.c
index 527bfc4487e0..3ceabddae629 100644
--- a/sound/soc/meson/axg-tdmout.c
+++ b/sound/soc/meson/axg-tdmout.c
@@ -24,6 +24,7 @@
 #define TDMOUT_CTRL1			0x04
 #define  TDMOUT_CTRL1_TYPE_MASK		GENMASK(6, 4)
 #define  TDMOUT_CTRL1_TYPE(x)		((x) << 4)
+#define  SM1_TDMOUT_CTRL1_GAIN_EN	7
 #define  TDMOUT_CTRL1_MSB_POS_MASK	GENMASK(12, 8)
 #define  TDMOUT_CTRL1_MSB_POS(x)	((x) << 8)
 #define  TDMOUT_CTRL1_SEL_SHIFT		24
@@ -51,25 +52,6 @@ static const struct regmap_config axg_tdmout_regmap_cfg = {
 	.max_register	= TDMOUT_MASK_VAL,
 };
 
-static const struct snd_kcontrol_new axg_tdmout_controls[] = {
-	SOC_DOUBLE("Lane 0 Volume", TDMOUT_GAIN0,  0,  8, 255, 0),
-	SOC_DOUBLE("Lane 1 Volume", TDMOUT_GAIN0, 16, 24, 255, 0),
-	SOC_DOUBLE("Lane 2 Volume", TDMOUT_GAIN1,  0,  8, 255, 0),
-	SOC_DOUBLE("Lane 3 Volume", TDMOUT_GAIN1, 16, 24, 255, 0),
-	SOC_SINGLE("Gain Enable Switch", TDMOUT_CTRL1,
-		   TDMOUT_CTRL1_GAIN_EN, 1, 0),
-};
-
-static const char * const tdmout_sel_texts[] = {
-	"IN 0", "IN 1", "IN 2",
-};
-
-static SOC_ENUM_SINGLE_DECL(axg_tdmout_sel_enum, TDMOUT_CTRL1,
-			    TDMOUT_CTRL1_SEL_SHIFT, tdmout_sel_texts);
-
-static const struct snd_kcontrol_new axg_tdmout_in_mux =
-	SOC_DAPM_ENUM("Input Source", axg_tdmout_sel_enum);
-
 static struct snd_soc_dai *
 axg_tdmout_get_be(struct snd_soc_dapm_widget *w)
 {
@@ -137,7 +119,6 @@ static int axg_tdmout_prepare(struct regmap *map,
 		break;
 
 	case SND_SOC_DAIFMT_LEFT_J:
-	case SND_SOC_DAIFMT_RIGHT_J:
 	case SND_SOC_DAIFMT_DSP_B:
 		skew += 1;
 		break;
@@ -198,6 +179,25 @@ static int axg_tdmout_prepare(struct regmap *map,
 	return axg_tdm_formatter_set_channel_masks(map, ts, TDMOUT_MASK0);
 }
 
+static const struct snd_kcontrol_new axg_tdmout_controls[] = {
+	SOC_DOUBLE("Lane 0 Volume", TDMOUT_GAIN0,  0,  8, 255, 0),
+	SOC_DOUBLE("Lane 1 Volume", TDMOUT_GAIN0, 16, 24, 255, 0),
+	SOC_DOUBLE("Lane 2 Volume", TDMOUT_GAIN1,  0,  8, 255, 0),
+	SOC_DOUBLE("Lane 3 Volume", TDMOUT_GAIN1, 16, 24, 255, 0),
+	SOC_SINGLE("Gain Enable Switch", TDMOUT_CTRL1,
+		   TDMOUT_CTRL1_GAIN_EN, 1, 0),
+};
+
+static const char * const axg_tdmout_sel_texts[] = {
+	"IN 0", "IN 1", "IN 2",
+};
+
+static SOC_ENUM_SINGLE_DECL(axg_tdmout_sel_enum, TDMOUT_CTRL1,
+			    TDMOUT_CTRL1_SEL_SHIFT, axg_tdmout_sel_texts);
+
+static const struct snd_kcontrol_new axg_tdmout_in_mux =
+	SOC_DAPM_ENUM("Input Source", axg_tdmout_sel_enum);
+
 static const struct snd_soc_dapm_widget axg_tdmout_dapm_widgets[] = {
 	SND_SOC_DAPM_AIF_IN("IN 0", NULL, 0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("IN 1", NULL, 0, SND_SOC_NOPM, 0, 0),
@@ -238,7 +238,6 @@ static const struct axg_tdm_formatter_driver axg_tdmout_drv = {
 	.regmap_cfg	= &axg_tdmout_regmap_cfg,
 	.ops		= &axg_tdmout_ops,
 	.quirks		= &(const struct axg_tdm_formatter_hw) {
-		.invert_sclk = true,
 		.skew_offset = 1,
 	},
 };
@@ -248,7 +247,66 @@ static const struct axg_tdm_formatter_driver g12a_tdmout_drv = {
 	.regmap_cfg	= &axg_tdmout_regmap_cfg,
 	.ops		= &axg_tdmout_ops,
 	.quirks		= &(const struct axg_tdm_formatter_hw) {
-		.invert_sclk = true,
+		.skew_offset = 2,
+	},
+};
+
+static const struct snd_kcontrol_new sm1_tdmout_controls[] = {
+	SOC_DOUBLE("Lane 0 Volume", TDMOUT_GAIN0,  0,  8, 255, 0),
+	SOC_DOUBLE("Lane 1 Volume", TDMOUT_GAIN0, 16, 24, 255, 0),
+	SOC_DOUBLE("Lane 2 Volume", TDMOUT_GAIN1,  0,  8, 255, 0),
+	SOC_DOUBLE("Lane 3 Volume", TDMOUT_GAIN1, 16, 24, 255, 0),
+	SOC_SINGLE("Gain Enable Switch", TDMOUT_CTRL1,
+		   SM1_TDMOUT_CTRL1_GAIN_EN, 1, 0),
+};
+
+static const char * const sm1_tdmout_sel_texts[] = {
+	"IN 0", "IN 1", "IN 2", "IN 3", "IN 4",
+};
+
+static SOC_ENUM_SINGLE_DECL(sm1_tdmout_sel_enum, TDMOUT_CTRL1,
+			    TDMOUT_CTRL1_SEL_SHIFT, sm1_tdmout_sel_texts);
+
+static const struct snd_kcontrol_new sm1_tdmout_in_mux =
+	SOC_DAPM_ENUM("Input Source", sm1_tdmout_sel_enum);
+
+static const struct snd_soc_dapm_widget sm1_tdmout_dapm_widgets[] = {
+	SND_SOC_DAPM_AIF_IN("IN 0", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 1", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 2", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 3", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 4", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_MUX("SRC SEL", SND_SOC_NOPM, 0, 0, &sm1_tdmout_in_mux),
+	SND_SOC_DAPM_PGA_E("ENC", SND_SOC_NOPM, 0, 0, NULL, 0,
+			   axg_tdm_formatter_event,
+			   (SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_PRE_PMD)),
+	SND_SOC_DAPM_AIF_OUT("OUT", NULL, 0, SND_SOC_NOPM, 0, 0),
+};
+
+static const struct snd_soc_dapm_route sm1_tdmout_dapm_routes[] = {
+	{ "SRC SEL", "IN 0", "IN 0" },
+	{ "SRC SEL", "IN 1", "IN 1" },
+	{ "SRC SEL", "IN 2", "IN 2" },
+	{ "SRC SEL", "IN 3", "IN 3" },
+	{ "SRC SEL", "IN 4", "IN 4" },
+	{ "ENC", NULL, "SRC SEL" },
+	{ "OUT", NULL, "ENC" },
+};
+
+static const struct snd_soc_component_driver sm1_tdmout_component_drv = {
+	.controls		= sm1_tdmout_controls,
+	.num_controls		= ARRAY_SIZE(sm1_tdmout_controls),
+	.dapm_widgets		= sm1_tdmout_dapm_widgets,
+	.num_dapm_widgets	= ARRAY_SIZE(sm1_tdmout_dapm_widgets),
+	.dapm_routes		= sm1_tdmout_dapm_routes,
+	.num_dapm_routes	= ARRAY_SIZE(sm1_tdmout_dapm_routes),
+};
+
+static const struct axg_tdm_formatter_driver sm1_tdmout_drv = {
+	.component_drv	= &sm1_tdmout_component_drv,
+	.regmap_cfg	= &axg_tdmout_regmap_cfg,
+	.ops		= &axg_tdmout_ops,
+	.quirks		= &(const struct axg_tdm_formatter_hw) {
 		.skew_offset = 2,
 	},
 };
@@ -260,6 +318,9 @@ static const struct of_device_id axg_tdmout_of_match[] = {
 	}, {
 		.compatible = "amlogic,g12a-tdmout",
 		.data = &g12a_tdmout_drv,
+	}, {
+		.compatible = "amlogic,sm1-tdmout",
+		.data = &sm1_tdmout_drv,
 	}, {}
 };
 MODULE_DEVICE_TABLE(of, axg_tdmout_of_match);
diff --git a/sound/soc/qcom/Kconfig b/sound/soc/qcom/Kconfig
index 8e3e86619b35..a0e94f3f7faf 100644
--- a/sound/soc/qcom/Kconfig
+++ b/sound/soc/qcom/Kconfig
@@ -72,7 +72,7 @@ config SND_SOC_QDSP6_ASM_DAI
 
 config SND_SOC_QDSP6
 	tristate "SoC ALSA audio driver for QDSP6"
-	depends on QCOM_APR && HAS_DMA
+	depends on QCOM_APR
 	select SND_SOC_QDSP6_COMMON
 	select SND_SOC_QDSP6_CORE
 	select SND_SOC_QDSP6_AFE
diff --git a/sound/soc/qcom/common.c b/sound/soc/qcom/common.c
index 5661025e8cec..de9e2f865b42 100644
--- a/sound/soc/qcom/common.c
+++ b/sound/soc/qcom/common.c
@@ -4,6 +4,7 @@
 
 #include <linux/module.h>
 #include "common.h"
+#include "qdsp6/q6afe.h"
 
 int qcom_snd_parse_of(struct snd_soc_card *card)
 {
@@ -83,11 +84,22 @@ int qcom_snd_parse_of(struct snd_soc_card *card)
 			}
 			link->no_pcm = 1;
 			link->ignore_pmdown_time = 1;
+
+			if (q6afe_is_rx_port(link->id)) {
+				link->dpcm_playback = 1;
+				link->dpcm_capture = 0;
+			} else {
+				link->dpcm_playback = 0;
+				link->dpcm_capture = 1;
+			}
+
 		} else {
 			link->platform_of_node = link->cpu_of_node;
 			link->codec_dai_name = "snd-soc-dummy-dai";
 			link->codec_name = "snd-soc-dummy";
 			link->dynamic = 1;
+			link->dpcm_playback = 1;
+			link->dpcm_capture = 1;
 		}
 
 		link->ignore_suspend = 1;
@@ -97,8 +109,6 @@ int qcom_snd_parse_of(struct snd_soc_card *card)
 			goto err;
 		}
 
-		link->dpcm_playback = 1;
-		link->dpcm_capture = 1;
 		link->stream_name = link->name;
 		link++;
 
diff --git a/sound/soc/qcom/qdsp6/q6afe-dai.c b/sound/soc/qcom/qdsp6/q6afe-dai.c
index dc645ba4d8d0..175d6d9b5031 100644
--- a/sound/soc/qcom/qdsp6/q6afe-dai.c
+++ b/sound/soc/qcom/qdsp6/q6afe-dai.c
@@ -901,6 +901,8 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 				 SNDRV_PCM_RATE_16000,
 			.formats = SNDRV_PCM_FMTBIT_S16_LE |
 				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 8,
 			.rate_min =     8000,
 			.rate_max =     48000,
 		},
@@ -916,6 +918,8 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 				 SNDRV_PCM_RATE_16000,
 			.formats = SNDRV_PCM_FMTBIT_S16_LE |
 				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 8,
 			.rate_min =     8000,
 			.rate_max =     48000,
 		},
@@ -930,6 +934,8 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
 				 SNDRV_PCM_RATE_16000,
 			.formats = SNDRV_PCM_FMTBIT_S16_LE,
+			.channels_min = 1,
+			.channels_max = 8,
 			.rate_min =     8000,
 			.rate_max =     48000,
 		},
@@ -945,6 +951,8 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 				 SNDRV_PCM_RATE_16000,
 			.formats = SNDRV_PCM_FMTBIT_S16_LE |
 				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 8,
 			.rate_min =     8000,
 			.rate_max =     48000,
 		},
@@ -959,6 +967,8 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
 				 SNDRV_PCM_RATE_16000,
 			.formats = SNDRV_PCM_FMTBIT_S16_LE,
+			.channels_min = 1,
+			.channels_max = 8,
 			.rate_min =     8000,
 			.rate_max =     48000,
 		},
@@ -974,6 +984,8 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 				 SNDRV_PCM_RATE_16000,
 			.formats = SNDRV_PCM_FMTBIT_S16_LE |
 				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 8,
 			.rate_min =     8000,
 			.rate_max =     48000,
 		},
@@ -988,6 +1000,8 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
 				 SNDRV_PCM_RATE_16000,
 			.formats = SNDRV_PCM_FMTBIT_S16_LE,
+			.channels_min = 1,
+			.channels_max = 8,
 			.rate_min =     8000,
 			.rate_max =     48000,
 		},
@@ -1003,6 +1017,8 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 				 SNDRV_PCM_RATE_16000,
 			.formats = SNDRV_PCM_FMTBIT_S16_LE |
 				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 8,
 			.rate_min =     8000,
 			.rate_max =     48000,
 		},
diff --git a/sound/soc/qcom/qdsp6/q6afe.c b/sound/soc/qcom/qdsp6/q6afe.c
index e0945f7a58c8..0ce4eb60f984 100644
--- a/sound/soc/qcom/qdsp6/q6afe.c
+++ b/sound/soc/qcom/qdsp6/q6afe.c
@@ -800,6 +800,14 @@ int q6afe_get_port_id(int index)
 }
 EXPORT_SYMBOL_GPL(q6afe_get_port_id);
 
+int q6afe_is_rx_port(int index)
+{
+	if (index < 0 || index >= AFE_PORT_MAX)
+		return -EINVAL;
+
+	return port_maps[index].is_rx;
+}
+EXPORT_SYMBOL_GPL(q6afe_is_rx_port);
 static int afe_apr_send_pkt(struct q6afe *afe, struct apr_pkt *pkt,
 			    struct q6afe_port *port)
 {
diff --git a/sound/soc/qcom/qdsp6/q6afe.h b/sound/soc/qcom/qdsp6/q6afe.h
index c7ed5422baff..1a0f80a14afe 100644
--- a/sound/soc/qcom/qdsp6/q6afe.h
+++ b/sound/soc/qcom/qdsp6/q6afe.h
@@ -198,6 +198,7 @@ int q6afe_port_start(struct q6afe_port *port);
 int q6afe_port_stop(struct q6afe_port *port);
 void q6afe_port_put(struct q6afe_port *port);
 int q6afe_get_port_id(int index);
+int q6afe_is_rx_port(int index);
 void q6afe_hdmi_port_prepare(struct q6afe_port *port,
 			    struct q6afe_hdmi_cfg *cfg);
 void q6afe_slim_port_prepare(struct q6afe_port *port,
diff --git a/sound/soc/qcom/qdsp6/q6asm-dai.c b/sound/soc/qcom/qdsp6/q6asm-dai.c
index 548eb4fa2da6..9f0ffdcef637 100644
--- a/sound/soc/qcom/qdsp6/q6asm-dai.c
+++ b/sound/soc/qcom/qdsp6/q6asm-dai.c
@@ -171,7 +171,7 @@ static const struct snd_compr_codec_caps q6asm_compr_caps = {
 };
 
 static void event_handler(uint32_t opcode, uint32_t token,
-			  uint32_t *payload, void *priv)
+			  void *payload, void *priv)
 {
 	struct q6asm_dai_rtd *prtd = priv;
 	struct snd_pcm_substream *substream = prtd->substream;
@@ -494,7 +494,7 @@ static struct snd_pcm_ops q6asm_dai_ops = {
 };
 
 static void compress_event_handler(uint32_t opcode, uint32_t token,
-				   uint32_t *payload, void *priv)
+				   void *payload, void *priv)
 {
 	struct q6asm_dai_rtd *prtd = priv;
 	struct snd_compr_stream *substream = prtd->cstream;
diff --git a/sound/soc/qcom/qdsp6/q6asm.c b/sound/soc/qcom/qdsp6/q6asm.c
index 4f85cb19a309..9cb014aa2fb7 100644
--- a/sound/soc/qcom/qdsp6/q6asm.c
+++ b/sound/soc/qcom/qdsp6/q6asm.c
@@ -25,6 +25,7 @@
 #define ASM_STREAM_CMD_FLUSH			0x00010BCE
 #define ASM_SESSION_CMD_PAUSE			0x00010BD3
 #define ASM_DATA_CMD_EOS			0x00010BDB
+#define ASM_DATA_EVENT_RENDERED_EOS		0x00010C1C
 #define ASM_NULL_POPP_TOPOLOGY			0x00010C68
 #define ASM_STREAM_CMD_FLUSH_READBUFS		0x00010C09
 #define ASM_STREAM_CMD_SET_ENCDEC_PARAM		0x00010C10
@@ -546,9 +547,6 @@ static int32_t q6asm_stream_callback(struct apr_device *adev,
 		case ASM_SESSION_CMD_SUSPEND:
 			client_event = ASM_CLIENT_EVENT_CMD_SUSPEND_DONE;
 			break;
-		case ASM_DATA_CMD_EOS:
-			client_event = ASM_CLIENT_EVENT_CMD_EOS_DONE;
-			break;
 		case ASM_STREAM_CMD_FLUSH:
 			client_event = ASM_CLIENT_EVENT_CMD_FLUSH_DONE;
 			break;
@@ -652,6 +650,9 @@ static int32_t q6asm_stream_callback(struct apr_device *adev,
 		}
 
 		break;
+	case ASM_DATA_EVENT_RENDERED_EOS:
+		client_event = ASM_CLIENT_EVENT_CMD_EOS_DONE;
+		break;
 	}
 
 	if (ac->cb)
diff --git a/sound/soc/rockchip/Kconfig b/sound/soc/rockchip/Kconfig
index 28a80c1cb41d..b43657e6e655 100644
--- a/sound/soc/rockchip/Kconfig
+++ b/sound/soc/rockchip/Kconfig
@@ -20,6 +20,7 @@ config SND_SOC_ROCKCHIP_PDM
 	tristate "Rockchip PDM Controller Driver"
 	depends on CLKDEV_LOOKUP && SND_SOC_ROCKCHIP
 	select SND_SOC_GENERIC_DMAENGINE_PCM
+	select RATIONAL
 	help
 	  Say Y or M if you want to add support for PDM driver for
 	  Rockchip PDM Controller. The Controller supports up to maximum of
diff --git a/sound/soc/rockchip/rockchip_pdm.c b/sound/soc/rockchip/rockchip_pdm.c
index 7cd42fcfcf38..1707414cfa92 100644
--- a/sound/soc/rockchip/rockchip_pdm.c
+++ b/sound/soc/rockchip/rockchip_pdm.c
@@ -590,8 +590,10 @@ static int rockchip_pdm_resume(struct device *dev)
 	int ret;
 
 	ret = pm_runtime_get_sync(dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put(dev);
 		return ret;
+	}
 
 	ret = regcache_sync(pdm->regmap);
 
diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c
index 4579827ea7c7..3e49a22f18ec 100644
--- a/sound/soc/sh/rcar/core.c
+++ b/sound/soc/sh/rcar/core.c
@@ -376,6 +376,17 @@ u32 rsnd_get_adinr_bit(struct rsnd_mod *mod, struct rsnd_dai_stream *io)
  */
 u32 rsnd_get_dalign(struct rsnd_mod *mod, struct rsnd_dai_stream *io)
 {
+	static const u32 dalign_values[8][2] = {
+		{0x76543210, 0x67452301},
+		{0x00000032, 0x00000023},
+		{0x00007654, 0x00006745},
+		{0x00000076, 0x00000067},
+		{0xfedcba98, 0xefcdab89},
+		{0x000000ba, 0x000000ab},
+		{0x0000fedc, 0x0000efcd},
+		{0x000000fe, 0x000000ef},
+	};
+	int id = 0, inv;
 	struct rsnd_mod *ssiu = rsnd_io_to_mod_ssiu(io);
 	struct rsnd_mod *target;
 	struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io);
@@ -411,13 +422,18 @@ u32 rsnd_get_dalign(struct rsnd_mod *mod, struct rsnd_dai_stream *io)
 		target = cmd ? cmd : ssiu;
 	}
 
+	if (mod == ssiu)
+		id = rsnd_mod_id_sub(mod);
+
 	/* Non target mod or non 16bit needs normal DALIGN */
 	if ((snd_pcm_format_width(runtime->format) != 16) ||
 	    (mod != target))
-		return 0x76543210;
+		inv = 0;
 	/* Target mod needs inverted DALIGN when 16bit */
 	else
-		return 0x67452301;
+		inv = 1;
+
+	return dalign_values[id][inv];
 }
 
 u32 rsnd_get_busif_shift(struct rsnd_dai_stream *io, struct rsnd_mod *mod)
diff --git a/sound/soc/sh/rcar/gen.c b/sound/soc/sh/rcar/gen.c
index af19010b9d88..8bd49c8a9517 100644
--- a/sound/soc/sh/rcar/gen.c
+++ b/sound/soc/sh/rcar/gen.c
@@ -224,6 +224,14 @@ static int rsnd_gen2_probe(struct rsnd_priv *priv)
 		RSND_GEN_S_REG(SSI_SYS_STATUS5,	0x884),
 		RSND_GEN_S_REG(SSI_SYS_STATUS6,	0x888),
 		RSND_GEN_S_REG(SSI_SYS_STATUS7,	0x88c),
+		RSND_GEN_S_REG(SSI_SYS_INT_ENABLE0, 0x850),
+		RSND_GEN_S_REG(SSI_SYS_INT_ENABLE1, 0x854),
+		RSND_GEN_S_REG(SSI_SYS_INT_ENABLE2, 0x858),
+		RSND_GEN_S_REG(SSI_SYS_INT_ENABLE3, 0x85c),
+		RSND_GEN_S_REG(SSI_SYS_INT_ENABLE4, 0x890),
+		RSND_GEN_S_REG(SSI_SYS_INT_ENABLE5, 0x894),
+		RSND_GEN_S_REG(SSI_SYS_INT_ENABLE6, 0x898),
+		RSND_GEN_S_REG(SSI_SYS_INT_ENABLE7, 0x89c),
 		RSND_GEN_S_REG(HDMI0_SEL,	0x9e0),
 		RSND_GEN_S_REG(HDMI1_SEL,	0x9e4),
 
diff --git a/sound/soc/sh/rcar/rsnd.h b/sound/soc/sh/rcar/rsnd.h
index 7727add3eb1a..dd7ea04c689f 100644
--- a/sound/soc/sh/rcar/rsnd.h
+++ b/sound/soc/sh/rcar/rsnd.h
@@ -189,6 +189,14 @@ enum rsnd_reg {
 	SSI_SYS_STATUS5,
 	SSI_SYS_STATUS6,
 	SSI_SYS_STATUS7,
+	SSI_SYS_INT_ENABLE0,
+	SSI_SYS_INT_ENABLE1,
+	SSI_SYS_INT_ENABLE2,
+	SSI_SYS_INT_ENABLE3,
+	SSI_SYS_INT_ENABLE4,
+	SSI_SYS_INT_ENABLE5,
+	SSI_SYS_INT_ENABLE6,
+	SSI_SYS_INT_ENABLE7,
 	HDMI0_SEL,
 	HDMI1_SEL,
 	SSI9_BUSIF0_MODE,
@@ -237,6 +245,7 @@ enum rsnd_reg {
 #define SSI9_BUSIF_ADINR(i)	(SSI9_BUSIF0_ADINR + (i))
 #define SSI9_BUSIF_DALIGN(i)	(SSI9_BUSIF0_DALIGN + (i))
 #define SSI_SYS_STATUS(i)	(SSI_SYS_STATUS0 + (i))
+#define SSI_SYS_INT_ENABLE(i) (SSI_SYS_INT_ENABLE0 + (i))
 
 
 struct rsnd_priv;
diff --git a/sound/soc/sh/rcar/ssi.c b/sound/soc/sh/rcar/ssi.c
index 44bda210256e..2664220f3302 100644
--- a/sound/soc/sh/rcar/ssi.c
+++ b/sound/soc/sh/rcar/ssi.c
@@ -372,6 +372,9 @@ static void rsnd_ssi_config_init(struct rsnd_mod *mod,
 	u32 wsr		= ssi->wsr;
 	int width;
 	int is_tdm, is_tdm_split;
+	int id = rsnd_mod_id(mod);
+	int i;
+	u32 sys_int_enable = 0;
 
 	is_tdm		= rsnd_runtime_is_tdm(io);
 	is_tdm_split	= rsnd_runtime_is_tdm_split(io);
@@ -447,6 +450,38 @@ static void rsnd_ssi_config_init(struct rsnd_mod *mod,
 		cr_mode = DIEN;		/* PIO : enable Data interrupt */
 	}
 
+	/* enable busif buffer over/under run interrupt. */
+	if (is_tdm || is_tdm_split) {
+		switch (id) {
+		case 0:
+		case 1:
+		case 2:
+		case 3:
+		case 4:
+			for (i = 0; i < 4; i++) {
+				sys_int_enable = rsnd_mod_read(mod,
+					SSI_SYS_INT_ENABLE(i * 2));
+				sys_int_enable |= 0xf << (id * 4);
+				rsnd_mod_write(mod,
+					       SSI_SYS_INT_ENABLE(i * 2),
+					       sys_int_enable);
+			}
+
+			break;
+		case 9:
+			for (i = 0; i < 4; i++) {
+				sys_int_enable = rsnd_mod_read(mod,
+					SSI_SYS_INT_ENABLE((i * 2) + 1));
+				sys_int_enable |= 0xf << 4;
+				rsnd_mod_write(mod,
+					       SSI_SYS_INT_ENABLE((i * 2) + 1),
+					       sys_int_enable);
+			}
+
+			break;
+		}
+	}
+
 init_end:
 	ssi->cr_own	= cr_own;
 	ssi->cr_mode	= cr_mode;
@@ -496,6 +531,13 @@ static int rsnd_ssi_quit(struct rsnd_mod *mod,
 {
 	struct rsnd_ssi *ssi = rsnd_mod_to_ssi(mod);
 	struct device *dev = rsnd_priv_to_dev(priv);
+	int is_tdm, is_tdm_split;
+	int id = rsnd_mod_id(mod);
+	int i;
+	u32 sys_int_enable = 0;
+
+	is_tdm		= rsnd_runtime_is_tdm(io);
+	is_tdm_split	= rsnd_runtime_is_tdm_split(io);
 
 	if (!rsnd_ssi_is_run_mods(mod, io))
 		return 0;
@@ -517,6 +559,38 @@ static int rsnd_ssi_quit(struct rsnd_mod *mod,
 		ssi->wsr	= 0;
 	}
 
+	/* disable busif buffer over/under run interrupt. */
+	if (is_tdm || is_tdm_split) {
+		switch (id) {
+		case 0:
+		case 1:
+		case 2:
+		case 3:
+		case 4:
+			for (i = 0; i < 4; i++) {
+				sys_int_enable = rsnd_mod_read(mod,
+						SSI_SYS_INT_ENABLE(i * 2));
+				sys_int_enable &= ~(0xf << (id * 4));
+				rsnd_mod_write(mod,
+					       SSI_SYS_INT_ENABLE(i * 2),
+					       sys_int_enable);
+			}
+
+			break;
+		case 9:
+			for (i = 0; i < 4; i++) {
+				sys_int_enable = rsnd_mod_read(mod,
+					SSI_SYS_INT_ENABLE((i * 2) + 1));
+				sys_int_enable &= ~(0xf << 4);
+				rsnd_mod_write(mod,
+					       SSI_SYS_INT_ENABLE((i * 2) + 1),
+					       sys_int_enable);
+			}
+
+			break;
+		}
+	}
+
 	return 0;
 }
 
@@ -594,10 +668,16 @@ static int rsnd_ssi_stop(struct rsnd_mod *mod,
 	 * Capture:  It might not receave data. Do nothing
 	 */
 	if (rsnd_io_is_play(io)) {
-		rsnd_mod_write(mod, SSICR, cr | EN);
+		rsnd_mod_write(mod, SSICR, cr | ssi->cr_en);
 		rsnd_ssi_status_check(mod, DIRQ);
 	}
 
+	/* In multi-SSI mode, stop is performed by setting ssi0129 in
+	 * SSI_CONTROL to 0 (in rsnd_ssio_stop_gen2). Do nothing here.
+	 */
+	if (rsnd_ssi_multi_slaves_runtime(io))
+		return 0;
+
 	/*
 	 * disable SSI,
 	 * and, wait idle state
@@ -616,6 +696,11 @@ static int rsnd_ssi_irq(struct rsnd_mod *mod,
 			int enable)
 {
 	u32 val = 0;
+	int is_tdm, is_tdm_split;
+	int id = rsnd_mod_id(mod);
+
+	is_tdm		= rsnd_runtime_is_tdm(io);
+	is_tdm_split	= rsnd_runtime_is_tdm_split(io);
 
 	if (rsnd_is_gen1(priv))
 		return 0;
@@ -629,6 +714,19 @@ static int rsnd_ssi_irq(struct rsnd_mod *mod,
 	if (enable)
 		val = rsnd_ssi_is_dma_mode(mod) ? 0x0e000000 : 0x0f000000;
 
+	if (is_tdm || is_tdm_split) {
+		switch (id) {
+		case 0:
+		case 1:
+		case 2:
+		case 3:
+		case 4:
+		case 9:
+			val |= 0x0000ff00;
+			break;
+		}
+	}
+
 	rsnd_mod_write(mod, SSI_INT_ENABLE, val);
 
 	return 0;
@@ -645,6 +743,12 @@ static void __rsnd_ssi_interrupt(struct rsnd_mod *mod,
 	u32 status;
 	bool elapsed = false;
 	bool stop = false;
+	int id = rsnd_mod_id(mod);
+	int i;
+	int is_tdm, is_tdm_split;
+
+	is_tdm		= rsnd_runtime_is_tdm(io);
+	is_tdm_split	= rsnd_runtime_is_tdm_split(io);
 
 	spin_lock(&priv->lock);
 
@@ -666,6 +770,53 @@ static void __rsnd_ssi_interrupt(struct rsnd_mod *mod,
 		stop = true;
 	}
 
+	status = 0;
+
+	if (is_tdm || is_tdm_split) {
+		switch (id) {
+		case 0:
+		case 1:
+		case 2:
+		case 3:
+		case 4:
+			for (i = 0; i < 4; i++) {
+				status = rsnd_mod_read(mod,
+						       SSI_SYS_STATUS(i * 2));
+				status &= 0xf << (id * 4);
+
+				if (status) {
+					rsnd_dbg_irq_status(dev,
+						"%s err status : 0x%08x\n",
+						rsnd_mod_name(mod), status);
+					rsnd_mod_write(mod,
+						       SSI_SYS_STATUS(i * 2),
+						       0xf << (id * 4));
+					stop = true;
+					break;
+				}
+			}
+			break;
+		case 9:
+			for (i = 0; i < 4; i++) {
+				status = rsnd_mod_read(mod,
+						SSI_SYS_STATUS((i * 2) + 1));
+				status &= 0xf << 4;
+
+				if (status) {
+					rsnd_dbg_irq_status(dev,
+						"%s err status : 0x%08x\n",
+						rsnd_mod_name(mod), status);
+					rsnd_mod_write(mod,
+						SSI_SYS_STATUS((i * 2) + 1),
+						0xf << 4);
+					stop = true;
+					break;
+				}
+			}
+			break;
+		}
+	}
+
 	rsnd_ssi_status_clear(mod);
 rsnd_ssi_interrupt_out:
 	spin_unlock(&priv->lock);
@@ -737,6 +888,9 @@ static void rsnd_ssi_parent_attach(struct rsnd_mod *mod,
 	if (!rsnd_rdai_is_clk_master(rdai))
 		return;
 
+	if (rsnd_ssi_is_multi_slave(mod, io))
+		return;
+
 	switch (rsnd_mod_id(mod)) {
 	case 1:
 	case 2:
diff --git a/sound/soc/sh/rcar/ssiu.c b/sound/soc/sh/rcar/ssiu.c
index 2347f3404c06..e0ac791338a6 100644
--- a/sound/soc/sh/rcar/ssiu.c
+++ b/sound/soc/sh/rcar/ssiu.c
@@ -225,7 +225,7 @@ static int rsnd_ssiu_init_gen2(struct rsnd_mod *mod,
 			i;
 
 		for_each_rsnd_mod_array(i, pos, io, rsnd_ssi_array) {
-			shift	= (i * 4) + 16;
+			shift	= (i * 4) + 20;
 			val	= (val & ~(0xF << shift)) |
 				rsnd_mod_id(pos) << shift;
 		}
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 6aeba0d66ec5..d0c2d78f3c19 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -2008,7 +2008,25 @@ match:
 			dai_link->platforms->name = component->name;
 
 			/* convert non BE into BE */
-			dai_link->no_pcm = 1;
+			if (!dai_link->no_pcm) {
+				dai_link->no_pcm = 1;
+
+				if (dai_link->dpcm_playback)
+					dev_warn(card->dev,
+						 "invalid configuration, dailink %s has flags no_pcm=0 and dpcm_playback=1\n",
+						 dai_link->name);
+				if (dai_link->dpcm_capture)
+					dev_warn(card->dev,
+						 "invalid configuration, dailink %s has flags no_pcm=0 and dpcm_capture=1\n",
+						 dai_link->name);
+
+				/* convert normal link into DPCM one */
+				if (!(dai_link->dpcm_playback ||
+				      dai_link->dpcm_capture)) {
+					dai_link->dpcm_playback = !dai_link->capture_only;
+					dai_link->dpcm_capture = !dai_link->playback_only;
+				}
+			}
 
 			/* override any BE fixups */
 			dai_link->be_hw_params_fixup =
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index f40adb604c25..60212214fc5d 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -423,7 +423,7 @@ static int dapm_kcontrol_data_alloc(struct snd_soc_dapm_widget *widget,
 
 			memset(&template, 0, sizeof(template));
 			template.reg = e->reg;
-			template.mask = e->mask << e->shift_l;
+			template.mask = e->mask;
 			template.shift = e->shift_l;
 			template.off_val = snd_soc_enum_item_to_val(e, 0);
 			template.on_val = template.off_val;
@@ -545,8 +545,22 @@ static bool dapm_kcontrol_set_value(const struct snd_kcontrol *kcontrol,
 	if (data->value == value)
 		return false;
 
-	if (data->widget)
-		data->widget->on_val = value;
+	if (data->widget) {
+		switch (dapm_kcontrol_get_wlist(kcontrol)->widgets[0]->id) {
+		case snd_soc_dapm_switch:
+		case snd_soc_dapm_mixer:
+		case snd_soc_dapm_mixer_named_ctl:
+			data->widget->on_val = value & data->widget->mask;
+			break;
+		case snd_soc_dapm_demux:
+		case snd_soc_dapm_mux:
+			data->widget->on_val = value >> data->widget->shift;
+			break;
+		default:
+			data->widget->on_val = value;
+			break;
+		}
+	}
 
 	data->value = value;
 
@@ -801,7 +815,13 @@ static void dapm_set_mixer_path_status(struct snd_soc_dapm_path *p, int i,
 			val = max - val;
 		p->connect = !!val;
 	} else {
-		p->connect = 0;
+		/* since a virtual mixer has no backing registers to
+		 * decide which path to connect, it will try to match
+		 * with initial state.  This is to ensure
+		 * that the default mixer choice will be
+		 * correctly powered up during initialization.
+		 */
+		p->connect = invert;
 	}
 }
 
@@ -4680,7 +4700,7 @@ static void soc_dapm_shutdown_dapm(struct snd_soc_dapm_context *dapm)
 			continue;
 		if (w->power) {
 			dapm_seq_insert(w, &down_list, false);
-			w->power = 0;
+			w->new_power = 0;
 			powerdown = 1;
 		}
 	}
diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c
index f4dc3d445aae..95fc24580f85 100644
--- a/sound/soc/soc-ops.c
+++ b/sound/soc/soc-ops.c
@@ -832,7 +832,7 @@ int snd_soc_get_xr_sx(struct snd_kcontrol *kcontrol,
 	unsigned int regbase = mc->regbase;
 	unsigned int regcount = mc->regcount;
 	unsigned int regwshift = component->val_bytes * BITS_PER_BYTE;
-	unsigned int regwmask = (1<<regwshift)-1;
+	unsigned int regwmask = (1UL<<regwshift)-1;
 	unsigned int invert = mc->invert;
 	unsigned long mask = (1UL<<mc->nbits)-1;
 	long min = mc->min;
@@ -881,7 +881,7 @@ int snd_soc_put_xr_sx(struct snd_kcontrol *kcontrol,
 	unsigned int regbase = mc->regbase;
 	unsigned int regcount = mc->regcount;
 	unsigned int regwshift = component->val_bytes * BITS_PER_BYTE;
-	unsigned int regwmask = (1<<regwshift)-1;
+	unsigned int regwmask = (1UL<<regwshift)-1;
 	unsigned int invert = mc->invert;
 	unsigned long mask = (1UL<<mc->nbits)-1;
 	long max = mc->max;
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index b994d27478e2..67eede91c695 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -2300,7 +2300,8 @@ int dpcm_be_dai_trigger(struct snd_soc_pcm_runtime *fe, int stream,
 		switch (cmd) {
 		case SNDRV_PCM_TRIGGER_START:
 			if ((be->dpcm[stream].state != SND_SOC_DPCM_STATE_PREPARE) &&
-			    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_STOP))
+			    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_STOP) &&
+			    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_PAUSED))
 				continue;
 
 			ret = dpcm_do_trigger(dpcm, be_substream, cmd);
@@ -2330,7 +2331,8 @@ int dpcm_be_dai_trigger(struct snd_soc_pcm_runtime *fe, int stream,
 			be->dpcm[stream].state = SND_SOC_DPCM_STATE_START;
 			break;
 		case SNDRV_PCM_TRIGGER_STOP:
-			if (be->dpcm[stream].state != SND_SOC_DPCM_STATE_START)
+			if ((be->dpcm[stream].state != SND_SOC_DPCM_STATE_START) &&
+			    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_PAUSED))
 				continue;
 
 			if (!snd_soc_dpcm_can_be_free_stop(fe, be, stream))
@@ -2375,42 +2377,81 @@ int dpcm_be_dai_trigger(struct snd_soc_pcm_runtime *fe, int stream,
 }
 EXPORT_SYMBOL_GPL(dpcm_be_dai_trigger);
 
+static int dpcm_dai_trigger_fe_be(struct snd_pcm_substream *substream,
+				  int cmd, bool fe_first)
+{
+	struct snd_soc_pcm_runtime *fe = substream->private_data;
+	int ret;
+
+	/* call trigger on the frontend before the backend. */
+	if (fe_first) {
+		dev_dbg(fe->dev, "ASoC: pre trigger FE %s cmd %d\n",
+			fe->dai_link->name, cmd);
+
+		ret = soc_pcm_trigger(substream, cmd);
+		if (ret < 0)
+			return ret;
+
+		ret = dpcm_be_dai_trigger(fe, substream->stream, cmd);
+		return ret;
+	}
+
+	/* call trigger on the frontend after the backend. */
+	ret = dpcm_be_dai_trigger(fe, substream->stream, cmd);
+	if (ret < 0)
+		return ret;
+
+	dev_dbg(fe->dev, "ASoC: post trigger FE %s cmd %d\n",
+		fe->dai_link->name, cmd);
+
+	ret = soc_pcm_trigger(substream, cmd);
+
+	return ret;
+}
+
 static int dpcm_fe_dai_do_trigger(struct snd_pcm_substream *substream, int cmd)
 {
 	struct snd_soc_pcm_runtime *fe = substream->private_data;
-	int stream = substream->stream, ret;
+	int stream = substream->stream;
+	int ret = 0;
 	enum snd_soc_dpcm_trigger trigger = fe->dai_link->trigger[stream];
 
 	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE;
 
 	switch (trigger) {
 	case SND_SOC_DPCM_TRIGGER_PRE:
-		/* call trigger on the frontend before the backend. */
-
-		dev_dbg(fe->dev, "ASoC: pre trigger FE %s cmd %d\n",
-				fe->dai_link->name, cmd);
-
-		ret = soc_pcm_trigger(substream, cmd);
-		if (ret < 0) {
-			dev_err(fe->dev,"ASoC: trigger FE failed %d\n", ret);
-			goto out;
+		switch (cmd) {
+		case SNDRV_PCM_TRIGGER_START:
+		case SNDRV_PCM_TRIGGER_RESUME:
+		case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+			ret = dpcm_dai_trigger_fe_be(substream, cmd, true);
+			break;
+		case SNDRV_PCM_TRIGGER_STOP:
+		case SNDRV_PCM_TRIGGER_SUSPEND:
+		case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
+			ret = dpcm_dai_trigger_fe_be(substream, cmd, false);
+			break;
+		default:
+			ret = -EINVAL;
+			break;
 		}
-
-		ret = dpcm_be_dai_trigger(fe, substream->stream, cmd);
 		break;
 	case SND_SOC_DPCM_TRIGGER_POST:
-		/* call trigger on the frontend after the backend. */
-
-		ret = dpcm_be_dai_trigger(fe, substream->stream, cmd);
-		if (ret < 0) {
-			dev_err(fe->dev,"ASoC: trigger FE failed %d\n", ret);
-			goto out;
+		switch (cmd) {
+		case SNDRV_PCM_TRIGGER_START:
+		case SNDRV_PCM_TRIGGER_RESUME:
+		case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+			ret = dpcm_dai_trigger_fe_be(substream, cmd, false);
+			break;
+		case SNDRV_PCM_TRIGGER_STOP:
+		case SNDRV_PCM_TRIGGER_SUSPEND:
+		case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
+			ret = dpcm_dai_trigger_fe_be(substream, cmd, true);
+			break;
+		default:
+			ret = -EINVAL;
+			break;
 		}
-
-		dev_dbg(fe->dev, "ASoC: post trigger FE %s cmd %d\n",
-				fe->dai_link->name, cmd);
-
-		ret = soc_pcm_trigger(substream, cmd);
 		break;
 	case SND_SOC_DPCM_TRIGGER_BESPOKE:
 		/* bespoke trigger() - handles both FE and BEs */
@@ -2419,10 +2460,6 @@ static int dpcm_fe_dai_do_trigger(struct snd_pcm_substream *substream, int cmd)
 				fe->dai_link->name, cmd);
 
 		ret = soc_pcm_bespoke_trigger(substream, cmd);
-		if (ret < 0) {
-			dev_err(fe->dev,"ASoC: trigger FE failed %d\n", ret);
-			goto out;
-		}
 		break;
 	default:
 		dev_err(fe->dev, "ASoC: invalid trigger cmd %d for %s\n", cmd,
@@ -2431,6 +2468,12 @@ static int dpcm_fe_dai_do_trigger(struct snd_pcm_substream *substream, int cmd)
 		goto out;
 	}
 
+	if (ret < 0) {
+		dev_err(fe->dev, "ASoC: trigger FE cmd: %d failed: %d\n",
+			cmd, ret);
+		goto out;
+	}
+
 	switch (cmd) {
 	case SNDRV_PCM_TRIGGER_START:
 	case SNDRV_PCM_TRIGGER_RESUME:
@@ -3364,16 +3407,16 @@ static ssize_t dpcm_show_state(struct snd_soc_pcm_runtime *fe,
 	unsigned long flags;
 
 	/* FE state */
-	offset += snprintf(buf + offset, size - offset,
+	offset += scnprintf(buf + offset, size - offset,
 			"[%s - %s]\n", fe->dai_link->name,
 			stream ? "Capture" : "Playback");
 
-	offset += snprintf(buf + offset, size - offset, "State: %s\n",
+	offset += scnprintf(buf + offset, size - offset, "State: %s\n",
 	                dpcm_state_string(fe->dpcm[stream].state));
 
 	if ((fe->dpcm[stream].state >= SND_SOC_DPCM_STATE_HW_PARAMS) &&
 	    (fe->dpcm[stream].state <= SND_SOC_DPCM_STATE_STOP))
-		offset += snprintf(buf + offset, size - offset,
+		offset += scnprintf(buf + offset, size - offset,
 				"Hardware Params: "
 				"Format = %s, Channels = %d, Rate = %d\n",
 				snd_pcm_format_name(params_format(params)),
@@ -3381,10 +3424,10 @@ static ssize_t dpcm_show_state(struct snd_soc_pcm_runtime *fe,
 				params_rate(params));
 
 	/* BEs state */
-	offset += snprintf(buf + offset, size - offset, "Backends:\n");
+	offset += scnprintf(buf + offset, size - offset, "Backends:\n");
 
 	if (list_empty(&fe->dpcm[stream].be_clients)) {
-		offset += snprintf(buf + offset, size - offset,
+		offset += scnprintf(buf + offset, size - offset,
 				" No active DSP links\n");
 		goto out;
 	}
@@ -3394,16 +3437,16 @@ static ssize_t dpcm_show_state(struct snd_soc_pcm_runtime *fe,
 		struct snd_soc_pcm_runtime *be = dpcm->be;
 		params = &dpcm->hw_params;
 
-		offset += snprintf(buf + offset, size - offset,
+		offset += scnprintf(buf + offset, size - offset,
 				"- %s\n", be->dai_link->name);
 
-		offset += snprintf(buf + offset, size - offset,
+		offset += scnprintf(buf + offset, size - offset,
 				"   State: %s\n",
 				dpcm_state_string(be->dpcm[stream].state));
 
 		if ((be->dpcm[stream].state >= SND_SOC_DPCM_STATE_HW_PARAMS) &&
 		    (be->dpcm[stream].state <= SND_SOC_DPCM_STATE_STOP))
-			offset += snprintf(buf + offset, size - offset,
+			offset += scnprintf(buf + offset, size - offset,
 				"   Hardware Params: "
 				"Format = %s, Channels = %d, Rate = %d\n",
 				snd_pcm_format_name(params_format(params)),
diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c
index 47ffeb555fba..b14bea746875 100644
--- a/sound/soc/soc-topology.c
+++ b/sound/soc/soc-topology.c
@@ -366,7 +366,7 @@ static int soc_tplg_add_kcontrol(struct soc_tplg *tplg,
 	struct snd_soc_component *comp = tplg->comp;
 
 	return soc_tplg_add_dcontrol(comp->card->snd_card,
-				comp->dev, k, NULL, comp, kcontrol);
+				comp->dev, k, comp->name_prefix, comp, kcontrol);
 }
 
 /* remove a mixer kcontrol */
@@ -558,12 +558,12 @@ static void remove_link(struct snd_soc_component *comp,
 	if (dobj->ops && dobj->ops->link_unload)
 		dobj->ops->link_unload(comp, dobj);
 
+	list_del(&dobj->list);
+	snd_soc_remove_dai_link(comp->card, link);
+
 	kfree(link->name);
 	kfree(link->stream_name);
 	kfree(link->cpu_dai_name);
-
-	list_del(&dobj->list);
-	snd_soc_remove_dai_link(comp->card, link);
 	kfree(link);
 }
 
@@ -614,9 +614,11 @@ static int soc_tplg_kcontrol_bind_io(struct snd_soc_tplg_ctl_hdr *hdr,
 		ext_ops = tplg->bytes_ext_ops;
 		num_ops = tplg->bytes_ext_ops_count;
 		for (i = 0; i < num_ops; i++) {
-			if (!sbe->put && ext_ops[i].id == be->ext_ops.put)
+			if (!sbe->put &&
+			    ext_ops[i].id == le32_to_cpu(be->ext_ops.put))
 				sbe->put = ext_ops[i].put;
-			if (!sbe->get && ext_ops[i].id == be->ext_ops.get)
+			if (!sbe->get &&
+			    ext_ops[i].id == le32_to_cpu(be->ext_ops.get))
 				sbe->get = ext_ops[i].get;
 		}
 
@@ -631,11 +633,11 @@ static int soc_tplg_kcontrol_bind_io(struct snd_soc_tplg_ctl_hdr *hdr,
 	num_ops = tplg->io_ops_count;
 	for (i = 0; i < num_ops; i++) {
 
-		if (k->put == NULL && ops[i].id == hdr->ops.put)
+		if (k->put == NULL && ops[i].id == le32_to_cpu(hdr->ops.put))
 			k->put = ops[i].put;
-		if (k->get == NULL && ops[i].id == hdr->ops.get)
+		if (k->get == NULL && ops[i].id == le32_to_cpu(hdr->ops.get))
 			k->get = ops[i].get;
-		if (k->info == NULL && ops[i].id == hdr->ops.info)
+		if (k->info == NULL && ops[i].id == le32_to_cpu(hdr->ops.info))
 			k->info = ops[i].info;
 	}
 
@@ -648,11 +650,11 @@ static int soc_tplg_kcontrol_bind_io(struct snd_soc_tplg_ctl_hdr *hdr,
 	num_ops = ARRAY_SIZE(io_ops);
 	for (i = 0; i < num_ops; i++) {
 
-		if (k->put == NULL && ops[i].id == hdr->ops.put)
+		if (k->put == NULL && ops[i].id == le32_to_cpu(hdr->ops.put))
 			k->put = ops[i].put;
-		if (k->get == NULL && ops[i].id == hdr->ops.get)
+		if (k->get == NULL && ops[i].id == le32_to_cpu(hdr->ops.get))
 			k->get = ops[i].get;
-		if (k->info == NULL && ops[i].id == hdr->ops.info)
+		if (k->info == NULL && ops[i].id == le32_to_cpu(hdr->ops.info))
 			k->info = ops[i].info;
 	}
 
@@ -901,7 +903,13 @@ static int soc_tplg_dmixer_create(struct soc_tplg *tplg, unsigned int count,
 		}
 
 		/* create any TLV data */
-		soc_tplg_create_tlv(tplg, &kc, &mc->hdr);
+		err = soc_tplg_create_tlv(tplg, &kc, &mc->hdr);
+		if (err < 0) {
+			dev_err(tplg->dev, "ASoC: failed to create TLV %s\n",
+				mc->hdr.name);
+			kfree(sm);
+			continue;
+		}
 
 		/* pass control to driver for optional further init */
 		err = soc_tplg_init_kcontrol(tplg, &kc,
@@ -941,7 +949,7 @@ static int soc_tplg_denum_create_texts(struct soc_enum *se,
 	if (se->dobj.control.dtexts == NULL)
 		return -ENOMEM;
 
-	for (i = 0; i < ec->items; i++) {
+	for (i = 0; i < le32_to_cpu(ec->items); i++) {
 
 		if (strnlen(ec->texts[i], SNDRV_CTL_ELEM_ID_NAME_MAXLEN) ==
 			SNDRV_CTL_ELEM_ID_NAME_MAXLEN) {
@@ -1112,6 +1120,7 @@ static int soc_tplg_kcontrol_elems_load(struct soc_tplg *tplg,
 	struct snd_soc_tplg_hdr *hdr)
 {
 	struct snd_soc_tplg_ctl_hdr *control_hdr;
+	int ret;
 	int i;
 
 	if (tplg->pass != SOC_TPLG_PASS_MIXER) {
@@ -1140,25 +1149,30 @@ static int soc_tplg_kcontrol_elems_load(struct soc_tplg *tplg,
 		case SND_SOC_TPLG_CTL_RANGE:
 		case SND_SOC_TPLG_DAPM_CTL_VOLSW:
 		case SND_SOC_TPLG_DAPM_CTL_PIN:
-			soc_tplg_dmixer_create(tplg, 1,
-					       le32_to_cpu(hdr->payload_size));
+			ret = soc_tplg_dmixer_create(tplg, 1,
+					le32_to_cpu(hdr->payload_size));
 			break;
 		case SND_SOC_TPLG_CTL_ENUM:
 		case SND_SOC_TPLG_CTL_ENUM_VALUE:
 		case SND_SOC_TPLG_DAPM_CTL_ENUM_DOUBLE:
 		case SND_SOC_TPLG_DAPM_CTL_ENUM_VIRT:
 		case SND_SOC_TPLG_DAPM_CTL_ENUM_VALUE:
-			soc_tplg_denum_create(tplg, 1,
-					      le32_to_cpu(hdr->payload_size));
+			ret = soc_tplg_denum_create(tplg, 1,
+					le32_to_cpu(hdr->payload_size));
 			break;
 		case SND_SOC_TPLG_CTL_BYTES:
-			soc_tplg_dbytes_create(tplg, 1,
-					       le32_to_cpu(hdr->payload_size));
+			ret = soc_tplg_dbytes_create(tplg, 1,
+					le32_to_cpu(hdr->payload_size));
 			break;
 		default:
 			soc_bind_err(tplg, control_hdr, i);
 			return -EINVAL;
 		}
+		if (ret < 0) {
+			dev_err(tplg->dev, "ASoC: invalid control\n");
+			return ret;
+		}
+
 	}
 
 	return 0;
@@ -1266,16 +1280,30 @@ static int soc_tplg_dapm_graph_elems_load(struct soc_tplg *tplg,
 		routes[i]->dobj.index = tplg->index;
 		list_add(&routes[i]->dobj.list, &tplg->comp->dobj_list);
 
-		soc_tplg_add_route(tplg, routes[i]);
+		ret = soc_tplg_add_route(tplg, routes[i]);
+		if (ret < 0) {
+			/*
+			 * this route was added to the list, it will
+			 * be freed in remove_route() so increment the
+			 * counter to skip it in the error handling
+			 * below.
+			 */
+			i++;
+			break;
+		}
 
 		/* add route, but keep going if some fail */
 		snd_soc_dapm_add_routes(dapm, routes[i], 1);
 	}
 
-	/* free memory allocated for all dapm routes in case of error */
-	if (ret < 0)
-		for (i = 0; i < count ; i++)
-			kfree(routes[i]);
+	/*
+	 * free memory allocated for all dapm routes not added to the
+	 * list in case of error
+	 */
+	if (ret < 0) {
+		while (i < count)
+			kfree(routes[i++]);
+	}
 
 	/*
 	 * free pointer to array of dapm routes as this is no longer needed.
@@ -1321,7 +1349,7 @@ static struct snd_kcontrol_new *soc_tplg_dapm_widget_dmixer_create(
 			goto err_str;
 		kc[i].private_value = (long)sm;
 		kc[i].iface = SNDRV_CTL_ELEM_IFACE_MIXER;
-		kc[i].access = mc->hdr.access;
+		kc[i].access = le32_to_cpu(mc->hdr.access);
 
 		/* we only support FL/FR channel mapping atm */
 		sm->reg = tplc_chan_get_reg(tplg, mc->channel,
@@ -1333,10 +1361,10 @@ static struct snd_kcontrol_new *soc_tplg_dapm_widget_dmixer_create(
 		sm->rshift = tplc_chan_get_shift(tplg, mc->channel,
 			SNDRV_CHMAP_FR);
 
-		sm->max = mc->max;
-		sm->min = mc->min;
-		sm->invert = mc->invert;
-		sm->platform_max = mc->platform_max;
+		sm->max = le32_to_cpu(mc->max);
+		sm->min = le32_to_cpu(mc->min);
+		sm->invert = le32_to_cpu(mc->invert);
+		sm->platform_max = le32_to_cpu(mc->platform_max);
 		sm->dobj.index = tplg->index;
 		INIT_LIST_HEAD(&sm->dobj.list);
 
@@ -1349,7 +1377,13 @@ static struct snd_kcontrol_new *soc_tplg_dapm_widget_dmixer_create(
 		}
 
 		/* create any TLV data */
-		soc_tplg_create_tlv(tplg, &kc[i], &mc->hdr);
+		err = soc_tplg_create_tlv(tplg, &kc[i], &mc->hdr);
+		if (err < 0) {
+			dev_err(tplg->dev, "ASoC: failed to create TLV %s\n",
+				mc->hdr.name);
+			kfree(sm);
+			continue;
+		}
 
 		/* pass control to driver for optional further init */
 		err = soc_tplg_init_kcontrol(tplg, &kc[i],
@@ -1399,7 +1433,7 @@ static struct snd_kcontrol_new *soc_tplg_dapm_widget_denum_create(
 			goto err;
 
 		tplg->pos += (sizeof(struct snd_soc_tplg_enum_control) +
-				ec->priv.size);
+			      le32_to_cpu(ec->priv.size));
 
 		dev_dbg(tplg->dev, " adding DAPM widget enum control %s\n",
 			ec->hdr.name);
@@ -1411,7 +1445,7 @@ static struct snd_kcontrol_new *soc_tplg_dapm_widget_denum_create(
 		}
 		kc[i].private_value = (long)se;
 		kc[i].iface = SNDRV_CTL_ELEM_IFACE_MIXER;
-		kc[i].access = ec->hdr.access;
+		kc[i].access = le32_to_cpu(ec->hdr.access);
 
 		/* we only support FL/FR channel mapping atm */
 		se->reg = tplc_chan_get_reg(tplg, ec->channel, SNDRV_CHMAP_FL);
@@ -1420,8 +1454,8 @@ static struct snd_kcontrol_new *soc_tplg_dapm_widget_denum_create(
 		se->shift_r = tplc_chan_get_shift(tplg, ec->channel,
 						  SNDRV_CHMAP_FR);
 
-		se->items = ec->items;
-		se->mask = ec->mask;
+		se->items = le32_to_cpu(ec->items);
+		se->mask = le32_to_cpu(ec->mask);
 		se->dobj.index = tplg->index;
 
 		switch (le32_to_cpu(ec->hdr.ops.info)) {
@@ -1528,9 +1562,9 @@ static struct snd_kcontrol_new *soc_tplg_dapm_widget_dbytes_create(
 		}
 		kc[i].private_value = (long)sbe;
 		kc[i].iface = SNDRV_CTL_ELEM_IFACE_MIXER;
-		kc[i].access = be->hdr.access;
+		kc[i].access = le32_to_cpu(be->hdr.access);
 
-		sbe->max = be->max;
+		sbe->max = le32_to_cpu(be->max);
 		INIT_LIST_HEAD(&sbe->dobj.list);
 
 		/* map standard io handlers and check for external handlers */
@@ -1885,6 +1919,10 @@ static int soc_tplg_fe_link_create(struct soc_tplg *tplg,
 	if (link == NULL)
 		return -ENOMEM;
 
+	link->dobj.index = tplg->index;
+	link->dobj.ops = tplg->ops;
+	link->dobj.type = SND_SOC_DOBJ_DAI_LINK;
+
 	if (strlen(pcm->pcm_name)) {
 		link->name = kstrdup(pcm->pcm_name, GFP_KERNEL);
 		link->stream_name = kstrdup(pcm->pcm_name, GFP_KERNEL);
@@ -1910,20 +1948,24 @@ static int soc_tplg_fe_link_create(struct soc_tplg *tplg,
 	ret = soc_tplg_dai_link_load(tplg, link, NULL);
 	if (ret < 0) {
 		dev_err(tplg->comp->dev, "ASoC: FE link loading failed\n");
-		kfree(link->name);
-		kfree(link->stream_name);
-		kfree(link->cpu_dai_name);
-		kfree(link);
-		return ret;
+		goto err;
+	}
+
+	ret = snd_soc_add_dai_link(tplg->comp->card, link);
+	if (ret < 0) {
+		dev_err(tplg->comp->dev, "ASoC: adding FE link failed\n");
+		goto err;
 	}
 
-	link->dobj.index = tplg->index;
-	link->dobj.ops = tplg->ops;
-	link->dobj.type = SND_SOC_DOBJ_DAI_LINK;
 	list_add(&link->dobj.list, &tplg->comp->dobj_list);
 
-	snd_soc_add_dai_link(tplg->comp->card, link);
 	return 0;
+err:
+	kfree(link->name);
+	kfree(link->stream_name);
+	kfree(link->cpu_dai_name);
+	kfree(link);
+	return ret;
 }
 
 /* create a FE DAI and DAI link from the PCM object */
@@ -2016,6 +2058,7 @@ static int soc_tplg_pcm_elems_load(struct soc_tplg *tplg,
 	int size;
 	int i;
 	bool abi_match;
+	int ret;
 
 	count = le32_to_cpu(hdr->count);
 
@@ -2053,11 +2096,18 @@ static int soc_tplg_pcm_elems_load(struct soc_tplg *tplg,
 			_pcm = pcm;
 		} else {
 			abi_match = false;
-			pcm_new_ver(tplg, pcm, &_pcm);
+			ret = pcm_new_ver(tplg, pcm, &_pcm);
+			if (ret < 0)
+				return ret;
 		}
 
 		/* create the FE DAIs and DAI links */
-		soc_tplg_pcm_create(tplg, _pcm);
+		ret = soc_tplg_pcm_create(tplg, _pcm);
+		if (ret < 0) {
+			if (!abi_match)
+				kfree(_pcm);
+			return ret;
+		}
 
 		/* offset by version-specific struct size and
 		 * real priv data size
@@ -2296,8 +2346,11 @@ static int soc_tplg_link_elems_load(struct soc_tplg *tplg,
 		}
 
 		ret = soc_tplg_link_config(tplg, _link);
-		if (ret < 0)
+		if (ret < 0) {
+			if (!abi_match)
+				kfree(_link);
 			return ret;
+		}
 
 		/* offset by version-specific struct size and
 		 * real priv data size
@@ -2382,7 +2435,7 @@ static int soc_tplg_dai_elems_load(struct soc_tplg *tplg,
 {
 	struct snd_soc_tplg_dai *dai;
 	int count;
-	int i;
+	int i, ret;
 
 	count = le32_to_cpu(hdr->count);
 
@@ -2397,7 +2450,12 @@ static int soc_tplg_dai_elems_load(struct soc_tplg *tplg,
 			return -EINVAL;
 		}
 
-		soc_tplg_dai_config(tplg, dai);
+		ret = soc_tplg_dai_config(tplg, dai);
+		if (ret < 0) {
+			dev_err(tplg->dev, "ASoC: failed to configure DAI\n");
+			return ret;
+		}
+
 		tplg->pos += (sizeof(*dai) + le32_to_cpu(dai->priv.size));
 	}
 
@@ -2461,7 +2519,7 @@ static int soc_tplg_manifest_load(struct soc_tplg *tplg,
 {
 	struct snd_soc_tplg_manifest *manifest, *_manifest;
 	bool abi_match;
-	int err;
+	int ret = 0;
 
 	if (tplg->pass != SOC_TPLG_PASS_MANIFEST)
 		return 0;
@@ -2474,19 +2532,19 @@ static int soc_tplg_manifest_load(struct soc_tplg *tplg,
 		_manifest = manifest;
 	} else {
 		abi_match = false;
-		err = manifest_new_ver(tplg, manifest, &_manifest);
-		if (err < 0)
-			return err;
+		ret = manifest_new_ver(tplg, manifest, &_manifest);
+		if (ret < 0)
+			return ret;
 	}
 
 	/* pass control to component driver for optional further init */
 	if (tplg->comp && tplg->ops && tplg->ops->manifest)
-		return tplg->ops->manifest(tplg->comp, tplg->index, _manifest);
+		ret = tplg->ops->manifest(tplg->comp, tplg->index, _manifest);
 
 	if (!abi_match)	/* free the duplicated one */
 		kfree(_manifest);
 
-	return 0;
+	return ret;
 }
 
 /* validate header magic, size and type */
@@ -2505,7 +2563,7 @@ static int soc_valid_header(struct soc_tplg *tplg,
 	}
 
 	/* big endian firmware objects not supported atm */
-	if (hdr->magic == SOC_TPLG_MAGIC_BIG_ENDIAN) {
+	if (le32_to_cpu(hdr->magic) == SOC_TPLG_MAGIC_BIG_ENDIAN) {
 		dev_err(tplg->dev,
 			"ASoC: pass %d big endian not supported header got %x at offset 0x%lx size 0x%zx.\n",
 			tplg->pass, hdr->magic,
diff --git a/sound/soc/sof/core.c b/sound/soc/sof/core.c
index 5beda47cdf9f..74cd1989157b 100644
--- a/sound/soc/sof/core.c
+++ b/sound/soc/sof/core.c
@@ -288,6 +288,46 @@ static int sof_machine_check(struct snd_sof_dev *sdev)
 #endif
 }
 
+/*
+ *			FW Boot State Transition Diagram
+ *
+ *    +-----------------------------------------------------------------------+
+ *    |									      |
+ * ------------------	     ------------------				      |
+ * |		    |	     |		      |				      |
+ * |   BOOT_FAILED  |	     |  READY_FAILED  |-------------------------+     |
+ * |		    |	     |	              |				|     |
+ * ------------------	     ------------------				|     |
+ *	^			    ^					|     |
+ *	|			    |					|     |
+ * (FW Boot Timeout)		(FW_READY FAIL)				|     |
+ *	|			    |					|     |
+ *	|			    |					|     |
+ * ------------------		    |		   ------------------	|     |
+ * |		    |		    |		   |		    |	|     |
+ * |   IN_PROGRESS  |---------------+------------->|    COMPLETE    |	|     |
+ * |		    | (FW Boot OK)   (FW_READY OK) |		    |	|     |
+ * ------------------				   ------------------	|     |
+ *	^						|		|     |
+ *	|						|		|     |
+ * (FW Loading OK)			       (System Suspend/Runtime Suspend)
+ *	|						|		|     |
+ *	|						|		|     |
+ * ------------------		------------------	|		|     |
+ * |		    |		|		 |<-----+		|     |
+ * |   PREPARE	    |		|   NOT_STARTED  |<---------------------+     |
+ * |		    |		|		 |<---------------------------+
+ * ------------------		------------------
+ *    |	    ^			    |	   ^
+ *    |	    |			    |	   |
+ *    |	    +-----------------------+	   |
+ *    |		(DSP Probe OK)		   |
+ *    |					   |
+ *    |					   |
+ *    +------------------------------------+
+ *	(System Suspend/Runtime Suspend)
+ */
+
 static int sof_probe_continue(struct snd_sof_dev *sdev)
 {
 	struct snd_sof_pdata *plat_data = sdev->pdata;
@@ -303,6 +343,8 @@ static int sof_probe_continue(struct snd_sof_dev *sdev)
 		return ret;
 	}
 
+	sdev->fw_state = SOF_FW_BOOT_PREPARE;
+
 	/* check machine info */
 	ret = sof_machine_check(sdev);
 	if (ret < 0) {
@@ -330,6 +372,7 @@ static int sof_probe_continue(struct snd_sof_dev *sdev)
 	/* init the IPC */
 	sdev->ipc = snd_sof_ipc_init(sdev);
 	if (!sdev->ipc) {
+		ret = -ENOMEM;
 		dev_err(sdev->dev, "error: failed to init DSP IPC %d\n", ret);
 		goto ipc_err;
 	}
@@ -342,7 +385,12 @@ static int sof_probe_continue(struct snd_sof_dev *sdev)
 		goto fw_load_err;
 	}
 
-	/* boot the firmware */
+	sdev->fw_state = SOF_FW_BOOT_IN_PROGRESS;
+
+	/*
+	 * Boot the firmware. The FW boot status will be modified
+	 * in snd_sof_run_firmware() depending on the outcome.
+	 */
 	ret = snd_sof_run_firmware(sdev);
 	if (ret < 0) {
 		dev_err(sdev->dev, "error: failed to boot DSP firmware %d\n",
@@ -368,7 +416,7 @@ static int sof_probe_continue(struct snd_sof_dev *sdev)
 	if (ret < 0) {
 		dev_err(sdev->dev,
 			"error: failed to register DSP DAI driver %d\n", ret);
-		goto fw_run_err;
+		goto fw_trace_err;
 	}
 
 	drv_name = plat_data->machine->drv_name;
@@ -382,7 +430,7 @@ static int sof_probe_continue(struct snd_sof_dev *sdev)
 
 	if (IS_ERR(plat_data->pdev_mach)) {
 		ret = PTR_ERR(plat_data->pdev_mach);
-		goto fw_run_err;
+		goto fw_trace_err;
 	}
 
 	dev_dbg(sdev->dev, "created machine %s\n",
@@ -393,7 +441,8 @@ static int sof_probe_continue(struct snd_sof_dev *sdev)
 
 	return 0;
 
-#if !IS_ENABLED(CONFIG_SND_SOC_SOF_PROBE_WORK_QUEUE)
+fw_trace_err:
+	snd_sof_free_trace(sdev);
 fw_run_err:
 	snd_sof_fw_unload(sdev);
 fw_load_err:
@@ -402,21 +451,10 @@ ipc_err:
 	snd_sof_free_debug(sdev);
 dbg_err:
 	snd_sof_remove(sdev);
-#else
-
-	/*
-	 * when the probe_continue is handled in a work queue, the
-	 * probe does not fail so we don't release resources here.
-	 * They will be released with an explicit call to
-	 * snd_sof_device_remove() when the PCI/ACPI device is removed
-	 */
 
-fw_run_err:
-fw_load_err:
-ipc_err:
-dbg_err:
-
-#endif
+	/* all resources freed, update state to match */
+	sdev->fw_state = SOF_FW_BOOT_NOT_STARTED;
+	sdev->first_boot = true;
 
 	return ret;
 }
@@ -447,6 +485,7 @@ int snd_sof_device_probe(struct device *dev, struct snd_sof_pdata *plat_data)
 
 	sdev->pdata = plat_data;
 	sdev->first_boot = true;
+	sdev->fw_state = SOF_FW_BOOT_NOT_STARTED;
 	dev_set_drvdata(dev, sdev);
 
 	/* check all mandatory ops */
@@ -494,10 +533,12 @@ int snd_sof_device_remove(struct device *dev)
 	if (IS_ENABLED(CONFIG_SND_SOC_SOF_PROBE_WORK_QUEUE))
 		cancel_work_sync(&sdev->probe_work);
 
-	snd_sof_fw_unload(sdev);
-	snd_sof_ipc_free(sdev);
-	snd_sof_free_debug(sdev);
-	snd_sof_free_trace(sdev);
+	if (sdev->fw_state > SOF_FW_BOOT_NOT_STARTED) {
+		snd_sof_fw_unload(sdev);
+		snd_sof_ipc_free(sdev);
+		snd_sof_free_debug(sdev);
+		snd_sof_free_trace(sdev);
+	}
 
 	/*
 	 * Unregister machine driver. This will unbind the snd_card which
@@ -513,7 +554,8 @@ int snd_sof_device_remove(struct device *dev)
 	 * scheduled on, when they are unloaded. Therefore, the DSP must be
 	 * removed only after the topology has been unloaded.
 	 */
-	snd_sof_remove(sdev);
+	if (sdev->fw_state > SOF_FW_BOOT_NOT_STARTED)
+		snd_sof_remove(sdev);
 
 	/* release firmware */
 	release_firmware(pdata->fw);
diff --git a/sound/soc/sof/intel/Kconfig b/sound/soc/sof/intel/Kconfig
index 8b5cd8ef260b..3045a3a37889 100644
--- a/sound/soc/sof/intel/Kconfig
+++ b/sound/soc/sof/intel/Kconfig
@@ -72,10 +72,18 @@ config SND_SOC_SOF_BAYTRAIL
 
 config SND_SOC_SOF_BROADWELL_SUPPORT
 	bool "SOF support for Broadwell"
+	depends on SND_SOC_INTEL_HASWELL=n
 	help
 	  This adds support for Sound Open Firmware for Intel(R) platforms
 	  using the Broadwell processors.
-	  Say Y if you have such a device.
+	  This option is mutually exclusive with the Haswell/Broadwell legacy
+	  driver. If you want to enable SOF on Broadwell you need to deselect
+	  the legacy driver first.
+	  SOF does fully support Broadwell yet, so this option is not
+	  recommended for distros. At some point all legacy drivers will be
+	  deprecated but not before all userspace firmware/topology/UCM files
+	  are made available to downstream distros.
+	  Say Y if you want to enable SOF on Broadwell
 	  If unsure select "N".
 
 config SND_SOC_SOF_BROADWELL
diff --git a/sound/soc/sof/intel/byt.c b/sound/soc/sof/intel/byt.c
index 73b1645ab971..7c09a619f238 100644
--- a/sound/soc/sof/intel/byt.c
+++ b/sound/soc/sof/intel/byt.c
@@ -24,7 +24,8 @@
 #define DRAM_OFFSET		0x100000
 #define DRAM_SIZE		(160 * 1024)
 #define SHIM_OFFSET		0x140000
-#define SHIM_SIZE		0x100
+#define SHIM_SIZE_BYT		0x100
+#define SHIM_SIZE_CHT		0x118
 #define MBOX_OFFSET		0x144000
 #define MBOX_SIZE		0x1000
 #define EXCEPT_OFFSET		0x800
@@ -75,7 +76,7 @@ static const struct snd_sof_debugfs_map byt_debugfs[] = {
 	 SOF_DEBUGFS_ACCESS_D0_ONLY},
 	{"dram", BYT_DSP_BAR, DRAM_OFFSET, DRAM_SIZE,
 	 SOF_DEBUGFS_ACCESS_D0_ONLY},
-	{"shim", BYT_DSP_BAR, SHIM_OFFSET, SHIM_SIZE,
+	{"shim", BYT_DSP_BAR, SHIM_OFFSET, SHIM_SIZE_BYT,
 	 SOF_DEBUGFS_ACCESS_ALWAYS},
 };
 
@@ -102,7 +103,7 @@ static const struct snd_sof_debugfs_map cht_debugfs[] = {
 	 SOF_DEBUGFS_ACCESS_D0_ONLY},
 	{"dram", BYT_DSP_BAR, DRAM_OFFSET, DRAM_SIZE,
 	 SOF_DEBUGFS_ACCESS_D0_ONLY},
-	{"shim", BYT_DSP_BAR, SHIM_OFFSET, SHIM_SIZE,
+	{"shim", BYT_DSP_BAR, SHIM_OFFSET, SHIM_SIZE_CHT,
 	 SOF_DEBUGFS_ACCESS_ALWAYS},
 };
 
diff --git a/sound/soc/sof/intel/hda-codec.c b/sound/soc/sof/intel/hda-codec.c
index 0d8437b080bf..2aa98b0de002 100644
--- a/sound/soc/sof/intel/hda-codec.c
+++ b/sound/soc/sof/intel/hda-codec.c
@@ -23,19 +23,18 @@
 #define IDISP_VID_INTEL	0x80860000
 
 /* load the legacy HDA codec driver */
-#ifdef MODULE
-static void hda_codec_load_module(struct hda_codec *codec)
+static int hda_codec_load_module(struct hda_codec *codec)
 {
+#ifdef MODULE
 	char alias[MODULE_NAME_LEN];
 	const char *module = alias;
 
 	snd_hdac_codec_modalias(&codec->core, alias, sizeof(alias));
 	dev_dbg(&codec->core.dev, "loading codec module: %s\n", module);
 	request_module(module);
-}
-#else
-static void hda_codec_load_module(struct hda_codec *codec) {}
 #endif
+	return device_attach(hda_codec_dev(codec));
+}
 
 #endif /* CONFIG_SND_SOC_SOF_HDA_AUDIO_CODEC */
 
@@ -76,10 +75,16 @@ static int hda_codec_probe(struct snd_sof_dev *sdev, int address)
 	/* use legacy bus only for HDA codecs, idisp uses ext bus */
 	if ((resp & 0xFFFF0000) != IDISP_VID_INTEL) {
 		hdev->type = HDA_DEV_LEGACY;
-		hda_codec_load_module(&hda_priv->codec);
+		ret = hda_codec_load_module(&hda_priv->codec);
+		/*
+		 * handle ret==0 (no driver bound) as an error, but pass
+		 * other return codes without modification
+		 */
+		if (ret == 0)
+			ret = -ENOENT;
 	}
 
-	return 0;
+	return ret;
 #else
 	hdev = devm_kzalloc(sdev->dev, sizeof(*hdev), GFP_KERNEL);
 	if (!hdev)
diff --git a/sound/soc/sof/intel/hda-dai.c b/sound/soc/sof/intel/hda-dai.c
index e1decf25aeac..2c748c1b361f 100644
--- a/sound/soc/sof/intel/hda-dai.c
+++ b/sound/soc/sof/intel/hda-dai.c
@@ -341,6 +341,10 @@ struct snd_soc_dai_driver skl_dai[] = {
 	.ops = &hda_link_dai_ops,
 },
 {
+	.name = "iDisp4 Pin",
+	.ops = &hda_link_dai_ops,
+},
+{
 	.name = "Analog CPU DAI",
 	.ops = &hda_link_dai_ops,
 },
diff --git a/sound/soc/sof/intel/hda-loader.c b/sound/soc/sof/intel/hda-loader.c
index 65c2af3fcaab..356bb134ae93 100644
--- a/sound/soc/sof/intel/hda-loader.c
+++ b/sound/soc/sof/intel/hda-loader.c
@@ -278,7 +278,6 @@ int hda_dsp_cl_boot_firmware(struct snd_sof_dev *sdev)
 
 	/* init for booting wait */
 	init_waitqueue_head(&sdev->boot_wait);
-	sdev->boot_complete = false;
 
 	/* prepare DMA for code loader stream */
 	tag = cl_stream_prepare(sdev, 0x40, stripped_firmware.size,
diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c
index 3f645cfa8574..35c9055ea439 100644
--- a/sound/soc/sof/intel/hda.c
+++ b/sound/soc/sof/intel/hda.c
@@ -151,7 +151,7 @@ void hda_dsp_dump_skl(struct snd_sof_dev *sdev, u32 flags)
 	panic = snd_sof_dsp_read(sdev, HDA_DSP_BAR,
 				 HDA_ADSP_ERROR_CODE_SKL + 0x4);
 
-	if (sdev->boot_complete) {
+	if (sdev->fw_state == SOF_FW_BOOT_COMPLETE) {
 		hda_dsp_get_registers(sdev, &xoops, &panic_info, stack,
 				      HDA_DSP_STACK_DUMP_SIZE);
 		snd_sof_get_status(sdev, status, panic, &xoops, &panic_info,
@@ -178,7 +178,7 @@ void hda_dsp_dump(struct snd_sof_dev *sdev, u32 flags)
 				  HDA_DSP_SRAM_REG_FW_STATUS);
 	panic = snd_sof_dsp_read(sdev, HDA_DSP_BAR, HDA_DSP_SRAM_REG_FW_TRACEP);
 
-	if (sdev->boot_complete) {
+	if (sdev->fw_state == SOF_FW_BOOT_COMPLETE) {
 		hda_dsp_get_registers(sdev, &xoops, &panic_info, stack,
 				      HDA_DSP_STACK_DUMP_SIZE);
 		snd_sof_get_status(sdev, status, panic, &xoops, &panic_info,
@@ -301,10 +301,23 @@ static int hda_init_caps(struct snd_sof_dev *sdev)
 	if (bus->ppcap)
 		dev_dbg(sdev->dev, "PP capability, will probe DSP later.\n");
 
+#if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA)
+	/* init i915 and HDMI codecs */
+	ret = hda_codec_i915_init(sdev);
+	if (ret < 0) {
+		dev_err(sdev->dev, "error: init i915 and HDMI codec failed\n");
+		return ret;
+	}
+#endif
+
+	/* Init HDA controller after i915 init */
 	ret = hda_dsp_ctrl_init_chip(sdev, true);
 	if (ret < 0) {
 		dev_err(bus->dev, "error: init chip failed with ret: %d\n",
 			ret);
+#if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA)
+		hda_codec_i915_exit(sdev);
+#endif
 		return ret;
 	}
 
@@ -312,13 +325,6 @@ static int hda_init_caps(struct snd_sof_dev *sdev)
 	if (bus->mlcap)
 		snd_hdac_ext_bus_get_ml_capabilities(bus);
 
-	/* init i915 and HDMI codecs */
-	ret = hda_codec_i915_init(sdev);
-	if (ret < 0) {
-		dev_err(sdev->dev, "error: no HDMI audio devices found\n");
-		return ret;
-	}
-
 	/* codec detection */
 	if (!bus->codec_mask) {
 		dev_info(bus->dev, "no hda codecs found!\n");
diff --git a/sound/soc/sof/intel/hda.h b/sound/soc/sof/intel/hda.h
index 137f2faf4726..54475ac93b4d 100644
--- a/sound/soc/sof/intel/hda.h
+++ b/sound/soc/sof/intel/hda.h
@@ -329,7 +329,7 @@
 
 /* Number of DAIs */
 #if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA)
-#define SOF_SKL_NUM_DAIS		14
+#define SOF_SKL_NUM_DAIS		15
 #else
 #define SOF_SKL_NUM_DAIS		8
 #endif
diff --git a/sound/soc/sof/ipc.c b/sound/soc/sof/ipc.c
index 666f7fe98693..b3bff871863b 100644
--- a/sound/soc/sof/ipc.c
+++ b/sound/soc/sof/ipc.c
@@ -344,19 +344,12 @@ void snd_sof_ipc_msgs_rx(struct snd_sof_dev *sdev)
 		break;
 	case SOF_IPC_FW_READY:
 		/* check for FW boot completion */
-		if (!sdev->boot_complete) {
+		if (sdev->fw_state == SOF_FW_BOOT_IN_PROGRESS) {
 			err = sof_ops(sdev)->fw_ready(sdev, cmd);
-			if (err < 0) {
-				/*
-				 * this indicates a mismatch in ABI
-				 * between the driver and fw
-				 */
-				dev_err(sdev->dev, "error: ABI mismatch %d\n",
-					err);
-			} else {
-				/* firmware boot completed OK */
-				sdev->boot_complete = true;
-			}
+			if (err < 0)
+				sdev->fw_state = SOF_FW_BOOT_READY_FAILED;
+			else
+				sdev->fw_state = SOF_FW_BOOT_COMPLETE;
 
 			/* wake up firmware loader */
 			wake_up(&sdev->boot_wait);
@@ -500,7 +493,7 @@ int snd_sof_ipc_stream_posn(struct snd_sof_dev *sdev,
 
 	/* send IPC to the DSP */
 	err = sof_ipc_tx_message(sdev->ipc,
-				 stream.hdr.cmd, &stream, sizeof(stream), &posn,
+				 stream.hdr.cmd, &stream, sizeof(stream), posn,
 				 sizeof(*posn));
 	if (err < 0) {
 		dev_err(sdev->dev, "error: failed to get stream %d position\n",
@@ -830,6 +823,9 @@ void snd_sof_ipc_free(struct snd_sof_dev *sdev)
 {
 	struct snd_sof_ipc *ipc = sdev->ipc;
 
+	if (!ipc)
+		return;
+
 	/* disable sending of ipc's */
 	mutex_lock(&ipc->tx_mutex);
 	ipc->disable_ipc_tx = true;
diff --git a/sound/soc/sof/loader.c b/sound/soc/sof/loader.c
index 66238ae44ab7..4cd6e2934922 100644
--- a/sound/soc/sof/loader.c
+++ b/sound/soc/sof/loader.c
@@ -68,6 +68,8 @@ int snd_sof_fw_parse_ext_data(struct snd_sof_dev *sdev, u32 bar, u32 offset)
 			ret = get_ext_windows(sdev, ext_hdr);
 			break;
 		default:
+			dev_warn(sdev->dev, "warning: unknown ext header type %d size 0x%x\n",
+				 ext_hdr->type, ext_hdr->hdr.size);
 			break;
 		}
 
@@ -335,7 +337,6 @@ int snd_sof_run_firmware(struct snd_sof_dev *sdev)
 	int init_core_mask;
 
 	init_waitqueue_head(&sdev->boot_wait);
-	sdev->boot_complete = false;
 
 	/* create fw_version debugfs to store boot version info */
 	if (sdev->first_boot) {
@@ -367,19 +368,27 @@ int snd_sof_run_firmware(struct snd_sof_dev *sdev)
 
 	init_core_mask = ret;
 
-	/* now wait for the DSP to boot */
-	ret = wait_event_timeout(sdev->boot_wait, sdev->boot_complete,
+	/*
+	 * now wait for the DSP to boot. There are 3 possible outcomes:
+	 * 1. Boot wait times out indicating FW boot failure.
+	 * 2. FW boots successfully and fw_ready op succeeds.
+	 * 3. FW boots but fw_ready op fails.
+	 */
+	ret = wait_event_timeout(sdev->boot_wait,
+				 sdev->fw_state > SOF_FW_BOOT_IN_PROGRESS,
 				 msecs_to_jiffies(sdev->boot_timeout));
 	if (ret == 0) {
 		dev_err(sdev->dev, "error: firmware boot failure\n");
 		snd_sof_dsp_dbg_dump(sdev, SOF_DBG_REGS | SOF_DBG_MBOX |
 			SOF_DBG_TEXT | SOF_DBG_PCI);
-		/* after this point FW_READY msg should be ignored */
-		sdev->boot_complete = true;
+		sdev->fw_state = SOF_FW_BOOT_FAILED;
 		return -EIO;
 	}
 
-	dev_info(sdev->dev, "firmware boot complete\n");
+	if (sdev->fw_state == SOF_FW_BOOT_COMPLETE)
+		dev_info(sdev->dev, "firmware boot complete\n");
+	else
+		return -EIO; /* FW boots but fw_ready op failed */
 
 	/* perform post fw run operations */
 	ret = snd_sof_dsp_post_fw_run(sdev);
diff --git a/sound/soc/sof/nocodec.c b/sound/soc/sof/nocodec.c
index f84b4344dcc3..906cd6bdd54f 100644
--- a/sound/soc/sof/nocodec.c
+++ b/sound/soc/sof/nocodec.c
@@ -14,6 +14,7 @@
 
 static struct snd_soc_card sof_nocodec_card = {
 	.name = "nocodec", /* the sof- prefix is added by the core */
+	.owner = THIS_MODULE
 };
 
 static int sof_nocodec_bes_setup(struct device *dev,
@@ -39,8 +40,10 @@ static int sof_nocodec_bes_setup(struct device *dev,
 		links[i].platform_name = dev_name(dev);
 		links[i].codec_dai_name = "snd-soc-dummy-dai";
 		links[i].codec_name = "snd-soc-dummy";
-		links[i].dpcm_playback = 1;
-		links[i].dpcm_capture = 1;
+		if (ops->drv[i].playback.channels_min)
+			links[i].dpcm_playback = 1;
+		if (ops->drv[i].capture.channels_min)
+			links[i].dpcm_capture = 1;
 	}
 
 	card->dai_link = links;
diff --git a/sound/soc/sof/pm.c b/sound/soc/sof/pm.c
index 8ef1d51025d8..62a98ca18da9 100644
--- a/sound/soc/sof/pm.c
+++ b/sound/soc/sof/pm.c
@@ -257,7 +257,14 @@ static int sof_resume(struct device *dev, bool runtime_resume)
 	int ret;
 
 	/* do nothing if dsp resume callbacks are not set */
-	if (!sof_ops(sdev)->resume || !sof_ops(sdev)->runtime_resume)
+	if (!runtime_resume && !sof_ops(sdev)->resume)
+		return 0;
+
+	if (runtime_resume && !sof_ops(sdev)->runtime_resume)
+		return 0;
+
+	/* DSP was never successfully started, nothing to resume */
+	if (sdev->first_boot)
 		return 0;
 
 	/*
@@ -274,6 +281,8 @@ static int sof_resume(struct device *dev, bool runtime_resume)
 		return ret;
 	}
 
+	sdev->fw_state = SOF_FW_BOOT_PREPARE;
+
 	/* load the firmware */
 	ret = snd_sof_load_firmware(sdev);
 	if (ret < 0) {
@@ -283,7 +292,12 @@ static int sof_resume(struct device *dev, bool runtime_resume)
 		return ret;
 	}
 
-	/* boot the firmware */
+	sdev->fw_state = SOF_FW_BOOT_IN_PROGRESS;
+
+	/*
+	 * Boot the firmware. The FW boot status will be modified
+	 * in snd_sof_run_firmware() depending on the outcome.
+	 */
 	ret = snd_sof_run_firmware(sdev);
 	if (ret < 0) {
 		dev_err(sdev->dev,
@@ -326,9 +340,15 @@ static int sof_suspend(struct device *dev, bool runtime_suspend)
 	int ret;
 
 	/* do nothing if dsp suspend callback is not set */
-	if (!sof_ops(sdev)->suspend)
+	if (!runtime_suspend && !sof_ops(sdev)->suspend)
 		return 0;
 
+	if (runtime_suspend && !sof_ops(sdev)->runtime_suspend)
+		return 0;
+
+	if (sdev->fw_state != SOF_FW_BOOT_COMPLETE)
+		goto power_down;
+
 	/* release trace */
 	snd_sof_release_trace(sdev);
 
@@ -350,6 +370,12 @@ static int sof_suspend(struct device *dev, bool runtime_suspend)
 		return ret;
 	}
 
+power_down:
+
+	/* return if the DSP was not probed successfully */
+	if (sdev->fw_state == SOF_FW_BOOT_NOT_STARTED)
+		return 0;
+
 	/* power down all DSP cores */
 	if (runtime_suspend)
 		ret = snd_sof_dsp_runtime_suspend(sdev, 0);
@@ -360,6 +386,9 @@ static int sof_suspend(struct device *dev, bool runtime_suspend)
 			"error: failed to power down DSP during suspend %d\n",
 			ret);
 
+	/* reset FW state */
+	sdev->fw_state = SOF_FW_BOOT_NOT_STARTED;
+
 	return ret;
 }
 
diff --git a/sound/soc/sof/sof-priv.h b/sound/soc/sof/sof-priv.h
index 1e85d6f9c5c3..05fde6f3cbc3 100644
--- a/sound/soc/sof/sof-priv.h
+++ b/sound/soc/sof/sof-priv.h
@@ -337,6 +337,15 @@ struct snd_sof_dai {
 	struct list_head list;	/* list in sdev dai list */
 };
 
+enum snd_sof_fw_state {
+	SOF_FW_BOOT_NOT_STARTED = 0,
+	SOF_FW_BOOT_PREPARE,
+	SOF_FW_BOOT_IN_PROGRESS,
+	SOF_FW_BOOT_FAILED,
+	SOF_FW_BOOT_READY_FAILED, /* firmware booted but fw_ready op failed */
+	SOF_FW_BOOT_COMPLETE,
+};
+
 /*
  * SOF Device Level.
  */
@@ -353,7 +362,7 @@ struct snd_sof_dev {
 
 	/* DSP firmware boot */
 	wait_queue_head_t boot_wait;
-	u32 boot_complete;
+	enum snd_sof_fw_state fw_state;
 	u32 first_boot;
 
 	/* work queue in case the probe is implemented in two steps */
diff --git a/sound/soc/sof/trace.c b/sound/soc/sof/trace.c
index d588e4b70fad..39bafe319556 100644
--- a/sound/soc/sof/trace.c
+++ b/sound/soc/sof/trace.c
@@ -291,7 +291,10 @@ void snd_sof_free_trace(struct snd_sof_dev *sdev)
 {
 	snd_sof_release_trace(sdev);
 
-	snd_dma_free_pages(&sdev->dmatb);
-	snd_dma_free_pages(&sdev->dmatp);
+	if (sdev->dma_trace_pages) {
+		snd_dma_free_pages(&sdev->dmatb);
+		snd_dma_free_pages(&sdev->dmatp);
+		sdev->dma_trace_pages = 0;
+	}
 }
 EXPORT_SYMBOL(snd_sof_free_trace);
diff --git a/sound/soc/sti/uniperif_player.c b/sound/soc/sti/uniperif_player.c
index 48ea915b24ba..2ed92c990b97 100644
--- a/sound/soc/sti/uniperif_player.c
+++ b/sound/soc/sti/uniperif_player.c
@@ -226,7 +226,6 @@ static void uni_player_set_channel_status(struct uniperif *player,
 	 * sampling frequency. If no sample rate is already specified, then
 	 * set one.
 	 */
-	mutex_lock(&player->ctrl_lock);
 	if (runtime) {
 		switch (runtime->rate) {
 		case 22050:
@@ -303,7 +302,6 @@ static void uni_player_set_channel_status(struct uniperif *player,
 		player->stream_settings.iec958.status[3 + (n * 4)] << 24;
 		SET_UNIPERIF_CHANNEL_STA_REGN(player, n, status);
 	}
-	mutex_unlock(&player->ctrl_lock);
 
 	/* Update the channel status */
 	if (player->ver < SND_ST_UNIPERIF_VERSION_UNI_PLR_TOP_1_0)
@@ -365,8 +363,10 @@ static int uni_player_prepare_iec958(struct uniperif *player,
 
 	SET_UNIPERIF_CTRL_ZERO_STUFF_HW(player);
 
+	mutex_lock(&player->ctrl_lock);
 	/* Update the channel status */
 	uni_player_set_channel_status(player, runtime);
+	mutex_unlock(&player->ctrl_lock);
 
 	/* Clear the user validity user bits */
 	SET_UNIPERIF_USER_VALIDITY_VALIDITY_LR(player, 0);
@@ -598,7 +598,6 @@ static int uni_player_ctl_iec958_put(struct snd_kcontrol *kcontrol,
 	iec958->status[1] = ucontrol->value.iec958.status[1];
 	iec958->status[2] = ucontrol->value.iec958.status[2];
 	iec958->status[3] = ucontrol->value.iec958.status[3];
-	mutex_unlock(&player->ctrl_lock);
 
 	spin_lock_irqsave(&player->irq_lock, flags);
 	if (player->substream && player->substream->runtime)
@@ -608,6 +607,8 @@ static int uni_player_ctl_iec958_put(struct snd_kcontrol *kcontrol,
 		uni_player_set_channel_status(player, NULL);
 
 	spin_unlock_irqrestore(&player->irq_lock, flags);
+	mutex_unlock(&player->ctrl_lock);
+
 	return 0;
 }
 
diff --git a/sound/soc/stm/stm32_sai_sub.c b/sound/soc/stm/stm32_sai_sub.c
index 49ee86d3dbec..79e6e18a0bde 100644
--- a/sound/soc/stm/stm32_sai_sub.c
+++ b/sound/soc/stm/stm32_sai_sub.c
@@ -184,6 +184,56 @@ static bool stm32_sai_sub_writeable_reg(struct device *dev, unsigned int reg)
 	}
 }
 
+static int stm32_sai_sub_reg_up(struct stm32_sai_sub_data *sai,
+				unsigned int reg, unsigned int mask,
+				unsigned int val)
+{
+	int ret;
+
+	ret = clk_enable(sai->pdata->pclk);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_update_bits(sai->regmap, reg, mask, val);
+
+	clk_disable(sai->pdata->pclk);
+
+	return ret;
+}
+
+static int stm32_sai_sub_reg_wr(struct stm32_sai_sub_data *sai,
+				unsigned int reg, unsigned int mask,
+				unsigned int val)
+{
+	int ret;
+
+	ret = clk_enable(sai->pdata->pclk);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write_bits(sai->regmap, reg, mask, val);
+
+	clk_disable(sai->pdata->pclk);
+
+	return ret;
+}
+
+static int stm32_sai_sub_reg_rd(struct stm32_sai_sub_data *sai,
+				unsigned int reg, unsigned int *val)
+{
+	int ret;
+
+	ret = clk_enable(sai->pdata->pclk);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_read(sai->regmap, reg, val);
+
+	clk_disable(sai->pdata->pclk);
+
+	return ret;
+}
+
 static const struct regmap_config stm32_sai_sub_regmap_config_f4 = {
 	.reg_bits = 32,
 	.reg_stride = 4,
@@ -295,7 +345,7 @@ static int stm32_sai_set_clk_div(struct stm32_sai_sub_data *sai,
 
 	mask = SAI_XCR1_MCKDIV_MASK(SAI_XCR1_MCKDIV_WIDTH(version));
 	cr1 = SAI_XCR1_MCKDIV_SET(div);
-	ret = regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX, mask, cr1);
+	ret = stm32_sai_sub_reg_up(sai, STM_SAI_CR1_REGX, mask, cr1);
 	if (ret < 0)
 		dev_err(&sai->pdev->dev, "Failed to update CR1 register\n");
 
@@ -372,8 +422,8 @@ static int stm32_sai_mclk_enable(struct clk_hw *hw)
 
 	dev_dbg(&sai->pdev->dev, "Enable master clock\n");
 
-	return regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX,
-				  SAI_XCR1_MCKEN, SAI_XCR1_MCKEN);
+	return stm32_sai_sub_reg_up(sai, STM_SAI_CR1_REGX,
+				    SAI_XCR1_MCKEN, SAI_XCR1_MCKEN);
 }
 
 static void stm32_sai_mclk_disable(struct clk_hw *hw)
@@ -383,7 +433,7 @@ static void stm32_sai_mclk_disable(struct clk_hw *hw)
 
 	dev_dbg(&sai->pdev->dev, "Disable master clock\n");
 
-	regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX, SAI_XCR1_MCKEN, 0);
+	stm32_sai_sub_reg_up(sai, STM_SAI_CR1_REGX, SAI_XCR1_MCKEN, 0);
 }
 
 static const struct clk_ops mclk_ops = {
@@ -446,15 +496,15 @@ static irqreturn_t stm32_sai_isr(int irq, void *devid)
 	unsigned int sr, imr, flags;
 	snd_pcm_state_t status = SNDRV_PCM_STATE_RUNNING;
 
-	regmap_read(sai->regmap, STM_SAI_IMR_REGX, &imr);
-	regmap_read(sai->regmap, STM_SAI_SR_REGX, &sr);
+	stm32_sai_sub_reg_rd(sai, STM_SAI_IMR_REGX, &imr);
+	stm32_sai_sub_reg_rd(sai, STM_SAI_SR_REGX, &sr);
 
 	flags = sr & imr;
 	if (!flags)
 		return IRQ_NONE;
 
-	regmap_write_bits(sai->regmap, STM_SAI_CLRFR_REGX, SAI_XCLRFR_MASK,
-			  SAI_XCLRFR_MASK);
+	stm32_sai_sub_reg_wr(sai, STM_SAI_CLRFR_REGX, SAI_XCLRFR_MASK,
+			     SAI_XCLRFR_MASK);
 
 	if (!sai->substream) {
 		dev_err(&pdev->dev, "Device stopped. Spurious IRQ 0x%x\n", sr);
@@ -503,8 +553,8 @@ static int stm32_sai_set_sysclk(struct snd_soc_dai *cpu_dai,
 	int ret;
 
 	if (dir == SND_SOC_CLOCK_OUT && sai->sai_mclk) {
-		ret = regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX,
-					 SAI_XCR1_NODIV,
+		ret = stm32_sai_sub_reg_up(sai, STM_SAI_CR1_REGX,
+					   SAI_XCR1_NODIV,
 					 (unsigned int)~SAI_XCR1_NODIV);
 		if (ret < 0)
 			return ret;
@@ -573,7 +623,7 @@ static int stm32_sai_set_dai_tdm_slot(struct snd_soc_dai *cpu_dai, u32 tx_mask,
 
 	slotr_mask |= SAI_XSLOTR_SLOTEN_MASK;
 
-	regmap_update_bits(sai->regmap, STM_SAI_SLOTR_REGX, slotr_mask, slotr);
+	stm32_sai_sub_reg_up(sai, STM_SAI_SLOTR_REGX, slotr_mask, slotr);
 
 	sai->slot_width = slot_width;
 	sai->slots = slots;
@@ -655,7 +705,7 @@ static int stm32_sai_set_dai_fmt(struct snd_soc_dai *cpu_dai, unsigned int fmt)
 	cr1_mask |= SAI_XCR1_CKSTR;
 	frcr_mask |= SAI_XFRCR_FSPOL;
 
-	regmap_update_bits(sai->regmap, STM_SAI_FRCR_REGX, frcr_mask, frcr);
+	stm32_sai_sub_reg_up(sai, STM_SAI_FRCR_REGX, frcr_mask, frcr);
 
 	/* DAI clock master masks */
 	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
@@ -683,7 +733,7 @@ static int stm32_sai_set_dai_fmt(struct snd_soc_dai *cpu_dai, unsigned int fmt)
 	cr1_mask |= SAI_XCR1_SLAVE;
 
 conf_update:
-	ret = regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX, cr1_mask, cr1);
+	ret = stm32_sai_sub_reg_up(sai, STM_SAI_CR1_REGX, cr1_mask, cr1);
 	if (ret < 0) {
 		dev_err(cpu_dai->dev, "Failed to update CR1 register\n");
 		return ret;
@@ -720,12 +770,12 @@ static int stm32_sai_startup(struct snd_pcm_substream *substream,
 	}
 
 	/* Enable ITs */
-	regmap_write_bits(sai->regmap, STM_SAI_CLRFR_REGX,
-			  SAI_XCLRFR_MASK, SAI_XCLRFR_MASK);
+	stm32_sai_sub_reg_wr(sai, STM_SAI_CLRFR_REGX,
+			     SAI_XCLRFR_MASK, SAI_XCLRFR_MASK);
 
 	imr = SAI_XIMR_OVRUDRIE;
 	if (STM_SAI_IS_CAPTURE(sai)) {
-		regmap_read(sai->regmap, STM_SAI_CR2_REGX, &cr2);
+		stm32_sai_sub_reg_rd(sai, STM_SAI_CR2_REGX, &cr2);
 		if (cr2 & SAI_XCR2_MUTECNT_MASK)
 			imr |= SAI_XIMR_MUTEDETIE;
 	}
@@ -735,8 +785,8 @@ static int stm32_sai_startup(struct snd_pcm_substream *substream,
 	else
 		imr |= SAI_XIMR_AFSDETIE | SAI_XIMR_LFSDETIE;
 
-	regmap_update_bits(sai->regmap, STM_SAI_IMR_REGX,
-			   SAI_XIMR_MASK, imr);
+	stm32_sai_sub_reg_up(sai, STM_SAI_IMR_REGX,
+			     SAI_XIMR_MASK, imr);
 
 	return 0;
 }
@@ -753,10 +803,10 @@ static int stm32_sai_set_config(struct snd_soc_dai *cpu_dai,
 	 * SAI fifo threshold is set to half fifo, to keep enough space
 	 * for DMA incoming bursts.
 	 */
-	regmap_write_bits(sai->regmap, STM_SAI_CR2_REGX,
-			  SAI_XCR2_FFLUSH | SAI_XCR2_FTH_MASK,
-			  SAI_XCR2_FFLUSH |
-			  SAI_XCR2_FTH_SET(STM_SAI_FIFO_TH_HALF));
+	stm32_sai_sub_reg_wr(sai, STM_SAI_CR2_REGX,
+			     SAI_XCR2_FFLUSH | SAI_XCR2_FTH_MASK,
+			     SAI_XCR2_FFLUSH |
+			     SAI_XCR2_FTH_SET(STM_SAI_FIFO_TH_HALF));
 
 	/* DS bits in CR1 not set for SPDIF (size forced to 24 bits).*/
 	if (STM_SAI_PROTOCOL_IS_SPDIF(sai)) {
@@ -785,7 +835,7 @@ static int stm32_sai_set_config(struct snd_soc_dai *cpu_dai,
 	if ((sai->slots == 2) && (params_channels(params) == 1))
 		cr1 |= SAI_XCR1_MONO;
 
-	ret = regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX, cr1_mask, cr1);
+	ret = stm32_sai_sub_reg_up(sai, STM_SAI_CR1_REGX, cr1_mask, cr1);
 	if (ret < 0) {
 		dev_err(cpu_dai->dev, "Failed to update CR1 register\n");
 		return ret;
@@ -799,7 +849,7 @@ static int stm32_sai_set_slots(struct snd_soc_dai *cpu_dai)
 	struct stm32_sai_sub_data *sai = snd_soc_dai_get_drvdata(cpu_dai);
 	int slotr, slot_sz;
 
-	regmap_read(sai->regmap, STM_SAI_SLOTR_REGX, &slotr);
+	stm32_sai_sub_reg_rd(sai, STM_SAI_SLOTR_REGX, &slotr);
 
 	/*
 	 * If SLOTSZ is set to auto in SLOTR, align slot width on data size
@@ -821,16 +871,16 @@ static int stm32_sai_set_slots(struct snd_soc_dai *cpu_dai)
 		sai->slots = 2;
 
 	/* The number of slots in the audio frame is equal to NBSLOT[3:0] + 1*/
-	regmap_update_bits(sai->regmap, STM_SAI_SLOTR_REGX,
-			   SAI_XSLOTR_NBSLOT_MASK,
-			   SAI_XSLOTR_NBSLOT_SET((sai->slots - 1)));
+	stm32_sai_sub_reg_up(sai, STM_SAI_SLOTR_REGX,
+			     SAI_XSLOTR_NBSLOT_MASK,
+			     SAI_XSLOTR_NBSLOT_SET((sai->slots - 1)));
 
 	/* Set default slots mask if not already set from DT */
 	if (!(slotr & SAI_XSLOTR_SLOTEN_MASK)) {
 		sai->slot_mask = (1 << sai->slots) - 1;
-		regmap_update_bits(sai->regmap,
-				   STM_SAI_SLOTR_REGX, SAI_XSLOTR_SLOTEN_MASK,
-				   SAI_XSLOTR_SLOTEN_SET(sai->slot_mask));
+		stm32_sai_sub_reg_up(sai,
+				     STM_SAI_SLOTR_REGX, SAI_XSLOTR_SLOTEN_MASK,
+				     SAI_XSLOTR_SLOTEN_SET(sai->slot_mask));
 	}
 
 	dev_dbg(cpu_dai->dev, "Slots %d, slot width %d\n",
@@ -860,14 +910,14 @@ static void stm32_sai_set_frame(struct snd_soc_dai *cpu_dai)
 	dev_dbg(cpu_dai->dev, "Frame length %d, frame active %d\n",
 		sai->fs_length, fs_active);
 
-	regmap_update_bits(sai->regmap, STM_SAI_FRCR_REGX, frcr_mask, frcr);
+	stm32_sai_sub_reg_up(sai, STM_SAI_FRCR_REGX, frcr_mask, frcr);
 
 	if ((sai->fmt & SND_SOC_DAIFMT_FORMAT_MASK) == SND_SOC_DAIFMT_LSB) {
 		offset = sai->slot_width - sai->data_size;
 
-		regmap_update_bits(sai->regmap, STM_SAI_SLOTR_REGX,
-				   SAI_XSLOTR_FBOFF_MASK,
-				   SAI_XSLOTR_FBOFF_SET(offset));
+		stm32_sai_sub_reg_up(sai, STM_SAI_SLOTR_REGX,
+				     SAI_XSLOTR_FBOFF_MASK,
+				     SAI_XSLOTR_FBOFF_SET(offset));
 	}
 }
 
@@ -984,9 +1034,9 @@ static int stm32_sai_configure_clock(struct snd_soc_dai *cpu_dai,
 					return -EINVAL;
 				}
 
-				regmap_update_bits(sai->regmap,
-						   STM_SAI_CR1_REGX,
-						   SAI_XCR1_OSR, cr1);
+				stm32_sai_sub_reg_up(sai,
+						     STM_SAI_CR1_REGX,
+						     SAI_XCR1_OSR, cr1);
 
 				div = stm32_sai_get_clk_div(sai, sai_clk_rate,
 							    sai->mclk_rate);
@@ -1048,12 +1098,12 @@ static int stm32_sai_trigger(struct snd_pcm_substream *substream, int cmd,
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
 		dev_dbg(cpu_dai->dev, "Enable DMA and SAI\n");
 
-		regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX,
-				   SAI_XCR1_DMAEN, SAI_XCR1_DMAEN);
+		stm32_sai_sub_reg_up(sai, STM_SAI_CR1_REGX,
+				     SAI_XCR1_DMAEN, SAI_XCR1_DMAEN);
 
 		/* Enable SAI */
-		ret = regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX,
-					 SAI_XCR1_SAIEN, SAI_XCR1_SAIEN);
+		ret = stm32_sai_sub_reg_up(sai, STM_SAI_CR1_REGX,
+					   SAI_XCR1_SAIEN, SAI_XCR1_SAIEN);
 		if (ret < 0)
 			dev_err(cpu_dai->dev, "Failed to update CR1 register\n");
 		break;
@@ -1062,16 +1112,16 @@ static int stm32_sai_trigger(struct snd_pcm_substream *substream, int cmd,
 	case SNDRV_PCM_TRIGGER_STOP:
 		dev_dbg(cpu_dai->dev, "Disable DMA and SAI\n");
 
-		regmap_update_bits(sai->regmap, STM_SAI_IMR_REGX,
-				   SAI_XIMR_MASK, 0);
+		stm32_sai_sub_reg_up(sai, STM_SAI_IMR_REGX,
+				     SAI_XIMR_MASK, 0);
 
-		regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX,
-				   SAI_XCR1_SAIEN,
-				   (unsigned int)~SAI_XCR1_SAIEN);
+		stm32_sai_sub_reg_up(sai, STM_SAI_CR1_REGX,
+				     SAI_XCR1_SAIEN,
+				     (unsigned int)~SAI_XCR1_SAIEN);
 
-		ret = regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX,
-					 SAI_XCR1_DMAEN,
-					 (unsigned int)~SAI_XCR1_DMAEN);
+		ret = stm32_sai_sub_reg_up(sai, STM_SAI_CR1_REGX,
+					   SAI_XCR1_DMAEN,
+					   (unsigned int)~SAI_XCR1_DMAEN);
 		if (ret < 0)
 			dev_err(cpu_dai->dev, "Failed to update CR1 register\n");
 
@@ -1091,7 +1141,7 @@ static void stm32_sai_shutdown(struct snd_pcm_substream *substream,
 	struct stm32_sai_sub_data *sai = snd_soc_dai_get_drvdata(cpu_dai);
 	unsigned long flags;
 
-	regmap_update_bits(sai->regmap, STM_SAI_IMR_REGX, SAI_XIMR_MASK, 0);
+	stm32_sai_sub_reg_up(sai, STM_SAI_IMR_REGX, SAI_XIMR_MASK, 0);
 
 	regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX, SAI_XCR1_NODIV,
 			   SAI_XCR1_NODIV);
@@ -1166,7 +1216,7 @@ static int stm32_sai_dai_probe(struct snd_soc_dai *cpu_dai)
 	cr1_mask |= SAI_XCR1_SYNCEN_MASK;
 	cr1 |= SAI_XCR1_SYNCEN_SET(sai->sync);
 
-	return regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX, cr1_mask, cr1);
+	return stm32_sai_sub_reg_up(sai, STM_SAI_CR1_REGX, cr1_mask, cr1);
 }
 
 static const struct snd_soc_dai_ops stm32_sai_pcm_dai_ops = {
@@ -1319,8 +1369,13 @@ static int stm32_sai_sub_parse_of(struct platform_device *pdev,
 	if (STM_SAI_IS_H7(sai->pdata) && STM_SAI_IS_SUB_A(sai))
 		sai->regmap_config = &stm32_sai_sub_regmap_config_h7;
 
-	sai->regmap = devm_regmap_init_mmio_clk(&pdev->dev, "sai_ck",
-						base, sai->regmap_config);
+	/*
+	 * Do not manage peripheral clock through regmap framework as this
+	 * can lead to circular locking issue with sai master clock provider.
+	 * Manage peripheral clock directly in driver instead.
+	 */
+	sai->regmap = devm_regmap_init_mmio(&pdev->dev, base,
+					    sai->regmap_config);
 	if (IS_ERR(sai->regmap)) {
 		dev_err(&pdev->dev, "Failed to initialize MMIO\n");
 		return PTR_ERR(sai->regmap);
@@ -1417,6 +1472,10 @@ static int stm32_sai_sub_parse_of(struct platform_device *pdev,
 		return PTR_ERR(sai->sai_ck);
 	}
 
+	ret = clk_prepare(sai->pdata->pclk);
+	if (ret < 0)
+		return ret;
+
 	if (STM_SAI_IS_F4(sai->pdata))
 		return 0;
 
@@ -1481,20 +1540,31 @@ static int stm32_sai_sub_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	ret = devm_snd_soc_register_component(&pdev->dev, &stm32_component,
-					      &sai->cpu_dai_drv, 1);
-	if (ret)
-		return ret;
-
 	if (STM_SAI_PROTOCOL_IS_SPDIF(sai))
 		conf = &stm32_sai_pcm_config_spdif;
 
-	ret = devm_snd_dmaengine_pcm_register(&pdev->dev, conf, 0);
+	ret = snd_dmaengine_pcm_register(&pdev->dev, conf, 0);
 	if (ret) {
 		dev_err(&pdev->dev, "Could not register pcm dma\n");
 		return ret;
 	}
 
+	ret = snd_soc_register_component(&pdev->dev, &stm32_component,
+					 &sai->cpu_dai_drv, 1);
+	if (ret)
+		snd_dmaengine_pcm_unregister(&pdev->dev);
+
+	return ret;
+}
+
+static int stm32_sai_sub_remove(struct platform_device *pdev)
+{
+	struct stm32_sai_sub_data *sai = dev_get_drvdata(&pdev->dev);
+
+	clk_unprepare(sai->pdata->pclk);
+	snd_dmaengine_pcm_unregister(&pdev->dev);
+	snd_soc_unregister_component(&pdev->dev);
+
 	return 0;
 }
 
@@ -1502,18 +1572,35 @@ static int stm32_sai_sub_probe(struct platform_device *pdev)
 static int stm32_sai_sub_suspend(struct device *dev)
 {
 	struct stm32_sai_sub_data *sai = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_enable(sai->pdata->pclk);
+	if (ret < 0)
+		return ret;
 
 	regcache_cache_only(sai->regmap, true);
 	regcache_mark_dirty(sai->regmap);
+
+	clk_disable(sai->pdata->pclk);
+
 	return 0;
 }
 
 static int stm32_sai_sub_resume(struct device *dev)
 {
 	struct stm32_sai_sub_data *sai = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_enable(sai->pdata->pclk);
+	if (ret < 0)
+		return ret;
 
 	regcache_cache_only(sai->regmap, false);
-	return regcache_sync(sai->regmap);
+	ret = regcache_sync(sai->regmap);
+
+	clk_disable(sai->pdata->pclk);
+
+	return ret;
 }
 #endif /* CONFIG_PM_SLEEP */
 
@@ -1528,6 +1615,7 @@ static struct platform_driver stm32_sai_sub_driver = {
 		.pm = &stm32_sai_sub_pm_ops,
 	},
 	.probe = stm32_sai_sub_probe,
+	.remove = stm32_sai_sub_remove,
 };
 
 module_platform_driver(stm32_sai_sub_driver);
diff --git a/sound/soc/stm/stm32_spdifrx.c b/sound/soc/stm/stm32_spdifrx.c
index 56d79695577c..ac9ae434237a 100644
--- a/sound/soc/stm/stm32_spdifrx.c
+++ b/sound/soc/stm/stm32_spdifrx.c
@@ -11,7 +11,6 @@
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/of_platform.h>
-#include <linux/pinctrl/consumer.h>
 #include <linux/regmap.h>
 #include <linux/reset.h>
 
@@ -204,6 +203,7 @@
  * @slave_config: dma slave channel runtime config pointer
  * @phys_addr: SPDIFRX registers physical base address
  * @lock: synchronization enabling lock
+ * @irq_lock: prevent race condition with IRQ on stream state
  * @cs: channel status buffer
  * @ub: user data buffer
  * @irq: SPDIFRX interrupt line
@@ -224,6 +224,7 @@ struct stm32_spdifrx_data {
 	struct dma_slave_config slave_config;
 	dma_addr_t phys_addr;
 	spinlock_t lock;  /* Sync enabling lock */
+	spinlock_t irq_lock; /* Prevent race condition on stream state */
 	unsigned char cs[SPDIFRX_CS_BYTES_NB];
 	unsigned char ub[SPDIFRX_UB_BYTES_NB];
 	int irq;
@@ -304,6 +305,7 @@ static void stm32_spdifrx_dma_ctrl_stop(struct stm32_spdifrx_data *spdifrx)
 static int stm32_spdifrx_start_sync(struct stm32_spdifrx_data *spdifrx)
 {
 	int cr, cr_mask, imr, ret;
+	unsigned long flags;
 
 	/* Enable IRQs */
 	imr = SPDIFRX_IMR_IFEIE | SPDIFRX_IMR_SYNCDIE | SPDIFRX_IMR_PERRIE;
@@ -311,7 +313,7 @@ static int stm32_spdifrx_start_sync(struct stm32_spdifrx_data *spdifrx)
 	if (ret)
 		return ret;
 
-	spin_lock(&spdifrx->lock);
+	spin_lock_irqsave(&spdifrx->lock, flags);
 
 	spdifrx->refcount++;
 
@@ -344,7 +346,7 @@ static int stm32_spdifrx_start_sync(struct stm32_spdifrx_data *spdifrx)
 				"Failed to start synchronization\n");
 	}
 
-	spin_unlock(&spdifrx->lock);
+	spin_unlock_irqrestore(&spdifrx->lock, flags);
 
 	return ret;
 }
@@ -352,11 +354,12 @@ static int stm32_spdifrx_start_sync(struct stm32_spdifrx_data *spdifrx)
 static void stm32_spdifrx_stop(struct stm32_spdifrx_data *spdifrx)
 {
 	int cr, cr_mask, reg;
+	unsigned long flags;
 
-	spin_lock(&spdifrx->lock);
+	spin_lock_irqsave(&spdifrx->lock, flags);
 
 	if (--spdifrx->refcount) {
-		spin_unlock(&spdifrx->lock);
+		spin_unlock_irqrestore(&spdifrx->lock, flags);
 		return;
 	}
 
@@ -375,7 +378,7 @@ static void stm32_spdifrx_stop(struct stm32_spdifrx_data *spdifrx)
 	regmap_read(spdifrx->regmap, STM32_SPDIFRX_DR, &reg);
 	regmap_read(spdifrx->regmap, STM32_SPDIFRX_CSR, &reg);
 
-	spin_unlock(&spdifrx->lock);
+	spin_unlock_irqrestore(&spdifrx->lock, flags);
 }
 
 static int stm32_spdifrx_dma_ctrl_register(struct device *dev,
@@ -462,8 +465,6 @@ static int stm32_spdifrx_get_ctrl_data(struct stm32_spdifrx_data *spdifrx)
 	memset(spdifrx->cs, 0, SPDIFRX_CS_BYTES_NB);
 	memset(spdifrx->ub, 0, SPDIFRX_UB_BYTES_NB);
 
-	pinctrl_pm_select_default_state(&spdifrx->pdev->dev);
-
 	ret = stm32_spdifrx_dma_ctrl_start(spdifrx);
 	if (ret < 0)
 		return ret;
@@ -495,7 +496,6 @@ static int stm32_spdifrx_get_ctrl_data(struct stm32_spdifrx_data *spdifrx)
 
 end:
 	clk_disable_unprepare(spdifrx->kclk);
-	pinctrl_pm_select_sleep_state(&spdifrx->pdev->dev);
 
 	return ret;
 }
@@ -643,7 +643,6 @@ static const struct regmap_config stm32_h7_spdifrx_regmap_conf = {
 static irqreturn_t stm32_spdifrx_isr(int irq, void *devid)
 {
 	struct stm32_spdifrx_data *spdifrx = (struct stm32_spdifrx_data *)devid;
-	struct snd_pcm_substream *substream = spdifrx->substream;
 	struct platform_device *pdev = spdifrx->pdev;
 	unsigned int cr, mask, sr, imr;
 	unsigned int flags;
@@ -711,14 +710,19 @@ static irqreturn_t stm32_spdifrx_isr(int irq, void *devid)
 		regmap_update_bits(spdifrx->regmap, STM32_SPDIFRX_CR,
 				   SPDIFRX_CR_SPDIFEN_MASK, cr);
 
-		if (substream)
-			snd_pcm_stop(substream, SNDRV_PCM_STATE_DISCONNECTED);
+		spin_lock(&spdifrx->irq_lock);
+		if (spdifrx->substream)
+			snd_pcm_stop(spdifrx->substream,
+				     SNDRV_PCM_STATE_DISCONNECTED);
+		spin_unlock(&spdifrx->irq_lock);
 
 		return IRQ_HANDLED;
 	}
 
-	if (err_xrun && substream)
-		snd_pcm_stop_xrun(substream);
+	spin_lock(&spdifrx->irq_lock);
+	if (err_xrun && spdifrx->substream)
+		snd_pcm_stop_xrun(spdifrx->substream);
+	spin_unlock(&spdifrx->irq_lock);
 
 	return IRQ_HANDLED;
 }
@@ -727,9 +731,12 @@ static int stm32_spdifrx_startup(struct snd_pcm_substream *substream,
 				 struct snd_soc_dai *cpu_dai)
 {
 	struct stm32_spdifrx_data *spdifrx = snd_soc_dai_get_drvdata(cpu_dai);
+	unsigned long flags;
 	int ret;
 
+	spin_lock_irqsave(&spdifrx->irq_lock, flags);
 	spdifrx->substream = substream;
+	spin_unlock_irqrestore(&spdifrx->irq_lock, flags);
 
 	ret = clk_prepare_enable(spdifrx->kclk);
 	if (ret)
@@ -805,8 +812,12 @@ static void stm32_spdifrx_shutdown(struct snd_pcm_substream *substream,
 				   struct snd_soc_dai *cpu_dai)
 {
 	struct stm32_spdifrx_data *spdifrx = snd_soc_dai_get_drvdata(cpu_dai);
+	unsigned long flags;
 
+	spin_lock_irqsave(&spdifrx->irq_lock, flags);
 	spdifrx->substream = NULL;
+	spin_unlock_irqrestore(&spdifrx->irq_lock, flags);
+
 	clk_disable_unprepare(spdifrx->kclk);
 }
 
@@ -911,6 +922,7 @@ static int stm32_spdifrx_probe(struct platform_device *pdev)
 	spdifrx->pdev = pdev;
 	init_completion(&spdifrx->cs_completion);
 	spin_lock_init(&spdifrx->lock);
+	spin_lock_init(&spdifrx->irq_lock);
 
 	platform_set_drvdata(pdev, spdifrx);
 
diff --git a/sound/soc/sunxi/sun8i-codec.c b/sound/soc/sunxi/sun8i-codec.c
index 0e0e8ebaa571..f9603c14ab57 100644
--- a/sound/soc/sunxi/sun8i-codec.c
+++ b/sound/soc/sunxi/sun8i-codec.c
@@ -80,6 +80,7 @@
 
 #define SUN8I_SYS_SR_CTRL_AIF1_FS_MASK		GENMASK(15, 12)
 #define SUN8I_SYS_SR_CTRL_AIF2_FS_MASK		GENMASK(11, 8)
+#define SUN8I_AIF1CLK_CTRL_AIF1_DATA_FMT_MASK	GENMASK(3, 2)
 #define SUN8I_AIF1CLK_CTRL_AIF1_WORD_SIZ_MASK	GENMASK(5, 4)
 #define SUN8I_AIF1CLK_CTRL_AIF1_LRCK_DIV_MASK	GENMASK(8, 6)
 #define SUN8I_AIF1CLK_CTRL_AIF1_BCLK_DIV_MASK	GENMASK(12, 9)
@@ -241,7 +242,7 @@ static int sun8i_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 		return -EINVAL;
 	}
 	regmap_update_bits(scodec->regmap, SUN8I_AIF1CLK_CTRL,
-			   BIT(SUN8I_AIF1CLK_CTRL_AIF1_DATA_FMT),
+			   SUN8I_AIF1CLK_CTRL_AIF1_DATA_FMT_MASK,
 			   value << SUN8I_AIF1CLK_CTRL_AIF1_DATA_FMT);
 
 	return 0;
diff --git a/sound/soc/tegra/tegra_wm8903.c b/sound/soc/tegra/tegra_wm8903.c
index 4c94c39f14d6..054b863a6301 100644
--- a/sound/soc/tegra/tegra_wm8903.c
+++ b/sound/soc/tegra/tegra_wm8903.c
@@ -159,6 +159,7 @@ static int tegra_wm8903_init(struct snd_soc_pcm_runtime *rtd)
 	struct snd_soc_component *component = codec_dai->component;
 	struct snd_soc_card *card = rtd->card;
 	struct tegra_wm8903 *machine = snd_soc_card_get_drvdata(card);
+	int shrt = 0;
 
 	if (gpio_is_valid(machine->gpio_hp_det)) {
 		tegra_wm8903_hp_jack_gpio.gpio = machine->gpio_hp_det;
@@ -171,12 +172,15 @@ static int tegra_wm8903_init(struct snd_soc_pcm_runtime *rtd)
 					&tegra_wm8903_hp_jack_gpio);
 	}
 
+	if (of_property_read_bool(card->dev->of_node, "nvidia,headset"))
+		shrt = SND_JACK_MICROPHONE;
+
 	snd_soc_card_jack_new(rtd->card, "Mic Jack", SND_JACK_MICROPHONE,
 			      &tegra_wm8903_mic_jack,
 			      tegra_wm8903_mic_jack_pins,
 			      ARRAY_SIZE(tegra_wm8903_mic_jack_pins));
 	wm8903_mic_detect(component, &tegra_wm8903_mic_jack, SND_JACK_MICROPHONE,
-				0);
+				shrt);
 
 	snd_soc_dapm_force_enable_pin(&card->dapm, "MICBIAS");
 
diff --git a/sound/soc/ti/davinci-mcasp.c b/sound/soc/ti/davinci-mcasp.c
index 56009d147208..e6fa200e822b 100644
--- a/sound/soc/ti/davinci-mcasp.c
+++ b/sound/soc/ti/davinci-mcasp.c
@@ -1807,8 +1807,10 @@ static int davinci_mcasp_get_dma_type(struct davinci_mcasp *mcasp)
 				PTR_ERR(chan));
 		return PTR_ERR(chan);
 	}
-	if (WARN_ON(!chan->device || !chan->device->dev))
+	if (WARN_ON(!chan->device || !chan->device->dev)) {
+		dma_release_channel(chan);
 		return -EINVAL;
+	}
 
 	if (chan->device->dev->of_node)
 		ret = of_property_read_string(chan->device->dev->of_node,
@@ -2260,7 +2262,7 @@ static int davinci_mcasp_probe(struct platform_device *pdev)
 		ret = edma_pcm_platform_register(&pdev->dev);
 		break;
 	case PCM_SDMA:
-		ret = sdma_pcm_platform_register(&pdev->dev, NULL, NULL);
+		ret = sdma_pcm_platform_register(&pdev->dev, "tx", "rx");
 		break;
 	default:
 		dev_err(&pdev->dev, "No DMA controller found (%d)\n", ret);
diff --git a/sound/soc/ti/omap-mcbsp.c b/sound/soc/ti/omap-mcbsp.c
index 1ab3c7df4f8b..3273b317fa3b 100644
--- a/sound/soc/ti/omap-mcbsp.c
+++ b/sound/soc/ti/omap-mcbsp.c
@@ -686,7 +686,7 @@ static int omap_mcbsp_init(struct platform_device *pdev)
 	mcbsp->dma_data[1].addr = omap_mcbsp_dma_reg_params(mcbsp,
 						SNDRV_PCM_STREAM_CAPTURE);
 
-	mcbsp->fclk = clk_get(&pdev->dev, "fck");
+	mcbsp->fclk = devm_clk_get(&pdev->dev, "fck");
 	if (IS_ERR(mcbsp->fclk)) {
 		ret = PTR_ERR(mcbsp->fclk);
 		dev_err(mcbsp->dev, "unable to get fck: %d\n", ret);
@@ -711,7 +711,7 @@ static int omap_mcbsp_init(struct platform_device *pdev)
 		if (ret) {
 			dev_err(mcbsp->dev,
 				"Unable to create additional controls\n");
-			goto err_thres;
+			return ret;
 		}
 	}
 
@@ -724,8 +724,6 @@ static int omap_mcbsp_init(struct platform_device *pdev)
 err_st:
 	if (mcbsp->pdata->buffer_size)
 		sysfs_remove_group(&mcbsp->dev->kobj, &additional_attr_group);
-err_thres:
-	clk_put(mcbsp->fclk);
 	return ret;
 }
 
@@ -1424,7 +1422,7 @@ static int asoc_mcbsp_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	return sdma_pcm_platform_register(&pdev->dev, NULL, NULL);
+	return sdma_pcm_platform_register(&pdev->dev, "tx", "rx");
 }
 
 static int asoc_mcbsp_remove(struct platform_device *pdev)
@@ -1442,8 +1440,6 @@ static int asoc_mcbsp_remove(struct platform_device *pdev)
 
 	omap_mcbsp_st_cleanup(pdev);
 
-	clk_put(mcbsp->fclk);
-
 	return 0;
 }
 
diff --git a/sound/soc/ux500/mop500.c b/sound/soc/ux500/mop500.c
index 759c635412a2..5315adc1134b 100644
--- a/sound/soc/ux500/mop500.c
+++ b/sound/soc/ux500/mop500.c
@@ -59,10 +59,11 @@ static void mop500_of_node_put(void)
 {
 	int i;
 
-	for (i = 0; i < 2; i++) {
+	for (i = 0; i < 2; i++)
 		of_node_put(mop500_dai_links[i].cpu_of_node);
-		of_node_put(mop500_dai_links[i].codec_of_node);
-	}
+
+	/* Both links use the same codec, which is refcounted only once */
+	of_node_put(mop500_dai_links[0].codec_of_node);
 }
 
 static int mop500_of_probe(struct platform_device *pdev,
@@ -77,7 +78,9 @@ static int mop500_of_probe(struct platform_device *pdev,
 
 	if (!(msp_np[0] && msp_np[1] && codec_np)) {
 		dev_err(&pdev->dev, "Phandle missing or invalid\n");
-		mop500_of_node_put();
+		for (i = 0; i < 2; i++)
+			of_node_put(msp_np[i]);
+		of_node_put(codec_np);
 		return -EINVAL;
 	}
 
diff --git a/sound/usb/card.c b/sound/usb/card.c
index db91dc76cc91..230d862cfa3a 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -597,6 +597,10 @@ static int usb_audio_probe(struct usb_interface *intf,
 		}
 	}
 	if (! chip) {
+		err = snd_usb_apply_boot_quirk_once(dev, intf, quirk, id);
+		if (err < 0)
+			goto __error;
+
 		/* it's a fresh one.
 		 * now look for an empty slot and create a new card instance
 		 */
@@ -655,10 +659,14 @@ static int usb_audio_probe(struct usb_interface *intf,
 			goto __error;
 	}
 
-	/* we are allowed to call snd_card_register() many times */
-	err = snd_card_register(chip->card);
-	if (err < 0)
-		goto __error;
+	/* we are allowed to call snd_card_register() many times, but first
+	 * check to see if a device needs to skip it or do anything special
+	 */
+	if (!snd_usb_registration_quirk(chip, ifnum)) {
+		err = snd_card_register(chip->card);
+		if (err < 0)
+			goto __error;
+	}
 
 	if (quirk && quirk->shares_media_device) {
 		/* don't want to fail when snd_media_device_create() fails */
@@ -806,9 +814,6 @@ static int usb_audio_suspend(struct usb_interface *intf, pm_message_t message)
 	if (chip == (void *)-1L)
 		return 0;
 
-	chip->autosuspended = !!PMSG_IS_AUTO(message);
-	if (!chip->autosuspended)
-		snd_power_change_state(chip->card, SNDRV_CTL_POWER_D3hot);
 	if (!chip->num_suspended_intf++) {
 		list_for_each_entry(as, &chip->pcm_list, list) {
 			snd_usb_pcm_suspend(as);
@@ -821,6 +826,11 @@ static int usb_audio_suspend(struct usb_interface *intf, pm_message_t message)
 			snd_usb_mixer_suspend(mixer);
 	}
 
+	if (!PMSG_IS_AUTO(message) && !chip->system_suspend) {
+		snd_power_change_state(chip->card, SNDRV_CTL_POWER_D3hot);
+		chip->system_suspend = chip->num_suspended_intf;
+	}
+
 	return 0;
 }
 
@@ -834,10 +844,10 @@ static int __usb_audio_resume(struct usb_interface *intf, bool reset_resume)
 
 	if (chip == (void *)-1L)
 		return 0;
-	if (--chip->num_suspended_intf)
-		return 0;
 
 	atomic_inc(&chip->active); /* avoid autopm */
+	if (chip->num_suspended_intf > 1)
+		goto out;
 
 	list_for_each_entry(as, &chip->pcm_list, list) {
 		err = snd_usb_pcm_resume(as);
@@ -859,9 +869,12 @@ static int __usb_audio_resume(struct usb_interface *intf, bool reset_resume)
 		snd_usbmidi_resume(p);
 	}
 
-	if (!chip->autosuspended)
+ out:
+	if (chip->num_suspended_intf == chip->system_suspend) {
 		snd_power_change_state(chip->card, SNDRV_CTL_POWER_D0);
-	chip->autosuspended = 0;
+		chip->system_suspend = 0;
+	}
+	chip->num_suspended_intf--;
 
 err_out:
 	atomic_dec(&chip->active); /* allow autopm after this point */
diff --git a/sound/usb/card.h b/sound/usb/card.h
index 2991b9986f66..5351d7183b1b 100644
--- a/sound/usb/card.h
+++ b/sound/usb/card.h
@@ -84,6 +84,10 @@ struct snd_usb_endpoint {
 	dma_addr_t sync_dma;		/* DMA address of syncbuf */
 
 	unsigned int pipe;		/* the data i/o pipe */
+	unsigned int packsize[2];	/* small/large packet sizes in samples */
+	unsigned int sample_rem;	/* remainder from division fs/pps */
+	unsigned int sample_accum;	/* sample accumulator */
+	unsigned int pps;		/* packets per second */
 	unsigned int freqn;		/* nominal sampling rate in fs/fps in Q16.16 format */
 	unsigned int freqm;		/* momentary sampling rate in fs/fps in Q16.16 format */
 	int	   freqshift;		/* how much to shift the feedback value to get Q16.16 */
@@ -104,6 +108,7 @@ struct snd_usb_endpoint {
 	int iface, altsetting;
 	int skip_packets;		/* quirks for devices to ignore the first n packets
 					   in a stream */
+	bool is_implicit_feedback;      /* This endpoint is used as implicit feedback */
 
 	spinlock_t lock;
 	struct list_head list;
@@ -132,6 +137,7 @@ struct snd_usb_substream {
 	unsigned int tx_length_quirk:1;	/* add length specifier to transfers */
 	unsigned int fmt_type;		/* USB audio format type (1-3) */
 	unsigned int pkt_offset_adj;	/* Bytes to drop from beginning of packets (for non-compliant devices) */
+	unsigned int stream_offset_adj;	/* Bytes to drop from beginning of stream (for non-compliant devices) */
 
 	unsigned int running: 1;	/* running status */
 
@@ -145,6 +151,7 @@ struct snd_usb_substream {
 	struct snd_usb_endpoint *sync_endpoint;
 	unsigned long flags;
 	bool need_setup_ep;		/* (re)configure EP at prepare? */
+	bool need_setup_fmt;		/* (re)configure fmt after resume? */
 	unsigned int speed;		/* USB_SPEED_XXX */
 
 	u64 formats;			/* format bitmasks (all or'ed) */
diff --git a/sound/usb/clock.c b/sound/usb/clock.c
index 6b8c14f9b5d4..b118cf97607f 100644
--- a/sound/usb/clock.c
+++ b/sound/usb/clock.c
@@ -151,8 +151,71 @@ static int uac_clock_selector_set_val(struct snd_usb_audio *chip, int selector_i
 	return ret;
 }
 
+static bool uac_clock_source_is_valid_quirk(struct snd_usb_audio *chip,
+					    struct audioformat *fmt,
+					    int source_id)
+{
+	bool ret = false;
+	int count;
+	unsigned char data;
+	struct usb_device *dev = chip->dev;
+
+	if (fmt->protocol == UAC_VERSION_2) {
+		struct uac_clock_source_descriptor *cs_desc =
+			snd_usb_find_clock_source(chip->ctrl_intf, source_id);
+
+		if (!cs_desc)
+			return false;
+
+		/*
+		 * Assume the clock is valid if clock source supports only one
+		 * single sample rate, the terminal is connected directly to it
+		 * (there is no clock selector) and clock type is internal.
+		 * This is to deal with some Denon DJ controllers that always
+		 * reports that clock is invalid.
+		 */
+		if (fmt->nr_rates == 1 &&
+		    (fmt->clock & 0xff) == cs_desc->bClockID &&
+		    (cs_desc->bmAttributes & 0x3) !=
+				UAC_CLOCK_SOURCE_TYPE_EXT)
+			return true;
+	}
+
+	/*
+	 * MOTU MicroBook IIc
+	 * Sample rate changes takes more than 2 seconds for this device. Clock
+	 * validity request returns false during that period.
+	 */
+	if (chip->usb_id == USB_ID(0x07fd, 0x0004)) {
+		count = 0;
+
+		while ((!ret) && (count < 50)) {
+			int err;
+
+			msleep(100);
+
+			err = snd_usb_ctl_msg(dev, usb_rcvctrlpipe(dev, 0), UAC2_CS_CUR,
+					      USB_TYPE_CLASS | USB_RECIP_INTERFACE | USB_DIR_IN,
+					      UAC2_CS_CONTROL_CLOCK_VALID << 8,
+					      snd_usb_ctrl_intf(chip) | (source_id << 8),
+					      &data, sizeof(data));
+			if (err < 0) {
+				dev_warn(&dev->dev,
+					 "%s(): cannot get clock validity for id %d\n",
+					   __func__, source_id);
+				return false;
+			}
+
+			ret = !!data;
+			count++;
+		}
+	}
+
+	return ret;
+}
+
 static bool uac_clock_source_is_valid(struct snd_usb_audio *chip,
-				      int protocol,
+				      struct audioformat *fmt,
 				      int source_id)
 {
 	int err;
@@ -160,26 +223,26 @@ static bool uac_clock_source_is_valid(struct snd_usb_audio *chip,
 	struct usb_device *dev = chip->dev;
 	u32 bmControls;
 
-	if (protocol == UAC_VERSION_3) {
+	if (fmt->protocol == UAC_VERSION_3) {
 		struct uac3_clock_source_descriptor *cs_desc =
 			snd_usb_find_clock_source_v3(chip->ctrl_intf, source_id);
 
 		if (!cs_desc)
-			return 0;
+			return false;
 		bmControls = le32_to_cpu(cs_desc->bmControls);
 	} else { /* UAC_VERSION_1/2 */
 		struct uac_clock_source_descriptor *cs_desc =
 			snd_usb_find_clock_source(chip->ctrl_intf, source_id);
 
 		if (!cs_desc)
-			return 0;
+			return false;
 		bmControls = cs_desc->bmControls;
 	}
 
 	/* If a clock source can't tell us whether it's valid, we assume it is */
 	if (!uac_v2v3_control_is_readable(bmControls,
 				      UAC2_CS_CONTROL_CLOCK_VALID))
-		return 1;
+		return true;
 
 	err = snd_usb_ctl_msg(dev, usb_rcvctrlpipe(dev, 0), UAC2_CS_CUR,
 			      USB_TYPE_CLASS | USB_RECIP_INTERFACE | USB_DIR_IN,
@@ -191,13 +254,17 @@ static bool uac_clock_source_is_valid(struct snd_usb_audio *chip,
 		dev_warn(&dev->dev,
 			 "%s(): cannot get clock validity for id %d\n",
 			   __func__, source_id);
-		return 0;
+		return false;
 	}
 
-	return !!data;
+	if (data)
+		return true;
+	else
+		return uac_clock_source_is_valid_quirk(chip, fmt, source_id);
 }
 
-static int __uac_clock_find_source(struct snd_usb_audio *chip, int entity_id,
+static int __uac_clock_find_source(struct snd_usb_audio *chip,
+				   struct audioformat *fmt, int entity_id,
 				   unsigned long *visited, bool validate)
 {
 	struct uac_clock_source_descriptor *source;
@@ -217,7 +284,7 @@ static int __uac_clock_find_source(struct snd_usb_audio *chip, int entity_id,
 	source = snd_usb_find_clock_source(chip->ctrl_intf, entity_id);
 	if (source) {
 		entity_id = source->bClockID;
-		if (validate && !uac_clock_source_is_valid(chip, UAC_VERSION_2,
+		if (validate && !uac_clock_source_is_valid(chip, fmt,
 								entity_id)) {
 			usb_audio_err(chip,
 				"clock source %d is not valid, cannot use\n",
@@ -248,8 +315,9 @@ static int __uac_clock_find_source(struct snd_usb_audio *chip, int entity_id,
 		}
 
 		cur = ret;
-		ret = __uac_clock_find_source(chip, selector->baCSourceID[ret - 1],
-					       visited, validate);
+		ret = __uac_clock_find_source(chip, fmt,
+					      selector->baCSourceID[ret - 1],
+					      visited, validate);
 		if (!validate || ret > 0 || !chip->autoclock)
 			return ret;
 
@@ -260,8 +328,9 @@ static int __uac_clock_find_source(struct snd_usb_audio *chip, int entity_id,
 			if (i == cur)
 				continue;
 
-			ret = __uac_clock_find_source(chip, selector->baCSourceID[i - 1],
-				visited, true);
+			ret = __uac_clock_find_source(chip, fmt,
+						      selector->baCSourceID[i - 1],
+						      visited, true);
 			if (ret < 0)
 				continue;
 
@@ -281,14 +350,16 @@ static int __uac_clock_find_source(struct snd_usb_audio *chip, int entity_id,
 	/* FIXME: multipliers only act as pass-thru element for now */
 	multiplier = snd_usb_find_clock_multiplier(chip->ctrl_intf, entity_id);
 	if (multiplier)
-		return __uac_clock_find_source(chip, multiplier->bCSourceID,
-						visited, validate);
+		return __uac_clock_find_source(chip, fmt,
+					       multiplier->bCSourceID,
+					       visited, validate);
 
 	return -EINVAL;
 }
 
-static int __uac3_clock_find_source(struct snd_usb_audio *chip, int entity_id,
-				   unsigned long *visited, bool validate)
+static int __uac3_clock_find_source(struct snd_usb_audio *chip,
+				    struct audioformat *fmt, int entity_id,
+				    unsigned long *visited, bool validate)
 {
 	struct uac3_clock_source_descriptor *source;
 	struct uac3_clock_selector_descriptor *selector;
@@ -307,7 +378,7 @@ static int __uac3_clock_find_source(struct snd_usb_audio *chip, int entity_id,
 	source = snd_usb_find_clock_source_v3(chip->ctrl_intf, entity_id);
 	if (source) {
 		entity_id = source->bClockID;
-		if (validate && !uac_clock_source_is_valid(chip, UAC_VERSION_3,
+		if (validate && !uac_clock_source_is_valid(chip, fmt,
 								entity_id)) {
 			usb_audio_err(chip,
 				"clock source %d is not valid, cannot use\n",
@@ -338,7 +409,8 @@ static int __uac3_clock_find_source(struct snd_usb_audio *chip, int entity_id,
 		}
 
 		cur = ret;
-		ret = __uac3_clock_find_source(chip, selector->baCSourceID[ret - 1],
+		ret = __uac3_clock_find_source(chip, fmt,
+					       selector->baCSourceID[ret - 1],
 					       visited, validate);
 		if (!validate || ret > 0 || !chip->autoclock)
 			return ret;
@@ -350,8 +422,9 @@ static int __uac3_clock_find_source(struct snd_usb_audio *chip, int entity_id,
 			if (i == cur)
 				continue;
 
-			ret = __uac3_clock_find_source(chip, selector->baCSourceID[i - 1],
-				visited, true);
+			ret = __uac3_clock_find_source(chip, fmt,
+						       selector->baCSourceID[i - 1],
+						       visited, true);
 			if (ret < 0)
 				continue;
 
@@ -372,7 +445,8 @@ static int __uac3_clock_find_source(struct snd_usb_audio *chip, int entity_id,
 	multiplier = snd_usb_find_clock_multiplier_v3(chip->ctrl_intf,
 						      entity_id);
 	if (multiplier)
-		return __uac3_clock_find_source(chip, multiplier->bCSourceID,
+		return __uac3_clock_find_source(chip, fmt,
+						multiplier->bCSourceID,
 						visited, validate);
 
 	return -EINVAL;
@@ -389,18 +463,18 @@ static int __uac3_clock_find_source(struct snd_usb_audio *chip, int entity_id,
  *
  * Returns the clock source UnitID (>=0) on success, or an error.
  */
-int snd_usb_clock_find_source(struct snd_usb_audio *chip, int protocol,
-			      int entity_id, bool validate)
+int snd_usb_clock_find_source(struct snd_usb_audio *chip,
+			      struct audioformat *fmt, bool validate)
 {
 	DECLARE_BITMAP(visited, 256);
 	memset(visited, 0, sizeof(visited));
 
-	switch (protocol) {
+	switch (fmt->protocol) {
 	case UAC_VERSION_2:
-		return __uac_clock_find_source(chip, entity_id, visited,
+		return __uac_clock_find_source(chip, fmt, fmt->clock, visited,
 					       validate);
 	case UAC_VERSION_3:
-		return __uac3_clock_find_source(chip, entity_id, visited,
+		return __uac3_clock_find_source(chip, fmt, fmt->clock, visited,
 					       validate);
 	default:
 		return -EINVAL;
@@ -501,8 +575,7 @@ static int set_sample_rate_v2v3(struct snd_usb_audio *chip, int iface,
 	 * automatic clock selection if the current clock is not
 	 * valid.
 	 */
-	clock = snd_usb_clock_find_source(chip, fmt->protocol,
-					  fmt->clock, true);
+	clock = snd_usb_clock_find_source(chip, fmt, true);
 	if (clock < 0) {
 		/* We did not find a valid clock, but that might be
 		 * because the current sample rate does not match an
@@ -510,8 +583,7 @@ static int set_sample_rate_v2v3(struct snd_usb_audio *chip, int iface,
 		 * and we will do another validation after setting the
 		 * rate.
 		 */
-		clock = snd_usb_clock_find_source(chip, fmt->protocol,
-						  fmt->clock, false);
+		clock = snd_usb_clock_find_source(chip, fmt, false);
 		if (clock < 0)
 			return clock;
 	}
@@ -577,7 +649,7 @@ static int set_sample_rate_v2v3(struct snd_usb_audio *chip, int iface,
 
 validation:
 	/* validate clock after rate change */
-	if (!uac_clock_source_is_valid(chip, fmt->protocol, clock))
+	if (!uac_clock_source_is_valid(chip, fmt, clock))
 		return -ENXIO;
 	return 0;
 }
diff --git a/sound/usb/clock.h b/sound/usb/clock.h
index 076e31b79ee0..68df0fbe09d0 100644
--- a/sound/usb/clock.h
+++ b/sound/usb/clock.h
@@ -6,7 +6,7 @@ int snd_usb_init_sample_rate(struct snd_usb_audio *chip, int iface,
 			     struct usb_host_interface *alts,
 			     struct audioformat *fmt, int rate);
 
-int snd_usb_clock_find_source(struct snd_usb_audio *chip, int protocol,
-			     int entity_id, bool validate);
+int snd_usb_clock_find_source(struct snd_usb_audio *chip,
+			      struct audioformat *fmt, bool validate);
 
 #endif /* __USBAUDIO_CLOCK_H */
diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index 4a9a2f6ef5a4..88760268fb55 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -124,12 +124,12 @@ int snd_usb_endpoint_implicit_feedback_sink(struct snd_usb_endpoint *ep)
 
 /*
  * For streaming based on information derived from sync endpoints,
- * prepare_outbound_urb_sizes() will call next_packet_size() to
+ * prepare_outbound_urb_sizes() will call slave_next_packet_size() to
  * determine the number of samples to be sent in the next packet.
  *
- * For implicit feedback, next_packet_size() is unused.
+ * For implicit feedback, slave_next_packet_size() is unused.
  */
-int snd_usb_endpoint_next_packet_size(struct snd_usb_endpoint *ep)
+int snd_usb_endpoint_slave_next_packet_size(struct snd_usb_endpoint *ep)
 {
 	unsigned long flags;
 	int ret;
@@ -146,6 +146,29 @@ int snd_usb_endpoint_next_packet_size(struct snd_usb_endpoint *ep)
 	return ret;
 }
 
+/*
+ * For adaptive and synchronous endpoints, prepare_outbound_urb_sizes()
+ * will call next_packet_size() to determine the number of samples to be
+ * sent in the next packet.
+ */
+int snd_usb_endpoint_next_packet_size(struct snd_usb_endpoint *ep)
+{
+	int ret;
+
+	if (ep->fill_max)
+		return ep->maxframesize;
+
+	ep->sample_accum += ep->sample_rem;
+	if (ep->sample_accum >= ep->pps) {
+		ep->sample_accum -= ep->pps;
+		ret = ep->packsize[1];
+	} else {
+		ret = ep->packsize[0];
+	}
+
+	return ret;
+}
+
 static void retire_outbound_urb(struct snd_usb_endpoint *ep,
 				struct snd_urb_ctx *urb_ctx)
 {
@@ -190,6 +213,8 @@ static void prepare_silent_urb(struct snd_usb_endpoint *ep,
 
 		if (ctx->packet_size[i])
 			counts = ctx->packet_size[i];
+		else if (ep->sync_master)
+			counts = snd_usb_endpoint_slave_next_packet_size(ep);
 		else
 			counts = snd_usb_endpoint_next_packet_size(ep);
 
@@ -321,17 +346,17 @@ static void queue_pending_output_urbs(struct snd_usb_endpoint *ep)
 			ep->next_packet_read_pos %= MAX_URBS;
 
 			/* take URB out of FIFO */
-			if (!list_empty(&ep->ready_playback_urbs))
+			if (!list_empty(&ep->ready_playback_urbs)) {
 				ctx = list_first_entry(&ep->ready_playback_urbs,
 					       struct snd_urb_ctx, ready_list);
+				list_del_init(&ctx->ready_list);
+			}
 		}
 		spin_unlock_irqrestore(&ep->lock, flags);
 
 		if (ctx == NULL)
 			return;
 
-		list_del_init(&ctx->ready_list);
-
 		/* copy over the length information */
 		for (i = 0; i < packet->packets; i++)
 			ctx->packet_size[i] = packet->packet_size[i];
@@ -497,6 +522,8 @@ struct snd_usb_endpoint *snd_usb_add_endpoint(struct snd_usb_audio *chip,
 
 	list_add_tail(&ep->list, &chip->ep_list);
 
+	ep->is_implicit_feedback = 0;
+
 __exit_unlock:
 	mutex_unlock(&chip->mutex);
 
@@ -597,6 +624,178 @@ static void release_urbs(struct snd_usb_endpoint *ep, int force)
 }
 
 /*
+ * Check data endpoint for format differences
+ */
+static bool check_ep_params(struct snd_usb_endpoint *ep,
+			      snd_pcm_format_t pcm_format,
+			      unsigned int channels,
+			      unsigned int period_bytes,
+			      unsigned int frames_per_period,
+			      unsigned int periods_per_buffer,
+			      struct audioformat *fmt,
+			      struct snd_usb_endpoint *sync_ep)
+{
+	unsigned int maxsize, minsize, packs_per_ms, max_packs_per_urb;
+	unsigned int max_packs_per_period, urbs_per_period, urb_packs;
+	unsigned int max_urbs;
+	int frame_bits = snd_pcm_format_physical_width(pcm_format) * channels;
+	int tx_length_quirk = (ep->chip->tx_length_quirk &&
+			       usb_pipeout(ep->pipe));
+	bool ret = 1;
+
+	if (pcm_format == SNDRV_PCM_FORMAT_DSD_U16_LE && fmt->dsd_dop) {
+		/*
+		 * When operating in DSD DOP mode, the size of a sample frame
+		 * in hardware differs from the actual physical format width
+		 * because we need to make room for the DOP markers.
+		 */
+		frame_bits += channels << 3;
+	}
+
+	ret = ret && (ep->datainterval == fmt->datainterval);
+	ret = ret && (ep->stride == frame_bits >> 3);
+
+	switch (pcm_format) {
+	case SNDRV_PCM_FORMAT_U8:
+		ret = ret && (ep->silence_value == 0x80);
+		break;
+	case SNDRV_PCM_FORMAT_DSD_U8:
+	case SNDRV_PCM_FORMAT_DSD_U16_LE:
+	case SNDRV_PCM_FORMAT_DSD_U32_LE:
+	case SNDRV_PCM_FORMAT_DSD_U16_BE:
+	case SNDRV_PCM_FORMAT_DSD_U32_BE:
+		ret = ret && (ep->silence_value == 0x69);
+		break;
+	default:
+		ret = ret && (ep->silence_value == 0);
+	}
+
+	/* assume max. frequency is 50% higher than nominal */
+	ret = ret && (ep->freqmax == ep->freqn + (ep->freqn >> 1));
+	/* Round up freqmax to nearest integer in order to calculate maximum
+	 * packet size, which must represent a whole number of frames.
+	 * This is accomplished by adding 0x0.ffff before converting the
+	 * Q16.16 format into integer.
+	 * In order to accurately calculate the maximum packet size when
+	 * the data interval is more than 1 (i.e. ep->datainterval > 0),
+	 * multiply by the data interval prior to rounding. For instance,
+	 * a freqmax of 41 kHz will result in a max packet size of 6 (5.125)
+	 * frames with a data interval of 1, but 11 (10.25) frames with a
+	 * data interval of 2.
+	 * (ep->freqmax << ep->datainterval overflows at 8.192 MHz for the
+	 * maximum datainterval value of 3, at USB full speed, higher for
+	 * USB high speed, noting that ep->freqmax is in units of
+	 * frames per packet in Q16.16 format.)
+	 */
+	maxsize = (((ep->freqmax << ep->datainterval) + 0xffff) >> 16) *
+			 (frame_bits >> 3);
+	if (tx_length_quirk)
+		maxsize += sizeof(__le32); /* Space for length descriptor */
+	/* but wMaxPacketSize might reduce this */
+	if (ep->maxpacksize && ep->maxpacksize < maxsize) {
+		/* whatever fits into a max. size packet */
+		unsigned int data_maxsize = maxsize = ep->maxpacksize;
+
+		if (tx_length_quirk)
+			/* Need to remove the length descriptor to calc freq */
+			data_maxsize -= sizeof(__le32);
+		ret = ret && (ep->freqmax == (data_maxsize / (frame_bits >> 3))
+				<< (16 - ep->datainterval));
+	}
+
+	if (ep->fill_max)
+		ret = ret && (ep->curpacksize == ep->maxpacksize);
+	else
+		ret = ret && (ep->curpacksize == maxsize);
+
+	if (snd_usb_get_speed(ep->chip->dev) != USB_SPEED_FULL) {
+		packs_per_ms = 8 >> ep->datainterval;
+		max_packs_per_urb = MAX_PACKS_HS;
+	} else {
+		packs_per_ms = 1;
+		max_packs_per_urb = MAX_PACKS;
+	}
+	if (sync_ep && !snd_usb_endpoint_implicit_feedback_sink(ep))
+		max_packs_per_urb = min(max_packs_per_urb,
+					1U << sync_ep->syncinterval);
+	max_packs_per_urb = max(1u, max_packs_per_urb >> ep->datainterval);
+
+	/*
+	 * Capture endpoints need to use small URBs because there's no way
+	 * to tell in advance where the next period will end, and we don't
+	 * want the next URB to complete much after the period ends.
+	 *
+	 * Playback endpoints with implicit sync much use the same parameters
+	 * as their corresponding capture endpoint.
+	 */
+	if (usb_pipein(ep->pipe) ||
+			snd_usb_endpoint_implicit_feedback_sink(ep)) {
+
+		urb_packs = packs_per_ms;
+		/*
+		 * Wireless devices can poll at a max rate of once per 4ms.
+		 * For dataintervals less than 5, increase the packet count to
+		 * allow the host controller to use bursting to fill in the
+		 * gaps.
+		 */
+		if (snd_usb_get_speed(ep->chip->dev) == USB_SPEED_WIRELESS) {
+			int interval = ep->datainterval;
+
+			while (interval < 5) {
+				urb_packs <<= 1;
+				++interval;
+			}
+		}
+		/* make capture URBs <= 1 ms and smaller than a period */
+		urb_packs = min(max_packs_per_urb, urb_packs);
+		while (urb_packs > 1 && urb_packs * maxsize >= period_bytes)
+			urb_packs >>= 1;
+		ret = ret && (ep->nurbs == MAX_URBS);
+
+	/*
+	 * Playback endpoints without implicit sync are adjusted so that
+	 * a period fits as evenly as possible in the smallest number of
+	 * URBs.  The total number of URBs is adjusted to the size of the
+	 * ALSA buffer, subject to the MAX_URBS and MAX_QUEUE limits.
+	 */
+	} else {
+		/* determine how small a packet can be */
+		minsize = (ep->freqn >> (16 - ep->datainterval)) *
+				(frame_bits >> 3);
+		/* with sync from device, assume it can be 12% lower */
+		if (sync_ep)
+			minsize -= minsize >> 3;
+		minsize = max(minsize, 1u);
+
+		/* how many packets will contain an entire ALSA period? */
+		max_packs_per_period = DIV_ROUND_UP(period_bytes, minsize);
+
+		/* how many URBs will contain a period? */
+		urbs_per_period = DIV_ROUND_UP(max_packs_per_period,
+				max_packs_per_urb);
+		/* how many packets are needed in each URB? */
+		urb_packs = DIV_ROUND_UP(max_packs_per_period, urbs_per_period);
+
+		/* limit the number of frames in a single URB */
+		ret = ret && (ep->max_urb_frames ==
+			DIV_ROUND_UP(frames_per_period, urbs_per_period));
+
+		/* try to use enough URBs to contain an entire ALSA buffer */
+		max_urbs = min((unsigned) MAX_URBS,
+				MAX_QUEUE * packs_per_ms / urb_packs);
+		ret = ret && (ep->nurbs == min(max_urbs,
+				urbs_per_period * periods_per_buffer));
+	}
+
+	ret = ret && (ep->datainterval == fmt->datainterval);
+	ret = ret && (ep->maxpacksize == fmt->maxpacksize);
+	ret = ret &&
+		(ep->fill_max == !!(fmt->attributes & UAC_EP_CS_ATTR_FILL_MAX));
+
+	return ret;
+}
+
+/*
  * configure a data endpoint
  */
 static int data_ep_set_params(struct snd_usb_endpoint *ep,
@@ -861,10 +1060,23 @@ int snd_usb_endpoint_set_params(struct snd_usb_endpoint *ep,
 	int err;
 
 	if (ep->use_count != 0) {
-		usb_audio_warn(ep->chip,
-			 "Unable to change format on ep #%x: already in use\n",
-			 ep->ep_num);
-		return -EBUSY;
+		bool check = ep->is_implicit_feedback &&
+			check_ep_params(ep, pcm_format,
+					     channels, period_bytes,
+					     period_frames, buffer_periods,
+					     fmt, sync_ep);
+
+		if (!check) {
+			usb_audio_warn(ep->chip,
+				"Unable to change format on ep #%x: already in use\n",
+				ep->ep_num);
+			return -EBUSY;
+		}
+
+		usb_audio_dbg(ep->chip,
+			      "Ep #%x already in use as implicit feedback but format not changed\n",
+			      ep->ep_num);
+		return 0;
 	}
 
 	/* release old buffers, if any */
@@ -874,10 +1086,17 @@ int snd_usb_endpoint_set_params(struct snd_usb_endpoint *ep,
 	ep->maxpacksize = fmt->maxpacksize;
 	ep->fill_max = !!(fmt->attributes & UAC_EP_CS_ATTR_FILL_MAX);
 
-	if (snd_usb_get_speed(ep->chip->dev) == USB_SPEED_FULL)
+	if (snd_usb_get_speed(ep->chip->dev) == USB_SPEED_FULL) {
 		ep->freqn = get_usb_full_speed_rate(rate);
-	else
+		ep->pps = 1000 >> ep->datainterval;
+	} else {
 		ep->freqn = get_usb_high_speed_rate(rate);
+		ep->pps = 8000 >> ep->datainterval;
+	}
+
+	ep->sample_rem = rate % ep->pps;
+	ep->packsize[0] = rate / ep->pps;
+	ep->packsize[1] = (rate + (ep->pps - 1)) / ep->pps;
 
 	/* calculate the frequency in 16.16 format */
 	ep->freqm = ep->freqn;
@@ -936,6 +1155,7 @@ int snd_usb_endpoint_start(struct snd_usb_endpoint *ep)
 	ep->active_mask = 0;
 	ep->unlink_mask = 0;
 	ep->phase = 0;
+	ep->sample_accum = 0;
 
 	snd_usb_endpoint_start_quirk(ep);
 
diff --git a/sound/usb/endpoint.h b/sound/usb/endpoint.h
index 63a39d4fa8d8..d23fa0a8c11b 100644
--- a/sound/usb/endpoint.h
+++ b/sound/usb/endpoint.h
@@ -28,6 +28,7 @@ void snd_usb_endpoint_release(struct snd_usb_endpoint *ep);
 void snd_usb_endpoint_free(struct snd_usb_endpoint *ep);
 
 int snd_usb_endpoint_implicit_feedback_sink(struct snd_usb_endpoint *ep);
+int snd_usb_endpoint_slave_next_packet_size(struct snd_usb_endpoint *ep);
 int snd_usb_endpoint_next_packet_size(struct snd_usb_endpoint *ep);
 
 void snd_usb_handle_sync_urb(struct snd_usb_endpoint *ep,
diff --git a/sound/usb/format.c b/sound/usb/format.c
index c02b51a82775..f4f0cf3deaf0 100644
--- a/sound/usb/format.c
+++ b/sound/usb/format.c
@@ -285,6 +285,36 @@ static int parse_uac2_sample_rate_range(struct snd_usb_audio *chip,
 	return nr_rates;
 }
 
+/* Line6 Helix series don't support the UAC2_CS_RANGE usb function
+ * call. Return a static table of known clock rates.
+ */
+static int line6_parse_audio_format_rates_quirk(struct snd_usb_audio *chip,
+						struct audioformat *fp)
+{
+	switch (chip->usb_id) {
+	case USB_ID(0x0E41, 0x4241): /* Line6 Helix */
+	case USB_ID(0x0E41, 0x4242): /* Line6 Helix Rack */
+	case USB_ID(0x0E41, 0x4244): /* Line6 Helix LT */
+	case USB_ID(0x0E41, 0x4246): /* Line6 HX-Stomp */
+	case USB_ID(0x0E41, 0x4248): /* Line6 Helix >= fw 2.82 */
+	case USB_ID(0x0E41, 0x4249): /* Line6 Helix Rack >= fw 2.82 */
+	case USB_ID(0x0E41, 0x424a): /* Line6 Helix LT >= fw 2.82 */
+		/* supported rates: 48Khz */
+		kfree(fp->rate_table);
+		fp->rate_table = kmalloc(sizeof(int), GFP_KERNEL);
+		if (!fp->rate_table)
+			return -ENOMEM;
+		fp->nr_rates = 1;
+		fp->rate_min = 48000;
+		fp->rate_max = 48000;
+		fp->rates = SNDRV_PCM_RATE_48000;
+		fp->rate_table[0] = 48000;
+		return 0;
+	}
+
+	return -ENODEV;
+}
+
 /*
  * parse the format descriptor and stores the possible sample rates
  * on the audioformat table (audio class v2 and v3).
@@ -294,9 +324,8 @@ static int parse_audio_format_rates_v2v3(struct snd_usb_audio *chip,
 {
 	struct usb_device *dev = chip->dev;
 	unsigned char tmp[2], *data;
-	int nr_triplets, data_size, ret = 0;
-	int clock = snd_usb_clock_find_source(chip, fp->protocol,
-					      fp->clock, false);
+	int nr_triplets, data_size, ret = 0, ret_l6;
+	int clock = snd_usb_clock_find_source(chip, fp, false);
 
 	if (clock < 0) {
 		dev_err(&dev->dev,
@@ -313,9 +342,22 @@ static int parse_audio_format_rates_v2v3(struct snd_usb_audio *chip,
 			      tmp, sizeof(tmp));
 
 	if (ret < 0) {
-		dev_err(&dev->dev,
-			"%s(): unable to retrieve number of sample rates (clock %d)\n",
+		/* line6 helix devices don't support UAC2_CS_CONTROL_SAM_FREQ call */
+		ret_l6 = line6_parse_audio_format_rates_quirk(chip, fp);
+		if (ret_l6 == -ENODEV) {
+			/* no line6 device found continue showing the error */
+			dev_err(&dev->dev,
+				"%s(): unable to retrieve number of sample rates (clock %d)\n",
+				__func__, clock);
+			goto err;
+		}
+		if (ret_l6 == 0) {
+			dev_info(&dev->dev,
+				"%s(): unable to retrieve number of sample rates: set it to a predefined value (clock %d).\n",
 				__func__, clock);
+			return 0;
+		}
+		ret = ret_l6;
 		goto err;
 	}
 
diff --git a/sound/usb/line6/capture.c b/sound/usb/line6/capture.c
index 82abef3fe90d..4b6e99e055dc 100644
--- a/sound/usb/line6/capture.c
+++ b/sound/usb/line6/capture.c
@@ -287,6 +287,8 @@ int line6_create_audio_in_urbs(struct snd_line6_pcm *line6pcm)
 		urb->interval = LINE6_ISO_INTERVAL;
 		urb->error_count = 0;
 		urb->complete = audio_in_callback;
+		if (usb_urb_ep_type_check(urb))
+			return -EINVAL;
 	}
 
 	return 0;
diff --git a/sound/usb/line6/driver.c b/sound/usb/line6/driver.c
index e63a2451c88f..9eac35587f9d 100644
--- a/sound/usb/line6/driver.c
+++ b/sound/usb/line6/driver.c
@@ -316,7 +316,7 @@ static void line6_data_received(struct urb *urb)
 				line6_midibuf_read(mb, line6->buffer_message,
 						LINE6_MIDI_MESSAGE_MAXLEN);
 
-			if (done == 0)
+			if (done <= 0)
 				break;
 
 			line6->message_length = done;
@@ -831,7 +831,7 @@ void line6_disconnect(struct usb_interface *interface)
 	if (WARN_ON(usbdev != line6->usbdev))
 		return;
 
-	cancel_delayed_work(&line6->startup_work);
+	cancel_delayed_work_sync(&line6->startup_work);
 
 	if (line6->urb_listen != NULL)
 		line6_stop_listen(line6);
diff --git a/sound/usb/line6/midibuf.c b/sound/usb/line6/midibuf.c
index 8d6eefa0d936..6a70463f82c4 100644
--- a/sound/usb/line6/midibuf.c
+++ b/sound/usb/line6/midibuf.c
@@ -159,7 +159,7 @@ int line6_midibuf_read(struct midi_buffer *this, unsigned char *data,
 			int midi_length_prev =
 			    midibuf_message_length(this->command_prev);
 
-			if (midi_length_prev > 0) {
+			if (midi_length_prev > 1) {
 				midi_length = midi_length_prev - 1;
 				repeat = 1;
 			} else
diff --git a/sound/usb/line6/playback.c b/sound/usb/line6/playback.c
index 2e8ead3f9bc2..797ced329b79 100644
--- a/sound/usb/line6/playback.c
+++ b/sound/usb/line6/playback.c
@@ -432,6 +432,8 @@ int line6_create_audio_out_urbs(struct snd_line6_pcm *line6pcm)
 		urb->interval = LINE6_ISO_INTERVAL;
 		urb->error_count = 0;
 		urb->complete = audio_out_callback;
+		if (usb_urb_ep_type_check(urb))
+			return -EINVAL;
 	}
 
 	return 0;
diff --git a/sound/usb/line6/podhd.c b/sound/usb/line6/podhd.c
index 53b53a9a4c6f..db2395a95e3f 100644
--- a/sound/usb/line6/podhd.c
+++ b/sound/usb/line6/podhd.c
@@ -31,8 +31,7 @@ enum {
 enum {
 	LINE6_PODHD300,
 	LINE6_PODHD400,
-	LINE6_PODHD500_0,
-	LINE6_PODHD500_1,
+	LINE6_PODHD500,
 	LINE6_PODX3,
 	LINE6_PODX3LIVE,
 	LINE6_PODHD500X,
@@ -374,8 +373,7 @@ static const struct usb_device_id podhd_id_table[] = {
 	/* TODO: no need to alloc data interfaces when only audio is used */
 	{ LINE6_DEVICE(0x5057),    .driver_info = LINE6_PODHD300 },
 	{ LINE6_DEVICE(0x5058),    .driver_info = LINE6_PODHD400 },
-	{ LINE6_IF_NUM(0x414D, 0), .driver_info = LINE6_PODHD500_0 },
-	{ LINE6_IF_NUM(0x414D, 1), .driver_info = LINE6_PODHD500_1 },
+	{ LINE6_IF_NUM(0x414D, 0), .driver_info = LINE6_PODHD500 },
 	{ LINE6_IF_NUM(0x414A, 0), .driver_info = LINE6_PODX3 },
 	{ LINE6_IF_NUM(0x414B, 0), .driver_info = LINE6_PODX3LIVE },
 	{ LINE6_IF_NUM(0x4159, 0), .driver_info = LINE6_PODHD500X },
@@ -408,23 +406,13 @@ static const struct line6_properties podhd_properties_table[] = {
 		.ep_audio_r = 0x82,
 		.ep_audio_w = 0x01,
 	},
-	[LINE6_PODHD500_0] = {
+	[LINE6_PODHD500] = {
 		.id = "PODHD500",
 		.name = "POD HD500",
-		.capabilities	= LINE6_CAP_PCM
-				| LINE6_CAP_HWMON,
-		.altsetting = 0,
-		.ep_ctrl_r = 0x81,
-		.ep_ctrl_w = 0x01,
-		.ep_audio_r = 0x86,
-		.ep_audio_w = 0x02,
-	},
-	[LINE6_PODHD500_1] = {
-		.id = "PODHD500",
-		.name = "POD HD500",
-		.capabilities	= LINE6_CAP_PCM
+		.capabilities	= LINE6_CAP_PCM | LINE6_CAP_CONTROL
 				| LINE6_CAP_HWMON,
 		.altsetting = 1,
+		.ctrl_if = 1,
 		.ep_ctrl_r = 0x81,
 		.ep_ctrl_w = 0x01,
 		.ep_audio_r = 0x86,
diff --git a/sound/usb/midi.c b/sound/usb/midi.c
index b737f0ec77d0..0cb4142b05f6 100644
--- a/sound/usb/midi.c
+++ b/sound/usb/midi.c
@@ -1499,6 +1499,8 @@ void snd_usbmidi_disconnect(struct list_head *p)
 	spin_unlock_irq(&umidi->disc_lock);
 	up_write(&umidi->disc_rwsem);
 
+	del_timer_sync(&umidi->error_timer);
+
 	for (i = 0; i < MIDI_MAX_ENDPOINTS; ++i) {
 		struct snd_usb_midi_endpoint *ep = &umidi->endpoints[i];
 		if (ep->out)
@@ -1525,7 +1527,6 @@ void snd_usbmidi_disconnect(struct list_head *p)
 			ep->in = NULL;
 		}
 	}
-	del_timer_sync(&umidi->error_timer);
 }
 EXPORT_SYMBOL(snd_usbmidi_disconnect);
 
@@ -2282,16 +2283,22 @@ void snd_usbmidi_input_stop(struct list_head *p)
 }
 EXPORT_SYMBOL(snd_usbmidi_input_stop);
 
-static void snd_usbmidi_input_start_ep(struct snd_usb_midi_in_endpoint *ep)
+static void snd_usbmidi_input_start_ep(struct snd_usb_midi *umidi,
+				       struct snd_usb_midi_in_endpoint *ep)
 {
 	unsigned int i;
+	unsigned long flags;
 
 	if (!ep)
 		return;
 	for (i = 0; i < INPUT_URBS; ++i) {
 		struct urb *urb = ep->urbs[i];
-		urb->dev = ep->umidi->dev;
-		snd_usbmidi_submit_urb(urb, GFP_KERNEL);
+		spin_lock_irqsave(&umidi->disc_lock, flags);
+		if (!atomic_read(&urb->use_count)) {
+			urb->dev = ep->umidi->dev;
+			snd_usbmidi_submit_urb(urb, GFP_ATOMIC);
+		}
+		spin_unlock_irqrestore(&umidi->disc_lock, flags);
 	}
 }
 
@@ -2307,7 +2314,7 @@ void snd_usbmidi_input_start(struct list_head *p)
 	if (umidi->input_running || !umidi->opened[1])
 		return;
 	for (i = 0; i < MIDI_MAX_ENDPOINTS; ++i)
-		snd_usbmidi_input_start_ep(umidi->endpoints[i].in);
+		snd_usbmidi_input_start_ep(umidi, umidi->endpoints[i].in);
 	umidi->input_running = 1;
 }
 EXPORT_SYMBOL(snd_usbmidi_input_start);
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index bd1cffb2ab50..ff8d29bf601f 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -576,8 +576,9 @@ static int check_matrix_bitmap(unsigned char *bmap,
  * if failed, give up and free the control instance.
  */
 
-int snd_usb_mixer_add_control(struct usb_mixer_elem_list *list,
-			      struct snd_kcontrol *kctl)
+int snd_usb_mixer_add_list(struct usb_mixer_elem_list *list,
+			   struct snd_kcontrol *kctl,
+			   bool is_std_info)
 {
 	struct usb_mixer_interface *mixer = list->mixer;
 	int err;
@@ -591,6 +592,7 @@ int snd_usb_mixer_add_control(struct usb_mixer_elem_list *list,
 		return err;
 	}
 	list->kctl = kctl;
+	list->is_std_info = is_std_info;
 	list->next_id_elem = mixer->id_elems[list->id];
 	mixer->id_elems[list->id] = list;
 	return 0;
@@ -897,6 +899,15 @@ static int parse_term_proc_unit(struct mixer_build *state,
 	return 0;
 }
 
+static int parse_term_effect_unit(struct mixer_build *state,
+				  struct usb_audio_term *term,
+				  void *p1, int id)
+{
+	term->type = UAC3_EFFECT_UNIT << 16; /* virtual type */
+	term->id = id;
+	return 0;
+}
+
 static int parse_term_uac2_clock_source(struct mixer_build *state,
 					struct usb_audio_term *term,
 					void *p1, int id)
@@ -981,8 +992,7 @@ static int __check_input_term(struct mixer_build *state, int id,
 						    UAC3_PROCESSING_UNIT);
 		case PTYPE(UAC_VERSION_2, UAC2_EFFECT_UNIT):
 		case PTYPE(UAC_VERSION_3, UAC3_EFFECT_UNIT):
-			return parse_term_proc_unit(state, term, p1, id,
-						    UAC3_EFFECT_UNIT);
+			return parse_term_effect_unit(state, term, p1, id);
 		case PTYPE(UAC_VERSION_1, UAC1_EXTENSION_UNIT):
 		case PTYPE(UAC_VERSION_2, UAC2_EXTENSION_UNIT_V2):
 		case PTYPE(UAC_VERSION_3, UAC3_EXTENSION_UNIT):
@@ -1163,6 +1173,14 @@ static void volume_control_quirks(struct usb_mixer_elem_info *cval,
 			cval->res = 384;
 		}
 		break;
+	case USB_ID(0x0495, 0x3042): /* ESS Technology Asus USB DAC */
+		if ((strstr(kctl->id.name, "Playback Volume") != NULL) ||
+			strstr(kctl->id.name, "Capture Volume") != NULL) {
+			cval->min >>= 8;
+			cval->max = 0;
+			cval->res = 1;
+		}
+		break;
 	}
 }
 
@@ -1438,7 +1456,7 @@ error:
 		usb_audio_err(chip,
 			"cannot get connectors status: req = %#x, wValue = %#x, wIndex = %#x, type = %d\n",
 			UAC_GET_CUR, validx, idx, cval->val_type);
-		return ret;
+		return filter_error(cval, ret);
 	}
 
 	ucontrol->value.integer.value[0] = val;
@@ -1742,10 +1760,16 @@ static void get_connector_control_name(struct usb_mixer_interface *mixer,
 
 /* Build a mixer control for a UAC connector control (jack-detect) */
 static void build_connector_control(struct usb_mixer_interface *mixer,
+				    const struct usbmix_name_map *imap,
 				    struct usb_audio_term *term, bool is_input)
 {
 	struct snd_kcontrol *kctl;
 	struct usb_mixer_elem_info *cval;
+	const struct usbmix_name_map *map;
+
+	map = find_map(imap, term->id, 0);
+	if (check_ignored_ctl(map))
+		return;
 
 	cval = kzalloc(sizeof(*cval), GFP_KERNEL);
 	if (!cval)
@@ -1776,8 +1800,12 @@ static void build_connector_control(struct usb_mixer_interface *mixer,
 		usb_mixer_elem_info_free(cval);
 		return;
 	}
-	get_connector_control_name(mixer, term, is_input, kctl->id.name,
-				   sizeof(kctl->id.name));
+
+	if (check_mapped_name(map, kctl->id.name, sizeof(kctl->id.name)))
+		strlcat(kctl->id.name, " Jack", sizeof(kctl->id.name));
+	else
+		get_connector_control_name(mixer, term, is_input, kctl->id.name,
+					   sizeof(kctl->id.name));
 	kctl->private_free = snd_usb_mixer_elem_free;
 	snd_usb_mixer_add_control(&cval->head, kctl);
 }
@@ -2080,8 +2108,9 @@ static int parse_audio_input_terminal(struct mixer_build *state, int unitid,
 	check_input_term(state, term_id, &iterm);
 
 	/* Check for jack detection. */
-	if (uac_v2v3_control_is_readable(bmctls, control))
-		build_connector_control(state->mixer, &iterm, true);
+	if ((iterm.type & 0xff00) != 0x0100 &&
+	    uac_v2v3_control_is_readable(bmctls, control))
+		build_connector_control(state->mixer, state->map, &iterm, true);
 
 	return 0;
 }
@@ -3042,13 +3071,13 @@ static int snd_usb_mixer_controls_badd(struct usb_mixer_interface *mixer,
 		memset(&iterm, 0, sizeof(iterm));
 		iterm.id = UAC3_BADD_IT_ID4;
 		iterm.type = UAC_BIDIR_TERMINAL_HEADSET;
-		build_connector_control(mixer, &iterm, true);
+		build_connector_control(mixer, map->map, &iterm, true);
 
 		/* Output Term - Insertion control */
 		memset(&oterm, 0, sizeof(oterm));
 		oterm.id = UAC3_BADD_OT_ID3;
 		oterm.type = UAC_BIDIR_TERMINAL_HEADSET;
-		build_connector_control(mixer, &oterm, false);
+		build_connector_control(mixer, map->map, &oterm, false);
 	}
 
 	return 0;
@@ -3077,7 +3106,8 @@ static int snd_usb_mixer_controls(struct usb_mixer_interface *mixer)
 		if (map->id == state.chip->usb_id) {
 			state.map = map->map;
 			state.selector_map = map->selector_map;
-			mixer->ignore_ctl_error = map->ignore_ctl_error;
+			mixer->connector_map = map->connector_map;
+			mixer->ignore_ctl_error |= map->ignore_ctl_error;
 			break;
 		}
 	}
@@ -3120,10 +3150,11 @@ static int snd_usb_mixer_controls(struct usb_mixer_interface *mixer)
 			if (err < 0 && err != -EINVAL)
 				return err;
 
-			if (uac_v2v3_control_is_readable(le16_to_cpu(desc->bmControls),
+			if ((state.oterm.type & 0xff00) != 0x0100 &&
+			    uac_v2v3_control_is_readable(le16_to_cpu(desc->bmControls),
 							 UAC2_TE_CONNECTOR)) {
-				build_connector_control(state.mixer, &state.oterm,
-							false);
+				build_connector_control(state.mixer, state.map,
+							&state.oterm, false);
 			}
 		} else {  /* UAC_VERSION_3 */
 			struct uac3_output_terminal_descriptor *desc = p;
@@ -3145,10 +3176,11 @@ static int snd_usb_mixer_controls(struct usb_mixer_interface *mixer)
 			if (err < 0 && err != -EINVAL)
 				return err;
 
-			if (uac_v2v3_control_is_readable(le32_to_cpu(desc->bmControls),
+			if ((state.oterm.type & 0xff00) != 0x0100 &&
+			    uac_v2v3_control_is_readable(le32_to_cpu(desc->bmControls),
 							 UAC3_TE_INSERTION)) {
-				build_connector_control(state.mixer, &state.oterm,
-							false);
+				build_connector_control(state.mixer, state.map,
+							&state.oterm, false);
 			}
 		}
 	}
@@ -3156,13 +3188,38 @@ static int snd_usb_mixer_controls(struct usb_mixer_interface *mixer)
 	return 0;
 }
 
+static int delegate_notify(struct usb_mixer_interface *mixer, int unitid,
+			   u8 *control, u8 *channel)
+{
+	const struct usbmix_connector_map *map = mixer->connector_map;
+
+	if (!map)
+		return unitid;
+
+	for (; map->id; map++) {
+		if (map->id == unitid) {
+			if (control && map->control)
+				*control = map->control;
+			if (channel && map->channel)
+				*channel = map->channel;
+			return map->delegated_id;
+		}
+	}
+	return unitid;
+}
+
 void snd_usb_mixer_notify_id(struct usb_mixer_interface *mixer, int unitid)
 {
 	struct usb_mixer_elem_list *list;
 
+	unitid = delegate_notify(mixer, unitid, NULL, NULL);
+
 	for_each_mixer_elem(list, mixer, unitid) {
-		struct usb_mixer_elem_info *info =
-			mixer_elem_list_to_info(list);
+		struct usb_mixer_elem_info *info;
+
+		if (!list->is_std_info)
+			continue;
+		info = mixer_elem_list_to_info(list);
 		/* invalidate cache, so the value is read from the device */
 		info->cached = 0;
 		snd_ctl_notify(mixer->chip->card, SNDRV_CTL_EVENT_MASK_VALUE,
@@ -3229,6 +3286,8 @@ static void snd_usb_mixer_interrupt_v2(struct usb_mixer_interface *mixer,
 		return;
 	}
 
+	unitid = delegate_notify(mixer, unitid, &control, &channel);
+
 	for_each_mixer_elem(list, mixer, unitid)
 		count++;
 
@@ -3240,6 +3299,8 @@ static void snd_usb_mixer_interrupt_v2(struct usb_mixer_interface *mixer,
 
 		if (!list->kctl)
 			continue;
+		if (!list->is_std_info)
+			continue;
 
 		info = mixer_elem_list_to_info(list);
 		if (count > 1 && info->control != control)
diff --git a/sound/usb/mixer.h b/sound/usb/mixer.h
index 394cd9107507..2d494d1646b6 100644
--- a/sound/usb/mixer.h
+++ b/sound/usb/mixer.h
@@ -6,6 +6,13 @@
 
 struct media_mixer_ctl;
 
+struct usbmix_connector_map {
+	u8 id;
+	u8 delegated_id;
+	u8 control;
+	u8 channel;
+};
+
 struct usb_mixer_interface {
 	struct snd_usb_audio *chip;
 	struct usb_host_interface *hostif;
@@ -18,6 +25,9 @@ struct usb_mixer_interface {
 	/* the usb audio specification version this interface complies to */
 	int protocol;
 
+	/* optional connector delegation map */
+	const struct usbmix_connector_map *connector_map;
+
 	/* Sound Blaster remote control stuff */
 	const struct rc_config *rc_cfg;
 	u32 rc_code;
@@ -52,6 +62,7 @@ struct usb_mixer_elem_list {
 	struct usb_mixer_elem_list *next_id_elem; /* list of controls with same id */
 	struct snd_kcontrol *kctl;
 	unsigned int id;
+	bool is_std_info;
 	usb_mixer_elem_dump_func_t dump;
 	usb_mixer_elem_resume_func_t resume;
 };
@@ -89,8 +100,12 @@ void snd_usb_mixer_notify_id(struct usb_mixer_interface *mixer, int unitid);
 int snd_usb_mixer_set_ctl_value(struct usb_mixer_elem_info *cval,
 				int request, int validx, int value_set);
 
-int snd_usb_mixer_add_control(struct usb_mixer_elem_list *list,
-			      struct snd_kcontrol *kctl);
+int snd_usb_mixer_add_list(struct usb_mixer_elem_list *list,
+			   struct snd_kcontrol *kctl,
+			   bool is_std_info);
+
+#define snd_usb_mixer_add_control(list, kctl) \
+	snd_usb_mixer_add_list(list, kctl, true)
 
 void snd_usb_mixer_elem_init_std(struct usb_mixer_elem_list *list,
 				 struct usb_mixer_interface *mixer,
diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c
index 73baf398c84a..ac84f0b2b0bc 100644
--- a/sound/usb/mixer_maps.c
+++ b/sound/usb/mixer_maps.c
@@ -27,6 +27,7 @@ struct usbmix_ctl_map {
 	u32 id;
 	const struct usbmix_name_map *map;
 	const struct usbmix_selector_map *selector_map;
+	const struct usbmix_connector_map *connector_map;
 	int ignore_ctl_error;
 };
 
@@ -349,6 +350,58 @@ static const struct usbmix_name_map dell_alc4020_map[] = {
 	{ 0 }
 };
 
+/* Some mobos shipped with a dummy HD-audio show the invalid GET_MIN/GET_MAX
+ * response for Input Gain Pad (id=19, control=12) and the connector status
+ * for SPDIF terminal (id=18).  Skip them.
+ */
+static const struct usbmix_name_map asus_rog_map[] = {
+	{ 18, NULL }, /* OT, connector control */
+	{ 19, NULL, 12 }, /* FU, Input Gain Pad */
+	{}
+};
+
+/* TRX40 mobos with Realtek ALC1220-VB */
+static const struct usbmix_name_map trx40_mobo_map[] = {
+	{ 18, NULL }, /* OT, IEC958 - broken response, disabled */
+	{ 19, NULL, 12 }, /* FU, Input Gain Pad - broken response, disabled */
+	{ 16, "Speaker" },		/* OT */
+	{ 22, "Speaker Playback" },	/* FU */
+	{ 7, "Line" },			/* IT */
+	{ 19, "Line Capture" },		/* FU */
+	{ 17, "Front Headphone" },	/* OT */
+	{ 23, "Front Headphone Playback" },	/* FU */
+	{ 8, "Mic" },			/* IT */
+	{ 20, "Mic Capture" },		/* FU */
+	{ 9, "Front Mic" },		/* IT */
+	{ 21, "Front Mic Capture" },	/* FU */
+	{ 24, "IEC958 Playback" },	/* FU */
+	{}
+};
+
+static const struct usbmix_connector_map trx40_mobo_connector_map[] = {
+	{ 10, 16 },	/* (Back) Speaker */
+	{ 11, 17 },	/* Front Headphone */
+	{ 13, 7 },	/* Line */
+	{ 14, 8 },	/* Mic */
+	{ 15, 9 },	/* Front Mic */
+	{}
+};
+
+/* Rear panel + front mic on Gigabyte TRX40 Aorus Master with ALC1220-VB */
+static const struct usbmix_name_map aorus_master_alc1220vb_map[] = {
+	{ 17, NULL },			/* OT, IEC958?, disabled */
+	{ 19, NULL, 12 }, /* FU, Input Gain Pad - broken response, disabled */
+	{ 16, "Line Out" },		/* OT */
+	{ 22, "Line Out Playback" },	/* FU */
+	{ 7, "Line" },			/* IT */
+	{ 19, "Line Capture" },		/* FU */
+	{ 8, "Mic" },			/* IT */
+	{ 20, "Mic Capture" },		/* FU */
+	{ 9, "Front Mic" },		/* IT */
+	{ 21, "Front Mic Capture" },	/* FU */
+	{}
+};
+
 /*
  * Control map entries
  */
@@ -468,6 +521,38 @@ static struct usbmix_ctl_map usbmix_ctl_maps[] = {
 		.id = USB_ID(0x05a7, 0x1020),
 		.map = bose_companion5_map,
 	},
+	{	/* Gigabyte TRX40 Aorus Master (rear panel + front mic) */
+		.id = USB_ID(0x0414, 0xa001),
+		.map = aorus_master_alc1220vb_map,
+	},
+	{	/* Gigabyte TRX40 Aorus Pro WiFi */
+		.id = USB_ID(0x0414, 0xa002),
+		.map = trx40_mobo_map,
+		.connector_map = trx40_mobo_connector_map,
+	},
+	{	/* ASUS ROG Zenith II */
+		.id = USB_ID(0x0b05, 0x1916),
+		.map = asus_rog_map,
+	},
+	{	/* ASUS ROG Strix */
+		.id = USB_ID(0x0b05, 0x1917),
+		.map = asus_rog_map,
+	},
+	{	/* MSI TRX40 Creator */
+		.id = USB_ID(0x0db0, 0x0d64),
+		.map = trx40_mobo_map,
+		.connector_map = trx40_mobo_connector_map,
+	},
+	{	/* MSI TRX40 */
+		.id = USB_ID(0x0db0, 0x543d),
+		.map = trx40_mobo_map,
+		.connector_map = trx40_mobo_connector_map,
+	},
+	{	/* Asrock TRX40 Creator */
+		.id = USB_ID(0x26ce, 0x0a01),
+		.map = trx40_mobo_map,
+		.connector_map = trx40_mobo_connector_map,
+	},
 	{ 0 } /* terminator */
 };
 
diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c
index 27dcb3743690..c48104208fed 100644
--- a/sound/usb/mixer_quirks.c
+++ b/sound/usb/mixer_quirks.c
@@ -156,7 +156,8 @@ static int add_single_ctl_with_resume(struct usb_mixer_interface *mixer,
 		return -ENOMEM;
 	}
 	kctl->private_free = snd_usb_mixer_elem_free;
-	return snd_usb_mixer_add_control(list, kctl);
+	/* don't use snd_usb_mixer_add_control() here, this is a special list element */
+	return snd_usb_mixer_add_list(list, kctl, false);
 }
 
 /*
@@ -182,6 +183,7 @@ static const struct rc_config {
 	{ USB_ID(0x041e, 0x3042), 0, 1, 1, 1,  1,  0x000d }, /* Usb X-Fi S51 */
 	{ USB_ID(0x041e, 0x30df), 0, 1, 1, 1,  1,  0x000d }, /* Usb X-Fi S51 Pro */
 	{ USB_ID(0x041e, 0x3237), 0, 1, 1, 1,  1,  0x000d }, /* Usb X-Fi S51 Pro */
+	{ USB_ID(0x041e, 0x3263), 0, 1, 1, 1,  1,  0x000d }, /* Usb X-Fi S51 Pro */
 	{ USB_ID(0x041e, 0x3048), 2, 2, 6, 6,  2,  0x6e91 }, /* Toshiba SB0500 */
 };
 
@@ -1507,11 +1509,15 @@ static int snd_microii_spdif_default_get(struct snd_kcontrol *kcontrol,
 
 	/* use known values for that card: interface#1 altsetting#1 */
 	iface = usb_ifnum_to_if(chip->dev, 1);
-	if (!iface || iface->num_altsetting < 2)
-		return -EINVAL;
+	if (!iface || iface->num_altsetting < 2) {
+		err = -EINVAL;
+		goto end;
+	}
 	alts = &iface->altsetting[1];
-	if (get_iface_desc(alts)->bNumEndpoints < 1)
-		return -EINVAL;
+	if (get_iface_desc(alts)->bNumEndpoints < 1) {
+		err = -EINVAL;
+		goto end;
+	}
 	ep = get_endpoint(alts, 0)->bEndpointAddress;
 
 	err = snd_usb_ctl_msg(chip->dev,
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index ff5ab24f3bd1..e837ce55f6ad 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -344,10 +344,22 @@ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs,
 		ep = 0x81;
 		ifnum = 1;
 		goto add_sync_ep_from_ifnum;
-	case USB_ID(0x07fd, 0x0004): /* MOTU MicroBook II */
+	case USB_ID(0x07fd, 0x0004): /* MOTU MicroBook II/IIc */
+		/* MicroBook IIc */
+		if (altsd->bInterfaceClass == USB_CLASS_AUDIO)
+			return 0;
+
+		/* MicroBook II */
 		ep = 0x84;
 		ifnum = 0;
 		goto add_sync_ep_from_ifnum;
+	case USB_ID(0x07fd, 0x0008): /* MOTU M Series */
+	case USB_ID(0x31e9, 0x0001): /* Solid State Logic SSL2 */
+	case USB_ID(0x31e9, 0x0002): /* Solid State Logic SSL2+ */
+	case USB_ID(0x0d9a, 0x00df): /* RTX6001 */
+		ep = 0x81;
+		ifnum = 2;
+		goto add_sync_ep_from_ifnum;
 	case USB_ID(0x0582, 0x01d8): /* BOSS Katana */
 		/* BOSS Katana amplifiers do not need quirks */
 		return 0;
@@ -370,7 +382,7 @@ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs,
 add_sync_ep_from_ifnum:
 	iface = usb_ifnum_to_if(dev, ifnum);
 
-	if (!iface || iface->num_altsetting == 0)
+	if (!iface || iface->num_altsetting < 2)
 		return -EINVAL;
 
 	alts = &iface->altsetting[1];
@@ -382,6 +394,8 @@ add_sync_ep:
 	if (!subs->sync_endpoint)
 		return -EINVAL;
 
+	subs->sync_endpoint->is_implicit_feedback = 1;
+
 	subs->data_endpoint->sync_master = subs->sync_endpoint;
 
 	return 1;
@@ -480,12 +494,15 @@ static int set_sync_endpoint(struct snd_usb_substream *subs,
 						   implicit_fb ?
 							SND_USB_ENDPOINT_TYPE_DATA :
 							SND_USB_ENDPOINT_TYPE_SYNC);
+
 	if (!subs->sync_endpoint) {
 		if (is_playback && attr == USB_ENDPOINT_SYNC_NONE)
 			return 0;
 		return -EINVAL;
 	}
 
+	subs->sync_endpoint->is_implicit_feedback = implicit_fb;
+
 	subs->data_endpoint->sync_master = subs->sync_endpoint;
 
 	return 0;
@@ -506,15 +523,15 @@ static int set_format(struct snd_usb_substream *subs, struct audioformat *fmt)
 	if (WARN_ON(!iface))
 		return -EINVAL;
 	alts = usb_altnum_to_altsetting(iface, fmt->altsetting);
-	altsd = get_iface_desc(alts);
-	if (WARN_ON(altsd->bAlternateSetting != fmt->altsetting))
+	if (WARN_ON(!alts))
 		return -EINVAL;
+	altsd = get_iface_desc(alts);
 
-	if (fmt == subs->cur_audiofmt)
+	if (fmt == subs->cur_audiofmt && !subs->need_setup_fmt)
 		return 0;
 
 	/* close the old interface */
-	if (subs->interface >= 0 && subs->interface != fmt->iface) {
+	if (subs->interface >= 0 && (subs->interface != fmt->iface || subs->need_setup_fmt)) {
 		if (!subs->stream->chip->keep_iface) {
 			err = usb_set_interface(subs->dev, subs->interface, 0);
 			if (err < 0) {
@@ -528,6 +545,9 @@ static int set_format(struct snd_usb_substream *subs, struct audioformat *fmt)
 		subs->altset_idx = 0;
 	}
 
+	if (subs->need_setup_fmt)
+		subs->need_setup_fmt = false;
+
 	/* set interface */
 	if (iface->cur_altsetting != alts) {
 		err = snd_usb_select_mode_quirk(subs, fmt);
@@ -1397,6 +1417,12 @@ static void retire_capture_urb(struct snd_usb_substream *subs,
 			// continue;
 		}
 		bytes = urb->iso_frame_desc[i].actual_length;
+		if (subs->stream_offset_adj > 0) {
+			unsigned int adj = min(subs->stream_offset_adj, bytes);
+			cp += adj;
+			bytes -= adj;
+			subs->stream_offset_adj -= adj;
+		}
 		frames = bytes / stride;
 		if (!subs->txfr_quirk)
 			bytes = frames * stride;
@@ -1568,6 +1594,8 @@ static void prepare_playback_urb(struct snd_usb_substream *subs,
 	for (i = 0; i < ctx->packets; i++) {
 		if (ctx->packet_size[i])
 			counts = ctx->packet_size[i];
+		else if (ep->sync_master)
+			counts = snd_usb_endpoint_slave_next_packet_size(ep);
 		else
 			counts = snd_usb_endpoint_next_packet_size(ep);
 
@@ -1727,6 +1755,7 @@ static int snd_usb_substream_playback_trigger(struct snd_pcm_substream *substrea
 		return 0;
 	case SNDRV_PCM_TRIGGER_STOP:
 		stop_endpoints(subs, false);
+		subs->data_endpoint->retire_data_urb = NULL;
 		subs->running = 0;
 		return 0;
 	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
@@ -1735,6 +1764,13 @@ static int snd_usb_substream_playback_trigger(struct snd_pcm_substream *substrea
 		subs->data_endpoint->retire_data_urb = retire_playback_urb;
 		subs->running = 0;
 		return 0;
+	case SNDRV_PCM_TRIGGER_SUSPEND:
+		if (subs->stream->chip->setup_fmt_after_resume_quirk) {
+			stop_endpoints(subs, true);
+			subs->need_setup_fmt = true;
+			return 0;
+		}
+		break;
 	}
 
 	return -EINVAL;
@@ -1767,6 +1803,13 @@ static int snd_usb_substream_capture_trigger(struct snd_pcm_substream *substream
 		subs->data_endpoint->retire_data_urb = retire_capture_urb;
 		subs->running = 1;
 		return 0;
+	case SNDRV_PCM_TRIGGER_SUSPEND:
+		if (subs->stream->chip->setup_fmt_after_resume_quirk) {
+			stop_endpoints(subs, true);
+			subs->need_setup_fmt = true;
+			return 0;
+		}
+		break;
 	}
 
 	return -EINVAL;
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index 9e049f60e80e..f55b605cfeb7 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -25,6 +25,26 @@
 	.idProduct = prod, \
 	.bInterfaceClass = USB_CLASS_VENDOR_SPEC
 
+/* HP Thunderbolt Dock Audio Headset */
+{
+	USB_DEVICE(0x03f0, 0x0269),
+	.driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
+		.vendor_name = "HP",
+		.product_name = "Thunderbolt Dock Audio Headset",
+		.profile_name = "HP-Thunderbolt-Dock-Audio-Headset",
+		.ifnum = QUIRK_NO_INTERFACE
+	}
+},
+/* HP Thunderbolt Dock Audio Module */
+{
+	USB_DEVICE(0x03f0, 0x0567),
+	.driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
+		.vendor_name = "HP",
+		.product_name = "Thunderbolt Dock Audio Module",
+		.profile_name = "HP-Thunderbolt-Dock-Audio-Module",
+		.ifnum = QUIRK_NO_INTERFACE
+	}
+},
 /* FTDI devices */
 {
 	USB_DEVICE(0x0403, 0xb8d8),
@@ -2756,90 +2776,6 @@ YAMAHA_DEVICE(0x7010, "UB99"),
 		.type = QUIRK_MIDI_NOVATION
 	}
 },
-{
-	/*
-	 * Focusrite Scarlett Solo 2nd generation
-	 * Reports that playback should use Synch: Synchronous
-	 * while still providing a feedback endpoint. Synchronous causes
-	 * snapping on some sample rates.
-	 * Force it to use Synch: Asynchronous.
-	 */
-	USB_DEVICE(0x1235, 0x8205),
-	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
-		.ifnum = QUIRK_ANY_INTERFACE,
-		.type = QUIRK_COMPOSITE,
-		.data = (const struct snd_usb_audio_quirk[]) {
-			{
-				.ifnum = 1,
-				.type = QUIRK_AUDIO_FIXED_ENDPOINT,
-				.data = & (const struct audioformat) {
-					.formats = SNDRV_PCM_FMTBIT_S32_LE,
-					.channels = 2,
-					.iface = 1,
-					.altsetting = 1,
-					.altset_idx = 1,
-					.attributes = 0,
-					.endpoint = 0x01,
-					.ep_attr = USB_ENDPOINT_XFER_ISOC |
-						   USB_ENDPOINT_SYNC_ASYNC,
-					.protocol = UAC_VERSION_2,
-					.rates = SNDRV_PCM_RATE_44100 |
-						 SNDRV_PCM_RATE_48000 |
-						 SNDRV_PCM_RATE_88200 |
-						 SNDRV_PCM_RATE_96000 |
-						 SNDRV_PCM_RATE_176400 |
-						 SNDRV_PCM_RATE_192000,
-					.rate_min = 44100,
-					.rate_max = 192000,
-					.nr_rates = 6,
-					.rate_table = (unsigned int[]) {
-						44100, 48000, 88200,
-						96000, 176400, 192000
-					},
-					.clock = 41
-				}
-			},
-			{
-				.ifnum = 2,
-				.type = QUIRK_AUDIO_FIXED_ENDPOINT,
-				.data = & (const struct audioformat) {
-					.formats = SNDRV_PCM_FMTBIT_S32_LE,
-					.channels = 2,
-					.iface = 2,
-					.altsetting = 1,
-					.altset_idx = 1,
-					.attributes = 0,
-					.endpoint = 0x82,
-					.ep_attr = USB_ENDPOINT_XFER_ISOC |
-						   USB_ENDPOINT_SYNC_ASYNC |
-						   USB_ENDPOINT_USAGE_IMPLICIT_FB,
-					.protocol = UAC_VERSION_2,
-					.rates = SNDRV_PCM_RATE_44100 |
-						 SNDRV_PCM_RATE_48000 |
-						 SNDRV_PCM_RATE_88200 |
-						 SNDRV_PCM_RATE_96000 |
-						 SNDRV_PCM_RATE_176400 |
-						 SNDRV_PCM_RATE_192000,
-					.rate_min = 44100,
-					.rate_max = 192000,
-					.nr_rates = 6,
-					.rate_table = (unsigned int[]) {
-						44100, 48000, 88200,
-						96000, 176400, 192000
-					},
-					.clock = 41
-				}
-			},
-			{
-				.ifnum = 3,
-				.type = QUIRK_IGNORE_INTERFACE
-			},
-			{
-				.ifnum = -1
-			}
-		}
-	}
-},
 
 /* Access Music devices */
 {
@@ -3466,12 +3402,13 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"),
 		.vendor_name = "Dell",
 		.product_name = "WD19 Dock",
 		.profile_name = "Dell-WD15-Dock",
-		.ifnum = QUIRK_NO_INTERFACE
+		.ifnum = QUIRK_ANY_INTERFACE,
+		.type = QUIRK_SETUP_FMT_AFTER_RESUME
 	}
 },
 /* MOTU Microbook II */
 {
-	USB_DEVICE(0x07fd, 0x0004),
+	USB_DEVICE_VENDOR_SPEC(0x07fd, 0x0004),
 	.driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
 		.vendor_name = "MOTU",
 		.product_name = "MicroBookII",
@@ -3534,5 +3471,201 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"),
 		}
 	}
 },
+{
+	/*
+	 * Pioneer DJ DJM-250MK2
+	 * PCM is 8 channels out @ 48 fixed (endpoints 0x01).
+	 * The output from computer to the mixer is usable.
+	 *
+	 * The input (phono or line to computer) is not working.
+	 * It should be at endpoint 0x82 and probably also 8 channels,
+	 * but it seems that it works only with Pioneer proprietary software.
+	 * Even on officially supported OS, the Audacity was unable to record
+	 * and Mixxx to recognize the control vinyls.
+	 */
+	USB_DEVICE_VENDOR_SPEC(0x2b73, 0x0017),
+	.driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
+		.ifnum = QUIRK_ANY_INTERFACE,
+		.type = QUIRK_COMPOSITE,
+		.data = (const struct snd_usb_audio_quirk[]) {
+			{
+				.ifnum = 0,
+				.type = QUIRK_AUDIO_FIXED_ENDPOINT,
+				.data = &(const struct audioformat) {
+					.formats = SNDRV_PCM_FMTBIT_S24_3LE,
+					.channels = 8, // outputs
+					.iface = 0,
+					.altsetting = 1,
+					.altset_idx = 1,
+					.endpoint = 0x01,
+					.ep_attr = USB_ENDPOINT_XFER_ISOC|
+						USB_ENDPOINT_SYNC_ASYNC,
+					.rates = SNDRV_PCM_RATE_48000,
+					.rate_min = 48000,
+					.rate_max = 48000,
+					.nr_rates = 1,
+					.rate_table = (unsigned int[]) { 48000 }
+				}
+			},
+			{
+				.ifnum = -1
+			}
+		}
+	}
+},
+{
+	/*
+	 * PIONEER DJ DDJ-RB
+	 * PCM is 4 channels out, 2 dummy channels in @ 44.1 fixed
+	 * The feedback for the output is the dummy input.
+	 */
+	USB_DEVICE_VENDOR_SPEC(0x2b73, 0x000e),
+	.driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
+		.ifnum = QUIRK_ANY_INTERFACE,
+		.type = QUIRK_COMPOSITE,
+		.data = (const struct snd_usb_audio_quirk[]) {
+			{
+				.ifnum = 0,
+				.type = QUIRK_AUDIO_FIXED_ENDPOINT,
+				.data = &(const struct audioformat) {
+					.formats = SNDRV_PCM_FMTBIT_S24_3LE,
+					.channels = 4,
+					.iface = 0,
+					.altsetting = 1,
+					.altset_idx = 1,
+					.endpoint = 0x01,
+					.ep_attr = USB_ENDPOINT_XFER_ISOC|
+						   USB_ENDPOINT_SYNC_ASYNC,
+					.rates = SNDRV_PCM_RATE_44100,
+					.rate_min = 44100,
+					.rate_max = 44100,
+					.nr_rates = 1,
+					.rate_table = (unsigned int[]) { 44100 }
+				}
+			},
+			{
+				.ifnum = 0,
+				.type = QUIRK_AUDIO_FIXED_ENDPOINT,
+				.data = &(const struct audioformat) {
+					.formats = SNDRV_PCM_FMTBIT_S24_3LE,
+					.channels = 2,
+					.iface = 0,
+					.altsetting = 1,
+					.altset_idx = 1,
+					.endpoint = 0x82,
+					.ep_attr = USB_ENDPOINT_XFER_ISOC|
+						 USB_ENDPOINT_SYNC_ASYNC|
+						 USB_ENDPOINT_USAGE_IMPLICIT_FB,
+					.rates = SNDRV_PCM_RATE_44100,
+					.rate_min = 44100,
+					.rate_max = 44100,
+					.nr_rates = 1,
+					.rate_table = (unsigned int[]) { 44100 }
+				}
+			},
+			{
+				.ifnum = -1
+			}
+		}
+	}
+},
+
+#define ALC1220_VB_DESKTOP(vend, prod) { \
+	USB_DEVICE(vend, prod),	\
+	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { \
+		.vendor_name = "Realtek", \
+		.product_name = "ALC1220-VB-DT", \
+		.profile_name = "Realtek-ALC1220-VB-Desktop", \
+		.ifnum = QUIRK_NO_INTERFACE \
+	} \
+}
+ALC1220_VB_DESKTOP(0x0414, 0xa002), /* Gigabyte TRX40 Aorus Pro WiFi */
+ALC1220_VB_DESKTOP(0x0db0, 0x0d64), /* MSI TRX40 Creator */
+ALC1220_VB_DESKTOP(0x0db0, 0x543d), /* MSI TRX40 */
+ALC1220_VB_DESKTOP(0x26ce, 0x0a01), /* Asrock TRX40 Creator */
+#undef ALC1220_VB_DESKTOP
+
+/* Two entries for Gigabyte TRX40 Aorus Master:
+ * TRX40 Aorus Master has two USB-audio devices, one for the front headphone
+ * with ESS SABRE9218 DAC chip, while another for the rest I/O (the rear
+ * panel and the front mic) with Realtek ALC1220-VB.
+ * Here we provide two distinct names for making UCM profiles easier.
+ */
+{
+	USB_DEVICE(0x0414, 0xa000),
+	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
+		.vendor_name = "Gigabyte",
+		.product_name = "Aorus Master Front Headphone",
+		.profile_name = "Gigabyte-Aorus-Master-Front-Headphone",
+		.ifnum = QUIRK_NO_INTERFACE
+	}
+},
+{
+	USB_DEVICE(0x0414, 0xa001),
+	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
+		.vendor_name = "Gigabyte",
+		.product_name = "Aorus Master Main Audio",
+		.profile_name = "Gigabyte-Aorus-Master-Main-Audio",
+		.ifnum = QUIRK_NO_INTERFACE
+	}
+},
+
+/*
+ * MacroSilicon MS2109 based HDMI capture cards
+ *
+ * These claim 96kHz 1ch in the descriptors, but are actually 48kHz 2ch.
+ * They also need QUIRK_AUDIO_ALIGN_TRANSFER, which makes one wonder if
+ * they pretend to be 96kHz mono as a workaround for stereo being broken
+ * by that...
+ *
+ * They also have an issue with initial stream alignment that causes the
+ * channels to be swapped and out of phase, which is dealt with in quirks.c.
+ */
+{
+	.match_flags = USB_DEVICE_ID_MATCH_DEVICE |
+		       USB_DEVICE_ID_MATCH_INT_CLASS |
+		       USB_DEVICE_ID_MATCH_INT_SUBCLASS,
+	.idVendor = 0x534d,
+	.idProduct = 0x2109,
+	.bInterfaceClass = USB_CLASS_AUDIO,
+	.bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL,
+	.driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
+		.vendor_name = "MacroSilicon",
+		.product_name = "MS2109",
+		.ifnum = QUIRK_ANY_INTERFACE,
+		.type = QUIRK_COMPOSITE,
+		.data = &(const struct snd_usb_audio_quirk[]) {
+			{
+				.ifnum = 2,
+				.type = QUIRK_AUDIO_ALIGN_TRANSFER,
+			},
+			{
+				.ifnum = 2,
+				.type = QUIRK_AUDIO_STANDARD_MIXER,
+			},
+			{
+				.ifnum = 3,
+				.type = QUIRK_AUDIO_FIXED_ENDPOINT,
+				.data = &(const struct audioformat) {
+					.formats = SNDRV_PCM_FMTBIT_S16_LE,
+					.channels = 2,
+					.iface = 3,
+					.altsetting = 1,
+					.altset_idx = 1,
+					.attributes = 0,
+					.endpoint = 0x82,
+					.ep_attr = USB_ENDPOINT_XFER_ISOC |
+						USB_ENDPOINT_SYNC_ASYNC,
+					.rates = SNDRV_PCM_RATE_CONTINUOUS,
+					.rate_min = 48000,
+					.rate_max = 48000,
+				}
+			},
+			{
+				.ifnum = -1
+			}
+		}
+	}
+},
 
 #undef USB_DEVICE_VENDOR_SPEC
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 349e1e52996d..a756f50d9f07 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -508,6 +508,16 @@ static int create_standard_mixer_quirk(struct snd_usb_audio *chip,
 	return snd_usb_create_mixer(chip, quirk->ifnum, 0);
 }
 
+
+static int setup_fmt_after_resume_quirk(struct snd_usb_audio *chip,
+				       struct usb_interface *iface,
+				       struct usb_driver *driver,
+				       const struct snd_usb_audio_quirk *quirk)
+{
+	chip->setup_fmt_after_resume_quirk = 1;
+	return 1;	/* Continue with creating streams and mixer */
+}
+
 /*
  * audio-interface quirks
  *
@@ -546,6 +556,7 @@ int snd_usb_create_quirk(struct snd_usb_audio *chip,
 		[QUIRK_AUDIO_EDIROL_UAXX] = create_uaxx_quirk,
 		[QUIRK_AUDIO_ALIGN_TRANSFER] = create_align_transfer_quirk,
 		[QUIRK_AUDIO_STANDARD_MIXER] = create_standard_mixer_quirk,
+		[QUIRK_SETUP_FMT_AFTER_RESUME] = setup_fmt_after_resume_quirk,
 	};
 
 	if (quirk->type < QUIRK_TYPE_COUNT) {
@@ -1102,6 +1113,31 @@ free_buf:
 	return err;
 }
 
+static int snd_usb_motu_m_series_boot_quirk(struct usb_device *dev)
+{
+	int ret;
+
+	if (snd_usb_pipe_sanity_check(dev, usb_sndctrlpipe(dev, 0)))
+		return -EINVAL;
+	ret = usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
+			      1, USB_TYPE_VENDOR | USB_RECIP_DEVICE,
+			      0x0, 0, NULL, 0, 1000);
+
+	if (ret < 0)
+		return ret;
+
+	msleep(2000);
+
+	ret = usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
+			      1, USB_TYPE_VENDOR | USB_RECIP_DEVICE,
+			      0x20, 0, NULL, 0, 1000);
+
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
 /*
  * Setup quirks
  */
@@ -1280,7 +1316,28 @@ int snd_usb_apply_boot_quirk(struct usb_device *dev,
 	case USB_ID(0x2466, 0x8010): /* Fractal Audio Axe-Fx 3 */
 		return snd_usb_axefx3_boot_quirk(dev);
 	case USB_ID(0x07fd, 0x0004): /* MOTU MicroBook II */
-		return snd_usb_motu_microbookii_boot_quirk(dev);
+		/*
+		 * For some reason interface 3 with vendor-spec class is
+		 * detected on MicroBook IIc.
+		 */
+		if (get_iface_desc(intf->altsetting)->bInterfaceClass ==
+		    USB_CLASS_VENDOR_SPEC &&
+		    get_iface_desc(intf->altsetting)->bInterfaceNumber < 3)
+			return snd_usb_motu_microbookii_boot_quirk(dev);
+		break;
+	}
+
+	return 0;
+}
+
+int snd_usb_apply_boot_quirk_once(struct usb_device *dev,
+				  struct usb_interface *intf,
+				  const struct snd_usb_audio_quirk *quirk,
+				  unsigned int id)
+{
+	switch (id) {
+	case USB_ID(0x07fd, 0x0008): /* MOTU M Series */
+		return snd_usb_motu_m_series_boot_quirk(dev);
 	}
 
 	return 0;
@@ -1375,6 +1432,9 @@ void snd_usb_set_format_quirk(struct snd_usb_substream *subs,
 	case USB_ID(0x041e, 0x3f19): /* E-Mu 0204 USB */
 		set_format_emu_quirk(subs, fmt);
 		break;
+	case USB_ID(0x534d, 0x2109): /* MacroSilicon MS2109 */
+		subs->stream_offset_adj = 2;
+		break;
 	}
 }
 
@@ -1386,10 +1446,12 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip)
 	case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */
 	case USB_ID(0x0556, 0x0014): /* Phoenix Audio TMX320VC */
 	case USB_ID(0x05A3, 0x9420): /* ELP HD USB Camera */
+	case USB_ID(0x05a7, 0x1020): /* Bose Companion 5 */
 	case USB_ID(0x074D, 0x3553): /* Outlaw RR2150 (Micronas UAC3553B) */
 	case USB_ID(0x1395, 0x740a): /* Sennheiser DECT */
 	case USB_ID(0x1901, 0x0191): /* GE B850V3 CP2114 audio interface */
 	case USB_ID(0x21B4, 0x0081): /* AudioQuest DragonFly */
+	case USB_ID(0x2912, 0x30c8): /* Audioengine D1 */
 		return true;
 	}
 
@@ -1410,6 +1472,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip)
 static bool is_itf_usb_dsd_dac(unsigned int id)
 {
 	switch (id) {
+	case USB_ID(0x154e, 0x1002): /* Denon DCD-1500RE */
 	case USB_ID(0x154e, 0x1003): /* Denon DA-300USB */
 	case USB_ID(0x154e, 0x3005): /* Marantz HD-DAC1 */
 	case USB_ID(0x154e, 0x3006): /* Marantz SA-14S1 */
@@ -1541,15 +1604,24 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe,
 	    && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
 		msleep(20);
 
-	/* Zoom R16/24, Logitech H650e, Jabra 550a needs a tiny delay here,
-	 * otherwise requests like get/set frequency return as failed despite
-	 * actually succeeding.
+	/* Zoom R16/24, Logitech H650e, Jabra 550a, Kingston HyperX needs a tiny
+	 * delay here, otherwise requests like get/set frequency return as
+	 * failed despite actually succeeding.
 	 */
 	if ((chip->usb_id == USB_ID(0x1686, 0x00dd) ||
 	     chip->usb_id == USB_ID(0x046d, 0x0a46) ||
-	     chip->usb_id == USB_ID(0x0b0e, 0x0349)) &&
+	     chip->usb_id == USB_ID(0x0b0e, 0x0349) ||
+	     chip->usb_id == USB_ID(0x0951, 0x16ad)) &&
 	    (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
 		usleep_range(1000, 2000);
+
+	/*
+	 * Samsung USBC Headset (AKG) need a tiny delay after each
+	 * class compliant request. (Model number: AAM625R or AAM627R)
+	 */
+	if (chip->usb_id == USB_ID(0x04e8, 0xa051) &&
+	    (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
+		usleep_range(5000, 6000);
 }
 
 /*
@@ -1592,7 +1664,7 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip,
 
 	case USB_ID(0x0d8c, 0x0316): /* Hegel HD12 DSD */
 	case USB_ID(0x10cb, 0x0103): /* The Bit Opus #3; with fp->dsd_raw */
-	case USB_ID(0x16b0, 0x06b2): /* NuPrime DAC-10 */
+	case USB_ID(0x16d0, 0x06b2): /* NuPrime DAC-10 */
 	case USB_ID(0x16d0, 0x09dd): /* Encore mDSD */
 	case USB_ID(0x16d0, 0x0733): /* Furutech ADL Stratos */
 	case USB_ID(0x16d0, 0x09db): /* NuPrime Audio DAC-9 */
@@ -1703,5 +1775,62 @@ void snd_usb_audioformat_attributes_quirk(struct snd_usb_audio *chip,
 		else
 			fp->ep_attr |= USB_ENDPOINT_SYNC_SYNC;
 		break;
+	case USB_ID(0x07fd, 0x0004):  /* MOTU MicroBook IIc */
+		/*
+		 * MaxPacketsOnly attribute is erroneously set in endpoint
+		 * descriptors. As a result this card produces noise with
+		 * all sample rates other than 96 KHz.
+		 */
+		fp->attributes &= ~UAC_EP_CS_ATTR_FILL_MAX;
+		break;
+	case USB_ID(0x1235, 0x8202):  /* Focusrite Scarlett 2i2 2nd gen */
+	case USB_ID(0x1235, 0x8205):  /* Focusrite Scarlett Solo 2nd gen */
+		/*
+		 * Reports that playback should use Synch: Synchronous
+		 * while still providing a feedback endpoint.
+		 * Synchronous causes snapping on some sample rates.
+		 * Force it to use Synch: Asynchronous.
+		 */
+		if (stream == SNDRV_PCM_STREAM_PLAYBACK) {
+			fp->ep_attr &= ~USB_ENDPOINT_SYNCTYPE;
+			fp->ep_attr |= USB_ENDPOINT_SYNC_ASYNC;
+		}
+		break;
 	}
 }
+
+/*
+ * registration quirk:
+ * the registration is skipped if a device matches with the given ID,
+ * unless the interface reaches to the defined one.  This is for delaying
+ * the registration until the last known interface, so that the card and
+ * devices appear at the same time.
+ */
+
+struct registration_quirk {
+	unsigned int usb_id;	/* composed via USB_ID() */
+	unsigned int interface;	/* the interface to trigger register */
+};
+
+#define REG_QUIRK_ENTRY(vendor, product, iface) \
+	{ .usb_id = USB_ID(vendor, product), .interface = (iface) }
+
+static const struct registration_quirk registration_quirks[] = {
+	REG_QUIRK_ENTRY(0x0951, 0x16d8, 2),	/* Kingston HyperX AMP */
+	REG_QUIRK_ENTRY(0x0951, 0x16ed, 2),	/* Kingston HyperX Cloud Alpha S */
+	REG_QUIRK_ENTRY(0x0951, 0x16ea, 2),	/* Kingston HyperX Cloud Flight S */
+	{ 0 }					/* terminator */
+};
+
+/* return true if skipping registration */
+bool snd_usb_registration_quirk(struct snd_usb_audio *chip, int iface)
+{
+	const struct registration_quirk *q;
+
+	for (q = registration_quirks; q->usb_id; q++)
+		if (chip->usb_id == q->usb_id)
+			return iface != q->interface;
+
+	/* Register as normal */
+	return false;
+}
diff --git a/sound/usb/quirks.h b/sound/usb/quirks.h
index a80e0ddd0736..c76cf24a640a 100644
--- a/sound/usb/quirks.h
+++ b/sound/usb/quirks.h
@@ -20,6 +20,11 @@ int snd_usb_apply_boot_quirk(struct usb_device *dev,
 			     const struct snd_usb_audio_quirk *quirk,
 			     unsigned int usb_id);
 
+int snd_usb_apply_boot_quirk_once(struct usb_device *dev,
+				  struct usb_interface *intf,
+				  const struct snd_usb_audio_quirk *quirk,
+				  unsigned int usb_id);
+
 void snd_usb_set_format_quirk(struct snd_usb_substream *subs,
 			      struct audioformat *fmt);
 
@@ -46,4 +51,6 @@ void snd_usb_audioformat_attributes_quirk(struct snd_usb_audio *chip,
 					  struct audioformat *fp,
 					  int stream);
 
+bool snd_usb_registration_quirk(struct snd_usb_audio *chip, int iface);
+
 #endif /* __USBAUDIO_QUIRKS_H */
diff --git a/sound/usb/stream.c b/sound/usb/stream.c
index a0649c8ae460..3a17c4c53f87 100644
--- a/sound/usb/stream.c
+++ b/sound/usb/stream.c
@@ -89,6 +89,7 @@ static void snd_usb_init_substream(struct snd_usb_stream *as,
 	subs->tx_length_quirk = as->chip->tx_length_quirk;
 	subs->speed = snd_usb_get_speed(subs->dev);
 	subs->pkt_offset_adj = 0;
+	subs->stream_offset_adj = 0;
 
 	snd_usb_set_pcm_ops(as->pcm, stream);
 
diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h
index feb30f9c1716..55a2119c2411 100644
--- a/sound/usb/usbaudio.h
+++ b/sound/usb/usbaudio.h
@@ -26,14 +26,14 @@ struct snd_usb_audio {
 	struct usb_interface *pm_intf;
 	u32 usb_id;
 	struct mutex mutex;
-	unsigned int autosuspended:1;	
+	unsigned int system_suspend;
 	atomic_t active;
 	atomic_t shutdown;
 	atomic_t usage_count;
 	wait_queue_head_t shutdown_wait;
 	unsigned int txfr_quirk:1; /* Subframe boundaries on transfers */
 	unsigned int tx_length_quirk:1; /* Put length specifier in transfers */
-	
+	unsigned int setup_fmt_after_resume_quirk:1; /* setup the format to interface after resume */
 	int num_interfaces;
 	int num_suspended_intf;
 	int sample_rate_read_error;
@@ -98,6 +98,7 @@ enum quirk_type {
 	QUIRK_AUDIO_EDIROL_UAXX,
 	QUIRK_AUDIO_ALIGN_TRANSFER,
 	QUIRK_AUDIO_STANDARD_MIXER,
+	QUIRK_SETUP_FMT_AFTER_RESUME,
 
 	QUIRK_TYPE_COUNT
 };
diff --git a/sound/usb/usx2y/usX2Yhwdep.c b/sound/usb/usx2y/usX2Yhwdep.c
index d1caa8ed9e68..9985fc139487 100644
--- a/sound/usb/usx2y/usX2Yhwdep.c
+++ b/sound/usb/usx2y/usX2Yhwdep.c
@@ -119,7 +119,7 @@ static int snd_usX2Y_hwdep_dsp_status(struct snd_hwdep *hw,
 	info->num_dsps = 2;		// 0: Prepad Data, 1: FPGA Code
 	if (us428->chip_status & USX2Y_STAT_CHIP_INIT)
 		info->chip_ready = 1;
- 	info->version = USX2Y_DRIVER_VERSION; 
+	info->version = USX2Y_DRIVER_VERSION;
 	return 0;
 }
 
diff --git a/sound/usb/usx2y/usbusx2yaudio.c b/sound/usb/usx2y/usbusx2yaudio.c
index 89fa287678fc..e0bace4d1c40 100644
--- a/sound/usb/usx2y/usbusx2yaudio.c
+++ b/sound/usb/usx2y/usbusx2yaudio.c
@@ -681,6 +681,8 @@ static int usX2Y_rate_set(struct usX2Ydev *usX2Y, int rate)
 			us->submitted =	2*NOOF_SETRATE_URBS;
 			for (i = 0; i < NOOF_SETRATE_URBS; ++i) {
 				struct urb *urb = us->urb[i];
+				if (!urb)
+					continue;
 				if (urb->status) {
 					if (!err)
 						err = -ENODEV;
diff --git a/sound/usb/validate.c b/sound/usb/validate.c
index fb6613883a1d..079f1713e6d1 100644
--- a/sound/usb/validate.c
+++ b/sound/usb/validate.c
@@ -110,7 +110,7 @@ static bool validate_processing_unit(const void *p,
 	default:
 		if (v->type == UAC1_EXTENSION_UNIT)
 			return true; /* OK */
-		switch (d->wProcessType) {
+		switch (le16_to_cpu(d->wProcessType)) {
 		case UAC_PROCESS_UP_DOWNMIX:
 		case UAC_PROCESS_DOLBY_PROLOGIC:
 			if (d->bLength < len + 1) /* bNrModes */
@@ -125,7 +125,7 @@ static bool validate_processing_unit(const void *p,
 	case UAC_VERSION_2:
 		if (v->type == UAC2_EXTENSION_UNIT_V2)
 			return true; /* OK */
-		switch (d->wProcessType) {
+		switch (le16_to_cpu(d->wProcessType)) {
 		case UAC2_PROCESS_UP_DOWNMIX:
 		case UAC2_PROCESS_DOLBY_PROLOCIC: /* SiC! */
 			if (d->bLength < len + 1) /* bNrModes */
@@ -142,7 +142,7 @@ static bool validate_processing_unit(const void *p,
 			len += 2; /* wClusterDescrID */
 			break;
 		}
-		switch (d->wProcessType) {
+		switch (le16_to_cpu(d->wProcessType)) {
 		case UAC3_PROCESS_UP_DOWNMIX:
 			if (d->bLength < len + 1) /* bNrModes */
 				return false;
diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c
index 8cb504d30384..5ef1c15e88ad 100644
--- a/tools/accounting/getdelays.c
+++ b/tools/accounting/getdelays.c
@@ -136,7 +136,7 @@ static int send_cmd(int sd, __u16 nlmsg_type, __u32 nlmsg_pid,
 	msg.g.version = 0x1;
 	na = (struct nlattr *) GENLMSG_DATA(&msg);
 	na->nla_type = nla_type;
-	na->nla_len = nla_len + 1 + NLA_HDRLEN;
+	na->nla_len = nla_len + NLA_HDRLEN;
 	memcpy(NLA_DATA(na), nla_data, nla_len);
 	msg.n.nlmsg_len += NLMSG_ALIGN(na->nla_len);
 
diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h
index 4703d218663a..f83a70e07df8 100644
--- a/tools/arch/arm64/include/uapi/asm/unistd.h
+++ b/tools/arch/arm64/include/uapi/asm/unistd.h
@@ -19,5 +19,6 @@
 #define __ARCH_WANT_NEW_STAT
 #define __ARCH_WANT_SET_GET_RLIMIT
 #define __ARCH_WANT_TIME32_SYSCALLS
+#define __ARCH_WANT_SYS_CLONE3
 
 #include <asm-generic/unistd.h>
diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c
index 7317438ecd9e..5c67bbcdf914 100644
--- a/tools/bpf/bpftool/btf.c
+++ b/tools/bpf/bpftool/btf.c
@@ -517,7 +517,7 @@ static int do_dump(int argc, char **argv)
 
 		btf_id = strtoul(*argv, &endptr, 0);
 		if (*endptr) {
-			p_err("can't parse %s as ID", **argv);
+			p_err("can't parse %s as ID", *argv);
 			return -1;
 		}
 		NEXT_ARG();
@@ -539,7 +539,7 @@ static int do_dump(int argc, char **argv)
 			goto done;
 		}
 		if (!btf) {
-			err = ENOENT;
+			err = -ENOENT;
 			p_err("can't find btf with ID (%u)", btf_id);
 			goto done;
 		}
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 3d63feb7f852..ce75b76d17b1 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -74,6 +74,7 @@ static const char * const prog_type_name[] = {
 	[BPF_PROG_TYPE_SK_REUSEPORT]		= "sk_reuseport",
 	[BPF_PROG_TYPE_FLOW_DISSECTOR]		= "flow_dissector",
 	[BPF_PROG_TYPE_CGROUP_SYSCTL]		= "cgroup_sysctl",
+	[BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE]	= "raw_tracepoint_writable",
 };
 
 extern const char * const map_type_name[];
diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c
index 67e99c56bc88..e3b770082a39 100644
--- a/tools/bpf/bpftool/net.c
+++ b/tools/bpf/bpftool/net.c
@@ -197,7 +197,7 @@ static int query_flow_dissector(struct bpf_attach_info *attach_info)
 
 	fd = open("/proc/self/ns/net", O_RDONLY);
 	if (fd < 0) {
-		p_err("can't open /proc/self/ns/net: %d",
+		p_err("can't open /proc/self/ns/net: %s",
 		      strerror(errno));
 		return -1;
 	}
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index d41651afe5f6..9e6dc94726b3 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -492,14 +492,14 @@ static int do_dump(int argc, char **argv)
 
 	info = &info_linear->info;
 	if (mode == DUMP_JITED) {
-		if (info->jited_prog_len == 0) {
+		if (info->jited_prog_len == 0 || !info->jited_prog_insns) {
 			p_info("no instructions returned");
 			goto err_free;
 		}
 		buf = (unsigned char *)(info->jited_prog_insns);
 		member_len = info->jited_prog_len;
 	} else {	/* DUMP_XLATED */
-		if (info->xlated_prog_len == 0) {
+		if (info->xlated_prog_len == 0 || !info->xlated_prog_insns) {
 			p_err("error retrieving insn dump: kernel.kptr_restrict set?");
 			goto err_free;
 		}
diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c
index 0bb17bf88b18..0ad5fe6b432b 100644
--- a/tools/bpf/bpftool/xlated_dumper.c
+++ b/tools/bpf/bpftool/xlated_dumper.c
@@ -176,7 +176,7 @@ static const char *print_call(void *private_data,
 	struct kernel_sym *sym;
 
 	if (insn->src_reg == BPF_PSEUDO_CALL &&
-	    (__u32) insn->imm < dd->nr_jited_ksyms)
+	    (__u32) insn->imm < dd->nr_jited_ksyms && dd->jited_ksyms)
 		address = dd->jited_ksyms[insn->imm];
 
 	sym = kernel_syms_search(dd, address);
diff --git a/tools/build/Build.include b/tools/build/Build.include
index 9ec01f4454f9..585486e40995 100644
--- a/tools/build/Build.include
+++ b/tools/build/Build.include
@@ -74,7 +74,8 @@ dep-cmd = $(if $(wildcard $(fixdep)),
 #                   dependencies in the cmd file
 if_changed_dep = $(if $(strip $(any-prereq) $(arg-check)),         \
                   @set -e;                                         \
-                  $(echo-cmd) $(cmd_$(1)) && $(dep-cmd))
+                  $(echo-cmd) $(cmd_$(1));                         \
+                  $(dep-cmd))
 
 # if_changed      - execute command if any prerequisite is newer than
 #                   target, or command line has changed
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 3b24231c58a2..5cc7a3131e20 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -8,7 +8,7 @@ endif
 
 feature_check = $(eval $(feature_check_code))
 define feature_check_code
-  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" CXXFLAGS="$(EXTRA_CXXFLAGS) $(FEATURE_CHECK_CXXFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C $(feature_dir) $(OUTPUT_FEATURES)test-$1.bin >/dev/null 2>/dev/null && echo 1 || echo 0)
+  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CC="$(CC)" CXX="$(CXX)" CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" CXXFLAGS="$(EXTRA_CXXFLAGS) $(FEATURE_CHECK_CXXFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C $(feature_dir) $(OUTPUT_FEATURES)test-$1.bin >/dev/null 2>/dev/null && echo 1 || echo 0)
 endef
 
 feature_set = $(eval $(feature_set_code))
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 4b8244ee65ce..a8dbda61f034 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -67,8 +67,6 @@ FILES=                                          \
 
 FILES := $(addprefix $(OUTPUT),$(FILES))
 
-CC ?= $(CROSS_COMPILE)gcc
-CXX ?= $(CROSS_COMPILE)g++
 PKG_CONFIG ?= $(CROSS_COMPILE)pkg-config
 LLVM_CONFIG ?= llvm-config
 
diff --git a/tools/gpio/Makefile b/tools/gpio/Makefile
index 6080de58861f..6289b8d20dff 100644
--- a/tools/gpio/Makefile
+++ b/tools/gpio/Makefile
@@ -35,7 +35,7 @@ $(OUTPUT)include/linux/gpio.h: ../../include/uapi/linux/gpio.h
 
 prepare: $(OUTPUT)include/linux/gpio.h
 
-GPIO_UTILS_IN := $(output)gpio-utils-in.o
+GPIO_UTILS_IN := $(OUTPUT)gpio-utils-in.o
 $(GPIO_UTILS_IN): prepare FORCE
 	$(Q)$(MAKE) $(build)=gpio-utils
 
diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat
index ad1b9e646c49..4cf93110c259 100755
--- a/tools/kvm/kvm_stat/kvm_stat
+++ b/tools/kvm/kvm_stat/kvm_stat
@@ -270,6 +270,7 @@ class ArchX86(Arch):
     def __init__(self, exit_reasons):
         self.sc_perf_evt_open = 298
         self.ioctl_numbers = IOCTL_NUMBERS
+        self.exit_reason_field = 'exit_reason'
         self.exit_reasons = exit_reasons
 
     def debugfs_is_child(self, field):
@@ -289,6 +290,7 @@ class ArchPPC(Arch):
         # numbers depend on the wordsize.
         char_ptr_size = ctypes.sizeof(ctypes.c_char_p)
         self.ioctl_numbers['SET_FILTER'] = 0x80002406 | char_ptr_size << 16
+        self.exit_reason_field = 'exit_nr'
         self.exit_reasons = {}
 
     def debugfs_is_child(self, field):
@@ -300,6 +302,7 @@ class ArchA64(Arch):
     def __init__(self):
         self.sc_perf_evt_open = 241
         self.ioctl_numbers = IOCTL_NUMBERS
+        self.exit_reason_field = 'esr_ec'
         self.exit_reasons = AARCH64_EXIT_REASONS
 
     def debugfs_is_child(self, field):
@@ -311,6 +314,7 @@ class ArchS390(Arch):
     def __init__(self):
         self.sc_perf_evt_open = 331
         self.ioctl_numbers = IOCTL_NUMBERS
+        self.exit_reason_field = None
         self.exit_reasons = None
 
     def debugfs_is_child(self, field):
@@ -541,8 +545,8 @@ class TracepointProvider(Provider):
         """
         filters = {}
         filters['kvm_userspace_exit'] = ('reason', USERSPACE_EXIT_REASONS)
-        if ARCH.exit_reasons:
-            filters['kvm_exit'] = ('exit_reason', ARCH.exit_reasons)
+        if ARCH.exit_reason_field and ARCH.exit_reasons:
+            filters['kvm_exit'] = (ARCH.exit_reason_field, ARCH.exit_reasons)
         return filters
 
     def _get_available_fields(self):
diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index 7aba8243a0e7..4cc69675c2a9 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -90,6 +90,7 @@ struct fs {
 	const char * const	*mounts;
 	char			 path[PATH_MAX];
 	bool			 found;
+	bool			 checked;
 	long			 magic;
 };
 
@@ -111,31 +112,37 @@ static struct fs fs__entries[] = {
 		.name	= "sysfs",
 		.mounts	= sysfs__fs_known_mountpoints,
 		.magic	= SYSFS_MAGIC,
+		.checked = false,
 	},
 	[FS__PROCFS] = {
 		.name	= "proc",
 		.mounts	= procfs__known_mountpoints,
 		.magic	= PROC_SUPER_MAGIC,
+		.checked = false,
 	},
 	[FS__DEBUGFS] = {
 		.name	= "debugfs",
 		.mounts	= debugfs__known_mountpoints,
 		.magic	= DEBUGFS_MAGIC,
+		.checked = false,
 	},
 	[FS__TRACEFS] = {
 		.name	= "tracefs",
 		.mounts	= tracefs__known_mountpoints,
 		.magic	= TRACEFS_MAGIC,
+		.checked = false,
 	},
 	[FS__HUGETLBFS] = {
 		.name	= "hugetlbfs",
 		.mounts = hugetlbfs__known_mountpoints,
 		.magic	= HUGETLBFS_MAGIC,
+		.checked = false,
 	},
 	[FS__BPF_FS] = {
 		.name	= "bpf",
 		.mounts = bpf_fs__known_mountpoints,
 		.magic	= BPF_FS_MAGIC,
+		.checked = false,
 	},
 };
 
@@ -158,6 +165,7 @@ static bool fs__read_mounts(struct fs *fs)
 	}
 
 	fclose(fp);
+	fs->checked = true;
 	return fs->found = found;
 }
 
@@ -210,6 +218,7 @@ static bool fs__env_override(struct fs *fs)
 	size_t name_len = strlen(fs->name);
 	/* name + "_PATH" + '\0' */
 	char upper_name[name_len + 5 + 1];
+
 	memcpy(upper_name, fs->name, name_len);
 	mem_toupper(upper_name, name_len);
 	strcpy(&upper_name[name_len], "_PATH");
@@ -219,7 +228,9 @@ static bool fs__env_override(struct fs *fs)
 		return false;
 
 	fs->found = true;
-	strncpy(fs->path, override_path, sizeof(fs->path));
+	fs->checked = true;
+	strncpy(fs->path, override_path, sizeof(fs->path) - 1);
+	fs->path[sizeof(fs->path) - 1] = '\0';
 	return true;
 }
 
@@ -244,6 +255,14 @@ static const char *fs__mountpoint(int idx)
 	if (fs->found)
 		return (const char *)fs->path;
 
+	/* the mount point was already checked for the mount point
+	 * but and did not exist, so return NULL to avoid scanning again.
+	 * This makes the found and not found paths cost equivalent
+	 * in case of multiple calls.
+	 */
+	if (fs->checked)
+		return NULL;
+
 	return fs__get_mountpoint(fs);
 }
 
diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h
index 92d03b8396b1..3b70003e7cfb 100644
--- a/tools/lib/api/fs/fs.h
+++ b/tools/lib/api/fs/fs.h
@@ -18,6 +18,18 @@
 	const char *name##__mount(void);	\
 	bool name##__configured(void);		\
 
+/*
+ * The xxxx__mountpoint() entry points find the first match mount point for each
+ * filesystems listed below, where xxxx is the filesystem type.
+ *
+ * The interface is as follows:
+ *
+ * - If a mount point is found on first call, it is cached and used for all
+ *   subsequent calls.
+ *
+ * - If a mount point is not found, NULL is returned on first call and all
+ *   subsequent calls.
+ */
 FS(sysfs)
 FS(procfs)
 FS(debugfs)
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index c4a48086dc9a..65f993562203 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -192,7 +192,7 @@ static void *
 alloc_zero_tailing_info(const void *orecord, __u32 cnt,
 			__u32 actual_rec_size, __u32 expected_rec_size)
 {
-	__u64 info_len = actual_rec_size * cnt;
+	__u64 info_len = (__u64)actual_rec_size * cnt;
 	void *info, *nrecord;
 	int i;
 
diff --git a/tools/lib/bpf/bpf_prog_linfo.c b/tools/lib/bpf/bpf_prog_linfo.c
index 6978314ea7f6..0ca04865a339 100644
--- a/tools/lib/bpf/bpf_prog_linfo.c
+++ b/tools/lib/bpf/bpf_prog_linfo.c
@@ -104,6 +104,7 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
 {
 	struct bpf_prog_linfo *prog_linfo;
 	__u32 nr_linfo, nr_jited_func;
+	__u64 data_sz;
 
 	nr_linfo = info->nr_line_info;
 
@@ -125,11 +126,11 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
 	/* Copy xlated line_info */
 	prog_linfo->nr_linfo = nr_linfo;
 	prog_linfo->rec_size = info->line_info_rec_size;
-	prog_linfo->raw_linfo = malloc(nr_linfo * prog_linfo->rec_size);
+	data_sz = (__u64)nr_linfo * prog_linfo->rec_size;
+	prog_linfo->raw_linfo = malloc(data_sz);
 	if (!prog_linfo->raw_linfo)
 		goto err_free;
-	memcpy(prog_linfo->raw_linfo, (void *)(long)info->line_info,
-	       nr_linfo * prog_linfo->rec_size);
+	memcpy(prog_linfo->raw_linfo, (void *)(long)info->line_info, data_sz);
 
 	nr_jited_func = info->nr_jited_ksyms;
 	if (!nr_jited_func ||
@@ -145,13 +146,12 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
 	/* Copy jited_line_info */
 	prog_linfo->nr_jited_func = nr_jited_func;
 	prog_linfo->jited_rec_size = info->jited_line_info_rec_size;
-	prog_linfo->raw_jited_linfo = malloc(nr_linfo *
-					     prog_linfo->jited_rec_size);
+	data_sz = (__u64)nr_linfo * prog_linfo->jited_rec_size;
+	prog_linfo->raw_jited_linfo = malloc(data_sz);
 	if (!prog_linfo->raw_jited_linfo)
 		goto err_free;
 	memcpy(prog_linfo->raw_jited_linfo,
-	       (void *)(long)info->jited_line_info,
-	       nr_linfo * prog_linfo->jited_rec_size);
+	       (void *)(long)info->jited_line_info, data_sz);
 
 	/* Number of jited_line_info per jited func */
 	prog_linfo->nr_jited_linfo_per_func = malloc(nr_jited_func *
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 03348c4d6bd4..0c94d53ec796 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -316,10 +316,9 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
 		t = btf__type_by_id(btf, type_id);
 	}
 
+done:
 	if (size < 0)
 		return -EINVAL;
-
-done:
 	if (nelems && size > UINT32_MAX / nelems)
 		return -E2BIG;
 
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 88d506951b07..774aa4f546c5 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1924,6 +1924,7 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
 			pr_warning("oom in prog realloc\n");
 			return -ENOMEM;
 		}
+		prog->insns = new_insn;
 
 		if (obj->btf_ext) {
 			err = bpf_program_reloc_btf_ext(prog, obj,
@@ -1935,7 +1936,6 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
 
 		memcpy(new_insn + prog->insns_cnt, text->insns,
 		       text->insns_cnt * sizeof(*insn));
-		prog->insns = new_insn;
 		prog->main_prog_cnt = prog->insns_cnt;
 		prog->insns_cnt = new_cnt;
 		pr_debug("added %zd insn from %s to prog %s\n",
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index ce3ec81b71c0..88416be2bf99 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -137,7 +137,7 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 		struct ifinfomsg ifinfo;
 		char             attrbuf[64];
 	} req;
-	__u32 nl_pid;
+	__u32 nl_pid = 0;
 
 	sock = libbpf_netlink_open(&nl_pid);
 	if (sock < 0)
@@ -254,7 +254,7 @@ int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags)
 {
 	struct xdp_id_md xdp_id = {};
 	int sock, ret;
-	__u32 nl_pid;
+	__u32 nl_pid = 0;
 	__u32 mask;
 
 	if (flags & ~XDP_FLAGS_MASK)
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index a39cdd0d890d..8d5b83c1ee10 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -122,6 +122,7 @@ EVENT_PARSE_VERSION = $(EP_VERSION).$(EP_PATCHLEVEL).$(EP_EXTRAVERSION)
 
 LIB_TARGET  = libtraceevent.a libtraceevent.so.$(EVENT_PARSE_VERSION)
 LIB_INSTALL = libtraceevent.a libtraceevent.so*
+LIB_INSTALL := $(addprefix $(OUTPUT),$(LIB_INSTALL))
 
 INCLUDES = -I. -I $(srctree)/tools/include $(CONFIG_INCLUDES)
 
@@ -269,7 +270,7 @@ define do_generate_dynamic_list_file
 	xargs echo "U w W" | tr 'w ' 'W\n' | sort -u | xargs echo`;\
 	if [ "$$symbol_type" = "U W" ];then				\
 		(echo '{';						\
-		$(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;\
+		$(NM) -u -D $1 | awk 'NF>1 {sub("@.*", "", $$2); print "\t"$$2";"}' | sort -u;\
 		echo '};';						\
 		) > $2;							\
 	else								\
@@ -277,10 +278,11 @@ define do_generate_dynamic_list_file
 	fi
 endef
 
-PKG_CONFIG_FILE = libtraceevent.pc
+PKG_CONFIG_SOURCE_FILE = libtraceevent.pc
+PKG_CONFIG_FILE := $(addprefix $(OUTPUT),$(PKG_CONFIG_SOURCE_FILE))
 define do_install_pkgconfig_file
 	if [ -n "${pkgconfig_dir}" ]; then 					\
-		cp -f ${PKG_CONFIG_FILE}.template ${PKG_CONFIG_FILE}; 		\
+		cp -f ${PKG_CONFIG_SOURCE_FILE}.template ${PKG_CONFIG_FILE};	\
 		sed -i "s|INSTALL_PREFIX|${1}|g" ${PKG_CONFIG_FILE}; 		\
 		sed -i "s|LIB_VERSION|${EVENT_PARSE_VERSION}|g" ${PKG_CONFIG_FILE}; \
 		sed -i "s|LIB_DIR|${libdir}|g" ${PKG_CONFIG_FILE}; \
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 13fd9fdf91e0..36af2bec523c 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -1392,13 +1392,28 @@ static unsigned int type_size(const char *name)
 	return 0;
 }
 
+static int append(char **buf, const char *delim, const char *str)
+{
+	char *new_buf;
+
+	new_buf = realloc(*buf, strlen(*buf) + strlen(delim) + strlen(str) + 1);
+	if (!new_buf)
+		return -1;
+	strcat(new_buf, delim);
+	strcat(new_buf, str);
+	*buf = new_buf;
+	return 0;
+}
+
 static int event_read_fields(struct tep_event *event, struct tep_format_field **fields)
 {
 	struct tep_format_field *field = NULL;
 	enum tep_event_type type;
 	char *token;
 	char *last_token;
+	char *delim = " ";
 	int count = 0;
+	int ret;
 
 	do {
 		unsigned int size_dynamic = 0;
@@ -1457,24 +1472,51 @@ static int event_read_fields(struct tep_event *event, struct tep_format_field **
 					field->flags |= TEP_FIELD_IS_POINTER;
 
 				if (field->type) {
-					char *new_type;
-					new_type = realloc(field->type,
-							   strlen(field->type) +
-							   strlen(last_token) + 2);
-					if (!new_type) {
-						free(last_token);
-						goto fail;
-					}
-					field->type = new_type;
-					strcat(field->type, " ");
-					strcat(field->type, last_token);
+					ret = append(&field->type, delim, last_token);
 					free(last_token);
+					if (ret < 0)
+						goto fail;
 				} else
 					field->type = last_token;
 				last_token = token;
+				delim = " ";
 				continue;
 			}
 
+			/* Handle __attribute__((user)) */
+			if ((type == TEP_EVENT_DELIM) &&
+			    strcmp("__attribute__", last_token) == 0 &&
+			    token[0] == '(') {
+				int depth = 1;
+				int ret;
+
+				ret = append(&field->type, " ", last_token);
+				ret |= append(&field->type, "", "(");
+				if (ret < 0)
+					goto fail;
+
+				delim = " ";
+				while ((type = read_token(&token)) != TEP_EVENT_NONE) {
+					if (type == TEP_EVENT_DELIM) {
+						if (token[0] == '(')
+							depth++;
+						else if (token[0] == ')')
+							depth--;
+						if (!depth)
+							break;
+						ret = append(&field->type, "", token);
+						delim = "";
+					} else {
+						ret = append(&field->type, delim, token);
+						delim = " ";
+					}
+					if (ret < 0)
+						goto fail;
+					free(last_token);
+					last_token = token;
+				}
+				continue;
+			}
 			break;
 		}
 
@@ -1490,8 +1532,6 @@ static int event_read_fields(struct tep_event *event, struct tep_format_field **
 		if (strcmp(token, "[") == 0) {
 			enum tep_event_type last_type = type;
 			char *brackets = token;
-			char *new_brackets;
-			int len;
 
 			field->flags |= TEP_FIELD_IS_ARRAY;
 
@@ -1503,29 +1543,27 @@ static int event_read_fields(struct tep_event *event, struct tep_format_field **
 				field->arraylen = 0;
 
 		        while (strcmp(token, "]") != 0) {
+				const char *delim;
+
 				if (last_type == TEP_EVENT_ITEM &&
 				    type == TEP_EVENT_ITEM)
-					len = 2;
+					delim = " ";
 				else
-					len = 1;
+					delim = "";
+
 				last_type = type;
 
-				new_brackets = realloc(brackets,
-						       strlen(brackets) +
-						       strlen(token) + len);
-				if (!new_brackets) {
+				ret = append(&brackets, delim, token);
+				if (ret < 0) {
 					free(brackets);
 					goto fail;
 				}
-				brackets = new_brackets;
-				if (len == 2)
-					strcat(brackets, " ");
-				strcat(brackets, token);
 				/* We only care about the last token */
 				field->arraylen = strtoul(token, NULL, 0);
 				free_token(token);
 				type = read_token(&token);
 				if (type == TEP_EVENT_NONE) {
+					free(brackets);
 					do_warning_event(event, "failed to find token");
 					goto fail;
 				}
@@ -1533,13 +1571,11 @@ static int event_read_fields(struct tep_event *event, struct tep_format_field **
 
 			free_token(token);
 
-			new_brackets = realloc(brackets, strlen(brackets) + 2);
-			if (!new_brackets) {
+			ret = append(&brackets, "", "]");
+			if (ret < 0) {
 				free(brackets);
 				goto fail;
 			}
-			brackets = new_brackets;
-			strcat(brackets, "]");
 
 			/* add brackets to type */
 
@@ -1549,34 +1585,23 @@ static int event_read_fields(struct tep_event *event, struct tep_format_field **
 			 * the format: type [] item;
 			 */
 			if (type == TEP_EVENT_ITEM) {
-				char *new_type;
-				new_type = realloc(field->type,
-						   strlen(field->type) +
-						   strlen(field->name) +
-						   strlen(brackets) + 2);
-				if (!new_type) {
+				ret = append(&field->type, " ", field->name);
+				if (ret < 0) {
 					free(brackets);
 					goto fail;
 				}
-				field->type = new_type;
-				strcat(field->type, " ");
-				strcat(field->type, field->name);
+				ret = append(&field->type, "", brackets);
+
 				size_dynamic = type_size(field->name);
 				free_token(field->name);
-				strcat(field->type, brackets);
 				field->name = field->alias = token;
 				type = read_token(&token);
 			} else {
-				char *new_type;
-				new_type = realloc(field->type,
-						   strlen(field->type) +
-						   strlen(brackets) + 1);
-				if (!new_type) {
+				ret = append(&field->type, "", brackets);
+				if (ret < 0) {
 					free(brackets);
 					goto fail;
 				}
-				field->type = new_type;
-				strcat(field->type, brackets);
 			}
 			free(brackets);
 		}
@@ -2013,19 +2038,16 @@ process_op(struct tep_event *event, struct tep_print_arg *arg, char **tok)
 		/* could just be a type pointer */
 		if ((strcmp(arg->op.op, "*") == 0) &&
 		    type == TEP_EVENT_DELIM && (strcmp(token, ")") == 0)) {
-			char *new_atom;
+			int ret;
 
 			if (left->type != TEP_PRINT_ATOM) {
 				do_warning_event(event, "bad pointer type");
 				goto out_free;
 			}
-			new_atom = realloc(left->atom.atom,
-					    strlen(left->atom.atom) + 3);
-			if (!new_atom)
+			ret = append(&left->atom.atom, " ", "*");
+			if (ret < 0)
 				goto out_warn_free;
 
-			left->atom.atom = new_atom;
-			strcat(left->atom.atom, " *");
 			free(arg->op.op);
 			*arg = *left;
 			free(left);
@@ -2806,6 +2828,7 @@ process_dynamic_array_len(struct tep_event *event, struct tep_print_arg *arg,
 	if (read_expected(TEP_EVENT_DELIM, ")") < 0)
 		goto out_err;
 
+	free_token(token);
 	type = read_token(&token);
 	*tok = token;
 
@@ -3118,18 +3141,15 @@ process_arg_token(struct tep_event *event, struct tep_print_arg *arg,
 		}
 		/* atoms can be more than one token long */
 		while (type == TEP_EVENT_ITEM) {
-			char *new_atom;
-			new_atom = realloc(atom,
-					   strlen(atom) + strlen(token) + 2);
-			if (!new_atom) {
+			int ret;
+
+			ret = append(&atom, " ", token);
+			if (ret < 0) {
 				free(atom);
 				*tok = NULL;
 				free_token(token);
 				return TEP_EVENT_ERROR;
 			}
-			atom = new_atom;
-			strcat(atom, " ");
-			strcat(atom, token);
 			free_token(token);
 			type = read_token_item(&token);
 		}
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index f3cbf86e51ac..20eed719542e 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -1228,8 +1228,10 @@ filter_event(struct tep_event_filter *filter, struct tep_event *event,
 	}
 
 	filter_type = add_filter_type(filter, event->id);
-	if (filter_type == NULL)
+	if (filter_type == NULL) {
+		free_arg(arg);
 		return TEP_ERRNO__MEM_ALLOC_FAILED;
+	}
 
 	if (filter_type->filter)
 		free_arg(filter_type->filter);
diff --git a/tools/objtool/arch/x86/lib/x86-opcode-map.txt b/tools/objtool/arch/x86/lib/x86-opcode-map.txt
index 0a0e9112f284..5cb9f009f2be 100644
--- a/tools/objtool/arch/x86/lib/x86-opcode-map.txt
+++ b/tools/objtool/arch/x86/lib/x86-opcode-map.txt
@@ -909,7 +909,7 @@ EndTable
 
 GrpTable: Grp3_2
 0: TEST Ev,Iz
-1:
+1: TEST Ev,Iz
 2: NOT Ev
 3: NEG Ev
 4: MUL rAX,Ev
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index f2f284bd4c85..c4d40e8c37d2 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -866,6 +866,12 @@ static int add_special_section_alts(struct objtool_file *file)
 		}
 
 		if (special_alt->group) {
+			if (!special_alt->orig_len) {
+				WARN_FUNC("empty alternative entry",
+					  orig_insn->sec, orig_insn->offset);
+				continue;
+			}
+
 			ret = handle_group_alt(file, special_alt, orig_insn,
 					       &new_insn);
 			if (ret)
@@ -1005,10 +1011,7 @@ static struct rela *find_switch_table(struct objtool_file *file,
 	 * it.
 	 */
 	for (;
-	     &insn->list != &file->insn_list &&
-	     insn->sec == func->sec &&
-	     insn->offset >= func->offset;
-
+	     &insn->list != &file->insn_list && insn->func && insn->func->pfunc == func;
 	     insn = insn->first_jump_src ?: list_prev_entry(insn, list)) {
 
 		if (insn != orig_insn && insn->type == INSN_JUMP_DYNAMIC)
@@ -1386,7 +1389,7 @@ static int update_insn_state_regs(struct instruction *insn, struct insn_state *s
 	struct cfi_reg *cfa = &state->cfa;
 	struct stack_op *op = &insn->stack_op;
 
-	if (cfa->base != CFI_SP)
+	if (cfa->base != CFI_SP && cfa->base != CFI_SP_INDIRECT)
 		return 0;
 
 	/* push */
@@ -2297,14 +2300,27 @@ static bool ignore_unreachable_insn(struct instruction *insn)
 	    !strcmp(insn->sec->name, ".altinstr_aux"))
 		return true;
 
+	if (!insn->func)
+		return false;
+
+	/*
+	 * CONFIG_UBSAN_TRAP inserts a UD2 when it sees
+	 * __builtin_unreachable().  The BUG() macro has an unreachable() after
+	 * the UD2, which causes GCC's undefined trap logic to emit another UD2
+	 * (or occasionally a JMP to UD2).
+	 */
+	if (list_prev_entry(insn, list)->dead_end &&
+	    (insn->type == INSN_BUG ||
+	     (insn->type == INSN_JUMP_UNCONDITIONAL &&
+	      insn->jump_dest && insn->jump_dest->type == INSN_BUG)))
+		return true;
+
 	/*
 	 * Check if this (or a subsequent) instruction is related to
 	 * CONFIG_UBSAN or CONFIG_KASAN.
 	 *
 	 * End the search at 5 instructions to avoid going into the weeds.
 	 */
-	if (!insn->func)
-		return false;
 	for (i = 0; i < 5; i++) {
 
 		if (is_kasan_insn(insn) || is_ubsan_insn(insn))
diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c
index 13ccf775a83a..ba4cbb1cdd63 100644
--- a/tools/objtool/orc_dump.c
+++ b/tools/objtool/orc_dump.c
@@ -66,7 +66,7 @@ int orc_dump(const char *_objname)
 	char *name;
 	size_t nr_sections;
 	Elf64_Addr orc_ip_addr = 0;
-	size_t shstrtab_idx;
+	size_t shstrtab_idx, strtab_idx = 0;
 	Elf *elf;
 	Elf_Scn *scn;
 	GElf_Shdr sh;
@@ -127,6 +127,8 @@ int orc_dump(const char *_objname)
 
 		if (!strcmp(name, ".symtab")) {
 			symtab = data;
+		} else if (!strcmp(name, ".strtab")) {
+			strtab_idx = i;
 		} else if (!strcmp(name, ".orc_unwind")) {
 			orc = data->d_buf;
 			orc_size = sh.sh_size;
@@ -138,7 +140,7 @@ int orc_dump(const char *_objname)
 		}
 	}
 
-	if (!symtab || !orc || !orc_ip)
+	if (!symtab || !strtab_idx || !orc || !orc_ip)
 		return 0;
 
 	if (orc_size % sizeof(*orc) != 0) {
@@ -159,21 +161,29 @@ int orc_dump(const char *_objname)
 				return -1;
 			}
 
-			scn = elf_getscn(elf, sym.st_shndx);
-			if (!scn) {
-				WARN_ELF("elf_getscn");
-				return -1;
-			}
-
-			if (!gelf_getshdr(scn, &sh)) {
-				WARN_ELF("gelf_getshdr");
-				return -1;
-			}
-
-			name = elf_strptr(elf, shstrtab_idx, sh.sh_name);
-			if (!name || !*name) {
-				WARN_ELF("elf_strptr");
-				return -1;
+			if (GELF_ST_TYPE(sym.st_info) == STT_SECTION) {
+				scn = elf_getscn(elf, sym.st_shndx);
+				if (!scn) {
+					WARN_ELF("elf_getscn");
+					return -1;
+				}
+
+				if (!gelf_getshdr(scn, &sh)) {
+					WARN_ELF("gelf_getshdr");
+					return -1;
+				}
+
+				name = elf_strptr(elf, shstrtab_idx, sh.sh_name);
+				if (!name) {
+					WARN_ELF("elf_strptr");
+					return -1;
+				}
+			} else {
+				name = elf_strptr(elf, strtab_idx, sym.st_name);
+				if (!name) {
+					WARN_ELF("elf_strptr");
+					return -1;
+				}
 			}
 
 			printf("%s+%llx:", name, (unsigned long long)rela.r_addend);
diff --git a/tools/pci/pcitest.c b/tools/pci/pcitest.c
index 49ddfa6f5a8c..32b7c6f9043d 100644
--- a/tools/pci/pcitest.c
+++ b/tools/pci/pcitest.c
@@ -129,6 +129,7 @@ static int run_test(struct pci_test *test)
 	}
 
 	fflush(stdout);
+	close(fd);
 	return (ret < 0) ? ret : 1 - ret; /* return 0 if test succeeded */
 }
 
@@ -212,7 +213,7 @@ usage:
 			"\t-r			Read buffer test\n"
 			"\t-w			Write buffer test\n"
 			"\t-c			Copy buffer test\n"
-			"\t-s <size>		Size of buffer {default: 100KB}\n",
+			"\t-s <size>		Size of buffer {default: 100KB}\n"
 			"\t-h			Print this help message\n",
 			argv[0]);
 		return -EINVAL;
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 7902a5681fc8..b8fc7d972be9 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -35,7 +35,7 @@ endif
 # Only pass canonical directory names as the output directory:
 #
 ifneq ($(O),)
-  FULL_O := $(shell readlink -f $(O) || echo $(O))
+  FULL_O := $(shell cd $(PWD); readlink -f $(O) || echo $(O))
 endif
 
 #
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 53e6f32c8bd7..45997e10a335 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -224,8 +224,17 @@ strip-libs  = $(filter-out -l%,$(1))
 
 PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
 
+# Python 3.8 changed the output of `python-config --ldflags` to not include the
+# '-lpythonX.Y' flag unless '--embed' is also passed. The feature check for
+# libpython fails if that flag is not included in LDFLAGS
+ifeq ($(shell $(PYTHON_CONFIG_SQ) --ldflags --embed 2>&1 1>/dev/null; echo $$?), 0)
+  PYTHON_CONFIG_LDFLAGS := --ldflags --embed
+else
+  PYTHON_CONFIG_LDFLAGS := --ldflags
+endif
+
 ifdef PYTHON_CONFIG
-  PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
+  PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) $(PYTHON_CONFIG_LDFLAGS) 2>/dev/null)
   PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
   PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
   PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null)
diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c
index 1ce6bdbda561..b9d471a0babd 100644
--- a/tools/perf/arch/arm/util/auxtrace.c
+++ b/tools/perf/arch/arm/util/auxtrace.c
@@ -54,7 +54,7 @@ struct auxtrace_record
 	struct perf_pmu	*cs_etm_pmu;
 	struct perf_evsel *evsel;
 	bool found_etm = false;
-	bool found_spe = false;
+	struct perf_pmu *found_spe = NULL;
 	static struct perf_pmu **arm_spe_pmus = NULL;
 	static int nr_spes = 0;
 	int i = 0;
@@ -72,12 +72,12 @@ struct auxtrace_record
 		    evsel->attr.type == cs_etm_pmu->type)
 			found_etm = true;
 
-		if (!nr_spes)
+		if (!nr_spes || found_spe)
 			continue;
 
 		for (i = 0; i < nr_spes; i++) {
 			if (evsel->attr.type == arm_spe_pmus[i]->type) {
-				found_spe = true;
+				found_spe = arm_spe_pmus[i];
 				break;
 			}
 		}
@@ -94,7 +94,7 @@ struct auxtrace_record
 
 #if defined(__aarch64__)
 	if (found_spe)
-		return arm_spe_recording_init(err, arm_spe_pmus[i]);
+		return arm_spe_recording_init(err, found_spe);
 #endif
 
 	/*
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index fddb3ced9db6..4aa6de1aa67d 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -2,6 +2,10 @@
 #ifndef BENCH_H
 #define BENCH_H
 
+#include <sys/time.h>
+
+extern struct timeval bench__start, bench__end, bench__runtime;
+
 /*
  * The madvise transparent hugepage constants were added in glibc
  * 2.13. For compatibility with older versions of glibc, define these
diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c
index 2af067859966..8a383c3e0967 100644
--- a/tools/perf/bench/epoll-ctl.c
+++ b/tools/perf/bench/epoll-ctl.c
@@ -33,7 +33,6 @@
 
 static unsigned int nthreads = 0;
 static unsigned int nsecs    = 8;
-struct timeval start, end, runtime;
 static bool done, __verbose, randomize;
 
 /*
@@ -92,8 +91,8 @@ static void toggle_done(int sig __maybe_unused,
 {
 	/* inform all threads that we're done for the day */
 	done = true;
-	gettimeofday(&end, NULL);
-	timersub(&end, &start, &runtime);
+	gettimeofday(&bench__end, NULL);
+	timersub(&bench__end, &bench__start, &bench__runtime);
 }
 
 static void nest_epollfd(void)
@@ -359,7 +358,7 @@ int bench_epoll_ctl(int argc, const char **argv)
 
 	threads_starting = nthreads;
 
-	gettimeofday(&start, NULL);
+	gettimeofday(&bench__start, NULL);
 
 	do_threads(worker, cpu);
 
diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c
index fe85448abd45..235e3aa28aad 100644
--- a/tools/perf/bench/epoll-wait.c
+++ b/tools/perf/bench/epoll-wait.c
@@ -88,7 +88,6 @@
 
 static unsigned int nthreads = 0;
 static unsigned int nsecs    = 8;
-struct timeval start, end, runtime;
 static bool wdone, done, __verbose, randomize, nonblocking;
 
 /*
@@ -274,8 +273,8 @@ static void toggle_done(int sig __maybe_unused,
 {
 	/* inform all threads that we're done for the day */
 	done = true;
-	gettimeofday(&end, NULL);
-	timersub(&end, &start, &runtime);
+	gettimeofday(&bench__end, NULL);
+	timersub(&bench__end, &bench__start, &bench__runtime);
 }
 
 static void print_summary(void)
@@ -285,7 +284,7 @@ static void print_summary(void)
 
 	printf("\nAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n",
 	       avg, rel_stddev_stats(stddev, avg),
-	       (int) runtime.tv_sec);
+	       (int)bench__runtime.tv_sec);
 }
 
 static int do_threads(struct worker *worker, struct cpu_map *cpu)
@@ -477,7 +476,7 @@ int bench_epoll_wait(int argc, const char **argv)
 
 	threads_starting = nthreads;
 
-	gettimeofday(&start, NULL);
+	gettimeofday(&bench__start, NULL);
 
 	do_threads(worker, cpu);
 
@@ -517,7 +516,7 @@ int bench_epoll_wait(int argc, const char **argv)
 		qsort(worker, nthreads, sizeof(struct worker), cmpworker);
 
 	for (i = 0; i < nthreads; i++) {
-		unsigned long t = worker[i].ops/runtime.tv_sec;
+		unsigned long t = worker[i].ops / bench__runtime.tv_sec;
 
 		update_stats(&throughput_stats, t);
 
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index 9aa3a674829b..ee9b28065109 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -35,7 +35,7 @@ static unsigned int nfutexes = 1024;
 static bool fshared = false, done = false, silent = false;
 static int futex_flag = 0;
 
-struct timeval start, end, runtime;
+struct timeval bench__start, bench__end, bench__runtime;
 static pthread_mutex_t thread_lock;
 static unsigned int threads_starting;
 static struct stats throughput_stats;
@@ -101,8 +101,8 @@ static void toggle_done(int sig __maybe_unused,
 {
 	/* inform all threads that we're done for the day */
 	done = true;
-	gettimeofday(&end, NULL);
-	timersub(&end, &start, &runtime);
+	gettimeofday(&bench__end, NULL);
+	timersub(&bench__end, &bench__start, &bench__runtime);
 }
 
 static void print_summary(void)
@@ -112,7 +112,7 @@ static void print_summary(void)
 
 	printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n",
 	       !silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg),
-	       (int) runtime.tv_sec);
+	       (int)bench__runtime.tv_sec);
 }
 
 int bench_futex_hash(int argc, const char **argv)
@@ -159,7 +159,7 @@ int bench_futex_hash(int argc, const char **argv)
 
 	threads_starting = nthreads;
 	pthread_attr_init(&thread_attr);
-	gettimeofday(&start, NULL);
+	gettimeofday(&bench__start, NULL);
 	for (i = 0; i < nthreads; i++) {
 		worker[i].tid = i;
 		worker[i].futex = calloc(nfutexes, sizeof(*worker[i].futex));
@@ -202,7 +202,7 @@ int bench_futex_hash(int argc, const char **argv)
 	pthread_mutex_destroy(&thread_lock);
 
 	for (i = 0; i < nthreads; i++) {
-		unsigned long t = worker[i].ops/runtime.tv_sec;
+		unsigned long t = worker[i].ops / bench__runtime.tv_sec;
 		update_stats(&throughput_stats, t);
 		if (!silent) {
 			if (nfutexes == 1)
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 8e9c4753e304..017609ae3590 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -35,7 +35,6 @@ static bool silent = false, multi = false;
 static bool done = false, fshared = false;
 static unsigned int nthreads = 0;
 static int futex_flag = 0;
-struct timeval start, end, runtime;
 static pthread_mutex_t thread_lock;
 static unsigned int threads_starting;
 static struct stats throughput_stats;
@@ -62,7 +61,7 @@ static void print_summary(void)
 
 	printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n",
 	       !silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg),
-	       (int) runtime.tv_sec);
+	       (int)bench__runtime.tv_sec);
 }
 
 static void toggle_done(int sig __maybe_unused,
@@ -71,8 +70,8 @@ static void toggle_done(int sig __maybe_unused,
 {
 	/* inform all threads that we're done for the day */
 	done = true;
-	gettimeofday(&end, NULL);
-	timersub(&end, &start, &runtime);
+	gettimeofday(&bench__end, NULL);
+	timersub(&bench__end, &bench__start, &bench__runtime);
 }
 
 static void *workerfn(void *arg)
@@ -183,7 +182,7 @@ int bench_futex_lock_pi(int argc, const char **argv)
 
 	threads_starting = nthreads;
 	pthread_attr_init(&thread_attr);
-	gettimeofday(&start, NULL);
+	gettimeofday(&bench__start, NULL);
 
 	create_threads(worker, thread_attr, cpu);
 	pthread_attr_destroy(&thread_attr);
@@ -209,7 +208,7 @@ int bench_futex_lock_pi(int argc, const char **argv)
 	pthread_mutex_destroy(&thread_lock);
 
 	for (i = 0; i < nthreads; i++) {
-		unsigned long t = worker[i].ops/runtime.tv_sec;
+		unsigned long t = worker[i].ops / bench__runtime.tv_sec;
 
 		update_stats(&throughput_stats, t);
 		if (!silent)
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index e8181ad7d088..e62006342b18 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -42,7 +42,7 @@ static bool done = false, silent = false, fshared = false;
 static pthread_mutex_t thread_lock;
 static pthread_cond_t thread_parent, thread_worker;
 static struct stats waketime_stats, wakeup_stats;
-static unsigned int ncpus, threads_starting, nthreads = 0;
+static unsigned int threads_starting, nthreads = 0;
 static int futex_flag = 0;
 
 static const struct option options[] = {
@@ -140,7 +140,7 @@ int bench_futex_wake(int argc, const char **argv)
 	sigaction(SIGINT, &act, NULL);
 
 	if (!nthreads)
-		nthreads = ncpus;
+		nthreads = cpu->nr;
 
 	worker = calloc(nthreads, sizeof(*worker));
 	if (!worker)
diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c
index 0251dd348124..4864fc67d01b 100644
--- a/tools/perf/bench/mem-functions.c
+++ b/tools/perf/bench/mem-functions.c
@@ -222,12 +222,8 @@ static int bench_mem_common(int argc, const char **argv, struct bench_mem_info *
 	return 0;
 }
 
-static u64 do_memcpy_cycles(const struct function *r, size_t size, void *src, void *dst)
+static void memcpy_prefault(memcpy_t fn, size_t size, void *src, void *dst)
 {
-	u64 cycle_start = 0ULL, cycle_end = 0ULL;
-	memcpy_t fn = r->fn.memcpy;
-	int i;
-
 	/* Make sure to always prefault zero pages even if MMAP_THRESH is crossed: */
 	memset(src, 0, size);
 
@@ -236,6 +232,15 @@ static u64 do_memcpy_cycles(const struct function *r, size_t size, void *src, vo
 	 * to not measure page fault overhead:
 	 */
 	fn(dst, src, size);
+}
+
+static u64 do_memcpy_cycles(const struct function *r, size_t size, void *src, void *dst)
+{
+	u64 cycle_start = 0ULL, cycle_end = 0ULL;
+	memcpy_t fn = r->fn.memcpy;
+	int i;
+
+	memcpy_prefault(fn, size, src, dst);
 
 	cycle_start = get_cycles();
 	for (i = 0; i < nr_loops; ++i)
@@ -251,11 +256,7 @@ static double do_memcpy_gettimeofday(const struct function *r, size_t size, void
 	memcpy_t fn = r->fn.memcpy;
 	int i;
 
-	/*
-	 * We prefault the freshly allocated memory range here,
-	 * to not measure page fault overhead:
-	 */
-	fn(dst, src, size);
+	memcpy_prefault(fn, size, src, dst);
 
 	BUG_ON(gettimeofday(&tv_start, NULL));
 	for (i = 0; i < nr_loops; ++i)
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 3c39b72e1e74..d1811190b702 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -587,8 +587,8 @@ tot_hitm_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 {
 	struct c2c_hist_entry *c2c_left;
 	struct c2c_hist_entry *c2c_right;
-	unsigned int tot_hitm_left;
-	unsigned int tot_hitm_right;
+	uint64_t tot_hitm_left;
+	uint64_t tot_hitm_right;
 
 	c2c_left  = container_of(left, struct c2c_hist_entry, he);
 	c2c_right = container_of(right, struct c2c_hist_entry, he);
@@ -621,7 +621,8 @@ __f ## _cmp(struct perf_hpp_fmt *fmt __maybe_unused,			\
 									\
 	c2c_left  = container_of(left, struct c2c_hist_entry, he);	\
 	c2c_right = container_of(right, struct c2c_hist_entry, he);	\
-	return c2c_left->stats.__f - c2c_right->stats.__f;		\
+	return (uint64_t) c2c_left->stats.__f -				\
+	       (uint64_t) c2c_right->stats.__f;				\
 }
 
 #define STAT_FN(__f)		\
@@ -674,7 +675,8 @@ ld_llcmiss_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 	c2c_left  = container_of(left, struct c2c_hist_entry, he);
 	c2c_right = container_of(right, struct c2c_hist_entry, he);
 
-	return llc_miss(&c2c_left->stats) - llc_miss(&c2c_right->stats);
+	return (uint64_t) llc_miss(&c2c_left->stats) -
+	       (uint64_t) llc_miss(&c2c_right->stats);
 }
 
 static uint64_t total_records(struct c2c_stats *stats)
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 2c376f5b2120..e3cfaab86c7a 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -363,6 +363,9 @@ static int perf_add_probe_events(struct perf_probe_event *pevs, int npevs)
 
 		for (k = 0; k < pev->ntevs; k++) {
 			struct probe_trace_event *tev = &pev->tevs[k];
+			/* Skipped events have no event name */
+			if (!tev->event)
+				continue;
 
 			/* We use tev's name for showing new events */
 			show_perf_probe_event(tev->group, tev->event, pev,
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index abd6779435d8..f063465ee253 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -170,24 +170,23 @@ static int hist_iter__branch_callback(struct hist_entry_iter *iter,
 {
 	struct hist_entry *he = iter->he;
 	struct report *rep = arg;
-	struct branch_info *bi;
+	struct branch_info *bi = he->branch_info;
 	struct perf_sample *sample = iter->sample;
 	struct perf_evsel *evsel = iter->evsel;
 	int err;
 
+	branch_type_count(&rep->brtype_stat, &bi->flags,
+			  bi->from.addr, bi->to.addr);
+
 	if (!ui__has_annotation() && !rep->symbol_ipc)
 		return 0;
 
-	bi = he->branch_info;
 	err = addr_map_symbol__inc_samples(&bi->from, sample, evsel);
 	if (err)
 		goto out;
 
 	err = addr_map_symbol__inc_samples(&bi->to, sample, evsel);
 
-	branch_type_count(&rep->brtype_stat, &bi->flags,
-			  bi->from.addr, bi->to.addr);
-
 out:
 	return err;
 }
@@ -449,8 +448,7 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report
 	if (rep->time_str)
 		ret += fprintf(fp, " (time slices: %s)", rep->time_str);
 
-	if (symbol_conf.show_ref_callgraph &&
-	    strstr(evname, "call-graph=no")) {
+	if (symbol_conf.show_ref_callgraph && evname && strstr(evname, "call-graph=no")) {
 		ret += fprintf(fp, ", show reference callgraph");
 	}
 
@@ -1018,6 +1016,7 @@ int cmd_report(int argc, const char **argv)
 	struct stat st;
 	bool has_br_stack = false;
 	int branch_mode = -1;
+	int last_key = 0;
 	bool branch_call_mode = false;
 #define CALLCHAIN_DEFAULT_OPT  "graph,0.5,caller,function,percent"
 	static const char report_callchain_help[] = "Display call graph (stack chain/backtrace):\n\n"
@@ -1376,7 +1375,8 @@ repeat:
 		sort_order = sort_tmp;
 	}
 
-	if (setup_sorting(session->evlist) < 0) {
+	if ((last_key != K_SWITCH_INPUT_DATA) &&
+	    (setup_sorting(session->evlist) < 0)) {
 		if (sort_order)
 			parse_options_usage(report_usage, options, "s", 1);
 		if (field_order)
@@ -1451,6 +1451,7 @@ repeat:
 	ret = __cmd_report(&report);
 	if (ret == K_SWITCH_INPUT_DATA) {
 		perf_session__delete(session);
+		last_key = K_SWITCH_INPUT_DATA;
 		goto repeat;
 	} else
 		ret = 0;
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 676734c1fb35..b218c44e7226 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -3500,11 +3500,6 @@ int cmd_script(int argc, const char **argv)
 		}
 	}
 
-	if (script.time_str && reltime) {
-		fprintf(stderr, "Don't combine --reltime with --time\n");
-		return -1;
-	}
-
 	if (itrace_synth_opts.callchain &&
 	    itrace_synth_opts.callchain_sz > scripting_max_stack)
 		scripting_max_stack = itrace_synth_opts.callchain_sz;
@@ -3764,10 +3759,11 @@ int cmd_script(int argc, const char **argv)
 		goto out_delete;
 
 	if (script.time_str) {
-		err = perf_time__parse_for_ranges(script.time_str, session,
+		err = perf_time__parse_for_ranges_reltime(script.time_str, session,
 						  &script.ptime_range,
 						  &script.range_size,
-						  &script.range_num);
+						  &script.range_num,
+						  reltime);
 		if (err < 0)
 			goto out_delete;
 	}
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
index 68618152ea2c..89e070727e1b 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
@@ -4,7 +4,7 @@
 		"EventCode": "128",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
-		"PublicDescription": "L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
+		"PublicDescription": "A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
 	},
 	{
 		"Unit": "CPU-M-CF",
diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index affed7d149be..b9a038b27d42 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -686,7 +686,8 @@ class CallGraphModel(CallGraphModelBase):
 						" FROM calls"
 						" INNER JOIN call_paths ON calls.call_path_id = call_paths.id"
 						" INNER JOIN symbols ON call_paths.symbol_id = symbols.id"
-						" WHERE symbols.name" + match +
+						" WHERE calls.id <> 0"
+						" AND symbols.name" + match +
 						" GROUP BY comm_id, thread_id, call_path_id"
 						" ORDER BY comm_id, thread_id, call_path_id")
 
@@ -834,7 +835,8 @@ class CallTreeModel(CallGraphModelBase):
 						" FROM calls"
 						" INNER JOIN call_paths ON calls.call_path_id = call_paths.id"
 						" INNER JOIN symbols ON call_paths.symbol_id = symbols.id"
-						" WHERE symbols.name" + match +
+						" WHERE calls.id <> 0"
+						" AND symbols.name" + match +
 						" ORDER BY comm_id, thread_id, call_time, calls.id")
 
 	def FindPath(self, query):
@@ -900,6 +902,7 @@ class TreeWindowBase(QMdiSubWindow):
 				child = self.model.index(row, 0, parent)
 				if child.internalPointer().dbid == dbid:
 					found = True
+					self.view.setExpanded(parent, True)
 					self.view.setCurrentIndex(child)
 					parent = child
 					break
diff --git a/tools/perf/tests/bp_account.c b/tools/perf/tests/bp_account.c
index 57fc544aedb0..92226772d3c4 100644
--- a/tools/perf/tests/bp_account.c
+++ b/tools/perf/tests/bp_account.c
@@ -21,7 +21,7 @@
 #include "perf.h"
 #include "cloexec.h"
 
-volatile long the_var;
+static volatile long the_var;
 
 static noinline int test_function(void)
 {
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index c1dd9b54dc6e..6cfd5eee2a95 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -2216,6 +2216,11 @@ static struct thread *hist_browser__selected_thread(struct hist_browser *browser
 	return browser->he_selection->thread;
 }
 
+static struct res_sample *hist_browser__selected_res_sample(struct hist_browser *browser)
+{
+	return browser->he_selection ? browser->he_selection->res_samples : NULL;
+}
+
 /* Check whether the browser is for 'top' or 'report' */
 static inline bool is_report_browser(void *timer)
 {
@@ -3043,6 +3048,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 
 				continue;
 			}
+			actions->ms.map = map;
 			top = pstack__peek(browser->pstack);
 			if (top == &browser->hists->dso_filter) {
 				/*
@@ -3158,16 +3164,16 @@ skip_annotation:
 					     &options[nr_options], NULL, NULL, evsel);
 		nr_options += add_res_sample_opt(browser, &actions[nr_options],
 						 &options[nr_options],
-				 hist_browser__selected_entry(browser)->res_samples,
-				 evsel, A_NORMAL);
+						 hist_browser__selected_res_sample(browser),
+						 evsel, A_NORMAL);
 		nr_options += add_res_sample_opt(browser, &actions[nr_options],
 						 &options[nr_options],
-				 hist_browser__selected_entry(browser)->res_samples,
-				 evsel, A_ASM);
+						 hist_browser__selected_res_sample(browser),
+						 evsel, A_ASM);
 		nr_options += add_res_sample_opt(browser, &actions[nr_options],
 						 &options[nr_options],
-				 hist_browser__selected_entry(browser)->res_samples,
-				 evsel, A_SOURCE);
+						 hist_browser__selected_res_sample(browser),
+						 evsel, A_SOURCE);
 		nr_options += add_switch_opt(browser, &actions[nr_options],
 					     &options[nr_options]);
 skip_scripting:
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index e059976d9d93..01d76a990cf5 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -41,6 +41,7 @@ char dso__symtab_origin(const struct dso *dso)
 		[DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO]	= 'D',
 		[DSO_BINARY_TYPE__FEDORA_DEBUGINFO]		= 'f',
 		[DSO_BINARY_TYPE__UBUNTU_DEBUGINFO]		= 'u',
+		[DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO]	= 'x',
 		[DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO]	= 'o',
 		[DSO_BINARY_TYPE__BUILDID_DEBUGINFO]		= 'b',
 		[DSO_BINARY_TYPE__SYSTEM_PATH_DSO]		= 'd',
@@ -123,6 +124,21 @@ int dso__read_binary_type_filename(const struct dso *dso,
 		snprintf(filename + len, size - len, "%s", dso->long_name);
 		break;
 
+	case DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO:
+		/*
+		 * Ubuntu can mixup /usr/lib with /lib, putting debuginfo in
+		 * /usr/lib/debug/lib when it is expected to be in
+		 * /usr/lib/debug/usr/lib
+		 */
+		if (strlen(dso->long_name) < 9 ||
+		    strncmp(dso->long_name, "/usr/lib/", 9)) {
+			ret = -1;
+			break;
+		}
+		len = __symbol__join_symfs(filename, size, "/usr/lib/debug");
+		snprintf(filename + len, size - len, "%s", dso->long_name + 4);
+		break;
+
 	case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO:
 	{
 		const char *last_slash;
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 6e3f63781e51..560c492c44b1 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -27,6 +27,7 @@ enum dso_binary_type {
 	DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO,
 	DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
 	DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
+	DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO,
 	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
 	DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
 	DSO_BINARY_TYPE__GUEST_KMODULE,
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 6a3eaf7d9353..725bf9270762 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -322,11 +322,11 @@ static const char *normalize_arch(char *arch)
 
 const char *perf_env__arch(struct perf_env *env)
 {
-	struct utsname uts;
 	char *arch_name;
 
 	if (!env || !env->arch) { /* Assume local operation */
-		if (uname(&uts) < 0)
+		static struct utsname uts = { .machine[0] = '\0', };
+		if (uts.machine[0] == '\0' && uname(&uts) < 0)
 			return NULL;
 		arch_name = uts.machine;
 	} else
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 76ff6c6d03b8..490b1c88f76a 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -331,10 +331,10 @@ static inline void perf_hpp__prepend_sort_field(struct perf_hpp_fmt *format)
 	list_for_each_entry_safe(format, tmp, &(_list)->sorts, sort_list)
 
 #define hists__for_each_format(hists, format) \
-	perf_hpp_list__for_each_format((hists)->hpp_list, fmt)
+	perf_hpp_list__for_each_format((hists)->hpp_list, format)
 
 #define hists__for_each_sort_list(hists, format) \
-	perf_hpp_list__for_each_sort_list((hists)->hpp_list, fmt)
+	perf_hpp_list__for_each_sort_list((hists)->hpp_list, format)
 
 extern struct perf_hpp_fmt perf_hpp__format[];
 
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 9d189e90fbdc..b030de6eb546 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -1120,6 +1120,7 @@ static int intel_pt_walk_fup(struct intel_pt_decoder *decoder)
 			return 0;
 		if (err == -EAGAIN ||
 		    intel_pt_fup_with_nlip(decoder, &intel_pt_insn, ip, err)) {
+			decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
 			if (intel_pt_fup_event(decoder))
 				return 0;
 			return -EAGAIN;
@@ -1783,17 +1784,13 @@ next:
 			}
 			if (decoder->set_fup_mwait)
 				no_tip = true;
+			if (no_tip)
+				decoder->pkt_state = INTEL_PT_STATE_FUP_NO_TIP;
+			else
+				decoder->pkt_state = INTEL_PT_STATE_FUP;
 			err = intel_pt_walk_fup(decoder);
-			if (err != -EAGAIN) {
-				if (err)
-					return err;
-				if (no_tip)
-					decoder->pkt_state =
-						INTEL_PT_STATE_FUP_NO_TIP;
-				else
-					decoder->pkt_state = INTEL_PT_STATE_FUP;
-				return 0;
-			}
+			if (err != -EAGAIN)
+				return err;
 			if (no_tip) {
 				no_tip = false;
 				break;
@@ -2382,15 +2379,11 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
 			err = intel_pt_walk_tip(decoder);
 			break;
 		case INTEL_PT_STATE_FUP:
-			decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
 			err = intel_pt_walk_fup(decoder);
 			if (err == -EAGAIN)
 				err = intel_pt_walk_fup_tip(decoder);
-			else if (!err)
-				decoder->pkt_state = INTEL_PT_STATE_FUP;
 			break;
 		case INTEL_PT_STATE_FUP_NO_TIP:
-			decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
 			err = intel_pt_walk_fup(decoder);
 			if (err == -EAGAIN)
 				err = intel_pt_walk_trace(decoder);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 081fe4bdebaa..68a5c9b0d06a 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -743,24 +743,6 @@ int machine__process_ksymbol(struct machine *machine __maybe_unused,
 	return machine__process_ksymbol_register(machine, event, sample);
 }
 
-static void dso__adjust_kmod_long_name(struct dso *dso, const char *filename)
-{
-	const char *dup_filename;
-
-	if (!filename || !dso || !dso->long_name)
-		return;
-	if (dso->long_name[0] != '[')
-		return;
-	if (!strchr(filename, '/'))
-		return;
-
-	dup_filename = strdup(filename);
-	if (!dup_filename)
-		return;
-
-	dso__set_long_name(dso, dup_filename, true);
-}
-
 struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 					const char *filename)
 {
@@ -772,15 +754,8 @@ struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 		return NULL;
 
 	map = map_groups__find_by_name(&machine->kmaps, m.name);
-	if (map) {
-		/*
-		 * If the map's dso is an offline module, give dso__load()
-		 * a chance to find the file path of that module by fixing
-		 * long_name.
-		 */
-		dso__adjust_kmod_long_name(map->dso, filename);
+	if (map)
 		goto out;
-	}
 
 	dso = machine__findnew_module_dso(machine, &m, filename);
 	if (dso == NULL)
@@ -1241,9 +1216,9 @@ static char *get_kernel_version(const char *root_dir)
 		return NULL;
 
 	tmp = fgets(version, sizeof(version), file);
-	if (!tmp)
-		*version = '\0';
 	fclose(file);
+	if (!tmp)
+		return NULL;
 
 	name = strstr(version, prefix);
 	if (!name)
@@ -2370,7 +2345,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	}
 
 check_calls:
-	if (callchain_param.order != ORDER_CALLEE) {
+	if (chain && callchain_param.order != ORDER_CALLEE) {
 		err = find_prev_cpumode(chain, thread, cursor, parent, root_al,
 					&cpumode, chain->nr - first_call);
 		if (err)
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index e6458145a428..b7c20d14a611 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -87,7 +87,7 @@ static inline bool replace_android_lib(const char *filename, char *newfilename)
 		return true;
 	}
 
-	if (!strncmp(filename, "/system/lib/", 11)) {
+	if (!strncmp(filename, "/system/lib/", 12)) {
 		char *ndk, *app;
 		const char *arch;
 		size_t ndk_length;
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 2ebf8673f8e9..787e5971519d 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -100,7 +100,7 @@ void exit_probe_symbol_maps(void)
 	symbol__exit();
 }
 
-static struct ref_reloc_sym *kernel_get_ref_reloc_sym(void)
+static struct ref_reloc_sym *kernel_get_ref_reloc_sym(struct map **pmap)
 {
 	/* kmap->ref_reloc_sym should be set if host_machine is initialized */
 	struct kmap *kmap;
@@ -112,6 +112,10 @@ static struct ref_reloc_sym *kernel_get_ref_reloc_sym(void)
 	kmap = map__kmap(map);
 	if (!kmap)
 		return NULL;
+
+	if (pmap)
+		*pmap = map;
+
 	return kmap->ref_reloc_sym;
 }
 
@@ -123,7 +127,7 @@ static int kernel_get_symbol_address_by_name(const char *name, u64 *addr,
 	struct map *map;
 
 	/* ref_reloc_sym is just a label. Need a special fix*/
-	reloc_sym = kernel_get_ref_reloc_sym();
+	reloc_sym = kernel_get_ref_reloc_sym(NULL);
 	if (reloc_sym && strcmp(name, reloc_sym->name) == 0)
 		*addr = (reloc) ? reloc_sym->addr : reloc_sym->unrelocated_addr;
 	else {
@@ -230,21 +234,22 @@ static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
 static bool kprobe_blacklist__listed(unsigned long address);
 static bool kprobe_warn_out_range(const char *symbol, unsigned long address)
 {
-	u64 etext_addr = 0;
-	int ret;
-
-	/* Get the address of _etext for checking non-probable text symbol */
-	ret = kernel_get_symbol_address_by_name("_etext", &etext_addr,
-						false, false);
+	struct map *map;
+	bool ret = false;
 
-	if (ret == 0 && etext_addr < address)
-		pr_warning("%s is out of .text, skip it.\n", symbol);
-	else if (kprobe_blacklist__listed(address))
+	map = kernel_get_module_map(NULL);
+	if (map) {
+		ret = address <= map->start || map->end < address;
+		if (ret)
+			pr_warning("%s is out of .text, skip it.\n", symbol);
+		map__put(map);
+	}
+	if (!ret && kprobe_blacklist__listed(address)) {
 		pr_warning("%s is blacklisted function, skip it.\n", symbol);
-	else
-		return false;
+		ret = true;
+	}
 
-	return true;
+	return ret;
 }
 
 /*
@@ -743,6 +748,7 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs,
 				       int ntevs)
 {
 	struct ref_reloc_sym *reloc_sym;
+	struct map *map;
 	char *tmp;
 	int i, skipped = 0;
 
@@ -751,7 +757,7 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs,
 		return post_process_offline_probe_trace_events(tevs, ntevs,
 						symbol_conf.vmlinux_name);
 
-	reloc_sym = kernel_get_ref_reloc_sym();
+	reloc_sym = kernel_get_ref_reloc_sym(&map);
 	if (!reloc_sym) {
 		pr_warning("Relocated base symbol is not found!\n");
 		return -EINVAL;
@@ -762,9 +768,13 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs,
 			continue;
 		if (tevs[i].point.retprobe && !kretprobe_offset_is_supported())
 			continue;
-		/* If we found a wrong one, mark it by NULL symbol */
+		/*
+		 * If we found a wrong one, mark it by NULL symbol.
+		 * Since addresses in debuginfo is same as objdump, we need
+		 * to convert it to addresses on memory.
+		 */
 		if (kprobe_warn_out_range(tevs[i].point.symbol,
-					  tevs[i].point.address)) {
+			map__objdump_2mem(map, tevs[i].point.address))) {
 			tmp = NULL;
 			skipped++;
 		} else {
@@ -1745,8 +1755,7 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev)
 	fmt1_str = strtok_r(argv0_str, ":", &fmt);
 	fmt2_str = strtok_r(NULL, "/", &fmt);
 	fmt3_str = strtok_r(NULL, " \t", &fmt);
-	if (fmt1_str == NULL || strlen(fmt1_str) != 1 || fmt2_str == NULL
-	    || fmt3_str == NULL) {
+	if (fmt1_str == NULL || fmt2_str == NULL || fmt3_str == NULL) {
 		semantic_error("Failed to parse event name: %s\n", argv[0]);
 		ret = -EINVAL;
 		goto out;
@@ -2911,7 +2920,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 	/* Note that the symbols in the kmodule are not relocated */
 	if (!pev->uprobes && !pev->target &&
 			(!pp->retprobe || kretprobe_offset_is_supported())) {
-		reloc_sym = kernel_get_ref_reloc_sym();
+		reloc_sym = kernel_get_ref_reloc_sym(NULL);
 		if (!reloc_sym) {
 			pr_warning("Relocated base symbol is not found!\n");
 			ret = -EINVAL;
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 6ef738baed4e..8f4cf2e2b5aa 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -100,6 +100,7 @@ enum dso_binary_type distro_dwarf_types[] = {
 	DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
 	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
 	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
+	DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO,
 	DSO_BINARY_TYPE__NOT_FOUND,
 };
 
@@ -598,38 +599,31 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod,
 				  const char *function,
 				  struct probe_trace_point *tp)
 {
-	Dwarf_Addr eaddr, highaddr;
+	Dwarf_Addr eaddr;
 	GElf_Sym sym;
 	const char *symbol;
 
 	/* Verify the address is correct */
-	if (dwarf_entrypc(sp_die, &eaddr) != 0) {
-		pr_warning("Failed to get entry address of %s\n",
-			   dwarf_diename(sp_die));
-		return -ENOENT;
-	}
-	if (dwarf_highpc(sp_die, &highaddr) != 0) {
-		pr_warning("Failed to get end address of %s\n",
-			   dwarf_diename(sp_die));
-		return -ENOENT;
-	}
-	if (paddr > highaddr) {
-		pr_warning("Offset specified is greater than size of %s\n",
+	if (!dwarf_haspc(sp_die, paddr)) {
+		pr_warning("Specified offset is out of %s\n",
 			   dwarf_diename(sp_die));
 		return -EINVAL;
 	}
 
-	symbol = dwarf_diename(sp_die);
-	if (!symbol) {
-		/* Try to get the symbol name from symtab */
+	if (dwarf_entrypc(sp_die, &eaddr) == 0) {
+		/* If the DIE has entrypc, use it. */
+		symbol = dwarf_diename(sp_die);
+	} else {
+		/* Try to get actual symbol name and address from symtab */
 		symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL);
-		if (!symbol) {
-			pr_warning("Failed to find symbol at 0x%lx\n",
-				   (unsigned long)paddr);
-			return -ENOENT;
-		}
 		eaddr = sym.st_value;
 	}
+	if (!symbol) {
+		pr_warning("Failed to find symbol at 0x%lx\n",
+			   (unsigned long)paddr);
+		return -ENOENT;
+	}
+
 	tp->offset = (unsigned long)(paddr - eaddr);
 	tp->address = (unsigned long)paddr;
 	tp->symbol = strdup(symbol);
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 94bed4031def..5280e84b9318 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -648,7 +648,7 @@ static void print_aggr(struct perf_stat_config *config,
 	int s;
 	bool first;
 
-	if (!(config->aggr_map || config->aggr_get_id))
+	if (!config->aggr_map || !config->aggr_get_id)
 		return;
 
 	aggr_update_shadow(config, evlist);
@@ -1120,7 +1120,7 @@ static void print_percore(struct perf_stat_config *config,
 	int s;
 	bool first = true;
 
-	if (!(config->aggr_map || config->aggr_get_id))
+	if (!config->aggr_map || !config->aggr_get_id)
 		return;
 
 	for (s = 0; s < config->aggr_map->nr; s++) {
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index e2ce6021e6c4..17cd7e4a645e 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -358,8 +358,10 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 	 * interval mode, otherwise overall avg running
 	 * averages will be shown for each interval.
 	 */
-	if (config->interval)
-		init_stats(ps->res_stats);
+	if (config->interval) {
+		for (i = 0; i < 3; i++)
+			init_stats(&ps->res_stats[i]);
+	}
 
 	if (counter->per_pkg)
 		zero_per_pkg(counter);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 3b49eb4e3ed9..ad893b4bd526 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -70,6 +70,7 @@ static enum dso_binary_type binary_type_symtab[] = {
 	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
 	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP,
 	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
+	DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO,
 	DSO_BINARY_TYPE__NOT_FOUND,
 };
 
@@ -1432,6 +1433,7 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
 	case DSO_BINARY_TYPE__SYSTEM_PATH_DSO:
 	case DSO_BINARY_TYPE__FEDORA_DEBUGINFO:
 	case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO:
+	case DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO:
 	case DSO_BINARY_TYPE__BUILDID_DEBUGINFO:
 	case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO:
 		return !kmod && dso->kernel == DSO_TYPE_USER;
diff --git a/tools/perf/util/time-utils.c b/tools/perf/util/time-utils.c
index 20663a460df3..ff07ea319406 100644
--- a/tools/perf/util/time-utils.c
+++ b/tools/perf/util/time-utils.c
@@ -398,53 +398,75 @@ bool perf_time__ranges_skip_sample(struct perf_time_interval *ptime_buf,
 	return (i == num) ? true : false;
 }
 
-int perf_time__parse_for_ranges(const char *time_str,
+int perf_time__parse_for_ranges_reltime(const char *time_str,
 				struct perf_session *session,
 				struct perf_time_interval **ranges,
-				int *range_size, int *range_num)
+				int *range_size, int *range_num,
+				bool reltime)
 {
+	bool has_percent = strchr(time_str, '%');
 	struct perf_time_interval *ptime_range;
-	int size, num, ret;
+	int size, num, ret = -EINVAL;
 
 	ptime_range = perf_time__range_alloc(time_str, &size);
 	if (!ptime_range)
 		return -ENOMEM;
 
-	if (perf_time__parse_str(ptime_range, time_str) != 0) {
+	if (has_percent || reltime) {
 		if (session->evlist->first_sample_time == 0 &&
 		    session->evlist->last_sample_time == 0) {
 			pr_err("HINT: no first/last sample time found in perf data.\n"
 			       "Please use latest perf binary to execute 'perf record'\n"
 			       "(if '--buildid-all' is enabled, please set '--timestamp-boundary').\n");
-			ret = -EINVAL;
 			goto error;
 		}
+	}
 
+	if (has_percent) {
 		num = perf_time__percent_parse_str(
 				ptime_range, size,
 				time_str,
 				session->evlist->first_sample_time,
 				session->evlist->last_sample_time);
 
-		if (num < 0) {
-			pr_err("Invalid time string\n");
-			ret = -EINVAL;
-			goto error;
-		}
+		if (num < 0)
+			goto error_invalid;
 	} else {
+		if (perf_time__parse_str(ptime_range, time_str))
+			goto error_invalid;
 		num = 1;
 	}
 
+	if (reltime) {
+		int i;
+
+		for (i = 0; i < num; i++) {
+			ptime_range[i].start += session->evlist->first_sample_time;
+			ptime_range[i].end += session->evlist->first_sample_time;
+		}
+	}
+
 	*range_size = size;
 	*range_num = num;
 	*ranges = ptime_range;
 	return 0;
 
+error_invalid:
+	pr_err("Invalid time string\n");
 error:
 	free(ptime_range);
 	return ret;
 }
 
+int perf_time__parse_for_ranges(const char *time_str,
+				struct perf_session *session,
+				struct perf_time_interval **ranges,
+				int *range_size, int *range_num)
+{
+	return perf_time__parse_for_ranges_reltime(time_str, session, ranges,
+					range_size, range_num, false);
+}
+
 int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz)
 {
 	u64  sec = timestamp / NSEC_PER_SEC;
diff --git a/tools/perf/util/time-utils.h b/tools/perf/util/time-utils.h
index 72a42ea1d513..e07b698172f5 100644
--- a/tools/perf/util/time-utils.h
+++ b/tools/perf/util/time-utils.h
@@ -25,6 +25,11 @@ bool perf_time__ranges_skip_sample(struct perf_time_interval *ptime_buf,
 
 struct perf_session;
 
+int perf_time__parse_for_ranges_reltime(const char *str, struct perf_session *session,
+				struct perf_time_interval **ranges,
+				int *range_size, int *range_num,
+				bool reltime);
+
 int perf_time__parse_for_ranges(const char *str, struct perf_session *session,
 				struct perf_time_interval **ranges,
 				int *range_size, int *range_num);
diff --git a/tools/power/acpi/Makefile.config b/tools/power/acpi/Makefile.config
index 0111d246d1ca..54a2857c2510 100644
--- a/tools/power/acpi/Makefile.config
+++ b/tools/power/acpi/Makefile.config
@@ -15,7 +15,7 @@ include $(srctree)/../../scripts/Makefile.include
 
 OUTPUT=$(srctree)/
 ifeq ("$(origin O)", "command line")
-	OUTPUT := $(O)/power/acpi/
+	OUTPUT := $(O)/tools/power/acpi/
 endif
 #$(info Determined 'OUTPUT' to be $(OUTPUT))
 
diff --git a/tools/power/cpupower/lib/cpufreq.c b/tools/power/cpupower/lib/cpufreq.c
index 2f55d4d23446..6e04304560ca 100644
--- a/tools/power/cpupower/lib/cpufreq.c
+++ b/tools/power/cpupower/lib/cpufreq.c
@@ -332,21 +332,74 @@ void cpufreq_put_available_governors(struct cpufreq_available_governors *any)
 }
 
 
-struct cpufreq_frequencies
-*cpufreq_get_frequencies(const char *type, unsigned int cpu)
+struct cpufreq_available_frequencies
+*cpufreq_get_available_frequencies(unsigned int cpu)
 {
-	struct cpufreq_frequencies *first = NULL;
-	struct cpufreq_frequencies *current = NULL;
+	struct cpufreq_available_frequencies *first = NULL;
+	struct cpufreq_available_frequencies *current = NULL;
 	char one_value[SYSFS_PATH_MAX];
 	char linebuf[MAX_LINE_LEN];
-	char fname[MAX_LINE_LEN];
 	unsigned int pos, i;
 	unsigned int len;
 
-	snprintf(fname, MAX_LINE_LEN, "scaling_%s_frequencies", type);
+	len = sysfs_cpufreq_read_file(cpu, "scaling_available_frequencies",
+				      linebuf, sizeof(linebuf));
+	if (len == 0)
+		return NULL;
 
-	len = sysfs_cpufreq_read_file(cpu, fname,
-				linebuf, sizeof(linebuf));
+	pos = 0;
+	for (i = 0; i < len; i++) {
+		if (linebuf[i] == ' ' || linebuf[i] == '\n') {
+			if (i - pos < 2)
+				continue;
+			if (i - pos >= SYSFS_PATH_MAX)
+				goto error_out;
+			if (current) {
+				current->next = malloc(sizeof(*current));
+				if (!current->next)
+					goto error_out;
+				current = current->next;
+			} else {
+				first = malloc(sizeof(*first));
+				if (!first)
+					goto error_out;
+				current = first;
+			}
+			current->first = first;
+			current->next = NULL;
+
+			memcpy(one_value, linebuf + pos, i - pos);
+			one_value[i - pos] = '\0';
+			if (sscanf(one_value, "%lu", &current->frequency) != 1)
+				goto error_out;
+
+			pos = i + 1;
+		}
+	}
+
+	return first;
+
+ error_out:
+	while (first) {
+		current = first->next;
+		free(first);
+		first = current;
+	}
+	return NULL;
+}
+
+struct cpufreq_available_frequencies
+*cpufreq_get_boost_frequencies(unsigned int cpu)
+{
+	struct cpufreq_available_frequencies *first = NULL;
+	struct cpufreq_available_frequencies *current = NULL;
+	char one_value[SYSFS_PATH_MAX];
+	char linebuf[MAX_LINE_LEN];
+	unsigned int pos, i;
+	unsigned int len;
+
+	len = sysfs_cpufreq_read_file(cpu, "scaling_boost_frequencies",
+				      linebuf, sizeof(linebuf));
 	if (len == 0)
 		return NULL;
 
@@ -391,9 +444,9 @@ struct cpufreq_frequencies
 	return NULL;
 }
 
-void cpufreq_put_frequencies(struct cpufreq_frequencies *any)
+void cpufreq_put_available_frequencies(struct cpufreq_available_frequencies *any)
 {
-	struct cpufreq_frequencies *tmp, *next;
+	struct cpufreq_available_frequencies *tmp, *next;
 
 	if (!any)
 		return;
@@ -406,6 +459,11 @@ void cpufreq_put_frequencies(struct cpufreq_frequencies *any)
 	}
 }
 
+void cpufreq_put_boost_frequencies(struct cpufreq_available_frequencies *any)
+{
+	cpufreq_put_available_frequencies(any);
+}
+
 static struct cpufreq_affected_cpus *sysfs_get_cpu_list(unsigned int cpu,
 							const char *file)
 {
diff --git a/tools/power/cpupower/lib/cpufreq.h b/tools/power/cpupower/lib/cpufreq.h
index a55f0d19215b..95f4fd9e2656 100644
--- a/tools/power/cpupower/lib/cpufreq.h
+++ b/tools/power/cpupower/lib/cpufreq.h
@@ -20,10 +20,10 @@ struct cpufreq_available_governors {
 	struct cpufreq_available_governors *first;
 };
 
-struct cpufreq_frequencies {
+struct cpufreq_available_frequencies {
 	unsigned long frequency;
-	struct cpufreq_frequencies *next;
-	struct cpufreq_frequencies *first;
+	struct cpufreq_available_frequencies *next;
+	struct cpufreq_available_frequencies *first;
 };
 
 
@@ -124,11 +124,17 @@ void cpufreq_put_available_governors(
  * cpufreq_put_frequencies after use.
  */
 
-struct cpufreq_frequencies
-*cpufreq_get_frequencies(const char *type, unsigned int cpu);
+struct cpufreq_available_frequencies
+*cpufreq_get_available_frequencies(unsigned int cpu);
 
-void cpufreq_put_frequencies(
-		struct cpufreq_frequencies *first);
+void cpufreq_put_available_frequencies(
+		struct cpufreq_available_frequencies *first);
+
+struct cpufreq_available_frequencies
+*cpufreq_get_boost_frequencies(unsigned int cpu);
+
+void cpufreq_put_boost_frequencies(
+		struct cpufreq_available_frequencies *first);
 
 
 /* determine affected CPUs
diff --git a/tools/power/cpupower/utils/cpufreq-info.c b/tools/power/cpupower/utils/cpufreq-info.c
index e63cf55f81cf..6efc0f6b1b11 100644
--- a/tools/power/cpupower/utils/cpufreq-info.c
+++ b/tools/power/cpupower/utils/cpufreq-info.c
@@ -244,14 +244,14 @@ static int get_boost_mode_x86(unsigned int cpu)
 
 static int get_boost_mode(unsigned int cpu)
 {
-	struct cpufreq_frequencies *freqs;
+	struct cpufreq_available_frequencies *freqs;
 
 	if (cpupower_cpu_info.vendor == X86_VENDOR_AMD ||
 	    cpupower_cpu_info.vendor == X86_VENDOR_HYGON ||
 	    cpupower_cpu_info.vendor == X86_VENDOR_INTEL)
 		return get_boost_mode_x86(cpu);
 
-	freqs = cpufreq_get_frequencies("boost", cpu);
+	freqs = cpufreq_get_boost_frequencies(cpu);
 	if (freqs) {
 		printf(_("  boost frequency steps: "));
 		while (freqs->next) {
@@ -261,7 +261,7 @@ static int get_boost_mode(unsigned int cpu)
 		}
 		print_speed(freqs->frequency);
 		printf("\n");
-		cpufreq_put_frequencies(freqs);
+		cpufreq_put_available_frequencies(freqs);
 	}
 
 	return 0;
@@ -475,7 +475,7 @@ static int get_latency(unsigned int cpu, unsigned int human)
 
 static void debug_output_one(unsigned int cpu)
 {
-	struct cpufreq_frequencies *freqs;
+	struct cpufreq_available_frequencies *freqs;
 
 	get_driver(cpu);
 	get_related_cpus(cpu);
@@ -483,7 +483,7 @@ static void debug_output_one(unsigned int cpu)
 	get_latency(cpu, 1);
 	get_hardware_limits(cpu, 1);
 
-	freqs = cpufreq_get_frequencies("available", cpu);
+	freqs = cpufreq_get_available_frequencies(cpu);
 	if (freqs) {
 		printf(_("  available frequency steps:  "));
 		while (freqs->next) {
@@ -493,7 +493,7 @@ static void debug_output_one(unsigned int cpu)
 		}
 		print_speed(freqs->frequency);
 		printf("\n");
-		cpufreq_put_frequencies(freqs);
+		cpufreq_put_available_frequencies(freqs);
 	}
 
 	get_available_governors(cpu);
diff --git a/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c b/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c
index 3f893b99b337..555cb338a71a 100644
--- a/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c
+++ b/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c
@@ -82,7 +82,7 @@ static struct pci_access *pci_acc;
 static struct pci_dev *amd_fam14h_pci_dev;
 static int nbp1_entered;
 
-struct timespec start_time;
+static struct timespec start_time;
 static unsigned long long timediff;
 
 #ifdef DEBUG
diff --git a/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c b/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c
index f634aeb65c5f..7fb4f7a291ad 100644
--- a/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c
+++ b/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c
@@ -19,7 +19,7 @@ struct cpuidle_monitor cpuidle_sysfs_monitor;
 
 static unsigned long long **previous_count;
 static unsigned long long **current_count;
-struct timespec start_time;
+static struct timespec start_time;
 static unsigned long long timediff;
 
 static int cpuidle_get_count_percent(unsigned int id, double *percent,
diff --git a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c
index d3c3e6e7aa26..3d54fd433626 100644
--- a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c
+++ b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c
@@ -27,6 +27,8 @@ struct cpuidle_monitor *all_monitors[] = {
 0
 };
 
+int cpu_count;
+
 static struct cpuidle_monitor *monitors[MONITORS_MAX];
 static unsigned int avail_monitors;
 
diff --git a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h
index a2d901d3bfaf..eafef38f1982 100644
--- a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h
+++ b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h
@@ -25,7 +25,7 @@
 #endif
 #define CSTATE_DESC_LEN 60
 
-int cpu_count;
+extern int cpu_count;
 
 /* Hard to define the right names ...: */
 enum power_range_e {
diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index 045f5f7d68ab..7354392ce260 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -15,7 +15,7 @@ override CFLAGS +=	-DINTEL_FAMILY_HEADER='"../../../../arch/x86/include/asm/inte
 
 %: %.c
 	@mkdir -p $(BUILD_OUTPUT)
-	$(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ $(LDFLAGS)
+	$(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ $(LDFLAGS) -lcap
 
 .PHONY : clean
 clean :
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 5c0154cf190c..9ed09e129e00 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -30,7 +30,7 @@
 #include <sched.h>
 #include <time.h>
 #include <cpuid.h>
-#include <linux/capability.h>
+#include <sys/capability.h>
 #include <errno.h>
 #include <math.h>
 
@@ -302,6 +302,10 @@ int *irqs_per_cpu;		/* indexed by cpu_num */
 
 void setup_all_buffers(void);
 
+char *sys_lpi_file;
+char *sys_lpi_file_sysfs = "/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us";
+char *sys_lpi_file_debugfs = "/sys/kernel/debug/pmc_core/slp_s0_residency_usec";
+
 int cpu_is_not_present(int cpu)
 {
 	return !CPU_ISSET_S(cpu, cpu_present_setsize, cpu_present_set);
@@ -2909,8 +2913,6 @@ int snapshot_gfx_mhz(void)
  *
  * record snapshot of
  * /sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us
- *
- * return 1 if config change requires a restart, else return 0
  */
 int snapshot_cpu_lpi_us(void)
 {
@@ -2934,17 +2936,14 @@ int snapshot_cpu_lpi_us(void)
 /*
  * snapshot_sys_lpi()
  *
- * record snapshot of
- * /sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us
- *
- * return 1 if config change requires a restart, else return 0
+ * record snapshot of sys_lpi_file
  */
 int snapshot_sys_lpi_us(void)
 {
 	FILE *fp;
 	int retval;
 
-	fp = fopen_or_die("/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us", "r");
+	fp = fopen_or_die(sys_lpi_file, "r");
 
 	retval = fscanf(fp, "%lld", &cpuidle_cur_sys_lpi_us);
 	if (retval != 1) {
@@ -3137,28 +3136,42 @@ void check_dev_msr()
 			err(-5, "no /dev/cpu/0/msr, Try \"# modprobe msr\" ");
 }
 
-void check_permissions()
+/*
+ * check for CAP_SYS_RAWIO
+ * return 0 on success
+ * return 1 on fail
+ */
+int check_for_cap_sys_rawio(void)
 {
-	struct __user_cap_header_struct cap_header_data;
-	cap_user_header_t cap_header = &cap_header_data;
-	struct __user_cap_data_struct cap_data_data;
-	cap_user_data_t cap_data = &cap_data_data;
-	extern int capget(cap_user_header_t hdrp, cap_user_data_t datap);
-	int do_exit = 0;
-	char pathname[32];
+	cap_t caps;
+	cap_flag_value_t cap_flag_value;
 
-	/* check for CAP_SYS_RAWIO */
-	cap_header->pid = getpid();
-	cap_header->version = _LINUX_CAPABILITY_VERSION;
-	if (capget(cap_header, cap_data) < 0)
-		err(-6, "capget(2) failed");
+	caps = cap_get_proc();
+	if (caps == NULL)
+		err(-6, "cap_get_proc\n");
 
-	if ((cap_data->effective & (1 << CAP_SYS_RAWIO)) == 0) {
-		do_exit++;
+	if (cap_get_flag(caps, CAP_SYS_RAWIO, CAP_EFFECTIVE, &cap_flag_value))
+		err(-6, "cap_get\n");
+
+	if (cap_flag_value != CAP_SET) {
 		warnx("capget(CAP_SYS_RAWIO) failed,"
 			" try \"# setcap cap_sys_rawio=ep %s\"", progname);
+		return 1;
 	}
 
+	if (cap_free(caps) == -1)
+		err(-6, "cap_free\n");
+
+	return 0;
+}
+void check_permissions(void)
+{
+	int do_exit = 0;
+	char pathname[32];
+
+	/* check for CAP_SYS_RAWIO */
+	do_exit += check_for_cap_sys_rawio();
+
 	/* test file permissions */
 	sprintf(pathname, "/dev/cpu/%d/msr", base_cpu);
 	if (euidaccess(pathname, R_OK)) {
@@ -4886,10 +4899,16 @@ void process_cpuid()
 	else
 		BIC_NOT_PRESENT(BIC_CPU_LPI);
 
-	if (!access("/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us", R_OK))
+	if (!access(sys_lpi_file_sysfs, R_OK)) {
+		sys_lpi_file = sys_lpi_file_sysfs;
 		BIC_PRESENT(BIC_SYS_LPI);
-	else
+	} else if (!access(sys_lpi_file_debugfs, R_OK)) {
+		sys_lpi_file = sys_lpi_file_debugfs;
+		BIC_PRESENT(BIC_SYS_LPI);
+	} else {
+		sys_lpi_file_sysfs = NULL;
 		BIC_NOT_PRESENT(BIC_SYS_LPI);
+	}
 
 	if (!quiet)
 		decode_misc_feature_control();
@@ -5302,9 +5321,9 @@ int add_counter(unsigned int msr_num, char *path, char *name,
 	}
 
 	msrp->msr_num = msr_num;
-	strncpy(msrp->name, name, NAME_BYTES);
+	strncpy(msrp->name, name, NAME_BYTES - 1);
 	if (path)
-		strncpy(msrp->path, path, PATH_BYTES);
+		strncpy(msrp->path, path, PATH_BYTES - 1);
 	msrp->width = width;
 	msrp->type = type;
 	msrp->format = format;
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index 495066bafbe3..8fc6b1ca47dc 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -1,8 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 ifneq ($(O),)
 ifeq ($(origin O), command line)
-	dummy := $(if $(shell test -d $(O) || echo $(O)),$(error O=$(O) does not exist),)
-	ABSOLUTE_O := $(shell cd $(O) ; pwd)
+	dummy := $(if $(shell cd $(PWD); test -d $(O) || echo $(O)),$(error O=$(O) does not exist),)
+	ABSOLUTE_O := $(shell cd $(PWD); cd $(O) ; pwd)
 	OUTPUT := $(ABSOLUTE_O)/$(if $(subdir),$(subdir)/)
 	COMMAND_O := O=$(ABSOLUTE_O)
 ifeq ($(objtree),)
diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index 220d04f958a6..42b6cd41d2ea 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -1383,7 +1383,7 @@ sub reboot {
 
     } else {
 	# Make sure everything has been written to disk
-	run_ssh("sync");
+	run_ssh("sync", 10);
 
 	if (defined($time)) {
 	    start_monitor;
diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild
index c4a9196d794c..cb80d3b81179 100644
--- a/tools/testing/nvdimm/Kbuild
+++ b/tools/testing/nvdimm/Kbuild
@@ -21,8 +21,8 @@ DRIVERS := ../../../drivers
 NVDIMM_SRC := $(DRIVERS)/nvdimm
 ACPI_SRC := $(DRIVERS)/acpi/nfit
 DAX_SRC := $(DRIVERS)/dax
-ccflags-y := -I$(src)/$(NVDIMM_SRC)/
-ccflags-y += -I$(src)/$(ACPI_SRC)/
+ccflags-y := -I$(srctree)/drivers/nvdimm/
+ccflags-y += -I$(srctree)/drivers/acpi/nfit/
 
 obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o
 obj-$(CONFIG_BLK_DEV_PMEM) += nd_pmem.o
diff --git a/tools/testing/nvdimm/test/Kbuild b/tools/testing/nvdimm/test/Kbuild
index fb3c3d7cdb9b..75baebf8f4ba 100644
--- a/tools/testing/nvdimm/test/Kbuild
+++ b/tools/testing/nvdimm/test/Kbuild
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
-ccflags-y := -I$(src)/../../../../drivers/nvdimm/
-ccflags-y += -I$(src)/../../../../drivers/acpi/nfit/
+ccflags-y := -I$(srctree)/drivers/nvdimm/
+ccflags-y += -I$(srctree)/drivers/acpi/nfit/
 
 obj-m += nfit_test.o
 obj-m += nfit_test_iomap.o
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 507e6f4cbb53..33989e69da24 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -3165,7 +3165,9 @@ static __init int nfit_test_init(void)
 	mcsafe_test();
 	dax_pmem_test();
 	dax_pmem_core_test();
+#ifdef CONFIG_DEV_DAX_PMEM_COMPAT
 	dax_pmem_compat_test();
+#endif
 
 	nfit_test_setup(nfit_test_lookup, nfit_test_evaluate_dsm);
 
diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
index 397d6b612502..aa6abfe0749c 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -7,8 +7,8 @@ LDLIBS+= -lpthread -lurcu
 TARGETS = main idr-test multiorder xarray
 CORE_OFILES := xarray.o radix-tree.o idr.o linux.o test.o find_bit.o bitmap.o
 OFILES = main.o $(CORE_OFILES) regression1.o regression2.o regression3.o \
-	 regression4.o \
-	 tag_check.o multiorder.o idr-test.o iteration_check.o benchmark.o
+	 regression4.o tag_check.o multiorder.o idr-test.o iteration_check.o \
+	 iteration_check_2.o benchmark.o
 
 ifndef SHIFT
 	SHIFT=3
diff --git a/tools/testing/radix-tree/iteration_check_2.c b/tools/testing/radix-tree/iteration_check_2.c
new file mode 100644
index 000000000000..aac5c50a3674
--- /dev/null
+++ b/tools/testing/radix-tree/iteration_check_2.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * iteration_check_2.c: Check that deleting a tagged entry doesn't cause
+ * an RCU walker to finish early.
+ * Copyright (c) 2020 Oracle
+ * Author: Matthew Wilcox <willy@infradead.org>
+ */
+#include <pthread.h>
+#include "test.h"
+
+static volatile bool test_complete;
+
+static void *iterator(void *arg)
+{
+	XA_STATE(xas, arg, 0);
+	void *entry;
+
+	rcu_register_thread();
+
+	while (!test_complete) {
+		xas_set(&xas, 0);
+		rcu_read_lock();
+		xas_for_each_marked(&xas, entry, ULONG_MAX, XA_MARK_0)
+			;
+		rcu_read_unlock();
+		assert(xas.xa_index >= 100);
+	}
+
+	rcu_unregister_thread();
+	return NULL;
+}
+
+static void *throbber(void *arg)
+{
+	struct xarray *xa = arg;
+
+	rcu_register_thread();
+
+	while (!test_complete) {
+		int i;
+
+		for (i = 0; i < 100; i++) {
+			xa_store(xa, i, xa_mk_value(i), GFP_KERNEL);
+			xa_set_mark(xa, i, XA_MARK_0);
+		}
+		for (i = 0; i < 100; i++)
+			xa_erase(xa, i);
+	}
+
+	rcu_unregister_thread();
+	return NULL;
+}
+
+void iteration_test2(unsigned test_duration)
+{
+	pthread_t threads[2];
+	DEFINE_XARRAY(array);
+	int i;
+
+	printv(1, "Running iteration test 2 for %d seconds\n", test_duration);
+
+	test_complete = false;
+
+	xa_store(&array, 100, xa_mk_value(100), GFP_KERNEL);
+	xa_set_mark(&array, 100, XA_MARK_0);
+
+	if (pthread_create(&threads[0], NULL, iterator, &array)) {
+		perror("create iterator thread");
+		exit(1);
+	}
+	if (pthread_create(&threads[1], NULL, throbber, &array)) {
+		perror("create throbber thread");
+		exit(1);
+	}
+
+	sleep(test_duration);
+	test_complete = true;
+
+	for (i = 0; i < 2; i++) {
+		if (pthread_join(threads[i], NULL)) {
+			perror("pthread_join");
+			exit(1);
+		}
+	}
+
+	xa_destroy(&array);
+}
diff --git a/tools/testing/radix-tree/main.c b/tools/testing/radix-tree/main.c
index 7a22d6e3732e..f2cbc8e5b97c 100644
--- a/tools/testing/radix-tree/main.c
+++ b/tools/testing/radix-tree/main.c
@@ -311,6 +311,7 @@ int main(int argc, char **argv)
 	regression4_test();
 	iteration_test(0, 10 + 90 * long_run);
 	iteration_test(7, 10 + 90 * long_run);
+	iteration_test2(10 + 90 * long_run);
 	single_thread_tests(long_run);
 
 	/* Free any remaining preallocated nodes */
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index 1ee4b2c0ad10..34dab4d18744 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -34,6 +34,7 @@ void xarray_tests(void);
 void tag_check(void);
 void multiorder_checks(void);
 void iteration_test(unsigned order, unsigned duration);
+void iteration_test2(unsigned duration);
 void benchmark(void);
 void idr_checks(void);
 void ida_tests(void);
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
index c938283ac232..00316afb06ac 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
@@ -265,6 +265,7 @@ void test_flow_dissector(void)
 		CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys);
 	}
 
+	close(tap_fd);
 	bpf_prog_detach(prog_fd, BPF_FLOW_DISSECTOR);
 	bpf_object__close(obj);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c
index c2a0a9d5591b..1b46764265f6 100644
--- a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c
+++ b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c
@@ -77,12 +77,17 @@ static int get_stack_print_output(void *data, int size)
 void test_get_stack_raw_tp(void)
 {
 	const char *file = "./test_get_stack_rawtp.o";
+	const char *file_err = "./test_get_stack_rawtp_err.o";
 	int i, efd, err, prog_fd, pmu_fd, perfmap_fd;
 	struct perf_event_attr attr = {};
 	struct timespec tv = {0, 10};
 	__u32 key = 0, duration = 0;
 	struct bpf_object *obj;
 
+	err = bpf_prog_load(file_err, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd);
+	if (CHECK(err >= 0, "prog_load raw tp", "err %d errno %d\n", err, errno))
+		return;
+
 	err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd);
 	if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno))
 		return;
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
new file mode 100644
index 000000000000..aa43e0bd210c
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -0,0 +1,79 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Cloudflare
+
+#include "test_progs.h"
+
+#define TCP_REPAIR		19	/* TCP sock is under repair right now */
+
+#define TCP_REPAIR_ON		1
+#define TCP_REPAIR_OFF_NO_WP	-1	/* Turn off without window probes */
+
+static int connected_socket_v4(void)
+{
+	struct sockaddr_in addr = {
+		.sin_family = AF_INET,
+		.sin_port = htons(80),
+		.sin_addr = { inet_addr("127.0.0.1") },
+	};
+	socklen_t len = sizeof(addr);
+	int s, repair, err;
+
+	s = socket(AF_INET, SOCK_STREAM, 0);
+	if (CHECK_FAIL(s == -1))
+		goto error;
+
+	repair = TCP_REPAIR_ON;
+	err = setsockopt(s, SOL_TCP, TCP_REPAIR, &repair, sizeof(repair));
+	if (CHECK_FAIL(err))
+		goto error;
+
+	err = connect(s, (struct sockaddr *)&addr, len);
+	if (CHECK_FAIL(err))
+		goto error;
+
+	repair = TCP_REPAIR_OFF_NO_WP;
+	err = setsockopt(s, SOL_TCP, TCP_REPAIR, &repair, sizeof(repair));
+	if (CHECK_FAIL(err))
+		goto error;
+
+	return s;
+error:
+	perror(__func__);
+	close(s);
+	return -1;
+}
+
+/* Create a map, populate it with one socket, and free the map. */
+static void test_sockmap_create_update_free(enum bpf_map_type map_type)
+{
+	const int zero = 0;
+	int s, map, err;
+
+	s = connected_socket_v4();
+	if (CHECK_FAIL(s == -1))
+		return;
+
+	map = bpf_create_map(map_type, sizeof(int), sizeof(int), 1, 0);
+	if (CHECK_FAIL(map == -1)) {
+		perror("bpf_create_map");
+		goto out;
+	}
+
+	err = bpf_map_update_elem(map, &zero, &s, BPF_NOEXIST);
+	if (CHECK_FAIL(err)) {
+		perror("bpf_map_update");
+		goto out;
+	}
+
+out:
+	close(map);
+	close(s);
+}
+
+void test_sockmap_basic(void)
+{
+	if (test__start_subtest("sockmap create_update_free"))
+		test_sockmap_create_update_free(BPF_MAP_TYPE_SOCKMAP);
+	if (test__start_subtest("sockhash create_update_free"))
+		test_sockmap_create_update_free(BPF_MAP_TYPE_SOCKHASH);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
index 1c1a2f75f3d8..30153add86b3 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
@@ -42,8 +42,12 @@ retry:
 	pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */,
 			 0 /* cpu 0 */, -1 /* group id */,
 			 0 /* flags */);
-	if (CHECK(pmu_fd < 0, "perf_event_open",
-		  "err %d errno %d. Does the test host support PERF_COUNT_HW_CPU_CYCLES?\n",
+	if (pmu_fd < 0 && errno == ENOENT) {
+		printf("%s:SKIP:no PERF_COUNT_HW_CPU_CYCLES\n", __func__);
+		test__skip();
+		goto close_prog;
+	}
+	if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n",
 		  pmu_fd, errno))
 		goto close_prog;
 
diff --git a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp_err.c b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp_err.c
new file mode 100644
index 000000000000..8941a41c2a55
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp_err.c
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+#define MAX_STACK_RAWTP 10
+
+SEC("raw_tracepoint/sys_enter")
+int bpf_prog2(void *ctx)
+{
+	__u64 stack[MAX_STACK_RAWTP];
+	int error;
+
+	/* set all the flags which should return -EINVAL */
+	error = bpf_get_stack(ctx, stack, 0, -1);
+	if (error < 0)
+		goto loop;
+
+	return error;
+loop:
+	while (1) {
+		error++;
+	}
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
index 5b54ec637ada..e189f1036322 100644
--- a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
@@ -113,6 +113,12 @@ int _select_by_skb_data(struct sk_reuseport_md *reuse_md)
 		data_check.skb_ports[0] = th->source;
 		data_check.skb_ports[1] = th->dest;
 
+		if (th->fin)
+			/* The connection is being torn down at the end of a
+			 * test. It can't contain a cmd, so return early.
+			 */
+			return SK_PASS;
+
 		if ((th->doff << 2) + sizeof(*cmd) > data_check.len)
 			GOTO_DONE(DROP_ERR_SKB_DATA);
 		if (bpf_skb_load_bytes(reuse_md, th->doff << 2, &cmd_copy,
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index a3fbc571280a..116aa8f7b691 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -778,19 +778,19 @@ static void test_sockmap(unsigned int tasks, void *data)
 	}
 
 	err = bpf_prog_detach(fd, BPF_SK_SKB_STREAM_PARSER);
-	if (err) {
+	if (!err) {
 		printf("Failed empty parser prog detach\n");
 		goto out_sockmap;
 	}
 
 	err = bpf_prog_detach(fd, BPF_SK_SKB_STREAM_VERDICT);
-	if (err) {
+	if (!err) {
 		printf("Failed empty verdict prog detach\n");
 		goto out_sockmap;
 	}
 
 	err = bpf_prog_detach(fd, BPF_SK_MSG_VERDICT);
-	if (err) {
+	if (!err) {
 		printf("Failed empty msg verdict prog detach\n");
 		goto out_sockmap;
 	}
@@ -1079,19 +1079,19 @@ static void test_sockmap(unsigned int tasks, void *data)
 		assert(status == 0);
 	}
 
-	err = bpf_prog_detach(map_fd_rx, __MAX_BPF_ATTACH_TYPE);
+	err = bpf_prog_detach2(parse_prog, map_fd_rx, __MAX_BPF_ATTACH_TYPE);
 	if (!err) {
 		printf("Detached an invalid prog type.\n");
 		goto out_sockmap;
 	}
 
-	err = bpf_prog_detach(map_fd_rx, BPF_SK_SKB_STREAM_PARSER);
+	err = bpf_prog_detach2(parse_prog, map_fd_rx, BPF_SK_SKB_STREAM_PARSER);
 	if (err) {
 		printf("Failed parser prog detach\n");
 		goto out_sockmap;
 	}
 
-	err = bpf_prog_detach(map_fd_rx, BPF_SK_SKB_STREAM_VERDICT);
+	err = bpf_prog_detach2(verdict_prog, map_fd_rx, BPF_SK_SKB_STREAM_VERDICT);
 	if (err) {
 		printf("Failed parser prog detach\n");
 		goto out_sockmap;
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index dae0819b1141..af7dfad148db 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -137,6 +137,7 @@ int extract_build_id(char *build_id, size_t size)
 		len = size;
 	memcpy(build_id, line, len);
 	build_id[len] = '\0';
+	free(line);
 	return 0;
 err:
 	fclose(fp);
diff --git a/tools/testing/selftests/bpf/test_select_reuseport.c b/tools/testing/selftests/bpf/test_select_reuseport.c
index 75646d9b34aa..7f102c5d39db 100644
--- a/tools/testing/selftests/bpf/test_select_reuseport.c
+++ b/tools/testing/selftests/bpf/test_select_reuseport.c
@@ -30,7 +30,7 @@
 #define REUSEPORT_ARRAY_SIZE 32
 
 static int result_map, tmp_index_ovr_map, linum_map, data_check_map;
-static enum result expected_results[NR_RESULTS];
+static __u32 expected_results[NR_RESULTS];
 static int sk_fds[REUSEPORT_ARRAY_SIZE];
 static int reuseport_array, outer_map;
 static int select_by_skb_data_prog;
@@ -610,7 +610,19 @@ static void setup_per_test(int type, unsigned short family, bool inany)
 
 static void cleanup_per_test(void)
 {
-	int i, err;
+	int i, err, zero = 0;
+
+	memset(expected_results, 0, sizeof(expected_results));
+
+	for (i = 0; i < NR_RESULTS; i++) {
+		err = bpf_map_update_elem(result_map, &i, &zero, BPF_ANY);
+		CHECK(err, "reset elem in result_map",
+		       "i:%u err:%d errno:%d\n", i, err, errno);
+	}
+
+	err = bpf_map_update_elem(linum_map, &zero, &zero, BPF_ANY);
+	CHECK(err, "reset line number in linum_map", "err:%d errno:%d\n",
+	       err, errno);
 
 	for (i = 0; i < REUSEPORT_ARRAY_SIZE; i++)
 		close(sk_fds[i]);
diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 8b838e91cfe5..3fe10daa8772 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -331,7 +331,7 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt,
 	FILE *file;
 	int i, fp;
 
-	file = fopen(".sendpage_tst.tmp", "w+");
+	file = tmpfile();
 	if (!file) {
 		perror("create file for sendpage");
 		return 1;
@@ -340,13 +340,8 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt,
 		fwrite(&k, sizeof(char), 1, file);
 	fflush(file);
 	fseek(file, 0, SEEK_SET);
-	fclose(file);
 
-	fp = open(".sendpage_tst.tmp", O_RDONLY);
-	if (fp < 0) {
-		perror("reopen file for sendpage");
-		return 1;
-	}
+	fp = fileno(file);
 
 	clock_gettime(CLOCK_MONOTONIC, &s->start);
 	for (i = 0; i < cnt; i++) {
@@ -354,11 +349,11 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt,
 
 		if (!drop && sent < 0) {
 			perror("send loop error:");
-			close(fp);
+			fclose(file);
 			return sent;
 		} else if (drop && sent >= 0) {
 			printf("sendpage loop error expected: %i\n", sent);
-			close(fp);
+			fclose(file);
 			return -EIO;
 		}
 
@@ -366,7 +361,7 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt,
 			s->bytes_sent += sent;
 	}
 	clock_gettime(CLOCK_MONOTONIC, &s->end);
-	close(fp);
+	fclose(file);
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/test_sysctl.c b/tools/testing/selftests/bpf/test_sysctl.c
index c938f1767ca7..3f21eb83f5f5 100644
--- a/tools/testing/selftests/bpf/test_sysctl.c
+++ b/tools/testing/selftests/bpf/test_sysctl.c
@@ -13,6 +13,7 @@
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
 
+#include "bpf_endian.h"
 #include "bpf_rlimit.h"
 #include "bpf_util.h"
 #include "cgroup_helpers.h"
@@ -100,7 +101,7 @@ static struct sysctl_test tests[] = {
 		.descr = "ctx:write sysctl:write read ok",
 		.insns = {
 			/* If (write) */
-			BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_1,
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
 				    offsetof(struct bpf_sysctl, write)),
 			BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 1, 2),
 
@@ -220,7 +221,8 @@ static struct sysctl_test tests[] = {
 			/* if (ret == expected && */
 			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, sizeof("tcp_mem") - 1, 6),
 			/*     buf == "tcp_mem\0") */
-			BPF_LD_IMM64(BPF_REG_8, 0x006d656d5f706374ULL),
+			BPF_LD_IMM64(BPF_REG_8,
+				     bpf_be64_to_cpu(0x7463705f6d656d00ULL)),
 			BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
 			BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2),
 
@@ -261,7 +263,8 @@ static struct sysctl_test tests[] = {
 			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -E2BIG, 6),
 
 			/*     buf[0:7] == "tcp_me\0") */
-			BPF_LD_IMM64(BPF_REG_8, 0x00656d5f706374ULL),
+			BPF_LD_IMM64(BPF_REG_8,
+				     bpf_be64_to_cpu(0x7463705f6d650000ULL)),
 			BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
 			BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2),
 
@@ -304,12 +307,14 @@ static struct sysctl_test tests[] = {
 			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 16, 14),
 
 			/*     buf[0:8] == "net/ipv4" && */
-			BPF_LD_IMM64(BPF_REG_8, 0x347670692f74656eULL),
+			BPF_LD_IMM64(BPF_REG_8,
+				     bpf_be64_to_cpu(0x6e65742f69707634ULL)),
 			BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
 			BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 10),
 
 			/*     buf[8:16] == "/tcp_mem" && */
-			BPF_LD_IMM64(BPF_REG_8, 0x6d656d5f7063742fULL),
+			BPF_LD_IMM64(BPF_REG_8,
+				     bpf_be64_to_cpu(0x2f7463705f6d656dULL)),
 			BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 8),
 			BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 6),
 
@@ -356,12 +361,14 @@ static struct sysctl_test tests[] = {
 			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -E2BIG, 10),
 
 			/*     buf[0:8] == "net/ipv4" && */
-			BPF_LD_IMM64(BPF_REG_8, 0x347670692f74656eULL),
+			BPF_LD_IMM64(BPF_REG_8,
+				     bpf_be64_to_cpu(0x6e65742f69707634ULL)),
 			BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
 			BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 6),
 
 			/*     buf[8:16] == "/tcp_me\0") */
-			BPF_LD_IMM64(BPF_REG_8, 0x00656d5f7063742fULL),
+			BPF_LD_IMM64(BPF_REG_8,
+				     bpf_be64_to_cpu(0x2f7463705f6d6500ULL)),
 			BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 8),
 			BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2),
 
@@ -402,7 +409,8 @@ static struct sysctl_test tests[] = {
 			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -E2BIG, 6),
 
 			/*     buf[0:8] == "net/ip\0") */
-			BPF_LD_IMM64(BPF_REG_8, 0x000070692f74656eULL),
+			BPF_LD_IMM64(BPF_REG_8,
+				     bpf_be64_to_cpu(0x6e65742f69700000ULL)),
 			BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
 			BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2),
 
@@ -437,7 +445,8 @@ static struct sysctl_test tests[] = {
 			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 6, 6),
 
 			/*     buf[0:6] == "Linux\n\0") */
-			BPF_LD_IMM64(BPF_REG_8, 0x000a78756e694cULL),
+			BPF_LD_IMM64(BPF_REG_8,
+				     bpf_be64_to_cpu(0x4c696e75780a0000ULL)),
 			BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
 			BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2),
 
@@ -475,7 +484,8 @@ static struct sysctl_test tests[] = {
 			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 6, 6),
 
 			/*     buf[0:6] == "Linux\n\0") */
-			BPF_LD_IMM64(BPF_REG_8, 0x000a78756e694cULL),
+			BPF_LD_IMM64(BPF_REG_8,
+				     bpf_be64_to_cpu(0x4c696e75780a0000ULL)),
 			BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
 			BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2),
 
@@ -513,7 +523,8 @@ static struct sysctl_test tests[] = {
 			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -E2BIG, 6),
 
 			/*     buf[0:6] == "Linux\0") */
-			BPF_LD_IMM64(BPF_REG_8, 0x000078756e694cULL),
+			BPF_LD_IMM64(BPF_REG_8,
+				     bpf_be64_to_cpu(0x4c696e7578000000ULL)),
 			BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
 			BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2),
 
@@ -656,7 +667,8 @@ static struct sysctl_test tests[] = {
 
 			/*     buf[0:4] == "606\0") */
 			BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_7, 0),
-			BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0x00363036, 2),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_9,
+				    bpf_ntohl(0x36303600), 2),
 
 			/* return DENY; */
 			BPF_MOV64_IMM(BPF_REG_0, 0),
@@ -691,17 +703,20 @@ static struct sysctl_test tests[] = {
 			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 23, 14),
 
 			/*     buf[0:8] == "3000000 " && */
-			BPF_LD_IMM64(BPF_REG_8, 0x2030303030303033ULL),
+			BPF_LD_IMM64(BPF_REG_8,
+				     bpf_be64_to_cpu(0x3330303030303020ULL)),
 			BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
 			BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 10),
 
 			/*     buf[8:16] == "4000000 " && */
-			BPF_LD_IMM64(BPF_REG_8, 0x2030303030303034ULL),
+			BPF_LD_IMM64(BPF_REG_8,
+				     bpf_be64_to_cpu(0x3430303030303020ULL)),
 			BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 8),
 			BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 6),
 
 			/*     buf[16:24] == "6000000\0") */
-			BPF_LD_IMM64(BPF_REG_8, 0x0030303030303036ULL),
+			BPF_LD_IMM64(BPF_REG_8,
+				     bpf_be64_to_cpu(0x3630303030303000ULL)),
 			BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 16),
 			BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2),
 
@@ -741,7 +756,8 @@ static struct sysctl_test tests[] = {
 
 			/*     buf[0:3] == "60\0") */
 			BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_7, 0),
-			BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0x003036, 2),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_9,
+				    bpf_ntohl(0x36300000), 2),
 
 			/* return DENY; */
 			BPF_MOV64_IMM(BPF_REG_0, 0),
@@ -763,7 +779,8 @@ static struct sysctl_test tests[] = {
 			/* sysctl_set_new_value arg2 (buf) */
 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
-			BPF_MOV64_IMM(BPF_REG_0, 0x00303036),
+			BPF_MOV64_IMM(BPF_REG_0,
+				      bpf_ntohl(0x36303000)),
 			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
 
 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
@@ -797,7 +814,7 @@ static struct sysctl_test tests[] = {
 			/* sysctl_set_new_value arg2 (buf) */
 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
-			BPF_MOV64_IMM(BPF_REG_0, FIXUP_SYSCTL_VALUE),
+			BPF_LD_IMM64(BPF_REG_0, FIXUP_SYSCTL_VALUE),
 			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
 
 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
@@ -831,8 +848,9 @@ static struct sysctl_test tests[] = {
 			/* arg1 (buf) */
 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
-			BPF_MOV64_IMM(BPF_REG_0, 0x00303036),
-			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0,
+				      bpf_ntohl(0x36303000)),
+			BPF_STX_MEM(BPF_W, BPF_REG_7, BPF_REG_0, 0),
 
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
 
@@ -875,7 +893,8 @@ static struct sysctl_test tests[] = {
 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
 			/* "600 602\0" */
-			BPF_LD_IMM64(BPF_REG_0, 0x0032303620303036ULL),
+			BPF_LD_IMM64(BPF_REG_0,
+				     bpf_be64_to_cpu(0x3630302036303200ULL)),
 			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
 
@@ -943,7 +962,8 @@ static struct sysctl_test tests[] = {
 			/* arg1 (buf) */
 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
-			BPF_MOV64_IMM(BPF_REG_0, 0x00303036),
+			BPF_MOV64_IMM(BPF_REG_0,
+				      bpf_ntohl(0x36303000)),
 			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
 
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
@@ -975,8 +995,9 @@ static struct sysctl_test tests[] = {
 			/* arg1 (buf) */
 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
-			BPF_MOV64_IMM(BPF_REG_0, 0x00373730),
-			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0,
+				      bpf_ntohl(0x30373700)),
+			BPF_STX_MEM(BPF_W, BPF_REG_7, BPF_REG_0, 0),
 
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
 
@@ -1018,7 +1039,8 @@ static struct sysctl_test tests[] = {
 			/* arg1 (buf) */
 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
-			BPF_MOV64_IMM(BPF_REG_0, 0x00303036),
+			BPF_MOV64_IMM(BPF_REG_0,
+				      bpf_ntohl(0x36303000)),
 			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
 
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
@@ -1058,7 +1080,8 @@ static struct sysctl_test tests[] = {
 			/* arg1 (buf) */
 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
-			BPF_MOV64_IMM(BPF_REG_0, 0x090a0c0d),
+			BPF_MOV64_IMM(BPF_REG_0,
+				      bpf_ntohl(0x0d0c0a09)),
 			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
 
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
@@ -1098,7 +1121,9 @@ static struct sysctl_test tests[] = {
 			/* arg1 (buf) */
 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
-			BPF_MOV64_IMM(BPF_REG_0, 0x00362d0a), /* " -6\0" */
+			/* " -6\0" */
+			BPF_MOV64_IMM(BPF_REG_0,
+				      bpf_ntohl(0x0a2d3600)),
 			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
 
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
@@ -1138,8 +1163,10 @@ static struct sysctl_test tests[] = {
 			/* arg1 (buf) */
 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
-			BPF_MOV64_IMM(BPF_REG_0, 0x00362d0a), /* " -6\0" */
-			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+			/* " -6\0" */
+			BPF_MOV64_IMM(BPF_REG_0,
+				      bpf_ntohl(0x0a2d3600)),
+			BPF_STX_MEM(BPF_W, BPF_REG_7, BPF_REG_0, 0),
 
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
 
@@ -1181,8 +1208,10 @@ static struct sysctl_test tests[] = {
 			/* arg1 (buf) */
 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
-			BPF_MOV64_IMM(BPF_REG_0, 0x65667830), /* "0xfe" */
-			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+			/* "0xfe" */
+			BPF_MOV64_IMM(BPF_REG_0,
+				      bpf_ntohl(0x30786665)),
+			BPF_STX_MEM(BPF_W, BPF_REG_7, BPF_REG_0, 0),
 
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
 
@@ -1224,11 +1253,14 @@ static struct sysctl_test tests[] = {
 			/* arg1 (buf) 9223372036854775807 */
 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -24),
-			BPF_LD_IMM64(BPF_REG_0, 0x3032373333323239ULL),
+			BPF_LD_IMM64(BPF_REG_0,
+				     bpf_be64_to_cpu(0x3932323333373230ULL)),
 			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
-			BPF_LD_IMM64(BPF_REG_0, 0x3537373435383633ULL),
+			BPF_LD_IMM64(BPF_REG_0,
+				     bpf_be64_to_cpu(0x3336383534373735ULL)),
 			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 8),
-			BPF_LD_IMM64(BPF_REG_0, 0x0000000000373038ULL),
+			BPF_LD_IMM64(BPF_REG_0,
+				     bpf_be64_to_cpu(0x3830370000000000ULL)),
 			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 16),
 
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
@@ -1272,11 +1304,14 @@ static struct sysctl_test tests[] = {
 			/* arg1 (buf) 9223372036854775808 */
 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -24),
-			BPF_LD_IMM64(BPF_REG_0, 0x3032373333323239ULL),
+			BPF_LD_IMM64(BPF_REG_0,
+				     bpf_be64_to_cpu(0x3932323333373230ULL)),
 			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
-			BPF_LD_IMM64(BPF_REG_0, 0x3537373435383633ULL),
+			BPF_LD_IMM64(BPF_REG_0,
+				     bpf_be64_to_cpu(0x3336383534373735ULL)),
 			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 8),
-			BPF_LD_IMM64(BPF_REG_0, 0x0000000000383038ULL),
+			BPF_LD_IMM64(BPF_REG_0,
+				     bpf_be64_to_cpu(0x3830380000000000ULL)),
 			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 16),
 
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
@@ -1350,20 +1385,24 @@ static size_t probe_prog_length(const struct bpf_insn *fp)
 static int fixup_sysctl_value(const char *buf, size_t buf_len,
 			      struct bpf_insn *prog, size_t insn_num)
 {
-	uint32_t value_num = 0;
+	union {
+		uint8_t raw[sizeof(uint64_t)];
+		uint64_t num;
+	} value = {};
 	uint8_t c, i;
 
-	if (buf_len > sizeof(value_num)) {
+	if (buf_len > sizeof(value)) {
 		log_err("Value is too big (%zd) to use in fixup", buf_len);
 		return -1;
 	}
-
-	for (i = 0; i < buf_len; ++i) {
-		c = buf[i];
-		value_num |= (c << i * 8);
+	if (prog[insn_num].code != (BPF_LD | BPF_DW | BPF_IMM)) {
+		log_err("Can fixup only BPF_LD_IMM64 insns");
+		return -1;
 	}
 
-	prog[insn_num].imm = value_num;
+	memcpy(value.raw, buf, buf_len);
+	prog[insn_num].imm = (uint32_t)value.num;
+	prog[insn_num + 1].imm = (uint32_t)(value.num >> 32);
 
 	return 0;
 }
@@ -1505,6 +1544,7 @@ static int run_test_case(int cgfd, struct sysctl_test *test)
 			goto err;
 	}
 
+	errno = 0;
 	if (access_sysctl(sysctl_path, test) == -1) {
 		if (test->result == OP_EPERM && errno == EPERM)
 			goto out;
@@ -1513,7 +1553,7 @@ static int run_test_case(int cgfd, struct sysctl_test *test)
 	}
 
 	if (test->result != SUCCESS) {
-		log_err("Unexpected failure");
+		log_err("Unexpected success");
 		goto err;
 	}
 
diff --git a/tools/testing/selftests/bpf/verifier/bpf_get_stack.c b/tools/testing/selftests/bpf/verifier/bpf_get_stack.c
index f24d50f09dbe..371926771db5 100644
--- a/tools/testing/selftests/bpf/verifier/bpf_get_stack.c
+++ b/tools/testing/selftests/bpf/verifier/bpf_get_stack.c
@@ -9,17 +9,17 @@
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
 	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 28),
 	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_9, sizeof(struct test_val)),
+	BPF_MOV64_IMM(BPF_REG_9, sizeof(struct test_val)/2),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
 	BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
-	BPF_MOV64_IMM(BPF_REG_3, sizeof(struct test_val)),
+	BPF_MOV64_IMM(BPF_REG_3, sizeof(struct test_val)/2),
 	BPF_MOV64_IMM(BPF_REG_4, 256),
 	BPF_EMIT_CALL(BPF_FUNC_get_stack),
 	BPF_MOV64_IMM(BPF_REG_1, 0),
 	BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
 	BPF_ALU64_IMM(BPF_LSH, BPF_REG_8, 32),
 	BPF_ALU64_IMM(BPF_ARSH, BPF_REG_8, 32),
-	BPF_JMP_REG(BPF_JSLT, BPF_REG_1, BPF_REG_8, 16),
+	BPF_JMP_REG(BPF_JSLT, BPF_REG_8, BPF_REG_1, 16),
 	BPF_ALU64_REG(BPF_SUB, BPF_REG_9, BPF_REG_8),
 	BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
 	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_8),
@@ -29,7 +29,7 @@
 	BPF_MOV64_REG(BPF_REG_3, BPF_REG_2),
 	BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_1),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
-	BPF_MOV64_IMM(BPF_REG_5, sizeof(struct test_val)),
+	BPF_MOV64_IMM(BPF_REG_5, sizeof(struct test_val)/2),
 	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_5),
 	BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 4),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
diff --git a/tools/testing/selftests/cgroup/test_freezer.c b/tools/testing/selftests/cgroup/test_freezer.c
index 2bfddb6d6d3b..ed7057733e05 100644
--- a/tools/testing/selftests/cgroup/test_freezer.c
+++ b/tools/testing/selftests/cgroup/test_freezer.c
@@ -73,6 +73,7 @@ static int cg_prepare_for_wait(const char *cgroup)
 	if (ret == -1) {
 		debug("Error: inotify_add_watch() failed\n");
 		close(fd);
+		fd = -1;
 	}
 
 	return fd;
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
index 71231ad2dbfb..7f0ad9f89ea0 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
@@ -232,7 +232,7 @@ test_mc_aware()
 	stop_traffic
 	local ucth1=${uc_rate[1]}
 
-	start_traffic $h1 own bc bc
+	start_traffic $h1 192.0.2.65 bc bc
 
 	local d0=$(date +%s)
 	local t0=$(ethtool_stats_get $h3 rx_octets_prio_0)
@@ -254,7 +254,11 @@ test_mc_aware()
 			ret = 100 * ($ucth1 - $ucth2) / $ucth1
 			if (ret > 0) { ret } else { 0 }
 		    ")
-	check_err $(bc <<< "$deg > 25")
+
+	# Minimum shaper of 200Mbps on MC TCs should cause about 20% of
+	# degradation on 1Gbps link.
+	check_err $(bc <<< "$deg < 15") "Minimum shaper not in effect"
+	check_err $(bc <<< "$deg > 25") "MC traffic degrades UC performance too much"
 
 	local interval=$((d1 - d0))
 	local mc_ir=$(rate $u0 $u1 $interval)
@@ -296,7 +300,7 @@ test_uc_aware()
 	local i
 
 	for ((i = 0; i < attempts; ++i)); do
-		if $ARPING -c 1 -I $h1 -b 192.0.2.66 -q -w 0.1; then
+		if $ARPING -c 1 -I $h1 -b 192.0.2.66 -q -w 1; then
 			((passes++))
 		fi
 
diff --git a/tools/testing/selftests/firmware/fw_lib.sh b/tools/testing/selftests/firmware/fw_lib.sh
index 1cbb12e284a6..8a853ace55a2 100755
--- a/tools/testing/selftests/firmware/fw_lib.sh
+++ b/tools/testing/selftests/firmware/fw_lib.sh
@@ -28,6 +28,12 @@ test_modprobe()
 
 check_mods()
 {
+	local uid=$(id -u)
+	if [ $uid -ne 0 ]; then
+		echo "skip all tests: must be run as root" >&2
+		exit $ksft_skip
+	fi
+
 	trap "test_modprobe" EXIT
 	if [ ! -d $DIR ]; then
 		modprobe test_firmware
diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile
index cd1f5b3a7774..d6e106fbce11 100644
--- a/tools/testing/selftests/ftrace/Makefile
+++ b/tools/testing/selftests/ftrace/Makefile
@@ -2,7 +2,7 @@
 all:
 
 TEST_PROGS := ftracetest
-TEST_FILES := test.d
+TEST_FILES := test.d settings
 EXTRA_CLEAN := $(OUTPUT)/logs/*
 
 include ../lib.mk
diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest
index 6d5e9e87c4b7..faacd539487d 100755
--- a/tools/testing/selftests/ftrace/ftracetest
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -17,14 +17,32 @@ echo "		-v|--verbose Increase verbosity of test messages"
 echo "		-vv        Alias of -v -v (Show all results in stdout)"
 echo "		-vvv       Alias of -v -v -v (Show all commands immediately)"
 echo "		--fail-unsupported Treat UNSUPPORTED as a failure"
+echo "		--fail-unresolved Treat UNRESOLVED as a failure"
 echo "		-d|--debug Debug mode (trace all shell commands)"
 echo "		-l|--logdir <dir> Save logs on the <dir>"
 echo "		            If <dir> is -, all logs output in console only"
 exit $1
 }
 
+# cgroup RT scheduling prevents chrt commands from succeeding, which
+# induces failures in test wakeup tests.  Disable for the duration of
+# the tests.
+
+readonly sched_rt_runtime=/proc/sys/kernel/sched_rt_runtime_us
+
+sched_rt_runtime_orig=$(cat $sched_rt_runtime)
+
+setup() {
+  echo -1 > $sched_rt_runtime
+}
+
+cleanup() {
+  echo $sched_rt_runtime_orig > $sched_rt_runtime
+}
+
 errexit() { # message
   echo "Error: $1" 1>&2
+  cleanup
   exit 1
 }
 
@@ -33,6 +51,8 @@ if [ `id -u` -ne 0 ]; then
   errexit "this must be run by root user"
 fi
 
+setup
+
 # Utilities
 absdir() { # file_path
   (cd `dirname $1`; pwd)
@@ -87,6 +107,10 @@ parse_opts() { # opts
       UNSUPPORTED_RESULT=1
       shift 1
     ;;
+    --fail-unresolved)
+      UNRESOLVED_RESULT=1
+      shift 1
+    ;;
     --logdir|-l)
       LOG_DIR=$2
       shift 2
@@ -131,6 +155,7 @@ KEEP_LOG=0
 DEBUG=0
 VERBOSE=0
 UNSUPPORTED_RESULT=0
+UNRESOLVED_RESULT=0
 STOP_FAILURE=0
 # Parse command-line options
 parse_opts $*
@@ -209,6 +234,7 @@ TOTAL_RESULT=0
 
 INSTANCE=
 CASENO=0
+
 testcase() { # testfile
   CASENO=$((CASENO+1))
   desc=`grep "^#[ \t]*description:" $1 | cut -f2 -d:`
@@ -234,7 +260,7 @@ eval_result() { # sigval
     $UNRESOLVED)
       prlog "	[${color_blue}UNRESOLVED${color_reset}]"
       UNRESOLVED_CASES="$UNRESOLVED_CASES $CASENO"
-      return 1 # this is a kind of bug.. something happened.
+      return $UNRESOLVED_RESULT # depends on use case
     ;;
     $UNTESTED)
       prlog "	[${color_blue}UNTESTED${color_reset}]"
@@ -380,5 +406,7 @@ prlog "# of unsupported: " `echo $UNSUPPORTED_CASES | wc -w`
 prlog "# of xfailed: " `echo $XFAILED_CASES | wc -w`
 prlog "# of undefined(test bug): " `echo $UNDEFINED_CASES | wc -w`
 
+cleanup
+
 # if no error, return 0
 exit $TOTAL_RESULT
diff --git a/tools/testing/selftests/ftrace/settings b/tools/testing/selftests/ftrace/settings
new file mode 100644
index 000000000000..e7b9417537fb
--- /dev/null
+++ b/tools/testing/selftests/ftrace/settings
@@ -0,0 +1 @@
+timeout=0
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc
index 36fb59f886ea..1a52f2883fe0 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc
@@ -3,6 +3,8 @@
 # description: ftrace - stacktrace filter command
 # flags: instance
 
+[ ! -f set_ftrace_filter ] && exit_unsupported
+
 echo _do_fork:stacktrace >> set_ftrace_filter
 
 grep -q "_do_fork:stacktrace:unlimited" set_ftrace_filter
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_cpumask.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_cpumask.tc
index 86a1f07ef2ca..71fa3f49e35e 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_cpumask.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_cpumask.tc
@@ -15,6 +15,11 @@ if [ $NP -eq 1 ] ;then
   exit_unresolved
 fi
 
+if ! grep -q "function" available_tracers ; then
+  echo "Function trace is not enabled"
+  exit_unsupported
+fi
+
 ORIG_CPUMASK=`cat tracing_cpumask`
 
 do_reset() {
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/tracing-error-log.tc b/tools/testing/selftests/ftrace/test.d/ftrace/tracing-error-log.tc
index 021c03fd885d..23465823532b 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/tracing-error-log.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/tracing-error-log.tc
@@ -14,6 +14,8 @@ if [ ! -f set_event ]; then
     exit_unsupported
 fi
 
+[ -f error_log ] || exit_unsupported
+
 ftrace_errlog_check 'event filter parse error' '((sig >= 10 && sig < 15) || dsig ^== 17) && comm != bash' 'events/signal/signal_generate/filter'
 
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions
index 779ec11f61bd..0f3c53ddc073 100644
--- a/tools/testing/selftests/ftrace/test.d/functions
+++ b/tools/testing/selftests/ftrace/test.d/functions
@@ -46,6 +46,9 @@ reset_events_filter() { # reset all current setting filters
 }
 
 reset_ftrace_filter() { # reset all triggers in set_ftrace_filter
+    if [ ! -f set_ftrace_filter ]; then
+      return 0
+    fi
     echo > set_ftrace_filter
     grep -v '^#' set_ftrace_filter | while read t; do
 	tr=`echo $t | cut -d: -f2`
@@ -91,9 +94,9 @@ initialize_ftrace() { # Reset ftrace to initial-state
     reset_events_filter
     reset_ftrace_filter
     disable_events
-    echo > set_event_pid	# event tracer is always on
-    echo > set_ftrace_pid
-    [ -f set_ftrace_filter ] && echo | tee set_ftrace_*
+    [ -f set_event_pid ] && echo > set_event_pid
+    [ -f set_ftrace_pid ] && echo > set_ftrace_pid
+    [ -f set_ftrace_notrace ] && echo > set_ftrace_notrace
     [ -f set_graph_function ] && echo | tee set_graph_*
     [ -f stack_trace_filter ] && echo > stack_trace_filter
     [ -f kprobe_events ] && echo > kprobe_events
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
index 1bcb67dcae26..81490ecaaa92 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
@@ -38,7 +38,7 @@ for width in 64 32 16 8; do
   echo 0 > events/kprobes/testprobe/enable
 
   : "Confirm the arguments is recorded in given types correctly"
-  ARGS=`grep "testprobe" trace | sed -e 's/.* arg1=\(.*\) arg2=\(.*\) arg3=\(.*\) arg4=\(.*\)/\1 \2 \3 \4/'`
+  ARGS=`grep "testprobe" trace | head -n 1 | sed -e 's/.* arg1=\(.*\) arg2=\(.*\) arg3=\(.*\) arg4=\(.*\)/\1 \2 \3 \4/'`
   check_types $ARGS $width
 
   : "Clear event for next loop"
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc
index 5862eee91e1d..6e3dbe5f96b7 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc
@@ -20,9 +20,9 @@ while read i; do
   test $N -eq 256 && break
 done
 
-L=`wc -l kprobe_events`
-if [ $L -ne $N ]; then
-  echo "The number of kprobes events ($L) is not $N"
+L=`cat kprobe_events | wc -l`
+if [ $L -ne 256 ]; then
+  echo "The number of kprobes events ($L) is not 256"
   exit_fail
 fi
 
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-action-hist-xfail.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-action-hist-xfail.tc
index 1221240f8cf6..3f2aee115f6e 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-action-hist-xfail.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-action-hist-xfail.tc
@@ -21,10 +21,10 @@ grep -q "snapshot()" README || exit_unsupported # version issue
 
 echo "Test expected snapshot action failure"
 
-echo 'hist:keys=comm:onmatch(sched.sched_wakeup).snapshot()' >> /sys/kernel/debug/tracing/events/sched/sched_waking/trigger && exit_fail
+echo 'hist:keys=comm:onmatch(sched.sched_wakeup).snapshot()' >> events/sched/sched_waking/trigger && exit_fail
 
 echo "Test expected save action failure"
 
-echo 'hist:keys=comm:onmatch(sched.sched_wakeup).save(comm,prio)' >> /sys/kernel/debug/tracing/events/sched/sched_waking/trigger && exit_fail
+echo 'hist:keys=comm:onmatch(sched.sched_wakeup).save(comm,prio)' >> events/sched/sched_waking/trigger && exit_fail
 
 exit_xfail
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onchange-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onchange-action-hist.tc
index 064a284e4e75..c80007aa9f86 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onchange-action-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onchange-action-hist.tc
@@ -16,7 +16,7 @@ grep -q "onchange(var)" README || exit_unsupported # version issue
 
 echo "Test onchange action"
 
-echo 'hist:keys=comm:newprio=prio:onchange($newprio).save(comm,prio) if comm=="ping"' >> /sys/kernel/debug/tracing/events/sched/sched_waking/trigger
+echo 'hist:keys=comm:newprio=prio:onchange($newprio).save(comm,prio) if comm=="ping"' >> events/sched/sched_waking/trigger
 
 ping $LOCALHOST -c 3
 nice -n 1 ping $LOCALHOST -c 3
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-snapshot-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-snapshot-action-hist.tc
index 18fff69fc433..f546c1b66a9b 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-snapshot-action-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-snapshot-action-hist.tc
@@ -23,9 +23,9 @@ grep -q "snapshot()" README || exit_unsupported # version issue
 
 echo "Test snapshot action"
 
-echo 1 > /sys/kernel/debug/tracing/events/sched/enable
+echo 1 > events/sched/enable
 
-echo 'hist:keys=comm:newprio=prio:onchange($newprio).save(comm,prio):onchange($newprio).snapshot() if comm=="ping"' >> /sys/kernel/debug/tracing/events/sched/sched_waking/trigger
+echo 'hist:keys=comm:newprio=prio:onchange($newprio).save(comm,prio):onchange($newprio).snapshot() if comm=="ping"' >> events/sched/sched_waking/trigger
 
 ping $LOCALHOST -c 3
 nice -n 1 ping $LOCALHOST -c 3
diff --git a/tools/testing/selftests/gen_kselftest_tar.sh b/tools/testing/selftests/gen_kselftest_tar.sh
index a27e2eec3586..8b2b6088540d 100755
--- a/tools/testing/selftests/gen_kselftest_tar.sh
+++ b/tools/testing/selftests/gen_kselftest_tar.sh
@@ -38,16 +38,21 @@ main()
 	esac
 	fi
 
-	install_dir=./kselftest
+	# Create working directory.
+	dest=`pwd`
+	install_work="$dest"/kselftest_install
+	install_name=kselftest
+	install_dir="$install_work"/"$install_name"
+	mkdir -p "$install_dir"
 
-# Run install using INSTALL_KSFT_PATH override to generate install
-# directory
-./kselftest_install.sh
-tar $copts kselftest${ext} $install_dir
-echo "Kselftest archive kselftest${ext} created!"
+	# Run install using INSTALL_KSFT_PATH override to generate install
+	# directory
+	./kselftest_install.sh "$install_dir"
+	(cd "$install_work"; tar $copts "$dest"/kselftest${ext} $install_name)
+	echo "Kselftest archive kselftest${ext} created!"
 
-# clean up install directory
-rm -rf kselftest
+	# clean up top-level install work directory
+	rm -rf "$install_work"
 }
 
 main "$@"
diff --git a/tools/testing/selftests/ipc/msgque.c b/tools/testing/selftests/ipc/msgque.c
index 4c156aeab6b8..5ec4d9e18806 100644
--- a/tools/testing/selftests/ipc/msgque.c
+++ b/tools/testing/selftests/ipc/msgque.c
@@ -137,7 +137,7 @@ int dump_queue(struct msgque_data *msgque)
 	for (kern_id = 0; kern_id < 256; kern_id++) {
 		ret = msgctl(kern_id, MSG_STAT, &ds);
 		if (ret < 0) {
-			if (errno == -EINVAL)
+			if (errno == EINVAL)
 				continue;
 			printf("Failed to get stats for IPC queue with id %d\n",
 					kern_id);
diff --git a/tools/testing/selftests/kmod/kmod.sh b/tools/testing/selftests/kmod/kmod.sh
index 0a76314b4414..1f118916a83e 100755
--- a/tools/testing/selftests/kmod/kmod.sh
+++ b/tools/testing/selftests/kmod/kmod.sh
@@ -505,18 +505,23 @@ function test_num()
 	fi
 }
 
-function get_test_count()
+function get_test_data()
 {
 	test_num $1
-	TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$1'}')
+	local field_num=$(echo $1 | sed 's/^0*//')
+	echo $ALL_TESTS | awk '{print $'$field_num'}'
+}
+
+function get_test_count()
+{
+	TEST_DATA=$(get_test_data $1)
 	LAST_TWO=${TEST_DATA#*:*}
 	echo ${LAST_TWO%:*}
 }
 
 function get_test_enabled()
 {
-	test_num $1
-	TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$1'}')
+	TEST_DATA=$(get_test_data $1)
 	echo ${TEST_DATA#*:*:}
 }
 
diff --git a/tools/testing/selftests/kselftest/prefix.pl b/tools/testing/selftests/kselftest/prefix.pl
index ec7e48118183..31f7c2a0a8bd 100755
--- a/tools/testing/selftests/kselftest/prefix.pl
+++ b/tools/testing/selftests/kselftest/prefix.pl
@@ -3,6 +3,7 @@
 # Prefix all lines with "# ", unbuffered. Command being piped in may need
 # to have unbuffering forced with "stdbuf -i0 -o0 -e0 $cmd".
 use strict;
+use IO::Handle;
 
 binmode STDIN;
 binmode STDOUT;
diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh
index 84de7bc74f2c..e84d901f8567 100644
--- a/tools/testing/selftests/kselftest/runner.sh
+++ b/tools/testing/selftests/kselftest/runner.sh
@@ -79,6 +79,7 @@ run_one()
 		if [ $rc -eq $skip_rc ]; then	\
 			echo "not ok $test_num $TEST_HDR_MSG # SKIP"
 		elif [ $rc -eq $timeout_rc ]; then \
+			echo "#"
 			echo "not ok $test_num $TEST_HDR_MSG # TIMEOUT"
 		else
 			echo "not ok $test_num $TEST_HDR_MSG # exit=$rc"
@@ -90,7 +91,7 @@ run_one()
 run_many()
 {
 	echo "TAP version 13"
-	DIR=$(basename "$PWD")
+	DIR="${PWD#${BASE_DIR}/}"
 	test_num=0
 	total=$(echo "$@" | wc -w)
 	echo "1..$total"
diff --git a/tools/testing/selftests/kselftest_install.sh b/tools/testing/selftests/kselftest_install.sh
index ec304463883c..bcc65f7230b1 100755..100644
--- a/tools/testing/selftests/kselftest_install.sh
+++ b/tools/testing/selftests/kselftest_install.sh
@@ -6,30 +6,30 @@
 # Author: Shuah Khan <shuahkh@osg.samsung.com>
 # Copyright (C) 2015 Samsung Electronics Co., Ltd.
 
-install_loc=`pwd`
-
 main()
 {
-	if [ $(basename $install_loc) !=  "selftests" ]; then
+	base_dir=`pwd`
+	install_dir="$base_dir"/kselftest_install
+
+	# Make sure we're in the selftests top-level directory.
+	if [ $(basename "$base_dir") !=  "selftests" ]; then
 		echo "$0: Please run it in selftests directory ..."
 		exit 1;
 	fi
+
+	# Only allow installation into an existing location.
 	if [ "$#" -eq 0 ]; then
-		echo "$0: Installing in default location - $install_loc ..."
+		echo "$0: Installing in default location - $install_dir ..."
 	elif [ ! -d "$1" ]; then
 		echo "$0: $1 doesn't exist!!"
 		exit 1;
 	else
-		install_loc=$1
-		echo "$0: Installing in specified location - $install_loc ..."
+		install_dir="$1"
+		echo "$0: Installing in specified location - $install_dir ..."
 	fi
 
-	install_dir=$install_loc/kselftest
-
-# Create install directory
-	mkdir -p $install_dir
-# Build tests
-	INSTALL_PATH=$install_dir make install
+	# Build tests
+	INSTALL_PATH="$install_dir" make install
 }
 
 main "$@"
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 077337195783..c8b8aa6156f6 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -83,17 +83,20 @@ else
 	$(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS))
 endif
 
+define INSTALL_SINGLE_RULE
+	$(if $(INSTALL_LIST),@mkdir -p $(INSTALL_PATH))
+	$(if $(INSTALL_LIST),@echo rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/)
+	$(if $(INSTALL_LIST),@rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/)
+endef
+
 define INSTALL_RULE
-	@if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then					\
-		mkdir -p ${INSTALL_PATH};										\
-		echo "rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/";	\
-		rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/;		\
-	fi
-	@if [ "X$(TEST_GEN_PROGS)$(TEST_CUSTOM_PROGS)$(TEST_GEN_PROGS_EXTENDED)$(TEST_GEN_FILES)" != "X" ]; then					\
-		mkdir -p ${INSTALL_PATH};										\
-		echo "rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/";	\
-		rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/;		\
-	fi
+	$(eval INSTALL_LIST = $(TEST_PROGS)) $(INSTALL_SINGLE_RULE)
+	$(eval INSTALL_LIST = $(TEST_PROGS_EXTENDED)) $(INSTALL_SINGLE_RULE)
+	$(eval INSTALL_LIST = $(TEST_FILES)) $(INSTALL_SINGLE_RULE)
+	$(eval INSTALL_LIST = $(TEST_GEN_PROGS)) $(INSTALL_SINGLE_RULE)
+	$(eval INSTALL_LIST = $(TEST_CUSTOM_PROGS)) $(INSTALL_SINGLE_RULE)
+	$(eval INSTALL_LIST = $(TEST_GEN_PROGS_EXTENDED)) $(INSTALL_SINGLE_RULE)
+	$(eval INSTALL_LIST = $(TEST_GEN_FILES)) $(INSTALL_SINGLE_RULE)
 endef
 
 install: all
diff --git a/tools/testing/selftests/livepatch/Makefile b/tools/testing/selftests/livepatch/Makefile
index fd405402c3ff..485696a01989 100644
--- a/tools/testing/selftests/livepatch/Makefile
+++ b/tools/testing/selftests/livepatch/Makefile
@@ -6,4 +6,6 @@ TEST_PROGS := \
 	test-callbacks.sh \
 	test-shadow-vars.sh
 
+TEST_FILES := settings
+
 include ../lib.mk
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index dacf1ffb7d46..249c463c4f89 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -586,16 +586,22 @@ fib_nexthop_test()
 
 fib_suppress_test()
 {
+	echo
+	echo "FIB rule with suppress_prefixlength"
+	setup
+
 	$IP link add dummy1 type dummy
 	$IP link set dummy1 up
 	$IP -6 route add default dev dummy1
 	$IP -6 rule add table main suppress_prefixlength 0
-	ping -f -c 1000 -W 1 1234::1 || true
+	ping -f -c 1000 -W 1 1234::1 >/dev/null 2>&1
 	$IP -6 rule del table main suppress_prefixlength 0
 	$IP link del dummy1
 
 	# If we got here without crashing, we're good.
-	return 0
+	log_test 0 0 "FIB rule suppress test"
+
+	cleanup
 }
 
 ################################################################################
@@ -878,6 +884,12 @@ ipv6_rt_replace_mpath()
 	check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024"
 	log_test $? 0 "Multipath with single path via multipath attribute"
 
+	# multipath with dev-only
+	add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+	run_cmd "$IP -6 ro replace 2001:db8:104::/64 dev veth1"
+	check_route6 "2001:db8:104::/64 dev veth1 metric 1024"
+	log_test $? 0 "Multipath with dev-only"
+
 	# route replace fails - invalid nexthop 1
 	add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
 	run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:111::3 nexthop via 2001:db8:103::3"
@@ -1003,6 +1015,27 @@ ipv6_addr_metric_test()
 	fi
 	log_test $rc 0 "Prefix route with metric on link up"
 
+	# verify peer metric added correctly
+	set -e
+	run_cmd "$IP -6 addr flush dev dummy2"
+	run_cmd "$IP -6 addr add dev dummy2 2001:db8:104::1 peer 2001:db8:104::2 metric 260"
+	set +e
+
+	check_route6 "2001:db8:104::1 dev dummy2 proto kernel metric 260"
+	log_test $? 0 "Set metric with peer route on local side"
+	log_test $? 0 "User specified metric on local address"
+	check_route6 "2001:db8:104::2 dev dummy2 proto kernel metric 260"
+	log_test $? 0 "Set metric with peer route on peer side"
+
+	set -e
+	run_cmd "$IP -6 addr change dev dummy2 2001:db8:104::1 peer 2001:db8:104::3 metric 261"
+	set +e
+
+	check_route6 "2001:db8:104::1 dev dummy2 proto kernel metric 261"
+	log_test $? 0 "Modify metric and peer address on local side"
+	check_route6 "2001:db8:104::3 dev dummy2 proto kernel metric 261"
+	log_test $? 0 "Modify metric and peer address on peer side"
+
 	$IP li del dummy1
 	$IP li del dummy2
 	cleanup
@@ -1419,13 +1452,20 @@ ipv4_addr_metric_test()
 
 	run_cmd "$IP addr flush dev dummy2"
 	run_cmd "$IP addr add dev dummy2 172.16.104.1/32 peer 172.16.104.2 metric 260"
-	run_cmd "$IP addr change dev dummy2 172.16.104.1/32 peer 172.16.104.2 metric 261"
 	rc=$?
 	if [ $rc -eq 0 ]; then
-		check_route "172.16.104.2 dev dummy2 proto kernel scope link src 172.16.104.1 metric 261"
+		check_route "172.16.104.2 dev dummy2 proto kernel scope link src 172.16.104.1 metric 260"
+		rc=$?
+	fi
+	log_test $rc 0 "Set metric of address with peer route"
+
+	run_cmd "$IP addr change dev dummy2 172.16.104.1/32 peer 172.16.104.3 metric 261"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route "172.16.104.3 dev dummy2 proto kernel scope link src 172.16.104.1 metric 261"
 		rc=$?
 	fi
-	log_test $rc 0 "Modify metric of address with peer route"
+	log_test $rc 0 "Modify metric and peer address for peer route"
 
 	$IP li del dummy1
 	$IP li del dummy2
diff --git a/tools/testing/selftests/net/forwarding/loopback.sh b/tools/testing/selftests/net/forwarding/loopback.sh
index 6e4626ae71b0..8f4057310b5b 100755
--- a/tools/testing/selftests/net/forwarding/loopback.sh
+++ b/tools/testing/selftests/net/forwarding/loopback.sh
@@ -1,6 +1,9 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
 ALL_TESTS="loopback_test"
 NUM_NETIFS=2
 source tc_common.sh
@@ -72,6 +75,11 @@ setup_prepare()
 
 	h1_create
 	h2_create
+
+	if ethtool -k $h1 | grep loopback | grep -q fixed; then
+		log_test "SKIP: dev $h1 does not support loopback feature"
+		exit $ksft_skip
+	fi
 }
 
 cleanup()
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre.sh b/tools/testing/selftests/net/forwarding/mirror_gre.sh
index e6fd7a18c655..0266443601bc 100755
--- a/tools/testing/selftests/net/forwarding/mirror_gre.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_gre.sh
@@ -63,22 +63,23 @@ test_span_gre_mac()
 {
 	local tundev=$1; shift
 	local direction=$1; shift
-	local prot=$1; shift
 	local what=$1; shift
 
-	local swp3mac=$(mac_get $swp3)
-	local h3mac=$(mac_get $h3)
+	case "$direction" in
+	ingress) local src_mac=$(mac_get $h1); local dst_mac=$(mac_get $h2)
+		;;
+	egress) local src_mac=$(mac_get $h2); local dst_mac=$(mac_get $h1)
+		;;
+	esac
 
 	RET=0
 
 	mirror_install $swp1 $direction $tundev "matchall $tcflags"
-	tc filter add dev $h3 ingress pref 77 prot $prot \
-		flower ip_proto 0x2f src_mac $swp3mac dst_mac $h3mac \
-		action pass
+	icmp_capture_install h3-${tundev} "src_mac $src_mac dst_mac $dst_mac"
 
-	mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 10
+	mirror_test v$h1 192.0.2.1 192.0.2.2 h3-${tundev} 100 10
 
-	tc filter del dev $h3 ingress pref 77
+	icmp_capture_uninstall h3-${tundev}
 	mirror_uninstall $swp1 $direction
 
 	log_test "$direction $what: envelope MAC ($tcflags)"
@@ -120,14 +121,14 @@ test_ip6gretap()
 
 test_gretap_mac()
 {
-	test_span_gre_mac gt4 ingress ip "mirror to gretap"
-	test_span_gre_mac gt4 egress ip "mirror to gretap"
+	test_span_gre_mac gt4 ingress "mirror to gretap"
+	test_span_gre_mac gt4 egress "mirror to gretap"
 }
 
 test_ip6gretap_mac()
 {
-	test_span_gre_mac gt6 ingress ipv6 "mirror to ip6gretap"
-	test_span_gre_mac gt6 egress ipv6 "mirror to ip6gretap"
+	test_span_gre_mac gt6 ingress "mirror to ip6gretap"
+	test_span_gre_mac gt6 egress "mirror to ip6gretap"
 }
 
 test_all()
diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index bb10e33690b2..ce6bea9675c0 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -516,9 +516,9 @@ test_tos()
 	RET=0
 
 	tc filter add dev v1 egress pref 77 prot ip \
-		flower ip_tos 0x40 action pass
-	vxlan_ping_test $h1 192.0.2.3 "-Q 0x40" v1 egress 77 10
-	vxlan_ping_test $h1 192.0.2.3 "-Q 0x30" v1 egress 77 0
+		flower ip_tos 0x14 action pass
+	vxlan_ping_test $h1 192.0.2.3 "-Q 0x14" v1 egress 77 10
+	vxlan_ping_test $h1 192.0.2.3 "-Q 0x18" v1 egress 77 0
 	tc filter del dev v1 egress pref 77 prot ip
 
 	log_test "VXLAN: envelope TOS inheritance"
diff --git a/tools/testing/selftests/net/ip_defrag.sh b/tools/testing/selftests/net/ip_defrag.sh
index 15d3489ecd9c..ceb7ad4dbd94 100755
--- a/tools/testing/selftests/net/ip_defrag.sh
+++ b/tools/testing/selftests/net/ip_defrag.sh
@@ -6,6 +6,8 @@
 set +x
 set -e
 
+modprobe -q nf_defrag_ipv6
+
 readonly NETNS="ns-$(mktemp -u XXXXXX)"
 
 setup() {
diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c
index 4b02933cab8a..bdc03a2097e8 100644
--- a/tools/testing/selftests/net/msg_zerocopy.c
+++ b/tools/testing/selftests/net/msg_zerocopy.c
@@ -125,9 +125,8 @@ static int do_setcpu(int cpu)
 	CPU_ZERO(&mask);
 	CPU_SET(cpu, &mask);
 	if (sched_setaffinity(0, sizeof(mask), &mask))
-		error(1, 0, "setaffinity %d", cpu);
-
-	if (cfg_verbose)
+		fprintf(stderr, "cpu: unable to pin, may increase variance.\n");
+	else if (cfg_verbose)
 		fprintf(stderr, "cpu: %u\n", cpu);
 
 	return 0;
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 317dafcd605d..8e065ada6a0f 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -11,9 +11,9 @@
 #	R1 and R2 (also implemented with namespaces), with different MTUs:
 #
 #	  segment a_r1    segment b_r1		a_r1: 2000
-#	.--------------R1--------------.	a_r2: 1500
-#	A                               B	a_r3: 2000
-#	'--------------R2--------------'	a_r4: 1400
+#	.--------------R1--------------.	b_r1: 1400
+#	A                               B	a_r2: 2000
+#	'--------------R2--------------'	b_r2: 1500
 #	  segment a_r2    segment b_r2
 #
 #	Check that PMTU exceptions with the correct PMTU are created. Then
diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c
index 8c8c7d79c38d..2c522f7a0aec 100644
--- a/tools/testing/selftests/net/psock_fanout.c
+++ b/tools/testing/selftests/net/psock_fanout.c
@@ -350,7 +350,8 @@ static int test_datapath(uint16_t typeflags, int port_off,
 	int fds[2], fds_udp[2][2], ret;
 
 	fprintf(stderr, "\ntest: datapath 0x%hx ports %hu,%hu\n",
-		typeflags, PORT_BASE, PORT_BASE + port_off);
+		typeflags, (uint16_t)PORT_BASE,
+		(uint16_t)(PORT_BASE + port_off));
 
 	fds[0] = sock_fanout_open(typeflags, 0);
 	fds[1] = sock_fanout_open(typeflags, 0);
diff --git a/tools/testing/selftests/net/reuseport_addr_any.c b/tools/testing/selftests/net/reuseport_addr_any.c
index c6233935fed1..b8475cb29be7 100644
--- a/tools/testing/selftests/net/reuseport_addr_any.c
+++ b/tools/testing/selftests/net/reuseport_addr_any.c
@@ -21,6 +21,10 @@
 #include <sys/socket.h>
 #include <unistd.h>
 
+#ifndef SOL_DCCP
+#define SOL_DCCP 269
+#endif
+
 static const char *IP4_ADDR = "127.0.0.1";
 static const char *IP6_ADDR = "::1";
 static const char *IP4_MAPPED6 = "::ffff:127.0.0.1";
diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh
index 1be55e705780..d7e07f4c3d7f 100755
--- a/tools/testing/selftests/netfilter/nft_nat.sh
+++ b/tools/testing/selftests/netfilter/nft_nat.sh
@@ -8,9 +8,14 @@ ksft_skip=4
 ret=0
 test_inet_nat=true
 
+sfx=$(mktemp -u "XXXXXXXX")
+ns0="ns0-$sfx"
+ns1="ns1-$sfx"
+ns2="ns2-$sfx"
+
 cleanup()
 {
-	for i in 0 1 2; do ip netns del ns$i;done
+	for i in 0 1 2; do ip netns del ns$i-"$sfx";done
 }
 
 nft --version > /dev/null 2>&1
@@ -25,40 +30,49 @@ if [ $? -ne 0 ];then
 	exit $ksft_skip
 fi
 
-ip netns add ns0
+ip netns add "$ns0"
 if [ $? -ne 0 ];then
-	echo "SKIP: Could not create net namespace"
+	echo "SKIP: Could not create net namespace $ns0"
 	exit $ksft_skip
 fi
 
 trap cleanup EXIT
 
-ip netns add ns1
-ip netns add ns2
+ip netns add "$ns1"
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not create net namespace $ns1"
+	exit $ksft_skip
+fi
+
+ip netns add "$ns2"
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not create net namespace $ns2"
+	exit $ksft_skip
+fi
 
-ip link add veth0 netns ns0 type veth peer name eth0 netns ns1 > /dev/null 2>&1
+ip link add veth0 netns "$ns0" type veth peer name eth0 netns "$ns1" > /dev/null 2>&1
 if [ $? -ne 0 ];then
     echo "SKIP: No virtual ethernet pair device support in kernel"
     exit $ksft_skip
 fi
-ip link add veth1 netns ns0 type veth peer name eth0 netns ns2
+ip link add veth1 netns "$ns0" type veth peer name eth0 netns "$ns2"
 
-ip -net ns0 link set lo up
-ip -net ns0 link set veth0 up
-ip -net ns0 addr add 10.0.1.1/24 dev veth0
-ip -net ns0 addr add dead:1::1/64 dev veth0
+ip -net "$ns0" link set lo up
+ip -net "$ns0" link set veth0 up
+ip -net "$ns0" addr add 10.0.1.1/24 dev veth0
+ip -net "$ns0" addr add dead:1::1/64 dev veth0
 
-ip -net ns0 link set veth1 up
-ip -net ns0 addr add 10.0.2.1/24 dev veth1
-ip -net ns0 addr add dead:2::1/64 dev veth1
+ip -net "$ns0" link set veth1 up
+ip -net "$ns0" addr add 10.0.2.1/24 dev veth1
+ip -net "$ns0" addr add dead:2::1/64 dev veth1
 
 for i in 1 2; do
-  ip -net ns$i link set lo up
-  ip -net ns$i link set eth0 up
-  ip -net ns$i addr add 10.0.$i.99/24 dev eth0
-  ip -net ns$i route add default via 10.0.$i.1
-  ip -net ns$i addr add dead:$i::99/64 dev eth0
-  ip -net ns$i route add default via dead:$i::1
+  ip -net ns$i-$sfx link set lo up
+  ip -net ns$i-$sfx link set eth0 up
+  ip -net ns$i-$sfx addr add 10.0.$i.99/24 dev eth0
+  ip -net ns$i-$sfx route add default via 10.0.$i.1
+  ip -net ns$i-$sfx addr add dead:$i::99/64 dev eth0
+  ip -net ns$i-$sfx route add default via dead:$i::1
 done
 
 bad_counter()
@@ -66,8 +80,9 @@ bad_counter()
 	local ns=$1
 	local counter=$2
 	local expect=$3
+	local tag=$4
 
-	echo "ERROR: $counter counter in $ns has unexpected value (expected $expect)" 1>&2
+	echo "ERROR: $counter counter in $ns has unexpected value (expected $expect) at $tag" 1>&2
 	ip netns exec $ns nft list counter inet filter $counter 1>&2
 }
 
@@ -78,24 +93,24 @@ check_counters()
 
 	cnt=$(ip netns exec $ns nft list counter inet filter ns0in | grep -q "packets 1 bytes 84")
 	if [ $? -ne 0 ]; then
-		bad_counter $ns ns0in "packets 1 bytes 84"
+		bad_counter $ns ns0in "packets 1 bytes 84" "check_counters 1"
 		lret=1
 	fi
 	cnt=$(ip netns exec $ns nft list counter inet filter ns0out | grep -q "packets 1 bytes 84")
 	if [ $? -ne 0 ]; then
-		bad_counter $ns ns0out "packets 1 bytes 84"
+		bad_counter $ns ns0out "packets 1 bytes 84" "check_counters 2"
 		lret=1
 	fi
 
 	expect="packets 1 bytes 104"
 	cnt=$(ip netns exec $ns nft list counter inet filter ns0in6 | grep -q "$expect")
 	if [ $? -ne 0 ]; then
-		bad_counter $ns ns0in6 "$expect"
+		bad_counter $ns ns0in6 "$expect" "check_counters 3"
 		lret=1
 	fi
 	cnt=$(ip netns exec $ns nft list counter inet filter ns0out6 | grep -q "$expect")
 	if [ $? -ne 0 ]; then
-		bad_counter $ns ns0out6 "$expect"
+		bad_counter $ns ns0out6 "$expect" "check_counters 4"
 		lret=1
 	fi
 
@@ -107,41 +122,41 @@ check_ns0_counters()
 	local ns=$1
 	local lret=0
 
-	cnt=$(ip netns exec ns0 nft list counter inet filter ns0in | grep -q "packets 0 bytes 0")
+	cnt=$(ip netns exec "$ns0" nft list counter inet filter ns0in | grep -q "packets 0 bytes 0")
 	if [ $? -ne 0 ]; then
-		bad_counter ns0 ns0in "packets 0 bytes 0"
+		bad_counter "$ns0" ns0in "packets 0 bytes 0" "check_ns0_counters 1"
 		lret=1
 	fi
 
-	cnt=$(ip netns exec ns0 nft list counter inet filter ns0in6 | grep -q "packets 0 bytes 0")
+	cnt=$(ip netns exec "$ns0" nft list counter inet filter ns0in6 | grep -q "packets 0 bytes 0")
 	if [ $? -ne 0 ]; then
-		bad_counter ns0 ns0in6 "packets 0 bytes 0"
+		bad_counter "$ns0" ns0in6 "packets 0 bytes 0"
 		lret=1
 	fi
 
-	cnt=$(ip netns exec ns0 nft list counter inet filter ns0out | grep -q "packets 0 bytes 0")
+	cnt=$(ip netns exec "$ns0" nft list counter inet filter ns0out | grep -q "packets 0 bytes 0")
 	if [ $? -ne 0 ]; then
-		bad_counter ns0 ns0out "packets 0 bytes 0"
+		bad_counter "$ns0" ns0out "packets 0 bytes 0" "check_ns0_counters 2"
 		lret=1
 	fi
-	cnt=$(ip netns exec ns0 nft list counter inet filter ns0out6 | grep -q "packets 0 bytes 0")
+	cnt=$(ip netns exec "$ns0" nft list counter inet filter ns0out6 | grep -q "packets 0 bytes 0")
 	if [ $? -ne 0 ]; then
-		bad_counter ns0 ns0out6 "packets 0 bytes 0"
+		bad_counter "$ns0" ns0out6 "packets 0 bytes 0" "check_ns0_counters3 "
 		lret=1
 	fi
 
 	for dir in "in" "out" ; do
 		expect="packets 1 bytes 84"
-		cnt=$(ip netns exec ns0 nft list counter inet filter ${ns}${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns0" nft list counter inet filter ${ns}${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns0 $ns$dir "$expect"
+			bad_counter "$ns0" $ns$dir "$expect" "check_ns0_counters 4"
 			lret=1
 		fi
 
 		expect="packets 1 bytes 104"
-		cnt=$(ip netns exec ns0 nft list counter inet filter ${ns}${dir}6 | grep -q "$expect")
+		cnt=$(ip netns exec "$ns0" nft list counter inet filter ${ns}${dir}6 | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns0 $ns$dir6 "$expect"
+			bad_counter "$ns0" $ns$dir6 "$expect" "check_ns0_counters 5"
 			lret=1
 		fi
 	done
@@ -152,7 +167,7 @@ check_ns0_counters()
 reset_counters()
 {
 	for i in 0 1 2;do
-		ip netns exec ns$i nft reset counters inet > /dev/null
+		ip netns exec ns$i-$sfx nft reset counters inet > /dev/null
 	done
 }
 
@@ -166,7 +181,7 @@ test_local_dnat6()
 		IPF="ip6"
 	fi
 
-ip netns exec ns0 nft -f - <<EOF
+ip netns exec "$ns0" nft -f /dev/stdin <<EOF
 table $family nat {
 	chain output {
 		type nat hook output priority 0; policy accept;
@@ -180,7 +195,7 @@ EOF
 	fi
 
 	# ping netns1, expect rewrite to netns2
-	ip netns exec ns0 ping -q -c 1 dead:1::99 > /dev/null
+	ip netns exec "$ns0" ping -q -c 1 dead:1::99 > /dev/null
 	if [ $? -ne 0 ]; then
 		lret=1
 		echo "ERROR: ping6 failed"
@@ -189,18 +204,18 @@ EOF
 
 	expect="packets 0 bytes 0"
 	for dir in "in6" "out6" ; do
-		cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns0 ns1$dir "$expect"
+			bad_counter "$ns0" ns1$dir "$expect" "test_local_dnat6 1"
 			lret=1
 		fi
 	done
 
 	expect="packets 1 bytes 104"
 	for dir in "in6" "out6" ; do
-		cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns0" nft list counter inet filter ns2${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns0 ns2$dir "$expect"
+			bad_counter "$ns0" ns2$dir "$expect" "test_local_dnat6 2"
 			lret=1
 		fi
 	done
@@ -208,9 +223,9 @@ EOF
 	# expect 0 count in ns1
 	expect="packets 0 bytes 0"
 	for dir in "in6" "out6" ; do
-		cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns1 ns0$dir "$expect"
+			bad_counter "$ns1" ns0$dir "$expect" "test_local_dnat6 3"
 			lret=1
 		fi
 	done
@@ -218,15 +233,15 @@ EOF
 	# expect 1 packet in ns2
 	expect="packets 1 bytes 104"
 	for dir in "in6" "out6" ; do
-		cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns2" nft list counter inet filter ns0${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns2 ns0$dir "$expect"
+			bad_counter "$ns2" ns0$dir "$expect" "test_local_dnat6 4"
 			lret=1
 		fi
 	done
 
-	test $lret -eq 0 && echo "PASS: ipv6 ping to ns1 was $family NATted to ns2"
-	ip netns exec ns0 nft flush chain ip6 nat output
+	test $lret -eq 0 && echo "PASS: ipv6 ping to $ns1 was $family NATted to $ns2"
+	ip netns exec "$ns0" nft flush chain ip6 nat output
 
 	return $lret
 }
@@ -241,7 +256,7 @@ test_local_dnat()
 		IPF="ip"
 	fi
 
-ip netns exec ns0 nft -f - <<EOF 2>/dev/null
+ip netns exec "$ns0" nft -f /dev/stdin <<EOF 2>/dev/null
 table $family nat {
 	chain output {
 		type nat hook output priority 0; policy accept;
@@ -260,7 +275,7 @@ EOF
 	fi
 
 	# ping netns1, expect rewrite to netns2
-	ip netns exec ns0 ping -q -c 1 10.0.1.99 > /dev/null
+	ip netns exec "$ns0" ping -q -c 1 10.0.1.99 > /dev/null
 	if [ $? -ne 0 ]; then
 		lret=1
 		echo "ERROR: ping failed"
@@ -269,18 +284,18 @@ EOF
 
 	expect="packets 0 bytes 0"
 	for dir in "in" "out" ; do
-		cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns0 ns1$dir "$expect"
+			bad_counter "$ns0" ns1$dir "$expect" "test_local_dnat 1"
 			lret=1
 		fi
 	done
 
 	expect="packets 1 bytes 84"
 	for dir in "in" "out" ; do
-		cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns0" nft list counter inet filter ns2${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns0 ns2$dir "$expect"
+			bad_counter "$ns0" ns2$dir "$expect" "test_local_dnat 2"
 			lret=1
 		fi
 	done
@@ -288,9 +303,9 @@ EOF
 	# expect 0 count in ns1
 	expect="packets 0 bytes 0"
 	for dir in "in" "out" ; do
-		cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns1 ns0$dir "$expect"
+			bad_counter "$ns1" ns0$dir "$expect" "test_local_dnat 3"
 			lret=1
 		fi
 	done
@@ -298,19 +313,19 @@ EOF
 	# expect 1 packet in ns2
 	expect="packets 1 bytes 84"
 	for dir in "in" "out" ; do
-		cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns2" nft list counter inet filter ns0${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns2 ns0$dir "$expect"
+			bad_counter "$ns2" ns0$dir "$expect" "test_local_dnat 4"
 			lret=1
 		fi
 	done
 
-	test $lret -eq 0 && echo "PASS: ping to ns1 was $family NATted to ns2"
+	test $lret -eq 0 && echo "PASS: ping to $ns1 was $family NATted to $ns2"
 
-	ip netns exec ns0 nft flush chain $family nat output
+	ip netns exec "$ns0" nft flush chain $family nat output
 
 	reset_counters
-	ip netns exec ns0 ping -q -c 1 10.0.1.99 > /dev/null
+	ip netns exec "$ns0" ping -q -c 1 10.0.1.99 > /dev/null
 	if [ $? -ne 0 ]; then
 		lret=1
 		echo "ERROR: ping failed"
@@ -319,17 +334,17 @@ EOF
 
 	expect="packets 1 bytes 84"
 	for dir in "in" "out" ; do
-		cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns1 ns1$dir "$expect"
+			bad_counter "$ns1" ns1$dir "$expect" "test_local_dnat 5"
 			lret=1
 		fi
 	done
 	expect="packets 0 bytes 0"
 	for dir in "in" "out" ; do
-		cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns0" nft list counter inet filter ns2${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns0 ns2$dir "$expect"
+			bad_counter "$ns0" ns2$dir "$expect" "test_local_dnat 6"
 			lret=1
 		fi
 	done
@@ -337,9 +352,9 @@ EOF
 	# expect 1 count in ns1
 	expect="packets 1 bytes 84"
 	for dir in "in" "out" ; do
-		cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns0 ns0$dir "$expect"
+			bad_counter "$ns0" ns0$dir "$expect" "test_local_dnat 7"
 			lret=1
 		fi
 	done
@@ -347,14 +362,14 @@ EOF
 	# expect 0 packet in ns2
 	expect="packets 0 bytes 0"
 	for dir in "in" "out" ; do
-		cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns2" nft list counter inet filter ns0${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns2 ns2$dir "$expect"
+			bad_counter "$ns2" ns0$dir "$expect" "test_local_dnat 8"
 			lret=1
 		fi
 	done
 
-	test $lret -eq 0 && echo "PASS: ping to ns1 OK after $family nat output chain flush"
+	test $lret -eq 0 && echo "PASS: ping to $ns1 OK after $family nat output chain flush"
 
 	return $lret
 }
@@ -366,26 +381,26 @@ test_masquerade6()
 	local natflags=$2
 	local lret=0
 
-	ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
+	ip netns exec "$ns0" sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
 
-	ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
+	ip netns exec "$ns2" ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
 	if [ $? -ne 0 ] ; then
-		echo "ERROR: cannot ping ns1 from ns2 via ipv6"
+		echo "ERROR: cannot ping $ns1 from $ns2 via ipv6"
 		return 1
 		lret=1
 	fi
 
 	expect="packets 1 bytes 104"
 	for dir in "in6" "out6" ; do
-		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns1 ns2$dir "$expect"
+			bad_counter "$ns1" ns2$dir "$expect" "test_masquerade6 1"
 			lret=1
 		fi
 
-		cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns2 ns1$dir "$expect"
+			bad_counter "$ns2" ns1$dir "$expect" "test_masquerade6 2"
 			lret=1
 		fi
 	done
@@ -393,7 +408,7 @@ test_masquerade6()
 	reset_counters
 
 # add masquerading rule
-ip netns exec ns0 nft -f - <<EOF
+ip netns exec "$ns0" nft -f /dev/stdin <<EOF
 table $family nat {
 	chain postrouting {
 		type nat hook postrouting priority 0; policy accept;
@@ -406,24 +421,24 @@ EOF
 		return $ksft_skip
 	fi
 
-	ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
+	ip netns exec "$ns2" ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
 	if [ $? -ne 0 ] ; then
-		echo "ERROR: cannot ping ns1 from ns2 with active $family masquerade $natflags"
+		echo "ERROR: cannot ping $ns1 from $ns2 with active $family masquerade $natflags"
 		lret=1
 	fi
 
 	# ns1 should have seen packets from ns0, due to masquerade
 	expect="packets 1 bytes 104"
 	for dir in "in6" "out6" ; do
-		cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns1 ns0$dir "$expect"
+			bad_counter "$ns1" ns0$dir "$expect" "test_masquerade6 3"
 			lret=1
 		fi
 
-		cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns2 ns1$dir "$expect"
+			bad_counter "$ns2" ns1$dir "$expect" "test_masquerade6 4"
 			lret=1
 		fi
 	done
@@ -431,32 +446,32 @@ EOF
 	# ns1 should not have seen packets from ns2, due to masquerade
 	expect="packets 0 bytes 0"
 	for dir in "in6" "out6" ; do
-		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns1 ns0$dir "$expect"
+			bad_counter "$ns1" ns0$dir "$expect" "test_masquerade6 5"
 			lret=1
 		fi
 
-		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns2 ns1$dir "$expect"
+			bad_counter "$ns0" ns1$dir "$expect" "test_masquerade6 6"
 			lret=1
 		fi
 	done
 
-	ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
+	ip netns exec "$ns2" ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
 	if [ $? -ne 0 ] ; then
-		echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerade $natflags (attempt 2)"
+		echo "ERROR: cannot ping $ns1 from $ns2 with active ipv6 masquerade $natflags (attempt 2)"
 		lret=1
 	fi
 
-	ip netns exec ns0 nft flush chain $family nat postrouting
+	ip netns exec "$ns0" nft flush chain $family nat postrouting
 	if [ $? -ne 0 ]; then
 		echo "ERROR: Could not flush $family nat postrouting" 1>&2
 		lret=1
 	fi
 
-	test $lret -eq 0 && echo "PASS: $family IPv6 masquerade $natflags for ns2"
+	test $lret -eq 0 && echo "PASS: $family IPv6 masquerade $natflags for $ns2"
 
 	return $lret
 }
@@ -467,26 +482,26 @@ test_masquerade()
 	local natflags=$2
 	local lret=0
 
-	ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
-	ip netns exec ns0 sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
+	ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
+	ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
 
-	ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+	ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
 	if [ $? -ne 0 ] ; then
-		echo "ERROR: cannot ping ns1 from ns2 $natflags"
+		echo "ERROR: cannot ping $ns1 from "$ns2" $natflags"
 		lret=1
 	fi
 
 	expect="packets 1 bytes 84"
 	for dir in "in" "out" ; do
-		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns1 ns2$dir "$expect"
+			bad_counter "$ns1" ns2$dir "$expect" "test_masquerade 1"
 			lret=1
 		fi
 
-		cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns2 ns1$dir "$expect"
+			bad_counter "$ns2" ns1$dir "$expect" "test_masquerade 2"
 			lret=1
 		fi
 	done
@@ -494,7 +509,7 @@ test_masquerade()
 	reset_counters
 
 # add masquerading rule
-ip netns exec ns0 nft -f - <<EOF
+ip netns exec "$ns0" nft -f /dev/stdin <<EOF
 table $family nat {
 	chain postrouting {
 		type nat hook postrouting priority 0; policy accept;
@@ -507,24 +522,24 @@ EOF
 		return $ksft_skip
 	fi
 
-	ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+	ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
 	if [ $? -ne 0 ] ; then
-		echo "ERROR: cannot ping ns1 from ns2 with active $family masquerade $natflags"
+		echo "ERROR: cannot ping $ns1 from $ns2 with active $family masquerade $natflags"
 		lret=1
 	fi
 
 	# ns1 should have seen packets from ns0, due to masquerade
 	expect="packets 1 bytes 84"
 	for dir in "in" "out" ; do
-		cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns1 ns0$dir "$expect"
+			bad_counter "$ns1" ns0$dir "$expect" "test_masquerade 3"
 			lret=1
 		fi
 
-		cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns2 ns1$dir "$expect"
+			bad_counter "$ns2" ns1$dir "$expect" "test_masquerade 4"
 			lret=1
 		fi
 	done
@@ -532,32 +547,32 @@ EOF
 	# ns1 should not have seen packets from ns2, due to masquerade
 	expect="packets 0 bytes 0"
 	for dir in "in" "out" ; do
-		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns1 ns0$dir "$expect"
+			bad_counter "$ns1" ns0$dir "$expect" "test_masquerade 5"
 			lret=1
 		fi
 
-		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns2 ns1$dir "$expect"
+			bad_counter "$ns0" ns1$dir "$expect" "test_masquerade 6"
 			lret=1
 		fi
 	done
 
-	ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+	ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
 	if [ $? -ne 0 ] ; then
-		echo "ERROR: cannot ping ns1 from ns2 with active ip masquerade $natflags (attempt 2)"
+		echo "ERROR: cannot ping $ns1 from $ns2 with active ip masquerade $natflags (attempt 2)"
 		lret=1
 	fi
 
-	ip netns exec ns0 nft flush chain $family nat postrouting
+	ip netns exec "$ns0" nft flush chain $family nat postrouting
 	if [ $? -ne 0 ]; then
 		echo "ERROR: Could not flush $family nat postrouting" 1>&2
 		lret=1
 	fi
 
-	test $lret -eq 0 && echo "PASS: $family IP masquerade $natflags for ns2"
+	test $lret -eq 0 && echo "PASS: $family IP masquerade $natflags for $ns2"
 
 	return $lret
 }
@@ -567,25 +582,25 @@ test_redirect6()
 	local family=$1
 	local lret=0
 
-	ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
+	ip netns exec "$ns0" sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
 
-	ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
+	ip netns exec "$ns2" ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
 	if [ $? -ne 0 ] ; then
-		echo "ERROR: cannnot ping ns1 from ns2 via ipv6"
+		echo "ERROR: cannnot ping $ns1 from $ns2 via ipv6"
 		lret=1
 	fi
 
 	expect="packets 1 bytes 104"
 	for dir in "in6" "out6" ; do
-		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns1 ns2$dir "$expect"
+			bad_counter "$ns1" ns2$dir "$expect" "test_redirect6 1"
 			lret=1
 		fi
 
-		cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns2 ns1$dir "$expect"
+			bad_counter "$ns2" ns1$dir "$expect" "test_redirect6 2"
 			lret=1
 		fi
 	done
@@ -593,7 +608,7 @@ test_redirect6()
 	reset_counters
 
 # add redirect rule
-ip netns exec ns0 nft -f - <<EOF
+ip netns exec "$ns0" nft -f /dev/stdin <<EOF
 table $family nat {
 	chain prerouting {
 		type nat hook prerouting priority 0; policy accept;
@@ -606,18 +621,18 @@ EOF
 		return $ksft_skip
 	fi
 
-	ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
+	ip netns exec "$ns2" ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
 	if [ $? -ne 0 ] ; then
-		echo "ERROR: cannot ping ns1 from ns2 via ipv6 with active $family redirect"
+		echo "ERROR: cannot ping $ns1 from $ns2 via ipv6 with active $family redirect"
 		lret=1
 	fi
 
 	# ns1 should have seen no packets from ns2, due to redirection
 	expect="packets 0 bytes 0"
 	for dir in "in6" "out6" ; do
-		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns1 ns0$dir "$expect"
+			bad_counter "$ns1" ns0$dir "$expect" "test_redirect6 3"
 			lret=1
 		fi
 	done
@@ -625,20 +640,20 @@ EOF
 	# ns0 should have seen packets from ns2, due to masquerade
 	expect="packets 1 bytes 104"
 	for dir in "in6" "out6" ; do
-		cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns0" nft list counter inet filter ns2${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns1 ns0$dir "$expect"
+			bad_counter "$ns1" ns0$dir "$expect" "test_redirect6 4"
 			lret=1
 		fi
 	done
 
-	ip netns exec ns0 nft delete table $family nat
+	ip netns exec "$ns0" nft delete table $family nat
 	if [ $? -ne 0 ]; then
 		echo "ERROR: Could not delete $family nat table" 1>&2
 		lret=1
 	fi
 
-	test $lret -eq 0 && echo "PASS: $family IPv6 redirection for ns2"
+	test $lret -eq 0 && echo "PASS: $family IPv6 redirection for $ns2"
 
 	return $lret
 }
@@ -648,26 +663,26 @@ test_redirect()
 	local family=$1
 	local lret=0
 
-	ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
-	ip netns exec ns0 sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
+	ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
+	ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
 
-	ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+	ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
 	if [ $? -ne 0 ] ; then
-		echo "ERROR: cannot ping ns1 from ns2"
+		echo "ERROR: cannot ping $ns1 from $ns2"
 		lret=1
 	fi
 
 	expect="packets 1 bytes 84"
 	for dir in "in" "out" ; do
-		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns1 ns2$dir "$expect"
+			bad_counter "$ns1" $ns2$dir "$expect" "test_redirect 1"
 			lret=1
 		fi
 
-		cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns2 ns1$dir "$expect"
+			bad_counter "$ns2" ns1$dir "$expect" "test_redirect 2"
 			lret=1
 		fi
 	done
@@ -675,7 +690,7 @@ test_redirect()
 	reset_counters
 
 # add redirect rule
-ip netns exec ns0 nft -f - <<EOF
+ip netns exec "$ns0" nft -f /dev/stdin <<EOF
 table $family nat {
 	chain prerouting {
 		type nat hook prerouting priority 0; policy accept;
@@ -688,9 +703,9 @@ EOF
 		return $ksft_skip
 	fi
 
-	ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+	ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
 	if [ $? -ne 0 ] ; then
-		echo "ERROR: cannot ping ns1 from ns2 with active $family ip redirect"
+		echo "ERROR: cannot ping $ns1 from $ns2 with active $family ip redirect"
 		lret=1
 	fi
 
@@ -698,9 +713,9 @@ EOF
 	expect="packets 0 bytes 0"
 	for dir in "in" "out" ; do
 
-		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns1 ns0$dir "$expect"
+			bad_counter "$ns1" ns0$dir "$expect" "test_redirect 3"
 			lret=1
 		fi
 	done
@@ -708,28 +723,28 @@ EOF
 	# ns0 should have seen packets from ns2, due to masquerade
 	expect="packets 1 bytes 84"
 	for dir in "in" "out" ; do
-		cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		cnt=$(ip netns exec "$ns0" nft list counter inet filter ns2${dir} | grep -q "$expect")
 		if [ $? -ne 0 ]; then
-			bad_counter ns1 ns0$dir "$expect"
+			bad_counter "$ns0" ns0$dir "$expect" "test_redirect 4"
 			lret=1
 		fi
 	done
 
-	ip netns exec ns0 nft delete table $family nat
+	ip netns exec "$ns0" nft delete table $family nat
 	if [ $? -ne 0 ]; then
 		echo "ERROR: Could not delete $family nat table" 1>&2
 		lret=1
 	fi
 
-	test $lret -eq 0 && echo "PASS: $family IP redirection for ns2"
+	test $lret -eq 0 && echo "PASS: $family IP redirection for $ns2"
 
 	return $lret
 }
 
 
-# ip netns exec ns0 ping -c 1 -q 10.0.$i.99
+# ip netns exec "$ns0" ping -c 1 -q 10.0.$i.99
 for i in 0 1 2; do
-ip netns exec ns$i nft -f - <<EOF
+ip netns exec ns$i-$sfx nft -f /dev/stdin <<EOF
 table inet filter {
 	counter ns0in {}
 	counter ns1in {}
@@ -796,18 +811,18 @@ done
 sleep 3
 # test basic connectivity
 for i in 1 2; do
-  ip netns exec ns0 ping -c 1 -q 10.0.$i.99 > /dev/null
+  ip netns exec "$ns0" ping -c 1 -q 10.0.$i.99 > /dev/null
   if [ $? -ne 0 ];then
   	echo "ERROR: Could not reach other namespace(s)" 1>&2
 	ret=1
   fi
 
-  ip netns exec ns0 ping -c 1 -q dead:$i::99 > /dev/null
+  ip netns exec "$ns0" ping -c 1 -q dead:$i::99 > /dev/null
   if [ $? -ne 0 ];then
 	echo "ERROR: Could not reach other namespace(s) via ipv6" 1>&2
 	ret=1
   fi
-  check_counters ns$i
+  check_counters ns$i-$sfx
   if [ $? -ne 0 ]; then
 	ret=1
   fi
@@ -820,7 +835,7 @@ for i in 1 2; do
 done
 
 if [ $ret -eq 0 ];then
-	echo "PASS: netns routing/connectivity: ns0 can reach ns1 and ns2"
+	echo "PASS: netns routing/connectivity: $ns0 can reach $ns1 and $ns2"
 fi
 
 reset_counters
@@ -846,4 +861,9 @@ reset_counters
 $test_inet_nat && test_redirect inet
 $test_inet_nat && test_redirect6 inet
 
+if [ $ret -ne 0 ];then
+	echo -n "FAIL: "
+	nft --version
+fi
+
 exit $ret
diff --git a/tools/testing/selftests/networking/timestamping/rxtimestamp.c b/tools/testing/selftests/networking/timestamping/rxtimestamp.c
index 6dee9e636a95..bcb79ba1f214 100644
--- a/tools/testing/selftests/networking/timestamping/rxtimestamp.c
+++ b/tools/testing/selftests/networking/timestamping/rxtimestamp.c
@@ -115,6 +115,7 @@ static struct option long_options[] = {
 	{ "tcp", no_argument, 0, 't' },
 	{ "udp", no_argument, 0, 'u' },
 	{ "ip", no_argument, 0, 'i' },
+	{ NULL, 0, NULL, 0 },
 };
 
 static int next_port = 19999;
@@ -328,8 +329,7 @@ int main(int argc, char **argv)
 	bool all_tests = true;
 	int arg_index = 0;
 	int failures = 0;
-	int s, t;
-	char opt;
+	int s, t, opt;
 
 	while ((opt = getopt_long(argc, argv, "", long_options,
 				  &arg_index)) != -1) {
diff --git a/tools/testing/selftests/networking/timestamping/timestamping.c b/tools/testing/selftests/networking/timestamping/timestamping.c
index 0fbed67bf4f6..96473df878fa 100644
--- a/tools/testing/selftests/networking/timestamping/timestamping.c
+++ b/tools/testing/selftests/networking/timestamping/timestamping.c
@@ -320,10 +320,16 @@ int main(int argc, char **argv)
 	int val;
 	socklen_t len;
 	struct timeval next;
+	size_t if_len;
 
 	if (argc < 2)
 		usage(0);
 	interface = argv[1];
+	if_len = strlen(interface);
+	if (if_len >= IFNAMSIZ) {
+		printf("interface name exceeds IFNAMSIZ\n");
+		exit(1);
+	}
 
 	for (i = 2; i < argc; i++) {
 		if (!strcasecmp(argv[i], "SO_TIMESTAMP"))
@@ -357,12 +363,12 @@ int main(int argc, char **argv)
 		bail("socket");
 
 	memset(&device, 0, sizeof(device));
-	strncpy(device.ifr_name, interface, sizeof(device.ifr_name));
+	memcpy(device.ifr_name, interface, if_len + 1);
 	if (ioctl(sock, SIOCGIFADDR, &device) < 0)
 		bail("getting interface IP address");
 
 	memset(&hwtstamp, 0, sizeof(hwtstamp));
-	strncpy(hwtstamp.ifr_name, interface, sizeof(hwtstamp.ifr_name));
+	memcpy(hwtstamp.ifr_name, interface, if_len + 1);
 	hwtstamp.ifr_data = (void *)&hwconfig;
 	memset(&hwconfig, 0, sizeof(hwconfig));
 	hwconfig.tx_type =
diff --git a/tools/testing/selftests/ntb/ntb_test.sh b/tools/testing/selftests/ntb/ntb_test.sh
index 8a20e03d4cb7..618440062d22 100755
--- a/tools/testing/selftests/ntb/ntb_test.sh
+++ b/tools/testing/selftests/ntb/ntb_test.sh
@@ -241,7 +241,7 @@ function get_files_count()
 	split_remote $LOC
 
 	if [[ "$REMOTE" == "" ]]; then
-		echo $(ls -1 "$LOC"/${NAME}* 2>/dev/null | wc -l)
+		echo $(ls -1 "$VPATH"/${NAME}* 2>/dev/null | wc -l)
 	else
 		echo $(ssh "$REMOTE" "ls -1 \"$VPATH\"/${NAME}* | \
 		       wc -l" 2> /dev/null)
diff --git a/tools/testing/selftests/powerpc/benchmarks/Makefile b/tools/testing/selftests/powerpc/benchmarks/Makefile
index d40300a65b42..a32a6ab89914 100644
--- a/tools/testing/selftests/powerpc/benchmarks/Makefile
+++ b/tools/testing/selftests/powerpc/benchmarks/Makefile
@@ -2,6 +2,8 @@
 TEST_GEN_PROGS := gettimeofday context_switch fork mmap_bench futex_bench null_syscall
 TEST_GEN_FILES := exec_target
 
+TEST_FILES := settings
+
 CFLAGS += -O2
 
 top_srcdir = ../../../../..
diff --git a/tools/testing/selftests/powerpc/benchmarks/context_switch.c b/tools/testing/selftests/powerpc/benchmarks/context_switch.c
index a2e8c9da7fa5..d50cc05df495 100644
--- a/tools/testing/selftests/powerpc/benchmarks/context_switch.c
+++ b/tools/testing/selftests/powerpc/benchmarks/context_switch.c
@@ -19,6 +19,7 @@
 #include <limits.h>
 #include <sys/time.h>
 #include <sys/syscall.h>
+#include <sys/sysinfo.h>
 #include <sys/types.h>
 #include <sys/shm.h>
 #include <linux/futex.h>
@@ -104,8 +105,9 @@ static void start_thread_on(void *(*fn)(void *), void *arg, unsigned long cpu)
 
 static void start_process_on(void *(*fn)(void *), void *arg, unsigned long cpu)
 {
-	int pid;
-	cpu_set_t cpuset;
+	int pid, ncpus;
+	cpu_set_t *cpuset;
+	size_t size;
 
 	pid = fork();
 	if (pid == -1) {
@@ -116,14 +118,23 @@ static void start_process_on(void *(*fn)(void *), void *arg, unsigned long cpu)
 	if (pid)
 		return;
 
-	CPU_ZERO(&cpuset);
-	CPU_SET(cpu, &cpuset);
+	ncpus = get_nprocs();
+	size = CPU_ALLOC_SIZE(ncpus);
+	cpuset = CPU_ALLOC(ncpus);
+	if (!cpuset) {
+		perror("malloc");
+		exit(1);
+	}
+	CPU_ZERO_S(size, cpuset);
+	CPU_SET_S(cpu, size, cpuset);
 
-	if (sched_setaffinity(0, sizeof(cpuset), &cpuset)) {
+	if (sched_setaffinity(0, size, cpuset)) {
 		perror("sched_setaffinity");
+		CPU_FREE(cpuset);
 		exit(1);
 	}
 
+	CPU_FREE(cpuset);
 	fn(arg);
 
 	exit(0);
diff --git a/tools/testing/selftests/powerpc/benchmarks/settings b/tools/testing/selftests/powerpc/benchmarks/settings
new file mode 100644
index 000000000000..e7b9417537fb
--- /dev/null
+++ b/tools/testing/selftests/powerpc/benchmarks/settings
@@ -0,0 +1 @@
+timeout=0
diff --git a/tools/testing/selftests/powerpc/dscr/Makefile b/tools/testing/selftests/powerpc/dscr/Makefile
index 5df476364b4d..cfa6eedcb66c 100644
--- a/tools/testing/selftests/powerpc/dscr/Makefile
+++ b/tools/testing/selftests/powerpc/dscr/Makefile
@@ -3,6 +3,8 @@ TEST_GEN_PROGS := dscr_default_test dscr_explicit_test dscr_user_test	\
 	      dscr_inherit_test dscr_inherit_exec_test dscr_sysfs_test	\
 	      dscr_sysfs_thread_test
 
+TEST_FILES := settings
+
 top_srcdir = ../../../../..
 include ../../lib.mk
 
diff --git a/tools/testing/selftests/powerpc/dscr/settings b/tools/testing/selftests/powerpc/dscr/settings
new file mode 100644
index 000000000000..e7b9417537fb
--- /dev/null
+++ b/tools/testing/selftests/powerpc/dscr/settings
@@ -0,0 +1 @@
+timeout=0
diff --git a/tools/testing/selftests/powerpc/mm/.gitignore b/tools/testing/selftests/powerpc/mm/.gitignore
index d503b8764a8e..d021172fa2eb 100644
--- a/tools/testing/selftests/powerpc/mm/.gitignore
+++ b/tools/testing/selftests/powerpc/mm/.gitignore
@@ -4,4 +4,5 @@ tempfile
 prot_sao
 segv_errors
 wild_bctr
-large_vm_fork_separation
\ No newline at end of file
+large_vm_fork_separation
+tlbie_test
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c b/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c
index bdbbbe8431e0..3694613f418f 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c
@@ -44,7 +44,7 @@ struct shared_info {
 	unsigned long amr2;
 
 	/* AMR value that ptrace should refuse to write to the child. */
-	unsigned long amr3;
+	unsigned long invalid_amr;
 
 	/* IAMR value the parent expects to read from the child. */
 	unsigned long expected_iamr;
@@ -57,8 +57,8 @@ struct shared_info {
 	 * (even though they're valid ones) because userspace doesn't have
 	 * access to those registers.
 	 */
-	unsigned long new_iamr;
-	unsigned long new_uamor;
+	unsigned long invalid_iamr;
+	unsigned long invalid_uamor;
 };
 
 static int sys_pkey_alloc(unsigned long flags, unsigned long init_access_rights)
@@ -66,11 +66,6 @@ static int sys_pkey_alloc(unsigned long flags, unsigned long init_access_rights)
 	return syscall(__NR_pkey_alloc, flags, init_access_rights);
 }
 
-static int sys_pkey_free(int pkey)
-{
-	return syscall(__NR_pkey_free, pkey);
-}
-
 static int child(struct shared_info *info)
 {
 	unsigned long reg;
@@ -100,28 +95,32 @@ static int child(struct shared_info *info)
 
 	info->amr1 |= 3ul << pkeyshift(pkey1);
 	info->amr2 |= 3ul << pkeyshift(pkey2);
-	info->amr3 |= info->amr2 | 3ul << pkeyshift(pkey3);
+	/*
+	 * invalid amr value where we try to force write
+	 * things which are deined by a uamor setting.
+	 */
+	info->invalid_amr = info->amr2 | (~0x0UL & ~info->expected_uamor);
 
+	/*
+	 * if PKEY_DISABLE_EXECUTE succeeded we should update the expected_iamr
+	 */
 	if (disable_execute)
 		info->expected_iamr |= 1ul << pkeyshift(pkey1);
 	else
 		info->expected_iamr &= ~(1ul << pkeyshift(pkey1));
 
-	info->expected_iamr &= ~(1ul << pkeyshift(pkey2) | 1ul << pkeyshift(pkey3));
-
-	info->expected_uamor |= 3ul << pkeyshift(pkey1) |
-				3ul << pkeyshift(pkey2);
-	info->new_iamr |= 1ul << pkeyshift(pkey1) | 1ul << pkeyshift(pkey2);
-	info->new_uamor |= 3ul << pkeyshift(pkey1);
+	/*
+	 * We allocated pkey2 and pkey 3 above. Clear the IAMR bits.
+	 */
+	info->expected_iamr &= ~(1ul << pkeyshift(pkey2));
+	info->expected_iamr &= ~(1ul << pkeyshift(pkey3));
 
 	/*
-	 * We won't use pkey3. We just want a plausible but invalid key to test
-	 * whether ptrace will let us write to AMR bits we are not supposed to.
-	 *
-	 * This also tests whether the kernel restores the UAMOR permissions
-	 * after a key is freed.
+	 * Create an IAMR value different from expected value.
+	 * Kernel will reject an IAMR and UAMOR change.
 	 */
-	sys_pkey_free(pkey3);
+	info->invalid_iamr = info->expected_iamr | (1ul << pkeyshift(pkey1) | 1ul << pkeyshift(pkey2));
+	info->invalid_uamor = info->expected_uamor & ~(0x3ul << pkeyshift(pkey1));
 
 	printf("%-30s AMR: %016lx pkey1: %d pkey2: %d pkey3: %d\n",
 	       user_write, info->amr1, pkey1, pkey2, pkey3);
@@ -196,9 +195,9 @@ static int parent(struct shared_info *info, pid_t pid)
 	PARENT_SKIP_IF_UNSUPPORTED(ret, &info->child_sync);
 	PARENT_FAIL_IF(ret, &info->child_sync);
 
-	info->amr1 = info->amr2 = info->amr3 = regs[0];
-	info->expected_iamr = info->new_iamr = regs[1];
-	info->expected_uamor = info->new_uamor = regs[2];
+	info->amr1 = info->amr2 = regs[0];
+	info->expected_iamr = regs[1];
+	info->expected_uamor = regs[2];
 
 	/* Wake up child so that it can set itself up. */
 	ret = prod_child(&info->child_sync);
@@ -234,10 +233,10 @@ static int parent(struct shared_info *info, pid_t pid)
 		return ret;
 
 	/* Write invalid AMR value in child. */
-	ret = ptrace_write_regs(pid, NT_PPC_PKEY, &info->amr3, 1);
+	ret = ptrace_write_regs(pid, NT_PPC_PKEY, &info->invalid_amr, 1);
 	PARENT_FAIL_IF(ret, &info->child_sync);
 
-	printf("%-30s AMR: %016lx\n", ptrace_write_running, info->amr3);
+	printf("%-30s AMR: %016lx\n", ptrace_write_running, info->invalid_amr);
 
 	/* Wake up child so that it can verify it didn't change. */
 	ret = prod_child(&info->child_sync);
@@ -249,7 +248,7 @@ static int parent(struct shared_info *info, pid_t pid)
 
 	/* Try to write to IAMR. */
 	regs[0] = info->amr1;
-	regs[1] = info->new_iamr;
+	regs[1] = info->invalid_iamr;
 	ret = ptrace_write_regs(pid, NT_PPC_PKEY, regs, 2);
 	PARENT_FAIL_IF(!ret, &info->child_sync);
 
@@ -257,7 +256,7 @@ static int parent(struct shared_info *info, pid_t pid)
 	       ptrace_write_running, regs[0], regs[1]);
 
 	/* Try to write to IAMR and UAMOR. */
-	regs[2] = info->new_uamor;
+	regs[2] = info->invalid_uamor;
 	ret = ptrace_write_regs(pid, NT_PPC_PKEY, regs, 3);
 	PARENT_FAIL_IF(!ret, &info->child_sync);
 
diff --git a/tools/testing/selftests/powerpc/signal/Makefile b/tools/testing/selftests/powerpc/signal/Makefile
index 113838fbbe7f..153fafccd828 100644
--- a/tools/testing/selftests/powerpc/signal/Makefile
+++ b/tools/testing/selftests/powerpc/signal/Makefile
@@ -5,6 +5,8 @@ CFLAGS += -maltivec
 $(OUTPUT)/signal_tm: CFLAGS += -mhtm
 $(OUTPUT)/sigfuz: CFLAGS += -pthread -m64
 
+TEST_FILES := settings
+
 top_srcdir = ../../../../..
 include ../../lib.mk
 
diff --git a/tools/testing/selftests/powerpc/signal/settings b/tools/testing/selftests/powerpc/signal/settings
new file mode 100644
index 000000000000..e7b9417537fb
--- /dev/null
+++ b/tools/testing/selftests/powerpc/signal/settings
@@ -0,0 +1 @@
+timeout=0
diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile
index c0734ed0ef56..8704c5424ecc 100644
--- a/tools/testing/selftests/powerpc/tm/Makefile
+++ b/tools/testing/selftests/powerpc/tm/Makefile
@@ -7,6 +7,8 @@ TEST_GEN_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack
 	$(SIGNAL_CONTEXT_CHK_TESTS) tm-sigreturn tm-signal-sigreturn-nt \
 	tm-signal-context-force-tm
 
+TEST_FILES := settings
+
 top_srcdir = ../../../../..
 include ../../lib.mk
 
diff --git a/tools/testing/selftests/powerpc/tm/settings b/tools/testing/selftests/powerpc/tm/settings
new file mode 100644
index 000000000000..e7b9417537fb
--- /dev/null
+++ b/tools/testing/selftests/powerpc/tm/settings
@@ -0,0 +1 @@
+timeout=0
diff --git a/tools/testing/selftests/powerpc/utils.c b/tools/testing/selftests/powerpc/utils.c
index c02d24835db4..176102eca994 100644
--- a/tools/testing/selftests/powerpc/utils.c
+++ b/tools/testing/selftests/powerpc/utils.c
@@ -16,6 +16,7 @@
 #include <string.h>
 #include <sys/ioctl.h>
 #include <sys/stat.h>
+#include <sys/sysinfo.h>
 #include <sys/types.h>
 #include <sys/utsname.h>
 #include <unistd.h>
@@ -88,28 +89,40 @@ void *get_auxv_entry(int type)
 
 int pick_online_cpu(void)
 {
-	cpu_set_t mask;
-	int cpu;
+	int ncpus, cpu = -1;
+	cpu_set_t *mask;
+	size_t size;
+
+	ncpus = get_nprocs_conf();
+	size = CPU_ALLOC_SIZE(ncpus);
+	mask = CPU_ALLOC(ncpus);
+	if (!mask) {
+		perror("malloc");
+		return -1;
+	}
 
-	CPU_ZERO(&mask);
+	CPU_ZERO_S(size, mask);
 
-	if (sched_getaffinity(0, sizeof(mask), &mask)) {
+	if (sched_getaffinity(0, size, mask)) {
 		perror("sched_getaffinity");
-		return -1;
+		goto done;
 	}
 
 	/* We prefer a primary thread, but skip 0 */
-	for (cpu = 8; cpu < CPU_SETSIZE; cpu += 8)
-		if (CPU_ISSET(cpu, &mask))
-			return cpu;
+	for (cpu = 8; cpu < ncpus; cpu += 8)
+		if (CPU_ISSET_S(cpu, size, mask))
+			goto done;
 
 	/* Search for anything, but in reverse */
-	for (cpu = CPU_SETSIZE - 1; cpu >= 0; cpu--)
-		if (CPU_ISSET(cpu, &mask))
-			return cpu;
+	for (cpu = ncpus - 1; cpu >= 0; cpu--)
+		if (CPU_ISSET_S(cpu, size, mask))
+			goto done;
 
 	printf("No cpus in affinity mask?!\n");
-	return -1;
+
+done:
+	CPU_FREE(mask);
+	return cpu;
 }
 
 bool is_ppc64le(void)
diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile
index d6469535630a..2af9d39a9716 100644
--- a/tools/testing/selftests/rseq/Makefile
+++ b/tools/testing/selftests/rseq/Makefile
@@ -4,7 +4,7 @@ ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),)
 CLANG_FLAGS += -no-integrated-as
 endif
 
-CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L./ -Wl,-rpath=./ \
+CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L$(OUTPUT) -Wl,-rpath=./ \
 	  $(CLANG_FLAGS)
 LDLIBS += -lpthread
 
@@ -19,6 +19,8 @@ TEST_GEN_PROGS_EXTENDED = librseq.so
 
 TEST_PROGS = run_param_test.sh
 
+TEST_FILES := settings
+
 include ../lib.mk
 
 $(OUTPUT)/librseq.so: rseq.c rseq.h rseq-*.h
diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c
index eec2663261f2..e8a657a5f48a 100644
--- a/tools/testing/selftests/rseq/param_test.c
+++ b/tools/testing/selftests/rseq/param_test.c
@@ -15,7 +15,7 @@
 #include <errno.h>
 #include <stddef.h>
 
-static inline pid_t gettid(void)
+static inline pid_t rseq_gettid(void)
 {
 	return syscall(__NR_gettid);
 }
@@ -373,11 +373,12 @@ void *test_percpu_spinlock_thread(void *arg)
 		rseq_percpu_unlock(&data->lock, cpu);
 #ifndef BENCHMARK
 		if (i != 0 && !(i % (reps / 10)))
-			printf_verbose("tid %d: count %lld\n", (int) gettid(), i);
+			printf_verbose("tid %d: count %lld\n",
+				       (int) rseq_gettid(), i);
 #endif
 	}
 	printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n",
-		       (int) gettid(), nr_abort, signals_delivered);
+		       (int) rseq_gettid(), nr_abort, signals_delivered);
 	if (!opt_disable_rseq && thread_data->reg &&
 	    rseq_unregister_current_thread())
 		abort();
@@ -454,11 +455,12 @@ void *test_percpu_inc_thread(void *arg)
 		} while (rseq_unlikely(ret));
 #ifndef BENCHMARK
 		if (i != 0 && !(i % (reps / 10)))
-			printf_verbose("tid %d: count %lld\n", (int) gettid(), i);
+			printf_verbose("tid %d: count %lld\n",
+				       (int) rseq_gettid(), i);
 #endif
 	}
 	printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n",
-		       (int) gettid(), nr_abort, signals_delivered);
+		       (int) rseq_gettid(), nr_abort, signals_delivered);
 	if (!opt_disable_rseq && thread_data->reg &&
 	    rseq_unregister_current_thread())
 		abort();
@@ -605,7 +607,7 @@ void *test_percpu_list_thread(void *arg)
 	}
 
 	printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n",
-		       (int) gettid(), nr_abort, signals_delivered);
+		       (int) rseq_gettid(), nr_abort, signals_delivered);
 	if (!opt_disable_rseq && rseq_unregister_current_thread())
 		abort();
 
@@ -796,7 +798,7 @@ void *test_percpu_buffer_thread(void *arg)
 	}
 
 	printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n",
-		       (int) gettid(), nr_abort, signals_delivered);
+		       (int) rseq_gettid(), nr_abort, signals_delivered);
 	if (!opt_disable_rseq && rseq_unregister_current_thread())
 		abort();
 
@@ -1011,7 +1013,7 @@ void *test_percpu_memcpy_buffer_thread(void *arg)
 	}
 
 	printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n",
-		       (int) gettid(), nr_abort, signals_delivered);
+		       (int) rseq_gettid(), nr_abort, signals_delivered);
 	if (!opt_disable_rseq && rseq_unregister_current_thread())
 		abort();
 
diff --git a/tools/testing/selftests/rseq/settings b/tools/testing/selftests/rseq/settings
new file mode 100644
index 000000000000..e7b9417537fb
--- /dev/null
+++ b/tools/testing/selftests/rseq/settings
@@ -0,0 +1 @@
+timeout=0
diff --git a/tools/testing/selftests/rtc/Makefile b/tools/testing/selftests/rtc/Makefile
index de9c8566672a..90fa1a346908 100644
--- a/tools/testing/selftests/rtc/Makefile
+++ b/tools/testing/selftests/rtc/Makefile
@@ -6,4 +6,6 @@ TEST_GEN_PROGS = rtctest
 
 TEST_GEN_PROGS_EXTENDED = setdate
 
+TEST_FILES := settings
+
 include ../lib.mk
diff --git a/tools/testing/selftests/safesetid/Makefile b/tools/testing/selftests/safesetid/Makefile
index 98da7a504737..fa02c4d5ec13 100644
--- a/tools/testing/selftests/safesetid/Makefile
+++ b/tools/testing/selftests/safesetid/Makefile
@@ -1,8 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for mount selftests.
-CFLAGS = -Wall -lcap -O2
+CFLAGS = -Wall -O2
+LDLIBS = -lcap
 
-TEST_PROGS := run_tests.sh
+TEST_PROGS := safesetid-test.sh
 TEST_GEN_FILES := safesetid-test
 
 include ../lib.mk
diff --git a/tools/testing/selftests/safesetid/safesetid-test.c b/tools/testing/selftests/safesetid/safesetid-test.c
index 892c8e8b1b8b..1491a0df93fc 100644
--- a/tools/testing/selftests/safesetid/safesetid-test.c
+++ b/tools/testing/selftests/safesetid/safesetid-test.c
@@ -217,7 +217,8 @@ static void test_setuid(uid_t child_uid, bool expect_success)
 	}
 
 	if (cpid == 0) {	    /* Code executed by child */
-		setuid(child_uid);
+		if (setuid(child_uid) < 0)
+			exit(EXIT_FAILURE);
 		if (getuid() == child_uid)
 			exit(EXIT_SUCCESS);
 		else
@@ -295,8 +296,10 @@ int main(int argc, char **argv)
 
 	// First test to make sure we can write userns mappings from a user
 	// that doesn't have any restrictions (as long as it has CAP_SETUID);
-	setuid(NO_POLICY_USER);
-	setgid(NO_POLICY_USER);
+	if (setuid(NO_POLICY_USER) < 0)
+		die("Error with set uid(%d)\n", NO_POLICY_USER);
+	if (setgid(NO_POLICY_USER) < 0)
+		die("Error with set gid(%d)\n", NO_POLICY_USER);
 
 	// Take away all but setid caps
 	drop_caps(true);
@@ -310,8 +313,10 @@ int main(int argc, char **argv)
 		die("test_userns failed when it should work\n");
 	}
 
-	setuid(RESTRICTED_PARENT);
-	setgid(RESTRICTED_PARENT);
+	if (setuid(RESTRICTED_PARENT) < 0)
+		die("Error with set uid(%d)\n", RESTRICTED_PARENT);
+	if (setgid(RESTRICTED_PARENT) < 0)
+		die("Error with set gid(%d)\n", RESTRICTED_PARENT);
 
 	test_setuid(ROOT_USER, false);
 	test_setuid(ALLOWED_CHILD1, true);
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index f29d50097625..40629f92ea05 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -177,7 +177,7 @@ struct seccomp_metadata {
 #define SECCOMP_IOCTL_NOTIF_RECV	SECCOMP_IOWR(0, struct seccomp_notif)
 #define SECCOMP_IOCTL_NOTIF_SEND	SECCOMP_IOWR(1,	\
 						struct seccomp_notif_resp)
-#define SECCOMP_IOCTL_NOTIF_ID_VALID	SECCOMP_IOR(2, __u64)
+#define SECCOMP_IOCTL_NOTIF_ID_VALID	SECCOMP_IOW(2, __u64)
 
 struct seccomp_notif {
 	__u64 id;
@@ -3142,7 +3142,18 @@ TEST(user_notification_basic)
 	EXPECT_GT(poll(&pollfd, 1, -1), 0);
 	EXPECT_EQ(pollfd.revents, POLLIN);
 
-	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
+	/* Test that we can't pass garbage to the kernel. */
+	memset(&req, 0, sizeof(req));
+	req.pid = -1;
+	errno = 0;
+	ret = ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EINVAL, errno);
+
+	if (ret) {
+		req.pid = 0;
+		EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
+	}
 
 	pollfd.fd = listener;
 	pollfd.events = POLLIN | POLLOUT;
@@ -3262,6 +3273,7 @@ TEST(user_notification_signal)
 
 	close(sk_pair[1]);
 
+	memset(&req, 0, sizeof(req));
 	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
 
 	EXPECT_EQ(kill(pid, SIGUSR1), 0);
@@ -3280,6 +3292,7 @@ TEST(user_notification_signal)
 	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), -1);
 	EXPECT_EQ(errno, ENOENT);
 
+	memset(&req, 0, sizeof(req));
 	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
 
 	resp.id = req.id;
diff --git a/tools/testing/selftests/size/get_size.c b/tools/testing/selftests/size/get_size.c
index 2ad45b944355..2980b1a63366 100644
--- a/tools/testing/selftests/size/get_size.c
+++ b/tools/testing/selftests/size/get_size.c
@@ -11,23 +11,35 @@
  * own execution.  It also attempts to have as few dependencies
  * on kernel features as possible.
  *
- * It should be statically linked, with startup libs avoided.
- * It uses no library calls, and only the following 3 syscalls:
+ * It should be statically linked, with startup libs avoided.  It uses
+ * no library calls except the syscall() function for the following 3
+ * syscalls:
  *   sysinfo(), write(), and _exit()
  *
  * For output, it avoids printf (which in some C libraries
  * has large external dependencies) by  implementing it's own
  * number output and print routines, and using __builtin_strlen()
+ *
+ * The test may crash if any of the above syscalls fails because in some
+ * libc implementations (e.g. the GNU C Library) errno is saved in
+ * thread-local storage, which does not get initialized due to avoiding
+ * startup libs.
  */
 
 #include <sys/sysinfo.h>
 #include <unistd.h>
+#include <sys/syscall.h>
 
 #define STDOUT_FILENO 1
 
 static int print(const char *s)
 {
-	return write(STDOUT_FILENO, s, __builtin_strlen(s));
+	size_t len = 0;
+
+	while (s[len] != '\0')
+		len++;
+
+	return syscall(SYS_write, STDOUT_FILENO, s, len);
 }
 
 static inline char *num_to_str(unsigned long num, char *buf, int len)
@@ -79,12 +91,12 @@ void _start(void)
 	print("TAP version 13\n");
 	print("# Testing system size.\n");
 
-	ccode = sysinfo(&info);
+	ccode = syscall(SYS_sysinfo, &info);
 	if (ccode < 0) {
 		print("not ok 1");
 		print(test_name);
 		print(" ---\n reason: \"could not get sysinfo\"\n ...\n");
-		_exit(ccode);
+		syscall(SYS_exit, ccode);
 	}
 	print("ok 1");
 	print(test_name);
@@ -100,5 +112,5 @@ void _start(void)
 	print(" ...\n");
 	print("1..1\n");
 
-	_exit(0);
+	syscall(SYS_exit, 0);
 }
diff --git a/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py
index 9f0ba10c44b4..6c03a6bbcc2f 100644
--- a/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py
+++ b/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py
@@ -53,7 +53,7 @@ class SubPlugin(TdcPlugin):
             shell=True,
             stdout=subprocess.PIPE,
             stderr=subprocess.PIPE,
-            env=ENVIR)
+            env=os.environ.copy())
         (rawout, serr) = proc.communicate()
 
         if proc.returncode != 0 and len(serr) > 0:
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
index e2f92cefb8d5..0bccd1b188e6 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
@@ -39,6 +39,25 @@
         ]
     },
     {
+        "id": "2ff3",
+        "name": "Add flower with max handle and then dump it",
+        "category": [
+            "filter",
+            "flower"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV2 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress handle 0xffffffff flower action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter show dev $DEV2 ingress",
+        "matchPattern": "filter protocol ip pref 1 flower.*handle 0xffffffff",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV2 ingress"
+        ]
+    },
+    {
         "id": "d052",
         "name": "Add 1M filters with the same action",
         "category": [
@@ -68,9 +87,9 @@
         ],
         "setup": [
             "$TC qdisc add dev $DEV2 ingress",
-            "$TC filter add dev $DEV2 protocol ip prio 1 parent ffff: flower dst_mac e4:11:22:11:4a:51 src_mac e4:11:22:11:4a:50 ip_proto tcp src_ip 1.1.1.1 dst_ip 2.2.2.2 action drop"
+            "$TC filter add dev $DEV2 protocol ip prio 1 ingress flower dst_mac e4:11:22:11:4a:51 src_mac e4:11:22:11:4a:50 ip_proto tcp src_ip 1.1.1.1 dst_ip 2.2.2.2 action drop"
         ],
-        "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip prio 1 parent ffff: flower dst_mac e4:11:22:11:4a:51 src_mac e4:11:22:11:4a:50 ip_proto tcp src_ip 1.1.1.1 dst_ip 2.2.2.2 action drop",
+        "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip prio 1 ingress flower dst_mac e4:11:22:11:4a:51 src_mac e4:11:22:11:4a:50 ip_proto tcp src_ip 1.1.1.1 dst_ip 2.2.2.2 action drop",
         "expExitCode": "2",
         "verifyCmd": "$TC -s filter show dev $DEV2 ingress",
         "matchPattern": "filter protocol ip pref 1 flower chain 0 handle",
diff --git a/tools/testing/selftests/tc-testing/tdc_batch.py b/tools/testing/selftests/tc-testing/tdc_batch.py
index 6a2bd2cf528e..995f66ce43eb 100755
--- a/tools/testing/selftests/tc-testing/tdc_batch.py
+++ b/tools/testing/selftests/tc-testing/tdc_batch.py
@@ -72,21 +72,21 @@ mac_prefix = args.mac_prefix
 
 def format_add_filter(device, prio, handle, skip, src_mac, dst_mac,
                       share_action):
-    return ("filter add dev {} {} protocol ip parent ffff: handle {} "
+    return ("filter add dev {} {} protocol ip ingress handle {} "
             " flower {} src_mac {} dst_mac {} action drop {}".format(
                 device, prio, handle, skip, src_mac, dst_mac, share_action))
 
 
 def format_rep_filter(device, prio, handle, skip, src_mac, dst_mac,
                       share_action):
-    return ("filter replace dev {} {} protocol ip parent ffff: handle {} "
+    return ("filter replace dev {} {} protocol ip ingress handle {} "
             " flower {} src_mac {} dst_mac {} action drop {}".format(
                 device, prio, handle, skip, src_mac, dst_mac, share_action))
 
 
 def format_del_filter(device, prio, handle, skip, src_mac, dst_mac,
                       share_action):
-    return ("filter del dev {} {} protocol ip parent ffff: handle {} "
+    return ("filter del dev {} {} protocol ip ingress handle {} "
             "flower".format(device, prio, handle))
 
 
diff --git a/tools/testing/selftests/timers/Makefile b/tools/testing/selftests/timers/Makefile
index 7656c7ce79d9..0e73a16874c4 100644
--- a/tools/testing/selftests/timers/Makefile
+++ b/tools/testing/selftests/timers/Makefile
@@ -13,6 +13,7 @@ DESTRUCTIVE_TESTS = alarmtimer-suspend valid-adjtimex adjtick change_skew \
 
 TEST_GEN_PROGS_EXTENDED = $(DESTRUCTIVE_TESTS)
 
+TEST_FILES := settings
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/timers/settings b/tools/testing/selftests/timers/settings
new file mode 100644
index 000000000000..e7b9417537fb
--- /dev/null
+++ b/tools/testing/selftests/timers/settings
@@ -0,0 +1 @@
+timeout=0
diff --git a/tools/testing/selftests/tpm2/test_smoke.sh b/tools/testing/selftests/tpm2/test_smoke.sh
index 80521d46220c..31fb8265f643 100755
--- a/tools/testing/selftests/tpm2/test_smoke.sh
+++ b/tools/testing/selftests/tpm2/test_smoke.sh
@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/bin/sh
 # SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
 
 python -m unittest -v tpm2_tests.SmokeTest
diff --git a/tools/testing/selftests/tpm2/test_space.sh b/tools/testing/selftests/tpm2/test_space.sh
index a6f5e346635e..3ded3011b642 100755
--- a/tools/testing/selftests/tpm2/test_space.sh
+++ b/tools/testing/selftests/tpm2/test_space.sh
@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/bin/sh
 # SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
 
 python -m unittest -v tpm2_tests.SpaceTest
diff --git a/tools/testing/selftests/vm/map_hugetlb.c b/tools/testing/selftests/vm/map_hugetlb.c
index 5a2d7b8efc40..6af951900aa3 100644
--- a/tools/testing/selftests/vm/map_hugetlb.c
+++ b/tools/testing/selftests/vm/map_hugetlb.c
@@ -45,20 +45,20 @@ static void check_bytes(char *addr)
 	printf("First hex is %x\n", *((unsigned int *)addr));
 }
 
-static void write_bytes(char *addr)
+static void write_bytes(char *addr, size_t length)
 {
 	unsigned long i;
 
-	for (i = 0; i < LENGTH; i++)
+	for (i = 0; i < length; i++)
 		*(addr + i) = (char)i;
 }
 
-static int read_bytes(char *addr)
+static int read_bytes(char *addr, size_t length)
 {
 	unsigned long i;
 
 	check_bytes(addr);
-	for (i = 0; i < LENGTH; i++)
+	for (i = 0; i < length; i++)
 		if (*(addr + i) != (char)i) {
 			printf("Mismatch at %lu\n", i);
 			return 1;
@@ -96,11 +96,11 @@ int main(int argc, char **argv)
 
 	printf("Returned address is %p\n", addr);
 	check_bytes(addr);
-	write_bytes(addr);
-	ret = read_bytes(addr);
+	write_bytes(addr, length);
+	ret = read_bytes(addr, length);
 
 	/* munmap() length of MAP_HUGETLB memory must be hugepage aligned */
-	if (munmap(addr, LENGTH)) {
+	if (munmap(addr, length)) {
 		perror("munmap");
 		exit(1);
 	}
diff --git a/tools/testing/selftests/vm/mlock2-tests.c b/tools/testing/selftests/vm/mlock2-tests.c
index 637b6d0ac0d0..11b2301f3aa3 100644
--- a/tools/testing/selftests/vm/mlock2-tests.c
+++ b/tools/testing/selftests/vm/mlock2-tests.c
@@ -67,59 +67,6 @@ out:
 	return ret;
 }
 
-static uint64_t get_pageflags(unsigned long addr)
-{
-	FILE *file;
-	uint64_t pfn;
-	unsigned long offset;
-
-	file = fopen("/proc/self/pagemap", "r");
-	if (!file) {
-		perror("fopen pagemap");
-		_exit(1);
-	}
-
-	offset = addr / getpagesize() * sizeof(pfn);
-
-	if (fseek(file, offset, SEEK_SET)) {
-		perror("fseek pagemap");
-		_exit(1);
-	}
-
-	if (fread(&pfn, sizeof(pfn), 1, file) != 1) {
-		perror("fread pagemap");
-		_exit(1);
-	}
-
-	fclose(file);
-	return pfn;
-}
-
-static uint64_t get_kpageflags(unsigned long pfn)
-{
-	uint64_t flags;
-	FILE *file;
-
-	file = fopen("/proc/kpageflags", "r");
-	if (!file) {
-		perror("fopen kpageflags");
-		_exit(1);
-	}
-
-	if (fseek(file, pfn * sizeof(flags), SEEK_SET)) {
-		perror("fseek kpageflags");
-		_exit(1);
-	}
-
-	if (fread(&flags, sizeof(flags), 1, file) != 1) {
-		perror("fread kpageflags");
-		_exit(1);
-	}
-
-	fclose(file);
-	return flags;
-}
-
 #define VMFLAGS "VmFlags:"
 
 static bool is_vmflag_set(unsigned long addr, const char *vmflag)
@@ -159,19 +106,13 @@ out:
 #define RSS  "Rss:"
 #define LOCKED "lo"
 
-static bool is_vma_lock_on_fault(unsigned long addr)
+static unsigned long get_value_for_name(unsigned long addr, const char *name)
 {
-	bool ret = false;
-	bool locked;
-	FILE *smaps = NULL;
-	unsigned long vma_size, vma_rss;
 	char *line = NULL;
-	char *value;
 	size_t size = 0;
-
-	locked = is_vmflag_set(addr, LOCKED);
-	if (!locked)
-		goto out;
+	char *value_ptr;
+	FILE *smaps = NULL;
+	unsigned long value = -1UL;
 
 	smaps = seek_to_smaps_entry(addr);
 	if (!smaps) {
@@ -180,112 +121,70 @@ static bool is_vma_lock_on_fault(unsigned long addr)
 	}
 
 	while (getline(&line, &size, smaps) > 0) {
-		if (!strstr(line, SIZE)) {
+		if (!strstr(line, name)) {
 			free(line);
 			line = NULL;
 			size = 0;
 			continue;
 		}
 
-		value = line + strlen(SIZE);
-		if (sscanf(value, "%lu kB", &vma_size) < 1) {
+		value_ptr = line + strlen(name);
+		if (sscanf(value_ptr, "%lu kB", &value) < 1) {
 			printf("Unable to parse smaps entry for Size\n");
 			goto out;
 		}
 		break;
 	}
 
-	while (getline(&line, &size, smaps) > 0) {
-		if (!strstr(line, RSS)) {
-			free(line);
-			line = NULL;
-			size = 0;
-			continue;
-		}
-
-		value = line + strlen(RSS);
-		if (sscanf(value, "%lu kB", &vma_rss) < 1) {
-			printf("Unable to parse smaps entry for Rss\n");
-			goto out;
-		}
-		break;
-	}
-
-	ret = locked && (vma_rss < vma_size);
 out:
-	free(line);
 	if (smaps)
 		fclose(smaps);
-	return ret;
+	free(line);
+	return value;
 }
 
-#define PRESENT_BIT     0x8000000000000000ULL
-#define PFN_MASK        0x007FFFFFFFFFFFFFULL
-#define UNEVICTABLE_BIT (1UL << 18)
-
-static int lock_check(char *map)
+static bool is_vma_lock_on_fault(unsigned long addr)
 {
-	unsigned long page_size = getpagesize();
-	uint64_t page1_flags, page2_flags;
+	bool locked;
+	unsigned long vma_size, vma_rss;
 
-	page1_flags = get_pageflags((unsigned long)map);
-	page2_flags = get_pageflags((unsigned long)map + page_size);
+	locked = is_vmflag_set(addr, LOCKED);
+	if (!locked)
+		return false;
 
-	/* Both pages should be present */
-	if (((page1_flags & PRESENT_BIT) == 0) ||
-	    ((page2_flags & PRESENT_BIT) == 0)) {
-		printf("Failed to make both pages present\n");
-		return 1;
-	}
+	vma_size = get_value_for_name(addr, SIZE);
+	vma_rss = get_value_for_name(addr, RSS);
 
-	page1_flags = get_kpageflags(page1_flags & PFN_MASK);
-	page2_flags = get_kpageflags(page2_flags & PFN_MASK);
+	/* only one page is faulted in */
+	return (vma_rss < vma_size);
+}
 
-	/* Both pages should be unevictable */
-	if (((page1_flags & UNEVICTABLE_BIT) == 0) ||
-	    ((page2_flags & UNEVICTABLE_BIT) == 0)) {
-		printf("Failed to make both pages unevictable\n");
-		return 1;
-	}
+#define PRESENT_BIT     0x8000000000000000ULL
+#define PFN_MASK        0x007FFFFFFFFFFFFFULL
+#define UNEVICTABLE_BIT (1UL << 18)
 
-	if (!is_vmflag_set((unsigned long)map, LOCKED)) {
-		printf("VMA flag %s is missing on page 1\n", LOCKED);
-		return 1;
-	}
+static int lock_check(unsigned long addr)
+{
+	bool locked;
+	unsigned long vma_size, vma_rss;
 
-	if (!is_vmflag_set((unsigned long)map + page_size, LOCKED)) {
-		printf("VMA flag %s is missing on page 2\n", LOCKED);
-		return 1;
-	}
+	locked = is_vmflag_set(addr, LOCKED);
+	if (!locked)
+		return false;
 
-	return 0;
+	vma_size = get_value_for_name(addr, SIZE);
+	vma_rss = get_value_for_name(addr, RSS);
+
+	return (vma_rss == vma_size);
 }
 
 static int unlock_lock_check(char *map)
 {
-	unsigned long page_size = getpagesize();
-	uint64_t page1_flags, page2_flags;
-
-	page1_flags = get_pageflags((unsigned long)map);
-	page2_flags = get_pageflags((unsigned long)map + page_size);
-	page1_flags = get_kpageflags(page1_flags & PFN_MASK);
-	page2_flags = get_kpageflags(page2_flags & PFN_MASK);
-
-	if ((page1_flags & UNEVICTABLE_BIT) || (page2_flags & UNEVICTABLE_BIT)) {
-		printf("A page is still marked unevictable after unlock\n");
-		return 1;
-	}
-
 	if (is_vmflag_set((unsigned long)map, LOCKED)) {
 		printf("VMA flag %s is present on page 1 after unlock\n", LOCKED);
 		return 1;
 	}
 
-	if (is_vmflag_set((unsigned long)map + page_size, LOCKED)) {
-		printf("VMA flag %s is present on page 2 after unlock\n", LOCKED);
-		return 1;
-	}
-
 	return 0;
 }
 
@@ -311,7 +210,7 @@ static int test_mlock_lock()
 		goto unmap;
 	}
 
-	if (lock_check(map))
+	if (!lock_check((unsigned long)map))
 		goto unmap;
 
 	/* Now unlock and recheck attributes */
@@ -330,64 +229,18 @@ out:
 
 static int onfault_check(char *map)
 {
-	unsigned long page_size = getpagesize();
-	uint64_t page1_flags, page2_flags;
-
-	page1_flags = get_pageflags((unsigned long)map);
-	page2_flags = get_pageflags((unsigned long)map + page_size);
-
-	/* Neither page should be present */
-	if ((page1_flags & PRESENT_BIT) || (page2_flags & PRESENT_BIT)) {
-		printf("Pages were made present by MLOCK_ONFAULT\n");
-		return 1;
-	}
-
 	*map = 'a';
-	page1_flags = get_pageflags((unsigned long)map);
-	page2_flags = get_pageflags((unsigned long)map + page_size);
-
-	/* Only page 1 should be present */
-	if ((page1_flags & PRESENT_BIT) == 0) {
-		printf("Page 1 is not present after fault\n");
-		return 1;
-	} else if (page2_flags & PRESENT_BIT) {
-		printf("Page 2 was made present\n");
-		return 1;
-	}
-
-	page1_flags = get_kpageflags(page1_flags & PFN_MASK);
-
-	/* Page 1 should be unevictable */
-	if ((page1_flags & UNEVICTABLE_BIT) == 0) {
-		printf("Failed to make faulted page unevictable\n");
-		return 1;
-	}
-
 	if (!is_vma_lock_on_fault((unsigned long)map)) {
 		printf("VMA is not marked for lock on fault\n");
 		return 1;
 	}
 
-	if (!is_vma_lock_on_fault((unsigned long)map + page_size)) {
-		printf("VMA is not marked for lock on fault\n");
-		return 1;
-	}
-
 	return 0;
 }
 
 static int unlock_onfault_check(char *map)
 {
 	unsigned long page_size = getpagesize();
-	uint64_t page1_flags;
-
-	page1_flags = get_pageflags((unsigned long)map);
-	page1_flags = get_kpageflags(page1_flags & PFN_MASK);
-
-	if (page1_flags & UNEVICTABLE_BIT) {
-		printf("Page 1 is still marked unevictable after unlock\n");
-		return 1;
-	}
 
 	if (is_vma_lock_on_fault((unsigned long)map) ||
 	    is_vma_lock_on_fault((unsigned long)map + page_size)) {
@@ -445,7 +298,6 @@ static int test_lock_onfault_of_present()
 	char *map;
 	int ret = 1;
 	unsigned long page_size = getpagesize();
-	uint64_t page1_flags, page2_flags;
 
 	map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
 		   MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
@@ -465,17 +317,6 @@ static int test_lock_onfault_of_present()
 		goto unmap;
 	}
 
-	page1_flags = get_pageflags((unsigned long)map);
-	page2_flags = get_pageflags((unsigned long)map + page_size);
-	page1_flags = get_kpageflags(page1_flags & PFN_MASK);
-	page2_flags = get_kpageflags(page2_flags & PFN_MASK);
-
-	/* Page 1 should be unevictable */
-	if ((page1_flags & UNEVICTABLE_BIT) == 0) {
-		printf("Failed to make present page unevictable\n");
-		goto unmap;
-	}
-
 	if (!is_vma_lock_on_fault((unsigned long)map) ||
 	    !is_vma_lock_on_fault((unsigned long)map + page_size)) {
 		printf("VMA with present pages is not marked lock on fault\n");
@@ -507,7 +348,7 @@ static int test_munlockall()
 		goto out;
 	}
 
-	if (lock_check(map))
+	if (!lock_check((unsigned long)map))
 		goto unmap;
 
 	if (munlockall()) {
@@ -549,7 +390,7 @@ static int test_munlockall()
 		goto out;
 	}
 
-	if (lock_check(map))
+	if (!lock_check((unsigned long)map))
 		goto unmap;
 
 	if (munlockall()) {
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index 186520198de7..2f9a691ed970 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -16,7 +16,7 @@ TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap
 TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \
 			test_FCMOV test_FCOMI test_FISTTP \
 			vdso_restorer
-TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip
+TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip syscall_numbering
 # Some selftests require 32bit support enabled also on 64bit systems
 TARGETS_C_32BIT_NEEDED := ldt_gdt ptrace_syscall
 
diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/x86/protection_keys.c
index 5d546dcdbc80..b8778960da10 100644
--- a/tools/testing/selftests/x86/protection_keys.c
+++ b/tools/testing/selftests/x86/protection_keys.c
@@ -24,6 +24,7 @@
 #define _GNU_SOURCE
 #include <errno.h>
 #include <linux/futex.h>
+#include <time.h>
 #include <sys/time.h>
 #include <sys/syscall.h>
 #include <string.h>
@@ -612,10 +613,10 @@ int alloc_random_pkey(void)
 	int nr_alloced = 0;
 	int random_index;
 	memset(alloced_pkeys, 0, sizeof(alloced_pkeys));
+	srand((unsigned int)time(NULL));
 
 	/* allocate every possible key and make a note of which ones we got */
 	max_nr_pkey_allocs = NR_PKEYS;
-	max_nr_pkey_allocs = 1;
 	for (i = 0; i < max_nr_pkey_allocs; i++) {
 		int new_pkey = alloc_pkey();
 		if (new_pkey < 0)
diff --git a/tools/testing/selftests/x86/ptrace_syscall.c b/tools/testing/selftests/x86/ptrace_syscall.c
index 6f22238f3217..12aaa063196e 100644
--- a/tools/testing/selftests/x86/ptrace_syscall.c
+++ b/tools/testing/selftests/x86/ptrace_syscall.c
@@ -414,8 +414,12 @@ int main()
 
 #if defined(__i386__) && (!defined(__GLIBC__) || __GLIBC__ > 2 || __GLIBC_MINOR__ >= 16)
 	vsyscall32 = (void *)getauxval(AT_SYSINFO);
-	printf("[RUN]\tCheck AT_SYSINFO return regs\n");
-	test_sys32_regs(do_full_vsyscall32);
+	if (vsyscall32) {
+		printf("[RUN]\tCheck AT_SYSINFO return regs\n");
+		test_sys32_regs(do_full_vsyscall32);
+	} else {
+		printf("[SKIP]\tAT_SYSINFO is not available\n");
+	}
 #endif
 
 	test_ptrace_syscall_restart();
diff --git a/tools/testing/selftests/x86/syscall_numbering.c b/tools/testing/selftests/x86/syscall_numbering.c
new file mode 100644
index 000000000000..d6b09cb1aa2c
--- /dev/null
+++ b/tools/testing/selftests/x86/syscall_numbering.c
@@ -0,0 +1,89 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * syscall_arg_fault.c - tests faults 32-bit fast syscall stack args
+ * Copyright (c) 2018 Andrew Lutomirski
+ */
+
+#define _GNU_SOURCE
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <stdbool.h>
+#include <errno.h>
+#include <unistd.h>
+#include <syscall.h>
+
+static int nerrs;
+
+#define X32_BIT 0x40000000UL
+
+static void check_enosys(unsigned long nr, bool *ok)
+{
+	/* If this fails, a segfault is reasonably likely. */
+	fflush(stdout);
+
+	long ret = syscall(nr, 0, 0, 0, 0, 0, 0);
+	if (ret == 0) {
+		printf("[FAIL]\tsyscall %lu succeeded, but it should have failed\n", nr);
+		*ok = false;
+	} else if (errno != ENOSYS) {
+		printf("[FAIL]\tsyscall %lu had error code %d, but it should have reported ENOSYS\n", nr, errno);
+		*ok = false;
+	}
+}
+
+static void test_x32_without_x32_bit(void)
+{
+	bool ok = true;
+
+	/*
+	 * Syscalls 512-547 are "x32" syscalls.  They are intended to be
+	 * called with the x32 (0x40000000) bit set.  Calling them without
+	 * the x32 bit set is nonsense and should not work.
+	 */
+	printf("[RUN]\tChecking syscalls 512-547\n");
+	for (int i = 512; i <= 547; i++)
+		check_enosys(i, &ok);
+
+	/*
+	 * Check that a handful of 64-bit-only syscalls are rejected if the x32
+	 * bit is set.
+	 */
+	printf("[RUN]\tChecking some 64-bit syscalls in x32 range\n");
+	check_enosys(16 | X32_BIT, &ok);	/* ioctl */
+	check_enosys(19 | X32_BIT, &ok);	/* readv */
+	check_enosys(20 | X32_BIT, &ok);	/* writev */
+
+	/*
+	 * Check some syscalls with high bits set.
+	 */
+	printf("[RUN]\tChecking numbers above 2^32-1\n");
+	check_enosys((1UL << 32), &ok);
+	check_enosys(X32_BIT | (1UL << 32), &ok);
+
+	if (!ok)
+		nerrs++;
+	else
+		printf("[OK]\tThey all returned -ENOSYS\n");
+}
+
+int main()
+{
+	/*
+	 * Anyone diagnosing a failure will want to know whether the kernel
+	 * supports x32.  Tell them.
+	 */
+	printf("\tChecking for x32...");
+	fflush(stdout);
+	if (syscall(39 | X32_BIT, 0, 0, 0, 0, 0, 0) >= 0) {
+		printf(" supported\n");
+	} else if (errno == ENOSYS) {
+		printf(" not supported\n");
+	} else {
+		printf(" confused\n");
+	}
+
+	test_x32_without_x32_bit();
+
+	return nerrs ? 1 : 0;
+}
diff --git a/tools/usb/usbip/src/usbip_network.c b/tools/usb/usbip/src/usbip_network.c
index d595d72693fb..ed4dc8c14269 100644
--- a/tools/usb/usbip/src/usbip_network.c
+++ b/tools/usb/usbip/src/usbip_network.c
@@ -50,39 +50,39 @@ void usbip_setup_port_number(char *arg)
 	info("using port %d (\"%s\")", usbip_port, usbip_port_string);
 }
 
-void usbip_net_pack_uint32_t(int pack, uint32_t *num)
+uint32_t usbip_net_pack_uint32_t(int pack, uint32_t num)
 {
 	uint32_t i;
 
 	if (pack)
-		i = htonl(*num);
+		i = htonl(num);
 	else
-		i = ntohl(*num);
+		i = ntohl(num);
 
-	*num = i;
+	return i;
 }
 
-void usbip_net_pack_uint16_t(int pack, uint16_t *num)
+uint16_t usbip_net_pack_uint16_t(int pack, uint16_t num)
 {
 	uint16_t i;
 
 	if (pack)
-		i = htons(*num);
+		i = htons(num);
 	else
-		i = ntohs(*num);
+		i = ntohs(num);
 
-	*num = i;
+	return i;
 }
 
 void usbip_net_pack_usb_device(int pack, struct usbip_usb_device *udev)
 {
-	usbip_net_pack_uint32_t(pack, &udev->busnum);
-	usbip_net_pack_uint32_t(pack, &udev->devnum);
-	usbip_net_pack_uint32_t(pack, &udev->speed);
+	udev->busnum = usbip_net_pack_uint32_t(pack, udev->busnum);
+	udev->devnum = usbip_net_pack_uint32_t(pack, udev->devnum);
+	udev->speed = usbip_net_pack_uint32_t(pack, udev->speed);
 
-	usbip_net_pack_uint16_t(pack, &udev->idVendor);
-	usbip_net_pack_uint16_t(pack, &udev->idProduct);
-	usbip_net_pack_uint16_t(pack, &udev->bcdDevice);
+	udev->idVendor = usbip_net_pack_uint16_t(pack, udev->idVendor);
+	udev->idProduct = usbip_net_pack_uint16_t(pack, udev->idProduct);
+	udev->bcdDevice = usbip_net_pack_uint16_t(pack, udev->bcdDevice);
 }
 
 void usbip_net_pack_usb_interface(int pack __attribute__((unused)),
@@ -129,6 +129,14 @@ ssize_t usbip_net_send(int sockfd, void *buff, size_t bufflen)
 	return usbip_net_xmit(sockfd, buff, bufflen, 1);
 }
 
+static inline void usbip_net_pack_op_common(int pack,
+					    struct op_common *op_common)
+{
+	op_common->version = usbip_net_pack_uint16_t(pack, op_common->version);
+	op_common->code = usbip_net_pack_uint16_t(pack, op_common->code);
+	op_common->status = usbip_net_pack_uint32_t(pack, op_common->status);
+}
+
 int usbip_net_send_op_common(int sockfd, uint32_t code, uint32_t status)
 {
 	struct op_common op_common;
@@ -140,7 +148,7 @@ int usbip_net_send_op_common(int sockfd, uint32_t code, uint32_t status)
 	op_common.code    = code;
 	op_common.status  = status;
 
-	PACK_OP_COMMON(1, &op_common);
+	usbip_net_pack_op_common(1, &op_common);
 
 	rc = usbip_net_send(sockfd, &op_common, sizeof(op_common));
 	if (rc < 0) {
@@ -164,7 +172,7 @@ int usbip_net_recv_op_common(int sockfd, uint16_t *code, int *status)
 		goto err;
 	}
 
-	PACK_OP_COMMON(0, &op_common);
+	usbip_net_pack_op_common(0, &op_common);
 
 	if (op_common.version != USBIP_VERSION) {
 		err("USBIP Kernel and tool version mismatch: %d %d:",
diff --git a/tools/usb/usbip/src/usbip_network.h b/tools/usb/usbip/src/usbip_network.h
index 555215eae43e..83b4c5344f72 100644
--- a/tools/usb/usbip/src/usbip_network.h
+++ b/tools/usb/usbip/src/usbip_network.h
@@ -32,12 +32,6 @@ struct op_common {
 
 } __attribute__((packed));
 
-#define PACK_OP_COMMON(pack, op_common)  do {\
-	usbip_net_pack_uint16_t(pack, &(op_common)->version);\
-	usbip_net_pack_uint16_t(pack, &(op_common)->code);\
-	usbip_net_pack_uint32_t(pack, &(op_common)->status);\
-} while (0)
-
 /* ---------------------------------------------------------------------- */
 /* Dummy Code */
 #define OP_UNSPEC	0x00
@@ -163,11 +157,11 @@ struct op_devlist_reply_extra {
 } while (0)
 
 #define PACK_OP_DEVLIST_REPLY(pack, reply)  do {\
-	usbip_net_pack_uint32_t(pack, &(reply)->ndev);\
+	(reply)->ndev = usbip_net_pack_uint32_t(pack, (reply)->ndev);\
 } while (0)
 
-void usbip_net_pack_uint32_t(int pack, uint32_t *num);
-void usbip_net_pack_uint16_t(int pack, uint16_t *num);
+uint32_t usbip_net_pack_uint32_t(int pack, uint32_t num);
+uint16_t usbip_net_pack_uint16_t(int pack, uint16_t num);
 void usbip_net_pack_usb_device(int pack, struct usbip_usb_device *udev);
 void usbip_net_pack_usb_interface(int pack, struct usbip_usb_interface *uinf);
 
diff --git a/tools/vm/Makefile b/tools/vm/Makefile
index 20f6cf04377f..9860622cbb15 100644
--- a/tools/vm/Makefile
+++ b/tools/vm/Makefile
@@ -1,6 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for vm tools
 #
+include ../scripts/Makefile.include
+
 TARGETS=page-types slabinfo page_owner_sort
 
 LIB_DIR = ../lib/api
diff --git a/usr/Kconfig b/usr/Kconfig
index 43658b8a975e..8b4826de1189 100644
--- a/usr/Kconfig
+++ b/usr/Kconfig
@@ -131,17 +131,6 @@ choice
 
 	  If in doubt, select 'None'
 
-config INITRAMFS_COMPRESSION_NONE
-	bool "None"
-	help
-	  Do not compress the built-in initramfs at all. This may sound wasteful
-	  in space, but, you should be aware that the built-in initramfs will be
-	  compressed at a later stage anyways along with the rest of the kernel,
-	  on those architectures that support this. However, not compressing the
-	  initramfs may lead to slightly higher memory consumption during a
-	  short time at boot, while both the cpio image and the unpacked
-	  filesystem image will be present in memory simultaneously
-
 config INITRAMFS_COMPRESSION_GZIP
 	bool "Gzip"
 	depends on RD_GZIP
@@ -214,6 +203,17 @@ config INITRAMFS_COMPRESSION_LZ4
 	  If you choose this, keep in mind that most distros don't provide lz4
 	  by default which could cause a build failure.
 
+config INITRAMFS_COMPRESSION_NONE
+	bool "None"
+	help
+	  Do not compress the built-in initramfs at all. This may sound wasteful
+	  in space, but, you should be aware that the built-in initramfs will be
+	  compressed at a later stage anyways along with the rest of the kernel,
+	  on those architectures that support this. However, not compressing the
+	  initramfs may lead to slightly higher memory consumption during a
+	  short time at boot, while both the cpio image and the unpacked
+	  filesystem image will be present in memory simultaneously
+
 endchoice
 
 config INITRAMFS_COMPRESSION
diff --git a/usr/gen_initramfs_list.sh b/usr/gen_initramfs_list.sh
index 0aad760fcd8c..2bbac73e6477 100755
--- a/usr/gen_initramfs_list.sh
+++ b/usr/gen_initramfs_list.sh
@@ -128,7 +128,7 @@ parse() {
 			str="${ftype} ${name} ${location} ${str}"
 			;;
 		"nod")
-			local dev=`LC_ALL=C ls -l "${location}"`
+			local dev="`LC_ALL=C ls -l "${location}"`"
 			local maj=`field 5 ${dev}`
 			local min=`field 6 ${dev}`
 			maj=${maj%,}
diff --git a/virt/kvm/arm/aarch32.c b/virt/kvm/arm/aarch32.c
index c4c57ba99e90..40a62a99fbf8 100644
--- a/virt/kvm/arm/aarch32.c
+++ b/virt/kvm/arm/aarch32.c
@@ -10,10 +10,15 @@
  * Author: Christoffer Dall <c.dall@virtualopensystems.com>
  */
 
+#include <linux/bits.h>
 #include <linux/kvm_host.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.h>
 
+#define DFSR_FSC_EXTABT_LPAE	0x10
+#define DFSR_FSC_EXTABT_nLPAE	0x08
+#define DFSR_LPAE		BIT(9)
+
 /*
  * Table taken from ARMv8 ARM DDI0487B-B, table G1-10.
  */
@@ -28,25 +33,135 @@ static const u8 return_offsets[8][2] = {
 	[7] = { 4, 4 },		/* FIQ, unused */
 };
 
+static bool pre_fault_synchronize(struct kvm_vcpu *vcpu)
+{
+	preempt_disable();
+	if (vcpu->arch.sysregs_loaded_on_cpu) {
+		kvm_arch_vcpu_put(vcpu);
+		return true;
+	}
+
+	preempt_enable();
+	return false;
+}
+
+static void post_fault_synchronize(struct kvm_vcpu *vcpu, bool loaded)
+{
+	if (loaded) {
+		kvm_arch_vcpu_load(vcpu, smp_processor_id());
+		preempt_enable();
+	}
+}
+
+/*
+ * When an exception is taken, most CPSR fields are left unchanged in the
+ * handler. However, some are explicitly overridden (e.g. M[4:0]).
+ *
+ * The SPSR/SPSR_ELx layouts differ, and the below is intended to work with
+ * either format. Note: SPSR.J bit doesn't exist in SPSR_ELx, but this bit was
+ * obsoleted by the ARMv7 virtualization extensions and is RES0.
+ *
+ * For the SPSR layout seen from AArch32, see:
+ * - ARM DDI 0406C.d, page B1-1148
+ * - ARM DDI 0487E.a, page G8-6264
+ *
+ * For the SPSR_ELx layout for AArch32 seen from AArch64, see:
+ * - ARM DDI 0487E.a, page C5-426
+ *
+ * Here we manipulate the fields in order of the AArch32 SPSR_ELx layout, from
+ * MSB to LSB.
+ */
+static unsigned long get_except32_cpsr(struct kvm_vcpu *vcpu, u32 mode)
+{
+	u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR);
+	unsigned long old, new;
+
+	old = *vcpu_cpsr(vcpu);
+	new = 0;
+
+	new |= (old & PSR_AA32_N_BIT);
+	new |= (old & PSR_AA32_Z_BIT);
+	new |= (old & PSR_AA32_C_BIT);
+	new |= (old & PSR_AA32_V_BIT);
+	new |= (old & PSR_AA32_Q_BIT);
+
+	// CPSR.IT[7:0] are set to zero upon any exception
+	// See ARM DDI 0487E.a, section G1.12.3
+	// See ARM DDI 0406C.d, section B1.8.3
+
+	new |= (old & PSR_AA32_DIT_BIT);
+
+	// CPSR.SSBS is set to SCTLR.DSSBS upon any exception
+	// See ARM DDI 0487E.a, page G8-6244
+	if (sctlr & BIT(31))
+		new |= PSR_AA32_SSBS_BIT;
+
+	// CPSR.PAN is unchanged unless SCTLR.SPAN == 0b0
+	// SCTLR.SPAN is RES1 when ARMv8.1-PAN is not implemented
+	// See ARM DDI 0487E.a, page G8-6246
+	new |= (old & PSR_AA32_PAN_BIT);
+	if (!(sctlr & BIT(23)))
+		new |= PSR_AA32_PAN_BIT;
+
+	// SS does not exist in AArch32, so ignore
+
+	// CPSR.IL is set to zero upon any exception
+	// See ARM DDI 0487E.a, page G1-5527
+
+	new |= (old & PSR_AA32_GE_MASK);
+
+	// CPSR.IT[7:0] are set to zero upon any exception
+	// See prior comment above
+
+	// CPSR.E is set to SCTLR.EE upon any exception
+	// See ARM DDI 0487E.a, page G8-6245
+	// See ARM DDI 0406C.d, page B4-1701
+	if (sctlr & BIT(25))
+		new |= PSR_AA32_E_BIT;
+
+	// CPSR.A is unchanged upon an exception to Undefined, Supervisor
+	// CPSR.A is set upon an exception to other modes
+	// See ARM DDI 0487E.a, pages G1-5515 to G1-5516
+	// See ARM DDI 0406C.d, page B1-1182
+	new |= (old & PSR_AA32_A_BIT);
+	if (mode != PSR_AA32_MODE_UND && mode != PSR_AA32_MODE_SVC)
+		new |= PSR_AA32_A_BIT;
+
+	// CPSR.I is set upon any exception
+	// See ARM DDI 0487E.a, pages G1-5515 to G1-5516
+	// See ARM DDI 0406C.d, page B1-1182
+	new |= PSR_AA32_I_BIT;
+
+	// CPSR.F is set upon an exception to FIQ
+	// CPSR.F is unchanged upon an exception to other modes
+	// See ARM DDI 0487E.a, pages G1-5515 to G1-5516
+	// See ARM DDI 0406C.d, page B1-1182
+	new |= (old & PSR_AA32_F_BIT);
+	if (mode == PSR_AA32_MODE_FIQ)
+		new |= PSR_AA32_F_BIT;
+
+	// CPSR.T is set to SCTLR.TE upon any exception
+	// See ARM DDI 0487E.a, page G8-5514
+	// See ARM DDI 0406C.d, page B1-1181
+	if (sctlr & BIT(30))
+		new |= PSR_AA32_T_BIT;
+
+	new |= mode;
+
+	return new;
+}
+
 static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset)
 {
-	unsigned long cpsr;
-	unsigned long new_spsr_value = *vcpu_cpsr(vcpu);
-	bool is_thumb = (new_spsr_value & PSR_AA32_T_BIT);
+	unsigned long spsr = *vcpu_cpsr(vcpu);
+	bool is_thumb = (spsr & PSR_AA32_T_BIT);
 	u32 return_offset = return_offsets[vect_offset >> 2][is_thumb];
 	u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR);
 
-	cpsr = mode | PSR_AA32_I_BIT;
-
-	if (sctlr & (1 << 30))
-		cpsr |= PSR_AA32_T_BIT;
-	if (sctlr & (1 << 25))
-		cpsr |= PSR_AA32_E_BIT;
-
-	*vcpu_cpsr(vcpu) = cpsr;
+	*vcpu_cpsr(vcpu) = get_except32_cpsr(vcpu, mode);
 
 	/* Note: These now point to the banked copies */
-	vcpu_write_spsr(vcpu, new_spsr_value);
+	vcpu_write_spsr(vcpu, host_spsr_to_spsr32(spsr));
 	*vcpu_reg32(vcpu, 14) = *vcpu_pc(vcpu) + return_offset;
 
 	/* Branch to exception vector */
@@ -60,7 +175,10 @@ static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset)
 
 void kvm_inject_undef32(struct kvm_vcpu *vcpu)
 {
+	bool loaded = pre_fault_synchronize(vcpu);
+
 	prepare_fault32(vcpu, PSR_AA32_MODE_UND, 4);
+	post_fault_synchronize(vcpu, loaded);
 }
 
 /*
@@ -73,6 +191,9 @@ static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt,
 	u32 vect_offset;
 	u32 *far, *fsr;
 	bool is_lpae;
+	bool loaded;
+
+	loaded = pre_fault_synchronize(vcpu);
 
 	if (is_pabt) {
 		vect_offset = 12;
@@ -84,16 +205,20 @@ static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt,
 		fsr = &vcpu_cp15(vcpu, c5_DFSR);
 	}
 
-	prepare_fault32(vcpu, PSR_AA32_MODE_ABT | PSR_AA32_A_BIT, vect_offset);
+	prepare_fault32(vcpu, PSR_AA32_MODE_ABT, vect_offset);
 
 	*far = addr;
 
 	/* Give the guest an IMPLEMENTATION DEFINED exception */
 	is_lpae = (vcpu_cp15(vcpu, c2_TTBCR) >> 31);
-	if (is_lpae)
-		*fsr = 1 << 9 | 0x34;
-	else
-		*fsr = 0x14;
+	if (is_lpae) {
+		*fsr = DFSR_LPAE | DFSR_FSC_EXTABT_LPAE;
+	} else {
+		/* no need to shuffle FS[4] into DFSR[10] as its 0 */
+		*fsr = DFSR_FSC_EXTABT_nLPAE;
+	}
+
+	post_fault_synchronize(vcpu, loaded);
 }
 
 void kvm_inject_dabt32(struct kvm_vcpu *vcpu, unsigned long addr)
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index 1be486d5d7cb..ca90c0974ae8 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -805,6 +805,7 @@ static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu,
 	switch (treg) {
 	case TIMER_REG_TVAL:
 		val = timer->cnt_cval - kvm_phys_timer_read() + timer->cntvoff;
+		val &= lower_32_bits(val);
 		break;
 
 	case TIMER_REG_CTL:
@@ -850,7 +851,7 @@ static void kvm_arm_timer_write(struct kvm_vcpu *vcpu,
 {
 	switch (treg) {
 	case TIMER_REG_TVAL:
-		timer->cnt_cval = kvm_phys_timer_read() - timer->cntvoff + val;
+		timer->cnt_cval = kvm_phys_timer_read() - timer->cntvoff + (s32)val;
 		break;
 
 	case TIMER_REG_CTL:
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index 9b778c51af1b..d9585f6a897a 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -356,6 +356,12 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	return kvm_vgic_vcpu_init(vcpu);
 }
 
+#define __ptrauth_save_key(regs, key)						\
+({										\
+	regs[key ## KEYLO_EL1] = read_sysreg_s(SYS_ ## key ## KEYLO_EL1);	\
+	regs[key ## KEYHI_EL1] = read_sysreg_s(SYS_ ## key ## KEYHI_EL1);	\
+})
+
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	int *last_ran;
@@ -388,7 +394,17 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	else
 		vcpu_set_wfe_traps(vcpu);
 
-	vcpu_ptrauth_setup_lazy(vcpu);
+	if (vcpu_has_ptrauth(vcpu)) {
+		struct kvm_cpu_context *ctxt = vcpu->arch.host_cpu_context;
+
+		__ptrauth_save_key(ctxt->sys_regs, APIA);
+		__ptrauth_save_key(ctxt->sys_regs, APIB);
+		__ptrauth_save_key(ctxt->sys_regs, APDA);
+		__ptrauth_save_key(ctxt->sys_regs, APDB);
+		__ptrauth_save_key(ctxt->sys_regs, APGA);
+
+		vcpu_ptrauth_disable(vcpu);
+	}
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
diff --git a/virt/kvm/arm/hyp/aarch32.c b/virt/kvm/arm/hyp/aarch32.c
index d31f267961e7..25c0e47d57cb 100644
--- a/virt/kvm/arm/hyp/aarch32.c
+++ b/virt/kvm/arm/hyp/aarch32.c
@@ -125,12 +125,16 @@ static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu)
  */
 void __hyp_text kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr)
 {
+	u32 pc = *vcpu_pc(vcpu);
 	bool is_thumb;
 
 	is_thumb = !!(*vcpu_cpsr(vcpu) & PSR_AA32_T_BIT);
 	if (is_thumb && !is_wide_instr)
-		*vcpu_pc(vcpu) += 2;
+		pc += 2;
 	else
-		*vcpu_pc(vcpu) += 4;
+		pc += 4;
+
+	*vcpu_pc(vcpu) = pc;
+
 	kvm_adjust_itstate(vcpu);
 }
diff --git a/virt/kvm/arm/mmio.c b/virt/kvm/arm/mmio.c
index 6af5c91337f2..f274fabb4301 100644
--- a/virt/kvm/arm/mmio.c
+++ b/virt/kvm/arm/mmio.c
@@ -105,6 +105,9 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
 			data = (data ^ mask) - mask;
 		}
 
+		if (!vcpu->arch.mmio_decode.sixty_four)
+			data = data & 0xffffffff;
+
 		trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr,
 			       &data);
 		data = vcpu_data_host_to_guest(vcpu, data, len);
@@ -125,6 +128,7 @@ static int decode_hsr(struct kvm_vcpu *vcpu, bool *is_write, int *len)
 	unsigned long rt;
 	int access_size;
 	bool sign_extend;
+	bool sixty_four;
 
 	if (kvm_vcpu_dabt_iss1tw(vcpu)) {
 		/* page table accesses IO mem: tell guest to fix its TTBR */
@@ -138,11 +142,13 @@ static int decode_hsr(struct kvm_vcpu *vcpu, bool *is_write, int *len)
 
 	*is_write = kvm_vcpu_dabt_iswrite(vcpu);
 	sign_extend = kvm_vcpu_dabt_issext(vcpu);
+	sixty_four = kvm_vcpu_dabt_issf(vcpu);
 	rt = kvm_vcpu_dabt_get_rd(vcpu);
 
 	*len = access_size;
 	vcpu->arch.mmio_decode.sign_extend = sign_extend;
 	vcpu->arch.mmio_decode.rt = rt;
+	vcpu->arch.mmio_decode.sixty_four = sixty_four;
 
 	return 0;
 }
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index 0569ae328294..1f0d95c2f5f9 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -1199,7 +1199,7 @@ static bool stage2_get_leaf_entry(struct kvm *kvm, phys_addr_t addr,
 	return true;
 }
 
-static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr)
+static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr, unsigned long sz)
 {
 	pud_t *pudp;
 	pmd_t *pmdp;
@@ -1211,11 +1211,11 @@ static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr)
 		return false;
 
 	if (pudp)
-		return kvm_s2pud_exec(pudp);
+		return sz <= PUD_SIZE && kvm_s2pud_exec(pudp);
 	else if (pmdp)
-		return kvm_s2pmd_exec(pmdp);
+		return sz <= PMD_SIZE && kvm_s2pmd_exec(pmdp);
 	else
-		return kvm_s2pte_exec(ptep);
+		return sz == PAGE_SIZE && kvm_s2pte_exec(ptep);
 }
 
 static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
@@ -1805,7 +1805,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * execute permissions, and we preserve whatever we have.
 	 */
 	needs_exec = exec_fault ||
-		(fault_status == FSC_PERM && stage2_is_exec(kvm, fault_ipa));
+		(fault_status == FSC_PERM &&
+		 stage2_is_exec(kvm, fault_ipa, vma_pagesize));
 
 	if (vma_pagesize == PUD_SIZE) {
 		pud_t new_pud = kvm_pfn_pud(pfn, mem_type);
@@ -2147,7 +2148,8 @@ int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
 	if (!kvm->arch.pgd)
 		return 0;
 	trace_kvm_test_age_hva(hva);
-	return handle_hva_to_gpa(kvm, hva, hva, kvm_test_age_hva_handler, NULL);
+	return handle_hva_to_gpa(kvm, hva, hva + PAGE_SIZE,
+				 kvm_test_age_hva_handler, NULL);
 }
 
 void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu)
diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
index da740764a7ee..87cde3c6701e 100644
--- a/virt/kvm/arm/pmu.c
+++ b/virt/kvm/arm/pmu.c
@@ -305,6 +305,9 @@ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val)
 	if (val == 0)
 		return;
 
+	if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E))
+		return;
+
 	enable = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
 	for (i = 0; i < ARMV8_PMU_CYCLE_IDX; i++) {
 		if (!(val & BIT(i)))
diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c
index 482036612adf..21a18ad58e7e 100644
--- a/virt/kvm/arm/vgic/vgic-its.c
+++ b/virt/kvm/arm/vgic/vgic-its.c
@@ -2265,7 +2265,8 @@ static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa, int esz)
 	target_addr = (u32)(val >> KVM_ITS_CTE_RDBASE_SHIFT);
 	coll_id = val & KVM_ITS_CTE_ICID_MASK;
 
-	if (target_addr >= atomic_read(&kvm->online_vcpus))
+	if (target_addr != COLLECTION_NOT_MAPPED &&
+	    target_addr >= atomic_read(&kvm->online_vcpus))
 		return -EINVAL;
 
 	collection = find_collection(its, coll_id);
diff --git a/virt/kvm/arm/vgic/vgic-mmio-v2.c b/virt/kvm/arm/vgic/vgic-mmio-v2.c
index 5945f062d749..7b288eb391b8 100644
--- a/virt/kvm/arm/vgic/vgic-mmio-v2.c
+++ b/virt/kvm/arm/vgic/vgic-mmio-v2.c
@@ -415,18 +415,20 @@ static const struct vgic_register_region vgic_v2_dist_registers[] = {
 		vgic_mmio_read_enable, vgic_mmio_write_cenable, NULL, NULL, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_SET,
-		vgic_mmio_read_pending, vgic_mmio_write_spending, NULL, NULL, 1,
+		vgic_mmio_read_pending, vgic_mmio_write_spending,
+		NULL, vgic_uaccess_write_spending, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_CLEAR,
-		vgic_mmio_read_pending, vgic_mmio_write_cpending, NULL, NULL, 1,
+		vgic_mmio_read_pending, vgic_mmio_write_cpending,
+		NULL, vgic_uaccess_write_cpending, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ACTIVE_SET,
 		vgic_mmio_read_active, vgic_mmio_write_sactive,
-		NULL, vgic_mmio_uaccess_write_sactive, 1,
+		vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ACTIVE_CLEAR,
 		vgic_mmio_read_active, vgic_mmio_write_cactive,
-		NULL, vgic_mmio_uaccess_write_cactive, 1,
+		vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PRI,
 		vgic_mmio_read_priority, vgic_mmio_write_priority, NULL, NULL,
diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c
index 936962abc38d..89f0ce81d01b 100644
--- a/virt/kvm/arm/vgic/vgic-mmio-v3.c
+++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c
@@ -489,11 +489,11 @@ static const struct vgic_register_region vgic_v3_dist_registers[] = {
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISACTIVER,
 		vgic_mmio_read_active, vgic_mmio_write_sactive,
-		NULL, vgic_mmio_uaccess_write_sactive, 1,
+		vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICACTIVER,
 		vgic_mmio_read_active, vgic_mmio_write_cactive,
-		NULL, vgic_mmio_uaccess_write_cactive,
+		vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive,
 		1, VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IPRIORITYR,
 		vgic_mmio_read_priority, vgic_mmio_write_priority, NULL, NULL,
@@ -562,12 +562,12 @@ static const struct vgic_register_region vgic_v3_sgibase_registers[] = {
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_LENGTH_UACCESS(GICR_ISACTIVER0,
 		vgic_mmio_read_active, vgic_mmio_write_sactive,
-		NULL, vgic_mmio_uaccess_write_sactive,
-		4, VGIC_ACCESS_32bit),
+		vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 4,
+		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_LENGTH_UACCESS(GICR_ICACTIVER0,
 		vgic_mmio_read_active, vgic_mmio_write_cactive,
-		NULL, vgic_mmio_uaccess_write_cactive,
-		4, VGIC_ACCESS_32bit),
+		vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, 4,
+		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_LENGTH(GICR_IPRIORITYR0,
 		vgic_mmio_read_priority, vgic_mmio_write_priority, 32,
 		VGIC_ACCESS_32bit | VGIC_ACCESS_8bit),
diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c
index b249220025bc..e3bd622f2fe4 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.c
+++ b/virt/kvm/arm/vgic/vgic-mmio.c
@@ -184,17 +184,6 @@ static struct kvm_vcpu *vgic_get_mmio_requester_vcpu(void)
 	return vcpu;
 }
 
-/* Must be called with irq->irq_lock held */
-static void vgic_hw_irq_spending(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
-				 bool is_uaccess)
-{
-	if (is_uaccess)
-		return;
-
-	irq->pending_latch = true;
-	vgic_irq_set_phys_active(irq, true);
-}
-
 static bool is_vgic_v2_sgi(struct kvm_vcpu *vcpu, struct vgic_irq *irq)
 {
 	return (vgic_irq_is_sgi(irq->intid) &&
@@ -205,7 +194,6 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
 			      gpa_t addr, unsigned int len,
 			      unsigned long val)
 {
-	bool is_uaccess = !vgic_get_mmio_requester_vcpu();
 	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
 	int i;
 	unsigned long flags;
@@ -220,22 +208,48 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
 		}
 
 		raw_spin_lock_irqsave(&irq->irq_lock, flags);
+		irq->pending_latch = true;
 		if (irq->hw)
-			vgic_hw_irq_spending(vcpu, irq, is_uaccess);
-		else
-			irq->pending_latch = true;
+			vgic_irq_set_phys_active(irq, true);
+
 		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
 		vgic_put_irq(vcpu->kvm, irq);
 	}
 }
 
-/* Must be called with irq->irq_lock held */
-static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
-				 bool is_uaccess)
+int vgic_uaccess_write_spending(struct kvm_vcpu *vcpu,
+				gpa_t addr, unsigned int len,
+				unsigned long val)
 {
-	if (is_uaccess)
-		return;
+	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
+	int i;
+	unsigned long flags;
+
+	for_each_set_bit(i, &val, len * 8) {
+		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+
+		raw_spin_lock_irqsave(&irq->irq_lock, flags);
+		irq->pending_latch = true;
+
+		/*
+		 * GICv2 SGIs are terribly broken. We can't restore
+		 * the source of the interrupt, so just pick the vcpu
+		 * itself as the source...
+		 */
+		if (is_vgic_v2_sgi(vcpu, irq))
+			irq->source |= BIT(vcpu->vcpu_id);
+
+		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
+
+		vgic_put_irq(vcpu->kvm, irq);
+	}
 
+	return 0;
+}
+
+/* Must be called with irq->irq_lock held */
+static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq)
+{
 	irq->pending_latch = false;
 
 	/*
@@ -258,7 +272,6 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
 			      gpa_t addr, unsigned int len,
 			      unsigned long val)
 {
-	bool is_uaccess = !vgic_get_mmio_requester_vcpu();
 	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
 	int i;
 	unsigned long flags;
@@ -275,7 +288,7 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
 		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 
 		if (irq->hw)
-			vgic_hw_irq_cpending(vcpu, irq, is_uaccess);
+			vgic_hw_irq_cpending(vcpu, irq);
 		else
 			irq->pending_latch = false;
 
@@ -284,8 +297,39 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
 	}
 }
 
-unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu,
-				    gpa_t addr, unsigned int len)
+
+/*
+ * If we are fiddling with an IRQ's active state, we have to make sure the IRQ
+ * is not queued on some running VCPU's LRs, because then the change to the
+ * active state can be overwritten when the VCPU's state is synced coming back
+ * from the guest.
+ *
+ * For shared interrupts as well as GICv3 private interrupts, we have to
+ * stop all the VCPUs because interrupts can be migrated while we don't hold
+ * the IRQ locks and we don't want to be chasing moving targets.
+ *
+ * For GICv2 private interrupts we don't have to do anything because
+ * userspace accesses to the VGIC state already require all VCPUs to be
+ * stopped, and only the VCPU itself can modify its private interrupts
+ * active state, which guarantees that the VCPU is not running.
+ */
+static void vgic_access_active_prepare(struct kvm_vcpu *vcpu, u32 intid)
+{
+	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 ||
+	    intid >= VGIC_NR_PRIVATE_IRQS)
+		kvm_arm_halt_guest(vcpu->kvm);
+}
+
+/* See vgic_access_active_prepare */
+static void vgic_access_active_finish(struct kvm_vcpu *vcpu, u32 intid)
+{
+	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 ||
+	    intid >= VGIC_NR_PRIVATE_IRQS)
+		kvm_arm_resume_guest(vcpu->kvm);
+}
+
+static unsigned long __vgic_mmio_read_active(struct kvm_vcpu *vcpu,
+					     gpa_t addr, unsigned int len)
 {
 	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
 	u32 value = 0;
@@ -295,6 +339,10 @@ unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu,
 	for (i = 0; i < len * 8; i++) {
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 
+		/*
+		 * Even for HW interrupts, don't evaluate the HW state as
+		 * all the guest is interested in is the virtual state.
+		 */
 		if (irq->active)
 			value |= (1U << i);
 
@@ -304,6 +352,29 @@ unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu,
 	return value;
 }
 
+unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu,
+				    gpa_t addr, unsigned int len)
+{
+	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
+	u32 val;
+
+	mutex_lock(&vcpu->kvm->lock);
+	vgic_access_active_prepare(vcpu, intid);
+
+	val = __vgic_mmio_read_active(vcpu, addr, len);
+
+	vgic_access_active_finish(vcpu, intid);
+	mutex_unlock(&vcpu->kvm->lock);
+
+	return val;
+}
+
+unsigned long vgic_uaccess_read_active(struct kvm_vcpu *vcpu,
+				    gpa_t addr, unsigned int len)
+{
+	return __vgic_mmio_read_active(vcpu, addr, len);
+}
+
 /* Must be called with irq->irq_lock held */
 static void vgic_hw_irq_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
 				      bool active, bool is_uaccess)
@@ -355,34 +426,34 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
 		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
 }
 
-/*
- * If we are fiddling with an IRQ's active state, we have to make sure the IRQ
- * is not queued on some running VCPU's LRs, because then the change to the
- * active state can be overwritten when the VCPU's state is synced coming back
- * from the guest.
- *
- * For shared interrupts, we have to stop all the VCPUs because interrupts can
- * be migrated while we don't hold the IRQ locks and we don't want to be
- * chasing moving targets.
- *
- * For private interrupts we don't have to do anything because userspace
- * accesses to the VGIC state already require all VCPUs to be stopped, and
- * only the VCPU itself can modify its private interrupts active state, which
- * guarantees that the VCPU is not running.
- */
-static void vgic_change_active_prepare(struct kvm_vcpu *vcpu, u32 intid)
+int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu,
+				gpa_t addr, unsigned int len,
+				unsigned long val)
 {
-	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 ||
-	    intid > VGIC_NR_PRIVATE_IRQS)
-		kvm_arm_halt_guest(vcpu->kvm);
-}
+	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
+	int i;
+	unsigned long flags;
 
-/* See vgic_change_active_prepare */
-static void vgic_change_active_finish(struct kvm_vcpu *vcpu, u32 intid)
-{
-	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 ||
-	    intid > VGIC_NR_PRIVATE_IRQS)
-		kvm_arm_resume_guest(vcpu->kvm);
+	for_each_set_bit(i, &val, len * 8) {
+		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+
+		raw_spin_lock_irqsave(&irq->irq_lock, flags);
+		/*
+		 * More fun with GICv2 SGIs! If we're clearing one of them
+		 * from userspace, which source vcpu to clear? Let's not
+		 * even think of it, and blow the whole set.
+		 */
+		if (is_vgic_v2_sgi(vcpu, irq))
+			irq->source = 0;
+
+		irq->pending_latch = false;
+
+		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
+
+		vgic_put_irq(vcpu->kvm, irq);
+	}
+
+	return 0;
 }
 
 static void __vgic_mmio_write_cactive(struct kvm_vcpu *vcpu,
@@ -406,11 +477,11 @@ void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu,
 	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
 
 	mutex_lock(&vcpu->kvm->lock);
-	vgic_change_active_prepare(vcpu, intid);
+	vgic_access_active_prepare(vcpu, intid);
 
 	__vgic_mmio_write_cactive(vcpu, addr, len, val);
 
-	vgic_change_active_finish(vcpu, intid);
+	vgic_access_active_finish(vcpu, intid);
 	mutex_unlock(&vcpu->kvm->lock);
 }
 
@@ -443,11 +514,11 @@ void vgic_mmio_write_sactive(struct kvm_vcpu *vcpu,
 	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
 
 	mutex_lock(&vcpu->kvm->lock);
-	vgic_change_active_prepare(vcpu, intid);
+	vgic_access_active_prepare(vcpu, intid);
 
 	__vgic_mmio_write_sactive(vcpu, addr, len, val);
 
-	vgic_change_active_finish(vcpu, intid);
+	vgic_access_active_finish(vcpu, intid);
 	mutex_unlock(&vcpu->kvm->lock);
 }
 
diff --git a/virt/kvm/arm/vgic/vgic-mmio.h b/virt/kvm/arm/vgic/vgic-mmio.h
index 836f418f1ee8..71f01ef40533 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.h
+++ b/virt/kvm/arm/vgic/vgic-mmio.h
@@ -154,9 +154,20 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
 			      gpa_t addr, unsigned int len,
 			      unsigned long val);
 
+int vgic_uaccess_write_spending(struct kvm_vcpu *vcpu,
+				gpa_t addr, unsigned int len,
+				unsigned long val);
+
+int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu,
+				gpa_t addr, unsigned int len,
+				unsigned long val);
+
 unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu,
 				    gpa_t addr, unsigned int len);
 
+unsigned long vgic_uaccess_read_active(struct kvm_vcpu *vcpu,
+				    gpa_t addr, unsigned int len);
+
 void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu,
 			     gpa_t addr, unsigned int len,
 			     unsigned long val);
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index 35305d6e68cc..d8ef708a2ef6 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -64,7 +64,7 @@ static void async_pf_execute(struct work_struct *work)
 	struct mm_struct *mm = apf->mm;
 	struct kvm_vcpu *vcpu = apf->vcpu;
 	unsigned long addr = apf->addr;
-	gva_t gva = apf->gva;
+	gpa_t cr2_or_gpa = apf->cr2_or_gpa;
 	int locked = 1;
 
 	might_sleep();
@@ -92,7 +92,7 @@ static void async_pf_execute(struct work_struct *work)
 	 * this point
 	 */
 
-	trace_kvm_async_pf_completed(addr, gva);
+	trace_kvm_async_pf_completed(addr, cr2_or_gpa);
 
 	if (swq_has_sleeper(&vcpu->wq))
 		swake_up_one(&vcpu->wq);
@@ -165,8 +165,8 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu)
 	}
 }
 
-int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
-		       struct kvm_arch_async_pf *arch)
+int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+		       unsigned long hva, struct kvm_arch_async_pf *arch)
 {
 	struct kvm_async_pf *work;
 
@@ -185,7 +185,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
 
 	work->wakeup_all = false;
 	work->vcpu = vcpu;
-	work->gva = gva;
+	work->cr2_or_gpa = cr2_or_gpa;
 	work->addr = hva;
 	work->arch = *arch;
 	work->mm = current->mm;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index f19943bfa362..db65c81400b7 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -144,10 +144,9 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm);
 static unsigned long long kvm_createvm_count;
 static unsigned long long kvm_active_vms;
 
-__weak int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
-		unsigned long start, unsigned long end, bool blockable)
+__weak void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
+						   unsigned long start, unsigned long end)
 {
-	return 0;
 }
 
 bool kvm_is_zone_device_pfn(kvm_pfn_t pfn)
@@ -367,6 +366,18 @@ static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn)
 	return container_of(mn, struct kvm, mmu_notifier);
 }
 
+static void kvm_mmu_notifier_invalidate_range(struct mmu_notifier *mn,
+					      struct mm_struct *mm,
+					      unsigned long start, unsigned long end)
+{
+	struct kvm *kvm = mmu_notifier_to_kvm(mn);
+	int idx;
+
+	idx = srcu_read_lock(&kvm->srcu);
+	kvm_arch_mmu_notifier_invalidate_range(kvm, start, end);
+	srcu_read_unlock(&kvm->srcu, idx);
+}
+
 static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
 					struct mm_struct *mm,
 					unsigned long address,
@@ -391,7 +402,6 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 {
 	struct kvm *kvm = mmu_notifier_to_kvm(mn);
 	int need_tlb_flush = 0, idx;
-	int ret;
 
 	idx = srcu_read_lock(&kvm->srcu);
 	spin_lock(&kvm->mmu_lock);
@@ -408,14 +418,9 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 		kvm_flush_remote_tlbs(kvm);
 
 	spin_unlock(&kvm->mmu_lock);
-
-	ret = kvm_arch_mmu_notifier_invalidate_range(kvm, range->start,
-					range->end,
-					mmu_notifier_range_blockable(range));
-
 	srcu_read_unlock(&kvm->srcu, idx);
 
-	return ret;
+	return 0;
 }
 
 static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
@@ -521,6 +526,7 @@ static void kvm_mmu_notifier_release(struct mmu_notifier *mn,
 }
 
 static const struct mmu_notifier_ops kvm_mmu_notifier_ops = {
+	.invalidate_range	= kvm_mmu_notifier_invalidate_range,
 	.invalidate_range_start	= kvm_mmu_notifier_invalidate_range_start,
 	.invalidate_range_end	= kvm_mmu_notifier_invalidate_range_end,
 	.clear_flush_young	= kvm_mmu_notifier_clear_flush_young,
@@ -1376,14 +1382,14 @@ bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
 }
 EXPORT_SYMBOL_GPL(kvm_is_visible_gfn);
 
-unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn)
+unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn)
 {
 	struct vm_area_struct *vma;
 	unsigned long addr, size;
 
 	size = PAGE_SIZE;
 
-	addr = gfn_to_hva(kvm, gfn);
+	addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gfn, NULL);
 	if (kvm_is_error_hva(addr))
 		return PAGE_SIZE;
 
@@ -2258,12 +2264,12 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 	if (slots->generation != ghc->generation)
 		__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len);
 
-	if (unlikely(!ghc->memslot))
-		return kvm_write_guest(kvm, gpa, data, len);
-
 	if (kvm_is_error_hva(ghc->hva))
 		return -EFAULT;
 
+	if (unlikely(!ghc->memslot))
+		return kvm_write_guest(kvm, gpa, data, len);
+
 	r = __copy_to_user((void __user *)ghc->hva + offset, data, len);
 	if (r)
 		return -EFAULT;
@@ -2291,12 +2297,12 @@ int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 	if (slots->generation != ghc->generation)
 		__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len);
 
-	if (unlikely(!ghc->memslot))
-		return kvm_read_guest(kvm, ghc->gpa, data, len);
-
 	if (kvm_is_error_hva(ghc->hva))
 		return -EFAULT;
 
+	if (unlikely(!ghc->memslot))
+		return kvm_read_guest(kvm, ghc->gpa, data, len);
+
 	r = __copy_from_user(data, (void __user *)ghc->hva, len);
 	if (r)
 		return -EFAULT;